diff options
Diffstat (limited to 'kernel')
167 files changed, 5524 insertions, 2240 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index 986c8214dabf..179848ad33e9 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -84,7 +84,6 @@ static struct ctl_table kern_acct_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static __init int kernel_acct_sysctls_init(void) diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 1b07e6f12a07..f2f38903b2fe 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -463,7 +463,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) int n; fsnotify_group_lock(audit_tree_group); - mark = fsnotify_find_mark(&inode->i_fsnotify_marks, audit_tree_group); + mark = fsnotify_find_inode_mark(inode, audit_tree_group); if (!mark) return create_chunk(inode, tree); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 7a98cd176a12..7f358740e958 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -90,7 +90,7 @@ static inline struct audit_parent *audit_find_parent(struct inode *inode) struct audit_parent *parent = NULL; struct fsnotify_mark *entry; - entry = fsnotify_find_mark(&inode->i_fsnotify_marks, audit_watch_group); + entry = fsnotify_find_inode_mark(inode, audit_watch_group); if (entry) parent = container_of(entry, struct audit_parent, mark); diff --git a/kernel/bounds.c b/kernel/bounds.c index c5a9fcd2d622..29b2cd00df2c 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/Kconfig b/kernel/bpf/Kconfig index bc25f5098a25..17067dcb4386 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -28,7 +28,7 @@ config BPF_SYSCALL bool "Enable bpf() system call" select BPF select IRQ_WORK - select TASKS_RCU if PREEMPTION + select NEED_TASKS_RCU select TASKS_TRACE_RCU select BINARY_PRINTF select NET_SOCK_MSG if NET @@ -43,7 +43,7 @@ config BPF_JIT bool "Enable BPF Just In Time compiler" depends on BPF depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT - depends on MODULES + select EXECMEM help BPF programs are normally handled by a BPF interpreter. This option allows the kernel to generate native code when a program is loaded diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 368c5d86b5b7..7eb9ad3a3ae6 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 token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o @@ -44,6 +44,9 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o obj-$(CONFIG_BPF_SYSCALL) += cpumask.o obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif +ifneq ($(CONFIG_CRYPTO),) +obj-$(CONFIG_BPF_SYSCALL) += crypto.o +endif obj-$(CONFIG_BPF_PRELOAD) += preload/ obj-$(CONFIG_BPF_SYSCALL) += relo_core.o diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 86571e760dd6..583ee4fe48ef 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -37,8 +37,8 @@ */ /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ -#define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8) -#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ) +#define GUARD_SZ (1ull << sizeof_field(struct bpf_insn, off) * 8) +#define KERN_VM_SZ (SZ_4G + GUARD_SZ) struct bpf_arena { struct bpf_map map; @@ -110,7 +110,7 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr) return ERR_PTR(-EINVAL); vm_range = (u64)attr->max_entries * PAGE_SIZE; - if (vm_range > (1ull << 32)) + if (vm_range > SZ_4G) return ERR_PTR(-E2BIG); if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32)) @@ -251,7 +251,7 @@ static vm_fault_t arena_vm_fault(struct vm_fault *vmf) int ret; kbase = bpf_arena_get_kern_vm_start(arena); - kaddr = kbase + (u32)(vmf->address & PAGE_MASK); + kaddr = kbase + (u32)(vmf->address); guard(mutex)(&arena->lock); page = vmalloc_to_page((void *)kaddr); @@ -301,7 +301,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad if (pgoff) return -EINVAL; - if (len > (1ull << 32)) + if (len > SZ_4G) return -E2BIG; /* if user_vm_start was specified at arena creation time */ @@ -314,7 +314,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad return -EINVAL; } - ret = current->mm->get_unmapped_area(filp, addr, len * 2, 0, flags); + ret = mm_get_unmapped_area(current->mm, filp, addr, len * 2, 0, flags); if (IS_ERR_VALUE(ret)) return ret; if ((ret >> 32) == ((ret + len - 1) >> 32)) @@ -322,7 +322,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad if (WARN_ON_ONCE(arena->user_vm_start)) /* checks at map creation time should prevent this */ return -EFAULT; - return round_up(ret, 1ull << 32); + return round_up(ret, SZ_4G); } static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) @@ -346,7 +346,7 @@ static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) return -EBUSY; /* Earlier checks should prevent this */ - if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff)) + if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > SZ_4G || vma->vm_pgoff)) return -EFAULT; if (remember_vma(arena, vma)) @@ -420,7 +420,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt if (uaddr & ~PAGE_MASK) return 0; pgoff = compute_pgoff(arena, uaddr); - if (pgoff + page_cnt > page_cnt_max) + if (pgoff > page_cnt_max - page_cnt) /* requested address will be outside of user VMA */ return 0; } @@ -447,7 +447,13 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt goto out; uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE); - /* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */ + /* Earlier checks made sure that uaddr32 + page_cnt * PAGE_SIZE - 1 + * will not overflow 32-bit. Lower 32-bit need to represent + * contiguous user address range. + * Map these pages at kern_vm_start base. + * kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE - 1 can overflow + * lower 32-bit and it's ok. + */ ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32, kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages); if (ret) { @@ -510,6 +516,11 @@ static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt) if (!page) continue; if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */ + /* Optimization for the common case of page_cnt==1: + * If page wasn't mapped into some user vma there + * is no need to call zap_pages which is slow. When + * page_cnt is big it's faster to do the batched zap. + */ zap_pages(arena, full_uaddr, 1); vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE); __free_page(page); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 13358675ff2e..feabc0193852 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -246,6 +246,38 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) return this_cpu_ptr(array->pptrs[index & array->index_mask]); } +/* emit BPF instructions equivalent to C code of percpu_array_map_lookup_elem() */ +static int percpu_array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_insn *insn = insn_buf; + + if (!bpf_jit_supports_percpu_insn()) + return -EOPNOTSUPP; + + if (map->map_flags & BPF_F_INNER_MAP) + return -EOPNOTSUPP; + + BUILD_BUG_ON(offsetof(struct bpf_array, map) != 0); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct bpf_array, pptrs)); + + *insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0); + if (!map->bypass_spec_v1) { + *insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 6); + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_0, array->index_mask); + } else { + *insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 5); + } + + *insn++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); + *insn++ = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); + *insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *insn++ = BPF_MOV64_IMM(BPF_REG_0, 0); + return insn - insn_buf; +} + static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) { struct bpf_array *array = container_of(map, struct bpf_array, map); @@ -396,17 +428,22 @@ static void *array_map_vmalloc_addr(struct bpf_array *array) return (void *)round_down((unsigned long)array, PAGE_SIZE); } -static void array_map_free_timers(struct bpf_map *map) +static void array_map_free_timers_wq(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - /* We don't reset or free fields other than timer on uref dropping to zero. */ - if (!btf_record_has_field(map->record, BPF_TIMER)) - return; - - for (i = 0; i < array->map.max_entries; i++) - bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); + /* We don't reset or free fields other than timer and workqueue + * on uref dropping to zero. + */ + if (btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE)) { + for (i = 0; i < array->map.max_entries; i++) { + if (btf_record_has_field(map->record, BPF_TIMER)) + bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i)); + } + } } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ @@ -750,7 +787,7 @@ const struct bpf_map_ops array_map_ops = { .map_alloc = array_map_alloc, .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, - .map_release_uref = array_map_free_timers, + .map_release_uref = array_map_free_timers_wq, .map_lookup_elem = array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, @@ -776,6 +813,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = percpu_array_map_lookup_elem, + .map_gen_lookup = percpu_array_map_gen_lookup, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, .map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem, diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index addf3dd57b59..35e1ddca74d2 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -80,6 +80,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key return -EOPNOTSUPP; } +/* Called from syscall */ +static int bloom_map_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -191,6 +203,7 @@ static u64 bloom_map_mem_usage(const struct bpf_map *map) BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index bdea1a459153..976cb258a0ed 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -318,7 +318,7 @@ static bool check_storage_bpf_ma(struct bpf_local_storage *local_storage, * * If the local_storage->list is already empty, the caller will not * care about the bpf_ma value also because the caller is not - * responsibile to free the local_storage. + * responsible to free the local_storage. */ if (storage_smap) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 43356faaa057..86c7884abaf8 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -728,8 +728,6 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, cur_image = image; trampoline_start = 0; } - if (err < 0) - goto reset_unlock; *(void **)(kdata + moff) = image + trampoline_start + cfi_get_offset(); @@ -742,8 +740,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) goto reset_unlock; } - for (i = 0; i < st_map->image_pages_cnt; i++) - arch_protect_bpf_trampoline(st_map->image_pages[i], PAGE_SIZE); + for (i = 0; i < st_map->image_pages_cnt; i++) { + err = arch_protect_bpf_trampoline(st_map->image_pages[i], + PAGE_SIZE); + if (err) + goto reset_unlock; + } if (st_map->map.map_flags & BPF_F_LINK) { err = 0; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 90c4a32d89ff..821063660d9f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -218,6 +218,7 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_SOCKET_FILTER, BTF_KFUNC_HOOK_LWT, BTF_KFUNC_HOOK_NETFILTER, + BTF_KFUNC_HOOK_KPROBE, BTF_KFUNC_HOOK_MAX, }; @@ -3464,6 +3465,15 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } + if (field_mask & BPF_WORKQUEUE) { + if (!strcmp(name, "bpf_wq")) { + if (*seen_mask & BPF_WORKQUEUE) + return -E2BIG; + *seen_mask |= BPF_WORKQUEUE; + type = BPF_WORKQUEUE; + goto end; + } + } field_mask_test_name(BPF_LIST_HEAD, "bpf_list_head"); field_mask_test_name(BPF_LIST_NODE, "bpf_list_node"); field_mask_test_name(BPF_RB_ROOT, "bpf_rb_root"); @@ -3515,6 +3525,7 @@ static int btf_find_struct_field(const struct btf *btf, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: @@ -3582,6 +3593,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: @@ -3816,6 +3828,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type rec->spin_lock_off = -EINVAL; rec->timer_off = -EINVAL; + rec->wq_off = -EINVAL; rec->refcount_off = -EINVAL; for (i = 0; i < cnt; i++) { field_type_size = btf_field_type_size(info_arr[i].type); @@ -3846,6 +3859,11 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type /* Cache offset for faster lookup at runtime */ rec->timer_off = rec->fields[i].offset; break; + case BPF_WORKQUEUE: + WARN_ON_ONCE(rec->wq_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->wq_off = rec->fields[i].offset; + break; case BPF_REFCOUNT: WARN_ON_ONCE(rec->refcount_off >= 0); /* Cache offset for faster lookup at runtime */ @@ -5642,8 +5660,8 @@ errout_free: return ERR_PTR(err); } -extern char __weak __start_BTF[]; -extern char __weak __stop_BTF[]; +extern char __start_BTF[]; +extern char __stop_BTF[]; extern struct btf *btf_vmlinux; #define BPF_MAP_TYPE(_id, _ops) @@ -5971,6 +5989,9 @@ struct btf *btf_parse_vmlinux(void) struct btf *btf = NULL; int err; + if (!IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) + return ERR_PTR(-ENOENT); + env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); @@ -8137,6 +8158,8 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) return BTF_KFUNC_HOOK_LWT; case BPF_PROG_TYPE_NETFILTER: return BTF_KFUNC_HOOK_NETFILTER; + case BPF_PROG_TYPE_KPROBE: + return BTF_KFUNC_HOOK_KPROBE; default: return BTF_KFUNC_HOOK_MAX; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 82243cb6c54d..8ba73042a239 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -2575,8 +2575,6 @@ cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; #ifdef CONFIG_CGROUP_NET_CLASSID diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 696bc55de8e8..1a6c3faa6e4a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -22,10 +22,10 @@ #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> -#include <linux/moduleloader.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/objtool.h> +#include <linux/overflow.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> @@ -37,6 +37,7 @@ #include <linux/nospec.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> +#include <linux/execmem.h> #include <asm/barrier.h> #include <asm/unaligned.h> @@ -747,7 +748,7 @@ const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long symbol_start = ksym->start; unsigned long symbol_end = ksym->end; - strncpy(sym, ksym->name, KSYM_NAME_LEN); + strscpy(sym, ksym->name, KSYM_NAME_LEN); ret = sym; if (size) @@ -813,7 +814,7 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (it++ != symnum) continue; - strncpy(sym, ksym->name, KSYM_NAME_LEN); + strscpy(sym, ksym->name, KSYM_NAME_LEN); *value = ksym->start; *type = BPF_SYM_ELF_TYPE; @@ -849,7 +850,7 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, return -EINVAL; } - tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL); + tab = krealloc_array(tab, size, sizeof(*poke), GFP_KERNEL); if (!tab) return -ENOMEM; @@ -908,23 +909,30 @@ static LIST_HEAD(pack_list); static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; + int err; pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)), GFP_KERNEL); if (!pack) return NULL; pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE); - if (!pack->ptr) { - kfree(pack); - return NULL; - } + if (!pack->ptr) + goto out; bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE); bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); - list_add_tail(&pack->list, &pack_list); set_vm_flush_reset_perms(pack->ptr); - set_memory_rox((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); + err = set_memory_rox((unsigned long)pack->ptr, + BPF_PROG_PACK_SIZE / PAGE_SIZE); + if (err) + goto out; + list_add_tail(&pack->list, &pack_list); return pack; + +out: + bpf_jit_free_exec(pack->ptr); + kfree(pack); + return NULL; } void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) @@ -939,9 +947,16 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) size = round_up(size, PAGE_SIZE); ptr = bpf_jit_alloc_exec(size); if (ptr) { + int err; + bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); - set_memory_rox((unsigned long)ptr, size / PAGE_SIZE); + err = set_memory_rox((unsigned long)ptr, + size / PAGE_SIZE); + if (err) { + bpf_jit_free_exec(ptr); + ptr = NULL; + } } goto out; } @@ -1050,12 +1065,12 @@ void bpf_jit_uncharge_modmem(u32 size) void *__weak bpf_jit_alloc_exec(unsigned long size) { - return module_alloc(size); + return execmem_alloc(EXECMEM_BPF, size); } void __weak bpf_jit_free_exec(void *addr) { - module_memfree(addr); + execmem_free(addr); } struct bpf_binary_header * @@ -2204,6 +2219,7 @@ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG] = {}; \ \ + kmsan_unpoison_memory(stack, sizeof(stack)); \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ ARG1 = (u64) (unsigned long) ctx; \ return ___bpf_prog_run(regs, insn); \ @@ -2217,6 +2233,7 @@ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG]; \ \ + kmsan_unpoison_memory(stack, sizeof(stack)); \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ BPF_R1 = r1; \ BPF_R2 = r2; \ @@ -2403,7 +2420,9 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } finalize: - bpf_prog_lock_ro(fp); + *err = bpf_prog_lock_ro(fp); + if (*err) + return fp; /* The tail call compatibility check can only be done at * this late stage as we need to determine, if we deal @@ -2437,13 +2456,14 @@ EXPORT_SYMBOL(bpf_empty_prog_array); struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { + struct bpf_prog_array *p; + if (prog_cnt) - return kzalloc(sizeof(struct bpf_prog_array) + - sizeof(struct bpf_prog_array_item) * - (prog_cnt + 1), - flags); + p = kzalloc(struct_size(p, items, prog_cnt + 1), flags); + else + p = &bpf_empty_prog_array.hdr; - return &bpf_empty_prog_array.hdr; + return p; } void bpf_prog_array_free(struct bpf_prog_array *progs) @@ -2796,7 +2816,7 @@ void bpf_prog_free(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_free); -/* RNG for unpriviledged user space with separated state from prandom_u32(). */ +/* RNG for unprivileged user space with separated state from prandom_u32(). */ static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state); void bpf_user_rnd_init_once(void) @@ -2921,12 +2941,28 @@ bool __weak bpf_jit_needs_zext(void) return false; } +/* Return true if the JIT inlines the call to the helper corresponding to + * the imm. + * + * The verifier will not patch the insn->imm for the call to the helper if + * this returns true. + */ +bool __weak bpf_jit_inlines_helper_call(s32 imm) +{ + return false; +} + /* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */ bool __weak bpf_jit_supports_subprog_tailcalls(void) { return false; } +bool __weak bpf_jit_supports_percpu_insn(void) +{ + return false; +} + bool __weak bpf_jit_supports_kfunc_call(void) { return false; @@ -2942,6 +2978,20 @@ bool __weak bpf_jit_supports_arena(void) return false; } +bool __weak bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) +{ + return false; +} + +u64 __weak bpf_arch_uaddress_limit(void) +{ +#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) + return TASK_SIZE; +#else + return 0; +#endif +} + /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index dad0fb1c8e87..33c473d676a5 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -474,6 +474,7 @@ static int __init cpumask_kfunc_init(void) ret = bpf_mem_alloc_init(&bpf_cpumask_ma, sizeof(struct bpf_cpumask), false); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &cpumask_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &cpumask_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &cpumask_kfunc_set); return ret ?: register_btf_id_dtor_kfuncs(cpumask_dtors, ARRAY_SIZE(cpumask_dtors), THIS_MODULE); diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c new file mode 100644 index 000000000000..2bee4af91e38 --- /dev/null +++ b/kernel/bpf/crypto.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Meta, Inc */ +#include <linux/bpf.h> +#include <linux/bpf_crypto.h> +#include <linux/bpf_mem_alloc.h> +#include <linux/btf.h> +#include <linux/btf_ids.h> +#include <linux/filter.h> +#include <linux/scatterlist.h> +#include <linux/skbuff.h> +#include <crypto/skcipher.h> + +struct bpf_crypto_type_list { + const struct bpf_crypto_type *type; + struct list_head list; +}; + +/* BPF crypto initialization parameters struct */ +/** + * struct bpf_crypto_params - BPF crypto initialization parameters structure + * @type: The string of crypto operation type. + * @reserved: Reserved member, will be reused for more options in future + * Values: + * 0 + * @algo: The string of algorithm to initialize. + * @key: The cipher key used to init crypto algorithm. + * @key_len: The length of cipher key. + * @authsize: The length of authentication tag used by algorithm. + */ +struct bpf_crypto_params { + char type[14]; + u8 reserved[2]; + char algo[128]; + u8 key[256]; + u32 key_len; + u32 authsize; +}; + +static LIST_HEAD(bpf_crypto_types); +static DECLARE_RWSEM(bpf_crypto_types_sem); + +/** + * struct bpf_crypto_ctx - refcounted BPF crypto context structure + * @type: The pointer to bpf crypto type + * @tfm: The pointer to instance of crypto API struct. + * @siv_len: Size of IV and state storage for cipher + * @rcu: The RCU head used to free the crypto context with RCU safety. + * @usage: Object reference counter. When the refcount goes to 0, the + * memory is released back to the BPF allocator, which provides + * RCU safety. + */ +struct bpf_crypto_ctx { + const struct bpf_crypto_type *type; + void *tfm; + u32 siv_len; + struct rcu_head rcu; + refcount_t usage; +}; + +int bpf_crypto_register_type(const struct bpf_crypto_type *type) +{ + struct bpf_crypto_type_list *node; + int err = -EEXIST; + + down_write(&bpf_crypto_types_sem); + list_for_each_entry(node, &bpf_crypto_types, list) { + if (!strcmp(node->type->name, type->name)) + goto unlock; + } + + node = kmalloc(sizeof(*node), GFP_KERNEL); + err = -ENOMEM; + if (!node) + goto unlock; + + node->type = type; + list_add(&node->list, &bpf_crypto_types); + err = 0; + +unlock: + up_write(&bpf_crypto_types_sem); + + return err; +} +EXPORT_SYMBOL_GPL(bpf_crypto_register_type); + +int bpf_crypto_unregister_type(const struct bpf_crypto_type *type) +{ + struct bpf_crypto_type_list *node; + int err = -ENOENT; + + down_write(&bpf_crypto_types_sem); + list_for_each_entry(node, &bpf_crypto_types, list) { + if (strcmp(node->type->name, type->name)) + continue; + + list_del(&node->list); + kfree(node); + err = 0; + break; + } + up_write(&bpf_crypto_types_sem); + + return err; +} +EXPORT_SYMBOL_GPL(bpf_crypto_unregister_type); + +static const struct bpf_crypto_type *bpf_crypto_get_type(const char *name) +{ + const struct bpf_crypto_type *type = ERR_PTR(-ENOENT); + struct bpf_crypto_type_list *node; + + down_read(&bpf_crypto_types_sem); + list_for_each_entry(node, &bpf_crypto_types, list) { + if (strcmp(node->type->name, name)) + continue; + + if (try_module_get(node->type->owner)) + type = node->type; + break; + } + up_read(&bpf_crypto_types_sem); + + return type; +} + +__bpf_kfunc_start_defs(); + +/** + * bpf_crypto_ctx_create() - Create a mutable BPF crypto context. + * + * Allocates a crypto context that can be used, acquired, and released by + * a BPF program. The crypto context returned by this function must either + * be embedded in a map as a kptr, or freed with bpf_crypto_ctx_release(). + * As crypto API functions use GFP_KERNEL allocations, this function can + * only be used in sleepable BPF programs. + * + * bpf_crypto_ctx_create() allocates memory for crypto context. + * It may return NULL if no memory is available. + * @params: pointer to struct bpf_crypto_params which contains all the + * details needed to initialise crypto context. + * @params__sz: size of steuct bpf_crypto_params usef by bpf program + * @err: integer to store error code when NULL is returned. + */ +__bpf_kfunc struct bpf_crypto_ctx * +bpf_crypto_ctx_create(const struct bpf_crypto_params *params, u32 params__sz, + int *err) +{ + const struct bpf_crypto_type *type; + struct bpf_crypto_ctx *ctx; + + if (!params || params->reserved[0] || params->reserved[1] || + params__sz != sizeof(struct bpf_crypto_params)) { + *err = -EINVAL; + return NULL; + } + + type = bpf_crypto_get_type(params->type); + if (IS_ERR(type)) { + *err = PTR_ERR(type); + return NULL; + } + + if (!type->has_algo(params->algo)) { + *err = -EOPNOTSUPP; + goto err_module_put; + } + + if (!!params->authsize ^ !!type->setauthsize) { + *err = -EOPNOTSUPP; + goto err_module_put; + } + + if (!params->key_len || params->key_len > sizeof(params->key)) { + *err = -EINVAL; + goto err_module_put; + } + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + *err = -ENOMEM; + goto err_module_put; + } + + ctx->type = type; + ctx->tfm = type->alloc_tfm(params->algo); + if (IS_ERR(ctx->tfm)) { + *err = PTR_ERR(ctx->tfm); + goto err_free_ctx; + } + + if (params->authsize) { + *err = type->setauthsize(ctx->tfm, params->authsize); + if (*err) + goto err_free_tfm; + } + + *err = type->setkey(ctx->tfm, params->key, params->key_len); + if (*err) + goto err_free_tfm; + + if (type->get_flags(ctx->tfm) & CRYPTO_TFM_NEED_KEY) { + *err = -EINVAL; + goto err_free_tfm; + } + + ctx->siv_len = type->ivsize(ctx->tfm) + type->statesize(ctx->tfm); + + refcount_set(&ctx->usage, 1); + + return ctx; + +err_free_tfm: + type->free_tfm(ctx->tfm); +err_free_ctx: + kfree(ctx); +err_module_put: + module_put(type->owner); + + return NULL; +} + +static void crypto_free_cb(struct rcu_head *head) +{ + struct bpf_crypto_ctx *ctx; + + ctx = container_of(head, struct bpf_crypto_ctx, rcu); + ctx->type->free_tfm(ctx->tfm); + module_put(ctx->type->owner); + kfree(ctx); +} + +/** + * bpf_crypto_ctx_acquire() - Acquire a reference to a BPF crypto context. + * @ctx: The BPF crypto context being acquired. The ctx must be a trusted + * pointer. + * + * Acquires a reference to a BPF crypto context. The context returned by this function + * must either be embedded in a map as a kptr, or freed with + * bpf_crypto_ctx_release(). + */ +__bpf_kfunc struct bpf_crypto_ctx * +bpf_crypto_ctx_acquire(struct bpf_crypto_ctx *ctx) +{ + if (!refcount_inc_not_zero(&ctx->usage)) + return NULL; + return ctx; +} + +/** + * bpf_crypto_ctx_release() - Release a previously acquired BPF crypto context. + * @ctx: The crypto context being released. + * + * Releases a previously acquired reference to a BPF crypto context. When the final + * reference of the BPF crypto context has been released, its memory + * will be released. + */ +__bpf_kfunc void bpf_crypto_ctx_release(struct bpf_crypto_ctx *ctx) +{ + if (refcount_dec_and_test(&ctx->usage)) + call_rcu(&ctx->rcu, crypto_free_cb); +} + +static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx, + const struct bpf_dynptr_kern *src, + const struct bpf_dynptr_kern *dst, + const struct bpf_dynptr_kern *siv, + bool decrypt) +{ + u32 src_len, dst_len, siv_len; + const u8 *psrc; + u8 *pdst, *piv; + int err; + + if (__bpf_dynptr_is_rdonly(dst)) + return -EINVAL; + + siv_len = __bpf_dynptr_size(siv); + src_len = __bpf_dynptr_size(src); + dst_len = __bpf_dynptr_size(dst); + if (!src_len || !dst_len) + return -EINVAL; + + if (siv_len != ctx->siv_len) + return -EINVAL; + + psrc = __bpf_dynptr_data(src, src_len); + if (!psrc) + return -EINVAL; + pdst = __bpf_dynptr_data_rw(dst, dst_len); + if (!pdst) + return -EINVAL; + + piv = siv_len ? __bpf_dynptr_data_rw(siv, siv_len) : NULL; + if (siv_len && !piv) + return -EINVAL; + + err = decrypt ? ctx->type->decrypt(ctx->tfm, psrc, pdst, src_len, piv) + : ctx->type->encrypt(ctx->tfm, psrc, pdst, src_len, piv); + + return err; +} + +/** + * bpf_crypto_decrypt() - Decrypt buffer using configured context and IV provided. + * @ctx: The crypto context being used. The ctx must be a trusted pointer. + * @src: bpf_dynptr to the encrypted data. Must be a trusted pointer. + * @dst: bpf_dynptr to the buffer where to store the result. Must be a trusted pointer. + * @siv: bpf_dynptr to IV data and state data to be used by decryptor. + * + * Decrypts provided buffer using IV data and the crypto context. Crypto context must be configured. + */ +__bpf_kfunc int bpf_crypto_decrypt(struct bpf_crypto_ctx *ctx, + const struct bpf_dynptr_kern *src, + const struct bpf_dynptr_kern *dst, + const struct bpf_dynptr_kern *siv) +{ + return bpf_crypto_crypt(ctx, src, dst, siv, true); +} + +/** + * bpf_crypto_encrypt() - Encrypt buffer using configured context and IV provided. + * @ctx: The crypto context being used. The ctx must be a trusted pointer. + * @src: bpf_dynptr to the plain data. Must be a trusted pointer. + * @dst: bpf_dynptr to buffer where to store the result. Must be a trusted pointer. + * @siv: bpf_dynptr to IV data and state data to be used by decryptor. + * + * Encrypts provided buffer using IV data and the crypto context. Crypto context must be configured. + */ +__bpf_kfunc int bpf_crypto_encrypt(struct bpf_crypto_ctx *ctx, + const struct bpf_dynptr_kern *src, + const struct bpf_dynptr_kern *dst, + const struct bpf_dynptr_kern *siv) +{ + return bpf_crypto_crypt(ctx, src, dst, siv, false); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(crypt_init_kfunc_btf_ids) +BTF_ID_FLAGS(func, bpf_crypto_ctx_create, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_crypto_ctx_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_crypto_ctx_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL) +BTF_KFUNCS_END(crypt_init_kfunc_btf_ids) + +static const struct btf_kfunc_id_set crypt_init_kfunc_set = { + .owner = THIS_MODULE, + .set = &crypt_init_kfunc_btf_ids, +}; + +BTF_KFUNCS_START(crypt_kfunc_btf_ids) +BTF_ID_FLAGS(func, bpf_crypto_decrypt, KF_RCU) +BTF_ID_FLAGS(func, bpf_crypto_encrypt, KF_RCU) +BTF_KFUNCS_END(crypt_kfunc_btf_ids) + +static const struct btf_kfunc_id_set crypt_kfunc_set = { + .owner = THIS_MODULE, + .set = &crypt_kfunc_btf_ids, +}; + +BTF_ID_LIST(bpf_crypto_dtor_ids) +BTF_ID(struct, bpf_crypto_ctx) +BTF_ID(func, bpf_crypto_ctx_release) + +static int __init crypto_kfunc_init(void) +{ + int ret; + const struct btf_id_dtor_kfunc bpf_crypto_dtors[] = { + { + .btf_id = bpf_crypto_dtor_ids[0], + .kfunc_btf_id = bpf_crypto_dtor_ids[1] + }, + }; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &crypt_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &crypt_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &crypt_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, + &crypt_init_kfunc_set); + return ret ?: register_btf_id_dtor_kfuncs(bpf_crypto_dtors, + ARRAY_SIZE(bpf_crypto_dtors), + THIS_MODULE); +} + +late_initcall(crypto_kfunc_init); diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index bd2e2dd04740..309c4aa1b026 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -172,6 +172,17 @@ static bool is_addr_space_cast(const struct bpf_insn *insn) insn->off == BPF_ADDR_SPACE_CAST; } +/* Special (internal-only) form of mov, used to resolve per-CPU addrs: + * dst_reg = src_reg + <percpu_base_off> + * BPF_ADDR_PERCPU is used as a special insn->off value. + */ +#define BPF_ADDR_PERCPU (-1) + +static inline bool is_mov_percpu_addr(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; +} + void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) @@ -194,6 +205,9 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %d, %d)\n", insn->code, insn->dst_reg, insn->src_reg, ((u32)insn->imm) >> 16, (u16)insn->imm); + } else if (is_mov_percpu_addr(insn)) { + verbose(cbs->private_data, "(%02x) r%d = &(void __percpu *)(r%d)\n", + insn->code, insn->dst_reg, insn->src_reg); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3a088a5349bc..06115f8728e8 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -221,13 +221,11 @@ static bool htab_has_extra_elems(struct bpf_htab *htab) return !htab_is_percpu(htab) && !htab_is_lru(htab); } -static void htab_free_prealloced_timers(struct bpf_htab *htab) +static void htab_free_prealloced_timers_and_wq(struct bpf_htab *htab) { u32 num_entries = htab->map.max_entries; int i; - if (!btf_record_has_field(htab->map.record, BPF_TIMER)) - return; if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); @@ -235,7 +233,12 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_obj_free_timer(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_TIMER)) + bpf_obj_free_timer(htab->map.record, + elem->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(htab->map.record, + elem->key + round_up(htab->map.key_size, 8)); cond_resched(); } } @@ -1490,11 +1493,12 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_nulls_del_rcu(&l->hash_node); htab_elem_free(htab, l); } + cond_resched(); } migrate_enable(); } -static void htab_free_malloced_timers(struct bpf_htab *htab) +static void htab_free_malloced_timers_and_wq(struct bpf_htab *htab) { int i; @@ -1506,24 +1510,29 @@ static void htab_free_malloced_timers(struct bpf_htab *htab) hlist_nulls_for_each_entry(l, n, head, hash_node) { /* We only free timer on uref dropping to zero */ - bpf_obj_free_timer(htab->map.record, l->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_TIMER)) + bpf_obj_free_timer(htab->map.record, + l->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(htab->map.record, + l->key + round_up(htab->map.key_size, 8)); } cond_resched_rcu(); } rcu_read_unlock(); } -static void htab_map_free_timers(struct bpf_map *map) +static void htab_map_free_timers_and_wq(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - /* We only free timer on uref dropping to zero */ - if (!btf_record_has_field(htab->map.record, BPF_TIMER)) - return; - if (!htab_is_prealloc(htab)) - htab_free_malloced_timers(htab); - else - htab_free_prealloced_timers(htab); + /* We only free timer and workqueue on uref dropping to zero */ + if (btf_record_has_field(htab->map.record, BPF_TIMER | BPF_WORKQUEUE)) { + if (!htab_is_prealloc(htab)) + htab_free_malloced_timers_and_wq(htab); + else + htab_free_prealloced_timers_and_wq(htab); + } } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ @@ -1538,7 +1547,7 @@ static void htab_map_free(struct bpf_map *map) */ /* htab no longer uses call_rcu() directly. bpf_mem_alloc does it - * underneath and is reponsible for waiting for callbacks to finish + * underneath and is responsible for waiting for callbacks to finish * during bpf_mem_alloc_destroy(). */ if (!htab_is_prealloc(htab)) { @@ -2259,7 +2268,7 @@ const struct bpf_map_ops htab_map_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, - .map_release_uref = htab_map_free_timers, + .map_release_uref = htab_map_free_timers_and_wq, .map_lookup_elem = htab_map_lookup_elem, .map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem, .map_update_elem = htab_map_update_elem, @@ -2280,7 +2289,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, - .map_release_uref = htab_map_free_timers, + .map_release_uref = htab_map_free_timers_and_wq, .map_lookup_elem = htab_lru_map_lookup_elem, .map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem, .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, @@ -2307,6 +2316,26 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +/* inline bpf_map_lookup_elem() call for per-CPU hashmap */ +static int htab_percpu_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + + if (!bpf_jit_supports_percpu_insn()) + return -EOPNOTSUPP; + + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, + offsetof(struct htab_elem, key) + map->key_size); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); + *insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); + + return insn - insn_buf; +} + static void *htab_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) { struct htab_elem *l; @@ -2435,6 +2464,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_percpu_map_lookup_elem, + .map_gen_lookup = htab_percpu_map_gen_lookup, .map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a89587859571..2a69a9a36c0f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1079,11 +1079,20 @@ const struct bpf_func_proto bpf_snprintf_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +struct bpf_async_cb { + struct bpf_map *map; + struct bpf_prog *prog; + void __rcu *callback_fn; + void *value; + struct rcu_head rcu; + u64 flags; +}; + /* BPF map elements can contain 'struct bpf_timer'. * Such map owns all of its BPF timers. * 'struct bpf_timer' is allocated as part of map element allocation * and it's zero initialized. - * That space is used to keep 'struct bpf_timer_kern'. + * That space is used to keep 'struct bpf_async_kern'. * bpf_timer_init() allocates 'struct bpf_hrtimer', inits hrtimer, and * remembers 'struct bpf_map *' pointer it's part of. * bpf_timer_set_callback() increments prog refcnt and assign bpf callback_fn. @@ -1096,17 +1105,23 @@ const struct bpf_func_proto bpf_snprintf_proto = { * freeing the timers when inner map is replaced or deleted by user space. */ struct bpf_hrtimer { + struct bpf_async_cb cb; struct hrtimer timer; - struct bpf_map *map; - struct bpf_prog *prog; - void __rcu *callback_fn; - void *value; - struct rcu_head rcu; }; -/* the actual struct hidden inside uapi struct bpf_timer */ -struct bpf_timer_kern { - struct bpf_hrtimer *timer; +struct bpf_work { + struct bpf_async_cb cb; + struct work_struct work; + struct work_struct delete_work; +}; + +/* the actual struct hidden inside uapi struct bpf_timer and bpf_wq */ +struct bpf_async_kern { + union { + struct bpf_async_cb *cb; + struct bpf_hrtimer *timer; + struct bpf_work *work; + }; /* bpf_spin_lock is used here instead of spinlock_t to make * sure that it always fits into space reserved by struct bpf_timer * regardless of LOCKDEP and spinlock debug flags. @@ -1114,19 +1129,24 @@ struct bpf_timer_kern { struct bpf_spin_lock lock; } __attribute__((aligned(8))); +enum bpf_async_type { + BPF_ASYNC_TYPE_TIMER = 0, + BPF_ASYNC_TYPE_WQ, +}; + static DEFINE_PER_CPU(struct bpf_hrtimer *, hrtimer_running); static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) { struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer); - struct bpf_map *map = t->map; - void *value = t->value; + struct bpf_map *map = t->cb.map; + void *value = t->cb.value; bpf_callback_t callback_fn; void *key; u32 idx; BTF_TYPE_EMIT(struct bpf_timer); - callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held()); + callback_fn = rcu_dereference_check(t->cb.callback_fn, rcu_read_lock_bh_held()); if (!callback_fn) goto out; @@ -1155,46 +1175,112 @@ out: return HRTIMER_NORESTART; } -BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map, - u64, flags) +static void bpf_wq_work(struct work_struct *work) +{ + struct bpf_work *w = container_of(work, struct bpf_work, work); + struct bpf_async_cb *cb = &w->cb; + struct bpf_map *map = cb->map; + bpf_callback_t callback_fn; + void *value = cb->value; + void *key; + u32 idx; + + BTF_TYPE_EMIT(struct bpf_wq); + + callback_fn = READ_ONCE(cb->callback_fn); + if (!callback_fn) + return; + + if (map->map_type == BPF_MAP_TYPE_ARRAY) { + struct bpf_array *array = container_of(map, struct bpf_array, map); + + /* compute the key */ + idx = ((char *)value - array->value) / array->elem_size; + key = &idx; + } else { /* hash or lru */ + key = value - round_up(map->key_size, 8); + } + + rcu_read_lock_trace(); + migrate_disable(); + + callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); + + migrate_enable(); + rcu_read_unlock_trace(); +} + +static void bpf_wq_delete_work(struct work_struct *work) +{ + struct bpf_work *w = container_of(work, struct bpf_work, delete_work); + + cancel_work_sync(&w->work); + + kfree_rcu(w, cb.rcu); +} + +static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u64 flags, + enum bpf_async_type type) { - clockid_t clockid = flags & (MAX_CLOCKS - 1); + struct bpf_async_cb *cb; struct bpf_hrtimer *t; + struct bpf_work *w; + clockid_t clockid; + size_t size; int ret = 0; - BUILD_BUG_ON(MAX_CLOCKS != 16); - BUILD_BUG_ON(sizeof(struct bpf_timer_kern) > sizeof(struct bpf_timer)); - BUILD_BUG_ON(__alignof__(struct bpf_timer_kern) != __alignof__(struct bpf_timer)); - if (in_nmi()) return -EOPNOTSUPP; - if (flags >= MAX_CLOCKS || - /* similar to timerfd except _ALARM variants are not supported */ - (clockid != CLOCK_MONOTONIC && - clockid != CLOCK_REALTIME && - clockid != CLOCK_BOOTTIME)) + switch (type) { + case BPF_ASYNC_TYPE_TIMER: + size = sizeof(struct bpf_hrtimer); + break; + case BPF_ASYNC_TYPE_WQ: + size = sizeof(struct bpf_work); + break; + default: return -EINVAL; - __bpf_spin_lock_irqsave(&timer->lock); - t = timer->timer; + } + + __bpf_spin_lock_irqsave(&async->lock); + t = async->timer; if (t) { ret = -EBUSY; goto out; } + /* allocate hrtimer via map_kmalloc to use memcg accounting */ - t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node); - if (!t) { + cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node); + if (!cb) { ret = -ENOMEM; goto out; } - t->value = (void *)timer - map->record->timer_off; - t->map = map; - t->prog = NULL; - rcu_assign_pointer(t->callback_fn, NULL); - hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT); - t->timer.function = bpf_timer_cb; - WRITE_ONCE(timer->timer, t); - /* Guarantee the order between timer->timer and map->usercnt. So + + switch (type) { + case BPF_ASYNC_TYPE_TIMER: + clockid = flags & (MAX_CLOCKS - 1); + t = (struct bpf_hrtimer *)cb; + + hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT); + t->timer.function = bpf_timer_cb; + cb->value = (void *)async - map->record->timer_off; + break; + case BPF_ASYNC_TYPE_WQ: + w = (struct bpf_work *)cb; + + INIT_WORK(&w->work, bpf_wq_work); + INIT_WORK(&w->delete_work, bpf_wq_delete_work); + cb->value = (void *)async - map->record->wq_off; + break; + } + cb->map = map; + cb->prog = NULL; + cb->flags = flags; + rcu_assign_pointer(cb->callback_fn, NULL); + + WRITE_ONCE(async->cb, cb); + /* Guarantee the order between async->cb and map->usercnt. So * when there are concurrent uref release and bpf timer init, either * bpf_timer_cancel_and_free() called by uref release reads a no-NULL * timer or atomic64_read() below returns a zero usercnt. @@ -1204,15 +1290,34 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map /* maps with timers must be either held by user space * or pinned in bpffs. */ - WRITE_ONCE(timer->timer, NULL); - kfree(t); + WRITE_ONCE(async->cb, NULL); + kfree(cb); ret = -EPERM; } out: - __bpf_spin_unlock_irqrestore(&timer->lock); + __bpf_spin_unlock_irqrestore(&async->lock); return ret; } +BPF_CALL_3(bpf_timer_init, struct bpf_async_kern *, timer, struct bpf_map *, map, + u64, flags) +{ + clock_t clockid = flags & (MAX_CLOCKS - 1); + + BUILD_BUG_ON(MAX_CLOCKS != 16); + BUILD_BUG_ON(sizeof(struct bpf_async_kern) > sizeof(struct bpf_timer)); + BUILD_BUG_ON(__alignof__(struct bpf_async_kern) != __alignof__(struct bpf_timer)); + + if (flags >= MAX_CLOCKS || + /* similar to timerfd except _ALARM variants are not supported */ + (clockid != CLOCK_MONOTONIC && + clockid != CLOCK_REALTIME && + clockid != CLOCK_BOOTTIME)) + return -EINVAL; + + return __bpf_async_init(timer, map, flags, BPF_ASYNC_TYPE_TIMER); +} + static const struct bpf_func_proto bpf_timer_init_proto = { .func = bpf_timer_init, .gpl_only = true, @@ -1222,22 +1327,23 @@ static const struct bpf_func_proto bpf_timer_init_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_timer_set_callback, struct bpf_timer_kern *, timer, void *, callback_fn, - struct bpf_prog_aux *, aux) +static int __bpf_async_set_callback(struct bpf_async_kern *async, void *callback_fn, + struct bpf_prog_aux *aux, unsigned int flags, + enum bpf_async_type type) { struct bpf_prog *prev, *prog = aux->prog; - struct bpf_hrtimer *t; + struct bpf_async_cb *cb; int ret = 0; if (in_nmi()) return -EOPNOTSUPP; - __bpf_spin_lock_irqsave(&timer->lock); - t = timer->timer; - if (!t) { + __bpf_spin_lock_irqsave(&async->lock); + cb = async->cb; + if (!cb) { ret = -EINVAL; goto out; } - if (!atomic64_read(&t->map->usercnt)) { + if (!atomic64_read(&cb->map->usercnt)) { /* maps with timers must be either held by user space * or pinned in bpffs. Otherwise timer might still be * running even when bpf prog is detached and user space @@ -1246,7 +1352,7 @@ BPF_CALL_3(bpf_timer_set_callback, struct bpf_timer_kern *, timer, void *, callb ret = -EPERM; goto out; } - prev = t->prog; + prev = cb->prog; if (prev != prog) { /* Bump prog refcnt once. Every bpf_timer_set_callback() * can pick different callback_fn-s within the same prog. @@ -1259,14 +1365,20 @@ BPF_CALL_3(bpf_timer_set_callback, struct bpf_timer_kern *, timer, void *, callb if (prev) /* Drop prev prog refcnt when swapping with new prog */ bpf_prog_put(prev); - t->prog = prog; + cb->prog = prog; } - rcu_assign_pointer(t->callback_fn, callback_fn); + rcu_assign_pointer(cb->callback_fn, callback_fn); out: - __bpf_spin_unlock_irqrestore(&timer->lock); + __bpf_spin_unlock_irqrestore(&async->lock); return ret; } +BPF_CALL_3(bpf_timer_set_callback, struct bpf_async_kern *, timer, void *, callback_fn, + struct bpf_prog_aux *, aux) +{ + return __bpf_async_set_callback(timer, callback_fn, aux, 0, BPF_ASYNC_TYPE_TIMER); +} + static const struct bpf_func_proto bpf_timer_set_callback_proto = { .func = bpf_timer_set_callback, .gpl_only = true, @@ -1275,7 +1387,7 @@ static const struct bpf_func_proto bpf_timer_set_callback_proto = { .arg2_type = ARG_PTR_TO_FUNC, }; -BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, flags) +BPF_CALL_3(bpf_timer_start, struct bpf_async_kern *, timer, u64, nsecs, u64, flags) { struct bpf_hrtimer *t; int ret = 0; @@ -1287,7 +1399,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; - if (!t || !t->prog) { + if (!t || !t->cb.prog) { ret = -EINVAL; goto out; } @@ -1315,18 +1427,18 @@ static const struct bpf_func_proto bpf_timer_start_proto = { .arg3_type = ARG_ANYTHING, }; -static void drop_prog_refcnt(struct bpf_hrtimer *t) +static void drop_prog_refcnt(struct bpf_async_cb *async) { - struct bpf_prog *prog = t->prog; + struct bpf_prog *prog = async->prog; if (prog) { bpf_prog_put(prog); - t->prog = NULL; - rcu_assign_pointer(t->callback_fn, NULL); + async->prog = NULL; + rcu_assign_pointer(async->callback_fn, NULL); } } -BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) +BPF_CALL_1(bpf_timer_cancel, struct bpf_async_kern *, timer) { struct bpf_hrtimer *t; int ret = 0; @@ -1348,7 +1460,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) ret = -EDEADLK; goto out; } - drop_prog_refcnt(t); + drop_prog_refcnt(&t->cb); out: __bpf_spin_unlock_irqrestore(&timer->lock); /* Cancel the timer and wait for associated callback to finish @@ -1366,36 +1478,44 @@ static const struct bpf_func_proto bpf_timer_cancel_proto = { .arg1_type = ARG_PTR_TO_TIMER, }; -/* This function is called by map_delete/update_elem for individual element and - * by ops->map_release_uref when the user space reference to a map reaches zero. - */ -void bpf_timer_cancel_and_free(void *val) +static struct bpf_async_cb *__bpf_async_cancel_and_free(struct bpf_async_kern *async) { - struct bpf_timer_kern *timer = val; - struct bpf_hrtimer *t; + struct bpf_async_cb *cb; - /* Performance optimization: read timer->timer without lock first. */ - if (!READ_ONCE(timer->timer)) - return; + /* Performance optimization: read async->cb without lock first. */ + if (!READ_ONCE(async->cb)) + return NULL; - __bpf_spin_lock_irqsave(&timer->lock); + __bpf_spin_lock_irqsave(&async->lock); /* re-read it under lock */ - t = timer->timer; - if (!t) + cb = async->cb; + if (!cb) goto out; - drop_prog_refcnt(t); + drop_prog_refcnt(cb); /* The subsequent bpf_timer_start/cancel() helpers won't be able to use * this timer, since it won't be initialized. */ - WRITE_ONCE(timer->timer, NULL); + WRITE_ONCE(async->cb, NULL); out: - __bpf_spin_unlock_irqrestore(&timer->lock); + __bpf_spin_unlock_irqrestore(&async->lock); + return cb; +} + +/* This function is called by map_delete/update_elem for individual element and + * by ops->map_release_uref when the user space reference to a map reaches zero. + */ +void bpf_timer_cancel_and_free(void *val) +{ + struct bpf_hrtimer *t; + + t = (struct bpf_hrtimer *)__bpf_async_cancel_and_free(val); + if (!t) return; /* Cancel the timer and wait for callback to complete if it was running. * If hrtimer_cancel() can be safely called it's safe to call kfree(t) * right after for both preallocated and non-preallocated maps. - * The timer->timer = NULL was already done and no code path can + * The async->cb = NULL was already done and no code path can * see address 't' anymore. * * Check that bpf_map_delete/update_elem() wasn't called from timer @@ -1404,13 +1524,33 @@ out: * return -1). Though callback_fn is still running on this cpu it's * safe to do kfree(t) because bpf_timer_cb() read everything it needed * from 't'. The bpf subprog callback_fn won't be able to access 't', - * since timer->timer = NULL was already done. The timer will be + * since async->cb = NULL was already done. The timer will be * effectively cancelled because bpf_timer_cb() will return * HRTIMER_NORESTART. */ if (this_cpu_read(hrtimer_running) != t) hrtimer_cancel(&t->timer); - kfree_rcu(t, rcu); + kfree_rcu(t, cb.rcu); +} + +/* This function is called by map_delete/update_elem for individual element and + * by ops->map_release_uref when the user space reference to a map reaches zero. + */ +void bpf_wq_cancel_and_free(void *val) +{ + struct bpf_work *work; + + BTF_TYPE_EMIT(struct bpf_wq); + + work = (struct bpf_work *)__bpf_async_cancel_and_free(val); + if (!work) + return; + /* Trigger cancel of the sleepable work, but *do not* wait for + * it to finish if it was running as we might not be in a + * sleepable context. + * kfree will be called once the work has finished. + */ + schedule_work(&work->delete_work); } BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) @@ -1443,7 +1583,7 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = { #define DYNPTR_SIZE_MASK 0xFFFFFF #define DYNPTR_RDONLY_BIT BIT(31) -static bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr) +bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_RDONLY_BIT; } @@ -1730,6 +1870,10 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_strtol_proto; case BPF_FUNC_strtoul: return &bpf_strtoul_proto; + case BPF_FUNC_get_current_pid_tgid: + return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_get_ns_current_pid_tgid: + return &bpf_get_ns_current_pid_tgid_proto; default: break; } @@ -2408,7 +2552,7 @@ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 o /* bpf_dynptr_slice_rdwr is the same logic as bpf_dynptr_slice. * * For skb-type dynptrs, it is safe to write into the returned pointer - * if the bpf program allows skb data writes. There are two possiblities + * if the bpf program allows skb data writes. There are two possibilities * that may occur when calling bpf_dynptr_slice_rdwr: * * 1) The requested slice is in the head of the skb. In this case, the @@ -2545,10 +2689,65 @@ __bpf_kfunc void bpf_throw(u64 cookie) WARN(1, "A call to BPF exception callback should never return\n"); } +__bpf_kfunc int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) +{ + struct bpf_async_kern *async = (struct bpf_async_kern *)wq; + struct bpf_map *map = p__map; + + BUILD_BUG_ON(sizeof(struct bpf_async_kern) > sizeof(struct bpf_wq)); + BUILD_BUG_ON(__alignof__(struct bpf_async_kern) != __alignof__(struct bpf_wq)); + + if (flags) + return -EINVAL; + + return __bpf_async_init(async, map, flags, BPF_ASYNC_TYPE_WQ); +} + +__bpf_kfunc int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) +{ + struct bpf_async_kern *async = (struct bpf_async_kern *)wq; + struct bpf_work *w; + + if (in_nmi()) + return -EOPNOTSUPP; + if (flags) + return -EINVAL; + w = READ_ONCE(async->work); + if (!w || !READ_ONCE(w->cb.prog)) + return -EINVAL; + + schedule_work(&w->work); + return 0; +} + +__bpf_kfunc int bpf_wq_set_callback_impl(struct bpf_wq *wq, + int (callback_fn)(void *map, int *key, struct bpf_wq *wq), + unsigned int flags, + void *aux__ign) +{ + struct bpf_prog_aux *aux = (struct bpf_prog_aux *)aux__ign; + struct bpf_async_kern *async = (struct bpf_async_kern *)wq; + + if (flags) + return -EINVAL; + + return __bpf_async_set_callback(async, callback_fn, aux, flags, BPF_ASYNC_TYPE_WQ); +} + +__bpf_kfunc void bpf_preempt_disable(void) +{ + preempt_disable(); +} + +__bpf_kfunc void bpf_preempt_enable(void) +{ + preempt_enable(); +} + __bpf_kfunc_end_defs(); BTF_KFUNCS_START(generic_btf_ids) -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL) @@ -2621,6 +2820,12 @@ BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) BTF_ID_FLAGS(func, bpf_dynptr_size) BTF_ID_FLAGS(func, bpf_dynptr_clone) +BTF_ID_FLAGS(func, bpf_modify_return_test_tp) +BTF_ID_FLAGS(func, bpf_wq_init) +BTF_ID_FLAGS(func, bpf_wq_set_callback_impl) +BTF_ID_FLAGS(func, bpf_wq_start) +BTF_ID_FLAGS(func, bpf_preempt_disable) +BTF_ID_FLAGS(func, bpf_preempt_enable) BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { @@ -2648,6 +2853,7 @@ static int __init kfunc_init(void) 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_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &generic_kfunc_set); ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors, ARRAY_SIZE(generic_dtors), THIS_MODULE); diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 2a243cf37c60..4bd8f17a9f24 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -467,9 +467,9 @@ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) if (type & PTR_MAYBE_NULL) { if (base_type(type) == PTR_TO_BTF_ID) - strncpy(postfix, "or_null_", 16); + strscpy(postfix, "or_null_"); else - strncpy(postfix, "_or_null", 16); + strscpy(postfix, "_or_null"); } snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 050fe1ebf0f7..0218a5132ab5 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -155,16 +155,17 @@ static inline int extract_bit(const u8 *data, size_t index) } /** - * longest_prefix_match() - determine the longest prefix + * __longest_prefix_match() - determine the longest prefix * @trie: The trie to get internal sizes from * @node: The node to operate on * @key: The key to compare to @node * * Determine the longest prefix of @node that matches the bits in @key. */ -static size_t longest_prefix_match(const struct lpm_trie *trie, - const struct lpm_trie_node *node, - const struct bpf_lpm_trie_key_u8 *key) +static __always_inline +size_t __longest_prefix_match(const struct lpm_trie *trie, + const struct lpm_trie_node *node, + const struct bpf_lpm_trie_key_u8 *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; @@ -224,6 +225,13 @@ static size_t longest_prefix_match(const struct lpm_trie *trie, return prefixlen; } +static size_t longest_prefix_match(const struct lpm_trie *trie, + const struct lpm_trie_node *node, + const struct bpf_lpm_trie_key_u8 *key) +{ + return __longest_prefix_match(trie, node, key); +} + /* Called from syscall or from eBPF program */ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { @@ -245,7 +253,7 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) * If it's the maximum possible prefix for this trie, we have * an exact match and can return it directly. */ - matchlen = longest_prefix_match(trie, node, key); + matchlen = __longest_prefix_match(trie, node, key); if (matchlen == trie->max_prefixlen) { found = node; break; @@ -308,6 +316,7 @@ static long trie_update_elem(struct bpf_map *map, { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; + struct lpm_trie_node *free_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key_u8 *key = _key; unsigned long irq_flags; @@ -382,7 +391,7 @@ static long trie_update_elem(struct bpf_map *map, trie->n_entries--; rcu_assign_pointer(*slot, new_node); - kfree_rcu(node, rcu); + free_node = node; goto out; } @@ -429,6 +438,7 @@ out: } spin_unlock_irqrestore(&trie->lock, irq_flags); + kfree_rcu(free_node, rcu); return ret; } @@ -437,6 +447,7 @@ out: static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct lpm_trie_node *free_node = NULL, *free_parent = NULL; struct bpf_lpm_trie_key_u8 *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; @@ -506,8 +517,8 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) else rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[0])); - kfree_rcu(parent, rcu); - kfree_rcu(node, rcu); + free_parent = parent; + free_node = node; goto out; } @@ -521,10 +532,12 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); else RCU_INIT_POINTER(*trim, NULL); - kfree_rcu(node, rcu); + free_node = node; out: spin_unlock_irqrestore(&trie->lock, irq_flags); + kfree_rcu(free_parent, rcu); + kfree_rcu(free_node, rcu); return ret; } diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 8ef269e66ba5..b4f18c85d7bc 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -32,7 +32,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta_size = sizeof(*inner_map_meta); /* In some cases verifier needs to access beyond just base map. */ - if (inner_map->ops == &array_map_ops) + if (inner_map->ops == &array_map_ops || inner_map->ops == &percpu_array_map_ops) inner_map_meta_size = sizeof(struct bpf_array); inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER); @@ -68,7 +68,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) /* Misc members not needed in bpf_map_meta_equal() check. */ inner_map_meta->ops = inner_map->ops; - if (inner_map->ops == &array_map_ops) { + if (inner_map->ops == &array_map_ops || inner_map->ops == &percpu_array_map_ops) { struct bpf_array *inner_array_meta = container_of(inner_map_meta, struct bpf_array, map); struct bpf_array *inner_array = container_of(inner_map, struct bpf_array, map); diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 550f02e2cb13..a546aba46d5d 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -759,8 +759,7 @@ 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); } - if (ma->objcg) - obj_cgroup_put(ma->objcg); + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { @@ -776,8 +775,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } - if (ma->objcg) - obj_cgroup_put(ma->objcg); + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ae2ff73bde7e..2222c3ff88e7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -559,6 +559,7 @@ void btf_record_free(struct btf_record *rec) case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: + case BPF_WORKQUEUE: /* Nothing to release */ break; default: @@ -608,6 +609,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: + case BPF_WORKQUEUE: /* Nothing to acquire */ break; default: @@ -659,6 +661,13 @@ void bpf_obj_free_timer(const struct btf_record *rec, void *obj) bpf_timer_cancel_and_free(obj + rec->timer_off); } +void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj) +{ + if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_WORKQUEUE))) + return; + bpf_wq_cancel_and_free(obj + rec->wq_off); +} + void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; @@ -679,6 +688,9 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) case BPF_TIMER: bpf_timer_cancel_and_free(field_ptr); break; + case BPF_WORKQUEUE: + bpf_wq_cancel_and_free(field_ptr); + break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; @@ -980,7 +992,7 @@ static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr if (map->ops->map_get_unmapped_area) return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); #ifdef CONFIG_MMU - return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags); #else return addr; #endif @@ -1085,7 +1097,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token, map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | - BPF_RB_ROOT | BPF_REFCOUNT, + BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1115,6 +1127,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token, } break; case BPF_TIMER: + case BPF_WORKQUEUE: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { @@ -3024,17 +3037,46 @@ 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->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) @@ -3469,17 +3511,12 @@ out_put_prog: return err; } -struct bpf_raw_tp_link { - struct bpf_link link; - struct bpf_raw_event_map *btp; -}; - static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); - bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog); + bpf_probe_unregister(raw_tp->btp, raw_tp); bpf_put_raw_tracepoint(raw_tp->btp); } @@ -3544,7 +3581,7 @@ 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, }; @@ -3779,7 +3816,7 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro #endif /* CONFIG_PERF_EVENTS */ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, - const char __user *user_tp_name) + const char __user *user_tp_name, u64 cookie) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; @@ -3826,6 +3863,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog); link->btp = btp; + link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -3833,7 +3871,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, goto out_put_btp; } - err = bpf_probe_register(link->btp, prog); + err = bpf_probe_register(link->btp, link); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; @@ -3846,11 +3884,13 @@ out_put_btp: return err; } -#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd +#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_prog *prog; + void __user *tp_name; + __u64 cookie; int fd; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) @@ -3860,7 +3900,9 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - fd = bpf_raw_tp_link_attach(prog, u64_to_user_ptr(attr->raw_tracepoint.name)); + tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); + cookie = attr->raw_tracepoint.cookie; + fd = bpf_raw_tp_link_attach(prog, tp_name, cookie); if (fd < 0) bpf_prog_put(prog); return fd; @@ -3956,6 +3998,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, * check permissions at attach time. */ return -EPERM; + + ptype = attach_type_to_prog_type(attach_type); + if (prog->type != ptype) + return -EINVAL; + return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; @@ -3974,11 +4021,15 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; + if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION && + attach_type != BPF_TRACE_KPROBE_SESSION) + return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; if (attach_type != BPF_PERF_EVENT && attach_type != BPF_TRACE_KPROBE_MULTI && + attach_type != BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; return 0; @@ -5198,7 +5249,7 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) goto out; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) - ret = bpf_raw_tp_link_attach(prog, NULL); + ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) @@ -5213,6 +5264,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_SK_LOOKUP: ret = netns_bpf_link_create(attr, prog); break; + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_SK_SKB: + ret = sock_map_link_create(attr, prog); + break; #ifdef CONFIG_NET case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); @@ -5235,7 +5290,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); - else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI) + else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || + attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION) ret = bpf_kprobe_multi_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI) ret = bpf_uprobe_multi_link_attach(attr, prog); @@ -5979,7 +6035,6 @@ static struct ctl_table bpf_syscall_table[] = { .mode = 0644, .proc_handler = bpf_stats_handler, }, - { } }; static int __init bpf_syscall_sysctl_init(void) diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index ef6911aee3bb..fedb54c94cdb 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -9,8 +9,8 @@ #include <linux/sysfs.h> /* See scripts/link-vmlinux.sh, gen_btf() func for details */ -extern char __weak __start_BTF[]; -extern char __weak __stop_BTF[]; +extern char __start_BTF[]; +extern char __stop_BTF[]; static ssize_t btf_vmlinux_read(struct file *file, struct kobject *kobj, @@ -32,7 +32,7 @@ static int __init btf_vmlinux_init(void) { bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; - if (!__start_BTF || bin_attr_btf_vmlinux.size == 0) + if (bin_attr_btf_vmlinux.size == 0) return 0; btf_kobj = kobject_create_and_add("btf", kernel_kobj); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index db7599c59c78..f8302a5ca400 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -333,7 +333,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP, NULL, im->ip_epilogue); WARN_ON(err); - if (IS_ENABLED(CONFIG_PREEMPTION)) + if (IS_ENABLED(CONFIG_TASKS_RCU)) call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks); else percpu_ref_kill(&im->pcref); @@ -456,7 +456,9 @@ again: if (err < 0) goto out_free; - arch_protect_bpf_trampoline(im->image, im->size); + err = arch_protect_bpf_trampoline(im->image, im->size); + if (err) + goto out_free; WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) @@ -883,12 +885,13 @@ static void notrace update_prog_stats(struct bpf_prog *prog, * Hence check that 'start' is valid. */ start > NO_START_TIME) { + u64 duration = sched_clock() - start; unsigned long flags; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); - u64_stats_add(&stats->nsecs, sched_clock() - start); + u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } } @@ -1072,17 +1075,10 @@ void __weak arch_free_bpf_trampoline(void *image, unsigned int size) 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) +int __weak arch_protect_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); + return set_memory_rox((long)image, 1); } int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 63749ad5ac6b..77da1f438bec 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -172,7 +172,7 @@ static bool bpf_global_percpu_ma_set; /* verifier_state + insn_idx are pushed to stack when branch is encountered */ struct bpf_verifier_stack_elem { - /* verifer state is 'st' + /* verifier state is 'st' * before processing instruction 'insn_idx' * and after processing instruction 'prev_insn_idx' */ @@ -190,11 +190,6 @@ struct bpf_verifier_stack_elem { #define BPF_MAP_KEY_POISON (1ULL << 63) #define BPF_MAP_KEY_SEEN (1ULL << 62) -#define BPF_MAP_PTR_UNPRIV 1UL -#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ - 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); @@ -209,21 +204,22 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg); static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { - return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON; + return aux->map_ptr_state.poison; } static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) { - return aux->map_ptr_state & BPF_MAP_PTR_UNPRIV; + return aux->map_ptr_state.unpriv; } static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, - const struct bpf_map *map, bool unpriv) + struct bpf_map *map, + bool unpriv, bool poison) { - BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV); unpriv |= bpf_map_ptr_unpriv(aux); - aux->map_ptr_state = (unsigned long)map | - (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); + aux->map_ptr_state.unpriv = unpriv; + aux->map_ptr_state.poison = poison; + aux->map_ptr_state.map_ptr = map; } static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux) @@ -336,6 +332,10 @@ struct bpf_kfunc_call_arg_meta { u8 spi; u8 frameno; } iter; + struct { + struct bpf_map *ptr; + int uid; + } map; u64 mem_size; }; @@ -501,8 +501,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id) } static bool is_sync_callback_calling_kfunc(u32 btf_id); +static bool is_async_callback_calling_kfunc(u32 btf_id); +static bool is_callback_calling_kfunc(u32 btf_id); static bool is_bpf_throw_kfunc(struct bpf_insn *insn); +static bool is_bpf_wq_set_callback_impl_kfunc(u32 btf_id); + static bool is_sync_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || @@ -530,7 +534,8 @@ static bool is_sync_callback_calling_insn(struct bpf_insn *insn) static bool is_async_callback_calling_insn(struct bpf_insn *insn) { - return bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm); + return (bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm)) || + (bpf_pseudo_kfunc_call(insn) && is_async_callback_calling_kfunc(insn->imm)); } static bool is_may_goto_insn(struct bpf_insn *insn) @@ -1429,6 +1434,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, } dst_state->speculative = src->speculative; dst_state->active_rcu_lock = src->active_rcu_lock; + dst_state->active_preempt_lock = src->active_preempt_lock; + dst_state->in_sleepable = src->in_sleepable; dst_state->curframe = src->curframe; dst_state->active_lock.ptr = src->active_lock.ptr; dst_state->active_lock.id = src->active_lock.id; @@ -1842,6 +1849,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) */ if (btf_record_has_field(map->inner_map_meta->record, BPF_TIMER)) reg->map_uid = reg->id; + if (btf_record_has_field(map->inner_map_meta->record, BPF_WORKQUEUE)) + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -2135,7 +2144,7 @@ static void __reg64_deduce_bounds(struct bpf_reg_state *reg) 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. + * values on both sides of 64-bit range in hope to have tighter 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 @@ -2143,7 +2152,7 @@ static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg) * _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 + * with are well-formed ranges in respective s64 or u64 domain, just * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments. */ __u64 new_umin, new_umax; @@ -2359,6 +2368,8 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env, regs[regno].type = PTR_TO_BTF_ID | flag; regs[regno].btf = btf; regs[regno].btf_id = btf_id; + if (type_may_be_null(flag)) + regs[regno].id = ++env->id_gen; } #define DEF_NOT_SUBREG (0) @@ -2402,7 +2413,7 @@ static void init_func_state(struct bpf_verifier_env *env, /* Similar to push_stack(), but for async callbacks */ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, - int subprog) + int subprog, bool is_sleepable) { struct bpf_verifier_stack_elem *elem; struct bpf_func_state *frame; @@ -2429,6 +2440,7 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, * Initialize it similar to do_check_common(). */ elem->st.branches = 1; + elem->st.in_sleepable = is_sleepable; frame = kzalloc(sizeof(*frame), GFP_KERNEL); if (!frame) goto err; @@ -3615,7 +3627,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * sreg needs precision before this insn */ bt_clear_reg(bt, dreg); - bt_set_reg(bt, sreg); + if (sreg != BPF_REG_FP) + bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. @@ -3631,7 +3644,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * both dreg and sreg need precision * before this insn */ - bt_set_reg(bt, sreg); + if (sreg != BPF_REG_FP) + bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ @@ -5274,7 +5288,8 @@ bad_type: static bool in_sleepable(struct bpf_verifier_env *env) { - return env->prog->sleepable; + return env->prog->sleepable || + (env->cur_state && env->cur_state->in_sleepable); } /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() @@ -5297,6 +5312,7 @@ BTF_ID(struct, cgroup) BTF_ID(struct, bpf_cpumask) #endif BTF_ID(struct, task_struct) +BTF_ID(struct, bpf_crypto_ctx) BTF_SET_END(rcu_protected_types) static bool rcu_protected_object(const struct btf *btf, u32 btf_id) @@ -5386,8 +5402,6 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, */ mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field)); - /* For mark_ptr_or_null_reg */ - val_reg->id = ++env->id_gen; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && @@ -5682,6 +5696,13 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_FLOW_KEYS; } +static bool is_arena_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = reg_state(env, regno); + + return reg->type == PTR_TO_ARENA; +} + static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { #ifdef CONFIG_NET [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], @@ -5698,7 +5719,8 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg) return true; /* Types listed in the reg2btf_ids are always trusted */ - if (reg2btf_ids[base_type(reg->type)]) + if (reg2btf_ids[base_type(reg->type)] && + !bpf_type_has_unsafe_modifiers(reg->type)) return true; /* If a register is not referenced, it is trusted if it has the @@ -6318,6 +6340,7 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, #define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu) #define BTF_TYPE_SAFE_RCU_OR_NULL(__type) __PASTE(__type, __safe_rcu_or_null) #define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted) +#define BTF_TYPE_SAFE_TRUSTED_OR_NULL(__type) __PASTE(__type, __safe_trusted_or_null) /* * Allow list few fields as RCU trusted or full trusted. @@ -6381,7 +6404,7 @@ BTF_TYPE_SAFE_TRUSTED(struct dentry) { struct inode *d_inode; }; -BTF_TYPE_SAFE_TRUSTED(struct socket) { +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) { struct sock *sk; }; @@ -6416,11 +6439,20 @@ static bool type_is_trusted(struct bpf_verifier_env *env, BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); - BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct socket)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); } +static bool type_is_trusted_or_null(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const char *field_name, u32 btf_id) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, + "__safe_trusted_or_null"); +} + static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, @@ -6529,6 +6561,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, */ if (type_is_trusted(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED; + } else if (type_is_trusted_or_null(env, reg, field_name, btf_id)) { + flag |= PTR_TRUSTED | PTR_MAYBE_NULL; } else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) { if (type_is_rcu(env, reg, field_name, btf_id)) { /* ignore __rcu tag and mark it MEM_RCU */ @@ -6694,6 +6728,11 @@ 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)) { @@ -6960,6 +6999,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return err; } +static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, + bool allow_trust_mismatch); + static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { int load_reg; @@ -7019,7 +7061,8 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || is_flow_key_reg(env, insn->dst_reg) || - is_sk_reg(env, insn->dst_reg)) { + is_sk_reg(env, insn->dst_reg) || + (is_arena_reg(env, insn->dst_reg) && !bpf_jit_supports_insn(insn, true))) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); @@ -7055,6 +7098,11 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (err) return err; + if (is_arena_reg(env, insn->dst_reg)) { + err = save_aux_ptr_type(env, PTR_TO_ARENA, false); + if (err) + return err; + } /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); @@ -7577,6 +7625,23 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, return 0; } +static int process_wq_func(struct bpf_verifier_env *env, int regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + struct bpf_map *map = reg->map_ptr; + u64 val = reg->var_off.value; + + if (map->record->wq_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct bpf_wq' that is at %d\n", + val + reg->off, map->record->wq_off); + return -EINVAL; + } + meta->map.uid = reg->map_uid; + meta->map.ptr = map; + return 0; +} + static int process_kptr_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { @@ -9471,7 +9536,7 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins */ env->subprog_info[subprog].is_cb = true; if (bpf_pseudo_kfunc_call(insn) && - !is_sync_callback_calling_kfunc(insn->imm)) { + !is_callback_calling_kfunc(insn->imm)) { verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", func_id_name(insn->imm), insn->imm); return -EFAULT; @@ -9485,10 +9550,11 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins if (is_async_callback_calling_insn(insn)) { struct bpf_verifier_state *async_cb; - /* there is no real recursion here. timer callbacks are async */ + /* there is no real recursion here. timer and workqueue callbacks are async */ env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, - insn_idx, subprog); + insn_idx, subprog, + is_bpf_wq_set_callback_impl_kfunc(insn->imm)); if (!async_cb) return -EFAULT; callee = async_cb->frame[0]; @@ -9548,6 +9614,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EINVAL; } + /* Only global subprogs cannot be called with preemption disabled. */ + if (env->cur_state->active_preempt_lock) { + verbose(env, "global function calls are not allowed with preemption disabled,\n" + "use static function instead\n"); + return -EINVAL; + } + if (err) { verbose(env, "Caller passes invalid args into func#%d ('%s')\n", subprog, sub_name); @@ -9640,12 +9713,8 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, struct bpf_map *map; int err; - if (bpf_map_ptr_poisoned(insn_aux)) { - verbose(env, "tail_call abusing map_ptr\n"); - return -EINVAL; - } - - map = BPF_MAP_PTR(insn_aux->map_ptr_state); + /* valid map_ptr and poison value does not matter */ + map = insn_aux->map_ptr_state.map_ptr; if (!map->ops->map_set_for_each_callback_args || !map->ops->map_for_each_callback) { verbose(env, "callback function not allowed for map\n"); @@ -10004,12 +10073,12 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return -EACCES; } - if (!BPF_MAP_PTR(aux->map_ptr_state)) + if (!aux->map_ptr_state.map_ptr) + bpf_map_ptr_store(aux, meta->map_ptr, + !meta->map_ptr->bypass_spec_v1, false); + else if (aux->map_ptr_state.map_ptr != meta->map_ptr) bpf_map_ptr_store(aux, meta->map_ptr, - !meta->map_ptr->bypass_spec_v1); - else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr) - bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON, - !meta->map_ptr->bypass_spec_v1); + !meta->map_ptr->bypass_spec_v1, true); return 0; } @@ -10188,8 +10257,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (env->ops->get_func_proto) fn = env->ops->get_func_proto(func_id, env->prog); if (!fn) { - verbose(env, "unknown func %s#%d\n", func_id_name(func_id), - func_id); + verbose(env, "program of this type cannot use helper %s#%d\n", + func_id_name(func_id), func_id); return -EINVAL; } @@ -10238,6 +10307,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } + if (env->cur_state->active_preempt_lock) { + if (fn->might_sleep) { + verbose(env, "sleepable helper %s#%d in non-preemptible region\n", + func_id_name(func_id), func_id); + return -EINVAL; + } + + if (in_sleepable(env) && is_storage_get_function(func_id)) + env->insn_aux_data[insn_idx].storage_get_func_atomic = true; + } + meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { @@ -10826,6 +10906,7 @@ enum { KF_ARG_LIST_NODE_ID, KF_ARG_RB_ROOT_ID, KF_ARG_RB_NODE_ID, + KF_ARG_WORKQUEUE_ID, }; BTF_ID_LIST(kf_arg_btf_ids) @@ -10834,6 +10915,7 @@ BTF_ID(struct, bpf_list_head) BTF_ID(struct, bpf_list_node) BTF_ID(struct, bpf_rb_root) BTF_ID(struct, bpf_rb_node) +BTF_ID(struct, bpf_wq) static bool __is_kfunc_ptr_arg_type(const struct btf *btf, const struct btf_param *arg, int type) @@ -10877,6 +10959,11 @@ static bool is_kfunc_arg_rbtree_node(const struct btf *btf, const struct btf_par return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_NODE_ID); } +static bool is_kfunc_arg_wq(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_WORKQUEUE_ID); +} + static bool is_kfunc_arg_callback(struct bpf_verifier_env *env, const struct btf *btf, const struct btf_param *arg) { @@ -10946,6 +11033,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_NULL, KF_ARG_PTR_TO_CONST_STR, KF_ARG_PTR_TO_MAP, + KF_ARG_PTR_TO_WORKQUEUE, }; enum special_kfunc_type { @@ -10971,7 +11059,11 @@ enum special_kfunc_type { KF_bpf_percpu_obj_new_impl, KF_bpf_percpu_obj_drop_impl, KF_bpf_throw, + KF_bpf_wq_set_callback_impl, + KF_bpf_preempt_disable, + KF_bpf_preempt_enable, KF_bpf_iter_css_task_new, + KF_bpf_session_cookie, }; BTF_SET_START(special_kfunc_set) @@ -10995,6 +11087,7 @@ BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) +BTF_ID(func, bpf_wq_set_callback_impl) #ifdef CONFIG_CGROUPS BTF_ID(func, bpf_iter_css_task_new) #endif @@ -11023,11 +11116,15 @@ BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) +BTF_ID(func, bpf_wq_set_callback_impl) +BTF_ID(func, bpf_preempt_disable) +BTF_ID(func, bpf_preempt_enable) #ifdef CONFIG_CGROUPS BTF_ID(func, bpf_iter_css_task_new) #else BTF_ID_UNUSED #endif +BTF_ID(func, bpf_session_cookie) static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -11049,6 +11146,16 @@ static bool is_kfunc_bpf_rcu_read_unlock(struct bpf_kfunc_call_arg_meta *meta) return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_unlock]; } +static bool is_kfunc_bpf_preempt_disable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_preempt_disable]; +} + +static bool is_kfunc_bpf_preempt_enable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_preempt_enable]; +} + static enum kfunc_ptr_arg_type get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, @@ -11102,6 +11209,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_map(meta->btf, &args[argno])) return KF_ARG_PTR_TO_MAP; + if (is_kfunc_arg_wq(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_WORKQUEUE; + 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", @@ -11353,12 +11463,28 @@ static bool is_sync_callback_calling_kfunc(u32 btf_id) return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]; } +static bool is_async_callback_calling_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_wq_set_callback_impl]; +} + static bool is_bpf_throw_kfunc(struct bpf_insn *insn) { return bpf_pseudo_kfunc_call(insn) && insn->off == 0 && insn->imm == special_kfunc_list[KF_bpf_throw]; } +static bool is_bpf_wq_set_callback_impl_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_wq_set_callback_impl]; +} + +static bool is_callback_calling_kfunc(u32 btf_id) +{ + return is_sync_callback_calling_kfunc(btf_id) || + is_async_callback_calling_kfunc(btf_id); +} + static bool is_rbtree_lock_required_kfunc(u32 btf_id) { return is_bpf_rbtree_api_kfunc(btf_id); @@ -11703,6 +11829,34 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_NULL: continue; case KF_ARG_PTR_TO_MAP: + if (!reg->map_ptr) { + verbose(env, "pointer in R%d isn't map pointer\n", regno); + return -EINVAL; + } + if (meta->map.ptr && reg->map_ptr->record->wq_off >= 0) { + /* Use map_uid (which is unique id of inner map) to reject: + * inner_map1 = bpf_map_lookup_elem(outer_map, key1) + * inner_map2 = bpf_map_lookup_elem(outer_map, key2) + * if (inner_map1 && inner_map2) { + * wq = bpf_map_lookup_elem(inner_map1); + * if (wq) + * // mismatch would have been allowed + * bpf_wq_init(wq, inner_map2); + * } + * + * Comparing map_ptr is enough to distinguish normal and outer maps. + */ + if (meta->map.ptr != reg->map_ptr || + meta->map.uid != reg->map_uid) { + verbose(env, + "workqueue pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", + meta->map.uid, reg->map_uid); + return -EINVAL; + } + } + meta->map.ptr = reg->map_ptr; + meta->map.uid = reg->map_uid; + fallthrough; case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) @@ -11735,6 +11889,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_CALLBACK: case KF_ARG_PTR_TO_REFCOUNTED_KPTR: case KF_ARG_PTR_TO_CONST_STR: + case KF_ARG_PTR_TO_WORKQUEUE: /* Trusted by default */ break; default: @@ -12021,6 +12176,15 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (ret) return ret; break; + case KF_ARG_PTR_TO_WORKQUEUE: + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "arg#%d doesn't point to a map value\n", i); + return -EINVAL; + } + ret = process_wq_func(env, regno, meta); + if (ret < 0) + return ret; + break; } } @@ -12080,11 +12244,11 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { - const struct btf_type *t, *ptr_type; + bool sleepable, rcu_lock, rcu_unlock, preempt_disable, preempt_enable; u32 i, nargs, ptr_type_id, release_ref_obj_id; struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; - bool sleepable, rcu_lock, rcu_unlock; + const struct btf_type *t, *ptr_type; struct bpf_kfunc_call_arg_meta meta; struct bpf_insn_aux_data *insn_aux; int err, insn_idx = *insn_idx_p; @@ -12132,9 +12296,27 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } } + if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) { + meta.r0_size = sizeof(u64); + meta.r0_rdonly = false; + } + + if (is_bpf_wq_set_callback_impl_kfunc(meta.func_id)) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_timer_callback_state); + if (err) { + verbose(env, "kfunc %s#%d failed callback verification\n", + func_name, meta.func_id); + return err; + } + } + rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); + preempt_disable = is_kfunc_bpf_preempt_disable(&meta); + preempt_enable = is_kfunc_bpf_preempt_enable(&meta); + if (env->cur_state->active_rcu_lock) { struct bpf_func_state *state; struct bpf_reg_state *reg; @@ -12167,6 +12349,22 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EINVAL; } + if (env->cur_state->active_preempt_lock) { + if (preempt_disable) { + env->cur_state->active_preempt_lock++; + } else if (preempt_enable) { + env->cur_state->active_preempt_lock--; + } else if (sleepable) { + verbose(env, "kernel func %s is sleepable within non-preemptible region\n", func_name); + return -EACCES; + } + } else if (preempt_disable) { + env->cur_state->active_preempt_lock++; + } else if (preempt_enable) { + verbose(env, "unmatched attempt to enable preemption (kernel function %s)\n", func_name); + return -EINVAL; + } + /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ @@ -13305,7 +13503,6 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); - s32 smin_val = src_reg->s32_min_value; u32 umax_val = src_reg->u32_max_value; if (src_known && dst_known) { @@ -13318,18 +13515,16 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val); - if (dst_reg->s32_min_value < 0 || smin_val < 0) { - /* Lose signed bounds when ANDing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->s32_min_value = S32_MIN; - dst_reg->s32_max_value = S32_MAX; - } else { - /* ANDing two positives gives a positive, so safe to - * cast result into s64. - */ + + /* Safe to set s32 bounds by casting u32 result into s32 when u32 + * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. + */ + if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; + } else { + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; } } @@ -13338,7 +13533,6 @@ static void scalar_min_max_and(struct bpf_reg_state *dst_reg, { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); - s64 smin_val = src_reg->smin_value; u64 umax_val = src_reg->umax_value; if (src_known && dst_known) { @@ -13351,18 +13545,16 @@ static void scalar_min_max_and(struct bpf_reg_state *dst_reg, */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = min(dst_reg->umax_value, umax_val); - if (dst_reg->smin_value < 0 || smin_val < 0) { - /* Lose signed bounds when ANDing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - /* ANDing two positives gives a positive, so safe to - * cast result into s64. - */ + + /* Safe to set s64 bounds by casting u64 result into s64 when u64 + * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. + */ + if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; + } else { + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); @@ -13374,7 +13566,6 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); - s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; if (src_known && dst_known) { @@ -13387,18 +13578,16 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, */ dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val); dst_reg->u32_max_value = var32_off.value | var32_off.mask; - if (dst_reg->s32_min_value < 0 || smin_val < 0) { - /* Lose signed bounds when ORing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->s32_min_value = S32_MIN; - dst_reg->s32_max_value = S32_MAX; - } else { - /* ORing two positives gives a positive, so safe to - * cast result into s64. - */ + + /* Safe to set s32 bounds by casting u32 result into s32 when u32 + * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. + */ + if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; + } else { + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; } } @@ -13407,7 +13596,6 @@ static void scalar_min_max_or(struct bpf_reg_state *dst_reg, { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); - s64 smin_val = src_reg->smin_value; u64 umin_val = src_reg->umin_value; if (src_known && dst_known) { @@ -13420,18 +13608,16 @@ static void scalar_min_max_or(struct bpf_reg_state *dst_reg, */ dst_reg->umin_value = max(dst_reg->umin_value, umin_val); dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; - if (dst_reg->smin_value < 0 || smin_val < 0) { - /* Lose signed bounds when ORing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - /* ORing two positives gives a positive, so safe to - * cast result into s64. - */ + + /* Safe to set s64 bounds by casting u64 result into s64 when u64 + * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. + */ + if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; + } else { + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); @@ -13443,7 +13629,6 @@ static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); - s32 smin_val = src_reg->s32_min_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); @@ -13454,10 +13639,10 @@ static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = var32_off.value | var32_off.mask; - if (dst_reg->s32_min_value >= 0 && smin_val >= 0) { - /* XORing two positive sign numbers gives a positive, - * so safe to cast u32 result into s32. - */ + /* Safe to set s32 bounds by casting u32 result into s32 when u32 + * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. + */ + if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { @@ -13471,7 +13656,6 @@ static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); - s64 smin_val = src_reg->smin_value; if (src_known && dst_known) { /* dst_reg->var_off.value has been updated earlier */ @@ -13483,10 +13667,10 @@ static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; - if (dst_reg->smin_value >= 0 && smin_val >= 0) { - /* XORing two positive sign numbers gives a positive, - * so safe to cast u64 result into s64. - */ + /* Safe to set s64 bounds by casting u64 result into s64 when u64 + * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. + */ + if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { @@ -13694,6 +13878,46 @@ static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, __update_reg_bounds(dst_reg); } +static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn, + const struct bpf_reg_state *src_reg) +{ + bool src_is_const = false; + u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; + + if (insn_bitness == 32) { + if (tnum_subreg_is_const(src_reg->var_off) + && src_reg->s32_min_value == src_reg->s32_max_value + && src_reg->u32_min_value == src_reg->u32_max_value) + src_is_const = true; + } else { + if (tnum_is_const(src_reg->var_off) + && src_reg->smin_value == src_reg->smax_value + && src_reg->umin_value == src_reg->umax_value) + src_is_const = true; + } + + switch (BPF_OP(insn->code)) { + case BPF_ADD: + case BPF_SUB: + case BPF_AND: + case BPF_XOR: + case BPF_OR: + case BPF_MUL: + return true; + + /* Shift operators range is only computable if shift dimension operand + * is a constant. Shifts greater than 31 or 63 are undefined. This + * includes shifts by a negative number. + */ + case BPF_LSH: + case BPF_RSH: + case BPF_ARSH: + return (src_is_const && src_reg->umax_value < insn_bitness); + default: + return false; + } +} + /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. @@ -13703,53 +13927,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *dst_reg, struct bpf_reg_state src_reg) { - struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); - bool src_known; - s64 smin_val, smax_val; - u64 umin_val, umax_val; - s32 s32_min_val, s32_max_val; - u32 u32_min_val, u32_max_val; - u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); int ret; - smin_val = src_reg.smin_value; - smax_val = src_reg.smax_value; - umin_val = src_reg.umin_value; - umax_val = src_reg.umax_value; - - s32_min_val = src_reg.s32_min_value; - s32_max_val = src_reg.s32_max_value; - u32_min_val = src_reg.u32_min_value; - u32_max_val = src_reg.u32_max_value; - - if (alu32) { - src_known = tnum_subreg_is_const(src_reg.var_off); - if ((src_known && - (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) || - s32_min_val > s32_max_val || u32_min_val > u32_max_val) { - /* Taint dst register if offset had invalid bounds - * derived from e.g. dead branches. - */ - __mark_reg_unknown(env, dst_reg); - return 0; - } - } else { - src_known = tnum_is_const(src_reg.var_off); - if ((src_known && - (smin_val != smax_val || umin_val != umax_val)) || - smin_val > smax_val || umin_val > umax_val) { - /* Taint dst register if offset had invalid bounds - * derived from e.g. dead branches. - */ - __mark_reg_unknown(env, dst_reg); - return 0; - } - } - - if (!src_known && - opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { + if (!is_safe_to_compute_dst_reg_range(insn, &src_reg)) { __mark_reg_unknown(env, dst_reg); return 0; } @@ -13806,46 +13988,24 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, scalar_min_max_xor(dst_reg, &src_reg); break; case BPF_LSH: - if (umax_val >= insn_bitness) { - /* Shifts greater than 31 or 63 are undefined. - * This includes shifts by a negative number. - */ - mark_reg_unknown(env, regs, insn->dst_reg); - break; - } if (alu32) scalar32_min_max_lsh(dst_reg, &src_reg); else scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: - if (umax_val >= insn_bitness) { - /* Shifts greater than 31 or 63 are undefined. - * This includes shifts by a negative number. - */ - mark_reg_unknown(env, regs, insn->dst_reg); - break; - } if (alu32) scalar32_min_max_rsh(dst_reg, &src_reg); else scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: - if (umax_val >= insn_bitness) { - /* Shifts greater than 31 or 63 are undefined. - * This includes shifts by a negative number. - */ - mark_reg_unknown(env, regs, insn->dst_reg); - break; - } if (alu32) scalar32_min_max_arsh(dst_reg, &src_reg); else scalar_min_max_arsh(dst_reg, &src_reg); break; default: - mark_reg_unknown(env, regs, insn->dst_reg); break; } @@ -14014,6 +14174,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n"); return -EINVAL; } + if (!env->prog->aux->arena) { + verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n"); + return -EINVAL; + } } else { if ((insn->off != 0 && insn->off != 8 && insn->off != 16 && insn->off != 32) || insn->imm) { @@ -14046,8 +14210,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->imm) { /* off == BPF_ADDR_SPACE_CAST */ mark_reg_unknown(env, regs, insn->dst_reg); - if (insn->imm == 1) /* cast from as(1) to as(0) */ + if (insn->imm == 1) { /* cast from as(1) to as(0) */ dst_reg->type = PTR_TO_ARENA; + /* PTR_TO_ARENA is 32-bit */ + dst_reg->subreg_def = env->insn_idx + 1; + } } else if (insn->off == 0) { /* case: R1 = R2 * copy register state to dest reg @@ -14544,7 +14711,19 @@ static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state struct tnum t; u64 val; -again: + /* In case of GE/GT/SGE/JST, reuse LE/LT/SLE/SLT logic from below */ + switch (opcode) { + case BPF_JGE: + case BPF_JGT: + case BPF_JSGE: + case BPF_JSGT: + opcode = flip_opcode(opcode); + swap(reg1, reg2); + break; + default: + break; + } + switch (opcode) { case BPF_JEQ: if (is_jmp32) { @@ -14687,14 +14866,6 @@ again: 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; } @@ -14702,7 +14873,7 @@ again: /* 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). + * check, in which case we have a 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. */ @@ -15317,6 +15488,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if (env->cur_state->active_preempt_lock) { + verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_preempt_disable-ed region\n"); + return -EINVAL; + } + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -16884,6 +17060,12 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->active_rcu_lock != cur->active_rcu_lock) return false; + if (old->active_preempt_lock != cur->active_preempt_lock) + return false; + + if (old->in_sleepable != cur->in_sleepable) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -17340,7 +17522,7 @@ hit: err = propagate_liveness(env, &sl->state, cur); /* if previous state reached the exit with precision and - * current state is equivalent to it (except precsion marks) + * current state is equivalent to it (except precision marks) * the precision needs to be propagated back in * the current state. */ @@ -17518,7 +17700,7 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) } static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, - bool allow_trust_missmatch) + bool allow_trust_mismatch) { enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type; @@ -17536,7 +17718,7 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ * src_reg == stack|map in some other branch. * Reject it. */ - if (allow_trust_missmatch && + if (allow_trust_mismatch && base_type(type) == PTR_TO_BTF_ID && base_type(*prev_type) == PTR_TO_BTF_ID) { /* @@ -17832,6 +18014,13 @@ process_bpf_exit_full: return -EINVAL; } + if (env->cur_state->active_preempt_lock && !env->cur_state->curframe) { + verbose(env, "%d bpf_preempt_enable%s missing\n", + env->cur_state->active_preempt_lock, + env->cur_state->active_preempt_lock == 1 ? " is" : "(s) are"); + return -EINVAL; + } + /* We must do check_reference_leak here before * prepare_func_exit to handle the case when * state->curframe > 0, it may be a callback @@ -18129,6 +18318,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_wq yet\n"); + return -EINVAL; + } + } + if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); @@ -18269,8 +18465,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose(env, "fd %d is not pointing to valid bpf_map\n", - insn[0].imm); + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } @@ -18324,6 +18519,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) } if (env->used_map_cnt >= MAX_USED_MAPS) { + verbose(env, "The total number of maps per program has reached the limit of %u\n", + MAX_USED_MAPS); fdput(f); return -E2BIG; } @@ -18359,15 +18556,18 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) } if (!env->prog->jit_requested) { verbose(env, "JIT is required to use arena\n"); + fdput(f); return -EOPNOTSUPP; } if (!bpf_jit_supports_arena()) { verbose(env, "JIT doesn't support arena\n"); + fdput(f); return -EOPNOTSUPP; } env->prog->aux->arena = (void *)map; if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { verbose(env, "arena's user address must be set via map_extra or mmap()\n"); + fdput(f); return -EINVAL; } } @@ -18935,6 +19135,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->code == (BPF_ST | BPF_MEM | BPF_W) || insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; + } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || + insn->code == (BPF_STX | BPF_ATOMIC | BPF_DW)) && + env->insn_aux_data[i + delta].ptr_type == PTR_TO_ARENA) { + insn->code = BPF_STX | BPF_PROBE_ATOMIC | BPF_SIZE(insn->code); + env->prog->aux->num_exentries++; + continue; } else { continue; } @@ -19121,12 +19327,19 @@ static int jit_subprogs(struct bpf_verifier_env *env) env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; - if (bpf_pseudo_func(insn)) + if (bpf_pseudo_func(insn)) { +#if defined(MODULES_VADDR) + u64 addr = MODULES_VADDR; +#else + u64 addr = VMALLOC_START; +#endif /* jit (e.g. x86_64) may emit fewer instructions * if it learns a u32 imm is the same as a u64 imm. - * Force a non zero here. + * Set close enough to possible prog address. */ - insn[1].imm = 1; + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; + } } err = bpf_prog_alloc_jited_linfo(prog); @@ -19158,6 +19371,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; + func[i]->sleepable = prog->sleepable; func[i]->aux->func_idx = i; /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; @@ -19198,6 +19412,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) BPF_CLASS(insn->code) == BPF_ST) && BPF_MODE(insn->code) == BPF_PROBE_MEM32) num_exentries++; + if (BPF_CLASS(insn->code) == BPF_STX && + BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) + num_exentries++; } func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; @@ -19262,10 +19479,14 @@ static int jit_subprogs(struct bpf_verifier_env *env) * bpf_prog_load will add the kallsyms for the main program. */ for (i = 1; i < env->subprog_cnt; i++) { - bpf_prog_lock_ro(func[i]); - bpf_prog_kallsyms_add(func[i]); + err = bpf_prog_lock_ro(func[i]); + if (err) + goto out_free; } + for (i = 1; i < env->subprog_cnt; i++) + bpf_prog_kallsyms_add(func[i]); + /* Last step: make now unused interpreter insns from main * prog consistent for later dump requests, so they can * later look the same as if they were interpreted only. @@ -19525,6 +19746,13 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *cnt = 1; + } else if (is_bpf_wq_set_callback_impl_kfunc(desc->func_id)) { + struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(BPF_REG_4, (long)env->prog->aux) }; + + insn_buf[0] = ld_addrs[0]; + insn_buf[1] = ld_addrs[1]; + insn_buf[2] = *insn; + *cnt = 3; } return 0; } @@ -19601,8 +19829,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env) (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) { /* convert to 32-bit mov that clears upper 32-bit */ insn->code = BPF_ALU | BPF_MOV | BPF_X; - /* clear off, so it's a normal 'wX = wY' from JIT pov */ + /* clear off and imm, so it's a normal 'wX = wY' from JIT pov */ insn->off = 0; + insn->imm = 0; } /* cast from as(0) to as(1) should be handled by JIT */ goto next_insn; } @@ -19652,6 +19881,36 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto next_insn; } + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + goto next_insn; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } + /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || @@ -19766,6 +20025,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto next_insn; } + /* Skip inlining the helper call if the JIT does it. */ + if (bpf_jit_inlines_helper_call(insn->imm)) + goto next_insn; + if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) @@ -19799,7 +20062,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) !bpf_map_ptr_unpriv(aux)) { struct bpf_jit_poke_descriptor desc = { .reason = BPF_POKE_REASON_TAIL_CALL, - .tail_call.map = BPF_MAP_PTR(aux->map_ptr_state), + .tail_call.map = aux->map_ptr_state.map_ptr, .tail_call.key = bpf_map_key_immediate(aux), .insn_idx = i + delta, }; @@ -19828,7 +20091,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) return -EINVAL; } - map_ptr = BPF_MAP_PTR(aux->map_ptr_state); + map_ptr = aux->map_ptr_state.map_ptr; insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, @@ -19936,7 +20199,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; - map_ptr = BPF_MAP_PTR(aux->map_ptr_state); + map_ptr = aux->map_ptr_state.map_ptr; ops = map_ptr->ops; if (insn->imm == BPF_FUNC_map_lookup_elem && ops->map_gen_lookup) { @@ -20042,6 +20305,30 @@ patch_map_ops_generic: goto next_insn; } +#ifdef CONFIG_X86_64 + /* Implement bpf_get_smp_processor_id() inline. */ + if (insn->imm == BPF_FUNC_get_smp_processor_id && + prog->jit_requested && bpf_jit_supports_percpu_insn()) { + /* BPF_FUNC_get_smp_processor_id inlining is an + * optimization, so if pcpu_hot.cpu_number is ever + * changed in some incompatible and hard to support + * way, it's fine to back out this inlining logic + */ + insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number); + insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); + insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0); + cnt = 3; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } +#endif /* Implement bpf_get_func_arg inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_arg) { @@ -20125,6 +20412,62 @@ patch_map_ops_generic: goto next_insn; } + /* Implement bpf_get_branch_snapshot inline. */ + if (IS_ENABLED(CONFIG_PERF_EVENTS) && + prog->jit_requested && BITS_PER_LONG == 64 && + insn->imm == BPF_FUNC_get_branch_snapshot) { + /* We are dealing with the following func protos: + * u64 bpf_get_branch_snapshot(void *buf, u32 size, u64 flags); + * int perf_snapshot_branch_stack(struct perf_branch_entry *entries, u32 cnt); + */ + const u32 br_entry_size = sizeof(struct perf_branch_entry); + + /* struct perf_branch_entry is part of UAPI and is + * used as an array element, so extremely unlikely to + * ever grow or shrink + */ + BUILD_BUG_ON(br_entry_size != 24); + + /* if (unlikely(flags)) return -EINVAL */ + insn_buf[0] = BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 0, 7); + + /* Transform size (bytes) into number of entries (cnt = size / 24). + * But to avoid expensive division instruction, we implement + * divide-by-3 through multiplication, followed by further + * division by 8 through 3-bit right shift. + * Refer to book "Hacker's Delight, 2nd ed." by Henry S. Warren, Jr., + * p. 227, chapter "Unsigned Division by 3" for details and proofs. + * + * N / 3 <=> M * N / 2^33, where M = (2^33 + 1) / 3 = 0xaaaaaaab. + */ + insn_buf[1] = BPF_MOV32_IMM(BPF_REG_0, 0xaaaaaaab); + insn_buf[2] = BPF_ALU64_REG(BPF_MUL, BPF_REG_2, BPF_REG_0); + insn_buf[3] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 36); + + /* call perf_snapshot_branch_stack implementation */ + insn_buf[4] = BPF_EMIT_CALL(static_call_query(perf_snapshot_branch_stack)); + /* if (entry_cnt == 0) return -ENOENT */ + insn_buf[5] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4); + /* return entry_cnt * sizeof(struct perf_branch_entry) */ + insn_buf[6] = BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, br_entry_size); + insn_buf[7] = BPF_JMP_A(3); + /* return -EINVAL; */ + insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); + insn_buf[9] = BPF_JMP_A(1); + /* return -ENOENT; */ + insn_buf[10] = BPF_MOV64_IMM(BPF_REG_0, -ENOENT); + cnt = 11; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + /* Implement bpf_kptr_xchg inline */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_kptr_xchg && diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 520a11cb12f4..b9dbf6bf2779 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1335,6 +1335,7 @@ static int __init cgroup_no_v1(char *str) continue; cgroup_no_v1_mask |= 1 << i; + break; } } return 1; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index a66c088c851c..e32b6972c478 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5368,7 +5368,8 @@ static void css_free_rwork_fn(struct work_struct *work) } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); - cgroup1_pidlist_destroy_all(cgrp); + if (!cgroup_on_dfl(cgrp)) + cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); bpf_cgrp_storage_free(cgrp); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 4237c8748715..c12b9fdb22a4 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -202,6 +202,14 @@ struct cpuset { }; /* + * Legacy hierarchy call to cgroup_transfer_tasks() is handled asynchrously + */ +struct cpuset_remove_tasks_struct { + struct work_struct work; + struct cpuset *cs; +}; + +/* * Exclusive CPUs distributed out to sub-partitions of top_cpuset */ static cpumask_var_t subpartitions_cpus; @@ -360,9 +368,10 @@ static inline void notify_partition_change(struct cpuset *cs, int old_prs) } static struct cpuset top_cpuset = { - .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | - (1 << CS_MEM_EXCLUSIVE)), + .flags = BIT(CS_ONLINE) | BIT(CS_CPU_EXCLUSIVE) | + BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE), .partition_root_state = PRS_ROOT, + .relax_domain_level = -1, .remote_sibling = LIST_HEAD_INIT(top_cpuset.remote_sibling), }; @@ -449,12 +458,6 @@ static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; -/* - * CPU / memory hotplug is handled asynchronously. - */ -static void cpuset_hotplug_workfn(struct work_struct *work); -static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); - static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); static inline void check_insane_mems_config(nodemask_t *nodes) @@ -540,22 +543,10 @@ static void guarantee_online_cpus(struct task_struct *tsk, rcu_read_lock(); cs = task_cs(tsk); - while (!cpumask_intersects(cs->effective_cpus, pmask)) { + while (!cpumask_intersects(cs->effective_cpus, pmask)) cs = parent_cs(cs); - if (unlikely(!cs)) { - /* - * The top cpuset doesn't have any online cpu as a - * consequence of a race between cpuset_hotplug_work - * and cpu hotplug notifier. But we know the top - * cpuset's effective_cpus is on its way to be - * identical to cpu_online_mask. - */ - goto out_unlock; - } - } - cpumask_and(pmask, pmask, cs->effective_cpus); -out_unlock: + cpumask_and(pmask, pmask, cs->effective_cpus); rcu_read_unlock(); } @@ -1217,7 +1208,7 @@ static void rebuild_sched_domains_locked(void) /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). - * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. + * Anyways, cpuset_handle_hotplug() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset @@ -1260,12 +1251,17 @@ static void rebuild_sched_domains_locked(void) } #endif /* CONFIG_SMP */ -void rebuild_sched_domains(void) +static void rebuild_sched_domains_cpuslocked(void) { - cpus_read_lock(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); +} + +void rebuild_sched_domains(void) +{ + cpus_read_lock(); + rebuild_sched_domains_cpuslocked(); cpus_read_unlock(); } @@ -2079,14 +2075,11 @@ write_error: /* * For partcmd_update without newmask, it is being called from - * cpuset_hotplug_workfn() where cpus_read_lock() wasn't taken. - * Update the load balance flag and scheduling domain if - * cpus_read_trylock() is successful. + * cpuset_handle_hotplug(). Update the load balance flag and + * scheduling domain accordingly. */ - if ((cmd == partcmd_update) && !newmask && cpus_read_trylock()) { + if ((cmd == partcmd_update) && !newmask) update_partition_sd_lb(cs, old_prs); - cpus_read_unlock(); - } notify_partition_change(cs, old_prs); return 0; @@ -2948,7 +2941,7 @@ bool current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP - if (val < -1 || val >= sched_domain_level_max) + if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif @@ -3599,8 +3592,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * - * cpuset_hotplug_work calls back into cgroup core via - * cgroup_transfer_tasks() and waiting for it from a cgroupfs + * cpuset_handle_hotplug may call back into cgroup core asynchronously + * via cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after @@ -3609,7 +3602,6 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, */ css_get(&cs->css); kernfs_break_active_protection(of->kn); - flush_work(&cpuset_hotplug_work); cpus_read_lock(); mutex_lock(&cpuset_mutex); @@ -3782,9 +3774,6 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, buf = strstrip(buf); - /* - * Convert "root" to ENABLED, and convert "member" to DISABLED. - */ if (!strcmp(buf, "root")) val = PRS_ROOT; else if (!strcmp(buf, "member")) @@ -4060,11 +4049,6 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; - /* - * Clear CS_SCHED_LOAD_BALANCE if parent is isolated - */ - if (!is_sched_load_balance(parent)) - clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } /* @@ -4318,8 +4302,6 @@ int __init cpuset_init(void) nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); - set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); - top_cpuset.relax_domain_level = -1; INIT_LIST_HEAD(&remote_children); BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); @@ -4354,6 +4336,16 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) } } +static void cpuset_migrate_tasks_workfn(struct work_struct *work) +{ + struct cpuset_remove_tasks_struct *s; + + s = container_of(work, struct cpuset_remove_tasks_struct, work); + remove_tasks_in_empty_cpuset(s->cs); + css_put(&s->cs->css); + kfree(s); +} + static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, @@ -4383,12 +4375,21 @@ hotplug_update_tasks_legacy(struct cpuset *cs, /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into - * cpuset. Should be done outside any lock. + * cpuset. Execute it asynchronously using workqueue. */ - if (is_empty) { - mutex_unlock(&cpuset_mutex); - remove_tasks_in_empty_cpuset(cs); - mutex_lock(&cpuset_mutex); + if (is_empty && cs->css.cgroup->nr_populated_csets && + css_tryget_online(&cs->css)) { + struct cpuset_remove_tasks_struct *s; + + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (WARN_ON_ONCE(!s)) { + css_put(&cs->css); + return; + } + + s->cs = cs; + INIT_WORK(&s->work, cpuset_migrate_tasks_workfn); + schedule_work(&s->work); } } @@ -4421,30 +4422,6 @@ 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 @@ -4493,13 +4470,11 @@ retry: compute_partition_effective_cpumask(cs, &new_cpus); if (remote && cpumask_empty(&new_cpus) && - partition_is_populated(cs, NULL) && - cpuset_hotplug_cpus_read_trylock()) { + partition_is_populated(cs, NULL)) { remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); remote = false; cpuset_force_rebuild(); - cpus_read_unlock(); } /* @@ -4519,18 +4494,8 @@ retry: 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(); @@ -4558,8 +4523,7 @@ unlock: } /** - * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset - * @work: unused + * cpuset_handle_hotplug - handle CPU/memory hot{,un}plug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always @@ -4573,8 +4537,10 @@ unlock: * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. + * + * CPU / memory hotplug is handled synchronously. */ -static void cpuset_hotplug_workfn(struct work_struct *work) +static void cpuset_handle_hotplug(void) { static cpumask_t new_cpus; static nodemask_t new_mems; @@ -4585,6 +4551,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; + lockdep_assert_cpus_held(); mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ @@ -4666,7 +4633,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; - rebuild_sched_domains(); + rebuild_sched_domains_cpuslocked(); } free_cpumasks(NULL, ptmp); @@ -4679,12 +4646,7 @@ void cpuset_update_active_cpus(void) * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ - schedule_work(&cpuset_hotplug_work); -} - -void cpuset_wait_for_hotplug(void) -{ - flush_work(&cpuset_hotplug_work); + cpuset_handle_hotplug(); } /* @@ -4695,7 +4657,7 @@ void cpuset_wait_for_hotplug(void) static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { - schedule_work(&cpuset_hotplug_work); + cpuset_handle_hotplug(); return NOTIFY_OK; } diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 66d1708042a7..074653f964c1 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -106,8 +106,7 @@ freezer_css_alloc(struct cgroup_subsys_state *parent_css) * @css: css being created * * We're committing to creation of @css. Mark it online and inherit - * parent's freezing state while holding both parent's and our - * freezer->lock. + * parent's freezing state while holding cpus read lock and freezer_mutex. */ static int freezer_css_online(struct cgroup_subsys_state *css) { @@ -133,7 +132,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css) * freezer_css_offline - initiate destruction of a freezer css * @css: css being destroyed * - * @css is going away. Mark it dead and decrement system_freezing_count if + * @css is going away. Mark it dead and decrement freezer_active if * it was holding one. */ static void freezer_css_offline(struct cgroup_subsys_state *css) diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index 7695e60bcb40..0e5ec7d59b4d 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -75,9 +75,7 @@ pids_css_alloc(struct cgroup_subsys_state *parent) if (!pids) return ERR_PTR(-ENOMEM); - atomic64_set(&pids->counter, 0); atomic64_set(&pids->limit, PIDS_MAX); - atomic64_set(&pids->events_limit, 0); return &pids->css; } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 07e2284bb499..fb8b49437573 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -7,6 +7,8 @@ #include <linux/btf.h> #include <linux/btf_ids.h> +#include <trace/events/cgroup.h> + static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); @@ -17,6 +19,60 @@ static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) return per_cpu_ptr(cgrp->rstat_cpu, cpu); } +/* + * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock). + * + * This makes it easier to diagnose locking issues and contention in + * production environments. The parameter @fast_path determine the + * tracepoints being added, allowing us to diagnose "flush" related + * operations without handling high-frequency fast-path "update" events. + */ +static __always_inline +unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu, + struct cgroup *cgrp, const bool fast_path) +{ + unsigned long flags; + bool contended; + + /* + * 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. + */ + contended = !raw_spin_trylock_irqsave(cpu_lock, flags); + if (contended) { + if (fast_path) + trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended); + else + trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended); + + raw_spin_lock_irqsave(cpu_lock, flags); + } + + if (fast_path) + trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended); + else + trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended); + + return flags; +} + +static __always_inline +void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu, + struct cgroup *cgrp, unsigned long flags, + const bool fast_path) +{ + if (fast_path) + trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false); + else + trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false); + + raw_spin_unlock_irqrestore(cpu_lock, flags); +} + /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup @@ -42,7 +98,7 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) return; - raw_spin_lock_irqsave(cpu_lock, flags); + flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true); /* put @cgrp and all ancestors on the corresponding updated lists */ while (true) { @@ -70,7 +126,7 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) cgrp = parent; } - raw_spin_unlock_irqrestore(cpu_lock, flags); + _cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true); } /** @@ -151,15 +207,7 @@ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) struct cgroup *head = NULL, *parent, *child; unsigned long flags; - /* - * 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); + flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) @@ -196,7 +244,7 @@ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) if (child != root) head = cgroup_rstat_push_children(head, child, cpu); unlock_ret: - raw_spin_unlock_irqrestore(cpu_lock, flags); + _cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false); return head; } @@ -222,6 +270,35 @@ __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, __bpf_hook_end(); +/* + * Helper functions for locking cgroup_rstat_lock. + * + * This makes it easier to diagnose locking issues and contention in + * production environments. The parameter @cpu_in_loop indicate lock + * was released and re-taken when collection data from the CPUs. The + * value -1 is used when obtaining the main lock else this is the CPU + * number processed last. + */ +static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop) + __acquires(&cgroup_rstat_lock) +{ + bool contended; + + contended = !spin_trylock_irq(&cgroup_rstat_lock); + if (contended) { + trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); + spin_lock_irq(&cgroup_rstat_lock); + } + trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); +} + +static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop) + __releases(&cgroup_rstat_lock) +{ + trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); + spin_unlock_irq(&cgroup_rstat_lock); +} + /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) @@ -248,10 +325,10 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { - spin_unlock_irq(&cgroup_rstat_lock); + __cgroup_rstat_unlock(cgrp, cpu); if (!cond_resched()) cpu_relax(); - spin_lock_irq(&cgroup_rstat_lock); + __cgroup_rstat_lock(cgrp, cpu); } } } @@ -273,9 +350,9 @@ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); - spin_lock_irq(&cgroup_rstat_lock); + __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); - spin_unlock_irq(&cgroup_rstat_lock); + __cgroup_rstat_unlock(cgrp, -1); } /** @@ -291,17 +368,18 @@ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); - spin_lock_irq(&cgroup_rstat_lock); + __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() + * @cgrp: cgroup used by tracepoint */ -void cgroup_rstat_flush_release(void) +void cgroup_rstat_flush_release(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) { - spin_unlock_irq(&cgroup_rstat_lock); + __cgroup_rstat_unlock(cgrp, -1); } int cgroup_rstat_init(struct cgroup *cgrp) @@ -533,7 +611,7 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq) #ifdef CONFIG_SCHED_CORE forceidle_time = cgrp->bstat.forceidle_sum; #endif - cgroup_rstat_flush_release(); + cgroup_rstat_flush_release(cgrp); } else { root_cgroup_cputime(&bstat); usage = bstat.cputime.sum_exec_runtime; diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config index 7a5bbfc024b7..8a7ce7a6b3ab 100644 --- a/kernel/configs/hardening.config +++ b/kernel/configs/hardening.config @@ -23,6 +23,10 @@ CONFIG_SLAB_FREELIST_HARDENED=y CONFIG_SHUFFLE_PAGE_ALLOCATOR=y CONFIG_RANDOM_KMALLOC_CACHES=y +# Sanity check userspace page table mappings. +CONFIG_PAGE_TABLE_CHECK=y +CONFIG_PAGE_TABLE_CHECK_ENFORCED=y + # Randomize kernel stack offset on syscall entry. CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT=y @@ -39,11 +43,12 @@ CONFIG_UBSAN=y CONFIG_UBSAN_TRAP=y CONFIG_UBSAN_BOUNDS=y # CONFIG_UBSAN_SHIFT is not set -# CONFIG_UBSAN_DIV_ZERO -# CONFIG_UBSAN_UNREACHABLE -# CONFIG_UBSAN_BOOL -# CONFIG_UBSAN_ENUM -# CONFIG_UBSAN_ALIGNMENT +# CONFIG_UBSAN_DIV_ZERO is not set +# CONFIG_UBSAN_UNREACHABLE is not set +# CONFIG_UBSAN_SIGNED_WRAP is not set +# CONFIG_UBSAN_BOOL is not set +# CONFIG_UBSAN_ENUM is not set +# CONFIG_UBSAN_ALIGNMENT is not set # Sampling-based heap out-of-bounds and use-after-free detection. CONFIG_KFENCE=y @@ -81,6 +86,10 @@ CONFIG_SECCOMP_FILTER=y # Provides some protections against SYN flooding. CONFIG_SYN_COOKIES=y +# Enable Kernel Control Flow Integrity (currently Clang only). +CONFIG_CFI_CLANG=y +# CONFIG_CFI_PERMISSIVE is not set + # Attack surface reduction: do not autoload TTY line disciplines. # CONFIG_LDISC_AUTOLOAD is not set diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 70ae70d03823..24b1e1143260 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -432,7 +432,7 @@ static __always_inline void ct_kernel_enter(bool user, int offset) { } #define CREATE_TRACE_POINTS #include <trace/events/context_tracking.h> -DEFINE_STATIC_KEY_FALSE(context_tracking_key); +DEFINE_STATIC_KEY_FALSE_RO(context_tracking_key); EXPORT_SYMBOL_GPL(context_tracking_key); static noinstr bool context_tracking_recursion_enter(void) diff --git a/kernel/cpu.c b/kernel/cpu.c index 8f6affd051f7..563877d6c28b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1208,52 +1208,6 @@ void __init cpuhp_threads_init(void) kthread_unpark(this_cpu_read(cpuhp_state.thread)); } -/* - * - * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock - * protected region. - * - * The operation is still serialized against concurrent CPU hotplug via - * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ - * serialized against other hotplug related activity like adding or - * removing of state callbacks and state instances, which invoke either the - * startup or the teardown callback of the affected state. - * - * This is required for subsystems which are unfixable vs. CPU hotplug and - * evade lock inversion problems by scheduling work which has to be - * completed _before_ cpu_up()/_cpu_down() returns. - * - * Don't even think about adding anything to this for any new code or even - * drivers. It's only purpose is to keep existing lock order trainwrecks - * working. - * - * For cpu_down() there might be valid reasons to finish cleanups which are - * not required to be done under cpu_hotplug_lock, but that's a different - * story and would be not invoked via this. - */ -static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) -{ - /* - * cpusets delegate hotplug operations to a worker to "solve" the - * lock order problems. Wait for the worker, but only if tasks are - * _not_ frozen (suspend, hibernate) as that would wait forever. - * - * The wait is required because otherwise the hotplug operation - * returns with inconsistent state, which could even be observed in - * user space when a new CPU is brought up. The CPU plug uevent - * would be delivered and user space reacting on it would fail to - * move tasks to the newly plugged CPU up to the point where the - * work has finished because up to that point the newly plugged CPU - * is not assignable in cpusets/cgroups. On unplug that's not - * necessarily a visible issue, but it is still inconsistent state, - * which is the real problem which needs to be "fixed". This can't - * prevent the transient state between scheduling the work and - * returning from waiting for it. - */ - if (!tasks_frozen) - cpuset_wait_for_hotplug(); -} - #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) @@ -1494,7 +1448,6 @@ out: */ lockup_detector_cleanup(); arch_smt_update(); - cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -1728,7 +1681,6 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) out: cpus_write_unlock(); arch_smt_update(); - cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -3196,6 +3148,7 @@ void __init boot_cpu_hotplug_init(void) this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } +#ifdef CONFIG_CPU_MITIGATIONS /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. @@ -3206,8 +3159,7 @@ enum cpu_mitigations { CPU_MITIGATIONS_AUTO_NOSMT, }; -static enum cpu_mitigations cpu_mitigations __ro_after_init = - CPU_MITIGATIONS_AUTO; +static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { @@ -3223,7 +3175,6 @@ static int __init mitigations_parse_cmdline(char *arg) return 0; } -early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) @@ -3238,3 +3189,11 @@ bool cpu_mitigations_auto_nosmt(void) return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); +#else +static int __init mitigations_parse_cmdline(char *arg) +{ + pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); + return 0; +} +#endif +early_param("mitigations", mitigations_parse_cmdline); diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 78b5dc7cee3a..63cf89393c6e 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -4,6 +4,8 @@ * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/buildid.h> #include <linux/init.h> #include <linux/utsname.h> @@ -493,10 +495,10 @@ static DEFINE_MUTEX(__crash_hotplug_lock); /* * This routine utilized when the crash_hotplug sysfs node is read. - * It reflects the kernel's ability/permission to update the crash - * elfcorehdr directly. + * It reflects the kernel's ability/permission to update the kdump + * image directly. */ -int crash_check_update_elfcorehdr(void) +int crash_check_hotplug_support(void) { int rc = 0; @@ -508,10 +510,7 @@ int crash_check_update_elfcorehdr(void) return 0; } if (kexec_crash_image) { - if (kexec_crash_image->file_mode) - rc = 1; - else - rc = kexec_crash_image->update_elfcorehdr; + rc = kexec_crash_image->hotplug_support; } /* Release lock now that update complete */ kexec_unlock(); @@ -534,7 +533,7 @@ int crash_check_update_elfcorehdr(void) * list of segments it checks (since the elfcorehdr changes and thus * would require an update to purgatory itself to update the digest). */ -static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) +static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, void *arg) { struct kimage *image; @@ -552,8 +551,8 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) image = kexec_crash_image; - /* Check that updating elfcorehdr is permitted */ - if (!(image->file_mode || image->update_elfcorehdr)) + /* Check that kexec segments update is permitted */ + if (!image->hotplug_support) goto out; if (hp_action == KEXEC_CRASH_HP_ADD_CPU || @@ -596,7 +595,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) image->hp_action = hp_action; /* Now invoke arch-specific update handler */ - arch_crash_handle_hotplug_event(image); + arch_crash_handle_hotplug_event(image, arg); /* No longer handling a hotplug event */ image->hp_action = KEXEC_CRASH_HP_NONE; @@ -612,17 +611,17 @@ out: crash_hotplug_unlock(); } -static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v) +static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *arg) { switch (val) { case MEM_ONLINE: crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY, - KEXEC_CRASH_HP_INVALID_CPU); + KEXEC_CRASH_HP_INVALID_CPU, arg); break; case MEM_OFFLINE: crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY, - KEXEC_CRASH_HP_INVALID_CPU); + KEXEC_CRASH_HP_INVALID_CPU, arg); break; } return NOTIFY_OK; @@ -635,13 +634,13 @@ static struct notifier_block crash_memhp_nb = { static int crash_cpuhp_online(unsigned int cpu) { - crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu); + crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu, NULL); return 0; } static int crash_cpuhp_offline(unsigned int cpu) { - crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu); + crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu, NULL); return 0; } diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index bbb6c3cb00e4..5b2722a93a48 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -109,7 +109,7 @@ static int __init parse_crashkernel_mem(char *cmdline, size = memparse(cur, &tmp); if (cur == tmp) { - pr_warn("Memory value expected\n"); + pr_warn("crashkernel: Memory value expected\n"); return -EINVAL; } cur = tmp; @@ -132,7 +132,7 @@ static int __init parse_crashkernel_mem(char *cmdline, cur++; *crash_base = memparse(cur, &tmp); if (cur == tmp) { - pr_warn("Memory value expected after '@'\n"); + pr_warn("crahskernel: Memory value expected after '@'\n"); return -EINVAL; } } @@ -366,8 +366,10 @@ static int __init reserve_crashkernel_low(unsigned long long low_size) crashk_low_res.start = low_base; crashk_low_res.end = low_base + low_size - 1; +#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY insert_resource(&iomem_resource, &crashk_low_res); #endif +#endif return 0; } @@ -448,8 +450,12 @@ retry: crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; +#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + insert_resource(&iomem_resource, &crashk_res); +#endif } +#ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY static __init int insert_crashkernel_resources(void) { if (crashk_res.start < crashk_res.end) @@ -462,3 +468,4 @@ static __init int insert_crashkernel_resources(void) } early_initcall(insert_crashkernel_resources); #endif +#endif diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 9443bc63c5a2..3131334d7a81 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -184,6 +184,33 @@ char kdb_getchar(void) unreachable(); } +/** + * kdb_position_cursor() - Place cursor in the correct horizontal position + * @prompt: Nil-terminated string containing the prompt string + * @buffer: Nil-terminated string containing the entire command line + * @cp: Cursor position, pointer the character in buffer where the cursor + * should be positioned. + * + * The cursor is positioned by sending a carriage-return and then printing + * the content of the line until we reach the correct cursor position. + * + * There is some additional fine detail here. + * + * Firstly, even though kdb_printf() will correctly format zero-width fields + * we want the second call to kdb_printf() to be conditional. That keeps things + * a little cleaner when LOGGING=1. + * + * Secondly, we can't combine everything into one call to kdb_printf() since + * that renders into a fixed length buffer and the combined print could result + * in unwanted truncation. + */ +static void kdb_position_cursor(char *prompt, char *buffer, char *cp) +{ + kdb_printf("\r%s", kdb_prompt_str); + if (cp > buffer) + kdb_printf("%.*s", (int)(cp - buffer), buffer); +} + /* * kdb_read * @@ -220,8 +247,7 @@ static char *kdb_read(char *buffer, size_t bufsize) int count; int i; int diag, dtab_count; - int key, buf_size, ret; - + int key, ret; diag = kdbgetintenv("DTABCOUNT", &dtab_count); if (diag) @@ -243,18 +269,11 @@ poll_again: switch (key) { case 8: /* backspace */ if (cp > buffer) { - if (cp < lastchar) { - memcpy(tmpbuffer, cp, lastchar - cp); - memcpy(cp-1, tmpbuffer, lastchar - cp); - } - *(--lastchar) = '\0'; - --cp; - kdb_printf("\b%s \r", cp); - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + memmove(cp-1, cp, lastchar - cp + 1); + lastchar--; + cp--; + kdb_printf("\b%s ", cp); + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 10: /* linefeed */ @@ -269,22 +288,16 @@ poll_again: return buffer; case 4: /* Del */ if (cp < lastchar) { - memcpy(tmpbuffer, cp+1, lastchar - cp - 1); - memcpy(cp, tmpbuffer, lastchar - cp - 1); - *(--lastchar) = '\0'; - kdb_printf("%s \r", cp); - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + memmove(cp, cp+1, lastchar - cp); + lastchar--; + kdb_printf("%s ", cp); + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 1: /* Home */ if (cp > buffer) { - kdb_printf("\r"); - kdb_printf(kdb_prompt_str); cp = buffer; + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 5: /* End */ @@ -300,11 +313,10 @@ poll_again: } break; case 14: /* Down */ - memset(tmpbuffer, ' ', - strlen(kdb_prompt_str) + (lastchar-buffer)); - *(tmpbuffer+strlen(kdb_prompt_str) + - (lastchar-buffer)) = '\0'; - kdb_printf("\r%s\r", tmpbuffer); + case 16: /* Up */ + kdb_printf("\r%*c\r", + (int)(strlen(kdb_prompt_str) + (lastchar - buffer)), + ' '); *lastchar = (char)key; *(lastchar+1) = '\0'; return lastchar; @@ -314,33 +326,19 @@ poll_again: ++cp; } break; - case 16: /* Up */ - memset(tmpbuffer, ' ', - strlen(kdb_prompt_str) + (lastchar-buffer)); - *(tmpbuffer+strlen(kdb_prompt_str) + - (lastchar-buffer)) = '\0'; - kdb_printf("\r%s\r", tmpbuffer); - *lastchar = (char)key; - *(lastchar+1) = '\0'; - return lastchar; case 9: /* Tab */ if (tab < 2) ++tab; - p_tmp = buffer; - while (*p_tmp == ' ') - p_tmp++; - if (p_tmp > cp) - break; - memcpy(tmpbuffer, p_tmp, cp-p_tmp); - *(tmpbuffer + (cp-p_tmp)) = '\0'; - p_tmp = strrchr(tmpbuffer, ' '); - if (p_tmp) - ++p_tmp; - else - p_tmp = tmpbuffer; - len = strlen(p_tmp); - buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer); - count = kallsyms_symbol_complete(p_tmp, buf_size); + + tmp = *cp; + *cp = '\0'; + p_tmp = strrchr(buffer, ' '); + p_tmp = (p_tmp ? p_tmp + 1 : buffer); + strscpy(tmpbuffer, p_tmp, sizeof(tmpbuffer)); + *cp = tmp; + + len = strlen(tmpbuffer); + count = kallsyms_symbol_complete(tmpbuffer, sizeof(tmpbuffer)); if (tab == 2 && count > 0) { kdb_printf("\n%d symbols are found.", count); if (count > dtab_count) { @@ -352,46 +350,51 @@ poll_again: } kdb_printf("\n"); for (i = 0; i < count; i++) { - ret = kallsyms_symbol_next(p_tmp, i, buf_size); + ret = kallsyms_symbol_next(tmpbuffer, i, sizeof(tmpbuffer)); if (WARN_ON(!ret)) break; if (ret != -E2BIG) - kdb_printf("%s ", p_tmp); + kdb_printf("%s ", tmpbuffer); else - kdb_printf("%s... ", p_tmp); - *(p_tmp + len) = '\0'; + kdb_printf("%s... ", tmpbuffer); + tmpbuffer[len] = '\0'; } if (i >= dtab_count) kdb_printf("..."); kdb_printf("\n"); kdb_printf(kdb_prompt_str); kdb_printf("%s", buffer); + if (cp != lastchar) + kdb_position_cursor(kdb_prompt_str, buffer, cp); } else if (tab != 2 && count > 0) { - len_tmp = strlen(p_tmp); - strncpy(p_tmp+len_tmp, cp, lastchar-cp+1); - len_tmp = strlen(p_tmp); - strncpy(cp, p_tmp+len, len_tmp-len + 1); - len = len_tmp - len; - kdb_printf("%s", cp); - cp += len; - lastchar += len; + /* How many new characters do we want from tmpbuffer? */ + len_tmp = strlen(tmpbuffer) - len; + if (lastchar + len_tmp >= bufend) + len_tmp = bufend - lastchar; + + if (len_tmp) { + /* + 1 ensures the '\0' is memmove'd */ + memmove(cp+len_tmp, cp, (lastchar-cp) + 1); + memcpy(cp, tmpbuffer+len, len_tmp); + kdb_printf("%s", cp); + cp += len_tmp; + lastchar += len_tmp; + if (cp != lastchar) + kdb_position_cursor(kdb_prompt_str, + buffer, cp); + } } kdb_nextline = 1; /* reset output line number */ break; default: if (key >= 32 && lastchar < bufend) { if (cp < lastchar) { - memcpy(tmpbuffer, cp, lastchar - cp); - memcpy(cp+1, tmpbuffer, lastchar - cp); - *++lastchar = '\0'; + memmove(cp+1, cp, lastchar - cp + 1); + lastchar++; *cp = key; - kdb_printf("%s\r", cp); + kdb_printf("%s", cp); ++cp; - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + kdb_position_cursor(kdb_prompt_str, buffer, cp); } else { *++lastchar = '\0'; *cp++ = key; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index d05066cb40b2..664bae55f2c9 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2517,7 +2517,7 @@ static int kdb_summary(int argc, const char **argv) if (val.uptime > (24*60*60)) { int days = val.uptime / (24*60*60); val.uptime %= (24*60*60); - kdb_printf("%d day%s ", days, days == 1 ? "" : "s"); + kdb_printf("%d day%s ", days, str_plural(days)); } kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60); diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 6f0c358e73d8..e039b0f99a0b 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -74,7 +74,6 @@ static struct ctl_table kern_delayacct_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - { } }; static __init int kernel_delayacct_sysctls_init(void) diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index d62f5957f36b..c06e56be0ca1 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -107,6 +107,11 @@ config DMA_BOUNCE_UNALIGNED_KMALLOC bool depends on SWIOTLB +config DMA_NEED_SYNC + def_bool ARCH_HAS_SYNC_DMA_FOR_DEVICE || ARCH_HAS_SYNC_DMA_FOR_CPU || \ + ARCH_HAS_SYNC_DMA_FOR_CPU_ALL || DMA_API_DEBUG || DMA_OPS || \ + SWIOTLB + config DMA_RESTRICTED_POOL bool "DMA Restricted Pool" depends on OF && OF_RESERVED_MEM && SWIOTLB diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 58db8fd70471..81de84318ccc 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -329,7 +329,8 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, } EXPORT_SYMBOL(dma_unmap_resource); -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, +#ifdef CONFIG_DMA_NEED_SYNC +void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -341,9 +342,9 @@ void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, ops->sync_single_for_cpu(dev, addr, size, dir); debug_dma_sync_single_for_cpu(dev, addr, size, dir); } -EXPORT_SYMBOL(dma_sync_single_for_cpu); +EXPORT_SYMBOL(__dma_sync_single_for_cpu); -void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, +void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -355,9 +356,9 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, ops->sync_single_for_device(dev, addr, size, dir); debug_dma_sync_single_for_device(dev, addr, size, dir); } -EXPORT_SYMBOL(dma_sync_single_for_device); +EXPORT_SYMBOL(__dma_sync_single_for_device); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -369,9 +370,9 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, ops->sync_sg_for_cpu(dev, sg, nelems, dir); debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); } -EXPORT_SYMBOL(dma_sync_sg_for_cpu); +EXPORT_SYMBOL(__dma_sync_sg_for_cpu); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -383,7 +384,47 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, ops->sync_sg_for_device(dev, sg, nelems, dir); debug_dma_sync_sg_for_device(dev, sg, nelems, dir); } -EXPORT_SYMBOL(dma_sync_sg_for_device); +EXPORT_SYMBOL(__dma_sync_sg_for_device); + +bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_map_direct(dev, ops)) + /* + * dma_skip_sync could've been reset on first SWIOTLB buffer + * mapping, but @dma_addr is not necessary an SWIOTLB buffer. + * In this case, fall back to more granular check. + */ + return dma_direct_need_sync(dev, dma_addr); + return true; +} +EXPORT_SYMBOL_GPL(__dma_need_sync); + +static void dma_setup_need_sync(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_map_direct(dev, ops) || (ops->flags & DMA_F_CAN_SKIP_SYNC)) + /* + * dma_skip_sync will be reset to %false on first SWIOTLB buffer + * mapping, if any. During the device initialization, it's + * enough to check only for the DMA coherence. + */ + dev->dma_skip_sync = dev_is_dma_coherent(dev); + else if (!ops->sync_single_for_device && !ops->sync_single_for_cpu && + !ops->sync_sg_for_device && !ops->sync_sg_for_cpu) + /* + * Synchronization is not possible when none of DMA sync ops + * is set. + */ + dev->dma_skip_sync = true; + else + dev->dma_skip_sync = false; +} +#else /* !CONFIG_DMA_NEED_SYNC */ +static inline void dma_setup_need_sync(struct device *dev) { } +#endif /* !CONFIG_DMA_NEED_SYNC */ /* * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems @@ -570,9 +611,9 @@ static struct page *__dma_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_alloc_direct(dev, ops)) return dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp); - if (!ops->alloc_pages) + if (!ops->alloc_pages_op) return NULL; - return ops->alloc_pages(dev, size, dma_handle, dir, gfp); + return ops->alloc_pages_op(dev, size, dma_handle, dir, gfp); } struct page *dma_alloc_pages(struct device *dev, size_t size, @@ -773,6 +814,8 @@ int dma_set_mask(struct device *dev, u64 mask) arch_dma_set_mask(dev, mask); *dev->dma_mask = mask; + dma_setup_need_sync(dev); + return 0; } EXPORT_SYMBOL(dma_set_mask); @@ -841,16 +884,6 @@ size_t dma_opt_mapping_size(struct device *dev) } EXPORT_SYMBOL_GPL(dma_opt_mapping_size); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - if (dma_map_direct(dev, ops)) - return dma_direct_need_sync(dev, dma_addr); - return ops->sync_single_for_cpu || ops->sync_single_for_device; -} -EXPORT_SYMBOL_GPL(dma_need_sync); - unsigned long dma_get_merge_boundary(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 86fe172b5958..fe1ccb53596f 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -69,11 +69,14 @@ * @alloc_size: Size of the allocated buffer. * @list: The free list describing the number of free entries available * from each index. + * @pad_slots: Number of preceding padding slots. Valid only in the first + * allocated non-padding slot. */ struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; - unsigned int list; + unsigned short list; + unsigned short pad_slots; }; static bool swiotlb_force_bounce; @@ -287,6 +290,7 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start, mem->nslabs - i); mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; + mem->slots[i].pad_slots = 0; } memset(vaddr, 0, bytes); @@ -821,12 +825,30 @@ void swiotlb_dev_init(struct device *dev) #endif } -/* - * Return the offset into a iotlb slot required to keep the device happy. +/** + * swiotlb_align_offset() - Get required offset into an IO TLB allocation. + * @dev: Owning device. + * @align_mask: Allocation alignment mask. + * @addr: DMA address. + * + * Return the minimum offset from the start of an IO TLB allocation which is + * required for a given buffer address and allocation alignment to keep the + * device happy. + * + * First, the address bits covered by min_align_mask must be identical in the + * original address and the bounce buffer address. High bits are preserved by + * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra + * padding bytes before the bounce buffer. + * + * Second, @align_mask specifies which bits of the first allocated slot must + * be zero. This may require allocating additional padding slots, and then the + * offset (in bytes) from the first such padding slot is returned. */ -static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) +static unsigned int swiotlb_align_offset(struct device *dev, + unsigned int align_mask, u64 addr) { - return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); + return addr & dma_get_min_align_mask(dev) & + (align_mask | (IO_TLB_SIZE - 1)); } /* @@ -841,27 +863,23 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; - unsigned int tlb_offset, orig_addr_offset; + int tlb_offset; if (orig_addr == INVALID_PHYS_ADDR) return; - tlb_offset = tlb_addr & (IO_TLB_SIZE - 1); - orig_addr_offset = swiotlb_align_offset(dev, orig_addr); - if (tlb_offset < orig_addr_offset) { - dev_WARN_ONCE(dev, 1, - "Access before mapping start detected. orig offset %u, requested offset %u.\n", - orig_addr_offset, tlb_offset); - return; - } - - tlb_offset -= orig_addr_offset; - if (tlb_offset > alloc_size) { - dev_WARN_ONCE(dev, 1, - "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n", - alloc_size, size, tlb_offset); - return; - } + /* + * It's valid for tlb_offset to be negative. This can happen when the + * "offset" returned by swiotlb_align_offset() is non-zero, and the + * tlb_addr is pointing within the first "offset" bytes of the second + * or subsequent slots of the allocated swiotlb area. While it's not + * valid for tlb_addr to be pointing within the first "offset" bytes + * of the first slot, there's no way to check for such an error since + * this function can't distinguish the first slot from the second and + * subsequent slots. + */ + tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) - + swiotlb_align_offset(dev, 0, orig_addr); orig_addr += tlb_offset; alloc_size -= tlb_offset; @@ -1005,7 +1023,7 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; - unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr); unsigned int index, slots_checked, count = 0, i; unsigned long flags; unsigned int slot_base; @@ -1322,17 +1340,43 @@ static unsigned long mem_used(struct io_tlb_mem *mem) #endif /* CONFIG_DEBUG_FS */ +/** + * swiotlb_tbl_map_single() - bounce buffer map a single contiguous physical area + * @dev: Device which maps the buffer. + * @orig_addr: Original (non-bounced) physical IO buffer address + * @mapping_size: Requested size of the actual bounce buffer, excluding + * any pre- or post-padding for alignment + * @alloc_align_mask: Required start and end alignment of the allocated buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Find and allocate a suitable sequence of IO TLB slots for the request. + * The allocated space starts at an alignment specified by alloc_align_mask, + * and the size of the allocated space is rounded up so that the total amount + * of allocated space is a multiple of (alloc_align_mask + 1). If + * alloc_align_mask is zero, the allocated space may be at any alignment and + * the size is not rounded up. + * + * The returned address is within the allocated space and matches the bits + * of orig_addr that are specified in the DMA min_align_mask for the device. As + * such, this returned address may be offset from the beginning of the allocated + * space. The bounce buffer space starting at the returned address for + * mapping_size bytes is initialized to the contents of the original IO buffer + * area. Any pre-padding (due to an offset) and any post-padding (due to + * rounding-up the size) is not initialized. + */ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, - size_t mapping_size, size_t alloc_size, - unsigned int alloc_align_mask, enum dma_data_direction dir, - unsigned long attrs) + size_t mapping_size, unsigned int alloc_align_mask, + enum dma_data_direction dir, unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; - unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned int offset; struct io_tlb_pool *pool; unsigned int i; + size_t size; int index; phys_addr_t tlb_addr; + unsigned short pad_slots; if (!mem || !mem->nslabs) { dev_warn_ratelimited(dev, @@ -1343,28 +1387,43 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); - if (mapping_size > alloc_size) { - dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)", - mapping_size, alloc_size); - return (phys_addr_t)DMA_MAPPING_ERROR; - } + /* + * The default swiotlb memory pool is allocated with PAGE_SIZE + * alignment. If a mapping is requested with larger alignment, + * the mapping may be unable to use the initial slot(s) in all + * sets of IO_TLB_SEGSIZE slots. In such case, a mapping request + * of or near the maximum mapping size would always fail. + */ + dev_WARN_ONCE(dev, alloc_align_mask > ~PAGE_MASK, + "Alloc alignment may prevent fulfilling requests with max mapping_size\n"); - index = swiotlb_find_slots(dev, orig_addr, - alloc_size + offset, alloc_align_mask, &pool); + offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr); + size = ALIGN(mapping_size + offset, alloc_align_mask + 1); + index = swiotlb_find_slots(dev, orig_addr, size, alloc_align_mask, &pool); if (index == -1) { if (!(attrs & DMA_ATTR_NO_WARN)) dev_warn_ratelimited(dev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", - alloc_size, mem->nslabs, mem_used(mem)); + size, mem->nslabs, mem_used(mem)); return (phys_addr_t)DMA_MAPPING_ERROR; } /* + * If dma_skip_sync was set, reset it on first SWIOTLB buffer + * mapping to always sync SWIOTLB buffers. + */ + dma_reset_need_sync(dev); + + /* * Save away the mapping from the original address to the DMA address. * This is needed when we sync the memory. Then we sync the buffer if * needed. */ - for (i = 0; i < nr_slots(alloc_size + offset); i++) + pad_slots = offset >> IO_TLB_SHIFT; + offset &= (IO_TLB_SIZE - 1); + index += pad_slots; + pool->slots[index].pad_slots = pad_slots; + for (i = 0; i < (nr_slots(size) - pad_slots); i++) pool->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(pool->start, index) + offset; /* @@ -1384,13 +1443,17 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) { struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr); unsigned long flags; - unsigned int offset = swiotlb_align_offset(dev, tlb_addr); - int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; - int nslots = nr_slots(mem->slots[index].alloc_size + offset); - int aindex = index / mem->area_nslabs; - struct io_tlb_area *area = &mem->areas[aindex]; + unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr); + int index, nslots, aindex; + struct io_tlb_area *area; int count, i; + index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; + index -= mem->slots[index].pad_slots; + nslots = nr_slots(mem->slots[index].alloc_size + offset); + aindex = index / mem->area_nslabs; + area = &mem->areas[aindex]; + /* * Return the buffer to the free list by setting the corresponding * entries to indicate the number of contiguous entries available. @@ -1413,6 +1476,7 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) mem->slots[i].list = ++count; mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; + mem->slots[i].pad_slots = 0; } /* @@ -1514,8 +1578,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size); - swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir, - attrs); + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, 0, dir, attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; @@ -1647,9 +1710,6 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get, static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, const char *dirname) { - atomic_long_set(&mem->total_used, 0); - atomic_long_set(&mem->used_hiwater, 0); - mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs); if (!mem->nslabs) return; @@ -1660,7 +1720,6 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem, &fops_io_tlb_hiwater); #ifdef CONFIG_SWIOTLB_DYNAMIC - atomic_long_set(&mem->transient_nslabs, 0); debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs, mem, &fops_io_tlb_transient_used); #endif @@ -1773,6 +1832,7 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, mem->for_alloc = true; #ifdef CONFIG_SWIOTLB_DYNAMIC spin_lock_init(&mem->lock); + INIT_LIST_HEAD_RCU(&mem->pools); #endif add_mem_pool(mem, pool); diff --git a/kernel/events/core.c b/kernel/events/core.c index 724e6d7e128f..f0128c5ff278 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2302,8 +2302,10 @@ event_sched_out(struct perf_event *event, struct perf_event_context *ctx) if (!is_software_event(event)) cpc->active_oncpu--; - if (event->attr.freq && event->attr.sample_freq) + if (event->attr.freq && event->attr.sample_freq) { ctx->nr_freq--; + epc->nr_freq--; + } if (event->attr.exclusive || !cpc->active_oncpu) cpc->exclusive = 0; @@ -2558,9 +2560,10 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx) if (!is_software_event(event)) cpc->active_oncpu++; - if (event->attr.freq && event->attr.sample_freq) + if (event->attr.freq && event->attr.sample_freq) { ctx->nr_freq++; - + epc->nr_freq++; + } if (event->attr.exclusive) cpc->exclusive = 1; @@ -4123,30 +4126,14 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bo } } -/* - * combine freq adjustment with unthrottling to avoid two passes over the - * events. At the same time, make sure, having freq events does not change - * the rate of unthrottling as that would introduce bias. - */ -static void -perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle) +static void perf_adjust_freq_unthr_events(struct list_head *event_list) { struct perf_event *event; struct hw_perf_event *hwc; u64 now, period = TICK_NSEC; s64 delta; - /* - * only need to iterate over all events iff: - * - context have events in frequency mode (needs freq adjust) - * - there are events to unthrottle on this cpu - */ - if (!(ctx->nr_freq || unthrottle)) - return; - - raw_spin_lock(&ctx->lock); - - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + list_for_each_entry(event, event_list, active_list) { if (event->state != PERF_EVENT_STATE_ACTIVE) continue; @@ -4154,18 +4141,17 @@ perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle) if (!event_filter_match(event)) continue; - perf_pmu_disable(event->pmu); - hwc = &event->hw; if (hwc->interrupts == MAX_INTERRUPTS) { hwc->interrupts = 0; perf_log_throttle(event, 1); - event->pmu->start(event, 0); + if (!event->attr.freq || !event->attr.sample_freq) + event->pmu->start(event, 0); } if (!event->attr.freq || !event->attr.sample_freq) - goto next; + continue; /* * stop the event and update event->count @@ -4187,8 +4173,41 @@ perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle) perf_adjust_period(event, period, delta, false); event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0); - next: - perf_pmu_enable(event->pmu); + } +} + +/* + * combine freq adjustment with unthrottling to avoid two passes over the + * events. At the same time, make sure, having freq events does not change + * the rate of unthrottling as that would introduce bias. + */ +static void +perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle) +{ + struct perf_event_pmu_context *pmu_ctx; + + /* + * only need to iterate over all events iff: + * - context have events in frequency mode (needs freq adjust) + * - there are events to unthrottle on this cpu + */ + if (!(ctx->nr_freq || unthrottle)) + return; + + raw_spin_lock(&ctx->lock); + + list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { + if (!(pmu_ctx->nr_freq || unthrottle)) + continue; + if (!perf_pmu_ctx_is_active(pmu_ctx)) + continue; + if (pmu_ctx->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) + continue; + + perf_pmu_disable(pmu_ctx->pmu); + perf_adjust_freq_unthr_events(&pmu_ctx->pinned_active); + perf_adjust_freq_unthr_events(&pmu_ctx->flexible_active); + perf_pmu_enable(pmu_ctx->pmu); } raw_spin_unlock(&ctx->lock); @@ -6684,14 +6703,6 @@ static const struct file_operations perf_fops = { * to user-space before waking everybody up. */ -static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) -{ - /* only the parent has fasync state */ - if (event->parent) - event = event->parent; - return &event->fasync; -} - void perf_event_wakeup(struct perf_event *event) { ring_buffer_wakeup(event); @@ -7539,7 +7550,7 @@ static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr) { u64 size = 0; -#ifdef CONFIG_HAVE_FAST_GUP +#ifdef CONFIG_HAVE_GUP_FAST pgd_t *pgdp, pgd; p4d_t *p4dp, p4d; pud_t *pudp, pud; @@ -7587,7 +7598,7 @@ again: if (pte_present(pte)) size = pte_leaf_size(pte); pte_unmap(ptep); -#endif /* CONFIG_HAVE_FAST_GUP */ +#endif /* CONFIG_HAVE_GUP_FAST */ return size; } @@ -9544,6 +9555,100 @@ static inline bool sample_is_allowed(struct perf_event *event, struct pt_regs *r return true; } +#ifdef CONFIG_BPF_SYSCALL +static int bpf_overflow_handler(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct bpf_perf_event_data_kern ctx = { + .data = data, + .event = event, + }; + struct bpf_prog *prog; + int ret = 0; + + ctx.regs = perf_arch_bpf_user_pt_regs(regs); + if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) + goto out; + rcu_read_lock(); + prog = READ_ONCE(event->prog); + if (prog) { + perf_prepare_sample(data, event, regs); + ret = bpf_prog_run(prog, &ctx); + } + rcu_read_unlock(); +out: + __this_cpu_dec(bpf_prog_active); + + return ret; +} + +static inline int perf_event_set_bpf_handler(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie) +{ + if (event->overflow_handler_context) + /* hw breakpoint or kernel counter */ + return -EINVAL; + + if (event->prog) + return -EEXIST; + + if (prog->type != BPF_PROG_TYPE_PERF_EVENT) + return -EINVAL; + + if (event->attr.precise_ip && + prog->call_get_stack && + (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) || + event->attr.exclude_callchain_kernel || + event->attr.exclude_callchain_user)) { + /* + * On perf_event with precise_ip, calling bpf_get_stack() + * may trigger unwinder warnings and occasional crashes. + * bpf_get_[stack|stackid] works around this issue by using + * callchain attached to perf_sample_data. If the + * perf_event does not full (kernel and user) callchain + * attached to perf_sample_data, do not allow attaching BPF + * program that calls bpf_get_[stack|stackid]. + */ + return -EPROTO; + } + + event->prog = prog; + event->bpf_cookie = bpf_cookie; + return 0; +} + +static inline void perf_event_free_bpf_handler(struct perf_event *event) +{ + struct bpf_prog *prog = event->prog; + + if (!prog) + return; + + event->prog = NULL; + bpf_prog_put(prog); +} +#else +static inline int bpf_overflow_handler(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + return 1; +} + +static inline int perf_event_set_bpf_handler(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie) +{ + return -EOPNOTSUPP; +} + +static inline void perf_event_free_bpf_handler(struct perf_event *event) +{ +} +#endif + /* * Generic event overflow handling, sampling. */ @@ -9564,6 +9669,9 @@ static int __perf_event_overflow(struct perf_event *event, ret = __perf_event_account_interrupt(event, throttle); + if (event->prog && !bpf_overflow_handler(event, data, regs)) + return ret; + /* * XXX event_limit might not quite work as expected on inherited * events @@ -10422,97 +10530,6 @@ static void perf_event_free_filter(struct perf_event *event) ftrace_profile_free_filter(event); } -#ifdef CONFIG_BPF_SYSCALL -static void bpf_overflow_handler(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) -{ - struct bpf_perf_event_data_kern ctx = { - .data = data, - .event = event, - }; - struct bpf_prog *prog; - int ret = 0; - - ctx.regs = perf_arch_bpf_user_pt_regs(regs); - if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) - goto out; - rcu_read_lock(); - prog = READ_ONCE(event->prog); - if (prog) { - perf_prepare_sample(data, event, regs); - ret = bpf_prog_run(prog, &ctx); - } - rcu_read_unlock(); -out: - __this_cpu_dec(bpf_prog_active); - if (!ret) - return; - - event->orig_overflow_handler(event, data, regs); -} - -static int perf_event_set_bpf_handler(struct perf_event *event, - struct bpf_prog *prog, - u64 bpf_cookie) -{ - if (event->overflow_handler_context) - /* hw breakpoint or kernel counter */ - return -EINVAL; - - if (event->prog) - return -EEXIST; - - if (prog->type != BPF_PROG_TYPE_PERF_EVENT) - return -EINVAL; - - if (event->attr.precise_ip && - prog->call_get_stack && - (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) || - event->attr.exclude_callchain_kernel || - event->attr.exclude_callchain_user)) { - /* - * On perf_event with precise_ip, calling bpf_get_stack() - * may trigger unwinder warnings and occasional crashes. - * bpf_get_[stack|stackid] works around this issue by using - * callchain attached to perf_sample_data. If the - * perf_event does not full (kernel and user) callchain - * attached to perf_sample_data, do not allow attaching BPF - * program that calls bpf_get_[stack|stackid]. - */ - return -EPROTO; - } - - event->prog = prog; - event->bpf_cookie = bpf_cookie; - event->orig_overflow_handler = READ_ONCE(event->overflow_handler); - WRITE_ONCE(event->overflow_handler, bpf_overflow_handler); - return 0; -} - -static void perf_event_free_bpf_handler(struct perf_event *event) -{ - struct bpf_prog *prog = event->prog; - - if (!prog) - return; - - WRITE_ONCE(event->overflow_handler, event->orig_overflow_handler); - event->prog = NULL; - bpf_prog_put(prog); -} -#else -static int perf_event_set_bpf_handler(struct perf_event *event, - struct bpf_prog *prog, - u64 bpf_cookie) -{ - return -EOPNOTSUPP; -} -static void perf_event_free_bpf_handler(struct perf_event *event) -{ -} -#endif - /* * returns true if the event is a tracepoint, or a kprobe/upprobe created * with perf_event_open() @@ -11971,13 +11988,11 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, overflow_handler = parent_event->overflow_handler; context = parent_event->overflow_handler_context; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING) - if (overflow_handler == bpf_overflow_handler) { + if (parent_event->prog) { struct bpf_prog *prog = parent_event->prog; bpf_prog_inc(prog); event->prog = prog; - event->orig_overflow_handler = - parent_event->orig_overflow_handler; } #endif } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 60ed43d1c29e..4013408ce012 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -22,6 +22,10 @@ static void perf_output_wakeup(struct perf_output_handle *handle) atomic_set(&handle->rb->poll, EPOLLIN); handle->event->pending_wakeup = 1; + + if (*perf_event_fasync(handle->event) && !handle->event->pending_kill) + handle->event->pending_kill = POLL_IN; + irq_work_queue(&handle->event->pending_irq); } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e4834d23e1d1..2c83ba776fc7 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -18,7 +18,7 @@ #include <linux/sched/coredump.h> #include <linux/export.h> #include <linux/rmap.h> /* anon_vma_prepare */ -#include <linux/mmu_notifier.h> /* set_pte_at_notify */ +#include <linux/mmu_notifier.h> #include <linux/swap.h> /* folio_free_swap */ #include <linux/ptrace.h> /* user_enable_single_step */ #include <linux/kdebug.h> /* notifier mechanism */ @@ -39,7 +39,7 @@ static struct rb_root uprobes_tree = RB_ROOT; */ #define no_uprobe_events() RB_EMPTY_ROOT(&uprobes_tree) -static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ +static DEFINE_RWLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 /* serialize uprobe->pending_list */ @@ -195,8 +195,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, flush_cache_page(vma, addr, pte_pfn(ptep_get(pvmw.pte))); ptep_clear_flush(vma, addr, pvmw.pte); if (new_page) - set_pte_at_notify(mm, addr, pvmw.pte, - mk_pte(new_page, vma->vm_page_prot)); + set_pte_at(mm, addr, pvmw.pte, + mk_pte(new_page, vma->vm_page_prot)); folio_remove_rmap_pte(old_folio, old_page, vma); if (!folio_mapped(old_folio)) @@ -669,9 +669,9 @@ static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) { struct uprobe *uprobe; - spin_lock(&uprobes_treelock); + read_lock(&uprobes_treelock); uprobe = __find_uprobe(inode, offset); - spin_unlock(&uprobes_treelock); + read_unlock(&uprobes_treelock); return uprobe; } @@ -701,9 +701,9 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe) { struct uprobe *u; - spin_lock(&uprobes_treelock); + write_lock(&uprobes_treelock); u = __insert_uprobe(uprobe); - spin_unlock(&uprobes_treelock); + write_unlock(&uprobes_treelock); return u; } @@ -935,9 +935,9 @@ static void delete_uprobe(struct uprobe *uprobe) if (WARN_ON(!uprobe_is_active(uprobe))) return; - spin_lock(&uprobes_treelock); + write_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); - spin_unlock(&uprobes_treelock); + write_unlock(&uprobes_treelock); RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ put_uprobe(uprobe); } @@ -1298,7 +1298,7 @@ static void build_probe_list(struct inode *inode, min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; - spin_lock(&uprobes_treelock); + read_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); if (n) { for (t = n; t; t = rb_prev(t)) { @@ -1316,7 +1316,7 @@ static void build_probe_list(struct inode *inode, get_uprobe(u); } } - spin_unlock(&uprobes_treelock); + read_unlock(&uprobes_treelock); } /* @vma contains reference counter, not the probed instruction. */ @@ -1407,9 +1407,9 @@ vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long e min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; - spin_lock(&uprobes_treelock); + read_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); - spin_unlock(&uprobes_treelock); + read_unlock(&uprobes_treelock); return !!n; } diff --git a/kernel/exit.c b/kernel/exit.c index 41a12630cbbc..cd3aa9042f1a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -94,7 +94,6 @@ static struct ctl_table kern_exit_table[] = { .mode = 0644, .proc_handler = proc_douintvec, }, - { } }; static __init int kernel_exit_sysctls_init(void) diff --git a/kernel/fork.c b/kernel/fork.c index 39a5046c2f0b..99076dbe27d8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -714,6 +714,23 @@ 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; @@ -730,25 +747,9 @@ 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. 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_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); - if (tmp->vm_ops && tmp->vm_ops->open) - tmp->vm_ops->open(tmp); - if (retval) { mpnt = vma_next(&vmi); goto loop_out; @@ -1343,7 +1344,7 @@ static inline void __mmput(struct mm_struct *mm) ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); - mm_put_huge_zero_page(mm); + mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 1e78ef24321e..06a1f091be81 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1150,7 +1150,7 @@ static int __init futex_init(void) unsigned int futex_shift; unsigned long i; -#if CONFIG_BASE_SMALL +#ifdef CONFIG_BASE_SMALL futex_hashsize = 16; #else futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); diff --git a/kernel/hung_task.c b/kernel/hung_task.c index b2fc2727d654..1d92016b0b3c 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -314,7 +314,6 @@ static struct ctl_table hung_task_sysctls[] = { .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_NEG_ONE, }, - {} }; static void __init hung_task_sysctl_init(void) diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 2531f3496ab6..529adb1f5859 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -108,6 +108,10 @@ config GENERIC_IRQ_MATRIX_ALLOCATOR config GENERIC_IRQ_RESERVATION_MODE bool +# Snapshot for interrupt statistics +config GENERIC_IRQ_STAT_SNAPSHOT + bool + # Support forced irq threading config IRQ_FORCED_THREADING bool diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 1ed2b1739363..75cadbc3c232 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -130,6 +130,22 @@ static bool migrate_one_irq(struct irq_desc *desc) * CPU. */ err = irq_do_set_affinity(d, affinity, false); + + /* + * If there are online CPUs in the affinity mask, but they have no + * vectors left to make the migration work, try to break the + * affinity by migrating to any online CPU. + */ + if (err == -ENOSPC && !irqd_affinity_is_managed(d) && affinity != cpu_online_mask) { + pr_debug("IRQ%u: set affinity failed for %*pbl, re-try with online CPUs\n", + d->irq, cpumask_pr_args(affinity)); + + affinity = cpu_online_mask; + brokeaff = true; + + err = irq_do_set_affinity(d, affinity, false); + } + if (err) { pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n", d->irq, err); @@ -195,10 +211,15 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) !irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity)) return; - if (irqd_is_managed_and_shutdown(data)) { - irq_startup(desc, IRQ_RESEND, IRQ_START_COND); + /* + * Don't restore suspended interrupts here when a system comes back + * from S3. They are reenabled via resume_device_irqs(). + */ + if (desc->istate & IRQS_SUSPENDED) return; - } + + if (irqd_is_managed_and_shutdown(data)) + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); /* * If the interrupt can only be directed to a single target diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index bcc7f21db9ee..ed28059e9849 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -98,6 +98,8 @@ extern void mask_irq(struct irq_desc *desc); extern void unmask_irq(struct irq_desc *desc); extern void unmask_threaded_irq(struct irq_desc *desc); +extern unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask); + #ifdef CONFIG_SPARSE_IRQ static inline void irq_mark_irq(unsigned int irq) { } #else @@ -258,7 +260,7 @@ static inline void irq_state_set_masked(struct irq_desc *desc) static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc) { - __this_cpu_inc(*desc->kstat_irqs); + __this_cpu_inc(desc->kstat_irqs->cnt); __this_cpu_inc(kstat.irqs_sum); } @@ -278,6 +280,11 @@ static inline int irq_desc_is_chained(struct irq_desc *desc) return (desc->action && desc->action == &chained_action); } +static inline bool irq_is_nmi(struct irq_desc *desc) +{ + return desc->istate & IRQS_NMI; +} + #ifdef CONFIG_PM_SLEEP bool irq_pm_check_wakeup(struct irq_desc *desc); void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 4c6b32318ce3..88ac3652fcf2 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -134,7 +134,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, desc->name = NULL; desc->owner = owner; for_each_possible_cpu(cpu) - *per_cpu_ptr(desc->kstat_irqs, cpu) = 0; + *per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { }; desc_smp_init(desc, node, affinity); } @@ -186,7 +186,7 @@ static int init_desc(struct irq_desc *desc, int irq, int node, const struct cpumask *affinity, struct module *owner) { - desc->kstat_irqs = alloc_percpu(unsigned int); + desc->kstat_irqs = alloc_percpu(struct irqstat); if (!desc->kstat_irqs) return -ENOMEM; @@ -911,10 +911,7 @@ int irq_set_percpu_devid_partition(unsigned int irq, { struct irq_desc *desc = irq_to_desc(irq); - if (!desc) - return -EINVAL; - - if (desc->percpu_enabled) + if (!desc || desc->percpu_enabled) return -EINVAL; desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL); @@ -922,10 +919,7 @@ int irq_set_percpu_devid_partition(unsigned int irq, if (!desc->percpu_enabled) return -ENOMEM; - if (affinity) - desc->percpu_affinity = affinity; - else - desc->percpu_affinity = cpu_possible_mask; + desc->percpu_affinity = affinity ? : cpu_possible_mask; irq_set_percpu_devid_flags(irq); return 0; @@ -968,33 +962,58 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); - return desc && desc->kstat_irqs ? - *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; + return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } -static bool irq_is_nmi(struct irq_desc *desc) +unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask) { - return desc->istate & IRQS_NMI; -} - -static unsigned int kstat_irqs(unsigned int irq) -{ - struct irq_desc *desc = irq_to_desc(irq); unsigned int sum = 0; int cpu; - if (!desc || !desc->kstat_irqs) - return 0; if (!irq_settings_is_per_cpu_devid(desc) && !irq_settings_is_per_cpu(desc) && !irq_is_nmi(desc)) return data_race(desc->tot_count); - for_each_possible_cpu(cpu) - sum += data_race(*per_cpu_ptr(desc->kstat_irqs, cpu)); + for_each_cpu(cpu, cpumask) + sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu)); return sum; } +static unsigned int kstat_irqs(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || !desc->kstat_irqs) + return 0; + return kstat_irqs_desc(desc, cpu_possible_mask); +} + +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT + +void kstat_snapshot_irqs(void) +{ + struct irq_desc *desc; + unsigned int irq; + + for_each_irq_desc(irq, desc) { + if (!desc->kstat_irqs) + continue; + this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt)); + } +} + +unsigned int kstat_get_irq_since_snapshot(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || !desc->kstat_irqs) + return 0; + return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref); +} + +#endif + /** * kstat_irqs_usr - Get the statistics for an interrupt from thread context * @irq: The interrupt number diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 3dd1c871e091..aadc8891cc16 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -909,10 +909,11 @@ EXPORT_SYMBOL_GPL(irq_create_of_mapping); */ void irq_dispose_mapping(unsigned int virq) { - struct irq_data *irq_data = irq_get_irq_data(virq); + struct irq_data *irq_data; struct irq_domain *domain; - if (!virq || !irq_data) + irq_data = virq ? irq_get_irq_data(virq) : NULL; + if (!irq_data) return; domain = irq_data->domain; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ad3eaf2ab959..71b0fc2d0aea 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -564,7 +564,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) /* The release function is promised process context */ might_sleep(); - if (!desc || desc->istate & IRQS_NMI) + if (!desc || irq_is_nmi(desc)) return -EINVAL; /* Complete initialisation of *notify */ @@ -800,10 +800,14 @@ void __enable_irq(struct irq_desc *desc) irq_settings_set_noprobe(desc); /* * Call irq_startup() not irq_enable() here because the - * interrupt might be marked NOAUTOEN. So irq_startup() - * needs to be invoked when it gets enabled the first - * time. If it was already started up, then irq_startup() - * will invoke irq_enable() under the hood. + * interrupt might be marked NOAUTOEN so irq_startup() + * needs to be invoked when it gets enabled the first time. + * This is also required when __enable_irq() is invoked for + * a managed and shutdown interrupt from the S3 resume + * path. + * + * If it was already started up, then irq_startup() will + * invoke irq_enable() under the hood. */ irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE); break; @@ -898,7 +902,7 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on) return -EINVAL; /* Don't use NMIs as wake up interrupts please */ - if (desc->istate & IRQS_NMI) { + if (irq_is_nmi(desc)) { ret = -EINVAL; goto out_unlock; } @@ -1624,7 +1628,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ unsigned int oldtype; - if (desc->istate & IRQS_NMI) { + if (irq_is_nmi(desc)) { pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n", new->name, irq, desc->irq_data.chip->name); ret = -EINVAL; @@ -1643,8 +1647,13 @@ __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 */ @@ -2077,7 +2086,7 @@ const void *free_nmi(unsigned int irq, void *dev_id) unsigned long flags; const void *devname; - if (!desc || WARN_ON(!(desc->istate & IRQS_NMI))) + if (!desc || WARN_ON(!irq_is_nmi(desc))) return NULL; if (WARN_ON(irq_settings_is_per_cpu_devid(desc))) @@ -2543,7 +2552,7 @@ void free_percpu_nmi(unsigned int irq, void __percpu *dev_id) if (!desc || !irq_settings_is_per_cpu_devid(desc)) return; - if (WARN_ON(!(desc->istate & IRQS_NMI))) + if (WARN_ON(!irq_is_nmi(desc))) return; kfree(__free_percpu_irq(irq, dev_id)); @@ -2679,7 +2688,7 @@ int request_percpu_nmi(unsigned int irq, irq_handler_t handler, return -EINVAL; /* The line cannot already be NMI */ - if (desc->istate & IRQS_NMI) + if (irq_is_nmi(desc)) return -EINVAL; action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); @@ -2740,7 +2749,7 @@ int prepare_percpu_nmi(unsigned int irq) if (!desc) return -EINVAL; - if (WARN(!(desc->istate & IRQS_NMI), + if (WARN(!irq_is_nmi(desc), KERN_ERR "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n", irq)) { ret = -EINVAL; @@ -2782,7 +2791,7 @@ void teardown_percpu_nmi(unsigned int irq) if (!desc) return; - if (WARN_ON(!(desc->istate & IRQS_NMI))) + if (WARN_ON(!irq_is_nmi(desc))) goto out; irq_nmi_teardown(desc); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index f90952ebc494..2024f89baea4 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1434,6 +1434,7 @@ int msi_domain_alloc_irqs_range(struct device *dev, unsigned int domid, msi_unlock_descs(dev); return ret; } +EXPORT_SYMBOL_GPL(msi_domain_alloc_irqs_range); /** * msi_domain_alloc_irqs_all_locked - Allocate all interrupts from a MSI interrupt domain @@ -1680,6 +1681,7 @@ void msi_domain_free_irqs_range(struct device *dev, unsigned int domid, msi_domain_free_irqs_range_locked(dev, domid, first, last); msi_unlock_descs(dev); } +EXPORT_SYMBOL_GPL(msi_domain_free_irqs_all); /** * msi_domain_free_irqs_all_locked - Free all interrupts from a MSI interrupt domain diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 623b8136e9af..5c320c3f10a7 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -488,18 +488,15 @@ int show_interrupts(struct seq_file *p, void *v) if (!desc || irq_settings_is_hidden(desc)) goto outsparse; - if (desc->kstat_irqs) { - for_each_online_cpu(j) - any_count |= data_race(*per_cpu_ptr(desc->kstat_irqs, j)); - } + if (desc->kstat_irqs) + any_count = kstat_irqs_desc(desc, cpu_online_mask); if ((!desc->action || irq_desc_is_chained(desc)) && !any_count) goto outsparse; seq_printf(p, "%*d: ", prec, i); for_each_online_cpu(j) - seq_printf(p, "%10u ", desc->kstat_irqs ? - *per_cpu_ptr(desc->kstat_irqs, j) : 0); + seq_printf(p, "%10u ", desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, j) : 0); raw_spin_lock_irqsave(&desc->lock, flags); if (desc->irq_data.chip) { diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 5f2c66860ac6..b07a2d732ffb 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -190,7 +190,7 @@ int irq_inject_interrupt(unsigned int irq) * - not NMI type * - activated */ - if ((desc->istate & IRQS_NMI) || !irqd_is_activated(&desc->irq_data)) + if (irq_is_nmi(desc) || !irqd_is_activated(&desc->irq_data)) err = -EINVAL; else err = check_irq_resend(desc, true); diff --git a/kernel/jump_label.c b/kernel/jump_label.c index d9c822bbffb8..3218fa5688b9 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -530,6 +530,45 @@ void __init jump_label_init(void) cpus_read_unlock(); } +static inline bool static_key_sealed(struct static_key *key) +{ + return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); +} + +static inline void static_key_seal(struct static_key *key) +{ + unsigned long type = key->type & JUMP_TYPE_TRUE; + key->type = JUMP_TYPE_LINKED | type; +} + +void jump_label_init_ro(void) +{ + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __stop___jump_table; + struct jump_entry *iter; + + if (WARN_ON_ONCE(!static_key_initialized)) + return; + + cpus_read_lock(); + jump_label_lock(); + + for (iter = iter_start; iter < iter_stop; iter++) { + struct static_key *iterk = jump_entry_key(iter); + + if (!is_kernel_ro_after_init((unsigned long)iterk)) + continue; + + if (static_key_sealed(iterk)) + continue; + + static_key_seal(iterk); + } + + jump_label_unlock(); + cpus_read_unlock(); +} + #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) @@ -650,6 +689,15 @@ static int jump_label_add_module(struct module *mod) static_key_set_entries(key, iter); continue; } + + /* + * If the key was sealed at init, then there's no need to keep a + * reference to its module entries - just patch them now and be + * done with it. + */ + if (static_key_sealed(key)) + goto do_poke; + jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; @@ -675,6 +723,7 @@ static int jump_label_add_module(struct module *mod) static_key_set_linked(key); /* Only update if we've changed from our initial state */ +do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } @@ -699,6 +748,10 @@ static void jump_label_del_module(struct module *mod) if (within_module((unsigned long)key, mod)) continue; + /* No @jlm allocated because key was sealed at init. */ + if (static_key_sealed(key)) + continue; + /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 18edd57b5fe8..22ea19a36e6e 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -325,12 +325,6 @@ static unsigned long get_symbol_pos(unsigned long addr, unsigned long symbol_start = 0, symbol_end = 0; unsigned long i, low, high, mid; - /* This kernel should never had been booted. */ - if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) - BUG_ON(!kallsyms_addresses); - else - BUG_ON(!kallsyms_offsets); - /* Do a binary search on the sorted kallsyms_addresses array. */ low = 0; high = kallsyms_num_syms; diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h index 27fabdcc40f5..85480274fc8f 100644 --- a/kernel/kallsyms_internal.h +++ b/kernel/kallsyms_internal.h @@ -5,27 +5,21 @@ #include <linux/types.h> /* - * These will be re-linked against their real values - * during the second link stage. + * These will be re-linked against their real values during the second link + * stage. Preliminary values must be provided in the linker script using the + * PROVIDE() directive so that the first link stage can complete successfully. */ -extern const unsigned long kallsyms_addresses[] __weak; -extern const int kallsyms_offsets[] __weak; -extern const u8 kallsyms_names[] __weak; +extern const unsigned long kallsyms_addresses[]; +extern const int kallsyms_offsets[]; +extern const u8 kallsyms_names[]; -/* - * Tell the compiler that the count isn't in the small data section if the arch - * has one (eg: FRV). - */ -extern const unsigned int kallsyms_num_syms -__section(".rodata") __attribute__((weak)); - -extern const unsigned long kallsyms_relative_base -__section(".rodata") __attribute__((weak)); +extern const unsigned int kallsyms_num_syms; +extern const unsigned long kallsyms_relative_base; -extern const char kallsyms_token_table[] __weak; -extern const u16 kallsyms_token_index[] __weak; +extern const char kallsyms_token_table[]; +extern const u16 kallsyms_token_index[]; -extern const unsigned int kallsyms_markers[] __weak; -extern const u8 kallsyms_seqs_of_names[] __weak; +extern const unsigned int kallsyms_markers[]; +extern const u8 kallsyms_seqs_of_names[]; #endif // LINUX_KALLSYMS_INTERNAL_H_ diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index 8a689b4ff4f9..2f84896a7bcb 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -82,7 +82,7 @@ static struct test_item test_items[] = { ITEM_FUNC(kallsyms_test_func_static), ITEM_FUNC(kallsyms_test_func), ITEM_FUNC(kallsyms_test_func_weak), - ITEM_FUNC(vmalloc), + ITEM_FUNC(vmalloc_noprof), ITEM_FUNC(vfree), #ifdef CONFIG_KALLSYMS_ALL ITEM_DATA(kallsyms_test_var_bss_static), diff --git a/kernel/kcov.c b/kernel/kcov.c index f9ac2e9e460f..c3124f6d5536 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -627,7 +627,8 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, mode = kcov_get_mode(remote_arg->trace_mode); if (mode < 0) return mode; - if (remote_arg->area_size > LONG_MAX / sizeof(unsigned long)) + if ((unsigned long)remote_arg->area_size > + LONG_MAX / sizeof(unsigned long)) return -EINVAL; kcov->mode = mode; t->kcov = kcov; diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index 015586217875..0c17b4c83e1c 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -304,6 +304,7 @@ static long test_array[3 * PAGE_SIZE / sizeof(long)]; static struct { long val[8]; } test_struct; +static long __data_racy test_data_racy; static DEFINE_SEQLOCK(test_seqlock); static DEFINE_SPINLOCK(test_spinlock); static DEFINE_MUTEX(test_mutex); @@ -358,6 +359,8 @@ static noinline void test_kernel_write_uninstrumented(void) { test_var++; } static noinline void test_kernel_data_race(void) { data_race(test_var++); } +static noinline void test_kernel_data_racy_qualifier(void) { test_data_racy++; } + static noinline void test_kernel_assert_writer(void) { ASSERT_EXCLUSIVE_WRITER(test_var); @@ -1009,6 +1012,19 @@ static void test_data_race(struct kunit *test) KUNIT_EXPECT_FALSE(test, match_never); } +/* Test the __data_racy type qualifier. */ +__no_kcsan +static void test_data_racy_qualifier(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_data_racy_qualifier, test_kernel_data_racy_qualifier); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + __no_kcsan static void test_assert_exclusive_writer(struct kunit *test) { @@ -1424,6 +1440,7 @@ static struct kunit_case kcsan_test_cases[] = { KCSAN_KUNIT_CASE(test_read_plain_atomic_rmw), KCSAN_KUNIT_CASE(test_zero_size_access), KCSAN_KUNIT_CASE(test_data_race), + KCSAN_KUNIT_CASE(test_data_racy_qualifier), KCSAN_KUNIT_CASE(test_assert_exclusive_writer), KCSAN_KUNIT_CASE(test_assert_exclusive_access), KCSAN_KUNIT_CASE(test_assert_exclusive_access_writer), diff --git a/kernel/kexec.c b/kernel/kexec.c index bab542fc1463..a6b3f96bb50c 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -135,8 +135,8 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, image->preserve_context = 1; #ifdef CONFIG_CRASH_HOTPLUG - if (flags & KEXEC_UPDATE_ELFCOREHDR) - image->update_elfcorehdr = 1; + if ((flags & KEXEC_ON_CRASH) && arch_crash_hotplug_support(image, flags)) + image->hotplug_support = 1; #endif ret = machine_kexec_prepare(image); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 0e96f6b24344..9112d69d68b0 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -948,7 +948,6 @@ static struct ctl_table kexec_core_sysctls[] = { .mode = 0644, .proc_handler = kexec_limit_handler, }, - { } }; static int __init kexec_core_sysctl_init(void) diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 2d1db05fbf04..3d64290d24c9 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -376,6 +376,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (ret) goto out; +#ifdef CONFIG_CRASH_HOTPLUG + if ((flags & KEXEC_FILE_ON_CRASH) && arch_crash_hotplug_support(image, flags)) + image->hotplug_support = 1; +#endif + ret = machine_kexec_prepare(image); if (ret) goto out; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9d9095e81792..6a76a8100073 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -26,7 +26,6 @@ #include <linux/slab.h> #include <linux/stddef.h> #include <linux/export.h> -#include <linux/moduleloader.h> #include <linux/kallsyms.h> #include <linux/freezer.h> #include <linux/seq_file.h> @@ -39,6 +38,7 @@ #include <linux/jump_label.h> #include <linux/static_call.h> #include <linux/perf_event.h> +#include <linux/execmem.h> #include <asm/sections.h> #include <asm/cacheflush.h> @@ -113,17 +113,17 @@ enum kprobe_slot_state { void __weak *alloc_insn_page(void) { /* - * Use module_alloc() so this page is within +/- 2GB of where the + * Use execmem_alloc() so this page is within +/- 2GB of where the * kernel image and loaded module images reside. This is required * for most of the architectures. * (e.g. x86-64 needs this to handle the %rip-relative fixups.) */ - return module_alloc(PAGE_SIZE); + return execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE); } static void free_insn_page(void *page) { - module_memfree(page); + execmem_free(page); } struct kprobe_insn_cache kprobe_insn_slots = { @@ -968,7 +968,6 @@ static struct ctl_table kprobe_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static void __init kprobe_sysctls_init(void) @@ -1068,6 +1067,7 @@ static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; +bool kprobe_ftrace_disabled; static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) @@ -1136,6 +1136,11 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } + +void kprobe_ftrace_kill(void) +{ + kprobe_ftrace_disabled = true; +} #else /* !CONFIG_KPROBES_ON_FTRACE */ static inline int arm_kprobe_ftrace(struct kprobe *p) { @@ -1567,10 +1572,17 @@ 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) || @@ -1580,9 +1592,8 @@ 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); - if (*probed_mod) { + /* Get module refcount and reject __init functions for loaded modules. */ + if (IS_ENABLED(CONFIG_MODULES) && *probed_mod) { /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. @@ -1597,12 +1608,13 @@ static int check_kprobe_address_safe(struct kprobe *p, * kprobes in there. */ if (within_module_init((unsigned long)p->addr, *probed_mod) && - (*probed_mod)->state != MODULE_STATE_COMING) { + !module_is_coming(*probed_mod)) { module_put(*probed_mod); *probed_mod = NULL; ret = -ENOENT; } } + out: preempt_enable(); jump_label_unlock(); @@ -2482,24 +2494,6 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end) return 0; } -/* Remove all symbols in given area from kprobe blacklist */ -static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) -{ - struct kprobe_blacklist_entry *ent, *n; - - list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { - if (ent->start_addr < start || ent->start_addr >= end) - continue; - list_del(&ent->list); - kfree(ent); - } -} - -static void kprobe_remove_ksym_blacklist(unsigned long entry) -{ - kprobe_remove_area_blacklist(entry, entry + 1); -} - int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, char *type, char *sym) { @@ -2564,6 +2558,25 @@ static int __init populate_kprobe_blacklist(unsigned long *start, return ret ? : arch_populate_kprobe_blacklist(); } +#ifdef CONFIG_MODULES +/* Remove all symbols in given area from kprobe blacklist */ +static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) +{ + struct kprobe_blacklist_entry *ent, *n; + + list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { + if (ent->start_addr < start || ent->start_addr >= end) + continue; + list_del(&ent->list); + kfree(ent); + } +} + +static void kprobe_remove_ksym_blacklist(unsigned long entry) +{ + kprobe_remove_area_blacklist(entry, entry + 1); +} + static void add_module_kprobe_blacklist(struct module *mod) { unsigned long start, end; @@ -2666,6 +2679,17 @@ static struct notifier_block kprobe_module_nb = { .priority = 0 }; +static int kprobe_register_module_notifier(void) +{ + return register_module_notifier(&kprobe_module_nb); +} +#else +static int kprobe_register_module_notifier(void) +{ + return 0; +} +#endif /* CONFIG_MODULES */ + void kprobe_free_init_mem(void) { void *start = (void *)(&__init_begin); @@ -2725,7 +2749,7 @@ static int __init init_kprobes(void) if (!err) err = register_die_notifier(&kprobe_exceptions_nb); if (!err) - err = register_module_notifier(&kprobe_module_nb); + err = kprobe_register_module_notifier(); kprobes_initialized = (err == 0); kprobe_sysctls_init(); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 495b69a71a5d..07fb5987b42b 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -228,8 +228,8 @@ KERNEL_ATTR_RW(rcu_normal); /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ -extern const void __start_notes __weak; -extern const void __stop_notes __weak; +extern const void __start_notes; +extern const void __stop_notes; #define notes_size (&__stop_notes - &__start_notes) static ssize_t notes_read(struct file *filp, struct kobject *kobj, diff --git a/kernel/kthread.c b/kernel/kthread.c index c5e40830c1f2..f7be976ff88a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -315,6 +315,7 @@ void __noreturn kthread_exit(long result) kthread->result = result; do_exit(0); } +EXPORT_SYMBOL(kthread_exit); /** * kthread_complete_and_exit - Exit the current kthread. diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 781249098cb6..84c53285f499 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -85,7 +85,6 @@ static struct ctl_table latencytop_sysctl[] = { .mode = 0644, .proc_handler = sysctl_latencytop, }, - {} }; #endif diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index ecbc9b6aba3a..52426665eecc 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -973,7 +973,7 @@ static int __klp_disable_patch(struct klp_patch *patch) if (klp_transition_patch) return -EBUSY; - klp_init_transition(patch, KLP_UNPATCHED); + klp_init_transition(patch, KLP_TRANSITION_UNPATCHED); klp_for_each_object(patch, obj) if (obj->patched) @@ -1008,7 +1008,7 @@ static int __klp_enable_patch(struct klp_patch *patch) pr_notice("enabling patch '%s'\n", patch->mod->name); - klp_init_transition(patch, KLP_PATCHED); + klp_init_transition(patch, KLP_TRANSITION_PATCHED); /* * Enforce the order of the func->transition writes in diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index 4152c71507e2..90408500e5a3 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -95,9 +95,9 @@ static void notrace klp_ftrace_handler(unsigned long ip, patch_state = current->patch_state; - WARN_ON_ONCE(patch_state == KLP_UNDEFINED); + WARN_ON_ONCE(patch_state == KLP_TRANSITION_IDLE); - if (patch_state == KLP_UNPATCHED) { + if (patch_state == KLP_TRANSITION_UNPATCHED) { /* * Use the previously patched version of the function. * If no previous patches exist, continue with the diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index e54c3d60a904..ba069459c101 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -23,7 +23,7 @@ static DEFINE_PER_CPU(unsigned long[MAX_STACK_ENTRIES], klp_stack_entries); struct klp_patch *klp_transition_patch; -static int klp_target_state = KLP_UNDEFINED; +static int klp_target_state = KLP_TRANSITION_IDLE; static unsigned int klp_signals_cnt; @@ -96,16 +96,16 @@ static void klp_complete_transition(void) pr_debug("'%s': completing %s transition\n", klp_transition_patch->mod->name, - klp_target_state == KLP_PATCHED ? "patching" : "unpatching"); + klp_target_state == KLP_TRANSITION_PATCHED ? "patching" : "unpatching"); - if (klp_transition_patch->replace && klp_target_state == KLP_PATCHED) { + if (klp_transition_patch->replace && klp_target_state == KLP_TRANSITION_PATCHED) { klp_unpatch_replaced_patches(klp_transition_patch); klp_discard_nops(klp_transition_patch); } - if (klp_target_state == KLP_UNPATCHED) { + if (klp_target_state == KLP_TRANSITION_UNPATCHED) { /* - * All tasks have transitioned to KLP_UNPATCHED so we can now + * All tasks have transitioned to KLP_TRANSITION_UNPATCHED so we can now * remove the new functions from the func_stack. */ klp_unpatch_objects(klp_transition_patch); @@ -123,36 +123,36 @@ static void klp_complete_transition(void) klp_for_each_func(obj, func) func->transition = false; - /* Prevent klp_ftrace_handler() from seeing KLP_UNDEFINED state */ - if (klp_target_state == KLP_PATCHED) + /* Prevent klp_ftrace_handler() from seeing KLP_TRANSITION_IDLE state */ + if (klp_target_state == KLP_TRANSITION_PATCHED) klp_synchronize_transition(); read_lock(&tasklist_lock); for_each_process_thread(g, task) { WARN_ON_ONCE(test_tsk_thread_flag(task, TIF_PATCH_PENDING)); - task->patch_state = KLP_UNDEFINED; + task->patch_state = KLP_TRANSITION_IDLE; } read_unlock(&tasklist_lock); for_each_possible_cpu(cpu) { task = idle_task(cpu); WARN_ON_ONCE(test_tsk_thread_flag(task, TIF_PATCH_PENDING)); - task->patch_state = KLP_UNDEFINED; + task->patch_state = KLP_TRANSITION_IDLE; } klp_for_each_object(klp_transition_patch, obj) { if (!klp_is_object_loaded(obj)) continue; - if (klp_target_state == KLP_PATCHED) + if (klp_target_state == KLP_TRANSITION_PATCHED) klp_post_patch_callback(obj); - else if (klp_target_state == KLP_UNPATCHED) + else if (klp_target_state == KLP_TRANSITION_UNPATCHED) klp_post_unpatch_callback(obj); } pr_notice("'%s': %s complete\n", klp_transition_patch->mod->name, - klp_target_state == KLP_PATCHED ? "patching" : "unpatching"); + klp_target_state == KLP_TRANSITION_PATCHED ? "patching" : "unpatching"); - klp_target_state = KLP_UNDEFINED; + klp_target_state = KLP_TRANSITION_IDLE; klp_transition_patch = NULL; } @@ -164,13 +164,13 @@ static void klp_complete_transition(void) */ void klp_cancel_transition(void) { - if (WARN_ON_ONCE(klp_target_state != KLP_PATCHED)) + if (WARN_ON_ONCE(klp_target_state != KLP_TRANSITION_PATCHED)) return; pr_debug("'%s': canceling patching transition, going to unpatch\n", klp_transition_patch->mod->name); - klp_target_state = KLP_UNPATCHED; + klp_target_state = KLP_TRANSITION_UNPATCHED; klp_complete_transition(); } @@ -218,7 +218,7 @@ static int klp_check_stack_func(struct klp_func *func, unsigned long *entries, struct klp_ops *ops; int i; - if (klp_target_state == KLP_UNPATCHED) { + if (klp_target_state == KLP_TRANSITION_UNPATCHED) { /* * Check for the to-be-unpatched function * (the func itself). @@ -455,7 +455,7 @@ void klp_try_complete_transition(void) struct klp_patch *patch; bool complete = true; - WARN_ON_ONCE(klp_target_state == KLP_UNDEFINED); + WARN_ON_ONCE(klp_target_state == KLP_TRANSITION_IDLE); /* * Try to switch the tasks to the target patch state by walking their @@ -532,11 +532,11 @@ void klp_start_transition(void) struct task_struct *g, *task; unsigned int cpu; - WARN_ON_ONCE(klp_target_state == KLP_UNDEFINED); + WARN_ON_ONCE(klp_target_state == KLP_TRANSITION_IDLE); pr_notice("'%s': starting %s transition\n", klp_transition_patch->mod->name, - klp_target_state == KLP_PATCHED ? "patching" : "unpatching"); + klp_target_state == KLP_TRANSITION_PATCHED ? "patching" : "unpatching"); /* * Mark all normal tasks as needing a patch state update. They'll @@ -578,7 +578,7 @@ void klp_init_transition(struct klp_patch *patch, int state) struct klp_func *func; int initial_state = !state; - WARN_ON_ONCE(klp_target_state != KLP_UNDEFINED); + WARN_ON_ONCE(klp_target_state != KLP_TRANSITION_IDLE); klp_transition_patch = patch; @@ -589,7 +589,7 @@ void klp_init_transition(struct klp_patch *patch, int state) klp_target_state = state; pr_debug("'%s': initializing %s transition\n", patch->mod->name, - klp_target_state == KLP_PATCHED ? "patching" : "unpatching"); + klp_target_state == KLP_TRANSITION_PATCHED ? "patching" : "unpatching"); /* * Initialize all tasks to the initial patch state to prepare them for @@ -597,7 +597,7 @@ void klp_init_transition(struct klp_patch *patch, int state) */ read_lock(&tasklist_lock); for_each_process_thread(g, task) { - WARN_ON_ONCE(task->patch_state != KLP_UNDEFINED); + WARN_ON_ONCE(task->patch_state != KLP_TRANSITION_IDLE); task->patch_state = initial_state; } read_unlock(&tasklist_lock); @@ -607,19 +607,19 @@ void klp_init_transition(struct klp_patch *patch, int state) */ for_each_possible_cpu(cpu) { task = idle_task(cpu); - WARN_ON_ONCE(task->patch_state != KLP_UNDEFINED); + WARN_ON_ONCE(task->patch_state != KLP_TRANSITION_IDLE); task->patch_state = initial_state; } /* * Enforce the order of the task->patch_state initializations and the * func->transition updates to ensure that klp_ftrace_handler() doesn't - * see a func in transition with a task->patch_state of KLP_UNDEFINED. + * see a func in transition with a task->patch_state of KLP_TRANSITION_IDLE. * * Also enforce the order of the klp_target_state write and future * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() and * __klp_sched_try_switch() don't set a task->patch_state to - * KLP_UNDEFINED. + * KLP_TRANSITION_IDLE. */ smp_wmb(); @@ -652,7 +652,7 @@ void klp_reverse_transition(void) pr_debug("'%s': reversing transition from %s\n", klp_transition_patch->mod->name, - klp_target_state == KLP_PATCHED ? "patching to unpatching" : + klp_target_state == KLP_TRANSITION_PATCHED ? "patching to unpatching" : "unpatching to patching"); /* @@ -741,7 +741,7 @@ void klp_force_transition(void) klp_update_patch_state(idle_task(cpu)); /* Set forced flag for patches being removed. */ - if (klp_target_state == KLP_UNPATCHED) + if (klp_target_state == KLP_TRANSITION_UNPATCHED) klp_transition_patch->forced = true; else if (klp_transition_patch->replace) { klp_for_each_patch(patch) { diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h index a6016b91803d..d2345e9c0190 100644 --- a/kernel/locking/lock_events.h +++ b/kernel/locking/lock_events.h @@ -53,8 +53,8 @@ static inline void __lockevent_add(enum lock_events event, int inc) #else /* CONFIG_LOCK_EVENT_COUNTS */ #define lockevent_inc(ev) -#define lockevent_add(ev, c) -#define lockevent_cond_inc(ev, c) +#define lockevent_add(ev, c) do { (void)(c); } while (0) +#define lockevent_cond_inc(ev, c) do { (void)(c); } while (0) #endif /* CONFIG_LOCK_EVENT_COUNTS */ diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index ebe6b8ec7cb3..1df5fef8a656 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -220,21 +220,18 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock) */ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) { - u32 old, new, val = atomic_read(&lock->val); + u32 old, new; - for (;;) { - new = (val & _Q_LOCKED_PENDING_MASK) | tail; + old = atomic_read(&lock->val); + do { + new = (old & _Q_LOCKED_PENDING_MASK) | tail; /* * We can use relaxed semantics since the caller ensures that * the MCS node is properly initialized before updating the * tail. */ - old = atomic_cmpxchg_relaxed(&lock->val, val, new); - if (old == val) - break; + } while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new)); - val = old; - } return old; } #endif /* _Q_PENDING_BITS == 8 */ diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index ae2b12f68b90..f5a36e67b593 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -86,9 +86,10 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock) */ for (;;) { int val = atomic_read(&lock->val); + u8 old = 0; if (!(val & _Q_LOCKED_PENDING_MASK) && - (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) { + try_cmpxchg_acquire(&lock->locked, &old, _Q_LOCKED_VAL)) { lockevent_inc(pv_lock_stealing); return true; } @@ -116,11 +117,12 @@ static __always_inline void set_pending(struct qspinlock *lock) * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the * lock just to be sure that it will get it. */ -static __always_inline int trylock_clear_pending(struct qspinlock *lock) +static __always_inline bool trylock_clear_pending(struct qspinlock *lock) { + u16 old = _Q_PENDING_VAL; + return !READ_ONCE(lock->locked) && - (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL, - _Q_LOCKED_VAL) == _Q_PENDING_VAL); + try_cmpxchg_acquire(&lock->locked_pending, &old, _Q_LOCKED_VAL); } #else /* _Q_PENDING_BITS == 8 */ static __always_inline void set_pending(struct qspinlock *lock) @@ -128,27 +130,21 @@ static __always_inline void set_pending(struct qspinlock *lock) atomic_or(_Q_PENDING_VAL, &lock->val); } -static __always_inline int trylock_clear_pending(struct qspinlock *lock) +static __always_inline bool trylock_clear_pending(struct qspinlock *lock) { - int val = atomic_read(&lock->val); - - for (;;) { - int old, new; - - if (val & _Q_LOCKED_MASK) - break; + int old, new; + old = atomic_read(&lock->val); + do { + if (old & _Q_LOCKED_MASK) + return false; /* * Try to clear pending bit & set locked bit */ - old = val; - new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL; - val = atomic_cmpxchg_acquire(&lock->val, old, new); + new = (old & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL; + } while (!atomic_try_cmpxchg_acquire (&lock->val, &old, new)); - if (val == old) - return 1; - } - return 0; + return true; } #endif /* _Q_PENDING_BITS == 8 */ @@ -216,8 +212,9 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node) int hopcnt = 0; for_each_hash_entry(he, offset, hash) { + struct qspinlock *old = NULL; hopcnt++; - if (!cmpxchg(&he->lock, NULL, lock)) { + if (try_cmpxchg(&he->lock, &old, lock)) { WRITE_ONCE(he->node, node); lockevent_pv_hop(hopcnt); return &he->lock; @@ -294,7 +291,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) { struct pv_node *pn = (struct pv_node *)node; struct pv_node *pp = (struct pv_node *)prev; - bool __maybe_unused wait_early; + bool wait_early; int loop; for (;;) { @@ -360,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node) { struct pv_node *pn = (struct pv_node *)node; - + enum vcpu_state old = vcpu_halted; /* * If the vCPU is indeed halted, advance its state to match that of * pv_wait_node(). If OTOH this fails, the vCPU was running and will @@ -377,8 +374,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node) * subsequent writes. */ smp_mb__before_atomic(); - if (cmpxchg_relaxed(&pn->state, vcpu_halted, vcpu_hashed) - != vcpu_halted) + if (!try_cmpxchg_relaxed(&pn->state, &old, vcpu_hashed)) return; /* @@ -546,15 +542,14 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked) #ifndef __pv_queued_spin_unlock __visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock) { - u8 locked; + u8 locked = _Q_LOCKED_VAL; /* * We must not unlock if SLOW, because in that case we must first * unhash. Otherwise it would be possible to have multiple @lock * entries, which would be BAD. */ - locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0); - if (likely(locked == _Q_LOCKED_VAL)) + if (try_cmpxchg_release(&lock->locked, &locked, 0)) return; __pv_queued_spin_unlock_slowpath(lock, locked); diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index c3ced519e14b..4047b6d48255 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -2,6 +2,7 @@ menuconfig MODULES bool "Enable loadable module support" modules + select EXECMEM help Kernel modules are small pieces of compiled code which can be inserted in the running kernel, rather than being @@ -236,6 +237,10 @@ choice possible to load a signed module containing the algorithm to check the signature on that module. +config MODULE_SIG_SHA1 + bool "Sign modules with SHA-1" + select CRYPTO_SHA1 + config MODULE_SIG_SHA256 bool "Sign modules with SHA-256" select CRYPTO_SHA256 @@ -265,6 +270,7 @@ endchoice config MODULE_SIG_HASH string depends on MODULE_SIG || IMA_APPRAISE_MODSIG + default "sha1" if MODULE_SIG_SHA1 default "sha256" if MODULE_SIG_SHA256 default "sha384" if MODULE_SIG_SHA384 default "sha512" if MODULE_SIG_SHA512 @@ -387,7 +393,7 @@ config UNUSED_KSYMS_WHITELIST exported at all times, even in absence of in-tree users. The value to set here is the path to a text file containing the list of symbols, one per line. The path can be absolute, or relative to the kernel - source tree. + source or obj tree. config MODULES_TREE_LOOKUP def_bool y diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index ef73ae7c8909..62fb57bb9f16 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -348,7 +348,7 @@ const char *module_address_lookup(unsigned long addr, } /* Make a copy in here where it's safe */ if (ret) { - strncpy(namebuf, ret, KSYM_NAME_LEN - 1); + strscpy(namebuf, ret, KSYM_NAME_LEN); ret = namebuf; } preempt_enable(); diff --git a/kernel/module/main.c b/kernel/module/main.c index e1e8a7a9d6c1..d18a94b973e1 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -56,7 +56,9 @@ #include <linux/dynamic_debug.h> #include <linux/audit.h> #include <linux/cfi.h> +#include <linux/codetag.h> #include <linux/debugfs.h> +#include <linux/execmem.h> #include <uapi/linux/module.h> #include "internal.h" @@ -1179,16 +1181,6 @@ resolve_symbol_wait(struct module *mod, return ksym; } -void __weak module_memfree(void *module_region) -{ - /* - * This memory may be RO, and freeing RO memory in an interrupt is not - * supported by vmalloc. - */ - WARN_ON(in_interrupt()); - vfree(module_region); -} - void __weak module_arch_cleanup(struct module *mod) { } @@ -1197,28 +1189,54 @@ void __weak module_arch_freeing_init(struct module *mod) { } -static bool mod_mem_use_vmalloc(enum mod_mem_type type) +static int module_memory_alloc(struct module *mod, enum mod_mem_type type) { - return IS_ENABLED(CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC) && - mod_mem_type_is_core_data(type); -} + unsigned int size = PAGE_ALIGN(mod->mem[type].size); + enum execmem_type execmem_type; + void *ptr; -static void *module_memory_alloc(unsigned int size, enum mod_mem_type type) -{ - if (mod_mem_use_vmalloc(type)) - return vzalloc(size); - return module_alloc(size); + mod->mem[type].size = size; + + if (mod_mem_type_is_data(type)) + execmem_type = EXECMEM_MODULE_DATA; + else + execmem_type = EXECMEM_MODULE_TEXT; + + ptr = execmem_alloc(execmem_type, size); + if (!ptr) + return -ENOMEM; + + /* + * The pointer to these blocks of memory are stored on the module + * structure and we keep that around so long as the module is + * around. We only free that memory when we unload the module. + * Just mark them as not being a leak then. The .init* ELF + * sections *do* get freed after boot so we *could* treat them + * slightly differently with kmemleak_ignore() and only grey + * them out as they work as typical memory allocations which + * *do* eventually get freed, but let's just keep things simple + * and avoid *any* false positives. + */ + kmemleak_not_leak(ptr); + + memset(ptr, 0, size); + mod->mem[type].base = ptr; + + return 0; } -static void module_memory_free(void *ptr, enum mod_mem_type type) +static void module_memory_free(struct module *mod, enum mod_mem_type type, + bool unload_codetags) { - if (mod_mem_use_vmalloc(type)) - vfree(ptr); - else - module_memfree(ptr); + void *ptr = mod->mem[type].base; + + if (!unload_codetags && mod_mem_type_is_core_data(type)) + return; + + execmem_free(ptr); } -static void free_mod_mem(struct module *mod) +static void free_mod_mem(struct module *mod, bool unload_codetags) { for_each_mod_mem_type(type) { struct module_memory *mod_mem = &mod->mem[type]; @@ -1229,19 +1247,26 @@ static void free_mod_mem(struct module *mod) /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod_mem->base, mod_mem->size); if (mod_mem->size) - module_memory_free(mod_mem->base, type); + module_memory_free(mod, type, unload_codetags); } /* MOD_DATA hosts mod, so free it at last */ lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size); - module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA); + module_memory_free(mod, MOD_DATA, unload_codetags); } /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { + bool unload_codetags; + trace_module_free(mod); + unload_codetags = codetag_unload_module(mod); + if (!unload_codetags) + pr_warn("%s: memory allocation(s) from the module still alive, cannot unload cleanly\n", + mod->name); + mod_sysfs_teardown(mod); /* @@ -1283,7 +1308,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - free_mod_mem(mod); + free_mod_mem(mod, unload_codetags); } void *__symbol_get(const char *symbol) @@ -1610,13 +1635,6 @@ static void free_modinfo(struct module *mod) } } -void * __weak module_alloc(unsigned long size) -{ - return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, - NUMA_NO_NODE, __builtin_return_address(0)); -} - bool __weak module_init_section(const char *name) { return strstarts(name, ".init"); @@ -2225,7 +2243,6 @@ static int find_module_sections(struct module *mod, struct load_info *info) static int move_module(struct module *mod, struct load_info *info) { int i; - void *ptr; enum mod_mem_type t = 0; int ret = -ENOMEM; @@ -2234,26 +2251,12 @@ static int move_module(struct module *mod, struct load_info *info) mod->mem[type].base = NULL; continue; } - mod->mem[type].size = PAGE_ALIGN(mod->mem[type].size); - ptr = module_memory_alloc(mod->mem[type].size, type); - /* - * The pointer to these blocks of memory are stored on the module - * structure and we keep that around so long as the module is - * around. We only free that memory when we unload the module. - * Just mark them as not being a leak then. The .init* ELF - * sections *do* get freed after boot so we *could* treat them - * slightly differently with kmemleak_ignore() and only grey - * them out as they work as typical memory allocations which - * *do* eventually get freed, but let's just keep things simple - * and avoid *any* false positives. - */ - kmemleak_not_leak(ptr); - if (!ptr) { + + ret = module_memory_alloc(mod, type); + if (ret) { t = type; goto out_enomem; } - memset(ptr, 0, mod->mem[type].size); - mod->mem[type].base = ptr; } /* Transfer each section which specifies SHF_ALLOC */ @@ -2296,7 +2299,7 @@ static int move_module(struct module *mod, struct load_info *info) return 0; out_enomem: for (t--; t >= 0; t--) - module_memory_free(mod->mem[t].base, t); + module_memory_free(mod, t, true); return ret; } @@ -2426,7 +2429,7 @@ static void module_deallocate(struct module *mod, struct load_info *info) percpu_modfree(mod); module_arch_freeing_init(mod); - free_mod_mem(mod); + free_mod_mem(mod, true); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -2482,9 +2485,9 @@ static void do_free_init(struct work_struct *w) llist_for_each_safe(pos, n, list) { initfree = container_of(pos, struct mod_initfree, node); - module_memfree(initfree->init_text); - module_memfree(initfree->init_data); - module_memfree(initfree->init_rodata); + execmem_free(initfree->init_text); + execmem_free(initfree->init_data); + execmem_free(initfree->init_rodata); kfree(initfree); } } @@ -2594,10 +2597,10 @@ static noinline int do_init_module(struct module *mod) * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we * call synchronize_rcu(), but we don't want to slow down the success - * path. module_memfree() cannot be called in an interrupt, so do the + * path. execmem_free() cannot be called in an interrupt, so do the * work and call synchronize_rcu() in a work queue. * - * Note that module_alloc() on most architectures creates W+X page + * Note that execmem_alloc() on most architectures creates W+X page * mappings which won't be cleaned up until do_free_init() runs. Any * code such as mark_rodata_ro() which depends on those mappings to * be cleaned up needs to sync with the queued work by invoking @@ -2995,6 +2998,8 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Get rid of temporary copy. */ free_copy(info, flags); + codetag_load_module(mod); + /* Done! */ trace_module_load(mod); diff --git a/kernel/padata.c b/kernel/padata.c index e3f639ff1670..53f4bc912712 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -106,7 +106,7 @@ static int __init padata_work_alloc_mt(int nworks, void *data, { int i; - spin_lock(&padata_works_lock); + spin_lock_bh(&padata_works_lock); /* Start at 1 because the current task participates in the job. */ for (i = 1; i < nworks; ++i) { struct padata_work *pw = padata_work_alloc(); @@ -116,7 +116,7 @@ static int __init padata_work_alloc_mt(int nworks, void *data, padata_work_init(pw, padata_mt_helper, data, 0); list_add(&pw->pw_list, head); } - spin_unlock(&padata_works_lock); + spin_unlock_bh(&padata_works_lock); return i; } @@ -134,12 +134,12 @@ static void __init padata_works_free(struct list_head *works) if (list_empty(works)) return; - spin_lock(&padata_works_lock); + spin_lock_bh(&padata_works_lock); list_for_each_entry_safe(cur, next, works, pw_list) { list_del(&cur->pw_list); padata_work_free(cur); } - spin_unlock(&padata_works_lock); + spin_unlock_bh(&padata_works_lock); } static void padata_parallel_worker(struct work_struct *parallel_work) diff --git a/kernel/panic.c b/kernel/panic.c index 747c3f3d289a..8bff183d6180 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -100,7 +100,6 @@ static struct ctl_table kern_panic_table[] = { .mode = 0644, .proc_handler = proc_douintvec, }, - { } }; static __init int kernel_panic_sysctls_init(void) diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 7ade20e95232..dc48fecfa1dc 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -307,7 +307,6 @@ static struct ctl_table pid_ns_ctl_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = &pid_max, }, - { } }; #endif /* CONFIG_CHECKPOINT_RESTORE */ diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h index 2ee41a3a1dfd..fe9fb991dc42 100644 --- a/kernel/pid_sysctl.h +++ b/kernel/pid_sysctl.h @@ -41,7 +41,6 @@ static struct ctl_table pid_ns_ctl_table_vm[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, - { } }; static inline void register_pid_ns_sysctl_table_vm(void) { diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 9e1c9aa399ea..927cc55ba0b3 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -674,23 +674,15 @@ void em_dev_unregister_perf_domain(struct device *dev) } EXPORT_SYMBOL_GPL(em_dev_unregister_perf_domain); -/* - * Adjustment of CPU performance values after boot, when all CPUs capacites - * are correctly calculated. - */ -static void em_adjust_new_capacity(struct device *dev, - struct em_perf_domain *pd, - u64 max_cap) +static struct em_perf_table __rcu *em_table_dup(struct em_perf_domain *pd) { struct em_perf_table __rcu *em_table; struct em_perf_state *ps, *new_ps; - int ret, ps_size; + int ps_size; em_table = em_table_alloc(pd); - if (!em_table) { - dev_warn(dev, "EM: allocation failed\n"); - return; - } + if (!em_table) + return NULL; new_ps = em_table->state; @@ -702,24 +694,52 @@ static void em_adjust_new_capacity(struct device *dev, rcu_read_unlock(); - em_init_performance(dev, pd, new_ps, pd->nr_perf_states); - ret = em_compute_costs(dev, new_ps, NULL, pd->nr_perf_states, + return em_table; +} + +static int em_recalc_and_update(struct device *dev, struct em_perf_domain *pd, + struct em_perf_table __rcu *em_table) +{ + int ret; + + ret = em_compute_costs(dev, em_table->state, NULL, pd->nr_perf_states, pd->flags); - if (ret) { - dev_warn(dev, "EM: compute costs failed\n"); - return; - } + if (ret) + goto free_em_table; ret = em_dev_update_perf_domain(dev, em_table); if (ret) - dev_warn(dev, "EM: update failed %d\n", ret); + goto free_em_table; /* * This is one-time-update, so give up the ownership in this updater. * The EM framework has incremented the usage counter and from now * will keep the reference (then free the memory when needed). */ +free_em_table: em_table_free(em_table); + return ret; +} + +/* + * Adjustment of CPU performance values after boot, when all CPUs capacites + * are correctly calculated. + */ +static void em_adjust_new_capacity(struct device *dev, + struct em_perf_domain *pd, + u64 max_cap) +{ + struct em_perf_table __rcu *em_table; + + em_table = em_table_dup(pd); + if (!em_table) { + dev_warn(dev, "EM: allocation failed\n"); + return; + } + + em_init_performance(dev, pd, em_table->state, pd->nr_perf_states); + + em_recalc_and_update(dev, pd, em_table); } static void em_check_capacity_update(void) @@ -788,3 +808,51 @@ static void em_update_workfn(struct work_struct *work) { em_check_capacity_update(); } + +/** + * em_dev_update_chip_binning() - Update Energy Model after the new voltage + * information is present in the OPPs. + * @dev : Device for which the Energy Model has to be updated. + * + * This function allows to update easily the EM with new values available in + * the OPP framework and DT. It can be used after the chip has been properly + * verified by device drivers and the voltages adjusted for the 'chip binning'. + */ +int em_dev_update_chip_binning(struct device *dev) +{ + struct em_perf_table __rcu *em_table; + struct em_perf_domain *pd; + int i, ret; + + if (IS_ERR_OR_NULL(dev)) + return -EINVAL; + + pd = em_pd_get(dev); + if (!pd) { + dev_warn(dev, "Couldn't find Energy Model\n"); + return -EINVAL; + } + + em_table = em_table_dup(pd); + if (!em_table) { + dev_warn(dev, "EM: allocation failed\n"); + return -ENOMEM; + } + + /* Update power values which might change due to new voltage in OPPs */ + for (i = 0; i < pd->nr_perf_states; i++) { + unsigned long freq = em_table->state[i].frequency; + unsigned long power; + + ret = dev_pm_opp_calc_power(dev, &power, &freq); + if (ret) { + em_table_free(em_table); + return ret; + } + + em_table->state[i].power = power; + } + + return em_recalc_and_update(dev, pd, em_table); +} +EXPORT_SYMBOL_GPL(em_dev_update_chip_binning); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 43b1a82e800c..0a213f69a9e4 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1361,7 +1361,7 @@ static int __init resume_setup(char *str) if (noresume) return 1; - strncpy(resume_file, str, 255); + strscpy(resume_file, str); return 1; } diff --git a/kernel/power/process.c b/kernel/power/process.c index cae81a87cc91..66ac067d9ae6 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -194,8 +194,6 @@ void thaw_processes(void) __usermodehelper_set_disable_depth(UMH_FREEZING); thaw_workqueues(); - cpuset_wait_for_hotplug(); - read_lock(&tasklist_lock); for_each_process_thread(g, p) { /* No other threads should have PF_SUSPEND_TASK set */ diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index e3ae93bbcb9b..09f8397bae15 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 5bc04bfe2db1..d9abb7ab031d 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -368,11 +368,7 @@ static int swsusp_swap_check(void) if (IS_ERR(hib_resume_bdev_file)) return PTR_ERR(hib_resume_bdev_file); - res = set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE); - if (res < 0) - fput(hib_resume_bdev_file); - - return res; + return 0; } /** @@ -1574,7 +1570,6 @@ int swsusp_check(bool exclusive) hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device, BLK_OPEN_READ, holder, NULL); if (!IS_ERR(hib_resume_bdev_file)) { - set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE); clear_page(swsusp_header); error = hib_submit_io(REQ_OP_READ, swsusp_resume_block, swsusp_header, NULL); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ca5146006b94..3160d287d4cf 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -178,9 +178,9 @@ static int __init control_devkmsg(char *str) * Set sysctl string accordingly: */ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) - strcpy(devkmsg_log_str, "on"); + strscpy(devkmsg_log_str, "on"); else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) - strcpy(devkmsg_log_str, "off"); + strscpy(devkmsg_log_str, "off"); /* else "ratelimit" which is set by default. */ /* @@ -209,7 +209,7 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, return -EINVAL; old = devkmsg_log; - strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE); + strscpy(old_str, devkmsg_log_str); } err = proc_dostring(table, write, buffer, lenp, ppos); @@ -227,7 +227,7 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, /* ... and restore old setting. */ devkmsg_log = old; - strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE); + strscpy(devkmsg_log_str, old_str); return -EINVAL; } @@ -2009,6 +2009,12 @@ static int console_trylock_spinning(void) */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); + /* + * Update @console_may_schedule for trylock because the previous + * owner may have been schedulable. + */ + console_may_schedule = 0; + return 1; } @@ -2500,22 +2506,22 @@ static int __init console_setup(char *str) /* * Decode str into name, index, options. */ - if (str[0] >= '0' && str[0] <= '9') { - strcpy(buf, "ttyS"); - strncpy(buf + 4, str, sizeof(buf) - 5); - } else { - strncpy(buf, str, sizeof(buf) - 1); - } - buf[sizeof(buf) - 1] = 0; + if (isdigit(str[0])) + scnprintf(buf, sizeof(buf), "ttyS%s", str); + else + strscpy(buf, str); + options = strchr(str, ','); if (options) *(options++) = 0; + #ifdef __sparc__ if (!strcmp(str, "ttya")) - strcpy(buf, "ttyS0"); + strscpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) - strcpy(buf, "ttyS1"); + strscpy(buf, "ttyS1"); #endif + for (s = buf; *s; s++) if (isdigit(*s) || *s == ',') break; diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index c228343eeb97..3e47dedce9e5 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -76,7 +76,6 @@ static struct ctl_table printk_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, - {} }; void __init printk_sysctl_init(void) diff --git a/kernel/profile.c b/kernel/profile.c index 8a77769bc4b4..2b775cc5c28f 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -344,49 +344,6 @@ void profile_tick(int type) #include <linux/seq_file.h> #include <linux/uaccess.h> -static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); - return 0; -} - -static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, prof_cpu_mask_proc_show, NULL); -} - -static ssize_t prof_cpu_mask_proc_write(struct file *file, - const char __user *buffer, size_t count, loff_t *pos) -{ - cpumask_var_t new_value; - int err; - - if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) - return -ENOMEM; - - err = cpumask_parse_user(buffer, count, new_value); - if (!err) { - cpumask_copy(prof_cpu_mask, new_value); - err = count; - } - free_cpumask_var(new_value); - return err; -} - -static const struct proc_ops prof_cpu_mask_proc_ops = { - .proc_open = prof_cpu_mask_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = single_release, - .proc_write = prof_cpu_mask_proc_write, -}; - -void create_prof_cpu_mask(void) -{ - /* create /proc/irq/prof_cpu_mask */ - proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops); -} - /* * This function accesses profiling information. The returned data is * binary: the sampling step and the actual contents of the profile diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index e7d2dd267593..3e079de0f5b4 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -31,7 +31,7 @@ config PREEMPT_RCU config TINY_RCU bool - default y if !PREEMPTION && !SMP + default y if !PREEMPT_RCU && !SMP help This option selects the RCU implementation that is designed for UP systems from which real-time response @@ -85,9 +85,13 @@ config FORCE_TASKS_RCU idle, and user-mode execution as quiescent states. Not for manual selection in most cases. -config TASKS_RCU +config NEED_TASKS_RCU bool default n + +config TASKS_RCU + bool + default NEED_TASKS_RCU && (PREEMPTION || PREEMPT_AUTO) select IRQ_WORK config FORCE_TASKS_RUDE_RCU diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 86fce206560e..38238e595a61 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -522,12 +522,18 @@ static inline void show_rcu_tasks_gp_kthreads(void) {} #ifdef CONFIG_TASKS_RCU struct task_struct *get_rcu_tasks_gp_kthread(void); +void rcu_tasks_get_gp_data(int *flags, unsigned long *gp_seq); #endif // # ifdef CONFIG_TASKS_RCU #ifdef CONFIG_TASKS_RUDE_RCU struct task_struct *get_rcu_tasks_rude_gp_kthread(void); +void rcu_tasks_rude_get_gp_data(int *flags, unsigned long *gp_seq); #endif // # ifdef CONFIG_TASKS_RUDE_RCU +#ifdef CONFIG_TASKS_TRACE_RCU +void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq); +#endif + #ifdef CONFIG_TASKS_RCU_GENERIC void tasks_cblist_init_generic(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ @@ -557,8 +563,7 @@ static inline void rcu_set_jiffies_lazy_flush(unsigned long j) { } #endif #if defined(CONFIG_TREE_RCU) -void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gp_seq); +void rcutorture_get_gp_data(int *flags, unsigned long *gp_seq); void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, @@ -566,8 +571,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename, unsigned long c); void rcu_gp_set_torture_wait(int duration); #else -static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, - int *flags, unsigned long *gp_seq) +static inline void rcutorture_get_gp_data(int *flags, unsigned long *gp_seq) { *flags = 0; *gp_seq = 0; @@ -587,20 +591,16 @@ static inline void rcu_gp_set_torture_wait(int duration) { } #ifdef CONFIG_TINY_SRCU -static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, +static inline void srcutorture_get_gp_data(struct srcu_struct *sp, int *flags, unsigned long *gp_seq) { - if (test_type != SRCU_FLAVOR) - return; *flags = 0; *gp_seq = sp->srcu_idx; } #elif defined(CONFIG_TREE_SRCU) -void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, +void srcutorture_get_gp_data(struct srcu_struct *sp, int *flags, unsigned long *gp_seq); #endif diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 45d6b4c3d199..807fbf6123a7 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -381,6 +381,9 @@ struct rcu_torture_ops { void (*gp_kthread_dbg)(void); bool (*check_boost_failed)(unsigned long gp_state, int *cpup); int (*stall_dur)(void); + void (*get_gp_data)(int *flags, unsigned long *gp_seq); + void (*gp_slow_register)(atomic_t *rgssp); + void (*gp_slow_unregister)(atomic_t *rgssp); long cbflood_max; int irq_capable; int can_boost; @@ -461,12 +464,13 @@ rcu_torture_pipe_update_one(struct rcu_torture *rp) WRITE_ONCE(rp->rtort_chkp, NULL); smp_store_release(&rtrcp->rtc_ready, 1); // Pair with smp_load_acquire(). } - i = READ_ONCE(rp->rtort_pipe_count); + i = rp->rtort_pipe_count; if (i > RCU_TORTURE_PIPE_LEN) i = RCU_TORTURE_PIPE_LEN; atomic_inc(&rcu_torture_wcount[i]); WRITE_ONCE(rp->rtort_pipe_count, i + 1); - if (rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { + ASSERT_EXCLUSIVE_WRITER(rp->rtort_pipe_count); + if (i + 1 >= RCU_TORTURE_PIPE_LEN) { rp->rtort_mbtest = 0; return true; } @@ -564,10 +568,12 @@ static struct rcu_torture_ops rcu_ops = { .call = call_rcu_hurry, .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, - .stats = NULL, .gp_kthread_dbg = show_rcu_gp_kthreads, .check_boost_failed = rcu_check_boost_fail, .stall_dur = rcu_jiffies_till_stall_check, + .get_gp_data = rcutorture_get_gp_data, + .gp_slow_register = rcu_gp_slow_register, + .gp_slow_unregister = rcu_gp_slow_unregister, .irq_capable = 1, .can_boost = IS_ENABLED(CONFIG_RCU_BOOST), .extendables = RCUTORTURE_MAX_EXTEND, @@ -611,9 +617,6 @@ static struct rcu_torture_ops rcu_busted_ops = { .sync = synchronize_rcu_busted, .exp_sync = synchronize_rcu_busted, .call = call_rcu_busted, - .cb_barrier = NULL, - .fqs = NULL, - .stats = NULL, .irq_capable = 1, .name = "busted" }; @@ -627,6 +630,11 @@ static struct srcu_struct srcu_ctld; static struct srcu_struct *srcu_ctlp = &srcu_ctl; static struct rcu_torture_ops srcud_ops; +static void srcu_get_gp_data(int *flags, unsigned long *gp_seq) +{ + srcutorture_get_gp_data(srcu_ctlp, flags, gp_seq); +} + static int srcu_torture_read_lock(void) { if (cur_ops == &srcud_ops) @@ -735,6 +743,7 @@ static struct rcu_torture_ops srcu_ops = { .call = srcu_torture_call, .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, + .get_gp_data = srcu_get_gp_data, .cbflood_max = 50000, .irq_capable = 1, .no_pi_lock = IS_ENABLED(CONFIG_TINY_SRCU), @@ -773,6 +782,7 @@ static struct rcu_torture_ops srcud_ops = { .call = srcu_torture_call, .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, + .get_gp_data = srcu_get_gp_data, .cbflood_max = 50000, .irq_capable = 1, .no_pi_lock = IS_ENABLED(CONFIG_TINY_SRCU), @@ -837,8 +847,6 @@ static struct rcu_torture_ops trivial_ops = { .get_gp_seq = rcu_no_completed, .sync = synchronize_rcu_trivial, .exp_sync = synchronize_rcu_trivial, - .fqs = NULL, - .stats = NULL, .irq_capable = 1, .name = "trivial" }; @@ -881,8 +889,7 @@ static struct rcu_torture_ops tasks_ops = { .call = call_rcu_tasks, .cb_barrier = rcu_barrier_tasks, .gp_kthread_dbg = show_rcu_tasks_classic_gp_kthread, - .fqs = NULL, - .stats = NULL, + .get_gp_data = rcu_tasks_get_gp_data, .irq_capable = 1, .slow_gps = 1, .name = "tasks" @@ -921,9 +928,8 @@ static struct rcu_torture_ops tasks_rude_ops = { .call = call_rcu_tasks_rude, .cb_barrier = rcu_barrier_tasks_rude, .gp_kthread_dbg = show_rcu_tasks_rude_gp_kthread, + .get_gp_data = rcu_tasks_rude_get_gp_data, .cbflood_max = 50000, - .fqs = NULL, - .stats = NULL, .irq_capable = 1, .name = "tasks-rude" }; @@ -973,9 +979,8 @@ static struct rcu_torture_ops tasks_tracing_ops = { .call = call_rcu_tasks_trace, .cb_barrier = rcu_barrier_tasks_trace, .gp_kthread_dbg = show_rcu_tasks_trace_gp_kthread, + .get_gp_data = rcu_tasks_trace_get_gp_data, .cbflood_max = 50000, - .fqs = NULL, - .stats = NULL, .irq_capable = 1, .slow_gps = 1, .name = "tasks-tracing" @@ -1399,6 +1404,7 @@ rcu_torture_writer(void *arg) if (rp == NULL) continue; rp->rtort_pipe_count = 0; + ASSERT_EXCLUSIVE_WRITER(rp->rtort_pipe_count); rcu_torture_writer_state = RTWS_DELAY; udelay(torture_random(&rand) & 0x3ff); rcu_torture_writer_state = RTWS_REPLACE; @@ -1414,6 +1420,7 @@ rcu_torture_writer(void *arg) atomic_inc(&rcu_torture_wcount[i]); WRITE_ONCE(old_rp->rtort_pipe_count, old_rp->rtort_pipe_count + 1); + ASSERT_EXCLUSIVE_WRITER(old_rp->rtort_pipe_count); // Make sure readers block polled grace periods. if (cur_ops->get_gp_state && cur_ops->poll_gp_state) { @@ -1586,7 +1593,8 @@ rcu_torture_writer(void *arg) if (list_empty(&rcu_tortures[i].rtort_free) && rcu_access_pointer(rcu_torture_current) != &rcu_tortures[i]) { tracing_off(); - show_rcu_gp_kthreads(); + if (cur_ops->gp_kthread_dbg) + cur_ops->gp_kthread_dbg(); WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count); rcu_ftrace_dump(DUMP_ALL); } @@ -1997,7 +2005,8 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) preempt_disable(); pipe_count = READ_ONCE(p->rtort_pipe_count); if (pipe_count > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ + // Should not happen in a correct RCU implementation, + // happens quite often for torture_type=busted. pipe_count = RCU_TORTURE_PIPE_LEN; } completed = cur_ops->get_gp_seq(); @@ -2259,10 +2268,8 @@ rcu_torture_stats_print(void) int __maybe_unused flags = 0; unsigned long __maybe_unused gp_seq = 0; - rcutorture_get_gp_data(cur_ops->ttype, - &flags, &gp_seq); - srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, - &flags, &gp_seq); + if (cur_ops->get_gp_data) + cur_ops->get_gp_data(&flags, &gp_seq); wtp = READ_ONCE(writer_task); pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#x cpu %d\n", rcu_torture_writer_state_getname(), @@ -2486,8 +2493,8 @@ static int rcu_torture_stall(void *args) preempt_disable(); pr_alert("%s start on CPU %d.\n", __func__, raw_smp_processor_id()); - while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(), - stop_at)) + while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(), stop_at) && + !kthread_should_stop()) if (stall_cpu_block) { #ifdef CONFIG_PREEMPTION preempt_schedule(); @@ -2832,13 +2839,14 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp) if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) && !shutdown_time_arrived()) { - WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED); - pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n", + if (WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED) && cur_ops->gp_kthread_dbg) + cur_ops->gp_kthread_dbg(); + pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld #online %u\n", __func__, stoppedat - rfp->rcu_fwd_startat, jiffies - stoppedat, n_launders + n_max_cbs - n_launders_cb_snap, n_launders, n_launders_sa, - n_max_gps, n_max_cbs, cver, gps); + n_max_gps, n_max_cbs, cver, gps, num_online_cpus()); atomic_long_add(n_max_cbs, &rcu_fwd_max_cbs); mutex_lock(&rcu_fwd_mutex); // Serialize histograms. rcu_torture_fwd_cb_hist(rfp); @@ -3040,11 +3048,12 @@ static void rcu_torture_barrier_cbf(struct rcu_head *rcu) } /* IPI handler to get callback posted on desired CPU, if online. */ -static void rcu_torture_barrier1cb(void *rcu_void) +static int rcu_torture_barrier1cb(void *rcu_void) { struct rcu_head *rhp = rcu_void; cur_ops->call(rhp, rcu_torture_barrier_cbf); + return 0; } /* kthread function to register callbacks used to test RCU barriers. */ @@ -3070,11 +3079,9 @@ static int rcu_torture_barrier_cbs(void *arg) * The above smp_load_acquire() ensures barrier_phase load * is ordered before the following ->call(). */ - if (smp_call_function_single(myid, rcu_torture_barrier1cb, - &rcu, 1)) { - // IPI failed, so use direct call from current CPU. + if (smp_call_on_cpu(myid, rcu_torture_barrier1cb, &rcu, 1)) cur_ops->call(&rcu, rcu_torture_barrier_cbf); - } + if (atomic_dec_and_test(&barrier_cbs_count)) wake_up(&barrier_wq); } while (!torture_must_stop()); @@ -3340,12 +3347,12 @@ rcu_torture_cleanup(void) pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier); cur_ops->cb_barrier(); } - rcu_gp_slow_unregister(NULL); + if (cur_ops->gp_slow_unregister) + cur_ops->gp_slow_unregister(NULL); return; } if (!cur_ops) { torture_cleanup_end(); - rcu_gp_slow_unregister(NULL); return; } @@ -3384,8 +3391,8 @@ rcu_torture_cleanup(void) fakewriter_tasks = NULL; } - rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq); - srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq); + if (cur_ops->get_gp_data) + cur_ops->get_gp_data(&flags, &gp_seq); pr_alert("%s: End-test grace-period state: g%ld f%#x total-gps=%ld\n", cur_ops->name, (long)gp_seq, flags, rcutorture_seq_diff(gp_seq, start_gp_seq)); @@ -3444,7 +3451,8 @@ rcu_torture_cleanup(void) else rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS"); torture_cleanup_end(); - rcu_gp_slow_unregister(&rcu_fwd_cb_nodelay); + if (cur_ops->gp_slow_unregister) + cur_ops->gp_slow_unregister(NULL); } #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD @@ -3756,8 +3764,8 @@ rcu_torture_init(void) nrealreaders = 1; } rcu_torture_print_module_parms(cur_ops, "Start of test"); - rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq); - srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq); + if (cur_ops->get_gp_data) + cur_ops->get_gp_data(&flags, &gp_seq); start_gp_seq = gp_seq; pr_alert("%s: Start-test grace-period state: g%ld f%#x\n", cur_ops->name, (long)gp_seq, flags); @@ -3926,7 +3934,8 @@ rcu_torture_init(void) if (object_debug) rcu_test_debug_objects(); torture_init_end(); - rcu_gp_slow_register(&rcu_fwd_cb_nodelay); + if (cur_ops->gp_slow_register && !WARN_ON_ONCE(!cur_ops->gp_slow_unregister)) + cur_ops->gp_slow_register(&rcu_fwd_cb_nodelay); return 0; unwind: diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index c38e5933a5d6..5afd5cf494db 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -96,9 +96,12 @@ EXPORT_SYMBOL_GPL(cleanup_srcu_struct); */ void __srcu_read_unlock(struct srcu_struct *ssp, int idx) { - int newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1; + int newval; + preempt_disable(); // Needed for PREEMPT_AUTO + newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval); + preempt_enable(); if (!newval && READ_ONCE(ssp->srcu_gp_waiting) && in_task()) swake_up_one(&ssp->srcu_wq); } @@ -117,8 +120,11 @@ void srcu_drive_gp(struct work_struct *wp) struct srcu_struct *ssp; ssp = container_of(wp, struct srcu_struct, srcu_work); - if (ssp->srcu_gp_running || ULONG_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max))) + preempt_disable(); // Needed for PREEMPT_AUTO + if (ssp->srcu_gp_running || ULONG_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max))) { return; /* Already running or nothing to do. */ + preempt_enable(); + } /* Remove recently arrived callbacks and wait for readers. */ WRITE_ONCE(ssp->srcu_gp_running, true); @@ -130,9 +136,12 @@ void srcu_drive_gp(struct work_struct *wp) idx = (ssp->srcu_idx & 0x2) / 2; WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1); WRITE_ONCE(ssp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ + preempt_enable(); swait_event_exclusive(ssp->srcu_wq, !READ_ONCE(ssp->srcu_lock_nesting[idx])); + preempt_disable(); // Needed for PREEMPT_AUTO WRITE_ONCE(ssp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1); + preempt_enable(); /* Invoke the callbacks we removed above. */ while (lh) { @@ -150,8 +159,11 @@ void srcu_drive_gp(struct work_struct *wp) * at interrupt level, but the ->srcu_gp_running checks will * straighten that out. */ + preempt_disable(); // Needed for PREEMPT_AUTO WRITE_ONCE(ssp->srcu_gp_running, false); - if (ULONG_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max))) + idx = ULONG_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)); + preempt_enable(); + if (idx) schedule_work(&ssp->srcu_work); } EXPORT_SYMBOL_GPL(srcu_drive_gp); @@ -160,9 +172,12 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp) { unsigned long cookie; + preempt_disable(); // Needed for PREEMPT_AUTO cookie = get_state_synchronize_srcu(ssp); - if (ULONG_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie)) + if (ULONG_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie)) { + preempt_enable(); return; + } WRITE_ONCE(ssp->srcu_idx_max, cookie); if (!READ_ONCE(ssp->srcu_gp_running)) { if (likely(srcu_init_done)) @@ -170,6 +185,7 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp) else if (list_empty(&ssp->srcu_work.entry)) list_add(&ssp->srcu_work.entry, &srcu_boot_list); } + preempt_enable(); } /* @@ -183,11 +199,13 @@ void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp, rhp->func = func; rhp->next = NULL; + preempt_disable(); // Needed for PREEMPT_AUTO local_irq_save(flags); *ssp->srcu_cb_tail = rhp; ssp->srcu_cb_tail = &rhp->next; local_irq_restore(flags); srcu_gp_start_if_needed(ssp); + preempt_enable(); } EXPORT_SYMBOL_GPL(call_srcu); @@ -241,9 +259,12 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_srcu); */ unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp) { - unsigned long ret = get_state_synchronize_srcu(ssp); + unsigned long ret; + preempt_disable(); // Needed for PREEMPT_AUTO + ret = get_state_synchronize_srcu(ssp); srcu_gp_start_if_needed(ssp); + preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index e4d673fc30f4..bc4b58b0204e 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -1826,12 +1826,9 @@ static void process_srcu(struct work_struct *work) srcu_reschedule(ssp, curdelay); } -void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *ssp, int *flags, +void srcutorture_get_gp_data(struct srcu_struct *ssp, int *flags, unsigned long *gp_seq) { - if (test_type != SRCU_FLAVOR) - return; *flags = 0; *gp_seq = rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq); } diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 86df878a2fee..6c2bd9001adc 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -122,7 +122,7 @@ void rcu_sync_enter(struct rcu_sync *rsp) * we are called at early boot time but this shouldn't happen. */ } - rsp->gp_count++; + WRITE_ONCE(rsp->gp_count, rsp->gp_count + 1); spin_unlock_irq(&rsp->rss_lock); if (gp_state == GP_IDLE) { @@ -151,11 +151,15 @@ void rcu_sync_enter(struct rcu_sync *rsp) */ void rcu_sync_exit(struct rcu_sync *rsp) { + int gpc; + WARN_ON_ONCE(READ_ONCE(rsp->gp_state) == GP_IDLE); WARN_ON_ONCE(READ_ONCE(rsp->gp_count) == 0); spin_lock_irq(&rsp->rss_lock); - if (!--rsp->gp_count) { + gpc = rsp->gp_count - 1; + WRITE_ONCE(rsp->gp_count, gpc); + if (!gpc) { if (rsp->gp_state == GP_PASSED) { WRITE_ONCE(rsp->gp_state, GP_EXIT); rcu_sync_call(rsp); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 147b5945d67a..e1bf33018e6d 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -74,6 +74,7 @@ struct rcu_tasks_percpu { * @holdouts_func: This flavor's holdout-list scan function (optional). * @postgp_func: This flavor's post-grace-period function (optional). * @call_func: This flavor's call_rcu()-equivalent function. + * @wait_state: Task state for synchronous grace-period waits (default TASK_UNINTERRUPTIBLE). * @rtpcpu: This flavor's rcu_tasks_percpu structure. * @percpu_enqueue_shift: Shift down CPU ID this much when enqueuing callbacks. * @percpu_enqueue_lim: Number of per-CPU callback queues in use for enqueuing. @@ -107,6 +108,7 @@ struct rcu_tasks { holdouts_func_t holdouts_func; postgp_func_t postgp_func; call_rcu_func_t call_func; + unsigned int wait_state; struct rcu_tasks_percpu __percpu *rtpcpu; int percpu_enqueue_shift; int percpu_enqueue_lim; @@ -134,6 +136,7 @@ static struct rcu_tasks rt_name = \ .tasks_gp_mutex = __MUTEX_INITIALIZER(rt_name.tasks_gp_mutex), \ .gp_func = gp, \ .call_func = call, \ + .wait_state = TASK_UNINTERRUPTIBLE, \ .rtpcpu = &rt_name ## __percpu, \ .lazy_jiffies = DIV_ROUND_UP(HZ, 4), \ .name = n, \ @@ -147,7 +150,7 @@ static struct rcu_tasks rt_name = \ #ifdef CONFIG_TASKS_RCU -/* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */ +/* Report delay of scan exiting tasklist in rcu_tasks_postscan(). */ static void tasks_rcu_exit_srcu_stall(struct timer_list *unused); static DEFINE_TIMER(tasks_rcu_exit_srcu_stall_timer, tasks_rcu_exit_srcu_stall); #endif @@ -638,7 +641,7 @@ static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp) // If the grace-period kthread is running, use it. if (READ_ONCE(rtp->kthread_ptr)) { - wait_rcu_gp(rtp->call_func); + wait_rcu_gp_state(rtp->wait_state, rtp->call_func); return; } rcu_tasks_one_gp(rtp, true); @@ -1160,6 +1163,7 @@ static int __init rcu_spawn_tasks_kthread(void) rcu_tasks.postscan_func = rcu_tasks_postscan; rcu_tasks.holdouts_func = check_all_holdout_tasks; rcu_tasks.postgp_func = rcu_tasks_postgp; + rcu_tasks.wait_state = TASK_IDLE; rcu_spawn_tasks_kthread_generic(&rcu_tasks); return 0; } @@ -1178,6 +1182,13 @@ struct task_struct *get_rcu_tasks_gp_kthread(void) } EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread); +void rcu_tasks_get_gp_data(int *flags, unsigned long *gp_seq) +{ + *flags = 0; + *gp_seq = rcu_seq_current(&rcu_tasks.tasks_gp_seq); +} +EXPORT_SYMBOL_GPL(rcu_tasks_get_gp_data); + /* * Protect against tasklist scan blind spot while the task is exiting and * may be removed from the tasklist. Do this by adding the task to yet @@ -1199,8 +1210,7 @@ void exit_tasks_rcu_start(void) rtpcp = this_cpu_ptr(rcu_tasks.rtpcpu); t->rcu_tasks_exit_cpu = smp_processor_id(); raw_spin_lock_irqsave_rcu_node(rtpcp, flags); - if (!rtpcp->rtp_exit_list.next) - INIT_LIST_HEAD(&rtpcp->rtp_exit_list); + WARN_ON_ONCE(!rtpcp->rtp_exit_list.next); list_add(&t->rcu_tasks_exit_list, &rtpcp->rtp_exit_list); raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); preempt_enable(); @@ -1358,6 +1368,13 @@ struct task_struct *get_rcu_tasks_rude_gp_kthread(void) } EXPORT_SYMBOL_GPL(get_rcu_tasks_rude_gp_kthread); +void rcu_tasks_rude_get_gp_data(int *flags, unsigned long *gp_seq) +{ + *flags = 0; + *gp_seq = rcu_seq_current(&rcu_tasks_rude.tasks_gp_seq); +} +EXPORT_SYMBOL_GPL(rcu_tasks_rude_get_gp_data); + #endif /* #ifdef CONFIG_TASKS_RUDE_RCU */ //////////////////////////////////////////////////////////////////////// @@ -1457,6 +1474,7 @@ static void rcu_st_need_qs(struct task_struct *t, u8 v) /* * Do a cmpxchg() on ->trc_reader_special.b.need_qs, allowing for * the four-byte operand-size restriction of some platforms. + * * Returns the old value, which is often ignored. */ u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new) @@ -1468,7 +1486,14 @@ u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new) if (trs_old.b.need_qs != old) return trs_old.b.need_qs; trs_new.b.need_qs = new; - ret.s = cmpxchg(&t->trc_reader_special.s, trs_old.s, trs_new.s); + + // Although cmpxchg() appears to KCSAN to update all four bytes, + // only the .b.need_qs byte actually changes. + instrument_atomic_read_write(&t->trc_reader_special.b.need_qs, + sizeof(t->trc_reader_special.b.need_qs)); + // Avoid false-positive KCSAN failures. + ret.s = data_race(cmpxchg(&t->trc_reader_special.s, trs_old.s, trs_new.s)); + return ret.b.need_qs; } EXPORT_SYMBOL_GPL(rcu_trc_cmpxchg_need_qs); @@ -1994,7 +2019,7 @@ void show_rcu_tasks_trace_gp_kthread(void) { char buf[64]; - sprintf(buf, "N%lu h:%lu/%lu/%lu", + snprintf(buf, sizeof(buf), "N%lu h:%lu/%lu/%lu", data_race(n_trc_holdouts), data_race(n_heavy_reader_ofl_updates), data_race(n_heavy_reader_updates), @@ -2010,6 +2035,13 @@ struct task_struct *get_rcu_tasks_trace_gp_kthread(void) } EXPORT_SYMBOL_GPL(get_rcu_tasks_trace_gp_kthread); +void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq) +{ + *flags = 0; + *gp_seq = rcu_seq_current(&rcu_tasks_trace.tasks_gp_seq); +} +EXPORT_SYMBOL_GPL(rcu_tasks_trace_get_gp_data); + #else /* #ifdef CONFIG_TASKS_TRACE_RCU */ static void exit_tasks_rcu_finish_trace(struct task_struct *t) { } #endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */ diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 705c0d16850a..4402d6f5f857 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -130,9 +130,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused next = list->next; prefetch(next); debug_rcu_head_unqueue(list); - local_bh_disable(); rcu_reclaim_tiny(list); - local_bh_enable(); list = next; } } @@ -155,7 +153,9 @@ void synchronize_rcu(void) lock_is_held(&rcu_lock_map) || lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_rcu() in RCU read-side critical section"); + preempt_disable(); WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2); + preempt_enable(); } EXPORT_SYMBOL_GPL(synchronize_rcu); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index d9642dd06c25..28c7031711a3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -75,6 +75,7 @@ #define MODULE_PARAM_PREFIX "rcutree." /* Data structures. */ +static void rcu_sr_normal_gp_cleanup_work(struct work_struct *); static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { .gpwrap = true, @@ -93,6 +94,8 @@ static struct rcu_state rcu_state = { .exp_mutex = __MUTEX_INITIALIZER(rcu_state.exp_mutex), .exp_wake_mutex = __MUTEX_INITIALIZER(rcu_state.exp_wake_mutex), .ofl_lock = __ARCH_SPIN_LOCK_UNLOCKED, + .srs_cleanup_work = __WORK_INITIALIZER(rcu_state.srs_cleanup_work, + rcu_sr_normal_gp_cleanup_work), }; /* Dump rcu_node combining tree at boot to verify correct setup. */ @@ -240,8 +243,36 @@ static long rcu_get_n_cbs_cpu(int cpu) return 0; } +/** + * rcu_softirq_qs - Provide a set of RCU quiescent states in softirq processing + * + * Mark a quiescent state for RCU, Tasks RCU, and Tasks Trace RCU. + * This is a special-purpose function to be used in the softirq + * infrastructure and perhaps the occasional long-running softirq + * handler. + * + * Note that from RCU's viewpoint, a call to rcu_softirq_qs() is + * equivalent to momentarily completely enabling preemption. For + * example, given this code:: + * + * local_bh_disable(); + * do_something(); + * rcu_softirq_qs(); // A + * do_something_else(); + * local_bh_enable(); // B + * + * A call to synchronize_rcu() that began concurrently with the + * call to do_something() would be guaranteed to wait only until + * execution reached statement A. Without that rcu_softirq_qs(), + * that same synchronize_rcu() would instead be guaranteed to wait + * until execution reached statement B. + */ void rcu_softirq_qs(void) { + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal rcu_softirq_qs() in RCU read-side critical section"); rcu_qs(); rcu_preempt_deferred_qs(current); rcu_tasks_qs(current, false); @@ -508,17 +539,10 @@ static struct rcu_node *rcu_get_root(void) /* * Send along grace-period-related data for rcutorture diagnostics. */ -void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gp_seq) +void rcutorture_get_gp_data(int *flags, unsigned long *gp_seq) { - switch (test_type) { - case RCU_FLAVOR: - *flags = READ_ONCE(rcu_state.gp_flags); - *gp_seq = rcu_seq_current(&rcu_state.gp_seq); - break; - default: - break; - } + *flags = READ_ONCE(rcu_state.gp_flags); + *gp_seq = rcu_seq_current(&rcu_state.gp_seq); } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); @@ -813,8 +837,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask); pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n", __func__, rdp->cpu, ".o"[rcu_rdp_cpu_online(rdp)], - (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, - (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_state, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_state); return 1; /* Break things loose after complaining. */ } @@ -1423,6 +1447,305 @@ static void rcu_poll_gp_seq_end_unlocked(unsigned long *snap) } /* + * There is a single llist, which is used for handling + * synchronize_rcu() users' enqueued rcu_synchronize nodes. + * Within this llist, there are two tail pointers: + * + * wait tail: Tracks the set of nodes, which need to + * wait for the current GP to complete. + * done tail: Tracks the set of nodes, for which grace + * period has elapsed. These nodes processing + * will be done as part of the cleanup work + * execution by a kworker. + * + * At every grace period init, a new wait node is added + * to the llist. This wait node is used as wait tail + * for this new grace period. Given that there are a fixed + * number of wait nodes, if all wait nodes are in use + * (which can happen when kworker callback processing + * is delayed) and additional grace period is requested. + * This means, a system is slow in processing callbacks. + * + * TODO: If a slow processing is detected, a first node + * in the llist should be used as a wait-tail for this + * grace period, therefore users which should wait due + * to a slow process are handled by _this_ grace period + * and not next. + * + * Below is an illustration of how the done and wait + * tail pointers move from one set of rcu_synchronize nodes + * to the other, as grace periods start and finish and + * nodes are processed by kworker. + * + * + * a. Initial llist callbacks list: + * + * +----------+ +--------+ +-------+ + * | | | | | | + * | head |---------> | cb2 |--------->| cb1 | + * | | | | | | + * +----------+ +--------+ +-------+ + * + * + * + * b. New GP1 Start: + * + * WAIT TAIL + * | + * | + * v + * +----------+ +--------+ +--------+ +-------+ + * | | | | | | | | + * | head ------> wait |------> cb2 |------> | cb1 | + * | | | head1 | | | | | + * +----------+ +--------+ +--------+ +-------+ + * + * + * + * c. GP completion: + * + * WAIT_TAIL == DONE_TAIL + * + * DONE TAIL + * | + * | + * v + * +----------+ +--------+ +--------+ +-------+ + * | | | | | | | | + * | head ------> wait |------> cb2 |------> | cb1 | + * | | | head1 | | | | | + * +----------+ +--------+ +--------+ +-------+ + * + * + * + * d. New callbacks and GP2 start: + * + * WAIT TAIL DONE TAIL + * | | + * | | + * v v + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * | | | | | | | | | | | | | | + * | head ------> wait |--->| cb4 |--->| cb3 |--->|wait |--->| cb2 |--->| cb1 | + * | | | head2| | | | | |head1| | | | | + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * + * + * + * e. GP2 completion: + * + * WAIT_TAIL == DONE_TAIL + * DONE TAIL + * | + * | + * v + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * | | | | | | | | | | | | | | + * | head ------> wait |--->| cb4 |--->| cb3 |--->|wait |--->| cb2 |--->| cb1 | + * | | | head2| | | | | |head1| | | | | + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * + * + * While the llist state transitions from d to e, a kworker + * can start executing rcu_sr_normal_gp_cleanup_work() and + * can observe either the old done tail (@c) or the new + * done tail (@e). So, done tail updates and reads need + * to use the rel-acq semantics. If the concurrent kworker + * observes the old done tail, the newly queued work + * execution will process the updated done tail. If the + * concurrent kworker observes the new done tail, then + * the newly queued work will skip processing the done + * tail, as workqueue semantics guarantees that the new + * work is executed only after the previous one completes. + * + * f. kworker callbacks processing complete: + * + * + * DONE TAIL + * | + * | + * v + * +----------+ +--------+ + * | | | | + * | head ------> wait | + * | | | head2 | + * +----------+ +--------+ + * + */ +static bool rcu_sr_is_wait_head(struct llist_node *node) +{ + return &(rcu_state.srs_wait_nodes)[0].node <= node && + node <= &(rcu_state.srs_wait_nodes)[SR_NORMAL_GP_WAIT_HEAD_MAX - 1].node; +} + +static struct llist_node *rcu_sr_get_wait_head(void) +{ + struct sr_wait_node *sr_wn; + int i; + + for (i = 0; i < SR_NORMAL_GP_WAIT_HEAD_MAX; i++) { + sr_wn = &(rcu_state.srs_wait_nodes)[i]; + + if (!atomic_cmpxchg_acquire(&sr_wn->inuse, 0, 1)) + return &sr_wn->node; + } + + return NULL; +} + +static void rcu_sr_put_wait_head(struct llist_node *node) +{ + struct sr_wait_node *sr_wn = container_of(node, struct sr_wait_node, node); + + atomic_set_release(&sr_wn->inuse, 0); +} + +/* Disabled by default. */ +static int rcu_normal_wake_from_gp; +module_param(rcu_normal_wake_from_gp, int, 0644); +static struct workqueue_struct *sync_wq; + +static void rcu_sr_normal_complete(struct llist_node *node) +{ + struct rcu_synchronize *rs = container_of( + (struct rcu_head *) node, struct rcu_synchronize, head); + unsigned long oldstate = (unsigned long) rs->head.func; + + WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && + !poll_state_synchronize_rcu(oldstate), + "A full grace period is not passed yet: %lu", + rcu_seq_diff(get_state_synchronize_rcu(), oldstate)); + + /* Finally. */ + complete(&rs->completion); +} + +static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work) +{ + struct llist_node *done, *rcu, *next, *head; + + /* + * This work execution can potentially execute + * while a new done tail is being updated by + * grace period kthread in rcu_sr_normal_gp_cleanup(). + * So, read and updates of done tail need to + * follow acq-rel semantics. + * + * Given that wq semantics guarantees that a single work + * cannot execute concurrently by multiple kworkers, + * the done tail list manipulations are protected here. + */ + done = smp_load_acquire(&rcu_state.srs_done_tail); + if (!done) + return; + + WARN_ON_ONCE(!rcu_sr_is_wait_head(done)); + head = done->next; + done->next = NULL; + + /* + * The dummy node, which is pointed to by the + * done tail which is acq-read above is not removed + * here. This allows lockless additions of new + * rcu_synchronize nodes in rcu_sr_normal_add_req(), + * while the cleanup work executes. The dummy + * nodes is removed, in next round of cleanup + * work execution. + */ + llist_for_each_safe(rcu, next, head) { + if (!rcu_sr_is_wait_head(rcu)) { + rcu_sr_normal_complete(rcu); + continue; + } + + rcu_sr_put_wait_head(rcu); + } +} + +/* + * Helper function for rcu_gp_cleanup(). + */ +static void rcu_sr_normal_gp_cleanup(void) +{ + struct llist_node *wait_tail, *next, *rcu; + int done = 0; + + wait_tail = rcu_state.srs_wait_tail; + if (wait_tail == NULL) + return; + + rcu_state.srs_wait_tail = NULL; + ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_wait_tail); + WARN_ON_ONCE(!rcu_sr_is_wait_head(wait_tail)); + + /* + * Process (a) and (d) cases. See an illustration. + */ + llist_for_each_safe(rcu, next, wait_tail->next) { + if (rcu_sr_is_wait_head(rcu)) + break; + + rcu_sr_normal_complete(rcu); + // It can be last, update a next on this step. + wait_tail->next = next; + + if (++done == SR_MAX_USERS_WAKE_FROM_GP) + break; + } + + // concurrent sr_normal_gp_cleanup work might observe this update. + smp_store_release(&rcu_state.srs_done_tail, wait_tail); + ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_done_tail); + + /* + * We schedule a work in order to perform a final processing + * of outstanding users(if still left) and releasing wait-heads + * added by rcu_sr_normal_gp_init() call. + */ + queue_work(sync_wq, &rcu_state.srs_cleanup_work); +} + +/* + * Helper function for rcu_gp_init(). + */ +static bool rcu_sr_normal_gp_init(void) +{ + struct llist_node *first; + struct llist_node *wait_head; + bool start_new_poll = false; + + first = READ_ONCE(rcu_state.srs_next.first); + if (!first || rcu_sr_is_wait_head(first)) + return start_new_poll; + + wait_head = rcu_sr_get_wait_head(); + if (!wait_head) { + // Kick another GP to retry. + start_new_poll = true; + return start_new_poll; + } + + /* Inject a wait-dummy-node. */ + llist_add(wait_head, &rcu_state.srs_next); + + /* + * A waiting list of rcu_synchronize nodes should be empty on + * this step, since a GP-kthread, rcu_gp_init() -> gp_cleanup(), + * rolls it over. If not, it is a BUG, warn a user. + */ + WARN_ON_ONCE(rcu_state.srs_wait_tail != NULL); + rcu_state.srs_wait_tail = wait_head; + ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_wait_tail); + + return start_new_poll; +} + +static void rcu_sr_normal_add_req(struct rcu_synchronize *rs) +{ + llist_add((struct llist_node *) &rs->head, &rcu_state.srs_next); +} + +/* * Initialize a new grace period. Return false if no grace period required. */ static noinline_for_stack bool rcu_gp_init(void) @@ -1432,10 +1755,11 @@ static noinline_for_stack bool rcu_gp_init(void) unsigned long mask; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(); + bool start_new_poll; WRITE_ONCE(rcu_state.gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); - if (!READ_ONCE(rcu_state.gp_flags)) { + if (!rcu_state.gp_flags) { /* Spurious wakeup, tell caller to go back to sleep. */ raw_spin_unlock_irq_rcu_node(rnp); return false; @@ -1456,11 +1780,25 @@ static noinline_for_stack bool rcu_gp_init(void) /* Record GP times before starting GP, hence rcu_seq_start(). */ rcu_seq_start(&rcu_state.gp_seq); ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq); + start_new_poll = rcu_sr_normal_gp_init(); trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start")); rcu_poll_gp_seq_start(&rcu_state.gp_seq_polled_snap); raw_spin_unlock_irq_rcu_node(rnp); /* + * The "start_new_poll" is set to true, only when this GP is not able + * to handle anything and there are outstanding users. It happens when + * the rcu_sr_normal_gp_init() function was not able to insert a dummy + * separator to the llist, because there were no left any dummy-nodes. + * + * Number of dummy-nodes is fixed, it could be that we are run out of + * them, if so we start a new pool request to repeat a try. It is rare + * and it means that a system is doing a slow processing of callbacks. + */ + if (start_new_poll) + (void) start_poll_synchronize_rcu(); + + /* * Apply per-leaf buffered online and offline operations to * the rcu_node tree. Note that this new grace period need not * wait for subsequent online CPUs, and that RCU hooks in the CPU @@ -1620,8 +1958,7 @@ static void rcu_gp_fqs(bool first_time) /* Clear flag to prevent immediate re-entry. */ if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_lock_irq_rcu_node(rnp); - WRITE_ONCE(rcu_state.gp_flags, - READ_ONCE(rcu_state.gp_flags) & ~RCU_GP_FLAG_FQS); + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags & ~RCU_GP_FLAG_FQS); raw_spin_unlock_irq_rcu_node(rnp); } } @@ -1825,6 +2162,9 @@ static noinline void rcu_gp_cleanup(void) } raw_spin_unlock_irq_rcu_node(rnp); + // Make synchronize_rcu() users aware of the end of old grace period. + rcu_sr_normal_gp_cleanup(); + // If strict, make all CPUs aware of the end of the old grace period. if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) on_each_cpu(rcu_strict_gp_boundary, NULL, 0); @@ -1882,8 +2222,7 @@ static void rcu_report_qs_rsp(unsigned long flags) { raw_lockdep_assert_held_rcu_node(rcu_get_root()); WARN_ON_ONCE(!rcu_gp_in_progress()); - WRITE_ONCE(rcu_state.gp_flags, - READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS); + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(), flags); rcu_gp_kthread_wake(); } @@ -2398,8 +2737,7 @@ void rcu_force_quiescent_state(void) raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); return; /* Someone beat us to it. */ } - WRITE_ONCE(rcu_state.gp_flags, - READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS); + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); rcu_gp_kthread_wake(); } @@ -3559,6 +3897,43 @@ static int rcu_blocking_is_gp(void) return true; } +/* + * Helper function for the synchronize_rcu() API. + */ +static void synchronize_rcu_normal(void) +{ + struct rcu_synchronize rs; + + trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request")); + + if (!READ_ONCE(rcu_normal_wake_from_gp)) { + wait_rcu_gp(call_rcu_hurry); + goto trace_complete_out; + } + + init_rcu_head_on_stack(&rs.head); + init_completion(&rs.completion); + + /* + * This code might be preempted, therefore take a GP + * snapshot before adding a request. + */ + if (IS_ENABLED(CONFIG_PROVE_RCU)) + rs.head.func = (void *) get_state_synchronize_rcu(); + + rcu_sr_normal_add_req(&rs); + + /* Kick a GP and start waiting. */ + (void) start_poll_synchronize_rcu(); + + /* Now we can wait. */ + wait_for_completion(&rs.completion); + destroy_rcu_head_on_stack(&rs.head); + +trace_complete_out: + trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("complete")); +} + /** * synchronize_rcu - wait until a grace period has elapsed. * @@ -3610,7 +3985,7 @@ void synchronize_rcu(void) if (rcu_gp_is_expedited()) synchronize_rcu_expedited(); else - wait_rcu_gp(call_rcu_hurry); + synchronize_rcu_normal(); return; } @@ -4303,7 +4678,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); // whether spinlocks may be acquired safely. static bool rcu_init_invoked(void) { - return !!rcu_state.n_online_cpus; + return !!READ_ONCE(rcu_state.n_online_cpus); } /* @@ -4395,9 +4770,9 @@ rcu_boot_init_percpu_data(int cpu) WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu))); rdp->barrier_seq_snap = rcu_state.barrier_sequence; rdp->rcu_ofl_gp_seq = rcu_state.gp_seq; - rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; + rdp->rcu_ofl_gp_state = RCU_GP_CLEANED; rdp->rcu_onl_gp_seq = rcu_state.gp_seq; - rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; + rdp->rcu_onl_gp_state = RCU_GP_CLEANED; rdp->last_sched_clock = jiffies; rdp->cpu = cpu; rcu_boot_init_nocb_percpu_data(rdp); @@ -4513,6 +4888,7 @@ int rcutree_prepare_cpu(unsigned int cpu) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); rcu_spawn_rnp_kthreads(rnp); rcu_spawn_cpu_nocb_kthread(cpu); + ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1); return 0; @@ -4656,7 +5032,7 @@ void rcutree_report_cpu_starting(unsigned int cpu) ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus); rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq); - rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags); + rdp->rcu_onl_gp_state = READ_ONCE(rcu_state.gp_state); /* An incoming CPU should never be blocking a grace period. */ if (WARN_ON_ONCE(rnp->qsmask & mask)) { /* RCU waiting on incoming CPU? */ @@ -4707,7 +5083,7 @@ void rcutree_report_cpu_dead(void) arch_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq); - rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags); + rdp->rcu_ofl_gp_state = READ_ONCE(rcu_state.gp_state); if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */ /* Report quiescent state -before- changing ->qsmaskinitnext! */ rcu_disable_urgency_upon_qs(rdp); @@ -4781,6 +5157,7 @@ void rcutree_migrate_callbacks(int cpu) */ int rcutree_dead_cpu(unsigned int cpu) { + ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1); // Stop-machine done, so allow nohz_full to disable tick. tick_dep_clear(TICK_DEP_BIT_RCU); @@ -5229,6 +5606,9 @@ void __init rcu_init(void) rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0); WARN_ON(!rcu_gp_wq); + sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM, 0); + WARN_ON(!sync_wq); + /* Fill in default value for rcutree.qovld boot parameter. */ /* -After- the rcu_node ->lock fields are initialized! */ if (qovld < 0) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index df48160b3136..bae7925c497f 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -273,9 +273,9 @@ struct rcu_data { bool rcu_iw_pending; /* Is ->rcu_iw pending? */ unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */ unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */ - short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */ + short rcu_ofl_gp_state; /* ->gp_state at last offline. */ unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */ - short rcu_onl_gp_flags; /* ->gp_flags at last online. */ + short rcu_onl_gp_state; /* ->gp_state at last online. */ unsigned long last_fqs_resched; /* Time of last rcu_resched(). */ unsigned long last_sched_clock; /* Jiffies of last rcu_sched_clock_irq(). */ struct rcu_snap_record snap_record; /* Snapshot of core stats at half of */ @@ -316,6 +316,19 @@ do { \ } while (0) /* + * A max threshold for synchronize_rcu() users which are + * awaken directly by the rcu_gp_kthread(). Left part is + * deferred to the main worker. + */ +#define SR_MAX_USERS_WAKE_FROM_GP 5 +#define SR_NORMAL_GP_WAIT_HEAD_MAX 5 + +struct sr_wait_node { + atomic_t inuse; + struct llist_node node; +}; + +/* * RCU global state, including node hierarchy. This hierarchy is * represented in "heap" form in a dense array. The root (first level) * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second @@ -400,6 +413,13 @@ struct rcu_state { /* Synchronize offline with */ /* GP pre-initialization. */ int nocb_is_setup; /* nocb is setup from boot */ + + /* synchronize_rcu() part. */ + struct llist_head srs_next; /* request a GP users. */ + struct llist_node *srs_wait_tail; /* wait for GP users. */ + struct llist_node *srs_done_tail; /* ready for GP users. */ + struct sr_wait_node srs_wait_nodes[SR_NORMAL_GP_WAIT_HEAD_MAX]; + struct work_struct srs_cleanup_work; }; /* Values for rcu_state structure's gp_flags field. */ diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 6b83537480b1..8a1d9c8bd9f7 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -930,7 +930,7 @@ void synchronize_rcu_expedited(void) /* If expedited grace periods are prohibited, fall back to normal. */ if (rcu_gp_is_normal()) { - wait_rcu_gp(call_rcu_hurry); + synchronize_rcu_normal(); return; } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 36a8b5dbf5b5..340bbefe5f65 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -805,8 +805,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) rdp = per_cpu_ptr(&rcu_data, cpu); pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n", cpu, ".o"[rcu_rdp_cpu_online(rdp)], - (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, - (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_state, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_state); } } diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 5d666428546b..460efecd077b 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -504,7 +504,8 @@ static void print_cpu_stall_info(int cpu) rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu)); rcuc_starved = rcu_is_rcuc_kthread_starving(rdp, &j); if (rcuc_starved) - sprintf(buf, " rcuc=%ld jiffies(starved)", j); + // Print signed value, as negative values indicate a probable bug. + snprintf(buf, sizeof(buf), " rcuc=%ld jiffies(starved)", j); pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%04x/%ld/%#lx softirq=%u/%u fqs=%ld%s%s\n", cpu, "O."[!!cpu_online(cpu)], @@ -579,7 +580,7 @@ static void rcu_check_gp_kthread_expired_fqs_timer(void) pr_err("%s kthread timer wakeup didn't happen for %ld jiffies! g%ld f%#x %s(%d) ->state=%#x\n", rcu_state.name, (jiffies - jiffies_fqs), (long)rcu_seq_current(&rcu_state.gp_seq), - data_race(rcu_state.gp_flags), + data_race(READ_ONCE(rcu_state.gp_flags)), // Diagnostic read gp_state_getname(RCU_GP_WAIT_FQS), RCU_GP_WAIT_FQS, data_race(READ_ONCE(gpk->__state))); pr_err("\tPossible timer handling issue on cpu=%d timer-softirq=%u\n", @@ -628,7 +629,8 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) totqlen += rcu_get_n_cbs_cpu(cpu); pr_err("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu ncpus=%d)\n", smp_processor_id(), (long)(jiffies - gps), - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, + data_race(rcu_state.n_online_cpus)); // Diagnostic read if (ndetected) { rcu_dump_cpu_stacks(); @@ -689,7 +691,8 @@ static void print_cpu_stall(unsigned long gps) totqlen += rcu_get_n_cbs_cpu(cpu); pr_err("\t(t=%lu jiffies g=%ld q=%lu ncpus=%d)\n", jiffies - gps, - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, + data_race(rcu_state.n_online_cpus)); // Diagnostic read rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 46aaaa9fe339..f8436969e0c8 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -408,7 +408,7 @@ void wakeme_after_rcu(struct rcu_head *head) } EXPORT_SYMBOL_GPL(wakeme_after_rcu); -void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, +void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array) { int i; @@ -440,7 +440,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, if (crcu_array[j] == crcu_array[i]) break; if (j == i) { - wait_for_completion(&rs_array[i].completion); + wait_for_completion_state(&rs_array[i].completion, state); destroy_rcu_head_on_stack(&rs_array[i].head); } } diff --git a/kernel/reboot.c b/kernel/reboot.c index 22c16e2564cc..f05dbde2c93f 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -1295,7 +1295,6 @@ static struct ctl_table kern_reboot_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static void __init kernel_reboot_sysctls_init(void) diff --git a/kernel/regset.c b/kernel/regset.c index 586823786f39..b2871fa68b2a 100644 --- a/kernel/regset.c +++ b/kernel/regset.c @@ -16,14 +16,14 @@ static int __regset_get(struct task_struct *target, if (size > regset->n * regset->size) size = regset->n * regset->size; if (!p) { - to_free = p = kzalloc(size, GFP_KERNEL); + to_free = p = kvzalloc(size, GFP_KERNEL); if (!p) return -ENOMEM; } res = regset->regset_get(target, regset, (struct membuf){.p = p, .left = size}); if (res < 0) { - kfree(to_free); + kvfree(to_free); return res; } *data = p; @@ -71,6 +71,6 @@ int copy_regset_to_user(struct task_struct *target, ret = regset_get_alloc(target, regset, size, &buf); if (ret > 0) ret = copy_to_user(data, buf, ret) ? -EFAULT : 0; - kfree(buf); + kvfree(buf); return ret; } diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 991fc9002535..db68a964e34e 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -19,7 +19,6 @@ static struct ctl_table sched_autogroup_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static void __init sched_autogroup_sysctl_init(void) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7019a40457a6..bcf2c4cc0522 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -108,7 +108,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp); -EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_hw_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); @@ -4741,7 +4741,6 @@ static struct ctl_table sched_core_sysctls[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - {} }; static int __init sched_core_sysctl_init(void) { @@ -5662,13 +5661,13 @@ static inline u64 cpu_resched_latency(struct rq *rq) { return 0; } * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. */ -void scheduler_tick(void) +void sched_tick(void) { int cpu = smp_processor_id(); struct rq *rq = cpu_rq(cpu); struct task_struct *curr = rq->curr; struct rq_flags rf; - unsigned long thermal_pressure; + unsigned long hw_pressure; u64 resched_latency; if (housekeeping_cpu(cpu, HK_TYPE_TICK)) @@ -5679,8 +5678,8 @@ void scheduler_tick(void) rq_lock(rq, &rf); update_rq_clock(rq); - thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); - update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure); + hw_pressure = arch_scale_hw_pressure(cpu_of(rq)); + update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure); curr->sched_class->task_tick(rq, curr, 0); if (sched_feat(LATENCY_WARN)) resched_latency = cpu_resched_latency(rq); @@ -5700,7 +5699,7 @@ void scheduler_tick(void) #ifdef CONFIG_SMP rq->idle_balance = idle_cpu(cpu); - trigger_load_balance(rq); + sched_balance_trigger(rq); #endif } @@ -6585,7 +6584,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * paths. For example, see arch/x86/entry_64.S. * * To drive preemption between tasks, the scheduler sets the flag in timer - * interrupt handler scheduler_tick(). + * interrupt handler sched_tick(). * * 3. Wakeups don't really cause entry into schedule(). They add a * task to the run-queue and that's it. @@ -11402,7 +11401,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of, { struct task_group *tg = css_tg(of_css(of)); u64 period = tg_get_cfs_period(tg); - u64 burst = tg_get_cfs_burst(tg); + u64 burst = tg->cfs_bandwidth.burst; u64 quota; int ret; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index af7952f12e6c..aa48b2ec879d 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -424,19 +424,6 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_ */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -# ifndef __ARCH_HAS_VTIME_TASK_SWITCH -void vtime_task_switch(struct task_struct *prev) -{ - if (is_idle_task(prev)) - vtime_account_idle(prev); - else - vtime_account_kernel(prev); - - vtime_flush(prev); - arch_vtime_task_switch(prev); -} -# endif - void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { unsigned int pc = irq_count() - offset; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a04a436af8cc..c75d1307d86d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -43,7 +43,6 @@ static struct ctl_table sched_dl_sysctls[] = { .proc_handler = proc_douintvec_minmax, .extra2 = (void *)&sysctl_sched_dl_period_max, }, - {} }; static int __init sched_dl_sysctl_init(void) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 8d5d98a5834d..c1eb9a1afd13 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -425,6 +425,7 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent) debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops); debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops); + debugfs_create_u32("level", 0444, parent, (u32 *)&sd->level); } void update_sched_domain_debugfs(void) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 03be0d1330a6..8a5b1ae0aa55 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -78,15 +78,9 @@ static unsigned int normalized_sysctl_sched_base_slice = 750000ULL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; -int sched_thermal_decay_shift; static int __init setup_sched_thermal_decay_shift(char *str) { - int _shift = 0; - - if (kstrtoint(str, 0, &_shift)) - pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n"); - - sched_thermal_decay_shift = clamp(_shift, 0, 10); + pr_warn("Ignoring the deprecated sched_thermal_decay_shift= option\n"); return 1; } __setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift); @@ -157,7 +151,6 @@ static struct ctl_table sched_fair_sysctls[] = { .extra1 = SYSCTL_ZERO, }, #endif /* CONFIG_NUMA_BALANCING */ - {} }; static int __init sched_fair_sysctl_init(void) @@ -388,8 +381,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) /* * With cfs_rq being unthrottled/throttled during an enqueue, - * it can happen the tmp_alone_branch points the a leaf that - * we finally want to del. In this case, tmp_alone_branch moves + * it can happen the tmp_alone_branch points to the leaf that + * we finally want to delete. In this case, tmp_alone_branch moves * to the prev element but it will point to rq->leaf_cfs_rq_list * at the end of the enqueue. */ @@ -406,7 +399,7 @@ static inline void assert_list_leaf_cfs_rq(struct rq *rq) SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list); } -/* Iterate thr' all leaf cfs_rq's on a runqueue */ +/* Iterate through all leaf cfs_rq's on a runqueue */ #define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list, \ leaf_cfs_rq_list) @@ -595,13 +588,13 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) * * [[ NOTE: this is only equal to the ideal scheduler under the condition * that join/leave operations happen at lag_i = 0, otherwise the - * virtual time has non-continguous motion equivalent to: + * virtual time has non-contiguous motion equivalent to: * * V +-= lag_i / W * * Also see the comment in place_entity() that deals with this. ]] * - * However, since v_i is u64, and the multiplcation could easily overflow + * However, since v_i is u64, and the multiplication could easily overflow * transform it into a relative form that uses smaller quantities: * * Substitute: v_i == (v_i - v0) + v0 @@ -671,7 +664,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) } if (load) { - /* sign flips effective floor / ceil */ + /* sign flips effective floor / ceiling */ if (avg < 0) avg -= (load - 1); avg = div_s64(avg, load); @@ -696,15 +689,21 @@ 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); } /* @@ -721,7 +720,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) * * lag_i >= 0 -> \Sum (v_i - v)*w_i >= (v_i - v)*(\Sum w_i) * - * Note: using 'avg_vruntime() > se->vruntime' is inacurate due + * Note: using 'avg_vruntime() > se->vruntime' is inaccurate due * to the loss in precision caused by the division. */ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) @@ -1024,14 +1023,15 @@ void init_entity_runnable_average(struct sched_entity *se) if (entity_is_task(se)) sa->load_avg = scale_load_down(se->load.weight); - /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ + /* when this task is enqueued, it will contribute to its cfs_rq's load_avg */ } /* * With new tasks being created, their initial util_avgs are extrapolated * based on the cfs_rq's current util_avg: * - * util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight + * util_avg = cfs_rq->avg.util_avg / (cfs_rq->avg.load_avg + 1) + * * se_weight(se) * * However, in many cases, the above util_avg does not give a desired * value. Moreover, the sum of the util_avgs may be divergent, such @@ -1078,7 +1078,7 @@ void post_init_entity_util_avg(struct task_struct *p) if (cap > 0) { if (cfs_rq->avg.util_avg != 0) { - sa->util_avg = cfs_rq->avg.util_avg * se->load.weight; + sa->util_avg = cfs_rq->avg.util_avg * se_weight(se); sa->util_avg /= (cfs_rq->avg.load_avg + 1); if (sa->util_avg > cap) @@ -1616,7 +1616,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, max_dist = READ_ONCE(sched_max_numa_distance); /* * This code is called for each node, introducing N^2 complexity, - * which should be ok given the number of nodes rarely exceeds 8. + * which should be OK given the number of nodes rarely exceeds 8. */ for_each_online_node(node) { unsigned long faults; @@ -3290,7 +3290,7 @@ retry_pids: /* * Shared library pages mapped by multiple processes are not * migrated as it is expected they are cache replicated. Avoid - * hinting faults in read-only file-backed mappings or the vdso + * hinting faults in read-only file-backed mappings or the vDSO * as migrating the pages will be of marginal benefit. */ if (!vma->vm_mm || @@ -3301,7 +3301,7 @@ retry_pids: /* * Skip inaccessible VMAs to avoid any confusion between - * PROT_NONE and NUMA hinting ptes + * PROT_NONE and NUMA hinting PTEs */ if (!vma_is_accessible(vma)) { trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_INACCESSIBLE); @@ -3333,7 +3333,7 @@ retry_pids: } /* - * Scanning the VMA's of short lived tasks add more overhead. So + * Scanning the VMAs of short lived tasks add more overhead. So * delay the scan for new VMAs. */ if (mm->numa_scan_seq && time_before(jiffies, @@ -3377,7 +3377,7 @@ retry_pids: /* * Try to scan sysctl_numa_balancing_size worth of * hpages that have at least one present PTE that - * is not already pte-numa. If the VMA contains + * is not already PTE-numa. If the VMA contains * areas that are unused or already full of prot_numa * PTEs, scan up to virtpages, to skip through those * areas faster. @@ -3676,16 +3676,15 @@ 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; /* * VRUNTIME - * ======== + * -------- * * COROLLARY #1: The virtual runtime of the entity needs to be * adjusted if re-weight at !0-lag point. @@ -3761,14 +3760,14 @@ 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; } /* * DEADLINE - * ======== + * -------- * * When the weight changes, the virtual time slope changes and * we should adjust the relative virtual deadline accordingly. @@ -3787,25 +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); @@ -4739,7 +4739,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s /* * Track task load average for carrying it to new CPU after migrated, and - * track group sched_entity load average for task_h_load calc in migration + * track group sched_entity load average for task_h_load calculation in migration */ if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) __update_load_avg_se(now, cfs_rq, se); @@ -4822,7 +4822,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) return cfs_rq->avg.load_avg; } -static int newidle_balance(struct rq *this_rq, struct rq_flags *rf); +static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf); static inline unsigned long task_util(struct task_struct *p) { @@ -4965,13 +4965,22 @@ done: trace_sched_util_est_se_tp(&p->se); } +static inline unsigned long get_actual_cpu_capacity(int cpu) +{ + unsigned long capacity = arch_scale_cpu_capacity(cpu); + + capacity -= max(hw_load_avg(cpu_rq(cpu)), cpufreq_get_pressure(cpu)); + + return capacity; +} + static inline int util_fits_cpu(unsigned long util, unsigned long uclamp_min, unsigned long uclamp_max, int cpu) { - unsigned long capacity_orig, capacity_orig_thermal; unsigned long capacity = capacity_of(cpu); + unsigned long capacity_orig; bool fits, uclamp_max_fits; /* @@ -4993,7 +5002,7 @@ static inline int util_fits_cpu(unsigned long util, * Similarly if a task is capped to arch_scale_cpu_capacity(little_cpu), it * should fit a little cpu even if there's some pressure. * - * Only exception is for thermal pressure since it has a direct impact + * Only exception is for HW or cpufreq pressure since it has a direct impact * on available OPP of the system. * * We honour it for uclamp_min only as a drop in performance level @@ -5003,7 +5012,6 @@ static inline int util_fits_cpu(unsigned long util, * goal is to cap the task. So it's okay if it's getting less. */ capacity_orig = arch_scale_cpu_capacity(cpu); - capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); /* * We want to force a task to fit a cpu as implied by uclamp_max. @@ -5020,14 +5028,14 @@ static inline int util_fits_cpu(unsigned long util, * | | | | | | | * | | | | | | | * +---------------------------------------- - * cpu0 cpu1 cpu2 + * CPU0 CPU1 CPU2 * * In the above example if a task is capped to a specific performance * point, y, then when: * - * * util = 80% of x then it does not fit on cpu0 and should migrate - * to cpu1 - * * util = 80% of y then it is forced to fit on cpu1 to honour + * * util = 80% of x then it does not fit on CPU0 and should migrate + * to CPU1 + * * util = 80% of y then it is forced to fit on CPU1 to honour * uclamp_max request. * * which is what we're enforcing here. A task always fits if @@ -5058,7 +5066,7 @@ static inline int util_fits_cpu(unsigned long util, * | | | | | | | * | | | | | | | (region c, boosted, util < uclamp_min) * +---------------------------------------- - * cpu0 cpu1 cpu2 + * CPU0 CPU1 CPU2 * * a) If util > uclamp_max, then we're capped, we don't care about * actual fitness value here. We only care if uclamp_max fits @@ -5078,7 +5086,8 @@ static inline int util_fits_cpu(unsigned long util, * handle the case uclamp_min > uclamp_max. */ uclamp_min = min(uclamp_min, uclamp_max); - if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal)) + if (fits && (util < uclamp_min) && + (uclamp_min > get_actual_cpu_capacity(cpu))) return -1; return fits; @@ -5098,15 +5107,19 @@ static inline int task_fits_cpu(struct task_struct *p, int cpu) static inline void update_misfit_status(struct task_struct *p, struct rq *rq) { + int cpu = cpu_of(rq); + if (!sched_asym_cpucap_active()) return; - if (!p || p->nr_cpus_allowed == 1) { - rq->misfit_task_load = 0; - return; - } + /* + * Affinity allows us to go somewhere higher? Or are we on biggest + * available CPU already? Or do we fit into this CPU ? + */ + if (!p || (p->nr_cpus_allowed == 1) || + (arch_scale_cpu_capacity(cpu) == p->max_allowed_capacity) || + task_fits_cpu(p, cpu)) { - if (task_fits_cpu(p, cpu_of(rq))) { rq->misfit_task_load = 0; return; } @@ -5142,7 +5155,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} static inline void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} -static inline int newidle_balance(struct rq *rq, struct rq_flags *rf) +static inline int sched_balance_newidle(struct rq *rq, struct rq_flags *rf) { return 0; } @@ -5248,7 +5261,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) se->vruntime = vruntime - lag; /* - * When joining the competition; the exisiting tasks will be, + * When joining the competition; the existing tasks will be, * on average, halfway through their slice, as such start tasks * off with half a slice to ease into the competition. */ @@ -5397,7 +5410,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Now advance min_vruntime if @se was the entity holding it back, * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be * put back on, and if we advance min_vruntime, we'll be placed back - * further than we started -- ie. we'll be penalized. + * further than we started -- i.e. we'll be penalized. */ if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE) update_min_vruntime(cfs_rq); @@ -5433,7 +5446,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) /* * Track our maximum slice length, if the CPU's load is at - * least twice that of our own weight (i.e. dont track it + * least twice that of our own weight (i.e. don't track it * when there are only lesser-weight tasks around): */ if (schedstat_enabled() && @@ -6669,22 +6682,47 @@ static inline void hrtick_update(struct rq *rq) #ifdef CONFIG_SMP static inline bool cpu_overutilized(int cpu) { - unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); - unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + unsigned long rq_util_min, rq_util_max; + + if (!sched_energy_enabled()) + return false; + + rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); /* Return true only if the utilization doesn't fit CPU's capacity */ return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu); } -static inline void update_overutilized_status(struct rq *rq) +/* + * overutilized value make sense only if EAS is enabled + */ +static inline bool is_rd_overutilized(struct root_domain *rd) { - if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) { - WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); - trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED); - } + return !sched_energy_enabled() || READ_ONCE(rd->overutilized); +} + +static inline void set_rd_overutilized(struct root_domain *rd, bool flag) +{ + if (!sched_energy_enabled()) + return; + + WRITE_ONCE(rd->overutilized, flag); + trace_sched_overutilized_tp(rd, flag); +} + +static inline void check_update_overutilized_status(struct rq *rq) +{ + /* + * overutilized field is used for load balancing decisions only + * if energy aware scheduler is being used + */ + + if (!is_rd_overutilized(rq->rd) && cpu_overutilized(rq->cpu)) + set_rd_overutilized(rq->rd, 1); } #else -static inline void update_overutilized_status(struct rq *rq) { } +static inline void check_update_overutilized_status(struct rq *rq) { } #endif /* Runqueue only has SCHED_IDLE tasks enqueued */ @@ -6785,7 +6823,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * and the following generally works well enough in practice. */ if (!task_new) - update_overutilized_status(rq); + check_update_overutilized_status(rq); enqueue_throttle: assert_list_leaf_cfs_rq(rq); @@ -6872,7 +6910,7 @@ dequeue_throttle: #ifdef CONFIG_SMP -/* Working cpumask for: load_balance, load_balance_newidle. */ +/* Working cpumask for: sched_balance_rq(), sched_balance_newidle(). */ static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask); static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask); @@ -7104,13 +7142,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, } static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu); +sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int this_cpu); /* - * find_idlest_group_cpu - find the idlest CPU among the CPUs in the group. + * sched_balance_find_dst_group_cpu - find the idlest CPU among the CPUs in the group. */ static int -find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) +sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) { unsigned long load, min_load = ULONG_MAX; unsigned int min_exit_latency = UINT_MAX; @@ -7166,7 +7204,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; } -static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p, +static inline int sched_balance_find_dst_cpu(struct sched_domain *sd, struct task_struct *p, int cpu, int prev_cpu, int sd_flag) { int new_cpu = cpu; @@ -7191,13 +7229,13 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p continue; } - group = find_idlest_group(sd, p, cpu); + group = sched_balance_find_dst_group(sd, p, cpu); if (!group) { sd = sd->child; continue; } - new_cpu = find_idlest_group_cpu(group, p, cpu); + new_cpu = sched_balance_find_dst_group_cpu(group, p, cpu); if (new_cpu == cpu) { /* Now try balancing at a lower domain level of 'cpu': */ sd = sd->child; @@ -7465,7 +7503,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) * Look for the CPU with best capacity. */ else if (fits < 0) - cpu_cap = arch_scale_cpu_capacity(cpu) - thermal_load_avg(cpu_rq(cpu)); + cpu_cap = get_actual_cpu_capacity(cpu); /* * First, select CPU which fits better (-1 being better than 0). @@ -7509,7 +7547,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) /* * On asymmetric system, update task utilization because we will check - * that the task fits with cpu's capacity. + * that the task fits with CPU's capacity. */ if (sched_asym_cpucap_active()) { sync_entity_load_avg(&p->se); @@ -7861,8 +7899,8 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus, * Performance domain frequency: utilization clamping * must be considered since it affects the selection * of the performance domain frequency. - * NOTE: in case RT tasks are running, by default the - * FREQUENCY_UTIL's utilization can be max OPP. + * NOTE: in case RT tasks are running, by default the min + * utilization can be max OPP. */ eff_util = effective_cpu_util(cpu, util, &min, &max); @@ -7942,7 +7980,7 @@ compute_energy(struct energy_env *eenv, struct perf_domain *pd, * NOTE: Forkees are not accepted in the energy-aware wake-up path because * they don't have any useful utilization data yet and it's not possible to * forecast their impact on energy consumption. Consequently, they will be - * placed by find_idlest_cpu() on the least loaded CPU, which might turn out + * placed by sched_balance_find_dst_cpu() on the least loaded CPU, which might turn out * to be energy-inefficient in some use-cases. The alternative would be to * bias new tasks towards specific types of CPUs first, or to try to infer * their util_avg from the parent task, but those heuristics could hurt @@ -7958,15 +7996,15 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) struct root_domain *rd = this_rq()->rd; int cpu, best_energy_cpu, target = -1; int prev_fits = -1, best_fits = -1; - unsigned long best_thermal_cap = 0; - unsigned long prev_thermal_cap = 0; + unsigned long best_actual_cap = 0; + unsigned long prev_actual_cap = 0; struct sched_domain *sd; struct perf_domain *pd; struct energy_env eenv; rcu_read_lock(); pd = rcu_dereference(rd->pd); - if (!pd || READ_ONCE(rd->overutilized)) + if (!pd) goto unlock; /* @@ -7989,7 +8027,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) for (; pd; pd = pd->next) { unsigned long util_min = p_util_min, util_max = p_util_max; - unsigned long cpu_cap, cpu_thermal_cap, util; + unsigned long cpu_cap, cpu_actual_cap, util; long prev_spare_cap = -1, max_spare_cap = -1; unsigned long rq_util_min, rq_util_max; unsigned long cur_delta, base_energy; @@ -8001,18 +8039,17 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (cpumask_empty(cpus)) continue; - /* Account thermal pressure for the energy estimation */ + /* Account external pressure for the energy estimation */ cpu = cpumask_first(cpus); - cpu_thermal_cap = arch_scale_cpu_capacity(cpu); - cpu_thermal_cap -= arch_scale_thermal_pressure(cpu); + cpu_actual_cap = get_actual_cpu_capacity(cpu); - eenv.cpu_cap = cpu_thermal_cap; + eenv.cpu_cap = cpu_actual_cap; eenv.pd_cap = 0; for_each_cpu(cpu, cpus) { struct rq *rq = cpu_rq(cpu); - eenv.pd_cap += cpu_thermal_cap; + eenv.pd_cap += cpu_actual_cap; if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) continue; @@ -8033,7 +8070,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) { /* * Open code uclamp_rq_util_with() except for - * the clamp() part. Ie: apply max aggregation + * the clamp() part. I.e.: apply max aggregation * only. util_fits_cpu() logic requires to * operate on non clamped util but must use the * max-aggregated uclamp_{min, max}. @@ -8083,7 +8120,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (prev_delta < base_energy) goto unlock; prev_delta -= base_energy; - prev_thermal_cap = cpu_thermal_cap; + prev_actual_cap = cpu_actual_cap; best_delta = min(best_delta, prev_delta); } @@ -8098,7 +8135,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) * but best energy cpu has better capacity. */ if ((max_fits < 0) && - (cpu_thermal_cap <= best_thermal_cap)) + (cpu_actual_cap <= best_actual_cap)) continue; cur_delta = compute_energy(&eenv, pd, cpus, p, @@ -8119,14 +8156,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) best_delta = cur_delta; best_energy_cpu = max_spare_cap_cpu; best_fits = max_fits; - best_thermal_cap = cpu_thermal_cap; + best_actual_cap = cpu_actual_cap; } } rcu_read_unlock(); if ((best_fits > prev_fits) || ((best_fits > 0) && (best_delta < prev_delta)) || - ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap))) + ((best_fits < 0) && (best_actual_cap > prev_actual_cap))) target = best_energy_cpu; return target; @@ -8169,7 +8206,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags) cpumask_test_cpu(cpu, p->cpus_ptr)) return cpu; - if (sched_energy_enabled()) { + if (!is_rd_overutilized(this_rq()->rd)) { new_cpu = find_energy_efficient_cpu(p, prev_cpu); if (new_cpu >= 0) return new_cpu; @@ -8207,7 +8244,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags) if (unlikely(sd)) { /* Slow path */ - new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); + new_cpu = sched_balance_find_dst_cpu(sd, p, cpu, prev_cpu, sd_flag); } else if (wake_flags & WF_TTWU) { /* XXX always ? */ /* Fast path */ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); @@ -8253,14 +8290,46 @@ static void task_dead_fair(struct task_struct *p) remove_entity_load_avg(&p->se); } +/* + * Set the max capacity the task is allowed to run at for misfit detection. + */ +static void set_task_max_allowed_capacity(struct task_struct *p) +{ + struct asym_cap_data *entry; + + if (!sched_asym_cpucap_active()) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &asym_cap_list, link) { + cpumask_t *cpumask; + + cpumask = cpu_capacity_span(entry); + if (!cpumask_intersects(p->cpus_ptr, cpumask)) + continue; + + p->max_allowed_capacity = entry->capacity; + break; + } + rcu_read_unlock(); +} + +static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context *ctx) +{ + set_cpus_allowed_common(p, ctx); + set_task_max_allowed_capacity(p); +} + static int balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { if (rq->nr_running) return 1; - return newidle_balance(rq, rf) != 0; + return sched_balance_newidle(rq, rf) != 0; } +#else +static inline void set_task_max_allowed_capacity(struct task_struct *p) {} #endif /* CONFIG_SMP */ static void set_next_buddy(struct sched_entity *se) @@ -8511,10 +8580,10 @@ idle: if (!rf) return NULL; - new_tasks = newidle_balance(rq, rf); + new_tasks = sched_balance_newidle(rq, rf); /* - * Because newidle_balance() releases (and re-acquires) rq->lock, it is + * Because sched_balance_newidle() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we * must re-start the pick_next_entity() loop. */ @@ -8592,7 +8661,7 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p) if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se))) return false; - /* Tell the scheduler that we'd really like pse to run next. */ + /* Tell the scheduler that we'd really like se to run next. */ set_next_buddy(se); yield_task_fair(rq); @@ -8930,7 +8999,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) return 0; - /* Disregard pcpu kthreads; they are where they need to be. */ + /* Disregard percpu kthreads; they are where they need to be. */ if (kthread_is_per_cpu(p)) return 0; @@ -9076,7 +9145,7 @@ static int detach_tasks(struct lb_env *env) * We don't want to steal all, otherwise we may be treated likewise, * which could at worst lead to a livelock crash. */ - if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1) + if (env->idle && env->src_rq->nr_running <= 1) break; env->loop++; @@ -9255,7 +9324,7 @@ static inline bool others_have_blocked(struct rq *rq) if (cpu_util_dl(rq)) return true; - if (thermal_load_avg(rq)) + if (hw_load_avg(rq)) return true; if (cpu_util_irq(rq)) @@ -9285,7 +9354,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done) { const struct sched_class *curr_class; u64 now = rq_clock_pelt(rq); - unsigned long thermal_pressure; + unsigned long hw_pressure; bool decayed; /* @@ -9294,11 +9363,11 @@ static bool __update_blocked_others(struct rq *rq, bool *done) */ curr_class = rq->curr->sched_class; - thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); + hw_pressure = arch_scale_hw_pressure(cpu_of(rq)); decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) | update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) | - update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) | + update_hw_load_avg(now, rq, hw_pressure) | update_irq_load_avg(rq, 0); if (others_have_blocked(rq)) @@ -9417,7 +9486,7 @@ static unsigned long task_h_load(struct task_struct *p) } #endif -static void update_blocked_averages(int cpu) +static void sched_balance_update_blocked_averages(int cpu) { bool decayed = false, done = true; struct rq *rq = cpu_rq(cpu); @@ -9436,25 +9505,25 @@ static void update_blocked_averages(int cpu) rq_unlock_irqrestore(rq, &rf); } -/********** Helpers for find_busiest_group ************************/ +/********** Helpers for sched_balance_find_src_group ************************/ /* - * sg_lb_stats - stats of a sched_group required for load_balancing + * sg_lb_stats - stats of a sched_group required for load-balancing: */ struct sg_lb_stats { - unsigned long avg_load; /*Avg load across the CPUs of the group */ - unsigned long group_load; /* Total load over the CPUs of the group */ - unsigned long group_capacity; - unsigned long group_util; /* Total utilization over the CPUs of the group */ - unsigned long group_runnable; /* Total runnable time over the CPUs of the group */ - unsigned int sum_nr_running; /* Nr of tasks running in the group */ - unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */ - unsigned int idle_cpus; + unsigned long avg_load; /* Avg load over the CPUs of the group */ + unsigned long group_load; /* Total load over the CPUs of the group */ + unsigned long group_capacity; /* Capacity over the CPUs of the group */ + unsigned long group_util; /* Total utilization over the CPUs of the group */ + unsigned long group_runnable; /* Total runnable time over the CPUs of the group */ + unsigned int sum_nr_running; /* Nr of all tasks running in the group */ + unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */ + unsigned int idle_cpus; /* Nr of idle CPUs in the group */ unsigned int group_weight; enum group_type group_type; - unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */ - unsigned int group_smt_balance; /* Task on busy SMT be moved */ - unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */ + unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */ + unsigned int group_smt_balance; /* Task on busy SMT be moved */ + unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */ #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -9462,19 +9531,18 @@ struct sg_lb_stats { }; /* - * sd_lb_stats - Structure to store the statistics of a sched_domain - * during load balancing. + * sd_lb_stats - stats of a sched_domain required for load-balancing: */ struct sd_lb_stats { - struct sched_group *busiest; /* Busiest group in this sd */ - struct sched_group *local; /* Local group in this sd */ - unsigned long total_load; /* Total load of all groups in sd */ - unsigned long total_capacity; /* Total capacity of all groups in sd */ - unsigned long avg_load; /* Average load across all groups in sd */ - unsigned int prefer_sibling; /* tasks should go to sibling first */ - - struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ - struct sg_lb_stats local_stat; /* Statistics of the local group */ + struct sched_group *busiest; /* Busiest group in this sd */ + struct sched_group *local; /* Local group in this sd */ + unsigned long total_load; /* Total load of all groups in sd */ + unsigned long total_capacity; /* Total capacity of all groups in sd */ + unsigned long avg_load; /* Average load across all groups in sd */ + unsigned int prefer_sibling; /* Tasks should go to sibling first */ + + struct sg_lb_stats busiest_stat; /* Statistics of the busiest group */ + struct sg_lb_stats local_stat; /* Statistics of the local group */ }; static inline void init_sd_lb_stats(struct sd_lb_stats *sds) @@ -9500,8 +9568,8 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) static unsigned long scale_rt_capacity(int cpu) { + unsigned long max = get_actual_cpu_capacity(cpu); struct rq *rq = cpu_rq(cpu); - unsigned long max = arch_scale_cpu_capacity(cpu); unsigned long used, free; unsigned long irq; @@ -9513,12 +9581,9 @@ static unsigned long scale_rt_capacity(int cpu) /* * avg_rt.util_avg and avg_dl.util_avg track binary signals * (running and not running) with weights 0 and 1024 respectively. - * avg_thermal.load_avg tracks thermal pressure and the weighted - * average uses the actual delta max capacity(load). */ used = cpu_util_rt(rq); used += cpu_util_dl(rq); - used += thermal_load_avg(rq); if (unlikely(used >= max)) return 1; @@ -9611,16 +9676,10 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) (arch_scale_cpu_capacity(cpu_of(rq)) * 100)); } -/* - * Check whether a rq has a misfit task and if it looks like we can actually - * help that task: we can migrate the task to a CPU of higher capacity, or - * the task's current CPU is heavily pressured. - */ -static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) +/* Check if the rq has a misfit task */ +static inline bool check_misfit_status(struct rq *rq) { - return rq->misfit_task_load && - (arch_scale_cpu_capacity(rq->cpu) < rq->rd->max_cpu_capacity || - check_cpu_capacity(rq, sd)); + return rq->misfit_task_load; } /* @@ -9644,7 +9703,7 @@ static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) * * When this is so detected; this group becomes a candidate for busiest; see * update_sd_pick_busiest(). And calculate_imbalance() and - * find_busiest_group() avoid some of the usual balance conditions to allow it + * sched_balance_find_src_group() avoid some of the usual balance conditions to allow it * to create an effective group imbalance. * * This is a somewhat tricky proposition since the next run might not find the @@ -9809,7 +9868,7 @@ static inline bool smt_vs_nonsmt_groups(struct sched_group *sg1, static inline bool smt_balance(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group *group) { - if (env->idle == CPU_NOT_IDLE) + if (!env->idle) return false; /* @@ -9833,7 +9892,7 @@ static inline long sibling_imbalance(struct lb_env *env, int ncores_busiest, ncores_local; long imbalance; - if (env->idle == CPU_NOT_IDLE || !busiest->sum_nr_running) + if (!env->idle || !busiest->sum_nr_running) return 0; ncores_busiest = sds->busiest->cores; @@ -9879,13 +9938,15 @@ sched_reduced_capacity(struct rq *rq, struct sched_domain *sd) * @sds: Load-balancing data with statistics of the local group. * @group: sched_group whose statistics are to be updated. * @sgs: variable to hold the statistics for this group. - * @sg_status: Holds flag indicating the status of the sched_group + * @sg_overloaded: sched_group is overloaded + * @sg_overutilized: sched_group is overutilized */ static inline void update_sg_lb_stats(struct lb_env *env, struct sd_lb_stats *sds, struct sched_group *group, struct sg_lb_stats *sgs, - int *sg_status) + bool *sg_overloaded, + bool *sg_overutilized) { int i, nr_running, local_group; @@ -9906,10 +9967,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->sum_nr_running += nr_running; if (nr_running > 1) - *sg_status |= SG_OVERLOAD; + *sg_overloaded = 1; if (cpu_overutilized(i)) - *sg_status |= SG_OVERUTILIZED; + *sg_overutilized = 1; #ifdef CONFIG_NUMA_BALANCING sgs->nr_numa_running += rq->nr_numa_running; @@ -9931,10 +9992,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, /* Check for a misfit task on the cpu */ if (sgs->group_misfit_task_load < rq->misfit_task_load) { sgs->group_misfit_task_load = rq->misfit_task_load; - *sg_status |= SG_OVERLOAD; + *sg_overloaded = 1; } - } else if ((env->idle != CPU_NOT_IDLE) && - sched_reduced_capacity(rq, env->sd)) { + } else if (env->idle && sched_reduced_capacity(rq, env->sd)) { /* Check for a task running on a CPU with reduced capacity */ if (sgs->group_misfit_task_load < load) sgs->group_misfit_task_load = load; @@ -9946,7 +10006,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_weight = group->group_weight; /* Check if dst CPU is idle and preferred to this group */ - if (!local_group && env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running && + if (!local_group && env->idle && sgs->sum_h_nr_running && sched_group_asym(env, sgs, group)) sgs->group_asym_packing = 1; @@ -10084,7 +10144,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, has_spare: /* - * Select not overloaded group with lowest number of idle cpus + * Select not overloaded group with lowest number of idle CPUs * and highest number of running tasks. We could also compare * the spare capacity which is more stable but it can end up * that the group has less spare capacity but finally more idle @@ -10304,13 +10364,13 @@ static bool update_pick_idlest(struct sched_group *idlest, } /* - * find_idlest_group() finds and returns the least busy CPU group within the + * sched_balance_find_dst_group() finds and returns the least busy CPU group within the * domain. * * Assumes p is allowed on at least one CPU in sd. */ static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) +sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) { struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups; struct sg_lb_stats local_sgs, tmp_sgs; @@ -10558,7 +10618,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sg_lb_stats *local = &sds->local_stat; struct sg_lb_stats tmp_sgs; unsigned long sum_util = 0; - int sg_status = 0; + bool sg_overloaded = 0, sg_overutilized = 0; do { struct sg_lb_stats *sgs = &tmp_sgs; @@ -10574,7 +10634,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_group_capacity(env->sd, env->dst_cpu); } - update_sg_lb_stats(env, sds, sg, sgs, &sg_status); + update_sg_lb_stats(env, sds, sg, sgs, &sg_overloaded, &sg_overutilized); if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; @@ -10602,19 +10662,13 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd env->fbq_type = fbq_classify_group(&sds->busiest_stat); if (!env->sd->parent) { - struct root_domain *rd = env->dst_rq->rd; - /* update overload indicator if we are at root domain */ - WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD); + set_rd_overloaded(env->dst_rq->rd, sg_overloaded); /* Update over-utilization (tipping point, U >= 0) indicator */ - WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); - trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED); - } else if (sg_status & SG_OVERUTILIZED) { - struct root_domain *rd = env->dst_rq->rd; - - WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); - trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); + set_rd_overutilized(env->dst_rq->rd, sg_overutilized); + } else if (sg_overutilized) { + set_rd_overutilized(env->dst_rq->rd, sg_overutilized); } update_idle_cpu_scan(env, sum_util); @@ -10704,7 +10758,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * waiting task in this overloaded busiest group. Let's * try to pull it. */ - if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) { + if (env->idle && env->imbalance == 0) { env->migration_type = migrate_task; env->imbalance = 1; } @@ -10723,7 +10777,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* * If there is no overload, we just want to even the number of - * idle cpus. + * idle CPUs. */ env->migration_type = migrate_task; env->imbalance = max_t(long, 0, @@ -10796,7 +10850,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s ) / SCHED_CAPACITY_SCALE; } -/******* find_busiest_group() helpers end here *********************/ +/******* sched_balance_find_src_group() helpers end here *********************/ /* * Decision matrix according to the local and busiest group type: @@ -10819,7 +10873,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ /** - * find_busiest_group - Returns the busiest group within the sched_domain + * sched_balance_find_src_group - Returns the busiest group within the sched_domain * if there is an imbalance. * @env: The load balancing environment. * @@ -10828,7 +10882,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * * Return: - The busiest group if imbalance exists. */ -static struct sched_group *find_busiest_group(struct lb_env *env) +static struct sched_group *sched_balance_find_src_group(struct lb_env *env) { struct sg_lb_stats *local, *busiest; struct sd_lb_stats sds; @@ -10851,12 +10905,9 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (busiest->group_type == group_misfit_task) goto force_balance; - if (sched_energy_enabled()) { - struct root_domain *rd = env->dst_rq->rd; - - if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) - goto out_balanced; - } + if (!is_rd_overutilized(env->dst_rq->rd) && + rcu_dereference(env->dst_rq->rd->pd)) + goto out_balanced; /* ASYM feature bypasses nice load balance check */ if (busiest->group_type == group_asym_packing) @@ -10919,7 +10970,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; if (busiest->group_type != group_overloaded) { - if (env->idle == CPU_NOT_IDLE) { + if (!env->idle) { /* * If the busiest group is not overloaded (and as a * result the local one too) but this CPU is already @@ -10967,9 +11018,9 @@ out_balanced: } /* - * find_busiest_queue - find the busiest runqueue among the CPUs in the group. + * sched_balance_find_src_rq - find the busiest runqueue among the CPUs in the group. */ -static struct rq *find_busiest_queue(struct lb_env *env, +static struct rq *sched_balance_find_src_rq(struct lb_env *env, struct sched_group *group) { struct rq *busiest = NULL, *rq; @@ -11127,7 +11178,7 @@ asym_active_balance(struct lb_env *env) * the lower priority @env::dst_cpu help it. Do not follow * CPU priority. */ - return env->idle != CPU_NOT_IDLE && sched_use_asym_prio(env->sd, env->dst_cpu) && + return env->idle && sched_use_asym_prio(env->sd, env->dst_cpu) && (sched_asym_prefer(env->dst_cpu, env->src_cpu) || !sched_use_asym_prio(env->sd, env->src_cpu)); } @@ -11165,7 +11216,7 @@ static int need_active_balance(struct lb_env *env) * because of other sched_class or IRQs if more capacity stays * available on dst_cpu. */ - if ((env->idle != CPU_NOT_IDLE) && + if (env->idle && (env->src_rq->cfs.h_nr_running == 1)) { if ((check_cpu_capacity(env->src_rq, sd)) && (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) @@ -11250,7 +11301,7 @@ static int should_we_balance(struct lb_env *env) * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. */ -static int load_balance(int this_cpu, struct rq *this_rq, +static int sched_balance_rq(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, int *continue_balancing) { @@ -11282,13 +11333,13 @@ redo: goto out_balanced; } - group = find_busiest_group(&env); + group = sched_balance_find_src_group(&env); if (!group) { schedstat_inc(sd->lb_nobusyg[idle]); goto out_balanced; } - busiest = find_busiest_queue(&env, group); + busiest = sched_balance_find_src_rq(&env, group); if (!busiest) { schedstat_inc(sd->lb_nobusyq[idle]); goto out_balanced; @@ -11306,7 +11357,7 @@ redo: env.flags |= LBF_ALL_PINNED; if (busiest->nr_running > 1) { /* - * Attempt to move tasks. If find_busiest_group has found + * Attempt to move tasks. If sched_balance_find_src_group has found * an imbalance but busiest->nr_running <= 1, the group is * still unbalanced. ld_moved simply stays zero, so it is * correctly treated as an imbalance. @@ -11421,8 +11472,12 @@ more_balance: * We do not want newidle balance, which can be very * frequent, pollute the failure counter causing * excessive cache_hot migrations and active balances. + * + * Similarly for migration_misfit which is not related to + * load/util migration, don't pollute nr_balance_failed. */ - if (idle != CPU_NEWLY_IDLE) + if (idle != CPU_NEWLY_IDLE && + env.migration_type != migrate_misfit) sd->nr_balance_failed++; if (need_active_balance(&env)) { @@ -11501,12 +11556,17 @@ out_one_pinned: ld_moved = 0; /* - * newidle_balance() disregards balance intervals, so we could + * sched_balance_newidle() disregards balance intervals, so we could * repeatedly reach this code, which would lead to balance_interval * skyrocketing in a short amount of time. Skip the balance_interval * increase logic to avoid that. + * + * Similarly misfit migration which is not necessarily an indication of + * the system being busy and requires lb to backoff to let it settle + * down. */ - if (env.idle == CPU_NEWLY_IDLE) + if (env.idle == CPU_NEWLY_IDLE || + env.migration_type == migrate_misfit) goto out; /* tune up the balancing interval */ @@ -11639,10 +11699,23 @@ out_unlock: return 0; } -static DEFINE_SPINLOCK(balancing); +/* + * This flag serializes load-balancing passes over large domains + * (above the NODE topology level) - only one load-balancing instance + * may run at a time, to reduce overhead on very large systems with + * lots of CPUs and large NUMA distances. + * + * - Note that load-balancing passes triggered while another one + * is executing are skipped and not re-tried. + * + * - Also note that this does not serialize rebalance_domains() + * execution, as non-SD_SERIALIZE domains will still be + * load-balanced in parallel. + */ +static atomic_t sched_balance_running = ATOMIC_INIT(0); /* - * Scale the max load_balance interval with the number of CPUs in the system. + * Scale the max sched_balance_rq interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. */ void update_max_interval(void) @@ -11680,7 +11753,7 @@ static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) * * Balancing parameters are set up in init_sched_domains. */ -static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) +static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) { int continue_balancing = 1; int cpu = rq->cpu; @@ -11717,25 +11790,25 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) need_serialize = sd->flags & SD_SERIALIZE; if (need_serialize) { - if (!spin_trylock(&balancing)) + if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1)) goto out; } if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &continue_balancing)) { + if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) { /* * The LBF_DST_PINNED logic could have changed * env->dst_cpu, so we can't know our idle * state even if we migrated tasks. Update it. */ - idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; - busy = idle != CPU_IDLE && !sched_idle_cpu(cpu); + idle = idle_cpu(cpu); + busy = !idle && !sched_idle_cpu(cpu); } sd->last_balance = jiffies; interval = get_sd_balance_interval(sd, busy); } if (need_serialize) - spin_unlock(&balancing); + atomic_set_release(&sched_balance_running, 0); out: if (time_after(next_balance, sd->last_balance + interval)) { next_balance = sd->last_balance + interval; @@ -11895,7 +11968,7 @@ static void nohz_balancer_kick(struct rq *rq) * currently idle; in which case, kick the ILB to move tasks * around. * - * When balancing betwen cores, all the SMT siblings of the + * When balancing between cores, all the SMT siblings of the * preferred CPU must be idle. */ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { @@ -11912,7 +11985,7 @@ static void nohz_balancer_kick(struct rq *rq) * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU * to run the misfit task on. */ - if (check_misfit_status(rq, sd)) { + if (check_misfit_status(rq)) { flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } @@ -12056,7 +12129,7 @@ void nohz_balance_enter_idle(int cpu) out: /* * Each time a cpu enter idle, we assume that it has blocked load and - * enable the periodic update of the load of idle cpus + * enable the periodic update of the load of idle CPUs */ WRITE_ONCE(nohz.has_blocked, 1); } @@ -12074,13 +12147,13 @@ static bool update_nohz_stats(struct rq *rq) if (!time_after(jiffies, READ_ONCE(rq->last_blocked_load_update_tick))) return true; - update_blocked_averages(cpu); + sched_balance_update_blocked_averages(cpu); return rq->has_blocked_load; } /* - * Internal function that runs load balance for all idle cpus. The load balance + * Internal function that runs load balance for all idle CPUs. The load balance * can be a simple update of blocked load or a complete load balance with * tasks movement depending of flags. */ @@ -12156,7 +12229,7 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags) rq_unlock_irqrestore(rq, &rf); if (flags & NOHZ_BALANCE_KICK) - rebalance_domains(rq, CPU_IDLE); + sched_balance_domains(rq, CPU_IDLE); } if (time_after(next_balance, rq->next_balance)) { @@ -12185,7 +12258,7 @@ abort: /* * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the - * rebalancing for all the cpus for whom scheduler ticks are stopped. + * rebalancing for all the CPUs for whom scheduler ticks are stopped. */ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { @@ -12216,7 +12289,7 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) * called from this function on (this) CPU that's not yet in the mask. That's * OK because the goal of nohz_run_idle_balance() is to run ILB only for * updating the blocked load of already idle CPUs without waking up one of - * those idle CPUs and outside the preempt disable / irq off phase of the local + * those idle CPUs and outside the preempt disable / IRQ off phase of the local * cpu about to enter idle, because it can take a long time. */ void nohz_run_idle_balance(int cpu) @@ -12227,7 +12300,7 @@ void nohz_run_idle_balance(int cpu) /* * Update the blocked load only if no SCHED_SOFTIRQ is about to happen - * (ie NOHZ_STATS_KICK set) and will do the same. + * (i.e. NOHZ_STATS_KICK set) and will do the same. */ if ((flags == NOHZ_NEWILB_KICK) && !need_resched()) _nohz_idle_balance(cpu_rq(cpu), NOHZ_STATS_KICK); @@ -12272,7 +12345,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { } #endif /* CONFIG_NO_HZ_COMMON */ /* - * newidle_balance is called by schedule() if this_cpu is about to become + * sched_balance_newidle is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. * * Returns: @@ -12280,10 +12353,11 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { } * 0 - failed, no new tasks * > 0 - success, new (fair) tasks present */ -static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) +static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) { unsigned long next_balance = jiffies + HZ; int this_cpu = this_rq->cpu; + int continue_balancing = 1; u64 t0, t1, curr_cost = 0; struct sched_domain *sd; int pulled_task = 0; @@ -12298,8 +12372,9 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) return 0; /* - * We must set idle_stamp _before_ calling idle_balance(), such that we - * measure the duration of idle_balance() as idle time. + * We must set idle_stamp _before_ calling sched_balance_rq() + * for CPU_NEWLY_IDLE, such that we measure the this duration + * as idle time. */ this_rq->idle_stamp = rq_clock(this_rq); @@ -12320,7 +12395,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) rcu_read_lock(); sd = rcu_dereference_check_sched_domain(this_rq->sd); - if (!READ_ONCE(this_rq->rd->overload) || + if (!get_rd_overloaded(this_rq->rd) || (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) { if (sd) @@ -12334,11 +12409,10 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) raw_spin_rq_unlock(this_rq); t0 = sched_clock_cpu(this_cpu); - update_blocked_averages(this_cpu); + sched_balance_update_blocked_averages(this_cpu); rcu_read_lock(); for_each_domain(this_cpu, sd) { - int continue_balancing = 1; u64 domain_cost; update_next_balance(sd, &next_balance); @@ -12348,7 +12422,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) if (sd->flags & SD_BALANCE_NEWIDLE) { - pulled_task = load_balance(this_cpu, this_rq, + pulled_task = sched_balance_rq(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, &continue_balancing); @@ -12364,8 +12438,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) * Stop searching for tasks to pull if there are * now runnable tasks on this rq. */ - if (pulled_task || this_rq->nr_running > 0 || - this_rq->ttwu_pending) + if (pulled_task || !continue_balancing) break; } rcu_read_unlock(); @@ -12403,19 +12476,21 @@ out: } /* - * run_rebalance_domains is triggered when needed from the scheduler tick. - * Also triggered for nohz idle balancing (with nohz_balancing_kick set). + * This softirq handler is triggered via SCHED_SOFTIRQ from two places: + * + * - directly from the local scheduler_tick() for periodic load balancing + * + * - indirectly from a remote scheduler_tick() for NOHZ idle balancing + * through the SMP cross-call nohz_csd_func() */ -static __latent_entropy void run_rebalance_domains(struct softirq_action *h) +static __latent_entropy void sched_balance_softirq(struct softirq_action *h) { struct rq *this_rq = this_rq(); - enum cpu_idle_type idle = this_rq->idle_balance ? - CPU_IDLE : CPU_NOT_IDLE; - + enum cpu_idle_type idle = this_rq->idle_balance; /* - * If this CPU has a pending nohz_balance_kick, then do the + * If this CPU has a pending NOHZ_BALANCE_KICK, then do the * balancing on behalf of the other idle CPUs whose ticks are - * stopped. Do nohz_idle_balance *before* rebalance_domains to + * stopped. Do nohz_idle_balance *before* sched_balance_domains to * give the idle CPUs a chance to load balance. Else we may * load balance only within the local sched_domain hierarchy * and abort nohz_idle_balance altogether if we pull some load. @@ -12424,14 +12499,14 @@ static __latent_entropy void run_rebalance_domains(struct softirq_action *h) return; /* normal load balance */ - update_blocked_averages(this_rq->cpu); - rebalance_domains(this_rq, idle); + sched_balance_update_blocked_averages(this_rq->cpu); + sched_balance_domains(this_rq, idle); } /* * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. */ -void trigger_load_balance(struct rq *rq) +void sched_balance_trigger(struct rq *rq) { /* * Don't need to rebalance while attached to NULL domain or @@ -12615,7 +12690,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) task_tick_numa(rq, curr); update_misfit_status(curr, rq); - update_overutilized_status(task_rq(curr)); + check_update_overutilized_status(task_rq(curr)); task_tick_core(rq, curr); } @@ -12635,6 +12710,8 @@ static void task_fork_fair(struct task_struct *p) rq_lock(rq, &rf); update_rq_clock(rq); + set_task_max_allowed_capacity(p); + cfs_rq = task_cfs_rq(current); curr = cfs_rq->curr; if (curr) @@ -12758,6 +12835,8 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) { attach_task_cfs_rq(p); + set_task_max_allowed_capacity(p); + if (task_on_rq_queued(p)) { /* * We were most likely switched from sched_rt, so @@ -13129,7 +13208,7 @@ DEFINE_SCHED_CLASS(fair) = { .rq_offline = rq_offline_fair, .task_dead = task_dead_fair, - .set_cpus_allowed = set_cpus_allowed_common, + .set_cpus_allowed = set_cpus_allowed_fair, #endif .task_tick = task_tick_fair, @@ -13209,7 +13288,7 @@ __init void init_sched_fair_class(void) #endif } - open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); + open_softirq(SCHED_SOFTIRQ, sched_balance_softirq); #ifdef CONFIG_NO_HZ_COMMON nohz.next_balance = jiffies; diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 373d42c707bc..5891e715f00d 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -46,7 +46,16 @@ int housekeeping_any_cpu(enum hk_type type) if (cpu < nr_cpu_ids) return cpu; - return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask); + cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask); + if (likely(cpu < nr_cpu_ids)) + return cpu; + /* + * Unless we have another problem this can only happen + * at boot time before start_secondary() brings the 1st + * housekeeping CPU up. + */ + WARN_ON_ONCE(system_state == SYSTEM_RUNNING || + type != HK_TYPE_TIMER); } } return smp_processor_id(); @@ -109,6 +118,7 @@ static void __init housekeeping_setup_type(enum hk_type type, static int __init housekeeping_setup(char *str, unsigned long flags) { cpumask_var_t non_housekeeping_mask, housekeeping_staging; + unsigned int first_cpu; int err = 0; if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) { @@ -129,7 +139,8 @@ static int __init housekeeping_setup(char *str, unsigned long flags) cpumask_andnot(housekeeping_staging, cpu_possible_mask, non_housekeeping_mask); - if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) { + first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging); + if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) { __cpumask_set_cpu(smp_processor_id(), housekeeping_staging); __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); if (!housekeeping.flags) { @@ -138,6 +149,9 @@ static int __init housekeeping_setup(char *str, unsigned long flags) } } + if (cpumask_empty(non_housekeeping_mask)) + goto free_housekeeping_staging; + if (!housekeeping.flags) { /* First setup call ("nohz_full=" or "isolcpus=") */ enum hk_type type; diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 52c8f8226b0d..ca9da66cc894 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -379,7 +379,7 @@ void calc_global_load(void) } /* - * Called from scheduler_tick() to periodically update this CPU's + * Called from sched_tick() to periodically update this CPU's * active count. */ void calc_global_load_tick(struct rq *this_rq) diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index 63b6cf898220..ef00382de595 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -208,8 +208,8 @@ ___update_load_sum(u64 now, struct sched_avg *sa, * se has been already dequeued but cfs_rq->curr still points to it. * This means that weight will be 0 but not running for a sched_entity * but also for a cfs_rq if the latter becomes idle. As an example, - * this happens during idle_balance() which calls - * update_blocked_averages(). + * this happens during sched_balance_newidle() which calls + * sched_balance_update_blocked_averages(). * * Also see the comment in accumulate_sum(). */ @@ -384,30 +384,30 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) return 0; } -#ifdef CONFIG_SCHED_THERMAL_PRESSURE +#ifdef CONFIG_SCHED_HW_PRESSURE /* - * thermal: + * hardware: * * load_sum = \Sum se->avg.load_sum but se->avg.load_sum is not tracked * * util_avg and runnable_load_avg are not supported and meaningless. * * Unlike rt/dl utilization tracking that track time spent by a cpu - * running a rt/dl task through util_avg, the average thermal pressure is - * tracked through load_avg. This is because thermal pressure signal is + * running a rt/dl task through util_avg, the average HW pressure is + * tracked through load_avg. This is because HW pressure signal is * time weighted "delta" capacity unlike util_avg which is binary. * "delta capacity" = actual capacity - - * capped capacity a cpu due to a thermal event. + * capped capacity a cpu due to a HW event. */ -int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity) { - if (___update_load_sum(now, &rq->avg_thermal, + if (___update_load_sum(now, &rq->avg_hw, capacity, capacity, capacity)) { - ___update_load_avg(&rq->avg_thermal, 1); - trace_pelt_thermal_tp(rq); + ___update_load_avg(&rq->avg_hw, 1); + trace_pelt_hw_tp(rq); return 1; } diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 9e1083465fbc..2150062949d4 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -7,21 +7,21 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); -#ifdef CONFIG_SCHED_THERMAL_PRESSURE -int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity); +#ifdef CONFIG_SCHED_HW_PRESSURE +int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity); -static inline u64 thermal_load_avg(struct rq *rq) +static inline u64 hw_load_avg(struct rq *rq) { - return READ_ONCE(rq->avg_thermal.load_avg); + return READ_ONCE(rq->avg_hw.load_avg); } #else static inline int -update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +update_hw_load_avg(u64 now, struct rq *rq, u64 capacity) { return 0; } -static inline u64 thermal_load_avg(struct rq *rq) +static inline u64 hw_load_avg(struct rq *rq) { return 0; } @@ -202,12 +202,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running) } static inline int -update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +update_hw_load_avg(u64 now, struct rq *rq, u64 capacity) { return 0; } -static inline u64 thermal_load_avg(struct rq *rq) +static inline u64 hw_load_avg(struct rq *rq) { return 0; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 3261b067b67e..aa4c1c874fa4 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -56,7 +56,6 @@ static struct ctl_table sched_rt_sysctls[] = { .mode = 0644, .proc_handler = sched_rr_handler, }, - {} }; static int __init sched_rt_sysctl_init(void) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d2242679239e..a831af102070 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -79,6 +79,8 @@ # include <asm/paravirt_api_clock.h> #endif +#include <asm/barrier.h> + #include "cpupri.h" #include "cpudeadline.h" @@ -110,6 +112,20 @@ extern int sysctl_sched_rt_runtime; extern int sched_rr_timeslice; /* + * Asymmetric CPU capacity bits + */ +struct asym_cap_data { + struct list_head link; + struct rcu_head rcu; + unsigned long capacity; + unsigned long cpus[]; +}; + +extern struct list_head asym_cap_list; + +#define cpu_capacity_span(asym_data) to_cpumask((asym_data)->cpus) + +/* * Helpers for converting nanosecond timing to jiffy resolution */ #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) @@ -699,7 +715,7 @@ struct rt_rq { } highest_prio; #endif #ifdef CONFIG_SMP - int overloaded; + bool overloaded; struct plist_head pushable_tasks; #endif /* CONFIG_SMP */ @@ -743,7 +759,7 @@ struct dl_rq { u64 next; } earliest_dl; - int overloaded; + bool overloaded; /* * Tasks on this rq that can be pushed away. They are kept in @@ -836,10 +852,6 @@ struct perf_domain { struct rcu_head rcu; }; -/* Scheduling group status flags */ -#define SG_OVERLOAD 0x1 /* More than one runnable task on a CPU. */ -#define SG_OVERUTILIZED 0x2 /* One or more CPUs are over-utilized. */ - /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by @@ -860,10 +872,10 @@ struct root_domain { * - More than one runnable task * - Running task is misfit */ - int overload; + bool overloaded; /* Indicate one or more cpus over-utilized (tipping point) */ - int overutilized; + bool overutilized; /* * The bit corresponding to a CPU gets set here if such CPU has more @@ -903,8 +915,6 @@ struct root_domain { cpumask_var_t rto_mask; struct cpupri cpupri; - unsigned long max_cpu_capacity; - /* * NULL-terminated list of performance domains intersecting with the * CPUs of the rd. Protected by RCU. @@ -918,6 +928,17 @@ extern void rq_attach_root(struct rq *rq, struct root_domain *rd); extern void sched_get_rd(struct root_domain *rd); extern void sched_put_rd(struct root_domain *rd); +static inline int get_rd_overloaded(struct root_domain *rd) +{ + return READ_ONCE(rd->overloaded); +} + +static inline void set_rd_overloaded(struct root_domain *rd, int status) +{ + if (get_rd_overloaded(rd) != status) + WRITE_ONCE(rd->overloaded, status); +} + #ifdef HAVE_RT_PUSH_IPI extern void rto_push_irq_work_func(struct irq_work *work); #endif @@ -1089,8 +1110,8 @@ struct rq { #ifdef CONFIG_HAVE_SCHED_AVG_IRQ struct sched_avg avg_irq; #endif -#ifdef CONFIG_SCHED_THERMAL_PRESSURE - struct sched_avg avg_thermal; +#ifdef CONFIG_SCHED_HW_PRESSURE + struct sched_avg avg_hw; #endif u64 idle_stamp; u64 avg_idle; @@ -1531,24 +1552,6 @@ static inline u64 rq_clock_task(struct rq *rq) return rq->clock_task; } -/** - * By default the decay is the default pelt decay period. - * The decay shift can change the decay period in - * multiples of 32. - * Decay shift Decay period(ms) - * 0 32 - * 1 64 - * 2 128 - * 3 256 - * 4 512 - */ -extern int sched_thermal_decay_shift; - -static inline u64 rq_clock_thermal(struct rq *rq) -{ - return rq_clock_task(rq) >> sched_thermal_decay_shift; -} - static inline void rq_clock_skip_update(struct rq *rq) { lockdep_assert_rq_held(rq); @@ -2397,7 +2400,7 @@ extern struct task_struct *pick_next_task_idle(struct rq *rq); extern void update_group_capacity(struct sched_domain *sd, int cpu); -extern void trigger_load_balance(struct rq *rq); +extern void sched_balance_trigger(struct rq *rq); extern void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx); @@ -2517,10 +2520,8 @@ static inline void add_nr_running(struct rq *rq, unsigned count) } #ifdef CONFIG_SMP - if (prev_nr < 2 && rq->nr_running >= 2) { - if (!READ_ONCE(rq->rd->overload)) - WRITE_ONCE(rq->rd->overload, 1); - } + if (prev_nr < 2 && rq->nr_running >= 2) + set_rd_overloaded(rq->rd, 1); #endif sched_update_tick_dependency(rq); @@ -2904,7 +2905,7 @@ extern void cfs_bandwidth_usage_dec(void); #define NOHZ_NEWILB_KICK_BIT 2 #define NOHZ_NEXT_KICK_BIT 3 -/* Run rebalance_domains() */ +/* Run sched_balance_domains() */ #define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT) /* Update blocked load */ #define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT) @@ -3445,13 +3446,19 @@ 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/stats.c b/kernel/sched/stats.c index 857f837f52cb..78e48f5426ee 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -113,7 +113,7 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p, * Bump this up when changing the output format or the meaning of an existing * format, so that tools can adapt (or abort) */ -#define SCHEDSTAT_VERSION 15 +#define SCHEDSTAT_VERSION 16 static int show_schedstat(struct seq_file *seq, void *v) { @@ -150,8 +150,7 @@ static int show_schedstat(struct seq_file *seq, void *v) seq_printf(seq, "domain%d %*pb", dcount++, cpumask_pr_args(sched_domain_span(sd))); - for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES; - itype++) { + for (itype = 0; itype < CPU_MAX_IDLE_TYPES; itype++) { seq_printf(seq, " %u %u %u %u %u %u %u %u", sd->lb_count[itype], sd->lb_balanced[itype], diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 99ea5986038c..a6994a1fcc90 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -322,7 +322,6 @@ static struct ctl_table sched_energy_aware_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static int __init sched_energy_aware_sysctl_init(void) @@ -1330,23 +1329,12 @@ next: } /* - * Asymmetric CPU capacity bits - */ -struct asym_cap_data { - struct list_head link; - unsigned long capacity; - unsigned long cpus[]; -}; - -/* * Set of available CPUs grouped by their corresponding capacities * Each list entry contains a CPU mask reflecting CPUs that share the same * capacity. * The lifespan of data is unlimited. */ -static LIST_HEAD(asym_cap_list); - -#define cpu_capacity_span(asym_data) to_cpumask((asym_data)->cpus) +LIST_HEAD(asym_cap_list); /* * Verify whether there is any CPU capacity asymmetry in a given sched domain. @@ -1386,21 +1374,39 @@ asym_cpu_capacity_classify(const struct cpumask *sd_span, } +static void free_asym_cap_entry(struct rcu_head *head) +{ + struct asym_cap_data *entry = container_of(head, struct asym_cap_data, rcu); + kfree(entry); +} + static inline void asym_cpu_capacity_update_data(int cpu) { unsigned long capacity = arch_scale_cpu_capacity(cpu); - struct asym_cap_data *entry = NULL; + struct asym_cap_data *insert_entry = NULL; + struct asym_cap_data *entry; + /* + * Search if capacity already exits. If not, track which the entry + * where we should insert to keep the list ordered descendingly. + */ list_for_each_entry(entry, &asym_cap_list, link) { if (capacity == entry->capacity) goto done; + else if (!insert_entry && capacity > entry->capacity) + insert_entry = list_prev_entry(entry, link); } entry = kzalloc(sizeof(*entry) + cpumask_size(), GFP_KERNEL); if (WARN_ONCE(!entry, "Failed to allocate memory for asymmetry data\n")) return; entry->capacity = capacity; - list_add(&entry->link, &asym_cap_list); + + /* If NULL then the new capacity is the smallest, add last. */ + if (!insert_entry) + list_add_tail_rcu(&entry->link, &asym_cap_list); + else + list_add_rcu(&entry->link, &insert_entry->link); done: __cpumask_set_cpu(cpu, cpu_capacity_span(entry)); } @@ -1423,8 +1429,8 @@ static void asym_cpu_capacity_scan(void) list_for_each_entry_safe(entry, next, &asym_cap_list, link) { if (cpumask_empty(cpu_capacity_span(entry))) { - list_del(&entry->link); - kfree(entry); + list_del_rcu(&entry->link); + call_rcu(&entry->rcu, free_asym_cap_entry); } } @@ -1434,8 +1440,8 @@ static void asym_cpu_capacity_scan(void) */ if (list_is_singular(&asym_cap_list)) { entry = list_first_entry(&asym_cap_list, typeof(*entry), link); - list_del(&entry->link); - kfree(entry); + list_del_rcu(&entry->link); + call_rcu(&entry->rcu, free_asym_cap_entry); } } @@ -1468,7 +1474,7 @@ static void set_domain_attribute(struct sched_domain *sd, } else request = attr->relax_domain_level; - if (sd->level > request) { + if (sd->level >= request) { /* Turn off idle balance on this domain: */ sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); } @@ -2347,7 +2353,7 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve static bool topology_span_sane(struct sched_domain_topology_level *tl, const struct cpumask *cpu_map, int cpu) { - int i; + int i = cpu + 1; /* NUMA levels are allowed to overlap */ if (tl->flags & SDTL_OVERLAP) @@ -2359,9 +2365,7 @@ static bool topology_span_sane(struct sched_domain_topology_level *tl, * breaking the sched_group lists - i.e. a later get_group() pass * breaks the linking done for an earlier span. */ - for_each_cpu(i, cpu_map) { - if (i == cpu) - continue; + for_each_cpu_from(i, cpu_map) { /* * We should 'and' all those masks with 'cpu_map' to exactly * match the topology we're about to build, but that can only @@ -2507,16 +2511,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att /* Attach the domains */ rcu_read_lock(); for_each_cpu(i, cpu_map) { - unsigned long capacity; - rq = cpu_rq(i); sd = *per_cpu_ptr(d.sd, i); - capacity = arch_scale_cpu_capacity(i); - /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */ - if (capacity > READ_ONCE(d.rd->max_cpu_capacity)) - WRITE_ONCE(d.rd->max_cpu_capacity, capacity); - cpu_attach_domain(sd, d.rd, i); if (lowest_flag_domain(i, SD_CLUSTER)) @@ -2530,10 +2527,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att if (has_cluster) static_branch_inc_cpuslocked(&sched_cluster_active); - if (rq && sched_debug_verbose) { - pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n", - cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); - } + if (rq && sched_debug_verbose) + pr_info("root domain span: %*pbl\n", cpumask_pr_args(cpu_map)); ret = 0; error: diff --git a/kernel/seccomp.c b/kernel/seccomp.c index aca7b437882e..e30b60b57614 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -2334,7 +2334,7 @@ static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) return true; } -static int read_actions_logged(struct ctl_table *ro_table, void *buffer, +static int read_actions_logged(const struct ctl_table *ro_table, void *buffer, size_t *lenp, loff_t *ppos) { char names[sizeof(seccomp_actions_avail)]; @@ -2352,7 +2352,7 @@ static int read_actions_logged(struct ctl_table *ro_table, void *buffer, return proc_dostring(&table, 0, buffer, lenp, ppos); } -static int write_actions_logged(struct ctl_table *ro_table, void *buffer, +static int write_actions_logged(const struct ctl_table *ro_table, void *buffer, size_t *lenp, loff_t *ppos, u32 *actions_logged) { char names[sizeof(seccomp_actions_avail)]; @@ -2445,7 +2445,6 @@ static struct ctl_table seccomp_sysctl_table[] = { .mode = 0644, .proc_handler = seccomp_actions_logged_handler, }, - { } }; static int __init seccomp_sysctl_init(void) diff --git a/kernel/signal.c b/kernel/signal.c index 7bdbcf1b78d0..01c4c46a51a8 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4840,7 +4840,6 @@ static struct ctl_table signal_debug_table[] = { .proc_handler = proc_dointvec }, #endif - { } }; static int __init init_signal_sysctls(void) diff --git a/kernel/softirq.c b/kernel/softirq.c index b315b21fb28c..02582017759a 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -508,7 +508,7 @@ static inline bool lockdep_softirq_start(void) { return false; } static inline void lockdep_softirq_end(bool in_hardirq) { } #endif -asmlinkage __visible void __softirq_entry __do_softirq(void) +static void handle_softirqs(bool ksirqd) { unsigned long end = jiffies + MAX_SOFTIRQ_TIME; unsigned long old_flags = current->flags; @@ -563,8 +563,7 @@ restart: pending >>= softirq_bit; } - if (!IS_ENABLED(CONFIG_PREEMPT_RT) && - __this_cpu_read(ksoftirqd) == current) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd) rcu_softirq_qs(); local_irq_disable(); @@ -584,6 +583,11 @@ restart: current_restore_flags(old_flags, PF_MEMALLOC); } +asmlinkage __visible void __softirq_entry __do_softirq(void) +{ + handle_softirqs(false); +} + /** * irq_enter_rcu - Enter an interrupt context with RCU watching */ @@ -921,7 +925,7 @@ static void run_ksoftirqd(unsigned int cpu) * We can safely run softirq on inline stack, as we are not deep * in the task stack here. */ - __do_softirq(); + handle_softirqs(true); ksoftirqd_run_end(); cond_resched(); return; diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 34c9d81eea94..0f9712584913 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -27,10 +27,10 @@ static int stack_erasing_sysctl(struct ctl_table *table, int write, int ret = 0; int state = !static_branch_unlikely(&stack_erasing_bypass); int prev_state = state; + struct ctl_table table_copy = *table; - table->data = &state; - table->maxlen = sizeof(int); - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + table_copy.data = &state; + ret = proc_dointvec_minmax(&table_copy, write, buffer, lenp, ppos); state = !!state; if (ret || !write || state == prev_state) return ret; @@ -54,7 +54,6 @@ static struct ctl_table stackleak_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static int __init stackleak_sysctls_init(void) diff --git a/kernel/sys.c b/kernel/sys.c index f8e543f1e38a..3a2df1bd9f64 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -146,6 +146,15 @@ #ifndef RISCV_V_GET_CONTROL # define RISCV_V_GET_CONTROL() (-EINVAL) #endif +#ifndef RISCV_SET_ICACHE_FLUSH_CTX +# define RISCV_SET_ICACHE_FLUSH_CTX(a, b) (-EINVAL) +#endif +#ifndef PPC_GET_DEXCR_ASPECT +# define PPC_GET_DEXCR_ASPECT(a, b) (-EINVAL) +#endif +#ifndef PPC_SET_DEXCR_ASPECT +# define PPC_SET_DEXCR_ASPECT(a, b, c) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -2408,8 +2417,11 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; - /* PARISC cannot allow mdwe as it needs writable stacks */ - if (IS_ENABLED(CONFIG_PARISC)) + /* + * EOPNOTSUPP might be more appropriate here in principle, but + * existing userspace depends on EINVAL specifically. + */ + if (!arch_memory_deny_write_exec_supported()) return -EINVAL; current_bits = get_current_mdwe(); @@ -2723,6 +2735,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_GET_MDWE: error = prctl_get_mdwe(arg2, arg3, arg4, arg5); break; + case PR_PPC_GET_DEXCR: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = PPC_GET_DEXCR_ASPECT(me, arg2); + break; + case PR_PPC_SET_DEXCR: + if (arg4 || arg5) + return -EINVAL; + error = PPC_SET_DEXCR_ASPECT(me, arg2, arg3); + break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; @@ -2757,6 +2779,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_RISCV_V_GET_CONTROL: error = RISCV_V_GET_CONTROL(); break; + case PR_RISCV_SET_ICACHE_FLUSH_CTX: + error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3); + break; default: error = -EINVAL; break; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 81cc974913bb..e0b917328cf9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2034,7 +2034,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_INT_MAX, }, #endif - { } }; static struct ctl_table vm_table[] = { @@ -2240,7 +2239,6 @@ static struct ctl_table vm_table[] = { .extra2 = (void *)&mmap_rnd_compat_bits_max, }, #endif - { } }; int __init sysctl_init_bases(void) diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index fc3b1a06c981..8ebb6d5a106b 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -202,7 +202,7 @@ config HIGH_RES_TIMERS the size of the kernel image. config CLOCKSOURCE_WATCHDOG_MAX_SKEW_US - int "Clocksource watchdog maximum allowable skew (in μs)" + int "Clocksource watchdog maximum allowable skew (in microseconds)" depends on CLOCKSOURCE_WATCHDOG range 50 1000 default 125 diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index a7ca458cdd9c..60a6484831b1 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -677,7 +677,7 @@ static ssize_t current_device_show(struct device *dev, raw_spin_lock_irq(&clockevents_lock); td = tick_get_tick_dev(dev); if (td && td->evtdev) - count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name); + count = sysfs_emit(buf, "%s\n", td->evtdev->name); raw_spin_unlock_irq(&clockevents_lock); return count; } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e5b260aa0e02..d25ba49e313c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -20,6 +20,16 @@ #include "tick-internal.h" #include "timekeeping_internal.h" +static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) +{ + u64 delta = clocksource_delta(end, start, cs->mask); + + if (likely(delta < cs->max_cycles)) + return clocksource_cyc2ns(delta, cs->mult, cs->shift); + + return mul_u64_u32_shr(delta, cs->mult, cs->shift); +} + /** * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks * @mult: pointer to mult variable @@ -222,8 +232,8 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { unsigned int nretries, max_retries; - u64 wd_end, wd_end2, wd_delta; int64_t wd_delay, wd_seq_delay; + u64 wd_end, wd_end2; max_retries = clocksource_get_max_watchdog_retry(); for (nretries = 0; nretries <= max_retries; nretries++) { @@ -234,9 +244,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, wd_end2 = watchdog->read(watchdog); local_irq_enable(); - wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask); - wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, - watchdog->shift); + wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end); if (wd_delay <= WATCHDOG_MAX_SKEW) { if (nretries > 1 || nretries >= max_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", @@ -254,8 +262,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, * report system busy, reinit the watchdog and skip the current * watchdog test. */ - wd_delta = clocksource_delta(wd_end2, wd_end, watchdog->mask); - wd_seq_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); + wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2); if (wd_seq_delay > WATCHDOG_MAX_SKEW/2) goto skip_test; } @@ -366,8 +373,7 @@ void clocksource_verify_percpu(struct clocksource *cs) delta = (csnow_end - csnow_mid) & cs->mask; if (delta < 0) cpumask_set_cpu(cpu, &cpus_ahead); - delta = clocksource_delta(csnow_end, csnow_begin, cs->mask); - cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + cs_nsec = cycles_to_nsec_safe(cs, csnow_begin, csnow_end); if (cs_nsec > cs_nsec_max) cs_nsec_max = cs_nsec; if (cs_nsec < cs_nsec_min) @@ -398,8 +404,8 @@ static inline void clocksource_reset_watchdog(void) static void clocksource_watchdog(struct timer_list *unused) { - u64 csnow, wdnow, cslast, wdlast, delta; int64_t wd_nsec, cs_nsec, interval; + u64 csnow, wdnow, cslast, wdlast; int next_cpu, reset_pending; struct clocksource *cs; enum wd_read_status read_ret; @@ -456,12 +462,8 @@ static void clocksource_watchdog(struct timer_list *unused) continue; } - delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask); - wd_nsec = clocksource_cyc2ns(delta, watchdog->mult, - watchdog->shift); - - delta = clocksource_delta(csnow, cs->cs_last, cs->mask); - cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + wd_nsec = cycles_to_nsec_safe(watchdog, cs->wd_last, wdnow); + cs_nsec = cycles_to_nsec_safe(cs, cs->cs_last, csnow); wdlast = cs->wd_last; /* save these in case we print them */ cslast = cs->cs_last; cs->cs_last = csnow; @@ -832,7 +834,7 @@ void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles) */ u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) { - u64 now, delta, nsec = 0; + u64 now, nsec = 0; if (!suspend_clocksource) return 0; @@ -847,12 +849,8 @@ u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) else now = suspend_clocksource->read(suspend_clocksource); - if (now > suspend_start) { - delta = clocksource_delta(now, suspend_start, - suspend_clocksource->mask); - nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult, - suspend_clocksource->shift); - } + if (now > suspend_start) + nsec = cycles_to_nsec_safe(suspend_clocksource, suspend_start, now); /* * Disable the suspend timer to save power if current clocksource is @@ -1336,7 +1334,7 @@ static ssize_t current_clocksource_show(struct device *dev, ssize_t count = 0; mutex_lock(&clocksource_mutex); - count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name); + count = sysfs_emit(buf, "%s\n", curr_clocksource->name); mutex_unlock(&clocksource_mutex); return count; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 70625dff62ce..492c14aac642 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -644,17 +644,12 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) /* * Is the high resolution mode active ? */ -static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) +static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } -static inline int hrtimer_hres_active(void) -{ - return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases)); -} - static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) @@ -678,7 +673,7 @@ static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, * set. So we'd effectively block all timers until the T2 event * fires. */ - if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) + if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); @@ -789,12 +784,12 @@ static void retrigger_next_event(void *arg) * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. */ - if (!__hrtimer_hres_active(base) && !tick_nohz_active) + if (!hrtimer_hres_active(base) && !tick_nohz_active) return; raw_spin_lock(&base->lock); hrtimer_update_base(base); - if (__hrtimer_hres_active(base)) + if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); @@ -951,7 +946,7 @@ void clock_was_set(unsigned int bases) cpumask_var_t mask; int cpu; - if (!__hrtimer_hres_active(cpu_base) && !tick_nohz_active) + if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { @@ -1491,7 +1486,7 @@ u64 hrtimer_get_next_event(void) raw_spin_lock_irqsave(&cpu_base->lock, flags); - if (!__hrtimer_hres_active(cpu_base)) + if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); @@ -1514,7 +1509,7 @@ u64 hrtimer_next_event_without(const struct hrtimer *exclude) raw_spin_lock_irqsave(&cpu_base->lock, flags); - if (__hrtimer_hres_active(cpu_base)) { + if (hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { @@ -1875,25 +1870,7 @@ retry: tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } - -/* called with interrupts disabled */ -static inline void __hrtimer_peek_ahead_timers(void) -{ - struct tick_device *td; - - if (!hrtimer_hres_active()) - return; - - td = this_cpu_ptr(&tick_cpu_device); - if (td && td->evtdev) - hrtimer_interrupt(td->evtdev); -} - -#else /* CONFIG_HIGH_RES_TIMERS */ - -static inline void __hrtimer_peek_ahead_timers(void) { } - -#endif /* !CONFIG_HIGH_RES_TIMERS */ +#endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy @@ -1904,7 +1881,7 @@ void hrtimer_run_queues(void) unsigned long flags; ktime_t now; - if (__hrtimer_hres_active(cpu_base)) + if (hrtimer_hres_active(cpu_base)) return; /* diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 9de66bbbb3d1..4782edcbe7b9 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -129,15 +129,17 @@ static int posix_clock_open(struct inode *inode, struct file *fp) goto out; } pccontext->clk = clk; - fp->private_data = pccontext; - if (clk->ops.open) + if (clk->ops.open) { err = clk->ops.open(pccontext, fp->f_mode); - else - err = 0; - - if (!err) { - get_device(clk->dev); + if (err) { + kfree(pccontext); + goto out; + } } + + fp->private_data = pccontext; + get_device(clk->dev); + err = 0; out: up_read(&clk->rwsem); return err; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index fb0fdec8719a..d88b13076b79 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -7,6 +7,7 @@ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> @@ -84,7 +85,7 @@ int tick_is_oneshot_available(void) */ static void tick_periodic(int cpu) { - if (tick_do_timer_cpu == cpu) { + if (READ_ONCE(tick_do_timer_cpu) == cpu) { raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); @@ -215,8 +216,8 @@ static void tick_setup_device(struct tick_device *td, * If no cpu took the do_timer update, assign it to * this cpu: */ - if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - tick_do_timer_cpu = cpu; + if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) { + WRITE_ONCE(tick_do_timer_cpu, cpu); tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* @@ -232,7 +233,7 @@ static void tick_setup_device(struct tick_device *td, !tick_nohz_full_cpu(cpu)) { tick_take_do_timer_from_boot(); tick_do_timer_boot_cpu = -1; - WARN_ON(tick_do_timer_cpu != cpu); + WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu); #endif } @@ -406,10 +407,10 @@ void tick_assert_timekeeping_handover(void) int tick_cpu_dying(unsigned int dying_cpu) { /* - * If the current CPU is the timekeeper, it's the only one that - * can safely hand over its duty. Also all online CPUs are in - * stop machine, guaranteed not to be idle, therefore it's safe - * to pick any online successor. + * If the current CPU is the timekeeper, it's the only one that can + * safely hand over its duty. Also all online CPUs are in stop + * machine, guaranteed not to be idle, therefore there is no + * concurrency and it's safe to pick any online successor. */ if (tick_do_timer_cpu == dying_cpu) tick_do_timer_cpu = cpumask_first(cpu_online_mask); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 269e21590df5..71a792cd8936 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -8,6 +8,7 @@ * * Started by: Thomas Gleixner and Ingo Molnar */ +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> @@ -204,7 +205,7 @@ static inline void tick_sched_flag_clear(struct tick_sched *ts, static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { - int cpu = smp_processor_id(); + int tick_cpu, cpu = smp_processor_id(); /* * Check if the do_timer duty was dropped. We don't care about @@ -216,16 +217,18 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ - if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && - unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { + tick_cpu = READ_ONCE(tick_do_timer_cpu); + + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif - tick_do_timer_cpu = cpu; + WRITE_ONCE(tick_do_timer_cpu, cpu); + tick_cpu = cpu; } /* Check if jiffies need an update */ - if (tick_do_timer_cpu == cpu) + if (tick_cpu == cpu) tick_do_update_jiffies64(now); /* @@ -610,7 +613,7 @@ bool tick_nohz_cpu_hotpluggable(unsigned int cpu) * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ - if (tick_nohz_full_running && tick_do_timer_cpu == cpu) + if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu) return false; return true; } @@ -697,6 +700,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu) /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted + * @now: current ktime_t * * Called from interrupt entry when the CPU was idle * @@ -794,7 +798,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * This function returns -1 if NOHZ is not enabled. + * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { @@ -820,7 +824,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * This function returns -1 if NOHZ is not enabled. + * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { @@ -890,6 +894,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, delta, expires; unsigned long basejiff; + int tick_cpu; basemono = get_jiffies_update(&basejiff); ts->last_jiffies = basejiff; @@ -946,9 +951,9 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); - if (cpu != tick_do_timer_cpu && - (tick_do_timer_cpu != TICK_DO_TIMER_NONE || - !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) + tick_cpu = READ_ONCE(tick_do_timer_cpu); + if (tick_cpu != cpu && + (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) delta = KTIME_MAX; /* Calculate the next expiry time */ @@ -969,6 +974,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) unsigned long basejiff = ts->last_jiffies; u64 basemono = ts->timer_expires_base; bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED); + int tick_cpu; u64 expires; /* Make sure we won't be trying to stop it twice in a row. */ @@ -1006,10 +1012,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * do_timer() never gets invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ - if (cpu == tick_do_timer_cpu) { - tick_do_timer_cpu = TICK_DO_TIMER_NONE; + tick_cpu = READ_ONCE(tick_do_timer_cpu); + if (tick_cpu == cpu) { + WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE); tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST); - } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { + } else if (tick_cpu != TICK_DO_TIMER_NONE) { tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST); } @@ -1172,15 +1179,17 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; if (tick_nohz_full_enabled()) { + int tick_cpu = READ_ONCE(tick_do_timer_cpu); + /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ - if (tick_do_timer_cpu == cpu) + if (tick_cpu == cpu) return false; /* Should not happen for nohz-full */ - if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) + if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE)) return false; } @@ -1287,6 +1296,8 @@ void tick_nohz_irq_exit(void) /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run + * + * Return: %true if the tick handler has run, otherwise %false */ bool tick_nohz_idle_got_tick(void) { @@ -1305,6 +1316,8 @@ bool tick_nohz_idle_got_tick(void) * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled + * + * Return: the next expiration time */ ktime_t tick_nohz_get_next_hrtimer(void) { @@ -1320,6 +1333,8 @@ ktime_t tick_nohz_get_next_hrtimer(void) * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. + * + * Return: the expected length of the current sleep */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { @@ -1357,8 +1372,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. + * @cpu: target CPU number * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for @cpu */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { @@ -1371,6 +1389,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for the current CPU */ unsigned long tick_nohz_get_idle_calls(void) { @@ -1559,7 +1579,7 @@ early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer - * @mode: tick_nohz_mode to setup for + * @hrtimer: whether to use the hrtimer or not */ void tick_setup_sched_timer(bool hrtimer) { diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index e11c4dc65bcb..b4a7822f495d 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -46,8 +46,8 @@ struct tick_device { * @next_tick: Next tick to be fired when in dynticks mode. * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_waketime: Time when the idle was interrupted + * @idle_sleeptime_seq: sequence counter for data consistency * @idle_entrytime: Time when the idle call was entered - * @nohz_mode: Mode - one state of tick_nohz_mode * @last_jiffies: Base jiffies snapshot when next event was last computed * @timer_expires_base: Base time clock monotonic for @timer_expires * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b58dffc58a8f..4e18db1819f8 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -237,7 +237,9 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) } } -static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles); + +static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; @@ -264,34 +266,23 @@ static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ - if (unlikely((~delta & mask) < (mask >> 3))) { + if (unlikely((~delta & mask) < (mask >> 3))) tk->underflow_seen = 1; - delta = 0; - } - /* Cap delta value to the max_cycles values to avoid mult overflows */ - if (unlikely(delta > max)) { + /* Check for multiplication overflows */ + if (unlikely(delta > max)) tk->overflow_seen = 1; - delta = tkr->clock->max_cycles; - } - return delta; + /* timekeeping_cycles_to_ns() handles both under and overflow */ + return timekeeping_cycles_to_ns(tkr, now); } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } -static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) +static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { - u64 cycle_now, delta; - - /* read clocksource */ - cycle_now = tk_clock_read(tkr); - - /* calculate the delta since the last update_wall_time */ - delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); - - return delta; + BUG(); } #endif @@ -370,32 +361,46 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) } /* Timekeeper helper functions. */ +static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) +{ + return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); +} -static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { - u64 nsec; + /* Calculate the delta since the last update_wall_time() */ + u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; - nsec = delta * tkr->mult + tkr->xtime_nsec; - nsec >>= tkr->shift; + /* + * This detects both negative motion and the case where the delta + * overflows the multiplication with tkr->mult. + */ + if (unlikely(delta > tkr->clock->max_cycles)) { + /* + * Handle clocksource inconsistency between CPUs to prevent + * time from going backwards by checking for the MSB of the + * mask being set in the delta. + */ + if (delta & ~(mask >> 1)) + return tkr->xtime_nsec >> tkr->shift; + + return delta_to_ns_safe(tkr, delta); + } - return nsec; + return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } -static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) +static __always_inline u64 __timekeeping_get_ns(const struct tk_read_base *tkr) { - u64 delta; - - delta = timekeeping_get_delta(tkr); - return timekeeping_delta_to_ns(tkr, delta); + return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } -static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) +static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { - u64 delta; + if (IS_ENABLED(CONFIG_DEBUG_TIMEKEEPING)) + return timekeeping_debug_get_ns(tkr); - /* calculate the delta since the last update_wall_time */ - delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); - return timekeeping_delta_to_ns(tkr, delta); + return __timekeeping_get_ns(tkr); } /** @@ -431,14 +436,6 @@ static void update_fast_timekeeper(const struct tk_read_base *tkr, memcpy(base + 1, base, sizeof(*base)); } -static __always_inline u64 fast_tk_get_delta_ns(struct tk_read_base *tkr) -{ - u64 delta, cycles = tk_clock_read(tkr); - - delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); - return timekeeping_delta_to_ns(tkr, delta); -} - static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; @@ -449,7 +446,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); - now += fast_tk_get_delta_ns(tkr); + now += __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return now; @@ -565,7 +562,7 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); - delta = fast_tk_get_delta_ns(tkr); + delta = __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) @@ -800,10 +797,15 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; - tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; - tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult; + while (delta > 0) { + u64 max = tk->tkr_mono.clock->max_cycles; + u64 incr = delta < max ? delta : max; - tk_normalize_xtime(tk); + tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; + tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; + tk_normalize_xtime(tk); + delta -= incr; + } } /** diff --git a/kernel/time/timer.c b/kernel/time/timer.c index dee29f1f5b75..48288dd4a102 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -64,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of - * LVL_SIZE buckets. Each level is driven by its own clock and therefor each + * LVL_SIZE buckets. Each level is driven by its own clock and therefore each * level has a different granularity. * - * The level granularity is: LVL_CLK_DIV ^ lvl + * The level granularity is: LVL_CLK_DIV ^ level * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and - * therefor the granularity becomes. + * therefore the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading @@ -207,7 +207,7 @@ EXPORT_SYMBOL(jiffies_64); * struct timer_base - Per CPU timer base (number of base depends on config) * @lock: Lock protecting the timer_base * @running_timer: When expiring timers, the lock is dropped. To make - * sure not to race agains deleting/modifying a + * sure not to race against deleting/modifying a * currently running timer, the pointer is set to the * timer, which expires at the moment. If no timer is * running, the pointer is NULL. @@ -312,7 +312,6 @@ static struct ctl_table timer_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static int __init timer_sysctl_init(void) @@ -737,7 +736,7 @@ static bool timer_is_static_object(void *addr) } /* - * fixup_init is called when: + * timer_fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) @@ -761,7 +760,7 @@ static void stub_timer(struct timer_list *unused) } /* - * fixup_activate is called when: + * timer_fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ @@ -783,7 +782,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) } /* - * fixup_free is called when: + * timer_fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) @@ -801,7 +800,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state) } /* - * fixup_assert_init is called when: + * timer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) @@ -914,7 +913,7 @@ static void do_init_timer(struct timer_list *timer, * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * - * init_timer_key() must be done to a timer prior calling *any* of the + * init_timer_key() must be done to a timer prior to calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, @@ -1417,7 +1416,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown) * If @shutdown is set then the lock has to be taken whether the * timer is pending or not to protect against a concurrent rearm * which might hit between the lockless pending check and the lock - * aquisition. By taking the lock it is ensured that such a newly + * acquisition. By taking the lock it is ensured that such a newly * enqueued timer is dequeued and cannot end up with * timer->function == NULL in the expiry code. * @@ -2306,7 +2305,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, /* * When timer base is not set idle, undo the effect of - * tmigr_cpu_deactivate() to prevent inconsitent states - active + * tmigr_cpu_deactivate() to prevent inconsistent states - active * timer base but inactive timer migration hierarchy. * * When timer base was already marked idle, nothing will be @@ -2488,7 +2487,7 @@ void update_process_times(int user_tick) if (in_irq()) irq_work_tick(); #endif - scheduler_tick(); + sched_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c63a0afdcebe..84413114db5c 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -751,6 +751,33 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, first_childevt = evt = data->evt; + /* + * Walking the hierarchy is required in any case when a + * remote expiry was done before. This ensures to not lose + * already queued events in non active groups (see section + * "Required event and timerqueue update after a remote + * expiry" in the documentation at the top). + * + * The two call sites which are executed without a remote expiry + * before, are not prevented from propagating changes through + * the hierarchy by the return: + * - When entering this path by tmigr_new_timer(), @evt->ignore + * is never set. + * - tmigr_inactive_up() takes care of the propagation by + * itself and ignores the return value. But an immediate + * return is possible if there is a parent, sparing group + * locking at this level, because the upper walking call to + * the parent will take care about removing this event from + * within the group and update next_expiry accordingly. + * + * However if there is no parent, ie: the hierarchy has only a + * single level so @group is the top level group, make sure the + * first event information of the group is updated properly and + * also handled properly, so skip this fast return path. + */ + if (evt->ignore && !remote && group->parent) + return true; + raw_spin_lock(&group->lock); childstate.state = 0; @@ -762,8 +789,11 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, * queue when the expiry time changed only or when it could be ignored. */ if (timerqueue_node_queued(&evt->nextevt)) { - if ((evt->nextevt.expires == nextexp) && !evt->ignore) + if ((evt->nextevt.expires == nextexp) && !evt->ignore) { + /* Make sure not to miss a new CPU event with the same expiry */ + evt->cpu = first_childevt->cpu; goto check_toplvl; + } if (!timerqueue_del(&group->events, &evt->nextevt)) WRITE_ONCE(group->next_expiry, KTIME_MAX); @@ -1566,7 +1596,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) } while (i < tmigr_hierarchy_levels); - do { + while (i > 0) { group = stack[--i]; if (err < 0) { @@ -1615,7 +1645,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) tmigr_connect_child_parent(child, group); } } - } while (i > 0); + } kfree(stack); diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index f0d5062d9cbc..9193d6133e5d 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -22,10 +22,16 @@ static inline void update_vdso_data(struct vdso_data *vdata, u64 nsec, sec; vdata[CS_HRES_COARSE].cycle_last = tk->tkr_mono.cycle_last; +#ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT + vdata[CS_HRES_COARSE].max_cycles = tk->tkr_mono.clock->max_cycles; +#endif vdata[CS_HRES_COARSE].mask = tk->tkr_mono.mask; vdata[CS_HRES_COARSE].mult = tk->tkr_mono.mult; vdata[CS_HRES_COARSE].shift = tk->tkr_mono.shift; vdata[CS_RAW].cycle_last = tk->tkr_raw.cycle_last; +#ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT + vdata[CS_RAW].max_cycles = tk->tkr_raw.clock->max_cycles; +#endif vdata[CS_RAW].mask = tk->tkr_raw.mask; vdata[CS_RAW].mult = tk->tkr_raw.mult; vdata[CS_RAW].shift = tk->tkr_raw.shift; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 61c541c36596..166ad5444eea 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -163,7 +163,7 @@ config TRACING select BINARY_PRINTF select EVENT_TRACING select TRACE_CLOCK - select TASKS_RCU if PREEMPTION + select NEED_TASKS_RCU config GENERIC_TRACER bool @@ -204,7 +204,7 @@ config FUNCTION_TRACER select GENERIC_TRACER select CONTEXT_SWITCH_TRACER select GLOB - select TASKS_RCU if PREEMPTION + select NEED_TASKS_RCU select TASKS_RUDE_RCU help Enable the kernel to trace every kernel function. This is done @@ -965,7 +965,7 @@ config FTRACE_RECORD_RECURSION config FTRACE_RECORD_RECURSION_SIZE int "Max number of recursed functions to record" - default 128 + default 128 depends on FTRACE_RECORD_RECURSION help This defines the limit of number of functions that can be @@ -974,6 +974,19 @@ config FTRACE_RECORD_RECURSION_SIZE This file can be reset, but the limit can not change in size at runtime. +config FTRACE_VALIDATE_RCU_IS_WATCHING + bool "Validate RCU is on during ftrace execution" + depends on FUNCTION_TRACER + depends on ARCH_WANTS_NO_INSTR + help + All callbacks that attach to the function tracing have some sort of + protection against recursion. This option is only to verify that + ftrace (and other users of ftrace_test_recursion_trylock()) are not + called outside of RCU, as if they are, it can cause a race. But it + also has a noticeable overhead when enabled. + + If unsure, say N + config RING_BUFFER_RECORD_RECURSION bool "Record functions that recurse in the ring buffer" depends on FTRACE_RECORD_RECURSION diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index d5d94510afd3..8fd292d34d89 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -524,8 +524,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!buts->buf_size || !buts->buf_nr) return -EINVAL; - strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); - buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; + strscpy_pad(buts->name, name, BLKTRACE_BDEV_SIZE); /* * some device names have larger paths - convert the slashes diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0a5c4efc73c3..f5154c051d2c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1053,9 +1053,15 @@ static unsigned long get_entry_ip(unsigned long fentry_ip) { u32 instr; - /* Being extra safe in here in case entry ip is on the page-edge. */ - if (get_kernel_nofault(instr, (u32 *) fentry_ip - 1)) - return fentry_ip; + /* We want to be extra safe in case entry ip is on the page edge, + * but otherwise we need to avoid get_kernel_nofault()'s overhead. + */ + if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) { + if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE))) + return fentry_ip; + } else { + instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE); + } if (is_endbr(instr)) fentry_ip -= ENDBR_INSN_SIZE; return fentry_ip; @@ -1182,9 +1188,6 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_tracing = { BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) { -#ifndef CONFIG_X86 - return -ENOENT; -#else static const u32 br_entry_size = sizeof(struct perf_branch_entry); u32 entry_cnt = size / br_entry_size; @@ -1197,7 +1200,6 @@ BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) return -ENOENT; return entry_cnt * br_entry_size; -#endif } static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { @@ -1525,8 +1527,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; case BPF_FUNC_get_current_task_btf: @@ -1582,8 +1582,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_send_signal_thread_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; - case BPF_FUNC_get_ns_current_pid_tgid: - return &bpf_get_ns_current_pid_tgid_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: @@ -1633,6 +1631,17 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static bool is_kprobe_multi(const struct bpf_prog *prog) +{ + return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI || + prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; +} + +static inline bool is_kprobe_session(const struct bpf_prog *prog) +{ + return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; +} + static const struct bpf_func_proto * kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1648,13 +1657,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_override_return_proto; #endif case BPF_FUNC_get_func_ip: - if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI) + if (is_kprobe_multi(prog)) return &bpf_get_func_ip_proto_kprobe_multi; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI) return &bpf_get_func_ip_proto_uprobe_multi; return &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: - if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI) + if (is_kprobe_multi(prog)) return &bpf_get_attach_cookie_proto_kmulti; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI) return &bpf_get_attach_cookie_proto_umulti; @@ -2008,6 +2017,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; + case BPF_FUNC_get_attach_cookie: + return &bpf_get_attach_cookie_proto_tracing; default: return bpf_tracing_func_proto(func_id, prog); } @@ -2070,6 +2081,9 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_func_arg_cnt: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; case BPF_FUNC_get_attach_cookie: + if (prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_RAW_TP) + return &bpf_get_attach_cookie_proto_tracing; return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); @@ -2370,16 +2384,26 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) } static __always_inline -void __bpf_trace_run(struct bpf_prog *prog, u64 *args) +void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args) { + struct bpf_prog *prog = link->link.prog; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; + cant_sleep(); if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); goto out; } + + run_ctx.bpf_cookie = link->cookie; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + rcu_read_lock(); (void) bpf_prog_run(prog, args); rcu_read_unlock(); + + bpf_reset_run_ctx(old_run_ctx); out: this_cpu_dec(*(prog->active)); } @@ -2408,12 +2432,12 @@ out: #define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 #define BPF_TRACE_DEFN_x(x) \ - void bpf_trace_run##x(struct bpf_prog *prog, \ + void bpf_trace_run##x(struct bpf_raw_tp_link *link, \ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \ { \ u64 args[x]; \ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \ - __bpf_trace_run(prog, args); \ + __bpf_trace_run(link, args); \ } \ EXPORT_SYMBOL_GPL(bpf_trace_run##x) BPF_TRACE_DEFN_x(1); @@ -2429,9 +2453,10 @@ BPF_TRACE_DEFN_x(10); BPF_TRACE_DEFN_x(11); BPF_TRACE_DEFN_x(12); -static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { struct tracepoint *tp = btp->tp; + struct bpf_prog *prog = link->link.prog; /* * check that program doesn't access arguments beyond what's @@ -2443,18 +2468,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * if (prog->aux->max_tp_access > btp->writable_size) return -EINVAL; - return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, - prog); + return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, link); } -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { - return __bpf_probe_register(btp, prog); -} - -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) -{ - return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, link); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -2577,6 +2596,12 @@ static int __init bpf_event_init(void) fs_initcall(bpf_event_init); #endif /* CONFIG_MODULES */ +struct bpf_session_run_ctx { + struct bpf_run_ctx run_ctx; + bool is_return; + void *data; +}; + #ifdef CONFIG_FPROBE struct bpf_kprobe_multi_link { struct bpf_link link; @@ -2590,7 +2615,7 @@ struct bpf_kprobe_multi_link { }; struct bpf_kprobe_multi_run_ctx { - struct bpf_run_ctx run_ctx; + struct bpf_session_run_ctx session_ctx; struct bpf_kprobe_multi_link *link; unsigned long entry_ip; }; @@ -2728,7 +2753,7 @@ 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, }; @@ -2769,7 +2794,8 @@ static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) if (WARN_ON_ONCE(!ctx)) return 0; - run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); + run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, + session_ctx.run_ctx); link = run_ctx->link; if (!link->cookies) return 0; @@ -2786,15 +2812,21 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { struct bpf_kprobe_multi_run_ctx *run_ctx; - run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); + run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, + session_ctx.run_ctx); return run_ctx->entry_ip; } static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, - unsigned long entry_ip, struct pt_regs *regs) + unsigned long entry_ip, struct pt_regs *regs, + bool is_return, void *data) { struct bpf_kprobe_multi_run_ctx run_ctx = { + .session_ctx = { + .is_return = is_return, + .data = data, + }, .link = link, .entry_ip = entry_ip, }; @@ -2809,7 +2841,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, migrate_disable(); rcu_read_lock(); - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); @@ -2826,10 +2858,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, void *data) { struct bpf_kprobe_multi_link *link; + int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); - return 0; + err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); + return is_kprobe_session(link->link.prog) ? err : 0; } static void @@ -2840,7 +2873,7 @@ kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); + kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) @@ -2973,7 +3006,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (sizeof(u64) != sizeof(void *)) return -EOPNOTSUPP; - if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI) + if (!is_kprobe_multi(prog)) return -EINVAL; flags = attr->link_create.kprobe_multi.flags; @@ -3054,10 +3087,12 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (err) goto error; - if (flags & BPF_F_KPROBE_MULTI_RETURN) - link->fp.exit_handler = kprobe_multi_link_exit_handler; - else + if (!(flags & BPF_F_KPROBE_MULTI_RETURN)) link->fp.entry_handler = kprobe_multi_link_handler; + if ((flags & BPF_F_KPROBE_MULTI_RETURN) || is_kprobe_session(prog)) + link->fp.exit_handler = kprobe_multi_link_exit_handler; + if (is_kprobe_session(prog)) + link->fp.entry_data_size = sizeof(u64); link->addrs = addrs; link->cookies = cookies; @@ -3157,6 +3192,9 @@ 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) @@ -3164,9 +3202,6 @@ 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); } @@ -3242,7 +3277,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, 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, }; @@ -3483,3 +3518,54 @@ static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx) return 0; } #endif /* CONFIG_UPROBES */ + +#ifdef CONFIG_FPROBE +__bpf_kfunc_start_defs(); + +__bpf_kfunc bool bpf_session_is_return(void) +{ + struct bpf_session_run_ctx *session_ctx; + + session_ctx = container_of(current->bpf_ctx, struct bpf_session_run_ctx, run_ctx); + return session_ctx->is_return; +} + +__bpf_kfunc __u64 *bpf_session_cookie(void) +{ + struct bpf_session_run_ctx *session_ctx; + + session_ctx = container_of(current->bpf_ctx, struct bpf_session_run_ctx, run_ctx); + return session_ctx->data; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(kprobe_multi_kfunc_set_ids) +BTF_ID_FLAGS(func, bpf_session_is_return) +BTF_ID_FLAGS(func, bpf_session_cookie) +BTF_KFUNCS_END(kprobe_multi_kfunc_set_ids) + +static int bpf_kprobe_multi_filter(const struct bpf_prog *prog, u32 kfunc_id) +{ + if (!btf_id_set8_contains(&kprobe_multi_kfunc_set_ids, kfunc_id)) + return 0; + + if (!is_kprobe_session(prog)) + return -EACCES; + + return 0; +} + +static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = { + .owner = THIS_MODULE, + .set = &kprobe_multi_kfunc_set_ids, + .filter = bpf_kprobe_multi_filter, +}; + +static int __init bpf_kprobe_multi_kfuncs_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set); +} + +late_initcall(bpf_kprobe_multi_kfuncs_init); +#endif diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index c83c005e654e..a130b2d898f7 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -125,17 +125,6 @@ int function_graph_enter(unsigned long ret, unsigned long func, { struct ftrace_graph_ent trace; -#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS - /* - * Skip graph tracing if the return location is served by direct trampoline, - * since call sequence and return addresses are unpredictable anyway. - * Ex: BPF trampoline may call original function and may skip frame - * depending on type of BPF programs attached. - */ - if (ftrace_direct_func_count && - ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE)) - return -EBUSY; -#endif trace.func = func; trace.depth = ++current->curr_ret_depth; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index da1710499698..65208d3b5ed9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1595,12 +1595,15 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) unsigned long ftrace_location_range(unsigned long start, unsigned long end) { struct dyn_ftrace *rec; + unsigned long ip = 0; + rcu_read_lock(); rec = lookup_rec(start, end); if (rec) - return rec->ip; + ip = rec->ip; + rcu_read_unlock(); - return 0; + return ip; } /** @@ -1614,25 +1617,22 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end) */ unsigned long ftrace_location(unsigned long ip) { - struct dyn_ftrace *rec; + unsigned long loc; unsigned long offset; unsigned long size; - rec = lookup_rec(ip, ip); - if (!rec) { + loc = ftrace_location_range(ip, ip); + if (!loc) { if (!kallsyms_lookup_size_offset(ip, &size, &offset)) goto out; /* map sym+0 to __fentry__ */ if (!offset) - rec = lookup_rec(ip, ip + size - 1); + loc = ftrace_location_range(ip, ip + size - 1); } - if (rec) - return rec->ip; - out: - return 0; + return loc; } /** @@ -2538,7 +2538,6 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec) /* Protected by rcu_tasks for reading, and direct_mutex for writing */ static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH; static DEFINE_MUTEX(direct_mutex); -int ftrace_direct_func_count; /* * Search the direct_functions hash to see if the given instruction pointer @@ -3157,8 +3156,7 @@ out: * synchronize_rcu_tasks() will wait for those tasks to * execute and either schedule voluntarily or enter user space. */ - if (IS_ENABLED(CONFIG_PREEMPTION)) - synchronize_rcu_tasks(); + synchronize_rcu_tasks(); ftrace_trampoline_free(ops); } @@ -4202,12 +4200,12 @@ static int add_rec_by_index(struct ftrace_hash *hash, struct ftrace_glob *func_g, int clear_filter) { - long index = simple_strtoul(func_g->search, NULL, 0); + long index; struct ftrace_page *pg; struct dyn_ftrace *rec; /* The index starts at 1 */ - if (--index < 0) + if (kstrtoul(func_g->search, 0, &index) || --index < 0) return 0; do_for_each_ftrace_rec(pg, rec) { @@ -5318,14 +5316,6 @@ ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS -struct ftrace_direct_func { - struct list_head next; - unsigned long addr; - int count; -}; - -static LIST_HEAD(ftrace_direct_funcs); - static int register_ftrace_function_nolock(struct ftrace_ops *ops); /* @@ -5366,6 +5356,13 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long } } +static void register_ftrace_direct_cb(struct rcu_head *rhp) +{ + struct ftrace_hash *fhp = container_of(rhp, struct ftrace_hash, rcu); + + free_ftrace_hash(fhp); +} + /** * register_ftrace_direct - Call a custom trampoline directly * for multiple functions registered in @ops @@ -5464,10 +5461,8 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) out_unlock: mutex_unlock(&direct_mutex); - if (free_hash && free_hash != EMPTY_HASH) { - synchronize_rcu_tasks(); - free_ftrace_hash(free_hash); - } + if (free_hash && free_hash != EMPTY_HASH) + call_rcu_tasks(&free_hash->rcu, register_ftrace_direct_cb); if (new_hash) free_ftrace_hash(new_hash); @@ -5817,9 +5812,8 @@ __setup("ftrace_graph_notrace=", set_graph_notrace_function); static int __init set_graph_max_depth_function(char *str) { - if (!str) + if (!str || kstrtouint(str, 0, &fgraph_max_depth)) return 0; - fgraph_max_depth = simple_strtoul(str, NULL, 0); return 1; } __setup("ftrace_graph_max_depth=", set_graph_max_depth_function); @@ -6596,6 +6590,8 @@ static int ftrace_process_locs(struct module *mod, /* We should have used all pages unless we skipped some */ if (pg_unuse) { WARN_ON(!skipped); + /* Need to synchronize with ftrace_location_range() */ + synchronize_rcu(); ftrace_free_pages(pg_unuse); } return ret; @@ -6809,6 +6805,9 @@ void ftrace_release_mod(struct module *mod) out_unlock: mutex_unlock(&ftrace_lock); + /* Need to synchronize with ftrace_location_range() */ + if (tmp_page) + synchronize_rcu(); for (pg = tmp_page; pg; pg = tmp_page) { /* Needs to be called outside of ftrace_lock */ @@ -7142,6 +7141,7 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) unsigned long start = (unsigned long)(start_ptr); unsigned long end = (unsigned long)(end_ptr); struct ftrace_page **last_pg = &ftrace_pages_start; + struct ftrace_page *tmp_page = NULL; struct ftrace_page *pg; struct dyn_ftrace *rec; struct dyn_ftrace key; @@ -7183,12 +7183,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) ftrace_update_tot_cnt--; if (!pg->index) { *last_pg = pg->next; - if (pg->records) { - free_pages((unsigned long)pg->records, pg->order); - ftrace_number_of_pages -= 1 << pg->order; - } - ftrace_number_of_groups--; - kfree(pg); + pg->next = tmp_page; + tmp_page = pg; pg = container_of(last_pg, struct ftrace_page, next); if (!(*last_pg)) ftrace_pages = pg; @@ -7205,6 +7201,11 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) clear_func_from_hashes(func); kfree(func); } + /* Need to synchronize with ftrace_location_range() */ + if (tmp_page) { + synchronize_rcu(); + ftrace_free_pages(tmp_page); + } } void __init ftrace_free_init_mem(void) @@ -7895,6 +7896,7 @@ void ftrace_kill(void) ftrace_disabled = 1; ftrace_enabled = 0; ftrace_trace_function = ftrace_stub; + kprobe_ftrace_kill(); } /** @@ -8270,7 +8272,6 @@ static struct ctl_table ftrace_sysctls[] = { .mode = 0644, .proc_handler = ftrace_enable_sysctl, }, - {} }; static int __init ftrace_sysctl_init(void) diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index fa03094e9e69..30d224946881 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -166,6 +166,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh) if (unlikely(!handler)) return NULL; +#if defined(CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING) || defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE) /* * This expects the caller will set up a rethook on a function entry. * When the function returns, the rethook will eventually be reclaimed @@ -174,6 +175,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh) */ if (unlikely(!rcu_is_watching())) return NULL; +#endif return (struct rethook_node *)objpool_pop(&rh->pool); } @@ -248,7 +250,7 @@ unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame if (WARN_ON_ONCE(!cur)) return 0; - if (WARN_ON_ONCE(tsk != current && task_is_running(tsk))) + if (tsk != current && task_is_running(tsk)) return 0; do { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 25476ead681b..7345a8b625fb 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -9,6 +9,7 @@ #include <linux/ring_buffer.h> #include <linux/trace_clock.h> #include <linux/sched/clock.h> +#include <linux/cacheflush.h> #include <linux/trace_seq.h> #include <linux/spinlock.h> #include <linux/irq_work.h> @@ -26,6 +27,7 @@ #include <linux/list.h> #include <linux/cpu.h> #include <linux/oom.h> +#include <linux/mm.h> #include <asm/local64.h> #include <asm/local.h> @@ -312,6 +314,8 @@ static u64 rb_event_time_stamp(struct ring_buffer_event *event) /* Missed count stored at end */ #define RB_MISSED_STORED (1 << 30) +#define RB_MISSED_MASK (3 << 30) + struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ @@ -338,6 +342,7 @@ struct buffer_page { local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ unsigned order; /* order of the page */ + u32 id; /* ID for external mapping */ struct buffer_data_page *page; /* Actual data page */ }; @@ -484,6 +489,12 @@ struct ring_buffer_per_cpu { u64 read_stamp; /* pages removed since last reset */ unsigned long pages_removed; + + unsigned int mapped; + struct mutex mapping_lock; + unsigned long *subbuf_ids; /* ID to subbuf VA */ + struct trace_buffer_meta *meta_page; + /* ring buffer pages to update, > 0 to add, < 0 to remove */ long nr_pages_to_update; struct list_head new_pages; /* new pages to add */ @@ -1393,7 +1404,6 @@ 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. @@ -1430,8 +1440,9 @@ 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); } } @@ -1524,7 +1535,7 @@ 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 | __GFP_ZERO, + mflags | __GFP_COMP | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) goto free_pages; @@ -1599,6 +1610,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); init_waitqueue_head(&cpu_buffer->irq_work.waiters); init_waitqueue_head(&cpu_buffer->irq_work.full_waiters); + mutex_init(&cpu_buffer->mapping_lock); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -1609,7 +1621,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) cpu_buffer->reader_page = bpage; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO, + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_COMP | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) goto fail_free_reader; @@ -1789,8 +1801,6 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer) return buffer->time_stamp_abs; } -static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); - static inline unsigned long rb_page_entries(struct buffer_page *bpage) { return local_read(&bpage->entries) & RB_WRITE_MASK; @@ -2318,7 +2328,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) /* Size is determined by what has been committed */ static __always_inline unsigned rb_page_size(struct buffer_page *bpage) { - return rb_page_commit(bpage); + return rb_page_commit(bpage) & ~RB_MISSED_MASK; } static __always_inline unsigned @@ -3945,7 +3955,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) return true; /* Reader should exhaust content in reader page */ - if (reader->read != rb_page_commit(reader)) + if (reader->read != rb_page_size(reader)) return false; /* @@ -4416,7 +4426,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) return ((iter->head_page == commit_page && iter->head >= commit) || (iter->head_page == reader && commit_page == head_page && head_page->read == commit && - iter->head == rb_page_commit(cpu_buffer->reader_page))); + iter->head == rb_page_size(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); @@ -5211,6 +5221,22 @@ static void rb_clear_buffer_page(struct buffer_page *page) page->read = 0; } +static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct trace_buffer_meta *meta = cpu_buffer->meta_page; + + meta->reader.read = cpu_buffer->reader_page->read; + meta->reader.id = cpu_buffer->reader_page->id; + meta->reader.lost_events = cpu_buffer->lost_events; + + meta->entries = local_read(&cpu_buffer->entries); + meta->overrun = local_read(&cpu_buffer->overrun); + meta->read = cpu_buffer->read; + + /* Some archs do not have data cache coherency between kernel and user-space */ + flush_dcache_folio(virt_to_folio(cpu_buffer->meta_page)); +} + static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { @@ -5255,6 +5281,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->lost_events = 0; cpu_buffer->last_overrun = 0; + if (cpu_buffer->mapped) + rb_update_meta_page(cpu_buffer); + rb_head_page_activate(cpu_buffer); cpu_buffer->pages_removed = 0; } @@ -5469,6 +5498,12 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; + /* It's up to the callers to not try to swap mapped buffers */ + if (WARN_ON_ONCE(cpu_buffer_a->mapped || cpu_buffer_b->mapped)) { + ret = -EBUSY; + goto out; + } + /* At least make sure the two buffers are somewhat the same */ if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; @@ -5579,7 +5614,7 @@ ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) goto out; page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY | __GFP_ZERO, + GFP_KERNEL | __GFP_NORETRY | __GFP_COMP | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) { kfree(bpage); @@ -5720,7 +5755,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, event = rb_reader_event(cpu_buffer); read = reader->read; - commit = rb_page_commit(reader); + commit = rb_page_size(reader); /* Check if any events were dropped */ missed_events = cpu_buffer->lost_events; @@ -5733,7 +5768,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, * Otherwise, we can simply swap the page with the one passed in. */ if (read || (len < (commit - read)) || - cpu_buffer->reader_page == cpu_buffer->commit_page) { + cpu_buffer->reader_page == cpu_buffer->commit_page || + cpu_buffer->mapped) { struct buffer_data_page *rpage = cpu_buffer->reader_page->page; unsigned int rpos = read; unsigned int pos = 0; @@ -5796,7 +5832,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += rb_page_commit(reader); + cpu_buffer->read_bytes += rb_page_size(reader); /* swap the pages */ rb_init_page(bpage); @@ -5956,6 +5992,11 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) cpu_buffer = buffer->buffers[cpu]; + if (cpu_buffer->mapped) { + err = -EBUSY; + goto error; + } + /* 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); @@ -6057,6 +6098,414 @@ error: } EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set); +static int rb_alloc_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct page *page; + + if (cpu_buffer->meta_page) + return 0; + + page = alloc_page(GFP_USER | __GFP_ZERO); + if (!page) + return -ENOMEM; + + cpu_buffer->meta_page = page_to_virt(page); + + return 0; +} + +static void rb_free_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + unsigned long addr = (unsigned long)cpu_buffer->meta_page; + + free_page(addr); + cpu_buffer->meta_page = NULL; +} + +static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long *subbuf_ids) +{ + struct trace_buffer_meta *meta = cpu_buffer->meta_page; + unsigned int nr_subbufs = cpu_buffer->nr_pages + 1; + struct buffer_page *first_subbuf, *subbuf; + int id = 0; + + subbuf_ids[id] = (unsigned long)cpu_buffer->reader_page->page; + cpu_buffer->reader_page->id = id++; + + first_subbuf = subbuf = rb_set_head_page(cpu_buffer); + do { + if (WARN_ON(id >= nr_subbufs)) + break; + + subbuf_ids[id] = (unsigned long)subbuf->page; + subbuf->id = id; + + rb_inc_page(&subbuf); + id++; + } while (subbuf != first_subbuf); + + /* install subbuf ID to kern VA translation */ + cpu_buffer->subbuf_ids = subbuf_ids; + + meta->meta_page_size = PAGE_SIZE; + meta->meta_struct_len = sizeof(*meta); + meta->nr_subbufs = nr_subbufs; + meta->subbuf_size = cpu_buffer->buffer->subbuf_size + BUF_PAGE_HDR_SIZE; + + rb_update_meta_page(cpu_buffer); +} + +static struct ring_buffer_per_cpu * +rb_get_mapped_buffer(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return ERR_PTR(-EINVAL); + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + mutex_unlock(&cpu_buffer->mapping_lock); + return ERR_PTR(-ENODEV); + } + + return cpu_buffer; +} + +static void rb_put_mapped_buffer(struct ring_buffer_per_cpu *cpu_buffer) +{ + mutex_unlock(&cpu_buffer->mapping_lock); +} + +/* + * Fast-path for rb_buffer_(un)map(). Called whenever the meta-page doesn't need + * to be set-up or torn-down. + */ +static int __rb_inc_dec_mapped(struct ring_buffer_per_cpu *cpu_buffer, + bool inc) +{ + unsigned long flags; + + lockdep_assert_held(&cpu_buffer->mapping_lock); + + if (inc && cpu_buffer->mapped == UINT_MAX) + return -EBUSY; + + if (WARN_ON(!inc && cpu_buffer->mapped == 0)) + return -EINVAL; + + mutex_lock(&cpu_buffer->buffer->mutex); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + if (inc) + cpu_buffer->mapped++; + else + cpu_buffer->mapped--; + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + mutex_unlock(&cpu_buffer->buffer->mutex); + + return 0; +} + +/* + * +--------------+ pgoff == 0 + * | meta page | + * +--------------+ pgoff == 1 + * | subbuffer 0 | + * | | + * +--------------+ pgoff == (1 + (1 << subbuf_order)) + * | subbuffer 1 | + * | | + * ... + */ +#ifdef CONFIG_MMU +static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, + struct vm_area_struct *vma) +{ + unsigned long nr_subbufs, nr_pages, vma_pages, pgoff = vma->vm_pgoff; + unsigned int subbuf_pages, subbuf_order; + struct page **pages; + int p = 0, s = 0; + int err; + + /* Refuse MP_PRIVATE or writable mappings */ + if (vma->vm_flags & VM_WRITE || vma->vm_flags & VM_EXEC || + !(vma->vm_flags & VM_MAYSHARE)) + return -EPERM; + + /* + * Make sure the mapping cannot become writable later. Also tell the VM + * to not touch these pages (VM_DONTCOPY | VM_DONTEXPAND). + */ + vm_flags_mod(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP, + VM_MAYWRITE); + + lockdep_assert_held(&cpu_buffer->mapping_lock); + + subbuf_order = cpu_buffer->buffer->subbuf_order; + subbuf_pages = 1 << subbuf_order; + + nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ + nr_pages = ((nr_subbufs) << subbuf_order) - pgoff + 1; /* + meta-page */ + + vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + if (!vma_pages || vma_pages > nr_pages) + return -EINVAL; + + nr_pages = vma_pages; + + pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + if (!pgoff) { + pages[p++] = virt_to_page(cpu_buffer->meta_page); + + /* + * TODO: Align sub-buffers on their size, once + * vm_insert_pages() supports the zero-page. + */ + } else { + /* Skip the meta-page */ + pgoff--; + + if (pgoff % subbuf_pages) { + err = -EINVAL; + goto out; + } + + s += pgoff / subbuf_pages; + } + + while (p < nr_pages) { + struct page *page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + int off = 0; + + if (WARN_ON_ONCE(s >= nr_subbufs)) { + err = -EINVAL; + goto out; + } + + for (; off < (1 << (subbuf_order)); off++, page++) { + if (p >= nr_pages) + break; + + pages[p++] = page; + } + s++; + } + + err = vm_insert_pages(vma, vma->vm_start, pages, &nr_pages); + +out: + kfree(pages); + + return err; +} +#else +static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, + struct vm_area_struct *vma) +{ + return -EOPNOTSUPP; +} +#endif + +int ring_buffer_map(struct trace_buffer *buffer, int cpu, + struct vm_area_struct *vma) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags, *subbuf_ids; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (cpu_buffer->mapped) { + err = __rb_map_vma(cpu_buffer, vma); + if (!err) + err = __rb_inc_dec_mapped(cpu_buffer, true); + mutex_unlock(&cpu_buffer->mapping_lock); + return err; + } + + /* prevent another thread from changing buffer/sub-buffer sizes */ + mutex_lock(&buffer->mutex); + + err = rb_alloc_meta_page(cpu_buffer); + if (err) + goto unlock; + + /* subbuf_ids include the reader while nr_pages does not */ + subbuf_ids = kcalloc(cpu_buffer->nr_pages + 1, sizeof(*subbuf_ids), GFP_KERNEL); + if (!subbuf_ids) { + rb_free_meta_page(cpu_buffer); + err = -ENOMEM; + goto unlock; + } + + atomic_inc(&cpu_buffer->resize_disabled); + + /* + * Lock all readers to block any subbuf swap until the subbuf IDs are + * assigned. + */ + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rb_setup_ids_meta_page(cpu_buffer, subbuf_ids); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + err = __rb_map_vma(cpu_buffer, vma); + if (!err) { + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + cpu_buffer->mapped = 1; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } else { + kfree(cpu_buffer->subbuf_ids); + cpu_buffer->subbuf_ids = NULL; + rb_free_meta_page(cpu_buffer); + } + +unlock: + mutex_unlock(&buffer->mutex); + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + err = -ENODEV; + goto out; + } else if (cpu_buffer->mapped > 1) { + __rb_inc_dec_mapped(cpu_buffer, false); + goto out; + } + + mutex_lock(&buffer->mutex); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + cpu_buffer->mapped = 0; + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + kfree(cpu_buffer->subbuf_ids); + cpu_buffer->subbuf_ids = NULL; + rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); + + mutex_unlock(&buffer->mutex); + +out: + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + unsigned long missed_events; + unsigned long reader_size; + unsigned long flags; + + cpu_buffer = rb_get_mapped_buffer(buffer, cpu); + if (IS_ERR(cpu_buffer)) + return (int)PTR_ERR(cpu_buffer); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + +consume: + if (rb_per_cpu_empty(cpu_buffer)) + goto out; + + reader_size = rb_page_size(cpu_buffer->reader_page); + + /* + * There are data to be read on the current reader page, we can + * return to the caller. But before that, we assume the latter will read + * everything. Let's update the kernel reader accordingly. + */ + if (cpu_buffer->reader_page->read < reader_size) { + while (cpu_buffer->reader_page->read < reader_size) + rb_advance_reader(cpu_buffer); + goto out; + } + + reader = rb_get_reader_page(cpu_buffer); + if (WARN_ON(!reader)) + goto out; + + /* Check if any events were dropped */ + missed_events = cpu_buffer->lost_events; + + if (cpu_buffer->reader_page != cpu_buffer->commit_page) { + if (missed_events) { + struct buffer_data_page *bpage = reader->page; + unsigned int commit; + /* + * Use the real_end for the data size, + * This gives us a chance to store the lost events + * on the page. + */ + if (reader->real_end) + local_set(&bpage->commit, reader->real_end); + /* + * If there is room at the end of the page to save the + * missed events, then record it there. + */ + commit = rb_page_size(reader); + if (buffer->subbuf_size - commit >= sizeof(missed_events)) { + memcpy(&bpage->data[commit], &missed_events, + sizeof(missed_events)); + local_add(RB_MISSED_STORED, &bpage->commit); + } + local_add(RB_MISSED_EVENTS, &bpage->commit); + } + } else { + /* + * There really shouldn't be any missed events if the commit + * is on the reader page. + */ + WARN_ON_ONCE(missed_events); + } + + cpu_buffer->lost_events = 0; + + goto consume; + +out: + /* Some archs do not have data cache coherency between kernel and user-space */ + flush_dcache_folio(virt_to_folio(cpu_buffer->reader_page->page)); + + rb_update_meta_page(cpu_buffer); + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + rb_put_mapped_buffer(cpu_buffer); + + return 0; +} + /* * 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/trace.c b/kernel/trace/trace.c index 233d1af39fff..578a49ff5c32 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1191,6 +1191,12 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr, return; } + if (tr->mapped) { + trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); + return; + } + local_irq_save(flags); update_max_tr(tr, current, smp_processor_id(), cond_data); local_irq_restore(flags); @@ -1323,7 +1329,7 @@ static int tracing_arm_snapshot_locked(struct trace_array *tr) lockdep_assert_held(&trace_types_lock); spin_lock(&tr->snapshot_trigger_lock); - if (tr->snapshot == UINT_MAX) { + if (tr->snapshot == UINT_MAX || tr->mapped) { spin_unlock(&tr->snapshot_trigger_lock); return -EBUSY; } @@ -5540,7 +5546,7 @@ static const char readme_msg[] = "\t kernel return probes support: $retval, $arg<N>, $comm\n" "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n" "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" - "\t symstr, <type>\\[<array-size>\\]\n" + "\t symstr, %pd/%pD, <type>\\[<array-size>\\]\n" #ifdef CONFIG_HIST_TRIGGERS "\t field: <stype> <name>;\n" "\t stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n" @@ -6068,7 +6074,7 @@ static void tracing_set_nop(struct trace_array *tr) { if (tr->current_trace == &nop_trace) return; - + tr->current_trace->enabled--; if (tr->current_trace->reset) @@ -8194,15 +8200,32 @@ out: return ret; } -/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; + int err; + + if (cmd == TRACE_MMAP_IOCTL_GET_READER) { + if (!(file->f_flags & O_NONBLOCK)) { + err = ring_buffer_wait(iter->array_buffer->buffer, + iter->cpu_file, + iter->tr->buffer_percent, + NULL, NULL); + if (err) + return err; + } - if (cmd) - return -ENOIOCTLCMD; + return ring_buffer_map_get_reader(iter->array_buffer->buffer, + iter->cpu_file); + } else if (cmd) { + return -ENOTTY; + } + /* + * An ioctl call with cmd 0 to the ring buffer file will wake up all + * waiters + */ mutex_lock(&trace_types_lock); /* Make sure the waiters see the new wait_index */ @@ -8214,6 +8237,76 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned return 0; } +#ifdef CONFIG_TRACER_MAX_TRACE +static int get_snapshot_map(struct trace_array *tr) +{ + int err = 0; + + /* + * Called with mmap_lock held. lockdep would be unhappy if we would now + * take trace_types_lock. Instead use the specific + * snapshot_trigger_lock. + */ + spin_lock(&tr->snapshot_trigger_lock); + + if (tr->snapshot || tr->mapped == UINT_MAX) + err = -EBUSY; + else + tr->mapped++; + + spin_unlock(&tr->snapshot_trigger_lock); + + /* Wait for update_max_tr() to observe iter->tr->mapped */ + if (tr->mapped == 1) + synchronize_rcu(); + + return err; + +} +static void put_snapshot_map(struct trace_array *tr) +{ + spin_lock(&tr->snapshot_trigger_lock); + if (!WARN_ON(!tr->mapped)) + tr->mapped--; + spin_unlock(&tr->snapshot_trigger_lock); +} +#else +static inline int get_snapshot_map(struct trace_array *tr) { return 0; } +static inline void put_snapshot_map(struct trace_array *tr) { } +#endif + +static void tracing_buffers_mmap_close(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + WARN_ON(ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file)); + put_snapshot_map(iter->tr); +} + +static const struct vm_operations_struct tracing_buffers_vmops = { + .close = tracing_buffers_mmap_close, +}; + +static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + int ret = 0; + + ret = get_snapshot_map(iter->tr); + if (ret) + return ret; + + ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file, vma); + if (ret) + put_snapshot_map(iter->tr); + + vma->vm_ops = &tracing_buffers_vmops; + + return ret; +} + static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, @@ -8223,6 +8316,7 @@ static const struct file_operations tracing_buffers_fops = { .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, + .mmap = tracing_buffers_mmap, }; static ssize_t diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 64450615ca0c..749a182dab48 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -336,6 +336,7 @@ struct trace_array { bool allocated_snapshot; spinlock_t snapshot_trigger_lock; unsigned int snapshot; + unsigned int mapped; unsigned long max_latency; #ifdef CONFIG_FSNOTIFY struct dentry *d_max_latency; diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 811b08439406..e19c32f2a938 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -104,7 +104,7 @@ static void trace_do_benchmark(void) stddev = 0; delta = bm_total; - delta = div64_u64(delta, bm_cnt); + do_div(delta, (u32)bm_cnt); avg = delta; if (stddev > 0) { diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7c364b87352e..6ef29eba90ce 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, @@ -2152,10 +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, @@ -2548,6 +2552,14 @@ static int event_callback(const char *name, umode_t *mode, void **data, return 0; } +/* The file is incremented on creation and freeing the enable file decrements it */ +static void event_release(const char *name, void *data) +{ + struct trace_event_file *file = data; + + event_file_put(file); +} + static int event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) { @@ -2562,6 +2574,7 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) { .name = "enable", .callback = event_callback, + .release = event_release, }, { .name = "filter", @@ -2630,6 +2643,9 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) return ret; } + /* Gets decremented on freeing of the "enable" file */ + event_file_get(file); + return 0; } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 70d428c394b6..3a2b46847c8b 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1990,6 +1990,80 @@ static int user_event_set_tp_name(struct user_event *user) } /* + * Counts how many ';' without a trailing space are in the args. + */ +static int count_semis_no_space(char *args) +{ + int count = 0; + + while ((args = strchr(args, ';'))) { + args++; + + if (!isspace(*args)) + count++; + } + + return count; +} + +/* + * Copies the arguments while ensuring all ';' have a trailing space. + */ +static char *insert_space_after_semis(char *args, int count) +{ + char *fixed, *pos; + int len; + + len = strlen(args) + count; + fixed = kmalloc(len + 1, GFP_KERNEL); + + if (!fixed) + return NULL; + + pos = fixed; + + /* Insert a space after ';' if there is no trailing space. */ + while (*args) { + *pos = *args++; + + if (*pos++ == ';' && !isspace(*args)) + *pos++ = ' '; + } + + *pos = '\0'; + + return fixed; +} + +static char **user_event_argv_split(char *args, int *argc) +{ + char **split; + char *fixed; + int count; + + /* Count how many ';' without a trailing space */ + count = count_semis_no_space(args); + + /* No fixup is required */ + if (!count) + return argv_split(GFP_KERNEL, args, argc); + + /* We must fixup 'field;field' to 'field; field' */ + fixed = insert_space_after_semis(args, count); + + if (!fixed) + return NULL; + + /* We do a normal split afterwards */ + split = argv_split(GFP_KERNEL, fixed, argc); + + /* We can free since argv_split makes a copy */ + kfree(fixed); + + return split; +} + +/* * Parses the event name, arguments and flags then registers if successful. * The name buffer lifetime is owned by this method for success cases only. * Upon success the returned user_event has its ref count increased by 1. @@ -2012,7 +2086,7 @@ static int user_event_parse(struct user_event_group *group, char *name, return -EPERM; if (args) { - argv = argv_split(GFP_KERNEL, args, &argc); + argv = user_event_argv_split(args, &argc); if (!argv) return -ENOMEM; @@ -2833,7 +2907,6 @@ static struct ctl_table user_event_sysctls[] = { .mode = 0644, .proc_handler = set_max_user_events_sysctl, }, - {} }; static int __init trace_events_user_init(void) diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 4f4280815522..62e6a8f4aae9 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -994,6 +994,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) char gbuf[MAX_EVENT_NAME_LEN]; char sbuf[KSYM_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; + char *dbuf = NULL; bool is_tracepoint = false; struct tracepoint *tpoint = NULL; struct traceprobe_parse_context ctx = { @@ -1104,6 +1105,10 @@ static int __trace_fprobe_create(int argc, const char *argv[]) argv = new_argv; } + ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); + if (ret) + goto out; + /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, maxactive, argc, is_return); @@ -1154,6 +1159,7 @@ out: trace_probe_log_clear(); kfree(new_argv); kfree(symbol); + kfree(dbuf); return ret; parse_error: diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 14099cc17fc9..16383247bdbf 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -111,6 +111,7 @@ static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk, return strncmp(module_name(mod), name, len) == 0 && name[len] == ':'; } +#ifdef CONFIG_MODULES static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk) { char *p; @@ -129,6 +130,12 @@ static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk) return ret; } +#else +static inline bool trace_kprobe_module_exist(struct trace_kprobe *tk) +{ + return false; +} +#endif static bool trace_kprobe_is_busy(struct dyn_event *ev) { @@ -670,6 +677,7 @@ end: return ret; } +#ifdef CONFIG_MODULES /* Module notifier call back, checking event on the module */ static int trace_kprobe_module_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -704,6 +712,16 @@ static struct notifier_block trace_kprobe_module_nb = { .notifier_call = trace_kprobe_module_callback, .priority = 1 /* Invoked after kprobe module callback */ }; +static int trace_kprobe_register_module_notifier(void) +{ + return register_module_notifier(&trace_kprobe_module_nb); +} +#else +static int trace_kprobe_register_module_notifier(void) +{ + return 0; +} +#endif /* CONFIG_MODULES */ static int count_symbols(void *data, unsigned long unused) { @@ -782,6 +800,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; + char *dbuf = NULL; struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL }; switch (argv[0][0]) { @@ -933,6 +952,10 @@ static int __trace_kprobe_create(int argc, const char *argv[]) argv = new_argv; } + ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); + if (ret) + goto out; + /* setup a probe */ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, argc, is_return); @@ -979,6 +1002,7 @@ out: trace_probe_log_clear(); kfree(new_argv); kfree(symbol); + kfree(dbuf); return ret; parse_error: @@ -1933,7 +1957,7 @@ static __init int init_kprobe_trace_early(void) if (ret) return ret; - if (register_module_notifier(&trace_kprobe_module_nb)) + if (trace_kprobe_register_module_notifier()) return -EINVAL; return 0; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 217169de0920..5e263c141574 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) "trace_probe: " fmt #include <linux/bpf.h> +#include <linux/fs.h> #include "trace_btf.h" #include "trace_probe.h" @@ -839,7 +840,7 @@ out: void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs) { struct probe_entry_arg *earg = tp->entry_arg; - unsigned long val; + unsigned long val = 0; int i; if (!earg) @@ -1180,8 +1181,6 @@ parse_probe_arg(char *arg, const struct fetch_type *type, return ret; } -#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long)) - /* Bitfield type needs to be parsed into a fetch function */ static int __parse_bitfield_probe_arg(const char *bf, const struct fetch_type *t, @@ -1466,7 +1465,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, parg->fmt = kmalloc(len, GFP_KERNEL); if (!parg->fmt) { ret = -ENOMEM; - goto out; + goto fail; } snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, parg->count); @@ -1739,6 +1738,68 @@ error: return ERR_PTR(ret); } +/* @buf: *buf must be equal to NULL. Caller must to free *buf */ +int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf) +{ + int i, used, ret; + const int bufsize = MAX_DENTRY_ARGS_LEN; + char *tmpbuf = NULL; + + if (*buf) + return -EINVAL; + + used = 0; + for (i = 0; i < argc; i++) { + char *tmp; + char *equal; + size_t arg_len; + + if (!glob_match("*:%p[dD]", argv[i])) + continue; + + if (!tmpbuf) { + tmpbuf = kmalloc(bufsize, GFP_KERNEL); + if (!tmpbuf) + return -ENOMEM; + } + + tmp = kstrdup(argv[i], GFP_KERNEL); + if (!tmp) + goto nomem; + + equal = strchr(tmp, '='); + if (equal) + *equal = '\0'; + arg_len = strlen(argv[i]); + tmp[arg_len - 4] = '\0'; + if (argv[i][arg_len - 1] == 'd') + ret = snprintf(tmpbuf + used, bufsize - used, + "%s%s+0x0(+0x%zx(%s)):string", + equal ? tmp : "", equal ? "=" : "", + offsetof(struct dentry, d_name.name), + equal ? equal + 1 : tmp); + else + ret = snprintf(tmpbuf + used, bufsize - used, + "%s%s+0x0(+0x%zx(+0x%zx(%s))):string", + equal ? tmp : "", equal ? "=" : "", + offsetof(struct dentry, d_name.name), + offsetof(struct file, f_path.dentry), + equal ? equal + 1 : tmp); + + kfree(tmp); + if (ret >= bufsize - used) + goto nomem; + argv[i] = tmpbuf + used; + used += ret + 1; + } + + *buf = tmpbuf; + return 0; +nomem: + kfree(tmpbuf); + return -ENOMEM; +} + void traceprobe_finish_parse(struct traceprobe_parse_context *ctx) { clear_btf_context(ctx); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index cef3a50628a3..5803e6a41570 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -34,6 +34,7 @@ #define MAX_ARRAY_LEN 64 #define MAX_ARG_NAME_LEN 32 #define MAX_BTF_ARGS_LEN 128 +#define MAX_DENTRY_ARGS_LEN 256 #define MAX_STRING_SIZE PATH_MAX #define MAX_ARG_BUF_LEN (MAX_TRACE_ARGS * MAX_ARG_NAME_LEN) @@ -428,6 +429,7 @@ extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char **traceprobe_expand_meta_args(int argc, const char *argv[], int *new_argc, char *buf, int bufsize, struct traceprobe_parse_context *ctx); +extern int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf); extern int traceprobe_update_arg(struct probe_arg *arg); extern void traceprobe_free_probe_arg(struct probe_arg *arg); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 9e461362450a..8541fa1494ae 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -854,6 +854,7 @@ static const struct file_operations uprobe_profile_ops = { struct uprobe_cpu_buffer { struct mutex mutex; void *buf; + int dsize; }; static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; static int uprobe_buffer_refcnt; @@ -940,30 +941,56 @@ static struct uprobe_cpu_buffer *uprobe_buffer_get(void) static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) { + if (!ucb) + return; mutex_unlock(&ucb->mutex); } +static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, + struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) +{ + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + + if (*ucbp) + return *ucbp; + + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + dsize = __get_data_size(&tu->tp, regs, NULL); + + ucb = uprobe_buffer_get(); + ucb->dsize = tu->tp.size + dsize; + + store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize); + + *ucbp = ucb; + return ucb; +} + static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize, + struct uprobe_cpu_buffer **ucbp, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; struct trace_event_buffer fbuffer; + struct uprobe_cpu_buffer *ucb; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); WARN_ON(call != trace_file->event_call); - if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE)) return; if (trace_trigger_soft_disabled(trace_file)) return; esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - size = esize + tu->tp.size + dsize; + size = esize + ucb->dsize; entry = trace_event_buffer_reserve(&fbuffer, trace_file, size); if (!entry) return; @@ -977,14 +1004,14 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); } - memcpy(data, ucb->buf, tu->tp.size + dsize); + memcpy(data, ucb->buf, ucb->dsize); trace_event_buffer_commit(&fbuffer); } /* uprobe handler */ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; @@ -993,7 +1020,7 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); + __uprobe_trace_func(tu, 0, regs, ucbp, link->file); rcu_read_unlock(); return 0; @@ -1001,13 +1028,13 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); + __uprobe_trace_func(tu, func, regs, ucbp, link->file); rcu_read_unlock(); } @@ -1199,9 +1226,6 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) { struct perf_event *event; - if (filter->nr_systemwide) - return true; - list_for_each_entry(event, &filter->perf_events, hw.tp_list) { if (event->hw.target->mm == mm) return true; @@ -1326,6 +1350,13 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc, tu = container_of(uc, struct trace_uprobe, consumer); filter = tu->tp.event->filter; + /* + * speculative short-circuiting check to avoid unnecessarily taking + * filter->rwlock below, if the uprobe has system-wide consumer + */ + if (READ_ONCE(filter->nr_systemwide)) + return true; + read_lock(&filter->rwlock); ret = __uprobe_perf_filter(filter, mm); read_unlock(&filter->rwlock); @@ -1335,10 +1366,11 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc, static void __uprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; + struct uprobe_cpu_buffer *ucb; struct hlist_head *head; void *data; int size, esize; @@ -1356,7 +1388,8 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - size = esize + tu->tp.size + dsize; + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + size = esize + ucb->dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; @@ -1379,13 +1412,10 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); } - memcpy(data, ucb->buf, tu->tp.size + dsize); - - if (size - esize > tu->tp.size + dsize) { - int len = tu->tp.size + dsize; + memcpy(data, ucb->buf, ucb->dsize); - memset(data + len, 0, size - esize - len); - } + if (size - esize > ucb->dsize) + memset(data + ucb->dsize, 0, size - esize - ucb->dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); @@ -1395,21 +1425,21 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, /* uprobe profile handler */ static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) - __uprobe_perf_func(tu, 0, regs, ucb, dsize); + __uprobe_perf_func(tu, 0, regs, ucbp); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { - __uprobe_perf_func(tu, func, regs, ucb, dsize); + __uprobe_perf_func(tu, func, regs, ucbp); } int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, @@ -1474,11 +1504,9 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; - struct uprobe_cpu_buffer *ucb; - int dsize, esize; + struct uprobe_cpu_buffer *ucb = NULL; int ret = 0; - tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++; @@ -1490,18 +1518,12 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; - dsize = __get_data_size(&tu->tp, regs, NULL); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - - ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize); - if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) - ret |= uprobe_trace_func(tu, regs, ucb, dsize); + ret |= uprobe_trace_func(tu, regs, &ucb); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) - ret |= uprobe_perf_func(tu, regs, ucb, dsize); + ret |= uprobe_perf_func(tu, regs, &ucb); #endif uprobe_buffer_put(ucb); return ret; @@ -1512,8 +1534,7 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; - struct uprobe_cpu_buffer *ucb; - int dsize, esize; + struct uprobe_cpu_buffer *ucb = NULL; tu = container_of(con, struct trace_uprobe, consumer); @@ -1525,18 +1546,12 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; - dsize = __get_data_size(&tu->tp, regs, NULL); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - - ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize); - if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) - uretprobe_trace_func(tu, func, regs, ucb, dsize); + uretprobe_trace_func(tu, func, regs, &ucb); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) - uretprobe_perf_func(tu, func, regs, ucb, dsize); + uretprobe_perf_func(tu, func, regs, &ucb); #endif uprobe_buffer_put(ucb); return 0; diff --git a/kernel/ucount.c b/kernel/ucount.c index 4aa6166cb856..8c07714ff27d 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -38,7 +38,7 @@ static int set_is_seen(struct ctl_table_set *set) } static int set_permissions(struct ctl_table_header *head, - struct ctl_table *table) + const struct ctl_table *table) { struct user_namespace *user_ns = container_of(head->set, struct user_namespace, set); @@ -87,7 +87,6 @@ static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_fanotify_groups"), UCOUNT_ENTRY("max_fanotify_marks"), #endif - { } }; #endif /* CONFIG_SYSCTL */ @@ -96,7 +95,7 @@ bool setup_userns_sysctls(struct user_namespace *ns) #ifdef CONFIG_SYSCTL struct ctl_table *tbl; - BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS + 1); + BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS); setup_sysctl_set(&ns->set, &set_root, set_is_seen); tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL); if (tbl) { @@ -119,7 +118,7 @@ bool setup_userns_sysctls(struct user_namespace *ns) void retire_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL - struct ctl_table *tbl; + const struct ctl_table *tbl; tbl = ns->sysctls->ctl_table_arg; unregister_sysctl_table(ns->sysctls); diff --git a/kernel/umh.c b/kernel/umh.c index 1b13c5d34624..598b3ffe1522 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -560,7 +560,6 @@ static struct ctl_table usermodehelper_table[] = { .mode = 0600, .proc_handler = proc_cap_handler, }, - { } }; static int __init init_umh_sysctls(void) diff --git a/kernel/user.c b/kernel/user.c index 03cedc366dc9..aa1162deafe4 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -88,7 +88,7 @@ EXPORT_SYMBOL_GPL(init_user_ns); * when changing user ID's (ie setuid() and friends). */ -#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7) +#define UIDHASH_BITS (IS_ENABLED(CONFIG_BASE_SMALL) ? 3 : 7) #define UIDHASH_SZ (1 << UIDHASH_BITS) #define UIDHASH_MASK (UIDHASH_SZ - 1) #define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 019e3a1566cf..76a772072557 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -120,7 +120,6 @@ static struct ctl_table uts_kern_table[] = { .proc_handler = proc_do_uts_string, .poll = &domainname_poll, }, - {} }; #ifdef CONFIG_PROC_SYSCTL diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index f95516cd45bb..1d5eadd9dd61 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -198,18 +198,18 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_private); VMCOREINFO_NUMBER(PG_swapcache); VMCOREINFO_NUMBER(PG_swapbacked); - VMCOREINFO_NUMBER(PG_slab); +#define PAGE_SLAB_MAPCOUNT_VALUE (~PG_slab) + VMCOREINFO_NUMBER(PAGE_SLAB_MAPCOUNT_VALUE); #ifdef CONFIG_MEMORY_FAILURE VMCOREINFO_NUMBER(PG_hwpoison); #endif 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); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d7b2125503af..51915b44ac73 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -12,20 +12,25 @@ #define pr_fmt(fmt) "watchdog: " fmt -#include <linux/mm.h> #include <linux/cpu.h> -#include <linux/nmi.h> #include <linux/init.h> +#include <linux/irq.h> +#include <linux/irqdesc.h> +#include <linux/kernel_stat.h> +#include <linux/kvm_para.h> +#include <linux/math64.h> +#include <linux/mm.h> #include <linux/module.h> +#include <linux/nmi.h> +#include <linux/stop_machine.h> #include <linux/sysctl.h> #include <linux/tick.h> + #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> -#include <linux/stop_machine.h> #include <asm/irq_regs.h> -#include <linux/kvm_para.h> static DEFINE_MUTEX(watchdog_mutex); @@ -35,6 +40,8 @@ static DEFINE_MUTEX(watchdog_mutex); # define WATCHDOG_HARDLOCKUP_DEFAULT 0 #endif +#define NUM_SAMPLE_PERIODS 5 + unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = 1; static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT; @@ -71,6 +78,7 @@ void __init hardlockup_detector_disable(void) static int __init hardlockup_panic_setup(char *str) { +next: if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "nopanic", 7)) @@ -79,6 +87,14 @@ static int __init hardlockup_panic_setup(char *str) watchdog_hardlockup_user_enabled = 0; else if (!strncmp(str, "1", 1)) watchdog_hardlockup_user_enabled = 1; + else if (!strncmp(str, "r", 1)) + hardlockup_config_perf_event(str + 1); + while (*(str++)) { + if (*str == ',') { + str++; + goto next; + } + } return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -333,6 +349,188 @@ __setup("watchdog_thresh=", watchdog_thresh_setup); static void __lockup_detector_cleanup(void); +#ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM +enum stats_per_group { + STATS_SYSTEM, + STATS_SOFTIRQ, + STATS_HARDIRQ, + STATS_IDLE, + NUM_STATS_PER_GROUP, +}; + +static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = { + CPUTIME_SYSTEM, + CPUTIME_SOFTIRQ, + CPUTIME_IRQ, + CPUTIME_IDLE, +}; + +static DEFINE_PER_CPU(u16, cpustat_old[NUM_STATS_PER_GROUP]); +static DEFINE_PER_CPU(u8, cpustat_util[NUM_SAMPLE_PERIODS][NUM_STATS_PER_GROUP]); +static DEFINE_PER_CPU(u8, cpustat_tail); + +/* + * We don't need nanosecond resolution. A granularity of 16ms is + * sufficient for our precision, allowing us to use u16 to store + * cpustats, which will roll over roughly every ~1000 seconds. + * 2^24 ~= 16 * 10^6 + */ +static u16 get_16bit_precision(u64 data_ns) +{ + return data_ns >> 24LL; /* 2^24ns ~= 16.8ms */ +} + +static void update_cpustat(void) +{ + int i; + u8 util; + u16 old_stat, new_stat; + struct kernel_cpustat kcpustat; + u64 *cpustat = kcpustat.cpustat; + u8 tail = __this_cpu_read(cpustat_tail); + u16 sample_period_16 = get_16bit_precision(sample_period); + + kcpustat_cpu_fetch(&kcpustat, smp_processor_id()); + + for (i = 0; i < NUM_STATS_PER_GROUP; i++) { + old_stat = __this_cpu_read(cpustat_old[i]); + new_stat = get_16bit_precision(cpustat[tracked_stats[i]]); + util = DIV_ROUND_UP(100 * (new_stat - old_stat), sample_period_16); + __this_cpu_write(cpustat_util[tail][i], util); + __this_cpu_write(cpustat_old[i], new_stat); + } + + __this_cpu_write(cpustat_tail, (tail + 1) % NUM_SAMPLE_PERIODS); +} + +static void print_cpustat(void) +{ + int i, group; + u8 tail = __this_cpu_read(cpustat_tail); + u64 sample_period_second = sample_period; + + do_div(sample_period_second, NSEC_PER_SEC); + + /* + * Outputting the "watchdog" prefix on every line is redundant and not + * concise, and the original alarm information is sufficient for + * positioning in logs, hence here printk() is used instead of pr_crit(). + */ + printk(KERN_CRIT "CPU#%d Utilization every %llus during lockup:\n", + smp_processor_id(), sample_period_second); + + for (i = 0; i < NUM_SAMPLE_PERIODS; i++) { + group = (tail + i) % NUM_SAMPLE_PERIODS; + printk(KERN_CRIT "\t#%d: %3u%% system,\t%3u%% softirq,\t" + "%3u%% hardirq,\t%3u%% idle\n", i + 1, + __this_cpu_read(cpustat_util[group][STATS_SYSTEM]), + __this_cpu_read(cpustat_util[group][STATS_SOFTIRQ]), + __this_cpu_read(cpustat_util[group][STATS_HARDIRQ]), + __this_cpu_read(cpustat_util[group][STATS_IDLE])); + } +} + +#define HARDIRQ_PERCENT_THRESH 50 +#define NUM_HARDIRQ_REPORT 5 +struct irq_counts { + int irq; + u32 counts; +}; + +static DEFINE_PER_CPU(bool, snapshot_taken); + +/* Tabulate the most frequent interrupts. */ +static void tabulate_irq_count(struct irq_counts *irq_counts, int irq, u32 counts, int rank) +{ + int i; + struct irq_counts new_count = {irq, counts}; + + for (i = 0; i < rank; i++) { + if (counts > irq_counts[i].counts) + swap(new_count, irq_counts[i]); + } +} + +/* + * If the hardirq time exceeds HARDIRQ_PERCENT_THRESH% of the sample_period, + * then the cause of softlockup might be interrupt storm. In this case, it + * would be useful to start interrupt counting. + */ +static bool need_counting_irqs(void) +{ + u8 util; + int tail = __this_cpu_read(cpustat_tail); + + tail = (tail + NUM_HARDIRQ_REPORT - 1) % NUM_HARDIRQ_REPORT; + util = __this_cpu_read(cpustat_util[tail][STATS_HARDIRQ]); + return util > HARDIRQ_PERCENT_THRESH; +} + +static void start_counting_irqs(void) +{ + if (!__this_cpu_read(snapshot_taken)) { + kstat_snapshot_irqs(); + __this_cpu_write(snapshot_taken, true); + } +} + +static void stop_counting_irqs(void) +{ + __this_cpu_write(snapshot_taken, false); +} + +static void print_irq_counts(void) +{ + unsigned int i, count; + struct irq_counts irq_counts_sorted[NUM_HARDIRQ_REPORT] = { + {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0} + }; + + if (__this_cpu_read(snapshot_taken)) { + for_each_active_irq(i) { + count = kstat_get_irq_since_snapshot(i); + tabulate_irq_count(irq_counts_sorted, i, count, NUM_HARDIRQ_REPORT); + } + + /* + * Outputting the "watchdog" prefix on every line is redundant and not + * concise, and the original alarm information is sufficient for + * positioning in logs, hence here printk() is used instead of pr_crit(). + */ + printk(KERN_CRIT "CPU#%d Detect HardIRQ Time exceeds %d%%. Most frequent HardIRQs:\n", + smp_processor_id(), HARDIRQ_PERCENT_THRESH); + + for (i = 0; i < NUM_HARDIRQ_REPORT; i++) { + if (irq_counts_sorted[i].irq == -1) + break; + + printk(KERN_CRIT "\t#%u: %-10u\tirq#%d\n", + i + 1, irq_counts_sorted[i].counts, + irq_counts_sorted[i].irq); + } + + /* + * If the hardirq time is less than HARDIRQ_PERCENT_THRESH% in the last + * sample_period, then we suspect the interrupt storm might be subsiding. + */ + if (!need_counting_irqs()) + stop_counting_irqs(); + } +} + +static void report_cpu_status(void) +{ + print_cpustat(); + print_irq_counts(); +} +#else +static inline void update_cpustat(void) { } +static inline void report_cpu_status(void) { } +static inline bool need_counting_irqs(void) { return false; } +static inline void start_counting_irqs(void) { } +static inline void stop_counting_irqs(void) { } +#endif + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -364,7 +562,7 @@ static void set_sample_period(void) * and hard thresholds) to increment before the * hardlockup detector generates a warning */ - sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); + sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / NUM_SAMPLE_PERIODS); watchdog_update_hrtimer_threshold(sample_period); } @@ -434,6 +632,18 @@ static int is_softlockup(unsigned long touch_ts, unsigned long now) { if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) { + /* + * If period_ts has not been updated during a sample_period, then + * in the subsequent few sample_periods, period_ts might also not + * be updated, which could indicate a potential softlockup. In + * this case, if we suspect the cause of the potential softlockup + * might be interrupt storm, then we need to count the interrupts + * to find which interrupt is storming. + */ + if (time_after_eq(now, period_ts + get_softlockup_thresh() / NUM_SAMPLE_PERIODS) && + need_counting_irqs()) + start_counting_irqs(); + /* Warn about unreasonable delays. */ if (time_after(now, period_ts + get_softlockup_thresh())) return now - touch_ts; @@ -456,6 +666,7 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); static int softlockup_fn(void *data) { update_touch_ts(); + stop_counting_irqs(); complete(this_cpu_ptr(&softlockup_completion)); return 0; @@ -504,6 +715,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); + update_cpustat(); + /* Reset the interval when touched by known problematic code. */ if (period_ts == SOFTLOCKUP_DELAY_REPORT) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { @@ -539,6 +752,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); + report_cpu_status(); print_modules(); print_irqtrace_events(current); if (regs) @@ -950,7 +1164,6 @@ static struct ctl_table watchdog_sysctls[] = { }, #endif /* CONFIG_SMP */ #endif - {} }; static struct ctl_table watchdog_hardlockup_sysctl[] = { @@ -963,7 +1176,6 @@ static struct ctl_table watchdog_hardlockup_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static void __init watchdog_sysctl_init(void) diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c index 8ea00c4a24b2..d577c4a8321e 100644 --- a/kernel/watchdog_perf.c +++ b/kernel/watchdog_perf.c @@ -90,6 +90,14 @@ static struct perf_event_attr wd_hw_attr = { .disabled = 1, }; +static struct perf_event_attr fallback_wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 1, +}; + /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, struct perf_sample_data *data, @@ -123,6 +131,13 @@ static int hardlockup_detector_event_create(void) evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (IS_ERR(evt)) { + wd_attr = &fallback_wd_hw_attr; + wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + } + + if (IS_ERR(evt)) { pr_debug("Perf event create on CPU %d failed with %ld\n", cpu, PTR_ERR(evt)); return PTR_ERR(evt); @@ -133,7 +148,6 @@ static int hardlockup_detector_event_create(void) /** * watchdog_hardlockup_enable - Enable the local event - * * @cpu: The CPU to enable hard lockup on. */ void watchdog_hardlockup_enable(unsigned int cpu) @@ -152,7 +166,6 @@ void watchdog_hardlockup_enable(unsigned int cpu) /** * watchdog_hardlockup_disable - Disable the local event - * * @cpu: The CPU to enable hard lockup on. */ void watchdog_hardlockup_disable(unsigned int cpu) @@ -259,3 +272,33 @@ int __init watchdog_hardlockup_probe(void) } return ret; } + +/** + * hardlockup_config_perf_event - Overwrite config of wd_hw_attr. + * @str: number which identifies the raw perf event to use + */ +void __init hardlockup_config_perf_event(const char *str) +{ + u64 config; + char buf[24]; + char *comma = strchr(str, ','); + + if (!comma) { + if (kstrtoull(str, 16, &config)) + return; + } else { + unsigned int len = comma - str; + + if (len >= sizeof(buf)) + return; + + if (strscpy(buf, str, sizeof(buf)) < 0) + return; + buf[len] = 0; + if (kstrtoull(buf, 16, &config)) + return; + } + + wd_hw_attr.type = PERF_TYPE_RAW; + wd_hw_attr.config = config; +} diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0066c8f6c154..003474c9a77d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -99,6 +99,7 @@ enum worker_flags { enum work_cancel_flags { WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ + WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */ }; enum wq_internal_consts { @@ -392,6 +393,12 @@ struct wq_pod_type { int *cpu_pod; /* cpu -> pod */ }; +struct work_offq_data { + u32 pool_id; + u32 disable; + u32 flags; +}; + static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", @@ -490,12 +497,6 @@ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* - * Used to synchronize multiple cancel_sync attempts on the same work item. See - * work_grab_pending() and __cancel_work_sync(). - */ -static DECLARE_WAIT_QUEUE_HEAD(wq_cancel_waitq); - -/* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. @@ -763,6 +764,11 @@ static int work_next_color(int color) return (color + 1) % WORK_NR_COLORS; } +static unsigned long pool_offq_flags(struct worker_pool *pool) +{ + return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0; +} + /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag @@ -776,11 +782,6 @@ static int work_next_color(int color) * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. - * - * %WORK_OFFQ_CANCELING is used to mark a work item which is being - * canceled. While being canceled, a work item may have its PENDING set - * but stay off timer and worklist for arbitrarily long and nobody should - * try to steal the PENDING bit. */ static inline void set_work_data(struct work_struct *work, unsigned long data) { @@ -892,36 +893,26 @@ static struct worker_pool *get_work_pool(struct work_struct *work) return idr_find(&worker_pool_idr, pool_id); } -/** - * get_work_pool_id - return the worker pool ID a given work is associated with - * @work: the work item of interest - * - * Return: The worker_pool ID @work was last associated with. - * %WORK_OFFQ_POOL_NONE if none. - */ -static int get_work_pool_id(struct work_struct *work) +static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { - unsigned long data = atomic_long_read(&work->data); - - if (data & WORK_STRUCT_PWQ) - return work_struct_pwq(data)->pool->id; - - return data >> WORK_OFFQ_POOL_SHIFT; + return (v >> shift) & ((1 << bits) - 1); } -static void mark_work_canceling(struct work_struct *work) +static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) { - unsigned long pool_id = get_work_pool_id(work); + WARN_ON_ONCE(data & WORK_STRUCT_PWQ); - pool_id <<= WORK_OFFQ_POOL_SHIFT; - set_work_data(work, pool_id | WORK_STRUCT_PENDING | WORK_OFFQ_CANCELING); + offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT, + WORK_OFFQ_POOL_BITS); + offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT, + WORK_OFFQ_DISABLE_BITS); + offqd->flags = data & WORK_OFFQ_FLAG_MASK; } -static bool work_is_canceling(struct work_struct *work) +static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd) { - unsigned long data = atomic_long_read(&work->data); - - return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING); + return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) | + ((unsigned long)offqd->flags); } /* @@ -1277,8 +1268,12 @@ static bool kick_pool(struct worker_pool *pool) !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); - p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask); - get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; + int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, + cpu_online_mask); + if (wake_cpu < nr_cpu_ids) { + p->wake_cpu = wake_cpu; + get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; + } } #endif wake_up_process(p); @@ -1464,7 +1459,7 @@ void wq_worker_sleeping(struct task_struct *task) * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * - * Called from scheduler_tick(). We're in the IRQ context and the current + * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) @@ -1594,6 +1589,15 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) if (off_cpu >= 0) total_cpus--; + /* If all CPUs of the wq get offline, use the default values */ + if (unlikely(!total_cpus)) { + for_each_node(node) + wq_node_nr_active(wq, node)->max = min_active; + + wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; + return; + } + for_each_node(node) { int node_cpus; @@ -1606,7 +1610,7 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) min_active, max_active); } - wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active; + wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** @@ -2054,8 +2058,6 @@ out_put: * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry - * -ENOENT if someone else is canceling @work, this state may persist - * for arbitrarily long * ======== ================================================================ * * Note: @@ -2138,7 +2140,8 @@ static int try_to_grab_pending(struct work_struct *work, u32 cflags, * this destroys work->data needed by the next step, stash it. */ work_data = *work_data_bits(work); - set_work_pool_and_keep_pending(work, pool->id, 0); + set_work_pool_and_keep_pending(work, pool->id, + pool_offq_flags(pool)); /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); @@ -2151,26 +2154,9 @@ static int try_to_grab_pending(struct work_struct *work, u32 cflags, fail: rcu_read_unlock(); local_irq_restore(*irq_flags); - if (work_is_canceling(work)) - return -ENOENT; - cpu_relax(); return -EAGAIN; } -struct cwt_wait { - wait_queue_entry_t wait; - struct work_struct *work; -}; - -static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) -{ - struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); - - if (cwait->work != key) - return 0; - return autoremove_wake_function(wait, mode, sync, key); -} - /** * work_grab_pending - steal work item from worklist and disable irq * @work: work item to steal @@ -2180,7 +2166,7 @@ static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *k * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer * or on worklist. * - * Must be called in process context. IRQ is disabled on return with IRQ state + * Can be called from any context. IRQ is disabled on return with IRQ state * stored in *@irq_flags. The caller is responsible for re-enabling it using * local_irq_restore(). * @@ -2189,41 +2175,14 @@ static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *k static bool work_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { - struct cwt_wait cwait; int ret; - might_sleep(); -repeat: - ret = try_to_grab_pending(work, cflags, irq_flags); - if (likely(ret >= 0)) - return ret; - if (ret != -ENOENT) - goto repeat; - - /* - * Someone is already canceling. Wait for it to finish. flush_work() - * doesn't work for PREEMPT_NONE because we may get woken up between - * @work's completion and the other canceling task resuming and clearing - * CANCELING - flush_work() will return false immediately as @work is no - * longer busy, try_to_grab_pending() will return -ENOENT as @work is - * still being canceled and the other canceling task won't be able to - * clear CANCELING as we're hogging the CPU. - * - * Let's wait for completion using a waitqueue. As this may lead to the - * thundering herd problem, use a custom wake function which matches - * @work along with exclusive wait and wakeup. - */ - init_wait(&cwait.wait); - cwait.wait.func = cwt_wakefn; - cwait.work = work; - - prepare_to_wait_exclusive(&wq_cancel_waitq, &cwait.wait, - TASK_UNINTERRUPTIBLE); - if (work_is_canceling(work)) - schedule(); - finish_wait(&wq_cancel_waitq, &cwait.wait); - - goto repeat; + while (true) { + ret = try_to_grab_pending(work, cflags, irq_flags); + if (ret >= 0) + return ret; + cpu_relax(); + } } /** @@ -2409,6 +2368,21 @@ out: rcu_read_unlock(); } +static bool clear_pending_if_disabled(struct work_struct *work) +{ + unsigned long data = *work_data_bits(work); + struct work_offq_data offqd; + + if (likely((data & WORK_STRUCT_PWQ) || + !(data & WORK_OFFQ_DISABLE_MASK))) + return false; + + work_offqd_unpack(&offqd, data); + set_work_pool_and_clear_pending(work, offqd.pool_id, + work_offqd_pack_flags(&offqd)); + return true; +} + /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on @@ -2431,7 +2405,8 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, local_irq_save(irq_flags); - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && + !clear_pending_if_disabled(work)) { __queue_work(cpu, wq, work); ret = true; } @@ -2509,7 +2484,8 @@ bool queue_work_node(int node, struct workqueue_struct *wq, local_irq_save(irq_flags); - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && + !clear_pending_if_disabled(work)) { int cpu = select_numa_node_cpu(node); __queue_work(cpu, wq, work); @@ -2591,7 +2567,8 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, /* read the comment in __queue_work() */ local_irq_save(irq_flags); - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && + !clear_pending_if_disabled(work)) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } @@ -2623,19 +2600,14 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long irq_flags; - int ret; + bool ret; - do { - ret = try_to_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, - &irq_flags); - } while (unlikely(ret == -EAGAIN)); + ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags); - if (likely(ret >= 0)) { + if (!clear_pending_if_disabled(&dwork->work)) __queue_delayed_work(cpu, wq, dwork, delay); - local_irq_restore(irq_flags); - } - /* -ENOENT from try_to_grab_pending() becomes %true */ + local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); @@ -2664,7 +2636,12 @@ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + /* + * rcu_work can't be canceled or disabled. Warn if the user reached + * inside @rwork and disabled the inner work. + */ + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && + !WARN_ON_ONCE(clear_pending_if_disabled(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; @@ -2940,7 +2917,7 @@ static void idle_worker_timeout(struct timer_list *t) unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ - worker = list_entry(pool->idle_list.prev, struct worker, entry); + worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; do_cull = !time_before(jiffies, expires); @@ -2982,7 +2959,7 @@ static void idle_cull_fn(struct work_struct *work) struct worker *worker; unsigned long expires; - worker = list_entry(pool->idle_list.prev, struct worker, entry); + worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { @@ -3217,7 +3194,7 @@ __acquires(&pool->lock) * PENDING and queued state changes happen together while IRQ is * disabled. */ - set_work_pool_and_clear_pending(work, pool->id, 0); + set_work_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool)); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); @@ -3687,7 +3664,7 @@ void workqueue_softirq_dead(unsigned int cpu) if (!need_more_worker(pool)) continue; - INIT_WORK(&dead_work.work, drain_dead_softirq_workfn); + INIT_WORK_ONSTACK(&dead_work.work, drain_dead_softirq_workfn); dead_work.pool = pool; init_completion(&dead_work.done); @@ -3697,6 +3674,7 @@ void workqueue_softirq_dead(unsigned int cpu) queue_work(system_bh_wq, &dead_work.work); wait_for_completion(&dead_work.done); + destroy_work_on_stack(&dead_work.work); } } @@ -4141,8 +4119,6 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, struct pool_workqueue *pwq; struct workqueue_struct *wq; - might_sleep(); - rcu_read_lock(); pool = get_work_pool(work); if (!pool) { @@ -4194,6 +4170,7 @@ already_gone: static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; + unsigned long data; if (WARN_ON(!wq_online)) return false; @@ -4201,13 +4178,41 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) if (WARN_ON(!work->func)) return false; - if (start_flush_work(work, &barr, from_cancel)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - return true; - } else { + if (!start_flush_work(work, &barr, from_cancel)) return false; + + /* + * start_flush_work() returned %true. If @from_cancel is set, we know + * that @work must have been executing during start_flush_work() and + * can't currently be queued. Its data must contain OFFQ bits. If @work + * was queued on a BH workqueue, we also know that it was running in the + * BH context and thus can be busy-waited. + */ + data = *work_data_bits(work); + if (from_cancel && + !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { + /* + * On RT, prevent a live lock when %current preempted soft + * interrupt processing or prevents ksoftirqd from running by + * keeping flipping BH. If the BH work item runs on a different + * CPU then this has no effect other than doing the BH + * disable/enable dance for nothing. This is copied from + * kernel/softirq.c::tasklet_unlock_spin_wait(). + */ + while (!try_wait_for_completion(&barr.done)) { + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + local_bh_disable(); + local_bh_enable(); + } else { + cpu_relax(); + } + } + } else { + wait_for_completion(&barr.done); } + + destroy_work_on_stack(&barr.work); + return true; } /** @@ -4223,6 +4228,7 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) */ bool flush_work(struct work_struct *work) { + might_sleep(); return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); @@ -4269,32 +4275,53 @@ bool flush_rcu_work(struct rcu_work *rwork) } EXPORT_SYMBOL(flush_rcu_work); +static void work_offqd_disable(struct work_offq_data *offqd) +{ + const unsigned long max = (1lu << WORK_OFFQ_DISABLE_BITS) - 1; + + if (likely(offqd->disable < max)) + offqd->disable++; + else + WARN_ONCE(true, "workqueue: work disable count overflowed\n"); +} + +static void work_offqd_enable(struct work_offq_data *offqd) +{ + if (likely(offqd->disable > 0)) + offqd->disable--; + else + WARN_ONCE(true, "workqueue: work disable count underflowed\n"); +} + static bool __cancel_work(struct work_struct *work, u32 cflags) { + struct work_offq_data offqd; unsigned long irq_flags; int ret; - do { - ret = try_to_grab_pending(work, cflags, &irq_flags); - } while (unlikely(ret == -EAGAIN)); + ret = work_grab_pending(work, cflags, &irq_flags); - if (unlikely(ret < 0)) - return false; + work_offqd_unpack(&offqd, *work_data_bits(work)); + + if (cflags & WORK_CANCEL_DISABLE) + work_offqd_disable(&offqd); - set_work_pool_and_clear_pending(work, get_work_pool_id(work), 0); + set_work_pool_and_clear_pending(work, offqd.pool_id, + work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return ret; } static bool __cancel_work_sync(struct work_struct *work, u32 cflags) { - unsigned long irq_flags; bool ret; - /* claim @work and tell other tasks trying to grab @work to back off */ - ret = work_grab_pending(work, cflags, &irq_flags); - mark_work_canceling(work); - local_irq_restore(irq_flags); + ret = __cancel_work(work, cflags | WORK_CANCEL_DISABLE); + + if (*work_data_bits(work) & WORK_OFFQ_BH) + WARN_ON_ONCE(in_hardirq()); + else + might_sleep(); /* * Skip __flush_work() during early boot when we know that @work isn't @@ -4303,15 +4330,8 @@ static bool __cancel_work_sync(struct work_struct *work, u32 cflags) if (wq_online) __flush_work(work, true); - /* - * smp_mb() at the end of set_work_pool_and_clear_pending() is paired - * with prepare_to_wait() above so that either waitqueue_active() is - * visible here or !work_is_canceling() is visible there. - */ - set_work_pool_and_clear_pending(work, WORK_OFFQ_POOL_NONE, 0); - - if (waitqueue_active(&wq_cancel_waitq)) - __wake_up(&wq_cancel_waitq, TASK_NORMAL, 1, work); + if (!(cflags & WORK_CANCEL_DISABLE)) + enable_work(work); return ret; } @@ -4329,19 +4349,19 @@ EXPORT_SYMBOL(cancel_work); * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * - * Cancel @work and wait for its execution to finish. This function - * can be used even if the work re-queues itself or migrates to - * another workqueue. On return from this function, @work is - * guaranteed to be not pending or executing on any CPU. + * Cancel @work and wait for its execution to finish. This function can be used + * even if the work re-queues itself or migrates to another workqueue. On return + * from this function, @work is guaranteed to be not pending or executing on any + * CPU as long as there aren't racing enqueues. * - * cancel_work_sync(&delayed_work->work) must not be used for - * delayed_work's. Use cancel_delayed_work_sync() instead. + * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's. + * Use cancel_delayed_work_sync() instead. * - * The caller must ensure that the workqueue on which @work was last - * queued can't be destroyed before this function returns. + * Must be called from a sleepable context if @work was last queued on a non-BH + * workqueue. Can also be called from non-hardirq atomic contexts including BH + * if @work was last queued on a BH workqueue. * - * Return: - * %true if @work was pending, %false otherwise. + * Returns %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { @@ -4387,6 +4407,108 @@ bool cancel_delayed_work_sync(struct delayed_work *dwork) EXPORT_SYMBOL(cancel_delayed_work_sync); /** + * disable_work - Disable and cancel a work item + * @work: work item to disable + * + * Disable @work by incrementing its disable count and cancel it if currently + * pending. As long as the disable count is non-zero, any attempt to queue @work + * will fail and return %false. The maximum supported disable depth is 2 to the + * power of %WORK_OFFQ_DISABLE_BITS, currently 65536. + * + * Can be called from any context. Returns %true if @work was pending, %false + * otherwise. + */ +bool disable_work(struct work_struct *work) +{ + return __cancel_work(work, WORK_CANCEL_DISABLE); +} +EXPORT_SYMBOL_GPL(disable_work); + +/** + * disable_work_sync - Disable, cancel and drain a work item + * @work: work item to disable + * + * Similar to disable_work() but also wait for @work to finish if currently + * executing. + * + * Must be called from a sleepable context if @work was last queued on a non-BH + * workqueue. Can also be called from non-hardirq atomic contexts including BH + * if @work was last queued on a BH workqueue. + * + * Returns %true if @work was pending, %false otherwise. + */ +bool disable_work_sync(struct work_struct *work) +{ + return __cancel_work_sync(work, WORK_CANCEL_DISABLE); +} +EXPORT_SYMBOL_GPL(disable_work_sync); + +/** + * enable_work - Enable a work item + * @work: work item to enable + * + * Undo disable_work[_sync]() by decrementing @work's disable count. @work can + * only be queued if its disable count is 0. + * + * Can be called from any context. Returns %true if the disable count reached 0. + * Otherwise, %false. + */ +bool enable_work(struct work_struct *work) +{ + struct work_offq_data offqd; + unsigned long irq_flags; + + work_grab_pending(work, 0, &irq_flags); + + work_offqd_unpack(&offqd, *work_data_bits(work)); + work_offqd_enable(&offqd); + set_work_pool_and_clear_pending(work, offqd.pool_id, + work_offqd_pack_flags(&offqd)); + local_irq_restore(irq_flags); + + return !offqd.disable; +} +EXPORT_SYMBOL_GPL(enable_work); + +/** + * disable_delayed_work - Disable and cancel a delayed work item + * @dwork: delayed work item to disable + * + * disable_work() for delayed work items. + */ +bool disable_delayed_work(struct delayed_work *dwork) +{ + return __cancel_work(&dwork->work, + WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); +} +EXPORT_SYMBOL_GPL(disable_delayed_work); + +/** + * disable_delayed_work_sync - Disable, cancel and drain a delayed work item + * @dwork: delayed work item to disable + * + * disable_work_sync() for delayed work items. + */ +bool disable_delayed_work_sync(struct delayed_work *dwork) +{ + return __cancel_work_sync(&dwork->work, + WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); +} +EXPORT_SYMBOL_GPL(disable_delayed_work_sync); + +/** + * enable_delayed_work - Enable a delayed work item + * @dwork: delayed work item to enable + * + * enable_work() for delayed work items. + */ +bool enable_delayed_work(struct delayed_work *dwork) +{ + return enable_work(&dwork->work); +} +EXPORT_SYMBOL_GPL(enable_delayed_work); + +/** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * @@ -4517,6 +4639,8 @@ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; + if (attrs->affn_strict) + cpumask_copy(attrs->cpumask, cpu_possible_mask); } /* hash value of the content of @attr */ @@ -4525,11 +4649,12 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) u32 hash = 0; hash = jhash_1word(attrs->nice, hash); - hash = jhash(cpumask_bits(attrs->cpumask), - BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); + hash = jhash_1word(attrs->affn_strict, hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); - hash = jhash_1word(attrs->affn_strict, hash); + if (!attrs->affn_strict) + hash = jhash(cpumask_bits(attrs->cpumask), + BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } @@ -4539,11 +4664,11 @@ static bool wqattrs_equal(const struct workqueue_attrs *a, { if (a->nice != b->nice) return false; - if (!cpumask_equal(a->cpumask, b->cpumask)) + if (a->affn_strict != b->affn_strict) return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; - if (a->affn_strict != b->affn_strict) + if (!a->affn_strict && !cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } @@ -7135,25 +7260,27 @@ static ssize_t __wq_cpumask_show(struct device *dev, return written; } -static ssize_t wq_unbound_cpumask_show(struct device *dev, +static ssize_t cpumask_requested_show(struct device *dev, struct device_attribute *attr, char *buf) { - return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); + return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); } +static DEVICE_ATTR_RO(cpumask_requested); -static ssize_t wq_requested_cpumask_show(struct device *dev, +static ssize_t cpumask_isolated_show(struct device *dev, struct device_attribute *attr, char *buf) { - return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); + return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); } +static DEVICE_ATTR_RO(cpumask_isolated); -static ssize_t wq_isolated_cpumask_show(struct device *dev, +static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { - return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); + return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); } -static ssize_t wq_unbound_cpumask_store(struct device *dev, +static ssize_t cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; @@ -7169,36 +7296,19 @@ static ssize_t wq_unbound_cpumask_store(struct device *dev, free_cpumask_var(cpumask); return ret ? ret : count; } +static DEVICE_ATTR_RW(cpumask); -static struct device_attribute wq_sysfs_cpumask_attrs[] = { - __ATTR(cpumask, 0644, wq_unbound_cpumask_show, - 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 struct attribute *wq_sysfs_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + &dev_attr_cpumask_requested.attr, + &dev_attr_cpumask_isolated.attr, + NULL, }; +ATTRIBUTE_GROUPS(wq_sysfs_cpumask); static int __init wq_sysfs_init(void) { - struct device *dev_root; - int err; - - err = subsys_virtual_register(&wq_subsys, NULL); - if (err) - return err; - - dev_root = bus_get_dev_root(&wq_subsys); - if (dev_root) { - 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; + return subsys_virtual_register(&wq_subsys, wq_sysfs_cpumask_groups); } core_initcall(wq_sysfs_init); |