From 8665bd53f2f2e27e5511d90428cb3f60e6d0ce15 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 20:50:12 +0200 Subject: Merging upstream version 6.8.9. Signed-off-by: Daniel Baumann --- kernel/Makefile | 1 + kernel/async.c | 5 +- kernel/bounds.c | 2 +- kernel/bpf/Makefile | 2 +- kernel/bpf/arraymap.c | 2 +- kernel/bpf/bpf_cgrp_storage.c | 6 +- kernel/bpf/bpf_lsm.c | 12 + kernel/bpf/bpf_struct_ops.c | 35 +- kernel/bpf/btf.c | 537 ++++---- kernel/bpf/core.c | 50 +- kernel/bpf/cpumask.c | 20 +- kernel/bpf/dispatcher.c | 7 +- kernel/bpf/hashtab.c | 7 + kernel/bpf/helpers.c | 61 +- kernel/bpf/inode.c | 53 +- kernel/bpf/log.c | 504 +++++++ kernel/bpf/map_in_map.c | 14 +- kernel/bpf/memalloc.c | 93 +- kernel/bpf/syscall.c | 96 +- kernel/bpf/task_iter.c | 31 +- kernel/bpf/tnum.c | 13 +- kernel/bpf/trampoline.c | 101 +- kernel/bpf/verifier.c | 2501 +++++++++++++++++----------------- kernel/cgroup/cgroup-internal.h | 4 +- kernel/cgroup/cgroup-v1.c | 36 +- kernel/cgroup/cgroup.c | 80 +- kernel/cgroup/cpuset.c | 299 +++- kernel/cgroup/rstat.c | 150 +- kernel/cpu.c | 8 +- kernel/crash_core.c | 98 +- kernel/dma/debug.c | 5 +- kernel/dma/direct.c | 10 +- kernel/dma/pool.c | 6 +- kernel/dma/swiotlb.c | 97 +- kernel/entry/common.c | 108 +- kernel/events/core.c | 8 + kernel/events/ring_buffer.c | 10 +- kernel/events/uprobes.c | 6 +- kernel/exit.c | 14 +- kernel/fork.c | 98 +- kernel/freezer.c | 1 + kernel/futex/core.c | 1 + kernel/futex/requeue.c | 1 + kernel/futex/waitwake.c | 1 + kernel/irq/manage.c | 9 +- kernel/kexec_core.c | 21 +- kernel/kexec_file.c | 20 +- kernel/kprobes.c | 22 +- kernel/locking/locktorture.c | 18 +- kernel/locking/mutex.c | 5 + kernel/locking/spinlock_debug.c | 1 + kernel/module/dups.c | 2 +- kernel/module/main.c | 3 + kernel/numa.c | 26 + kernel/panic.c | 8 + kernel/params.c | 52 +- kernel/pid.c | 2 +- kernel/pid_namespace.c | 1 + kernel/power/hibernate.c | 10 +- kernel/power/main.c | 16 - kernel/power/power.h | 2 + kernel/power/snapshot.c | 16 +- kernel/power/suspend.c | 6 + kernel/power/swap.c | 3 +- kernel/printk/internal.h | 1 - kernel/printk/printk.c | 3 +- kernel/ptrace.c | 141 +- kernel/rcu/rcutorture.c | 4 +- kernel/rcu/srcutree.c | 24 +- kernel/rcu/tasks.h | 4 +- kernel/rcu/tree.c | 2 + kernel/rcu/tree_nocb.h | 2 +- kernel/reboot.c | 51 +- kernel/relay.c | 162 --- kernel/resource.c | 57 + kernel/sched/core.c | 141 +- kernel/sched/cpufreq_schedutil.c | 94 +- kernel/sched/deadline.c | 479 ++++--- kernel/sched/debug.c | 18 +- kernel/sched/fair.c | 420 +++--- kernel/sched/features.h | 1 - kernel/sched/idle.c | 30 + kernel/sched/pelt.h | 4 +- kernel/sched/rt.c | 15 +- kernel/sched/sched.h | 166 +-- kernel/sched/stop_task.c | 13 +- kernel/seccomp.c | 2 +- kernel/signal.c | 28 +- kernel/stacktrace.c | 2 +- kernel/sys_ni.c | 3 + kernel/time/tick-internal.h | 3 +- kernel/time/tick-sched.c | 25 +- kernel/time/timer.c | 110 +- kernel/trace/bpf_trace.c | 183 ++- kernel/trace/ring_buffer.c | 784 +++++++---- kernel/trace/ring_buffer_benchmark.c | 10 +- kernel/trace/trace.c | 277 +++- kernel/trace/trace.h | 2 + kernel/trace/trace_boot.c | 2 +- kernel/trace/trace_events.c | 111 +- kernel/trace/trace_events_hist.c | 49 +- kernel/trace/trace_events_user.c | 4 +- kernel/trace/trace_kprobe.c | 4 +- kernel/trace/trace_output.c | 6 +- kernel/trace/trace_seq.c | 3 - kernel/trace/trace_uprobe.c | 2 +- kernel/user_namespace.c | 20 +- kernel/watch_queue.c | 2 +- kernel/watchdog.c | 40 +- kernel/workqueue.c | 924 ++++--------- 110 files changed, 5617 insertions(+), 4248 deletions(-) create mode 100644 kernel/numa.c (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index 3947122d6..ce105a555 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -114,6 +114,7 @@ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o +obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/async.c b/kernel/async.c index 673bba6bd..97f224a52 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -46,11 +46,12 @@ asynchronous and synchronous parts of the kernel. #include #include -#include #include -#include +#include +#include #include #include +#include #include #include "workqueue_internal.h" diff --git a/kernel/bounds.c b/kernel/bounds.c index c5a9fcd2d..29b2cd00d 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); #ifdef CONFIG_SMP - DEFINE(NR_CPUS_BITS, bits_per(CONFIG_NR_CPUS)); + DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS)); #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); #ifdef CONFIG_LRU_GEN diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573..418a8188a 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,7 +4,7 @@ ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y) # ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif -CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) +CFLAGS_core.o += -Wno-override-init $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c9843dde6..0bdbbbeab 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1157,7 +1157,7 @@ static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, { struct bpf_event_entry *ee; - ee = kzalloc(sizeof(*ee), GFP_ATOMIC); + ee = kzalloc(sizeof(*ee), GFP_KERNEL); if (ee) { ee->event = perf_file->private_data; ee->perf_file = perf_file; diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index d44fe8dd9..28efd0a3f 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -82,7 +82,7 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) int fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return ERR_CAST(cgroup); @@ -101,7 +101,7 @@ static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, int fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); @@ -131,7 +131,7 @@ static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) int err, fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index e14c822f8..e8e910395 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -298,6 +298,18 @@ BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernel_read_file) BTF_ID(func, bpf_lsm_kernfs_init_security) +#ifdef CONFIG_SECURITY_PATH +BTF_ID(func, bpf_lsm_path_unlink) +BTF_ID(func, bpf_lsm_path_mkdir) +BTF_ID(func, bpf_lsm_path_rmdir) +BTF_ID(func, bpf_lsm_path_truncate) +BTF_ID(func, bpf_lsm_path_symlink) +BTF_ID(func, bpf_lsm_path_link) +BTF_ID(func, bpf_lsm_path_rename) +BTF_ID(func, bpf_lsm_path_chmod) +BTF_ID(func, bpf_lsm_path_chown) +#endif /* CONFIG_SECURITY_PATH */ + #ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) #endif /* CONFIG_KEYS */ diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index db6176fb6..02068bd0e 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -352,18 +352,24 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = { int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, - void *image, void *image_end) + void *stub_func, void *image, void *image_end) { - u32 flags; + u32 flags = BPF_TRAMP_F_INDIRECT; + int size; tlinks[BPF_TRAMP_FENTRY].links[0] = link; tlinks[BPF_TRAMP_FENTRY].nr_links = 1; - /* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, - * and it must be used alone. - */ - flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; + + if (model->ret_size > 0) + flags |= BPF_TRAMP_F_RET_FENTRY_RET; + + size = arch_bpf_trampoline_size(model, flags, tlinks, NULL); + if (size < 0) + return size; + if (size > (unsigned long)image_end - (unsigned long)image) + return -E2BIG; return arch_prepare_bpf_trampoline(NULL, image, image_end, - model, flags, tlinks, NULL); + model, flags, tlinks, stub_func); } static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, @@ -497,11 +503,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[i], + *(void **)(st_ops->cfi_stubs + moff), image, image_end); if (err < 0) goto reset_unlock; - *(void **)(kdata + moff) = image; + *(void **)(kdata + moff) = image + cfi_get_offset(); image += err; /* put prog_id to udata */ @@ -515,7 +522,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) goto reset_unlock; } - set_memory_rox((long)st_map->image, 1); + arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); /* Let bpf_link handle registration & unregistration. * * Pair with smp_load_acquire() during lookup_elem(). @@ -524,7 +531,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto unlock; } - set_memory_rox((long)st_map->image, 1); + arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); err = st_ops->reg(kdata); if (likely(!err)) { /* This refcnt increment on the map here after @@ -547,8 +554,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * there was a race in registering the struct_ops (under the same name) to * a sub-system through different struct_ops's maps. */ - set_memory_nx((long)st_map->image, 1); - set_memory_rw((long)st_map->image, 1); + arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE); reset_unlock: bpf_struct_ops_map_put_progs(st_map); @@ -616,7 +622,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) bpf_struct_ops_map_put_progs(st_map); bpf_map_area_free(st_map->links); if (st_map->image) { - bpf_jit_free_exec(st_map->image); + arch_free_bpf_trampoline(st_map->image, PAGE_SIZE); bpf_jit_uncharge_modmem(PAGE_SIZE); } bpf_map_area_free(st_map->uvalue); @@ -691,7 +697,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) return ERR_PTR(ret); } - st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); + st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE); if (!st_map->image) { /* __bpf_struct_ops_map_free() uses st_map->image as flag * for "charged or not". In this case, we need to unchange @@ -711,7 +717,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) } mutex_init(&st_map->lock); - set_vm_flush_reset_perms(st_map->image); bpf_map_init_from_attr(map, attr); return map; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 15d71d298..92aa3cf03 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3840,9 +3840,6 @@ end: return ERR_PTR(ret); } -#define GRAPH_ROOT_MASK (BPF_LIST_HEAD | BPF_RB_ROOT) -#define GRAPH_NODE_MASK (BPF_LIST_NODE | BPF_RB_NODE) - int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) { int i; @@ -3855,13 +3852,13 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) * Hence we only need to ensure that bpf_{list_head,rb_root} ownership * does not form cycles. */ - if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & GRAPH_ROOT_MASK)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_GRAPH_ROOT)) return 0; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *meta; u32 btf_id; - if (!(rec->fields[i].type & GRAPH_ROOT_MASK)) + if (!(rec->fields[i].type & BPF_GRAPH_ROOT)) continue; btf_id = rec->fields[i].graph_root.value_btf_id; meta = btf_find_struct_meta(btf, btf_id); @@ -3873,7 +3870,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) * to check ownership cycle for a type unless it's also a * node type. */ - if (!(rec->field_mask & GRAPH_NODE_MASK)) + if (!(rec->field_mask & BPF_GRAPH_NODE)) continue; /* We need to ensure ownership acyclicity among all types. The @@ -3909,7 +3906,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) * - A is both an root and node. * - B is only an node. */ - if (meta->record->field_mask & GRAPH_ROOT_MASK) + if (meta->record->field_mask & BPF_GRAPH_ROOT) return -ELOOP; } return 0; @@ -5618,21 +5615,46 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -const struct btf_member * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type) { const struct btf_type *conv_struct; - const struct btf_type *ctx_struct; const struct btf_member *ctx_type; - const char *tname, *ctx_tname; conv_struct = bpf_ctx_convert.t; - if (!conv_struct) { - bpf_log(log, "btf_vmlinux is malformed\n"); + if (!conv_struct) return NULL; - } + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct __sk_buff' + */ + return btf_type_by_id(btf_vmlinux, ctx_type->type); +} + +static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) +{ + const struct btf_type *conv_struct; + const struct btf_member *ctx_type; + + conv_struct = bpf_ctx_convert.t; + if (!conv_struct) + return -EFAULT; + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct sk_buff' + */ + return ctx_type->type; +} + +const struct btf_type * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); @@ -5649,17 +5671,15 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, bpf_log(log, "arg#%d struct doesn't have a name\n", arg); return NULL; } - /* prog_type is valid bpf program type. No need for bounds check. */ - ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; - /* ctx_struct is a pointer to prog_ctx_type in vmlinux. - * Like 'struct __sk_buff' - */ - ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type); - if (!ctx_struct) + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ return NULL; + } again: - ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); @@ -5680,28 +5700,167 @@ again: /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ - if (!btf_type_is_modifier(ctx_struct)) + if (!btf_type_is_modifier(ctx_type)) return NULL; - while (btf_type_is_modifier(ctx_struct)) - ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type); + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); goto again; } return ctx_type; } +/* forward declarations for arch-specific underlying types of + * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef + * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still + * works correctly with __builtin_types_compatible_p() on respective + * architectures + */ +struct user_regs_struct; +struct user_pt_regs; + +static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int arg, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + + if (!btf_is_ptr(t)) { + bpf_log(log, "arg#%d type isn't a pointer\n", arg); + return -EINVAL; + } + t = btf_type_by_id(btf, t->type); + + /* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */ + if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) { + while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) + t = btf_type_by_id(btf, t->type); + + if (btf_type_is_typedef(t)) { + tname = btf_name_by_offset(btf, t->name_off); + if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) + return 0; + } + } + + /* all other program types don't use typedefs for context type */ + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + + /* `void *ctx __arg_ctx` is always valid */ + if (btf_type_is_void(t)) + return 0; + + tname = btf_name_by_offset(btf, t->name_off); + if (str_is_empty(tname)) { + bpf_log(log, "arg#%d type doesn't have a name\n", arg); + return -EINVAL; + } + + /* special cases */ + switch (prog_type) { + case BPF_PROG_TYPE_KPROBE: + if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + break; + case BPF_PROG_TYPE_PERF_EVENT: + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) && + __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0) + return 0; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACING: + switch (attach_type) { + case BPF_TRACE_RAW_TP: + /* tp_btf program is TRACING, so need special case here */ + if (__btf_type_is_struct(t) && + strcmp(tname, "bpf_raw_tracepoint_args") == 0) + return 0; + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_TRACE_ITER: + /* allow struct bpf_iter__xxx types only */ + if (__btf_type_is_struct(t) && + strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0) + return 0; + break; + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + default: + break; + } + break; + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_SYSCALL: + case BPF_PROG_TYPE_EXT: + return 0; /* anything goes */ + default: + break; + } + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + /* should not happen */ + bpf_log(log, "btf_vmlinux is malformed\n"); + return -EINVAL; + } + + /* resolve typedefs and check that underlying structs are matching as well */ + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); + + /* if program type doesn't have distinctly named struct type for + * context, then __arg_ctx argument can only be `void *`, which we + * already checked above + */ + if (!__btf_type_is_struct(ctx_type)) { + bpf_log(log, "arg#%d should be void pointer\n", arg); + return -EINVAL; + } + + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); + if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) { + bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname); + return -EINVAL; + } + + return 0; +} + static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { - const struct btf_member *prog_ctx_type, *kern_ctx_type; - - prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg); - if (!prog_ctx_type) + if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; - kern_ctx_type = prog_ctx_type + 1; - return kern_ctx_type->type; + return find_kern_ctx_type_id(prog_type); } int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) @@ -6768,222 +6927,64 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr return btf_check_func_type_match(log, btf1, t1, btf2, t2); } -static int btf_check_func_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - bool ptr_to_mem_ok, - bool processing_call) +static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) { - enum bpf_prog_type prog_type = resolve_prog_type(env->prog); - struct bpf_verifier_log *log = &env->log; - const char *func_name, *ref_tname; - const struct btf_type *t, *ref_t; - const struct btf_param *args; - u32 i, nargs, ref_id; - int ret; - - t = btf_type_by_id(btf, func_id); - if (!t || !btf_type_is_func(t)) { - /* These checks were already done by the verifier while loading - * struct bpf_func_info or in add_kfunc_call(). - */ - bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n", - func_id); - return -EFAULT; - } - func_name = btf_name_by_offset(btf, t->name_off); - - t = btf_type_by_id(btf, t->type); - if (!t || !btf_type_is_func_proto(t)) { - bpf_log(log, "Invalid BTF of func %s\n", func_name); - return -EFAULT; - } - args = (const struct btf_param *)(t + 1); - nargs = btf_type_vlen(t); - if (nargs > MAX_BPF_FUNC_REG_ARGS) { - bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs, - MAX_BPF_FUNC_REG_ARGS); - return -EINVAL; - } - - /* check that BTF function arguments match actual types that the - * verifier sees. - */ - for (i = 0; i < nargs; i++) { - enum bpf_arg_type arg_type = ARG_DONTCARE; - u32 regno = i + 1; - struct bpf_reg_state *reg = ®s[regno]; - - t = btf_type_skip_modifiers(btf, args[i].type, NULL); - if (btf_type_is_scalar(t)) { - if (reg->type == SCALAR_VALUE) - continue; - bpf_log(log, "R%d is not a scalar\n", regno); - return -EINVAL; - } - - if (!btf_type_is_ptr(t)) { - bpf_log(log, "Unrecognized arg#%d type %s\n", - i, btf_type_str(t)); - return -EINVAL; - } - - ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); - ref_tname = btf_name_by_offset(btf, ref_t->name_off); - - ret = check_func_arg_reg_off(env, reg, regno, arg_type); - if (ret < 0) - return ret; + const char *name; - if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { - /* If function expects ctx type in BTF check that caller - * is passing PTR_TO_CTX. - */ - if (reg->type != PTR_TO_CTX) { - bpf_log(log, - "arg#%d expected pointer to ctx, but got %s\n", - i, btf_type_str(t)); - return -EINVAL; - } - } else if (ptr_to_mem_ok && processing_call) { - const struct btf_type *resolve_ret; - u32 type_size; + t = btf_type_by_id(btf, t->type); /* skip PTR */ - resolve_ret = btf_resolve_size(btf, ref_t, &type_size); - if (IS_ERR(resolve_ret)) { - bpf_log(log, - "arg#%d reference type('%s %s') size cannot be determined: %ld\n", - i, btf_type_str(ref_t), ref_tname, - PTR_ERR(resolve_ret)); - return -EINVAL; - } + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); - if (check_mem_reg(env, reg, regno, type_size)) - return -EINVAL; - } else { - bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i, - func_name, func_id); - return -EINVAL; - } + /* allow either struct or struct forward declaration */ + if (btf_type_is_struct(t) || + (btf_type_is_fwd(t) && btf_type_kflag(t) == 0)) { + name = btf_str_by_offset(btf, t->name_off); + return name && strcmp(name, "bpf_dynptr") == 0; } - return 0; -} - -/* Compare BTF of a function declaration with given bpf_reg_state. - * Returns: - * EFAULT - there is a verifier bug. Abort verification. - * EINVAL - there is a type mismatch or BTF is not available. - * 0 - BTF matches with what bpf_reg_state expects. - * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. - */ -int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) -{ - struct bpf_prog *prog = env->prog; - struct btf *btf = prog->aux->btf; - bool is_global; - u32 btf_id; - int err; - - if (!prog->aux->func_info) - return -EINVAL; - - btf_id = prog->aux->func_info[subprog].type_id; - if (!btf_id) - return -EFAULT; - - if (prog->aux->func_info_aux[subprog].unreliable) - return -EINVAL; - - is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false); - - /* Compiler optimizations can remove arguments from static functions - * or mismatched type can be passed into a global function. - * In such cases mark the function as unreliable from BTF point of view. - */ - if (err) - prog->aux->func_info_aux[subprog].unreliable = true; - return err; -} - -/* Compare BTF of a function call with given bpf_reg_state. - * Returns: - * EFAULT - there is a verifier bug. Abort verification. - * EINVAL - there is a type mismatch or BTF is not available. - * 0 - BTF matches with what bpf_reg_state expects. - * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. - * - * NOTE: the code is duplicated from btf_check_subprog_arg_match() - * because btf_check_func_arg_match() is still doing both. Once that - * function is split in 2, we can call from here btf_check_subprog_arg_match() - * first, and then treat the calling part in a new code path. - */ -int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) -{ - struct bpf_prog *prog = env->prog; - struct btf *btf = prog->aux->btf; - bool is_global; - u32 btf_id; - int err; - - if (!prog->aux->func_info) - return -EINVAL; - - btf_id = prog->aux->func_info[subprog].type_id; - if (!btf_id) - return -EFAULT; - - if (prog->aux->func_info_aux[subprog].unreliable) - return -EINVAL; - - is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true); - - /* Compiler optimizations can remove arguments from static functions - * or mismatched type can be passed into a global function. - * In such cases mark the function as unreliable from BTF point of view. - */ - if (err) - prog->aux->func_info_aux[subprog].unreliable = true; - return err; + return false; } -/* Convert BTF of a function into bpf_reg_state if possible +/* Process BTF of a function to produce high-level expectation of function + * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information + * is cached in subprog info for reuse. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - cannot convert BTF. - * 0 - Successfully converted BTF into bpf_reg_state - * (either PTR_TO_CTX or SCALAR_VALUE). + * 0 - Successfully processed BTF and constructed argument expectations. */ -int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs, bool is_ex_cb) +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) { + bool is_global = subprog_aux(env, subprog)->linkage == BTF_FUNC_GLOBAL; + struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; enum bpf_prog_type prog_type = prog->type; struct btf *btf = prog->aux->btf; const struct btf_param *args; - const struct btf_type *t, *ref_t; + const struct btf_type *t, *ref_t, *fn_t; u32 i, nargs, btf_id; const char *tname; - if (!prog->aux->func_info || - prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) { + if (sub->args_cached) + return 0; + + if (!prog->aux->func_info) { bpf_log(log, "Verifier bug\n"); return -EFAULT; } btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) { + if (!is_global) /* not fatal for static funcs */ + return -EINVAL; bpf_log(log, "Global functions need valid BTF\n"); return -EFAULT; } - t = btf_type_by_id(btf, btf_id); - if (!t || !btf_type_is_func(t)) { + fn_t = btf_type_by_id(btf, btf_id); + if (!fn_t || !btf_type_is_func(fn_t)) { /* These checks were already done by the verifier while loading * struct bpf_func_info */ @@ -6991,11 +6992,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, subprog); return -EFAULT; } - tname = btf_name_by_offset(btf, t->name_off); - - if (log->level & BPF_LOG_LEVEL) - bpf_log(log, "Validating %s() func#%d...\n", - tname, subprog); + tname = btf_name_by_offset(btf, fn_t->name_off); if (prog->aux->func_info_aux[subprog].unreliable) { bpf_log(log, "Verifier bug in function %s()\n", tname); @@ -7004,7 +7001,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, if (prog_type == BPF_PROG_TYPE_EXT) prog_type = prog->aux->dst_prog->type; - t = btf_type_by_id(btf, t->type); + t = btf_type_by_id(btf, fn_t->type); if (!t || !btf_type_is_func_proto(t)) { bpf_log(log, "Invalid type of function %s()\n", tname); return -EFAULT; @@ -7012,6 +7009,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() with %d > %d args. Buggy compiler.\n", tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; @@ -7021,6 +7020,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_int(t) && !btf_is_any_enum(t)) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() doesn't return scalar. Only those are supported.\n", tname); @@ -7030,24 +7031,50 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { - struct bpf_reg_state *reg = ®s[i + 1]; + bool is_nonnull = false; + const char *tag; t = btf_type_by_id(btf, args[i].type); + + tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); + if (IS_ERR(tag) && PTR_ERR(tag) == -ENOENT) { + tag = NULL; + } else if (IS_ERR(tag)) { + bpf_log(log, "arg#%d type's tag fetching failure: %ld\n", i, PTR_ERR(tag)); + return PTR_ERR(tag); + } + /* 'arg:' decl_tag takes precedence over derivation of + * register type from BTF type itself + */ + if (tag) { + /* disallow arg tags in static subprogs */ + if (!is_global) { + bpf_log(log, "arg#%d type tag is not supported in static functions\n", i); + return -EOPNOTSUPP; + } + if (strcmp(tag, "ctx") == 0) { + sub->args[i].arg_type = ARG_PTR_TO_CTX; + continue; + } + if (strcmp(tag, "nonnull") == 0) + is_nonnull = true; + } + while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t) || btf_is_any_enum(t)) { - reg->type = SCALAR_VALUE; + if (btf_type_is_ptr(t) && btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + sub->args[i].arg_type = ARG_PTR_TO_CTX; continue; } - if (btf_type_is_ptr(t)) { - if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { - reg->type = PTR_TO_CTX; - continue; - } + if (btf_type_is_ptr(t) && btf_is_dynptr_ptr(btf, t)) { + sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY; + continue; + } + if (is_global && btf_type_is_ptr(t)) { + u32 mem_size; t = btf_type_skip_modifiers(btf, t->type, NULL); - - ref_t = btf_resolve_size(btf, t, ®->mem_size); + ref_t = btf_resolve_size(btf, t, &mem_size); if (IS_ERR(ref_t)) { bpf_log(log, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", @@ -7056,23 +7083,45 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, return -EINVAL; } - reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; - reg->id = ++env->id_gen; - + sub->args[i].arg_type = is_nonnull ? ARG_PTR_TO_MEM : ARG_PTR_TO_MEM_OR_NULL; + sub->args[i].mem_size = mem_size; + continue; + } + if (is_nonnull) { + bpf_log(log, "arg#%d marked as non-null, but is not a pointer type\n", i); + return -EINVAL; + } + if (btf_type_is_int(t) || btf_is_any_enum(t)) { + sub->args[i].arg_type = ARG_ANYTHING; continue; } + if (!is_global) + return -EINVAL; bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; } - /* We have already ensured that the callback returns an integer, just - * like all global subprogs. We need to determine it only has a single - * scalar argument. - */ - if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) { - bpf_log(log, "exception cb only supports single integer argument\n"); - return -EINVAL; + + for (i = 0; i < nargs; i++) { + const char *tag; + + if (sub->args[i].arg_type != ARG_PTR_TO_CTX) + continue; + + /* check if arg has "arg:ctx" tag */ + t = btf_type_by_id(btf, args[i].type); + tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); + if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0) + continue; + + if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type, + prog->expected_attach_type)) + return -EINVAL; } + + sub->arg_cnt = nargs; + sub->args_cached = true; + return 0; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 27fd41777..026627226 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -121,6 +121,9 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag #endif INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); +#ifdef CONFIG_FINEIBT + INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode); +#endif mutex_init(&fp->aux->used_maps_mutex); mutex_init(&fp->aux->dst_mutex); @@ -687,6 +690,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp) fp->aux->ksym.prog = true; bpf_ksym_add(&fp->aux->ksym); + +#ifdef CONFIG_FINEIBT + /* + * When FineIBT, code in the __cfi_foo() symbols can get executed + * and hence unwinder needs help. + */ + if (cfi_mode != CFI_FINEIBT) + return; + + snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN, + "__cfi_%s", fp->aux->ksym.name); + + fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16; + fp->aux->ksym_prefix.end = (unsigned long) fp->bpf_func; + + bpf_ksym_add(&fp->aux->ksym_prefix); +#endif } void bpf_prog_kallsyms_del(struct bpf_prog *fp) @@ -695,6 +715,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp) return; bpf_ksym_del(&fp->aux->ksym); +#ifdef CONFIG_FINEIBT + if (cfi_mode != CFI_FINEIBT) + return; + bpf_ksym_del(&fp->aux->ksym_prefix); +#endif } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) @@ -937,20 +962,20 @@ out: return ptr; } -void bpf_prog_pack_free(struct bpf_binary_header *hdr) +void bpf_prog_pack_free(void *ptr, u32 size) { struct bpf_prog_pack *pack = NULL, *tmp; unsigned int nbits; unsigned long pos; mutex_lock(&pack_mutex); - if (hdr->size > BPF_PROG_PACK_SIZE) { - bpf_jit_free_exec(hdr); + if (size > BPF_PROG_PACK_SIZE) { + bpf_jit_free_exec(ptr); goto out; } list_for_each_entry(tmp, &pack_list, list) { - if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) { + if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) { pack = tmp; break; } @@ -959,10 +984,10 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr) if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) goto out; - nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); - pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; + nbits = BPF_PROG_SIZE_TO_NBITS(size); + pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; - WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size), + WARN_ONCE(bpf_arch_text_invalidate(ptr, size), "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); bitmap_clear(pack->bitmap, pos, nbits); @@ -1109,8 +1134,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, *rw_header = kvmalloc(size, GFP_KERNEL); if (!*rw_header) { - bpf_arch_text_copy(&ro_header->size, &size, sizeof(size)); - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); bpf_jit_uncharge_modmem(size); return NULL; } @@ -1141,7 +1165,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, kvfree(rw_header); if (IS_ERR(ptr)) { - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, ro_header->size); return PTR_ERR(ptr); } return 0; @@ -1162,7 +1186,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, { u32 size = ro_header->size; - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); kvfree(rw_header); bpf_jit_uncharge_modmem(size); } @@ -2673,12 +2697,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; + bool sleepable; u32 i; + sleepable = aux->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); + if (sleepable) + atomic64_dec(&map->sleepable_refcnt); bpf_map_put(map); } } diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index e01c741e5..2e73533a3 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -96,6 +96,12 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) migrate_enable(); } +__bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask) +{ + bpf_cpumask_release(cpumask); +} +CFI_NOSEAL(bpf_cpumask_release_dtor); + /** * bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask. * @cpumask: The cpumask being queried. @@ -405,6 +411,17 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, return cpumask_any_and_distribute(src1, src2); } +/** + * bpf_cpumask_weight() - Return the number of bits in @cpumask. + * @cpumask: The cpumask being queried. + * + * Count the number of set bits in the given cpumask. + */ +__bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask) +{ + return cpumask_weight(cpumask); +} + __bpf_kfunc_end_defs(); BTF_SET8_START(cpumask_kfunc_btf_ids) @@ -432,6 +449,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU) BTF_SET8_END(cpumask_kfunc_btf_ids) static const struct btf_kfunc_id_set cpumask_kfunc_set = { @@ -441,7 +459,7 @@ static const struct btf_kfunc_id_set cpumask_kfunc_set = { BTF_ID_LIST(cpumask_dtor_ids) BTF_ID(struct, bpf_cpumask) -BTF_ID(func, bpf_cpumask_release) +BTF_ID(func, bpf_cpumask_release_dtor) static int __init cpumask_kfunc_init(void) { diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index fa3e9225a..70fb82bf1 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -150,14 +150,11 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, goto out; d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE); if (!d->rw_image) { - u32 size = PAGE_SIZE; - - bpf_arch_text_copy(d->image, &size, sizeof(size)); - bpf_prog_pack_free((struct bpf_binary_header *)d->image); + bpf_prog_pack_free(d->image, PAGE_SIZE); d->image = NULL; goto out; } - bpf_image_ksym_add(d->image, &d->ksym); + bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym); } prev_num_progs = d->num_progs; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 85cd17ca3..3a088a534 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -2527,7 +2528,13 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, if (IS_ERR(ptr)) return PTR_ERR(ptr); + /* The htab bucket lock is always held during update operations in fd + * htab map, and the following rcu_read_lock() is only used to avoid + * the WARN_ON_ONCE in htab_map_update_elem(). + */ + rcu_read_lock(); ret = htab_map_update_elem(map, key, &ptr, map_flags); + rcu_read_unlock(); if (ret) map->ops->map_fd_put_ptr(map, ptr, false); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b912d055a..b10092754 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1943,10 +1943,7 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu) ma = &bpf_global_percpu_ma; else ma = &bpf_global_ma; - if (rec && rec->refcount_off >= 0) - bpf_mem_free_rcu(ma, p); - else - bpf_mem_free(ma, p); + bpf_mem_free_rcu(ma, p); } __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) @@ -2156,6 +2153,12 @@ __bpf_kfunc void bpf_task_release(struct task_struct *p) put_task_struct_rcu_user(p); } +__bpf_kfunc void bpf_task_release_dtor(void *p) +{ + put_task_struct_rcu_user(p); +} +CFI_NOSEAL(bpf_task_release_dtor); + #ifdef CONFIG_CGROUPS /** * bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by @@ -2180,6 +2183,12 @@ __bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp) cgroup_put(cgrp); } +__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp) +{ + cgroup_put(cgrp); +} +CFI_NOSEAL(bpf_cgroup_release_dtor); + /** * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor * array. A cgroup returned by this kfunc which is not subsequently stored in a @@ -2237,6 +2246,25 @@ __bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task, rcu_read_unlock(); return ret; } + +/** + * bpf_task_get_cgroup1 - Acquires the associated cgroup of a task within a + * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its + * hierarchy ID. + * @task: The target task + * @hierarchy_id: The ID of a cgroup1 hierarchy + * + * On success, the cgroup is returen. On failure, NULL is returned. + */ +__bpf_kfunc struct cgroup * +bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) +{ + struct cgroup *cgrp = task_get_cgroup1(task, hierarchy_id); + + if (IS_ERR(cgrp)) + return NULL; + return cgrp; +} #endif /* CONFIG_CGROUPS */ /** @@ -2543,6 +2571,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU) +BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_throw) @@ -2556,10 +2585,10 @@ static const struct btf_kfunc_id_set generic_kfunc_set = { BTF_ID_LIST(generic_dtor_ids) BTF_ID(struct, task_struct) -BTF_ID(func, bpf_task_release) +BTF_ID(func, bpf_task_release_dtor) #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) -BTF_ID(func, bpf_cgroup_release) +BTF_ID(func, bpf_cgroup_release_dtor) #endif BTF_SET8_START(common_btf_ids) @@ -2616,6 +2645,7 @@ static int __init kfunc_init(void) ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &generic_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set); ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors, ARRAY_SIZE(generic_dtors), @@ -2624,3 +2654,22 @@ static int __init kfunc_init(void) } late_initcall(kfunc_init); + +/* Get a pointer to dynptr data up to len bytes for read only access. If + * the dynptr doesn't have continuous data up to len bytes, return NULL. + */ +const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len) +{ + return bpf_dynptr_slice(ptr, 0, NULL, len); +} + +/* Get a pointer to dynptr data up to len bytes for read write access. If + * the dynptr doesn't have continuous data up to len bytes, or the dynptr + * is read only, return NULL. + */ +void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len) +{ + if (__bpf_dynptr_is_rdonly(ptr)) + return NULL; + return (void *)__bpf_dynptr_data(ptr, len); +} diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 1aafb2ff2..41e0a55c3 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -599,8 +599,15 @@ EXPORT_SYMBOL(bpf_prog_get_type_path); */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { - umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; - + struct inode *inode = d_inode(root); + umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; + + if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, inode->i_uid)); + if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); return 0; @@ -625,15 +632,21 @@ static const struct super_operations bpf_super_ops = { }; enum { + OPT_UID, + OPT_GID, OPT_MODE, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { + fsparam_u32 ("uid", OPT_UID), + fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), {} }; struct bpf_mount_opts { + kuid_t uid; + kgid_t gid; umode_t mode; }; @@ -641,6 +654,8 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct bpf_mount_opts *opts = fc->fs_private; struct fs_parse_result result; + kuid_t uid; + kgid_t gid; int opt; opt = fs_parse(fc, bpf_fs_parameters, param, &result); @@ -662,12 +677,42 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) } switch (opt) { + case OPT_UID: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + goto bad_value; + + /* + * The requested uid must be representable in the + * filesystem's idmapping. + */ + if (!kuid_has_mapping(fc->user_ns, uid)) + goto bad_value; + + opts->uid = uid; + break; + case OPT_GID: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + goto bad_value; + + /* + * The requested gid must be representable in the + * filesystem's idmapping. + */ + if (!kgid_has_mapping(fc->user_ns, gid)) + goto bad_value; + + opts->gid = gid; + break; case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; } return 0; +bad_value: + return invalfc(fc, "Bad value for '%s'", param->key); } struct bpf_preload_ops *bpf_preload_ops; @@ -750,6 +795,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; + inode->i_uid = opts->uid; + inode->i_gid = opts->gid; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); @@ -785,6 +832,8 @@ static int bpf_init_fs_context(struct fs_context *fc) return -ENOMEM; opts->mode = S_IRWXUGO; + opts->uid = current_fsuid(); + opts->gid = current_fsgid(); fc->fs_private = opts; fc->ops = &bpf_context_ops; diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 850494423..594a234f1 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -10,6 +10,8 @@ #include #include +#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) + static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) { /* ubuf and len_total should both be specified (or not) together */ @@ -325,3 +327,505 @@ __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, va_end(args); } EXPORT_SYMBOL_GPL(bpf_log); + +static const struct bpf_line_info * +find_linfo(const struct bpf_verifier_env *env, u32 insn_off) +{ + const struct bpf_line_info *linfo; + const struct bpf_prog *prog; + u32 i, nr_linfo; + + prog = env->prog; + nr_linfo = prog->aux->nr_linfo; + + if (!nr_linfo || insn_off >= prog->len) + return NULL; + + linfo = prog->aux->linfo; + for (i = 1; i < nr_linfo; i++) + if (insn_off < linfo[i].insn_off) + break; + + return &linfo[i - 1]; +} + +static const char *ltrim(const char *s) +{ + while (isspace(*s)) + s++; + + return s; +} + +__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, + u32 insn_off, + const char *prefix_fmt, ...) +{ + const struct bpf_line_info *linfo; + + if (!bpf_verifier_log_needed(&env->log)) + return; + + linfo = find_linfo(env, insn_off); + if (!linfo || linfo == env->prev_linfo) + return; + + if (prefix_fmt) { + va_list args; + + va_start(args, prefix_fmt); + bpf_verifier_vlog(&env->log, prefix_fmt, args); + va_end(args); + } + + verbose(env, "%s\n", + ltrim(btf_name_by_offset(env->prog->aux->btf, + linfo->line_off))); + + env->prev_linfo = linfo; +} + +static const char *btf_type_name(const struct btf *btf, u32 id) +{ + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); +} + +/* string representation of 'enum bpf_reg_type' + * + * Note that reg_type_str() can not appear more than once in a single verbose() + * statement. + */ +const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) +{ + char postfix[16] = {0}, prefix[64] = {0}; + static const char * const str[] = { + [NOT_INIT] = "?", + [SCALAR_VALUE] = "scalar", + [PTR_TO_CTX] = "ctx", + [CONST_PTR_TO_MAP] = "map_ptr", + [PTR_TO_MAP_VALUE] = "map_value", + [PTR_TO_STACK] = "fp", + [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", + [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCK_COMMON] = "sock_common", + [PTR_TO_TCP_SOCK] = "tcp_sock", + [PTR_TO_TP_BUFFER] = "tp_buffer", + [PTR_TO_XDP_SOCK] = "xdp_sock", + [PTR_TO_BTF_ID] = "ptr_", + [PTR_TO_MEM] = "mem", + [PTR_TO_BUF] = "buf", + [PTR_TO_FUNC] = "func", + [PTR_TO_MAP_KEY] = "map_key", + [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", + }; + + if (type & PTR_MAYBE_NULL) { + if (base_type(type) == PTR_TO_BTF_ID) + strncpy(postfix, "or_null_", 16); + else + strncpy(postfix, "_or_null", 16); + } + + snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", + type & MEM_RDONLY ? "rdonly_" : "", + type & MEM_RINGBUF ? "ringbuf_" : "", + type & MEM_USER ? "user_" : "", + type & MEM_PERCPU ? "percpu_" : "", + type & MEM_RCU ? "rcu_" : "", + type & PTR_UNTRUSTED ? "untrusted_" : "", + type & PTR_TRUSTED ? "trusted_" : "" + ); + + snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", + prefix, str[base_type(type)], postfix); + return env->tmp_str_buf; +} + +const char *dynptr_type_str(enum bpf_dynptr_type type) +{ + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + return "local"; + case BPF_DYNPTR_TYPE_RINGBUF: + return "ringbuf"; + case BPF_DYNPTR_TYPE_SKB: + return "skb"; + case BPF_DYNPTR_TYPE_XDP: + return "xdp"; + case BPF_DYNPTR_TYPE_INVALID: + return ""; + default: + WARN_ONCE(1, "unknown dynptr type %d\n", type); + return ""; + } +} + +const char *iter_type_str(const struct btf *btf, u32 btf_id) +{ + if (!btf || btf_id == 0) + return ""; + + /* we already validated that type is valid and has conforming name */ + return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1; +} + +const char *iter_state_str(enum bpf_iter_state state) +{ + switch (state) { + case BPF_ITER_STATE_ACTIVE: + return "active"; + case BPF_ITER_STATE_DRAINED: + return "drained"; + case BPF_ITER_STATE_INVALID: + return ""; + default: + WARN_ONCE(1, "unknown iter state %d\n", state); + return ""; + } +} + +static char slot_type_char[] = { + [STACK_INVALID] = '?', + [STACK_SPILL] = 'r', + [STACK_MISC] = 'm', + [STACK_ZERO] = '0', + [STACK_DYNPTR] = 'd', + [STACK_ITER] = 'i', +}; + +static void print_liveness(struct bpf_verifier_env *env, + enum bpf_reg_liveness live) +{ + if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) + verbose(env, "_"); + if (live & REG_LIVE_READ) + verbose(env, "r"); + if (live & REG_LIVE_WRITTEN) + verbose(env, "w"); + if (live & REG_LIVE_DONE) + verbose(env, "D"); +} + +#define UNUM_MAX_DECIMAL U16_MAX +#define SNUM_MAX_DECIMAL S16_MAX +#define SNUM_MIN_DECIMAL S16_MIN + +static bool is_unum_decimal(u64 num) +{ + return num <= UNUM_MAX_DECIMAL; +} + +static bool is_snum_decimal(s64 num) +{ + return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL; +} + +static void verbose_unum(struct bpf_verifier_env *env, u64 num) +{ + if (is_unum_decimal(num)) + verbose(env, "%llu", num); + else + verbose(env, "%#llx", num); +} + +static void verbose_snum(struct bpf_verifier_env *env, s64 num) +{ + if (is_snum_decimal(num)) + verbose(env, "%lld", num); + else + verbose(env, "%#llx", num); +} + +int tnum_strn(char *str, size_t size, struct tnum a) +{ + /* print as a constant, if tnum is fully known */ + if (a.mask == 0) { + if (is_unum_decimal(a.value)) + return snprintf(str, size, "%llu", a.value); + else + return snprintf(str, size, "%#llx", a.value); + } + return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); +} +EXPORT_SYMBOL_GPL(tnum_strn); + +static void print_scalar_ranges(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + const char **sep) +{ + /* For signed ranges, we want to unify 64-bit and 32-bit values in the + * output as much as possible, but there is a bit of a complication. + * If we choose to print values as decimals, this is natural to do, + * because negative 64-bit and 32-bit values >= -S32_MIN have the same + * representation due to sign extension. But if we choose to print + * them in hex format (see is_snum_decimal()), then sign extension is + * misleading. + * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in + * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two + * very different numbers. + * So we avoid sign extension if we choose to print values in hex. + */ + struct { + const char *name; + u64 val; + bool omit; + } minmaxs[] = { + {"smin", reg->smin_value, reg->smin_value == S64_MIN}, + {"smax", reg->smax_value, reg->smax_value == S64_MAX}, + {"umin", reg->umin_value, reg->umin_value == 0}, + {"umax", reg->umax_value, reg->umax_value == U64_MAX}, + {"smin32", + is_snum_decimal((s64)reg->s32_min_value) + ? (s64)reg->s32_min_value + : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN}, + {"smax32", + is_snum_decimal((s64)reg->s32_max_value) + ? (s64)reg->s32_max_value + : (u32)reg->s32_max_value, reg->s32_max_value == S32_MAX}, + {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, + {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, + }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; + bool neg1, neg2; + + for (m1 = &minmaxs[0]; m1 < mend; m1++) { + if (m1->omit) + continue; + + neg1 = m1->name[0] == 's' && (s64)m1->val < 0; + + verbose(env, "%s%s=", *sep, m1->name); + *sep = ","; + + for (m2 = m1 + 2; m2 < mend; m2 += 2) { + if (m2->omit || m2->val != m1->val) + continue; + /* don't mix negatives with positives */ + neg2 = m2->name[0] == 's' && (s64)m2->val < 0; + if (neg2 != neg1) + continue; + m2->omit = true; + verbose(env, "%s=", m2->name); + } + + if (m1->name[0] == 's') + verbose_snum(env, m1->val); + else + verbose_unum(env, m1->val); + } +} + +static bool type_is_map_ptr(enum bpf_reg_type t) { + switch (base_type(t)) { + case CONST_PTR_TO_MAP: + case PTR_TO_MAP_KEY: + case PTR_TO_MAP_VALUE: + return true; + default: + return false; + } +} + +/* + * _a stands for append, was shortened to avoid multiline statements below. + * This macro is used to output a comma separated list of attributes. + */ +#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) + +static void print_reg_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state, + const struct bpf_reg_state *reg) +{ + enum bpf_reg_type t; + const char *sep = ""; + + t = reg->type; + if (t == SCALAR_VALUE && reg->precise) + verbose(env, "P"); + if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) { + /* reg->off should be 0 for SCALAR_VALUE */ + verbose_snum(env, reg->var_off.value + reg->off); + return; + } + + verbose(env, "%s", reg_type_str(env, t)); + if (t == PTR_TO_STACK) { + if (state->frameno != reg->frameno) + verbose(env, "[%d]", reg->frameno); + if (tnum_is_const(reg->var_off)) { + verbose_snum(env, reg->var_off.value + reg->off); + return; + } + } + if (base_type(t) == PTR_TO_BTF_ID) + verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); + verbose(env, "("); + if (reg->id) + verbose_a("id=%d", reg->id); + if (reg->ref_obj_id) + verbose_a("ref_obj_id=%d", reg->ref_obj_id); + if (type_is_non_owning_ref(reg->type)) + verbose_a("%s", "non_own_ref"); + if (type_is_map_ptr(t)) { + if (reg->map_ptr->name[0]) + verbose_a("map=%s", reg->map_ptr->name); + verbose_a("ks=%d,vs=%d", + reg->map_ptr->key_size, + reg->map_ptr->value_size); + } + if (t != SCALAR_VALUE && reg->off) { + verbose_a("off="); + verbose_snum(env, reg->off); + } + if (type_is_pkt_pointer(t)) { + verbose_a("r="); + verbose_unum(env, reg->range); + } + if (base_type(t) == PTR_TO_MEM) { + verbose_a("sz="); + verbose_unum(env, reg->mem_size); + } + if (t == CONST_PTR_TO_DYNPTR) + verbose_a("type=%s", dynptr_type_str(reg->dynptr.type)); + if (tnum_is_const(reg->var_off)) { + /* a pointer register with fixed offset */ + if (reg->var_off.value) { + verbose_a("imm="); + verbose_snum(env, reg->var_off.value); + } + } else { + print_scalar_ranges(env, reg, &sep); + if (!tnum_is_unknown(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose_a("var_off=%s", tn_buf); + } + } + verbose(env, ")"); +} + +void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, + bool print_all) +{ + const struct bpf_reg_state *reg; + int i; + + if (state->frameno) + verbose(env, " frame%d:", state->frameno); + for (i = 0; i < MAX_BPF_REG; i++) { + reg = &state->regs[i]; + if (reg->type == NOT_INIT) + continue; + if (!print_all && !reg_scratched(env, i)) + continue; + verbose(env, " R%d", i); + print_liveness(env, reg->live); + verbose(env, "="); + print_reg_state(env, state, reg); + } + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + char types_buf[BPF_REG_SIZE + 1]; + const char *sep = ""; + bool valid = false; + u8 slot_type; + int j; + + if (!print_all && !stack_slot_scratched(env, i)) + continue; + + for (j = 0; j < BPF_REG_SIZE; j++) { + slot_type = state->stack[i].slot_type[j]; + if (slot_type != STACK_INVALID) + valid = true; + types_buf[j] = slot_type_char[slot_type]; + } + types_buf[BPF_REG_SIZE] = 0; + if (!valid) + continue; + + reg = &state->stack[i].spilled_ptr; + switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { + case STACK_SPILL: + /* print MISC/ZERO/INVALID slots above subreg spill */ + for (j = 0; j < BPF_REG_SIZE; j++) + if (state->stack[i].slot_type[j] == STACK_SPILL) + break; + types_buf[j] = '\0'; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=%s", types_buf); + print_reg_state(env, state, reg); + break; + case STACK_DYNPTR: + /* skip to main dynptr slot */ + i += BPF_DYNPTR_NR_SLOTS - 1; + reg = &state->stack[i].spilled_ptr; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type)); + if (reg->id) + verbose_a("id=%d", reg->id); + if (reg->ref_obj_id) + verbose_a("ref_id=%d", reg->ref_obj_id); + if (reg->dynptr_id) + verbose_a("dynptr_id=%d", reg->dynptr_id); + verbose(env, ")"); + break; + case STACK_ITER: + /* only main slot has ref_obj_id set; skip others */ + if (!reg->ref_obj_id) + continue; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)", + iter_type_str(reg->iter.btf, reg->iter.btf_id), + reg->ref_obj_id, iter_state_str(reg->iter.state), + reg->iter.depth); + break; + case STACK_MISC: + case STACK_ZERO: + default: + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=%s", types_buf); + break; + } + } + if (state->acquired_refs && state->refs[0].id) { + verbose(env, " refs=%d", state->refs[0].id); + for (i = 1; i < state->acquired_refs; i++) + if (state->refs[i].id) + verbose(env, ",%d", state->refs[i].id); + } + if (state->in_callback_fn) + verbose(env, " cb"); + if (state->in_async_callback_fn) + verbose(env, " async_cb"); + verbose(env, "\n"); + if (!print_all) + mark_verifier_state_clean(env); +} + +static inline u32 vlog_alignment(u32 pos) +{ + return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), + BPF_LOG_MIN_ALIGNMENT) - pos - 1; +} + +void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) +{ + if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { + /* remove new line character */ + bpf_vlog_reset(&env->log, env->prev_log_pos - 1); + verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' '); + } else { + verbose(env, "%d:", env->insn_idx); + } + print_verifier_state(env, state, false); +} diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 3248ff5d8..8ef269e66 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -131,12 +131,16 @@ void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { struct bpf_map *inner_map = ptr; - /* The inner map may still be used by both non-sleepable and sleepable - * bpf program, so free it after one RCU grace period and one tasks - * trace RCU grace period. + /* Defer the freeing of inner map according to the sleepable attribute + * of bpf program which owns the outer map, so unnecessary waiting for + * RCU tasks trace grace period can be avoided. */ - if (need_defer) - WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + if (need_defer) { + if (atomic64_read(&map->sleepable_refcnt)) + WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + else + WRITE_ONCE(inner_map->free_after_rcu_gp, true); + } bpf_map_put(inner_map); } diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index aa0fbf000..550f02e2c 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -121,6 +121,8 @@ struct bpf_mem_caches { struct bpf_mem_cache cache[NUM_CACHES]; }; +static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; + static struct llist_node notrace *__llist_del_first(struct llist_head *head) { struct llist_node *entry, *next; @@ -462,11 +464,17 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c) * consume ~ 11 Kbyte per cpu. * Typical case will be between 11K and 116K closer to 11K. * bpf progs can and should share bpf_mem_cache when possible. + * + * Percpu allocation is typically rare. To avoid potential unnecessary large + * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1. */ static void init_refill_work(struct bpf_mem_cache *c) { init_irq_work(&c->refill_work, bpf_mem_refill); - if (c->unit_size <= 256) { + if (c->percpu_size) { + c->low_watermark = 1; + c->high_watermark = 3; + } else if (c->unit_size <= 256) { c->low_watermark = 32; c->high_watermark = 96; } else { @@ -483,11 +491,16 @@ static void init_refill_work(struct bpf_mem_cache *c) static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) { - /* To avoid consuming memory assume that 1st run of bpf - * prog won't be doing more than 4 map_update_elem from - * irq disabled region + int cnt = 1; + + /* To avoid consuming memory, for non-percpu allocation, assume that + * 1st run of bpf prog won't be doing more than 4 map_update_elem from + * irq disabled region if unit size is less than or equal to 256. + * For all other cases, let us just do one allocation. */ - alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false); + if (!c->percpu_size && c->unit_size <= 256) + cnt = 4; + alloc_bulk(c, cnt, cpu_to_node(cpu), false); } /* When size != 0 bpf_mem_cache for each cpu. @@ -499,12 +512,14 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { - static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; struct bpf_mem_caches *cc, __percpu *pcc; struct bpf_mem_cache *c, __percpu *pc; struct obj_cgroup *objcg = NULL; int cpu, i, unit_size, percpu_size = 0; + if (percpu && size == 0) + return -EINVAL; + /* room for llist_node and per-cpu pointer */ if (percpu) percpu_size = LLIST_NODE_SZ + sizeof(void *); @@ -523,6 +538,8 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) if (memcg_bpf_enabled()) objcg = get_obj_cgroup_from_current(); #endif + ma->objcg = objcg; + for_each_possible_cpu(cpu) { c = per_cpu_ptr(pc, cpu); c->unit_size = unit_size; @@ -542,6 +559,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) #ifdef CONFIG_MEMCG_KMEM objcg = get_obj_cgroup_from_current(); #endif + ma->objcg = objcg; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); for (i = 0; i < NUM_CACHES; i++) { @@ -560,6 +578,56 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) return 0; } +int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg) +{ + struct bpf_mem_caches __percpu *pcc; + + pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL); + if (!pcc) + return -ENOMEM; + + ma->caches = pcc; + ma->objcg = objcg; + ma->percpu = true; + return 0; +} + +int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size) +{ + struct bpf_mem_caches *cc, __percpu *pcc; + int cpu, i, unit_size, percpu_size; + struct obj_cgroup *objcg; + struct bpf_mem_cache *c; + + i = bpf_mem_cache_idx(size); + if (i < 0) + return -EINVAL; + + /* room for llist_node and per-cpu pointer */ + percpu_size = LLIST_NODE_SZ + sizeof(void *); + + unit_size = sizes[i]; + objcg = ma->objcg; + pcc = ma->caches; + + for_each_possible_cpu(cpu) { + cc = per_cpu_ptr(pcc, cpu); + c = &cc->cache[i]; + if (c->unit_size) + break; + + c->unit_size = unit_size; + c->objcg = objcg; + c->percpu_size = percpu_size; + c->tgt = c; + + init_refill_work(c); + prefill_mem_cache(c, cpu); + } + + return 0; +} + static void drain_mem_cache(struct bpf_mem_cache *c) { bool percpu = !!c->percpu_size; @@ -691,9 +759,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } - /* objcg is the same across cpus */ - if (c->objcg) - obj_cgroup_put(c->objcg); + if (ma->objcg) + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { @@ -709,8 +776,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } - if (c->objcg) - obj_cgroup_put(c->objcg); + if (ma->objcg) + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } @@ -833,7 +900,9 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) if (!size) return NULL; - idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ); + if (!ma->percpu) + size += LLIST_NODE_SZ; + idx = bpf_mem_cache_idx(size); if (idx < 0) return NULL; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 349d735b4..0f90b6b27 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -142,9 +142,13 @@ static u32 bpf_map_value_size(const struct bpf_map *map) static void maybe_wait_bpf_programs(struct bpf_map *map) { - /* Wait for any running BPF programs to complete so that - * userspace, when we return to it, knows that all programs - * that could be running use the new map value. + /* Wait for any running non-sleepable BPF programs to complete so that + * userspace, when we return to it, knows that all non-sleepable + * programs that could be running use the new map value. For sleepable + * BPF programs, synchronize_rcu_tasks_trace() should be used to wait + * for the completions of these programs, but considering the waiting + * time can be very long and userspace may think it will hang forever, + * so don't handle sleepable BPF programs now. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) @@ -180,15 +184,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { - rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); - rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - rcu_read_lock(); err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); - rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, @@ -203,7 +203,6 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, rcu_read_unlock(); } bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); return err; } @@ -264,7 +263,6 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); return err; } @@ -755,8 +753,11 @@ void bpf_map_put(struct bpf_map *map) /* bpf_map_free_id() must be called first */ bpf_map_free_id(map); + WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); if (READ_ONCE(map->free_after_mult_rcu_gp)) call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); + else if (READ_ONCE(map->free_after_rcu_gp)) + call_rcu(&map->rcu, bpf_map_free_rcu_gp); else bpf_map_free_in_work(map); } @@ -1550,6 +1551,8 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) } err = bpf_map_update_value(map, f.file, key, value, attr->flags); + if (!err) + maybe_wait_bpf_programs(map); kvfree(value); free_key: @@ -1605,7 +1608,8 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); + if (!err) + maybe_wait_bpf_programs(map); out: kvfree(key); err_put: @@ -1734,7 +1738,6 @@ int generic_map_delete_batch(struct bpf_map *map, kvfree(key); - maybe_wait_bpf_programs(map); return err; } @@ -1795,6 +1798,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, kvfree(value); kvfree(key); + return err; } @@ -2605,7 +2609,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | - BPF_F_XDP_DEV_BOUND_ONLY)) + BPF_F_XDP_DEV_BOUND_ONLY | + BPF_F_TEST_REG_INVARIANTS)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -2733,6 +2738,22 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) goto free_prog_sec; } + /* + * Bookkeeping for managing the program attachment chain. + * + * It might be tempting to set attach_tracing_prog flag at the attachment + * time, but this will not prevent from loading bunch of tracing prog + * first, then attach them one to another. + * + * The flag attach_tracing_prog is set for the whole program lifecycle, and + * doesn't have to be cleared in bpf_tracing_link_release, since tracing + * programs cannot change attachment target. + */ + if (type == BPF_PROG_TYPE_TRACING && dst_prog && + dst_prog->type == BPF_PROG_TYPE_TRACING) { + prog->aux->attach_tracing_prog = true; + } + /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) @@ -2874,17 +2895,46 @@ void bpf_link_inc(struct bpf_link *link) atomic64_inc(&link->refcnt); } +static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) +{ + struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); + + /* free bpf_link and its containing memory */ + link->ops->dealloc_deferred(link); +} + +static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_link_defer_dealloc_rcu_gp(rcu); + else + call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); +} + /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { + bool sleepable = false; + bpf_link_free_id(link->id); if (link->prog) { + sleepable = link->prog->aux->sleepable; /* detach BPF program, clean up used resources */ link->ops->release(link); bpf_prog_put(link->prog); } - /* free bpf_link and its containing memory */ - link->ops->dealloc(link); + if (link->ops->dealloc_deferred) { + /* schedule BPF link deallocation; if underlying BPF program + * is sleepable, we need to first wait for RCU tasks trace + * sync, then go through "classic" RCU grace period + */ + if (sleepable) + call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); + else + call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); + } + if (link->ops->dealloc) + link->ops->dealloc(link); } static void bpf_link_put_deferred(struct work_struct *work) @@ -3166,7 +3216,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, } if (tgt_prog_fd) { - /* For now we only allow new targets for BPF_PROG_TYPE_EXT */ + /* + * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this + * part would be changed to implement the same for + * BPF_PROG_TYPE_TRACING, do not forget to update the way how + * attach_tracing_prog flag is set. + */ if (prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; @@ -3389,7 +3444,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, - .dealloc = bpf_raw_tp_link_dealloc, + .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; @@ -4960,8 +5015,10 @@ static int bpf_map_do_batch(const union bpf_attr *attr, else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: - if (has_write) + if (has_write) { + maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); + } fdput(f); return err; } @@ -5363,6 +5420,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr) goto out_unlock; } + /* The bpf program will not access the bpf map, but for the sake of + * simplicity, increase sleepable_refcnt for sleepable program as well. + */ + if (prog->aux->sleepable) + atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 26082b978..ec4e97c61 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -70,15 +70,13 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm return NULL; retry: - task = next_thread(task); + task = __next_thread(task); + if (!task) + return NULL; next_tid = __task_pid_nr_ns(task, PIDTYPE_PID, common->ns); - if (!next_tid || next_tid == common->pid) { - /* Run out of tasks of a process. The tasks of a - * thread_group are linked as circular linked list. - */ - return NULL; - } + if (!next_tid) + goto retry; if (skip_if_dup_files && task->files == task->group_leader->files) goto retry; @@ -980,7 +978,8 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != __alignof__(struct bpf_iter_task)); - kit->task = kit->pos = NULL; + kit->pos = NULL; + switch (flags) { case BPF_TASK_ITER_ALL_THREADS: case BPF_TASK_ITER_ALL_PROCS: @@ -1017,20 +1016,16 @@ __bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) if (flags == BPF_TASK_ITER_ALL_PROCS) goto get_next_task; - kit->pos = next_thread(kit->pos); - if (kit->pos == kit->task) { - if (flags == BPF_TASK_ITER_PROC_THREADS) { - kit->pos = NULL; - return pos; - } - } else + kit->pos = __next_thread(kit->pos); + if (kit->pos || flags == BPF_TASK_ITER_PROC_THREADS) return pos; get_next_task: - kit->pos = next_task(kit->pos); - kit->task = kit->pos; - if (kit->pos == &init_task) + kit->task = next_task(kit->task); + if (kit->task == &init_task) kit->pos = NULL; + else + kit->pos = kit->task; return pos; } diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index 3d7127f43..9dbc31b25 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -172,12 +172,6 @@ bool tnum_in(struct tnum a, struct tnum b) return a.value == b.value; } -int tnum_strn(char *str, size_t size, struct tnum a) -{ - return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); -} -EXPORT_SYMBOL_GPL(tnum_strn); - int tnum_sbin(char *str, size_t size, struct tnum a) { size_t n; @@ -208,7 +202,12 @@ struct tnum tnum_clear_subreg(struct tnum a) return tnum_lshift(tnum_rshift(a, 32), 32); } +struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg) +{ + return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg)); +} + struct tnum tnum_const_subreg(struct tnum a, u32 value) { - return tnum_or(tnum_clear_subreg(a), tnum_const(value)); + return tnum_with_subreg(a, tnum_const(value)); } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index e97aeda3a..d382f5ebe 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -115,10 +115,10 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog) (ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC); } -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym) +void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym) { ksym->start = (unsigned long) data; - ksym->end = ksym->start + PAGE_SIZE; + ksym->end = ksym->start + size; bpf_ksym_add(ksym); perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, PAGE_SIZE, false, ksym->name); @@ -254,8 +254,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a static void bpf_tramp_image_free(struct bpf_tramp_image *im) { bpf_image_ksym_del(&im->ksym); - bpf_jit_free_exec(im->image); - bpf_jit_uncharge_modmem(PAGE_SIZE); + arch_free_bpf_trampoline(im->image, im->size); + bpf_jit_uncharge_modmem(im->size); percpu_ref_exit(&im->pcref); kfree_rcu(im, rcu); } @@ -349,7 +349,7 @@ 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) +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size) { struct bpf_tramp_image *im; struct bpf_ksym *ksym; @@ -360,15 +360,15 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) if (!im) goto out; - err = bpf_jit_charge_modmem(PAGE_SIZE); + err = bpf_jit_charge_modmem(size); if (err) goto out_free_im; + im->size = size; err = -ENOMEM; - im->image = image = bpf_jit_alloc_exec(PAGE_SIZE); + im->image = image = arch_alloc_bpf_trampoline(size); if (!image) goto out_uncharge; - set_vm_flush_reset_perms(image); err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL); if (err) @@ -377,13 +377,13 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) ksym = &im->ksym; INIT_LIST_HEAD_RCU(&ksym->lnode); snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key); - bpf_image_ksym_add(image, ksym); + bpf_image_ksym_add(image, size, ksym); return im; out_free_image: - bpf_jit_free_exec(im->image); + arch_free_bpf_trampoline(im->image, im->size); out_uncharge: - bpf_jit_uncharge_modmem(PAGE_SIZE); + bpf_jit_uncharge_modmem(size); out_free_im: kfree(im); out: @@ -396,7 +396,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut struct bpf_tramp_links *tlinks; u32 orig_flags = tr->flags; bool ip_arg = false; - int err, total; + int err, total, size; tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg); if (IS_ERR(tlinks)) @@ -409,12 +409,6 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut goto out; } - im = bpf_tramp_image_alloc(tr->key); - if (IS_ERR(im)) { - err = PTR_ERR(im); - goto out; - } - /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */ tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX); @@ -438,13 +432,31 @@ again: tr->flags |= BPF_TRAMP_F_ORIG_STACK; #endif - err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, + size = arch_bpf_trampoline_size(&tr->func.model, tr->flags, + tlinks, tr->func.addr); + if (size < 0) { + err = size; + goto out; + } + + if (size > PAGE_SIZE) { + err = -E2BIG; + goto out; + } + + im = bpf_tramp_image_alloc(tr->key, size); + if (IS_ERR(im)) { + err = PTR_ERR(im); + goto out; + } + + err = arch_prepare_bpf_trampoline(im, im->image, im->image + size, &tr->func.model, tr->flags, tlinks, tr->func.addr); if (err < 0) goto out_free; - set_memory_rox((long)im->image, 1); + arch_protect_bpf_trampoline(im->image, im->size); WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) @@ -464,9 +476,8 @@ again: tr->fops->func = NULL; tr->fops->trampoline = 0; - /* reset im->image memory attr for arch_prepare_bpf_trampoline */ - set_memory_nx((long)im->image, 1); - set_memory_rw((long)im->image, 1); + /* free im memory and reallocate later */ + bpf_tramp_image_free(im); goto again; } #endif @@ -1032,10 +1043,50 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) } int __weak -arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call) + void *func_addr) +{ + return -ENOTSUPP; +} + +void * __weak arch_alloc_bpf_trampoline(unsigned int size) +{ + void *image; + + if (WARN_ON_ONCE(size > PAGE_SIZE)) + return NULL; + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (image) + set_vm_flush_reset_perms(image); + return image; +} + +void __weak arch_free_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + /* bpf_jit_free_exec doesn't need "size", but + * bpf_prog_pack_free() needs it. + */ + bpf_jit_free_exec(image); +} + +void __weak arch_protect_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + set_memory_rox((long)image, 1); +} + +void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + set_memory_nx((long)image, 1); + set_memory_rw((long)image, 1); +} + +int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) { return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 890d4c4bf..19e575e6b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -195,6 +195,8 @@ struct bpf_verifier_stack_elem { POISON_POINTER_DELTA)) #define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV)) +#define BPF_GLOBAL_PERCPU_MA_MAX_SIZE 512 + static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); static void invalidate_non_owning_refs(struct bpf_verifier_env *env); @@ -339,30 +341,14 @@ struct bpf_kfunc_call_arg_meta { struct btf *btf_vmlinux; -static DEFINE_MUTEX(bpf_verifier_lock); -static DEFINE_MUTEX(bpf_percpu_ma_lock); - -static const struct bpf_line_info * -find_linfo(const struct bpf_verifier_env *env, u32 insn_off) +static const char *btf_type_name(const struct btf *btf, u32 id) { - const struct bpf_line_info *linfo; - const struct bpf_prog *prog; - u32 i, nr_linfo; - - prog = env->prog; - nr_linfo = prog->aux->nr_linfo; - - if (!nr_linfo || insn_off >= prog->len) - return NULL; - - linfo = prog->aux->linfo; - for (i = 1; i < nr_linfo; i++) - if (insn_off < linfo[i].insn_off) - break; - - return &linfo[i - 1]; + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } +static DEFINE_MUTEX(bpf_verifier_lock); +static DEFINE_MUTEX(bpf_percpu_ma_lock); + __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { struct bpf_verifier_env *env = private_data; @@ -376,73 +362,25 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) va_end(args); } -static const char *ltrim(const char *s) -{ - while (isspace(*s)) - s++; - - return s; -} - -__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env, - u32 insn_off, - const char *prefix_fmt, ...) -{ - const struct bpf_line_info *linfo; - - if (!bpf_verifier_log_needed(&env->log)) - return; - - linfo = find_linfo(env, insn_off); - if (!linfo || linfo == env->prev_linfo) - return; - - if (prefix_fmt) { - va_list args; - - va_start(args, prefix_fmt); - bpf_verifier_vlog(&env->log, prefix_fmt, args); - va_end(args); - } - - verbose(env, "%s\n", - ltrim(btf_name_by_offset(env->prog->aux->btf, - linfo->line_off))); - - env->prev_linfo = linfo; -} - static void verbose_invalid_scalar(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - struct tnum *range, const char *ctx, + struct bpf_retval_range range, const char *ctx, const char *reg_name) { - char tn_buf[48]; + bool unknown = true; - verbose(env, "At %s the register %s ", ctx, reg_name); - if (!tnum_is_unknown(reg->var_off)) { - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "has value %s", tn_buf); - } else { - verbose(env, "has unknown scalar value"); + verbose(env, "%s the register %s has", ctx, reg_name); + if (reg->smin_value > S64_MIN) { + verbose(env, " smin=%lld", reg->smin_value); + unknown = false; } - tnum_strn(tn_buf, sizeof(tn_buf), *range); - verbose(env, " should have been in %s\n", tn_buf); -} - -static bool type_is_pkt_pointer(enum bpf_reg_type type) -{ - type = base_type(type); - return type == PTR_TO_PACKET || - type == PTR_TO_PACKET_META; -} - -static bool type_is_sk_pointer(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET || - type == PTR_TO_SOCK_COMMON || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_XDP_SOCK; + if (reg->smax_value < S64_MAX) { + verbose(env, " smax=%lld", reg->smax_value); + unknown = false; + } + if (unknown) + verbose(env, " unknown scalar value"); + verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval); } static bool type_may_be_null(u32 type) @@ -468,16 +406,6 @@ static bool reg_not_null(const struct bpf_reg_state *reg) type == PTR_TO_MEM; } -static bool type_is_ptr_alloc_obj(u32 type) -{ - return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; -} - -static bool type_is_non_owning_ref(u32 type) -{ - return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF; -} - static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) { struct btf_record *rec = NULL; @@ -500,6 +428,31 @@ static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL; } +static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) +{ + struct bpf_func_info *info; + + if (!env->prog->aux->func_info) + return ""; + + info = &env->prog->aux->func_info[subprog]; + return btf_type_name(env->prog->aux->btf, info->type_id); +} + +static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog) +{ + struct bpf_subprog_info *info = subprog_info(env, subprog); + + info->is_cb = true; + info->is_async_cb = true; + info->is_exception_cb = true; +} + +static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog) +{ + return subprog_info(env, subprog)->is_exception_cb; +} + static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); @@ -605,83 +558,6 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) insn->imm == BPF_CMPXCHG; } -/* string representation of 'enum bpf_reg_type' - * - * Note that reg_type_str() can not appear more than once in a single verbose() - * statement. - */ -static const char *reg_type_str(struct bpf_verifier_env *env, - enum bpf_reg_type type) -{ - char postfix[16] = {0}, prefix[64] = {0}; - static const char * const str[] = { - [NOT_INIT] = "?", - [SCALAR_VALUE] = "scalar", - [PTR_TO_CTX] = "ctx", - [CONST_PTR_TO_MAP] = "map_ptr", - [PTR_TO_MAP_VALUE] = "map_value", - [PTR_TO_STACK] = "fp", - [PTR_TO_PACKET] = "pkt", - [PTR_TO_PACKET_META] = "pkt_meta", - [PTR_TO_PACKET_END] = "pkt_end", - [PTR_TO_FLOW_KEYS] = "flow_keys", - [PTR_TO_SOCKET] = "sock", - [PTR_TO_SOCK_COMMON] = "sock_common", - [PTR_TO_TCP_SOCK] = "tcp_sock", - [PTR_TO_TP_BUFFER] = "tp_buffer", - [PTR_TO_XDP_SOCK] = "xdp_sock", - [PTR_TO_BTF_ID] = "ptr_", - [PTR_TO_MEM] = "mem", - [PTR_TO_BUF] = "buf", - [PTR_TO_FUNC] = "func", - [PTR_TO_MAP_KEY] = "map_key", - [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", - }; - - if (type & PTR_MAYBE_NULL) { - if (base_type(type) == PTR_TO_BTF_ID) - strncpy(postfix, "or_null_", 16); - else - strncpy(postfix, "_or_null", 16); - } - - snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", - type & MEM_RDONLY ? "rdonly_" : "", - type & MEM_RINGBUF ? "ringbuf_" : "", - type & MEM_USER ? "user_" : "", - type & MEM_PERCPU ? "percpu_" : "", - type & MEM_RCU ? "rcu_" : "", - type & PTR_UNTRUSTED ? "untrusted_" : "", - type & PTR_TRUSTED ? "trusted_" : "" - ); - - snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", - prefix, str[base_type(type)], postfix); - return env->tmp_str_buf; -} - -static char slot_type_char[] = { - [STACK_INVALID] = '?', - [STACK_SPILL] = 'r', - [STACK_MISC] = 'm', - [STACK_ZERO] = '0', - [STACK_DYNPTR] = 'd', - [STACK_ITER] = 'i', -}; - -static void print_liveness(struct bpf_verifier_env *env, - enum bpf_reg_liveness live) -{ - if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) - verbose(env, "_"); - if (live & REG_LIVE_READ) - verbose(env, "r"); - if (live & REG_LIVE_WRITTEN) - verbose(env, "w"); - if (live & REG_LIVE_DONE) - verbose(env, "D"); -} - static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; @@ -746,92 +622,6 @@ static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); } -static const char *btf_type_name(const struct btf *btf, u32 id) -{ - return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); -} - -static const char *dynptr_type_str(enum bpf_dynptr_type type) -{ - switch (type) { - case BPF_DYNPTR_TYPE_LOCAL: - return "local"; - case BPF_DYNPTR_TYPE_RINGBUF: - return "ringbuf"; - case BPF_DYNPTR_TYPE_SKB: - return "skb"; - case BPF_DYNPTR_TYPE_XDP: - return "xdp"; - case BPF_DYNPTR_TYPE_INVALID: - return ""; - default: - WARN_ONCE(1, "unknown dynptr type %d\n", type); - return ""; - } -} - -static const char *iter_type_str(const struct btf *btf, u32 btf_id) -{ - if (!btf || btf_id == 0) - return ""; - - /* we already validated that type is valid and has conforming name */ - return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1; -} - -static const char *iter_state_str(enum bpf_iter_state state) -{ - switch (state) { - case BPF_ITER_STATE_ACTIVE: - return "active"; - case BPF_ITER_STATE_DRAINED: - return "drained"; - case BPF_ITER_STATE_INVALID: - return ""; - default: - WARN_ONCE(1, "unknown iter state %d\n", state); - return ""; - } -} - -static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) -{ - env->scratched_regs |= 1U << regno; -} - -static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) -{ - env->scratched_stack_slots |= 1ULL << spi; -} - -static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) -{ - return (env->scratched_regs >> regno) & 1; -} - -static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) -{ - return (env->scratched_stack_slots >> regno) & 1; -} - -static bool verifier_state_scratched(const struct bpf_verifier_env *env) -{ - return env->scratched_regs || env->scratched_stack_slots; -} - -static void mark_verifier_state_clean(struct bpf_verifier_env *env) -{ - env->scratched_regs = 0U; - env->scratched_stack_slots = 0ULL; -} - -/* Used for printing the entire verifier state. */ -static void mark_verifier_state_scratched(struct bpf_verifier_env *env) -{ - env->scratched_regs = ~0U; - env->scratched_stack_slots = ~0ULL; -} - static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) { switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { @@ -1365,230 +1155,25 @@ static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) stack->spilled_ptr.type == SCALAR_VALUE; } -static void scrub_spilled_slot(u8 *stype) -{ - if (*stype != STACK_INVALID) - *stype = STACK_MISC; -} - -static void print_scalar_ranges(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, - const char **sep) -{ - struct { - const char *name; - u64 val; - bool omit; - } minmaxs[] = { - {"smin", reg->smin_value, reg->smin_value == S64_MIN}, - {"smax", reg->smax_value, reg->smax_value == S64_MAX}, - {"umin", reg->umin_value, reg->umin_value == 0}, - {"umax", reg->umax_value, reg->umax_value == U64_MAX}, - {"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN}, - {"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX}, - {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, - {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, - }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; - bool neg1, neg2; - - for (m1 = &minmaxs[0]; m1 < mend; m1++) { - if (m1->omit) - continue; - - neg1 = m1->name[0] == 's' && (s64)m1->val < 0; - - verbose(env, "%s%s=", *sep, m1->name); - *sep = ","; - - for (m2 = m1 + 2; m2 < mend; m2 += 2) { - if (m2->omit || m2->val != m1->val) - continue; - /* don't mix negatives with positives */ - neg2 = m2->name[0] == 's' && (s64)m2->val < 0; - if (neg2 != neg1) - continue; - m2->omit = true; - verbose(env, "%s=", m2->name); - } - - verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val); - } -} - -static void print_verifier_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state, - bool print_all) -{ - const struct bpf_reg_state *reg; - enum bpf_reg_type t; - int i; - - if (state->frameno) - verbose(env, " frame%d:", state->frameno); - for (i = 0; i < MAX_BPF_REG; i++) { - reg = &state->regs[i]; - t = reg->type; - if (t == NOT_INIT) - continue; - if (!print_all && !reg_scratched(env, i)) - continue; - verbose(env, " R%d", i); - print_liveness(env, reg->live); - verbose(env, "="); - if (t == SCALAR_VALUE && reg->precise) - verbose(env, "P"); - if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && - tnum_is_const(reg->var_off)) { - /* reg->off should be 0 for SCALAR_VALUE */ - verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t)); - verbose(env, "%lld", reg->var_off.value + reg->off); - } else { - const char *sep = ""; - - verbose(env, "%s", reg_type_str(env, t)); - if (base_type(t) == PTR_TO_BTF_ID) - verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); - verbose(env, "("); -/* - * _a stands for append, was shortened to avoid multiline statements below. - * This macro is used to output a comma separated list of attributes. +/* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which + * case they are equivalent, or it's STACK_ZERO, in which case we preserve + * more precise STACK_ZERO. + * Note, in uprivileged mode leaving STACK_INVALID is wrong, so we take + * env->allow_ptr_leaks into account and force STACK_MISC, if necessary. */ -#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; }) - - if (reg->id) - verbose_a("id=%d", reg->id); - if (reg->ref_obj_id) - verbose_a("ref_obj_id=%d", reg->ref_obj_id); - if (type_is_non_owning_ref(reg->type)) - verbose_a("%s", "non_own_ref"); - if (t != SCALAR_VALUE) - verbose_a("off=%d", reg->off); - if (type_is_pkt_pointer(t)) - verbose_a("r=%d", reg->range); - else if (base_type(t) == CONST_PTR_TO_MAP || - base_type(t) == PTR_TO_MAP_KEY || - base_type(t) == PTR_TO_MAP_VALUE) - verbose_a("ks=%d,vs=%d", - reg->map_ptr->key_size, - reg->map_ptr->value_size); - if (tnum_is_const(reg->var_off)) { - /* Typically an immediate SCALAR_VALUE, but - * could be a pointer whose offset is too big - * for reg->off - */ - verbose_a("imm=%llx", reg->var_off.value); - } else { - print_scalar_ranges(env, reg, &sep); - if (!tnum_is_unknown(reg->var_off)) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose_a("var_off=%s", tn_buf); - } - } -#undef verbose_a - - verbose(env, ")"); - } - } - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - char types_buf[BPF_REG_SIZE + 1]; - bool valid = false; - int j; - - for (j = 0; j < BPF_REG_SIZE; j++) { - if (state->stack[i].slot_type[j] != STACK_INVALID) - valid = true; - types_buf[j] = slot_type_char[state->stack[i].slot_type[j]]; - } - types_buf[BPF_REG_SIZE] = 0; - if (!valid) - continue; - if (!print_all && !stack_slot_scratched(env, i)) - continue; - switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { - case STACK_SPILL: - reg = &state->stack[i].spilled_ptr; - t = reg->type; - - verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); - print_liveness(env, reg->live); - verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t)); - if (t == SCALAR_VALUE && reg->precise) - verbose(env, "P"); - if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) - verbose(env, "%lld", reg->var_off.value + reg->off); - break; - case STACK_DYNPTR: - i += BPF_DYNPTR_NR_SLOTS - 1; - reg = &state->stack[i].spilled_ptr; - - verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); - print_liveness(env, reg->live); - verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type)); - if (reg->ref_obj_id) - verbose(env, "(ref_id=%d)", reg->ref_obj_id); - break; - case STACK_ITER: - /* only main slot has ref_obj_id set; skip others */ - reg = &state->stack[i].spilled_ptr; - if (!reg->ref_obj_id) - continue; - - verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); - print_liveness(env, reg->live); - verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)", - iter_type_str(reg->iter.btf, reg->iter.btf_id), - reg->ref_obj_id, iter_state_str(reg->iter.state), - reg->iter.depth); - break; - case STACK_MISC: - case STACK_ZERO: - default: - reg = &state->stack[i].spilled_ptr; - - for (j = 0; j < BPF_REG_SIZE; j++) - types_buf[j] = slot_type_char[state->stack[i].slot_type[j]]; - types_buf[BPF_REG_SIZE] = 0; - - verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); - print_liveness(env, reg->live); - verbose(env, "=%s", types_buf); - break; - } - } - if (state->acquired_refs && state->refs[0].id) { - verbose(env, " refs=%d", state->refs[0].id); - for (i = 1; i < state->acquired_refs; i++) - if (state->refs[i].id) - verbose(env, ",%d", state->refs[i].id); - } - if (state->in_callback_fn) - verbose(env, " cb"); - if (state->in_async_callback_fn) - verbose(env, " async_cb"); - verbose(env, "\n"); - if (!print_all) - mark_verifier_state_clean(env); -} - -static inline u32 vlog_alignment(u32 pos) +static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype) { - return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), - BPF_LOG_MIN_ALIGNMENT) - pos - 1; + if (*stype == STACK_ZERO) + return; + if (env->allow_ptr_leaks && *stype == STACK_INVALID) + return; + *stype = STACK_MISC; } -static void print_insn_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state) +static void scrub_spilled_slot(u8 *stype) { - if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { - /* remove new line character */ - bpf_vlog_reset(&env->log, env->prev_log_pos - 1); - verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' '); - } else { - verbose(env, "%d:", env->insn_idx); - } - print_verifier_state(env, state, false); + if (*stype != STACK_INVALID) + *stype = STACK_MISC; } /* copy array src of length n * size bytes to dst. dst is reallocated if it's too @@ -1690,7 +1275,11 @@ static int resize_reference_state(struct bpf_func_state *state, size_t n) */ static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size) { - size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE; + size_t old_n = state->allocated_stack / BPF_REG_SIZE, n; + + /* The stack size is always a multiple of BPF_REG_SIZE. */ + size = round_up(size, BPF_REG_SIZE); + n = size / BPF_REG_SIZE; if (old_n >= n) return 0; @@ -1804,8 +1393,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, int i, err; dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history, - src->jmp_history_cnt, sizeof(struct bpf_idx_pair), - GFP_USER); + src->jmp_history_cnt, sizeof(*dst_state->jmp_history), + GFP_USER); if (!dst_state->jmp_history) return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; @@ -2180,10 +1769,14 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) __mark_reg_known(reg, 0); } -static void __mark_reg_const_zero(struct bpf_reg_state *reg) +static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); reg->type = SCALAR_VALUE; + /* all scalars are assumed imprecise initially (unless unprivileged, + * in which case everything is forced to be precise) + */ + reg->precise = !env->bpf_capable; } static void mark_reg_known_zero(struct bpf_verifier_env *env, @@ -2349,69 +1942,214 @@ static void __update_reg_bounds(struct bpf_reg_state *reg) /* Uses signed min/max values to inform unsigned, and vice-versa */ static void __reg32_deduce_bounds(struct bpf_reg_state *reg) { - /* Learn sign from signed bounds. - * If we cannot cross the sign boundary, then signed and unsigned bounds - * are the same, so combine. This works even in the negative case, e.g. - * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. + /* If upper 32 bits of u64/s64 range don't change, we can use lower 32 + * bits to improve our u32/s32 boundaries. + * + * E.g., the case where we have upper 32 bits as zero ([10, 20] in + * u64) is pretty trivial, it's obvious that in u32 we'll also have + * [10, 20] range. But this property holds for any 64-bit range as + * long as upper 32 bits in that entire range of values stay the same. + * + * E.g., u64 range [0x10000000A, 0x10000000F] ([4294967306, 4294967311] + * in decimal) has the same upper 32 bits throughout all the values in + * that range. As such, lower 32 bits form a valid [0xA, 0xF] ([10, 15]) + * range. + * + * Note also, that [0xA, 0xF] is a valid range both in u32 and in s32, + * following the rules outlined below about u64/s64 correspondence + * (which equally applies to u32 vs s32 correspondence). In general it + * depends on actual hexadecimal values of 32-bit range. They can form + * only valid u32, or only valid s32 ranges in some cases. + * + * So we use all these insights to derive bounds for subregisters here. */ - if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) { - reg->s32_min_value = reg->u32_min_value = - max_t(u32, reg->s32_min_value, reg->u32_min_value); - reg->s32_max_value = reg->u32_max_value = - min_t(u32, reg->s32_max_value, reg->u32_max_value); - return; + if ((reg->umin_value >> 32) == (reg->umax_value >> 32)) { + /* u64 to u32 casting preserves validity of low 32 bits as + * a range, if upper 32 bits are the same + */ + reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->umin_value); + reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->umax_value); + + if ((s32)reg->umin_value <= (s32)reg->umax_value) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); + } + } + if ((reg->smin_value >> 32) == (reg->smax_value >> 32)) { + /* low 32 bits should form a proper u32 range */ + if ((u32)reg->smin_value <= (u32)reg->smax_value) { + reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->smin_value); + reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->smax_value); + } + /* low 32 bits should form a proper s32 range */ + if ((s32)reg->smin_value <= (s32)reg->smax_value) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); + } + } + /* Special case where upper bits form a small sequence of two + * sequential numbers (in 32-bit unsigned space, so 0xffffffff to + * 0x00000000 is also valid), while lower bits form a proper s32 range + * going from negative numbers to positive numbers. E.g., let's say we + * have s64 range [-1, 1] ([0xffffffffffffffff, 0x0000000000000001]). + * Possible s64 values are {-1, 0, 1} ({0xffffffffffffffff, + * 0x0000000000000000, 0x00000000000001}). Ignoring upper 32 bits, + * we still get a valid s32 range [-1, 1] ([0xffffffff, 0x00000001]). + * Note that it doesn't have to be 0xffffffff going to 0x00000000 in + * upper 32 bits. As a random example, s64 range + * [0xfffffff0fffffff0; 0xfffffff100000010], forms a valid s32 range + * [-16, 16] ([0xfffffff0; 0x00000010]) in its 32 bit subregister. + */ + if ((u32)(reg->umin_value >> 32) + 1 == (u32)(reg->umax_value >> 32) && + (s32)reg->umin_value < 0 && (s32)reg->umax_value >= 0) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); + } + if ((u32)(reg->smin_value >> 32) + 1 == (u32)(reg->smax_value >> 32) && + (s32)reg->smin_value < 0 && (s32)reg->smax_value >= 0) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); + } + /* if u32 range forms a valid s32 range (due to matching sign bit), + * try to learn from that + */ + if ((s32)reg->u32_min_value <= (s32)reg->u32_max_value) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, reg->u32_min_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, reg->u32_max_value); } - /* Learn sign from unsigned bounds. Signed bounds cross the sign - * boundary, so we must be careful. + /* If we cannot cross the sign boundary, then signed and unsigned bounds + * are the same, so combine. This works even in the negative case, e.g. + * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ - if ((s32)reg->u32_max_value >= 0) { - /* Positive. We can't learn anything from the smin, but smax - * is positive, hence safe. - */ - reg->s32_min_value = reg->u32_min_value; - reg->s32_max_value = reg->u32_max_value = - min_t(u32, reg->s32_max_value, reg->u32_max_value); - } else if ((s32)reg->u32_min_value < 0) { - /* Negative. We can't learn anything from the smax, but smin - * is negative, hence safe. - */ - reg->s32_min_value = reg->u32_min_value = - max_t(u32, reg->s32_min_value, reg->u32_min_value); - reg->s32_max_value = reg->u32_max_value; + if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { + reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); + reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); } } static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { - /* Learn sign from signed bounds. - * If we cannot cross the sign boundary, then signed and unsigned bounds + /* If u64 range forms a valid s64 range (due to matching sign bit), + * try to learn from that. Let's do a bit of ASCII art to see when + * this is happening. Let's take u64 range first: + * + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * + * Valid u64 range is formed when umin and umax are anywhere in the + * range [0, U64_MAX], and umin <= umax. u64 case is simple and + * straightforward. Let's see how s64 range maps onto the same range + * of values, annotated below the line for comparison: + * + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * 0 S64_MAX S64_MIN -1 + * + * So s64 values basically start in the middle and they are logically + * contiguous to the right of it, wrapping around from -1 to 0, and + * then finishing as S64_MAX (0x7fffffffffffffff) right before + * S64_MIN. We can try drawing the continuity of u64 vs s64 values + * more visually as mapped to sign-agnostic range of hex values. + * + * u64 start u64 end + * _______________________________________________________________ + * / \ + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * 0 S64_MAX S64_MIN -1 + * / \ + * >------------------------------ -------------------------------> + * s64 continues... s64 end s64 start s64 "midpoint" + * + * What this means is that, in general, we can't always derive + * something new about u64 from any random s64 range, and vice versa. + * + * But we can do that in two particular cases. One is when entire + * u64/s64 range is *entirely* contained within left half of the above + * diagram or when it is *entirely* contained in the right half. I.e.: + * + * |-------------------------------|--------------------------------| + * ^ ^ ^ ^ + * A B C D + * + * [A, B] and [C, D] are contained entirely in their respective halves + * and form valid contiguous ranges as both u64 and s64 values. [A, B] + * will be non-negative both as u64 and s64 (and in fact it will be + * identical ranges no matter the signedness). [C, D] treated as s64 + * will be a range of negative values, while in u64 it will be + * non-negative range of values larger than 0x8000000000000000. + * + * Now, any other range here can't be represented in both u64 and s64 + * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid + * contiguous u64 ranges, but they are discontinuous in s64. [B, C] + * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX], + * for example. Similarly, valid s64 range [D, A] (going from negative + * to positive values), would be two separate [D, U64_MAX] and [0, A] + * ranges as u64. Currently reg_state can't represent two segments per + * numeric domain, so in such situations we can only derive maximal + * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64). + * + * So we use these facts to derive umin/umax from smin/smax and vice + * versa only if they stay within the same "half". This is equivalent + * to checking sign bit: lower half will have sign bit as zero, upper + * half have sign bit 1. Below in code we simplify this by just + * casting umin/umax as smin/smax and checking if they form valid + * range, and vice versa. Those are equivalent checks. + */ + if ((s64)reg->umin_value <= (s64)reg->umax_value) { + reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value); + reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value); + } + /* If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ - if (reg->smin_value >= 0 || reg->smax_value < 0) { - reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, - reg->umin_value); - reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, - reg->umax_value); - return; + if ((u64)reg->smin_value <= (u64)reg->smax_value) { + reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); + reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); } - /* Learn sign from unsigned bounds. Signed bounds cross the sign - * boundary, so we must be careful. +} + +static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg) +{ + /* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit + * values on both sides of 64-bit range in hope to have tigher range. + * E.g., if r1 is [0x1'00000000, 0x3'80000000], and we learn from + * 32-bit signed > 0 operation that s32 bounds are now [1; 0x7fffffff]. + * With this, we can substitute 1 as low 32-bits of _low_ 64-bit bound + * (0x100000000 -> 0x100000001) and 0x7fffffff as low 32-bits of + * _high_ 64-bit bound (0x380000000 -> 0x37fffffff) and arrive at a + * better overall bounds for r1 as [0x1'000000001; 0x3'7fffffff]. + * We just need to make sure that derived bounds we are intersecting + * with are well-formed ranges in respecitve s64 or u64 domain, just + * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments. */ - if ((s64)reg->umax_value >= 0) { - /* Positive. We can't learn anything from the smin, but smax - * is positive, hence safe. - */ - reg->smin_value = reg->umin_value; - reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, - reg->umax_value); - } else if ((s64)reg->umin_value < 0) { - /* Negative. We can't learn anything from the smax, but smin - * is negative, hence safe. - */ - reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, - reg->umin_value); - reg->smax_value = reg->umax_value; + __u64 new_umin, new_umax; + __s64 new_smin, new_smax; + + /* u32 -> u64 tightening, it's always well-formed */ + new_umin = (reg->umin_value & ~0xffffffffULL) | reg->u32_min_value; + new_umax = (reg->umax_value & ~0xffffffffULL) | reg->u32_max_value; + reg->umin_value = max_t(u64, reg->umin_value, new_umin); + reg->umax_value = min_t(u64, reg->umax_value, new_umax); + /* u32 -> s64 tightening, u32 range embedded into s64 preserves range validity */ + new_smin = (reg->smin_value & ~0xffffffffULL) | reg->u32_min_value; + new_smax = (reg->smax_value & ~0xffffffffULL) | reg->u32_max_value; + reg->smin_value = max_t(s64, reg->smin_value, new_smin); + reg->smax_value = min_t(s64, reg->smax_value, new_smax); + + /* if s32 can be treated as valid u32 range, we can use it as well */ + if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { + /* s32 -> u64 tightening */ + new_umin = (reg->umin_value & ~0xffffffffULL) | (u32)reg->s32_min_value; + new_umax = (reg->umax_value & ~0xffffffffULL) | (u32)reg->s32_max_value; + reg->umin_value = max_t(u64, reg->umin_value, new_umin); + reg->umax_value = min_t(u64, reg->umax_value, new_umax); + /* s32 -> s64 tightening */ + new_smin = (reg->smin_value & ~0xffffffffULL) | (u32)reg->s32_min_value; + new_smax = (reg->smax_value & ~0xffffffffULL) | (u32)reg->s32_max_value; + reg->smin_value = max_t(s64, reg->smin_value, new_smin); + reg->smax_value = min_t(s64, reg->smax_value, new_smax); } } @@ -2419,6 +2157,7 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg) { __reg32_deduce_bounds(reg); __reg64_deduce_bounds(reg); + __reg_deduce_mixed_bounds(reg); } /* Attempts to improve var_off based on unsigned min/max information */ @@ -2440,6 +2179,7 @@ static void reg_bounds_sync(struct bpf_reg_state *reg) __update_reg_bounds(reg); /* We might have learned something about the sign bit. */ __reg_deduce_bounds(reg); + __reg_deduce_bounds(reg); /* We might have learned some bits from the bounds. */ __reg_bound_offset(reg); /* Intersecting with the old var_off might have improved our bounds @@ -2449,6 +2189,56 @@ static void reg_bounds_sync(struct bpf_reg_state *reg) __update_reg_bounds(reg); } +static int reg_bounds_sanity_check(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, const char *ctx) +{ + const char *msg; + + if (reg->umin_value > reg->umax_value || + reg->smin_value > reg->smax_value || + reg->u32_min_value > reg->u32_max_value || + reg->s32_min_value > reg->s32_max_value) { + msg = "range bounds violation"; + goto out; + } + + if (tnum_is_const(reg->var_off)) { + u64 uval = reg->var_off.value; + s64 sval = (s64)uval; + + if (reg->umin_value != uval || reg->umax_value != uval || + reg->smin_value != sval || reg->smax_value != sval) { + msg = "const tnum out of sync with range bounds"; + goto out; + } + } + + if (tnum_subreg_is_const(reg->var_off)) { + u32 uval32 = tnum_subreg(reg->var_off).value; + s32 sval32 = (s32)uval32; + + if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 || + reg->s32_min_value != sval32 || reg->s32_max_value != sval32) { + msg = "const subreg tnum out of sync with range bounds"; + goto out; + } + } + + return 0; +out: + verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] " + "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n", + ctx, msg, reg->umin_value, reg->umax_value, + reg->smin_value, reg->smax_value, + reg->u32_min_value, reg->u32_max_value, + reg->s32_min_value, reg->s32_max_value, + reg->var_off.value, reg->var_off.mask); + if (env->test_reg_invariants) + return -EFAULT; + __mark_reg_unbounded(reg); + return 0; +} + static bool __reg32_bound_s64(s32 a) { return a >= 0 && a <= S32_MAX; @@ -2473,51 +2263,6 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg) } } -static void __reg_combine_32_into_64(struct bpf_reg_state *reg) -{ - /* special case when 64-bit register has upper 32-bit register - * zeroed. Typically happens after zext or <<32, >>32 sequence - * allowing us to use 32-bit bounds directly, - */ - if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) { - __reg_assign_32_into_64(reg); - } else { - /* Otherwise the best we can do is push lower 32bit known and - * unknown bits into register (var_off set from jmp logic) - * then learn as much as possible from the 64-bit tnum - * known and unknown bits. The previous smin/smax bounds are - * invalid here because of jmp32 compare so mark them unknown - * so they do not impact tnum bounds calculation. - */ - __mark_reg64_unbounded(reg); - } - reg_bounds_sync(reg); -} - -static bool __reg64_bound_s32(s64 a) -{ - return a >= S32_MIN && a <= S32_MAX; -} - -static bool __reg64_bound_u32(u64 a) -{ - return a >= U32_MIN && a <= U32_MAX; -} - -static void __reg_combine_64_into_32(struct bpf_reg_state *reg) -{ - __mark_reg32_unbounded(reg); - if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) { - reg->s32_min_value = (s32)reg->smin_value; - reg->s32_max_value = (s32)reg->smax_value; - } - if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) { - reg->u32_min_value = (u32)reg->umin_value; - reg->u32_max_value = (u32)reg->umax_value; - } - reg_bounds_sync(reg); -} - /* Mark a register as having a completely unknown (scalar) value. */ static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) @@ -2605,6 +2350,11 @@ static void init_reg_state(struct bpf_verifier_env *env, regs[BPF_REG_FP].frameno = state->frameno; } +static struct bpf_retval_range retval_range(s32 minval, s32 maxval) +{ + return (struct bpf_retval_range){ minval, maxval }; +} + #define BPF_MAIN_FUNC (-1) static void init_func_state(struct bpf_verifier_env *env, struct bpf_func_state *state, @@ -2613,7 +2363,7 @@ static void init_func_state(struct bpf_verifier_env *env, state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; - state->callback_ret_range = tnum_range(0, 0); + state->callback_ret_range = retval_range(0, 0); init_reg_state(env, state); mark_verifier_state_scratched(env); } @@ -3157,6 +2907,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) if (env->subprog_info[i].start != ex_cb_insn) continue; env->exception_callback_subprog = i; + mark_subprog_exc_cb(env, i); break; } } @@ -3513,6 +3264,21 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return __check_reg_arg(env, state->regs, regno, t); } +static int insn_stack_access_flags(int frameno, int spi) +{ + return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno; +} + +static int insn_stack_access_spi(int insn_flags) +{ + return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK; +} + +static int insn_stack_access_frameno(int insn_flags) +{ + return insn_flags & INSN_F_FRAMENO_MASK; +} + static void mark_jmp_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].jmp_point = true; @@ -3524,28 +3290,51 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) } /* for any branch, call, exit record the history of jmps in the given state */ -static int push_jmp_history(struct bpf_verifier_env *env, - struct bpf_verifier_state *cur) +static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, + int insn_flags) { u32 cnt = cur->jmp_history_cnt; - struct bpf_idx_pair *p; + struct bpf_jmp_history_entry *p; size_t alloc_size; - if (!is_jmp_point(env, env->insn_idx)) + /* combine instruction flags if we already recorded this instruction */ + if (env->cur_hist_ent) { + /* atomic instructions push insn_flags twice, for READ and + * WRITE sides, but they should agree on stack slot + */ + WARN_ONCE((env->cur_hist_ent->flags & insn_flags) && + (env->cur_hist_ent->flags & insn_flags) != insn_flags, + "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n", + env->insn_idx, env->cur_hist_ent->flags, insn_flags); + env->cur_hist_ent->flags |= insn_flags; return 0; + } cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_USER); if (!p) return -ENOMEM; - p[cnt - 1].idx = env->insn_idx; - p[cnt - 1].prev_idx = env->prev_insn_idx; cur->jmp_history = p; + + p = &cur->jmp_history[cnt - 1]; + p->idx = env->insn_idx; + p->prev_idx = env->prev_insn_idx; + p->flags = insn_flags; cur->jmp_history_cnt = cnt; + env->cur_hist_ent = p; + return 0; } +static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st, + u32 hist_end, int insn_idx) +{ + if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx) + return &st->jmp_history[hist_end - 1]; + return NULL; +} + /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. * Return -ENOENT if we exhausted all instructions within given state. @@ -3672,16 +3461,6 @@ static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u3 bt->stack_masks[frame] &= ~(1ull << slot); } -static inline void bt_set_slot(struct backtrack_state *bt, u32 slot) -{ - bt_set_frame_slot(bt, bt->frame, slot); -} - -static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot) -{ - bt_clear_frame_slot(bt, bt->frame, slot); -} - static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) { return bt->reg_masks[frame]; @@ -3707,9 +3486,9 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) return bt->reg_masks[bt->frame] & (1 << reg); } -static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot) +static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot) { - return bt->stack_masks[bt->frame] & (1ull << slot); + return bt->stack_masks[frame] & (1ull << slot); } /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ @@ -3763,7 +3542,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); * - *was* processed previously during backtracking. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, - struct backtrack_state *bt) + struct bpf_jmp_history_entry *hist, struct backtrack_state *bt) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, @@ -3776,7 +3555,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, u8 mode = BPF_MODE(insn->code); u32 dreg = insn->dst_reg; u32 sreg = insn->src_reg; - u32 spi, i; + u32 spi, i, fr; if (insn->code == 0) return 0; @@ -3837,20 +3616,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ - if (insn->src_reg != BPF_REG_FP) + if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; - /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ - spi = (-insn->off - 1) / BPF_REG_SIZE; - if (spi >= 64) { - verbose(env, "BUG spi %d\n", spi); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; - } - bt_set_slot(bt, spi); + spi = insn_stack_access_spi(hist->flags); + fr = insn_stack_access_frameno(hist->flags); + bt_set_frame_slot(bt, fr, spi); } else if (class == BPF_STX || class == BPF_ST) { if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg @@ -3859,17 +3633,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, */ return -ENOTSUPP; /* scalars can only be spilled into stack */ - if (insn->dst_reg != BPF_REG_FP) + if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; - spi = (-insn->off - 1) / BPF_REG_SIZE; - if (spi >= 64) { - verbose(env, "BUG spi %d\n", spi); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; - } - if (!bt_is_slot_set(bt, spi)) + spi = insn_stack_access_spi(hist->flags); + fr = insn_stack_access_frameno(hist->flags); + if (!bt_is_frame_slot_set(bt, fr, spi)) return 0; - bt_clear_slot(bt, spi); + bt_clear_frame_slot(bt, fr, spi); if (class == BPF_STX) bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { @@ -3913,10 +3683,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - /* we don't track register spills perfectly, - * so fallback to force-precise instead of failing */ - if (bt_stack_mask(bt) != 0) - return -ENOTSUPP; + /* we are now tracking register spills correctly, + * so any instance of leftover slots is a bug + */ + if (bt_stack_mask(bt) != 0) { + verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)"); + return -EFAULT; + } /* propagate r1-r5 to the caller */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (bt_is_reg_set(bt, i)) { @@ -3941,8 +3715,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - if (bt_stack_mask(bt) != 0) - return -ENOTSUPP; + if (bt_stack_mask(bt) != 0) { + verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)"); + return -EFAULT; + } /* clear r1-r5 in callback subprog's mask */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); @@ -4379,6 +4156,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; + struct bpf_jmp_history_entry *hist; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", @@ -4442,7 +4220,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) err = 0; skip_first = false; } else { - err = backtrack_insn(env, i, subseq_idx, bt); + hist = get_jmp_hist_entry(st, history, i); + err = backtrack_insn(env, i, subseq_idx, hist, bt); } if (err == -ENOTSUPP) { mark_all_scalars_precise(env, env->cur_state); @@ -4495,22 +4274,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { - /* the sequence of instructions: - * 2: (bf) r3 = r10 - * 3: (7b) *(u64 *)(r3 -8) = r0 - * 4: (79) r4 = *(u64 *)(r10 -8) - * doesn't contain jmps. It's backtracked - * as a single block. - * During backtracking insn 3 is not recognized as - * stack access, so at the end of backtracking - * stack slot fp-8 is still marked in stack_mask. - * However the parent state may not have accessed - * fp-8 and it's "unallocated" stack space. - * In such case fallback to conservative. - */ - mark_all_scalars_precise(env, env->cur_state); - bt_reset(bt); - return 0; + verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n", + i, func->allocated_stack / BPF_REG_SIZE); + WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)"); + return -EFAULT; } if (!is_spilled_scalar_reg(&func->stack[i])) { @@ -4600,9 +4367,17 @@ static bool register_is_null(struct bpf_reg_state *reg) return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); } -static bool register_is_const(struct bpf_reg_state *reg) +/* check if register is a constant scalar value */ +static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32) +{ + return reg->type == SCALAR_VALUE && + tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off); +} + +/* assuming is_reg_const() is true, return constant value of a register */ +static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32) { - return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off); + return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value; } static bool __is_scalar_unbounded(struct bpf_reg_state *reg) @@ -4639,7 +4414,8 @@ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_ dst->live = live; } -static void save_register_state(struct bpf_func_state *state, +static void save_register_state(struct bpf_verifier_env *env, + struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { @@ -4654,7 +4430,7 @@ static void save_register_state(struct bpf_func_state *state, /* size < 8 bytes spill */ for (; i; i--) - scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); + mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]); } static bool is_bpf_st_mem(struct bpf_insn *insn) @@ -4675,7 +4451,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; - u32 dst_reg = insn->dst_reg; + int insn_flags = insn_stack_access_flags(state->frameno, spi); /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits @@ -4711,20 +4487,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; mark_stack_slot_scratched(env, spi); - if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && - !register_is_null(reg) && env->bpf_capable) { - if (dst_reg != BPF_REG_FP) { - /* The backtracking logic can only recognize explicit - * stack slot address like [fp - 8]. Other spill of - * scalar via different register has to be conservative. - * Backtrack from here and mark all registers as precise - * that contributed into 'reg' being a constant. - */ - err = mark_chain_precision(env, value_regno); - if (err) - return err; - } - save_register_state(state, spi, reg, size); + if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && env->bpf_capable) { + save_register_state(env, state, spi, reg, size); /* Break the relation on a narrowing spill. */ if (fls64(reg->umax_value) > BITS_PER_BYTE * size) state->stack[spi].spilled_ptr.id = 0; @@ -4734,7 +4498,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, __mark_reg_known(&fake_reg, insn->imm); fake_reg.type = SCALAR_VALUE; - save_register_state(state, spi, &fake_reg, size); + save_register_state(env, state, spi, &fake_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -4746,7 +4510,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - save_register_state(state, spi, reg, size); + save_register_state(env, state, spi, reg, size); } else { u8 type = STACK_MISC; @@ -4771,7 +4535,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* when we zero initialize stack slots mark them as such */ if ((reg && register_is_null(reg)) || (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { - /* backtracking doesn't work for STACK_ZERO yet. */ + /* STACK_ZERO case happened because register spill + * wasn't properly aligned at the stack slot boundary, + * so it's not a register spill anymore; force + * originating register to be precise to make + * STACK_ZERO correct for subsequent states + */ err = mark_chain_precision(env, value_regno); if (err) return err; @@ -4780,9 +4549,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) - state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = - type; + state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; + insn_flags = 0; /* not a register spill */ } + + if (insn_flags) + return push_jmp_history(env, env->cur_state, insn_flags); return 0; } @@ -4930,21 +4702,10 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env, zeros++; } if (zeros == max_off - min_off) { - /* any access_size read into register is zero extended, - * so the whole register == const_zero + /* Any access_size read into register is zero extended, + * so the whole register == const_zero. */ - __mark_reg_const_zero(&state->regs[dst_regno]); - /* backtracking doesn't support STACK_ZERO yet, - * so mark it precise here, so that later - * backtracking can stop here. - * Backtracking may not need this if this register - * doesn't participate in pointer adjustment. - * Forward propagation of precise flag is not - * necessary either. This mark is only to stop - * backtracking. Any register that contributed - * to const 0 was marked precise before spill. - */ - state->regs[dst_regno].precise = true; + __mark_reg_const_zero(env, &state->regs[dst_regno]); } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, dst_regno); @@ -4971,6 +4732,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; u8 *stype, type; + int insn_flags = insn_stack_access_flags(reg_state->frameno, spi); stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; @@ -5003,25 +4765,42 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { + int spill_cnt = 0, zero_cnt = 0; + for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; - if (type == STACK_SPILL) + if (type == STACK_SPILL) { + spill_cnt++; continue; + } if (type == STACK_MISC) continue; + if (type == STACK_ZERO) { + zero_cnt++; + continue; + } if (type == STACK_INVALID && env->allow_uninit_stack) continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } - mark_reg_unknown(env, state->regs, dst_regno); + + if (spill_cnt == size && + tnum_is_const(reg->var_off) && reg->var_off.value == 0) { + __mark_reg_const_zero(env, &state->regs[dst_regno]); + /* this IS register fill, so keep insn_flags */ + } else if (zero_cnt == size) { + /* similarly to mark_reg_stack_read(), preserve zeroes */ + __mark_reg_const_zero(env, &state->regs[dst_regno]); + insn_flags = 0; /* not restoring original register state */ + } else { + mark_reg_unknown(env, state->regs, dst_regno); + insn_flags = 0; /* not restoring original register state */ + } } state->regs[dst_regno].live |= REG_LIVE_WRITTEN; - return 0; - } - - if (dst_regno >= 0) { + } else if (dst_regno >= 0) { /* restore register state from stack */ copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely @@ -5057,7 +4836,10 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno >= 0) mark_reg_stack_read(env, reg_state, off, off + size, dst_regno); + insn_flags = 0; /* we are not restoring spilled register */ } + if (insn_flags) + return push_jmp_history(env, env->cur_state, insn_flags); return 0; } @@ -5347,8 +5129,8 @@ static int __check_ptr_off_reg(struct bpf_verifier_env *env, return 0; } -int check_ptr_off_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +static int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) { return __check_ptr_off_reg(env, reg, regno, false); } @@ -5454,10 +5236,23 @@ BTF_SET_END(rcu_protected_types) static bool rcu_protected_object(const struct btf *btf, u32 btf_id) { if (!btf_is_kernel(btf)) - return false; + return true; return btf_id_set_contains(&rcu_protected_types, btf_id); } +static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field) +{ + struct btf_struct_meta *meta; + + if (btf_is_kernel(kptr_field->kptr.btf)) + return NULL; + + meta = btf_find_struct_meta(kptr_field->kptr.btf, + kptr_field->kptr.btf_id); + + return meta ? meta->record : NULL; +} + static bool rcu_safe_kptr(const struct btf_field *field) { const struct btf_field_kptr *kptr = &field->kptr; @@ -5468,12 +5263,25 @@ static bool rcu_safe_kptr(const struct btf_field *field) static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field) { + struct btf_record *rec; + u32 ret; + + ret = PTR_MAYBE_NULL; if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) { - if (kptr_field->type != BPF_KPTR_PERCPU) - return PTR_MAYBE_NULL | MEM_RCU; - return PTR_MAYBE_NULL | MEM_RCU | MEM_PERCPU; + ret |= MEM_RCU; + if (kptr_field->type == BPF_KPTR_PERCPU) + ret |= MEM_PERCPU; + else if (!btf_is_kernel(kptr_field->kptr.btf)) + ret |= MEM_ALLOC; + + rec = kptr_pointee_btf_record(kptr_field); + if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE)) + ret |= NON_OWN_REF; + } else { + ret |= PTR_UNTRUSTED; } - return PTR_MAYBE_NULL | PTR_UNTRUSTED; + + return ret; } static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, @@ -6233,9 +6041,10 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ - if (size >= 4) - return; - __reg_combine_64_into_32(reg); + if (size < 4) { + __mark_reg32_unbounded(reg); + reg_bounds_sync(reg); + } } static void set_sext64_default_val(struct bpf_reg_state *reg, int size) @@ -6809,6 +6618,11 @@ static int check_stack_access_within_bounds( err = check_stack_slot_within_bounds(env, min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ + if (!err && access_size < 0) + /* access_size should not be negative (or overflow an int); others checks + * along the way should have prevented such an access. + */ + err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { @@ -6818,13 +6632,16 @@ static int check_stack_access_within_bounds( char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n", - err_extra, regno, tn_buf, access_size); + verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n", + err_extra, regno, tn_buf, off, access_size); } return err; } - return grow_stack_state(env, state, round_up(-min_off, BPF_REG_SIZE)); + /* Note that there is no stack access with offset zero, so the needed stack + * size is -min_off, not -min_off+1. + */ + return grow_stack_state(env, state, -min_off /* size */); } /* check whether memory at (regno + off) is accessible for t = (read | write) @@ -7169,7 +6986,6 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); if (err) return err; - return 0; } @@ -7432,6 +7248,12 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +/* verify arguments to helpers or kfuncs consisting of a pointer and an access + * size. + * + * @regno is the register containing the access size. regno-1 is the register + * containing the pointer. + */ static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, bool zero_size_allowed, @@ -7466,12 +7288,10 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, return -EACCES; } - if (reg->umin_value == 0) { - err = check_helper_mem_access(env, regno - 1, 0, - zero_size_allowed, - meta); - if (err) - return err; + if (reg->umin_value == 0 && !zero_size_allowed) { + verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n", + regno, reg->umin_value, reg->umax_value); + return -EACCES; } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { @@ -7487,8 +7307,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, return err; } -int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno, u32 mem_size) +static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno, u32 mem_size) { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; @@ -8133,7 +7953,7 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, /* switch to DRAINED state, but keep the depth unchanged */ /* mark current iter state as drained and assume returned NULL */ cur_iter->iter.state = BPF_ITER_STATE_DRAINED; - __mark_reg_const_zero(&cur_fr->regs[BPF_REG_0]); + __mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]); return 0; } @@ -8473,9 +8293,9 @@ reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields) return field; } -int check_func_arg_reg_off(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type) +static int check_func_arg_reg_off(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + enum bpf_arg_type arg_type) { u32 type = reg->type; @@ -8609,6 +8429,54 @@ static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env, return state->stack[spi].spilled_ptr.dynptr.type; } +static int check_reg_const_str(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno) +{ + struct bpf_map *map = reg->map_ptr; + int err; + int map_off; + u64 map_addr; + char *str_ptr; + + if (reg->type != PTR_TO_MAP_VALUE) + return -EINVAL; + + if (!bpf_map_is_rdonly(map)) { + verbose(env, "R%d does not point to a readonly map'\n", regno); + return -EACCES; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d is not a constant address'\n", regno); + return -EACCES; + } + + if (!map->ops->map_direct_value_addr) { + verbose(env, "no direct value access support for this map type\n"); + return -EACCES; + } + + err = check_map_access(env, regno, reg->off, + map->value_size - reg->off, false, + ACCESS_HELPER); + if (err) + return err; + + map_off = reg->off + reg->var_off.value; + err = map->ops->map_direct_value_addr(map, &map_addr, map_off); + if (err) { + verbose(env, "direct value access on string failed\n"); + return err; + } + + str_ptr = (char *)(long)(map_addr); + if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) { + verbose(env, "string is not zero-terminated\n"); + return -EINVAL; + } + return 0; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn, @@ -8853,44 +8721,9 @@ skip_type_check: } case ARG_PTR_TO_CONST_STR: { - struct bpf_map *map = reg->map_ptr; - int map_off; - u64 map_addr; - char *str_ptr; - - if (!bpf_map_is_rdonly(map)) { - verbose(env, "R%d does not point to a readonly map'\n", regno); - return -EACCES; - } - - if (!tnum_is_const(reg->var_off)) { - verbose(env, "R%d is not a constant address'\n", regno); - return -EACCES; - } - - if (!map->ops->map_direct_value_addr) { - verbose(env, "no direct value access support for this map type\n"); - return -EACCES; - } - - err = check_map_access(env, regno, reg->off, - map->value_size - reg->off, false, - ACCESS_HELPER); + err = check_reg_const_str(env, reg, regno); if (err) return err; - - map_off = reg->off + reg->var_off.value; - err = map->ops->map_direct_value_addr(map, &map_addr, map_off); - if (err) { - verbose(env, "direct value access on string failed\n"); - return err; - } - - str_ptr = (char *)(long)(map_addr); - if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) { - verbose(env, "string is not zero-terminated\n"); - return -EINVAL; - } break; } case ARG_PTR_TO_KPTR: @@ -9423,6 +9256,102 @@ err_out: return err; } +static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, + const struct btf *btf, + struct bpf_reg_state *regs) +{ + struct bpf_subprog_info *sub = subprog_info(env, subprog); + struct bpf_verifier_log *log = &env->log; + u32 i; + int ret; + + ret = btf_prepare_func_args(env, subprog); + if (ret) + return ret; + + /* check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < sub->arg_cnt; i++) { + u32 regno = i + 1; + struct bpf_reg_state *reg = ®s[regno]; + struct bpf_subprog_arg_info *arg = &sub->args[i]; + + if (arg->arg_type == ARG_ANYTHING) { + if (reg->type != SCALAR_VALUE) { + bpf_log(log, "R%d is not a scalar\n", regno); + return -EINVAL; + } + } else if (arg->arg_type == ARG_PTR_TO_CTX) { + ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); + if (ret < 0) + return ret; + /* If function expects ctx type in BTF check that caller + * is passing PTR_TO_CTX. + */ + if (reg->type != PTR_TO_CTX) { + bpf_log(log, "arg#%d expects pointer to ctx\n", i); + return -EINVAL; + } + } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { + ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); + if (ret < 0) + return ret; + if (check_mem_reg(env, reg, regno, arg->mem_size)) + return -EINVAL; + if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) { + bpf_log(log, "arg#%d is expected to be non-NULL\n", i); + return -EINVAL; + } + } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { + ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); + if (ret) + return ret; + } else { + bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n", + i, arg->arg_type); + return -EFAULT; + } + } + + return 0; +} + +/* Compare BTF of a function call with given bpf_reg_state. + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - there is a type mismatch or BTF is not available. + * 0 - BTF matches with what bpf_reg_state expects. + * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. + */ +static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *regs) +{ + struct bpf_prog *prog = env->prog; + struct btf *btf = prog->aux->btf; + u32 btf_id; + int err; + + if (!prog->aux->func_info) + return -EINVAL; + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) + return -EFAULT; + + if (prog->aux->func_info_aux[subprog].unreliable) + return -EINVAL; + + err = btf_check_func_arg_match(env, subprog, btf, regs); + /* Compiler optimizations can remove arguments from static functions + * or mismatched type can be passed into a global function. + * In such cases mark the function as unreliable from BTF point of view. + */ + if (err) + prog->aux->func_info_aux[subprog].unreliable = true; + return err; +} + static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, int subprog, set_callee_state_fn set_callee_state_cb) @@ -9512,13 +9441,18 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (err == -EFAULT) return err; if (subprog_is_global(env, subprog)) { + const char *sub_name = subprog_name(env, subprog); + if (err) { - verbose(env, "Caller passes invalid args into func#%d\n", subprog); + verbose(env, "Caller passes invalid args into func#%d ('%s')\n", + subprog, sub_name); return err; } - if (env->log.level & BPF_LOG_LEVEL) - verbose(env, "Func#%d is global and valid. Skipping.\n", subprog); + verbose(env, "Func#%d ('%s') is global and assumed valid.\n", + subprog, sub_name); + /* mark global subprog for verifying after main prog */ + subprog_aux(env, subprog)->called = true; clear_caller_saved_regs(env, caller->regs); /* All global functions return a 64-bit SCALAR_VALUE */ @@ -9618,7 +9552,7 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return err; callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9640,7 +9574,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9670,7 +9604,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_async_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9689,7 +9623,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].btf = btf_vmlinux; - callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA], + callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; /* pointer to stack or null */ callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; @@ -9698,7 +9632,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9721,7 +9655,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9753,7 +9687,7 @@ static int set_rbtree_add_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9782,6 +9716,11 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) return is_rbtree_lock_required_kfunc(kfunc_btf_id); } +static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg) +{ + return range.minval <= reg->smin_value && reg->smax_value <= range.maxval; +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state, *prev_st; @@ -9805,9 +9744,6 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) caller = state->frame[state->curframe - 1]; if (callee->in_callback_fn) { - /* enforce R0 return value range [0, 1]. */ - struct tnum range = callee->callback_ret_range; - if (r0->type != SCALAR_VALUE) { verbose(env, "R0 not a scalar value\n"); return -EACCES; @@ -9819,8 +9755,10 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) if (err) return err; - if (!tnum_in(range, r0->var_off)) { - verbose_invalid_scalar(env, r0, &range, "callback return", "R0"); + /* enforce R0 return value range */ + if (!retval_range_within(callee->callback_ret_range, r0)) { + verbose_invalid_scalar(env, r0, callee->callback_ret_range, + "At callback return", "R0"); return -EINVAL; } if (!calls_callback(env, callee->callsite)) { @@ -9886,14 +9824,15 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return 0; } -static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, - int func_id, - struct bpf_call_arg_meta *meta) +static int do_refine_retval_range(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, int ret_type, + int func_id, + struct bpf_call_arg_meta *meta) { struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; if (ret_type != RET_INTEGER) - return; + return 0; switch (func_id) { case BPF_FUNC_get_stack: @@ -9919,6 +9858,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, reg_bounds_sync(ret_reg); break; } + + return reg_bounds_sanity_check(env, ret_reg, "retval"); } static int @@ -9988,7 +9929,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, val = reg->var_off.value; max = map->max_entries; - if (!(register_is_const(reg) && val < max)) { + if (!(is_reg_const(reg, false) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } @@ -10583,7 +10524,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].ref_obj_id = id; } - do_refine_retval_range(regs, fn->ret_type, func_id, &meta); + err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta); + if (err) + return err; err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) @@ -10761,6 +10704,11 @@ static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param return __kfunc_param_match_suffix(btf, arg, "__nullable"); } +static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__str"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -10904,6 +10852,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_RB_ROOT, KF_ARG_PTR_TO_RB_NODE, KF_ARG_PTR_TO_NULL, + KF_ARG_PTR_TO_CONST_STR, }; enum special_kfunc_type { @@ -11054,6 +11003,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno])) return KF_ARG_PTR_TO_RB_NODE; + if (is_kfunc_arg_const_str(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_CONST_STR; + if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { if (!btf_type_is_struct(ref_t)) { verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", @@ -11685,6 +11637,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_MEM_SIZE: case KF_ARG_PTR_TO_CALLBACK: case KF_ARG_PTR_TO_REFCOUNTED_KPTR: + case KF_ARG_PTR_TO_CONST_STR: /* Trusted by default */ break; default: @@ -11956,6 +11909,15 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ meta->arg_btf = reg->btf; meta->arg_btf_id = reg->btf_id; break; + case KF_ARG_PTR_TO_CONST_STR: + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "arg#%d doesn't point to a const string\n", i); + return -EINVAL; + } + ret = check_reg_const_str(env, reg, regno); + if (ret) + return ret; + break; } } @@ -12010,7 +11972,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env, return 0; } -static int check_return_code(struct bpf_verifier_env *env, int regno); +static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name); static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) @@ -12147,7 +12109,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, * to bpf_throw becomes the return value of the program. */ if (!env->exception_callback_subprog) { - err = check_return_code(env, BPF_REG_1); + err = check_return_code(env, BPF_REG_1, "R1"); if (err < 0) return err; } @@ -12186,20 +12148,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set) return -ENOMEM; - if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { - if (!bpf_global_percpu_ma_set) { - mutex_lock(&bpf_percpu_ma_lock); - if (!bpf_global_percpu_ma_set) { - err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true); - if (!err) - bpf_global_percpu_ma_set = true; - } - mutex_unlock(&bpf_percpu_ma_lock); - if (err) - return err; - } - } - if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); return -EINVAL; @@ -12220,6 +12168,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EINVAL; } + if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { + if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) { + verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n", + ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE); + return -EINVAL; + } + + if (!bpf_global_percpu_ma_set) { + mutex_lock(&bpf_percpu_ma_lock); + if (!bpf_global_percpu_ma_set) { + /* Charge memory allocated with bpf_global_percpu_ma to + * root memcg. The obj_cgroup for root memcg is NULL. + */ + err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL); + if (!err) + bpf_global_percpu_ma_set = true; + } + mutex_unlock(&bpf_percpu_ma_lock); + if (err) + return err; + } + + mutex_lock(&bpf_percpu_ma_lock); + err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size); + mutex_unlock(&bpf_percpu_ma_lock); + if (err) + return err; + } + struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id); if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) { @@ -14080,13 +14057,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); + err = err ?: adjust_reg_min_max_vals(env, insn); if (err) return err; - - return adjust_reg_min_max_vals(env, insn); } - return 0; + return reg_bounds_sanity_check(env, ®s[insn->dst_reg], "alu"); } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, @@ -14168,161 +14144,130 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, })); } -static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) -{ - struct tnum subreg = tnum_subreg(reg->var_off); - s32 sval = (s32)val; - - switch (opcode) { - case BPF_JEQ: - if (tnum_is_const(subreg)) - return !!tnum_equals_const(subreg, val); - else if (val < reg->u32_min_value || val > reg->u32_max_value) - return 0; - else if (sval < reg->s32_min_value || sval > reg->s32_max_value) - return 0; - break; - case BPF_JNE: - if (tnum_is_const(subreg)) - return !tnum_equals_const(subreg, val); - else if (val < reg->u32_min_value || val > reg->u32_max_value) - return 1; - else if (sval < reg->s32_min_value || sval > reg->s32_max_value) - return 1; - break; - case BPF_JSET: - if ((~subreg.mask & subreg.value) & val) - return 1; - if (!((subreg.mask | subreg.value) & val)) - return 0; - break; - case BPF_JGT: - if (reg->u32_min_value > val) - return 1; - else if (reg->u32_max_value <= val) - return 0; - break; - case BPF_JSGT: - if (reg->s32_min_value > sval) - return 1; - else if (reg->s32_max_value <= sval) - return 0; - break; - case BPF_JLT: - if (reg->u32_max_value < val) - return 1; - else if (reg->u32_min_value >= val) - return 0; - break; - case BPF_JSLT: - if (reg->s32_max_value < sval) - return 1; - else if (reg->s32_min_value >= sval) - return 0; - break; - case BPF_JGE: - if (reg->u32_min_value >= val) - return 1; - else if (reg->u32_max_value < val) - return 0; - break; - case BPF_JSGE: - if (reg->s32_min_value >= sval) - return 1; - else if (reg->s32_max_value < sval) - return 0; - break; - case BPF_JLE: - if (reg->u32_max_value <= val) - return 1; - else if (reg->u32_min_value > val) - return 0; - break; - case BPF_JSLE: - if (reg->s32_max_value <= sval) - return 1; - else if (reg->s32_min_value > sval) - return 0; - break; - } - - return -1; -} - - -static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) -{ - s64 sval = (s64)val; +/* + * , currently assuming reg2 is a constant + */ +static int is_scalar_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, + u8 opcode, bool is_jmp32) +{ + struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off; + struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off; + u64 umin1 = is_jmp32 ? (u64)reg1->u32_min_value : reg1->umin_value; + u64 umax1 = is_jmp32 ? (u64)reg1->u32_max_value : reg1->umax_value; + s64 smin1 = is_jmp32 ? (s64)reg1->s32_min_value : reg1->smin_value; + s64 smax1 = is_jmp32 ? (s64)reg1->s32_max_value : reg1->smax_value; + u64 umin2 = is_jmp32 ? (u64)reg2->u32_min_value : reg2->umin_value; + u64 umax2 = is_jmp32 ? (u64)reg2->u32_max_value : reg2->umax_value; + s64 smin2 = is_jmp32 ? (s64)reg2->s32_min_value : reg2->smin_value; + s64 smax2 = is_jmp32 ? (s64)reg2->s32_max_value : reg2->smax_value; switch (opcode) { case BPF_JEQ: - if (tnum_is_const(reg->var_off)) - return !!tnum_equals_const(reg->var_off, val); - else if (val < reg->umin_value || val > reg->umax_value) + /* constants, umin/umax and smin/smax checks would be + * redundant in this case because they all should match + */ + if (tnum_is_const(t1) && tnum_is_const(t2)) + return t1.value == t2.value; + /* non-overlapping ranges */ + if (umin1 > umax2 || umax1 < umin2) return 0; - else if (sval < reg->smin_value || sval > reg->smax_value) + if (smin1 > smax2 || smax1 < smin2) return 0; + if (!is_jmp32) { + /* if 64-bit ranges are inconclusive, see if we can + * utilize 32-bit subrange knowledge to eliminate + * branches that can't be taken a priori + */ + if (reg1->u32_min_value > reg2->u32_max_value || + reg1->u32_max_value < reg2->u32_min_value) + return 0; + if (reg1->s32_min_value > reg2->s32_max_value || + reg1->s32_max_value < reg2->s32_min_value) + return 0; + } break; case BPF_JNE: - if (tnum_is_const(reg->var_off)) - return !tnum_equals_const(reg->var_off, val); - else if (val < reg->umin_value || val > reg->umax_value) + /* constants, umin/umax and smin/smax checks would be + * redundant in this case because they all should match + */ + if (tnum_is_const(t1) && tnum_is_const(t2)) + return t1.value != t2.value; + /* non-overlapping ranges */ + if (umin1 > umax2 || umax1 < umin2) return 1; - else if (sval < reg->smin_value || sval > reg->smax_value) + if (smin1 > smax2 || smax1 < smin2) return 1; + if (!is_jmp32) { + /* if 64-bit ranges are inconclusive, see if we can + * utilize 32-bit subrange knowledge to eliminate + * branches that can't be taken a priori + */ + if (reg1->u32_min_value > reg2->u32_max_value || + reg1->u32_max_value < reg2->u32_min_value) + return 1; + if (reg1->s32_min_value > reg2->s32_max_value || + reg1->s32_max_value < reg2->s32_min_value) + return 1; + } break; case BPF_JSET: - if ((~reg->var_off.mask & reg->var_off.value) & val) + if (!is_reg_const(reg2, is_jmp32)) { + swap(reg1, reg2); + swap(t1, t2); + } + if (!is_reg_const(reg2, is_jmp32)) + return -1; + if ((~t1.mask & t1.value) & t2.value) return 1; - if (!((reg->var_off.mask | reg->var_off.value) & val)) + if (!((t1.mask | t1.value) & t2.value)) return 0; break; case BPF_JGT: - if (reg->umin_value > val) + if (umin1 > umax2) return 1; - else if (reg->umax_value <= val) + else if (umax1 <= umin2) return 0; break; case BPF_JSGT: - if (reg->smin_value > sval) + if (smin1 > smax2) return 1; - else if (reg->smax_value <= sval) + else if (smax1 <= smin2) return 0; break; case BPF_JLT: - if (reg->umax_value < val) + if (umax1 < umin2) return 1; - else if (reg->umin_value >= val) + else if (umin1 >= umax2) return 0; break; case BPF_JSLT: - if (reg->smax_value < sval) + if (smax1 < smin2) return 1; - else if (reg->smin_value >= sval) + else if (smin1 >= smax2) return 0; break; case BPF_JGE: - if (reg->umin_value >= val) + if (umin1 >= umax2) return 1; - else if (reg->umax_value < val) + else if (umax1 < umin2) return 0; break; case BPF_JSGE: - if (reg->smin_value >= sval) + if (smin1 >= smax2) return 1; - else if (reg->smax_value < sval) + else if (smax1 < smin2) return 0; break; case BPF_JLE: - if (reg->umax_value <= val) + if (umax1 <= umin2) return 1; - else if (reg->umin_value > val) + else if (umin1 > umax2) return 0; break; case BPF_JSLE: - if (reg->smax_value <= sval) + if (smax1 <= smin2) return 1; - else if (reg->smin_value > sval) + else if (smin1 > smax2) return 0; break; } @@ -14330,41 +14275,6 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) return -1; } -/* compute branch direction of the expression "if (reg opcode val) goto target;" - * and return: - * 1 - branch will be taken and "goto target" will be executed - * 0 - branch will not be taken and fall-through to next insn - * -1 - unknown. Example: "if (reg < 5)" is unknown when register value - * range [0,10] - */ -static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, - bool is_jmp32) -{ - if (__is_pointer_value(false, reg)) { - if (!reg_not_null(reg)) - return -1; - - /* If pointer is valid tests against zero will fail so we can - * use this to direct branch taken. - */ - if (val != 0) - return -1; - - switch (opcode) { - case BPF_JEQ: - return 0; - case BPF_JNE: - return 1; - default: - return -1; - } - } - - if (is_jmp32) - return is_branch32_taken(reg, val, opcode); - return is_branch64_taken(reg, val, opcode); -} - static int flip_opcode(u32 opcode) { /* How can we transform "a b" into "b a"? */ @@ -14426,216 +14336,280 @@ static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg, return -1; } -/* Adjusts the register min/max values in the case that the dst_reg is the - * variable register that we are working on, and src_reg is a constant or we're - * simply doing a BPF_K check. - * In JEQ/JNE cases we also adjust the var_off values. +/* compute branch direction of the expression "if ( opcode ) goto target;" + * and return: + * 1 - branch will be taken and "goto target" will be executed + * 0 - branch will not be taken and fall-through to next insn + * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value + * range [0,10] */ -static void reg_set_min_max(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, - u64 val, u32 val32, - u8 opcode, bool is_jmp32) -{ - struct tnum false_32off = tnum_subreg(false_reg->var_off); - struct tnum false_64off = false_reg->var_off; - struct tnum true_32off = tnum_subreg(true_reg->var_off); - struct tnum true_64off = true_reg->var_off; - s64 sval = (s64)val; - s32 sval32 = (s32)val32; - - /* If the dst_reg is a pointer, we can't learn anything about its - * variable offset from the compare (unless src_reg were a pointer into - * the same object, but we don't bother with that. - * Since false_reg and true_reg have the same type by construction, we - * only need to check one of them for pointerness. - */ - if (__is_pointer_value(false, false_reg)) - return; +static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, + u8 opcode, bool is_jmp32) +{ + if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32) + return is_pkt_ptr_branch_taken(reg1, reg2, opcode); + + if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) { + u64 val; + + /* arrange that reg2 is a scalar, and reg1 is a pointer */ + if (!is_reg_const(reg2, is_jmp32)) { + opcode = flip_opcode(opcode); + swap(reg1, reg2); + } + /* and ensure that reg2 is a constant */ + if (!is_reg_const(reg2, is_jmp32)) + return -1; + + if (!reg_not_null(reg1)) + return -1; + + /* If pointer is valid tests against zero will fail so we can + * use this to direct branch taken. + */ + val = reg_const_value(reg2, is_jmp32); + if (val != 0) + return -1; + + switch (opcode) { + case BPF_JEQ: + return 0; + case BPF_JNE: + return 1; + default: + return -1; + } + } + + /* now deal with two scalars, but not necessarily constants */ + return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32); +} +/* Opcode that corresponds to a *false* branch condition. + * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2 + */ +static u8 rev_opcode(u8 opcode) +{ switch (opcode) { - /* JEQ/JNE comparison doesn't change the register equivalence. - * - * r1 = r2; - * if (r1 == 42) goto label; - * ... - * label: // here both r1 and r2 are known to be 42. - * - * Hence when marking register as known preserve it's ID. + case BPF_JEQ: return BPF_JNE; + case BPF_JNE: return BPF_JEQ; + /* JSET doesn't have it's reverse opcode in BPF, so add + * BPF_X flag to denote the reverse of that operation */ + case BPF_JSET: return BPF_JSET | BPF_X; + case BPF_JSET | BPF_X: return BPF_JSET; + case BPF_JGE: return BPF_JLT; + case BPF_JGT: return BPF_JLE; + case BPF_JLE: return BPF_JGT; + case BPF_JLT: return BPF_JGE; + case BPF_JSGE: return BPF_JSLT; + case BPF_JSGT: return BPF_JSLE; + case BPF_JSLE: return BPF_JSGT; + case BPF_JSLT: return BPF_JSGE; + default: return 0; + } +} + +/* Refine range knowledge for 2 conditional operation. */ +static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, + u8 opcode, bool is_jmp32) +{ + struct tnum t; + u64 val; + +again: + switch (opcode) { case BPF_JEQ: if (is_jmp32) { - __mark_reg32_known(true_reg, val32); - true_32off = tnum_subreg(true_reg->var_off); + reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); + reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); + reg2->u32_min_value = reg1->u32_min_value; + reg2->u32_max_value = reg1->u32_max_value; + reg2->s32_min_value = reg1->s32_min_value; + reg2->s32_max_value = reg1->s32_max_value; + + t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); + reg2->var_off = tnum_with_subreg(reg2->var_off, t); } else { - ___mark_reg_known(true_reg, val); - true_64off = true_reg->var_off; + reg1->umin_value = max(reg1->umin_value, reg2->umin_value); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value); + reg1->smin_value = max(reg1->smin_value, reg2->smin_value); + reg1->smax_value = min(reg1->smax_value, reg2->smax_value); + reg2->umin_value = reg1->umin_value; + reg2->umax_value = reg1->umax_value; + reg2->smin_value = reg1->smin_value; + reg2->smax_value = reg1->smax_value; + + reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off); + reg2->var_off = reg1->var_off; } break; case BPF_JNE: + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + + /* try to recompute the bound of reg1 if reg2 is a const and + * is exactly the edge of reg1. + */ + val = reg_const_value(reg2, is_jmp32); if (is_jmp32) { - __mark_reg32_known(false_reg, val32); - false_32off = tnum_subreg(false_reg->var_off); + /* u32_min_value is not equal to 0xffffffff at this point, + * because otherwise u32_max_value is 0xffffffff as well, + * in such a case both reg1 and reg2 would be constants, + * jump would be predicted and reg_set_min_max() won't + * be called. + * + * Same reasoning works for all {u,s}{min,max}{32,64} cases + * below. + */ + if (reg1->u32_min_value == (u32)val) + reg1->u32_min_value++; + if (reg1->u32_max_value == (u32)val) + reg1->u32_max_value--; + if (reg1->s32_min_value == (s32)val) + reg1->s32_min_value++; + if (reg1->s32_max_value == (s32)val) + reg1->s32_max_value--; } else { - ___mark_reg_known(false_reg, val); - false_64off = false_reg->var_off; + if (reg1->umin_value == (u64)val) + reg1->umin_value++; + if (reg1->umax_value == (u64)val) + reg1->umax_value--; + if (reg1->smin_value == (s64)val) + reg1->smin_value++; + if (reg1->smax_value == (s64)val) + reg1->smax_value--; } break; case BPF_JSET: + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + val = reg_const_value(reg2, is_jmp32); + /* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X) + * requires single bit to learn something useful. E.g., if we + * know that `r1 & 0x3` is true, then which bits (0, 1, or both) + * are actually set? We can learn something definite only if + * it's a single-bit value to begin with. + * + * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have + * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor + * bit 1 is set, which we can readily use in adjustments. + */ + if (!is_power_of_2(val)) + break; if (is_jmp32) { - false_32off = tnum_and(false_32off, tnum_const(~val32)); - if (is_power_of_2(val32)) - true_32off = tnum_or(true_32off, - tnum_const(val32)); + t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { - false_64off = tnum_and(false_64off, tnum_const(~val)); - if (is_power_of_2(val)) - true_64off = tnum_or(true_64off, - tnum_const(val)); + reg1->var_off = tnum_or(reg1->var_off, tnum_const(val)); } break; - case BPF_JGE: - case BPF_JGT: - { + case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */ + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + val = reg_const_value(reg2, is_jmp32); if (is_jmp32) { - u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1; - u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32; - - false_reg->u32_max_value = min(false_reg->u32_max_value, - false_umax); - true_reg->u32_min_value = max(true_reg->u32_min_value, - true_umin); + t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { - u64 false_umax = opcode == BPF_JGT ? val : val - 1; - u64 true_umin = opcode == BPF_JGT ? val + 1 : val; - - false_reg->umax_value = min(false_reg->umax_value, false_umax); - true_reg->umin_value = max(true_reg->umin_value, true_umin); + reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val)); } break; - } - case BPF_JSGE: - case BPF_JSGT: - { + case BPF_JLE: if (is_jmp32) { - s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1; - s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32; - - false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax); - true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); + reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); } else { - s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; - s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; - - false_reg->smax_value = min(false_reg->smax_value, false_smax); - true_reg->smin_value = max(true_reg->smin_value, true_smin); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value); + reg2->umin_value = max(reg1->umin_value, reg2->umin_value); } break; - } - case BPF_JLE: case BPF_JLT: - { if (is_jmp32) { - u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1; - u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32; - - false_reg->u32_min_value = max(false_reg->u32_min_value, - false_umin); - true_reg->u32_max_value = min(true_reg->u32_max_value, - true_umax); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1); + reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value); } else { - u64 false_umin = opcode == BPF_JLT ? val : val + 1; - u64 true_umax = opcode == BPF_JLT ? val - 1 : val; - - false_reg->umin_value = max(false_reg->umin_value, false_umin); - true_reg->umax_value = min(true_reg->umax_value, true_umax); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1); + reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value); } break; - } case BPF_JSLE: + if (is_jmp32) { + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); + reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); + } else { + reg1->smax_value = min(reg1->smax_value, reg2->smax_value); + reg2->smin_value = max(reg1->smin_value, reg2->smin_value); + } + break; case BPF_JSLT: - { if (is_jmp32) { - s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1; - s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32; - - false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin); - true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax); + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1); + reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value); } else { - s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; - s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; - - false_reg->smin_value = max(false_reg->smin_value, false_smin); - true_reg->smax_value = min(true_reg->smax_value, true_smax); + reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1); + reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value); } break; - } + case BPF_JGE: + case BPF_JGT: + case BPF_JSGE: + case BPF_JSGT: + /* just reuse LE/LT logic above */ + opcode = flip_opcode(opcode); + swap(reg1, reg2); + goto again; default: return; } - - if (is_jmp32) { - false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off), - tnum_subreg(false_32off)); - true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off), - tnum_subreg(true_32off)); - __reg_combine_32_into_64(false_reg); - __reg_combine_32_into_64(true_reg); - } else { - false_reg->var_off = false_64off; - true_reg->var_off = true_64off; - __reg_combine_64_into_32(false_reg); - __reg_combine_64_into_32(true_reg); - } } -/* Same as above, but for the case that dst_reg holds a constant and src_reg is - * the variable reg. +/* Adjusts the register min/max values in the case that the dst_reg and + * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K + * check, in which case we havea fake SCALAR_VALUE representing insn->imm). + * Technically we can do similar adjustments for pointers to the same object, + * but we don't support that right now. */ -static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, - u64 val, u32 val32, - u8 opcode, bool is_jmp32) +static int reg_set_min_max(struct bpf_verifier_env *env, + struct bpf_reg_state *true_reg1, + struct bpf_reg_state *true_reg2, + struct bpf_reg_state *false_reg1, + struct bpf_reg_state *false_reg2, + u8 opcode, bool is_jmp32) { - opcode = flip_opcode(opcode); - /* This uses zero as "not present in table"; luckily the zero opcode, - * BPF_JA, can't get here. + int err; + + /* If either register is a pointer, we can't learn anything about its + * variable offset from the compare (unless they were a pointer into + * the same object, but we don't bother with that). */ - if (opcode) - reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32); -} - -/* Regs are known to be equal, so intersect their min/max/var_off */ -static void __reg_combine_min_max(struct bpf_reg_state *src_reg, - struct bpf_reg_state *dst_reg) -{ - src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value, - dst_reg->umin_value); - src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value, - dst_reg->umax_value); - src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value, - dst_reg->smin_value); - src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value, - dst_reg->smax_value); - src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off, - dst_reg->var_off); - reg_bounds_sync(src_reg); - reg_bounds_sync(dst_reg); -} + if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE) + return 0; -static void reg_combine_min_max(struct bpf_reg_state *true_src, - struct bpf_reg_state *true_dst, - struct bpf_reg_state *false_src, - struct bpf_reg_state *false_dst, - u8 opcode) -{ - switch (opcode) { - case BPF_JEQ: - __reg_combine_min_max(true_src, true_dst); - break; - case BPF_JNE: - __reg_combine_min_max(false_src, false_dst); - break; - } + /* fallthrough (FALSE) branch */ + regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32); + reg_bounds_sync(false_reg1); + reg_bounds_sync(false_reg2); + + /* jump (TRUE) branch */ + regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32); + reg_bounds_sync(true_reg1); + reg_bounds_sync(true_reg2); + + err = reg_bounds_sanity_check(env, true_reg1, "true_reg1"); + err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2"); + err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1"); + err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2"); + return err; } static void mark_ptr_or_null_reg(struct bpf_func_state *state, @@ -14833,6 +14807,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; + struct bpf_reg_state fake_reg = {}; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; @@ -14873,42 +14848,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } + src_reg = &fake_reg; + src_reg->type = SCALAR_VALUE; + __mark_reg_known(src_reg, insn->imm); } is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - - if (BPF_SRC(insn->code) == BPF_K) { - pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32); - } else if (src_reg->type == SCALAR_VALUE && - is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) { - pred = is_branch_taken(dst_reg, - tnum_subreg(src_reg->var_off).value, - opcode, - is_jmp32); - } else if (src_reg->type == SCALAR_VALUE && - !is_jmp32 && tnum_is_const(src_reg->var_off)) { - pred = is_branch_taken(dst_reg, - src_reg->var_off.value, - opcode, - is_jmp32); - } else if (dst_reg->type == SCALAR_VALUE && - is_jmp32 && tnum_is_const(tnum_subreg(dst_reg->var_off))) { - pred = is_branch_taken(src_reg, - tnum_subreg(dst_reg->var_off).value, - flip_opcode(opcode), - is_jmp32); - } else if (dst_reg->type == SCALAR_VALUE && - !is_jmp32 && tnum_is_const(dst_reg->var_off)) { - pred = is_branch_taken(src_reg, - dst_reg->var_off.value, - flip_opcode(opcode), - is_jmp32); - } else if (reg_is_pkt_pointer_any(dst_reg) && - reg_is_pkt_pointer_any(src_reg) && - !is_jmp32) { - pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode); - } - + pred = is_branch_taken(dst_reg, src_reg, opcode, is_jmp32); if (pred >= 0) { /* If we get here with a dst_reg pointer type it is because * above is_branch_taken() special cased the 0 comparison. @@ -14956,53 +14902,27 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EFAULT; other_branch_regs = other_branch->frame[other_branch->curframe]->regs; - /* detect if we are comparing against a constant value so we can adjust - * our min/max values for our dst register. - * this is only legit if both are scalars (or pointers to the same - * object, I suppose, see the PTR_MAYBE_NULL related if block below), - * because otherwise the different base pointers mean the offsets aren't - * comparable. - */ if (BPF_SRC(insn->code) == BPF_X) { - struct bpf_reg_state *src_reg = ®s[insn->src_reg]; - - if (dst_reg->type == SCALAR_VALUE && - src_reg->type == SCALAR_VALUE) { - if (tnum_is_const(src_reg->var_off) || - (is_jmp32 && - tnum_is_const(tnum_subreg(src_reg->var_off)))) - reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, - src_reg->var_off.value, - tnum_subreg(src_reg->var_off).value, - opcode, is_jmp32); - else if (tnum_is_const(dst_reg->var_off) || - (is_jmp32 && - tnum_is_const(tnum_subreg(dst_reg->var_off)))) - reg_set_min_max_inv(&other_branch_regs[insn->src_reg], - src_reg, - dst_reg->var_off.value, - tnum_subreg(dst_reg->var_off).value, - opcode, is_jmp32); - else if (!is_jmp32 && - (opcode == BPF_JEQ || opcode == BPF_JNE)) - /* Comparing for equality, we can combine knowledge */ - reg_combine_min_max(&other_branch_regs[insn->src_reg], - &other_branch_regs[insn->dst_reg], - src_reg, dst_reg, opcode); - if (src_reg->id && - !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { - find_equal_scalars(this_branch, src_reg); - find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]); - } - - } - } else if (dst_reg->type == SCALAR_VALUE) { - reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, insn->imm, (u32)insn->imm, - opcode, is_jmp32); + err = reg_set_min_max(env, + &other_branch_regs[insn->dst_reg], + &other_branch_regs[insn->src_reg], + dst_reg, src_reg, opcode, is_jmp32); + } else /* BPF_SRC(insn->code) == BPF_K */ { + err = reg_set_min_max(env, + &other_branch_regs[insn->dst_reg], + src_reg /* fake one */, + dst_reg, src_reg /* same fake one */, + opcode, is_jmp32); } + if (err) + return err; + if (BPF_SRC(insn->code) == BPF_X && + src_reg->type == SCALAR_VALUE && src_reg->id && + !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { + find_equal_scalars(this_branch, src_reg); + find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]); + } if (dst_reg->type == SCALAR_VALUE && dst_reg->id && !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) { find_equal_scalars(this_branch, dst_reg); @@ -15274,12 +15194,13 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } -static int check_return_code(struct bpf_verifier_env *env, int regno) +static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name) { + const char *exit_ctx = "At program exit"; struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; - struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0); + struct bpf_retval_range range = retval_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; struct bpf_func_state *frame = env->cur_state->frame[0]; @@ -15321,17 +15242,9 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) if (frame->in_async_callback_fn) { /* enforce return zero from async callbacks like timer */ - if (reg->type != SCALAR_VALUE) { - verbose(env, "In async callback the register R%d is not a known value (%s)\n", - regno, reg_type_str(env, reg->type)); - return -EINVAL; - } - - if (!tnum_in(const_0, reg->var_off)) { - verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0"); - return -EINVAL; - } - return 0; + exit_ctx = "At async callback return"; + range = retval_range(0, 0); + goto enforce_retval; } if (is_subprog && !frame->in_exception_callback_fn) { @@ -15354,14 +15267,14 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME) - range = tnum_range(1, 1); + range = retval_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) - range = tnum_range(0, 3); + range = retval_range(0, 3); break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { - range = tnum_range(0, 3); + range = retval_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } break; @@ -15374,13 +15287,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) case BPF_PROG_TYPE_RAW_TRACEPOINT: if (!env->prog->aux->attach_btf_id) return 0; - range = tnum_const(0); + range = retval_range(0, 0); break; case BPF_PROG_TYPE_TRACING: switch (env->prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: - range = tnum_const(0); + range = retval_range(0, 0); break; case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: @@ -15392,7 +15305,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) } break; case BPF_PROG_TYPE_SK_LOOKUP: - range = tnum_range(SK_DROP, SK_PASS); + range = retval_range(SK_DROP, SK_PASS); break; case BPF_PROG_TYPE_LSM: @@ -15406,12 +15319,12 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) /* Make sure programs that attach to void * hooks don't try to modify return value. */ - range = tnum_range(1, 1); + range = retval_range(1, 1); } break; case BPF_PROG_TYPE_NETFILTER: - range = tnum_range(NF_DROP, NF_ACCEPT); + range = retval_range(NF_DROP, NF_ACCEPT); break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value @@ -15421,15 +15334,21 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) return 0; } +enforce_retval: if (reg->type != SCALAR_VALUE) { - verbose(env, "At program exit the register R%d is not a known value (%s)\n", - regno, reg_type_str(env, reg->type)); + verbose(env, "%s the register R%d is not a known value (%s)\n", + exit_ctx, regno, reg_type_str(env, reg->type)); return -EINVAL; } - if (!tnum_in(range, reg->var_off)) { - verbose_invalid_scalar(env, reg, &range, "program exit", "R0"); - if (prog->expected_attach_type == BPF_LSM_CGROUP && + err = mark_chain_precision(env, regno); + if (err) + return err; + + if (!retval_range_within(range, reg)) { + verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name); + if (!is_subprog && + prog->expected_attach_type == BPF_LSM_CGROUP && prog_type == BPF_PROG_TYPE_LSM && !prog->aux->attach_func_proto->type) verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); @@ -17197,7 +17116,8 @@ hit: * the precision needs to be propagated back in * the current state. */ - err = err ? : push_jmp_history(env, cur); + if (is_jmp_point(env, env->insn_idx)) + err = err ? : push_jmp_history(env, cur, 0); err = err ? : propagate_precision(env, &sl->state); if (err) return err; @@ -17422,6 +17342,9 @@ static int do_check(struct bpf_verifier_env *env) u8 class; int err; + /* reset current history entry on each new instruction */ + env->cur_hist_ent = NULL; + env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", @@ -17461,7 +17384,7 @@ static int do_check(struct bpf_verifier_env *env) } if (is_jmp_point(env, env->insn_idx)) { - err = push_jmp_history(env, state); + err = push_jmp_history(env, state, 0); if (err) return err; } @@ -17538,10 +17461,8 @@ static int do_check(struct bpf_verifier_env *env) insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, false, BPF_MODE(insn->code) == BPF_MEMSX); - if (err) - return err; - - err = save_aux_ptr_type(env, src_reg_type, true); + err = err ?: save_aux_ptr_type(env, src_reg_type, true); + err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], "ldx"); if (err) return err; } else if (class == BPF_STX) { @@ -17717,7 +17638,7 @@ process_bpf_exit_full: continue; } - err = check_return_code(env, BPF_REG_0); + err = check_return_code(env, BPF_REG_0, "R0"); if (err) return err; process_bpf_exit: @@ -18178,10 +18099,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) return -E2BIG; } + if (env->prog->aux->sleepable) + atomic64_inc(&map->sleepable_refcnt); /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded - * and all maps are released in free_used_maps() + * and all maps are released in bpf_free_used_maps() */ bpf_map_inc(map); @@ -19398,9 +19321,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) env->exception_callback_subprog = env->subprog_cnt - 1; /* Don't update insn_cnt, as add_hidden_subprog always appends insns */ - env->subprog_info[env->exception_callback_subprog].is_cb = true; - env->subprog_info[env->exception_callback_subprog].is_async_cb = true; - env->subprog_info[env->exception_callback_subprog].is_exception_cb = true; + mark_subprog_exc_cb(env, env->exception_callback_subprog); } for (i = 0; i < insn_cnt; i++, insn++) { @@ -20100,9 +20021,10 @@ static void free_states(struct bpf_verifier_env *env) } } -static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb) +static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); + struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; @@ -20129,46 +20051,71 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex state->first_insn_idx = env->subprog_info[subprog].start; state->last_insn_idx = -1; + regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { - ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb); + const char *sub_name = subprog_name(env, subprog); + struct bpf_subprog_arg_info *arg; + struct bpf_reg_state *reg; + + verbose(env, "Validating %s() func#%d...\n", sub_name, subprog); + ret = btf_prepare_func_args(env, subprog); if (ret) goto out; - for (i = BPF_REG_1; i <= BPF_REG_5; i++) { - if (regs[i].type == PTR_TO_CTX) + + if (subprog_is_exc_cb(env, subprog)) { + state->frame[0]->in_exception_callback_fn = true; + /* We have already ensured that the callback returns an integer, just + * like all global subprogs. We need to determine it only has a single + * scalar argument. + */ + if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) { + verbose(env, "exception cb only supports single integer argument\n"); + ret = -EINVAL; + goto out; + } + } + for (i = BPF_REG_1; i <= sub->arg_cnt; i++) { + arg = &sub->args[i - BPF_REG_1]; + reg = ®s[i]; + + if (arg->arg_type == ARG_PTR_TO_CTX) { + reg->type = PTR_TO_CTX; mark_reg_known_zero(env, regs, i); - else if (regs[i].type == SCALAR_VALUE) + } else if (arg->arg_type == ARG_ANYTHING) { + reg->type = SCALAR_VALUE; mark_reg_unknown(env, regs, i); - else if (base_type(regs[i].type) == PTR_TO_MEM) { - const u32 mem_size = regs[i].mem_size; - + } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { + /* assume unspecial LOCAL dynptr type */ + __mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen); + } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { + reg->type = PTR_TO_MEM; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->type |= PTR_MAYBE_NULL; mark_reg_known_zero(env, regs, i); - regs[i].mem_size = mem_size; - regs[i].id = ++env->id_gen; + reg->mem_size = arg->mem_size; + reg->id = ++env->id_gen; + } else { + WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", + i - BPF_REG_1, arg->arg_type); + ret = -EFAULT; + goto out; } } - if (is_ex_cb) { - state->frame[0]->in_exception_callback_fn = true; - env->subprog_info[subprog].is_cb = true; - env->subprog_info[subprog].is_async_cb = true; - env->subprog_info[subprog].is_exception_cb = true; - } } else { + /* if main BPF program has associated BTF info, validate that + * it's matching expected signature, and otherwise mark BTF + * info for main program as unreliable + */ + if (env->prog->aux->func_info_aux) { + ret = btf_prepare_func_args(env, 0); + if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX) + env->prog->aux->func_info_aux[0].unreliable = true; + } + /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); - ret = btf_check_subprog_arg_match(env, subprog, regs); - if (ret == -EFAULT) - /* unlikely verifier bug. abort. - * ret == 0 and ret < 0 are sadly acceptable for - * main() function due to backward compatibility. - * Like socket filter program may be written as: - * int bpf_prog(struct pt_regs *ctx) - * and never dereference that ctx in the program. - * 'struct pt_regs' is a type mismatch for socket - * filter that should be using 'struct __sk_buff'. - */ - goto out; } ret = do_check(env); @@ -20187,8 +20134,11 @@ out: return ret; } -/* Verify all global functions in a BPF program one by one based on their BTF. - * All global functions must pass verification. Otherwise the whole program is rejected. +/* Lazily verify all global functions based on their BTF, if they are called + * from main BPF program or any of subprograms transitively. + * BPF global subprogs called from dead code are not validated. + * All callable global functions must pass verification. + * Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) @@ -20207,25 +20157,50 @@ out: static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; - int i, ret; + struct bpf_func_info_aux *sub_aux; + int 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; + +again: + new_cnt = 0; for (i = 1; i < env->subprog_cnt; i++) { - if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) + if (!subprog_is_global(env, i)) + continue; + + sub_aux = subprog_aux(env, i); + if (!sub_aux->called || sub_aux->verified) continue; + env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); - ret = do_check_common(env, i, env->exception_callback_subprog == i); + ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { - verbose(env, - "Func#%d is safe for any args that match its prototype\n", - i); + verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n", + i, 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++; } + + /* We can't loop forever as we verify at least one global subprog on + * each pass. + */ + if (new_cnt) + goto again; + return 0; } @@ -20234,7 +20209,7 @@ static int do_check_main(struct bpf_verifier_env *env) int ret; env->insn_idx = 0; - ret = do_check_common(env, 0, false); + ret = do_check_common(env, 0); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; @@ -20356,6 +20331,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, struct bpf_attach_target_info *tgt_info) { bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; + bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING; const char prefix[] = "btf_trace_"; int ret = 0, subprog = -1, i; const struct btf_type *t; @@ -20426,10 +20402,21 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, bpf_log(log, "Can attach to only JITed progs\n"); return -EINVAL; } - if (tgt_prog->type == prog->type) { - /* Cannot fentry/fexit another fentry/fexit program. - * Cannot attach program extension to another extension. - * It's ok to attach fentry/fexit to extension program. + if (prog_tracing) { + if (aux->attach_tracing_prog) { + /* + * Target program is an fentry/fexit which is already attached + * to another tracing program. More levels of nesting + * attachment are not allowed. + */ + bpf_log(log, "Cannot nest tracing program attach more than once\n"); + return -EINVAL; + } + } else if (tgt_prog->type == prog->type) { + /* + * To avoid potential call chain cycles, prevent attaching of a + * program extension to another extension. It's ok to attach + * fentry/fexit to extension program. */ bpf_log(log, "Cannot recursively attach\n"); return -EINVAL; @@ -20442,16 +20429,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, * except fentry/fexit. The reason is the following. * The fentry/fexit programs are used for performance * analysis, stats and can be attached to any program - * type except themselves. When extension program is - * replacing XDP function it is necessary to allow - * performance analysis of all functions. Both original - * XDP program and its program extension. Hence - * attaching fentry/fexit to BPF_PROG_TYPE_EXT is - * allowed. If extending of fentry/fexit was allowed it - * would be possible to create long call chain - * fentry->extension->fentry->extension beyond - * reasonable stack size. Hence extending fentry is not - * allowed. + * type. When extension program is replacing XDP function + * it is necessary to allow performance analysis of all + * functions. Both original XDP program and its program + * extension. Hence attaching fentry/fexit to + * BPF_PROG_TYPE_EXT is allowed. If extending of + * fentry/fexit was allowed it would be possible to create + * long call chain fentry->extension->fentry->extension + * beyond reasonable stack size. Hence extending fentry + * is not allowed. */ bpf_log(log, "Cannot extend fentry/fexit\n"); return -EINVAL; @@ -20828,6 +20814,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; + env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), @@ -20870,8 +20857,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret < 0) goto skip_full_check; - ret = do_check_subprogs(env); - ret = ret ?: do_check_main(env); + ret = do_check_main(env); + ret = ret ?: do_check_subprogs(env); if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux)) ret = bpf_prog_offload_finalize(env); diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index c56071f15..520b90dd9 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -164,13 +164,13 @@ struct cgroup_mgctx { #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) -extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; /* iterate across the hierarchies */ #define for_each_root(root) \ - list_for_each_entry((root), &cgroup_roots, root_list) + list_for_each_entry_rcu((root), &cgroup_roots, root_list, \ + lockdep_is_held(&cgroup_mutex)) /** * for_each_subsys - iterate all enabled cgroup subsystems diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 76db6c67e..520a11cb1 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -802,7 +802,7 @@ void cgroup1_release_agent(struct work_struct *work) goto out_free; ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); - if (ret < 0 || ret >= PATH_MAX) + if (ret < 0) goto out_free; argv[0] = agentbuf; @@ -1262,6 +1262,40 @@ int cgroup1_get_tree(struct fs_context *fc) return ret; } +/** + * task_get_cgroup1 - Acquires the associated cgroup of a task within a + * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its + * hierarchy ID. + * @tsk: The target task + * @hierarchy_id: The ID of a cgroup1 hierarchy + * + * On success, the cgroup is returned. On failure, ERR_PTR is returned. + * We limit it to cgroup1 only. + */ +struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id) +{ + struct cgroup *cgrp = ERR_PTR(-ENOENT); + struct cgroup_root *root; + unsigned long flags; + + rcu_read_lock(); + for_each_root(root) { + /* cgroup1 only*/ + if (root == &cgrp_dfl_root) + continue; + if (root->hierarchy_id != hierarchy_id) + continue; + spin_lock_irqsave(&css_set_lock, flags); + cgrp = task_cgroup_from_root(tsk, root); + if (!cgrp || !cgroup_tryget(cgrp)) + cgrp = ERR_PTR(-ENOENT); + spin_unlock_irqrestore(&css_set_lock, flags); + break; + } + rcu_read_unlock(); + return cgrp; +} + static int __init cgroup1_wq_init(void) { /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4b9ff41ca..a66c088c8 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1315,7 +1315,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root) void cgroup_free_root(struct cgroup_root *root) { - kfree(root); + kfree_rcu(root, rcu); } static void cgroup_destroy_root(struct cgroup_root *root) @@ -1347,10 +1347,9 @@ static void cgroup_destroy_root(struct cgroup_root *root) spin_unlock_irq(&css_set_lock); - if (!list_empty(&root->root_list)) { - list_del(&root->root_list); - cgroup_root_count--; - } + WARN_ON_ONCE(list_empty(&root->root_list)); + list_del_rcu(&root->root_list); + cgroup_root_count--; if (!have_favordynmods) cgroup_favor_dynmods(root, false); @@ -1390,7 +1389,15 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, } } - BUG_ON(!res_cgroup); + /* + * If cgroup_mutex is not held, the cgrp_cset_link will be freed + * before we remove the cgroup root from the root_list. Consequently, + * when accessing a cgroup root, the cset_link may have already been + * freed, resulting in a NULL res_cgroup. However, by holding the + * cgroup_mutex, we ensure that res_cgroup can't be NULL. + * If we don't hold cgroup_mutex in the caller, we must do the NULL + * check. + */ return res_cgroup; } @@ -1413,6 +1420,11 @@ current_cgns_cgroup_from_root(struct cgroup_root *root) rcu_read_unlock(); + /* + * The namespace_sem is held by current, so the root cgroup can't + * be umounted. Therefore, we can ensure that the res is non-NULL. + */ + WARN_ON_ONCE(!res); return res; } @@ -1449,7 +1461,6 @@ static struct cgroup *current_cgns_cgroup_dfl(void) static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { - lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); return __cset_cgroup_from_root(cset, root); @@ -1457,7 +1468,9 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, /* * Return the cgroup for "task" from the given hierarchy. Must be - * called with cgroup_mutex and css_set_lock held. + * called with css_set_lock held to prevent task's groups from being modified. + * Must be called with either cgroup_mutex or rcu read lock to prevent the + * cgroup root from being destroyed. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) @@ -1893,7 +1906,7 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock); - if (len >= PATH_MAX) + if (len == -E2BIG) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); @@ -2032,7 +2045,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx) struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; - INIT_LIST_HEAD(&root->root_list); + INIT_LIST_HEAD_RCU(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); @@ -2115,7 +2128,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ - list_add(&root->root_list, &cgroup_roots); + list_add_rcu(&root->root_list, &cgroup_roots); cgroup_root_count++; /* @@ -4169,20 +4182,6 @@ static struct kernfs_ops cgroup_kf_ops = { .seq_show = cgroup_seqfile_show, }; -/* set uid and gid of cgroup dirs and files to that of the creator */ -static int cgroup_kn_set_ugid(struct kernfs_node *kn) -{ - struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, - .ia_uid = current_fsuid(), - .ia_gid = current_fsgid(), }; - - if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && - gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) - return 0; - - return kernfs_setattr(kn, &iattr); -} - static void cgroup_file_notify_timer(struct timer_list *timer) { cgroup_file_notify(container_of(timer, struct cgroup_file, @@ -4195,25 +4194,18 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; - int ret; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + current_fsuid(), current_fsgid(), 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); - ret = cgroup_kn_set_ugid(kn); - if (ret) { - kernfs_remove(kn); - return ret; - } - if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; @@ -5616,7 +5608,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, goto out_cancel_ref; /* create the directory */ - kn = kernfs_create_dir(parent->kn, name, mode, cgrp); + kn = kernfs_create_dir_ns(parent->kn, name, mode, + current_fsuid(), current_fsgid(), + cgrp, NULL); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_stat_exit; @@ -5761,10 +5755,6 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) */ kernfs_get(cgrp->kn); - ret = cgroup_kn_set_ugid(cgrp->kn); - if (ret) - goto out_destroy; - ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; @@ -6265,7 +6255,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, if (!buf) goto out; - cgroup_lock(); + rcu_read_lock(); spin_lock_irq(&css_set_lock); for_each_root(root) { @@ -6276,6 +6266,11 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue; + cgrp = task_cgroup_from_root(tsk, root); + /* The root has already been unmounted. */ + if (!cgrp) + continue; + seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) @@ -6286,9 +6281,6 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); - - cgrp = task_cgroup_from_root(tsk, root); - /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, @@ -6301,7 +6293,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); - if (retval >= PATH_MAX) + if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) goto out_unlock; @@ -6320,7 +6312,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); - cgroup_unlock(); + rcu_read_unlock(); kfree(buf); out: return retval; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ffe0e0029..927bef3a5 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -43,6 +44,7 @@ #include #include #include +#include DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); @@ -204,6 +206,11 @@ struct cpuset { */ static cpumask_var_t subpartitions_cpus; +/* + * Exclusive CPUs in isolated partitions + */ +static cpumask_var_t isolated_cpus; + /* List of remote partition root children */ static struct list_head remote_children; @@ -1317,6 +1324,7 @@ static void compute_effective_cpumask(struct cpumask *new_cpus, */ enum partition_cmd { partcmd_enable, /* Enable partition root */ + partcmd_enablei, /* Enable isolated partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's effective_cpus */ partcmd_invalidate, /* Make partition invalid */ @@ -1418,6 +1426,109 @@ static void reset_partition_data(struct cpuset *cs) } } +/* + * partition_xcpus_newstate - Exclusive CPUs state change + * @old_prs: old partition_root_state + * @new_prs: new partition_root_state + * @xcpus: exclusive CPUs with state change + */ +static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus) +{ + WARN_ON_ONCE(old_prs == new_prs); + if (new_prs == PRS_ISOLATED) + cpumask_or(isolated_cpus, isolated_cpus, xcpus); + else + cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); +} + +/* + * partition_xcpus_add - Add new exclusive CPUs to partition + * @new_prs: new partition_root_state + * @parent: parent cpuset + * @xcpus: exclusive CPUs to be added + * Return: true if isolated_cpus modified, false otherwise + * + * Remote partition if parent == NULL + */ +static bool partition_xcpus_add(int new_prs, struct cpuset *parent, + struct cpumask *xcpus) +{ + bool isolcpus_updated; + + WARN_ON_ONCE(new_prs < 0); + lockdep_assert_held(&callback_lock); + if (!parent) + parent = &top_cpuset; + + + if (parent == &top_cpuset) + cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus); + + isolcpus_updated = (new_prs != parent->partition_root_state); + if (isolcpus_updated) + partition_xcpus_newstate(parent->partition_root_state, new_prs, + xcpus); + + cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus); + return isolcpus_updated; +} + +/* + * partition_xcpus_del - Remove exclusive CPUs from partition + * @old_prs: old partition_root_state + * @parent: parent cpuset + * @xcpus: exclusive CPUs to be removed + * Return: true if isolated_cpus modified, false otherwise + * + * Remote partition if parent == NULL + */ +static bool partition_xcpus_del(int old_prs, struct cpuset *parent, + struct cpumask *xcpus) +{ + bool isolcpus_updated; + + WARN_ON_ONCE(old_prs < 0); + lockdep_assert_held(&callback_lock); + if (!parent) + parent = &top_cpuset; + + if (parent == &top_cpuset) + cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus); + + isolcpus_updated = (old_prs != parent->partition_root_state); + if (isolcpus_updated) + partition_xcpus_newstate(old_prs, parent->partition_root_state, + xcpus); + + cpumask_and(xcpus, xcpus, cpu_active_mask); + cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); + return isolcpus_updated; +} + +static void update_unbound_workqueue_cpumask(bool isolcpus_updated) +{ + int ret; + + lockdep_assert_cpus_held(); + + if (!isolcpus_updated) + return; + + ret = workqueue_unbound_exclude_cpumask(isolated_cpus); + WARN_ON_ONCE(ret < 0); +} + +/** + * cpuset_cpu_is_isolated - Check if the given CPU is isolated + * @cpu: the CPU number to be checked + * Return: true if CPU is used in an isolated partition, false otherwise + */ +bool cpuset_cpu_is_isolated(int cpu) +{ + return cpumask_test_cpu(cpu, isolated_cpus); +} +EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated); + /* * compute_effective_exclusive_cpumask - compute effective exclusive CPUs * @cs: cpuset @@ -1456,14 +1567,18 @@ static inline bool is_local_partition(struct cpuset *cs) /* * remote_partition_enable - Enable current cpuset as a remote partition root * @cs: the cpuset to update + * @new_prs: new partition_root_state * @tmp: temparary masks * Return: 1 if successful, 0 if error * * Enable the current cpuset to become a remote partition root taking CPUs * directly from the top cpuset. cpuset_mutex must be held by the caller. */ -static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp) +static int remote_partition_enable(struct cpuset *cs, int new_prs, + struct tmpmasks *tmp) { + bool isolcpus_updated; + /* * The user must have sysadmin privilege. */ @@ -1485,26 +1600,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp) return 0; spin_lock_irq(&callback_lock); - cpumask_andnot(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->new_cpus); - cpumask_or(subpartitions_cpus, - subpartitions_cpus, tmp->new_cpus); - + isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus); + list_add(&cs->remote_sibling, &remote_children); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } - list_add(&cs->remote_sibling, &remote_children); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. */ update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); - return 1; } @@ -1519,23 +1630,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp) */ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) { + bool isolcpus_updated; + compute_effective_exclusive_cpumask(cs, tmp->new_cpus); WARN_ON_ONCE(!is_remote_partition(cs)); WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus)); spin_lock_irq(&callback_lock); - cpumask_andnot(subpartitions_cpus, - subpartitions_cpus, tmp->new_cpus); - cpumask_and(tmp->new_cpus, - tmp->new_cpus, cpu_active_mask); - cpumask_or(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->new_cpus); list_del_init(&cs->remote_sibling); + isolcpus_updated = partition_xcpus_del(cs->partition_root_state, + NULL, tmp->new_cpus); cs->partition_root_state = -cs->partition_root_state; if (!cs->prs_err) cs->prs_err = PERR_INVCPUS; reset_partition_data(cs); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. @@ -1557,6 +1667,8 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask, struct tmpmasks *tmp) { bool adding, deleting; + int prs = cs->partition_root_state; + int isolcpus_updated = 0; if (WARN_ON_ONCE(!is_remote_partition(cs))) return; @@ -1580,21 +1692,12 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask, goto invalidate; spin_lock_irq(&callback_lock); - if (adding) { - cpumask_or(subpartitions_cpus, - subpartitions_cpus, tmp->addmask); - cpumask_andnot(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->addmask); - } - if (deleting) { - cpumask_andnot(subpartitions_cpus, - subpartitions_cpus, tmp->delmask); - cpumask_and(tmp->delmask, - tmp->delmask, cpu_active_mask); - cpumask_or(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->delmask); - } + if (adding) + isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask); + if (deleting) + isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. @@ -1676,11 +1779,11 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) * @tmp: Temporary addmask and delmask * Return: 0 or a partition root state error code * - * For partcmd_enable, the cpuset is being transformed from a non-partition - * root to a partition root. The effective_xcpus (cpus_allowed if effective_xcpus - * not set) mask of the given cpuset will be taken away from parent's - * effective_cpus. The function will return 0 if all the CPUs listed in - * effective_xcpus can be granted or an error code will be returned. + * For partcmd_enable*, the cpuset is being transformed from a non-partition + * root to a partition root. The effective_xcpus (cpus_allowed if + * effective_xcpus not set) mask of the given cpuset will be taken away from + * parent's effective_cpus. The function will return 0 if all the CPUs listed + * in effective_xcpus can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transformed from a partition * root back to a non-partition root. Any CPUs in effective_xcpus will be @@ -1695,7 +1798,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) * * For partcmd_invalidate, the current partition will be made invalid. * - * The partcmd_enable and partcmd_disable commands are used by + * The partcmd_enable* and partcmd_disable commands are used by * update_prstate(). An error code may be returned and the caller will check * for error. * @@ -1716,6 +1819,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, int part_error = PERR_NONE; /* Partition error? */ int subparts_delta = 0; struct cpumask *xcpus; /* cs effective_xcpus */ + int isolcpus_updated = 0; bool nocpu; lockdep_assert_held(&cpuset_mutex); @@ -1760,7 +1864,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, nocpu = tasks_nocpu_error(parent, cs, xcpus); - if (cmd == partcmd_enable) { + if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) { /* * Enabling partition root is not allowed if its * effective_xcpus is empty or doesn't overlap with @@ -1783,6 +1887,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, cpumask_copy(tmp->delmask, xcpus); deleting = true; subparts_delta++; + new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED; } else if (cmd == partcmd_disable) { /* * May need to add cpus to parent's effective_cpus for @@ -1792,6 +1897,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus); if (adding) subparts_delta--; + new_prs = PRS_MEMBER; } else if (newmask) { /* * Empty cpumask is not allowed @@ -1940,38 +2046,28 @@ write_error: * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); - if (adding) { - if (parent == &top_cpuset) - cpumask_andnot(subpartitions_cpus, - subpartitions_cpus, tmp->addmask); - /* - * Some of the CPUs in effective_xcpus might have been offlined. - */ - cpumask_or(parent->effective_cpus, - parent->effective_cpus, tmp->addmask); - cpumask_and(parent->effective_cpus, - parent->effective_cpus, cpu_active_mask); - } - if (deleting) { - if (parent == &top_cpuset) - cpumask_or(subpartitions_cpus, - subpartitions_cpus, tmp->delmask); - cpumask_andnot(parent->effective_cpus, - parent->effective_cpus, tmp->delmask); - } - - if (is_partition_valid(parent)) { - parent->nr_subparts += subparts_delta; - WARN_ON_ONCE(parent->nr_subparts < 0); - } - if (old_prs != new_prs) { cs->partition_root_state = new_prs; if (new_prs <= 0) cs->nr_subparts = 0; } + /* + * Adding to parent's effective_cpus means deletion CPUs from cs + * and vice versa. + */ + if (adding) + isolcpus_updated += partition_xcpus_del(old_prs, parent, + tmp->addmask); + if (deleting) + isolcpus_updated += partition_xcpus_add(new_prs, parent, + tmp->delmask); + if (is_partition_valid(parent)) { + parent->nr_subparts += subparts_delta; + WARN_ON_ONCE(parent->nr_subparts < 0); + } spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive(cs, new_prs); @@ -2948,6 +3044,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) int err = PERR_NONE, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; + bool new_xcpus_state = false; if (old_prs == new_prs) return 0; @@ -2977,6 +3074,9 @@ static int update_prstate(struct cpuset *cs, int new_prs) goto out; if (!old_prs) { + enum partition_cmd cmd = (new_prs == PRS_ROOT) + ? partcmd_enable : partcmd_enablei; + /* * cpus_allowed cannot be empty. */ @@ -2985,19 +3085,18 @@ static int update_prstate(struct cpuset *cs, int new_prs) goto out; } - err = update_parent_effective_cpumask(cs, partcmd_enable, - NULL, &tmpmask); + err = update_parent_effective_cpumask(cs, cmd, NULL, &tmpmask); /* * If an attempt to become local partition root fails, * try to become a remote partition root instead. */ - if (err && remote_partition_enable(cs, &tmpmask)) + if (err && remote_partition_enable(cs, new_prs, &tmpmask)) err = 0; } else if (old_prs && new_prs) { /* * A change in load balance state only, no change in cpumasks. */ - ; + new_xcpus_state = true; } else { /* * Switching back to member is always allowed even if it @@ -3029,7 +3128,10 @@ out: WRITE_ONCE(cs->prs_err, err); if (!is_partition_valid(cs)) reset_partition_data(cs); + else if (new_xcpus_state) + partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(new_xcpus_state); /* Force update if switching back to member */ update_cpumasks_hier(cs, &tmpmask, !new_prs ? HIER_CHECKALL : 0); @@ -3386,6 +3488,7 @@ typedef enum { FILE_SUBPARTS_CPULIST, FILE_EXCLUSIVE_CPULIST, FILE_EFFECTIVE_XCPULIST, + FILE_ISOLATED_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, @@ -3582,6 +3685,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus)); break; + case FILE_ISOLATED_CPULIST: + seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus)); + break; default: ret = -EINVAL; } @@ -3875,6 +3981,13 @@ static struct cftype dfl_files[] = { .flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG, }, + { + .name = "cpus.isolated", + .seq_show = cpuset_common_seq_show, + .private = FILE_ISOLATED_CPULIST, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + { } /* terminate */ }; @@ -4194,6 +4307,7 @@ int __init cpuset_init(void) BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_xcpus, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); @@ -4306,6 +4420,30 @@ void cpuset_force_rebuild(void) force_rebuild = true; } +/* + * Attempt to acquire a cpus_read_lock while a hotplug operation may be in + * progress. + * Return: true if successful, false otherwise + * + * To avoid circular lock dependency between cpuset_mutex and cpus_read_lock, + * cpus_read_trylock() is used here to acquire the lock. + */ +static bool cpuset_hotplug_cpus_read_trylock(void) +{ + int retries = 0; + + while (!cpus_read_trylock()) { + /* + * CPU hotplug still in progress. Retry 5 times + * with a 10ms wait before bailing out. + */ + if (++retries > 5) + return false; + msleep(10); + } + return true; +} + /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest @@ -4322,6 +4460,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) bool cpus_updated; bool mems_updated; bool remote; + int partcmd = -1; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); @@ -4353,11 +4492,13 @@ retry: compute_partition_effective_cpumask(cs, &new_cpus); if (remote && cpumask_empty(&new_cpus) && - partition_is_populated(cs, NULL)) { + partition_is_populated(cs, NULL) && + cpuset_hotplug_cpus_read_trylock()) { remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); remote = false; cpuset_force_rebuild(); + cpus_read_unlock(); } /* @@ -4368,18 +4509,28 @@ retry: * partitions. */ if (is_local_partition(cs) && (!is_partition_valid(parent) || - tasks_nocpu_error(parent, cs, &new_cpus))) { - update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, tmp); - compute_effective_cpumask(&new_cpus, cs, parent); - cpuset_force_rebuild(); - } + tasks_nocpu_error(parent, cs, &new_cpus))) + partcmd = partcmd_invalidate; /* * On the other hand, an invalid partition root may be transitioned * back to a regular one. */ - else if (is_partition_valid(parent) && is_partition_invalid(cs)) { - update_parent_effective_cpumask(cs, partcmd_update, NULL, tmp); - if (is_partition_valid(cs)) { + else if (is_partition_valid(parent) && is_partition_invalid(cs)) + partcmd = partcmd_update; + + /* + * cpus_read_lock needs to be held before calling + * update_parent_effective_cpumask(). To avoid circular lock + * dependency between cpuset_mutex and cpus_read_lock, + * cpus_read_trylock() is used here to acquire the lock. + */ + if (partcmd >= 0) { + if (!cpuset_hotplug_cpus_read_trylock()) + goto update_tasks; + + update_parent_effective_cpumask(cs, partcmd, NULL, tmp); + cpus_read_unlock(); + if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) { compute_partition_effective_cpumask(cs, &new_cpus); cpuset_force_rebuild(); } @@ -4941,7 +5092,7 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX, current->nsproxy->cgroup_ns); css_put(css); - if (retval >= PATH_MAX) + if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) goto out_free; diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index c0adb7254..a8350d2d6 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -74,64 +74,109 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) } /** - * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree - * @pos: current position - * @root: root of the tree to traversal + * cgroup_rstat_push_children - push children cgroups into the given list + * @head: current head of the list (= subtree root) + * @child: first child of the root * @cpu: target cpu + * Return: A new singly linked list of cgroups to be flush * - * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts - * the traversal and %NULL return indicates the end. During traversal, - * each returned cgroup is unlinked from the tree. Must be called with the - * matching cgroup_rstat_cpu_lock held. + * Iteratively traverse down the cgroup_rstat_cpu updated tree level by + * level and push all the parents first before their next level children + * into a singly linked list built from the tail backward like "pushing" + * cgroups into a stack. The root is pushed by the caller. + */ +static struct cgroup *cgroup_rstat_push_children(struct cgroup *head, + struct cgroup *child, int cpu) +{ + struct cgroup *chead = child; /* Head of child cgroup level */ + struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */ + struct cgroup *parent, *grandchild; + struct cgroup_rstat_cpu *crstatc; + + child->rstat_flush_next = NULL; + +next_level: + while (chead) { + child = chead; + chead = child->rstat_flush_next; + parent = cgroup_parent(child); + + /* updated_next is parent cgroup terminated */ + while (child != parent) { + child->rstat_flush_next = head; + head = child; + crstatc = cgroup_rstat_cpu(child, cpu); + grandchild = crstatc->updated_children; + if (grandchild != child) { + /* Push the grand child to the next level */ + crstatc->updated_children = child; + grandchild->rstat_flush_next = ghead; + ghead = grandchild; + } + child = crstatc->updated_next; + crstatc->updated_next = NULL; + } + } + + if (ghead) { + chead = ghead; + ghead = NULL; + goto next_level; + } + return head; +} + +/** + * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed + * @root: root of the cgroup subtree to traverse + * @cpu: target cpu + * Return: A singly linked list of cgroups to be flushed + * + * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, + * each returned cgroup is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair - * covered by a given traversal, if a child is visited, its parent is - * guaranteed to be visited afterwards. + * covered by a given traversal, the child is before its parent in + * the list. + * + * Note that updated_children is self terminated and points to a list of + * child cgroups if not empty. Whereas updated_next is like a sibling link + * within the children list and terminated by the parent cgroup. An exception + * here is the cgroup root whose updated_next can be self terminated. */ -static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, - struct cgroup *root, int cpu) +static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) { - struct cgroup_rstat_cpu *rstatc; - struct cgroup *parent; - - if (pos == root) - return NULL; + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu); + struct cgroup *head = NULL, *parent, *child; + unsigned long flags; /* - * We're gonna walk down to the first leaf and visit/remove it. We - * can pick whatever unvisited node as the starting point. + * The _irqsave() is needed because cgroup_rstat_lock is + * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring + * this lock with the _irq() suffix only disables interrupts on + * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables + * interrupts on both configurations. The _irqsave() ensures + * that interrupts are always disabled and later restored. */ - if (!pos) { - pos = root; - /* return NULL if this subtree is not on-list */ - if (!cgroup_rstat_cpu(pos, cpu)->updated_next) - return NULL; - } else { - pos = cgroup_parent(pos); - } + raw_spin_lock_irqsave(cpu_lock, flags); - /* walk down to the first leaf */ - while (true) { - rstatc = cgroup_rstat_cpu(pos, cpu); - if (rstatc->updated_children == pos) - break; - pos = rstatc->updated_children; - } + /* Return NULL if this subtree is not on-list */ + if (!rstatc->updated_next) + goto unlock_ret; /* - * Unlink @pos from the tree. As the updated_children list is + * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. - * However, due to the way we traverse, @pos will be the first - * child in most cases. The only exception is @root. */ - parent = cgroup_parent(pos); + parent = cgroup_parent(root); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; - while (*nextp != pos) { + while (*nextp != root) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); @@ -142,7 +187,17 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, } rstatc->updated_next = NULL; - return pos; + + /* Push @root to the list first before pushing the children */ + head = root; + root->rstat_flush_next = NULL; + child = rstatc->updated_children; + rstatc->updated_children = root; + if (child != root) + head = cgroup_rstat_push_children(head, child, cpu); +unlock_ret: + raw_spin_unlock_irqrestore(cpu_lock, flags); + return head; } /* @@ -176,21 +231,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { - raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, - cpu); - struct cgroup *pos = NULL; - unsigned long flags; + struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu); - /* - * The _irqsave() is needed because cgroup_rstat_lock is - * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring - * this lock with the _irq() suffix only disables interrupts on - * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables - * interrupts on both configurations. The _irqsave() ensures - * that interrupts are always disabled and later restored. - */ - raw_spin_lock_irqsave(cpu_lock, flags); - while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { + for (; pos; pos = pos->rstat_flush_next) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); @@ -202,7 +245,6 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } - raw_spin_unlock_irqrestore(cpu_lock, flags); /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { diff --git a/kernel/cpu.c b/kernel/cpu.c index a86972a91..f8a0406ce 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2125,11 +2125,6 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, - [CPUHP_SLAB_PREPARE] = { - .name = "slab:prepare", - .startup.single = slab_prepare_cpu, - .teardown.single = slab_dead_cpu, - }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, @@ -3212,7 +3207,8 @@ enum cpu_mitigations { }; static enum cpu_mitigations cpu_mitigations __ro_after_init = - CPU_MITIGATIONS_AUTO; + IS_ENABLED(CONFIG_CPU_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : + CPU_MITIGATIONS_OFF; static int __init mitigations_parse_cmdline(char *arg) { diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 9e337493d..ebde3063b 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include @@ -569,9 +568,11 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, phdr->p_filesz = phdr->p_memsz = mend - mstart + 1; phdr->p_align = 0; ehdr->e_phnum++; - pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n", - phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz, - ehdr->e_phnum, phdr->p_offset); +#ifdef CONFIG_KEXEC_FILE + kexec_dprintk("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n", + phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz, + ehdr->e_phnum, phdr->p_offset); +#endif phdr++; } @@ -583,9 +584,8 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend) { - int i, j; + int i; unsigned long long start, end, p_start, p_end; - struct range temp_range = {0, 0}; for (i = 0; i < mem->nr_ranges; i++) { start = mem->ranges[i].start; @@ -593,72 +593,51 @@ int crash_exclude_mem_range(struct crash_mem *mem, p_start = mstart; p_end = mend; - if (mstart > end || mend < start) + if (p_start > end) continue; + /* + * Because the memory ranges in mem->ranges are stored in + * ascending order, when we detect `p_end < start`, we can + * immediately exit the for loop, as the subsequent memory + * ranges will definitely be outside the range we are looking + * for. + */ + if (p_end < start) + break; + /* Truncate any area outside of range */ - if (mstart < start) + if (p_start < start) p_start = start; - if (mend > end) + if (p_end > end) p_end = end; /* Found completely overlapping range */ if (p_start == start && p_end == end) { - mem->ranges[i].start = 0; - mem->ranges[i].end = 0; - if (i < mem->nr_ranges - 1) { - /* Shift rest of the ranges to left */ - for (j = i; j < mem->nr_ranges - 1; j++) { - mem->ranges[j].start = - mem->ranges[j+1].start; - mem->ranges[j].end = - mem->ranges[j+1].end; - } - - /* - * Continue to check if there are another overlapping ranges - * from the current position because of shifting the above - * mem ranges. - */ - i--; - mem->nr_ranges--; - continue; - } + memmove(&mem->ranges[i], &mem->ranges[i + 1], + (mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i])); + i--; mem->nr_ranges--; - return 0; - } - - if (p_start > start && p_end < end) { + } else if (p_start > start && p_end < end) { /* Split original range */ + if (mem->nr_ranges >= mem->max_nr_ranges) + return -ENOMEM; + + memmove(&mem->ranges[i + 2], &mem->ranges[i + 1], + (mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i])); + mem->ranges[i].end = p_start - 1; - temp_range.start = p_end + 1; - temp_range.end = end; + mem->ranges[i + 1].start = p_end + 1; + mem->ranges[i + 1].end = end; + + i++; + mem->nr_ranges++; } else if (p_start != start) mem->ranges[i].end = p_start - 1; else mem->ranges[i].start = p_end + 1; - break; - } - - /* If a split happened, add the split to array */ - if (!temp_range.end) - return 0; - - /* Split happened */ - if (i == mem->max_nr_ranges - 1) - return -ENOMEM; - - /* Location where new range should go */ - j = i + 1; - if (j < mem->nr_ranges) { - /* Move over all ranges one slot towards the end */ - for (i = mem->nr_ranges - 1; i >= j; i--) - mem->ranges[i + 1] = mem->ranges[i]; } - mem->ranges[j].start = temp_range.start; - mem->ranges[j].end = temp_range.end; - mem->nr_ranges++; return 0; } @@ -820,7 +799,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(list_head, prev); VMCOREINFO_OFFSET(vmap_area, va_start); VMCOREINFO_OFFSET(vmap_area, list); - VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER + 1); + VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS); log_buf_vmcoreinfo_setup(); VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); VMCOREINFO_NUMBER(NR_FREE_PAGES); @@ -835,11 +814,10 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_head_mask); #define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(PG_hugetlb); +#define PAGE_HUGETLB_MAPCOUNT_VALUE (~PG_hugetlb) + VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE); #define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif #ifdef CONFIG_KALLSYMS VMCOREINFO_SYMBOL(kallsyms_names); @@ -906,7 +884,7 @@ subsys_initcall(crash_notes_memory_init); * regions are online. So mutex lock __crash_hotplug_lock is used to * serialize the crash hotplug handling specifically. */ -DEFINE_MUTEX(__crash_hotplug_lock); +static DEFINE_MUTEX(__crash_hotplug_lock); #define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock) #define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 3de494375..a6e3792b1 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -62,7 +62,8 @@ enum map_err_types { * @pfn: page frame of the start address * @offset: offset of mapping relative to pfn * @map_err_type: track whether dma_mapping_error() was checked - * @stacktrace: support backtraces when a violation is detected + * @stack_len: number of backtrace entries in @stack_entries + * @stack_entries: stack of backtrace history */ struct dma_debug_entry { struct list_head list; @@ -876,7 +877,7 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti return 0; } -void dma_debug_add_bus(struct bus_type *bus) +void dma_debug_add_bus(const struct bus_type *bus) { struct notifier_block *nb; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 73c958157..4d543b1e9 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -286,7 +286,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, } else { ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; } memset(ret, 0, size); @@ -307,6 +307,8 @@ out_encrypt_pages: out_free_pages: __dma_direct_free_pages(dev, page, size); return NULL; +out_leak_pages: + return NULL; } void dma_direct_free(struct device *dev, size_t size, @@ -367,12 +369,11 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; memset(ret, 0, size); *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); return page; -out_free_pages: - __dma_direct_free_pages(dev, page, size); +out_leak_pages: return NULL; } @@ -677,7 +678,6 @@ int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start, return -ENOMEM; map[0].cpu_start = cpu_start; map[0].dma_start = dma_start; - map[0].offset = offset; map[0].size = size; dev->dma_range_map = map; return 0; diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index b481c48a3..d10613eb0 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -84,8 +84,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, void *addr; int ret = -ENOMEM; - /* Cannot allocate larger than MAX_ORDER */ - order = min(get_order(pool_size), MAX_ORDER); + /* Cannot allocate larger than MAX_PAGE_ORDER */ + order = min(get_order(pool_size), MAX_PAGE_ORDER); do { pool_size = 1 << (PAGE_SHIFT + order); @@ -190,7 +190,7 @@ static int __init dma_atomic_pool_init(void) /* * If coherent_pool was not used on the command line, default the pool - * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER. + * sizes to 128KB per 1GB of memory, min 128KB, max MAX_PAGE_ORDER. */ if (!atomic_pool_size) { unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 9edfb3b77..877c4b8fa 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -686,8 +686,8 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev, size_t pool_size; size_t tlb_size; - if (nslabs > SLABS_PER_PAGE << MAX_ORDER) { - nslabs = SLABS_PER_PAGE << MAX_ORDER; + if (nslabs > SLABS_PER_PAGE << MAX_PAGE_ORDER) { + nslabs = SLABS_PER_PAGE << MAX_PAGE_ORDER; nareas = limit_nareas(nareas, nslabs); } @@ -957,7 +957,7 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) #endif /* CONFIG_DEBUG_FS */ /** - * swiotlb_area_find_slots() - search for slots in one IO TLB memory area + * swiotlb_search_pool_area() - search one memory area in one pool * @dev: Device which maps the buffer. * @pool: Memory pool to be searched. * @area_index: Index of the IO TLB memory area to be searched. @@ -972,7 +972,7 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) * * Return: Index of the first allocated slot, or -1 on error. */ -static int swiotlb_area_find_slots(struct device *dev, struct io_tlb_pool *pool, +static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool, int area_index, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask) { @@ -1075,41 +1075,50 @@ found: return slot_index; } +#ifdef CONFIG_SWIOTLB_DYNAMIC + /** - * swiotlb_pool_find_slots() - search for slots in one memory pool + * swiotlb_search_area() - search one memory area in all pools * @dev: Device which maps the buffer. - * @pool: Memory pool to be searched. + * @start_cpu: Start CPU number. + * @cpu_offset: Offset from @start_cpu. * @orig_addr: Original (non-bounced) IO buffer address. * @alloc_size: Total requested size of the bounce buffer, * including initial alignment padding. * @alloc_align_mask: Required alignment of the allocated buffer. + * @retpool: Used memory pool, updated on return. * - * Search through one memory pool to find a sequence of slots that match the + * Search one memory area in all pools for a sequence of slots that match the * allocation constraints. * * Return: Index of the first allocated slot, or -1 on error. */ -static int swiotlb_pool_find_slots(struct device *dev, struct io_tlb_pool *pool, - phys_addr_t orig_addr, size_t alloc_size, - unsigned int alloc_align_mask) +static int swiotlb_search_area(struct device *dev, int start_cpu, + int cpu_offset, phys_addr_t orig_addr, size_t alloc_size, + unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { - int start = raw_smp_processor_id() & (pool->nareas - 1); - int i = start, index; - - do { - index = swiotlb_area_find_slots(dev, pool, i, orig_addr, - alloc_size, alloc_align_mask); - if (index >= 0) - return index; - if (++i >= pool->nareas) - i = 0; - } while (i != start); + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + struct io_tlb_pool *pool; + int area_index; + int index = -1; - return -1; + rcu_read_lock(); + list_for_each_entry_rcu(pool, &mem->pools, node) { + if (cpu_offset >= pool->nareas) + continue; + area_index = (start_cpu + cpu_offset) & (pool->nareas - 1); + index = swiotlb_search_pool_area(dev, pool, area_index, + orig_addr, alloc_size, + alloc_align_mask); + if (index >= 0) { + *retpool = pool; + break; + } + } + rcu_read_unlock(); + return index; } -#ifdef CONFIG_SWIOTLB_DYNAMIC - /** * swiotlb_find_slots() - search for slots in the whole swiotlb * @dev: Device which maps the buffer. @@ -1133,18 +1142,20 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, unsigned long nslabs; unsigned long flags; u64 phys_limit; + int cpu, i; int index; - rcu_read_lock(); - list_for_each_entry_rcu(pool, &mem->pools, node) { - index = swiotlb_pool_find_slots(dev, pool, orig_addr, - alloc_size, alloc_align_mask); - if (index >= 0) { - rcu_read_unlock(); + if (alloc_size > IO_TLB_SEGSIZE * IO_TLB_SIZE) + return -1; + + cpu = raw_smp_processor_id(); + for (i = 0; i < default_nareas; ++i) { + index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size, + alloc_align_mask, &pool); + if (index >= 0) goto found; - } } - rcu_read_unlock(); + if (!mem->can_grow) return -1; @@ -1157,8 +1168,8 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, if (!pool) return -1; - index = swiotlb_pool_find_slots(dev, pool, orig_addr, - alloc_size, alloc_align_mask); + index = swiotlb_search_pool_area(dev, pool, 0, orig_addr, + alloc_size, alloc_align_mask); if (index < 0) { swiotlb_dyn_free(&pool->rcu); return -1; @@ -1201,9 +1212,21 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { - *retpool = &dev->dma_io_tlb_mem->defpool; - return swiotlb_pool_find_slots(dev, *retpool, - orig_addr, alloc_size, alloc_align_mask); + struct io_tlb_pool *pool; + int start, i; + int index; + + *retpool = pool = &dev->dma_io_tlb_mem->defpool; + i = start = raw_smp_processor_id() & (pool->nareas - 1); + do { + index = swiotlb_search_pool_area(dev, pool, i, orig_addr, + alloc_size, alloc_align_mask); + if (index >= 0) + return index; + if (++i >= pool->nareas) + i = 0; + } while (i != start); + return -1; } #endif /* CONFIG_SWIOTLB_DYNAMIC */ diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 5ff4f1cd3..90843cc38 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -15,26 +15,6 @@ #define CREATE_TRACE_POINTS #include -/* See comment for enter_from_user_mode() in entry-common.h */ -static __always_inline void __enter_from_user_mode(struct pt_regs *regs) -{ - arch_enter_from_user_mode(regs); - lockdep_hardirqs_off(CALLER_ADDR0); - - CT_WARN_ON(__ct_state() != CONTEXT_USER); - user_exit_irqoff(); - - instrumentation_begin(); - kmsan_unpoison_entry_regs(regs); - trace_hardirqs_off_finish(); - instrumentation_end(); -} - -void noinstr enter_from_user_mode(struct pt_regs *regs) -{ - __enter_from_user_mode(regs); -} - static inline void syscall_enter_audit(struct pt_regs *regs, long syscall) { if (unlikely(audit_context())) { @@ -45,7 +25,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall) } } -static long syscall_trace_enter(struct pt_regs *regs, long syscall, +long syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long work) { long ret = 0; @@ -91,67 +71,24 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, return ret ? : syscall; } -static __always_inline long -__syscall_enter_from_user_work(struct pt_regs *regs, long syscall) -{ - unsigned long work = READ_ONCE(current_thread_info()->syscall_work); - - if (work & SYSCALL_WORK_ENTER) - syscall = syscall_trace_enter(regs, syscall, work); - - return syscall; -} - -long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall) -{ - return __syscall_enter_from_user_work(regs, syscall); -} - -noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) -{ - long ret; - - __enter_from_user_mode(regs); - - instrumentation_begin(); - local_irq_enable(); - ret = __syscall_enter_from_user_work(regs, syscall); - instrumentation_end(); - - return ret; -} - noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs) { - __enter_from_user_mode(regs); + enter_from_user_mode(regs); instrumentation_begin(); local_irq_enable(); instrumentation_end(); } -/* See comment for exit_to_user_mode() in entry-common.h */ -static __always_inline void __exit_to_user_mode(void) -{ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(); - instrumentation_end(); - - user_enter_irqoff(); - arch_exit_to_user_mode(); - lockdep_hardirqs_on(CALLER_ADDR0); -} - -void noinstr exit_to_user_mode(void) -{ - __exit_to_user_mode(); -} - /* Workaround to allow gradual conversion of architecture code */ void __weak arch_do_signal_or_restart(struct pt_regs *regs) { } -static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, - unsigned long ti_work) +/** + * exit_to_user_mode_loop - do any pending work before leaving to user space + * @regs: Pointer to pt_regs on entry stack + * @ti_work: TIF work flags as read by the caller + */ +__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs, + unsigned long ti_work) { /* * Before returning to user space ensure that all pending work @@ -196,27 +133,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, return ti_work; } -static void exit_to_user_mode_prepare(struct pt_regs *regs) -{ - unsigned long ti_work; - - lockdep_assert_irqs_disabled(); - - /* Flush pending rcuog wakeup before the last need_resched() check */ - tick_nohz_user_enter_prepare(); - - ti_work = read_thread_flags(); - if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK)) - ti_work = exit_to_user_mode_loop(regs, ti_work); - - arch_exit_to_user_mode_prepare(regs, ti_work); - - /* Ensure that kernel state is sane for a return to userspace */ - kmap_assert_nomap(); - lockdep_assert_irqs_disabled(); - lockdep_sys_exit(); -} - /* * If SYSCALL_EMU is set, then the only reason to report is when * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall @@ -301,12 +217,12 @@ __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs) instrumentation_begin(); __syscall_exit_to_user_mode_work(regs); instrumentation_end(); - __exit_to_user_mode(); + exit_to_user_mode(); } noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs) { - __enter_from_user_mode(regs); + enter_from_user_mode(regs); } noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs) @@ -314,7 +230,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs) instrumentation_begin(); exit_to_user_mode_prepare(regs); instrumentation_end(); - __exit_to_user_mode(); + exit_to_user_mode(); } noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) diff --git a/kernel/events/core.c b/kernel/events/core.c index 7c0330579..f0f0f7121 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7397,6 +7397,14 @@ void perf_output_sample(struct perf_output_handle *handle, if (branch_sample_hw_index(event)) perf_output_put(handle, data->br_stack->hw_idx); perf_output_copy(handle, data->br_stack->entries, size); + /* + * Add the extension space which is appended + * right after the struct perf_branch_stack. + */ + if (data->br_stack_cntr) { + size = data->br_stack->nr * sizeof(u64); + perf_output_copy(handle, data->br_stack_cntr, size); + } } else { /* * we always store at least the value of nr diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index e8d82c2f0..60ed43d1c 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -610,8 +610,8 @@ static struct page *rb_alloc_aux_page(int node, int order) { struct page *page; - if (order > MAX_ORDER) - order = MAX_ORDER; + if (order > MAX_PAGE_ORDER) + order = MAX_PAGE_ORDER; do { page = alloc_pages_node(node, PERF_AUX_GFP, order); @@ -702,9 +702,9 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, /* * kcalloc_node() is unable to allocate buffer if the size is larger - * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case. + * than: PAGE_SIZE << MAX_PAGE_ORDER; directly bail out in this case. */ - if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER) + if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_PAGE_ORDER) return -ENOMEM; rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL, node); @@ -821,7 +821,7 @@ struct perf_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct perf_buffer); size += nr_pages * sizeof(void *); - if (order_base_2(size) > PAGE_SHIFT+MAX_ORDER) + if (order_base_2(size) > PAGE_SHIFT+MAX_PAGE_ORDER) goto fail; node = (cpu == -1) ? cpu : cpu_to_node(cpu); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 435aac1d8..929e98c62 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { folio_get(new_folio); - page_add_new_anon_rmap(new_page, vma, addr); + folio_add_new_anon_rmap(new_folio, vma, addr); folio_add_lru_vma(new_folio, vma); } else /* no new page, just dec_mm_counter for old_page */ @@ -198,7 +198,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, set_pte_at_notify(mm, addr, pvmw.pte, mk_pte(new_page, vma->vm_page_prot)); - page_remove_rmap(old_page, vma, false); + folio_remove_rmap_pte(old_folio, old_page, vma); if (!folio_mapped(old_folio)) folio_free_swap(old_folio); page_vma_mapped_walk_done(&pvmw); @@ -537,7 +537,7 @@ retry: } } - ret = __replace_page(vma, vaddr, old_page, new_page); + ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page); if (new_page) put_page(new_page); put_old: diff --git a/kernel/exit.c b/kernel/exit.c index aedc0832c..dfb963d2f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -69,8 +69,10 @@ #include #include #include - #include + +#include + #include #include @@ -1125,17 +1127,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) * and nobody can change them. * * psig->stats_lock also protects us from our sub-threads - * which can reap other children at the same time. Until - * we change k_getrusage()-like users to rely on this lock - * we have to take ->siglock as well. + * which can reap other children at the same time. * * We use thread_group_cputime_adjusted() to get times for * the thread group, which consolidates times for all threads * in the group including the group leader. */ thread_group_cputime_adjusted(p, &tgutime, &tgstime); - spin_lock_irq(¤t->sighand->siglock); - write_seqlock(&psig->stats_lock); + write_seqlock_irq(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; @@ -1158,8 +1157,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); - write_sequnlock(&psig->stats_lock); - spin_unlock_irq(¤t->sighand->siglock); + write_sequnlock_irq(&psig->stats_lock); } if (wo->wo_rusage) diff --git a/kernel/fork.c b/kernel/fork.c index 10917c3e1..3b9cdb42e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -99,6 +100,7 @@ #include #include #include +#include #include #include @@ -165,7 +167,6 @@ void __weak arch_release_task_struct(struct task_struct *tsk) { } -#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) @@ -177,9 +178,6 @@ static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } -#endif - -#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a @@ -412,24 +410,6 @@ void thread_stack_cache_init(void) } # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ -#else /* CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ - -static int alloc_thread_stack_node(struct task_struct *tsk, int node) -{ - unsigned long *stack; - - stack = arch_alloc_thread_stack_node(tsk, node); - tsk->stack = stack; - return stack ? 0 : -ENOMEM; -} - -static void free_thread_stack(struct task_struct *tsk) -{ - arch_free_thread_stack(tsk); - tsk->stack = NULL; -} - -#endif /* !CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; @@ -650,7 +630,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, int retval; unsigned long charge = 0; LIST_HEAD(uf); - VMA_ITERATOR(old_vmi, oldmm, 0); VMA_ITERATOR(vmi, mm, 0); uprobe_start_dup_mmap(); @@ -678,16 +657,22 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; khugepaged_fork(mm, oldmm); - retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count); - if (retval) + /* Use __mt_dup() to efficiently build an identical maple tree. */ + retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); + if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); - for_each_vma(old_vmi, mpnt) { + for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { + retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, + mpnt->vm_end, GFP_KERNEL); + if (retval) + goto loop_out; + vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } @@ -727,6 +712,23 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); + /* + * Copy/update hugetlb private vma information. + */ + if (is_vm_hugetlb_page(tmp)) + hugetlb_dup_vma_private(tmp); + + /* + * Link the vma into the MT. After using __mt_dup(), memory + * allocation is not necessary here, so it cannot fail. + */ + vma_iter_bulk_store(&vmi, tmp); + + mm->map_count++; + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; @@ -743,32 +745,31 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, i_mmap_unlock_write(mapping); } - /* - * Copy/update hugetlb private vma information. - */ - if (is_vm_hugetlb_page(tmp)) - hugetlb_dup_vma_private(tmp); - - /* Link the vma into the MT */ - if (vma_iter_bulk_store(&vmi, tmp)) - goto fail_nomem_vmi_store; - - mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); - if (tmp->vm_ops && tmp->vm_ops->open) - tmp->vm_ops->open(tmp); - - if (retval) + if (retval) { + mpnt = vma_next(&vmi); goto loop_out; + } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); - if (!retval) + if (!retval) { mt_set_in_rcu(vmi.mas.tree); + } else if (mpnt) { + /* + * The entire maple tree has already been duplicated. If the + * mmap duplication fails, mark the failure point with + * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, + * stop releasing VMAs that have not been duplicated after this + * point. + */ + mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); + mas_store(&vmi.mas, XA_ZERO_ENTRY); + } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); @@ -778,8 +779,6 @@ fail_uprobe_end: uprobe_end_dup_mmap(); return retval; -fail_nomem_vmi_store: - unlink_anon_vmas(tmp); fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: @@ -1021,7 +1020,6 @@ static void set_max_threads(unsigned int max_threads_suggested) int arch_task_struct_size __read_mostly; #endif -#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static void task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ @@ -1036,12 +1034,10 @@ static void task_struct_whitelist(unsigned long *offset, unsigned long *size) else *offset += offsetof(struct task_struct, thread); } -#endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */ void __init fork_init(void) { int i; -#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif @@ -1054,7 +1050,6 @@ void __init fork_init(void) arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); -#endif /* do the arch specific task caches init */ arch_task_cache_init(); @@ -1179,7 +1174,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->use_memdelay = 0; #endif -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif @@ -1588,7 +1583,7 @@ static void complete_vfork_done(struct task_struct *tsk) static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { - unsigned int state = TASK_UNINTERRUPTIBLE|TASK_KILLABLE|TASK_FREEZABLE; + unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); @@ -1754,6 +1749,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); + /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; @@ -2928,7 +2924,7 @@ pid_t kernel_clone(struct kernel_clone_args *args) get_task_struct(p); } - if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) { + if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); diff --git a/kernel/freezer.c b/kernel/freezer.c index 759006a9a..f57aaf96b 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -187,6 +187,7 @@ static int __restore_freezer_state(struct task_struct *p, void *arg) if (state != TASK_RUNNING) { WRITE_ONCE(p->__state, state); + p->saved_state = TASK_RUNNING; return 1; } diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 52d0bf67e..1e78ef243 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index eb21f0658..b47bb764b 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include #include #include "futex.h" diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index 61b112897..3a10375d9 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include #include #include #include diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1782f90cd..7389add52 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1642,8 +1642,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!((old->flags & new->flags) & IRQF_SHARED) || - (oldtype != (new->flags & IRQF_TRIGGER_MASK)) || - ((old->flags ^ new->flags) & IRQF_ONESHOT)) + (oldtype != (new->flags & IRQF_TRIGGER_MASK))) + goto mismatch; + + if ((old->flags & IRQF_ONESHOT) && + (new->flags & IRQF_COND_ONESHOT)) + new->flags |= IRQF_ONESHOT; + else if ((old->flags ^ new->flags) & IRQF_ONESHOT) goto mismatch; /* All handlers must agree on per-cpuness */ diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index b926c4db8..d08fc7b5d 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -52,6 +52,8 @@ atomic_t __kexec_lock = ATOMIC_INIT(0); /* Flag to indicate we are going to kexec a new kernel */ bool kexec_in_progress = false; +bool kexec_file_dbg_print; + int kexec_should_crash(struct task_struct *p) { /* @@ -276,8 +278,8 @@ int kimage_is_destination_range(struct kimage *image, unsigned long mstart, mend; mstart = image->segment[i].mem; - mend = mstart + image->segment[i].memsz; - if ((end > mstart) && (start < mend)) + mend = mstart + image->segment[i].memsz - 1; + if ((end >= mstart) && (start <= mend)) return 1; } @@ -370,7 +372,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, pfn = page_to_boot_pfn(pages); epfn = pfn + count; addr = pfn << PAGE_SHIFT; - eaddr = epfn << PAGE_SHIFT; + eaddr = (epfn << PAGE_SHIFT) - 1; if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) || kimage_is_destination_range(image, addr, eaddr)) { list_add(&pages->lru, &extra_pages); @@ -430,7 +432,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, pages = NULL; size = (1 << order) << PAGE_SHIFT; - hole_start = (image->control_page + (size - 1)) & ~(size - 1); + hole_start = ALIGN(image->control_page, size); hole_end = hole_start + size - 1; while (hole_end <= crashk_res.end) { unsigned long i; @@ -447,7 +449,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, mend = mstart + image->segment[i].memsz - 1; if ((hole_end >= mstart) && (hole_start <= mend)) { /* Advance the hole to the end of the segment */ - hole_start = (mend + (size - 1)) & ~(size - 1); + hole_start = ALIGN(mend, size); hole_end = hole_start + size - 1; break; } @@ -455,7 +457,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, /* If I don't overlap any segments I have found my hole! */ if (i == image->nr_segments) { pages = pfn_to_page(hole_start >> PAGE_SHIFT); - image->control_page = hole_end; + image->control_page = hole_end + 1; break; } } @@ -716,7 +718,7 @@ static struct page *kimage_alloc_page(struct kimage *image, /* If the page is not a destination page use it */ if (!kimage_is_destination_range(image, addr, - addr + PAGE_SIZE)) + addr + PAGE_SIZE - 1)) break; /* @@ -1063,9 +1065,10 @@ __bpf_kfunc void crash_kexec(struct pt_regs *regs) * panic(). Otherwise parallel calls of panic() and crash_kexec() * may stop each other. To exclude them, we use panic_cpu here too. */ + old_cpu = PANIC_CPU_INVALID; this_cpu = raw_smp_processor_id(); - old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); - if (old_cpu == PANIC_CPU_INVALID) { + + if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) { /* This is the 1st CPU which comes here, so go ahead. */ __crash_kexec(regs); diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index f9a419cd2..bef2f6f25 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -123,6 +123,8 @@ void kimage_file_post_load_cleanup(struct kimage *image) */ kfree(image->image_loader_data); image->image_loader_data = NULL; + + kexec_file_dbg_print = false; } #ifdef CONFIG_KEXEC_SIG @@ -202,6 +204,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, if (ret < 0) return ret; image->kernel_buf_len = ret; + kexec_dprintk("kernel: %p kernel_size: %#lx\n", + image->kernel_buf, image->kernel_buf_len); /* Call arch image probe handlers */ ret = arch_kexec_kernel_image_probe(image, image->kernel_buf, @@ -278,6 +282,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, if (!image) return -ENOMEM; + kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG); image->file_mode = 1; if (kexec_on_panic) { @@ -384,13 +389,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (ret) goto out; + kexec_dprintk("nr_segments = %lu\n", image->nr_segments); for (i = 0; i < image->nr_segments; i++) { struct kexec_segment *ksegment; ksegment = &image->segment[i]; - pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n", - i, ksegment->buf, ksegment->bufsz, ksegment->mem, - ksegment->memsz); + kexec_dprintk("segment[%d]: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n", + i, ksegment->buf, ksegment->bufsz, ksegment->mem, + ksegment->memsz); ret = kimage_load_segment(image, &image->segment[i]); if (ret) @@ -403,6 +409,8 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (ret) goto out; + kexec_dprintk("kexec_file_load: type:%u, start:0x%lx head:0x%lx flags:0x%lx\n", + image->type, image->start, image->head, flags); /* * Free up any temporary buffers allocated which are not needed * after image has been loaded @@ -426,11 +434,11 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end, unsigned long temp_start, temp_end; temp_end = min(end, kbuf->buf_max); - temp_start = temp_end - kbuf->memsz; + temp_start = temp_end - kbuf->memsz + 1; do { /* align down start */ - temp_start = temp_start & (~(kbuf->buf_align - 1)); + temp_start = ALIGN_DOWN(temp_start, kbuf->buf_align); if (temp_start < start || temp_start < kbuf->buf_min) return 0; @@ -592,6 +600,8 @@ static int kexec_walk_resources(struct kexec_buf *kbuf, IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, crashk_res.start, crashk_res.end, kbuf, func); + else if (kbuf->top_down) + return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func); else return walk_system_ram_res(0, ULONG_MAX, kbuf, func); } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d5a0ee40b..65adc815f 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1567,10 +1567,17 @@ static int check_kprobe_address_safe(struct kprobe *p, jump_label_lock(); preempt_disable(); - /* Ensure it is not in reserved area nor out of text */ - if (!(core_kernel_text((unsigned long) p->addr) || - is_module_text_address((unsigned long) p->addr)) || - in_gate_area_no_mm((unsigned long) p->addr) || + /* Ensure the address is in a text area, and find a module if exists. */ + *probed_mod = NULL; + if (!core_kernel_text((unsigned long) p->addr)) { + *probed_mod = __module_text_address((unsigned long) p->addr); + if (!(*probed_mod)) { + ret = -EINVAL; + goto out; + } + } + /* Ensure it is not in reserved area. */ + if (in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || @@ -1580,8 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p, goto out; } - /* Check if 'p' is probing a module. */ - *probed_mod = __module_text_address((unsigned long) p->addr); + /* Get module refcount and reject __init functions for loaded modules. */ if (*probed_mod) { /* * We must hold a refcount of the probed module while updating @@ -1993,7 +1999,7 @@ NOKPROBE_SYMBOL(__kretprobe_find_ret_addr); unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, struct llist_node **cur) { - struct kretprobe_instance *ri = NULL; + struct kretprobe_instance *ri; kprobe_opcode_t *ret; if (WARN_ON_ONCE(!cur)) @@ -2802,7 +2808,7 @@ static int show_kprobe_addr(struct seq_file *pi, void *v) { struct hlist_head *head; struct kprobe *p, *kp; - const char *sym = NULL; + const char *sym; unsigned int i = *(loff_t *) v; unsigned long offset = 0; char *modname, namebuf[KSYM_NAME_LEN]; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 69d3cd2cf..415d81e6c 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -124,7 +124,7 @@ struct call_rcu_chain { struct rcu_head crc_rh; bool crc_stop; }; -struct call_rcu_chain *call_rcu_chain; +struct call_rcu_chain *call_rcu_chain_list; /* Forward reference. */ static void lock_torture_cleanup(void); @@ -1074,12 +1074,12 @@ static int call_rcu_chain_init(void) if (call_rcu_chains <= 0) return 0; - call_rcu_chain = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain), GFP_KERNEL); - if (!call_rcu_chain) + call_rcu_chain_list = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain_list), GFP_KERNEL); + if (!call_rcu_chain_list) return -ENOMEM; for (i = 0; i < call_rcu_chains; i++) { - call_rcu_chain[i].crc_stop = false; - call_rcu(&call_rcu_chain[i].crc_rh, call_rcu_chain_cb); + call_rcu_chain_list[i].crc_stop = false; + call_rcu(&call_rcu_chain_list[i].crc_rh, call_rcu_chain_cb); } return 0; } @@ -1089,13 +1089,13 @@ static void call_rcu_chain_cleanup(void) { int i; - if (!call_rcu_chain) + if (!call_rcu_chain_list) return; for (i = 0; i < call_rcu_chains; i++) - smp_store_release(&call_rcu_chain[i].crc_stop, true); + smp_store_release(&call_rcu_chain_list[i].crc_stop, true); rcu_barrier(); - kfree(call_rcu_chain); - call_rcu_chain = NULL; + kfree(call_rcu_chain_list); + call_rcu_chain_list = NULL; } static void lock_torture_cleanup(void) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 2deeeca3e..cbae8c0b8 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -532,6 +532,11 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne * This function must not be used in interrupt context. Unlocking * of a not locked mutex is not allowed. * + * The caller must ensure that the mutex stays alive until this function has + * returned - mutex_unlock() can NOT directly be used to release an object such + * that another concurrent task can free it. + * Mutexes are different from spinlocks & refcounts in this aspect. + * * This function is similar to (but not equivalent to) up(). */ void __sched mutex_unlock(struct mutex *lock) diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 14235671a..87b03d2e4 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -12,6 +12,7 @@ #include #include #include +#include void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner) diff --git a/kernel/module/dups.c b/kernel/module/dups.c index f3d7ea1e9..9a92f2f8c 100644 --- a/kernel/module/dups.c +++ b/kernel/module/dups.c @@ -207,7 +207,7 @@ bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret) * optimization enabled ... */ ret = wait_for_completion_state(&kmod_req->first_req_done, - TASK_UNINTERRUPTIBLE | TASK_KILLABLE); + TASK_KILLABLE); if (ret) { *dup_ret = ret; return true; diff --git a/kernel/module/main.c b/kernel/module/main.c index 34d9e718c..b0b99348e 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2199,6 +2199,9 @@ static int find_module_sections(struct module *mod, struct load_info *info) mod->kunit_suites = section_objs(info, ".kunit_test_suites", sizeof(*mod->kunit_suites), &mod->num_kunit_suites); + mod->kunit_init_suites = section_objs(info, ".kunit_init_test_suites", + sizeof(*mod->kunit_init_suites), + &mod->num_kunit_init_suites); #endif mod->extable = section_objs(info, "__ex_table", diff --git a/kernel/numa.c b/kernel/numa.c new file mode 100644 index 000000000..67ca6b858 --- /dev/null +++ b/kernel/numa.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include + +/* Stub functions: */ + +#ifndef memory_add_physaddr_to_nid +int memory_add_physaddr_to_nid(u64 start) +{ + pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); +#endif + +#ifndef phys_to_target_node +int phys_to_target_node(u64 start) +{ + pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +EXPORT_SYMBOL_GPL(phys_to_target_node); +#endif diff --git a/kernel/panic.c b/kernel/panic.c index 2807639aa..f22d8f33e 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -446,6 +446,14 @@ void panic(const char *fmt, ...) /* Do not scroll important messages printed above */ suppress_printk = 1; + + /* + * The final messages may not have been printed if in a context that + * defers printing (such as NMI) and irq_work is not available. + * Explicitly flush the kernel log buffer one last time. + */ + console_flush_on_panic(CONSOLE_FLUSH_PENDING); + local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); diff --git a/kernel/params.c b/kernel/params.c index 2d4a05646..2e447f8ae 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -1,19 +1,20 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* Helpers for initial module or kernel cmdline parsing - Copyright (C) 2001 Rusty Russell. - -*/ +/* + * Helpers for initial module or kernel cmdline parsing + * Copyright (C) 2001 Rusty Russell. + */ +#include +#include +#include +#include #include #include -#include -#include #include #include -#include -#include -#include -#include +#include #include +#include +#include #ifdef CONFIG_SYSFS /* Protects all built-in parameters, modules use their own param_lock */ @@ -48,7 +49,7 @@ static void *kmalloc_parameter(unsigned int size) { struct kmalloced_param *p; - p = kmalloc(sizeof(*p) + size, GFP_KERNEL); + p = kmalloc(size_add(sizeof(*p), size), GFP_KERNEL); if (!p) return NULL; @@ -120,9 +121,7 @@ static int parse_one(char *param, unsigned num_params, s16 min_level, s16 max_level, - void *arg, - int (*handle_unknown)(char *param, char *val, - const char *doing, void *arg)) + void *arg, parse_unknown_fn handle_unknown) { unsigned int i; int err; @@ -165,9 +164,7 @@ char *parse_args(const char *doing, unsigned num, s16 min_level, s16 max_level, - void *arg, - int (*unknown)(char *param, char *val, - const char *doing, void *arg)) + void *arg, parse_unknown_fn unknown) { char *param, *val, *err = NULL; @@ -264,17 +261,22 @@ EXPORT_SYMBOL_GPL(param_set_uint_minmax); int param_set_charp(const char *val, const struct kernel_param *kp) { - if (strlen(val) > 1024) { + size_t len, maxlen = 1024; + + len = strnlen(val, maxlen + 1); + if (len == maxlen + 1) { pr_err("%s: string parameter too long\n", kp->name); return -ENOSPC; } maybe_kfree_parameter(*(char **)kp->arg); - /* This is a hack. We can't kmalloc in early boot, and we - * don't need to; this mangled commandline is preserved. */ + /* + * This is a hack. We can't kmalloc() in early boot, and we + * don't need to; this mangled commandline is preserved. + */ if (slab_is_available()) { - *(char **)kp->arg = kmalloc_parameter(strlen(val)+1); + *(char **)kp->arg = kmalloc_parameter(len + 1); if (!*(char **)kp->arg) return -ENOMEM; strcpy(*(char **)kp->arg, val); @@ -512,7 +514,7 @@ int param_set_copystring(const char *val, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - if (strlen(val)+1 > kps->maxlen) { + if (strnlen(val, kps->maxlen) == kps->maxlen) { pr_err("%s: string doesn't fit in %u chars.\n", kp->name, kps->maxlen-1); return -ENOSPC; @@ -743,8 +745,10 @@ void module_param_sysfs_remove(struct module *mod) { if (mod->mkobj.mp) { sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); - /* We are positive that no one is using any param - * attrs at this point. Deallocate immediately. */ + /* + * We are positive that no one is using any param + * attrs at this point. Deallocate immediately. + */ free_module_param_attrs(&mod->mkobj); } } diff --git a/kernel/pid.c b/kernel/pid.c index 6500ef956..b52b10865 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -700,7 +700,7 @@ static int pidfd_getfd(struct pid *pid, int fd) if (IS_ERR(file)) return PTR_ERR(file); - ret = receive_fd(file, O_CLOEXEC); + ret = receive_fd(file, NULL, O_CLOEXEC); fput(file); return ret; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 3028b2218..7ade20e95 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "pid_sysctl.h" static DEFINE_MUTEX(pid_caches_mutex); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index dee341ae4..4b0b7cf2e 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -642,9 +642,9 @@ int hibernation_platform_enter(void) */ static void power_down(void) { -#ifdef CONFIG_SUSPEND int error; +#ifdef CONFIG_SUSPEND if (hibernation_mode == HIBERNATION_SUSPEND) { error = suspend_devices_and_enter(mem_sleep_current); if (error) { @@ -667,7 +667,13 @@ static void power_down(void) kernel_restart(NULL); break; case HIBERNATION_PLATFORM: - hibernation_platform_enter(); + error = hibernation_platform_enter(); + if (error == -EAGAIN || error == -EBUSY) { + swsusp_unmark(); + events_check_enabled = false; + pr_info("Wakeup event detected during hibernation, rolling back.\n"); + return; + } fallthrough; case HIBERNATION_SHUTDOWN: if (kernel_can_power_off()) diff --git a/kernel/power/main.c b/kernel/power/main.c index f6425ae3e..b1ae9b677 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -60,22 +60,6 @@ EXPORT_SYMBOL_GPL(lock_system_sleep); void unlock_system_sleep(unsigned int flags) { - /* - * Don't use freezer_count() because we don't want the call to - * try_to_freeze() here. - * - * Reason: - * Fundamentally, we just don't need it, because freezing condition - * doesn't come into effect until we release the - * system_transition_mutex lock, since the freezer always works with - * system_transition_mutex held. - * - * More importantly, in the case of hibernation, - * unlock_system_sleep() gets called in snapshot_read() and - * snapshot_write() when the freezing condition is still in effect. - * Which means, if we use try_to_freeze() here, it would make them - * enter the refrigerator, thus causing hibernation to lockup. - */ if (!(flags & PF_NOFREEZE)) current->flags &= ~PF_NOFREEZE; mutex_unlock(&system_transition_mutex); diff --git a/kernel/power/power.h b/kernel/power/power.h index 17fd9aaaf..8499a39c6 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -175,6 +175,8 @@ extern int swsusp_write(unsigned int flags); void swsusp_close(void); #ifdef CONFIG_SUSPEND extern int swsusp_unmark(void); +#else +static inline int swsusp_unmark(void) { return 0; } #endif struct __kernel_old_timeval; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 50a15408c..5c96ff067 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1119,7 +1119,7 @@ static void mark_nosave_pages(struct memory_bitmap *bm) int create_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; - int error = 0; + int error; if (forbidden_pages_map && free_pages_map) return 0; @@ -1487,11 +1487,11 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) s_page = pfn_to_page(src_pfn); d_page = pfn_to_page(dst_pfn); if (PageHighMem(s_page)) { - src = kmap_atomic(s_page); - dst = kmap_atomic(d_page); + src = kmap_local_page(s_page); + dst = kmap_local_page(d_page); zeros_only = do_copy_page(dst, src); - kunmap_atomic(dst); - kunmap_atomic(src); + kunmap_local(dst); + kunmap_local(src); } else { if (PageHighMem(d_page)) { /* @@ -1499,9 +1499,9 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) * data modified by kmap_atomic() */ zeros_only = safe_copy_page(buffer, s_page); - dst = kmap_atomic(d_page); + dst = kmap_local_page(d_page); copy_page(dst, buffer); - kunmap_atomic(dst); + kunmap_local(dst); } else { zeros_only = safe_copy_page(page_address(d_page), s_page); } @@ -2778,7 +2778,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) int snapshot_write_next(struct snapshot_handle *handle) { static struct chain_allocator ca; - int error = 0; + int error; next: /* Check if we have already loaded the entire image */ diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index a718067de..3aae526cc 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -106,6 +106,12 @@ static void s2idle_enter(void) swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); + /* + * Kick all CPUs to ensure that they resume their timers and restore + * consistent system state. + */ + wake_up_all_idle_cpus(); + cpus_read_unlock(); raw_spin_lock_irq(&s2idle_lock); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index d44f5937f..6053dddda 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -451,7 +451,7 @@ err_close: static int swap_write_page(struct swap_map_handle *handle, void *buf, struct hib_bio_batch *hb) { - int error = 0; + int error; sector_t offset; if (!handle->cur) @@ -1566,7 +1566,6 @@ put: /** * swsusp_close - close resume device. - * @exclusive: Close the resume device which is exclusively opened. */ void swsusp_close(void) diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index ac2d9750e..6c2afee5e 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -130,7 +130,6 @@ struct printk_message { }; bool other_cpu_in_panic(void); -bool this_cpu_in_panic(void); bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_supress); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 7a835b277..e1b992652 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2328,8 +2328,7 @@ asmlinkage int vprintk_emit(int facility, int level, if (unlikely(suppress_printk)) return 0; - if (unlikely(suppress_panic_printk) && - atomic_read(&panic_cpu) != raw_smp_processor_id()) + if (unlikely(suppress_panic_printk) && other_cpu_in_panic()) return 0; if (level == LOGLEVEL_SCHED) { diff --git a/kernel/ptrace.c b/kernel/ptrace.c index d8b5e13a2..2fabd497d 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -145,20 +145,9 @@ void __ptrace_unlink(struct task_struct *child) */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || - child->signal->group_stop_count)) { + child->signal->group_stop_count)) child->jobctl |= JOBCTL_STOP_PENDING; - /* - * This is only possible if this thread was cloned by the - * traced task running in the stopped group, set the signal - * for the future reports. - * FIXME: we should change ptrace_init_task() to handle this - * case. - */ - if (!(child->jobctl & JOBCTL_STOP_SIGMASK)) - child->jobctl |= SIGSTOP; - } - /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child @@ -386,6 +375,34 @@ static int check_ptrace_options(unsigned long data) return 0; } +static inline void ptrace_set_stopped(struct task_struct *task) +{ + guard(spinlock)(&task->sighand->siglock); + + /* + * If the task is already STOPPED, set JOBCTL_TRAP_STOP and + * TRAPPING, and kick it so that it transits to TRACED. TRAPPING + * will be cleared if the child completes the transition or any + * event which clears the group stop states happens. We'll wait + * for the transition to complete before returning from this + * function. + * + * This hides STOPPED -> RUNNING -> TRACED transition from the + * attaching thread but a different thread in the same group can + * still observe the transient RUNNING state. IOW, if another + * thread's WNOHANG wait(2) on the stopped tracee races against + * ATTACH, the wait(2) may fail due to the transient RUNNING. + * + * The following task_is_stopped() test is safe as both transitions + * in and out of STOPPED are protected by siglock. + */ + if (task_is_stopped(task) && + task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { + task->jobctl &= ~JOBCTL_STOPPED; + signal_wake_up_state(task, __TASK_STOPPED); + } +} + static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) @@ -393,17 +410,17 @@ static int ptrace_attach(struct task_struct *task, long request, bool seize = (request == PTRACE_SEIZE); int retval; - retval = -EIO; if (seize) { if (addr != 0) - goto out; + return -EIO; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) - goto out; + return -EIO; + retval = check_ptrace_options(flags); if (retval) return retval; @@ -414,88 +431,54 @@ static int ptrace_attach(struct task_struct *task, long request, audit_ptrace(task); - retval = -EPERM; if (unlikely(task->flags & PF_KTHREAD)) - goto out; + return -EPERM; if (same_thread_group(task, current)) - goto out; + return -EPERM; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ - retval = -ERESTARTNOINTR; - if (mutex_lock_interruptible(&task->signal->cred_guard_mutex)) - goto out; + scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR, + &task->signal->cred_guard_mutex) { - task_lock(task); - retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); - task_unlock(task); - if (retval) - goto unlock_creds; + scoped_guard (task_lock, task) { + retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); + if (retval) + return retval; + } - write_lock_irq(&tasklist_lock); - retval = -EPERM; - if (unlikely(task->exit_state)) - goto unlock_tasklist; - if (task->ptrace) - goto unlock_tasklist; + scoped_guard (write_lock_irq, &tasklist_lock) { + if (unlikely(task->exit_state)) + return -EPERM; + if (task->ptrace) + return -EPERM; - task->ptrace = flags; + task->ptrace = flags; - ptrace_link(task, current); + ptrace_link(task, current); - /* SEIZE doesn't trap tracee on attach */ - if (!seize) - send_sig_info(SIGSTOP, SEND_SIG_PRIV, task); + /* SEIZE doesn't trap tracee on attach */ + if (!seize) + send_sig_info(SIGSTOP, SEND_SIG_PRIV, task); - spin_lock(&task->sighand->siglock); + ptrace_set_stopped(task); + } + } /* - * If the task is already STOPPED, set JOBCTL_TRAP_STOP and - * TRAPPING, and kick it so that it transits to TRACED. TRAPPING - * will be cleared if the child completes the transition or any - * event which clears the group stop states happens. We'll wait - * for the transition to complete before returning from this - * function. - * - * This hides STOPPED -> RUNNING -> TRACED transition from the - * attaching thread but a different thread in the same group can - * still observe the transient RUNNING state. IOW, if another - * thread's WNOHANG wait(2) on the stopped tracee races against - * ATTACH, the wait(2) may fail due to the transient RUNNING. - * - * The following task_is_stopped() test is safe as both transitions - * in and out of STOPPED are protected by siglock. + * We do not bother to change retval or clear JOBCTL_TRAPPING + * if wait_on_bit() was interrupted by SIGKILL. The tracer will + * not return to user-mode, it will exit and clear this bit in + * __ptrace_unlink() if it wasn't already cleared by the tracee; + * and until then nobody can ptrace this task. */ - if (task_is_stopped(task) && - task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { - task->jobctl &= ~JOBCTL_STOPPED; - signal_wake_up_state(task, __TASK_STOPPED); - } - - spin_unlock(&task->sighand->siglock); - - retval = 0; -unlock_tasklist: - write_unlock_irq(&tasklist_lock); -unlock_creds: - mutex_unlock(&task->signal->cred_guard_mutex); -out: - if (!retval) { - /* - * We do not bother to change retval or clear JOBCTL_TRAPPING - * if wait_on_bit() was interrupted by SIGKILL. The tracer will - * not return to user-mode, it will exit and clear this bit in - * __ptrace_unlink() if it wasn't already cleared by the tracee; - * and until then nobody can ptrace this task. - */ - wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); - proc_ptrace_connector(task, PTRACE_ATTACH); - } + wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); + proc_ptrace_connector(task, PTRACE_ATTACH); - return retval; + return 0; } /** diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 07a6a183c..7567ca8e7 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -3874,7 +3874,9 @@ rcu_torture_init(void) } if (fqs_duration < 0) fqs_duration = 0; - if (fqs_duration) { + if (fqs_holdoff < 0) + fqs_holdoff = 0; + if (fqs_duration && fqs_holdoff) { /* Create the fqs thread */ firsterr = torture_create_kthread(rcu_torture_fqs, NULL, fqs_task); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 560e99ec5..0351a4e83 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -772,20 +772,10 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock_nmisafe); */ static void srcu_gp_start(struct srcu_struct *ssp) { - struct srcu_data *sdp; int state; - if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) - sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id()); - else - sdp = this_cpu_ptr(ssp->sda); lockdep_assert_held(&ACCESS_PRIVATE(ssp->srcu_sup, lock)); WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed)); - spin_lock_rcu_node(sdp); /* Interrupts already disabled. */ - rcu_segcblist_advance(&sdp->srcu_cblist, - rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); - WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL)); - spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */ WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies); WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0); smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */ @@ -1271,9 +1261,11 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, * period (gp_num = X + 8). So acceleration fails. */ s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq); - rcu_segcblist_advance(&sdp->srcu_cblist, - rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); - WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp); + if (rhp) { + rcu_segcblist_advance(&sdp->srcu_cblist, + rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); + WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s)); + } if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) { sdp->srcu_gp_seq_needed = s; needgp = true; @@ -1723,6 +1715,11 @@ static void srcu_invoke_callbacks(struct work_struct *work) WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL)); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); + /* + * Although this function is theoretically re-entrant, concurrent + * callbacks invocation is disallowed to avoid executing an SRCU barrier + * too early. + */ if (sdp->srcu_cblist_invoking || !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) { spin_unlock_irq_rcu_node(sdp); @@ -1753,6 +1750,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) sdp->srcu_cblist_invoking = false; more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist); spin_unlock_irq_rcu_node(sdp); + /* An SRCU barrier or callbacks from previous nesting work pending */ if (more) srcu_schedule_cbs_sdp(sdp, 0); } diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index f54d5782e..732ad5b39 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -975,7 +975,7 @@ static void check_holdout_task(struct task_struct *t, t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) || !rcu_tasks_is_holdout(t) || (IS_ENABLED(CONFIG_NO_HZ_FULL) && - !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) { + !is_idle_task(t) && READ_ONCE(t->rcu_tasks_idle_cpu) >= 0)) { WRITE_ONCE(t->rcu_tasks_holdout, false); list_del_init(&t->rcu_tasks_holdout_list); put_task_struct(t); @@ -993,7 +993,7 @@ static void check_holdout_task(struct task_struct *t, t, ".I"[is_idle_task(t)], "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)], t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout, - t->rcu_tasks_idle_cpu, cpu); + data_race(t->rcu_tasks_idle_cpu), cpu); sched_show_task(t); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f544f24df..f2c10d351 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2370,6 +2370,8 @@ void rcu_force_quiescent_state(void) struct rcu_node *rnp; struct rcu_node *rnp_old = NULL; + if (!rcu_gp_in_progress()) + return; /* Funnel through hierarchy to reduce memory contention. */ rnp = raw_cpu_read(rcu_data.mynode); for (; rnp != NULL; rnp = rnp->parent) { diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 4efbf7333..d430b4656 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -1383,7 +1383,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) rcu_nocb_unlock_irqrestore(rdp, flags); continue; } - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false)); + rcu_nocb_try_flush_bypass(rdp, jiffies); rcu_nocb_unlock_irqrestore(rdp, flags); wake_nocb_gp(rdp, false); sc->nr_to_scan -= _count; diff --git a/kernel/reboot.c b/kernel/reboot.c index 395a0ea3c..22c16e256 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -58,6 +58,14 @@ struct sys_off_handler { struct device *dev; }; +/* + * This variable is used to indicate if a halt was initiated instead of a + * reboot when the reboot call was invoked with LINUX_REBOOT_CMD_POWER_OFF, but + * the system cannot be powered off. This allowes kernel_halt() to notify users + * of that. + */ +static bool poweroff_fallback_to_halt; + /* * Temporary stub that prevents linkage failure while we're in process * of removing all uses of legacy pm_power_off() around the kernel. @@ -297,7 +305,10 @@ void kernel_halt(void) kernel_shutdown_prepare(SYSTEM_HALT); migrate_to_reboot_cpu(); syscore_shutdown(); - pr_emerg("System halted\n"); + if (poweroff_fallback_to_halt) + pr_emerg("Power off not available: System halted instead\n"); + else + pr_emerg("System halted\n"); kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_halt(); } @@ -732,8 +743,10 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, /* Instead of trying to make the power_off code look like * halt when pm_power_off is not set do it the easy way. */ - if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off()) + if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off()) { + poweroff_fallback_to_halt = true; cmd = LINUX_REBOOT_CMD_HALT; + } mutex_lock(&system_transition_mutex); switch (cmd) { @@ -957,21 +970,24 @@ static void hw_failure_emergency_poweroff(int poweroff_delay_ms) } /** - * hw_protection_shutdown - Trigger an emergency system poweroff + * __hw_protection_shutdown - Trigger an emergency system shutdown or reboot * - * @reason: Reason of emergency shutdown to be printed. - * @ms_until_forced: Time to wait for orderly shutdown before tiggering a - * forced shudown. Negative value disables the forced - * shutdown. + * @reason: Reason of emergency shutdown or reboot to be printed. + * @ms_until_forced: Time to wait for orderly shutdown or reboot before + * triggering it. Negative value disables the forced + * shutdown or reboot. + * @shutdown: If true, indicates that a shutdown will happen + * after the critical tempeature is reached. + * If false, indicates that a reboot will happen + * after the critical tempeature is reached. * - * Initiate an emergency system shutdown in order to protect hardware from - * further damage. Usage examples include a thermal protection or a voltage or - * current regulator failures. - * NOTE: The request is ignored if protection shutdown is already pending even - * if the previous request has given a large timeout for forced shutdown. - * Can be called from any context. + * Initiate an emergency system shutdown or reboot in order to protect + * hardware from further damage. Usage examples include a thermal protection. + * NOTE: The request is ignored if protection shutdown or reboot is already + * pending even if the previous request has given a large timeout for forced + * shutdown/reboot. */ -void hw_protection_shutdown(const char *reason, int ms_until_forced) +void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown) { static atomic_t allow_proceed = ATOMIC_INIT(1); @@ -986,9 +1002,12 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) * orderly_poweroff failure */ hw_failure_emergency_poweroff(ms_until_forced); - orderly_poweroff(true); + if (shutdown) + orderly_poweroff(true); + else + orderly_reboot(); } -EXPORT_SYMBOL_GPL(hw_protection_shutdown); +EXPORT_SYMBOL_GPL(__hw_protection_shutdown); static int __init reboot_setup(char *str) { diff --git a/kernel/relay.c b/kernel/relay.c index 83fe0325c..a8e90e98b 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1073,167 +1073,6 @@ static ssize_t relay_file_read(struct file *filp, return written; } -static void relay_consume_bytes(struct rchan_buf *rbuf, int bytes_consumed) -{ - rbuf->bytes_consumed += bytes_consumed; - - if (rbuf->bytes_consumed >= rbuf->chan->subbuf_size) { - relay_subbufs_consumed(rbuf->chan, rbuf->cpu, 1); - rbuf->bytes_consumed %= rbuf->chan->subbuf_size; - } -} - -static void relay_pipe_buf_release(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - struct rchan_buf *rbuf; - - rbuf = (struct rchan_buf *)page_private(buf->page); - relay_consume_bytes(rbuf, buf->private); -} - -static const struct pipe_buf_operations relay_pipe_buf_ops = { - .release = relay_pipe_buf_release, - .try_steal = generic_pipe_buf_try_steal, - .get = generic_pipe_buf_get, -}; - -static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i) -{ -} - -/* - * subbuf_splice_actor - splice up to one subbuf's worth of data - */ -static ssize_t subbuf_splice_actor(struct file *in, - loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, - unsigned int flags, - int *nonpad_ret) -{ - unsigned int pidx, poff, total_len, subbuf_pages, nr_pages; - struct rchan_buf *rbuf = in->private_data; - unsigned int subbuf_size = rbuf->chan->subbuf_size; - uint64_t pos = (uint64_t) *ppos; - uint32_t alloc_size = (uint32_t) rbuf->chan->alloc_size; - size_t read_start = (size_t) do_div(pos, alloc_size); - size_t read_subbuf = read_start / subbuf_size; - size_t padding = rbuf->padding[read_subbuf]; - size_t nonpad_end = read_subbuf * subbuf_size + subbuf_size - padding; - struct page *pages[PIPE_DEF_BUFFERS]; - struct partial_page partial[PIPE_DEF_BUFFERS]; - struct splice_pipe_desc spd = { - .pages = pages, - .nr_pages = 0, - .nr_pages_max = PIPE_DEF_BUFFERS, - .partial = partial, - .ops = &relay_pipe_buf_ops, - .spd_release = relay_page_release, - }; - ssize_t ret; - - if (rbuf->subbufs_produced == rbuf->subbufs_consumed) - return 0; - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; - - /* - * Adjust read len, if longer than what is available - */ - if (len > (subbuf_size - read_start % subbuf_size)) - len = subbuf_size - read_start % subbuf_size; - - subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT; - pidx = (read_start / PAGE_SIZE) % subbuf_pages; - poff = read_start & ~PAGE_MASK; - nr_pages = min_t(unsigned int, subbuf_pages, spd.nr_pages_max); - - for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) { - unsigned int this_len, this_end, private; - unsigned int cur_pos = read_start + total_len; - - if (!len) - break; - - this_len = min_t(unsigned long, len, PAGE_SIZE - poff); - private = this_len; - - spd.pages[spd.nr_pages] = rbuf->page_array[pidx]; - spd.partial[spd.nr_pages].offset = poff; - - this_end = cur_pos + this_len; - if (this_end >= nonpad_end) { - this_len = nonpad_end - cur_pos; - private = this_len + padding; - } - spd.partial[spd.nr_pages].len = this_len; - spd.partial[spd.nr_pages].private = private; - - len -= this_len; - total_len += this_len; - poff = 0; - pidx = (pidx + 1) % subbuf_pages; - - if (this_end >= nonpad_end) { - spd.nr_pages++; - break; - } - } - - ret = 0; - if (!spd.nr_pages) - goto out; - - ret = *nonpad_ret = splice_to_pipe(pipe, &spd); - if (ret < 0 || ret < total_len) - goto out; - - if (read_start + ret == nonpad_end) - ret += padding; - -out: - splice_shrink_spd(&spd); - return ret; -} - -static ssize_t relay_file_splice_read(struct file *in, - loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, - unsigned int flags) -{ - ssize_t spliced; - int ret; - int nonpad_ret = 0; - - ret = 0; - spliced = 0; - - while (len && !spliced) { - ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret); - if (ret < 0) - break; - else if (!ret) { - if (flags & SPLICE_F_NONBLOCK) - ret = -EAGAIN; - break; - } - - *ppos += ret; - if (ret > len) - len = 0; - else - len -= ret; - spliced += nonpad_ret; - nonpad_ret = 0; - } - - if (spliced) - return spliced; - - return ret; -} const struct file_operations relay_file_operations = { .open = relay_file_open, @@ -1242,6 +1081,5 @@ const struct file_operations relay_file_operations = { .read = relay_file_read, .llseek = no_llseek, .release = relay_file_release, - .splice_read = relay_file_splice_read, }; EXPORT_SYMBOL_GPL(relay_file_operations); diff --git a/kernel/resource.c b/kernel/resource.c index 91be1bc50..fcbca39db 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -27,6 +27,8 @@ #include #include #include +#include +#include #include @@ -429,6 +431,61 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, func); } +/* + * This function, being a variant of walk_system_ram_res(), calls the @func + * callback against all memory ranges of type System RAM which are marked as + * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from + * higher to lower. + */ +int walk_system_ram_res_rev(u64 start, u64 end, void *arg, + int (*func)(struct resource *, void *)) +{ + struct resource res, *rams; + int rams_size = 16, i; + unsigned long flags; + int ret = -1; + + /* create a list */ + rams = kvcalloc(rams_size, sizeof(struct resource), GFP_KERNEL); + if (!rams) + return ret; + + flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + i = 0; + while ((start < end) && + (!find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res))) { + if (i >= rams_size) { + /* re-alloc */ + struct resource *rams_new; + + rams_new = kvrealloc(rams, rams_size * sizeof(struct resource), + (rams_size + 16) * sizeof(struct resource), + GFP_KERNEL); + if (!rams_new) + goto out; + + rams = rams_new; + rams_size += 16; + } + + rams[i].start = res.start; + rams[i++].end = res.end; + + start = res.end + 1; + } + + /* go reverse */ + for (i--; i >= 0; i--) { + ret = (*func)(&rams[i], arg); + if (ret) + break; + } + +out: + kvfree(rams); + return ret; +} + /* * This function calls the @func callback against all memory ranges, which * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a708d225c..9116bcc90 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include @@ -1131,6 +1132,28 @@ static void wake_up_idle_cpu(int cpu) if (cpu == smp_processor_id()) return; + /* + * Set TIF_NEED_RESCHED and send an IPI if in the non-polling + * part of the idle loop. This forces an exit from the idle loop + * and a round trip to schedule(). Now this could be optimized + * because a simple new idle loop iteration is enough to + * re-evaluate the next tick. Provided some re-ordering of tick + * nohz functions that would need to follow TIF_NR_POLLING + * clearing: + * + * - On most archs, a simple fetch_or on ti::flags with a + * "0" value would be enough to know if an IPI needs to be sent. + * + * - x86 needs to perform a last need_resched() check between + * monitor and mwait which doesn't take timers into account. + * There a dedicated TIF_TIMER flag would be required to + * fetch_or here and be checked along with TIF_NEED_RESCHED + * before mwait(). + * + * However, remote timer enqueue is not such a frequent event + * and testing of the above solutions didn't appear to report + * much benefits. + */ if (set_nr_and_not_polling(rq->idle)) smp_send_reschedule(cpu); else @@ -2124,12 +2147,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags) enqueue_task(rq, p, flags); - p->on_rq = TASK_ON_RQ_QUEUED; + WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED); + ASSERT_EXCLUSIVE_WRITER(p->on_rq); } void deactivate_task(struct rq *rq, struct task_struct *p, int flags) { - p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING; + WRITE_ONCE(p->on_rq, (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING); + ASSERT_EXCLUSIVE_WRITER(p->on_rq); dequeue_task(rq, p, flags); } @@ -3795,6 +3820,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, rq->idle_stamp = 0; } #endif + + p->dl_server = NULL; } /* @@ -4509,10 +4536,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) memset(&p->stats, 0, sizeof(p->stats)); #endif - RB_CLEAR_NODE(&p->dl.rb_node); - init_dl_task_timer(&p->dl); - init_dl_inactive_task_timer(&p->dl); - __dl_clear_params(p); + init_dl_entity(&p->dl); INIT_LIST_HEAD(&p->rt.run_list); p->rt.timeout = 0; @@ -6004,12 +6028,27 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) p = pick_next_task_idle(rq); } + /* + * This is the fast path; it cannot be a DL server pick; + * therefore even if @p == @prev, ->dl_server must be NULL. + */ + if (p->dl_server) + p->dl_server = NULL; + return p; } restart: put_prev_task_balance(rq, prev, rf); + /* + * We've updated @prev and no longer need the server link, clear it. + * Must be done before ->pick_next_task() because that can (re)set + * ->dl_server. + */ + if (prev->dl_server) + prev->dl_server = NULL; + for_each_class(class) { p = class->pick_next_task(rq); if (p) @@ -7429,18 +7468,13 @@ int sched_core_idle_cpu(int cpu) * required to meet deadlines. */ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, - enum cpu_util_type type, - struct task_struct *p) + unsigned long *min, + unsigned long *max) { - unsigned long dl_util, util, irq, max; + unsigned long util, irq, scale; struct rq *rq = cpu_rq(cpu); - max = arch_scale_cpu_capacity(cpu); - - if (!uclamp_is_used() && - type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) { - return max; - } + scale = arch_scale_cpu_capacity(cpu); /* * Early check to see if IRQ/steal time saturates the CPU, can be @@ -7448,45 +7482,49 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, * update_irq_load_avg(). */ irq = cpu_util_irq(rq); - if (unlikely(irq >= max)) - return max; + if (unlikely(irq >= scale)) { + if (min) + *min = scale; + if (max) + *max = scale; + return scale; + } + + if (min) { + /* + * The minimum utilization returns the highest level between: + * - the computed DL bandwidth needed with the IRQ pressure which + * steals time to the deadline task. + * - The minimum performance requirement for CFS and/or RT. + */ + *min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN)); + + /* + * When an RT task is runnable and uclamp is not used, we must + * ensure that the task will run at maximum compute capacity. + */ + if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt)) + *min = max(*min, scale); + } /* * Because the time spend on RT/DL tasks is visible as 'lost' time to * CFS tasks and we use the same metric to track the effective * utilization (PELT windows are synchronized) we can directly add them * to obtain the CPU's actual utilization. - * - * CFS and RT utilization can be boosted or capped, depending on - * utilization clamp constraints requested by currently RUNNABLE - * tasks. - * When there are no CFS RUNNABLE tasks, clamps are released and - * frequency will be gracefully reduced with the utilization decay. */ util = util_cfs + cpu_util_rt(rq); - if (type == FREQUENCY_UTIL) - util = uclamp_rq_util_with(rq, util, p); - - dl_util = cpu_util_dl(rq); + util += cpu_util_dl(rq); /* - * For frequency selection we do not make cpu_util_dl() a permanent part - * of this sum because we want to use cpu_bw_dl() later on, but we need - * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such - * that we select f_max when there is no idle time. - * - * NOTE: numerical errors or stop class might cause us to not quite hit - * saturation when we should -- something for later. + * The maximum hint is a soft bandwidth requirement, which can be lower + * than the actual utilization because of uclamp_max requirements. */ - if (util + dl_util >= max) - return max; + if (max) + *max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX)); - /* - * OTOH, for energy computation we need the estimated running time, so - * include util_dl and ignore dl_bw. - */ - if (type == ENERGY_UTIL) - util += dl_util; + if (util >= scale) + return scale; /* * There is still idle time; further improve the number by using the @@ -7497,28 +7535,15 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, * U' = irq + --------- * U * max */ - util = scale_irq_capacity(util, irq, max); + util = scale_irq_capacity(util, irq, scale); util += irq; - /* - * Bandwidth required by DEADLINE must always be granted while, for - * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism - * to gracefully reduce the frequency when no tasks show up for longer - * periods of time. - * - * Ideally we would like to set bw_dl as min/guaranteed freq and util + - * bw_dl as requested freq. However, cpufreq is not yet ready for such - * an interface. So, we only do the latter for now. - */ - if (type == FREQUENCY_UTIL) - util += cpu_bw_dl(rq); - - return min(max, util); + return min(scale, util); } unsigned long sched_cpu_util(int cpu) { - return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL); + return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL); } #endif /* CONFIG_SMP */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 588817635..eece6244f 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -47,7 +47,7 @@ struct sugov_cpu { u64 last_update; unsigned long util; - unsigned long bw_dl; + unsigned long bw_min; /* The field below is for single-CPU policies only: */ #ifdef CONFIG_NO_HZ_COMMON @@ -114,6 +114,32 @@ static void sugov_deferred_update(struct sugov_policy *sg_policy) } } +/** + * get_capacity_ref_freq - get the reference frequency that has been used to + * correlate frequency and compute capacity for a given cpufreq policy. We use + * the CPU managing it for the arch_scale_freq_ref() call in the function. + * @policy: the cpufreq policy of the CPU in question. + * + * Return: the reference CPU frequency to compute a capacity. + */ +static __always_inline +unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy) +{ + unsigned int freq = arch_scale_freq_ref(policy->cpu); + + if (freq) + return freq; + + if (arch_scale_freq_invariant()) + return policy->cpuinfo.max_freq; + + /* + * Apply a 25% margin so that we select a higher frequency than + * the current one before the CPU is fully busy: + */ + return policy->cur + (policy->cur >> 2); +} + /** * get_next_freq - Compute a new frequency for a given cpufreq policy. * @sg_policy: schedutil policy object to compute the new frequency for. @@ -140,10 +166,9 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, unsigned long util, unsigned long max) { struct cpufreq_policy *policy = sg_policy->policy; - unsigned int freq = arch_scale_freq_invariant() ? - policy->cpuinfo.max_freq : policy->cur; + unsigned int freq; - util = map_util_perf(util); + freq = get_capacity_ref_freq(policy); freq = map_util_freq(util, freq, max); if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) @@ -153,14 +178,31 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, return cpufreq_driver_resolve_freq(policy, freq); } -static void sugov_get_util(struct sugov_cpu *sg_cpu) +unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual, + unsigned long min, + unsigned long max) +{ + /* Add dvfs headroom to actual utilization */ + actual = map_util_perf(actual); + /* Actually we don't need to target the max performance */ + if (actual < max) + max = actual; + + /* + * Ensure at least minimum performance while providing more compute + * capacity when possible. + */ + return max(min, max); +} + +static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost) { - unsigned long util = cpu_util_cfs_boost(sg_cpu->cpu); - struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu); - sg_cpu->bw_dl = cpu_bw_dl(rq); - sg_cpu->util = effective_cpu_util(sg_cpu->cpu, util, - FREQUENCY_UTIL, NULL); + util = effective_cpu_util(sg_cpu->cpu, util, &min, &max); + util = max(util, boost); + sg_cpu->bw_min = min; + sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max); } /** @@ -251,18 +293,16 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, * This mechanism is designed to boost high frequently IO waiting tasks, while * being more conservative on tasks which does sporadic IO operations. */ -static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, +static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, unsigned long max_cap) { - unsigned long boost; - /* No boost currently required */ if (!sg_cpu->iowait_boost) - return; + return 0; /* Reset boost if the CPU appears to have been idle enough */ if (sugov_iowait_reset(sg_cpu, time, false)) - return; + return 0; if (!sg_cpu->iowait_boost_pending) { /* @@ -271,7 +311,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, sg_cpu->iowait_boost >>= 1; if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) { sg_cpu->iowait_boost = 0; - return; + return 0; } } @@ -281,10 +321,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, * sg_cpu->util is already in capacity scale; convert iowait_boost * into the same scale so we can compare. */ - boost = (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT; - boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL); - if (sg_cpu->util < boost) - sg_cpu->util = boost; + return (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT; } #ifdef CONFIG_NO_HZ_COMMON @@ -306,7 +343,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } */ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu) { - if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) + if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min) sg_cpu->sg_policy->limits_changed = true; } @@ -314,6 +351,8 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu, u64 time, unsigned long max_cap, unsigned int flags) { + unsigned long boost; + sugov_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -322,8 +361,8 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu, if (!sugov_should_update_freq(sg_cpu->sg_policy, time)) return false; - sugov_get_util(sg_cpu); - sugov_iowait_apply(sg_cpu, time, max_cap); + boost = sugov_iowait_apply(sg_cpu, time, max_cap); + sugov_get_util(sg_cpu, boost); return true; } @@ -407,8 +446,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util) sg_cpu->util = prev_util; - cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), - map_util_perf(sg_cpu->util), max_cap); + cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min, + sg_cpu->util, max_cap); sg_cpu->sg_policy->last_freq_update_time = time; } @@ -424,9 +463,10 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) for_each_cpu(j, policy->cpus) { struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); + unsigned long boost; - sugov_get_util(j_sg_cpu); - sugov_iowait_apply(j_sg_cpu, time, max_cap); + boost = sugov_iowait_apply(j_sg_cpu, time, max_cap); + sugov_get_util(j_sg_cpu, boost); util = max(j_sg_cpu->util, util); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b28114478..a04a436af 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -54,8 +54,14 @@ static int __init sched_dl_sysctl_init(void) late_initcall(sched_dl_sysctl_init); #endif +static bool dl_server(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_server; +} + static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) { + BUG_ON(dl_server(dl_se)); return container_of(dl_se, struct task_struct, dl); } @@ -64,12 +70,19 @@ static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq) return container_of(dl_rq, struct rq, dl); } -static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se) +static inline struct rq *rq_of_dl_se(struct sched_dl_entity *dl_se) { - struct task_struct *p = dl_task_of(dl_se); - struct rq *rq = task_rq(p); + struct rq *rq = dl_se->rq; + + if (!dl_server(dl_se)) + rq = task_rq(dl_task_of(dl_se)); + + return rq; +} - return &rq->dl; +static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se) +{ + return &rq_of_dl_se(dl_se)->dl; } static inline int on_dl_rq(struct sched_dl_entity *dl_se) @@ -335,6 +348,8 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw) __add_rq_bw(new_bw, &rq->dl); } +static void __dl_clear_params(struct sched_dl_entity *dl_se); + /* * The utilization of a task cannot be immediately removed from * the rq active utilization (running_bw) when the task blocks. @@ -389,12 +404,11 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw) * up, and checks if the task is still in the "ACTIVE non contending" * state or not (in the second case, it updates running_bw). */ -static void task_non_contending(struct task_struct *p) +static void task_non_contending(struct sched_dl_entity *dl_se) { - struct sched_dl_entity *dl_se = &p->dl; struct hrtimer *timer = &dl_se->inactive_timer; - struct dl_rq *dl_rq = dl_rq_of_se(dl_se); - struct rq *rq = rq_of_dl_rq(dl_rq); + struct rq *rq = rq_of_dl_se(dl_se); + struct dl_rq *dl_rq = &rq->dl; s64 zerolag_time; /* @@ -424,24 +438,33 @@ static void task_non_contending(struct task_struct *p) * utilization now, instead of starting a timer */ if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) { - if (dl_task(p)) + if (dl_server(dl_se)) { sub_running_bw(dl_se, dl_rq); - if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) { - struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - - if (READ_ONCE(p->__state) == TASK_DEAD) - sub_rq_bw(&p->dl, &rq->dl); - raw_spin_lock(&dl_b->lock); - __dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); - raw_spin_unlock(&dl_b->lock); - __dl_clear_params(p); + } else { + struct task_struct *p = dl_task_of(dl_se); + + if (dl_task(p)) + sub_running_bw(dl_se, dl_rq); + + if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) { + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + if (READ_ONCE(p->__state) == TASK_DEAD) + sub_rq_bw(dl_se, &rq->dl); + raw_spin_lock(&dl_b->lock); + __dl_sub(dl_b, dl_se->dl_bw, dl_bw_cpus(task_cpu(p))); + raw_spin_unlock(&dl_b->lock); + __dl_clear_params(dl_se); + } } return; } dl_se->dl_non_contending = 1; - get_task_struct(p); + if (!dl_server(dl_se)) + get_task_struct(dl_task_of(dl_se)); + hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD); } @@ -468,8 +491,10 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags) * will not touch the rq's active utilization, * so we are still safe. */ - if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) - put_task_struct(dl_task_of(dl_se)); + if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) { + if (!dl_server(dl_se)) + put_task_struct(dl_task_of(dl_se)); + } } else { /* * Since "dl_non_contending" is not set, the @@ -482,10 +507,8 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags) } } -static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) +static inline int is_leftmost(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { - struct sched_dl_entity *dl_se = &p->dl; - return rb_first_cached(&dl_rq->root) == &dl_se->rb_node; } @@ -737,8 +760,10 @@ static inline void deadline_queue_pull_task(struct rq *rq) } #endif /* CONFIG_SMP */ +static void +enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags); static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags); -static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags); +static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags); static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags); static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se, @@ -986,8 +1011,7 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) */ static void update_dl_entity(struct sched_dl_entity *dl_se) { - struct dl_rq *dl_rq = dl_rq_of_se(dl_se); - struct rq *rq = rq_of_dl_rq(dl_rq); + struct rq *rq = rq_of_dl_se(dl_se); if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, rq_clock(rq))) { @@ -1018,11 +1042,11 @@ static inline u64 dl_next_period(struct sched_dl_entity *dl_se) * actually started or not (i.e., the replenishment instant is in * the future or in the past). */ -static int start_dl_timer(struct task_struct *p) +static int start_dl_timer(struct sched_dl_entity *dl_se) { - struct sched_dl_entity *dl_se = &p->dl; struct hrtimer *timer = &dl_se->dl_timer; - struct rq *rq = task_rq(p); + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); ktime_t now, act; s64 delta; @@ -1056,13 +1080,33 @@ static int start_dl_timer(struct task_struct *p) * and observe our state. */ if (!hrtimer_is_queued(timer)) { - get_task_struct(p); + if (!dl_server(dl_se)) + get_task_struct(dl_task_of(dl_se)); hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD); } return 1; } +static void __push_dl_task(struct rq *rq, struct rq_flags *rf) +{ +#ifdef CONFIG_SMP + /* + * Queueing this task back might have overloaded rq, check if we need + * to kick someone away. + */ + if (has_pushable_dl_tasks(rq)) { + /* + * Nothing relies on rq->lock after this, so its safe to drop + * rq->lock. + */ + rq_unpin_lock(rq, rf); + push_dl_task(rq); + rq_repin_lock(rq, rf); + } +#endif +} + /* * This is the bandwidth enforcement timer callback. If here, we know * a task is not on its dl_rq, since the fact that the timer was running @@ -1081,10 +1125,34 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) struct sched_dl_entity *dl_se = container_of(timer, struct sched_dl_entity, dl_timer); - struct task_struct *p = dl_task_of(dl_se); + struct task_struct *p; struct rq_flags rf; struct rq *rq; + if (dl_server(dl_se)) { + struct rq *rq = rq_of_dl_se(dl_se); + struct rq_flags rf; + + rq_lock(rq, &rf); + if (dl_se->dl_throttled) { + sched_clock_tick(); + update_rq_clock(rq); + + if (dl_se->server_has_tasks(dl_se)) { + enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH); + resched_curr(rq); + __push_dl_task(rq, &rf); + } else { + replenish_dl_entity(dl_se); + } + + } + rq_unlock(rq, &rf); + + return HRTIMER_NORESTART; + } + + p = dl_task_of(dl_se); rq = task_rq_lock(p, &rf); /* @@ -1155,21 +1223,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) else resched_curr(rq); -#ifdef CONFIG_SMP - /* - * Queueing this task back might have overloaded rq, check if we need - * to kick someone away. - */ - if (has_pushable_dl_tasks(rq)) { - /* - * Nothing relies on rq->lock after this, so its safe to drop - * rq->lock. - */ - rq_unpin_lock(rq, &rf); - push_dl_task(rq); - rq_repin_lock(rq, &rf); - } -#endif + __push_dl_task(rq, &rf); unlock: task_rq_unlock(rq, p, &rf); @@ -1183,7 +1237,7 @@ unlock: return HRTIMER_NORESTART; } -void init_dl_task_timer(struct sched_dl_entity *dl_se) +static void init_dl_task_timer(struct sched_dl_entity *dl_se) { struct hrtimer *timer = &dl_se->dl_timer; @@ -1211,12 +1265,11 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) */ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) { - struct task_struct *p = dl_task_of(dl_se); - struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se)); + struct rq *rq = rq_of_dl_se(dl_se); if (dl_time_before(dl_se->deadline, rq_clock(rq)) && dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { - if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) return; dl_se->dl_throttled = 1; if (dl_se->runtime > 0) @@ -1267,44 +1320,19 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se) return (delta * u_act) >> BW_SHIFT; } -/* - * Update the current task's runtime statistics (provided it is still - * a -deadline task and has not been removed from the dl_rq). - */ -static void update_curr_dl(struct rq *rq) +static inline void +update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, + int flags); +static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec) { - struct task_struct *curr = rq->curr; - struct sched_dl_entity *dl_se = &curr->dl; - u64 delta_exec, scaled_delta_exec; - int cpu = cpu_of(rq); - u64 now; - - if (!dl_task(curr) || !on_dl_rq(dl_se)) - return; + s64 scaled_delta_exec; - /* - * Consumed budget is computed considering the time as - * observed by schedulable tasks (excluding time spent - * in hardirq context, etc.). Deadlines are instead - * computed using hard walltime. This seems to be the more - * natural solution, but the full ramifications of this - * approach need further study. - */ - now = rq_clock_task(rq); - delta_exec = now - curr->se.exec_start; - if (unlikely((s64)delta_exec <= 0)) { + if (unlikely(delta_exec <= 0)) { if (unlikely(dl_se->dl_yielded)) goto throttle; return; } - schedstat_set(curr->stats.exec_max, - max(curr->stats.exec_max, delta_exec)); - - trace_sched_stat_runtime(curr, delta_exec, 0); - - update_current_exec_runtime(curr, now, delta_exec); - if (dl_entity_is_special(dl_se)) return; @@ -1316,10 +1344,9 @@ static void update_curr_dl(struct rq *rq) * according to current frequency and CPU maximum capacity. */ if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) { - scaled_delta_exec = grub_reclaim(delta_exec, - rq, - &curr->dl); + scaled_delta_exec = grub_reclaim(delta_exec, rq, dl_se); } else { + int cpu = cpu_of(rq); unsigned long scale_freq = arch_scale_freq_capacity(cpu); unsigned long scale_cpu = arch_scale_cpu_capacity(cpu); @@ -1338,11 +1365,20 @@ throttle: (dl_se->flags & SCHED_FLAG_DL_OVERRUN)) dl_se->dl_overrun = 1; - __dequeue_task_dl(rq, curr, 0); - if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr))) - enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); + dequeue_dl_entity(dl_se, 0); + if (!dl_server(dl_se)) { + update_stats_dequeue_dl(&rq->dl, dl_se, 0); + dequeue_pushable_dl_task(rq, dl_task_of(dl_se)); + } + + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) { + if (dl_server(dl_se)) + enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH); + else + enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH); + } - if (!is_leftmost(curr, &rq->dl)) + if (!is_leftmost(dl_se, &rq->dl)) resched_curr(rq); } @@ -1372,20 +1408,82 @@ throttle: } } +void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) +{ + update_curr_dl_se(dl_se->rq, dl_se, delta_exec); +} + +void dl_server_start(struct sched_dl_entity *dl_se) +{ + if (!dl_server(dl_se)) { + dl_se->dl_server = 1; + setup_new_dl_entity(dl_se); + } + enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP); +} + +void dl_server_stop(struct sched_dl_entity *dl_se) +{ + dequeue_dl_entity(dl_se, DEQUEUE_SLEEP); +} + +void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, + dl_server_has_tasks_f has_tasks, + dl_server_pick_f pick) +{ + dl_se->rq = rq; + dl_se->server_has_tasks = has_tasks; + dl_se->server_pick = pick; +} + +/* + * Update the current task's runtime statistics (provided it is still + * a -deadline task and has not been removed from the dl_rq). + */ +static void update_curr_dl(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct sched_dl_entity *dl_se = &curr->dl; + s64 delta_exec; + + if (!dl_task(curr) || !on_dl_rq(dl_se)) + return; + + /* + * Consumed budget is computed considering the time as + * observed by schedulable tasks (excluding time spent + * in hardirq context, etc.). Deadlines are instead + * computed using hard walltime. This seems to be the more + * natural solution, but the full ramifications of this + * approach need further study. + */ + delta_exec = update_curr_common(rq); + update_curr_dl_se(rq, dl_se, delta_exec); +} + static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer) { struct sched_dl_entity *dl_se = container_of(timer, struct sched_dl_entity, inactive_timer); - struct task_struct *p = dl_task_of(dl_se); + struct task_struct *p = NULL; struct rq_flags rf; struct rq *rq; - rq = task_rq_lock(p, &rf); + if (!dl_server(dl_se)) { + p = dl_task_of(dl_se); + rq = task_rq_lock(p, &rf); + } else { + rq = dl_se->rq; + rq_lock(rq, &rf); + } sched_clock_tick(); update_rq_clock(rq); + if (dl_server(dl_se)) + goto no_task; + if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) { struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); @@ -1398,23 +1496,30 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer) raw_spin_lock(&dl_b->lock); __dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); raw_spin_unlock(&dl_b->lock); - __dl_clear_params(p); + __dl_clear_params(dl_se); goto unlock; } + +no_task: if (dl_se->dl_non_contending == 0) goto unlock; sub_running_bw(dl_se, &rq->dl); dl_se->dl_non_contending = 0; unlock: - task_rq_unlock(rq, p, &rf); - put_task_struct(p); + + if (!dl_server(dl_se)) { + task_rq_unlock(rq, p, &rf); + put_task_struct(p); + } else { + rq_unlock(rq, &rf); + } return HRTIMER_NORESTART; } -void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) +static void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) { struct hrtimer *timer = &dl_se->inactive_timer; @@ -1472,10 +1577,8 @@ static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {} static inline void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { - int prio = dl_task_of(dl_se)->prio; u64 deadline = dl_se->deadline; - WARN_ON(!dl_prio(prio)); dl_rq->dl_nr_running++; add_nr_running(rq_of_dl_rq(dl_rq), 1); @@ -1485,9 +1588,6 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) static inline void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { - int prio = dl_task_of(dl_se)->prio; - - WARN_ON(!dl_prio(prio)); WARN_ON(!dl_rq->dl_nr_running); dl_rq->dl_nr_running--; sub_nr_running(rq_of_dl_rq(dl_rq), 1); @@ -1608,6 +1708,41 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags); + /* + * Check if a constrained deadline task was activated + * after the deadline but before the next period. + * If that is the case, the task will be throttled and + * the replenishment timer will be set to the next period. + */ + if (!dl_se->dl_throttled && !dl_is_implicit(dl_se)) + dl_check_constrained_dl(dl_se); + + if (flags & (ENQUEUE_RESTORE|ENQUEUE_MIGRATING)) { + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + add_rq_bw(dl_se, dl_rq); + add_running_bw(dl_se, dl_rq); + } + + /* + * If p is throttled, we do not enqueue it. In fact, if it exhausted + * its budget it needs a replenishment and, since it now is on + * its rq, the bandwidth timer callback (which clearly has not + * run yet) will take care of this. + * However, the active utilization does not depend on the fact + * that the task is on the runqueue or not (but depends on the + * task's state - in GRUB parlance, "inactive" vs "active contending"). + * In other words, even if a task is throttled its utilization must + * be counted in the active utilization; hence, we need to call + * add_running_bw(). + */ + if (dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) { + if (flags & ENQUEUE_WAKEUP) + task_contending(dl_se, flags); + + return; + } + /* * If this is a wakeup or a new instance, the scheduling * parameters of the task might need updating. Otherwise, @@ -1619,17 +1754,35 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) } else if (flags & ENQUEUE_REPLENISH) { replenish_dl_entity(dl_se); } else if ((flags & ENQUEUE_RESTORE) && - dl_time_before(dl_se->deadline, - rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) { + dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) { setup_new_dl_entity(dl_se); } __enqueue_dl_entity(dl_se); } -static void dequeue_dl_entity(struct sched_dl_entity *dl_se) +static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags) { __dequeue_dl_entity(dl_se); + + if (flags & (DEQUEUE_SAVE|DEQUEUE_MIGRATING)) { + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + sub_running_bw(dl_se, dl_rq); + sub_rq_bw(dl_se, dl_rq); + } + + /* + * This check allows to start the inactive timer (or to immediately + * decrease the active utilization, if needed) in two cases: + * when the task blocks and when it is terminating + * (p->state == TASK_DEAD). We can handle the two cases in the same + * way, because from GRUB's point of view the same thing is happening + * (the task moves from "active contending" to "active non contending" + * or "inactive") + */ + if (flags & DEQUEUE_SLEEP) + task_non_contending(dl_se); } static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) @@ -1674,76 +1827,31 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } - /* - * Check if a constrained deadline task was activated - * after the deadline but before the next period. - * If that is the case, the task will be throttled and - * the replenishment timer will be set to the next period. - */ - if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl)) - dl_check_constrained_dl(&p->dl); - - if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) { - add_rq_bw(&p->dl, &rq->dl); - add_running_bw(&p->dl, &rq->dl); - } - - /* - * If p is throttled, we do not enqueue it. In fact, if it exhausted - * its budget it needs a replenishment and, since it now is on - * its rq, the bandwidth timer callback (which clearly has not - * run yet) will take care of this. - * However, the active utilization does not depend on the fact - * that the task is on the runqueue or not (but depends on the - * task's state - in GRUB parlance, "inactive" vs "active contending"). - * In other words, even if a task is throttled its utilization must - * be counted in the active utilization; hence, we need to call - * add_running_bw(). - */ - if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) { - if (flags & ENQUEUE_WAKEUP) - task_contending(&p->dl, flags); - - return; - } - check_schedstat_required(); update_stats_wait_start_dl(dl_rq_of_se(&p->dl), &p->dl); + if (p->on_rq == TASK_ON_RQ_MIGRATING) + flags |= ENQUEUE_MIGRATING; + enqueue_dl_entity(&p->dl, flags); - if (!task_current(rq, p) && p->nr_cpus_allowed > 1) - enqueue_pushable_dl_task(rq, p); -} + if (dl_server(&p->dl)) + return; -static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) -{ - update_stats_dequeue_dl(&rq->dl, &p->dl, flags); - dequeue_dl_entity(&p->dl); - dequeue_pushable_dl_task(rq, p); + if (!task_current(rq, p) && !p->dl.dl_throttled && p->nr_cpus_allowed > 1) + enqueue_pushable_dl_task(rq, p); } static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_curr_dl(rq); - __dequeue_task_dl(rq, p, flags); - if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) { - sub_running_bw(&p->dl, &rq->dl); - sub_rq_bw(&p->dl, &rq->dl); - } + if (p->on_rq == TASK_ON_RQ_MIGRATING) + flags |= DEQUEUE_MIGRATING; - /* - * This check allows to start the inactive timer (or to immediately - * decrease the active utilization, if needed) in two cases: - * when the task blocks and when it is terminating - * (p->state == TASK_DEAD). We can handle the two cases in the same - * way, because from GRUB's point of view the same thing is happening - * (the task moves from "active contending" to "active non contending" - * or "inactive") - */ - if (flags & DEQUEUE_SLEEP) - task_non_contending(p); + dequeue_dl_entity(&p->dl, flags); + if (!p->dl.dl_throttled && !dl_server(&p->dl)) + dequeue_pushable_dl_task(rq, p); } /* @@ -1933,12 +2041,12 @@ static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, } #ifdef CONFIG_SCHED_HRTICK -static void start_hrtick_dl(struct rq *rq, struct task_struct *p) +static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se) { - hrtick_start(rq, p->dl.runtime); + hrtick_start(rq, dl_se->runtime); } #else /* !CONFIG_SCHED_HRTICK */ -static void start_hrtick_dl(struct rq *rq, struct task_struct *p) +static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se) { } #endif @@ -1958,9 +2066,6 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first) if (!first) return; - if (hrtick_enabled_dl(rq)) - start_hrtick_dl(rq, p); - if (rq->curr->sched_class != &dl_sched_class) update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); @@ -1983,12 +2088,25 @@ static struct task_struct *pick_task_dl(struct rq *rq) struct dl_rq *dl_rq = &rq->dl; struct task_struct *p; +again: if (!sched_dl_runnable(rq)) return NULL; dl_se = pick_next_dl_entity(dl_rq); WARN_ON_ONCE(!dl_se); - p = dl_task_of(dl_se); + + if (dl_server(dl_se)) { + p = dl_se->server_pick(dl_se); + if (!p) { + WARN_ON_ONCE(1); + dl_se->dl_yielded = 1; + update_curr_dl_se(rq, dl_se, 0); + goto again; + } + p->dl_server = dl_se; + } else { + p = dl_task_of(dl_se); + } return p; } @@ -1998,9 +2116,15 @@ static struct task_struct *pick_next_task_dl(struct rq *rq) struct task_struct *p; p = pick_task_dl(rq); - if (p) + if (!p) + return p; + + if (!p->dl_server) set_next_task_dl(rq, p, true); + if (hrtick_enabled(rq)) + start_hrtick_dl(rq, &p->dl); + return p; } @@ -2038,8 +2162,8 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) * be set and schedule() will start a new hrtick for the next task. */ if (hrtick_enabled_dl(rq) && queued && p->dl.runtime > 0 && - is_leftmost(p, &rq->dl)) - start_hrtick_dl(rq, p); + is_leftmost(&p->dl, &rq->dl)) + start_hrtick_dl(rq, &p->dl); } static void task_fork_dl(struct task_struct *p) @@ -2558,7 +2682,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) * will reset the task parameters. */ if (task_on_rq_queued(p) && p->dl.dl_runtime) - task_non_contending(p); + task_non_contending(&p->dl); /* * In case a task is setscheduled out from SCHED_DEADLINE we need to @@ -2966,10 +3090,8 @@ bool __checkparam_dl(const struct sched_attr *attr) /* * This function clears the sched_dl_entity static params. */ -void __dl_clear_params(struct task_struct *p) +static void __dl_clear_params(struct sched_dl_entity *dl_se) { - struct sched_dl_entity *dl_se = &p->dl; - dl_se->dl_runtime = 0; dl_se->dl_deadline = 0; dl_se->dl_period = 0; @@ -2981,12 +3103,21 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_yielded = 0; dl_se->dl_non_contending = 0; dl_se->dl_overrun = 0; + dl_se->dl_server = 0; #ifdef CONFIG_RT_MUTEXES dl_se->pi_se = dl_se; #endif } +void init_dl_entity(struct sched_dl_entity *dl_se) +{ + RB_CLEAR_NODE(&dl_se->rb_node); + init_dl_task_timer(dl_se); + init_dl_inactive_task_timer(dl_se); + __dl_clear_params(dl_se); +} + bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) { struct sched_dl_entity *dl_se = &p->dl; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 4580a4507..8d5d98a58 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -628,8 +628,8 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) { - s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread; - struct sched_entity *last, *first; + s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread; + struct sched_entity *last, *first, *root; struct rq *rq = cpu_rq(cpu); unsigned long flags; @@ -644,15 +644,20 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SPLIT_NS(cfs_rq->exec_clock)); raw_spin_rq_lock_irqsave(rq, flags); + root = __pick_root_entity(cfs_rq); + if (root) + left_vruntime = root->min_vruntime; first = __pick_first_entity(cfs_rq); if (first) - left_vruntime = first->vruntime; + left_deadline = first->deadline; last = __pick_last_entity(cfs_rq); if (last) right_vruntime = last->vruntime; min_vruntime = cfs_rq->min_vruntime; raw_spin_rq_unlock_irqrestore(rq, flags); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline", + SPLIT_NS(left_deadline)); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime", SPLIT_NS(left_vruntime)); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime", @@ -679,8 +684,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cfs_rq->avg.runnable_avg); SEQ_printf(m, " .%-30s: %lu\n", "util_avg", cfs_rq->avg.util_avg); - SEQ_printf(m, " .%-30s: %u\n", "util_est_enqueued", - cfs_rq->avg.util_est.enqueued); + SEQ_printf(m, " .%-30s: %u\n", "util_est", + cfs_rq->avg.util_est); SEQ_printf(m, " .%-30s: %ld\n", "removed.load_avg", cfs_rq->removed.load_avg); SEQ_printf(m, " .%-30s: %ld\n", "removed.util_avg", @@ -1070,8 +1075,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(se.avg.runnable_avg); P(se.avg.util_avg); P(se.avg.last_update_time); - P(se.avg.util_est.ewma); - PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED); + PM(se.avg.util_est, ~UTIL_AVG_UNCHANGED); #endif #ifdef CONFIG_UCLAMP_TASK __PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c43b71792..aee5e7a70 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -551,7 +551,11 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) static inline bool entity_before(const struct sched_entity *a, const struct sched_entity *b) { - return (s64)(a->vruntime - b->vruntime) < 0; + /* + * Tiebreak on vruntime seems unnecessary since it can + * hardly happen. + */ + return (s64)(a->deadline - b->deadline) < 0; } static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -692,15 +696,21 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * * XXX could add max_slice to the augmented data to track this. */ -static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) +static s64 entity_lag(u64 avruntime, struct sched_entity *se) { - s64 lag, limit; + s64 vlag, limit; + + vlag = avruntime - se->vruntime; + limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + return clamp(vlag, -limit, limit); +} + +static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ SCHED_WARN_ON(!se->on_rq); - lag = avg_vruntime(cfs_rq) - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); - se->vlag = clamp(lag, -limit, limit); + se->vlag = entity_lag(avg_vruntime(cfs_rq), se); } /* @@ -720,7 +730,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) * Note: using 'avg_vruntime() > se->vruntime' is inacurate due * to the loss in precision caused by the division. */ -int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) +static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) { struct sched_entity *curr = cfs_rq->curr; s64 avg = cfs_rq->avg_vruntime; @@ -733,7 +743,12 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) load += weight; } - return avg >= entity_key(cfs_rq, se) * load; + return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load; +} + +int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + return vruntime_eligible(cfs_rq, se->vruntime); } static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime) @@ -752,9 +767,8 @@ static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime) static void update_min_vruntime(struct cfs_rq *cfs_rq) { - struct sched_entity *se = __pick_first_entity(cfs_rq); + struct sched_entity *se = __pick_root_entity(cfs_rq); struct sched_entity *curr = cfs_rq->curr; - u64 vruntime = cfs_rq->min_vruntime; if (curr) { @@ -766,9 +780,9 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) if (se) { if (!curr) - vruntime = se->vruntime; + vruntime = se->min_vruntime; else - vruntime = min_vruntime(vruntime, se->vruntime); + vruntime = min_vruntime(vruntime, se->min_vruntime); } /* ensure we never gain time by being placed backwards. */ @@ -781,34 +795,34 @@ static inline bool __entity_less(struct rb_node *a, const struct rb_node *b) return entity_before(__node_2_se(a), __node_2_se(b)); } -#define deadline_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; }) +#define vruntime_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; }) -static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node) +static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node *node) { if (node) { struct sched_entity *rse = __node_2_se(node); - if (deadline_gt(min_deadline, se, rse)) - se->min_deadline = rse->min_deadline; + if (vruntime_gt(min_vruntime, se, rse)) + se->min_vruntime = rse->min_vruntime; } } /* - * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline) + * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime) */ -static inline bool min_deadline_update(struct sched_entity *se, bool exit) +static inline bool min_vruntime_update(struct sched_entity *se, bool exit) { - u64 old_min_deadline = se->min_deadline; + u64 old_min_vruntime = se->min_vruntime; struct rb_node *node = &se->run_node; - se->min_deadline = se->deadline; - __update_min_deadline(se, node->rb_right); - __update_min_deadline(se, node->rb_left); + se->min_vruntime = se->vruntime; + __min_vruntime_update(se, node->rb_right); + __min_vruntime_update(se, node->rb_left); - return se->min_deadline == old_min_deadline; + return se->min_vruntime == old_min_vruntime; } -RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity, - run_node, min_deadline, min_deadline_update); +RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, + run_node, min_vruntime, min_vruntime_update); /* * Enqueue an entity into the rb-tree: @@ -816,18 +830,28 @@ RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity, static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { avg_vruntime_add(cfs_rq, se); - se->min_deadline = se->deadline; + se->min_vruntime = se->vruntime; rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, - __entity_less, &min_deadline_cb); + __entity_less, &min_vruntime_cb); } static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, - &min_deadline_cb); + &min_vruntime_cb); avg_vruntime_sub(cfs_rq, se); } +struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq) +{ + struct rb_node *root = cfs_rq->tasks_timeline.rb_root.rb_node; + + if (!root) + return NULL; + + return __node_2_se(root); +} + struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) { struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline); @@ -850,23 +874,29 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) * with the earliest virtual deadline. * * We can do this in O(log n) time due to an augmented RB-tree. The - * tree keeps the entries sorted on service, but also functions as a - * heap based on the deadline by keeping: + * tree keeps the entries sorted on deadline, but also functions as a + * heap based on the vruntime by keeping: * - * se->min_deadline = min(se->deadline, se->{left,right}->min_deadline) + * se->min_vruntime = min(se->vruntime, se->{left,right}->min_vruntime) * - * Which allows an EDF like search on (sub)trees. + * Which allows tree pruning through eligibility. */ -static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq) +static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) { struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node; + struct sched_entity *se = __pick_first_entity(cfs_rq); struct sched_entity *curr = cfs_rq->curr; struct sched_entity *best = NULL; - struct sched_entity *best_left = NULL; + + /* + * We can safely skip eligibility check if there is only one entity + * in this cfs_rq, saving some cycles. + */ + if (cfs_rq->nr_running == 1) + return curr && curr->on_rq ? curr : se; if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr))) curr = NULL; - best = curr; /* * Once selected, run a task until it either becomes non-eligible or @@ -875,95 +905,45 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq) if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline) return curr; + /* Pick the leftmost entity if it's eligible */ + if (se && entity_eligible(cfs_rq, se)) { + best = se; + goto found; + } + + /* Heap search for the EEVD entity */ while (node) { - struct sched_entity *se = __node_2_se(node); + struct rb_node *left = node->rb_left; /* - * If this entity is not eligible, try the left subtree. + * Eligible entities in left subtree are always better + * choices, since they have earlier deadlines. */ - if (!entity_eligible(cfs_rq, se)) { - node = node->rb_left; + if (left && vruntime_eligible(cfs_rq, + __node_2_se(left)->min_vruntime)) { + node = left; continue; } - /* - * Now we heap search eligible trees for the best (min_)deadline - */ - if (!best || deadline_gt(deadline, best, se)) - best = se; + se = __node_2_se(node); /* - * Every se in a left branch is eligible, keep track of the - * branch with the best min_deadline + * The left subtree either is empty or has no eligible + * entity, so check the current node since it is the one + * with earliest deadline that might be eligible. */ - if (node->rb_left) { - struct sched_entity *left = __node_2_se(node->rb_left); - - if (!best_left || deadline_gt(min_deadline, best_left, left)) - best_left = left; - - /* - * min_deadline is in the left branch. rb_left and all - * descendants are eligible, so immediately switch to the second - * loop. - */ - if (left->min_deadline == se->min_deadline) - break; - } - - /* min_deadline is at this node, no need to look right */ - if (se->deadline == se->min_deadline) + if (entity_eligible(cfs_rq, se)) { + best = se; break; - - /* else min_deadline is in the right branch. */ - node = node->rb_right; - } - - /* - * We ran into an eligible node which is itself the best. - * (Or nr_running == 0 and both are NULL) - */ - if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0) - return best; - - /* - * Now best_left and all of its children are eligible, and we are just - * looking for deadline == min_deadline - */ - node = &best_left->run_node; - while (node) { - struct sched_entity *se = __node_2_se(node); - - /* min_deadline is the current node */ - if (se->deadline == se->min_deadline) - return se; - - /* min_deadline is in the left branch */ - if (node->rb_left && - __node_2_se(node->rb_left)->min_deadline == se->min_deadline) { - node = node->rb_left; - continue; } - /* else min_deadline is in the right branch */ node = node->rb_right; } - return NULL; -} - -static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) -{ - struct sched_entity *se = __pick_eevdf(cfs_rq); - - if (!se) { - struct sched_entity *left = __pick_first_entity(cfs_rq); - if (left) { - pr_err("EEVDF scheduling fail, picking leftmost\n"); - return left; - } - } +found: + if (!best || (curr && entity_before(curr, best))) + best = curr; - return se; + return best; } #ifdef CONFIG_SCHED_DEBUG @@ -1129,23 +1109,17 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq) } #endif /* CONFIG_SMP */ -/* - * Update the current task's runtime statistics. - */ -static void update_curr(struct cfs_rq *cfs_rq) +static s64 update_curr_se(struct rq *rq, struct sched_entity *curr) { - struct sched_entity *curr = cfs_rq->curr; - u64 now = rq_clock_task(rq_of(cfs_rq)); - u64 delta_exec; - - if (unlikely(!curr)) - return; + u64 now = rq_clock_task(rq); + s64 delta_exec; delta_exec = now - curr->exec_start; - if (unlikely((s64)delta_exec <= 0)) - return; + if (unlikely(delta_exec <= 0)) + return delta_exec; curr->exec_start = now; + curr->sum_exec_runtime += delta_exec; if (schedstat_enabled()) { struct sched_statistics *stats; @@ -1155,20 +1129,54 @@ static void update_curr(struct cfs_rq *cfs_rq) max(delta_exec, stats->exec_max)); } - curr->sum_exec_runtime += delta_exec; - schedstat_add(cfs_rq->exec_clock, delta_exec); + return delta_exec; +} + +static inline void update_curr_task(struct task_struct *p, s64 delta_exec) +{ + trace_sched_stat_runtime(p, delta_exec); + account_group_exec_runtime(p, delta_exec); + cgroup_account_cputime(p, delta_exec); + if (p->dl_server) + dl_server_update(p->dl_server, delta_exec); +} + +/* + * Used by other classes to account runtime. + */ +s64 update_curr_common(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + s64 delta_exec; + + delta_exec = update_curr_se(rq, &curr->se); + if (likely(delta_exec > 0)) + update_curr_task(curr, delta_exec); + + return delta_exec; +} + +/* + * Update the current task's runtime statistics. + */ +static void update_curr(struct cfs_rq *cfs_rq) +{ + struct sched_entity *curr = cfs_rq->curr; + s64 delta_exec; + + if (unlikely(!curr)) + return; + + delta_exec = update_curr_se(rq_of(cfs_rq), curr); + if (unlikely(delta_exec <= 0)) + return; curr->vruntime += calc_delta_fair(delta_exec, curr); update_deadline(cfs_rq, curr); update_min_vruntime(cfs_rq); - if (entity_is_task(curr)) { - struct task_struct *curtask = task_of(curr); - - trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime); - cgroup_account_cputime(curtask, delta_exec); - account_group_exec_runtime(curtask, delta_exec); - } + if (entity_is_task(curr)) + update_curr_task(task_of(curr), delta_exec); account_cfs_rq_runtime(cfs_rq, delta_exec); } @@ -3668,11 +3676,10 @@ static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif -static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, +static void reweight_eevdf(struct sched_entity *se, u64 avruntime, unsigned long weight) { unsigned long old_weight = se->load.weight; - u64 avruntime = avg_vruntime(cfs_rq); s64 vlag, vslice; /* @@ -3753,7 +3760,7 @@ static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, * = V - vl' */ if (avruntime != se->vruntime) { - vlag = (s64)(avruntime - se->vruntime); + vlag = entity_lag(avruntime, se); vlag = div_s64(vlag * old_weight, weight); se->vruntime = avruntime - vlag; } @@ -3779,25 +3786,26 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { bool curr = cfs_rq->curr == se; + u64 avruntime; if (se->on_rq) { /* commit outstanding execution time */ - if (curr) - update_curr(cfs_rq); - else + update_curr(cfs_rq); + avruntime = avg_vruntime(cfs_rq); + if (!curr) __dequeue_entity(cfs_rq, se); update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - if (!se->on_rq) { + if (se->on_rq) { + reweight_eevdf(se, avruntime, weight); + } else { /* * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), * we need to scale se->vlag when w_i changes. */ se->vlag = div_s64(se->vlag * se->load.weight, weight); - } else { - reweight_eevdf(cfs_rq, se, weight); } update_load_set(&se->load, weight); @@ -4821,11 +4829,14 @@ static inline unsigned long task_util(struct task_struct *p) return READ_ONCE(p->se.avg.util_avg); } -static inline unsigned long _task_util_est(struct task_struct *p) +static inline unsigned long task_runnable(struct task_struct *p) { - struct util_est ue = READ_ONCE(p->se.avg.util_est); + return READ_ONCE(p->se.avg.runnable_avg); +} - return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED)); +static inline unsigned long _task_util_est(struct task_struct *p) +{ + return READ_ONCE(p->se.avg.util_est) & ~UTIL_AVG_UNCHANGED; } static inline unsigned long task_util_est(struct task_struct *p) @@ -4842,9 +4853,9 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq, return; /* Update root cfs_rq's estimated utilization */ - enqueued = cfs_rq->avg.util_est.enqueued; + enqueued = cfs_rq->avg.util_est; enqueued += _task_util_est(p); - WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued); + WRITE_ONCE(cfs_rq->avg.util_est, enqueued); trace_sched_util_est_cfs_tp(cfs_rq); } @@ -4858,34 +4869,20 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq, return; /* Update root cfs_rq's estimated utilization */ - enqueued = cfs_rq->avg.util_est.enqueued; + enqueued = cfs_rq->avg.util_est; enqueued -= min_t(unsigned int, enqueued, _task_util_est(p)); - WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued); + WRITE_ONCE(cfs_rq->avg.util_est, enqueued); trace_sched_util_est_cfs_tp(cfs_rq); } #define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) -/* - * Check if a (signed) value is within a specified (unsigned) margin, - * based on the observation that: - * - * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) - * - * NOTE: this only works when value + margin < INT_MAX. - */ -static inline bool within_margin(int value, int margin) -{ - return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); -} - static inline void util_est_update(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) { - long last_ewma_diff, last_enqueued_diff; - struct util_est ue; + unsigned int ewma, dequeued, last_ewma_diff; if (!sched_feat(UTIL_EST)) return; @@ -4897,71 +4894,73 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, if (!task_sleep) return; + /* Get current estimate of utilization */ + ewma = READ_ONCE(p->se.avg.util_est); + /* * If the PELT values haven't changed since enqueue time, * skip the util_est update. */ - ue = p->se.avg.util_est; - if (ue.enqueued & UTIL_AVG_UNCHANGED) + if (ewma & UTIL_AVG_UNCHANGED) return; - last_enqueued_diff = ue.enqueued; + /* Get utilization at dequeue */ + dequeued = task_util(p); /* * Reset EWMA on utilization increases, the moving average is used only * to smooth utilization decreases. */ - ue.enqueued = task_util(p); - if (sched_feat(UTIL_EST_FASTUP)) { - if (ue.ewma < ue.enqueued) { - ue.ewma = ue.enqueued; - goto done; - } + if (ewma <= dequeued) { + ewma = dequeued; + goto done; } /* * Skip update of task's estimated utilization when its members are * already ~1% close to its last activation value. */ - last_ewma_diff = ue.enqueued - ue.ewma; - last_enqueued_diff -= ue.enqueued; - if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) { - if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN)) - goto done; - - return; - } + last_ewma_diff = ewma - dequeued; + if (last_ewma_diff < UTIL_EST_MARGIN) + goto done; /* * To avoid overestimation of actual task utilization, skip updates if * we cannot grant there is idle time in this CPU. */ - if (task_util(p) > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)))) + if (dequeued > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)))) return; + /* + * To avoid underestimate of task utilization, skip updates of EWMA if + * we cannot grant that thread got all CPU time it wanted. + */ + if ((dequeued + UTIL_EST_MARGIN) < task_runnable(p)) + goto done; + + /* * Update Task's estimated utilization * * When *p completes an activation we can consolidate another sample - * of the task size. This is done by storing the current PELT value - * as ue.enqueued and by using this value to update the Exponential - * Weighted Moving Average (EWMA): + * of the task size. This is done by using this value to update the + * Exponential Weighted Moving Average (EWMA): * * ewma(t) = w * task_util(p) + (1-w) * ewma(t-1) * = w * task_util(p) + ewma(t-1) - w * ewma(t-1) * = w * (task_util(p) - ewma(t-1)) + ewma(t-1) - * = w * ( last_ewma_diff ) + ewma(t-1) - * = w * (last_ewma_diff + ewma(t-1) / w) + * = w * ( -last_ewma_diff ) + ewma(t-1) + * = w * (-last_ewma_diff + ewma(t-1) / w) * * Where 'w' is the weight of new samples, which is configured to be * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT) */ - ue.ewma <<= UTIL_EST_WEIGHT_SHIFT; - ue.ewma += last_ewma_diff; - ue.ewma >>= UTIL_EST_WEIGHT_SHIFT; + ewma <<= UTIL_EST_WEIGHT_SHIFT; + ewma -= last_ewma_diff; + ewma >>= UTIL_EST_WEIGHT_SHIFT; done: - ue.enqueued |= UTIL_AVG_UNCHANGED; - WRITE_ONCE(p->se.avg.util_est, ue); + ewma |= UTIL_AVG_UNCHANGED; + WRITE_ONCE(p->se.avg.util_est, ewma); trace_sched_util_est_se_tp(&p->se); } @@ -7695,16 +7694,16 @@ cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost) if (sched_feat(UTIL_EST)) { unsigned long util_est; - util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued); + util_est = READ_ONCE(cfs_rq->avg.util_est); /* * During wake-up @p isn't enqueued yet and doesn't contribute - * to any cpu_rq(cpu)->cfs.avg.util_est.enqueued. + * to any cpu_rq(cpu)->cfs.avg.util_est. * If @dst_cpu == @cpu add it to "simulate" cpu_util after @p * has been enqueued. * * During exec (@dst_cpu = -1) @p is enqueued and does - * contribute to cpu_rq(cpu)->cfs.util_est.enqueued. + * contribute to cpu_rq(cpu)->cfs.util_est. * Remove it to "simulate" cpu_util without @p's contribution. * * Despite the task_on_rq_queued(@p) check there is still a @@ -7833,7 +7832,7 @@ static inline void eenv_pd_busy_time(struct energy_env *eenv, for_each_cpu(cpu, pd_cpus) { unsigned long util = cpu_util(cpu, p, -1, 0); - busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL); + busy_time += effective_cpu_util(cpu, util, NULL, NULL); } eenv->pd_busy_time = min(eenv->pd_cap, busy_time); @@ -7856,7 +7855,7 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus, for_each_cpu(cpu, pd_cpus) { struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL; unsigned long util = cpu_util(cpu, p, dst_cpu, 1); - unsigned long eff_util; + unsigned long eff_util, min, max; /* * Performance domain frequency: utilization clamping @@ -7865,7 +7864,23 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus, * NOTE: in case RT tasks are running, by default the * FREQUENCY_UTIL's utilization can be max OPP. */ - eff_util = effective_cpu_util(cpu, util, FREQUENCY_UTIL, tsk); + eff_util = effective_cpu_util(cpu, util, &min, &max); + + /* Task's uclamp can modify min and max value */ + if (tsk && uclamp_is_used()) { + min = max(min, uclamp_eff_value(p, UCLAMP_MIN)); + + /* + * If there is no active max uclamp constraint, + * directly use task's one, otherwise keep max. + */ + if (uclamp_rq_is_idle(cpu_rq(cpu))) + max = uclamp_eff_value(p, UCLAMP_MAX); + else + max = max(max, uclamp_eff_value(p, UCLAMP_MAX)); + } + + eff_util = sugov_effective_cpu_perf(cpu, eff_util, min, max); max_util = max(max_util, eff_util); } @@ -8267,7 +8282,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int struct task_struct *curr = rq->curr; struct sched_entity *se = &curr->se, *pse = &p->se; struct cfs_rq *cfs_rq = task_cfs_rq(curr); - int next_buddy_marked = 0; int cse_is_idle, pse_is_idle; if (unlikely(se == pse)) @@ -8284,7 +8298,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) { set_next_buddy(pse); - next_buddy_marked = 1; } /* @@ -9117,7 +9130,7 @@ static int detach_tasks(struct lb_env *env) case migrate_util: util = task_util_est(p); - if (util > env->imbalance) + if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance) goto next; env->imbalance -= util; @@ -13096,19 +13109,6 @@ next_cpu: return 0; } -#else /* CONFIG_FAIR_GROUP_SCHED */ - -void free_fair_sched_group(struct task_group *tg) { } - -int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) -{ - return 1; -} - -void online_fair_sched_group(struct task_group *tg) { } - -void unregister_fair_sched_group(struct task_group *tg) { } - #endif /* CONFIG_FAIR_GROUP_SCHED */ diff --git a/kernel/sched/features.h b/kernel/sched/features.h index a3ddf84de..143f55df8 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -83,7 +83,6 @@ SCHED_FEAT(WA_BIAS, true) * UtilEstimation. Use estimated CPU utilization. */ SCHED_FEAT(UTIL_EST, true) -SCHED_FEAT(UTIL_EST_FASTUP, true) SCHED_FEAT(LATENCY_WARN, false) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 565f8374d..31231925f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -258,6 +258,36 @@ static void do_idle(void) while (!need_resched()) { rmb(); + /* + * Interrupts shouldn't be re-enabled from that point on until + * the CPU sleeping instruction is reached. Otherwise an interrupt + * may fire and queue a timer that would be ignored until the CPU + * wakes from the sleeping instruction. And testing need_resched() + * doesn't tell about pending needed timer reprogram. + * + * Several cases to consider: + * + * - SLEEP-UNTIL-PENDING-INTERRUPT based instructions such as + * "wfi" or "mwait" are fine because they can be entered with + * interrupt disabled. + * + * - sti;mwait() couple is fine because the interrupts are + * re-enabled only upon the execution of mwait, leaving no gap + * in-between. + * + * - ROLLBACK based idle handlers with the sleeping instruction + * called with interrupts enabled are NOT fine. In this scheme + * when the interrupt detects it has interrupted an idle handler, + * it rolls back to its beginning which performs the + * need_resched() check before re-executing the sleeping + * instruction. This can leak a pending needed timer reprogram. + * If such a scheme is really mandatory due to the lack of an + * appropriate CPU sleeping instruction, then a FAST-FORWARD + * must instead be applied: when the interrupt detects it has + * interrupted an idle handler, it must resume to the end of + * this idle handler so that the generic idle loop is iterated + * again to reprogram the tick. + */ local_irq_disable(); if (cpu_is_offline(cpu)) { diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 3a0e0dc28..9e1083465 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -52,13 +52,13 @@ static inline void cfs_se_util_change(struct sched_avg *avg) return; /* Avoid store if the flag has been already reset */ - enqueued = avg->util_est.enqueued; + enqueued = avg->util_est; if (!(enqueued & UTIL_AVG_UNCHANGED)) return; /* Reset flag to report util_avg has been updated */ enqueued &= ~UTIL_AVG_UNCHANGED; - WRITE_ONCE(avg->util_est.enqueued, enqueued); + WRITE_ONCE(avg->util_est, enqueued); } static inline u64 rq_clock_pelt(struct rq *rq) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 6aaf0a3d6..3261b067b 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1002,24 +1002,15 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; - u64 delta_exec; - u64 now; + s64 delta_exec; if (curr->sched_class != &rt_sched_class) return; - now = rq_clock_task(rq); - delta_exec = now - curr->se.exec_start; - if (unlikely((s64)delta_exec <= 0)) + delta_exec = update_curr_common(rq); + if (unlikely(delta_exec <= 0)) return; - schedstat_set(curr->stats.exec_max, - max(curr->stats.exec_max, delta_exec)); - - trace_sched_stat_runtime(curr, delta_exec, 0); - - update_current_exec_runtime(curr, now, delta_exec); - if (!rt_bandwidth_enabled()) return; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2e5a95486..8c817d0a9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -79,6 +79,8 @@ # include #endif +#include + #include "cpupri.h" #include "cpudeadline.h" @@ -273,8 +275,6 @@ struct rt_bandwidth { unsigned int rt_period_active; }; -void __dl_clear_params(struct task_struct *p); - static inline int dl_bandwidth_enabled(void) { return sysctl_sched_rt_runtime >= 0; @@ -315,6 +315,33 @@ extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *att extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int dl_bw_check_overflow(int cpu); +/* + * SCHED_DEADLINE supports servers (nested scheduling) with the following + * interface: + * + * dl_se::rq -- runqueue we belong to. + * + * dl_se::server_has_tasks() -- used on bandwidth enforcement; we 'stop' the + * server when it runs out of tasks to run. + * + * dl_se::server_pick() -- nested pick_next_task(); we yield the period if this + * returns NULL. + * + * dl_server_update() -- called from update_curr_common(), propagates runtime + * to the server. + * + * dl_server_start() + * dl_server_stop() -- start/stop the server when it has (no) tasks. + * + * dl_server_init() -- initializes the server. + */ +extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec); +extern void dl_server_start(struct sched_dl_entity *dl_se); +extern void dl_server_stop(struct sched_dl_entity *dl_se); +extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, + dl_server_has_tasks_f has_tasks, + dl_server_pick_f pick); + #ifdef CONFIG_CGROUP_SCHED struct cfs_rq; @@ -436,10 +463,21 @@ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) extern int tg_nop(struct task_group *tg, void *data); +#ifdef CONFIG_FAIR_GROUP_SCHED extern void free_fair_sched_group(struct task_group *tg); extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent); extern void online_fair_sched_group(struct task_group *tg); extern void unregister_fair_sched_group(struct task_group *tg); +#else +static inline void free_fair_sched_group(struct task_group *tg) { } +static inline int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} +static inline void online_fair_sched_group(struct task_group *tg) { } +static inline void unregister_fair_sched_group(struct task_group *tg) { } +#endif + extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, struct sched_entity *se, int cpu, struct sched_entity *parent); @@ -2179,6 +2217,10 @@ extern const u32 sched_prio_to_wmult[40]; * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location * in the runqueue. * + * NOCLOCK - skip the update_rq_clock() (avoids double updates) + * + * MIGRATION - p->on_rq == TASK_ON_RQ_MIGRATING (used for DEADLINE) + * * ENQUEUE_HEAD - place at front of runqueue (tail if not specified) * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline) * ENQUEUE_MIGRATED - the task was migrated during wakeup @@ -2189,6 +2231,7 @@ extern const u32 sched_prio_to_wmult[40]; #define DEQUEUE_SAVE 0x02 /* Matches ENQUEUE_RESTORE */ #define DEQUEUE_MOVE 0x04 /* Matches ENQUEUE_MOVE */ #define DEQUEUE_NOCLOCK 0x08 /* Matches ENQUEUE_NOCLOCK */ +#define DEQUEUE_MIGRATING 0x100 /* Matches ENQUEUE_MIGRATING */ #define ENQUEUE_WAKEUP 0x01 #define ENQUEUE_RESTORE 0x02 @@ -2203,6 +2246,7 @@ extern const u32 sched_prio_to_wmult[40]; #define ENQUEUE_MIGRATED 0x00 #endif #define ENQUEUE_INITIAL 0x80 +#define ENQUEUE_MIGRATING 0x100 #define RETRY_TASK ((void *)-1UL) @@ -2212,6 +2256,8 @@ struct affinity_context { unsigned int flags; }; +extern s64 update_curr_common(struct rq *rq); + struct sched_class { #ifdef CONFIG_UCLAMP_TASK @@ -2425,8 +2471,7 @@ extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); -extern void init_dl_task_timer(struct sched_dl_entity *dl_se); -extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se); +extern void init_dl_entity(struct sched_dl_entity *dl_se); #define BW_SHIFT 20 #define BW_UNIT (1 << BW_SHIFT) @@ -2822,6 +2867,7 @@ DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq, double_rq_lock(_T->lock, _T->lock2), double_rq_unlock(_T->lock, _T->lock2)) +extern struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq); extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq); extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq); @@ -2961,24 +3007,14 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif #ifdef CONFIG_SMP -/** - * enum cpu_util_type - CPU utilization type - * @FREQUENCY_UTIL: Utilization used to select frequency - * @ENERGY_UTIL: Utilization used during energy calculation - * - * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time - * need to be aggregated differently depending on the usage made of them. This - * enum is used within effective_cpu_util() to differentiate the types of - * utilization expected by the callers, and adjust the aggregation accordingly. - */ -enum cpu_util_type { - FREQUENCY_UTIL, - ENERGY_UTIL, -}; - unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, - enum cpu_util_type type, - struct task_struct *p); + unsigned long *min, + unsigned long *max); + +unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual, + unsigned long min, + unsigned long max); + /* * Verify the fitness of task @p to run on @cpu taking into account the @@ -3035,59 +3071,6 @@ static inline bool uclamp_rq_is_idle(struct rq *rq) return rq->uclamp_flags & UCLAMP_FLAG_IDLE; } -/** - * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values. - * @rq: The rq to clamp against. Must not be NULL. - * @util: The util value to clamp. - * @p: The task to clamp against. Can be NULL if you want to clamp - * against @rq only. - * - * Clamps the passed @util to the max(@rq, @p) effective uclamp values. - * - * If sched_uclamp_used static key is disabled, then just return the util - * without any clamping since uclamp aggregation at the rq level in the fast - * path is disabled, rendering this operation a NOP. - * - * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It - * will return the correct effective uclamp value of the task even if the - * static key is disabled. - */ -static __always_inline -unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, - struct task_struct *p) -{ - unsigned long min_util = 0; - unsigned long max_util = 0; - - if (!static_branch_likely(&sched_uclamp_used)) - return util; - - if (p) { - min_util = uclamp_eff_value(p, UCLAMP_MIN); - max_util = uclamp_eff_value(p, UCLAMP_MAX); - - /* - * Ignore last runnable task's max clamp, as this task will - * reset it. Similarly, no need to read the rq's min clamp. - */ - if (uclamp_rq_is_idle(rq)) - goto out; - } - - min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN)); - max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX)); -out: - /* - * Since CPU's {min,max}_util clamps are MAX aggregated considering - * RUNNABLE tasks with _different_ clamps, we can end up with an - * inversion. Fix it now when the clamps are applied. - */ - if (unlikely(min_util >= max_util)) - return min_util; - - return clamp(util, min_util, max_util); -} - /* Is the rq being capped/throttled by uclamp_max? */ static inline bool uclamp_rq_is_capped(struct rq *rq) { @@ -3125,13 +3108,6 @@ static inline unsigned long uclamp_eff_value(struct task_struct *p, return SCHED_CAPACITY_SCALE; } -static inline -unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, - struct task_struct *p) -{ - return util; -} - static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; } static inline bool uclamp_is_used(void) @@ -3261,16 +3237,6 @@ extern int sched_dynamic_mode(const char *str); extern void sched_dynamic_update(int mode); #endif -static inline void update_current_exec_runtime(struct task_struct *curr, - u64 now, u64 delta_exec) -{ - curr->se.sum_exec_runtime += delta_exec; - account_group_exec_runtime(curr, delta_exec); - - curr->se.exec_start = now; - cgroup_account_cputime(curr, delta_exec); -} - #ifdef CONFIG_SCHED_MM_CID #define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */ @@ -3481,13 +3447,19 @@ static inline void switch_mm_cid(struct rq *rq, * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu]. * Provide it here. */ - if (!prev->mm) // from kernel + if (!prev->mm) { // from kernel smp_mb(); - /* - * user -> user transition guarantees a memory barrier through - * switch_mm() when current->mm changes. If current->mm is - * unchanged, no barrier is needed. - */ + } else { // from user + /* + * user->user transition relies on an implicit + * memory barrier in switch_mm() when + * current->mm changes. If the architecture + * switch_mm() does not have an implicit memory + * barrier, it is emitted here. If current->mm + * is unchanged, no barrier is needed. + */ + smp_mb__after_switch_mm(); + } } if (prev->mm_cid_active) { mm_cid_snapshot_time(rq, prev->mm); diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 6cf7304e6..b1b8fe61c 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -70,18 +70,7 @@ static void yield_task_stop(struct rq *rq) static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) { - struct task_struct *curr = rq->curr; - u64 now, delta_exec; - - now = rq_clock_task(rq); - delta_exec = now - curr->se.exec_start; - if (unlikely((s64)delta_exec < 0)) - delta_exec = 0; - - schedstat_set(curr->stats.exec_max, - max(curr->stats.exec_max, delta_exec)); - - update_current_exec_runtime(curr, now, delta_exec); + update_curr_common(rq); } /* diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 255999ba9..aca7b4378 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1072,7 +1072,7 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn */ list_del_init(&addfd->list); if (!addfd->setfd) - fd = receive_fd(addfd->file, addfd->flags); + fd = receive_fd(addfd->file, NULL, addfd->flags); else fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags); addfd->ret = fd; diff --git a/kernel/signal.c b/kernel/signal.c index 47a7602df..c9c57d053 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -171,16 +171,6 @@ static bool recalc_sigpending_tsk(struct task_struct *t) return false; } -/* - * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up. - * This is superfluous when called on current, the wakeup is a harmless no-op. - */ -void recalc_sigpending_and_wake(struct task_struct *t) -{ - if (recalc_sigpending_tsk(t)) - signal_wake_up(t, 0); -} - void recalc_sigpending(void) { if (!recalc_sigpending_tsk(current) && !freezing(current)) @@ -1348,10 +1338,8 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, action->sa.sa_handler = SIG_DFL; if (handler == HANDLER_EXIT) action->sa.sa_flags |= SA_IMMUTABLE; - if (blocked) { + if (blocked) sigdelset(&t->blocked, sig); - recalc_sigpending_and_wake(t); - } } /* * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect @@ -1361,6 +1349,9 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, (!t->ptrace || (handler == HANDLER_EXIT))) t->signal->flags &= ~SIGNAL_UNKILLABLE; ret = send_signal_locked(sig, info, t, PIDTYPE_PID); + /* This can happen if the signal was already pending and blocked */ + if (!task_sigpending(t)) + signal_wake_up(t, 0); spin_unlock_irqrestore(&t->sighand->siglock, flags); return ret; @@ -1376,12 +1367,12 @@ int force_sig_info(struct kernel_siginfo *info) */ int zap_other_threads(struct task_struct *p) { - struct task_struct *t = p; + struct task_struct *t; int count = 0; p->signal->group_stop_count = 0; - while_each_thread(p, t) { + for_other_threads(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); /* Don't require de_thread to wait for the vhost_worker */ if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER) @@ -2465,12 +2456,10 @@ static bool do_signal_stop(int signr) sig->group_exit_code = signr; sig->group_stop_count = 0; - if (task_set_jobctl_pending(current, signr | gstop)) sig->group_stop_count++; - t = current; - while_each_thread(current, t) { + for_other_threads(current, t) { /* * Setting state to TASK_STOPPED for a group * stop is always done with the siglock held, @@ -2966,8 +2955,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) if (sigisemptyset(&retarget)) return; - t = tsk; - while_each_thread(tsk, t) { + for_other_threads(tsk, t) { if (t->flags & PF_EXITING) continue; diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 4f6582487..afb3c116d 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -126,7 +126,7 @@ EXPORT_SYMBOL_GPL(stack_trace_save); /** * stack_trace_save_tsk - Save a task stack trace into a storage array - * @task: The task to examine + * @tsk: The task to examine * @store: Pointer to storage array * @size: Size of the storage array * @skipnr: Number of entries to skip at the start of the stack trace diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 9a846439b..faad00cce 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -171,6 +171,9 @@ COND_SYSCALL(landlock_add_rule); COND_SYSCALL(landlock_restrict_self); COND_SYSCALL(fadvise64_64); COND_SYSCALL_COMPAT(fadvise64_64); +COND_SYSCALL(lsm_get_self_attr); +COND_SYSCALL(lsm_set_self_attr); +COND_SYSCALL(lsm_list_modules); /* CONFIG_MMU only */ COND_SYSCALL(swapon); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 649f2b48e..481b7ab65 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -56,7 +56,6 @@ extern int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force); extern void clockevents_handle_noop(struct clock_event_device *dev); extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); -extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); /* Broadcasting support */ # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST @@ -197,3 +196,5 @@ void hrtimers_resume_local(void); #else #define JIFFIES_SHIFT 8 #endif + +extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index ca2d59579..01fb50c1b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -839,6 +839,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) ts->next_timer = next_tick; } + /* Make sure next_tick is never before basemono! */ + if (WARN_ON_ONCE(basemono > next_tick)) + next_tick = basemono; + /* * If the tick is due in the next period, keep it ticking or * force prod the timer. @@ -887,7 +891,6 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); u64 basemono = ts->timer_expires_base; u64 expires = ts->timer_expires; - ktime_t tick = expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; @@ -910,7 +913,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) /* Skip reprogram of event if it's not changed */ if (ts->tick_stopped && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ - if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) + if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; WARN_ON_ONCE(1); @@ -920,11 +923,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) } /* - * nohz_stop_sched_tick() can be called several times before - * nohz_restart_sched_tick() is called. This happens when - * interrupts arrive which do not cause a reschedule. In the - * first call we save the current tick time, so we can restart - * the scheduler tick in nohz_restart_sched_tick(). + * tick_nohz_stop_tick() can be called several times before + * tick_nohz_restart_sched_tick() is called. This happens when + * interrupts arrive which do not cause a reschedule. In the first + * call we save the current tick time, so we can restart the + * scheduler tick in tick_nohz_restart_sched_tick(). */ if (!ts->tick_stopped) { calc_load_nohz_start(); @@ -935,7 +938,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) trace_tick_stop(1, TICK_DEP_MASK_NONE); } - ts->next_tick = tick; + ts->next_tick = expires; /* * If the expiration time == KTIME_MAX, then we simply stop @@ -950,11 +953,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) } if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start(&ts->sched_timer, tick, + hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED_HARD); } else { - hrtimer_set_expires(&ts->sched_timer, tick); - tick_program_event(tick, 1); + hrtimer_set_expires(&ts->sched_timer, expires); + tick_program_event(expires, 1); } } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 63a8ce717..352b16111 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -571,18 +571,15 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk, static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { - if (!is_timers_nohz_active()) - return; - /* - * TODO: This wants some optimizing similar to the code below, but we - * will do that when we switch from push to pull for deferrable timers. + * Deferrable timers do not prevent the CPU from entering dynticks and + * are not taken into account on the idle/nohz_full path. An IPI when a + * new deferrable timer is enqueued will wake up the remote CPU but + * nothing will be done with the deferrable timer base. Therefore skip + * the remote IPI for deferrable timers completely. */ - if (timer->flags & TIMER_DEFERRABLE) { - if (tick_nohz_full_cpu(base->cpu)) - wake_up_nohz_cpu(base->cpu); + if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE) return; - } /* * We might have to IPI the remote CPU if the base is idle and the @@ -606,7 +603,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); - trace_timer_start(timer, timer->expires, timer->flags); + trace_timer_start(timer, bucket_expiry); /* * Check whether this is the new first expiring timer. The @@ -942,31 +939,34 @@ get_target_base(struct timer_base *base, unsigned tflags) return get_timer_this_cpu_base(tflags); } -static inline void forward_timer_base(struct timer_base *base) +static inline void __forward_timer_base(struct timer_base *base, + unsigned long basej) { - unsigned long jnow = READ_ONCE(jiffies); - /* - * No need to forward if we are close enough below jiffies. - * Also while executing timers, base->clk is 1 offset ahead - * of jiffies to avoid endless requeuing to current jiffies. + * Check whether we can forward the base. We can only do that when + * @basej is past base->clk otherwise we might rewind base->clk. */ - if ((long)(jnow - base->clk) < 1) + if (time_before_eq(basej, base->clk)) return; /* * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ - if (time_after(base->next_expiry, jnow)) { - base->clk = jnow; + if (time_after(base->next_expiry, basej)) { + base->clk = basej; } else { if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) return; base->clk = base->next_expiry; } + } +static inline void forward_timer_base(struct timer_base *base) +{ + __forward_timer_base(base, READ_ONCE(jiffies)); +} /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means @@ -1803,8 +1803,10 @@ static int next_pending_bucket(struct timer_base *base, unsigned offset, /* * Search the first expiring timer in the various clock levels. Caller must * hold base->lock. + * + * Store next expiry time in base->next_expiry. */ -static unsigned long __next_timer_interrupt(struct timer_base *base) +static void next_expiry_recalc(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; @@ -1870,10 +1872,9 @@ static unsigned long __next_timer_interrupt(struct timer_base *base) clk += adj; } + base->next_expiry = next; base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); - - return next; } #ifdef CONFIG_NO_HZ_COMMON @@ -1921,8 +1922,9 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA; u64 expires = KTIME_MAX; - unsigned long nextevt; + bool was_idle; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1933,37 +1935,44 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) raw_spin_lock(&base->lock); if (base->next_expiry_recalc) - base->next_expiry = __next_timer_interrupt(base); - nextevt = base->next_expiry; + next_expiry_recalc(base); /* * We have a fresh next event. Check whether we can forward the - * base. We can only do that when @basej is past base->clk - * otherwise we might rewind base->clk. + * base. */ - if (time_after(basej, base->clk)) { - if (time_after(nextevt, basej)) - base->clk = basej; - else if (time_after(nextevt, base->clk)) - base->clk = nextevt; - } + __forward_timer_base(base, basej); - if (time_before_eq(nextevt, basej)) { - expires = basem; - base->is_idle = false; + if (base->timers_pending) { + nextevt = base->next_expiry; + + /* If we missed a tick already, force 0 delta */ + if (time_before(nextevt, basej)) + nextevt = basej; + expires = basem + (u64)(nextevt - basej) * TICK_NSEC; } else { - if (base->timers_pending) - expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* - * If we expect to sleep more than a tick, mark the base idle. - * Also the tick is stopped so any added timer must forward - * the base clk itself to keep granularity small. This idle - * logic is only maintained for the BASE_STD base, deferrable - * timers may still see large granularity skew (by design). + * Move next_expiry for the empty base into the future to + * prevent a unnecessary raise of the timer softirq when the + * next_expiry value will be reached even if there is no timer + * pending. */ - if ((expires - basem) > TICK_NSEC) - base->is_idle = true; + base->next_expiry = nextevt; } + + /* + * Base is idle if the next event is more than a tick away. + * + * If the base is marked idle then any timer add operation must forward + * the base clk itself to keep granularity small. This idle logic is + * only maintained for the BASE_STD base, deferrable timers may still + * see large granularity skew (by design). + */ + was_idle = base->is_idle; + base->is_idle = time_after(nextevt, basej + 1); + if (was_idle != base->is_idle) + trace_timer_base_idle(base->is_idle, base->cpu); + raw_spin_unlock(&base->lock); return cmp_next_hrtimer_event(basem, expires); @@ -1984,7 +1993,10 @@ void timer_clear_idle(void) * sending the IPI a few instructions smaller for the cost of taking * the lock in the exit from idle path. */ - base->is_idle = false; + if (base->is_idle) { + base->is_idle = false; + trace_timer_base_idle(false, smp_processor_id()); + } } #endif @@ -2015,8 +2027,12 @@ static inline void __run_timers(struct timer_base *base) */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); + /* + * While executing timers, base->clk is set 1 offset ahead of + * jiffies to avoid endless requeuing to current jiffies. + */ base->clk++; - base->next_expiry = __next_timer_interrupt(base); + next_expiry_recalc(base); while (levels--) expire_timers(base, heads + levels); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 652c40a14..c8d1ebc43 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -24,6 +24,7 @@ #include #include #include +#include #include @@ -1379,6 +1380,8 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, struct bpf_dynptr_kern *sig_ptr, struct bpf_key *trusted_keyring) { + const void *data, *sig; + u32 data_len, sig_len; int ret; if (trusted_keyring->has_ref) { @@ -1395,10 +1398,12 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, return ret; } - return verify_pkcs7_signature(data_ptr->data, - __bpf_dynptr_size(data_ptr), - sig_ptr->data, - __bpf_dynptr_size(sig_ptr), + data_len = __bpf_dynptr_size(data_ptr); + data = __bpf_dynptr_data(data_ptr, data_len); + sig_len = __bpf_dynptr_size(sig_ptr); + sig = __bpf_dynptr_data(sig_ptr, sig_len); + + return verify_pkcs7_signature(data, data_len, sig, sig_len, trusted_keyring->key, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); @@ -1430,6 +1435,72 @@ static int __init bpf_key_sig_kfuncs_init(void) late_initcall(bpf_key_sig_kfuncs_init); #endif /* CONFIG_KEYS */ +/* filesystem kfuncs */ +__bpf_kfunc_start_defs(); + +/** + * bpf_get_file_xattr - get xattr of a file + * @file: file to get xattr from + * @name__str: name of the xattr + * @value_ptr: output buffer of the xattr value + * + * Get xattr *name__str* of *file* and store the output in *value_ptr*. + * + * For security reasons, only *name__str* with prefix "user." is allowed. + * + * Return: 0 on success, a negative value on error. + */ +__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str, + struct bpf_dynptr_kern *value_ptr) +{ + struct dentry *dentry; + u32 value_len; + void *value; + int ret; + + if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) + return -EPERM; + + value_len = __bpf_dynptr_size(value_ptr); + value = __bpf_dynptr_data_rw(value_ptr, value_len); + if (!value) + return -EINVAL; + + dentry = file_dentry(file); + ret = inode_permission(&nop_mnt_idmap, dentry->d_inode, MAY_READ); + if (ret) + return ret; + return __vfs_getxattr(dentry, dentry->d_inode, name__str, value, value_len); +} + +__bpf_kfunc_end_defs(); + +BTF_SET8_START(fs_kfunc_set_ids) +BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS) +BTF_SET8_END(fs_kfunc_set_ids) + +static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id) +{ + if (!btf_id_set8_contains(&fs_kfunc_set_ids, kfunc_id)) + return 0; + + /* Only allow to attach from LSM hooks, to avoid recursion */ + return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0; +} + +static const struct btf_kfunc_id_set bpf_fs_kfunc_set = { + .owner = THIS_MODULE, + .set = &fs_kfunc_set_ids, + .filter = bpf_get_file_xattr_filter, +}; + +static int __init bpf_fs_kfuncs_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set); +} + +late_initcall(bpf_fs_kfuncs_init); + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -2642,7 +2713,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, - .dealloc = bpf_kprobe_multi_link_dealloc, + .dealloc_deferred = bpf_kprobe_multi_link_dealloc, .fill_link_info = bpf_kprobe_multi_link_fill_link_info, }; @@ -3034,6 +3105,7 @@ struct bpf_uprobe_multi_link; struct bpf_uprobe { struct bpf_uprobe_multi_link *link; loff_t offset; + unsigned long ref_ctr_offset; u64 cookie; struct uprobe_consumer consumer; }; @@ -3042,6 +3114,7 @@ struct bpf_uprobe_multi_link { struct path path; struct bpf_link link; u32 cnt; + u32 flags; struct bpf_uprobe *uprobes; struct task_struct *task; }; @@ -3069,6 +3142,9 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link) umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt); + if (umulti_link->task) + put_task_struct(umulti_link->task); + path_put(&umulti_link->path); } static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) @@ -3076,16 +3152,83 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); - if (umulti_link->task) - put_task_struct(umulti_link->task); - path_put(&umulti_link->path); kvfree(umulti_link->uprobes); kfree(umulti_link); } +static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + u64 __user *uref_ctr_offsets = u64_to_user_ptr(info->uprobe_multi.ref_ctr_offsets); + u64 __user *ucookies = u64_to_user_ptr(info->uprobe_multi.cookies); + u64 __user *uoffsets = u64_to_user_ptr(info->uprobe_multi.offsets); + u64 __user *upath = u64_to_user_ptr(info->uprobe_multi.path); + u32 upath_size = info->uprobe_multi.path_size; + struct bpf_uprobe_multi_link *umulti_link; + u32 ucount = info->uprobe_multi.count; + int err = 0, i; + long left; + + if (!upath ^ !upath_size) + return -EINVAL; + + if ((uoffsets || uref_ctr_offsets || ucookies) && !ucount) + return -EINVAL; + + umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); + info->uprobe_multi.count = umulti_link->cnt; + info->uprobe_multi.flags = umulti_link->flags; + info->uprobe_multi.pid = umulti_link->task ? + task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0; + + if (upath) { + char *p, *buf; + + upath_size = min_t(u32, upath_size, PATH_MAX); + + buf = kmalloc(upath_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = d_path(&umulti_link->path, buf, upath_size); + if (IS_ERR(p)) { + kfree(buf); + return PTR_ERR(p); + } + upath_size = buf + upath_size - p; + left = copy_to_user(upath, p, upath_size); + kfree(buf); + if (left) + return -EFAULT; + info->uprobe_multi.path_size = upath_size; + } + + if (!uoffsets && !ucookies && !uref_ctr_offsets) + return 0; + + if (ucount < umulti_link->cnt) + err = -ENOSPC; + else + ucount = umulti_link->cnt; + + for (i = 0; i < ucount; i++) { + if (uoffsets && + put_user(umulti_link->uprobes[i].offset, uoffsets + i)) + return -EFAULT; + if (uref_ctr_offsets && + put_user(umulti_link->uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) + return -EFAULT; + if (ucookies && + put_user(umulti_link->uprobes[i].cookie, ucookies + i)) + return -EFAULT; + } + + return err; +} + static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { .release = bpf_uprobe_multi_link_release, - .dealloc = bpf_uprobe_multi_link_dealloc, + .dealloc_deferred = bpf_uprobe_multi_link_dealloc, + .fill_link_info = bpf_uprobe_multi_link_fill_link_info, }; static int uprobe_prog_run(struct bpf_uprobe *uprobe, @@ -3173,7 +3316,6 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr { struct bpf_uprobe_multi_link *link = NULL; unsigned long __user *uref_ctr_offsets; - unsigned long *ref_ctr_offsets = NULL; struct bpf_link_primer link_primer; struct bpf_uprobe *uprobes = NULL; struct task_struct *task = NULL; @@ -3248,22 +3390,20 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (!uprobes || !link) goto error_free; - if (uref_ctr_offsets) { - ref_ctr_offsets = kvcalloc(cnt, sizeof(*ref_ctr_offsets), GFP_KERNEL); - if (!ref_ctr_offsets) - goto error_free; - } - for (i = 0; i < cnt; i++) { - if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) { + if (__get_user(uprobes[i].offset, uoffsets + i)) { err = -EFAULT; goto error_free; } - if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) { + if (uprobes[i].offset < 0) { + err = -EINVAL; + goto error_free; + } + if (uref_ctr_offsets && __get_user(uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) { err = -EFAULT; goto error_free; } - if (__get_user(uprobes[i].offset, uoffsets + i)) { + if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) { err = -EFAULT; goto error_free; } @@ -3283,6 +3423,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr link->uprobes = uprobes; link->path = path; link->task = task; + link->flags = flags; bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI, &bpf_uprobe_multi_link_lops, prog); @@ -3290,7 +3431,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr for (i = 0; i < cnt; i++) { err = uprobe_register_refctr(d_real_inode(link->path.dentry), uprobes[i].offset, - ref_ctr_offsets ? ref_ctr_offsets[i] : 0, + uprobes[i].ref_ctr_offset, &uprobes[i].consumer); if (err) { bpf_uprobe_unregister(&path, uprobes, i); @@ -3302,11 +3443,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (err) goto error_free; - kvfree(ref_ctr_offsets); return bpf_link_settle(&link_primer); error_free: - kvfree(ref_ctr_offsets); kvfree(uprobes); kfree(link); if (task) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 140f8eed8..faf56d9a9 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -27,6 +27,7 @@ #include #include +#include #include /* @@ -317,6 +318,11 @@ struct buffer_data_page { unsigned char data[] RB_ALIGN_DATA; /* data of buffer page */ }; +struct buffer_data_read_page { + unsigned order; /* order of the page */ + struct buffer_data_page *data; /* actual data, stored in this page */ +}; + /* * Note, the buffer_page list must be first. The buffer pages * are allocated in cache lines, which means that each buffer @@ -331,6 +337,7 @@ struct buffer_page { unsigned read; /* index for next read */ local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ + unsigned order; /* order of the page */ struct buffer_data_page *page; /* Actual data page */ }; @@ -361,7 +368,7 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) static void free_buffer_page(struct buffer_page *bpage) { - free_page((unsigned long)bpage->page); + free_pages((unsigned long)bpage->page, bpage->order); kfree(bpage); } @@ -373,45 +380,11 @@ static inline bool test_time_stamp(u64 delta) return !!(delta & TS_DELTA_TEST); } -#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE) - -/* Max payload is BUF_PAGE_SIZE - header (8bytes) */ -#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2)) - -int ring_buffer_print_page_header(struct trace_seq *s) -{ - struct buffer_data_page field; - - trace_seq_printf(s, "\tfield: u64 timestamp;\t" - "offset:0;\tsize:%u;\tsigned:%u;\n", - (unsigned int)sizeof(field.time_stamp), - (unsigned int)is_signed_type(u64)); - - trace_seq_printf(s, "\tfield: local_t commit;\t" - "offset:%u;\tsize:%u;\tsigned:%u;\n", - (unsigned int)offsetof(typeof(field), commit), - (unsigned int)sizeof(field.commit), - (unsigned int)is_signed_type(long)); - - trace_seq_printf(s, "\tfield: int overwrite;\t" - "offset:%u;\tsize:%u;\tsigned:%u;\n", - (unsigned int)offsetof(typeof(field), commit), - 1, - (unsigned int)is_signed_type(long)); - - trace_seq_printf(s, "\tfield: char data;\t" - "offset:%u;\tsize:%u;\tsigned:%u;\n", - (unsigned int)offsetof(typeof(field), data), - (unsigned int)BUF_PAGE_SIZE, - (unsigned int)is_signed_type(char)); - - return !trace_seq_has_overflowed(s); -} - struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; + atomic_t seq; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -462,27 +435,9 @@ enum { RB_CTX_MAX }; -#if BITS_PER_LONG == 32 -#define RB_TIME_32 -#endif - -/* To test on 64 bit machines */ -//#define RB_TIME_32 - -#ifdef RB_TIME_32 - -struct rb_time_struct { - local_t cnt; - local_t top; - local_t bottom; - local_t msb; -}; -#else -#include struct rb_time_struct { local64_t time; }; -#endif typedef struct rb_time_struct rb_time_t; #define MAX_NEST 5 @@ -556,6 +511,10 @@ struct trace_buffer { struct rb_irq_work irq_work; bool time_stamp_abs; + + unsigned int subbuf_size; + unsigned int subbuf_order; + unsigned int max_data_size; }; struct ring_buffer_iter { @@ -569,150 +528,48 @@ struct ring_buffer_iter { u64 read_stamp; u64 page_stamp; struct ring_buffer_event *event; + size_t event_size; int missed_events; }; -#ifdef RB_TIME_32 - -/* - * On 32 bit machines, local64_t is very expensive. As the ring - * buffer doesn't need all the features of a true 64 bit atomic, - * on 32 bit, it uses these functions (64 still uses local64_t). - * - * For the ring buffer, 64 bit required operations for the time is - * the following: - * - * - Reads may fail if it interrupted a modification of the time stamp. - * It will succeed if it did not interrupt another write even if - * the read itself is interrupted by a write. - * It returns whether it was successful or not. - * - * - Writes always succeed and will overwrite other writes and writes - * that were done by events interrupting the current write. - * - * - A write followed by a read of the same time stamp will always succeed, - * but may not contain the same value. - * - * - A cmpxchg will fail if it interrupted another write or cmpxchg. - * Other than that, it acts like a normal cmpxchg. - * - * The 60 bit time stamp is broken up by 30 bits in a top and bottom half - * (bottom being the least significant 30 bits of the 60 bit time stamp). - * - * The two most significant bits of each half holds a 2 bit counter (0-3). - * Each update will increment this counter by one. - * When reading the top and bottom, if the two counter bits match then the - * top and bottom together make a valid 60 bit number. - */ -#define RB_TIME_SHIFT 30 -#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1) -#define RB_TIME_MSB_SHIFT 60 - -static inline int rb_time_cnt(unsigned long val) -{ - return (val >> RB_TIME_SHIFT) & 3; -} - -static inline u64 rb_time_val(unsigned long top, unsigned long bottom) -{ - u64 val; - - val = top & RB_TIME_VAL_MASK; - val <<= RB_TIME_SHIFT; - val |= bottom & RB_TIME_VAL_MASK; - - return val; -} - -static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) -{ - unsigned long top, bottom, msb; - unsigned long c; - - /* - * If the read is interrupted by a write, then the cnt will - * be different. Loop until both top and bottom have been read - * without interruption. - */ - do { - c = local_read(&t->cnt); - top = local_read(&t->top); - bottom = local_read(&t->bottom); - msb = local_read(&t->msb); - } while (c != local_read(&t->cnt)); - - *cnt = rb_time_cnt(top); - - /* If top, msb or bottom counts don't match, this interrupted a write */ - if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom)) - return false; - - /* The shift to msb will lose its cnt bits */ - *ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT); - return true; -} - -static bool rb_time_read(rb_time_t *t, u64 *ret) -{ - unsigned long cnt; - - return __rb_time_read(t, ret, &cnt); -} - -static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt) +int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s) { - return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT); -} + struct buffer_data_page field; -static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom, - unsigned long *msb) -{ - *top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK); - *bottom = (unsigned long)(val & RB_TIME_VAL_MASK); - *msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT); -} + trace_seq_printf(s, "\tfield: u64 timestamp;\t" + "offset:0;\tsize:%u;\tsigned:%u;\n", + (unsigned int)sizeof(field.time_stamp), + (unsigned int)is_signed_type(u64)); -static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt) -{ - val = rb_time_val_cnt(val, cnt); - local_set(t, val); -} + trace_seq_printf(s, "\tfield: local_t commit;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), commit), + (unsigned int)sizeof(field.commit), + (unsigned int)is_signed_type(long)); -static void rb_time_set(rb_time_t *t, u64 val) -{ - unsigned long cnt, top, bottom, msb; + trace_seq_printf(s, "\tfield: int overwrite;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), commit), + 1, + (unsigned int)is_signed_type(long)); - rb_time_split(val, &top, &bottom, &msb); + trace_seq_printf(s, "\tfield: char data;\t" + "offset:%u;\tsize:%u;\tsigned:%u;\n", + (unsigned int)offsetof(typeof(field), data), + (unsigned int)buffer->subbuf_size, + (unsigned int)is_signed_type(char)); - /* Writes always succeed with a valid number even if it gets interrupted. */ - do { - cnt = local_inc_return(&t->cnt); - rb_time_val_set(&t->top, top, cnt); - rb_time_val_set(&t->bottom, bottom, cnt); - rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt); - } while (cnt != local_read(&t->cnt)); + return !trace_seq_has_overflowed(s); } -static inline bool -rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) -{ - return local_try_cmpxchg(l, &expect, set); -} - -#else /* 64 bits */ - -/* local64_t always succeeds */ - -static inline bool rb_time_read(rb_time_t *t, u64 *ret) +static inline void rb_time_read(rb_time_t *t, u64 *ret) { *ret = local64_read(&t->time); - return true; } static void rb_time_set(rb_time_t *t, u64 val) { local64_set(&t->time, val); } -#endif /* * Enable this to make sure that the event passed to @@ -819,10 +676,7 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, WARN_ONCE(1, "nest (%d) greater than max", nest); fail: - /* Can only fail on 32 bit */ - if (!rb_time_read(&cpu_buffer->write_stamp, &ts)) - /* Screw it, just read the current time */ - ts = rb_time_stamp(cpu_buffer->buffer); + rb_time_read(&cpu_buffer->write_stamp, &ts); return ts; } @@ -900,6 +754,9 @@ static void rb_wake_up_waiters(struct irq_work *work) { struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); + /* For waiters waiting for the first wake up */ + (void)atomic_fetch_inc_release(&rbwork->seq); + wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { /* Only cpu_buffer sets the above flags */ @@ -1028,20 +885,21 @@ rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, return false; } +struct rb_wait_data { + struct rb_irq_work *irq_work; + int seq; +}; + /* * The default wait condition for ring_buffer_wait() is to just to exit the * wait loop the first time it is woken up. */ static bool rb_wait_once(void *data) { - long *once = data; - - /* wait_event() actually calls this twice before scheduling*/ - if (*once > 1) - return true; + struct rb_wait_data *rdata = data; + struct rb_irq_work *rbwork = rdata->irq_work; - (*once)++; - return false; + return atomic_read_acquire(&rbwork->seq) != rdata->seq; } /** @@ -1049,24 +907,22 @@ static bool rb_wait_once(void *data) * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS + * @cond: condition function to break out of wait (NULL to run once) + * @data: the data to pass to @cond. * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data) { struct ring_buffer_per_cpu *cpu_buffer; struct wait_queue_head *waitq; - ring_buffer_cond_fn cond; struct rb_irq_work *rbwork; - void *data; - long once = 0; + struct rb_wait_data rdata; int ret = 0; - cond = rb_wait_once; - data = &once; - /* * Depending on what the caller is waiting for, either any * data in any cpu buffer, or a specific buffer, put the @@ -1088,6 +944,14 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) else waitq = &rbwork->waiters; + /* Set up to exit loop as soon as it is woken */ + if (!cond) { + cond = rb_wait_once; + rdata.irq_work = rbwork; + rdata.seq = atomic_read_acquire(&rbwork->seq); + data = &rdata; + } + ret = wait_event_interruptible((*waitq), rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); @@ -1536,7 +1400,6 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); - local_inc(&cpu_buffer->pages_touched); /* * Just make sure we have seen our old_write and synchronize * with any interrupts that come in. @@ -1573,8 +1436,9 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, */ local_set(&next_page->page->commit, 0); - /* Again, either we update tail_page or an interrupt does */ - (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page); + /* Either we update tail_page or an interrupt does */ + if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page)) + local_inc(&cpu_buffer->pages_touched); } } @@ -1666,10 +1530,12 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, list_add(&bpage->list, pages); - page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0); + page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, + cpu_buffer->buffer->subbuf_order); if (!page) goto free_pages; bpage->page = page_address(page); + bpage->order = cpu_buffer->buffer->subbuf_order; rb_init_page(bpage->page); if (user_thread && fatal_signal_pending(current)) @@ -1748,7 +1614,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) rb_check_bpage(cpu_buffer, bpage); cpu_buffer->reader_page = bpage; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); + + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order); if (!page) goto fail_free_reader; bpage->page = page_address(page); @@ -1831,7 +1698,14 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL)) goto fail_free_buffer; - nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + /* Default buffer page size - one system page */ + buffer->subbuf_order = 0; + buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE; + + /* Max payload is buffer page size - header (8bytes) */ + buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2); + + nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size); buffer->flags = flags; buffer->clock = trace_clock_local; buffer->reader_lock_key = key; @@ -2150,7 +2024,7 @@ static void update_pages_handler(struct work_struct *work) * @size: the new size. * @cpu_id: the cpu buffer to resize * - * Minimum size is 2 * BUF_PAGE_SIZE. + * Minimum size is 2 * buffer->subbuf_size. * * Returns 0 on success and < 0 on failure. */ @@ -2172,7 +2046,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, !cpumask_test_cpu(cpu_id, buffer->cpumask)) return 0; - nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size); /* we need a minimum of two pages */ if (nr_pages < 2) @@ -2419,7 +2293,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) */ barrier(); - if ((iter->head + length) > commit || length > BUF_PAGE_SIZE) + if ((iter->head + length) > commit || length > iter->event_size) /* Writer corrupted the read? */ goto reset; @@ -2459,11 +2333,13 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer) } static __always_inline unsigned -rb_event_index(struct ring_buffer_event *event) +rb_event_index(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { unsigned long addr = (unsigned long)event; - return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE; + addr &= (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1; + + return addr - BUF_PAGE_HDR_SIZE; } static void rb_inc_iter(struct ring_buffer_iter *iter) @@ -2652,6 +2528,7 @@ static inline void rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long tail, struct rb_event_info *info) { + unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size); struct buffer_page *tail_page = info->tail_page; struct ring_buffer_event *event; unsigned long length = info->length; @@ -2660,13 +2537,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * Only the event that crossed the page boundary * must fill the old tail_page with padding. */ - if (tail >= BUF_PAGE_SIZE) { + if (tail >= bsize) { /* * If the page was filled, then we still need * to update the real_end. Reset it to zero * and the reader will ignore it. */ - if (tail == BUF_PAGE_SIZE) + if (tail == bsize) tail_page->real_end = 0; local_sub(length, &tail_page->write); @@ -2694,7 +2571,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * If we are less than the minimum size, we don't need to * worry about it. */ - if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) { + if (tail > (bsize - RB_EVNT_MIN_SIZE)) { /* No room for any events */ /* Mark the rest of the page with padding */ @@ -2709,19 +2586,19 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, } /* Put in a discarded event */ - event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE; + event->array[0] = (bsize - tail) - RB_EVNT_HDR_SIZE; event->type_len = RINGBUF_TYPE_PADDING; /* time delta must be non zero */ event->time_delta = 1; /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + local_add(bsize - tail, &cpu_buffer->entries_bytes); /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); /* Set write to end of buffer */ - length = (tail + length) - BUF_PAGE_SIZE; + length = (tail + length) - bsize; local_sub(length, &tail_page->write); } @@ -2835,7 +2712,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, /* Slow path */ static struct ring_buffer_event * -rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs) +rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event, u64 delta, bool abs) { if (abs) event->type_len = RINGBUF_TYPE_TIME_STAMP; @@ -2843,7 +2721,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs) event->type_len = RINGBUF_TYPE_TIME_EXTEND; /* Not the first event on the page, or not delta? */ - if (abs || rb_event_index(event)) { + if (abs || rb_event_index(cpu_buffer, event)) { event->time_delta = delta & TS_MASK; event->array[0] = delta >> TS_SHIFT; } else { @@ -2873,7 +2751,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer, (unsigned long long)info->ts, (unsigned long long)info->before, (unsigned long long)info->after, - (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0), + (unsigned long long)({rb_time_read(&cpu_buffer->write_stamp, &write_stamp); write_stamp;}), sched_clock_stable() ? "" : "If you just came from a suspend/resume,\n" "please switch to the trace global clock:\n" @@ -2917,7 +2795,7 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer, if (!abs) info->delta = 0; } - *event = rb_add_time_stamp(*event, info->delta, abs); + *event = rb_add_time_stamp(cpu_buffer, *event, info->delta, abs); *length -= RB_LEN_TIME_EXTEND; *delta = 0; } @@ -3001,10 +2879,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage; unsigned long addr; - new_index = rb_event_index(event); + new_index = rb_event_index(cpu_buffer, event); old_index = new_index + rb_event_ts_length(event); addr = (unsigned long)event; - addr &= PAGE_MASK; + addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1); bpage = READ_ONCE(cpu_buffer->tail_page); @@ -3391,6 +3269,76 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit); #define CHECK_FULL_PAGE 1L #ifdef CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS + +static const char *show_irq_str(int bits) +{ + const char *type[] = { + ".", // 0 + "s", // 1 + "h", // 2 + "Hs", // 3 + "n", // 4 + "Ns", // 5 + "Nh", // 6 + "NHs", // 7 + }; + + return type[bits]; +} + +/* Assume this is an trace event */ +static const char *show_flags(struct ring_buffer_event *event) +{ + struct trace_entry *entry; + int bits = 0; + + if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry)) + return "X"; + + entry = ring_buffer_event_data(event); + + if (entry->flags & TRACE_FLAG_SOFTIRQ) + bits |= 1; + + if (entry->flags & TRACE_FLAG_HARDIRQ) + bits |= 2; + + if (entry->flags & TRACE_FLAG_NMI) + bits |= 4; + + return show_irq_str(bits); +} + +static const char *show_irq(struct ring_buffer_event *event) +{ + struct trace_entry *entry; + + if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry)) + return ""; + + entry = ring_buffer_event_data(event); + if (entry->flags & TRACE_FLAG_IRQS_OFF) + return "d"; + return ""; +} + +static const char *show_interrupt_level(void) +{ + unsigned long pc = preempt_count(); + unsigned char level = 0; + + if (pc & SOFTIRQ_OFFSET) + level |= 1; + + if (pc & HARDIRQ_MASK) + level |= 2; + + if (pc & NMI_MASK) + level |= 4; + + return show_irq_str(level); +} + static void dump_buffer_page(struct buffer_data_page *bpage, struct rb_event_info *info, unsigned long tail) @@ -3411,34 +3359,57 @@ static void dump_buffer_page(struct buffer_data_page *bpage, case RINGBUF_TYPE_TIME_EXTEND: delta = rb_event_time_stamp(event); ts += delta; - pr_warn(" [%lld] delta:%lld TIME EXTEND\n", ts, delta); + pr_warn(" 0x%x: [%lld] delta:%lld TIME EXTEND\n", + e, ts, delta); break; case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); ts = rb_fix_abs_ts(delta, ts); - pr_warn(" [%lld] absolute:%lld TIME STAMP\n", ts, delta); + pr_warn(" 0x%x: [%lld] absolute:%lld TIME STAMP\n", + e, ts, delta); break; case RINGBUF_TYPE_PADDING: ts += event->time_delta; - pr_warn(" [%lld] delta:%d PADDING\n", ts, event->time_delta); + pr_warn(" 0x%x: [%lld] delta:%d PADDING\n", + e, ts, event->time_delta); break; case RINGBUF_TYPE_DATA: ts += event->time_delta; - pr_warn(" [%lld] delta:%d\n", ts, event->time_delta); + pr_warn(" 0x%x: [%lld] delta:%d %s%s\n", + e, ts, event->time_delta, + show_flags(event), show_irq(event)); break; default: break; } } + pr_warn("expected end:0x%lx last event actually ended at:0x%x\n", tail, e); } static DEFINE_PER_CPU(atomic_t, checking); static atomic_t ts_dump; +#define buffer_warn_return(fmt, ...) \ + do { \ + /* If another report is happening, ignore this one */ \ + if (atomic_inc_return(&ts_dump) != 1) { \ + atomic_dec(&ts_dump); \ + goto out; \ + } \ + atomic_inc(&cpu_buffer->record_disabled); \ + pr_warn(fmt, ##__VA_ARGS__); \ + dump_buffer_page(bpage, info, tail); \ + atomic_dec(&ts_dump); \ + /* There's some cases in boot up that this can happen */ \ + if (WARN_ON_ONCE(system_state != SYSTEM_BOOTING)) \ + /* Do not re-enable checking */ \ + return; \ + } while (0) + /* * Check if the current event time stamp matches the deltas on * the buffer page. @@ -3492,7 +3463,12 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); - ts = rb_fix_abs_ts(delta, ts); + delta = rb_fix_abs_ts(delta, ts); + if (delta < ts) { + buffer_warn_return("[CPU: %d]ABSOLUTE TIME WENT BACKWARDS: last ts: %lld absolute ts: %lld\n", + cpu_buffer->cpu, ts, delta); + } + ts = delta; break; case RINGBUF_TYPE_PADDING: @@ -3509,23 +3485,11 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, } if ((full && ts > info->ts) || (!full && ts + info->delta != info->ts)) { - /* If another report is happening, ignore this one */ - if (atomic_inc_return(&ts_dump) != 1) { - atomic_dec(&ts_dump); - goto out; - } - atomic_inc(&cpu_buffer->record_disabled); - /* There's some cases in boot up that this can happen */ - WARN_ON_ONCE(system_state != SYSTEM_BOOTING); - pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s\n", - cpu_buffer->cpu, - ts + info->delta, info->ts, info->delta, - info->before, info->after, - full ? " (full)" : ""); - dump_buffer_page(bpage, info, tail); - atomic_dec(&ts_dump); - /* Do not re-enable checking */ - return; + buffer_warn_return("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s context:%s\n", + cpu_buffer->cpu, + ts + info->delta, info->ts, info->delta, + info->before, info->after, + full ? " (full)" : "", show_interrupt_level()); } out: atomic_dec(this_cpu_ptr(&checking)); @@ -3545,16 +3509,14 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event; struct buffer_page *tail_page; unsigned long tail, write, w; - bool a_ok; - bool b_ok; /* Don't let the compiler play games with cpu_buffer->tail_page */ tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page); /*A*/ w = local_read(&tail_page->write) & RB_WRITE_MASK; barrier(); - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + rb_time_read(&cpu_buffer->before_stamp, &info->before); + rb_time_read(&cpu_buffer->write_stamp, &info->after); barrier(); info->ts = rb_time_stamp(cpu_buffer->buffer); @@ -3569,7 +3531,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, if (!w) { /* Use the sub-buffer timestamp */ info->delta = 0; - } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) { + } else if (unlikely(info->before != info->after)) { info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND; info->length += RB_LEN_TIME_EXTEND; } else { @@ -3591,7 +3553,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, tail = write - info->length; /* See if we shot pass the end of this buffer page */ - if (unlikely(write > BUF_PAGE_SIZE)) { + if (unlikely(write > cpu_buffer->buffer->subbuf_size)) { check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } @@ -3618,8 +3580,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* SLOW PATH - Interrupted between A and C */ /* Save the old before_stamp */ - a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - RB_WARN_ON(cpu_buffer, !a_ok); + rb_time_read(&cpu_buffer->before_stamp, &info->before); /* * Read a new timestamp and update the before_stamp to make @@ -3631,9 +3592,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, rb_time_set(&cpu_buffer->before_stamp, ts); barrier(); - /*E*/ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - /* Was interrupted before here, write_stamp must be valid */ - RB_WARN_ON(cpu_buffer, !a_ok); + /*E*/ rb_time_read(&cpu_buffer->write_stamp, &info->after); barrier(); /*F*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && info->after == info->before && info->after < ts) { @@ -3725,7 +3684,7 @@ rb_reserve_next_event(struct trace_buffer *buffer, if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) { add_ts_default = RB_ADD_STAMP_ABSOLUTE; info.length += RB_LEN_TIME_EXTEND; - if (info.length > BUF_MAX_DATA_SIZE) + if (info.length > cpu_buffer->buffer->max_data_size) goto out_fail; } else { add_ts_default = RB_ADD_STAMP_NONE; @@ -3800,7 +3759,7 @@ ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length) if (unlikely(atomic_read(&cpu_buffer->record_disabled))) goto out; - if (unlikely(length > BUF_MAX_DATA_SIZE)) + if (unlikely(length > buffer->max_data_size)) goto out; if (unlikely(trace_recursive_lock(cpu_buffer))) @@ -3834,7 +3793,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage = cpu_buffer->commit_page; struct buffer_page *start; - addr &= PAGE_MASK; + addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1); /* Do the likely case first */ if (likely(bpage->page == (void *)addr)) { @@ -3950,7 +3909,7 @@ int ring_buffer_write(struct trace_buffer *buffer, if (atomic_read(&cpu_buffer->record_disabled)) goto out; - if (length > BUF_MAX_DATA_SIZE) + if (length > buffer->max_data_size) goto out; if (unlikely(trace_recursive_lock(cpu_buffer))) @@ -4436,7 +4395,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; - commit_page = cpu_buffer->commit_page; + commit_page = READ_ONCE(cpu_buffer->commit_page); commit_ts = commit_page->page->time_stamp; /* @@ -4530,6 +4489,7 @@ static struct buffer_page * rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = NULL; + unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size); unsigned long overwrite; unsigned long flags; int nr_loops = 0; @@ -4665,7 +4625,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) #define USECS_WAIT 1000000 for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { /* If the write is past the end of page, a writer is still updating it */ - if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE)) + if (likely(!reader || rb_page_write(reader) <= bsize)) break; udelay(1); @@ -5109,7 +5069,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) return NULL; /* Holds the entire event: data and meta data */ - iter->event = kmalloc(BUF_PAGE_SIZE, flags); + iter->event_size = buffer->subbuf_size; + iter->event = kmalloc(iter->event_size, flags); if (!iter->event) { kfree(iter); return NULL; @@ -5225,19 +5186,28 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_advance); */ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu) { - /* - * Earlier, this method returned - * BUF_PAGE_SIZE * buffer->nr_pages - * Since the nr_pages field is now removed, we have converted this to - * return the per cpu buffer value. - */ if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; - return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages; + return buffer->subbuf_size * buffer->buffers[cpu]->nr_pages; } EXPORT_SYMBOL_GPL(ring_buffer_size); +/** + * ring_buffer_max_event_size - return the max data size of an event + * @buffer: The ring buffer. + * + * Returns the maximum size an event can be. + */ +unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer) +{ + /* If abs timestamp is requested, events have a timestamp too */ + if (ring_buffer_time_stamp_abs(buffer)) + return buffer->max_data_size - RB_LEN_TIME_EXTEND; + return buffer->max_data_size; +} +EXPORT_SYMBOL_GPL(ring_buffer_max_event_size); + static void rb_clear_buffer_page(struct buffer_page *page) { local_set(&page->write, 0); @@ -5508,6 +5478,9 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; + if (buffer_a->subbuf_order != buffer_b->subbuf_order) + goto out; + ret = -EAGAIN; if (atomic_read(&buffer_a->record_disabled)) @@ -5579,40 +5552,48 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * Returns: * The page allocated, or ERR_PTR */ -void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) +struct buffer_data_read_page * +ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_page *bpage = NULL; + struct buffer_data_read_page *bpage = NULL; unsigned long flags; struct page *page; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return ERR_PTR(-ENODEV); + bpage = kzalloc(sizeof(*bpage), GFP_KERNEL); + if (!bpage) + return ERR_PTR(-ENOMEM); + + bpage->order = buffer->subbuf_order; cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (cpu_buffer->free_page) { - bpage = cpu_buffer->free_page; + bpage->data = cpu_buffer->free_page; cpu_buffer->free_page = NULL; } arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); - if (bpage) + if (bpage->data) goto out; - page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, + cpu_buffer->buffer->subbuf_order); + if (!page) { + kfree(bpage); return ERR_PTR(-ENOMEM); + } - bpage = page_address(page); + bpage->data = page_address(page); out: - rb_init_page(bpage); + rb_init_page(bpage->data); return bpage; } @@ -5622,14 +5603,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); * ring_buffer_free_read_page - free an allocated read page * @buffer: the buffer the page was allocate for * @cpu: the cpu buffer the page came from - * @data: the page to free + * @data_page: the page to free * * Free a page allocated from ring_buffer_alloc_read_page. */ -void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data) +void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page *data_page) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_page *bpage = data; + struct buffer_data_page *bpage = data_page->data; struct page *page = virt_to_page(bpage); unsigned long flags; @@ -5638,8 +5620,12 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data cpu_buffer = buffer->buffers[cpu]; - /* If the page is still in use someplace else, we can't reuse it */ - if (page_ref_count(page) > 1) + /* + * If the page is still in use someplace else, or order of the page + * is different from the subbuffer order of the buffer - + * we can't reuse it + */ + if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order) goto out; local_irq_save(flags); @@ -5654,7 +5640,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data local_irq_restore(flags); out: - free_page((unsigned long)bpage); + free_pages((unsigned long)bpage, data_page->order); + kfree(data_page); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); @@ -5675,9 +5662,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * rpage = ring_buffer_alloc_read_page(buffer, cpu); * if (IS_ERR(rpage)) * return PTR_ERR(rpage); - * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); + * ret = ring_buffer_read_page(buffer, rpage, len, cpu, 0); * if (ret >= 0) - * process_page(rpage, ret); + * process_page(ring_buffer_read_page_data(rpage), ret); + * ring_buffer_free_read_page(buffer, cpu, rpage); * * When @full is set, the function will not return true unless * the writer is off the reader page. @@ -5692,7 +5680,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * <0 if no data has been transferred. */ int ring_buffer_read_page(struct trace_buffer *buffer, - void **data_page, size_t len, int cpu, int full) + struct buffer_data_read_page *data_page, + size_t len, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; @@ -5717,10 +5706,12 @@ int ring_buffer_read_page(struct trace_buffer *buffer, len -= BUF_PAGE_HDR_SIZE; - if (!data_page) + if (!data_page || !data_page->data) + goto out; + if (data_page->order != buffer->subbuf_order) goto out; - bpage = *data_page; + bpage = data_page->data; if (!bpage) goto out; @@ -5814,11 +5805,11 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* swap the pages */ rb_init_page(bpage); bpage = reader->page; - reader->page = *data_page; + reader->page = data_page->data; local_set(&reader->write, 0); local_set(&reader->entries, 0); reader->read = 0; - *data_page = bpage; + data_page->data = bpage; /* * Use the real_end for the data size, @@ -5840,7 +5831,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* If there is room at the end of the page to save the * missed events, then record it there. */ - if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) { + if (buffer->subbuf_size - commit >= sizeof(missed_events)) { memcpy(&bpage->data[commit], &missed_events, sizeof(missed_events)); local_add(RB_MISSED_STORED, &bpage->commit); @@ -5852,8 +5843,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* * This page may be off to user land. Zero it out here. */ - if (commit < BUF_PAGE_SIZE) - memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); + if (commit < buffer->subbuf_size) + memset(&bpage->data[commit], 0, buffer->subbuf_size - commit); out_unlock: raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); @@ -5863,6 +5854,213 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_read_page); +/** + * ring_buffer_read_page_data - get pointer to the data in the page. + * @page: the page to get the data from + * + * Returns pointer to the actual data in this page. + */ +void *ring_buffer_read_page_data(struct buffer_data_read_page *page) +{ + return page->data; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_page_data); + +/** + * ring_buffer_subbuf_size_get - get size of the sub buffer. + * @buffer: the buffer to get the sub buffer size from + * + * Returns size of the sub buffer, in bytes. + */ +int ring_buffer_subbuf_size_get(struct trace_buffer *buffer) +{ + return buffer->subbuf_size + BUF_PAGE_HDR_SIZE; +} +EXPORT_SYMBOL_GPL(ring_buffer_subbuf_size_get); + +/** + * ring_buffer_subbuf_order_get - get order of system sub pages in one buffer page. + * @buffer: The ring_buffer to get the system sub page order from + * + * By default, one ring buffer sub page equals to one system page. This parameter + * is configurable, per ring buffer. The size of the ring buffer sub page can be + * extended, but must be an order of system page size. + * + * Returns the order of buffer sub page size, in system pages: + * 0 means the sub buffer size is 1 system page and so forth. + * In case of an error < 0 is returned. + */ +int ring_buffer_subbuf_order_get(struct trace_buffer *buffer) +{ + if (!buffer) + return -EINVAL; + + return buffer->subbuf_order; +} +EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get); + +/** + * ring_buffer_subbuf_order_set - set the size of ring buffer sub page. + * @buffer: The ring_buffer to set the new page size. + * @order: Order of the system pages in one sub buffer page + * + * By default, one ring buffer pages equals to one system page. This API can be + * used to set new size of the ring buffer page. The size must be order of + * system page size, that's why the input parameter @order is the order of + * system pages that are allocated for one ring buffer page: + * 0 - 1 system page + * 1 - 2 system pages + * 3 - 4 system pages + * ... + * + * Returns 0 on success or < 0 in case of an error. + */ +int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *bpage, *tmp; + int old_order, old_size; + int nr_pages; + int psize; + int err; + int cpu; + + if (!buffer || order < 0) + return -EINVAL; + + if (buffer->subbuf_order == order) + return 0; + + psize = (1 << order) * PAGE_SIZE; + if (psize <= BUF_PAGE_HDR_SIZE) + return -EINVAL; + + /* Size of a subbuf cannot be greater than the write counter */ + if (psize > RB_WRITE_MASK + 1) + return -EINVAL; + + old_order = buffer->subbuf_order; + old_size = buffer->subbuf_size; + + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + atomic_inc(&buffer->record_disabled); + + /* Make sure all commits have finished */ + synchronize_rcu(); + + buffer->subbuf_order = order; + buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE; + + /* Make sure all new buffers are allocated, before deleting the old ones */ + for_each_buffer_cpu(buffer, cpu) { + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + continue; + + cpu_buffer = buffer->buffers[cpu]; + + /* Update the number of pages to match the new size */ + nr_pages = old_size * buffer->buffers[cpu]->nr_pages; + nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size); + + /* we need a minimum of two pages */ + if (nr_pages < 2) + nr_pages = 2; + + cpu_buffer->nr_pages_to_update = nr_pages; + + /* Include the reader page */ + nr_pages++; + + /* Allocate the new size buffer */ + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (__rb_allocate_pages(cpu_buffer, nr_pages, + &cpu_buffer->new_pages)) { + /* not enough memory for new pages */ + err = -ENOMEM; + goto error; + } + } + + for_each_buffer_cpu(buffer, cpu) { + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + continue; + + cpu_buffer = buffer->buffers[cpu]; + + /* Clear the head bit to make the link list normal to read */ + rb_head_page_deactivate(cpu_buffer); + + /* Now walk the list and free all the old sub buffers */ + list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + /* The above loop stopped an the last page needing to be freed */ + bpage = list_entry(cpu_buffer->pages, struct buffer_page, list); + free_buffer_page(bpage); + + /* Free the current reader page */ + free_buffer_page(cpu_buffer->reader_page); + + /* One page was allocated for the reader page */ + cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next, + struct buffer_page, list); + list_del_init(&cpu_buffer->reader_page->list); + + /* The cpu_buffer pages are a link list with no head */ + cpu_buffer->pages = cpu_buffer->new_pages.next; + cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev; + cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next; + + /* Clear the new_pages list */ + INIT_LIST_HEAD(&cpu_buffer->new_pages); + + cpu_buffer->head_page + = list_entry(cpu_buffer->pages, struct buffer_page, list); + cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page; + + cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update; + cpu_buffer->nr_pages_to_update = 0; + + free_pages((unsigned long)cpu_buffer->free_page, old_order); + cpu_buffer->free_page = NULL; + + rb_head_page_activate(cpu_buffer); + + rb_check_pages(cpu_buffer); + } + + atomic_dec(&buffer->record_disabled); + mutex_unlock(&buffer->mutex); + + return 0; + +error: + buffer->subbuf_order = old_order; + buffer->subbuf_size = old_size; + + atomic_dec(&buffer->record_disabled); + mutex_unlock(&buffer->mutex); + + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + + if (!cpu_buffer->nr_pages_to_update) + continue; + + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + } + + return err; +} +EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set); + /* * We only allocate new buffers, never free them if the CPU goes down. * If we were to free the buffer, then the user would lose any trace that was in diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index aef34673d..008187ebd 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -104,10 +104,11 @@ static enum event_status read_event(int cpu) static enum event_status read_page(int cpu) { + struct buffer_data_read_page *bpage; struct ring_buffer_event *event; struct rb_page *rpage; unsigned long commit; - void *bpage; + int page_size; int *entry; int ret; int inc; @@ -117,14 +118,15 @@ static enum event_status read_page(int cpu) if (IS_ERR(bpage)) return EVENT_DROPPED; - ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1); + page_size = ring_buffer_subbuf_size_get(buffer); + ret = ring_buffer_read_page(buffer, bpage, page_size, cpu, 1); if (ret >= 0) { - rpage = bpage; + rpage = ring_buffer_read_page_data(bpage); /* The commit may have missed event flags set, clear them */ commit = local_read(&rpage->commit) & 0xfffff; for (i = 0; i < commit && !test_error ; i += inc) { - if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) { + if (i >= (page_size - offsetof(struct rb_page, data))) { TEST_ERROR(); break; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e03960f9f..d390fea3a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1264,10 +1264,17 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val); int tracing_alloc_snapshot_instance(struct trace_array *tr) { + int order; int ret; if (!tr->allocated_snapshot) { + /* Make the snapshot buffer have the same order as main buffer */ + order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); + if (ret < 0) + return ret; + /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->array_buffer, RING_BUFFER_ALL_CPUS); @@ -1287,6 +1294,7 @@ static void free_snapshot(struct trace_array *tr) * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ + ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0); ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&tr->max_buffer, 1); tracing_reset_online_cpus(&tr->max_buffer); @@ -1525,7 +1533,7 @@ void disable_trace_on_warning(void) bool tracer_tracing_is_on(struct trace_array *tr) { if (tr->array_buffer.buffer) - return ring_buffer_record_is_on(tr->array_buffer.buffer); + return ring_buffer_record_is_set_on(tr->array_buffer.buffer); return !tr->buffer_disabled; } @@ -1947,15 +1955,36 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) #endif /* CONFIG_TRACER_MAX_TRACE */ +struct pipe_wait { + struct trace_iterator *iter; + int wait_index; +}; + +static bool wait_pipe_cond(void *data) +{ + struct pipe_wait *pwait = data; + struct trace_iterator *iter = pwait->iter; + + if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) + return true; + + return iter->closed; +} + static int wait_on_pipe(struct trace_iterator *iter, int full) { + struct pipe_wait pwait; int ret; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + pwait.wait_index = atomic_read_acquire(&iter->wait_index); + pwait.iter = iter; + + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, + wait_pipe_cond, &pwait); #ifdef CONFIG_TRACER_MAX_TRACE /* @@ -3781,7 +3810,7 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, /* OK if part of the temp seq buffer */ if ((addr >= (unsigned long)iter->tmp_seq.buffer) && - (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE)) + (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE)) return true; /* Core rodata can not be freed */ @@ -5046,7 +5075,7 @@ static int tracing_release(struct inode *inode, struct file *file) return 0; } -static int tracing_release_generic_tr(struct inode *inode, struct file *file) +int tracing_release_generic_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; @@ -6948,8 +6977,8 @@ waitagain: goto out; } - if (cnt >= PAGE_SIZE) - cnt = PAGE_SIZE - 1; + if (cnt >= TRACE_SEQ_BUFFER_SIZE) + cnt = TRACE_SEQ_BUFFER_SIZE - 1; /* reset all but tr, trace, and overruns */ trace_iterator_reset(iter); @@ -7285,6 +7314,8 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) return 0; } +#define TRACE_MARKER_MAX_SIZE 4096 + static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) @@ -7294,8 +7325,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, enum event_trigger_type tt = ETT_NONE; struct trace_buffer *buffer; struct print_entry *entry; + int meta_size; ssize_t written; - int size; + size_t size; int len; /* Used in tracing_mark_raw_write() as well */ @@ -7308,12 +7340,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (!(tr->trace_flags & TRACE_ITER_MARKERS)) return -EINVAL; - if (cnt > TRACE_BUF_SIZE) - cnt = TRACE_BUF_SIZE; + if ((ssize_t)cnt < 0) + return -EINVAL; - BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); + if (cnt > TRACE_MARKER_MAX_SIZE) + cnt = TRACE_MARKER_MAX_SIZE; - size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */ + meta_size = sizeof(*entry) + 2; /* add '\0' and possible '\n' */ + again: + size = cnt + meta_size; /* If less than "", then make sure we can still add that */ if (cnt < FAULTED_SIZE) @@ -7322,9 +7357,25 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, tracing_gen_ctx()); - if (unlikely(!event)) + if (unlikely(!event)) { + /* + * If the size was greater than what was allowed, then + * make it smaller and try again. + */ + if (size > ring_buffer_max_event_size(buffer)) { + /* cnt < FAULTED size should never be bigger than max */ + if (WARN_ON_ONCE(cnt < FAULTED_SIZE)) + return -EBADF; + cnt = ring_buffer_max_event_size(buffer) - meta_size; + /* The above should only happen once */ + if (WARN_ON_ONCE(cnt + meta_size == size)) + return -EBADF; + goto again; + } + /* Ring buffer disabled, return as if not open for write */ return -EBADF; + } entry = ring_buffer_event_data(event); entry->ip = _THIS_IP_; @@ -7359,9 +7410,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, return written; } -/* Limit it for now to 3K (including tag) */ -#define RAW_DATA_MAX_SIZE (1024*3) - static ssize_t tracing_mark_raw_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) @@ -7383,19 +7431,18 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, return -EINVAL; /* The marker must at least have a tag id */ - if (cnt < sizeof(unsigned int) || cnt > RAW_DATA_MAX_SIZE) + if (cnt < sizeof(unsigned int)) return -EINVAL; - if (cnt > TRACE_BUF_SIZE) - cnt = TRACE_BUF_SIZE; - - BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); - size = sizeof(*entry) + cnt; if (cnt < FAULT_SIZE_ID) size += FAULT_SIZE_ID - cnt; buffer = tr->array_buffer.buffer; + + if (size > ring_buffer_max_event_size(buffer)) + return -EINVAL; + event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size, tracing_gen_ctx()); if (!event) @@ -7580,6 +7627,7 @@ struct ftrace_buffer_info { struct trace_iterator iter; void *spare; unsigned int spare_cpu; + unsigned int spare_size; unsigned int read; }; @@ -8284,6 +8332,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; + void *trace_data; + int page_size; ssize_t ret = 0; ssize_t size; @@ -8295,6 +8345,17 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return -EBUSY; #endif + page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); + + /* Make sure the spare matches the current sub buffer size */ + if (info->spare) { + if (page_size != info->spare_size) { + ring_buffer_free_read_page(iter->array_buffer->buffer, + info->spare_cpu, info->spare); + info->spare = NULL; + } + } + if (!info->spare) { info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file); @@ -8303,19 +8364,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, info->spare = NULL; } else { info->spare_cpu = iter->cpu_file; + info->spare_size = page_size; } } if (!info->spare) return ret; /* Do we have previous read data to read? */ - if (info->read < PAGE_SIZE) + if (info->read < page_size) goto read; again: trace_access_lock(iter->cpu_file); ret = ring_buffer_read_page(iter->array_buffer->buffer, - &info->spare, + info->spare, count, iter->cpu_file, 0); trace_access_unlock(iter->cpu_file); @@ -8336,11 +8398,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, info->read = 0; read: - size = PAGE_SIZE - info->read; + size = page_size - info->read; if (size > count) size = count; - - ret = copy_to_user(ubuf, info->spare + info->read, size); + trace_data = ring_buffer_read_page_data(info->spare); + ret = copy_to_user(ubuf, trace_data + info->read, size); if (ret == size) return -EFAULT; @@ -8357,9 +8419,9 @@ static int tracing_buffers_flush(struct file *file, fl_owner_t id) struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; - iter->wait_index++; + iter->closed = true; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); @@ -8459,6 +8521,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; + bool woken = false; + int page_size; int entries, i; ssize_t ret = 0; @@ -8467,13 +8531,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -EBUSY; #endif - if (*ppos & (PAGE_SIZE - 1)) + page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); + if (*ppos & (page_size - 1)) return -EINVAL; - if (len & (PAGE_SIZE - 1)) { - if (len < PAGE_SIZE) + if (len & (page_size - 1)) { + if (len < page_size) return -EINVAL; - len &= PAGE_MASK; + len &= (~(page_size - 1)); } if (splice_grow_spd(pipe, &spd)) @@ -8483,7 +8548,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); - for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) { + for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) { struct page *page; int r; @@ -8504,7 +8569,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, } ref->cpu = iter->cpu_file; - r = ring_buffer_read_page(ref->buffer, &ref->page, + r = ring_buffer_read_page(ref->buffer, ref->page, len, iter->cpu_file, 1); if (r < 0) { ring_buffer_free_read_page(ref->buffer, ref->cpu, @@ -8513,14 +8578,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - page = virt_to_page(ref->page); + page = virt_to_page(ring_buffer_read_page_data(ref->page)); spd.pages[i] = page; - spd.partial[i].len = PAGE_SIZE; + spd.partial[i].len = page_size; spd.partial[i].offset = 0; spd.partial[i].private = (unsigned long)ref; spd.nr_pages++; - *ppos += PAGE_SIZE; + *ppos += page_size; entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); } @@ -8530,17 +8595,17 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { - long wait_index; if (ret) goto out; + if (woken) + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; - wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; @@ -8549,10 +8614,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if (!tracer_tracing_is_on(iter->tr)) goto out; - /* Make sure we see the new wait_index */ - smp_rmb(); - if (wait_index != iter->wait_index) - goto out; + /* Iterate one more time to collect any new data then exit */ + woken = true; goto again; } @@ -8575,9 +8638,8 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned mutex_lock(&trace_types_lock); - iter->wait_index++; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); @@ -9365,6 +9427,103 @@ static const struct file_operations buffer_percent_fops = { .llseek = default_llseek, }; +static ssize_t +buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + size_t size; + char buf[64]; + int order; + int r; + + order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + size = (PAGE_SIZE << order) / 1024; + + r = sprintf(buf, "%zd\n", size); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + unsigned long val; + int old_order; + int order; + int pages; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + val *= 1024; /* value passed in is in KB */ + + pages = DIV_ROUND_UP(val, PAGE_SIZE); + order = fls(pages - 1); + + /* limit between 1 and 128 system pages */ + if (order < 0 || order > 7) + return -EINVAL; + + /* Do not allow tracing while changing the order of the ring buffer */ + tracing_stop_tr(tr); + + old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); + if (old_order == order) + goto out; + + ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order); + if (ret) + goto out; + +#ifdef CONFIG_TRACER_MAX_TRACE + + if (!tr->allocated_snapshot) + goto out_max; + + ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); + if (ret) { + /* Put back the old order */ + cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order); + if (WARN_ON_ONCE(cnt)) { + /* + * AARGH! We are left with different orders! + * The max buffer is our "snapshot" buffer. + * When a tracer needs a snapshot (one of the + * latency tracers), it swaps the max buffer + * with the saved snap shot. We succeeded to + * update the order of the main buffer, but failed to + * update the order of the max buffer. But when we tried + * to reset the main buffer to the original size, we + * failed there too. This is very unlikely to + * happen, but if it does, warn and kill all + * tracing. + */ + tracing_disabled = 1; + } + goto out; + } + out_max: +#endif + (*ppos)++; + out: + if (ret) + cnt = ret; + tracing_start_tr(tr); + return cnt; +} + +static const struct file_operations buffer_subbuf_size_fops = { + .open = tracing_open_generic_tr, + .read = buffer_subbuf_size_read, + .write = buffer_subbuf_size_write, + .release = tracing_release_generic_tr, + .llseek = default_llseek, +}; + static struct dentry *trace_instance_dir; static void @@ -9515,7 +9674,8 @@ static int trace_array_create_dir(struct trace_array *tr) return ret; } -static struct trace_array *trace_array_create(const char *name) +static struct trace_array * +trace_array_create_systems(const char *name, const char *systems) { struct trace_array *tr; int ret; @@ -9535,6 +9695,12 @@ static struct trace_array *trace_array_create(const char *name) if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) goto out_free_tr; + if (systems) { + tr->system_names = kstrdup_const(systems, GFP_KERNEL); + if (!tr->system_names) + goto out_free_tr; + } + tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; cpumask_copy(tr->tracing_cpumask, cpu_all_mask); @@ -9581,12 +9747,18 @@ static struct trace_array *trace_array_create(const char *name) free_trace_buffers(tr); free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); + kfree_const(tr->system_names); kfree(tr->name); kfree(tr); return ERR_PTR(ret); } +static struct trace_array *trace_array_create(const char *name) +{ + return trace_array_create_systems(name, NULL); +} + static int instance_mkdir(const char *name) { struct trace_array *tr; @@ -9612,6 +9784,7 @@ out_unlock: /** * trace_array_get_by_name - Create/Lookup a trace array, given its name. * @name: The name of the trace array to be looked up/created. + * @systems: A list of systems to create event directories for (NULL for all) * * Returns pointer to trace array with given name. * NULL, if it cannot be created. @@ -9625,7 +9798,7 @@ out_unlock: * trace_array_put() is called, user space can not delete it. * */ -struct trace_array *trace_array_get_by_name(const char *name) +struct trace_array *trace_array_get_by_name(const char *name, const char *systems) { struct trace_array *tr; @@ -9637,7 +9810,7 @@ struct trace_array *trace_array_get_by_name(const char *name) goto out_unlock; } - tr = trace_array_create(name); + tr = trace_array_create_systems(name, systems); if (IS_ERR(tr)) tr = NULL; @@ -9684,6 +9857,7 @@ static int __remove_instance(struct trace_array *tr) free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); + kfree_const(tr->system_names); kfree(tr->name); kfree(tr); @@ -9816,6 +9990,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer, tr, &buffer_percent_fops); + trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer, + tr, &buffer_subbuf_size_fops); + create_trace_options_dir(tr); #ifdef CONFIG_TRACER_MAX_TRACE @@ -10402,7 +10579,7 @@ __init static void enable_instances(void) if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE)) do_allocate_snapshot(tok); - tr = trace_array_get_by_name(tok); + tr = trace_array_get_by_name(tok, NULL); if (!tr) { pr_warn("Failed to create instance buffer %s\n", curr_str); continue; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0489e72c8..00f873910 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -377,6 +377,7 @@ struct trace_array { unsigned char trace_flags_index[TRACE_FLAGS_MAX_SIZE]; unsigned int flags; raw_spinlock_t start_lock; + const char *system_names; struct list_head err_log; struct dentry *dir; struct dentry *options; @@ -615,6 +616,7 @@ void tracing_reset_all_online_cpus(void); void tracing_reset_all_online_cpus_unlocked(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); +int tracing_release_generic_tr(struct inode *inode, struct file *file); int tracing_open_file_tr(struct inode *inode, struct file *filp); int tracing_release_file_tr(struct inode *inode, struct file *filp); int tracing_single_release_file_tr(struct inode *inode, struct file *filp); diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 7ccc7a8e1..dbe29b4c6 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -633,7 +633,7 @@ trace_boot_init_instances(struct xbc_node *node) if (!p || *p == '\0') continue; - tr = trace_array_get_by_name(p); + tr = trace_array_get_by_name(p, NULL); if (!tr) { pr_err("Failed to get trace instance %s\n", p); continue; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f29e815ca..52f75c36b 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1670,6 +1670,7 @@ static int trace_format_open(struct inode *inode, struct file *file) return 0; } +#ifdef CONFIG_PERF_EVENTS static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -1684,6 +1685,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } +#endif static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, @@ -1893,9 +1895,9 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, } static ssize_t -show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +show_header_page_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - int (*func)(struct trace_seq *s) = filp->private_data; + struct trace_array *tr = filp->private_data; struct trace_seq *s; int r; @@ -1908,7 +1910,31 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) trace_seq_init(s); - func(s); + ring_buffer_print_page_header(tr->array_buffer.buffer, s); + r = simple_read_from_buffer(ubuf, cnt, ppos, + s->buffer, trace_seq_used(s)); + + kfree(s); + + return r; +} + +static ssize_t +show_header_event_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct trace_seq *s; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + ring_buffer_print_entry_header(s); r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, trace_seq_used(s)); @@ -2128,10 +2154,12 @@ static const struct file_operations ftrace_event_format_fops = { .release = seq_release, }; +#ifdef CONFIG_PERF_EVENTS static const struct file_operations ftrace_event_id_fops = { .read = event_id_read, .llseek = default_llseek, }; +#endif static const struct file_operations ftrace_event_filter_fops = { .open = tracing_open_file_tr, @@ -2165,10 +2193,18 @@ static const struct file_operations ftrace_tr_enable_fops = { .release = subsystem_release, }; -static const struct file_operations ftrace_show_header_fops = { - .open = tracing_open_generic, - .read = show_header, +static const struct file_operations ftrace_show_header_page_fops = { + .open = tracing_open_generic_tr, + .read = show_header_page_file, + .llseek = default_llseek, + .release = tracing_release_generic_tr, +}; + +static const struct file_operations ftrace_show_header_event_fops = { + .open = tracing_open_generic_tr, + .read = show_header_event_file, .llseek = default_llseek, + .release = tracing_release_generic_tr, }; static int @@ -2896,6 +2932,27 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) up_write(&trace_event_sem); } +static bool event_in_systems(struct trace_event_call *call, + const char *systems) +{ + const char *system; + const char *p; + + if (!systems) + return true; + + system = call->class->system; + p = strstr(systems, system); + if (!p) + return false; + + if (p != systems && !isspace(*(p - 1)) && *(p - 1) != ',') + return false; + + p += strlen(system); + return !*p || isspace(*p) || *p == ','; +} + static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) @@ -2905,9 +2962,12 @@ trace_create_new_event(struct trace_event_call *call, struct trace_event_file *file; unsigned int first; + if (!event_in_systems(call, tr->system_names)) + return NULL; + file = kmem_cache_alloc(file_cachep, GFP_TRACE); if (!file) - return NULL; + return ERR_PTR(-ENOMEM); pid_list = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); @@ -2972,8 +3032,17 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr) struct trace_event_file *file; file = trace_create_new_event(call, tr); + /* + * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed + * allocation, or NULL if the event is not part of the tr->system_names. + * When the event is not part of the tr->system_names, return zero, not + * an error. + */ if (!file) - return -ENOMEM; + return 0; + + if (IS_ERR(file)) + return PTR_ERR(file); if (eventdir_initialized) return event_create_dir(tr->event_dir, file); @@ -3012,8 +3081,17 @@ __trace_early_add_new_event(struct trace_event_call *call, int ret; file = trace_create_new_event(call, tr); + /* + * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed + * allocation, or NULL if the event is not part of the tr->system_names. + * When the event is not part of the tr->system_names, return zero, not + * an error. + */ if (!file) - return -ENOMEM; + return 0; + + if (IS_ERR(file)) + return PTR_ERR(file); ret = event_define_fields(call); if (ret) @@ -3752,17 +3830,16 @@ static int events_callback(const char *name, umode_t *mode, void **data, return 1; } - if (strcmp(name, "header_page") == 0) - *data = ring_buffer_print_page_header; - - else if (strcmp(name, "header_event") == 0) - *data = ring_buffer_print_entry_header; + if (strcmp(name, "header_page") == 0) { + *mode = TRACE_MODE_READ; + *fops = &ftrace_show_header_page_fops; - else + } else if (strcmp(name, "header_event") == 0) { + *mode = TRACE_MODE_READ; + *fops = &ftrace_show_header_event_fops; + } else return 0; - *mode = TRACE_MODE_READ; - *fops = &ftrace_show_header_fops; return 1; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5ecf3c8bd..6ece1308d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4805,36 +4805,35 @@ static int parse_actions(struct hist_trigger_data *hist_data) int len; for (i = 0; i < hist_data->attrs->n_actions; i++) { + enum handler_id hid = 0; + char *action_str; + str = hist_data->attrs->action_str[i]; - if ((len = str_has_prefix(str, "onmatch("))) { - char *action_str = str + len; + if ((len = str_has_prefix(str, "onmatch("))) + hid = HANDLER_ONMATCH; + else if ((len = str_has_prefix(str, "onmax("))) + hid = HANDLER_ONMAX; + else if ((len = str_has_prefix(str, "onchange("))) + hid = HANDLER_ONCHANGE; - data = onmatch_parse(tr, action_str); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - } else if ((len = str_has_prefix(str, "onmax("))) { - char *action_str = str + len; + action_str = str + len; - data = track_data_parse(hist_data, action_str, - HANDLER_ONMAX); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - } else if ((len = str_has_prefix(str, "onchange("))) { - char *action_str = str + len; + switch (hid) { + case HANDLER_ONMATCH: + data = onmatch_parse(tr, action_str); + break; + case HANDLER_ONMAX: + case HANDLER_ONCHANGE: + data = track_data_parse(hist_data, action_str, hid); + break; + default: + data = ERR_PTR(-EINVAL); + break; + } - data = track_data_parse(hist_data, action_str, - HANDLER_ONCHANGE); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - } else { - ret = -EINVAL; + if (IS_ERR(data)) { + ret = PTR_ERR(data); break; } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 9365ce407..e76f5e1ef 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -2177,14 +2177,12 @@ static int user_events_open(struct inode *node, struct file *file) static ssize_t user_events_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { - struct iovec iov; struct iov_iter i; if (unlikely(*ppos != 0)) return -EFAULT; - if (unlikely(import_single_range(ITER_SOURCE, (char __user *)ubuf, - count, &iov, &i))) + if (unlikely(import_ubuf(ITER_SOURCE, (char __user *)ubuf, count, &i))) return -EFAULT; return user_events_write_core(file, &i); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 52f8b537d..c4c6e0e00 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -487,8 +487,8 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) return -EINVAL; if (within_notrace_func(tk)) { - pr_warn("Could not probe notrace function %s\n", - trace_kprobe_symbol(tk)); + pr_warn("Could not probe notrace function %ps\n", + (void *)trace_kprobe_address(tk)); return -EINVAL; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 3e7fa44dc..d8b302d01 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1587,12 +1587,11 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter, { struct print_entry *field; struct trace_seq *s = &iter->seq; - int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); seq_print_ip_sym(s, field->ip, flags); - trace_seq_printf(s, ": %.*s", max, field->buf); + trace_seq_printf(s, ": %s", field->buf); return trace_handle_return(s); } @@ -1601,11 +1600,10 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, struct trace_event *event) { struct print_entry *field; - int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); - trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf); + trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf); return trace_handle_return(&iter->seq); } diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 7be97229d..c158d65a8 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -13,9 +13,6 @@ * trace_seq_init() more than once to reset the trace_seq to start * from scratch. * - * The buffer size is currently PAGE_SIZE, although it may become dynamic - * in the future. - * * A write to the buffer will either succeed or fail. That is, unlike * sprintf() there will not be a partial write (well it may write into * the buffer but it wont update the pointers). This allows users to diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 99c051de4..a84b85d8a 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -151,7 +151,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base) return -ENOMEM; if (addr == FETCH_TOKEN_COMM) - ret = strlcpy(dst, current->comm, maxlen); + ret = strscpy(dst, current->comm, maxlen); else ret = strncpy_from_user(dst, src, maxlen); if (ret >= 0) { diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index eabe8bcc7..ce4d99df5 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -231,7 +231,7 @@ void __put_user_ns(struct user_namespace *ns) } EXPORT_SYMBOL(__put_user_ns); -/** +/* * struct idmap_key - holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ @@ -241,7 +241,7 @@ struct idmap_key { u32 count; /* == 0 unless used with map_id_range_down() */ }; -/** +/* * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ @@ -271,7 +271,7 @@ static int cmp_map_id(const void *k, const void *e) return 1; } -/** +/* * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ @@ -288,7 +288,7 @@ map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 cou sizeof(struct uid_gid_extent), cmp_map_id); } -/** +/* * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. @@ -332,12 +332,12 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) return id; } -static u32 map_id_down(struct uid_gid_map *map, u32 id) +u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } -/** +/* * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. @@ -358,7 +358,7 @@ map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) return NULL; } -/** +/* * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ @@ -375,7 +375,7 @@ map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) sizeof(struct uid_gid_extent), cmp_map_id); } -static u32 map_id_up(struct uid_gid_map *map, u32 id) +u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; @@ -770,7 +770,7 @@ static bool mappings_overlap(struct uid_gid_map *new_map, return false; } -/** +/* * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. @@ -839,7 +839,7 @@ static int cmp_extents_reverse(const void *a, const void *b) return 0; } -/** +/* * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 778b40567..03b90d7d2 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -270,7 +270,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) goto error; ret = -ENOMEM; - pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL); + pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) goto error; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5cd6d4e26..81a886229 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -91,7 +91,7 @@ static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts); static DEFINE_PER_CPU(int, hrtimer_interrupts_saved); static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned); static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched); -static unsigned long watchdog_hardlockup_all_cpu_dumped; +static unsigned long hard_lockup_nmi_warn; notrace void arch_touch_nmi_watchdog(void) { @@ -151,12 +151,32 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) */ if (is_hardlockup(cpu)) { unsigned int this_cpu = smp_processor_id(); + unsigned long flags; /* Only print hardlockups once. */ if (per_cpu(watchdog_hardlockup_warned, cpu)) return; + /* + * Prevent multiple hard-lockup reports if one cpu is already + * engaged in dumping all cpu back traces. + */ + if (sysctl_hardlockup_all_cpu_backtrace) { + if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn)) + return; + } + + /* + * NOTE: we call printk_cpu_sync_get_irqsave() after printing + * the lockup message. While it would be nice to serialize + * that printout, we really want to make sure that if some + * other CPU somehow locked up while holding the lock associated + * with printk_cpu_sync_get_irqsave() that we can still at least + * get the message about the lockup out. + */ pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu); + printk_cpu_sync_get_irqsave(flags); + print_modules(); print_irqtrace_events(current); if (cpu == this_cpu) { @@ -164,17 +184,17 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) show_regs(regs); else dump_stack(); + printk_cpu_sync_put_irqrestore(flags); } else { + printk_cpu_sync_put_irqrestore(flags); trigger_single_cpu_backtrace(cpu); } - /* - * Perform multi-CPU dump only once to avoid multiple - * hardlockups generating interleaving traces - */ - if (sysctl_hardlockup_all_cpu_backtrace && - !test_and_set_bit(0, &watchdog_hardlockup_all_cpu_dumped)) + if (sysctl_hardlockup_all_cpu_backtrace) { trigger_allbutcpu_cpu_backtrace(cpu); + if (!hardlockup_panic) + clear_bit_unlock(0, &hard_lockup_nmi_warn); + } if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); @@ -448,6 +468,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + unsigned long flags; if (!watchdog_enabled) return HRTIMER_NORESTART; @@ -514,6 +535,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* Start period for the next softlockup warning. */ update_report_ts(); + printk_cpu_sync_get_irqsave(flags); pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); @@ -523,10 +545,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) show_regs(regs); else dump_stack(); + printk_cpu_sync_put_irqrestore(flags); if (softlockup_all_cpu_backtrace) { trigger_allbutcpu_cpu_backtrace(smp_processor_id()); - clear_bit_unlock(0, &soft_lockup_nmi_warn); + if (!softlockup_panic) + clear_bit_unlock(0, &soft_lockup_nmi_warn); } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8f761417a..7b482a26d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -108,7 +108,7 @@ enum { RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, - WQ_NAME_LEN = 32, + WQ_NAME_LEN = 24, }; /* @@ -122,9 +122,6 @@ enum { * * L: pool->lock protected. Access with pool->lock held. * - * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for - * reads. - * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. @@ -146,9 +143,6 @@ enum { * * WR: wq->mutex protected for writes. RCU protected for reads. * - * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read - * with READ_ONCE() without locking. - * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. @@ -246,18 +240,18 @@ struct pool_workqueue { * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * - * All work items marked with WORK_STRUCT_INACTIVE do not participate in - * nr_active and all work items in pwq->inactive_works are marked with - * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are - * in pwq->inactive_works. Some of them are ready to run in - * pool->worklist or worker->scheduled. Those work itmes are only struct - * wq_barrier which is used for flush_work() and should not participate - * in nr_active. For non-barrier work item, it is marked with - * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. + * All work items marked with WORK_STRUCT_INACTIVE do not participate + * in pwq->nr_active and all work items in pwq->inactive_works are + * marked with WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE + * work items are in pwq->inactive_works. Some of them are ready to + * run in pool->worklist or worker->scheduled. Those work itmes are + * only struct wq_barrier which is used for flush_work() and should + * not participate in pwq->nr_active. For non-barrier work item, it + * is marked with WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ + int max_active; /* L: max active works */ struct list_head inactive_works; /* L: inactive works */ - struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ @@ -284,26 +278,6 @@ struct wq_flusher { struct wq_device; -/* - * Unlike in a per-cpu workqueue where max_active limits its concurrency level - * on each CPU, in an unbound workqueue, max_active applies to the whole system. - * As sharing a single nr_active across multiple sockets can be very expensive, - * the counting and enforcement is per NUMA node. - * - * The following struct is used to enforce per-node max_active. When a pwq wants - * to start executing a work item, it should increment ->nr using - * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over - * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish - * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in - * round-robin order. - */ -struct wq_node_nr_active { - int max; /* per-node max_active */ - atomic_t nr; /* per-node nr_active */ - raw_spinlock_t lock; /* nests inside pool locks */ - struct list_head pending_pwqs; /* LN: pwqs with inactive works */ -}; - /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. @@ -324,15 +298,10 @@ struct workqueue_struct { struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ - - /* See alloc_workqueue() function comment for info on min/max_active */ - int max_active; /* WO: max active works */ - int min_active; /* WO: min active works */ - int saved_max_active; /* WQ: saved max_active */ - int saved_min_active; /* WQ: saved min_active */ + int saved_max_active; /* WQ: saved pwq max_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ - struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ + struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ @@ -354,7 +323,6 @@ struct workqueue_struct { /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */ - struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; static struct kmem_cache *pwq_cache; @@ -413,6 +381,12 @@ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; +/* PL: user requested unbound cpumask via sysfs */ +static cpumask_var_t wq_requested_unbound_cpumask; + +/* PL: isolated cpumask to be excluded from unbound cpumask */ +static cpumask_var_t wq_isolated_cpumask; + /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; @@ -658,36 +632,6 @@ static int worker_pool_assign_id(struct worker_pool *pool) return ret; } -static struct pool_workqueue __rcu ** -unbound_pwq_slot(struct workqueue_struct *wq, int cpu) -{ - if (cpu >= 0) - return per_cpu_ptr(wq->cpu_pwq, cpu); - else - return &wq->dfl_pwq; -} - -/* @cpu < 0 for dfl_pwq */ -static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) -{ - return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), - lockdep_is_held(&wq_pool_mutex) || - lockdep_is_held(&wq->mutex)); -} - -/** - * unbound_effective_cpumask - effective cpumask of an unbound workqueue - * @wq: workqueue of interest - * - * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which - * is masked with wq_unbound_cpumask to determine the effective cpumask. The - * default pwq is always mapped to the pool with the current effective cpumask. - */ -static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) -{ - return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; -} - static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; @@ -1457,71 +1401,6 @@ work_func_t wq_worker_last_func(struct task_struct *task) return worker->last_func; } -/** - * wq_node_nr_active - Determine wq_node_nr_active to use - * @wq: workqueue of interest - * @node: NUMA node, can be %NUMA_NO_NODE - * - * Determine wq_node_nr_active to use for @wq on @node. Returns: - * - * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. - * - * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. - * - * - Otherwise, node_nr_active[@node]. - */ -static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, - int node) -{ - if (!(wq->flags & WQ_UNBOUND)) - return NULL; - - if (node == NUMA_NO_NODE) - node = nr_node_ids; - - return wq->node_nr_active[node]; -} - -/** - * wq_update_node_max_active - Update per-node max_actives to use - * @wq: workqueue to update - * @off_cpu: CPU that's going down, -1 if a CPU is not going down - * - * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is - * distributed among nodes according to the proportions of numbers of online - * cpus. The result is always between @wq->min_active and max_active. - */ -static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) -{ - struct cpumask *effective = unbound_effective_cpumask(wq); - int min_active = READ_ONCE(wq->min_active); - int max_active = READ_ONCE(wq->max_active); - int total_cpus, node; - - lockdep_assert_held(&wq->mutex); - - if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) - off_cpu = -1; - - total_cpus = cpumask_weight_and(effective, cpu_online_mask); - if (off_cpu >= 0) - total_cpus--; - - for_each_node(node) { - int node_cpus; - - node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); - if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) - node_cpus--; - - wq_node_nr_active(wq, node)->max = - clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), - min_active, max_active); - } - - wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active; -} - /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get @@ -1574,293 +1453,24 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) } } -static bool pwq_is_empty(struct pool_workqueue *pwq) -{ - return !pwq->nr_active && list_empty(&pwq->inactive_works); -} - -static void __pwq_activate_work(struct pool_workqueue *pwq, - struct work_struct *work) +static void pwq_activate_inactive_work(struct work_struct *work) { - unsigned long *wdb = work_data_bits(work); + struct pool_workqueue *pwq = get_work_pwq(work); - WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); - __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); -} - -/** - * pwq_activate_work - Activate a work item if inactive - * @pwq: pool_workqueue @work belongs to - * @work: work item to activate - * - * Returns %true if activated. %false if already active. - */ -static bool pwq_activate_work(struct pool_workqueue *pwq, - struct work_struct *work) -{ - struct worker_pool *pool = pwq->pool; - struct wq_node_nr_active *nna; - - lockdep_assert_held(&pool->lock); - - if (!(*work_data_bits(work) & WORK_STRUCT_INACTIVE)) - return false; - - nna = wq_node_nr_active(pwq->wq, pool->node); - if (nna) - atomic_inc(&nna->nr); - + __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); pwq->nr_active++; - __pwq_activate_work(pwq, work); - return true; -} - -static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) -{ - int max = READ_ONCE(nna->max); - - while (true) { - int old, tmp; - - old = atomic_read(&nna->nr); - if (old >= max) - return false; - tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1); - if (tmp == old) - return true; - } -} - -/** - * pwq_tryinc_nr_active - Try to increment nr_active for a pwq - * @pwq: pool_workqueue of interest - * @fill: max_active may have increased, try to increase concurrency level - * - * Try to increment nr_active for @pwq. Returns %true if an nr_active count is - * successfully obtained. %false otherwise. - */ -static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) -{ - struct workqueue_struct *wq = pwq->wq; - struct worker_pool *pool = pwq->pool; - struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); - bool obtained = false; - - lockdep_assert_held(&pool->lock); - - if (!nna) { - /* per-cpu workqueue, pwq->nr_active is sufficient */ - obtained = pwq->nr_active < READ_ONCE(wq->max_active); - goto out; - } - - /* - * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is - * already waiting on $nna, pwq_dec_nr_active() will maintain the - * concurrency level. Don't jump the line. - * - * We need to ignore the pending test after max_active has increased as - * pwq_dec_nr_active() can only maintain the concurrency level but not - * increase it. This is indicated by @fill. - */ - if (!list_empty(&pwq->pending_node) && likely(!fill)) - goto out; - - obtained = tryinc_node_nr_active(nna); - if (obtained) - goto out; - - /* - * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs - * and try again. The smp_mb() is paired with the implied memory barrier - * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either - * we see the decremented $nna->nr or they see non-empty - * $nna->pending_pwqs. - */ - raw_spin_lock(&nna->lock); - - if (list_empty(&pwq->pending_node)) - list_add_tail(&pwq->pending_node, &nna->pending_pwqs); - else if (likely(!fill)) - goto out_unlock; - - smp_mb(); - - obtained = tryinc_node_nr_active(nna); - - /* - * If @fill, @pwq might have already been pending. Being spuriously - * pending in cold paths doesn't affect anything. Let's leave it be. - */ - if (obtained && likely(!fill)) - list_del_init(&pwq->pending_node); - -out_unlock: - raw_spin_unlock(&nna->lock); -out: - if (obtained) - pwq->nr_active++; - return obtained; -} - -/** - * pwq_activate_first_inactive - Activate the first inactive work item on a pwq - * @pwq: pool_workqueue of interest - * @fill: max_active may have increased, try to increase concurrency level - * - * Activate the first inactive work item of @pwq if available and allowed by - * max_active limit. - * - * Returns %true if an inactive work item has been activated. %false if no - * inactive work item is found or max_active limit is reached. - */ -static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) -{ - struct work_struct *work = - list_first_entry_or_null(&pwq->inactive_works, - struct work_struct, entry); - - if (work && pwq_tryinc_nr_active(pwq, fill)) { - __pwq_activate_work(pwq, work); - return true; - } else { - return false; - } -} - -/** - * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active - * @nna: wq_node_nr_active to activate a pending pwq for - * @caller_pool: worker_pool the caller is locking - * - * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. - * @caller_pool may be unlocked and relocked to lock other worker_pools. - */ -static void node_activate_pending_pwq(struct wq_node_nr_active *nna, - struct worker_pool *caller_pool) -{ - struct worker_pool *locked_pool = caller_pool; - struct pool_workqueue *pwq; - struct work_struct *work; - - lockdep_assert_held(&caller_pool->lock); - - raw_spin_lock(&nna->lock); -retry: - pwq = list_first_entry_or_null(&nna->pending_pwqs, - struct pool_workqueue, pending_node); - if (!pwq) - goto out_unlock; - - /* - * If @pwq is for a different pool than @locked_pool, we need to lock - * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock - * / lock dance. For that, we also need to release @nna->lock as it's - * nested inside pool locks. - */ - if (pwq->pool != locked_pool) { - raw_spin_unlock(&locked_pool->lock); - locked_pool = pwq->pool; - if (!raw_spin_trylock(&locked_pool->lock)) { - raw_spin_unlock(&nna->lock); - raw_spin_lock(&locked_pool->lock); - raw_spin_lock(&nna->lock); - goto retry; - } - } - - /* - * $pwq may not have any inactive work items due to e.g. cancellations. - * Drop it from pending_pwqs and see if there's another one. - */ - work = list_first_entry_or_null(&pwq->inactive_works, - struct work_struct, entry); - if (!work) { - list_del_init(&pwq->pending_node); - goto retry; - } - - /* - * Acquire an nr_active count and activate the inactive work item. If - * $pwq still has inactive work items, rotate it to the end of the - * pending_pwqs so that we round-robin through them. This means that - * inactive work items are not activated in queueing order which is fine - * given that there has never been any ordering across different pwqs. - */ - if (likely(tryinc_node_nr_active(nna))) { - pwq->nr_active++; - __pwq_activate_work(pwq, work); - - if (list_empty(&pwq->inactive_works)) - list_del_init(&pwq->pending_node); - else - list_move_tail(&pwq->pending_node, &nna->pending_pwqs); - - /* if activating a foreign pool, make sure it's running */ - if (pwq->pool != caller_pool) - kick_pool(pwq->pool); - } - -out_unlock: - raw_spin_unlock(&nna->lock); - if (locked_pool != caller_pool) { - raw_spin_unlock(&locked_pool->lock); - raw_spin_lock(&caller_pool->lock); - } } -/** - * pwq_dec_nr_active - Retire an active count - * @pwq: pool_workqueue of interest - * - * Decrement @pwq's nr_active and try to activate the first inactive work item. - * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. - */ -static void pwq_dec_nr_active(struct pool_workqueue *pwq) +static void pwq_activate_first_inactive(struct pool_workqueue *pwq) { - struct worker_pool *pool = pwq->pool; - struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); - - lockdep_assert_held(&pool->lock); - - /* - * @pwq->nr_active should be decremented for both percpu and unbound - * workqueues. - */ - pwq->nr_active--; - - /* - * For a percpu workqueue, it's simple. Just need to kick the first - * inactive work item on @pwq itself. - */ - if (!nna) { - pwq_activate_first_inactive(pwq, false); - return; - } - - /* - * If @pwq is for an unbound workqueue, it's more complicated because - * multiple pwqs and pools may be sharing the nr_active count. When a - * pwq needs to wait for an nr_active count, it puts itself on - * $nna->pending_pwqs. The following atomic_dec_return()'s implied - * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to - * guarantee that either we see non-empty pending_pwqs or they see - * decremented $nna->nr. - * - * $nna->max may change as CPUs come online/offline and @pwq->wq's - * max_active gets updated. However, it is guaranteed to be equal to or - * larger than @pwq->wq->min_active which is above zero unless freezing. - * This maintains the forward progress guarantee. - */ - if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) - return; + struct work_struct *work = list_first_entry(&pwq->inactive_works, + struct work_struct, entry); - if (!list_empty(&nna->pending_pwqs)) - node_activate_pending_pwq(nna, pool); + pwq_activate_inactive_work(work); } /** @@ -1878,8 +1488,14 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_ { int color = get_work_color(work_data); - if (!(work_data & WORK_STRUCT_INACTIVE)) - pwq_dec_nr_active(pwq); + if (!(work_data & WORK_STRUCT_INACTIVE)) { + pwq->nr_active--; + if (!list_empty(&pwq->inactive_works)) { + /* one down, submit an inactive one */ + if (pwq->nr_active < pwq->max_active) + pwq_activate_first_inactive(pwq); + } + } pwq->nr_in_flight[color]--; @@ -1992,7 +1608,8 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, * management later on and cause stall. Make sure the work * item is activated before grabbing. */ - pwq_activate_work(pwq, work); + if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) + pwq_activate_inactive_work(work); list_del_init(&work->entry); pwq_dec_nr_in_flight(pwq, *work_data_bits(work)); @@ -2176,16 +1793,12 @@ retry: pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); - /* - * Limit the number of concurrently active work items to max_active. - * @work must also queue behind existing inactive work items to maintain - * ordering when max_active changes. See wq_adjust_max_active(). - */ - if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { + if (likely(pwq->nr_active < pwq->max_active)) { if (list_empty(&pool->worklist)) pool->watchdog_ts = jiffies; trace_workqueue_activate_work(work); + pwq->nr_active++; insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { @@ -3414,7 +3027,7 @@ static void insert_wq_barrier(struct pool_workqueue *pwq, barr->task = current; - /* The barrier work item does not participate in nr_active. */ + /* The barrier work item does not participate in pwq->nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* @@ -3703,7 +3316,7 @@ reflush: bool drained; raw_spin_lock_irq(&pwq->pool->lock); - drained = pwq_is_empty(pwq); + drained = !pwq->nr_active && list_empty(&pwq->inactive_works); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) @@ -4314,65 +3927,11 @@ static void wq_free_lockdep(struct workqueue_struct *wq) } #endif -static void free_node_nr_active(struct wq_node_nr_active **nna_ar) -{ - int node; - - for_each_node(node) { - kfree(nna_ar[node]); - nna_ar[node] = NULL; - } - - kfree(nna_ar[nr_node_ids]); - nna_ar[nr_node_ids] = NULL; -} - -static void init_node_nr_active(struct wq_node_nr_active *nna) -{ - atomic_set(&nna->nr, 0); - raw_spin_lock_init(&nna->lock); - INIT_LIST_HEAD(&nna->pending_pwqs); -} - -/* - * Each node's nr_active counter will be accessed mostly from its own node and - * should be allocated in the node. - */ -static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) -{ - struct wq_node_nr_active *nna; - int node; - - for_each_node(node) { - nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); - if (!nna) - goto err_free; - init_node_nr_active(nna); - nna_ar[node] = nna; - } - - /* [nr_node_ids] is used as the fallback */ - nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); - if (!nna) - goto err_free; - init_node_nr_active(nna); - nna_ar[nr_node_ids] = nna; - - return 0; - -err_free: - free_node_nr_active(nna_ar); - return -ENOMEM; -} - static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); - if (wq->flags & WQ_UNBOUND) - free_node_nr_active(wq->node_nr_active); - wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); @@ -4571,15 +4130,6 @@ static void pwq_release_workfn(struct kthread_work *work) mutex_unlock(&wq_pool_mutex); } - if (!list_empty(&pwq->pending_node)) { - struct wq_node_nr_active *nna = - wq_node_nr_active(pwq->wq, pwq->pool->node); - - raw_spin_lock_irq(&nna->lock); - list_del_init(&pwq->pending_node); - raw_spin_unlock_irq(&nna->lock); - } - call_rcu(&pwq->rcu, rcu_free_pwq); /* @@ -4592,6 +4142,50 @@ static void pwq_release_workfn(struct kthread_work *work) } } +/** + * pwq_adjust_max_active - update a pwq's max_active to the current setting + * @pwq: target pool_workqueue + * + * If @pwq isn't freezing, set @pwq->max_active to the associated + * workqueue's saved_max_active and activate inactive work items + * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. + */ +static void pwq_adjust_max_active(struct pool_workqueue *pwq) +{ + struct workqueue_struct *wq = pwq->wq; + bool freezable = wq->flags & WQ_FREEZABLE; + unsigned long flags; + + /* for @wq->saved_max_active */ + lockdep_assert_held(&wq->mutex); + + /* fast exit for non-freezable wqs */ + if (!freezable && pwq->max_active == wq->saved_max_active) + return; + + /* this function can be called during early boot w/ irq disabled */ + raw_spin_lock_irqsave(&pwq->pool->lock, flags); + + /* + * During [un]freezing, the caller is responsible for ensuring that + * this function is called at least once after @workqueue_freezing + * is updated and visible. + */ + if (!freezable || !workqueue_freezing) { + pwq->max_active = wq->saved_max_active; + + while (!list_empty(&pwq->inactive_works) && + pwq->nr_active < pwq->max_active) + pwq_activate_first_inactive(pwq); + + kick_pool(pwq->pool); + } else { + pwq->max_active = 0; + } + + raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); +} + /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) @@ -4605,7 +4199,6 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); - INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); @@ -4625,6 +4218,9 @@ static void link_pwq(struct pool_workqueue *pwq) /* set the matching work_color */ pwq->work_color = wq->work_color; + /* sync max_active to the current setting */ + pwq_adjust_max_active(pwq); + /* link in @pwq */ list_add_rcu(&pwq->pwqs_node, &wq->pwqs); } @@ -4693,11 +4289,10 @@ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu, "possible intersect\n"); } -/* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ +/* install @pwq into @wq's cpu_pwq and return the old pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { - struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); @@ -4706,8 +4301,8 @@ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, /* link_pwq() can handle duplicate calls */ link_pwq(pwq); - old_pwq = rcu_access_pointer(*slot); - rcu_assign_pointer(*slot, pwq); + old_pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu)); + rcu_assign_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu), pwq); return old_pwq; } @@ -4807,31 +4402,18 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); - /* save the previous pwqs and install the new ones */ + /* save the previous pwq and install the new one */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); - ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); - /* update node_nr_active->max */ - wq_update_node_max_active(ctx->wq, -1); + /* @dfl_pwq might not have been used, ensure it's linked */ + link_pwq(ctx->dfl_pwq); + swap(ctx->wq->dfl_pwq, ctx->dfl_pwq); mutex_unlock(&ctx->wq->mutex); } -static void apply_wqattrs_lock(void) -{ - /* CPUs should stay stable across pwq creations and installations */ - cpus_read_lock(); - mutex_lock(&wq_pool_mutex); -} - -static void apply_wqattrs_unlock(void) -{ - mutex_unlock(&wq_pool_mutex); - cpus_read_unlock(); -} - static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { @@ -4937,7 +4519,9 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu, off_cpu); - if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) + pwq = rcu_dereference_protected(*per_cpu_ptr(wq->cpu_pwq, cpu), + lockdep_is_held(&wq_pool_mutex)); + if (wqattrs_equal(target_attrs, pwq->pool->attrs)) return; /* create a new pwq */ @@ -4955,11 +4539,10 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, use_dfl_pwq: mutex_lock(&wq->mutex); - pwq = unbound_pwq(wq, -1); - raw_spin_lock_irq(&pwq->pool->lock); - get_pwq(pwq); - raw_spin_unlock_irq(&pwq->pool->lock); - old_pwq = install_unbound_pwq(wq, cpu, pwq); + raw_spin_lock_irq(&wq->dfl_pwq->pool->lock); + get_pwq(wq->dfl_pwq); + raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock); + old_pwq = install_unbound_pwq(wq, cpu, wq->dfl_pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); @@ -4997,13 +4580,10 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { - struct pool_workqueue *dfl_pwq; - ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ - dfl_pwq = rcu_access_pointer(wq->dfl_pwq); - WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || - wq->pwqs.prev != &dfl_pwq->pwqs_node), + WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || + wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); @@ -5078,69 +4658,6 @@ static int init_rescuer(struct workqueue_struct *wq) return 0; } -/** - * wq_adjust_max_active - update a wq's max_active to the current setting - * @wq: target workqueue - * - * If @wq isn't freezing, set @wq->max_active to the saved_max_active and - * activate inactive work items accordingly. If @wq is freezing, clear - * @wq->max_active to zero. - */ -static void wq_adjust_max_active(struct workqueue_struct *wq) -{ - bool activated; - int new_max, new_min; - - lockdep_assert_held(&wq->mutex); - - if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { - new_max = 0; - new_min = 0; - } else { - new_max = wq->saved_max_active; - new_min = wq->saved_min_active; - } - - if (wq->max_active == new_max && wq->min_active == new_min) - return; - - /* - * Update @wq->max/min_active and then kick inactive work items if more - * active work items are allowed. This doesn't break work item ordering - * because new work items are always queued behind existing inactive - * work items if there are any. - */ - WRITE_ONCE(wq->max_active, new_max); - WRITE_ONCE(wq->min_active, new_min); - - if (wq->flags & WQ_UNBOUND) - wq_update_node_max_active(wq, -1); - - if (new_max == 0) - return; - - /* - * Round-robin through pwq's activating the first inactive work item - * until max_active is filled. - */ - do { - struct pool_workqueue *pwq; - - activated = false; - for_each_pwq(pwq, wq) { - unsigned long flags; - - /* can be called during early boot w/ irq disabled */ - raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq_activate_first_inactive(pwq, true)) { - activated = true; - kick_pool(pwq->pool); - } - raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); - } - } while (activated); -} - __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, @@ -5148,8 +4665,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, { va_list args; struct workqueue_struct *wq; - size_t wq_size; - int name_len; + struct pool_workqueue *pwq; /* * Unbound && max_active == 1 used to imply ordered, which is no longer @@ -5165,12 +4681,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, flags |= WQ_UNBOUND; /* allocate wq and format name */ - if (flags & WQ_UNBOUND) - wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); - else - wq_size = sizeof(*wq); - - wq = kzalloc(wq_size, GFP_KERNEL); + wq = kzalloc(sizeof(*wq), GFP_KERNEL); if (!wq) return NULL; @@ -5181,22 +4692,15 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, } va_start(args, max_active); - name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); + vsnprintf(wq->name, sizeof(wq->name), fmt, args); va_end(args); - if (name_len >= WQ_NAME_LEN) - pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", - wq->name); - max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); /* init wq */ wq->flags = flags; - wq->max_active = max_active; - wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); - wq->saved_max_active = wq->max_active; - wq->saved_min_active = wq->min_active; + wq->saved_max_active = max_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); @@ -5207,13 +4711,8 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, wq_init_lockdep(wq); INIT_LIST_HEAD(&wq->list); - if (flags & WQ_UNBOUND) { - if (alloc_node_nr_active(wq->node_nr_active) < 0) - goto err_unreg_lockdep; - } - if (alloc_and_link_pwqs(wq) < 0) - goto err_free_node_nr_active; + goto err_unreg_lockdep; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; @@ -5229,7 +4728,8 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); - wq_adjust_max_active(wq); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); @@ -5238,9 +4738,6 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, return wq; -err_free_node_nr_active: - if (wq->flags & WQ_UNBOUND) - free_node_nr_active(wq->node_nr_active); err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); @@ -5262,9 +4759,9 @@ static bool pwq_busy(struct pool_workqueue *pwq) if (pwq->nr_in_flight[i]) return true; - if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) + if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) return true; - if (!pwq_is_empty(pwq)) + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) return true; return false; @@ -5346,12 +4843,13 @@ void destroy_workqueue(struct workqueue_struct *wq) rcu_read_lock(); for_each_possible_cpu(cpu) { - put_pwq_unlocked(unbound_pwq(wq, cpu)); - RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); + pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu)); + RCU_INIT_POINTER(*per_cpu_ptr(wq->cpu_pwq, cpu), NULL); + put_pwq_unlocked(pwq); } - put_pwq_unlocked(unbound_pwq(wq, -1)); - RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); + put_pwq_unlocked(wq->dfl_pwq); + wq->dfl_pwq = NULL; rcu_read_unlock(); } @@ -5362,14 +4860,15 @@ EXPORT_SYMBOL_GPL(destroy_workqueue); * @wq: target workqueue * @max_active: new max_active value. * - * Set max_active of @wq to @max_active. See the alloc_workqueue() function - * comment. + * Set max_active of @wq to @max_active. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { + struct pool_workqueue *pwq; + /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return; @@ -5380,10 +4879,9 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) wq->flags &= ~__WQ_ORDERED; wq->saved_max_active = max_active; - if (wq->flags & WQ_UNBOUND) - wq->saved_min_active = min(wq->saved_min_active, max_active); - wq_adjust_max_active(wq); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } @@ -5630,8 +5128,8 @@ static void show_pwq(struct pool_workqueue *pwq) pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); - pr_cont(" active=%d refcnt=%d%s\n", - pwq->nr_active, pwq->refcnt, + pr_cont(" active=%d/%d refcnt=%d%s\n", + pwq->nr_active, pwq->max_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { @@ -5705,7 +5203,7 @@ void show_one_workqueue(struct workqueue_struct *wq) unsigned long flags; for_each_pwq(pwq, wq) { - if (!pwq_is_empty(pwq)) { + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { idle = false; break; } @@ -5717,7 +5215,7 @@ void show_one_workqueue(struct workqueue_struct *wq) for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (!pwq_is_empty(pwq)) { + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks @@ -6064,10 +5562,6 @@ int workqueue_online_cpu(unsigned int cpu) for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, true); - - mutex_lock(&wq->mutex); - wq_update_node_max_active(wq, -1); - mutex_unlock(&wq->mutex); } } @@ -6096,10 +5590,6 @@ int workqueue_offline_cpu(unsigned int cpu) for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, false); - - mutex_lock(&wq->mutex); - wq_update_node_max_active(wq, cpu); - mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); @@ -6187,6 +5677,7 @@ EXPORT_SYMBOL_GPL(work_on_cpu_safe_key); void freeze_workqueues_begin(void) { struct workqueue_struct *wq; + struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); @@ -6195,7 +5686,8 @@ void freeze_workqueues_begin(void) list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); - wq_adjust_max_active(wq); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } @@ -6260,6 +5752,7 @@ out_unlock: void thaw_workqueues(void) { struct workqueue_struct *wq; + struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); @@ -6271,7 +5764,8 @@ void thaw_workqueues(void) /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); - wq_adjust_max_active(wq); + for_each_pwq(pwq, wq) + pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } @@ -6320,39 +5814,40 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) } /** - * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask - * @cpumask: the cpumask to set - * - * The low-level workqueues cpumask is a global cpumask that limits - * the affinity of all unbound workqueues. This function check the @cpumask - * and apply it to all unbound workqueues and updates all pwqs of them. + * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask + * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask * - * Return: 0 - Success - * -EINVAL - Invalid @cpumask - * -ENOMEM - Failed to allocate memory for attrs or pwqs. + * This function can be called from cpuset code to provide a set of isolated + * CPUs that should be excluded from wq_unbound_cpumask. The caller must hold + * either cpus_read_lock or cpus_write_lock. */ -int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) +int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask) { - int ret = -EINVAL; + cpumask_var_t cpumask; + int ret = 0; + + if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + + lockdep_assert_cpus_held(); + mutex_lock(&wq_pool_mutex); + + /* Save the current isolated cpumask & export it via sysfs */ + cpumask_copy(wq_isolated_cpumask, exclude_cpumask); /* - * Not excluding isolated cpus on purpose. - * If the user wishes to include them, we allow that. + * If the operation fails, it will fall back to + * wq_requested_unbound_cpumask which is initially set to + * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten + * by any subsequent write to workqueue/cpumask sysfs file. */ - cpumask_and(cpumask, cpumask, cpu_possible_mask); - if (!cpumask_empty(cpumask)) { - apply_wqattrs_lock(); - if (cpumask_equal(cpumask, wq_unbound_cpumask)) { - ret = 0; - goto out_unlock; - } - + if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask)) + cpumask_copy(cpumask, wq_requested_unbound_cpumask); + if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); -out_unlock: - apply_wqattrs_unlock(); - } - + mutex_unlock(&wq_pool_mutex); + free_cpumask_var(cpumask); return ret; } @@ -6474,6 +5969,19 @@ static struct attribute *wq_sysfs_attrs[] = { }; ATTRIBUTE_GROUPS(wq_sysfs); +static void apply_wqattrs_lock(void) +{ + /* CPUs should stay stable across pwq creations and installations */ + cpus_read_lock(); + mutex_lock(&wq_pool_mutex); +} + +static void apply_wqattrs_unlock(void) +{ + mutex_unlock(&wq_pool_mutex); + cpus_read_unlock(); +} + static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -6650,19 +6158,74 @@ static struct bus_type wq_subsys = { .dev_groups = wq_sysfs_groups, }; -static ssize_t wq_unbound_cpumask_show(struct device *dev, - struct device_attribute *attr, char *buf) +/** + * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask + * @cpumask: the cpumask to set + * + * The low-level workqueues cpumask is a global cpumask that limits + * the affinity of all unbound workqueues. This function check the @cpumask + * and apply it to all unbound workqueues and updates all pwqs of them. + * + * Return: 0 - Success + * -EINVAL - Invalid @cpumask + * -ENOMEM - Failed to allocate memory for attrs or pwqs. + */ +static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) +{ + int ret = -EINVAL; + + /* + * Not excluding isolated cpus on purpose. + * If the user wishes to include them, we allow that. + */ + cpumask_and(cpumask, cpumask, cpu_possible_mask); + if (!cpumask_empty(cpumask)) { + apply_wqattrs_lock(); + cpumask_copy(wq_requested_unbound_cpumask, cpumask); + if (cpumask_equal(cpumask, wq_unbound_cpumask)) { + ret = 0; + goto out_unlock; + } + + ret = workqueue_apply_unbound_cpumask(cpumask); + +out_unlock: + apply_wqattrs_unlock(); + } + + return ret; +} + +static ssize_t __wq_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); - written = scnprintf(buf, PAGE_SIZE, "%*pb\n", - cpumask_pr_args(wq_unbound_cpumask)); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } +static ssize_t wq_unbound_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); +} + +static ssize_t wq_requested_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); +} + +static ssize_t wq_isolated_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); +} + static ssize_t wq_unbound_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -6680,9 +6243,13 @@ static ssize_t wq_unbound_cpumask_store(struct device *dev, return ret ? ret : count; } -static struct device_attribute wq_sysfs_cpumask_attr = +static struct device_attribute wq_sysfs_cpumask_attrs[] = { __ATTR(cpumask, 0644, wq_unbound_cpumask_show, - wq_unbound_cpumask_store); + wq_unbound_cpumask_store), + __ATTR(cpumask_requested, 0444, wq_requested_cpumask_show, NULL), + __ATTR(cpumask_isolated, 0444, wq_isolated_cpumask_show, NULL), + __ATTR_NULL, +}; static int __init wq_sysfs_init(void) { @@ -6695,7 +6262,13 @@ static int __init wq_sysfs_init(void) dev_root = bus_get_dev_root(&wq_subsys); if (dev_root) { - err = device_create_file(dev_root, &wq_sysfs_cpumask_attr); + struct device_attribute *attr; + + for (attr = wq_sysfs_cpumask_attrs; attr->attr.name; attr++) { + err = device_create_file(dev_root, attr); + if (err) + break; + } put_device(dev_root); } return err; @@ -7037,12 +6610,17 @@ void __init workqueue_init_early(void) BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); + cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); + cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); + pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); wq_update_pod_attrs_buf = alloc_workqueue_attrs(); @@ -7109,7 +6687,7 @@ void __init workqueue_init_early(void) WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); - system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", + system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || @@ -7296,12 +6874,8 @@ void __init workqueue_init_topology(void) * combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { wq_update_pod(wq, cpu, cpu, true); - if (wq->flags & WQ_UNBOUND) { - mutex_lock(&wq->mutex); - wq_update_node_max_active(wq, -1); - mutex_unlock(&wq->mutex); } } -- cgit v1.2.3