diff options
Diffstat (limited to 'kernel/bpf')
74 files changed, 32657 insertions, 8904 deletions
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index 2dfe1079f772..eb3de35734f0 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -3,6 +3,7 @@ # BPF interpreter that, for example, classic socket filters depend on. config BPF bool + select CRYPTO_LIB_SHA256 # Used by archs to tell that they support BPF JIT compiler plus which # flavour. Only one of the two can be selected for a specific arch since @@ -27,10 +28,11 @@ 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 + select NET_XGRESS if NET select PAGE_POOL if NET default n help @@ -41,7 +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 3a12e6b400a2..232cbc97434d 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,22 +4,27 @@ 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 bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o liveness.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o -obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o bpf_insn_array.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o -obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o obj-$(CONFIG_BPF_JIT) += trampoline.o -obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o +obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o rqspinlock.o stream.o +ifeq ($(CONFIG_MMU)$(CONFIG_64BIT),yy) +obj-$(CONFIG_BPF_SYSCALL) += arena.o range_tree.o +endif obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o obj-$(CONFIG_BPF_SYSCALL) += offload.o obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o +obj-$(CONFIG_BPF_SYSCALL) += tcx.o endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o @@ -36,10 +41,25 @@ obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o endif ifeq ($(CONFIG_BPF_JIT),y) 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-$(CONFIG_BPF_SYSCALL) += relo_core.o -$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE - $(call if_changed_rule,cc_o_c) +obj-$(CONFIG_BPF_SYSCALL) += btf_iter.o +obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o +obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o +ifeq ($(CONFIG_DMA_SHARED_BUFFER),y) +obj-$(CONFIG_BPF_SYSCALL) += dmabuf_iter.o +endif + +CFLAGS_REMOVE_percpu_freelist.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rqspinlock.o = $(CC_FLAGS_FTRACE) diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c new file mode 100644 index 000000000000..872dc0e41c65 --- /dev/null +++ b/kernel/bpf/arena.c @@ -0,0 +1,665 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include "linux/filter.h" +#include <linux/btf_ids.h> +#include <linux/vmalloc.h> +#include <linux/pagemap.h> +#include "range_tree.h" + +/* + * bpf_arena is a sparsely populated shared memory region between bpf program and + * user space process. + * + * For example on x86-64 the values could be: + * user_vm_start 7f7d26200000 // picked by mmap() + * kern_vm_start ffffc90001e69000 // picked by get_vm_area() + * For user space all pointers within the arena are normal 8-byte addresses. + * In this example 7f7d26200000 is the address of the first page (pgoff=0). + * The bpf program will access it as: kern_vm_start + lower_32bit_of_user_ptr + * (u32)7f7d26200000 -> 26200000 + * hence + * ffffc90001e69000 + 26200000 == ffffc90028069000 is "pgoff=0" within 4Gb + * kernel memory region. + * + * BPF JITs generate the following code to access arena: + * mov eax, eax // eax has lower 32-bit of user pointer + * mov word ptr [rax + r12 + off], bx + * where r12 == kern_vm_start and off is s16. + * Hence allocate 4Gb + GUARD_SZ/2 on each side. + * + * Initially kernel vm_area and user vma are not populated. + * User space can fault-in any address which will insert the page + * into kernel and user vma. + * bpf program can allocate a page via bpf_arena_alloc_pages() kfunc + * which will insert it into kernel vm_area. + * The later fault-in from user space will populate that page into user vma. + */ + +/* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ +#define GUARD_SZ round_up(1ull << sizeof_field(struct bpf_insn, off) * 8, PAGE_SIZE << 1) +#define KERN_VM_SZ (SZ_4G + GUARD_SZ) + +struct bpf_arena { + struct bpf_map map; + u64 user_vm_start; + u64 user_vm_end; + struct vm_struct *kern_vm; + struct range_tree rt; + struct list_head vma_list; + struct mutex lock; +}; + +u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return arena ? (u64) (long) arena->kern_vm->addr + GUARD_SZ / 2 : 0; +} + +u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return arena ? arena->user_vm_start : 0; +} + +static long arena_map_peek_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_push_elem(struct bpf_map *map, void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static long arena_map_pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_delete_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static int arena_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EOPNOTSUPP; +} + +static long compute_pgoff(struct bpf_arena *arena, long uaddr) +{ + return (u32)(uaddr - (u32)arena->user_vm_start) >> PAGE_SHIFT; +} + +static struct bpf_map *arena_map_alloc(union bpf_attr *attr) +{ + struct vm_struct *kern_vm; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_arena *arena; + u64 vm_range; + int err = -ENOMEM; + + if (!bpf_jit_supports_arena()) + return ERR_PTR(-EOPNOTSUPP); + + if (attr->key_size || attr->value_size || attr->max_entries == 0 || + /* BPF_F_MMAPABLE must be set */ + !(attr->map_flags & BPF_F_MMAPABLE) || + /* No unsupported flags present */ + (attr->map_flags & ~(BPF_F_SEGV_ON_FAULT | BPF_F_MMAPABLE | BPF_F_NO_USER_CONV))) + return ERR_PTR(-EINVAL); + + if (attr->map_extra & ~PAGE_MASK) + /* If non-zero the map_extra is an expected user VMA start address */ + return ERR_PTR(-EINVAL); + + vm_range = (u64)attr->max_entries * PAGE_SIZE; + if (vm_range > SZ_4G) + return ERR_PTR(-E2BIG); + + if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32)) + /* user vma must not cross 32-bit boundary */ + return ERR_PTR(-ERANGE); + + kern_vm = get_vm_area(KERN_VM_SZ, VM_SPARSE | VM_USERMAP); + if (!kern_vm) + return ERR_PTR(-ENOMEM); + + arena = bpf_map_area_alloc(sizeof(*arena), numa_node); + if (!arena) + goto err; + + arena->kern_vm = kern_vm; + arena->user_vm_start = attr->map_extra; + if (arena->user_vm_start) + arena->user_vm_end = arena->user_vm_start + vm_range; + + INIT_LIST_HEAD(&arena->vma_list); + bpf_map_init_from_attr(&arena->map, attr); + range_tree_init(&arena->rt); + err = range_tree_set(&arena->rt, 0, attr->max_entries); + if (err) { + bpf_map_area_free(arena); + goto err; + } + mutex_init(&arena->lock); + + return &arena->map; +err: + free_vm_area(kern_vm); + return ERR_PTR(err); +} + +static int existing_page_cb(pte_t *ptep, unsigned long addr, void *data) +{ + struct page *page; + pte_t pte; + + pte = ptep_get(ptep); + if (!pte_present(pte)) /* sanity check */ + return 0; + page = pte_page(pte); + /* + * We do not update pte here: + * 1. Nobody should be accessing bpf_arena's range outside of a kernel bug + * 2. TLB flushing is batched or deferred. Even if we clear pte, + * the TLB entries can stick around and continue to permit access to + * the freed page. So it all relies on 1. + */ + __free_page(page); + return 0; +} + +static void arena_map_free(struct bpf_map *map) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + /* + * Check that user vma-s are not around when bpf map is freed. + * mmap() holds vm_file which holds bpf_map refcnt. + * munmap() must have happened on vma followed by arena_vm_close() + * which would clear arena->vma_list. + */ + if (WARN_ON_ONCE(!list_empty(&arena->vma_list))) + return; + + /* + * free_vm_area() calls remove_vm_area() that calls free_unmap_vmap_area(). + * It unmaps everything from vmalloc area and clears pgtables. + * Call apply_to_existing_page_range() first to find populated ptes and + * free those pages. + */ + apply_to_existing_page_range(&init_mm, bpf_arena_get_kern_vm_start(arena), + KERN_VM_SZ - GUARD_SZ, existing_page_cb, NULL); + free_vm_area(arena->kern_vm); + range_tree_destroy(&arena->rt); + bpf_map_area_free(arena); +} + +static void *arena_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-EINVAL); +} + +static long arena_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, const struct btf_type *value_type) +{ + return 0; +} + +static u64 arena_map_mem_usage(const struct bpf_map *map) +{ + return 0; +} + +struct vma_list { + struct vm_area_struct *vma; + struct list_head head; + refcount_t mmap_count; +}; + +static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) +{ + struct vma_list *vml; + + vml = kmalloc(sizeof(*vml), GFP_KERNEL); + if (!vml) + return -ENOMEM; + refcount_set(&vml->mmap_count, 1); + vma->vm_private_data = vml; + vml->vma = vma; + list_add(&vml->head, &arena->vma_list); + return 0; +} + +static void arena_vm_open(struct vm_area_struct *vma) +{ + struct vma_list *vml = vma->vm_private_data; + + refcount_inc(&vml->mmap_count); +} + +static void arena_vm_close(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct vma_list *vml = vma->vm_private_data; + + if (!refcount_dec_and_test(&vml->mmap_count)) + return; + guard(mutex)(&arena->lock); + /* update link list under lock */ + list_del(&vml->head); + vma->vm_private_data = NULL; + kfree(vml); +} + +static vm_fault_t arena_vm_fault(struct vm_fault *vmf) +{ + struct bpf_map *map = vmf->vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct page *page; + long kbase, kaddr; + int ret; + + kbase = bpf_arena_get_kern_vm_start(arena); + kaddr = kbase + (u32)(vmf->address); + + guard(mutex)(&arena->lock); + page = vmalloc_to_page((void *)kaddr); + if (page) + /* already have a page vmap-ed */ + goto out; + + if (arena->map.map_flags & BPF_F_SEGV_ON_FAULT) + /* User space requested to segfault when page is not allocated by bpf prog */ + return VM_FAULT_SIGSEGV; + + ret = range_tree_clear(&arena->rt, vmf->pgoff, 1); + if (ret) + return VM_FAULT_SIGSEGV; + + /* Account into memcg of the process that created bpf_arena */ + ret = bpf_map_alloc_pages(map, NUMA_NO_NODE, 1, &page); + if (ret) { + range_tree_set(&arena->rt, vmf->pgoff, 1); + return VM_FAULT_SIGSEGV; + } + + ret = vm_area_map_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE, &page); + if (ret) { + range_tree_set(&arena->rt, vmf->pgoff, 1); + __free_page(page); + return VM_FAULT_SIGSEGV; + } +out: + page_ref_add(page, 1); + vmf->page = page; + return 0; +} + +static const struct vm_operations_struct arena_vm_ops = { + .open = arena_vm_open, + .close = arena_vm_close, + .fault = arena_vm_fault, +}; + +static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct bpf_map *map = filp->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + long ret; + + if (pgoff) + return -EINVAL; + if (len > SZ_4G) + return -E2BIG; + + /* if user_vm_start was specified at arena creation time */ + if (arena->user_vm_start) { + if (len > arena->user_vm_end - arena->user_vm_start) + return -E2BIG; + if (len != arena->user_vm_end - arena->user_vm_start) + return -EINVAL; + if (addr != arena->user_vm_start) + return -EINVAL; + } + + ret = mm_get_unmapped_area(filp, addr, len * 2, 0, flags); + if (IS_ERR_VALUE(ret)) + return ret; + if ((ret >> 32) == ((ret + len - 1) >> 32)) + return ret; + if (WARN_ON_ONCE(arena->user_vm_start)) + /* checks at map creation time should prevent this */ + return -EFAULT; + return round_up(ret, SZ_4G); +} + +static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + guard(mutex)(&arena->lock); + if (arena->user_vm_start && arena->user_vm_start != vma->vm_start) + /* + * If map_extra was not specified at arena creation time then + * 1st user process can do mmap(NULL, ...) to pick user_vm_start + * 2nd user process must pass the same addr to mmap(addr, MAP_FIXED..); + * or + * specify addr in map_extra and + * use the same addr later with mmap(addr, MAP_FIXED..); + */ + return -EBUSY; + + if (arena->user_vm_end && arena->user_vm_end != vma->vm_end) + /* all user processes must have the same size of mmap-ed region */ + return -EBUSY; + + /* Earlier checks should prevent this */ + if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > SZ_4G || vma->vm_pgoff)) + return -EFAULT; + + if (remember_vma(arena, vma)) + return -ENOMEM; + + arena->user_vm_start = vma->vm_start; + arena->user_vm_end = vma->vm_end; + /* + * bpf_map_mmap() checks that it's being mmaped as VM_SHARED and + * clears VM_MAYEXEC. Set VM_DONTEXPAND as well to avoid + * potential change of user_vm_start. + */ + vm_flags_set(vma, VM_DONTEXPAND); + vma->vm_ops = &arena_vm_ops; + return 0; +} + +static int arena_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if ((u64)off > arena->user_vm_end - arena->user_vm_start) + return -ERANGE; + *imm = (unsigned long)arena->user_vm_start; + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_arena_map_btf_ids, struct, bpf_arena) +const struct bpf_map_ops arena_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = arena_map_alloc, + .map_free = arena_map_free, + .map_direct_value_addr = arena_map_direct_value_addr, + .map_mmap = arena_map_mmap, + .map_get_unmapped_area = arena_get_unmapped_area, + .map_get_next_key = arena_map_get_next_key, + .map_push_elem = arena_map_push_elem, + .map_peek_elem = arena_map_peek_elem, + .map_pop_elem = arena_map_pop_elem, + .map_lookup_elem = arena_map_lookup_elem, + .map_update_elem = arena_map_update_elem, + .map_delete_elem = arena_map_delete_elem, + .map_check_btf = arena_map_check_btf, + .map_mem_usage = arena_map_mem_usage, + .map_btf_id = &bpf_arena_map_btf_ids[0], +}; + +static u64 clear_lo32(u64 val) +{ + return val & ~(u64)~0U; +} + +/* + * Allocate pages and vmap them into kernel vmalloc area. + * Later the pages will be mmaped into user space vma. + */ +static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt, int node_id) +{ + /* user_vm_end/start are fixed before bpf prog runs */ + long page_cnt_max = (arena->user_vm_end - arena->user_vm_start) >> PAGE_SHIFT; + u64 kern_vm_start = bpf_arena_get_kern_vm_start(arena); + struct page **pages; + long pgoff = 0; + u32 uaddr32; + int ret, i; + + if (page_cnt > page_cnt_max) + return 0; + + if (uaddr) { + if (uaddr & ~PAGE_MASK) + return 0; + pgoff = compute_pgoff(arena, uaddr); + if (pgoff > page_cnt_max - page_cnt) + /* requested address will be outside of user VMA */ + return 0; + } + + /* zeroing is needed, since alloc_pages_bulk() only fills in non-zero entries */ + pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return 0; + + guard(mutex)(&arena->lock); + + if (uaddr) { + ret = is_range_tree_set(&arena->rt, pgoff, page_cnt); + if (ret) + goto out_free_pages; + ret = range_tree_clear(&arena->rt, pgoff, page_cnt); + } else { + ret = pgoff = range_tree_find(&arena->rt, page_cnt); + if (pgoff >= 0) + ret = range_tree_clear(&arena->rt, pgoff, page_cnt); + } + if (ret) + goto out_free_pages; + + ret = bpf_map_alloc_pages(&arena->map, node_id, page_cnt, pages); + if (ret) + goto out; + + uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE); + /* 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) { + for (i = 0; i < page_cnt; i++) + __free_page(pages[i]); + goto out; + } + kvfree(pages); + return clear_lo32(arena->user_vm_start) + uaddr32; +out: + range_tree_set(&arena->rt, pgoff, page_cnt); +out_free_pages: + kvfree(pages); + return 0; +} + +/* + * If page is present in vmalloc area, unmap it from vmalloc area, + * unmap it from all user space vma-s, + * and free it. + */ +static void zap_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + struct vma_list *vml; + + list_for_each_entry(vml, &arena->vma_list, head) + zap_page_range_single(vml->vma, uaddr, + PAGE_SIZE * page_cnt, NULL); +} + +static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + u64 full_uaddr, uaddr_end; + long kaddr, pgoff, i; + struct page *page; + + /* only aligned lower 32-bit are relevant */ + uaddr = (u32)uaddr; + uaddr &= PAGE_MASK; + full_uaddr = clear_lo32(arena->user_vm_start) + uaddr; + uaddr_end = min(arena->user_vm_end, full_uaddr + (page_cnt << PAGE_SHIFT)); + if (full_uaddr >= uaddr_end) + return; + + page_cnt = (uaddr_end - full_uaddr) >> PAGE_SHIFT; + + guard(mutex)(&arena->lock); + + pgoff = compute_pgoff(arena, uaddr); + /* clear range */ + range_tree_set(&arena->rt, pgoff, page_cnt); + + if (page_cnt > 1) + /* bulk zap if multiple pages being freed */ + zap_pages(arena, full_uaddr, page_cnt); + + kaddr = bpf_arena_get_kern_vm_start(arena) + uaddr; + for (i = 0; i < page_cnt; i++, kaddr += PAGE_SIZE, full_uaddr += PAGE_SIZE) { + page = vmalloc_to_page((void *)kaddr); + 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); + } +} + +/* + * Reserve an arena virtual address range without populating it. This call stops + * bpf_arena_alloc_pages from adding pages to this range. + */ +static int arena_reserve_pages(struct bpf_arena *arena, long uaddr, u32 page_cnt) +{ + long page_cnt_max = (arena->user_vm_end - arena->user_vm_start) >> PAGE_SHIFT; + long pgoff; + int ret; + + if (uaddr & ~PAGE_MASK) + return 0; + + pgoff = compute_pgoff(arena, uaddr); + if (pgoff + page_cnt > page_cnt_max) + return -EINVAL; + + guard(mutex)(&arena->lock); + + /* Cannot guard already allocated pages. */ + ret = is_range_tree_set(&arena->rt, pgoff, page_cnt); + if (ret) + return -EBUSY; + + /* "Allocate" the region to prevent it from being allocated. */ + return range_tree_clear(&arena->rt, pgoff, page_cnt); +} + +__bpf_kfunc_start_defs(); + +__bpf_kfunc void *bpf_arena_alloc_pages(void *p__map, void *addr__ign, u32 page_cnt, + int node_id, u64 flags) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || flags || !page_cnt) + return NULL; + + return (void *)arena_alloc_pages(arena, (long)addr__ign, page_cnt, node_id); +} + +__bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || !page_cnt || !ptr__ign) + return; + arena_free_pages(arena, (long)ptr__ign, page_cnt); +} + +__bpf_kfunc int bpf_arena_reserve_pages(void *p__map, void *ptr__ign, u32 page_cnt) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA) + return -EINVAL; + + if (!page_cnt) + return 0; + + return arena_reserve_pages(arena, (long)ptr__ign, page_cnt); +} +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(arena_kfuncs) +BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE | KF_ARENA_RET | KF_ARENA_ARG2) +BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE | KF_ARENA_ARG2) +BTF_ID_FLAGS(func, bpf_arena_reserve_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE | KF_ARENA_ARG2) +BTF_KFUNCS_END(arena_kfuncs) + +static const struct btf_kfunc_id_set common_kfunc_set = { + .owner = THIS_MODULE, + .set = &arena_kfuncs, +}; + +static int __init kfunc_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); +} +late_initcall(kfunc_init); + +void bpf_prog_report_arena_violation(bool write, unsigned long addr, unsigned long fault_ip) +{ + struct bpf_stream_stage ss; + struct bpf_prog *prog; + u64 user_vm_start; + + /* + * The RCU read lock is held to safely traverse the latch tree, but we + * don't need its protection when accessing the prog, since it will not + * disappear while we are handling the fault. + */ + rcu_read_lock(); + prog = bpf_prog_ksym_find(fault_ip); + rcu_read_unlock(); + if (!prog) + return; + + /* Use main prog for stream access */ + prog = prog->aux->main_prog_aux->prog; + + user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena); + addr += clear_lo32(user_vm_start); + + bpf_stream_stage(ss, prog, BPF_STDERR, ({ + bpf_stream_printk(ss, "ERROR: Arena %s access at unmapped address 0x%lx\n", + write ? "WRITE" : "READ", addr); + bpf_stream_dump_stack(ss); + })); +} diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 484706959556..1eeb31c5b317 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -12,6 +12,7 @@ #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/btf_ids.h> +#include <crypto/sha2.h> #include "map_in_map.h" @@ -73,6 +74,9 @@ int array_map_alloc_check(union bpf_attr *attr) /* avoid overflow on round_up(map->value_size) */ if (attr->value_size > INT_MAX) return -E2BIG; + /* percpu map value size is bound by PCPU_MIN_UNIT_SIZE */ + if (percpu && round_up(attr->value_size, 8) > PCPU_MIN_UNIT_SIZE) + return -E2BIG; return 0; } @@ -82,7 +86,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(); + bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; @@ -171,6 +175,17 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) return array->value + (u64)array->elem_size * (index & array->index_mask); } +static int array_map_get_hash(struct bpf_map *map, u32 hash_buf_size, + void *hash_buf) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + + sha256(array->value, (u64)array->elem_size * array->map.max_entries, + hash_buf); + memcpy(array->map.sha, hash_buf, sizeof(array->map.sha)); + return 0; +} + static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) { @@ -246,6 +261,38 @@ 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); @@ -288,18 +335,17 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) } /* Called from syscall */ -static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +int bpf_array_get_next_key(struct bpf_map *map, void *key, void *next_key) { - struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = (u32 *)next_key; - if (index >= array->map.max_entries) { + if (index >= map->max_entries) { *next = 0; return 0; } - if (index == array->map.max_entries - 1) + if (index == map->max_entries - 1) return -ENOENT; *next = index + 1; @@ -307,8 +353,8 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key } /* Called from syscall or from eBPF program */ -static int array_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long array_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; @@ -386,7 +432,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, } /* Called from syscall or from eBPF program */ -static int array_map_delete_elem(struct bpf_map *map, void *key) +static long array_map_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } @@ -396,17 +442,17 @@ 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_internal_structs(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)) + /* We only free internal structs on uref dropping to zero */ + if (!bpf_map_has_internal_structs(map)) return; for (i = 0; i < array->map.max_entries; i++) - bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); + bpf_map_free_internal_structs(map, array_map_elem_ptr(array, i)); } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ @@ -457,7 +503,7 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, if (map->btf_key_type_id) seq_printf(m, "%u: ", *(u32 *)key); btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); rcu_read_unlock(); } @@ -478,7 +524,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key, seq_printf(m, "\tcpu%d: ", cpu); btf_type_seq_show(map->btf, map->btf_value_type_id, per_cpu_ptr(pptr, cpu), m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); } seq_puts(m, "}\n"); @@ -490,8 +536,6 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) { - u32 int_data; - /* One exception for keyless BTF: .bss/.data/.rodata map */ if (btf_type_is_void(key_type)) { if (map->map_type != BPF_MAP_TYPE_ARRAY || @@ -504,14 +548,11 @@ static int array_map_check_btf(const struct bpf_map *map, return 0; } - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) - return -EINVAL; - - int_data = *(u32 *)(key_type + 1); - /* bpf array can only take a u32 key. This check makes sure + /* + * Bpf array can only take a u32 key. This check makes sure * that the btf matches the attr used during map_create. */ - if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) + if (!btf_type_is_i32(key_type)) return -EINVAL; return 0; @@ -563,7 +604,7 @@ static void *bpf_array_map_seq_start(struct seq_file *seq, loff_t *pos) array = container_of(map, struct bpf_array, map); index = info->index & array->index_mask; if (info->percpu_value_buf) - return array->pptrs[index]; + return (void *)(uintptr_t)array->pptrs[index]; return array_map_elem_ptr(array, index); } @@ -582,7 +623,7 @@ static void *bpf_array_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) array = container_of(map, struct bpf_array, map); index = info->index & array->index_mask; if (info->percpu_value_buf) - return array->pptrs[index]; + return (void *)(uintptr_t)array->pptrs[index]; return array_map_elem_ptr(array, index); } @@ -595,7 +636,7 @@ static int __bpf_array_map_seq_show(struct seq_file *seq, void *v) struct bpf_iter_meta meta; struct bpf_prog *prog; int off = 0, cpu = 0; - void __percpu **pptr; + void __percpu *pptr; u32 size; meta.seq = seq; @@ -611,7 +652,7 @@ static int __bpf_array_map_seq_show(struct seq_file *seq, void *v) if (!info->percpu_value_buf) { ctx.value = v; } else { - pptr = v; + pptr = (void __percpu *)(uintptr_t)v; size = array->elem_size; for_each_possible_cpu(cpu) { copy_map_value_long(map, info->percpu_value_buf + off, @@ -686,8 +727,8 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_array_map_info), }; -static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn, - void *callback_ctx, u64 flags) +static long bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn, + void *callback_ctx, u64 flags) { u32 i, key, num_elems = 0; struct bpf_array *array; @@ -695,13 +736,13 @@ static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_ u64 ret = 0; void *val; + cant_migrate(); + if (flags != 0) return -EINVAL; is_percpu = map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; array = container_of(map, struct bpf_array, map); - if (is_percpu) - migrate_disable(); for (i = 0; i < map->max_entries; i++) { if (is_percpu) val = this_cpu_ptr(array->pptrs[i]); @@ -716,19 +757,39 @@ static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_ break; } - if (is_percpu) - migrate_enable(); return num_elems; } +static u64 array_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; + u32 elem_size = array->elem_size; + u64 entries = map->max_entries; + u64 usage = sizeof(*array); + + if (percpu) { + usage += entries * sizeof(void *); + usage += entries * elem_size * num_possible_cpus(); + } else { + if (map->map_flags & BPF_F_MMAPABLE) { + usage = PAGE_ALIGN(usage); + usage += PAGE_ALIGN(entries * elem_size); + } else { + usage += entries * elem_size; + } + } + return usage; +} + BTF_ID_LIST_SINGLE(array_map_btf_ids, struct, bpf_array) const struct bpf_map_ops array_map_ops = { .map_meta_equal = array_map_meta_equal, .map_alloc_check = array_map_alloc_check, .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_get_next_key = bpf_array_get_next_key, + .map_release_uref = array_map_free_internal_structs, .map_lookup_elem = array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, @@ -742,8 +803,10 @@ const struct bpf_map_ops array_map_ops = { .map_update_batch = generic_map_update_batch, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_array_elem, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], .iter_seq_info = &iter_seq_info, + .map_get_hash = &array_map_get_hash, }; const struct bpf_map_ops percpu_array_map_ops = { @@ -751,8 +814,9 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = array_map_free, - .map_get_next_key = array_map_get_next_key, + .map_get_next_key = bpf_array_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, @@ -762,6 +826,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_update_batch = generic_map_update_batch, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_array_elem, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; @@ -843,11 +908,11 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, } if (old_ptr) - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, true); return 0; } -static int fd_array_map_delete_elem(struct bpf_map *map, void *key) +static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer) { struct bpf_array *array = container_of(map, struct bpf_array, map); void *old_ptr; @@ -866,32 +931,60 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) } if (old_ptr) { - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, need_defer); return 0; } else { return -ENOENT; } } +static long fd_array_map_delete_elem(struct bpf_map *map, void *key) +{ + return __fd_array_map_delete_elem(map, key, true); +} + static void *prog_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { struct bpf_prog *prog = bpf_prog_get(fd); + bool is_extended; if (IS_ERR(prog)) return prog; - if (!bpf_prog_map_compatible(map, prog)) { + if (prog->type == BPF_PROG_TYPE_EXT || + !bpf_prog_map_compatible(map, prog)) { bpf_prog_put(prog); return ERR_PTR(-EINVAL); } + mutex_lock(&prog->aux->ext_mutex); + is_extended = prog->aux->is_extended; + if (!is_extended) + prog->aux->prog_array_member_cnt++; + mutex_unlock(&prog->aux->ext_mutex); + if (is_extended) { + /* Extended prog can not be tail callee. It's to prevent a + * potential infinite loop like: + * tail callee prog entry -> tail callee prog subprog -> + * freplace prog entry --tailcall-> tail callee prog entry. + */ + bpf_prog_put(prog); + return ERR_PTR(-EBUSY); + } + return prog; } -static void prog_fd_array_put_ptr(void *ptr) +static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { - bpf_prog_put(ptr); + struct bpf_prog *prog = ptr; + + mutex_lock(&prog->aux->ext_mutex); + prog->aux->prog_array_member_cnt--; + mutex_unlock(&prog->aux->ext_mutex); + /* bpf_prog is freed after one RCU or tasks trace grace period */ + bpf_prog_put(prog); } static u32 prog_fd_array_sys_lookup_elem(void *ptr) @@ -900,13 +993,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr) } /* decrement refcnt of all bpf_progs that are stored in this map */ -static void bpf_fd_array_map_clear(struct bpf_map *map) +static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; for (i = 0; i < array->map.max_entries; i++) - fd_array_map_delete_elem(map, &i); + __fd_array_map_delete_elem(map, &i, need_defer); } static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, @@ -925,7 +1018,7 @@ static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, prog_id = prog_fd_array_sys_lookup_elem(ptr); btf_type_seq_show(map->btf, map->btf_value_type_id, &prog_id, m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); } } @@ -988,11 +1081,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map, mutex_unlock(&aux->poke_mutex); } +void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + WARN_ON_ONCE(1); +} + static void prog_array_map_poke_run(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new) { - u8 *old_addr, *new_addr, *old_bypass_addr; struct prog_poke_elem *elem; struct bpf_array_aux *aux; @@ -1001,7 +1099,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, list_for_each_entry(elem, &aux->poke_progs, list) { struct bpf_jit_poke_descriptor *poke; - int i, ret; + int i; for (i = 0; i < elem->aux->size_poke_tab; i++) { poke = &elem->aux->poke_tab[i]; @@ -1020,21 +1118,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, * activated, so tail call updates can arrive from here * while JIT is still finishing its final fixup for * non-activated poke entries. - * 3) On program teardown, the program's kallsym entry gets - * removed out of RCU callback, but we can only untrack - * from sleepable context, therefore bpf_arch_text_poke() - * might not see that this is in BPF text section and - * bails out with -EINVAL. As these are unreachable since - * RCU grace period already passed, we simply skip them. - * 4) Also programs reaching refcount of zero while patching + * 3) Also programs reaching refcount of zero while patching * is in progress is okay since we're protected under * poke_mutex and untrack the programs before the JIT - * buffer is freed. When we're still in the middle of - * patching and suddenly kallsyms entry of the program - * gets evicted, we just skip the rest which is fine due - * to point 3). - * 5) Any other error happening below from bpf_arch_text_poke() - * is a unexpected bug. + * buffer is freed. */ if (!READ_ONCE(poke->tailcall_target_stable)) continue; @@ -1044,39 +1131,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, poke->tail_call.key != key) continue; - old_bypass_addr = old ? NULL : poke->bypass_addr; - old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; - new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; - - if (new) { - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, new_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - if (!old) { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - poke->bypass_addr, - NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } - } else { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - old_bypass_addr, - poke->bypass_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - /* let other CPUs finish the execution of program - * so that it will not possible to expose them - * to invalid nop, stack unwind, nop state - */ - if (!ret) - synchronize_rcu(); - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } + bpf_arch_poke_desc_update(poke, new, old); } } } @@ -1085,7 +1140,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_array_aux, work)->map; - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, true); bpf_map_put(map); } @@ -1148,7 +1203,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_poke_track = prog_array_map_poke_track, .map_poke_untrack = prog_array_map_poke_untrack, .map_poke_run = prog_array_map_poke_run, - .map_get_next_key = array_map_get_next_key, + .map_get_next_key = bpf_array_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = prog_fd_array_get_ptr, @@ -1156,6 +1211,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = prog_array_map_clear, .map_seq_show_elem = prog_array_map_seq_show_elem, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; @@ -1164,7 +1220,7 @@ static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, { struct bpf_event_entry *ee; - ee = kzalloc(sizeof(*ee), GFP_ATOMIC); + ee = kzalloc(sizeof(*ee), GFP_KERNEL); if (ee) { ee->event = perf_file->private_data; ee->perf_file = perf_file; @@ -1214,8 +1270,9 @@ err_out: return ee; } -static void perf_event_fd_array_put_ptr(void *ptr) +static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + /* bpf_perf_event is freed after one RCU grace period */ bpf_event_entry_free_rcu(ptr); } @@ -1233,7 +1290,7 @@ static void perf_event_fd_array_release(struct bpf_map *map, for (i = 0; i < array->map.max_entries; i++) { ee = READ_ONCE(array->ptrs[i]); if (ee && ee->map_file == map_file) - fd_array_map_delete_elem(map, &i); + __fd_array_map_delete_elem(map, &i, true); } rcu_read_unlock(); } @@ -1241,7 +1298,7 @@ static void perf_event_fd_array_release(struct bpf_map *map, static void perf_event_fd_array_map_free(struct bpf_map *map) { if (map->map_flags & BPF_F_PRESERVE_ELEMS) - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, false); fd_array_map_free(map); } @@ -1250,13 +1307,14 @@ const struct bpf_map_ops perf_event_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = perf_event_fd_array_map_free, - .map_get_next_key = array_map_get_next_key, + .map_get_next_key = bpf_array_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = perf_event_fd_array_get_ptr, .map_fd_put_ptr = perf_event_fd_array_put_ptr, .map_release = perf_event_fd_array_release, .map_check_btf = map_check_no_btf, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; @@ -1268,7 +1326,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map, return cgroup_get_from_fd(fd); } -static void cgroup_fd_array_put_ptr(void *ptr) +static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { /* cgroup_put free cgrp after a rcu grace period */ cgroup_put(ptr); @@ -1276,7 +1334,7 @@ static void cgroup_fd_array_put_ptr(void *ptr) static void cgroup_fd_array_free(struct bpf_map *map) { - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, false); fd_array_map_free(map); } @@ -1285,12 +1343,13 @@ const struct bpf_map_ops cgroup_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = cgroup_fd_array_free, - .map_get_next_key = array_map_get_next_key, + .map_get_next_key = bpf_array_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = cgroup_fd_array_get_ptr, .map_fd_put_ptr = cgroup_fd_array_put_ptr, .map_check_btf = map_check_no_btf, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; #endif @@ -1320,7 +1379,7 @@ static void array_of_map_free(struct bpf_map *map) * is protected by fdget/fdput. */ bpf_map_meta_free(map->inner_map_meta); - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, false); fd_array_map_free(map); } @@ -1369,7 +1428,7 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_of_map_alloc, .map_free = array_of_map_free, - .map_get_next_key = array_map_get_next_key, + .map_get_next_key = bpf_array_get_next_key, .map_lookup_elem = array_of_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = bpf_map_fd_get_ptr, @@ -1379,5 +1438,6 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_lookup_batch = generic_map_lookup_batch, .map_update_batch = generic_map_update_batch, .map_check_btf = map_check_no_btf, + .map_mem_usage = array_map_mem_usage, .map_btf_id = &array_map_btf_ids[0], }; diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 48ee750849f2..35e1ddca74d2 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -16,13 +16,6 @@ struct bpf_bloom_filter { struct bpf_map map; u32 bitset_mask; u32 hash_seed; - /* If the size of the values in the bloom filter is u32 aligned, - * then it is more performant to use jhash2 as the underlying hash - * function, else we use jhash. This tracks the number of u32s - * in an u32-aligned value size. If the value size is not u32 aligned, - * this will be 0. - */ - u32 aligned_u32_count; u32 nr_hash_funcs; unsigned long bitset[]; }; @@ -32,16 +25,15 @@ static u32 hash(struct bpf_bloom_filter *bloom, void *value, { u32 h; - if (bloom->aligned_u32_count) - h = jhash2(value, bloom->aligned_u32_count, - bloom->hash_seed + index); + if (likely(value_size % 4 == 0)) + h = jhash2(value, value_size / 4, bloom->hash_seed + index); else h = jhash(value, value_size, bloom->hash_seed + index); return h & bloom->bitset_mask; } -static int bloom_map_peek_elem(struct bpf_map *map, void *value) +static long bloom_map_peek_elem(struct bpf_map *map, void *value) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); @@ -56,7 +48,7 @@ static int bloom_map_peek_elem(struct bpf_map *map, void *value) return 0; } -static int bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) +static long bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); @@ -73,12 +65,12 @@ static int bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) return 0; } -static int bloom_map_pop_elem(struct bpf_map *map, void *value) +static long bloom_map_pop_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } -static int bloom_map_delete_elem(struct bpf_map *map, void *value) +static long bloom_map_delete_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } @@ -88,15 +80,24 @@ 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; int numa_node = bpf_map_attr_numa_node(attr); struct bpf_bloom_filter *bloom; - if (!bpf_capable()) - return ERR_PTR(-EPERM); - if (attr->key_size != 0 || attr->value_size == 0 || attr->max_entries == 0 || attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || @@ -152,11 +153,6 @@ static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) bloom->nr_hash_funcs = nr_hash_funcs; bloom->bitset_mask = bitset_mask; - /* Check whether the value size is u32-aligned */ - if ((attr->value_size & (sizeof(u32) - 1)) == 0) - bloom->aligned_u32_count = - attr->value_size / sizeof(u32); - if (!(attr->map_flags & BPF_F_ZERO_SEED)) bloom->hash_seed = get_random_u32(); @@ -177,8 +173,8 @@ static void *bloom_map_lookup_elem(struct bpf_map *map, void *key) return ERR_PTR(-EINVAL); } -static int bloom_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long bloom_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { /* The eBPF program should use map_push_elem instead */ return -EINVAL; @@ -193,9 +189,21 @@ static int bloom_map_check_btf(const struct bpf_map *map, return btf_type_is_void(key_type) ? 0 : -EINVAL; } +static u64 bloom_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom; + u64 bitset_bytes; + + bloom = container_of(map, struct bpf_bloom_filter, map); + bitset_bytes = BITS_TO_BYTES((u64)bloom->bitset_mask + 1); + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + return sizeof(*bloom) + bitset_bytes; +} + 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, @@ -206,5 +214,6 @@ const struct bpf_map_ops bloom_filter_map_ops = { .map_update_elem = bloom_map_update_elem, .map_delete_elem = bloom_map_delete_elem, .map_check_btf = bloom_map_check_btf, + .map_mem_usage = bloom_map_mem_usage, .map_btf_id = &bpf_bloom_map_btf_ids[0], }; diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index 6cdf6d9ed91d..0687a760974a 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -15,22 +15,20 @@ static DEFINE_PER_CPU(int, bpf_cgrp_storage_busy); static void bpf_cgrp_storage_lock(void) { - migrate_disable(); + cant_migrate(); this_cpu_inc(bpf_cgrp_storage_busy); } static void bpf_cgrp_storage_unlock(void) { this_cpu_dec(bpf_cgrp_storage_busy); - migrate_enable(); } static bool bpf_cgrp_storage_trylock(void) { - migrate_disable(); + cant_migrate(); if (unlikely(this_cpu_inc_return(bpf_cgrp_storage_busy) != 1)) { this_cpu_dec(bpf_cgrp_storage_busy); - migrate_enable(); return false; } return true; @@ -46,25 +44,17 @@ static struct bpf_local_storage __rcu **cgroup_storage_ptr(void *owner) void bpf_cgrp_storage_free(struct cgroup *cgroup) { struct bpf_local_storage *local_storage; - bool free_cgroup_storage = false; - unsigned long flags; - rcu_read_lock(); + rcu_read_lock_dont_migrate(); local_storage = rcu_dereference(cgroup->bpf_cgrp_storage); - if (!local_storage) { - rcu_read_unlock(); - return; - } + if (!local_storage) + goto out; bpf_cgrp_storage_lock(); - raw_spin_lock_irqsave(&local_storage->lock, flags); - free_cgroup_storage = bpf_local_storage_unlink_nolock(local_storage); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_local_storage_destroy(local_storage); bpf_cgrp_storage_unlock(); - rcu_read_unlock(); - - if (free_cgroup_storage) - kfree_rcu(local_storage, rcu); +out: + rcu_read_unlock_migrate(); } static struct bpf_local_storage_data * @@ -89,7 +79,7 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) int fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return ERR_CAST(cgroup); @@ -100,21 +90,21 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) return sdata ? sdata->data : NULL; } -static int bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct cgroup *cgroup; int fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); bpf_cgrp_storage_lock(); sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, - value, map_flags, GFP_ATOMIC); + value, map_flags, false, GFP_ATOMIC); bpf_cgrp_storage_unlock(); cgroup_put(cgroup); return PTR_ERR_OR_ZERO(sdata); @@ -128,17 +118,17 @@ static int cgroup_storage_delete(struct cgroup *cgroup, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata), true); + bpf_selem_unlink(SELEM(sdata), false); return 0; } -static int bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) +static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) { struct cgroup *cgroup; int err, fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); @@ -156,12 +146,12 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { - return bpf_local_storage_map_alloc(attr, &cgroup_cache); + return bpf_local_storage_map_alloc(attr, &cgroup_cache, true); } static void cgroup_storage_map_free(struct bpf_map *map) { - bpf_local_storage_map_free(map, &cgroup_cache, NULL); + bpf_local_storage_map_free(map, &cgroup_cache, &bpf_cgrp_storage_busy); } /* *gfp_flags* is a hidden argument provided by the verifier */ @@ -169,6 +159,7 @@ BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, void *, value, u64, flags, gfp_t, gfp_flags) { struct bpf_local_storage_data *sdata; + bool nobusy; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) @@ -177,21 +168,21 @@ BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, if (!cgroup) return (unsigned long)NULL; - if (!bpf_cgrp_storage_trylock()) - return (unsigned long)NULL; + nobusy = bpf_cgrp_storage_trylock(); - sdata = cgroup_storage_lookup(cgroup, map, true); + sdata = cgroup_storage_lookup(cgroup, map, nobusy); if (sdata) goto unlock; /* only allocate new storage, when the cgroup is refcounted */ if (!percpu_ref_is_dying(&cgroup->self.refcnt) && - (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) + (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy) sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, - value, BPF_NOEXIST, gfp_flags); + value, BPF_NOEXIST, false, gfp_flags); unlock: - bpf_cgrp_storage_unlock(); + if (nobusy) + bpf_cgrp_storage_unlock(); return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } @@ -221,6 +212,7 @@ const struct bpf_map_ops cgrp_storage_map_ops = { .map_update_elem = bpf_cgrp_storage_update_elem, .map_delete_elem = bpf_cgrp_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, + .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = cgroup_storage_ptr, }; @@ -230,7 +222,7 @@ const struct bpf_func_proto bpf_cgrp_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_cgroup_btf_id[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -241,6 +233,6 @@ const struct bpf_func_proto bpf_cgrp_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_cgroup_btf_id[0], }; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 05f4c66c9089..e54cce2b9175 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -16,7 +16,6 @@ #include <uapi/linux/btf.h> #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> -#include <linux/fdtable.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(inode_cache); @@ -57,66 +56,49 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, void bpf_inode_storage_free(struct inode *inode) { struct bpf_local_storage *local_storage; - bool free_inode_storage = false; struct bpf_storage_blob *bsb; bsb = bpf_inode(inode); if (!bsb) return; - rcu_read_lock(); + rcu_read_lock_dont_migrate(); local_storage = rcu_dereference(bsb->storage); - if (!local_storage) { - rcu_read_unlock(); - return; - } - - raw_spin_lock_bh(&local_storage->lock); - free_inode_storage = bpf_local_storage_unlink_nolock(local_storage); - raw_spin_unlock_bh(&local_storage->lock); - rcu_read_unlock(); + if (!local_storage) + goto out; - if (free_inode_storage) - kfree_rcu(local_storage, rcu); + bpf_local_storage_destroy(local_storage); +out: + rcu_read_unlock_migrate(); } static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; - struct file *f; - int fd; + CLASS(fd_raw, f)(*(int *)key); - fd = *(int *)key; - f = fget_raw(fd); - if (!f) + if (fd_empty(f)) return ERR_PTR(-EBADF); - sdata = inode_storage_lookup(f->f_inode, map, true); - fput(f); + sdata = inode_storage_lookup(file_inode(fd_file(f)), map, true); return sdata ? sdata->data : NULL; } -static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; - struct file *f; - int fd; + CLASS(fd_raw, f)(*(int *)key); - fd = *(int *)key; - f = fget_raw(fd); - if (!f) + if (fd_empty(f)) return -EBADF; - if (!inode_storage_ptr(f->f_inode)) { - fput(f); + if (!inode_storage_ptr(file_inode(fd_file(f)))) return -EBADF; - } - sdata = bpf_local_storage_update(f->f_inode, + sdata = bpf_local_storage_update(file_inode(fd_file(f)), (struct bpf_local_storage_map *)map, - value, map_flags, GFP_ATOMIC); - fput(f); + value, map_flags, false, GFP_ATOMIC); return PTR_ERR_OR_ZERO(sdata); } @@ -128,24 +110,18 @@ static int inode_storage_delete(struct inode *inode, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata), true); + bpf_selem_unlink(SELEM(sdata), false); return 0; } -static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) +static long bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) { - struct file *f; - int fd, err; + CLASS(fd_raw, f)(*(int *)key); - fd = *(int *)key; - f = fget_raw(fd); - if (!f) + if (fd_empty(f)) return -EBADF; - - err = inode_storage_delete(f->f_inode, map); - fput(f); - return err; + return inode_storage_delete(file_inode(fd_file(f)), map); } /* *gfp_flags* is a hidden argument provided by the verifier */ @@ -176,7 +152,7 @@ BPF_CALL_5(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { sdata = bpf_local_storage_update( inode, (struct bpf_local_storage_map *)map, value, - BPF_NOEXIST, gfp_flags); + BPF_NOEXIST, false, gfp_flags); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } @@ -205,7 +181,7 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) { - return bpf_local_storage_map_alloc(attr, &inode_cache); + return bpf_local_storage_map_alloc(attr, &inode_cache, false); } static void inode_storage_map_free(struct bpf_map *map) @@ -223,6 +199,7 @@ const struct bpf_map_ops inode_storage_map_ops = { .map_update_elem = bpf_fd_inode_storage_update_elem, .map_delete_elem = bpf_fd_inode_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, + .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = inode_storage_ptr, }; @@ -234,7 +211,7 @@ const struct bpf_func_proto bpf_inode_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -245,6 +222,6 @@ const struct bpf_func_proto bpf_inode_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], }; diff --git a/kernel/bpf/bpf_insn_array.c b/kernel/bpf/bpf_insn_array.c new file mode 100644 index 000000000000..c96630cb75bf --- /dev/null +++ b/kernel/bpf/bpf_insn_array.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025 Isovalent */ + +#include <linux/bpf.h> + +struct bpf_insn_array { + struct bpf_map map; + atomic_t used; + long *ips; + DECLARE_FLEX_ARRAY(struct bpf_insn_array_value, values); +}; + +#define cast_insn_array(MAP_PTR) \ + container_of((MAP_PTR), struct bpf_insn_array, map) + +#define INSN_DELETED ((u32)-1) + +static inline u64 insn_array_alloc_size(u32 max_entries) +{ + const u64 base_size = sizeof(struct bpf_insn_array); + const u64 entry_size = sizeof(struct bpf_insn_array_value); + + return base_size + max_entries * (entry_size + sizeof(long)); +} + +static int insn_array_alloc_check(union bpf_attr *attr) +{ + u32 value_size = sizeof(struct bpf_insn_array_value); + + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != value_size || attr->map_flags != 0) + return -EINVAL; + + return 0; +} + +static void insn_array_free(struct bpf_map *map) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + + bpf_map_area_free(insn_array); +} + +static struct bpf_map *insn_array_alloc(union bpf_attr *attr) +{ + u64 size = insn_array_alloc_size(attr->max_entries); + struct bpf_insn_array *insn_array; + + insn_array = bpf_map_area_alloc(size, NUMA_NO_NODE); + if (!insn_array) + return ERR_PTR(-ENOMEM); + + /* ips are allocated right after the insn_array->values[] array */ + insn_array->ips = (void *)&insn_array->values[attr->max_entries]; + + bpf_map_init_from_attr(&insn_array->map, attr); + + /* BPF programs aren't allowed to write to the map */ + insn_array->map.map_flags |= BPF_F_RDONLY_PROG; + + return &insn_array->map; +} + +static void *insn_array_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + u32 index = *(u32 *)key; + + if (unlikely(index >= insn_array->map.max_entries)) + return NULL; + + return &insn_array->values[index]; +} + +static long insn_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + u32 index = *(u32 *)key; + struct bpf_insn_array_value val = {}; + + if (unlikely(index >= insn_array->map.max_entries)) + return -E2BIG; + + if (unlikely(map_flags & BPF_NOEXIST)) + return -EEXIST; + + copy_map_value(map, &val, value); + if (val.jitted_off || val.xlated_off) + return -EINVAL; + + insn_array->values[index].orig_off = val.orig_off; + + return 0; +} + +static long insn_array_delete_elem(struct bpf_map *map, void *key) +{ + return -EINVAL; +} + +static int insn_array_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + if (!btf_type_is_i32(key_type)) + return -EINVAL; + + if (!btf_type_is_i64(value_type)) + return -EINVAL; + + return 0; +} + +static u64 insn_array_mem_usage(const struct bpf_map *map) +{ + return insn_array_alloc_size(map->max_entries); +} + +static int insn_array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + + if ((off % sizeof(long)) != 0 || + (off / sizeof(long)) >= map->max_entries) + return -EINVAL; + + /* from BPF's point of view, this map is a jump table */ + *imm = (unsigned long)insn_array->ips + off; + + return 0; +} + +BTF_ID_LIST_SINGLE(insn_array_btf_ids, struct, bpf_insn_array) + +const struct bpf_map_ops insn_array_map_ops = { + .map_alloc_check = insn_array_alloc_check, + .map_alloc = insn_array_alloc, + .map_free = insn_array_free, + .map_get_next_key = bpf_array_get_next_key, + .map_lookup_elem = insn_array_lookup_elem, + .map_update_elem = insn_array_update_elem, + .map_delete_elem = insn_array_delete_elem, + .map_check_btf = insn_array_check_btf, + .map_mem_usage = insn_array_mem_usage, + .map_direct_value_addr = insn_array_map_direct_value_addr, + .map_btf_id = &insn_array_btf_ids[0], +}; + +static inline bool is_frozen(struct bpf_map *map) +{ + guard(mutex)(&map->freeze_mutex); + + return map->frozen; +} + +static bool is_insn_array(const struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_INSN_ARRAY; +} + +static inline bool valid_offsets(const struct bpf_insn_array *insn_array, + const struct bpf_prog *prog) +{ + u32 off; + int i; + + for (i = 0; i < insn_array->map.max_entries; i++) { + off = insn_array->values[i].orig_off; + + if (off >= prog->len) + return false; + + if (off > 0) { + if (prog->insnsi[off-1].code == (BPF_LD | BPF_DW | BPF_IMM)) + return false; + } + } + + return true; +} + +int bpf_insn_array_init(struct bpf_map *map, const struct bpf_prog *prog) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + struct bpf_insn_array_value *values = insn_array->values; + int i; + + if (!is_frozen(map)) + return -EINVAL; + + if (!valid_offsets(insn_array, prog)) + return -EINVAL; + + /* + * There can be only one program using the map + */ + if (atomic_xchg(&insn_array->used, 1)) + return -EBUSY; + + /* + * Reset all the map indexes to the original values. This is needed, + * e.g., when a replay of verification with different log level should + * be performed. + */ + for (i = 0; i < map->max_entries; i++) + values[i].xlated_off = values[i].orig_off; + + return 0; +} + +int bpf_insn_array_ready(struct bpf_map *map) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + int i; + + for (i = 0; i < map->max_entries; i++) { + if (insn_array->values[i].xlated_off == INSN_DELETED) + continue; + if (!insn_array->ips[i]) + return -EFAULT; + } + + return 0; +} + +void bpf_insn_array_release(struct bpf_map *map) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + + atomic_set(&insn_array->used, 0); +} + +void bpf_insn_array_adjust(struct bpf_map *map, u32 off, u32 len) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + int i; + + if (len <= 1) + return; + + for (i = 0; i < map->max_entries; i++) { + if (insn_array->values[i].xlated_off <= off) + continue; + if (insn_array->values[i].xlated_off == INSN_DELETED) + continue; + insn_array->values[i].xlated_off += len - 1; + } +} + +void bpf_insn_array_adjust_after_remove(struct bpf_map *map, u32 off, u32 len) +{ + struct bpf_insn_array *insn_array = cast_insn_array(map); + int i; + + for (i = 0; i < map->max_entries; i++) { + if (insn_array->values[i].xlated_off < off) + continue; + if (insn_array->values[i].xlated_off == INSN_DELETED) + continue; + if (insn_array->values[i].xlated_off < off + len) + insn_array->values[i].xlated_off = INSN_DELETED; + else + insn_array->values[i].xlated_off -= len; + } +} + +/* + * This function is called by JITs. The image is the real program + * image, the offsets array set up the xlated -> jitted mapping. + * The offsets[xlated] offset should point to the beginning of + * the jitted instruction. + */ +void bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image) +{ + struct bpf_insn_array *insn_array; + struct bpf_map *map; + u32 xlated_off; + int i, j; + + if (!offsets || !image) + return; + + for (i = 0; i < prog->aux->used_map_cnt; i++) { + map = prog->aux->used_maps[i]; + if (!is_insn_array(map)) + continue; + + insn_array = cast_insn_array(map); + for (j = 0; j < map->max_entries; j++) { + xlated_off = insn_array->values[j].xlated_off; + if (xlated_off == INSN_DELETED) + continue; + if (xlated_off < prog->aux->subprog_start) + continue; + xlated_off -= prog->aux->subprog_start; + if (xlated_off >= prog->len) + continue; + + insn_array->values[j].jitted_off = offsets[xlated_off]; + insn_array->ips[j] = (long)(image + offsets[xlated_off]); + } + } +} diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 5dc307bdeaeb..eec60b57bd3d 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -38,8 +38,7 @@ static DEFINE_MUTEX(link_mutex); /* incremented on every opened seq_file */ static atomic64_t session_id; -static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, - const struct bpf_iter_seq_info *seq_info); +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link); static void bpf_iter_inc_seq_num(struct seq_file *seq) { @@ -257,7 +256,7 @@ static int iter_open(struct inode *inode, struct file *file) { struct bpf_iter_link *link = inode->i_private; - return prepare_seq_file(file, link, __get_seq_info(link)); + return prepare_seq_file(file, link); } static int iter_release(struct inode *inode, struct file *file) @@ -283,7 +282,6 @@ static int iter_release(struct inode *inode, struct file *file) const struct file_operations bpf_iter_fops = { .open = iter_open, - .llseek = no_llseek, .read = bpf_seq_read, .release = iter_release, }; @@ -336,7 +334,7 @@ static void cache_btf_id(struct bpf_iter_target_info *tinfo, tinfo->btf_id = prog->aux->attach_btf_id; } -bool bpf_iter_prog_supported(struct bpf_prog *prog) +int bpf_iter_prog_supported(struct bpf_prog *prog) { const char *attach_fname = prog->aux->attach_func_name; struct bpf_iter_target_info *tinfo = NULL, *iter; @@ -345,7 +343,7 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) int prefix_len = strlen(prefix); if (strncmp(attach_fname, prefix, prefix_len)) - return false; + return -EINVAL; mutex_lock(&targets_mutex); list_for_each_entry(iter, &targets, list) { @@ -361,12 +359,11 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) } mutex_unlock(&targets_mutex); - if (tinfo) { - prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size; - prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info; - } + if (!tinfo) + return -EINVAL; - return tinfo != NULL; + return bpf_prog_ctx_arg_info_init(prog, tinfo->reg_info->ctx_arg_info, + tinfo->reg_info->ctx_arg_info_size); } const struct bpf_func_proto * @@ -548,14 +545,15 @@ int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, return -ENOENT; /* Only allow sleepable program for resched-able iterator */ - if (prog->aux->sleepable && !bpf_iter_target_support_resched(tinfo)) + if (prog->sleepable && !bpf_iter_target_support_resched(tinfo)) return -EINVAL; link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); if (!link) return -ENOMEM; - bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); + bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog, + attr->link_create.attach_type); link->tinfo = tinfo; err = bpf_link_prime(&link->link, &link_primer); @@ -588,9 +586,9 @@ static void init_seq_meta(struct bpf_iter_priv_data *priv_data, priv_data->done_stop = false; } -static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, - const struct bpf_iter_seq_info *seq_info) +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link) { + const struct bpf_iter_seq_info *seq_info = __get_seq_info(link); struct bpf_iter_priv_data *priv_data; struct bpf_iter_target_info *tinfo; struct bpf_prog *prog; @@ -636,37 +634,24 @@ release_prog: int bpf_iter_new_fd(struct bpf_link *link) { struct bpf_iter_link *iter_link; - struct file *file; unsigned int flags; - int err, fd; + int err; if (link->ops != &bpf_iter_link_lops) return -EINVAL; flags = O_RDONLY | O_CLOEXEC; - fd = get_unused_fd_flags(flags); - if (fd < 0) - return fd; - - file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags); - if (IS_ERR(file)) { - err = PTR_ERR(file); - goto free_fd; - } + + FD_PREPARE(fdf, flags, anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags)); + if (fdf.err) + return fdf.err; iter_link = container_of(link, struct bpf_iter_link, link); - err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link)); + err = prepare_seq_file(fd_prepare_file(fdf), iter_link); if (err) - goto free_file; - - fd_install(fd, file); - return fd; + return err; /* Automatic cleanup handles fput */ -free_file: - fput(file); -free_fd: - put_unused_fd(fd); - return err; + return fd_publish(fdf); } struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop) @@ -697,7 +682,7 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) struct bpf_run_ctx run_ctx, *old_run_ctx; int ret; - if (prog->aux->sleepable) { + if (prog->sleepable) { rcu_read_lock_trace(); migrate_disable(); might_fault(); @@ -707,13 +692,11 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) migrate_enable(); rcu_read_unlock_trace(); } else { - rcu_read_lock(); - migrate_disable(); + rcu_read_lock_dont_migrate(); old_run_ctx = bpf_set_run_ctx(&run_ctx); ret = bpf_prog_run(prog, ctx); bpf_reset_run_ctx(old_run_ctx); - migrate_enable(); - rcu_read_unlock(); + rcu_read_unlock_migrate(); } /* bpf program can only return 0 or 1: @@ -776,3 +759,69 @@ const struct bpf_func_proto bpf_loop_proto = { .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; + +struct bpf_iter_num_kern { + int cur; /* current value, inclusive */ + int end; /* final value, exclusive */ +} __aligned(8); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) +{ + struct bpf_iter_num_kern *s = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num)); + + /* start == end is legit, it's an empty range and we'll just get NULL + * on first (and any subsequent) bpf_iter_num_next() call + */ + if (start > end) { + s->cur = s->end = 0; + return -EINVAL; + } + + /* avoid overflows, e.g., if start == INT_MIN and end == INT_MAX */ + if ((s64)end - (s64)start > BPF_MAX_LOOPS) { + s->cur = s->end = 0; + return -E2BIG; + } + + /* user will call bpf_iter_num_next() first, + * which will set s->cur to exactly start value; + * underflow shouldn't matter + */ + s->cur = start - 1; + s->end = end; + + return 0; +} + +__bpf_kfunc int *bpf_iter_num_next(struct bpf_iter_num* it) +{ + struct bpf_iter_num_kern *s = (void *)it; + + /* check failed initialization or if we are done (same behavior); + * need to be careful about overflow, so convert to s64 for checks, + * e.g., if s->cur == s->end == INT_MAX, we can't just do + * s->cur + 1 >= s->end + */ + if ((s64)(s->cur + 1) >= s->end) { + s->cur = s->end = 0; + return NULL; + } + + s->cur++; + + return &s->cur; +} + +__bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it) +{ + struct bpf_iter_num_kern *s = (void *)it; + + s->cur = s->end = 0; +} + +__bpf_kfunc_end_defs(); diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index b39a46e8fb08..e2fe6c32822b 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -51,11 +51,21 @@ owner_storage(struct bpf_local_storage_map *smap, void *owner) return map->ops->map_owner_storage_ptr(owner); } +static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed_lockless(&selem->snode); +} + static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } +static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed_lockless(&selem->map_node); +} + static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); @@ -63,28 +73,40 @@ static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, - void *value, bool charge_mem, gfp_t gfp_flags) + void *value, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_elem *selem; - if (charge_mem && mem_charge(smap, owner, smap->elem_size)) + if (mem_charge(smap, owner, smap->elem_size)) return NULL; - selem = bpf_map_kzalloc(&smap->map, smap->elem_size, - gfp_flags | __GFP_NOWARN); + if (smap->use_kmalloc_nolock) { + selem = bpf_map_kmalloc_nolock(&smap->map, smap->elem_size, + __GFP_ZERO, NUMA_NO_NODE); + } else { + selem = bpf_map_kzalloc(&smap->map, smap->elem_size, + gfp_flags | __GFP_NOWARN); + } + if (selem) { - if (value) + RCU_INIT_POINTER(SDATA(selem)->smap, smap); + + if (value) { + /* No need to call check_and_init_map_value as memory is zero init */ copy_map_value(&smap->map, SDATA(selem)->data, value); + if (swap_uptrs) + bpf_obj_swap_uptrs(smap->map.record, SDATA(selem)->data, value); + } return selem; } - if (charge_mem) - mem_uncharge(smap, owner, smap->elem_size); + mem_uncharge(smap, owner, smap->elem_size); return NULL; } -void bpf_local_storage_free_rcu(struct rcu_head *rcu) +/* rcu tasks trace callback for use_kmalloc_nolock == false */ +static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; @@ -98,7 +120,55 @@ void bpf_local_storage_free_rcu(struct rcu_head *rcu) kfree_rcu(local_storage, rcu); } -static void bpf_selem_free_rcu(struct rcu_head *rcu) +/* Handle use_kmalloc_nolock == false */ +static void __bpf_local_storage_free(struct bpf_local_storage *local_storage, + bool vanilla_rcu) +{ + if (vanilla_rcu) + kfree_rcu(local_storage, rcu); + else + call_rcu_tasks_trace(&local_storage->rcu, + __bpf_local_storage_free_trace_rcu); +} + +static void bpf_local_storage_free_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage *local_storage; + + local_storage = container_of(rcu, struct bpf_local_storage, rcu); + kfree_nolock(local_storage); +} + +static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_local_storage_free_rcu(rcu); + else + call_rcu(rcu, bpf_local_storage_free_rcu); +} + +static void bpf_local_storage_free(struct bpf_local_storage *local_storage, + bool reuse_now) +{ + if (!local_storage) + return; + + if (!local_storage->use_kmalloc_nolock) { + __bpf_local_storage_free(local_storage, reuse_now); + return; + } + + if (reuse_now) { + call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu); + return; + } + + call_rcu_tasks_trace(&local_storage->rcu, + bpf_local_storage_free_trace_rcu); +} + +/* rcu tasks trace callback for use_kmalloc_nolock == false */ +static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; @@ -109,13 +179,90 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) kfree_rcu(selem, rcu); } +/* Handle use_kmalloc_nolock == false */ +static void __bpf_selem_free(struct bpf_local_storage_elem *selem, + bool vanilla_rcu) +{ + if (vanilla_rcu) + kfree_rcu(selem, rcu); + else + call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu); +} + +static void bpf_selem_free_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; + + selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + /* The bpf_local_storage_map_free will wait for rcu_barrier */ + smap = rcu_dereference_check(SDATA(selem)->smap, 1); + + migrate_disable(); + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + migrate_enable(); + kfree_nolock(selem); +} + +static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_selem_free_rcu(rcu); + else + call_rcu(rcu, bpf_selem_free_rcu); +} + +void bpf_selem_free(struct bpf_local_storage_elem *selem, + bool reuse_now) +{ + struct bpf_local_storage_map *smap; + + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); + + if (!smap->use_kmalloc_nolock) { + /* + * No uptr will be unpin even when reuse_now == false since uptr + * is only supported in task local storage, where + * smap->use_kmalloc_nolock == true. + */ + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + __bpf_selem_free(selem, reuse_now); + return; + } + + if (reuse_now) { + /* + * While it is okay to call bpf_obj_free_fields() that unpins uptr when + * reuse_now == true, keep it in bpf_selem_free_rcu() for simplicity. + */ + call_rcu(&selem->rcu, bpf_selem_free_rcu); + return; + } + + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); +} + +static void bpf_selem_free_list(struct hlist_head *list, bool reuse_now) +{ + struct bpf_local_storage_elem *selem; + struct hlist_node *n; + + /* The "_safe" iteration is needed. + * The loop is not removing the selem from the list + * but bpf_selem_free will use the selem->rcu_head + * which is union-ized with the selem->free_node. + */ + hlist_for_each_entry_safe(selem, n, list, free_node) + bpf_selem_free(selem, reuse_now); +} + /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_mem, bool use_trace_rcu) + struct hlist_head *free_selem_list) { struct bpf_local_storage_map *smap; bool free_local_storage; @@ -128,8 +275,7 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor * The owner may be freed once the last selem is unlinked * from local_storage. */ - if (uncharge_mem) - mem_uncharge(smap, owner, smap->elem_size); + mem_uncharge(smap, owner, smap->elem_size); free_local_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); @@ -159,40 +305,39 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - if (use_trace_rcu) - call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); - else - kfree_rcu(selem, rcu); + hlist_add_head(&selem->free_node, free_selem_list); + + if (rcu_access_pointer(local_storage->smap) == smap) + RCU_INIT_POINTER(local_storage->smap, NULL); return free_local_storage; } -static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, - bool use_trace_rcu) +static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, + bool reuse_now) { struct bpf_local_storage *local_storage; bool free_local_storage = false; + HLIST_HEAD(selem_free_list); unsigned long flags; - if (unlikely(!selem_linked_to_storage(selem))) + if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); + raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, true, use_trace_rcu); + local_storage, selem, &selem_free_list); raw_spin_unlock_irqrestore(&local_storage->lock, flags); - if (free_local_storage) { - if (use_trace_rcu) - call_rcu_tasks_trace(&local_storage->rcu, - bpf_local_storage_free_rcu); - else - kfree_rcu(local_storage, rcu); - } + bpf_selem_free_list(&selem_free_list, reuse_now); + + if (free_local_storage) + bpf_local_storage_free(local_storage, reuse_now); } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, @@ -202,13 +347,13 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, hlist_add_head_rcu(&selem->snode, &local_storage->list); } -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) +static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; unsigned long flags; - if (unlikely(!selem_linked_to_map(selem))) + if (unlikely(!selem_linked_to_map_lockless(selem))) /* selem has already be unlinked from smap */ return; @@ -227,62 +372,35 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap, unsigned long flags; raw_spin_lock_irqsave(&b->lock, flags); - RCU_INIT_POINTER(SDATA(selem)->smap, smap); hlist_add_head_rcu(&selem->map_node, &b->list); raw_spin_unlock_irqrestore(&b->lock, flags); } -void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu) +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ bpf_selem_unlink_map(selem); - __bpf_selem_unlink_storage(selem, use_trace_rcu); + bpf_selem_unlink_storage(selem, reuse_now); } -/* If cacheit_lockit is false, this lookup function is lockless */ -struct bpf_local_storage_data * -bpf_local_storage_lookup(struct bpf_local_storage *local_storage, - struct bpf_local_storage_map *smap, - bool cacheit_lockit) +void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_local_storage_data *sdata; - struct bpf_local_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx], - bpf_rcu_lock_held()); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &local_storage->list, snode, - rcu_read_lock_trace_held()) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - unsigned long flags; - - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next bpf_local_storage_lookup(). - */ - raw_spin_lock_irqsave(&local_storage->lock, flags); - if (selem_linked_to_storage(selem)) - rcu_assign_pointer(local_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); - } + unsigned long flags; - return sdata; + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next bpf_local_storage_lookup(). + */ + raw_spin_lock_irqsave(&local_storage->lock, flags); + if (selem_linked_to_storage(selem)) + rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, @@ -312,16 +430,22 @@ int bpf_local_storage_alloc(void *owner, if (err) return err; - storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), - gfp_flags | __GFP_NOWARN); + if (smap->use_kmalloc_nolock) + storage = bpf_map_kmalloc_nolock(&smap->map, sizeof(*storage), + __GFP_ZERO, NUMA_NO_NODE); + else + storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), + gfp_flags | __GFP_NOWARN); if (!storage) { err = -ENOMEM; goto uncharge; } + RCU_INIT_POINTER(storage->smap, smap); INIT_HLIST_HEAD(&storage->list); raw_spin_lock_init(&storage->lock); storage->owner = owner; + storage->use_kmalloc_nolock = smap->use_kmalloc_nolock; bpf_selem_link_storage_nolock(storage, first_selem); bpf_selem_link_map(smap, first_selem); @@ -343,22 +467,12 @@ int bpf_local_storage_alloc(void *owner, bpf_selem_unlink_map(first_selem); err = -EAGAIN; goto uncharge; - - /* Note that even first_selem was linked to smap's - * bucket->list, first_selem can be freed immediately - * (instead of kfree_rcu) because - * bpf_local_storage_map_free() does a - * synchronize_rcu_mult (waiting for both sleepable and - * normal programs) before walking the bucket->list. - * Hence, no one is accessing selem from the - * bucket->list under rcu_read_lock(). - */ } return 0; uncharge: - kfree(storage); + bpf_local_storage_free(storage, true); mem_uncharge(smap, owner, sizeof(*storage)); return err; } @@ -370,11 +484,12 @@ uncharge: */ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags, gfp_t gfp_flags) + void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_data *old_sdata = NULL; - struct bpf_local_storage_elem *selem = NULL; + struct bpf_local_storage_elem *alloc_selem, *selem = NULL; struct bpf_local_storage *local_storage; + HLIST_HEAD(old_selem_free_list); unsigned long flags; int err; @@ -396,13 +511,13 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (err) return ERR_PTR(err); - selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags); + selem = bpf_selem_alloc(smap, owner, value, swap_uptrs, gfp_flags); if (!selem) return ERR_PTR(-ENOMEM); err = bpf_local_storage_alloc(owner, smap, selem, gfp_flags); if (err) { - kfree(selem); + bpf_selem_free(selem, true); mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } @@ -420,18 +535,19 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); - if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { + if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; } } - if (gfp_flags == GFP_KERNEL) { - selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags); - if (!selem) - return ERR_PTR(-ENOMEM); - } + /* A lookup has just been done before and concluded a new selem is + * needed. The chance of an unnecessary alloc is unlikely. + */ + alloc_selem = selem = bpf_selem_alloc(smap, owner, value, swap_uptrs, gfp_flags); + if (!alloc_selem) + return ERR_PTR(-ENOMEM); raw_spin_lock_irqsave(&local_storage->lock, flags); @@ -443,13 +559,13 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, * simple. */ err = -EAGAIN; - goto unlock_err; + goto unlock; } old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) - goto unlock_err; + goto unlock; if (old_sdata && (map_flags & BPF_F_LOCK)) { copy_map_value_locked(&smap->map, old_sdata->data, value, @@ -458,23 +574,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, goto unlock; } - if (gfp_flags != GFP_KERNEL) { - /* local_storage->lock is held. Hence, we are sure - * we can unlink and uncharge the old_sdata successfully - * later. Hence, instead of charging the new selem now - * and then uncharge the old selem later (which may cause - * a potential but unnecessary charge failure), avoid taking - * a charge at all here (the "!old_sdata" check) and the - * old_sdata will not be uncharged later during - * bpf_selem_unlink_storage_nolock(). - */ - selem = bpf_selem_alloc(smap, owner, value, !old_sdata, gfp_flags); - if (!selem) { - err = -ENOMEM; - goto unlock_err; - } - } - + alloc_selem = NULL; /* First, link the new selem to the map */ bpf_selem_link_map(smap, selem); @@ -485,20 +585,17 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (old_sdata) { bpf_selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), - false, true); + &old_selem_free_list); } unlock: raw_spin_unlock_irqrestore(&local_storage->lock, flags); - return SDATA(selem); - -unlock_err: - raw_spin_unlock_irqrestore(&local_storage->lock, flags); - if (selem) { + bpf_selem_free_list(&old_selem_free_list, false); + if (alloc_selem) { mem_uncharge(smap, owner, smap->elem_size); - kfree(selem); + bpf_selem_free(alloc_selem, true); } - return ERR_PTR(err); + return err ? ERR_PTR(err) : SDATA(selem); } static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) @@ -543,71 +640,30 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr) !attr->btf_key_type_id || !attr->btf_value_type_id) return -EINVAL; - if (!bpf_capable()) - return -EPERM; - if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) return -E2BIG; return 0; } -static struct bpf_local_storage_map *__bpf_local_storage_map_alloc(union bpf_attr *attr) -{ - struct bpf_local_storage_map *smap; - unsigned int i; - u32 nbuckets; - - smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); - if (!smap) - return ERR_PTR(-ENOMEM); - bpf_map_init_from_attr(&smap->map, attr); - - nbuckets = roundup_pow_of_two(num_possible_cpus()); - /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - nbuckets = max_t(u32, 2, nbuckets); - smap->bucket_log = ilog2(nbuckets); - - smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); - if (!smap->buckets) { - bpf_map_area_free(smap); - return ERR_PTR(-ENOMEM); - } - - for (i = 0; i < nbuckets; i++) { - INIT_HLIST_HEAD(&smap->buckets[i].list); - raw_spin_lock_init(&smap->buckets[i].lock); - } - - smap->elem_size = - sizeof(struct bpf_local_storage_elem) + attr->value_size; - - return smap; -} - int bpf_local_storage_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { - u32 int_data; - - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) - return -EINVAL; - - int_data = *(u32 *)(key_type + 1); - if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) + if (!btf_type_is_i32(key_type)) return -EINVAL; return 0; } -bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) +void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) { struct bpf_local_storage_elem *selem; bool free_storage = false; + HLIST_HEAD(free_selem_list); struct hlist_node *n; + unsigned long flags; /* Neither the bpf_prog nor the bpf_map's syscall * could be modifying the local_storage->list now. @@ -618,6 +674,7 @@ bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) * when unlinking elem from the local_storage->list and * the map's bucket->list. */ + raw_spin_lock_irqsave(&local_storage->lock, flags); hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { /* Always unlink from map before unlinking from * local_storage. @@ -630,24 +687,74 @@ bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) * of the loop will set the free_cgroup_storage to true. */ free_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false, false); + local_storage, selem, &free_selem_list); } + raw_spin_unlock_irqrestore(&local_storage->lock, flags); + + bpf_selem_free_list(&free_selem_list, true); + + if (free_storage) + bpf_local_storage_free(local_storage, true); +} + +u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map; + u64 usage = sizeof(*smap); - return free_storage; + /* The dynamically callocated selems are not counted currently. */ + usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); + return usage; } struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, - struct bpf_local_storage_cache *cache) + struct bpf_local_storage_cache *cache, + bool use_kmalloc_nolock) { struct bpf_local_storage_map *smap; + unsigned int i; + u32 nbuckets; + int err; - smap = __bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); + smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); + if (!smap) + return ERR_PTR(-ENOMEM); + bpf_map_init_from_attr(&smap->map, attr); + + nbuckets = roundup_pow_of_two(num_possible_cpus()); + /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ + nbuckets = max_t(u32, 2, nbuckets); + smap->bucket_log = ilog2(nbuckets); + + smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets, + sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN); + if (!smap->buckets) { + err = -ENOMEM; + goto free_smap; + } + + for (i = 0; i < nbuckets; i++) { + INIT_HLIST_HEAD(&smap->buckets[i].list); + raw_spin_lock_init(&smap->buckets[i].lock); + } + + smap->elem_size = offsetof(struct bpf_local_storage_elem, + sdata.data[attr->value_size]); + + /* In PREEMPT_RT, kmalloc(GFP_ATOMIC) is still not safe in non + * preemptible context. Thus, enforce all storages to use + * kmalloc_nolock() when CONFIG_PREEMPT_RT is enabled. + */ + smap->use_kmalloc_nolock = IS_ENABLED(CONFIG_PREEMPT_RT) ? true : use_kmalloc_nolock; smap->cache_idx = bpf_local_storage_cache_idx_get(cache); return &smap->map; + +free_smap: + kvfree(smap->buckets); + bpf_map_area_free(smap); + return ERR_PTR(err); } void bpf_local_storage_map_free(struct bpf_map *map, @@ -685,15 +792,11 @@ void bpf_local_storage_map_free(struct bpf_map *map, while ((selem = hlist_entry_safe( rcu_dereference_raw(hlist_first_rcu(&b->list)), struct bpf_local_storage_elem, map_node))) { - if (busy_counter) { - migrate_disable(); + if (busy_counter) this_cpu_inc(*busy_counter); - } - bpf_selem_unlink(selem, false); - if (busy_counter) { + bpf_selem_unlink(selem, true); + if (busy_counter) this_cpu_dec(*busy_counter); - migrate_enable(); - } cond_resched_rcu(); } rcu_read_unlock(); @@ -713,6 +816,10 @@ void bpf_local_storage_map_free(struct bpf_map *map, */ synchronize_rcu(); + if (smap->use_kmalloc_nolock) { + rcu_barrier_tasks_trace(); + rcu_barrier(); + } kvfree(smap->buckets); bpf_map_area_free(smap); } diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index d99e89f113c4..e7a2fc60523f 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -19,14 +19,6 @@ #define LOCAL_PENDING_LIST_IDX LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_PENDING) #define IS_LOCAL_LIST_TYPE(t) ((t) >= BPF_LOCAL_LIST_T_OFFSET) -static int get_next_cpu(int cpu) -{ - cpu = cpumask_next(cpu, cpu_possible_mask); - if (cpu >= nr_cpu_ids) - cpu = cpumask_first(cpu_possible_mask); - return cpu; -} - /* Local list helpers */ static struct list_head *local_free_list(struct bpf_lru_locallist *loc_l) { @@ -41,7 +33,12 @@ static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { - return node->ref; + return READ_ONCE(node->ref); +} + +static void bpf_lru_node_clear_ref(struct bpf_lru_node *node) +{ + WRITE_ONCE(node->ref, 0); } static void bpf_lru_list_count_inc(struct bpf_lru_list *l, @@ -89,7 +86,7 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, &l->lists[tgt_type]); } @@ -110,7 +107,7 @@ static void __bpf_lru_node_move(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } - node->ref = 0; + bpf_lru_node_clear_ref(node); /* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. @@ -332,12 +329,12 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, list) { __bpf_lru_node_move_to_free(l, node, local_free_list(loc_l), BPF_LRU_LOCAL_LIST_T_FREE); - if (++nfree == LOCAL_FREE_TARGET) + if (++nfree == lru->target_free) break; } - if (nfree < LOCAL_FREE_TARGET) - __bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree, + if (nfree < lru->target_free) + __bpf_lru_list_shrink(lru, l, lru->target_free - nfree, local_free_list(loc_l), BPF_LRU_LOCAL_LIST_T_FREE); @@ -353,7 +350,7 @@ static void __local_list_add_pending(struct bpf_lru *lru, *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, local_pending_list(loc_l)); } @@ -419,7 +416,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; - node->ref = 0; + bpf_lru_node_clear_ref(node); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); } @@ -477,7 +474,7 @@ static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru, raw_spin_unlock_irqrestore(&steal_loc_l->lock, flags); - steal = get_next_cpu(steal); + steal = cpumask_next_wrap(steal, cpu_possible_mask); } while (!node && steal != first_steal); loc_l->next_steal = steal; @@ -522,7 +519,7 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru, } node->type = BPF_LRU_LOCAL_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, local_free_list(loc_l)); raw_spin_unlock_irqrestore(&loc_l->lock, flags); @@ -568,10 +565,13 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } + + lru->target_free = clamp((nr_elems / num_possible_cpus()) / 2, + 1, LOCAL_FREE_TARGET); } static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf, @@ -594,7 +594,7 @@ again: node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 4ea227c9c1ad..fe2661a58ea9 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -58,17 +58,15 @@ struct bpf_lru { del_from_htab_func del_from_htab; void *del_arg; unsigned int hash_offset; + unsigned int target_free; unsigned int nr_scans; bool percpu; }; static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { - /* ref is an approximation on access frequency. It does not - * have to be very accurate. Hence, no protection is used. - */ - if (!node->ref) - node->ref = 1; + if (!READ_ONCE(node->ref)) + WRITE_ONCE(node->ref, 1); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, @@ -78,6 +76,5 @@ void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, void bpf_lru_destroy(struct bpf_lru *lru); struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash); void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node); -void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node); #endif diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index a4a41ee3e80b..7cb6e8d4282c 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -11,7 +11,6 @@ #include <linux/lsm_hooks.h> #include <linux/bpf_lsm.h> #include <linux/kallsyms.h> -#include <linux/bpf_verifier.h> #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> #include <linux/btf_ids.h> @@ -36,6 +35,25 @@ BTF_SET_START(bpf_lsm_hooks) #undef LSM_HOOK BTF_SET_END(bpf_lsm_hooks) +BTF_SET_START(bpf_lsm_disabled_hooks) +BTF_ID(func, bpf_lsm_vm_enough_memory) +BTF_ID(func, bpf_lsm_inode_need_killpriv) +BTF_ID(func, bpf_lsm_inode_getsecurity) +BTF_ID(func, bpf_lsm_inode_listsecurity) +BTF_ID(func, bpf_lsm_inode_copy_up_xattr) +BTF_ID(func, bpf_lsm_getselfattr) +BTF_ID(func, bpf_lsm_getprocattr) +BTF_ID(func, bpf_lsm_setprocattr) +#ifdef CONFIG_KEYS +BTF_ID(func, bpf_lsm_key_getsecurity) +#endif +#ifdef CONFIG_AUDIT +BTF_ID(func, bpf_lsm_audit_rule_match) +#endif +BTF_ID(func, bpf_lsm_ismaclabel) +BTF_ID(func, bpf_lsm_file_alloc_security) +BTF_SET_END(bpf_lsm_disabled_hooks) + /* List of LSM hooks that should operate on 'current' cgroup regardless * of function signature. */ @@ -51,7 +69,6 @@ BTF_SET_END(bpf_lsm_current_hooks) */ BTF_SET_START(bpf_lsm_locked_sockopt_hooks) #ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_socket_sock_rcv_skb) BTF_ID(func, bpf_lsm_sock_graft) BTF_ID(func, bpf_lsm_inet_csk_clone) BTF_ID(func, bpf_lsm_inet_conn_established) @@ -98,15 +115,24 @@ void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) { + u32 btf_id = prog->aux->attach_btf_id; + const char *func_name = prog->aux->attach_func_name; + if (!prog->gpl_compatible) { bpf_log(vlog, "LSM programs must have a GPL compatible license\n"); return -EINVAL; } - if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { + if (btf_id_set_contains(&bpf_lsm_disabled_hooks, btf_id)) { + bpf_log(vlog, "attach_btf_id %u points to disabled hook %s\n", + btf_id, func_name); + return -EINVAL; + } + + if (!btf_id_set_contains(&bpf_lsm_hooks, btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", - prog->aux->attach_btf_id, prog->aux->attach_func_name); + btf_id, func_name); return -EINVAL; } @@ -261,9 +287,15 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) -BTF_ID(func, bpf_lsm_bpf_map_alloc_security) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_create) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) +BTF_ID(func, bpf_lsm_bpf_prog_load) +BTF_ID(func, bpf_lsm_bpf_prog_free) +BTF_ID(func, bpf_lsm_bpf_token_create) +BTF_ID(func, bpf_lsm_bpf_token_free) +BTF_ID(func, bpf_lsm_bpf_token_cmd) +BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) @@ -275,12 +307,9 @@ BTF_ID(func, bpf_lsm_cred_prepare) BTF_ID(func, bpf_lsm_file_ioctl) BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) +BTF_ID(func, bpf_lsm_file_post_open) BTF_ID(func, bpf_lsm_file_receive) -#ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_inet_conn_established) -#endif /* CONFIG_SECURITY_NETWORK */ - BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) @@ -288,7 +317,9 @@ BTF_ID(func, bpf_lsm_inode_getxattr) BTF_ID(func, bpf_lsm_inode_mknod) BTF_ID(func, bpf_lsm_inode_need_killpriv) BTF_ID(func, bpf_lsm_inode_post_setxattr) +BTF_ID(func, bpf_lsm_inode_post_removexattr) BTF_ID(func, bpf_lsm_inode_readlink) +BTF_ID(func, bpf_lsm_inode_removexattr) BTF_ID(func, bpf_lsm_inode_rename) BTF_ID(func, bpf_lsm_inode_rmdir) BTF_ID(func, bpf_lsm_inode_setattr) @@ -299,9 +330,17 @@ BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernel_read_file) BTF_ID(func, bpf_lsm_kernfs_init_security) -#ifdef CONFIG_KEYS -BTF_ID(func, bpf_lsm_key_free) -#endif /* CONFIG_KEYS */ +#ifdef CONFIG_SECURITY_PATH +BTF_ID(func, bpf_lsm_path_unlink) +BTF_ID(func, bpf_lsm_path_mkdir) +BTF_ID(func, bpf_lsm_path_rmdir) +BTF_ID(func, bpf_lsm_path_truncate) +BTF_ID(func, bpf_lsm_path_symlink) +BTF_ID(func, bpf_lsm_path_link) +BTF_ID(func, bpf_lsm_path_rename) +BTF_ID(func, bpf_lsm_path_chmod) +BTF_ID(func, bpf_lsm_path_chown) +#endif /* CONFIG_SECURITY_PATH */ BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) @@ -319,6 +358,8 @@ BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) #ifdef CONFIG_SECURITY_NETWORK +BTF_ID(func, bpf_lsm_inet_conn_established) + BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) @@ -337,8 +378,6 @@ BTF_ID(func, bpf_lsm_socket_socketpair) BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) -BTF_ID(func, bpf_lsm_current_getsecid_subj) -BTF_ID(func, bpf_lsm_task_getsecid_obj) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) BTF_ID(func, bpf_lsm_task_to_inode) @@ -346,9 +385,8 @@ BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) -BTF_ID(func, bpf_lsm_bpf_map_free_security) -BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) -BTF_ID(func, bpf_lsm_bpf_prog_free_security) +BTF_ID(func, bpf_lsm_bpf_map_free) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK @@ -375,3 +413,36 @@ const struct bpf_verifier_ops lsm_verifier_ops = { .get_func_proto = bpf_lsm_func_proto, .is_valid_access = btf_ctx_access, }; + +/* hooks return 0 or 1 */ +BTF_SET_START(bool_lsm_hooks) +#ifdef CONFIG_SECURITY_NETWORK_XFRM +BTF_ID(func, bpf_lsm_xfrm_state_pol_flow_match) +#endif +#ifdef CONFIG_AUDIT +BTF_ID(func, bpf_lsm_audit_rule_known) +#endif +BTF_ID(func, bpf_lsm_inode_xattr_skipcap) +BTF_SET_END(bool_lsm_hooks) + +int bpf_lsm_get_retval_range(const struct bpf_prog *prog, + struct bpf_retval_range *retval_range) +{ + /* no return value range for void hooks */ + if (!prog->aux->attach_func_proto->type) + return -EINVAL; + + if (btf_id_set_contains(&bool_lsm_hooks, prog->aux->attach_btf_id)) { + retval_range->minval = 0; + retval_range->maxval = 1; + } else { + /* All other available LSM hooks, except task_prctl, return 0 + * on success and negative error code on failure. + * To keep things simple, we only allow bpf progs to return 0 + * or negative errno for task_prctl too. + */ + retval_range->minval = -MAX_ERRNO; + retval_range->maxval = 0; + } + return 0; +} diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index ece9870cab68..278490683d28 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -11,26 +11,19 @@ #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/btf_ids.h> - -enum bpf_struct_ops_state { - BPF_STRUCT_OPS_STATE_INIT, - BPF_STRUCT_OPS_STATE_INUSE, - BPF_STRUCT_OPS_STATE_TOBEFREE, -}; - -#define BPF_STRUCT_OPS_COMMON_VALUE \ - refcount_t refcnt; \ - enum bpf_struct_ops_state state +#include <linux/rcupdate_wait.h> +#include <linux/poll.h> struct bpf_struct_ops_value { - BPF_STRUCT_OPS_COMMON_VALUE; + struct bpf_struct_ops_common_value common; char data[] ____cacheline_aligned_in_smp; }; +#define MAX_TRAMP_IMAGE_PAGES 8 + struct bpf_struct_ops_map { struct bpf_map map; - struct rcu_head rcu; - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; /* protect map_update */ struct mutex lock; /* link has all the bpf_links that is populated @@ -38,12 +31,16 @@ struct bpf_struct_ops_map { * (in kvalue.data). */ struct bpf_link **links; - /* image is a page that has all the trampolines + /* ksyms for bpf trampolines */ + struct bpf_ksym **ksyms; + u32 funcs_cnt; + u32 image_pages_cnt; + /* image_pages is an array of pages that has all the trampolines * that stores the func args before calling the bpf_prog. - * A PAGE_SIZE "image" is enough to store all trampoline for - * "links[]". */ - void *image; + void *image_pages[MAX_TRAMP_IMAGE_PAGES]; + /* The owner moduler's btf. */ + struct btf *btf; /* uvalue->data stores the kernel struct * (e.g. tcp_congestion_ops) that is more useful * to userspace than the kvalue. For example, @@ -58,37 +55,16 @@ struct bpf_struct_ops_map { struct bpf_struct_ops_value kvalue; }; -#define VALUE_PREFIX "bpf_struct_ops_" -#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) - -/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is - * the map's value exposed to the userspace and its btf-type-id is - * stored at the map->btf_vmlinux_value_type_id. - * - */ -#define BPF_STRUCT_OPS_TYPE(_name) \ -extern struct bpf_struct_ops bpf_##_name; \ - \ -struct bpf_struct_ops_##_name { \ - BPF_STRUCT_OPS_COMMON_VALUE; \ - struct _name data ____cacheline_aligned_in_smp; \ +struct bpf_struct_ops_link { + struct bpf_link link; + struct bpf_map __rcu *map; + wait_queue_head_t wait_hup; }; -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -enum { -#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - __NR_BPF_STRUCT_OPS_TYPE, -}; +static DEFINE_MUTEX(update_mutex); -static struct bpf_struct_ops * const bpf_struct_ops[] = { -#define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -}; +#define VALUE_PREFIX "bpf_struct_ops_" +#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; @@ -99,138 +75,398 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { #endif }; -static const struct btf_type *module_type; +BTF_ID_LIST(st_ops_ids) +BTF_ID(struct, module) +BTF_ID(struct, bpf_struct_ops_common_value) -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +enum { + IDX_MODULE_ID, + IDX_ST_OPS_COMMON_VALUE_ID, +}; + +extern struct btf *btf_vmlinux; + +static bool is_valid_value_type(struct btf *btf, s32 value_id, + const struct btf_type *type, + const char *value_name) { - s32 type_id, value_id, module_id; + const struct btf_type *common_value_type; const struct btf_member *member; - struct bpf_struct_ops *st_ops; - const struct btf_type *t; - char value_name[128]; - const char *mname; - u32 i, j; + const struct btf_type *vt, *mt; - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE + vt = btf_type_by_id(btf, value_id); + if (btf_vlen(vt) != 2) { + pr_warn("The number of %s's members should be 2, but we get %d\n", + value_name, btf_vlen(vt)); + return false; + } + member = btf_type_member(vt); + mt = btf_type_by_id(btf, member->type); + common_value_type = btf_type_by_id(btf_vmlinux, + st_ops_ids[IDX_ST_OPS_COMMON_VALUE_ID]); + if (mt != common_value_type) { + pr_warn("The first member of %s should be bpf_struct_ops_common_value\n", + value_name); + return false; + } + member++; + mt = btf_type_by_id(btf, member->type); + if (mt != type) { + pr_warn("The second member of %s should be %s\n", + value_name, btf_name_by_offset(btf, type->name_off)); + return false; + } - module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); - if (module_id < 0) { - pr_warn("Cannot find struct module in btf_vmlinux\n"); - return; + return true; +} + +static void *bpf_struct_ops_image_alloc(void) +{ + void *image; + int err; + + err = bpf_jit_charge_modmem(PAGE_SIZE); + if (err) + return ERR_PTR(err); + image = arch_alloc_bpf_trampoline(PAGE_SIZE); + if (!image) { + bpf_jit_uncharge_modmem(PAGE_SIZE); + return ERR_PTR(-ENOMEM); } - module_type = btf_type_by_id(btf, module_id); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; + return image; +} - if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= - sizeof(value_name)) { - pr_warn("struct_ops name %s is too long\n", - st_ops->name); +void bpf_struct_ops_image_free(void *image) +{ + if (image) { + arch_free_bpf_trampoline(image, PAGE_SIZE); + bpf_jit_uncharge_modmem(PAGE_SIZE); + } +} + +#define MAYBE_NULL_SUFFIX "__nullable" +#define REFCOUNTED_SUFFIX "__ref" + +/* Prepare argument info for every nullable argument of a member of a + * struct_ops type. + * + * Initialize a struct bpf_struct_ops_arg_info according to type info of + * the arguments of a stub function. (Check kCFI for more information about + * stub functions.) + * + * Each member in the struct_ops type has a struct bpf_struct_ops_arg_info + * to provide an array of struct bpf_ctx_arg_aux, which in turn provides + * the information that used by the verifier to check the arguments of the + * BPF struct_ops program assigned to the member. Here, we only care about + * the arguments that are marked as __nullable. + * + * The array of struct bpf_ctx_arg_aux is eventually assigned to + * prog->aux->ctx_arg_info of BPF struct_ops programs and passed to the + * verifier. (See check_struct_ops_btf_id()) + * + * arg_info->info will be the list of struct bpf_ctx_arg_aux if success. If + * fails, it will be kept untouched. + */ +static int prepare_arg_info(struct btf *btf, + const char *st_ops_name, + const char *member_name, + const struct btf_type *func_proto, void *stub_func_addr, + struct bpf_struct_ops_arg_info *arg_info) +{ + const struct btf_type *stub_func_proto, *pointed_type; + bool is_nullable = false, is_refcounted = false; + const struct btf_param *stub_args, *args; + struct bpf_ctx_arg_aux *info, *info_buf; + u32 nargs, arg_no, info_cnt = 0; + char ksym[KSYM_SYMBOL_LEN]; + const char *stub_fname; + const char *suffix; + s32 stub_func_id; + u32 arg_btf_id; + int offset; + + stub_fname = kallsyms_lookup((unsigned long)stub_func_addr, NULL, NULL, NULL, ksym); + if (!stub_fname) { + pr_warn("Cannot find the stub function name for the %s in struct %s\n", + member_name, st_ops_name); + return -ENOENT; + } + + stub_func_id = btf_find_by_name_kind(btf, stub_fname, BTF_KIND_FUNC); + if (stub_func_id < 0) { + pr_warn("Cannot find the stub function %s in btf\n", stub_fname); + return -ENOENT; + } + + stub_func_proto = btf_type_by_id(btf, stub_func_id); + stub_func_proto = btf_type_by_id(btf, stub_func_proto->type); + + /* Check if the number of arguments of the stub function is the same + * as the number of arguments of the function pointer. + */ + nargs = btf_type_vlen(func_proto); + if (nargs != btf_type_vlen(stub_func_proto)) { + pr_warn("the number of arguments of the stub function %s does not match the number of arguments of the member %s of struct %s\n", + stub_fname, member_name, st_ops_name); + return -EINVAL; + } + + if (!nargs) + return 0; + + args = btf_params(func_proto); + stub_args = btf_params(stub_func_proto); + + info_buf = kcalloc(nargs, sizeof(*info_buf), GFP_KERNEL); + if (!info_buf) + return -ENOMEM; + + /* Prepare info for every nullable argument */ + info = info_buf; + for (arg_no = 0; arg_no < nargs; arg_no++) { + /* Skip arguments that is not suffixed with + * "__nullable or __ref". + */ + is_nullable = btf_param_match_suffix(btf, &stub_args[arg_no], + MAYBE_NULL_SUFFIX); + is_refcounted = btf_param_match_suffix(btf, &stub_args[arg_no], + REFCOUNTED_SUFFIX); + + if (is_nullable) + suffix = MAYBE_NULL_SUFFIX; + else if (is_refcounted) + suffix = REFCOUNTED_SUFFIX; + else continue; + + /* Should be a pointer to struct */ + pointed_type = btf_type_resolve_ptr(btf, + args[arg_no].type, + &arg_btf_id); + if (!pointed_type || + !btf_type_is_struct(pointed_type)) { + pr_warn("stub function %s has %s tagging to an unsupported type\n", + stub_fname, suffix); + goto err_out; } - sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - value_name); - continue; + offset = btf_ctx_arg_offset(btf, func_proto, arg_no); + if (offset < 0) { + pr_warn("stub function %s has an invalid trampoline ctx offset for arg#%u\n", + stub_fname, arg_no); + goto err_out; } - type_id = btf_find_by_name_kind(btf, st_ops->name, - BTF_KIND_STRUCT); - if (type_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - st_ops->name); - continue; + if (args[arg_no].type != stub_args[arg_no].type) { + pr_warn("arg#%u type in stub function %s does not match with its original func_proto\n", + arg_no, stub_fname); + goto err_out; } - t = btf_type_by_id(btf, type_id); - if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { - pr_warn("Cannot support #%u members in struct %s\n", - btf_type_vlen(t), st_ops->name); - continue; + + /* Fill the information of the new argument */ + info->btf_id = arg_btf_id; + info->btf = btf; + info->offset = offset; + if (is_nullable) { + info->reg_type = PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; + } else if (is_refcounted) { + info->reg_type = PTR_TRUSTED | PTR_TO_BTF_ID; + info->refcounted = true; } - for_each_member(j, t, member) { - const struct btf_type *func_proto; + info++; + info_cnt++; + } - mname = btf_name_by_offset(btf, member->name_off); - if (!*mname) { - pr_warn("anon member in struct %s is not supported\n", - st_ops->name); - break; - } + if (info_cnt) { + arg_info->info = info_buf; + arg_info->cnt = info_cnt; + } else { + kfree(info_buf); + } - if (__btf_member_bitfield_size(t, member)) { - pr_warn("bit field member %s in struct %s is not supported\n", - mname, st_ops->name); - break; - } + return 0; - func_proto = btf_type_resolve_func_ptr(btf, - member->type, - NULL); - if (func_proto && - btf_distill_func_proto(log, btf, - func_proto, mname, - &st_ops->func_models[j])) { - pr_warn("Error in parsing func ptr %s in struct %s\n", - mname, st_ops->name); - break; - } - } +err_out: + kfree(info_buf); - if (j == btf_type_vlen(t)) { - if (st_ops->init(btf)) { - pr_warn("Error in init bpf_struct_ops %s\n", - st_ops->name); - } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); - } - } - } + return -EINVAL; } -extern struct btf *btf_vmlinux; +/* Clean up the arg_info in a struct bpf_struct_ops_desc. */ +void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) +{ + struct bpf_struct_ops_arg_info *arg_info; + int i; -static const struct bpf_struct_ops * -bpf_struct_ops_find_value(u32 value_id) + arg_info = st_ops_desc->arg_info; + for (i = 0; i < btf_type_vlen(st_ops_desc->type); i++) + kfree(arg_info[i].info); + + kfree(arg_info); +} + +static bool is_module_member(const struct btf *btf, u32 id) { - unsigned int i; + const struct btf_type *t; - if (!value_id || !btf_vmlinux) - return NULL; + t = btf_type_resolve_ptr(btf, id, NULL); + if (!t) + return false; - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->value_id == value_id) - return bpf_struct_ops[i]; - } + if (!__btf_type_is_struct(t) && !btf_type_is_fwd(t)) + return false; - return NULL; + return !strcmp(btf_name_by_offset(btf, t->name_off), "module"); } -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) { - unsigned int i; + void *func_ptr = *(void **)(st_ops->cfi_stubs + moff); + + return func_ptr ? 0 : -ENOTSUPP; +} + +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) +{ + struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; + struct bpf_struct_ops_arg_info *arg_info; + const struct btf_member *member; + const struct btf_type *t; + s32 type_id, value_id; + char value_name[128]; + const char *mname; + int i, err; - if (!type_id || !btf_vmlinux) - return NULL; + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + return -EINVAL; + } + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->type_id == type_id) - return bpf_struct_ops[i]; + if (!st_ops->cfi_stubs) { + pr_warn("struct_ops for %s has no cfi_stubs\n", st_ops->name); + return -EINVAL; } - return NULL; + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + st_ops->name, btf_get_name(btf)); + return -EINVAL; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + return -EINVAL; + } + + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); + return -EINVAL; + } + if (!is_valid_value_type(btf, value_id, t, value_name)) + return -EINVAL; + + arg_info = kcalloc(btf_type_vlen(t), sizeof(*arg_info), + GFP_KERNEL); + if (!arg_info) + return -ENOMEM; + + st_ops_desc->arg_info = arg_info; + st_ops_desc->type = t; + st_ops_desc->type_id = type_id; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, value_id); + + for_each_member(i, t, member) { + const struct btf_type *func_proto, *ret_type; + void **stub_func_addr; + u32 moff; + + moff = __btf_member_bit_offset(t, member) / 8; + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", + st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + if (__btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + if (!st_ops_ids[IDX_MODULE_ID] && is_module_member(btf, member->type)) { + pr_warn("'struct module' btf id not found. Is CONFIG_MODULES enabled? bpf_struct_ops '%s' needs module support.\n", + st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + + /* The member is not a function pointer or + * the function pointer is not supported. + */ + if (!func_proto || bpf_struct_ops_supported(st_ops, moff)) + continue; + + if (func_proto->type) { + ret_type = btf_type_resolve_ptr(btf, func_proto->type, NULL); + if (ret_type && !__btf_type_is_struct(ret_type)) { + pr_warn("func ptr %s in struct %s returns non-struct pointer, which is not supported\n", + mname, st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + } + + if (btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[i])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + err = -EINVAL; + goto errout; + } + + stub_func_addr = *(void **)(st_ops->cfi_stubs + moff); + err = prepare_arg_info(btf, st_ops->name, mname, + func_proto, stub_func_addr, + arg_info + i); + if (err) + goto errout; + } + + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + err = -EINVAL; + goto errout; + } + + return 0; + +errout: + bpf_struct_ops_desc_release(st_ops_desc); + + return err; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, @@ -249,13 +485,14 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; struct bpf_struct_ops_value *uvalue, *kvalue; enum bpf_struct_ops_state state; + s64 refcnt; if (unlikely(*(u32 *)key != 0)) return -ENOENT; kvalue = &st_map->kvalue; /* Pair with smp_store_release() during map_update */ - state = smp_load_acquire(&kvalue->state); + state = smp_load_acquire(&kvalue->common.state); if (state == BPF_STRUCT_OPS_STATE_INIT) { memset(value, 0, map->value_size); return 0; @@ -266,8 +503,15 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, */ uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); - uvalue->state = state; - refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt)); + uvalue->common.state = state; + + /* This value offers the user space a general estimate of how + * many sockets are still utilizing this struct_ops for TCP + * congestion control. The number might not be exact, but it + * should sufficiently meet our present goals. + */ + refcnt = atomic64_read(&map->refcnt) - atomic64_read(&map->usercnt); + refcount_set(&uvalue->common.refcnt, max_t(s64, refcnt, 0)); return 0; } @@ -279,18 +523,26 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops->type; u32 i; - for (i = 0; i < btf_type_vlen(t); i++) { - if (st_map->links[i]) { - bpf_link_put(st_map->links[i]); - st_map->links[i] = NULL; - } + for (i = 0; i < st_map->funcs_cnt; i++) { + if (!st_map->links[i]) + break; + bpf_link_put(st_map->links[i]); + st_map->links[i] = NULL; } } -static int check_zero_holes(const struct btf_type *t, void *data) +static void bpf_struct_ops_map_free_image(struct bpf_struct_ops_map *st_map) +{ + int i; + + for (i = 0; i < st_map->image_pages_cnt; i++) + bpf_struct_ops_image_free(st_map->image_pages[i]); + st_map->image_pages_cnt = 0; +} + +static int check_zero_holes(const struct btf *btf, const struct btf_type *t, void *data) { const struct btf_member *member; u32 i, moff, msize, prev_mend = 0; @@ -302,8 +554,8 @@ static int check_zero_holes(const struct btf_type *t, void *data) memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(btf, member->type); + mtype = btf_resolve_size(btf, mtype, &msize); if (IS_ERR(mtype)) return PTR_ERR(mtype); prev_mend = moff + msize; @@ -335,33 +587,110 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = { int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, - void *image, void *image_end) + void *stub_func, + void **_image, u32 *_image_off, + bool allow_alloc) { - u32 flags; + u32 image_off = *_image_off, flags = BPF_TRAMP_F_INDIRECT; + void *image = *_image; + int size; tlinks[BPF_TRAMP_FENTRY].links[0] = link; tlinks[BPF_TRAMP_FENTRY].nr_links = 1; - /* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, - * and it must be used alone. - */ - flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; - return arch_prepare_bpf_trampoline(NULL, image, image_end, - model, flags, tlinks, NULL); + + if (model->ret_size > 0) + flags |= BPF_TRAMP_F_RET_FENTRY_RET; + + size = arch_bpf_trampoline_size(model, flags, tlinks, stub_func); + if (size <= 0) + return size ? : -EFAULT; + + /* Allocate image buffer if necessary */ + if (!image || size > PAGE_SIZE - image_off) { + if (!allow_alloc) + return -E2BIG; + + image = bpf_struct_ops_image_alloc(); + if (IS_ERR(image)) + return PTR_ERR(image); + image_off = 0; + } + + size = arch_prepare_bpf_trampoline(NULL, image + image_off, + image + image_off + size, + model, flags, tlinks, stub_func); + if (size <= 0) { + if (image != *_image) + bpf_struct_ops_image_free(image); + return size ? : -EFAULT; + } + + *_image = image; + *_image_off = image_off + size; + return 0; +} + +static void bpf_struct_ops_ksym_init(const char *tname, const char *mname, + void *image, unsigned int size, + struct bpf_ksym *ksym) +{ + snprintf(ksym->name, KSYM_NAME_LEN, "bpf__%s_%s", tname, mname); + INIT_LIST_HEAD_RCU(&ksym->lnode); + bpf_image_ksym_init(image, size, ksym); +} + +static void bpf_struct_ops_map_add_ksyms(struct bpf_struct_ops_map *st_map) +{ + u32 i; + + for (i = 0; i < st_map->funcs_cnt; i++) { + if (!st_map->ksyms[i]) + break; + bpf_image_ksym_add(st_map->ksyms[i]); + } } -static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static void bpf_struct_ops_map_del_ksyms(struct bpf_struct_ops_map *st_map) +{ + u32 i; + + for (i = 0; i < st_map->funcs_cnt; i++) { + if (!st_map->ksyms[i]) + break; + bpf_image_ksym_del(st_map->ksyms[i]); + } +} + +static void bpf_struct_ops_map_free_ksyms(struct bpf_struct_ops_map *st_map) +{ + u32 i; + + for (i = 0; i < st_map->funcs_cnt; i++) { + if (!st_map->ksyms[i]) + break; + kfree(st_map->ksyms[i]); + st_map->ksyms[i] = NULL; + } +} + +static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; struct bpf_struct_ops_value *uvalue, *kvalue; + const struct btf_type *module_type; const struct btf_member *member; - const struct btf_type *t = st_ops->type; - struct bpf_tramp_links *tlinks = NULL; + const struct btf_type *t = st_ops_desc->type; + struct bpf_tramp_links *tlinks; void *udata, *kdata; - int prog_fd, err = 0; - void *image, *image_end; - u32 i; + int prog_fd, err; + u32 i, trampoline_start, image_off = 0; + void *cur_image = NULL, *image = NULL; + struct bpf_link **plink; + struct bpf_ksym **pksym; + const char *tname, *mname; if (flags) return -EINVAL; @@ -369,16 +698,16 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (*(u32 *)key != 0) return -E2BIG; - err = check_zero_holes(st_ops->value_type, value); + err = check_zero_holes(st_map->btf, st_ops_desc->value_type, value); if (err) return err; uvalue = value; - err = check_zero_holes(t, uvalue->data); + err = check_zero_holes(st_map->btf, t, uvalue->data); if (err) return err; - if (uvalue->state || refcount_read(&uvalue->refcnt)) + if (uvalue->common.state || refcount_read(&uvalue->common.refcnt)) return -EINVAL; tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); @@ -390,7 +719,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, mutex_lock(&st_map->lock); - if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + if (kvalue->common.state != BPF_STRUCT_OPS_STATE_INIT) { err = -EBUSY; goto unlock; } @@ -399,17 +728,21 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; - image = st_map->image; - image_end = st_map->image + PAGE_SIZE; + plink = st_map->links; + pksym = st_map->ksyms; + tname = btf_name_by_offset(st_map->btf, t->name_off); + module_type = btf_type_by_id(btf_vmlinux, st_ops_ids[IDX_MODULE_ID]); for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; struct bpf_tramp_link *link; + struct bpf_ksym *ksym; u32 moff; moff = __btf_member_bit_offset(t, member) / 8; - ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); + mname = btf_name_by_offset(st_map->btf, member->name_off); + ptype = btf_type_resolve_ptr(st_map->btf, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) goto reset_unlock; @@ -434,8 +767,8 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (!ptype || !btf_type_is_func_proto(ptype)) { u32 msize; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(st_map->btf, member->type); + mtype = btf_resolve_size(st_map->btf, mtype, &msize); if (IS_ERR(mtype)) { err = PTR_ERR(mtype); goto reset_unlock; @@ -461,7 +794,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, } if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->aux->attach_btf_id != st_ops->type_id || + prog->aux->attach_btf_id != st_ops_desc->type_id || prog->expected_attach_type != i) { bpf_prog_put(prog); err = -EINVAL; @@ -475,33 +808,79 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto reset_unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, - &bpf_struct_ops_link_lops, prog); - st_map->links[i] = &link->link; + &bpf_struct_ops_link_lops, prog, prog->expected_attach_type); + *plink++ = &link->link; + + ksym = kzalloc(sizeof(*ksym), GFP_USER); + if (!ksym) { + err = -ENOMEM; + goto reset_unlock; + } + *pksym++ = ksym; + trampoline_start = image_off; err = bpf_struct_ops_prepare_trampoline(tlinks, link, - &st_ops->func_models[i], - image, image_end); - if (err < 0) + &st_ops->func_models[i], + *(void **)(st_ops->cfi_stubs + moff), + &image, &image_off, + st_map->image_pages_cnt < MAX_TRAMP_IMAGE_PAGES); + if (err) goto reset_unlock; - *(void **)(kdata + moff) = image; - image += err; + if (cur_image != image) { + st_map->image_pages[st_map->image_pages_cnt++] = image; + cur_image = image; + trampoline_start = 0; + } + + *(void **)(kdata + moff) = image + trampoline_start + cfi_get_offset(); /* put prog_id to udata */ *(unsigned long *)(udata + moff) = prog->aux->id; + + /* init ksym for this trampoline */ + bpf_struct_ops_ksym_init(tname, mname, + image + trampoline_start, + image_off - trampoline_start, + ksym); } - refcount_set(&kvalue->refcnt, 1); - bpf_map_inc(map); + if (st_ops->validate) { + err = st_ops->validate(kdata); + if (err) + goto reset_unlock; + } + 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; + } - set_memory_rox((long)st_map->image, 1); - err = st_ops->reg(kdata); + if (st_map->map.map_flags & BPF_F_LINK) { + err = 0; + /* Let bpf_link handle registration & unregistration. + * + * Pair with smp_load_acquire() during lookup_elem(). + */ + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_READY); + goto unlock; + } + + err = st_ops->reg(kdata, NULL); if (likely(!err)) { + /* This refcnt increment on the map here after + * 'st_ops->reg()' is secure since the state of the + * map must be set to INIT at this moment, and thus + * bpf_struct_ops_map_delete_elem() can't unregister + * or transition it to TOBEFREE concurrently. + */ + bpf_map_inc(map); /* Pair with smp_load_acquire() during lookup_elem(). * It ensures the above udata updates (e.g. prog->aux->id) * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_INUSE); goto unlock; } @@ -510,34 +889,37 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * there was a race in registering the struct_ops (under the same name) to * a sub-system through different struct_ops's maps. */ - set_memory_nx((long)st_map->image, 1); - set_memory_rw((long)st_map->image, 1); - bpf_map_put(map); reset_unlock: + bpf_struct_ops_map_free_ksyms(st_map); + bpf_struct_ops_map_free_image(st_map); bpf_struct_ops_map_put_progs(st_map); memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); unlock: kfree(tlinks); mutex_unlock(&st_map->lock); + if (!err) + bpf_struct_ops_map_add_ksyms(st_map); return err; } -static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) +static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) { enum bpf_struct_ops_state prev_state; struct bpf_struct_ops_map *st_map; st_map = (struct bpf_struct_ops_map *)map; - prev_state = cmpxchg(&st_map->kvalue.state, + if (st_map->map.map_flags & BPF_F_LINK) + return -EOPNOTSUPP; + + prev_state = cmpxchg(&st_map->kvalue.common.state, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { case BPF_STRUCT_OPS_STATE_INUSE: - st_map->st_ops->unreg(&st_map->kvalue.data); - if (refcount_dec_and_test(&st_map->kvalue.refcnt)) - bpf_map_put(map); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, NULL); + bpf_map_put(map); return 0; case BPF_STRUCT_OPS_STATE_TOBEFREE: return -EINPROGRESS; @@ -553,6 +935,7 @@ static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; void *value; int err; @@ -562,54 +945,134 @@ static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); if (!err) { - btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id, + btf_type_seq_show(st_map->btf, + map->btf_vmlinux_value_type_id, value, m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); } kfree(value); } -static void bpf_struct_ops_map_free(struct bpf_map *map) +static void __bpf_struct_ops_map_free(struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; if (st_map->links) bpf_struct_ops_map_put_progs(st_map); + if (st_map->ksyms) + bpf_struct_ops_map_free_ksyms(st_map); bpf_map_area_free(st_map->links); - bpf_jit_free_exec(st_map->image); + bpf_map_area_free(st_map->ksyms); + bpf_struct_ops_map_free_image(st_map); bpf_map_area_free(st_map->uvalue); bpf_map_area_free(st_map); } +static void bpf_struct_ops_map_free(struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + /* st_ops->owner was acquired during map_alloc to implicitly holds + * the btf's refcnt. The acquire was only done when btf_is_module() + * st_map->btf cannot be NULL here. + */ + if (btf_is_module(st_map->btf)) + module_put(st_map->st_ops_desc->st_ops->owner); + + bpf_struct_ops_map_del_ksyms(st_map); + + /* The struct_ops's function may switch to another struct_ops. + * + * For example, bpf_tcp_cc_x->init() may switch to + * another tcp_cc_y by calling + * setsockopt(TCP_CONGESTION, "tcp_cc_y"). + * During the switch, bpf_struct_ops_put(tcp_cc_x) is called + * and its refcount may reach 0 which then free its + * trampoline image while tcp_cc_x is still running. + * + * A vanilla rcu gp is to wait for all bpf-tcp-cc prog + * to finish. bpf-tcp-cc prog is non sleepable. + * A rcu_tasks gp is to wait for the last few insn + * in the tramopline image to finish before releasing + * the trampoline image. + */ + synchronize_rcu_mult(call_rcu, call_rcu_tasks); + + __bpf_struct_ops_map_free(map); +} + static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) { if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || - attr->map_flags || !attr->btf_vmlinux_value_type_id) + (attr->map_flags & ~(BPF_F_LINK | BPF_F_VTYPE_BTF_OBJ_FD)) || + !attr->btf_vmlinux_value_type_id) return -EINVAL; return 0; } +static u32 count_func_ptrs(const struct btf *btf, const struct btf_type *t) +{ + int i; + u32 count; + const struct btf_member *member; + + count = 0; + for_each_member(i, t, member) + if (btf_type_resolve_func_ptr(btf, member->type, NULL)) + count++; + return count; +} + static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; + struct module *mod = NULL; struct bpf_map *map; + struct btf *btf; + int ret; + + if (attr->map_flags & BPF_F_VTYPE_BTF_OBJ_FD) { + /* The map holds btf for its whole life time. */ + btf = btf_get_by_fd(attr->value_type_btf_obj_fd); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf_is_module(btf)) { + btf_put(btf); + return ERR_PTR(-EINVAL); + } - if (!bpf_capable()) - return ERR_PTR(-EPERM); + mod = btf_try_get_module(btf); + /* mod holds a refcnt to btf. We don't need an extra refcnt + * here. + */ + btf_put(btf); + if (!mod) + return ERR_PTR(-EINVAL); + } else { + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf) + return ERR_PTR(-ENOTSUPP); + } - st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); - if (!st_ops) - return ERR_PTR(-ENOTSUPP); + st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id); + if (!st_ops_desc) { + ret = -ENOTSUPP; + goto errout; + } - vt = st_ops->value_type; - if (attr->value_size != vt->size) - return ERR_PTR(-EINVAL); + vt = st_ops_desc->value_type; + if (attr->value_size != vt->size) { + ret = -EINVAL; + goto errout; + } - t = st_ops->type; + t = st_ops_desc->type; st_map_size = sizeof(*st_map) + /* kvalue stores the @@ -618,27 +1081,56 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) (vt->size - sizeof(struct bpf_struct_ops_value)); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); - if (!st_map) - return ERR_PTR(-ENOMEM); + if (!st_map) { + ret = -ENOMEM; + goto errout; + } - st_map->st_ops = st_ops; + st_map->st_ops_desc = st_ops_desc; map = &st_map->map; st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->funcs_cnt = count_func_ptrs(btf, t); st_map->links = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), + bpf_map_area_alloc(st_map->funcs_cnt * sizeof(struct bpf_link *), NUMA_NO_NODE); - st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); - if (!st_map->uvalue || !st_map->links || !st_map->image) { - bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); + + st_map->ksyms = + bpf_map_area_alloc(st_map->funcs_cnt * sizeof(struct bpf_ksym *), + NUMA_NO_NODE); + if (!st_map->uvalue || !st_map->links || !st_map->ksyms) { + ret = -ENOMEM; + goto errout_free; } + st_map->btf = btf; mutex_init(&st_map->lock); - set_vm_flush_reset_perms(st_map->image); bpf_map_init_from_attr(map, attr); return map; + +errout_free: + __bpf_struct_ops_map_free(map); +errout: + module_put(mod); + + return ERR_PTR(ret); +} + +static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct btf_type *vt = st_ops_desc->value_type; + u64 usage; + + usage = sizeof(*st_map) + + vt->size - sizeof(struct bpf_struct_ops_value); + usage += vt->size; + usage += st_map->funcs_cnt * sizeof(struct bpf_link *); + usage += st_map->funcs_cnt * sizeof(struct bpf_ksym *); + usage += PAGE_SIZE; + return usage; } BTF_ID_LIST_SINGLE(bpf_struct_ops_map_btf_ids, struct, bpf_struct_ops_map) @@ -651,6 +1143,7 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = { .map_delete_elem = bpf_struct_ops_map_delete_elem, .map_update_elem = bpf_struct_ops_map_update_elem, .map_seq_show_elem = bpf_struct_ops_map_seq_show_elem, + .map_mem_usage = bpf_struct_ops_map_mem_usage, .map_btf_id = &bpf_struct_ops_map_btf_ids[0], }; @@ -660,41 +1153,252 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = { bool bpf_struct_ops_get(const void *kdata) { struct bpf_struct_ops_value *kvalue; + struct bpf_struct_ops_map *st_map; + struct bpf_map *map; kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + st_map = container_of(kvalue, struct bpf_struct_ops_map, kvalue); - return refcount_inc_not_zero(&kvalue->refcnt); + map = __bpf_map_inc_not_zero(&st_map->map, false); + return !IS_ERR(map); } +EXPORT_SYMBOL_GPL(bpf_struct_ops_get); -static void bpf_struct_ops_put_rcu(struct rcu_head *head) +void bpf_struct_ops_put(const void *kdata) { + struct bpf_struct_ops_value *kvalue; struct bpf_struct_ops_map *st_map; - st_map = container_of(head, struct bpf_struct_ops_map, rcu); + kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + st_map = container_of(kvalue, struct bpf_struct_ops_map, kvalue); + bpf_map_put(&st_map->map); } +EXPORT_SYMBOL_GPL(bpf_struct_ops_put); -void bpf_struct_ops_put(const void *kdata) +u32 bpf_struct_ops_id(const void *kdata) { struct bpf_struct_ops_value *kvalue; + struct bpf_struct_ops_map *st_map; kvalue = container_of(kdata, struct bpf_struct_ops_value, data); - if (refcount_dec_and_test(&kvalue->refcnt)) { - struct bpf_struct_ops_map *st_map; + st_map = container_of(kvalue, struct bpf_struct_ops_map, kvalue); - st_map = container_of(kvalue, struct bpf_struct_ops_map, - kvalue); - /* The struct_ops's function may switch to another struct_ops. - * - * For example, bpf_tcp_cc_x->init() may switch to - * another tcp_cc_y by calling - * setsockopt(TCP_CONGESTION, "tcp_cc_y"). - * During the switch, bpf_struct_ops_put(tcp_cc_x) is called - * and its map->refcnt may reach 0 which then free its - * trampoline image while tcp_cc_x is still running. - * - * Thus, a rcu grace period is needed here. - */ - call_rcu(&st_map->rcu, bpf_struct_ops_put_rcu); + return st_map->map.id; +} +EXPORT_SYMBOL_GPL(bpf_struct_ops_id); + +static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + return map->map_type == BPF_MAP_TYPE_STRUCT_OPS && + map->map_flags & BPF_F_LINK && + /* Pair with smp_store_release() during map_update */ + smp_load_acquire(&st_map->kvalue.common.state) == BPF_STRUCT_OPS_STATE_READY; +} + +static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) +{ + struct bpf_struct_ops_link *st_link; + struct bpf_struct_ops_map *st_map; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + st_map = (struct bpf_struct_ops_map *) + rcu_dereference_protected(st_link->map, true); + if (st_map) { + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link); + bpf_map_put(&st_map->map); + } + kfree(st_link); +} + +static void bpf_struct_ops_map_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_struct_ops_link *st_link; + struct bpf_map *map; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + rcu_read_lock(); + map = rcu_dereference(st_link->map); + if (map) + seq_printf(seq, "map_id:\t%d\n", map->id); + rcu_read_unlock(); +} + +static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_struct_ops_link *st_link; + struct bpf_map *map; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + rcu_read_lock(); + map = rcu_dereference(st_link->map); + if (map) + info->struct_ops.map_id = map->id; + rcu_read_unlock(); + return 0; +} + +static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map *new_map, + struct bpf_map *expected_old_map) +{ + struct bpf_struct_ops_map *st_map, *old_st_map; + struct bpf_map *old_map; + struct bpf_struct_ops_link *st_link; + int err; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + st_map = container_of(new_map, struct bpf_struct_ops_map, map); + + if (!bpf_struct_ops_valid_to_reg(new_map)) + return -EINVAL; + + if (!st_map->st_ops_desc->st_ops->update) + return -EOPNOTSUPP; + + mutex_lock(&update_mutex); + + old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex)); + if (!old_map) { + err = -ENOLINK; + goto err_out; + } + if (expected_old_map && old_map != expected_old_map) { + err = -EPERM; + goto err_out; + } + + old_st_map = container_of(old_map, struct bpf_struct_ops_map, map); + /* The new and old struct_ops must be the same type. */ + if (st_map->st_ops_desc != old_st_map->st_ops_desc) { + err = -EINVAL; + goto err_out; + } + + err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data, link); + if (err) + goto err_out; + + bpf_map_inc(new_map); + rcu_assign_pointer(st_link->map, new_map); + bpf_map_put(old_map); + +err_out: + mutex_unlock(&update_mutex); + + return err; +} + +static int bpf_struct_ops_map_link_detach(struct bpf_link *link) +{ + struct bpf_struct_ops_link *st_link = container_of(link, struct bpf_struct_ops_link, link); + struct bpf_struct_ops_map *st_map; + struct bpf_map *map; + + mutex_lock(&update_mutex); + + map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex)); + if (!map) { + mutex_unlock(&update_mutex); + return 0; + } + st_map = container_of(map, struct bpf_struct_ops_map, map); + + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data, link); + + RCU_INIT_POINTER(st_link->map, NULL); + /* Pair with bpf_map_get() in bpf_struct_ops_link_create() or + * bpf_map_inc() in bpf_struct_ops_map_link_update(). + */ + bpf_map_put(&st_map->map); + + mutex_unlock(&update_mutex); + + wake_up_interruptible_poll(&st_link->wait_hup, EPOLLHUP); + + return 0; +} + +static __poll_t bpf_struct_ops_map_link_poll(struct file *file, + struct poll_table_struct *pts) +{ + struct bpf_struct_ops_link *st_link = file->private_data; + + poll_wait(file, &st_link->wait_hup, pts); + + return rcu_access_pointer(st_link->map) ? 0 : EPOLLHUP; +} + +static const struct bpf_link_ops bpf_struct_ops_map_lops = { + .dealloc = bpf_struct_ops_map_link_dealloc, + .detach = bpf_struct_ops_map_link_detach, + .show_fdinfo = bpf_struct_ops_map_link_show_fdinfo, + .fill_link_info = bpf_struct_ops_map_link_fill_link_info, + .update_map = bpf_struct_ops_map_link_update, + .poll = bpf_struct_ops_map_link_poll, +}; + +int bpf_struct_ops_link_create(union bpf_attr *attr) +{ + struct bpf_struct_ops_link *link = NULL; + struct bpf_link_primer link_primer; + struct bpf_struct_ops_map *st_map; + struct bpf_map *map; + int err; + + map = bpf_map_get(attr->link_create.map_fd); + if (IS_ERR(map)) + return PTR_ERR(map); + + st_map = (struct bpf_struct_ops_map *)map; + + if (!bpf_struct_ops_valid_to_reg(map)) { + err = -EINVAL; + goto err_out; + } + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto err_out; } + bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_map_lops, NULL, + attr->link_create.attach_type); + + err = bpf_link_prime(&link->link, &link_primer); + if (err) + goto err_out; + + init_waitqueue_head(&link->wait_hup); + + /* Hold the update_mutex such that the subsystem cannot + * do link->ops->detach() before the link is fully initialized. + */ + mutex_lock(&update_mutex); + err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data, &link->link); + if (err) { + mutex_unlock(&update_mutex); + bpf_link_cleanup(&link_primer); + link = NULL; + goto err_out; + } + RCU_INIT_POINTER(link->map, map); + mutex_unlock(&update_mutex); + + return bpf_link_settle(&link_primer); + +err_out: + bpf_map_put(map); + kfree(link); + return err; +} + +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + info->btf_vmlinux_id = btf_obj_id(st_map->btf); } diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h deleted file mode 100644 index 5678a9ddf817..000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#ifdef CONFIG_NET -BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) -#endif -#ifdef CONFIG_INET -#include <net/tcp.h> -BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) -#endif -#endif diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 1e486055a523..a1dc1bf0848a 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -16,7 +16,6 @@ #include <linux/filter.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> -#include <linux/fdtable.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(task_cache); @@ -25,22 +24,20 @@ static DEFINE_PER_CPU(int, bpf_task_storage_busy); static void bpf_task_storage_lock(void) { - migrate_disable(); + cant_migrate(); this_cpu_inc(bpf_task_storage_busy); } static void bpf_task_storage_unlock(void) { this_cpu_dec(bpf_task_storage_busy); - migrate_enable(); } static bool bpf_task_storage_trylock(void) { - migrate_disable(); + cant_migrate(); if (unlikely(this_cpu_inc_return(bpf_task_storage_busy) != 1)) { this_cpu_dec(bpf_task_storage_busy); - migrate_enable(); return false; } return true; @@ -72,26 +69,18 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map, void bpf_task_storage_free(struct task_struct *task) { struct bpf_local_storage *local_storage; - bool free_task_storage = false; - unsigned long flags; - rcu_read_lock(); + rcu_read_lock_dont_migrate(); local_storage = rcu_dereference(task->bpf_storage); - if (!local_storage) { - rcu_read_unlock(); - return; - } + if (!local_storage) + goto out; bpf_task_storage_lock(); - raw_spin_lock_irqsave(&local_storage->lock, flags); - free_task_storage = bpf_local_storage_unlink_nolock(local_storage); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_local_storage_destroy(local_storage); bpf_task_storage_unlock(); - rcu_read_unlock(); - - if (free_task_storage) - kfree_rcu(local_storage, rcu); +out: + rcu_read_unlock_migrate(); } static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key) @@ -127,8 +116,8 @@ out: return ERR_PTR(err); } -static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct task_struct *task; @@ -136,6 +125,9 @@ static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, struct pid *pid; int fd, err; + if ((map_flags & BPF_F_LOCK) && btf_record_has_field(map->record, BPF_UPTR)) + return -EOPNOTSUPP; + fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) @@ -154,7 +146,7 @@ static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, bpf_task_storage_lock(); sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, map_flags, - GFP_ATOMIC); + true, GFP_ATOMIC); bpf_task_storage_unlock(); err = PTR_ERR_OR_ZERO(sdata); @@ -175,12 +167,12 @@ static int task_storage_delete(struct task_struct *task, struct bpf_map *map, if (!nobusy) return -EBUSY; - bpf_selem_unlink(SELEM(sdata), true); + bpf_selem_unlink(SELEM(sdata), false); return 0; } -static int bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) +static long bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) { struct task_struct *task; unsigned int f_flags; @@ -226,7 +218,7 @@ static void *__bpf_task_storage_get(struct bpf_map *map, (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy) { sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, - BPF_NOEXIST, gfp_flags); + BPF_NOEXIST, false, gfp_flags); return IS_ERR(sdata) ? NULL : sdata->data; } @@ -316,7 +308,7 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) { - return bpf_local_storage_map_alloc(attr, &task_cache); + return bpf_local_storage_map_alloc(attr, &task_cache, true); } static void task_storage_map_free(struct bpf_map *map) @@ -335,6 +327,7 @@ const struct bpf_map_ops task_storage_map_ops = { .map_update_elem = bpf_pid_task_storage_update_elem, .map_delete_elem = bpf_pid_task_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, + .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = task_storage_ptr, }; @@ -344,7 +337,7 @@ const struct bpf_func_proto bpf_task_storage_get_recur_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -355,7 +348,7 @@ const struct bpf_func_proto bpf_task_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -366,7 +359,7 @@ const struct bpf_func_proto bpf_task_storage_delete_recur_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; @@ -375,6 +368,6 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f7dd8af06413..0de8fc8a0e0b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,13 +19,19 @@ #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/btf_ids.h> +#include <linux/bpf.h> #include <linux/bpf_lsm.h> #include <linux/skmsg.h> #include <linux/perf_event.h> #include <linux/bsearch.h> #include <linux/kobject.h> #include <linux/sysfs.h> +#include <linux/overflow.h> + +#include <net/netfilter/nf_bpf_link.h> + #include <net/sock.h> +#include <net/xdp.h> #include "../tools/lib/bpf/relo_core.h" /* BTF (BPF Type Format) is the meta data format which describes @@ -207,16 +213,30 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_TRACING, BTF_KFUNC_HOOK_SYSCALL, BTF_KFUNC_HOOK_FMODRET, + BTF_KFUNC_HOOK_CGROUP, + BTF_KFUNC_HOOK_SCHED_ACT, + BTF_KFUNC_HOOK_SK_SKB, + BTF_KFUNC_HOOK_SOCKET_FILTER, + BTF_KFUNC_HOOK_LWT, + BTF_KFUNC_HOOK_NETFILTER, + BTF_KFUNC_HOOK_KPROBE, BTF_KFUNC_HOOK_MAX, }; enum { BTF_KFUNC_SET_MAX_CNT = 256, BTF_DTOR_KFUNC_MAX_CNT = 256, + BTF_KFUNC_FILTER_MAX_CNT = 16, +}; + +struct btf_kfunc_hook_filter { + btf_kfunc_filter_t filters[BTF_KFUNC_FILTER_MAX_CNT]; + u32 nr_filters; }; struct btf_kfunc_set_tab { struct btf_id_set8 *sets[BTF_KFUNC_HOOK_MAX]; + struct btf_kfunc_hook_filter hook_filters[BTF_KFUNC_HOOK_MAX]; }; struct btf_id_dtor_kfunc_tab { @@ -224,6 +244,12 @@ struct btf_id_dtor_kfunc_tab { struct btf_id_dtor_kfunc dtors[]; }; +struct btf_struct_ops_tab { + u32 cnt; + u32 capacity; + struct bpf_struct_ops_desc ops[]; +}; + struct btf { void *data; struct btf_type **types; @@ -241,6 +267,7 @@ struct btf { struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; struct btf_struct_metas *struct_meta_tab; + struct btf_struct_ops_tab *struct_ops_tab; /* split BTF support */ struct btf *base_btf; @@ -248,6 +275,7 @@ struct btf { u32 start_str_off; /* first string offset (0 for base BTF) */ char name[MODULE_NAME_LEN]; bool kernel_btf; + __u32 *base_id_map; /* map from distilled base BTF -> vmlinux BTF ids */ }; enum verifier_phase { @@ -337,6 +365,12 @@ const char *btf_type_str(const struct btf_type *t) #define BTF_SHOW_NAME_SIZE 80 /* + * The suffix of a type that indicates it cannot alias another type when + * comparing BTF IDs for kfunc invocations. + */ +#define NOCAST_ALIAS_SUFFIX "___init" + +/* * Common data to all BTF show operations. Private show functions can add * their own data to a structure containing a struct btf_show and consult it * in the show callback. See btf_type_show() below. @@ -382,7 +416,7 @@ const char *btf_type_str(const struct btf_type *t) struct btf_show { u64 flags; void *target; /* target of show operation (seq file, buffer) */ - void (*showfn)(struct btf_show *show, const char *fmt, va_list args); + __printf(2, 0) void (*showfn)(struct btf_show *show, const char *fmt, va_list args); const struct btf *btf; /* below are used during iteration */ struct { @@ -465,15 +499,21 @@ bool btf_type_is_void(const struct btf_type *t) return t == &btf_void; } -static bool btf_type_is_fwd(const struct btf_type *t) +static bool btf_type_is_datasec(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; +} + +static bool btf_type_is_decl_tag(const struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; + return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; } static bool btf_type_nosize(const struct btf_type *t) { return btf_type_is_void(t) || btf_type_is_fwd(t) || - btf_type_is_func(t) || btf_type_is_func_proto(t); + btf_type_is_func(t) || btf_type_is_func_proto(t) || + btf_type_is_decl_tag(t); } static bool btf_type_nosize_or_null(const struct btf_type *t) @@ -481,22 +521,17 @@ static bool btf_type_nosize_or_null(const struct btf_type *t) return !t || btf_type_nosize(t); } -static bool btf_type_is_datasec(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; -} - -static bool btf_type_is_decl_tag(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; -} - static bool btf_type_is_decl_tag_target(const struct btf_type *t) { return btf_type_is_func(t) || btf_type_is_struct(t) || btf_type_is_var(t) || btf_type_is_typedef(t); } +bool btf_is_vmlinux(const struct btf *btf) +{ + return btf->kernel_btf && !btf->base_btf; +} + u32 btf_nr_types(const struct btf *btf) { u32 total = 0; @@ -529,7 +564,7 @@ s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind) return -ENOENT; } -static s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p) +s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p) { struct btf *btf; s32 ret; @@ -566,12 +601,13 @@ static s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p) *btf_p = btf; return ret; } - spin_lock_bh(&btf_idr_lock); btf_put(btf); + spin_lock_bh(&btf_idr_lock); } spin_unlock_bh(&btf_idr_lock); return ret; } +EXPORT_SYMBOL_GPL(bpf_find_btf_id); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, u32 id, u32 *res_id) @@ -729,18 +765,17 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset) return offset < btf->hdr.str_len; } -static bool __btf_name_char_ok(char c, bool first, bool dot_ok) +static bool __btf_name_char_ok(char c, bool first) { if ((first ? !isalpha(c) : !isalnum(c)) && c != '_' && - ((c == '.' && !dot_ok) || - c != '.')) + c != '.') return false; return true; } -static const char *btf_str_by_offset(const struct btf *btf, u32 offset) +const char *btf_str_by_offset(const struct btf *btf, u32 offset) { while (offset < btf->start_str_off) btf = btf->base_btf; @@ -752,20 +787,20 @@ static const char *btf_str_by_offset(const struct btf *btf, u32 offset) return NULL; } -static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) +static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) { /* offset must be valid */ const char *src = btf_str_by_offset(btf, offset); const char *src_limit; - if (!__btf_name_char_ok(*src, true, dot_ok)) + if (!__btf_name_char_ok(*src, true)) return false; /* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; src++; while (*src && src < src_limit) { - if (!__btf_name_char_ok(*src, false, dot_ok)) + if (!__btf_name_char_ok(*src, false)) return false; src++; } @@ -773,17 +808,25 @@ static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) return !*src; } -/* Only C-style identifier is permitted. This can be relaxed if - * necessary. - */ -static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) -{ - return __btf_name_valid(btf, offset, false); -} - +/* Allow any printable character in DATASEC names */ static bool btf_name_valid_section(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset, true); + /* offset must be valid */ + const char *src = btf_str_by_offset(btf, offset); + const char *src_limit; + + if (!*src) + return false; + + /* set a limit on identifier length */ + src_limit = src + KSYM_NAME_LEN; + while (*src && src < src_limit) { + if (!isprint(*src)) + return false; + src++; + } + + return !*src; } static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) @@ -815,26 +858,43 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) EXPORT_SYMBOL_GPL(btf_type_by_id); /* - * Regular int is not a bit field and it must be either - * u8/u16/u32/u64 or __int128. + * Check that the type @t is a regular int. This means that @t is not + * a bit field and it has the same size as either of u8/u16/u32/u64 + * or __int128. If @expected_size is not zero, then size of @t should + * be the same. A caller should already have checked that the type @t + * is an integer. */ +static bool __btf_type_int_is_regular(const struct btf_type *t, size_t expected_size) +{ + u32 int_data = btf_type_int(t); + u8 nr_bits = BTF_INT_BITS(int_data); + u8 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); + + return BITS_PER_BYTE_MASKED(nr_bits) == 0 && + BTF_INT_OFFSET(int_data) == 0 && + (nr_bytes <= 16 && is_power_of_2(nr_bytes)) && + (expected_size == 0 || nr_bytes == expected_size); +} + static bool btf_type_int_is_regular(const struct btf_type *t) { - u8 nr_bits, nr_bytes; - u32 int_data; + return __btf_type_int_is_regular(t, 0); +} - int_data = btf_type_int(t); - nr_bits = BTF_INT_BITS(int_data); - nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); - if (BITS_PER_BYTE_MASKED(nr_bits) || - BTF_INT_OFFSET(int_data) || - (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) && - nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) && - nr_bytes != (2 * sizeof(u64)))) { - return false; - } +bool btf_type_is_i32(const struct btf_type *t) +{ + return btf_type_is_int(t) && __btf_type_int_is_regular(t, 4); +} - return true; +bool btf_type_is_i64(const struct btf_type *t) +{ + return btf_type_is_int(t) && __btf_type_int_is_regular(t, 8); +} + +bool btf_type_is_primitive(const struct btf_type *t) +{ + return (btf_type_is_int(t) && btf_type_int_is_regular(t)) || + btf_is_any_enum(t); } /* @@ -1397,12 +1457,18 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; - /* btf verifier prints all types it is processing via - * btf_verifier_log_type(..., fmt = NULL). - * Skip those prints for in-kernel BTF verification. - */ - if (log->level == BPF_LOG_KERNEL && !fmt) - return; + if (log->level == BPF_LOG_KERNEL) { + /* btf verifier prints all types it is processing via + * btf_verifier_log_type(..., fmt = NULL). + * Skip those prints for in-kernel BTF verification. + */ + if (!fmt) + return; + + /* Skip logging when loading module BTF with mismatches permitted */ + if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) + return; + } __btf_verifier_log(log, "[%u] %s %s%s", env->log_type_id, @@ -1441,8 +1507,15 @@ static void btf_verifier_log_member(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; - if (log->level == BPF_LOG_KERNEL && !fmt) - return; + if (log->level == BPF_LOG_KERNEL) { + if (!fmt) + return; + + /* Skip logging when loading module BTF with mismatches permitted */ + if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) + return; + } + /* The CHECK_META phase already did a btf dump. * * If member is logged again, it must hit an error in @@ -1614,14 +1687,8 @@ static void btf_free_kfunc_set_tab(struct btf *btf) if (!tab) return; - /* For module BTF, we directly assign the sets being registered, so - * there is nothing to free except kfunc_set_tab. - */ - if (btf_is_module(btf)) - goto free_tab; for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) kfree(tab->sets[hook]); -free_tab: kfree(tab); btf->kfunc_set_tab = NULL; } @@ -1642,10 +1709,8 @@ static void btf_struct_metas_free(struct btf_struct_metas *tab) if (!tab) return; - for (i = 0; i < tab->cnt; i++) { + for (i = 0; i < tab->cnt; i++) btf_record_free(tab->types[i].record); - kfree(tab->types[i].field_offs); - } kfree(tab); } @@ -1657,15 +1722,36 @@ static void btf_free_struct_meta_tab(struct btf *btf) btf->struct_meta_tab = NULL; } +static void btf_free_struct_ops_tab(struct btf *btf) +{ + struct btf_struct_ops_tab *tab = btf->struct_ops_tab; + u32 i; + + if (!tab) + return; + + for (i = 0; i < tab->cnt; i++) + bpf_struct_ops_desc_release(&tab->ops[i]); + + kfree(tab); + btf->struct_ops_tab = NULL; +} + static void btf_free(struct btf *btf) { btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); + btf_free_struct_ops_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); - kvfree(btf->data); + /* vmlinux does not allocate btf->data, it simply points it at + * __start_BTF. + */ + if (!btf_is_vmlinux(btf)) + kvfree(btf->data); + kvfree(btf->base_id_map); kfree(btf); } @@ -1676,6 +1762,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +const char *btf_get_name(const struct btf *btf) +{ + return btf->name; +} + void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); @@ -1689,6 +1780,23 @@ void btf_put(struct btf *btf) } } +struct btf *btf_base_btf(const struct btf *btf) +{ + return btf->base_btf; +} + +const struct btf_header *btf_header(const struct btf *btf) +{ + return &btf->hdr; +} + +void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) +{ + btf->base_btf = (struct btf *)base_btf; + btf->start_id = btf_nr_types(base_btf); + btf->start_str_off = base_btf->hdr.str_len; +} + static int env_resolve_init(struct btf_verifier_env *env) { struct btf *btf = env->btf; @@ -2486,7 +2594,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_kflag(t)) { + if (btf_type_kflag(t) && !btf_type_is_type_tag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } @@ -2714,7 +2822,7 @@ static void btf_ref_type_log(struct btf_verifier_env *env, btf_verifier_log(env, "type_id=%u", t->type); } -static struct btf_kind_operations modifier_ops = { +static const struct btf_kind_operations modifier_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_modifier_resolve, .check_member = btf_modifier_check_member, @@ -2723,7 +2831,7 @@ static struct btf_kind_operations modifier_ops = { .show = btf_modifier_show, }; -static struct btf_kind_operations ptr_ops = { +static const struct btf_kind_operations ptr_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_ptr_resolve, .check_member = btf_ptr_check_member, @@ -2764,7 +2872,7 @@ static void btf_fwd_type_log(struct btf_verifier_env *env, btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct"); } -static struct btf_kind_operations fwd_ops = { +static const struct btf_kind_operations fwd_ops = { .check_meta = btf_fwd_check_meta, .resolve = btf_df_resolve, .check_member = btf_df_check_member, @@ -3015,7 +3123,7 @@ static void btf_array_show(const struct btf *btf, const struct btf_type *t, __btf_array_show(btf, t, type_id, data, bits_offset, show); } -static struct btf_kind_operations array_ops = { +static const struct btf_kind_operations array_ops = { .check_meta = btf_array_check_meta, .resolve = btf_array_resolve, .check_member = btf_array_check_member, @@ -3207,12 +3315,6 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -enum btf_field_info_type { - BTF_FIELD_SPIN_LOCK, - BTF_FIELD_TIMER, - BTF_FIELD_KPTR, -}; - enum { BTF_FIELD_IGNORE = 0, BTF_FIELD_FOUND = 1, @@ -3228,7 +3330,7 @@ struct btf_field_info { struct { const char *node_name; u32 value_btf_id; - } list_head; + } graph_root; }; }; @@ -3246,9 +3348,11 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t, } static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, - u32 off, int sz, struct btf_field_info *info) + u32 off, int sz, struct btf_field_info *info, u32 field_mask) { enum btf_field_type type; + const char *tag_value; + bool is_type_tag; u32 res_id; /* Permit modifiers on the pointer itself */ @@ -3258,19 +3362,27 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, if (!btf_type_is_ptr(t)) return BTF_FIELD_IGNORE; t = btf_type_by_id(btf, t->type); - - if (!btf_type_is_type_tag(t)) + is_type_tag = btf_type_is_type_tag(t) && !btf_type_kflag(t); + if (!is_type_tag) return BTF_FIELD_IGNORE; /* Reject extra tags */ if (btf_type_is_type_tag(btf_type_by_id(btf, t->type))) return -EINVAL; - if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) + tag_value = __btf_name_by_offset(btf, t->name_off); + if (!strcmp("kptr_untrusted", tag_value)) type = BPF_KPTR_UNREF; - else if (!strcmp("kptr_ref", __btf_name_by_offset(btf, t->name_off))) + else if (!strcmp("kptr", tag_value)) type = BPF_KPTR_REF; + else if (!strcmp("percpu_kptr", tag_value)) + type = BPF_KPTR_PERCPU; + else if (!strcmp("uptr", tag_value)) + type = BPF_UPTR; else return -EINVAL; + if (!(type & field_mask)) + return BTF_FIELD_IGNORE; + /* Get the base type */ t = btf_type_skip_modifiers(btf, t->type, &res_id); /* Only pointer to struct is allowed */ @@ -3283,34 +3395,59 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, return BTF_FIELD_FOUND; } -static const char *btf_find_decl_tag_value(const struct btf *btf, - const struct btf_type *pt, - int comp_idx, const char *tag_key) +int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key, int last_id) { - int i; + int len = strlen(tag_key); + int i, n; - for (i = 1; i < btf_nr_types(btf); i++) { + for (i = last_id + 1, n = btf_nr_types(btf); i < n; i++) { const struct btf_type *t = btf_type_by_id(btf, i); - int len = strlen(tag_key); if (!btf_type_is_decl_tag(t)) continue; - if (pt != btf_type_by_id(btf, t->type) || - btf_type_decl_tag(t)->component_idx != comp_idx) + if (pt != btf_type_by_id(btf, t->type)) + continue; + if (btf_type_decl_tag(t)->component_idx != comp_idx) continue; if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) continue; - return __btf_name_by_offset(btf, t->name_off) + len; + return i; } - return NULL; + return -ENOENT; } -static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, - const struct btf_type *t, int comp_idx, - u32 off, int sz, struct btf_field_info *info) +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key) { + const char *value = NULL; + const struct btf_type *t; + int len, id; + + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, 0); + if (id < 0) + return ERR_PTR(id); + + t = btf_type_by_id(btf, id); + len = strlen(tag_key); + value = __btf_name_by_offset(btf, t->name_off) + len; + + /* Prevent duplicate entries for same type */ + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, id); + if (id >= 0) + return ERR_PTR(-EEXIST); + + return value; +} + +static int +btf_find_graph_root(const struct btf *btf, const struct btf_type *pt, + const struct btf_type *t, int comp_idx, u32 off, + int sz, struct btf_field_info *info, + enum btf_field_type head_type) +{ + const char *node_field_name; const char *value_type; - const char *list_node; s32 id; if (!__btf_type_is_struct(t)) @@ -3318,65 +3455,71 @@ static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, if (t->size != sz) return BTF_FIELD_IGNORE; value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); - if (!value_type) + if (IS_ERR(value_type)) return -EINVAL; - list_node = strstr(value_type, ":"); - if (!list_node) + node_field_name = strstr(value_type, ":"); + if (!node_field_name) return -EINVAL; - value_type = kstrndup(value_type, list_node - value_type, GFP_KERNEL | __GFP_NOWARN); + value_type = kstrndup(value_type, node_field_name - value_type, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!value_type) return -ENOMEM; id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT); kfree(value_type); if (id < 0) return id; - list_node++; - if (str_is_empty(list_node)) + node_field_name++; + if (str_is_empty(node_field_name)) return -EINVAL; - info->type = BPF_LIST_HEAD; + info->type = head_type; info->off = off; - info->list_head.value_btf_id = id; - info->list_head.node_name = list_node; + info->graph_root.value_btf_id = id; + info->graph_root.node_name = node_field_name; return BTF_FIELD_FOUND; } -static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, - int *align, int *sz) -{ - int type = 0; - - if (field_mask & BPF_SPIN_LOCK) { - if (!strcmp(name, "bpf_spin_lock")) { - if (*seen_mask & BPF_SPIN_LOCK) - return -E2BIG; - *seen_mask |= BPF_SPIN_LOCK; - type = BPF_SPIN_LOCK; - goto end; - } - } - if (field_mask & BPF_TIMER) { - if (!strcmp(name, "bpf_timer")) { - if (*seen_mask & BPF_TIMER) +static int btf_get_field_type(const struct btf *btf, const struct btf_type *var_type, + u32 field_mask, u32 *seen_mask, int *align, int *sz) +{ + const struct { + enum btf_field_type type; + const char *const name; + const bool is_unique; + } field_types[] = { + { BPF_SPIN_LOCK, "bpf_spin_lock", true }, + { BPF_RES_SPIN_LOCK, "bpf_res_spin_lock", true }, + { BPF_TIMER, "bpf_timer", true }, + { BPF_WORKQUEUE, "bpf_wq", true }, + { BPF_TASK_WORK, "bpf_task_work", true }, + { BPF_LIST_HEAD, "bpf_list_head", false }, + { BPF_LIST_NODE, "bpf_list_node", false }, + { BPF_RB_ROOT, "bpf_rb_root", false }, + { BPF_RB_NODE, "bpf_rb_node", false }, + { BPF_REFCOUNT, "bpf_refcount", false }, + }; + int type = 0, i; + const char *name = __btf_name_by_offset(btf, var_type->name_off); + const char *field_type_name; + enum btf_field_type field_type; + bool is_unique; + + for (i = 0; i < ARRAY_SIZE(field_types); ++i) { + field_type = field_types[i].type; + field_type_name = field_types[i].name; + is_unique = field_types[i].is_unique; + if (!(field_mask & field_type) || strcmp(name, field_type_name)) + continue; + if (is_unique) { + if (*seen_mask & field_type) return -E2BIG; - *seen_mask |= BPF_TIMER; - type = BPF_TIMER; - goto end; - } - } - if (field_mask & BPF_LIST_HEAD) { - if (!strcmp(name, "bpf_list_head")) { - type = BPF_LIST_HEAD; - goto end; - } - } - if (field_mask & BPF_LIST_NODE) { - if (!strcmp(name, "bpf_list_node")) { - type = BPF_LIST_NODE; - goto end; + *seen_mask |= field_type; } + type = field_type; + goto end; } + /* Only return BPF_KPTR when all other types with matchable names fail */ - if (field_mask & BPF_KPTR) { + if (field_mask & (BPF_KPTR | BPF_UPTR) && !__btf_type_is_struct(var_type)) { type = BPF_KPTR_REF; goto end; } @@ -3387,126 +3530,242 @@ end: return type; } +/* Repeat a number of fields for a specified number of times. + * + * Copy the fields starting from the first field and repeat them for + * repeat_cnt times. The fields are repeated by adding the offset of each + * field with + * (i + 1) * elem_size + * where i is the repeat index and elem_size is the size of an element. + */ +static int btf_repeat_fields(struct btf_field_info *info, int info_cnt, + u32 field_cnt, u32 repeat_cnt, u32 elem_size) +{ + u32 i, j; + u32 cur; + + /* Ensure not repeating fields that should not be repeated. */ + for (i = 0; i < field_cnt; i++) { + switch (info[i].type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: + case BPF_UPTR: + case BPF_LIST_HEAD: + case BPF_RB_ROOT: + break; + default: + return -EINVAL; + } + } + + /* The type of struct size or variable size is u32, + * so the multiplication will not overflow. + */ + if (field_cnt * (repeat_cnt + 1) > info_cnt) + return -E2BIG; + + cur = field_cnt; + for (i = 0; i < repeat_cnt; i++) { + memcpy(&info[cur], &info[0], field_cnt * sizeof(info[0])); + for (j = 0; j < field_cnt; j++) + info[cur++].off += (i + 1) * elem_size; + } + + return 0; +} + static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, u32 field_mask, - struct btf_field_info *info, int info_cnt) + struct btf_field_info *info, int info_cnt, + u32 level); + +/* Find special fields in the struct type of a field. + * + * This function is used to find fields of special types that is not a + * global variable or a direct field of a struct type. It also handles the + * repetition if it is the element type of an array. + */ +static int btf_find_nested_struct(const struct btf *btf, const struct btf_type *t, + u32 off, u32 nelems, + u32 field_mask, struct btf_field_info *info, + int info_cnt, u32 level) { - int ret, idx = 0, align, sz, field_type; - const struct btf_member *member; + int ret, err, i; + + level++; + if (level >= MAX_RESOLVE_DEPTH) + return -E2BIG; + + ret = btf_find_struct_field(btf, t, field_mask, info, info_cnt, level); + + if (ret <= 0) + return ret; + + /* Shift the offsets of the nested struct fields to the offsets + * related to the container. + */ + for (i = 0; i < ret; i++) + info[i].off += off; + + if (nelems > 1) { + err = btf_repeat_fields(info, info_cnt, ret, nelems - 1, t->size); + if (err == 0) + ret *= nelems; + else + ret = err; + } + + return ret; +} + +static int btf_find_field_one(const struct btf *btf, + const struct btf_type *var, + const struct btf_type *var_type, + int var_idx, + u32 off, u32 expected_size, + u32 field_mask, u32 *seen_mask, + struct btf_field_info *info, int info_cnt, + u32 level) +{ + int ret, align, sz, field_type; struct btf_field_info tmp; + const struct btf_array *array; + u32 i, nelems = 1; + + /* Walk into array types to find the element type and the number of + * elements in the (flattened) array. + */ + for (i = 0; i < MAX_RESOLVE_DEPTH && btf_type_is_array(var_type); i++) { + array = btf_array(var_type); + nelems *= array->nelems; + var_type = btf_type_by_id(btf, array->type); + } + if (i == MAX_RESOLVE_DEPTH) + return -E2BIG; + if (nelems == 0) + return 0; + + field_type = btf_get_field_type(btf, var_type, + field_mask, seen_mask, &align, &sz); + /* Look into variables of struct types */ + if (!field_type && __btf_type_is_struct(var_type)) { + sz = var_type->size; + if (expected_size && expected_size != sz * nelems) + return 0; + ret = btf_find_nested_struct(btf, var_type, off, nelems, field_mask, + &info[0], info_cnt, level); + return ret; + } + + if (field_type == 0) + return 0; + if (field_type < 0) + return field_type; + + if (expected_size && expected_size != sz * nelems) + return 0; + if (off % align) + return 0; + + switch (field_type) { + case BPF_SPIN_LOCK: + case BPF_RES_SPIN_LOCK: + case BPF_TIMER: + case BPF_WORKQUEUE: + case BPF_LIST_NODE: + case BPF_RB_NODE: + case BPF_REFCOUNT: + case BPF_TASK_WORK: + ret = btf_find_struct(btf, var_type, off, sz, field_type, + info_cnt ? &info[0] : &tmp); + if (ret < 0) + return ret; + break; + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: + case BPF_UPTR: + ret = btf_find_kptr(btf, var_type, off, sz, + info_cnt ? &info[0] : &tmp, field_mask); + if (ret < 0) + return ret; + break; + case BPF_LIST_HEAD: + case BPF_RB_ROOT: + ret = btf_find_graph_root(btf, var, var_type, + var_idx, off, sz, + info_cnt ? &info[0] : &tmp, + field_type); + if (ret < 0) + return ret; + break; + default: + return -EFAULT; + } + + if (ret == BTF_FIELD_IGNORE) + return 0; + if (!info_cnt) + return -E2BIG; + if (nelems > 1) { + ret = btf_repeat_fields(info, info_cnt, 1, nelems - 1, sz); + if (ret < 0) + return ret; + } + return nelems; +} + +static int btf_find_struct_field(const struct btf *btf, + const struct btf_type *t, u32 field_mask, + struct btf_field_info *info, int info_cnt, + u32 level) +{ + int ret, idx = 0; + const struct btf_member *member; u32 i, off, seen_mask = 0; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); - field_type = btf_get_field_type(__btf_name_by_offset(btf, member_type->name_off), - field_mask, &seen_mask, &align, &sz); - if (field_type == 0) - continue; - if (field_type < 0) - return field_type; - off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; off /= 8; - if (off % align) - continue; - - switch (field_type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - case BPF_LIST_NODE: - ret = btf_find_struct(btf, member_type, off, sz, field_type, - idx < info_cnt ? &info[idx] : &tmp); - if (ret < 0) - return ret; - break; - case BPF_KPTR_UNREF: - case BPF_KPTR_REF: - ret = btf_find_kptr(btf, member_type, off, sz, - idx < info_cnt ? &info[idx] : &tmp); - if (ret < 0) - return ret; - break; - case BPF_LIST_HEAD: - ret = btf_find_list_head(btf, t, member_type, i, off, sz, - idx < info_cnt ? &info[idx] : &tmp); - if (ret < 0) - return ret; - break; - default: - return -EFAULT; - } - if (ret == BTF_FIELD_IGNORE) - continue; - if (idx >= info_cnt) - return -E2BIG; - ++idx; + ret = btf_find_field_one(btf, t, member_type, i, + off, 0, + field_mask, &seen_mask, + &info[idx], info_cnt - idx, level); + if (ret < 0) + return ret; + idx += ret; } return idx; } static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, u32 field_mask, struct btf_field_info *info, - int info_cnt) + int info_cnt, u32 level) { - int ret, idx = 0, align, sz, field_type; + int ret, idx = 0; const struct btf_var_secinfo *vsi; - struct btf_field_info tmp; u32 i, off, seen_mask = 0; for_each_vsi(i, t, vsi) { const struct btf_type *var = btf_type_by_id(btf, vsi->type); const struct btf_type *var_type = btf_type_by_id(btf, var->type); - field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off), - field_mask, &seen_mask, &align, &sz); - if (field_type == 0) - continue; - if (field_type < 0) - return field_type; - off = vsi->offset; - if (vsi->size != sz) - continue; - if (off % align) - continue; - - switch (field_type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - case BPF_LIST_NODE: - ret = btf_find_struct(btf, var_type, off, sz, field_type, - idx < info_cnt ? &info[idx] : &tmp); - if (ret < 0) - return ret; - break; - case BPF_KPTR_UNREF: - case BPF_KPTR_REF: - ret = btf_find_kptr(btf, var_type, off, sz, - idx < info_cnt ? &info[idx] : &tmp); - if (ret < 0) - return ret; - break; - case BPF_LIST_HEAD: - ret = btf_find_list_head(btf, var, var_type, -1, off, sz, - idx < info_cnt ? &info[idx] : &tmp); - if (ret < 0) - return ret; - break; - default: - return -EFAULT; - } - - if (ret == BTF_FIELD_IGNORE) - continue; - if (idx >= info_cnt) - return -E2BIG; - ++idx; + ret = btf_find_field_one(btf, var, var_type, -1, off, vsi->size, + field_mask, &seen_mask, + &info[idx], info_cnt - idx, + level); + if (ret < 0) + return ret; + idx += ret; } return idx; } @@ -3516,18 +3775,22 @@ static int btf_find_field(const struct btf *btf, const struct btf_type *t, int info_cnt) { if (__btf_type_is_struct(t)) - return btf_find_struct_field(btf, t, field_mask, info, info_cnt); + return btf_find_struct_field(btf, t, field_mask, info, info_cnt, 0); else if (btf_type_is_datasec(t)) - return btf_find_datasec_var(btf, t, field_mask, info, info_cnt); + return btf_find_datasec_var(btf, t, field_mask, info, info_cnt, 0); return -EINVAL; } +/* Callers have to ensure the life cycle of btf if it is program BTF */ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, struct btf_field_info *info) { struct module *mod = NULL; const struct btf_type *t; - struct btf *kernel_btf; + /* If a matching btf type is found in kernel or module BTFs, kptr_ref + * is that BTF, otherwise it's program BTF + */ + struct btf *kptr_btf; int ret; s32 id; @@ -3536,7 +3799,19 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, */ t = btf_type_by_id(btf, info->kptr.type_id); id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), - &kernel_btf); + &kptr_btf); + if (id == -ENOENT) { + /* btf_parse_kptr should only be called w/ btf = program BTF */ + WARN_ON_ONCE(btf_is_kernel(btf)); + + /* Type exists only in program BTF. Assume that it's a MEM_ALLOC + * kptr allocated via bpf_obj_new + */ + field->kptr.dtor = NULL; + id = info->kptr.type_id; + kptr_btf = (struct btf *)btf; + goto found_dtor; + } if (id < 0) return id; @@ -3553,20 +3828,20 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, * can be used as a referenced pointer and be stored in a map at * the same time. */ - dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id); + dtor_btf_id = btf_find_dtor_kfunc(kptr_btf, id); if (dtor_btf_id < 0) { ret = dtor_btf_id; goto end_btf; } - dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id); + dtor_func = btf_type_by_id(kptr_btf, dtor_btf_id); if (!dtor_func) { ret = -ENOENT; goto end_btf; } - if (btf_is_module(kernel_btf)) { - mod = btf_try_get_module(kernel_btf); + if (btf_is_module(kptr_btf)) { + mod = btf_try_get_module(kptr_btf); if (!mod) { ret = -ENXIO; goto end_btf; @@ -3576,7 +3851,7 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, /* We already verified dtor_func to be btf_type_is_func * in register_btf_id_dtor_kfuncs. */ - dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off); + dtor_func_name = __btf_name_by_offset(kptr_btf, dtor_func->name_off); addr = kallsyms_lookup_name(dtor_func_name); if (!addr) { ret = -EINVAL; @@ -3585,32 +3860,37 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, field->kptr.dtor = (void *)addr; } +found_dtor: field->kptr.btf_id = id; - field->kptr.btf = kernel_btf; + field->kptr.btf = kptr_btf; field->kptr.module = mod; return 0; end_mod: module_put(mod); end_btf: - btf_put(kernel_btf); + btf_put(kptr_btf); return ret; } -static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, - struct btf_field_info *info) +static int btf_parse_graph_root(const struct btf *btf, + struct btf_field *field, + struct btf_field_info *info, + const char *node_type_name, + size_t node_type_align) { const struct btf_type *t, *n = NULL; const struct btf_member *member; u32 offset; int i; - t = btf_type_by_id(btf, info->list_head.value_btf_id); + t = btf_type_by_id(btf, info->graph_root.value_btf_id); /* We've already checked that value_btf_id is a struct type. We * just need to figure out the offset of the list_node, and * verify its type. */ for_each_member(i, t, member) { - if (strcmp(info->list_head.node_name, __btf_name_by_offset(btf, member->name_off))) + if (strcmp(info->graph_root.node_name, + __btf_name_by_offset(btf, member->name_off))) continue; /* Invalid BTF, two members with same name */ if (n) @@ -3618,30 +3898,56 @@ static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, n = btf_type_by_id(btf, member->type); if (!__btf_type_is_struct(n)) return -EINVAL; - if (strcmp("bpf_list_node", __btf_name_by_offset(btf, n->name_off))) + if (strcmp(node_type_name, __btf_name_by_offset(btf, n->name_off))) return -EINVAL; offset = __btf_member_bit_offset(n, member); if (offset % 8) return -EINVAL; offset /= 8; - if (offset % __alignof__(struct bpf_list_node)) + if (offset % node_type_align) return -EINVAL; - field->list_head.btf = (struct btf *)btf; - field->list_head.value_btf_id = info->list_head.value_btf_id; - field->list_head.node_offset = offset; + field->graph_root.btf = (struct btf *)btf; + field->graph_root.value_btf_id = info->graph_root.value_btf_id; + field->graph_root.node_offset = offset; } if (!n) return -ENOENT; return 0; } +static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + return btf_parse_graph_root(btf, field, info, "bpf_list_node", + __alignof__(struct bpf_list_node)); +} + +static int btf_parse_rb_root(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + return btf_parse_graph_root(btf, field, info, "bpf_rb_node", + __alignof__(struct bpf_rb_node)); +} + +static int btf_field_cmp(const void *_a, const void *_b, const void *priv) +{ + const struct btf_field *a = (const struct btf_field *)_a; + const struct btf_field *b = (const struct btf_field *)_b; + + if (a->offset < b->offset) + return -1; + else if (a->offset > b->offset) + return 1; + return 0; +} + struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size) { struct btf_field_info info_arr[BTF_FIELDS_MAX]; + u32 next_off = 0, field_type_size; struct btf_record *rec; - u32 next_off = 0; int ret, i, cnt; ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr)); @@ -3654,14 +3960,19 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type /* This needs to be kzalloc to zero out padding and unused fields, see * comment in btf_record_equal. */ - rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN); + rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!rec) return ERR_PTR(-ENOMEM); rec->spin_lock_off = -EINVAL; + rec->res_spin_lock_off = -EINVAL; rec->timer_off = -EINVAL; + rec->wq_off = -EINVAL; + rec->refcount_off = -EINVAL; + rec->task_work_off = -EINVAL; for (i = 0; i < cnt; i++) { - if (info_arr[i].off + btf_field_type_size(info_arr[i].type) > value_size) { + field_type_size = btf_field_type_size(info_arr[i].type); + if (info_arr[i].off + field_type_size > value_size) { WARN_ONCE(1, "verifier bug off %d size %d", info_arr[i].off, value_size); ret = -EFAULT; goto end; @@ -3670,11 +3981,12 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type ret = -EEXIST; goto end; } - next_off = info_arr[i].off + btf_field_type_size(info_arr[i].type); + next_off = info_arr[i].off + field_type_size; rec->field_mask |= info_arr[i].type; rec->fields[i].offset = info_arr[i].off; rec->fields[i].type = info_arr[i].type; + rec->fields[i].size = field_type_size; switch (info_arr[i].type) { case BPF_SPIN_LOCK: @@ -3682,13 +3994,34 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type /* Cache offset for faster lookup at runtime */ rec->spin_lock_off = rec->fields[i].offset; break; + case BPF_RES_SPIN_LOCK: + WARN_ON_ONCE(rec->spin_lock_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->res_spin_lock_off = rec->fields[i].offset; + break; case BPF_TIMER: WARN_ON_ONCE(rec->timer_off >= 0); /* 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_TASK_WORK: + WARN_ON_ONCE(rec->task_work_off >= 0); + rec->task_work_off = rec->fields[i].offset; + break; + case BPF_REFCOUNT: + WARN_ON_ONCE(rec->refcount_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->refcount_off = rec->fields[i].offset; + break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: + case BPF_UPTR: ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]); if (ret < 0) goto end; @@ -3698,7 +4031,13 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_RB_ROOT: + ret = btf_parse_rb_root(btf, &rec->fields[i], &info_arr[i]); + if (ret < 0) + goto end; + break; case BPF_LIST_NODE: + case BPF_RB_NODE: break; default: ret = -EFAULT; @@ -3707,12 +4046,29 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type rec->cnt++; } - /* bpf_list_head requires bpf_spin_lock */ - if (btf_record_has_field(rec, BPF_LIST_HEAD) && rec->spin_lock_off < 0) { + if (rec->spin_lock_off >= 0 && rec->res_spin_lock_off >= 0) { + ret = -EINVAL; + goto end; + } + + /* bpf_{list_head, rb_node} require bpf_spin_lock */ + if ((btf_record_has_field(rec, BPF_LIST_HEAD) || + btf_record_has_field(rec, BPF_RB_ROOT)) && + (rec->spin_lock_off < 0 && rec->res_spin_lock_off < 0)) { ret = -EINVAL; goto end; } + if (rec->refcount_off < 0 && + btf_record_has_field(rec, BPF_LIST_NODE) && + btf_record_has_field(rec, BPF_RB_NODE)) { + ret = -EINVAL; + goto end; + } + + sort_r(rec->fields, rec->cnt, sizeof(struct btf_field), btf_field_cmp, + NULL, rec); + return rec; end: btf_record_free(rec); @@ -3723,118 +4079,90 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) { int i; - /* There are two owning types, kptr_ref and bpf_list_head. The former - * only supports storing kernel types, which can never store references - * to program allocated local types, atleast not yet. Hence we only need - * to ensure that bpf_list_head ownership does not form cycles. + /* There are three types that signify ownership of some other type: + * kptr_ref, bpf_list_head, bpf_rb_root. + * kptr_ref only supports storing kernel types, which can't store + * references to program allocated local types. + * + * Hence we only need to ensure that bpf_{list_head,rb_root} ownership + * does not form cycles. */ - if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_LIST_HEAD)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & (BPF_GRAPH_ROOT | BPF_UPTR))) return 0; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *meta; + const struct btf_type *t; u32 btf_id; - if (!(rec->fields[i].type & BPF_LIST_HEAD)) + if (rec->fields[i].type == BPF_UPTR) { + /* The uptr only supports pinning one page and cannot + * point to a kernel struct + */ + if (btf_is_kernel(rec->fields[i].kptr.btf)) + return -EINVAL; + t = btf_type_by_id(rec->fields[i].kptr.btf, + rec->fields[i].kptr.btf_id); + if (!t->size) + return -EINVAL; + if (t->size > PAGE_SIZE) + return -E2BIG; + continue; + } + + if (!(rec->fields[i].type & BPF_GRAPH_ROOT)) continue; - btf_id = rec->fields[i].list_head.value_btf_id; + btf_id = rec->fields[i].graph_root.value_btf_id; meta = btf_find_struct_meta(btf, btf_id); if (!meta) return -EFAULT; - rec->fields[i].list_head.value_rec = meta->record; + rec->fields[i].graph_root.value_rec = meta->record; - if (!(rec->field_mask & BPF_LIST_NODE)) + /* We need to set value_rec for all root types, but no need + * to check ownership cycle for a type unless it's also a + * node type. + */ + if (!(rec->field_mask & BPF_GRAPH_NODE)) continue; /* We need to ensure ownership acyclicity among all types. The * proper way to do it would be to topologically sort all BTF * IDs based on the ownership edges, since there can be multiple - * bpf_list_head in a type. Instead, we use the following - * reasoning: + * bpf_{list_head,rb_node} in a type. Instead, we use the + * following resaoning: * * - A type can only be owned by another type in user BTF if it - * has a bpf_list_node. + * has a bpf_{list,rb}_node. Let's call these node types. * - A type can only _own_ another type in user BTF if it has a - * bpf_list_head. + * bpf_{list_head,rb_root}. Let's call these root types. * - * We ensure that if a type has both bpf_list_head and - * bpf_list_node, its element types cannot be owning types. + * We ensure that if a type is both a root and node, its + * element types cannot be root types. * * To ensure acyclicity: * - * When A only has bpf_list_head, ownership chain can be: + * When A is an root type but not a node, its ownership + * chain can be: * A -> B -> C * Where: - * - B has both bpf_list_head and bpf_list_node. - * - C only has bpf_list_node. + * - A is an root, e.g. has bpf_rb_root. + * - B is both a root and node, e.g. has bpf_rb_node and + * bpf_list_head. + * - C is only an root, e.g. has bpf_list_node * - * When A has both bpf_list_head and bpf_list_node, some other - * type already owns it in the BTF domain, hence it can not own - * another owning type through any of the bpf_list_head edges. + * When A is both a root and node, some other type already + * owns it in the BTF domain, hence it can not own + * another root type through any of the ownership edges. * A -> B * Where: - * - B only has bpf_list_node. + * - A is both an root and node. + * - B is only an node. */ - if (meta->record->field_mask & BPF_LIST_HEAD) + if (meta->record->field_mask & BPF_GRAPH_ROOT) return -ELOOP; } return 0; } -static int btf_field_offs_cmp(const void *_a, const void *_b, const void *priv) -{ - const u32 a = *(const u32 *)_a; - const u32 b = *(const u32 *)_b; - - if (a < b) - return -1; - else if (a > b) - return 1; - return 0; -} - -static void btf_field_offs_swap(void *_a, void *_b, int size, const void *priv) -{ - struct btf_field_offs *foffs = (void *)priv; - u32 *off_base = foffs->field_off; - u32 *a = _a, *b = _b; - u8 *sz_a, *sz_b; - - sz_a = foffs->field_sz + (a - off_base); - sz_b = foffs->field_sz + (b - off_base); - - swap(*a, *b); - swap(*sz_a, *sz_b); -} - -struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec) -{ - struct btf_field_offs *foffs; - u32 i, *off; - u8 *sz; - - BUILD_BUG_ON(ARRAY_SIZE(foffs->field_off) != ARRAY_SIZE(foffs->field_sz)); - if (IS_ERR_OR_NULL(rec)) - return NULL; - - foffs = kzalloc(sizeof(*foffs), GFP_KERNEL | __GFP_NOWARN); - if (!foffs) - return ERR_PTR(-ENOMEM); - - off = foffs->field_off; - sz = foffs->field_sz; - for (i = 0; i < rec->cnt; i++) { - off[i] = rec->fields[i].offset; - sz[i] = btf_field_type_size(rec->fields[i].type); - } - foffs->cnt = rec->cnt; - - if (foffs->cnt == 1) - return foffs; - sort_r(foffs->field_off, foffs->cnt, sizeof(foffs->field_off[0]), - btf_field_offs_cmp, btf_field_offs_swap, foffs); - return foffs; -} - static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) @@ -3916,7 +4244,7 @@ static void btf_struct_show(const struct btf *btf, const struct btf_type *t, __btf_struct_show(btf, t, type_id, data, bits_offset, show); } -static struct btf_kind_operations struct_ops = { +static const struct btf_kind_operations struct_ops = { .check_meta = btf_struct_check_meta, .resolve = btf_struct_resolve, .check_member = btf_struct_check_member, @@ -4084,7 +4412,7 @@ static void btf_enum_show(const struct btf *btf, const struct btf_type *t, btf_show_end_type(show); } -static struct btf_kind_operations enum_ops = { +static const struct btf_kind_operations enum_ops = { .check_meta = btf_enum_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, @@ -4187,7 +4515,7 @@ static void btf_enum64_show(const struct btf *btf, const struct btf_type *t, btf_show_end_type(show); } -static struct btf_kind_operations enum64_ops = { +static const struct btf_kind_operations enum64_ops = { .check_meta = btf_enum64_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, @@ -4265,7 +4593,7 @@ done: btf_verifier_log(env, ")"); } -static struct btf_kind_operations func_proto_ops = { +static const struct btf_kind_operations func_proto_ops = { .check_meta = btf_func_proto_check_meta, .resolve = btf_df_resolve, /* @@ -4323,7 +4651,7 @@ static int btf_func_resolve(struct btf_verifier_env *env, return 0; } -static struct btf_kind_operations func_ops = { +static const struct btf_kind_operations func_ops = { .check_meta = btf_func_check_meta, .resolve = btf_func_resolve, .check_member = btf_df_check_member, @@ -4357,7 +4685,7 @@ static s32 btf_var_check_meta(struct btf_verifier_env *env, } if (!t->name_off || - !__btf_name_valid(env->btf, t->name_off, true)) { + !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } @@ -4476,6 +4804,7 @@ static int btf_datasec_resolve(struct btf_verifier_env *env, struct btf *btf = env->btf; u16 i; + env->resolve_mode = RESOLVE_TBD; for_each_vsi_from(i, v->next_member, v->t, vsi) { u32 var_type_id = vsi->type, type_id, type_size = 0; const struct btf_type *var_type = btf_type_by_id(env->btf, @@ -4649,11 +4978,6 @@ static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_kflag(t)) { - btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); - return -EINVAL; - } - component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx < -1) { btf_verifier_log_type(env, t, "Invalid component_idx"); @@ -5236,68 +5560,102 @@ static const char *alloc_obj_fields[] = { "bpf_spin_lock", "bpf_list_head", "bpf_list_node", + "bpf_rb_root", + "bpf_rb_node", + "bpf_refcount", }; static struct btf_struct_metas * btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) { - union { - struct btf_id_set set; - struct { - u32 _cnt; - u32 _ids[ARRAY_SIZE(alloc_obj_fields)]; - } _arr; - } aof; struct btf_struct_metas *tab = NULL; + struct btf_id_set *aof; int i, n, id, ret; BUILD_BUG_ON(offsetof(struct btf_id_set, cnt) != 0); BUILD_BUG_ON(sizeof(struct btf_id_set) != sizeof(u32)); - memset(&aof, 0, sizeof(aof)); + aof = kmalloc(sizeof(*aof), GFP_KERNEL | __GFP_NOWARN); + if (!aof) + return ERR_PTR(-ENOMEM); + aof->cnt = 0; + for (i = 0; i < ARRAY_SIZE(alloc_obj_fields); i++) { /* Try to find whether this special type exists in user BTF, and * if so remember its ID so we can easily find it among members * of structs that we iterate in the next loop. */ + struct btf_id_set *new_aof; + id = btf_find_by_name_kind(btf, alloc_obj_fields[i], BTF_KIND_STRUCT); if (id < 0) continue; - aof.set.ids[aof.set.cnt++] = id; + + new_aof = krealloc(aof, struct_size(new_aof, ids, aof->cnt + 1), + GFP_KERNEL | __GFP_NOWARN); + if (!new_aof) { + ret = -ENOMEM; + goto free_aof; + } + aof = new_aof; + aof->ids[aof->cnt++] = id; + } + + n = btf_nr_types(btf); + for (i = 1; i < n; i++) { + /* Try to find if there are kptrs in user BTF and remember their ID */ + struct btf_id_set *new_aof; + struct btf_field_info tmp; + const struct btf_type *t; + + t = btf_type_by_id(btf, i); + if (!t) { + ret = -EINVAL; + goto free_aof; + } + + ret = btf_find_kptr(btf, t, 0, 0, &tmp, BPF_KPTR); + if (ret != BTF_FIELD_FOUND) + continue; + + new_aof = krealloc(aof, struct_size(new_aof, ids, aof->cnt + 1), + GFP_KERNEL | __GFP_NOWARN); + if (!new_aof) { + ret = -ENOMEM; + goto free_aof; + } + aof = new_aof; + aof->ids[aof->cnt++] = i; } - if (!aof.set.cnt) + if (!aof->cnt) { + kfree(aof); return NULL; - sort(&aof.set.ids, aof.set.cnt, sizeof(aof.set.ids[0]), btf_id_cmp_func, NULL); + } + sort(&aof->ids, aof->cnt, sizeof(aof->ids[0]), btf_id_cmp_func, NULL); - n = btf_nr_types(btf); for (i = 1; i < n; i++) { struct btf_struct_metas *new_tab; const struct btf_member *member; - struct btf_field_offs *foffs; struct btf_struct_meta *type; struct btf_record *record; const struct btf_type *t; int j, tab_cnt; t = btf_type_by_id(btf, i); - if (!t) { - ret = -EINVAL; - goto free; - } if (!__btf_type_is_struct(t)) continue; cond_resched(); for_each_member(j, t, member) { - if (btf_id_set_contains(&aof.set, member->type)) + if (btf_id_set_contains(aof, member->type)) goto parse; } continue; parse: tab_cnt = tab ? tab->cnt : 0; - new_tab = krealloc(tab, offsetof(struct btf_struct_metas, types[tab_cnt + 1]), + new_tab = krealloc(tab, struct_size(new_tab, types, tab_cnt + 1), GFP_KERNEL | __GFP_NOWARN); if (!new_tab) { ret = -ENOMEM; @@ -5309,28 +5667,23 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) type = &tab->types[tab->cnt]; type->btf_id = i; - record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size); + record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE | + BPF_RB_ROOT | BPF_RB_NODE | BPF_REFCOUNT | + BPF_KPTR, t->size); /* The record cannot be unset, treat it as an error if so */ if (IS_ERR_OR_NULL(record)) { ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT; goto free; } - foffs = btf_parse_field_offs(record); - /* We need the field_offs to be valid for a valid record, - * either both should be set or both should be unset. - */ - if (IS_ERR_OR_NULL(foffs)) { - btf_record_free(record); - ret = -EFAULT; - goto free; - } type->record = record; - type->field_offs = foffs; tab->cnt++; } + kfree(aof); return tab; free: btf_struct_metas_free(tab); +free_aof: + kfree(aof); return ERR_PTR(ret); } @@ -5392,38 +5745,45 @@ static int btf_check_type_tags(struct btf_verifier_env *env, return 0; } -static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, - u32 log_level, char __user *log_ubuf, u32 log_size) +static int finalize_log(struct bpf_verifier_log *log, bpfptr_t uattr, u32 uattr_size) { + u32 log_true_size; + int err; + + err = bpf_vlog_finalize(log, &log_true_size); + + if (uattr_size >= offsetofend(union bpf_attr, btf_log_true_size) && + copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, btf_log_true_size), + &log_true_size, sizeof(log_true_size))) + err = -EFAULT; + + return err; +} + +static struct btf *btf_parse(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) +{ + bpfptr_t btf_data = make_bpfptr(attr->btf, uattr.is_kernel); + char __user *log_ubuf = u64_to_user_ptr(attr->btf_log_buf); struct btf_struct_metas *struct_meta_tab; struct btf_verifier_env *env = NULL; - struct bpf_verifier_log *log; struct btf *btf = NULL; u8 *data; - int err; + int err, ret; - if (btf_data_size > BTF_MAX_SIZE) + if (attr->btf_size > BTF_MAX_SIZE) return ERR_PTR(-E2BIG); env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); - log = &env->log; - if (log_level || log_ubuf || log_size) { - /* user requested verbose verifier output - * and supplied buffer to store the verification trace - */ - log->level = log_level; - log->ubuf = log_ubuf; - log->len_total = log_size; - - /* log attributes have to be sane */ - if (!bpf_verifier_log_attr_valid(log)) { - err = -EINVAL; - goto errout; - } - } + /* user could have requested verbose verifier output + * and supplied buffer to store the verification trace + */ + err = bpf_vlog_init(&env->log, attr->btf_log_level, + log_ubuf, attr->btf_log_size); + if (err) + goto errout_free; btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); if (!btf) { @@ -5432,16 +5792,16 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, } env->btf = btf; - data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); + data = kvmalloc(attr->btf_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { err = -ENOMEM; goto errout; } btf->data = data; - btf->data_size = btf_data_size; + btf->data_size = attr->btf_size; - if (copy_from_bpfptr(data, btf_data, btf_data_size)) { + if (copy_from_bpfptr(data, btf_data, attr->btf_size)) { err = -EFAULT; goto errout; } @@ -5464,7 +5824,7 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, if (err) goto errout; - struct_meta_tab = btf_parse_struct_metas(log, btf); + struct_meta_tab = btf_parse_struct_metas(&env->log, btf); if (IS_ERR(struct_meta_tab)) { err = PTR_ERR(struct_meta_tab); goto errout; @@ -5481,10 +5841,9 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, } } - if (log->level && bpf_verifier_log_full(log)) { - err = -ENOSPC; - goto errout_meta; - } + err = finalize_log(&env->log, uattr, uattr_size); + if (err) + goto errout_free; btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); @@ -5493,14 +5852,19 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, errout_meta: btf_free_struct_meta_tab(btf); errout: + /* overwrite err with -ENOSPC or -EFAULT */ + ret = finalize_log(&env->log, uattr, uattr_size); + if (ret) + err = ret; +errout_free: btf_verifier_env_free(env); if (btf) btf_free(btf); 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) @@ -5533,22 +5897,70 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -const struct btf_member * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type) { const struct btf_type *conv_struct; - const struct btf_type *ctx_struct; const struct btf_member *ctx_type; - const char *tname, *ctx_tname; conv_struct = bpf_ctx_convert.t; - if (!conv_struct) { - bpf_log(log, "btf_vmlinux is malformed\n"); + if (!conv_struct) return NULL; - } + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct __sk_buff' + */ + return btf_type_by_id(btf_vmlinux, ctx_type->type); +} + +static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) +{ + const struct btf_type *conv_struct; + const struct btf_member *ctx_type; + + conv_struct = bpf_ctx_convert.t; + if (!conv_struct) + return -EFAULT; + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; + /* ctx_type is a pointer to prog_ctx_type in vmlinux. + * Like 'struct sk_buff' + */ + return ctx_type->type; +} + +bool btf_is_projection_of(const char *pname, const char *tname) +{ + if (strcmp(pname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0) + return true; + if (strcmp(pname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0) + return true; + return false; +} + +bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + t = btf_type_by_id(btf, t->type); + + /* KPROBE programs allow bpf_user_pt_regs_t typedef, which we need to + * check before we skip all the typedef below. + */ + if (prog_type == BPF_PROG_TYPE_KPROBE) { + while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) + t = btf_type_by_id(btf, t->type); + + if (btf_type_is_typedef(t)) { + tname = btf_name_by_offset(btf, t->name_off); + if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) + return true; + } + } + while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_struct(t)) { @@ -5557,28 +5969,30 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ - return NULL; + return false; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "arg#%d struct doesn't have a name\n", arg); - return NULL; + return false; } - /* prog_type is valid bpf program type. No need for bounds check. */ - ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; - /* ctx_struct is a pointer to prog_ctx_type in vmlinux. - * Like 'struct __sk_buff' - */ - ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type); - if (!ctx_struct) + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ - return NULL; - ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); + return false; + } +again: + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); - return NULL; + return false; } + /* program types without named context types work only with arg:ctx tag */ + if (ctx_tname[0] == '\0') + return false; /* only compare that prog's ctx type name is the same as * kernel expects. No need to compare field by field. * It's ok for bpf prog to do: @@ -5586,9 +6000,162 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, * int socket_filter_bpf_prog(struct __sk_buff *skb) * { // no fields of skb are ever used } */ - if (strcmp(ctx_tname, tname)) - return NULL; - return ctx_type; + if (btf_is_projection_of(ctx_tname, tname)) + return true; + if (strcmp(ctx_tname, tname)) { + /* bpf_user_pt_regs_t is a typedef, so resolve it to + * underlying struct and check name again + */ + if (!btf_type_is_modifier(ctx_type)) + return false; + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); + goto again; + } + return true; +} + +/* forward declarations for arch-specific underlying types of + * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef + * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still + * works correctly with __builtin_types_compatible_p() on respective + * architectures + */ +struct user_regs_struct; +struct user_pt_regs; + +static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int arg, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + const struct btf_type *ctx_type; + const char *tname, *ctx_tname; + + if (!btf_is_ptr(t)) { + bpf_log(log, "arg#%d type isn't a pointer\n", arg); + return -EINVAL; + } + t = btf_type_by_id(btf, t->type); + + /* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */ + if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) { + while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) + t = btf_type_by_id(btf, t->type); + + if (btf_type_is_typedef(t)) { + tname = btf_name_by_offset(btf, t->name_off); + if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) + return 0; + } + } + + /* all other program types don't use typedefs for context type */ + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + + /* `void *ctx __arg_ctx` is always valid */ + if (btf_type_is_void(t)) + return 0; + + tname = btf_name_by_offset(btf, t->name_off); + if (str_is_empty(tname)) { + bpf_log(log, "arg#%d type doesn't have a name\n", arg); + return -EINVAL; + } + + /* special cases */ + switch (prog_type) { + case BPF_PROG_TYPE_KPROBE: + if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + break; + case BPF_PROG_TYPE_PERF_EVENT: + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) && + __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0) + return 0; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) && + __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0) + return 0; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACING: + switch (attach_type) { + case BPF_TRACE_RAW_TP: + /* tp_btf program is TRACING, so need special case here */ + if (__btf_type_is_struct(t) && + strcmp(tname, "bpf_raw_tracepoint_args") == 0) + return 0; + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_TRACE_ITER: + /* allow struct bpf_iter__xxx types only */ + if (__btf_type_is_struct(t) && + strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0) + return 0; + break; + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + default: + break; + } + break; + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return 0; + break; + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_SYSCALL: + case BPF_PROG_TYPE_EXT: + return 0; /* anything goes */ + default: + break; + } + + ctx_type = find_canonical_prog_ctx_type(prog_type); + if (!ctx_type) { + /* should not happen */ + bpf_log(log, "btf_vmlinux is malformed\n"); + return -EINVAL; + } + + /* resolve typedefs and check that underlying structs are matching as well */ + while (btf_type_is_modifier(ctx_type)) + ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); + + /* if program type doesn't have distinctly named struct type for + * context, then __arg_ctx argument can only be `void *`, which we + * already checked above + */ + if (!__btf_type_is_struct(ctx_type)) { + bpf_log(log, "arg#%d should be void pointer\n", arg); + return -EINVAL; + } + + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); + if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) { + bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname); + return -EINVAL; + } + + return 0; } static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, @@ -5597,13 +6164,9 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, enum bpf_prog_type prog_type, int arg) { - const struct btf_member *prog_ctx_type, *kern_ctx_type; - - prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg); - if (!prog_ctx_type) + if (!btf_is_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; - kern_ctx_type = prog_ctx_type + 1; - return kern_ctx_type->type; + return find_kern_ctx_type_id(prog_type); } int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) @@ -5626,22 +6189,16 @@ int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_ty return kctx_type_id; } -BTF_ID_LIST(bpf_ctx_convert_btf_id) -BTF_ID(struct, bpf_ctx_convert) +BTF_ID_LIST_SINGLE(bpf_ctx_convert_btf_id, struct, bpf_ctx_convert) -struct btf *btf_parse_vmlinux(void) +static struct btf *btf_parse_base(struct btf_verifier_env *env, const char *name, + void *data, unsigned int data_size) { - struct btf_verifier_env *env = NULL; - struct bpf_verifier_log *log; struct btf *btf = NULL; int err; - env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); - if (!env) - return ERR_PTR(-ENOMEM); - - log = &env->log; - log->level = BPF_LOG_KERNEL; + if (!IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) + return ERR_PTR(-ENOENT); btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); if (!btf) { @@ -5650,10 +6207,10 @@ struct btf *btf_parse_vmlinux(void) } env->btf = btf; - btf->data = __start_BTF; - btf->data_size = __stop_BTF - __start_BTF; + btf->data = data; + btf->data_size = data_size; btf->kernel_btf = true; - snprintf(btf->name, sizeof(btf->name), "vmlinux"); + snprintf(btf->name, sizeof(btf->name), "%s", name); err = btf_parse_hdr(env); if (err) @@ -5673,22 +6230,11 @@ struct btf *btf_parse_vmlinux(void) if (err) goto errout; - /* btf_parse_vmlinux() runs under bpf_verifier_lock */ - bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - - bpf_struct_ops_init(btf, log); - refcount_set(&btf->refcnt, 1); - err = btf_alloc_id(btf); - if (err) - goto errout; - - btf_verifier_env_free(env); return btf; errout: - btf_verifier_env_free(env); if (btf) { kvfree(btf->types); kfree(btf); @@ -5696,19 +6242,61 @@ errout: return ERR_PTR(err); } +struct btf *btf_parse_vmlinux(void) +{ + struct btf_verifier_env *env = NULL; + struct bpf_verifier_log *log; + struct btf *btf; + int err; + + env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); + if (!env) + return ERR_PTR(-ENOMEM); + + log = &env->log; + log->level = BPF_LOG_KERNEL; + btf = btf_parse_base(env, "vmlinux", __start_BTF, __stop_BTF - __start_BTF); + if (IS_ERR(btf)) + goto err_out; + + /* btf_parse_vmlinux() runs under bpf_verifier_lock */ + bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); + err = btf_alloc_id(btf); + if (err) { + btf_free(btf); + btf = ERR_PTR(err); + } +err_out: + btf_verifier_env_free(env); + return btf; +} + +/* If .BTF_ids section was created with distilled base BTF, both base and + * split BTF ids will need to be mapped to actual base/split ids for + * BTF now that it has been relocated. + */ +static __u32 btf_relocate_id(const struct btf *btf, __u32 id) +{ + if (!btf->base_btf || !btf->base_id_map) + return id; + return btf->base_id_map[id]; +} + #ifdef CONFIG_DEBUG_INFO_BTF_MODULES -static struct btf *btf_parse_module(const char *module_name, const void *data, unsigned int data_size) +static struct btf *btf_parse_module(const char *module_name, const void *data, + unsigned int data_size, void *base_data, + unsigned int base_data_size) { + struct btf *btf = NULL, *vmlinux_btf, *base_btf = NULL; struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; - struct btf *btf = NULL, *base_btf; - int err; + int err = 0; - base_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(base_btf)) - return base_btf; - if (!base_btf) + vmlinux_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(vmlinux_btf)) + return vmlinux_btf; + if (!vmlinux_btf) return ERR_PTR(-EINVAL); env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); @@ -5718,6 +6306,16 @@ static struct btf *btf_parse_module(const char *module_name, const void *data, u log = &env->log; log->level = BPF_LOG_KERNEL; + if (base_data) { + base_btf = btf_parse_base(env, ".BTF.base", base_data, base_data_size); + if (IS_ERR(base_btf)) { + err = PTR_ERR(base_btf); + goto errout; + } + } else { + base_btf = vmlinux_btf; + } + btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); if (!btf) { err = -ENOMEM; @@ -5731,12 +6329,11 @@ static struct btf *btf_parse_module(const char *module_name, const void *data, u btf->kernel_btf = true; snprintf(btf->name, sizeof(btf->name), "%s", module_name); - btf->data = kvmalloc(data_size, GFP_KERNEL | __GFP_NOWARN); + btf->data = kvmemdup(data, data_size, GFP_KERNEL | __GFP_NOWARN); if (!btf->data) { err = -ENOMEM; goto errout; } - memcpy(btf->data, data, data_size); btf->data_size = data_size; err = btf_parse_hdr(env); @@ -5757,12 +6354,22 @@ static struct btf *btf_parse_module(const char *module_name, const void *data, u if (err) goto errout; + if (base_btf != vmlinux_btf) { + err = btf_relocate(btf, vmlinux_btf, &btf->base_id_map); + if (err) + goto errout; + btf_free(base_btf); + base_btf = vmlinux_btf; + } + btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; errout: btf_verifier_env_free(env); + if (!IS_ERR(base_btf) && base_btf != vmlinux_btf) + btf_free(base_btf); if (btf) { kvfree(btf->data); kvfree(btf->types); @@ -5783,20 +6390,15 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) return prog->aux->attach_btf; } -static bool is_int_ptr(struct btf *btf, const struct btf_type *t) +static bool is_void_or_int_ptr(struct btf *btf, const struct btf_type *t) { - /* t comes in already as a pointer */ - t = btf_type_by_id(btf, t->type); - - /* allow const */ - if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST) - t = btf_type_by_id(btf, t->type); - - return btf_type_is_int(t); + /* skip modifiers */ + t = btf_type_skip_modifiers(btf, t->type, NULL); + return btf_type_is_void(t) || btf_type_is_int(t); } -static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, - int off) +u32 btf_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, + int off) { const struct btf_param *args; const struct btf_type *t; @@ -5839,6 +6441,223 @@ static bool prog_args_trusted(const struct bpf_prog *prog) } } +int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, + u32 arg_no) +{ + const struct btf_param *args; + const struct btf_type *t; + int off = 0, i; + u32 sz; + + args = btf_params(func_proto); + for (i = 0; i < arg_no; i++) { + t = btf_type_by_id(btf, args[i].type); + t = btf_resolve_size(btf, t, &sz); + if (IS_ERR(t)) + return PTR_ERR(t); + off += roundup(sz, 8); + } + + return off; +} + +struct bpf_raw_tp_null_args { + const char *func; + u64 mask; +}; + +static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { + /* sched */ + { "sched_pi_setprio", 0x10 }, + /* ... from sched_numa_pair_template event class */ + { "sched_stick_numa", 0x100 }, + { "sched_swap_numa", 0x100 }, + /* afs */ + { "afs_make_fs_call", 0x10 }, + { "afs_make_fs_calli", 0x10 }, + { "afs_make_fs_call1", 0x10 }, + { "afs_make_fs_call2", 0x10 }, + { "afs_protocol_error", 0x1 }, + { "afs_flock_ev", 0x10 }, + /* cachefiles */ + { "cachefiles_lookup", 0x1 | 0x200 }, + { "cachefiles_unlink", 0x1 }, + { "cachefiles_rename", 0x1 }, + { "cachefiles_prep_read", 0x1 }, + { "cachefiles_mark_active", 0x1 }, + { "cachefiles_mark_failed", 0x1 }, + { "cachefiles_mark_inactive", 0x1 }, + { "cachefiles_vfs_error", 0x1 }, + { "cachefiles_io_error", 0x1 }, + { "cachefiles_ondemand_open", 0x1 }, + { "cachefiles_ondemand_copen", 0x1 }, + { "cachefiles_ondemand_close", 0x1 }, + { "cachefiles_ondemand_read", 0x1 }, + { "cachefiles_ondemand_cread", 0x1 }, + { "cachefiles_ondemand_fd_write", 0x1 }, + { "cachefiles_ondemand_fd_release", 0x1 }, + /* ext4, from ext4__mballoc event class */ + { "ext4_mballoc_discard", 0x10 }, + { "ext4_mballoc_free", 0x10 }, + /* fib */ + { "fib_table_lookup", 0x100 }, + /* filelock */ + /* ... from filelock_lock event class */ + { "posix_lock_inode", 0x10 }, + { "fcntl_setlk", 0x10 }, + { "locks_remove_posix", 0x10 }, + { "flock_lock_inode", 0x10 }, + /* ... from filelock_lease event class */ + { "break_lease_noblock", 0x10 }, + { "break_lease_block", 0x10 }, + { "break_lease_unblock", 0x10 }, + { "generic_delete_lease", 0x10 }, + { "time_out_leases", 0x10 }, + /* host1x */ + { "host1x_cdma_push_gather", 0x10000 }, + /* huge_memory */ + { "mm_khugepaged_scan_pmd", 0x10 }, + { "mm_collapse_huge_page_isolate", 0x1 }, + { "mm_khugepaged_scan_file", 0x10 }, + { "mm_khugepaged_collapse_file", 0x10 }, + /* kmem */ + { "mm_page_alloc", 0x1 }, + { "mm_page_pcpu_drain", 0x1 }, + /* .. from mm_page event class */ + { "mm_page_alloc_zone_locked", 0x1 }, + /* netfs */ + { "netfs_failure", 0x10 }, + /* power */ + { "device_pm_callback_start", 0x10 }, + /* qdisc */ + { "qdisc_dequeue", 0x1000 }, + /* rxrpc */ + { "rxrpc_recvdata", 0x1 }, + { "rxrpc_resend", 0x10 }, + { "rxrpc_tq", 0x10 }, + { "rxrpc_client", 0x1 }, + /* skb */ + {"kfree_skb", 0x1000}, + /* sunrpc */ + { "xs_stream_read_data", 0x1 }, + /* ... from xprt_cong_event event class */ + { "xprt_reserve_cong", 0x10 }, + { "xprt_release_cong", 0x10 }, + { "xprt_get_cong", 0x10 }, + { "xprt_put_cong", 0x10 }, + /* tcp */ + { "tcp_send_reset", 0x11 }, + { "tcp_sendmsg_locked", 0x100 }, + /* tegra_apb_dma */ + { "tegra_dma_tx_status", 0x100 }, + /* timer_migration */ + { "tmigr_update_events", 0x1 }, + /* writeback, from writeback_folio_template event class */ + { "writeback_dirty_folio", 0x10 }, + { "folio_wait_writeback", 0x10 }, + /* rdma */ + { "mr_integ_alloc", 0x2000 }, + /* bpf_testmod */ + { "bpf_testmod_test_read", 0x0 }, + /* amdgpu */ + { "amdgpu_vm_bo_map", 0x1 }, + { "amdgpu_vm_bo_unmap", 0x1 }, + /* netfs */ + { "netfs_folioq", 0x1 }, + /* xfs from xfs_defer_pending_class */ + { "xfs_defer_create_intent", 0x1 }, + { "xfs_defer_cancel_list", 0x1 }, + { "xfs_defer_pending_finish", 0x1 }, + { "xfs_defer_pending_abort", 0x1 }, + { "xfs_defer_relog_intent", 0x1 }, + { "xfs_defer_isolate_paused", 0x1 }, + { "xfs_defer_item_pause", 0x1 }, + { "xfs_defer_item_unpause", 0x1 }, + /* xfs from xfs_defer_pending_item_class */ + { "xfs_defer_add_item", 0x1 }, + { "xfs_defer_cancel_item", 0x1 }, + { "xfs_defer_finish_item", 0x1 }, + /* xfs from xfs_icwalk_class */ + { "xfs_ioc_free_eofblocks", 0x10 }, + { "xfs_blockgc_free_space", 0x10 }, + /* xfs from xfs_btree_cur_class */ + { "xfs_btree_updkeys", 0x100 }, + { "xfs_btree_overlapped_query_range", 0x100 }, + /* xfs from xfs_imap_class*/ + { "xfs_map_blocks_found", 0x10000 }, + { "xfs_map_blocks_alloc", 0x10000 }, + { "xfs_iomap_alloc", 0x1000 }, + { "xfs_iomap_found", 0x1000 }, + /* xfs from xfs_fs_class */ + { "xfs_inodegc_flush", 0x1 }, + { "xfs_inodegc_push", 0x1 }, + { "xfs_inodegc_start", 0x1 }, + { "xfs_inodegc_stop", 0x1 }, + { "xfs_inodegc_queue", 0x1 }, + { "xfs_inodegc_throttle", 0x1 }, + { "xfs_fs_sync_fs", 0x1 }, + { "xfs_blockgc_start", 0x1 }, + { "xfs_blockgc_stop", 0x1 }, + { "xfs_blockgc_worker", 0x1 }, + { "xfs_blockgc_flush_all", 0x1 }, + /* xfs_scrub */ + { "xchk_nlinks_live_update", 0x10 }, + /* xfs_scrub from xchk_metapath_class */ + { "xchk_metapath_lookup", 0x100 }, + /* nfsd */ + { "nfsd_dirent", 0x1 }, + { "nfsd_file_acquire", 0x1001 }, + { "nfsd_file_insert_err", 0x1 }, + { "nfsd_file_cons_err", 0x1 }, + /* nfs4 */ + { "nfs4_setup_sequence", 0x1 }, + { "pnfs_update_layout", 0x10000 }, + { "nfs4_inode_callback_event", 0x200 }, + { "nfs4_inode_stateid_callback_event", 0x200 }, + /* nfs from pnfs_layout_event */ + { "pnfs_mds_fallback_pg_init_read", 0x10000 }, + { "pnfs_mds_fallback_pg_init_write", 0x10000 }, + { "pnfs_mds_fallback_pg_get_mirror_count", 0x10000 }, + { "pnfs_mds_fallback_read_done", 0x10000 }, + { "pnfs_mds_fallback_write_done", 0x10000 }, + { "pnfs_mds_fallback_read_pagelist", 0x10000 }, + { "pnfs_mds_fallback_write_pagelist", 0x10000 }, + /* coda */ + { "coda_dec_pic_run", 0x10 }, + { "coda_dec_pic_done", 0x10 }, + /* cfg80211 */ + { "cfg80211_scan_done", 0x11 }, + { "rdev_set_coalesce", 0x10 }, + { "cfg80211_report_wowlan_wakeup", 0x100 }, + { "cfg80211_inform_bss_frame", 0x100 }, + { "cfg80211_michael_mic_failure", 0x10000 }, + /* cfg80211 from wiphy_work_event */ + { "wiphy_work_queue", 0x10 }, + { "wiphy_work_run", 0x10 }, + { "wiphy_work_cancel", 0x10 }, + { "wiphy_work_flush", 0x10 }, + /* hugetlbfs */ + { "hugetlbfs_alloc_inode", 0x10 }, + /* spufs */ + { "spufs_context", 0x10 }, + /* kvm_hv */ + { "kvm_page_fault_enter", 0x100 }, + /* dpu */ + { "dpu_crtc_setup_mixer", 0x100 }, + /* binder */ + { "binder_transaction", 0x100 }, + /* bcachefs */ + { "btree_path_free", 0x100 }, + /* hfi1_tx */ + { "hfi1_sdma_progress", 0x1000 }, + /* iptfs */ + { "iptfs_ingress_postq_event", 0x1000 }, + /* neigh */ + { "neigh_update", 0x10 }, + /* snd_firewire_lib */ + { "amdtp_packet", 0x100 }, +}; + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -5849,6 +6668,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; + bool ptr_err_raw_tp = false; const char *tag_value; u32 nr_args, arg; int i, ret; @@ -5858,7 +6678,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, tname, off); return false; } - arg = get_ctx_arg_idx(btf, t, off); + arg = btf_ctx_arg_idx(btf, t, off); args = (const struct btf_param *)(t + 1); /* if (t == NULL) Fall back to default BPF prog with * MAX_BPF_FUNC_REG_ARGS u64 arguments. @@ -5878,8 +6698,11 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (arg == nr_args) { switch (prog->expected_attach_type) { - case BPF_LSM_CGROUP: case BPF_LSM_MAC: + /* mark we are accessing the return value */ + info->is_retval = true; + fallthrough; + case BPF_LSM_CGROUP: case BPF_TRACE_FEXIT: /* When LSM programs are attached to void LSM hooks * they use FEXIT trampolines and when attached to @@ -5928,7 +6751,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_small_int(t) || btf_is_any_enum(t) || __btf_type_is_struct(t)) + if (btf_type_is_small_int(t) || btf_is_any_enum(t) || btf_type_is_struct(t)) /* accessing a scalar */ return true; if (!btf_type_is_ptr(t)) { @@ -5940,6 +6763,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return false; } + if (size != sizeof(u64)) { + bpf_log(log, "func '%s' size %d must be 8\n", + tname, size); + return false; + } + /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; @@ -5954,14 +6783,11 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } } - if (t->type == 0) - /* This is a pointer to void. - * It is the same as scalar from the verifier safety pov. - * No further pointer walking is allowed. - */ - return true; - - if (is_int_ptr(btf, t)) + /* + * If it's a pointer to void, it's the same as scalar from the verifier + * safety POV. Either way, no futher pointer walking is allowed. + */ + if (is_void_or_int_ptr(btf, t)) return true; /* this is a pointer to another type */ @@ -5975,8 +6801,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } info->reg_type = ctx_arg_info->reg_type; - info->btf = btf_vmlinux; + info->btf = ctx_arg_info->btf ? : btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; + info->ref_obj_id = ctx_arg_info->ref_obj_id; return true; } } @@ -5985,6 +6812,42 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (prog_args_trusted(prog)) info->reg_type |= PTR_TRUSTED; + if (btf_param_match_suffix(btf, &args[arg], "__nullable")) + info->reg_type |= PTR_MAYBE_NULL; + + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { + struct btf *btf = prog->aux->attach_btf; + const struct btf_type *t; + const char *tname; + + /* BTF lookups cannot fail, return false on error */ + t = btf_type_by_id(btf, prog->aux->attach_btf_id); + if (!t) + return false; + tname = btf_name_by_offset(btf, t->name_off); + if (!tname) + return false; + /* Checked by bpf_check_attach_target */ + tname += sizeof("btf_trace_") - 1; + for (i = 0; i < ARRAY_SIZE(raw_tp_null_args); i++) { + /* Is this a func with potential NULL args? */ + if (strcmp(tname, raw_tp_null_args[i].func)) + continue; + if (raw_tp_null_args[i].mask & (0x1ULL << (arg * 4))) + info->reg_type |= PTR_MAYBE_NULL; + /* Is the current arg IS_ERR? */ + if (raw_tp_null_args[i].mask & (0x2ULL << (arg * 4))) + ptr_err_raw_tp = true; + break; + } + /* If we don't know NULL-ness specification and the tracepoint + * is coming from a loadable module, be conservative and mark + * argument as PTR_MAYBE_NULL. + */ + if (i == ARRAY_SIZE(raw_tp_null_args) && btf_is_module(btf)) + info->reg_type |= PTR_MAYBE_NULL; + } + if (tgt_prog) { enum bpf_prog_type tgt_type; @@ -6007,7 +6870,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, info->btf_id = t->type; t = btf_type_by_id(btf, t->type); - if (btf_type_is_type_tag(t)) { + if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); if (strcmp(tag_value, "user") == 0) info->reg_type |= MEM_USER; @@ -6029,19 +6892,31 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + + /* Perform all checks on the validity of type for this argument, but if + * we know it can be IS_ERR at runtime, scrub pointer type and mark as + * scalar. + */ + if (ptr_err_raw_tp) { + bpf_log(log, "marking pointer arg%d as scalar as it may encode error", arg); + info->reg_type = SCALAR_VALUE; + } return true; } +EXPORT_SYMBOL_GPL(btf_ctx_access); enum bpf_struct_walk_result { /* < 0 error */ WALK_SCALAR = 0, WALK_PTR, + WALK_PTR_UNTRUSTED, WALK_STRUCT, }; static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, - u32 *next_btf_id, enum bpf_type_flag *flag) + u32 *next_btf_id, enum bpf_type_flag *flag, + const char **field_name) { u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; const struct btf_type *mtype, *elem_type = NULL; @@ -6050,6 +6925,8 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, u32 vlen, elem_id, mid; again: + if (btf_type_is_modifier(t)) + t = btf_type_skip_modifiers(btf, t->type, NULL); tname = __btf_name_by_offset(btf, t->name_off); if (!btf_type_is_struct(t)) { bpf_log(log, "Type '%s' is not a struct\n", tname); @@ -6057,6 +6934,14 @@ again: } vlen = btf_type_vlen(t); + if (BTF_INFO_KIND(t->info) == BTF_KIND_UNION && vlen != 1 && !(*flag & PTR_UNTRUSTED)) + /* + * walking unions yields untrusted pointers + * with exception of __bpf_md_ptr and other + * unions with a single member + */ + *flag |= PTR_UNTRUSTED; + if (off + size > t->size) { /* If the last element is a variable size array, we may * need to relax the rule. @@ -6080,11 +6965,13 @@ again: if (off < moff) goto error; - /* Only allow structure for now, can be relaxed for - * other types later. - */ + /* allow structure and integer */ t = btf_type_skip_modifiers(btf, array_elem->type, NULL); + + if (btf_type_is_int(t)) + return WALK_SCALAR; + if (!btf_type_is_struct(t)) goto error; @@ -6243,7 +7130,7 @@ error: /* check type tag */ t = btf_type_by_id(btf, mtype->type); - if (btf_type_is_type_tag(t)) { + if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); /* check __user tag */ if (strcmp(tag_value, "user") == 0) @@ -6259,9 +7146,13 @@ error: stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; - *flag = tmp_flag; + *flag |= tmp_flag; + if (field_name) + *field_name = mname; return WALK_PTR; } + + return WALK_PTR_UNTRUSTED; } /* Allow more flexible access within an int as long as @@ -6270,7 +7161,7 @@ error: * that also allows using an array of int as a scratch * space. e.g. skb->cb[]. */ - if (off + size > mtrue_end) { + if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) { bpf_log(log, "access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n", mname, mtrue_end, tname, off, size); @@ -6286,7 +7177,8 @@ error: int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype __maybe_unused, - u32 *next_btf_id, enum bpf_type_flag *flag) + u32 *next_btf_id, enum bpf_type_flag *flag, + const char **field_name) { const struct btf *btf = reg->btf; enum bpf_type_flag tmp_flag = 0; @@ -6306,7 +7198,7 @@ int btf_struct_access(struct bpf_verifier_log *log, for (i = 0; i < rec->cnt; i++) { struct btf_field *field = &rec->fields[i]; u32 offset = field->offset; - if (off < offset + btf_field_type_size(field->type) && offset < off + size) { + if (off < offset + field->size && offset < off + size) { bpf_log(log, "direct access to %s is disallowed\n", btf_field_type_name(field->type)); @@ -6318,7 +7210,7 @@ int btf_struct_access(struct bpf_verifier_log *log, t = btf_type_by_id(btf, id); do { - err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); + err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag, field_name); switch (err) { case WALK_PTR: @@ -6333,6 +7225,9 @@ int btf_struct_access(struct bpf_verifier_log *log, *next_btf_id = id; *flag = tmp_flag; return PTR_TO_BTF_ID; + case WALK_PTR_UNTRUSTED: + *flag = MEM_RDONLY | PTR_UNTRUSTED; + return PTR_TO_MEM; case WALK_SCALAR: return SCALAR_VALUE; case WALK_STRUCT: @@ -6377,7 +7272,7 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log, bool strict) { const struct btf_type *type; - enum bpf_type_flag flag; + enum bpf_type_flag flag = 0; int err; /* Are we already done? */ @@ -6393,7 +7288,7 @@ again: type = btf_type_by_id(btf, id); if (!type) return false; - err = btf_struct_walk(log, btf, type, off, 1, &id, &flag); + err = btf_struct_walk(log, btf, type, off, 1, &id, &flag, NULL); if (err != WALK_STRUCT) return false; @@ -6428,11 +7323,23 @@ static int __get_type_size(struct btf *btf, u32 btf_id, if (btf_type_is_ptr(t)) /* kernel size of pointer. Not BPF's size of pointer*/ return sizeof(void *); - if (btf_type_is_int(t) || btf_is_any_enum(t) || __btf_type_is_struct(t)) + if (btf_type_is_int(t) || btf_is_any_enum(t) || btf_type_is_struct(t)) return t->size; return -EINVAL; } +static u8 __get_type_fmodel_flags(const struct btf_type *t) +{ + u8 flags = 0; + + if (btf_type_is_struct(t)) + flags |= BTF_FMODEL_STRUCT_ARG; + if (btf_type_is_signed_int(t)) + flags |= BTF_FMODEL_SIGNED_ARG; + + return flags; +} + int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func, @@ -6453,6 +7360,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->arg_flags[i] = 0; } m->ret_size = 8; + m->ret_flags = 0; m->nr_args = MAX_BPF_FUNC_REG_ARGS; return 0; } @@ -6465,13 +7373,14 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return -EINVAL; } ret = __get_type_size(btf, func->type, &t); - if (ret < 0 || __btf_type_is_struct(t)) { + if (ret < 0 || btf_type_is_struct(t)) { bpf_log(log, "The function %s return type %s is unsupported.\n", tname, btf_type_str(t)); return -EINVAL; } m->ret_size = ret; + m->ret_flags = __get_type_fmodel_flags(t); for (i = 0; i < nargs; i++) { if (i == nargs - 1 && args[i].type == 0) { @@ -6496,7 +7405,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return -EINVAL; } m->arg_size[i] = ret; - m->arg_flags[i] = __btf_type_is_struct(t) ? BTF_FMODEL_STRUCT_ARG : 0; + m->arg_flags[i] = __get_type_fmodel_flags(t); } m->nr_args = nargs; return 0; @@ -6644,222 +7553,140 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr return btf_check_func_type_match(log, btf1, t1, btf2, t2); } -static int btf_check_func_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - bool ptr_to_mem_ok, - bool processing_call) +static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) { - enum bpf_prog_type prog_type = resolve_prog_type(env->prog); - struct bpf_verifier_log *log = &env->log; - const char *func_name, *ref_tname; - const struct btf_type *t, *ref_t; - const struct btf_param *args; - u32 i, nargs, ref_id; - int ret; - - t = btf_type_by_id(btf, func_id); - if (!t || !btf_type_is_func(t)) { - /* These checks were already done by the verifier while loading - * struct bpf_func_info or in add_kfunc_call(). - */ - bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n", - func_id); - return -EFAULT; - } - func_name = btf_name_by_offset(btf, t->name_off); - - t = btf_type_by_id(btf, t->type); - if (!t || !btf_type_is_func_proto(t)) { - bpf_log(log, "Invalid BTF of func %s\n", func_name); - return -EFAULT; - } - args = (const struct btf_param *)(t + 1); - nargs = btf_type_vlen(t); - if (nargs > MAX_BPF_FUNC_REG_ARGS) { - bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs, - MAX_BPF_FUNC_REG_ARGS); - return -EINVAL; - } - - /* check that BTF function arguments match actual types that the - * verifier sees. - */ - for (i = 0; i < nargs; i++) { - enum bpf_arg_type arg_type = ARG_DONTCARE; - u32 regno = i + 1; - struct bpf_reg_state *reg = ®s[regno]; - - t = btf_type_skip_modifiers(btf, args[i].type, NULL); - if (btf_type_is_scalar(t)) { - if (reg->type == SCALAR_VALUE) - continue; - bpf_log(log, "R%d is not a scalar\n", regno); - return -EINVAL; - } - - if (!btf_type_is_ptr(t)) { - bpf_log(log, "Unrecognized arg#%d type %s\n", - i, btf_type_str(t)); - return -EINVAL; - } - - ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); - ref_tname = btf_name_by_offset(btf, ref_t->name_off); - - ret = check_func_arg_reg_off(env, reg, regno, arg_type); - if (ret < 0) - return ret; + const char *name; - if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { - /* If function expects ctx type in BTF check that caller - * is passing PTR_TO_CTX. - */ - if (reg->type != PTR_TO_CTX) { - bpf_log(log, - "arg#%d expected pointer to ctx, but got %s\n", - i, btf_type_str(t)); - return -EINVAL; - } - } else if (ptr_to_mem_ok && processing_call) { - const struct btf_type *resolve_ret; - u32 type_size; + t = btf_type_by_id(btf, t->type); /* skip PTR */ - resolve_ret = btf_resolve_size(btf, ref_t, &type_size); - if (IS_ERR(resolve_ret)) { - bpf_log(log, - "arg#%d reference type('%s %s') size cannot be determined: %ld\n", - i, btf_type_str(ref_t), ref_tname, - PTR_ERR(resolve_ret)); - return -EINVAL; - } + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); - if (check_mem_reg(env, reg, regno, type_size)) - return -EINVAL; - } else { - bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i, - func_name, func_id); - return -EINVAL; - } + /* allow either struct or struct forward declaration */ + if (btf_type_is_struct(t) || + (btf_type_is_fwd(t) && btf_type_kflag(t) == 0)) { + name = btf_str_by_offset(btf, t->name_off); + return name && strcmp(name, "bpf_dynptr") == 0; } - return 0; + return false; } -/* Compare BTF of a function declaration with given bpf_reg_state. - * Returns: - * EFAULT - there is a verifier bug. Abort verification. - * EINVAL - there is a type mismatch or BTF is not available. - * 0 - BTF matches with what bpf_reg_state expects. - * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. - */ -int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) -{ - struct bpf_prog *prog = env->prog; - struct btf *btf = prog->aux->btf; - bool is_global; - u32 btf_id; - int err; - - if (!prog->aux->func_info) - return -EINVAL; - - btf_id = prog->aux->func_info[subprog].type_id; - if (!btf_id) - return -EFAULT; - - if (prog->aux->func_info_aux[subprog].unreliable) - return -EINVAL; +struct bpf_cand_cache { + const char *name; + u32 name_len; + u16 kind; + u16 cnt; + struct { + const struct btf *btf; + u32 id; + } cands[]; +}; - is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false); +static DEFINE_MUTEX(cand_cache_mutex); - /* Compiler optimizations can remove arguments from static functions - * or mismatched type can be passed into a global function. - * In such cases mark the function as unreliable from BTF point of view. - */ - if (err) - prog->aux->func_info_aux[subprog].unreliable = true; - return err; -} +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id); -/* Compare BTF of a function call with given bpf_reg_state. - * Returns: - * EFAULT - there is a verifier bug. Abort verification. - * EINVAL - there is a type mismatch or BTF is not available. - * 0 - BTF matches with what bpf_reg_state expects. - * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. - * - * NOTE: the code is duplicated from btf_check_subprog_arg_match() - * because btf_check_func_arg_match() is still doing both. Once that - * function is split in 2, we can call from here btf_check_subprog_arg_match() - * first, and then treat the calling part in a new code path. - */ -int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) +static int btf_get_ptr_to_btf_id(struct bpf_verifier_log *log, int arg_idx, + const struct btf *btf, const struct btf_type *t) { - struct bpf_prog *prog = env->prog; - struct btf *btf = prog->aux->btf; - bool is_global; - u32 btf_id; - int err; - - if (!prog->aux->func_info) - return -EINVAL; - - btf_id = prog->aux->func_info[subprog].type_id; - if (!btf_id) - return -EFAULT; - - if (prog->aux->func_info_aux[subprog].unreliable) - return -EINVAL; + struct bpf_cand_cache *cc; + struct bpf_core_ctx ctx = { + .btf = btf, + .log = log, + }; + u32 kern_type_id, type_id; + int err = 0; - is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true); + /* skip PTR and modifiers */ + type_id = t->type; + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) { + type_id = t->type; + t = btf_type_by_id(btf, t->type); + } - /* Compiler optimizations can remove arguments from static functions - * or mismatched type can be passed into a global function. - * In such cases mark the function as unreliable from BTF point of view. - */ + mutex_lock(&cand_cache_mutex); + cc = bpf_core_find_cands(&ctx, type_id); + if (IS_ERR(cc)) { + err = PTR_ERR(cc); + bpf_log(log, "arg#%d reference type('%s %s') candidate matching error: %d\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + err); + goto cand_cache_unlock; + } + if (cc->cnt != 1) { + bpf_log(log, "arg#%d reference type('%s %s') %s\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + cc->cnt == 0 ? "has no matches" : "is ambiguous"); + err = cc->cnt == 0 ? -ENOENT : -ESRCH; + goto cand_cache_unlock; + } + if (btf_is_module(cc->cands[0].btf)) { + bpf_log(log, "arg#%d reference type('%s %s') points to kernel module type (unsupported)\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + err = -EOPNOTSUPP; + goto cand_cache_unlock; + } + kern_type_id = cc->cands[0].id; + +cand_cache_unlock: + mutex_unlock(&cand_cache_mutex); if (err) - prog->aux->func_info_aux[subprog].unreliable = true; - return err; + return err; + + return kern_type_id; } -/* Convert BTF of a function into bpf_reg_state if possible +enum btf_arg_tag { + ARG_TAG_CTX = BIT_ULL(0), + ARG_TAG_NONNULL = BIT_ULL(1), + ARG_TAG_TRUSTED = BIT_ULL(2), + ARG_TAG_UNTRUSTED = BIT_ULL(3), + ARG_TAG_NULLABLE = BIT_ULL(4), + ARG_TAG_ARENA = BIT_ULL(5), +}; + +/* Process BTF of a function to produce high-level expectation of function + * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information + * is cached in subprog info for reuse. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - cannot convert BTF. - * 0 - Successfully converted BTF into bpf_reg_state - * (either PTR_TO_CTX or SCALAR_VALUE). + * 0 - Successfully processed BTF and constructed argument expectations. */ -int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) { + bool is_global = subprog_aux(env, subprog)->linkage == BTF_FUNC_GLOBAL; + struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; enum bpf_prog_type prog_type = prog->type; struct btf *btf = prog->aux->btf; const struct btf_param *args; - const struct btf_type *t, *ref_t; + const struct btf_type *t, *ref_t, *fn_t; u32 i, nargs, btf_id; const char *tname; - if (!prog->aux->func_info || - prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) { - bpf_log(log, "Verifier bug\n"); + if (sub->args_cached) + return 0; + + if (!prog->aux->func_info) { + verifier_bug(env, "func_info undefined"); return -EFAULT; } btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) { + if (!is_global) /* not fatal for static funcs */ + return -EINVAL; bpf_log(log, "Global functions need valid BTF\n"); return -EFAULT; } - t = btf_type_by_id(btf, btf_id); - if (!t || !btf_type_is_func(t)) { + fn_t = btf_type_by_id(btf, btf_id); + if (!fn_t || !btf_type_is_func(fn_t)) { /* These checks were already done by the verifier while loading * struct bpf_func_info */ @@ -6867,20 +7694,16 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, subprog); return -EFAULT; } - tname = btf_name_by_offset(btf, t->name_off); - - if (log->level & BPF_LOG_LEVEL) - bpf_log(log, "Validating %s() func#%d...\n", - tname, subprog); + tname = btf_name_by_offset(btf, fn_t->name_off); if (prog->aux->func_info_aux[subprog].unreliable) { - bpf_log(log, "Verifier bug in function %s()\n", tname); + verifier_bug(env, "unreliable BTF for function %s()", tname); return -EFAULT; } if (prog_type == BPF_PROG_TYPE_EXT) prog_type = prog->aux->dst_prog->type; - t = btf_type_by_id(btf, t->type); + t = btf_type_by_id(btf, fn_t->type); if (!t || !btf_type_is_func_proto(t)) { bpf_log(log, "Invalid type of function %s()\n", tname); return -EFAULT; @@ -6888,15 +7711,19 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() with %d > %d args. Buggy compiler.\n", tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } - /* check that function returns int */ + /* check that function returns int, exception cb also requires this */ t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_int(t) && !btf_is_any_enum(t)) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() doesn't return scalar. Only those are supported.\n", tname); @@ -6906,41 +7733,171 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { - struct bpf_reg_state *reg = ®s[i + 1]; + u32 tags = 0; + int id = 0; + + /* 'arg:<tag>' decl_tag takes precedence over derivation of + * register type from BTF type itself + */ + while ((id = btf_find_next_decl_tag(btf, fn_t, i, "arg:", id)) > 0) { + const struct btf_type *tag_t = btf_type_by_id(btf, id); + const char *tag = __btf_name_by_offset(btf, tag_t->name_off) + 4; + + /* disallow arg tags in static subprogs */ + if (!is_global) { + bpf_log(log, "arg#%d type tag is not supported in static functions\n", i); + return -EOPNOTSUPP; + } + + if (strcmp(tag, "ctx") == 0) { + tags |= ARG_TAG_CTX; + } else if (strcmp(tag, "trusted") == 0) { + tags |= ARG_TAG_TRUSTED; + } else if (strcmp(tag, "untrusted") == 0) { + tags |= ARG_TAG_UNTRUSTED; + } else if (strcmp(tag, "nonnull") == 0) { + tags |= ARG_TAG_NONNULL; + } else if (strcmp(tag, "nullable") == 0) { + tags |= ARG_TAG_NULLABLE; + } else if (strcmp(tag, "arena") == 0) { + tags |= ARG_TAG_ARENA; + } else { + bpf_log(log, "arg#%d has unsupported set of tags\n", i); + return -EOPNOTSUPP; + } + } + if (id != -ENOENT) { + bpf_log(log, "arg#%d type tag fetching failure: %d\n", i, id); + return id; + } t = btf_type_by_id(btf, args[i].type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t) || btf_is_any_enum(t)) { - reg->type = SCALAR_VALUE; + if (!btf_type_is_ptr(t)) + goto skip_pointer; + + if ((tags & ARG_TAG_CTX) || btf_is_prog_ctx_type(log, btf, t, prog_type, i)) { + if (tags & ~ARG_TAG_CTX) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + if ((tags & ARG_TAG_CTX) && + btf_validate_prog_ctx_type(log, btf, t, i, prog_type, + prog->expected_attach_type)) + return -EINVAL; + sub->args[i].arg_type = ARG_PTR_TO_CTX; + continue; + } + if (btf_is_dynptr_ptr(btf, t)) { + if (tags) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY; + continue; + } + if (tags & ARG_TAG_TRUSTED) { + int kern_type_id; + + if (tags & ARG_TAG_NONNULL) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + + kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t); + if (kern_type_id < 0) + return kern_type_id; + + sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_TRUSTED; + if (tags & ARG_TAG_NULLABLE) + sub->args[i].arg_type |= PTR_MAYBE_NULL; + sub->args[i].btf_id = kern_type_id; continue; } - if (btf_type_is_ptr(t)) { - if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { - reg->type = PTR_TO_CTX; + if (tags & ARG_TAG_UNTRUSTED) { + struct btf *vmlinux_btf; + int kern_type_id; + + if (tags & ~ARG_TAG_UNTRUSTED) { + bpf_log(log, "arg#%d untrusted cannot be combined with any other tags\n", i); + return -EINVAL; + } + + ref_t = btf_type_skip_modifiers(btf, t->type, NULL); + if (btf_type_is_void(ref_t) || btf_type_is_primitive(ref_t)) { + sub->args[i].arg_type = ARG_PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED; + sub->args[i].mem_size = 0; continue; } - t = btf_type_skip_modifiers(btf, t->type, NULL); + kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t); + if (kern_type_id < 0) + return kern_type_id; + + vmlinux_btf = bpf_get_btf_vmlinux(); + ref_t = btf_type_by_id(vmlinux_btf, kern_type_id); + if (!btf_type_is_struct(ref_t)) { + tname = __btf_name_by_offset(vmlinux_btf, t->name_off); + bpf_log(log, "arg#%d has type %s '%s', but only struct or primitive types are allowed\n", + i, btf_type_str(ref_t), tname); + return -EINVAL; + } + sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_UNTRUSTED; + sub->args[i].btf_id = kern_type_id; + continue; + } + if (tags & ARG_TAG_ARENA) { + if (tags & ~ARG_TAG_ARENA) { + bpf_log(log, "arg#%d arena cannot be combined with any other tags\n", i); + return -EINVAL; + } + sub->args[i].arg_type = ARG_PTR_TO_ARENA; + continue; + } + if (is_global) { /* generic user data pointer */ + u32 mem_size; - ref_t = btf_resolve_size(btf, t, ®->mem_size); + if (tags & ARG_TAG_NULLABLE) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + + t = btf_type_skip_modifiers(btf, t->type, NULL); + ref_t = btf_resolve_size(btf, t, &mem_size); if (IS_ERR(ref_t)) { - bpf_log(log, - "arg#%d reference type('%s %s') size cannot be determined: %ld\n", - i, btf_type_str(t), btf_name_by_offset(btf, t->name_off), + bpf_log(log, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", + i, btf_type_str(t), btf_name_by_offset(btf, t->name_off), PTR_ERR(ref_t)); return -EINVAL; } - reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; - reg->id = ++env->id_gen; + sub->args[i].arg_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL; + if (tags & ARG_TAG_NONNULL) + sub->args[i].arg_type &= ~PTR_MAYBE_NULL; + sub->args[i].mem_size = mem_size; + continue; + } +skip_pointer: + if (tags) { + bpf_log(log, "arg#%d has pointer tag, but is not a pointer type\n", i); + return -EINVAL; + } + if (btf_type_is_int(t) || btf_is_any_enum(t)) { + sub->args[i].arg_type = ARG_ANYTHING; continue; } + if (!is_global) + return -EINVAL; bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; } + + sub->arg_cnt = nargs; + sub->args_cached = true; + return 0; } @@ -6956,8 +7913,8 @@ static void btf_type_show(const struct btf *btf, u32 type_id, void *obj, btf_type_ops(t)->show(btf, t, type_id, obj, 0, show); } -static void btf_seq_show(struct btf_show *show, const char *fmt, - va_list args) +__printf(2, 0) static void btf_seq_show(struct btf_show *show, const char *fmt, + va_list args) { seq_vprintf((struct seq_file *)show->target, fmt, args); } @@ -6990,8 +7947,8 @@ struct btf_show_snprintf { int len; /* length we would have written */ }; -static void btf_snprintf_show(struct btf_show *show, const char *fmt, - va_list args) +__printf(2, 0) static void btf_snprintf_show(struct btf_show *show, const char *fmt, + va_list args) { struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show; int len; @@ -7060,15 +8017,12 @@ static int __btf_new_fd(struct btf *btf) return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); } -int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr) +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { struct btf *btf; int ret; - btf = btf_parse(make_bpfptr(attr->btf, uattr.is_kernel), - attr->btf_size, attr->btf_log_level, - u64_to_user_ptr(attr->btf_log_buf), - attr->btf_log_size); + btf = btf_parse(attr, uattr, uattr_size); if (IS_ERR(btf)) return PTR_ERR(btf); @@ -7094,21 +8048,11 @@ int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr) struct btf *btf_get_by_fd(int fd) { struct btf *btf; - struct fd f; - - f = fdget(fd); - - if (!f.file) - return ERR_PTR(-EBADF); - - if (f.file->f_op != &btf_fops) { - fdput(f); - return ERR_PTR(-EINVAL); - } + CLASS(fd, f)(fd); - btf = f.file->private_data; - refcount_inc(&btf->refcnt); - fdput(f); + btf = __btf_get_by_fd(f); + if (!IS_ERR(btf)) + refcount_inc(&btf->refcnt); return btf; } @@ -7225,17 +8169,6 @@ struct btf_module { static LIST_HEAD(btf_modules); static DEFINE_MUTEX(btf_module_mutex); -static ssize_t -btf_module_read(struct file *file, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t len) -{ - const struct btf *btf = bin_attr->private; - - memcpy(buf, btf->data + off, len); - return len; -} - static void purge_cand_cache(struct btf *btf); static int btf_module_notify(struct notifier_block *nb, unsigned long op, @@ -7258,13 +8191,17 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, err = -ENOMEM; goto out; } - btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size); + btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size, + mod->btf_base_data, mod->btf_base_data_size); if (IS_ERR(btf)) { - pr_warn("failed to validate module [%s] BTF: %ld\n", - mod->name, PTR_ERR(btf)); kfree(btf_mod); - if (!IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) + if (!IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) { + pr_warn("failed to validate module [%s] BTF: %ld\n", + mod->name, PTR_ERR(btf)); err = PTR_ERR(btf); + } else { + pr_warn_once("Kernel module BTF mismatch detected, BTF debug info may be unavailable for some modules\n"); + } goto out; } err = btf_alloc_id(btf); @@ -7292,8 +8229,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, attr->attr.name = btf->name; attr->attr.mode = 0444; attr->size = btf->data_size; - attr->private = btf; - attr->read = btf_module_read; + attr->private = btf->data; + attr->read = sysfs_bin_attr_simple_read; err = sysfs_create_bin_file(btf_kobj, attr); if (err) { @@ -7414,6 +8351,17 @@ static struct btf *btf_get_module_btf(const struct module *module) return btf; } +static int check_btf_kconfigs(const struct module *module, const char *feature) +{ + if (!module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + pr_err("missing vmlinux BTF, cannot register %s\n", feature); + return -ENOENT; + } + if (module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + pr_warn("missing module BTF, cannot register %s\n", feature); + return 0; +} + BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) { struct btf *btf = NULL; @@ -7455,15 +8403,142 @@ BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE +/* Validate well-formedness of iter argument type. + * On success, return positive BTF ID of iter state's STRUCT type. + * On error, negative error is returned. + */ +int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) +{ + const struct btf_param *arg; + const struct btf_type *t; + const char *name; + int btf_id; + + if (btf_type_vlen(func) <= arg_idx) + return -EINVAL; + + arg = &btf_params(func)[arg_idx]; + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + t = btf_type_skip_modifiers(btf, t->type, &btf_id); + if (!t || !__btf_type_is_struct(t)) + return -EINVAL; + + name = btf_name_by_offset(btf, t->name_off); + if (!name || strncmp(name, ITER_PREFIX, sizeof(ITER_PREFIX) - 1)) + return -EINVAL; + + return btf_id; +} + +static int btf_check_iter_kfuncs(struct btf *btf, const char *func_name, + const struct btf_type *func, u32 func_flags) +{ + u32 flags = func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); + const char *sfx, *iter_name; + const struct btf_type *t; + char exp_name[128]; + u32 nr_args; + int btf_id; + + /* exactly one of KF_ITER_{NEW,NEXT,DESTROY} can be set */ + if (!flags || (flags & (flags - 1))) + return -EINVAL; + + /* any BPF iter kfunc should have `struct bpf_iter_<type> *` first arg */ + nr_args = btf_type_vlen(func); + if (nr_args < 1) + return -EINVAL; + + btf_id = btf_check_iter_arg(btf, func, 0); + if (btf_id < 0) + return btf_id; + + /* sizeof(struct bpf_iter_<type>) should be a multiple of 8 to + * fit nicely in stack slots + */ + t = btf_type_by_id(btf, btf_id); + if (t->size == 0 || (t->size % 8)) + return -EINVAL; + + /* validate bpf_iter_<type>_{new,next,destroy}(struct bpf_iter_<type> *) + * naming pattern + */ + iter_name = btf_name_by_offset(btf, t->name_off) + sizeof(ITER_PREFIX) - 1; + if (flags & KF_ITER_NEW) + sfx = "new"; + else if (flags & KF_ITER_NEXT) + sfx = "next"; + else /* (flags & KF_ITER_DESTROY) */ + sfx = "destroy"; + + snprintf(exp_name, sizeof(exp_name), "bpf_iter_%s_%s", iter_name, sfx); + if (strcmp(func_name, exp_name)) + return -EINVAL; + + /* only iter constructor should have extra arguments */ + if (!(flags & KF_ITER_NEW) && nr_args != 1) + return -EINVAL; + + if (flags & KF_ITER_NEXT) { + /* bpf_iter_<type>_next() should return pointer */ + t = btf_type_skip_modifiers(btf, func->type, NULL); + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + } + + if (flags & KF_ITER_DESTROY) { + /* bpf_iter_<type>_destroy() should return void */ + t = btf_type_by_id(btf, func->type); + if (!t || !btf_type_is_void(t)) + return -EINVAL; + } + + return 0; +} + +static int btf_check_kfunc_protos(struct btf *btf, u32 func_id, u32 func_flags) +{ + const struct btf_type *func; + const char *func_name; + int err; + + /* any kfunc should be FUNC -> FUNC_PROTO */ + func = btf_type_by_id(btf, func_id); + if (!func || !btf_type_is_func(func)) + return -EINVAL; + + /* sanity check kfunc name */ + func_name = btf_name_by_offset(btf, func->name_off); + if (!func_name || !func_name[0]) + return -EINVAL; + + func = btf_type_by_id(btf, func->type); + if (!func || !btf_type_is_func_proto(func)) + return -EINVAL; + + if (func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY)) { + err = btf_check_iter_kfuncs(btf, func_name, func, func_flags); + if (err) + return err; + } + + return 0; +} + /* Kernel Function (kfunc) BTF ID set registration API */ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, - struct btf_id_set8 *add_set) + const struct btf_kfunc_id_set *kset) { + struct btf_kfunc_hook_filter *hook_filter; + struct btf_id_set8 *add_set = kset->set; bool vmlinux_set = !btf_is_module(btf); + bool add_filter = !!kset->filter; struct btf_kfunc_set_tab *tab; struct btf_id_set8 *set; - u32 set_cnt; + u32 set_cnt, i; int ret; if (hook >= BTF_KFUNC_HOOK_MAX) { @@ -7475,6 +8550,24 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, return 0; tab = btf->kfunc_set_tab; + + if (tab && add_filter) { + u32 i; + + hook_filter = &tab->hook_filters[hook]; + for (i = 0; i < hook_filter->nr_filters; i++) { + if (hook_filter->filters[i] == kset->filter) { + add_filter = false; + break; + } + } + + if (add_filter && hook_filter->nr_filters == BTF_KFUNC_FILTER_MAX_CNT) { + ret = -E2BIG; + goto end; + } + } + if (!tab) { tab = kzalloc(sizeof(*tab), GFP_KERNEL | __GFP_NOWARN); if (!tab) @@ -7491,21 +8584,15 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, goto end; } - /* We don't need to allocate, concatenate, and sort module sets, because - * only one is allowed per hook. Hence, we can directly assign the - * pointer and return. - */ - if (!vmlinux_set) { - tab->sets[hook] = add_set; - return 0; - } - /* In case of vmlinux sets, there may be more than one set being * registered per hook. To create a unified set, we allocate a new set * and concatenate all individual sets being registered. While each set * is individually sorted, they may become unsorted when concatenated, * hence re-sorting the final set again is required to make binary * searching the set using btf_id_set8_contains function work. + * + * For module sets, we need to allocate as we may need to relocate + * BTF ids. */ set_cnt = set ? set->cnt : 0; @@ -7521,7 +8608,7 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, /* Grow set */ set = krealloc(tab->sets[hook], - offsetof(struct btf_id_set8, pairs[set_cnt + add_set->cnt]), + struct_size(set, pairs, set_cnt + add_set->cnt), GFP_KERNEL | __GFP_NOWARN); if (!set) { ret = -ENOMEM; @@ -7535,10 +8622,18 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, /* Concatenate the two sets */ memcpy(set->pairs + set->cnt, add_set->pairs, add_set->cnt * sizeof(set->pairs[0])); + /* Now that the set is copied, update with relocated BTF ids */ + for (i = set->cnt; i < set->cnt + add_set->cnt; i++) + set->pairs[i].id = btf_relocate_id(btf, set->pairs[i].id); + set->cnt += add_set->cnt; sort(set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func, NULL); + if (add_filter) { + hook_filter = &tab->hook_filters[hook]; + hook_filter->filters[hook_filter->nr_filters++] = kset->filter; + } return 0; end: btf_free_kfunc_set_tab(btf); @@ -7547,15 +8642,22 @@ end: static u32 *__btf_kfunc_id_set_contains(const struct btf *btf, enum btf_kfunc_hook hook, - u32 kfunc_btf_id) + u32 kfunc_btf_id, + const struct bpf_prog *prog) { + struct btf_kfunc_hook_filter *hook_filter; struct btf_id_set8 *set; - u32 *id; + u32 *id, i; if (hook >= BTF_KFUNC_HOOK_MAX) return NULL; if (!btf->kfunc_set_tab) return NULL; + hook_filter = &btf->kfunc_set_tab->hook_filters[hook]; + for (i = 0; i < hook_filter->nr_filters; i++) { + if (hook_filter->filters[i](prog, kfunc_btf_id)) + return NULL; + } set = btf->kfunc_set_tab->sets[hook]; if (!set) return NULL; @@ -7578,10 +8680,35 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) case BPF_PROG_TYPE_STRUCT_OPS: return BTF_KFUNC_HOOK_STRUCT_OPS; case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_LSM: return BTF_KFUNC_HOOK_TRACING; case BPF_PROG_TYPE_SYSCALL: return BTF_KFUNC_HOOK_SYSCALL; + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_SOCK_OPS: + return BTF_KFUNC_HOOK_CGROUP; + case BPF_PROG_TYPE_SCHED_ACT: + return BTF_KFUNC_HOOK_SCHED_ACT; + case BPF_PROG_TYPE_SK_SKB: + return BTF_KFUNC_HOOK_SK_SKB; + case BPF_PROG_TYPE_SOCKET_FILTER: + return BTF_KFUNC_HOOK_SOCKET_FILTER; + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + 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; } @@ -7595,47 +8722,49 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) * protection for looking up a well-formed btf->kfunc_set_tab. */ u32 *btf_kfunc_id_set_contains(const struct btf *btf, - enum bpf_prog_type prog_type, - u32 kfunc_btf_id) + u32 kfunc_btf_id, + const struct bpf_prog *prog) { + enum bpf_prog_type prog_type = resolve_prog_type(prog); enum btf_kfunc_hook hook; u32 *kfunc_flags; - kfunc_flags = __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_COMMON, kfunc_btf_id); + kfunc_flags = __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_COMMON, kfunc_btf_id, prog); if (kfunc_flags) return kfunc_flags; hook = bpf_prog_type_to_kfunc_hook(prog_type); - return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); + return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id, prog); } -u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id) +u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, + const struct bpf_prog *prog) { - return __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id); + return __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id, prog); } static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, const struct btf_kfunc_id_set *kset) { struct btf *btf; - int ret; + int ret, i; btf = btf_get_module_btf(kset->owner); - if (!btf) { - if (!kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { - pr_err("missing vmlinux BTF, cannot register kfuncs\n"); - return -ENOENT; - } - if (kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) { - pr_err("missing module BTF, cannot register kfuncs\n"); - return -ENOENT; - } - return 0; - } + if (!btf) + return check_btf_kconfigs(kset->owner, "kfunc"); if (IS_ERR(btf)) return PTR_ERR(btf); - ret = btf_populate_kfunc_set(btf, hook, kset->set); + for (i = 0; i < kset->set->cnt; i++) { + ret = btf_check_kfunc_protos(btf, btf_relocate_id(btf, kset->set->pairs[i].id), + kset->set->pairs[i].flags); + if (ret) + goto err_out; + } + + ret = btf_populate_kfunc_set(btf, hook, kset); + +err_out: btf_put(btf); return ret; } @@ -7646,6 +8775,14 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, { enum btf_kfunc_hook hook; + /* All kfuncs need to be tagged as such in BTF. + * WARN() for initcall registrations that do not check errors. + */ + if (!(kset->set->flags & BTF_SET8_KFUNCS)) { + WARN_ON(!kset->owner); + return -EINVAL; + } + hook = bpf_prog_type_to_kfunc_hook(prog_type); return __register_btf_kfunc_id_set(hook, kset); } @@ -7683,7 +8820,7 @@ static int btf_check_dtor_kfuncs(struct btf *btf, const struct btf_id_dtor_kfunc u32 nr_args, i; for (i = 0; i < cnt; i++) { - dtor_btf_id = dtors[i].kfunc_btf_id; + dtor_btf_id = btf_relocate_id(btf, dtors[i].kfunc_btf_id); dtor_func = btf_type_by_id(btf, dtor_btf_id); if (!dtor_func || !btf_type_is_func(dtor_func)) @@ -7718,21 +8855,12 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c { struct btf_id_dtor_kfunc_tab *tab; struct btf *btf; - u32 tab_cnt; + u32 tab_cnt, i; int ret; btf = btf_get_module_btf(owner); - if (!btf) { - if (!owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { - pr_err("missing vmlinux BTF, cannot register dtor kfuncs\n"); - return -ENOENT; - } - if (owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) { - pr_err("missing module BTF, cannot register dtor kfuncs\n"); - return -ENOENT; - } - return 0; - } + if (!btf) + return check_btf_kconfigs(owner, "dtor kfuncs"); if (IS_ERR(btf)) return PTR_ERR(btf); @@ -7766,7 +8894,7 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c } tab = krealloc(btf->dtor_kfunc_tab, - offsetof(struct btf_id_dtor_kfunc_tab, dtors[tab_cnt + add_cnt]), + struct_size(tab, dtors, tab_cnt + add_cnt), GFP_KERNEL | __GFP_NOWARN); if (!tab) { ret = -ENOMEM; @@ -7778,13 +8906,20 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c btf->dtor_kfunc_tab = tab; memcpy(tab->dtors + tab->cnt, dtors, add_cnt * sizeof(tab->dtors[0])); + + /* remap BTF ids based on BTF relocation (if any) */ + for (i = tab_cnt; i < tab_cnt + add_cnt; i++) { + tab->dtors[i].btf_id = btf_relocate_id(btf, tab->dtors[i].btf_id); + tab->dtors[i].kfunc_btf_id = btf_relocate_id(btf, tab->dtors[i].kfunc_btf_id); + } + tab->cnt += add_cnt; sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); - return 0; end: - btf_free_dtor_kfunc_tab(btf); + if (ret) + btf_free_dtor_kfunc_tab(btf); btf_put(btf); return ret; } @@ -7847,17 +8982,6 @@ size_t bpf_core_essential_name_len(const char *name) return n; } -struct bpf_cand_cache { - const char *name; - u32 name_len; - u16 kind; - u16 cnt; - struct { - const struct btf *btf; - u32 id; - } cands[]; -}; - static void bpf_free_cands(struct bpf_cand_cache *cands) { if (!cands->cnt) @@ -7878,8 +9002,6 @@ static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; #define MODULE_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; -static DEFINE_MUTEX(cand_cache_mutex); - static void __print_cand_cache(struct bpf_verifier_log *log, struct bpf_cand_cache **cache, int cache_size) @@ -7944,7 +9066,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands, bpf_free_cands_from_cache(*cc); *cc = NULL; } - new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL); + new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL_ACCOUNT); if (!new_cands) { bpf_free_cands(cands); return ERR_PTR(-ENOMEM); @@ -7952,7 +9074,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands, /* strdup the name, since it will stay in cache. * the cands->name points to strings in prog's BTF and the prog can be unloaded. */ - new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL); + new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL_ACCOUNT); bpf_free_cands(cands); if (!new_cands->name) { kfree(new_cands); @@ -8036,7 +9158,7 @@ bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf, continue; /* most of the time there is only one candidate for a given kind+name pair */ - new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL); + new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL_ACCOUNT); if (!new_cands) { bpf_free_cands(cands); return ERR_PTR(-ENOMEM); @@ -8126,12 +9248,10 @@ check_modules: btf_get(mod_btf); spin_unlock_bh(&btf_idr_lock); cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf)); - if (IS_ERR(cands)) { - btf_put(mod_btf); + btf_put(mod_btf); + if (IS_ERR(cands)) return ERR_CAST(cands); - } spin_lock_bh(&btf_idr_lock); - btf_put(mod_btf); } spin_unlock_bh(&btf_idr_lock); /* cands is a pointer to kmalloced memory here if cands->cnt > 0 @@ -8149,15 +9269,24 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, struct bpf_core_cand_list cands = {}; struct bpf_core_relo_res targ_res; struct bpf_core_spec *specs; + const struct btf_type *type; int err; /* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5" * into arrays of btf_ids of struct fields and array indices. */ - specs = kcalloc(3, sizeof(*specs), GFP_KERNEL); + specs = kcalloc(3, sizeof(*specs), GFP_KERNEL_ACCOUNT); if (!specs) return -ENOMEM; + type = btf_type_by_id(ctx->btf, relo->type_id); + if (!type) { + bpf_log(ctx->log, "relo #%u: bad type id %u\n", + relo_idx, relo->type_id); + kfree(specs); + return -EINVAL; + } + if (need_cands) { struct bpf_cand_cache *cc; int i; @@ -8171,7 +9300,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, goto out; } if (cc->cnt) { - cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL); + cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL_ACCOUNT); if (!cands.cands) { err = -ENOMEM; goto out; @@ -8210,3 +9339,241 @@ out: } return err; } + +bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + const char *field_name, u32 btf_id, const char *suffix) +{ + struct btf *btf = reg->btf; + const struct btf_type *walk_type, *safe_type; + const char *tname; + char safe_tname[64]; + long ret, safe_id; + const struct btf_member *member; + u32 i; + + walk_type = btf_type_by_id(btf, reg->btf_id); + if (!walk_type) + return false; + + tname = btf_name_by_offset(btf, walk_type->name_off); + + ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix); + if (ret >= sizeof(safe_tname)) + return false; + + safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info)); + if (safe_id < 0) + return false; + + safe_type = btf_type_by_id(btf, safe_id); + if (!safe_type) + return false; + + for_each_member(i, safe_type, member) { + const char *m_name = __btf_name_by_offset(btf, member->name_off); + const struct btf_type *mtype = btf_type_by_id(btf, member->type); + u32 id; + + if (!btf_type_is_ptr(mtype)) + continue; + + btf_type_skip_modifiers(btf, mtype->type, &id); + /* If we match on both type and name, the field is considered trusted. */ + if (btf_id == id && !strcmp(field_name, m_name)) + return true; + } + + return false; +} + +bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, + const struct btf *reg_btf, u32 reg_id, + const struct btf *arg_btf, u32 arg_id) +{ + const char *reg_name, *arg_name, *search_needle; + const struct btf_type *reg_type, *arg_type; + int reg_len, arg_len, cmp_len; + size_t pattern_len = sizeof(NOCAST_ALIAS_SUFFIX) - sizeof(char); + + reg_type = btf_type_by_id(reg_btf, reg_id); + if (!reg_type) + return false; + + arg_type = btf_type_by_id(arg_btf, arg_id); + if (!arg_type) + return false; + + reg_name = btf_name_by_offset(reg_btf, reg_type->name_off); + arg_name = btf_name_by_offset(arg_btf, arg_type->name_off); + + reg_len = strlen(reg_name); + arg_len = strlen(arg_name); + + /* Exactly one of the two type names may be suffixed with ___init, so + * if the strings are the same size, they can't possibly be no-cast + * aliases of one another. If you have two of the same type names, e.g. + * they're both nf_conn___init, it would be improper to return true + * because they are _not_ no-cast aliases, they are the same type. + */ + if (reg_len == arg_len) + return false; + + /* Either of the two names must be the other name, suffixed with ___init. */ + if ((reg_len != arg_len + pattern_len) && + (arg_len != reg_len + pattern_len)) + return false; + + if (reg_len < arg_len) { + search_needle = strstr(arg_name, NOCAST_ALIAS_SUFFIX); + cmp_len = reg_len; + } else { + search_needle = strstr(reg_name, NOCAST_ALIAS_SUFFIX); + cmp_len = arg_len; + } + + if (!search_needle) + return false; + + /* ___init suffix must come at the end of the name */ + if (*(search_needle + pattern_len) != '\0') + return false; + + return !strncmp(reg_name, arg_name, cmp_len); +} + +#ifdef CONFIG_BPF_JIT +static int +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, + struct bpf_verifier_log *log) +{ + struct btf_struct_ops_tab *tab, *new_tab; + int i, err; + + tab = btf->struct_ops_tab; + if (!tab) { + tab = kzalloc(struct_size(tab, ops, 4), GFP_KERNEL); + if (!tab) + return -ENOMEM; + tab->capacity = 4; + btf->struct_ops_tab = tab; + } + + for (i = 0; i < tab->cnt; i++) + if (tab->ops[i].st_ops == st_ops) + return -EEXIST; + + if (tab->cnt == tab->capacity) { + new_tab = krealloc(tab, + struct_size(tab, ops, tab->capacity * 2), + GFP_KERNEL); + if (!new_tab) + return -ENOMEM; + tab = new_tab; + tab->capacity *= 2; + btf->struct_ops_tab = tab; + } + + tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + + err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); + if (err) + return err; + + btf->struct_ops_tab->cnt++; + + return 0; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!value_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].value_id == value_id) + return &st_ops_list[i]; + } + + return NULL; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!type_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].type_id == type_id) + return &st_ops_list[i]; + } + + return NULL; +} + +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) +{ + struct bpf_verifier_log *log; + struct btf *btf; + int err = 0; + + btf = btf_get_module_btf(st_ops->owner); + if (!btf) + return check_btf_kconfigs(st_ops->owner, "struct_ops"); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); + if (!log) { + err = -ENOMEM; + goto errout; + } + + log->level = BPF_LOG_KERNEL; + + err = btf_add_struct_ops(btf, st_ops, log); + +errout: + kfree(log); + btf_put(btf); + + return err; +} +EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); +#endif + +bool btf_param_match_suffix(const struct btf *btf, + const struct btf_param *arg, + const char *suffix) +{ + int suffix_len = strlen(suffix), len; + const char *param_name; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len <= suffix_len) + return false; + param_name += len - suffix_len; + return !strncmp(param_name, suffix, suffix_len); +} diff --git a/kernel/bpf/btf_iter.c b/kernel/bpf/btf_iter.c new file mode 100644 index 000000000000..0e2c66a52df9 --- /dev/null +++ b/kernel/bpf/btf_iter.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#include "../../tools/lib/bpf/btf_iter.c" diff --git a/kernel/bpf/btf_relocate.c b/kernel/bpf/btf_relocate.c new file mode 100644 index 000000000000..c12ccbf66507 --- /dev/null +++ b/kernel/bpf/btf_relocate.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#include "../../tools/lib/bpf/btf_relocate.c" diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index bf2fdb33fb31..69988af44b37 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -24,6 +24,37 @@ DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE); EXPORT_SYMBOL(cgroup_bpf_enabled_key); +/* + * cgroup bpf destruction makes heavy use of work items and there can be a lot + * of concurrent destructions. Use a separate workqueue so that cgroup bpf + * destruction work items don't end up filling up max_active of system_percpu_wq + * which may lead to deadlock. + */ +static struct workqueue_struct *cgroup_bpf_destroy_wq; + +static int __init cgroup_bpf_wq_init(void) +{ + cgroup_bpf_destroy_wq = alloc_workqueue("cgroup_bpf_destroy", + WQ_PERCPU, 1); + if (!cgroup_bpf_destroy_wq) + panic("Failed to alloc workqueue for cgroup bpf destroy.\n"); + return 0; +} +core_initcall(cgroup_bpf_wq_init); + +static int cgroup_bpf_lifetime_notify(struct notifier_block *nb, + unsigned long action, void *data); + +static struct notifier_block cgroup_bpf_lifetime_nb = { + .notifier_call = cgroup_bpf_lifetime_notify, +}; + +void __init cgroup_bpf_lifetime_notifier_init(void) +{ + BUG_ON(blocking_notifier_chain_register(&cgroup_lifetime_notifier, + &cgroup_bpf_lifetime_nb)); +} + /* __always_inline is necessary to prevent indirect call through run_prog * function pointer. */ @@ -41,8 +72,7 @@ bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, u32 func_ret; run_ctx.retval = retval; - migrate_disable(); - rcu_read_lock(); + rcu_read_lock_dont_migrate(); array = rcu_dereference(cgrp->effective[atype]); item = &array->items[0]; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); @@ -58,8 +88,7 @@ bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, item++; } bpf_reset_run_ctx(old_run_ctx); - rcu_read_unlock(); - migrate_enable(); + rcu_read_unlock_migrate(); return run_ctx.retval; } @@ -173,11 +202,11 @@ void bpf_cgroup_atype_put(int cgroup_atype) { int i = cgroup_atype - CGROUP_LSM_START; - mutex_lock(&cgroup_mutex); + cgroup_lock(); if (--cgroup_lsm_atype[i].refcnt <= 0) cgroup_lsm_atype[i].attach_btf_id = 0; WARN_ON_ONCE(cgroup_lsm_atype[i].refcnt < 0); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); } #else static enum cgroup_bpf_attach_type @@ -189,7 +218,7 @@ bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) } #endif /* CONFIG_BPF_LSM */ -void cgroup_bpf_offline(struct cgroup *cgrp) +static void cgroup_bpf_offline(struct cgroup *cgrp) { cgroup_get(cgrp); percpu_ref_kill(&cgrp->bpf.refcnt); @@ -282,7 +311,7 @@ static void cgroup_bpf_release(struct work_struct *work) unsigned int atype; - mutex_lock(&cgroup_mutex); + cgroup_lock(); for (atype = 0; atype < ARRAY_SIZE(cgrp->bpf.progs); atype++) { struct hlist_head *progs = &cgrp->bpf.progs[atype]; @@ -315,7 +344,7 @@ static void cgroup_bpf_release(struct work_struct *work) bpf_cgroup_storage_free(storage); } - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_put(p); @@ -334,7 +363,7 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref) struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt); INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release); - queue_work(system_wq, &cgrp->bpf.release_work); + queue_work(cgroup_bpf_destroy_wq, &cgrp->bpf.release_work); } /* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through @@ -352,7 +381,7 @@ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) /* count number of elements in the list. * it's slow but the list cannot be long */ -static u32 prog_list_length(struct hlist_head *head) +static u32 prog_list_length(struct hlist_head *head, int *preorder_cnt) { struct bpf_prog_list *pl; u32 cnt = 0; @@ -360,6 +389,8 @@ static u32 prog_list_length(struct hlist_head *head) hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; + if (preorder_cnt && (pl->flags & BPF_F_PREORDER)) + (*preorder_cnt)++; cnt++; } return cnt; @@ -383,7 +414,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, if (flags & BPF_F_ALLOW_MULTI) return true; - cnt = prog_list_length(&p->bpf.progs[atype]); + cnt = prog_list_length(&p->bpf.progs[atype], NULL); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); @@ -406,12 +437,12 @@ static int compute_effective_progs(struct cgroup *cgrp, struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; - int cnt = 0; + int i, j, cnt = 0, preorder_cnt = 0, fstart, bstart, init_bstart; /* count number of effective programs by walking parents */ do { if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) - cnt += prog_list_length(&p->bpf.progs[atype]); + cnt += prog_list_length(&p->bpf.progs[atype], &preorder_cnt); p = cgroup_parent(p); } while (p); @@ -422,20 +453,34 @@ static int compute_effective_progs(struct cgroup *cgrp, /* populate the array with effective progs */ cnt = 0; p = cgrp; + fstart = preorder_cnt; + bstart = preorder_cnt - 1; do { if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; + init_bstart = bstart; hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; - item = &progs->items[cnt]; + if (pl->flags & BPF_F_PREORDER) { + item = &progs->items[bstart]; + bstart--; + } else { + item = &progs->items[fstart]; + fstart++; + } item->prog = prog_list_prog(pl); bpf_cgroup_storages_assign(item->cgroup_storage, pl->storage); cnt++; } + + /* reverse pre-ordering progs at this cgroup level */ + for (i = bstart + 1, j = init_bstart; i < j; i++, j--) + swap(progs->items[i], progs->items[j]); + } while ((p = cgroup_parent(p))); *array = progs; @@ -458,7 +503,7 @@ static void activate_effective_progs(struct cgroup *cgrp, * cgroup_bpf_inherit() - inherit effective programs from parent * @cgrp: the cgroup to modify */ -int cgroup_bpf_inherit(struct cgroup *cgrp) +static int cgroup_bpf_inherit(struct cgroup *cgrp) { /* has to use marco instead of const int, since compiler thinks * that array below is variable length @@ -501,6 +546,27 @@ cleanup: return -ENOMEM; } +static int cgroup_bpf_lifetime_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct cgroup *cgrp = data; + int ret = 0; + + if (cgrp->root != &cgrp_dfl_root) + return NOTIFY_OK; + + switch (action) { + case CGROUP_LIFETIME_ONLINE: + ret = cgroup_bpf_inherit(cgrp); + break; + case CGROUP_LIFETIME_OFFLINE: + cgroup_bpf_offline(cgrp); + break; + } + + return notifier_from_errno(ret); +} + static int update_effective_progs(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype) { @@ -591,6 +657,116 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs, return NULL; } +static struct bpf_link *bpf_get_anchor_link(u32 flags, u32 id_or_fd) +{ + struct bpf_link *link = ERR_PTR(-EINVAL); + + if (flags & BPF_F_ID) + link = bpf_link_by_id(id_or_fd); + else if (id_or_fd) + link = bpf_link_get_from_fd(id_or_fd); + return link; +} + +static struct bpf_prog *bpf_get_anchor_prog(u32 flags, u32 id_or_fd) +{ + struct bpf_prog *prog = ERR_PTR(-EINVAL); + + if (flags & BPF_F_ID) + prog = bpf_prog_by_id(id_or_fd); + else if (id_or_fd) + prog = bpf_prog_get(id_or_fd); + return prog; +} + +static struct bpf_prog_list *get_prog_list(struct hlist_head *progs, struct bpf_prog *prog, + struct bpf_cgroup_link *link, u32 flags, u32 id_or_fd) +{ + bool is_link = flags & BPF_F_LINK, is_id = flags & BPF_F_ID; + struct bpf_prog_list *pltmp, *pl = ERR_PTR(-EINVAL); + bool preorder = flags & BPF_F_PREORDER; + struct bpf_link *anchor_link = NULL; + struct bpf_prog *anchor_prog = NULL; + bool is_before, is_after; + + is_before = flags & BPF_F_BEFORE; + is_after = flags & BPF_F_AFTER; + if (is_link || is_id || id_or_fd) { + /* flags must have either BPF_F_BEFORE or BPF_F_AFTER */ + if (is_before == is_after) + return ERR_PTR(-EINVAL); + if ((is_link && !link) || (!is_link && !prog)) + return ERR_PTR(-EINVAL); + } else if (!hlist_empty(progs)) { + /* flags cannot have both BPF_F_BEFORE and BPF_F_AFTER */ + if (is_before && is_after) + return ERR_PTR(-EINVAL); + } + + if (is_link) { + anchor_link = bpf_get_anchor_link(flags, id_or_fd); + if (IS_ERR(anchor_link)) + return ERR_CAST(anchor_link); + } else if (is_id || id_or_fd) { + anchor_prog = bpf_get_anchor_prog(flags, id_or_fd); + if (IS_ERR(anchor_prog)) + return ERR_CAST(anchor_prog); + } + + if (!anchor_prog && !anchor_link) { + /* if there is no anchor_prog/anchor_link, then BPF_F_PREORDER + * doesn't matter since either prepend or append to a combined + * list of progs will end up with correct result. + */ + hlist_for_each_entry(pltmp, progs, node) { + if (is_before) + return pltmp; + if (pltmp->node.next) + continue; + return pltmp; + } + return NULL; + } + + hlist_for_each_entry(pltmp, progs, node) { + if ((anchor_prog && anchor_prog == pltmp->prog) || + (anchor_link && anchor_link == &pltmp->link->link)) { + if (!!(pltmp->flags & BPF_F_PREORDER) != preorder) + goto out; + pl = pltmp; + goto out; + } + } + + pl = ERR_PTR(-ENOENT); +out: + if (anchor_link) + bpf_link_put(anchor_link); + else + bpf_prog_put(anchor_prog); + return pl; +} + +static int insert_pl_to_hlist(struct bpf_prog_list *pl, struct hlist_head *progs, + struct bpf_prog *prog, struct bpf_cgroup_link *link, + u32 flags, u32 id_or_fd) +{ + struct bpf_prog_list *pltmp; + + pltmp = get_prog_list(progs, prog, link, flags, id_or_fd); + if (IS_ERR(pltmp)) + return PTR_ERR(pltmp); + + if (!pltmp) + hlist_add_head(&pl->node, progs); + else if (flags & BPF_F_BEFORE) + hlist_add_before(&pl->node, &pltmp->node); + else + hlist_add_behind(&pl->node, &pltmp->node); + + return 0; +} + /** * __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and * propagate the change to descendants @@ -600,6 +776,8 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs, * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set * @type: Type of attach operation * @flags: Option flags + * @id_or_fd: Relative prog id or fd + * @revision: bpf_prog_list revision * * Exactly one of @prog or @link can be non-null. * Must be called with cgroup_mutex held. @@ -607,7 +785,8 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs, static int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *replace_prog, struct bpf_cgroup_link *link, - enum bpf_attach_type type, u32 flags) + enum bpf_attach_type type, u32 flags, u32 id_or_fd, + u64 revision) { u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); struct bpf_prog *old_prog = NULL; @@ -623,6 +802,9 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI))) /* invalid combination */ return -EINVAL; + if ((flags & BPF_F_REPLACE) && (flags & (BPF_F_BEFORE | BPF_F_AFTER))) + /* only either replace or insertion with before/after */ + return -EINVAL; if (link && (prog || replace_prog)) /* only either link or prog/replace_prog can be specified */ return -EINVAL; @@ -633,6 +815,8 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; + if (revision && revision != cgrp->bpf.revisions[atype]) + return -ESTALE; progs = &cgrp->bpf.progs[atype]; @@ -646,7 +830,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, */ return -EPERM; - if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + if (prog_list_length(progs, NULL) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; pl = find_attach_entry(progs, prog, link, replace_prog, @@ -661,31 +845,28 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, if (pl) { old_prog = pl->prog; } else { - struct hlist_node *last = NULL; - pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { bpf_cgroup_storages_free(new_storage); return -ENOMEM; } - if (hlist_empty(progs)) - hlist_add_head(&pl->node, progs); - else - hlist_for_each(last, progs) { - if (last->next) - continue; - hlist_add_behind(&pl->node, last); - break; - } + + err = insert_pl_to_hlist(pl, progs, prog, link, flags, id_or_fd); + if (err) { + kfree(pl); + bpf_cgroup_storages_free(new_storage); + return err; + } } pl->prog = prog; pl->link = link; + pl->flags = flags; bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[atype] = saved_flags; if (type == BPF_LSM_CGROUP) { - err = bpf_trampoline_link_cgroup_shim(new_prog, atype); + err = bpf_trampoline_link_cgroup_shim(new_prog, atype, type); if (err) goto cleanup; } @@ -694,6 +875,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, if (err) goto cleanup_trampoline; + cgrp->bpf.revisions[atype] += 1; if (old_prog) { if (type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(old_prog); @@ -725,13 +907,14 @@ static int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *replace_prog, struct bpf_cgroup_link *link, enum bpf_attach_type type, - u32 flags) + u32 flags, u32 id_or_fd, u64 revision) { int ret; - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); - mutex_unlock(&cgroup_mutex); + cgroup_lock(); + ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags, + id_or_fd, revision); + cgroup_unlock(); return ret; } @@ -785,7 +968,8 @@ found: * to descendants * @cgrp: The cgroup which descendants to traverse * @link: A link for which to replace BPF program - * @type: Type of attach operation + * @new_prog: &struct bpf_prog for the target BPF program with its refcnt + * incremented * * Must be called with cgroup_mutex held. */ @@ -799,7 +983,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, struct hlist_head *progs; bool found = false; - atype = bpf_cgroup_atype_find(link->type, new_prog->aux->attach_btf_id); + atype = bpf_cgroup_atype_find(link->link.attach_type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; @@ -817,6 +1001,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, if (!found) return -ENOENT; + cgrp->bpf.revisions[atype] += 1; old_prog = xchg(&link->link.prog, new_prog); replace_effective_prog(cgrp, atype, link); bpf_prog_put(old_prog); @@ -831,7 +1016,7 @@ static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog, cg_link = container_of(link, struct bpf_cgroup_link, link); - mutex_lock(&cgroup_mutex); + cgroup_lock(); /* link might have been auto-released by dying cgroup, so fail */ if (!cg_link->cgroup) { ret = -ENOLINK; @@ -843,7 +1028,7 @@ static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog, } ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); out_unlock: - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -942,12 +1127,14 @@ found: * @prog: A program to detach or NULL * @link: A link to detach or NULL * @type: Type of detach operation + * @revision: bpf_prog_list revision * * At most one of @prog or @link can be non-NULL. * Must be called with cgroup_mutex held. */ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_cgroup_link *link, enum bpf_attach_type type) + struct bpf_cgroup_link *link, enum bpf_attach_type type, + u64 revision) { enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; @@ -965,6 +1152,9 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, if (atype < 0) return -EINVAL; + if (revision && revision != cgrp->bpf.revisions[atype]) + return -ESTALE; + progs = &cgrp->bpf.progs[atype]; flags = cgrp->bpf.flags[atype]; @@ -990,6 +1180,7 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* now can actually delete it from this cgroup list */ hlist_del(&pl->node); + cgrp->bpf.revisions[atype] += 1; kfree(pl); if (hlist_empty(progs)) @@ -1005,13 +1196,13 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, } static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type) + enum bpf_attach_type type, u64 revision) { int ret; - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); - mutex_unlock(&cgroup_mutex); + cgroup_lock(); + ret = __cgroup_bpf_detach(cgrp, prog, NULL, type, revision); + cgroup_unlock(); return ret; } @@ -1028,6 +1219,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, struct bpf_prog_array *effective; int cnt, ret = 0, i; int total_cnt = 0; + u64 revision = 0; u32 flags; if (effective_query && prog_attach_flags) @@ -1055,7 +1247,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, lockdep_is_held(&cgroup_mutex)); total_cnt += bpf_prog_array_length(effective); } else { - total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); + total_cnt += prog_list_length(&cgrp->bpf.progs[atype], NULL); } } @@ -1065,6 +1257,10 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, return -EFAULT; if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt))) return -EFAULT; + if (!effective_query && from_atype == to_atype) + revision = cgrp->bpf.revisions[from_atype]; + if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision))) + return -EFAULT; if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt) /* return early if user requested only program count + flags */ return 0; @@ -1087,7 +1283,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, u32 id; progs = &cgrp->bpf.progs[atype]; - cnt = min_t(int, prog_list_length(progs), total_cnt); + cnt = min_t(int, prog_list_length(progs, NULL), total_cnt); i = 0; hlist_for_each_entry(pl, progs, node) { prog = prog_list_prog(pl); @@ -1120,9 +1316,9 @@ static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, { int ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); ret = __cgroup_bpf_query(cgrp, attr, uattr); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -1147,7 +1343,8 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr, } ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL, - attr->attach_type, attr->attach_flags); + attr->attach_type, attr->attach_flags, + attr->relative_fd, attr->expected_revision); if (replace_prog) bpf_prog_put(replace_prog); @@ -1169,7 +1366,7 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) if (IS_ERR(prog)) prog = NULL; - ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type); + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, attr->expected_revision); if (prog) bpf_prog_put(prog); @@ -1189,23 +1386,23 @@ static void bpf_cgroup_link_release(struct bpf_link *link) if (!cg_link->cgroup) return; - mutex_lock(&cgroup_mutex); + cgroup_lock(); /* re-check cgroup under lock again */ if (!cg_link->cgroup) { - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return; } WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link, - cg_link->type)); - if (cg_link->type == BPF_LSM_CGROUP) + link->attach_type, 0)); + if (link->attach_type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog); cg = cg_link->cgroup; cg_link->cgroup = NULL; - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); cgroup_put(cg); } @@ -1232,16 +1429,16 @@ static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link, container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; - mutex_lock(&cgroup_mutex); + cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); seq_printf(seq, "cgroup_id:\t%llu\n" "attach_type:\t%d\n", cg_id, - cg_link->type); + link->attach_type); } static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, @@ -1251,13 +1448,13 @@ static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; - mutex_lock(&cgroup_mutex); + cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); info->cgroup.cgroup_id = cg_id; - info->cgroup.attach_type = cg_link->type; + info->cgroup.attach_type = link->attach_type; return 0; } @@ -1270,6 +1467,13 @@ static const struct bpf_link_ops bpf_cgroup_link_lops = { .fill_link_info = bpf_cgroup_link_fill_link_info, }; +#define BPF_F_LINK_ATTACH_MASK \ + (BPF_F_ID | \ + BPF_F_BEFORE | \ + BPF_F_AFTER | \ + BPF_F_PREORDER | \ + BPF_F_LINK) + int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; @@ -1277,7 +1481,7 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) struct cgroup *cgrp; int err; - if (attr->link_create.flags) + if (attr->link_create.flags & (~BPF_F_LINK_ATTACH_MASK)) return -EINVAL; cgrp = cgroup_get_from_fd(attr->link_create.target_fd); @@ -1290,9 +1494,8 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) goto out_put_cgroup; } bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops, - prog); + prog, attr->link_create.attach_type); link->cgroup = cgrp; - link->type = attr->link_create.attach_type; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -1301,7 +1504,9 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) } err = cgroup_bpf_attach(cgrp, NULL, NULL, link, - link->type, BPF_F_ALLOW_MULTI); + link->link.attach_type, BPF_F_ALLOW_MULTI | attr->link_create.flags, + attr->link_create.cgroup.relative_fd, + attr->link_create.cgroup.expected_revision); if (err) { bpf_link_cleanup(&link_primer); goto out_put_cgroup; @@ -1334,7 +1539,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic * @skb: The skb that is being sent or received - * @type: The type of program to be executed + * @atype: The type of program to be executed * * If no socket is passed, or the socket is not of type INET or INET6, * this function does nothing and returns 0. @@ -1357,15 +1562,12 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype) { - unsigned int offset = skb->data - skb_network_header(skb); + unsigned int offset = -skb_network_offset(skb); struct sock *save_sk; void *saved_data_end; struct cgroup *cgrp; int ret; - if (!sk || !sk_fullsock(sk)) - return 0; - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; @@ -1424,7 +1626,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); /** * __cgroup_bpf_run_filter_sk() - Run a program on a sock * @sk: sock structure to manipulate - * @type: The type of program to be executed + * @atype: The type of program to be executed * * socket is passed is expected to be of type INET or INET6. * @@ -1449,18 +1651,22 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * provided by user sockaddr * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user - * @type: The type of program to be executed + * @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is + * read-only for AF_INET[6] uaddr but can be modified for AF_UNIX + * uaddr. + * @atype: The type of program to be executed * @t_ctx: Pointer to attach type specific context * @flags: Pointer to u32 which contains higher bits of BPF program * return value (OR'ed together). * - * socket is expected to be of type INET or INET6. + * socket is expected to be of type INET, INET6 or UNIX. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr_unsized *uaddr, + int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags) @@ -1470,23 +1676,33 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, .uaddr = uaddr, .t_ctx = t_ctx, }; - struct sockaddr_storage unspec; + struct sockaddr_storage storage; struct cgroup *cgrp; + int ret; /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). */ - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 && + sk->sk_family != AF_UNIX) return 0; if (!ctx.uaddr) { - memset(&unspec, 0, sizeof(unspec)); - ctx.uaddr = (struct sockaddr *)&unspec; + memset(&storage, 0, sizeof(storage)); + ctx.uaddr = (struct sockaddr_unsized *)&storage; + ctx.uaddrlen = 0; + } else { + ctx.uaddrlen = *uaddrlen; } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, - 0, flags); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, + 0, flags); + + if (!ret && uaddr) + *uaddrlen = ctx.uaddrlen; + + return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); @@ -1496,7 +1712,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains * sk with connection information (IP addresses, etc.) May not contain * cgroup info if it is a req sock. - * @type: The type of program to be executed + * @atype: The type of program to be executed * * socket passed is expected to be of type INET or INET6. * @@ -1607,15 +1823,11 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; - func_proto = cgroup_current_func_proto(func_id, prog); - if (func_proto) - return func_proto; - switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -1670,7 +1882,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { * @ppos: value-result argument: value is position at which read from or write * to sysctl is happening, result is new position if program overrode it, * initial value otherwise - * @type: type of program to be executed + * @atype: type of program to be executed * * Program is run when sysctl is being accessed, either read or written, and * can allow or deny such access. @@ -1679,7 +1891,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { * returned value != 1 during execution. In all other cases 0 is returned. */ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, - struct ctl_table *table, int write, + const struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, enum cgroup_bpf_attach_type atype) { @@ -1785,7 +1997,7 @@ static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx, } int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, - int *optname, char __user *optval, + int *optname, sockptr_t optval, int *optlen, char **kernel_optval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); @@ -1808,7 +2020,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, ctx.optlen = *optlen; - if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) { + if (copy_from_sockptr(ctx.optval, optval, + min(*optlen, max_optlen))) { ret = -EFAULT; goto out; } @@ -1826,6 +2039,12 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, ret = 1; } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ + if (*optlen > PAGE_SIZE && ctx.optlen >= 0) { + pr_info_once("bpf setsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", + ctx.optlen, max_optlen); + ret = 0; + goto out; + } ret = -EFAULT; } else { /* optlen within bounds, run kernel handler */ @@ -1869,8 +2088,8 @@ out: } int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, - int optname, char __user *optval, - int __user *optlen, int max_optlen, + int optname, sockptr_t optval, + sockptr_t optlen, int max_optlen, int retval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); @@ -1881,8 +2100,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, .optname = optname, .current_task = current, }; + int orig_optlen; int ret; + orig_optlen = max_optlen; ctx.optlen = max_optlen; max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) @@ -1895,8 +2116,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, * one that kernel returned as well to let * BPF programs inspect the value. */ - - if (get_user(ctx.optlen, optlen)) { + if (copy_from_sockptr(&ctx.optlen, optlen, + sizeof(ctx.optlen))) { ret = -EFAULT; goto out; } @@ -1905,9 +2126,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, ret = -EFAULT; goto out; } + orig_optlen = ctx.optlen; - if (copy_from_user(ctx.optval, optval, - min(ctx.optlen, max_optlen)) != 0) { + if (copy_from_sockptr(ctx.optval, optval, + min(ctx.optlen, max_optlen))) { ret = -EFAULT; goto out; } @@ -1921,14 +2143,25 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, if (ret < 0) goto out; - if (ctx.optlen > max_optlen || ctx.optlen < 0) { + if (!sockptr_is_null(optval) && + (ctx.optlen > max_optlen || ctx.optlen < 0)) { + if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) { + pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", + ctx.optlen, max_optlen); + ret = retval; + goto out; + } ret = -EFAULT; goto out; } if (ctx.optlen != 0) { - if (copy_to_user(optval, ctx.optval, ctx.optlen) || - put_user(ctx.optlen, optlen)) { + if (!sockptr_is_null(optval) && + copy_to_sockptr(optval, ctx.optval, ctx.optlen)) { + ret = -EFAULT; + goto out; + } + if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) { ret = -EFAULT; goto out; } @@ -2037,7 +2270,7 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -2137,10 +2370,6 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; - func_proto = cgroup_current_func_proto(func_id, prog); - if (func_proto) - return func_proto; - switch (func_id) { case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; @@ -2155,7 +2384,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2223,10 +2452,12 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); - *insn++ = BPF_STX_MEM( - BPF_SIZEOF(u32), treg, si->src_reg, + *insn++ = BPF_RAW_INSN( + BPF_CLASS(si->code) | BPF_MEM | BPF_SIZEOF(u32), + treg, si->src_reg, bpf_ctx_narrow_access_offset( - 0, sizeof(u32), sizeof(loff_t))); + 0, sizeof(u32), sizeof(loff_t)), + si->imm); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); @@ -2282,10 +2513,6 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; - func_proto = cgroup_current_func_proto(func_id, prog); - if (func_proto) - return func_proto; - switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_get_netns_cookie: @@ -2310,7 +2537,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2349,22 +2576,22 @@ static bool cg_sockopt_is_valid_access(int off, int size, } switch (off) { - case offsetof(struct bpf_sockopt, sk): + case bpf_ctx_range_ptr(struct bpf_sockopt, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; - case offsetof(struct bpf_sockopt, optval): + case bpf_ctx_range_ptr(struct bpf_sockopt, optval): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; - case offsetof(struct bpf_sockopt, optval_end): + case bpf_ctx_range_ptr(struct bpf_sockopt, optval_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; - case offsetof(struct bpf_sockopt, retval): + case bpf_ctx_range(struct bpf_sockopt, retval): if (size != size_default) return false; return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; @@ -2376,10 +2603,17 @@ static bool cg_sockopt_is_valid_access(int off, int size, return true; } -#define CG_SOCKOPT_ACCESS_FIELD(T, F) \ - T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \ - si->dst_reg, si->src_reg, \ - offsetof(struct bpf_sockopt_kern, F)) +#define CG_SOCKOPT_READ_FIELD(F) \ + BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sockopt_kern, F)) + +#define CG_SOCKOPT_WRITE_FIELD(F) \ + BPF_RAW_INSN((BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F) | \ + BPF_MEM | BPF_CLASS(si->code)), \ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sockopt_kern, F), \ + si->imm) static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, @@ -2391,25 +2625,25 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sockopt, sk): - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk); + *insn++ = CG_SOCKOPT_READ_FIELD(sk); break; case offsetof(struct bpf_sockopt, level): if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level); + *insn++ = CG_SOCKOPT_WRITE_FIELD(level); else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level); + *insn++ = CG_SOCKOPT_READ_FIELD(level); break; case offsetof(struct bpf_sockopt, optname): if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname); + *insn++ = CG_SOCKOPT_WRITE_FIELD(optname); else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname); + *insn++ = CG_SOCKOPT_READ_FIELD(optname); break; case offsetof(struct bpf_sockopt, optlen): if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen); + *insn++ = CG_SOCKOPT_WRITE_FIELD(optlen); else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen); + *insn++ = CG_SOCKOPT_READ_FIELD(optlen); break; case offsetof(struct bpf_sockopt, retval): BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0); @@ -2429,9 +2663,11 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), treg, treg, offsetof(struct task_struct, bpf_ctx)); - *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), - treg, si->src_reg, - offsetof(struct bpf_cg_run_ctx, retval)); + *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_MEM | + BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), + treg, si->src_reg, + offsetof(struct bpf_cg_run_ctx, retval), + si->imm); *insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sockopt_kern, tmp_reg)); } else { @@ -2447,10 +2683,10 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, } break; case offsetof(struct bpf_sockopt, optval): - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval); + *insn++ = CG_SOCKOPT_READ_FIELD(optval); break; case offsetof(struct bpf_sockopt, optval_end): - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end); + *insn++ = CG_SOCKOPT_READ_FIELD(optval_end); break; } @@ -2490,10 +2726,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_get_retval_proto; @@ -2505,10 +2744,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_set_retval_proto; @@ -2517,27 +2759,3 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } } - -/* Common helpers for cgroup hooks with valid process context. */ -const struct bpf_func_proto * -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; - case BPF_FUNC_get_current_cgroup_id: - return &bpf_get_current_cgroup_id_proto; - case BPF_FUNC_get_current_ancestor_cgroup_id: - return &bpf_get_current_ancestor_cgroup_id_proto; -#ifdef CONFIG_CGROUP_NET_CLASSID - case BPF_FUNC_get_cgroup_classid: - return &bpf_get_cgroup_classid_curr_proto; -#endif - default: - return NULL; - } -} diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 06989d278846..f04a468cf6a7 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -58,7 +58,7 @@ static void *cgroup_iter_seq_start(struct seq_file *seq, loff_t *pos) { struct cgroup_iter_priv *p = seq->private; - mutex_lock(&cgroup_mutex); + cgroup_lock(); /* cgroup_iter doesn't support read across multiple sessions. */ if (*pos > 0) { @@ -89,7 +89,7 @@ static void cgroup_iter_seq_stop(struct seq_file *seq, void *v) { struct cgroup_iter_priv *p = seq->private; - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); /* pass NULL to the prog for post-processing */ if (!v) { @@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = { .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__cgroup, cgroup), - PTR_TO_BTF_ID_OR_NULL }, + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .seq_info = &cgroup_iter_seq_info, }; @@ -294,3 +294,66 @@ static int __init bpf_cgroup_iter_init(void) } late_initcall(bpf_cgroup_iter_init); + +struct bpf_iter_css { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_kern { + struct cgroup_subsys_state *start; + struct cgroup_subsys_state *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, unsigned int flags) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css)); + + kit->start = NULL; + switch (flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + case BPF_CGROUP_ITER_DESCENDANTS_POST: + case BPF_CGROUP_ITER_ANCESTORS_UP: + break; + default: + return -EINVAL; + } + + kit->start = start; + kit->pos = NULL; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + if (!kit->start) + return NULL; + + switch (kit->flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + kit->pos = css_next_descendant_pre(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + kit->pos = css_next_descendant_post(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_ANCESTORS_UP: + kit->pos = kit->pos ? kit->pos->parent : kit->start; + } + + return kit->pos; +} + +__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it) +{ +} + +__bpf_kfunc_end_defs(); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ba3fff17e2f9..c8ae6ab31651 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -18,14 +18,15 @@ */ #include <uapi/linux/btf.h> +#include <crypto/sha1.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> -#include <linux/random.h> -#include <linux/moduleloader.h> +#include <linux/prandom.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> @@ -34,10 +35,14 @@ #include <linux/log2.h> #include <linux/bpf_verifier.h> #include <linux/nodemask.h> +#include <linux/nospec.h> #include <linux/bpf_mem_alloc.h> +#include <linux/memcontrol.h> +#include <linux/execmem.h> +#include <crypto/sha2.h> #include <asm/barrier.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] @@ -59,6 +64,7 @@ #define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] +#define OFF insn->off #define IMM insn->imm struct bpf_mem_alloc bpf_global_ma; @@ -85,23 +91,28 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns return NULL; } +/* tell bpf programs that include vmlinux.h kernel's PAGE_SIZE */ +enum page_size_enum { + __PAGE_SIZE = PAGE_SIZE +}; + struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog_aux *aux; struct bpf_prog *fp; - size = round_up(size, PAGE_SIZE); + size = round_up(size, __PAGE_SIZE); fp = __vmalloc(size, gfp_flags); if (fp == NULL) return NULL; - aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags); + aux = kzalloc(sizeof(*aux), bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (aux == NULL) { vfree(fp); return NULL; } - fp->active = alloc_percpu_gfp(int, GFP_KERNEL_ACCOUNT | gfp_extra_flags); + fp->active = alloc_percpu_gfp(int, bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (!fp->active) { vfree(fp); kfree(aux); @@ -110,6 +121,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag fp->pages = size / PAGE_SIZE; fp->aux = aux; + fp->aux->main_prog_aux = aux; fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); fp->blinding_requested = bpf_jit_blinding_enabled(fp); @@ -118,15 +130,23 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag #endif INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); +#ifdef CONFIG_FINEIBT + INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode); +#endif mutex_init(&fp->aux->used_maps_mutex); + mutex_init(&fp->aux->ext_mutex); mutex_init(&fp->aux->dst_mutex); +#ifdef CONFIG_BPF_SYSCALL + bpf_prog_stream_init(fp); +#endif + return fp; } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *prog; int cpu; @@ -159,7 +179,7 @@ int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) prog->aux->jited_linfo = kvcalloc(prog->aux->nr_linfo, sizeof(*prog->aux->jited_linfo), - GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + bpf_memcg_flags(GFP_KERNEL | __GFP_NOWARN)); if (!prog->aux->jited_linfo) return -ENOMEM; @@ -209,7 +229,7 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const struct bpf_line_info *linfo; void **jited_linfo; - if (!prog->aux->jited_linfo) + if (!prog->aux->jited_linfo || prog->aux->func_idx > prog->aux->func_cnt) /* Userspace did not provide linfo */ return; @@ -234,7 +254,7 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *fp; u32 pages; @@ -276,28 +296,18 @@ void __bpf_prog_free(struct bpf_prog *fp) int bpf_prog_calc_tag(struct bpf_prog *fp) { - const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64); - u32 raw_size = bpf_prog_tag_scratch_size(fp); - u32 digest[SHA1_DIGEST_WORDS]; - u32 ws[SHA1_WORKSPACE_WORDS]; - u32 i, bsize, psize, blocks; + size_t size = bpf_prog_insn_size(fp); struct bpf_insn *dst; bool was_ld_map; - u8 *raw, *todo; - __be32 *result; - __be64 *bits; + u32 i; - raw = vmalloc(raw_size); - if (!raw) + dst = vmalloc(size); + if (!dst) return -ENOMEM; - sha1_init(digest); - memset(ws, 0, sizeof(ws)); - /* We need to take out the map fd for the digest calculation * since they are unstable from user space side. */ - dst = (void *)raw; for (i = 0, was_ld_map = false; i < fp->len; i++) { dst[i] = fp->insnsi[i]; if (!was_ld_map && @@ -317,33 +327,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp) was_ld_map = false; } } - - psize = bpf_prog_insn_size(fp); - memset(&raw[psize], 0, raw_size - psize); - raw[psize++] = 0x80; - - bsize = round_up(psize, SHA1_BLOCK_SIZE); - blocks = bsize / SHA1_BLOCK_SIZE; - todo = raw; - if (bsize - psize >= sizeof(__be64)) { - bits = (__be64 *)(todo + bsize - sizeof(__be64)); - } else { - bits = (__be64 *)(todo + bsize + bits_offset); - blocks++; - } - *bits = cpu_to_be64((psize - 1) << 3); - - while (blocks--) { - sha1_transform(digest, todo, ws); - todo += SHA1_BLOCK_SIZE; - } - - result = (__force __be32 *)digest; - for (i = 0; i < SHA1_DIGEST_WORDS; i++) - result[i] = cpu_to_be32(digest[i]); - memcpy(fp->tag, result, sizeof(fp->tag)); - - vfree(raw); + sha256((u8 *)dst, size, fp->digest); + vfree(dst); return 0; } @@ -368,9 +353,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { - const s32 off_min = S16_MIN, off_max = S16_MAX; + s64 off_min, off_max, off; s32 delta = end_new - end_old; - s32 off = insn->off; + + if (insn->code == (BPF_JMP32 | BPF_JA)) { + off = insn->imm; + off_min = S32_MIN; + off_max = S32_MAX; + } else { + off = insn->off; + off_min = S16_MIN; + off_max = S16_MAX; + } if (curr < pos && curr + off + 1 >= end_old) off += delta; @@ -378,8 +372,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, off -= delta; if (off < off_min || off > off_max) return -ERANGE; - if (!probe_pass) - insn->off = off; + if (!probe_pass) { + if (insn->code == (BPF_JMP32 | BPF_JA)) + insn->imm = off; + else + insn->off = off; + } return 0; } @@ -513,6 +511,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { + int err; + /* Branch offsets can't overflow when program is shrinking, no need * to call bpf_adj_branches(..., true) here */ @@ -520,14 +520,16 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) sizeof(struct bpf_insn) * (prog->len - off - cnt)); prog->len -= cnt; - return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false)); + err = bpf_adj_branches(prog, off, off + cnt, off, false); + WARN_ON_ONCE(err); + return err; } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; - for (i = 0; i < fp->aux->func_cnt; i++) + for (i = 0; i < fp->aux->real_func_cnt; i++) bpf_prog_kallsyms_del(fp->aux->func[i]); } @@ -577,7 +579,7 @@ bpf_prog_ksym_set_name(struct bpf_prog *prog) sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); /* prog->aux->name will be ignored if full btf name is available */ - if (prog->aux->func_info_cnt) { + if (prog->aux->func_info_cnt && prog->aux->func_idx < prog->aux->func_info_cnt) { type = btf_type_by_id(prog->aux->btf, prog->aux->func_info[prog->aux->func_idx].type_id); func_name = btf_name_by_offset(prog->aux->btf, type->name_off); @@ -611,7 +613,11 @@ static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) if (val < ksym->start) return -1; - if (val >= ksym->end) + /* Ensure that we detect return addresses as part of the program, when + * the final instruction is a call for a program part of the stack + * trace. Therefore, do val > ksym->end instead of val >= ksym->end. + */ + if (val > ksym->end) return 1; return 0; @@ -659,7 +665,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || - !bpf_capable()) + !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); @@ -667,6 +673,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp) fp->aux->ksym.prog = true; bpf_ksym_add(&fp->aux->ksym); + +#ifdef CONFIG_FINEIBT + /* + * When FineIBT, code in the __cfi_foo() symbols can get executed + * and hence unwinder needs help. + */ + if (cfi_mode != CFI_FINEIBT) + return; + + snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN, + "__cfi_%s", fp->aux->ksym.name); + + fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16; + fp->aux->ksym_prefix.end = (unsigned long) fp->bpf_func; + + bpf_ksym_add(&fp->aux->ksym_prefix); +#endif } void bpf_prog_kallsyms_del(struct bpf_prog *fp) @@ -675,6 +698,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp) return; bpf_ksym_del(&fp->aux->ksym); +#ifdef CONFIG_FINEIBT + if (cfi_mode != CFI_FINEIBT) + return; + bpf_ksym_del(&fp->aux->ksym_prefix); +#endif } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) @@ -685,11 +713,11 @@ static struct bpf_ksym *bpf_ksym_find(unsigned long addr) return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } -const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, +int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { struct bpf_ksym *ksym; - char *ret = NULL; + int ret = 0; rcu_read_lock(); ksym = bpf_ksym_find(addr); @@ -697,9 +725,8 @@ 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); + ret = strscpy(sym, ksym->name, KSYM_NAME_LEN); - ret = sym; if (size) *size = symbol_end - symbol_start; if (off) @@ -721,9 +748,12 @@ bool is_bpf_text_address(unsigned long addr) return ret; } -static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) +struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { - struct bpf_ksym *ksym = bpf_ksym_find(addr); + struct bpf_ksym *ksym; + + WARN_ON_ONCE(!rcu_read_lock_held()); + ksym = bpf_ksym_find(addr); return ksym && ksym->prog ? container_of(ksym, struct bpf_prog_aux, ksym)->prog : @@ -763,7 +793,7 @@ 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; @@ -799,7 +829,7 @@ 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; @@ -843,7 +873,12 @@ static LIST_HEAD(pack_list); * CONFIG_MMU=n. Use PAGE_SIZE in these cases. */ #ifdef PMD_SIZE -#define BPF_PROG_PACK_SIZE (PMD_SIZE * num_possible_nodes()) +/* PMD_SIZE is really big for some archs. It doesn't make sense to + * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to + * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be + * greater than or equal to 2MB. + */ +#define BPF_PROG_PACK_SIZE (SZ_2M * num_possible_nodes()) #else #define BPF_PROG_PACK_SIZE PAGE_SIZE #endif @@ -853,23 +888,30 @@ 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 = module_alloc(BPF_PROG_PACK_SIZE); - if (!pack->ptr) { - kfree(pack); - return NULL; - } + pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE); + 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) @@ -882,11 +924,18 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) mutex_lock(&pack_mutex); if (size > BPF_PROG_PACK_SIZE) { size = round_up(size, PAGE_SIZE); - ptr = module_alloc(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; } @@ -912,20 +961,20 @@ out: return ptr; } -void bpf_prog_pack_free(struct bpf_binary_header *hdr) +void bpf_prog_pack_free(void *ptr, u32 size) { struct bpf_prog_pack *pack = NULL, *tmp; unsigned int nbits; unsigned long pos; mutex_lock(&pack_mutex); - if (hdr->size > BPF_PROG_PACK_SIZE) { - module_memfree(hdr); + if (size > BPF_PROG_PACK_SIZE) { + bpf_jit_free_exec(ptr); goto out; } list_for_each_entry(tmp, &pack_list, list) { - if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) { + if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) { pack = tmp; break; } @@ -934,17 +983,17 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr) if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) goto out; - nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); - pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; + nbits = BPF_PROG_SIZE_TO_NBITS(size); + pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; - WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size), + WARN_ONCE(bpf_arch_text_invalidate(ptr, size), "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); bitmap_clear(pack->bitmap, pos, nbits); if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, BPF_PROG_CHUNK_COUNT, 0) == 0) { list_del(&pack->list); - module_memfree(pack->ptr); + bpf_jit_free_exec(pack->ptr); kfree(pack); } out: @@ -970,7 +1019,7 @@ static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); - bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2, + bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } @@ -995,12 +1044,12 @@ 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 * @@ -1084,8 +1133,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, *rw_header = kvmalloc(size, GFP_KERNEL); if (!*rw_header) { - bpf_arch_text_copy(&ro_header->size, &size, sizeof(size)); - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); bpf_jit_uncharge_modmem(size); return NULL; } @@ -1105,8 +1153,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, } /* Copy JITed text from rw_header to its final location, the ro_header. */ -int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, - struct bpf_binary_header *ro_header, +int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header) { void *ptr; @@ -1116,7 +1163,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, kvfree(rw_header); if (IS_ERR(ptr)) { - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, ro_header->size); return PTR_ERR(ptr); } return 0; @@ -1137,7 +1184,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, { u32 size = ro_header->size; - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); kvfree(rw_header); bpf_jit_uncharge_modmem(size); } @@ -1185,6 +1232,7 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog, s16 off = insn->off; s32 imm = insn->imm; u8 *addr; + int err; *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; if (!*func_addr_fixed) { @@ -1195,10 +1243,15 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog, if (!extra_pass) addr = NULL; else if (prog->aux->func && - off >= 0 && off < prog->aux->func_cnt) + off >= 0 && off < prog->aux->real_func_cnt) addr = (u8 *)prog->aux->func[off]->bpf_func; else return -EINVAL; + } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && + bpf_jit_supports_far_kfunc_call()) { + err = bpf_get_kfunc_addr(prog, insn->imm, insn->off, &addr); + if (err) + return err; } else { /* Address of a BPF helper call. Since part of the core * kernel, it's always at a fixed location. __bpf_call_base @@ -1212,6 +1265,13 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog, return 0; } +const char *bpf_jit_get_prog_name(struct bpf_prog *prog) +{ + if (prog->aux->ksym.prog) + return prog->aux->ksym.name; + return prog->aux->name; +} + static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff, @@ -1263,7 +1323,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX); + *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_ALU64 | BPF_ADD | BPF_K: @@ -1277,7 +1337,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX); + *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_JMP | BPF_JEQ | BPF_K: @@ -1390,6 +1450,23 @@ void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) bpf_prog_clone_free(fp_other); } +static void adjust_insn_arrays(struct bpf_prog *prog, u32 off, u32 len) +{ +#ifdef CONFIG_BPF_SYSCALL + struct bpf_map *map; + int i; + + if (len <= 1) + return; + + for (i = 0; i < prog->aux->used_map_cnt; i++) { + map = prog->aux->used_maps[i]; + if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) + bpf_insn_array_adjust(map, off, len); + } +#endif +} + struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) { struct bpf_insn insn_buff[16], aux[2]; @@ -1445,6 +1522,9 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) clone = tmp; insn_delta = rewritten - 1; + /* Instructions arrays must be updated using absolute xlated offsets */ + adjust_insn_arrays(clone, prog->aux->subprog_start + i, rewritten); + /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; insn_cnt += insn_delta; @@ -1515,6 +1595,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(ALU64, DIV, X), \ INSN_3(ALU64, MOD, X), \ INSN_2(ALU64, NEG), \ + INSN_3(ALU64, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU64, ADD, K), \ INSN_3(ALU64, SUB, K), \ @@ -1583,14 +1664,18 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ + INSN_2(JMP32, JA), \ + /* Atomic operations. */ \ + INSN_3(STX, ATOMIC, B), \ + INSN_3(STX, ATOMIC, H), \ + INSN_3(STX, ATOMIC, W), \ + INSN_3(STX, ATOMIC, DW), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ - INSN_3(STX, ATOMIC, W), \ - INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ @@ -1602,6 +1687,9 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(LDX, MEM, H), \ INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ + INSN_3(LDX, MEMSX, B), \ + INSN_3(LDX, MEMSX, H), \ + INSN_3(LDX, MEMSX, W), \ /* Immediate based. */ \ INSN_3(LD, IMM, DW) @@ -1620,6 +1708,8 @@ bool bpf_opcode_in_insntable(u8 code) [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, + [BPF_JMP | BPF_JA | BPF_X] = true, + [BPF_JMP | BPF_JCOND] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL @@ -1627,12 +1717,6 @@ bool bpf_opcode_in_insntable(u8 code) } #ifndef CONFIG_BPF_JIT_ALWAYS_ON -u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) -{ - memset(dst, 0, size); - return -EFAULT; -} - /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers @@ -1658,6 +1742,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL @@ -1725,13 +1812,36 @@ select_insn: DST = -DST; CONT; ALU_MOV_X: - DST = (u32) SRC; + switch (OFF) { + case 0: + DST = (u32) SRC; + break; + case 8: + DST = (u32)(s8) SRC; + break; + case 16: + DST = (u32)(s16) SRC; + break; + } CONT; ALU_MOV_K: DST = (u32) IMM; CONT; ALU64_MOV_X: - DST = SRC; + switch (OFF) { + case 0: + DST = SRC; + break; + case 8: + DST = (s8) SRC; + break; + case 16: + DST = (s16) SRC; + break; + case 32: + DST = (s32) SRC; + break; + } CONT; ALU64_MOV_K: DST = IMM; @@ -1753,36 +1863,114 @@ select_insn: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: - div64_u64_rem(DST, SRC, &AX); - DST = AX; + switch (OFF) { + case 0: + div64_u64_rem(DST, SRC, &AX); + DST = AX; + break; + case 1: + AX = div64_s64(DST, SRC); + DST = DST - AX * SRC; + break; + } CONT; ALU_MOD_X: - AX = (u32) DST; - DST = do_div(AX, (u32) SRC); + switch (OFF) { + case 0: + AX = (u32) DST; + DST = do_div(AX, (u32) SRC); + break; + case 1: + AX = abs((s32)DST); + AX = do_div(AX, abs((s32)SRC)); + if ((s32)DST < 0) + DST = (u32)-AX; + else + DST = (u32)AX; + break; + } CONT; ALU64_MOD_K: - div64_u64_rem(DST, IMM, &AX); - DST = AX; + switch (OFF) { + case 0: + div64_u64_rem(DST, IMM, &AX); + DST = AX; + break; + case 1: + AX = div64_s64(DST, IMM); + DST = DST - AX * IMM; + break; + } CONT; ALU_MOD_K: - AX = (u32) DST; - DST = do_div(AX, (u32) IMM); + switch (OFF) { + case 0: + AX = (u32) DST; + DST = do_div(AX, (u32) IMM); + break; + case 1: + AX = abs((s32)DST); + AX = do_div(AX, abs((s32)IMM)); + if ((s32)DST < 0) + DST = (u32)-AX; + else + DST = (u32)AX; + break; + } CONT; ALU64_DIV_X: - DST = div64_u64(DST, SRC); + switch (OFF) { + case 0: + DST = div64_u64(DST, SRC); + break; + case 1: + DST = div64_s64(DST, SRC); + break; + } CONT; ALU_DIV_X: - AX = (u32) DST; - do_div(AX, (u32) SRC); - DST = (u32) AX; + switch (OFF) { + case 0: + AX = (u32) DST; + do_div(AX, (u32) SRC); + DST = (u32) AX; + break; + case 1: + AX = abs((s32)DST); + do_div(AX, abs((s32)SRC)); + if (((s32)DST < 0) == ((s32)SRC < 0)) + DST = (u32)AX; + else + DST = (u32)-AX; + break; + } CONT; ALU64_DIV_K: - DST = div64_u64(DST, IMM); + switch (OFF) { + case 0: + DST = div64_u64(DST, IMM); + break; + case 1: + DST = div64_s64(DST, IMM); + break; + } CONT; ALU_DIV_K: - AX = (u32) DST; - do_div(AX, (u32) IMM); - DST = (u32) AX; + switch (OFF) { + case 0: + AX = (u32) DST; + do_div(AX, (u32) IMM); + DST = (u32) AX; + break; + case 1: + AX = abs((s32)DST); + do_div(AX, abs((s32)IMM)); + if (((s32)DST < 0) == ((s32)IMM < 0)) + DST = (u32)AX; + else + DST = (u32)-AX; + break; + } CONT; ALU_END_TO_BE: switch (IMM) { @@ -1810,6 +1998,19 @@ select_insn: break; } CONT; + ALU64_END_TO_LE: + switch (IMM) { + case 16: + DST = (__force u16) __swab16(DST); + break; + case 32: + DST = (__force u32) __swab32(DST); + break; + case 64: + DST = (__force u64) __swab64(DST); + break; + } + CONT; /* CALL */ JMP_CALL: @@ -1859,6 +2060,9 @@ out: JMP_JA: insn += insn->off; CONT; + JMP32_JA: + insn += insn->imm; + CONT; JMP_EXIT: return BPF_R0; /* JMP */ @@ -1901,18 +2105,17 @@ out: #undef COND_JMP /* ST, STX and LDX*/ ST_NOSPEC: - /* Speculation barrier for mitigating Speculative Store Bypass. - * In case of arm64, we rely on the firmware mitigation as - * controlled via the ssbd kernel parameter. Whenever the - * mitigation is enabled, it works for all of the kernel code - * with no need to provide any additional instructions here. - * In case of x86, we use 'lfence' insn for mitigation. We - * reuse preexisting logic from Spectre v1 mitigation that - * happens to produce the required code on x86 for v4 as well. + /* Speculation barrier for mitigating Speculative Store Bypass, + * Bounds-Check Bypass and Type Confusion. In case of arm64, we + * rely on the firmware mitigation as controlled via the ssbd + * kernel parameter. Whenever the mitigation is enabled, it + * works for all of the kernel code with no need to provide any + * additional instructions here. In case of x86, we use 'lfence' + * insn for mitigation. We reuse preexisting logic from Spectre + * v1 mitigation that happens to produce the required code on + * x86 for v4 as well. */ -#ifdef CONFIG_X86 barrier_nospec(); -#endif CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ @@ -1925,8 +2128,8 @@ out: DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEM_##SIZEOP: \ - bpf_probe_read_kernel(&DST, sizeof(SIZE), \ - (const void *)(long) (SRC + insn->off)); \ + bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ + (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; @@ -1936,29 +2139,53 @@ out: LDST(DW, u64) #undef LDST +#define LDSX(SIZEOP, SIZE) \ + LDX_MEMSX_##SIZEOP: \ + DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ + CONT; \ + LDX_PROBE_MEMSX_##SIZEOP: \ + bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ + (const void *)(long) (SRC + insn->off)); \ + DST = *((SIZE *)&DST); \ + CONT; + + LDSX(B, s8) + LDSX(H, s16) + LDSX(W, s32) +#undef LDSX + #define ATOMIC_ALU_OP(BOP, KOP) \ case BOP: \ if (BPF_SIZE(insn->code) == BPF_W) \ atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \ (DST + insn->off)); \ - else \ + else if (BPF_SIZE(insn->code) == BPF_DW) \ atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ (DST + insn->off)); \ + else \ + goto default_label; \ break; \ case BOP | BPF_FETCH: \ if (BPF_SIZE(insn->code) == BPF_W) \ SRC = (u32) atomic_fetch_##KOP( \ (u32) SRC, \ (atomic_t *)(unsigned long) (DST + insn->off)); \ - else \ + else if (BPF_SIZE(insn->code) == BPF_DW) \ SRC = (u64) atomic64_fetch_##KOP( \ (u64) SRC, \ (atomic64_t *)(unsigned long) (DST + insn->off)); \ + else \ + goto default_label; \ break; STX_ATOMIC_DW: STX_ATOMIC_W: + STX_ATOMIC_H: + STX_ATOMIC_B: switch (IMM) { + /* Atomic read-modify-write instructions support only W and DW + * size modifiers. + */ ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) @@ -1970,20 +2197,63 @@ out: SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); - else + else if (BPF_SIZE(insn->code) == BPF_DW) SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); + else + goto default_label; break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); - else + else if (BPF_SIZE(insn->code) == BPF_DW) BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); + else + goto default_label; + break; + /* Atomic load and store instructions support all size + * modifiers. + */ + case BPF_LOAD_ACQ: + switch (BPF_SIZE(insn->code)) { +#define LOAD_ACQUIRE(SIZEOP, SIZE) \ + case BPF_##SIZEOP: \ + DST = (SIZE)smp_load_acquire( \ + (SIZE *)(unsigned long)(SRC + insn->off)); \ + break; + LOAD_ACQUIRE(B, u8) + LOAD_ACQUIRE(H, u16) + LOAD_ACQUIRE(W, u32) +#ifdef CONFIG_64BIT + LOAD_ACQUIRE(DW, u64) +#endif +#undef LOAD_ACQUIRE + default: + goto default_label; + } + break; + case BPF_STORE_REL: + switch (BPF_SIZE(insn->code)) { +#define STORE_RELEASE(SIZEOP, SIZE) \ + case BPF_##SIZEOP: \ + smp_store_release( \ + (SIZE *)(unsigned long)(DST + insn->off), (SIZE)SRC); \ + break; + STORE_RELEASE(B, u8) + STORE_RELEASE(H, u16) + STORE_RELEASE(W, u32) +#ifdef CONFIG_64BIT + STORE_RELEASE(DW, u64) +#endif +#undef STORE_RELEASE + default: + goto default_label; + } break; default: @@ -2011,6 +2281,7 @@ 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); \ @@ -2024,6 +2295,7 @@ 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; \ @@ -2058,14 +2330,16 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size), -static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, - const struct bpf_insn *insn) = { +static __maybe_unused +u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, + const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST +#ifdef CONFIG_BPF_SYSCALL void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) { stack_depth = max_t(u32, stack_depth, 1); @@ -2074,8 +2348,9 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } +#endif +#endif -#else static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { @@ -2085,36 +2360,84 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, WARN_ON_ONCE(1); return 0; } -#endif -bool bpf_prog_map_compatible(struct bpf_map *map, - const struct bpf_prog *fp) +static bool __bpf_prog_map_compatible(struct bpf_map *map, + const struct bpf_prog *fp) { enum bpf_prog_type prog_type = resolve_prog_type(fp); - bool ret; + struct bpf_prog_aux *aux = fp->aux; + enum bpf_cgroup_storage_type i; + bool ret = false; + u64 cookie; if (fp->kprobe_override) - return false; + return ret; - spin_lock(&map->owner.lock); - if (!map->owner.type) { - /* There's no owner yet where we could check for - * compatibility. - */ - map->owner.type = prog_type; - map->owner.jited = fp->jited; - map->owner.xdp_has_frags = fp->aux->xdp_has_frags; + spin_lock(&map->owner_lock); + /* There's no owner yet where we could check for compatibility. */ + if (!map->owner) { + map->owner = bpf_map_owner_alloc(map); + if (!map->owner) + goto err; + map->owner->type = prog_type; + map->owner->jited = fp->jited; + map->owner->xdp_has_frags = aux->xdp_has_frags; + map->owner->expected_attach_type = fp->expected_attach_type; + map->owner->attach_func_proto = aux->attach_func_proto; + for_each_cgroup_storage_type(i) { + map->owner->storage_cookie[i] = + aux->cgroup_storage[i] ? + aux->cgroup_storage[i]->cookie : 0; + } ret = true; } else { - ret = map->owner.type == prog_type && - map->owner.jited == fp->jited && - map->owner.xdp_has_frags == fp->aux->xdp_has_frags; + ret = map->owner->type == prog_type && + map->owner->jited == fp->jited && + map->owner->xdp_has_frags == aux->xdp_has_frags; + if (ret && + map->map_type == BPF_MAP_TYPE_PROG_ARRAY && + map->owner->expected_attach_type != fp->expected_attach_type) + ret = false; + for_each_cgroup_storage_type(i) { + if (!ret) + break; + cookie = aux->cgroup_storage[i] ? + aux->cgroup_storage[i]->cookie : 0; + ret = map->owner->storage_cookie[i] == cookie || + !cookie; + } + if (ret && + map->owner->attach_func_proto != aux->attach_func_proto) { + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_STRUCT_OPS: + ret = false; + break; + default: + break; + } + } } - spin_unlock(&map->owner.lock); - +err: + spin_unlock(&map->owner_lock); return ret; } +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp) +{ + /* XDP programs inserted into maps are not guaranteed to run on + * a particular netdev (and can run outside driver context entirely + * in the case of devmap and cpumap). Until device checks + * are implemented, prohibit adding dev-bound programs to program maps. + */ + if (bpf_prog_is_dev_bound(fp->aux)) + return false; + + return __bpf_prog_map_compatible(map, fp); +} + static int bpf_check_tail_call(const struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; @@ -2127,7 +2450,7 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) if (!map_type_contains_progs(map)) continue; - if (!bpf_prog_map_compatible(map, fp)) { + if (!__bpf_prog_map_compatible(map, fp)) { ret = -EINVAL; goto out; } @@ -2138,15 +2461,27 @@ out: return ret; } -static void bpf_prog_select_func(struct bpf_prog *fp) +static bool bpf_prog_select_interpreter(struct bpf_prog *fp) { + bool select_interpreter = false; #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + u32 idx = (round_up(stack_depth, 32) / 32) - 1; - fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; + /* may_goto may cause stack size > 512, leading to idx out-of-bounds. + * But for non-JITed programs, we don't need bpf_func, so no bounds + * check needed. + */ + if (idx < ARRAY_SIZE(interpreters)) { + fp->bpf_func = interpreters[idx]; + select_interpreter = true; + } else { + fp->bpf_func = __bpf_prog_ret0_warn; + } #else fp->bpf_func = __bpf_prog_ret0_warn; #endif + return select_interpreter; } /** @@ -2174,7 +2509,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) bpf_prog_has_kfunc_call(fp)) jit_needed = true; - bpf_prog_select_func(fp); + if (!bpf_prog_select_interpreter(fp)) + jit_needed = true; /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -2182,7 +2518,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ - if (!bpf_prog_is_dev_bound(fp->aux)) { + if (!bpf_prog_is_offloaded(fp->aux)) { *err = bpf_prog_alloc_jited_linfo(fp); if (*err) return fp; @@ -2200,7 +2536,9 @@ 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 @@ -2234,13 +2572,14 @@ 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) @@ -2500,12 +2839,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; + bool sleepable; u32 i; + sleepable = aux->prog->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); + if (sleepable) + atomic64_dec(&map->sleepable_refcnt); bpf_map_put(map); } } @@ -2516,8 +2859,7 @@ static void bpf_free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } -void __bpf_free_used_btfs(struct bpf_prog_aux *aux, - struct btf_mod_pair *used_btfs, u32 len) +void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len) { #ifdef CONFIG_BPF_SYSCALL struct btf_mod_pair *btf_mod; @@ -2534,7 +2876,7 @@ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, static void bpf_free_used_btfs(struct bpf_prog_aux *aux) { - __bpf_free_used_btfs(aux, aux->used_btfs, aux->used_btf_cnt); + __bpf_free_used_btfs(aux->used_btfs, aux->used_btf_cnt); kfree(aux->used_btfs); } @@ -2546,6 +2888,7 @@ static void bpf_prog_free_deferred(struct work_struct *work) aux = container_of(work, struct bpf_prog_aux, work); #ifdef CONFIG_BPF_SYSCALL bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab); + bpf_prog_stream_free(aux->prog); #endif #ifdef CONFIG_CGROUP_BPF if (aux->cgroup_atype != CGROUP_BPF_ATTACH_TYPE_INVALID) @@ -2554,14 +2897,14 @@ static void bpf_prog_free_deferred(struct work_struct *work) bpf_free_used_maps(aux); bpf_free_used_btfs(aux); if (bpf_prog_is_dev_bound(aux)) - bpf_prog_offload_destroy(aux->prog); + bpf_prog_dev_bound_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); - for (i = 0; i < aux->func_cnt; i++) { + for (i = 0; i < aux->real_func_cnt; i++) { /* We can just unlink the subprog poke descriptor table as * it was originally linked to the main program and is also * released along with it. @@ -2569,7 +2912,7 @@ static void bpf_prog_free_deferred(struct work_struct *work) aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); } - if (aux->func_cnt) { + if (aux->real_func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); } else { @@ -2583,12 +2926,13 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } 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) @@ -2661,6 +3005,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) return NULL; } +const struct bpf_func_proto * __weak bpf_get_perf_event_read_value_proto(void) +{ + return NULL; +} + u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) @@ -2671,7 +3020,10 @@ EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { - .func = NULL, + /* func is unused for tail_call, we set it to pass the + * get_helper_proto check + */ + .func = BPF_PTR_POISON, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_CTX, @@ -2695,7 +3047,7 @@ void __weak bpf_jit_compile(struct bpf_prog *prog) { } -bool __weak bpf_helper_changes_pkt_data(void *func) +bool __weak bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { return false; } @@ -2713,17 +3065,82 @@ bool __weak bpf_jit_needs_zext(void) return false; } +/* By default, enable the verifier's mitigations against Spectre v1 and v4 for + * all archs. The value returned must not change at runtime as there is + * currently no support for reloading programs that were loaded without + * mitigations. + */ +bool __weak bpf_jit_bypass_spec_v1(void) +{ + return false; +} + +bool __weak bpf_jit_bypass_spec_v4(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; } +bool __weak bpf_jit_supports_far_kfunc_call(void) +{ + return false; +} + +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 + * as atomic_xchg() on pointer-sized words. + */ +bool __weak bpf_jit_supports_ptr_xchg(void) +{ + return false; +} + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ @@ -2733,8 +3150,9 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, return -EFAULT; } -int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, - void *addr1, void *addr2) +int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, + enum bpf_text_poke_type new_t, void *old_addr, + void *new_addr) { return -ENOTSUPP; } @@ -2749,6 +3167,75 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len) return -ENOTSUPP; } +bool __weak bpf_jit_supports_exceptions(void) +{ + return false; +} + +bool __weak bpf_jit_supports_private_stack(void) +{ + return false; +} + +void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) +{ +} + +bool __weak bpf_jit_supports_timed_may_goto(void) +{ + return false; +} + +u64 __weak arch_bpf_timed_may_goto(void) +{ + return 0; +} + +static noinline void bpf_prog_report_may_goto_violation(void) +{ +#ifdef CONFIG_BPF_SYSCALL + struct bpf_stream_stage ss; + struct bpf_prog *prog; + + prog = bpf_prog_find_from_stack(); + if (!prog) + return; + bpf_stream_stage(ss, prog, BPF_STDERR, ({ + bpf_stream_printk(ss, "ERROR: Timeout detected for may_goto instruction\n"); + bpf_stream_dump_stack(ss); + })); +#endif +} + +u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *p) +{ + u64 time = ktime_get_mono_fast_ns(); + + /* Populate the timestamp for this stack frame, and refresh count. */ + if (!p->timestamp) { + p->timestamp = time; + return BPF_MAX_TIMED_LOOPS; + } + /* Check if we've exhausted our time slice, and zero count. */ + if (unlikely(time - p->timestamp >= (NSEC_PER_SEC / 4))) { + bpf_prog_report_may_goto_violation(); + return 0; + } + /* Refresh the count for the stack frame. */ + return BPF_MAX_TIMED_LOOPS; +} + +/* for configs without MMU or 32-bit */ +__weak const struct bpf_map_ops arena_map_ops; +__weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return 0; +} +__weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return 0; +} + #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { @@ -2770,3 +3257,84 @@ EXPORT_SYMBOL(bpf_stats_enabled_key); EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); + +#ifdef CONFIG_BPF_SYSCALL + +int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep, + const char **linep, int *nump) +{ + int idx = -1, insn_start, insn_end, len; + struct bpf_line_info *linfo; + void **jited_linfo; + struct btf *btf; + int nr_linfo; + + btf = prog->aux->btf; + linfo = prog->aux->linfo; + jited_linfo = prog->aux->jited_linfo; + + if (!btf || !linfo || !jited_linfo) + return -EINVAL; + len = prog->aux->func ? prog->aux->func[prog->aux->func_idx]->len : prog->len; + + linfo = &prog->aux->linfo[prog->aux->linfo_idx]; + jited_linfo = &prog->aux->jited_linfo[prog->aux->linfo_idx]; + + insn_start = linfo[0].insn_off; + insn_end = insn_start + len; + nr_linfo = prog->aux->nr_linfo - prog->aux->linfo_idx; + + for (int i = 0; i < nr_linfo && + linfo[i].insn_off >= insn_start && linfo[i].insn_off < insn_end; i++) { + if (jited_linfo[i] >= (void *)ip) + break; + idx = i; + } + + if (idx == -1) + return -ENOENT; + + /* Get base component of the file path. */ + *filep = btf_name_by_offset(btf, linfo[idx].file_name_off); + *filep = kbasename(*filep); + /* Obtain the source line, and strip whitespace in prefix. */ + *linep = btf_name_by_offset(btf, linfo[idx].line_off); + while (isspace(**linep)) + *linep += 1; + *nump = BPF_LINE_INFO_LINE_NUM(linfo[idx].line_col); + return 0; +} + +struct walk_stack_ctx { + struct bpf_prog *prog; +}; + +static bool find_from_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp) +{ + struct walk_stack_ctx *ctxp = cookie; + struct bpf_prog *prog; + + /* + * The RCU read lock is held to safely traverse the latch tree, but we + * don't need its protection when accessing the prog, since it has an + * active stack frame on the current stack trace, and won't disappear. + */ + rcu_read_lock(); + prog = bpf_prog_ksym_find(ip); + rcu_read_unlock(); + if (!prog) + return true; + /* Make sure we return the main prog if we found a subprog */ + ctxp->prog = prog->aux->main_prog_aux->prog; + return false; +} + +struct bpf_prog *bpf_prog_find_from_stack(void) +{ + struct walk_stack_ctx ctx = {}; + + arch_bpf_stack_walk(find_from_stack_cb, &ctx); + return ctx.prog; +} + +#endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e0b2d016f0bf..703e5df1f4ef 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -24,16 +24,17 @@ #include <linux/filter.h> #include <linux/ptr_ring.h> #include <net/xdp.h> +#include <net/hotdata.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/kthread.h> -#include <linux/capability.h> +#include <linux/completion.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> -#include <linux/netdevice.h> /* netif_receive_skb_list */ -#include <linux/etherdevice.h> /* eth_type_trans */ +#include <linux/netdevice.h> +#include <net/gro.h> /* General idea: XDP packets getting XDP redirected to another CPU, * will maximum be stored/queued for one driver ->poll() call. It is @@ -61,19 +62,16 @@ struct bpf_cpu_map_entry { /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ struct xdp_bulk_queue __percpu *bulkq; - struct bpf_cpu_map *cmap; - /* Queue with potential multi-producers, and single-consumer kthread */ struct ptr_ring *queue; struct task_struct *kthread; struct bpf_cpumap_val value; struct bpf_prog *prog; + struct gro_node gro; - atomic_t refcnt; /* Control when this struct can be free'ed */ - struct rcu_head rcu; - - struct work_struct kthread_stop_wq; + struct completion kthread_running; + struct rcu_work free_work; }; struct bpf_cpu_map { @@ -82,16 +80,11 @@ struct bpf_cpu_map { struct bpf_cpu_map_entry __rcu **cpu_map; }; -static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); - static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; struct bpf_cpu_map *cmap; - if (!bpf_capable()) - return ERR_PTR(-EPERM); - /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || (value_size != offsetofend(struct bpf_cpumap_val, qsize) && @@ -121,27 +114,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) return &cmap->map; } -static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - atomic_inc(&rcpu->refcnt); -} - -/* called from workqueue, to workaround syscall using preempt_disable */ -static void cpu_map_kthread_stop(struct work_struct *work) -{ - struct bpf_cpu_map_entry *rcpu; - - rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); - - /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, - * as it waits until all in-flight call_rcu() callbacks complete. - */ - rcu_barrier(); - - /* kthread_stop will wake_up_process and wait for it to complete */ - kthread_stop(rcpu->kthread); -} - static void __cpu_map_ring_cleanup(struct ptr_ring *ring) { /* The tear-down procedure should have made sure that queue is @@ -149,42 +121,36 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring) * invoked cpu_map_kthread_stop(). Catch any broken behaviour * gracefully and warn once. */ - struct xdp_frame *xdpf; + void *ptr; - while ((xdpf = ptr_ring_consume(ring))) - if (WARN_ON_ONCE(xdpf)) - xdp_return_frame(xdpf); -} - -static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - if (atomic_dec_and_test(&rcpu->refcnt)) { - if (rcpu->prog) - bpf_prog_put(rcpu->prog); - /* The queue should be empty at this point */ - __cpu_map_ring_cleanup(rcpu->queue); - ptr_ring_cleanup(rcpu->queue, NULL); - kfree(rcpu->queue); - kfree(rcpu); + while ((ptr = ptr_ring_consume(ring))) { + WARN_ON_ONCE(1); + if (unlikely(__ptr_test_bit(0, &ptr))) { + __ptr_clear_bit(0, &ptr); + kfree_skb(ptr); + continue; + } + xdp_return_frame(ptr); } } -static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, - struct list_head *listp, - struct xdp_cpumap_stats *stats) +static u32 cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, + void **skbs, u32 skb_n, + struct xdp_cpumap_stats *stats) { - struct sk_buff *skb, *tmp; struct xdp_buff xdp; - u32 act; + u32 act, pass = 0; int err; - list_for_each_entry_safe(skb, tmp, listp, list) { + for (u32 i = 0; i < skb_n; i++) { + struct sk_buff *skb = skbs[i]; + act = bpf_prog_run_generic_xdp(skb, &xdp, rcpu->prog); switch (act) { case XDP_PASS: + skbs[pass++] = skb; break; case XDP_REDIRECT: - skb_list_del_init(skb); err = xdp_do_generic_redirect(skb->dev, skb, &xdp, rcpu->prog); if (unlikely(err)) { @@ -193,7 +159,7 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, } else { stats->redirect++; } - return; + break; default: bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act); fallthrough; @@ -201,23 +167,25 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, trace_xdp_exception(skb->dev, rcpu->prog, act); fallthrough; case XDP_DROP: - skb_list_del_init(skb); - kfree_skb(skb); + napi_consume_skb(skb, true); stats->drop++; - return; + break; } } + + stats->pass += pass; + + return pass; } static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, void **frames, int n, struct xdp_cpumap_stats *stats) { - struct xdp_rxq_info rxq; + struct xdp_rxq_info rxq = {}; struct xdp_buff xdp; int i, nframes = 0; - xdp_set_return_frame_no_direct(); xdp.rxq = &rxq; for (i = 0; i < n; i++) { @@ -226,7 +194,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, int err; rxq.dev = xdpf->dev_rx; - rxq.mem = xdpf->mem; + rxq.mem.type = xdpf->mem_type; /* TODO: report queue_index to xdp_rxq_info */ xdp_convert_frame_to_buff(xdpf, &xdp); @@ -240,7 +208,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, stats->drop++; } else { frames[nframes++] = xdpf; - stats->pass++; } break; case XDP_REDIRECT: @@ -263,42 +230,68 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, } } - xdp_clear_return_frame_no_direct(); + stats->pass += nframes; return nframes; } #define CPUMAP_BATCH 8 -static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, - int xdp_n, struct xdp_cpumap_stats *stats, - struct list_head *list) +struct cpu_map_ret { + u32 xdp_n; + u32 skb_n; +}; + +static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, + void **skbs, struct cpu_map_ret *ret, + struct xdp_cpumap_stats *stats) { - int nframes; + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; if (!rcpu->prog) - return xdp_n; + goto out; - rcu_read_lock_bh(); + rcu_read_lock(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + xdp_set_return_frame_no_direct(); - nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats); + ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats); + if (unlikely(ret->skb_n)) + ret->skb_n = cpu_map_bpf_prog_run_skb(rcpu, skbs, ret->skb_n, + stats); if (stats->redirect) xdp_do_flush(); - if (unlikely(!list_empty(list))) - cpu_map_bpf_prog_run_skb(rcpu, list, stats); - - rcu_read_unlock_bh(); /* resched point, may call do_softirq() */ + xdp_clear_return_frame_no_direct(); + bpf_net_ctx_clear(bpf_net_ctx); + rcu_read_unlock(); - return nframes; +out: + if (unlikely(ret->skb_n) && ret->xdp_n) + memmove(&skbs[ret->xdp_n], skbs, ret->skb_n * sizeof(*skbs)); } +static void cpu_map_gro_flush(struct bpf_cpu_map_entry *rcpu, bool empty) +{ + /* + * If the ring is not empty, there'll be a new iteration soon, and we + * only need to do a full flush if a tick is long (> 1 ms). + * If the ring is empty, to not hold GRO packets in the stack for too + * long, do a full flush. + * This is equivalent to how NAPI decides whether to perform a full + * flush. + */ + gro_flush_normal(&rcpu->gro, !empty && HZ >= 1000); +} static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + unsigned long last_qs = jiffies; + u32 packets = 0; + complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); /* When kthread gives stop order, then rcpu have been disconnected @@ -309,11 +302,11 @@ static int cpu_map_kthread_run(void *data) while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { struct xdp_cpumap_stats stats = {}; /* zero stats */ unsigned int kmem_alloc_drops = 0, sched = 0; - gfp_t gfp = __GFP_ZERO | GFP_ATOMIC; - int i, n, m, nframes, xdp_n; + struct cpu_map_ret ret = { }; void *frames[CPUMAP_BATCH]; void *skbs[CPUMAP_BATCH]; - LIST_HEAD(list); + u32 i, n, m; + bool empty; /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { @@ -322,10 +315,12 @@ static int cpu_map_kthread_run(void *data) if (__ptr_ring_empty(rcpu->queue)) { schedule(); sched = 1; + last_qs = jiffies; } else { __set_current_state(TASK_RUNNING); } } else { + rcu_softirq_qs_periodic(last_qs); sched = cond_resched(); } @@ -336,7 +331,7 @@ static int cpu_map_kthread_run(void *data) */ n = __ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH); - for (i = 0, xdp_n = 0; i < n; i++) { + for (i = 0; i < n; i++) { void *f = frames[i]; struct page *page; @@ -344,11 +339,11 @@ static int cpu_map_kthread_run(void *data) struct sk_buff *skb = f; __ptr_clear_bit(0, &skb); - list_add_tail(&skb->list, &list); + skbs[ret.skb_n++] = skb; continue; } - frames[xdp_n++] = f; + frames[ret.xdp_n++] = f; page = virt_to_page(f); /* Bring struct page memory area to curr CPU. Read by @@ -358,42 +353,55 @@ static int cpu_map_kthread_run(void *data) prefetchw(page); } + local_bh_disable(); + /* Support running another XDP prog on this CPU */ - nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); - if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs); - if (unlikely(m == 0)) { - for (i = 0; i < nframes; i++) - skbs[i] = NULL; /* effect: xdp_return_frame */ - kmem_alloc_drops += nframes; - } + cpu_map_bpf_prog_run(rcpu, frames, skbs, &ret, &stats); + if (!ret.xdp_n) + goto stats; + + m = napi_skb_cache_get_bulk(skbs, ret.xdp_n); + if (unlikely(m < ret.xdp_n)) { + for (i = m; i < ret.xdp_n; i++) + xdp_return_frame(frames[i]); + + if (ret.skb_n) + memmove(&skbs[m], &skbs[ret.xdp_n], + ret.skb_n * sizeof(*skbs)); + + kmem_alloc_drops += ret.xdp_n - m; + ret.xdp_n = m; } - local_bh_disable(); - for (i = 0; i < nframes; i++) { + for (i = 0; i < ret.xdp_n; i++) { struct xdp_frame *xdpf = frames[i]; - struct sk_buff *skb = skbs[i]; - - skb = __xdp_build_skb_from_frame(xdpf, skb, - xdpf->dev_rx); - if (!skb) { - xdp_return_frame(xdpf); - continue; - } - list_add_tail(&skb->list, &list); + /* Can fail only when !skb -- already handled above */ + __xdp_build_skb_from_frame(xdpf, skbs[i], xdpf->dev_rx); } - netif_receive_skb_list(&list); - /* Feedback loop via tracepoint */ +stats: + /* Feedback loop via tracepoint. + * NB: keep before recv to allow measuring enqueue/dequeue latency. + */ trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops, sched, &stats); + for (i = 0; i < ret.xdp_n + ret.skb_n; i++) + gro_receive_skb(&rcpu->gro, skbs[i]); + + /* Flush either every 64 packets or in case of empty ring */ + packets += n; + empty = __ptr_ring_empty(rcpu->queue); + if (packets >= NAPI_POLL_WEIGHT || empty) { + cpu_map_gro_flush(rcpu, empty); + packets = 0; + } + local_bh_enable(); /* resched point, may call do_softirq() */ } __set_current_state(TASK_RUNNING); - put_cpu_map_entry(rcpu); return 0; } @@ -458,30 +466,36 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, rcpu->cpu = cpu; rcpu->map_id = map->id; rcpu->value.qsize = value->qsize; + gro_init(&rcpu->gro); if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd)) goto free_ptr_ring; /* Setup kthread */ + init_completion(&rcpu->kthread_running); rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, "cpumap/%d/map:%d", cpu, map->id); if (IS_ERR(rcpu->kthread)) goto free_prog; - get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ - get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ - /* Make sure kthread runs on a single CPU */ kthread_bind(rcpu->kthread, cpu); wake_up_process(rcpu->kthread); + /* Make sure kthread has been running, so kthread_stop() will not + * stop the kthread prematurely and all pending frames or skbs + * will be handled by the kthread before kthread_stop() returns. + */ + wait_for_completion(&rcpu->kthread_running); + return rcpu; free_prog: if (rcpu->prog) bpf_prog_put(rcpu->prog); free_ptr_ring: + gro_cleanup(&rcpu->gro); ptr_ring_cleanup(rcpu->queue, NULL); free_queue: kfree(rcpu->queue); @@ -492,40 +506,41 @@ free_rcu: return NULL; } -static void __cpu_map_entry_free(struct rcu_head *rcu) +static void __cpu_map_entry_free(struct work_struct *work) { struct bpf_cpu_map_entry *rcpu; /* This cpu_map_entry have been disconnected from map and one - * RCU grace-period have elapsed. Thus, XDP cannot queue any + * RCU grace-period have elapsed. Thus, XDP cannot queue any * new packets and cannot change/set flush_needed that can * find this entry. */ - rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); + rcpu = container_of(to_rcu_work(work), struct bpf_cpu_map_entry, free_work); + + /* kthread_stop will wake_up_process and wait for it to complete. + * cpu_map_kthread_run() makes sure the pointer ring is empty + * before exiting. + */ + kthread_stop(rcpu->kthread); + if (rcpu->prog) + bpf_prog_put(rcpu->prog); + gro_cleanup(&rcpu->gro); + /* The queue should be empty at this point */ + __cpu_map_ring_cleanup(rcpu->queue); + ptr_ring_cleanup(rcpu->queue, NULL); + kfree(rcpu->queue); free_percpu(rcpu->bulkq); - /* Cannot kthread_stop() here, last put free rcpu resources */ - put_cpu_map_entry(rcpu); + kfree(rcpu); } -/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to - * ensure any driver rcu critical sections have completed, but this - * does not guarantee a flush has happened yet. Because driver side - * rcu_read_lock/unlock only protects the running XDP program. The - * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a - * pending flush op doesn't fail. - * - * The bpf_cpu_map_entry is still used by the kthread, and there can - * still be pending packets (in queue and percpu bulkq). A refcnt - * makes sure to last user (kthread_stop vs. call_rcu) free memory - * resources. - * - * The rcu callback __cpu_map_entry_free flush remaining packets in - * percpu bulkq to queue. Due to caller map_delete_elem() disable - * preemption, cannot call kthread_stop() to make sure queue is empty. - * Instead a work_queue is started for stopping kthread, - * cpu_map_kthread_stop, which waits for an RCU grace period before - * stopping kthread, emptying the queue. +/* After the xchg of the bpf_cpu_map_entry pointer, we need to make sure the old + * entry is no longer in use before freeing. We use queue_rcu_work() to call + * __cpu_map_entry_free() in a separate workqueue after waiting for an RCU grace + * period. This means that (a) all pending enqueue and flush operations have + * completed (because of the RCU callback), and (b) we are in a workqueue + * context where we can stop the kthread and wait for it to exit before freeing + * everything. */ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, u32 key_cpu, struct bpf_cpu_map_entry *rcpu) @@ -534,13 +549,12 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu))); if (old_rcpu) { - call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); - INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); - schedule_work(&old_rcpu->kthread_stop_wq); + INIT_RCU_WORK(&old_rcpu->free_work, __cpu_map_entry_free); + queue_rcu_work(system_percpu_wq, &old_rcpu->free_work); } } -static int cpu_map_delete_elem(struct bpf_map *map, void *key) +static long cpu_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); u32 key_cpu = *(u32 *)key; @@ -548,13 +562,13 @@ static int cpu_map_delete_elem(struct bpf_map *map, void *key) if (key_cpu >= map->max_entries) return -EINVAL; - /* notice caller map_delete_elem() use preempt_disable() */ + /* notice caller map_delete_elem() uses rcu_read_lock() */ __cpu_map_entry_replace(cmap, key_cpu, NULL); return 0; } -static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); struct bpf_cpumap_val cpumap_value = {}; @@ -584,7 +598,6 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu); if (!rcpu) return -ENOMEM; - rcpu->cmap = cmap; } rcu_read_lock(); __cpu_map_entry_replace(cmap, key_cpu, rcpu); @@ -600,16 +613,15 @@ static void cpu_map_free(struct bpf_map *map) /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the bpf programs (can be more than one that used this map) were * disconnected from events. Wait for outstanding critical sections in - * these programs to complete. The rcu critical section only guarantees - * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map. - * It does __not__ ensure pending flush operations (if any) are - * complete. + * these programs to complete. synchronize_rcu() below not only + * guarantees no further "XDP/bpf-side" reads against + * bpf_cpu_map->cpu_map, but also ensure pending flush operations + * (if any) are completed. */ - synchronize_rcu(); - /* For cpu_map the remote CPUs can still be using the entries - * (struct bpf_cpu_map_entry). + /* The only possible user of bpf_cpu_map_entry is + * cpu_map_kthread_run(). */ for (i = 0; i < cmap->map.max_entries; i++) { struct bpf_cpu_map_entry *rcpu; @@ -618,8 +630,8 @@ static void cpu_map_free(struct bpf_map *map) if (!rcpu) continue; - /* bq flush and cleanup happens after RCU grace-period */ - __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ + /* Stop kthread and cleanup entry directly */ + __cpu_map_entry_free(&rcpu->free_work.work); } bpf_map_area_free(cmap->cpu_map); bpf_map_area_free(cmap); @@ -667,12 +679,21 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -static int cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags) +static long cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags) { return __bpf_xdp_redirect_map(map, index, flags, 0, __cpu_map_lookup_elem); } +static u64 cpu_map_mem_usage(const struct bpf_map *map) +{ + u64 usage = sizeof(struct bpf_cpu_map); + + /* Currently the dynamically allocated elements are not counted */ + usage += (u64)map->max_entries * sizeof(struct bpf_cpu_map_entry *); + return usage; +} + BTF_ID_LIST_SINGLE(cpu_map_btf_ids, struct, bpf_cpu_map) const struct bpf_map_ops cpu_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -683,6 +704,7 @@ const struct bpf_map_ops cpu_map_ops = { .map_lookup_elem = cpu_map_lookup_elem, .map_get_next_key = cpu_map_get_next_key, .map_check_btf = map_check_no_btf, + .map_mem_usage = cpu_map_mem_usage, .map_btf_id = &cpu_map_btf_ids[0], .map_redirect = cpu_map_redirect, }; @@ -726,7 +748,6 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq) */ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { - struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) @@ -743,8 +764,11 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) */ bq->q[bq->count++] = xdpf; - if (!bq->flush_node.prev) + if (!bq->flush_node.prev) { + struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list(); + list_add(&bq->flush_node, flush_list); + } } int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, @@ -776,9 +800,8 @@ trace: return ret; } -void __cpu_map_flush(void) +void __cpu_map_flush(struct list_head *flush_list) { - struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); struct xdp_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { @@ -788,14 +811,3 @@ void __cpu_map_flush(void) wake_up_process(bq->obj->kthread); } } - -static int __init cpu_map_init(void) -{ - int cpu; - - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu)); - return 0; -} - -subsys_initcall(cpu_map_init); diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c new file mode 100644 index 000000000000..9876c5fe6c2a --- /dev/null +++ b/kernel/bpf/cpumask.c @@ -0,0 +1,534 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2023 Meta, Inc */ +#include <linux/bpf.h> +#include <linux/bpf_mem_alloc.h> +#include <linux/btf.h> +#include <linux/btf_ids.h> +#include <linux/cpumask.h> + +/** + * struct bpf_cpumask - refcounted BPF cpumask wrapper structure + * @cpumask: The actual cpumask embedded in the struct. + * @usage: Object reference counter. When the refcount goes to 0, the + * memory is released back to the BPF allocator, which provides + * RCU safety. + * + * Note that we explicitly embed a cpumask_t rather than a cpumask_var_t. This + * is done to avoid confusing the verifier due to the typedef of cpumask_var_t + * changing depending on whether CONFIG_CPUMASK_OFFSTACK is defined or not. See + * the details in <linux/cpumask.h>. The consequence is that this structure is + * likely a bit larger than it needs to be when CONFIG_CPUMASK_OFFSTACK is + * defined due to embedding the whole NR_CPUS-size bitmap, but the extra memory + * overhead is minimal. For the more typical case of CONFIG_CPUMASK_OFFSTACK + * not being defined, the structure is the same size regardless. + */ +struct bpf_cpumask { + cpumask_t cpumask; + refcount_t usage; +}; + +static struct bpf_mem_alloc bpf_cpumask_ma; + +static bool cpu_valid(u32 cpu) +{ + return cpu < nr_cpu_ids; +} + +__bpf_kfunc_start_defs(); + +/** + * bpf_cpumask_create() - Create a mutable BPF cpumask. + * + * Allocates a cpumask that can be queried, mutated, acquired, and released by + * a BPF program. The cpumask returned by this function must either be embedded + * in a map as a kptr, or freed with bpf_cpumask_release(). + * + * bpf_cpumask_create() allocates memory using the BPF memory allocator, and + * will not block. It may return NULL if no memory is available. + * + * Return: + * * A pointer to a new struct bpf_cpumask instance on success. + * * NULL if the BPF memory allocator is out of memory. + */ +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_create(void) +{ + struct bpf_cpumask *cpumask; + + /* cpumask must be the first element so struct bpf_cpumask be cast to struct cpumask. */ + BUILD_BUG_ON(offsetof(struct bpf_cpumask, cpumask) != 0); + + cpumask = bpf_mem_cache_alloc(&bpf_cpumask_ma); + if (!cpumask) + return NULL; + + memset(cpumask, 0, sizeof(*cpumask)); + refcount_set(&cpumask->usage, 1); + + return cpumask; +} + +/** + * bpf_cpumask_acquire() - Acquire a reference to a BPF cpumask. + * @cpumask: The BPF cpumask being acquired. The cpumask must be a trusted + * pointer. + * + * Acquires a reference to a BPF cpumask. The cpumask returned by this function + * must either be embedded in a map as a kptr, or freed with + * bpf_cpumask_release(). + * + * Return: + * * The struct bpf_cpumask pointer passed to the function. + * + */ +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) +{ + refcount_inc(&cpumask->usage); + return cpumask; +} + +/** + * bpf_cpumask_release() - Release a previously acquired BPF cpumask. + * @cpumask: The cpumask being released. + * + * Releases a previously acquired reference to a BPF cpumask. When the final + * reference of the BPF cpumask has been released, it is subsequently freed in + * an RCU callback in the BPF memory allocator. + */ +__bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) +{ + if (!refcount_dec_and_test(&cpumask->usage)) + return; + + bpf_mem_cache_free_rcu(&bpf_cpumask_ma, cpumask); +} + +__bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask) +{ + bpf_cpumask_release(cpumask); +} +CFI_NOSEAL(bpf_cpumask_release_dtor); + +/** + * bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask. + * @cpumask: The cpumask being queried. + * + * Find the index of the first nonzero bit of the cpumask. A struct bpf_cpumask + * pointer may be safely passed to this function. + * + * Return: + * * The index of the first nonzero bit in the struct cpumask. + */ +__bpf_kfunc u32 bpf_cpumask_first(const struct cpumask *cpumask) +{ + return cpumask_first(cpumask); +} + +/** + * bpf_cpumask_first_zero() - Get the index of the first unset bit in the + * cpumask. + * @cpumask: The cpumask being queried. + * + * Find the index of the first unset bit of the cpumask. A struct bpf_cpumask + * pointer may be safely passed to this function. + * + * Return: + * * The index of the first zero bit in the struct cpumask. + */ +__bpf_kfunc u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) +{ + return cpumask_first_zero(cpumask); +} + +/** + * bpf_cpumask_first_and() - Return the index of the first nonzero bit from the + * AND of two cpumasks. + * @src1: The first cpumask. + * @src2: The second cpumask. + * + * Find the index of the first nonzero bit of the AND of two cpumasks. + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + * + * Return: + * * The index of the first bit that is nonzero in both cpumask instances. + */ +__bpf_kfunc u32 bpf_cpumask_first_and(const struct cpumask *src1, + const struct cpumask *src2) +{ + return cpumask_first_and(src1, src2); +} + +/** + * bpf_cpumask_set_cpu() - Set a bit for a CPU in a BPF cpumask. + * @cpu: The CPU to be set in the cpumask. + * @cpumask: The BPF cpumask in which a bit is being set. + */ +__bpf_kfunc void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return; + + cpumask_set_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_clear_cpu() - Clear a bit for a CPU in a BPF cpumask. + * @cpu: The CPU to be cleared from the cpumask. + * @cpumask: The BPF cpumask in which a bit is being cleared. + */ +__bpf_kfunc void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return; + + cpumask_clear_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_test_cpu() - Test whether a CPU is set in a cpumask. + * @cpu: The CPU being queried for. + * @cpumask: The cpumask being queried for containing a CPU. + * + * Return: + * * true - @cpu is set in the cpumask + * * false - @cpu was not set in the cpumask, or @cpu is an invalid cpu. + */ +__bpf_kfunc bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return false; + + return cpumask_test_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_test_and_set_cpu() - Atomically test and set a CPU in a BPF cpumask. + * @cpu: The CPU being set and queried for. + * @cpumask: The BPF cpumask being set and queried for containing a CPU. + * + * Return: + * * true - @cpu is set in the cpumask + * * false - @cpu was not set in the cpumask, or @cpu is invalid. + */ +__bpf_kfunc bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return false; + + return cpumask_test_and_set_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_test_and_clear_cpu() - Atomically test and clear a CPU in a BPF + * cpumask. + * @cpu: The CPU being cleared and queried for. + * @cpumask: The BPF cpumask being cleared and queried for containing a CPU. + * + * Return: + * * true - @cpu is set in the cpumask + * * false - @cpu was not set in the cpumask, or @cpu is invalid. + */ +__bpf_kfunc bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return false; + + return cpumask_test_and_clear_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_setall() - Set all of the bits in a BPF cpumask. + * @cpumask: The BPF cpumask having all of its bits set. + */ +__bpf_kfunc void bpf_cpumask_setall(struct bpf_cpumask *cpumask) +{ + cpumask_setall((struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_clear() - Clear all of the bits in a BPF cpumask. + * @cpumask: The BPF cpumask being cleared. + */ +__bpf_kfunc void bpf_cpumask_clear(struct bpf_cpumask *cpumask) +{ + cpumask_clear((struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_and() - AND two cpumasks and store the result. + * @dst: The BPF cpumask where the result is being stored. + * @src1: The first input. + * @src2: The second input. + * + * Return: + * * true - @dst has at least one bit set following the operation + * * false - @dst is empty following the operation + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_and(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) +{ + return cpumask_and((struct cpumask *)dst, src1, src2); +} + +/** + * bpf_cpumask_or() - OR two cpumasks and store the result. + * @dst: The BPF cpumask where the result is being stored. + * @src1: The first input. + * @src2: The second input. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc void bpf_cpumask_or(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) +{ + cpumask_or((struct cpumask *)dst, src1, src2); +} + +/** + * bpf_cpumask_xor() - XOR two cpumasks and store the result. + * @dst: The BPF cpumask where the result is being stored. + * @src1: The first input. + * @src2: The second input. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc void bpf_cpumask_xor(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) +{ + cpumask_xor((struct cpumask *)dst, src1, src2); +} + +/** + * bpf_cpumask_equal() - Check two cpumasks for equality. + * @src1: The first input. + * @src2: The second input. + * + * Return: + * * true - @src1 and @src2 have the same bits set. + * * false - @src1 and @src2 differ in at least one bit. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) +{ + return cpumask_equal(src1, src2); +} + +/** + * bpf_cpumask_intersects() - Check two cpumasks for overlap. + * @src1: The first input. + * @src2: The second input. + * + * Return: + * * true - @src1 and @src2 have at least one of the same bits set. + * * false - @src1 and @src2 don't have any of the same bits set. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) +{ + return cpumask_intersects(src1, src2); +} + +/** + * bpf_cpumask_subset() - Check if a cpumask is a subset of another. + * @src1: The first cpumask being checked as a subset. + * @src2: The second cpumask being checked as a superset. + * + * Return: + * * true - All of the bits of @src1 are set in @src2. + * * false - At least one bit in @src1 is not set in @src2. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) +{ + return cpumask_subset(src1, src2); +} + +/** + * bpf_cpumask_empty() - Check if a cpumask is empty. + * @cpumask: The cpumask being checked. + * + * Return: + * * true - None of the bits in @cpumask are set. + * * false - At least one bit in @cpumask is set. + * + * A struct bpf_cpumask pointer may be safely passed to @cpumask. + */ +__bpf_kfunc bool bpf_cpumask_empty(const struct cpumask *cpumask) +{ + return cpumask_empty(cpumask); +} + +/** + * bpf_cpumask_full() - Check if a cpumask has all bits set. + * @cpumask: The cpumask being checked. + * + * Return: + * * true - All of the bits in @cpumask are set. + * * false - At least one bit in @cpumask is cleared. + * + * A struct bpf_cpumask pointer may be safely passed to @cpumask. + */ +__bpf_kfunc bool bpf_cpumask_full(const struct cpumask *cpumask) +{ + return cpumask_full(cpumask); +} + +/** + * bpf_cpumask_copy() - Copy the contents of a cpumask into a BPF cpumask. + * @dst: The BPF cpumask being copied into. + * @src: The cpumask being copied. + * + * A struct bpf_cpumask pointer may be safely passed to @src. + */ +__bpf_kfunc void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) +{ + cpumask_copy((struct cpumask *)dst, src); +} + +/** + * bpf_cpumask_any_distribute() - Return a random set CPU from a cpumask. + * @cpumask: The cpumask being queried. + * + * Return: + * * A random set bit within [0, num_cpus) if at least one bit is set. + * * >= num_cpus if no bit is set. + * + * A struct bpf_cpumask pointer may be safely passed to @src. + */ +__bpf_kfunc u32 bpf_cpumask_any_distribute(const struct cpumask *cpumask) +{ + return cpumask_any_distribute(cpumask); +} + +/** + * bpf_cpumask_any_and_distribute() - Return a random set CPU from the AND of + * two cpumasks. + * @src1: The first cpumask. + * @src2: The second cpumask. + * + * Return: + * * A random set bit within [0, num_cpus) from the AND of two cpumasks, if at + * least one bit is set. + * * >= num_cpus if no bit is set. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, + const struct cpumask *src2) +{ + return cpumask_any_and_distribute(src1, src2); +} + +/** + * bpf_cpumask_weight() - Return the number of bits in @cpumask. + * @cpumask: The cpumask being queried. + * + * Count the number of set bits in the given cpumask. + * + * Return: + * * The number of bits set in the mask. + */ +__bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask) +{ + return cpumask_weight(cpumask); +} + +/** + * bpf_cpumask_populate() - Populate the CPU mask from the contents of + * a BPF memory region. + * + * @cpumask: The cpumask being populated. + * @src: The BPF memory holding the bit pattern. + * @src__sz: Length of the BPF memory region in bytes. + * + * Return: + * * 0 if the struct cpumask * instance was populated successfully. + * * -EACCES if the memory region is too small to populate the cpumask. + * * -EINVAL if the memory region is not aligned to the size of a long + * and the architecture does not support efficient unaligned accesses. + */ +__bpf_kfunc int bpf_cpumask_populate(struct cpumask *cpumask, void *src, size_t src__sz) +{ + unsigned long source = (unsigned long)src; + + /* The memory region must be large enough to populate the entire CPU mask. */ + if (src__sz < bitmap_size(nr_cpu_ids)) + return -EACCES; + + /* If avoiding unaligned accesses, the input region must be aligned to the nearest long. */ + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && + !IS_ALIGNED(source, sizeof(long))) + return -EINVAL; + + bitmap_copy(cpumask_bits(cpumask), src, nr_cpu_ids); + + return 0; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(cpumask_kfunc_btf_ids) +BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_first, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_first_zero, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_first_and, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_set_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_clear_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_test_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_test_and_set_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_test_and_clear_cpu, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_setall, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_clear, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_and, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_or, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_xor, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_equal, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_intersects, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_subset, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_empty, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_populate, KF_RCU) +BTF_KFUNCS_END(cpumask_kfunc_btf_ids) + +static const struct btf_kfunc_id_set cpumask_kfunc_set = { + .owner = THIS_MODULE, + .set = &cpumask_kfunc_btf_ids, +}; + +BTF_ID_LIST(cpumask_dtor_ids) +BTF_ID(struct, bpf_cpumask) +BTF_ID(func, bpf_cpumask_release_dtor) + +static int __init cpumask_kfunc_init(void) +{ + int ret; + const struct btf_id_dtor_kfunc cpumask_dtors[] = { + { + .btf_id = cpumask_dtor_ids[0], + .kfunc_btf_id = cpumask_dtor_ids[1] + }, + }; + + 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); +} + +late_initcall(cpumask_kfunc_init); diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c new file mode 100644 index 000000000000..83c4d9943084 --- /dev/null +++ b/kernel/bpf/crypto.c @@ -0,0 +1,393 @@ +// 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 = siv ? __bpf_dynptr_size(siv) : 0; + src_len = __bpf_dynptr_size(src); + dst_len = __bpf_dynptr_size(dst); + if (!src_len || !dst_len || 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__nullable: bpf_dynptr to IV data and state data to be used by decryptor. May be NULL. + * + * 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 *src, + const struct bpf_dynptr *dst, + const struct bpf_dynptr *siv__nullable) +{ + const struct bpf_dynptr_kern *src_kern = (struct bpf_dynptr_kern *)src; + const struct bpf_dynptr_kern *dst_kern = (struct bpf_dynptr_kern *)dst; + const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv__nullable; + + return bpf_crypto_crypt(ctx, src_kern, dst_kern, siv_kern, 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 the buffer where to store the result. Must be a trusted pointer. + * @siv__nullable: bpf_dynptr to IV data and state data to be used by decryptor. May be NULL. + * + * 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 *src, + const struct bpf_dynptr *dst, + const struct bpf_dynptr *siv__nullable) +{ + const struct bpf_dynptr_kern *src_kern = (struct bpf_dynptr_kern *)src; + const struct bpf_dynptr_kern *dst_kern = (struct bpf_dynptr_kern *)dst; + const struct bpf_dynptr_kern *siv_kern = (struct bpf_dynptr_kern *)siv__nullable; + + return bpf_crypto_crypt(ctx, src_kern, dst_kern, siv_kern, 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/devmap.c b/kernel/bpf/devmap.c index d01e4c55b376..2625601de76e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -65,7 +65,6 @@ struct xdp_dev_bulk_queue { struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; - struct bpf_dtab *dtab; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; @@ -84,7 +83,6 @@ struct bpf_dtab { u32 n_buckets; }; -static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); @@ -108,7 +106,7 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } -static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) +static int dev_map_alloc_check(union bpf_attr *attr) { u32 valsize = attr->value_size; @@ -122,22 +120,28 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + /* Hash table size must be power of 2; roundup_pow_of_two() + * can overflow into UB on 32-bit arches + */ + if (attr->max_entries > 1UL << 31) + return -EINVAL; + } + + return 0; +} + +static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) +{ /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; - - bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + /* Hash table size must be power of 2 */ dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); - - if (!dtab->n_buckets) /* Overflow check */ - return -EINVAL; - } - - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) @@ -160,9 +164,6 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) struct bpf_dtab *dtab; int err; - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); if (!dtab) return ERR_PTR(-ENOMEM); @@ -183,7 +184,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - int i; + u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were @@ -199,7 +200,14 @@ static void dev_map_free(struct bpf_map *map) list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); - bpf_clear_redirect_map(map); + /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() + * during NAPI callback and cleared after the XDP redirect. There is no + * explicit RCU read section which protects bpf_redirect_info->map but + * local_bh_disable() also marks the beginning an RCU section. This + * makes the complete softirq callback RCU protected. Thus after + * following synchronize_rcu() there no bpf_redirect_info->map == map + * assignment. + */ synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ @@ -325,9 +333,11 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, - struct net_device *dev) + struct net_device *tx_dev, + struct net_device *rx_dev) { - struct xdp_txq_info txq = { .dev = dev }; + struct xdp_txq_info txq = { .dev = tx_dev }; + struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; @@ -338,6 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; + xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { @@ -352,7 +363,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(dev, xdp_prog, act); + trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); @@ -380,7 +391,7 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) } if (bq->xdp_prog) { - to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev); + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } @@ -409,9 +420,8 @@ out: * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ -void __dev_flush(void) +void __dev_flush(struct list_head *flush_list) { - struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { @@ -446,7 +456,6 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) @@ -460,6 +469,8 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, * are only ever modified together. */ if (!bq->dev_rx) { + struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); + bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); @@ -474,7 +485,11 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, { int err; - if (!dev->netdev_ops->ndo_xdp_xmit) + if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) + return -EOPNOTSUPP; + + if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); @@ -532,8 +547,14 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { - if (!obj || - !obj->dev->netdev_ops->ndo_xdp_xmit) + if (!obj) + return false; + + if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) + return false; + + if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) @@ -657,7 +678,7 @@ int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { int err; @@ -680,7 +701,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; @@ -699,8 +720,8 @@ static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress) + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; @@ -743,9 +764,6 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { - if (!dst) - continue; - if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; @@ -799,26 +817,28 @@ static void __dev_map_entry_free(struct rcu_head *rcu) kfree(dev); } -static int dev_map_delete_elem(struct bpf_map *map, void *key) +static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; - int k = *(u32 *)key; + u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); - if (old_dev) + if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); + atomic_dec((atomic_t *)&dtab->items); + } return 0; } -static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) +static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; - int k = *(u32 *)key; + u32 k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; @@ -845,7 +865,7 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), - GFP_NOWAIT | __GFP_NOWARN, + GFP_NOWAIT, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); @@ -865,7 +885,6 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, } dev->idx = idx; - dev->dtab = dtab; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; @@ -885,8 +904,8 @@ err_out: return ERR_PTR(-EINVAL); } -static int __dev_map_update_elem(struct net *net, struct bpf_map *map, - void *key, void *value, u64 map_flags) +static long __dev_map_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; @@ -921,19 +940,21 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); + else + atomic_inc((atomic_t *)&dtab->items); return 0; } -static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } -static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, - void *key, void *value, u64 map_flags) +static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; @@ -985,30 +1006,45 @@ out_err: return err; } -static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } -static int dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) +static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } -static int dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) +static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } +static u64 dev_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u64 usage = sizeof(struct bpf_dtab); + + if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) + usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); + else + usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); + usage += atomic_read((atomic_t *)&dtab->items) * + (u64)sizeof(struct bpf_dtab_netdev); + return usage; +} + BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, @@ -1016,12 +1052,14 @@ const struct bpf_map_ops dev_map_ops = { .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, + .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, @@ -1029,6 +1067,7 @@ const struct bpf_map_ops dev_map_hash_ops = { .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, + .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; @@ -1099,9 +1138,11 @@ static int dev_map_notification(struct notifier_block *notifier, if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); - if (dev == odev) + if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); + atomic_dec((atomic_t *)&dtab->items); + } } } rcu_read_unlock(); @@ -1118,15 +1159,11 @@ static struct notifier_block dev_map_notifier = { static int __init dev_map_init(void) { - int cpu; - /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 7b4afb7d96db..f8a3c7eb451e 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -87,6 +87,17 @@ const char *const bpf_alu_string[16] = { [BPF_END >> 4] = "endian", }; +static const char *const bpf_alu_sign_string[16] = { + [BPF_DIV >> 4] = "s/=", + [BPF_MOD >> 4] = "s%=", +}; + +static const char *const bpf_movsx_string[4] = { + [0] = "(s8)", + [1] = "(s16)", + [3] = "(s32)", +}; + static const char *const bpf_atomic_alu_string[16] = { [BPF_ADD >> 4] = "add", [BPF_AND >> 4] = "and", @@ -101,6 +112,12 @@ static const char *const bpf_ldst_string[] = { [BPF_DW >> 3] = "u64", }; +static const char *const bpf_ldsx_string[] = { + [BPF_W >> 3] = "s32", + [BPF_H >> 3] = "s16", + [BPF_B >> 3] = "s8", +}; + static const char *const bpf_jmp_string[16] = { [BPF_JA >> 4] = "jmp", [BPF_JEQ >> 4] = "==", @@ -128,6 +145,44 @@ static void print_bpf_end_insn(bpf_insn_print_t verbose, insn->imm, insn->dst_reg); } +static void print_bpf_bswap_insn(bpf_insn_print_t verbose, + void *private_data, + const struct bpf_insn *insn) +{ + verbose(private_data, "(%02x) r%d = bswap%d r%d\n", + insn->code, insn->dst_reg, + insn->imm, insn->dst_reg); +} + +static bool is_sdiv_smod(const struct bpf_insn *insn) +{ + return (BPF_OP(insn->code) == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) && + insn->off == 1; +} + +static bool is_movsx(const struct bpf_insn *insn) +{ + return BPF_OP(insn->code) == BPF_MOV && + (insn->off == 8 || insn->off == 16 || insn->off == 32); +} + +static bool is_addr_space_cast(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + 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) @@ -138,7 +193,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, if (class == BPF_ALU || class == BPF_ALU64) { if (BPF_OP(insn->code) == BPF_END) { if (class == BPF_ALU64) - verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code); + print_bpf_bswap_insn(verbose, cbs->private_data, insn); else print_bpf_end_insn(verbose, cbs->private_data, insn); } else if (BPF_OP(insn->code) == BPF_NEG) { @@ -146,18 +201,28 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); + } else if (is_addr_space_cast(insn)) { + verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %u, %u)\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 %c%d\n", + verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], + is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] + : bpf_alu_string[BPF_OP(insn->code) >> 4], + is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "", class == BPF_ALU ? 'w' : 'r', insn->src_reg); } else { verbose(cbs->private_data, "(%02x) %c%d %s %d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], + is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] + : bpf_alu_string[BPF_OP(insn->code) >> 4], insn->imm); } } else if (class == BPF_STX) { @@ -202,6 +267,18 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_LOAD_ACQ) { + verbose(cbs->private_data, "(%02x) r%d = load_acquire((%s *)(r%d %+d))\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_STORE_REL) { + verbose(cbs->private_data, "(%02x) store_release((%s *)(r%d %+d), r%d)\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, insn->src_reg); } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); } @@ -218,13 +295,15 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); } } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); return; } verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n", insn->code, insn->dst_reg, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + BPF_MODE(insn->code) == BPF_MEM ? + bpf_ldst_string[BPF_SIZE(insn->code) >> 3] : + bpf_ldsx_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->off); } else if (class == BPF_LD) { if (BPF_MODE(insn->code) == BPF_ABS) { @@ -279,6 +358,16 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_JA | BPF_X)) { + verbose(cbs->private_data, "(%02x) gotox r%d\n", + insn->code, insn->dst_reg); + } else if (insn->code == (BPF_JMP | BPF_JCOND) && + insn->src_reg == BPF_MAY_GOTO) { + verbose(cbs->private_data, "(%02x) may_goto pc%+d\n", + insn->code, insn->off); + } else if (insn->code == (BPF_JMP32 | BPF_JA)) { + verbose(cbs->private_data, "(%02x) gotol pc%+d\n", + insn->code, insn->imm); } else if (insn->code == (BPF_JMP | BPF_EXIT)) { verbose(cbs->private_data, "(%02x) exit\n", insn->code); } else if (BPF_SRC(insn->code) == BPF_X) { @@ -295,7 +384,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->code, class == BPF_JMP32 ? 'w' : 'r', insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->imm, insn->off); + (u32)insn->imm, insn->off); } } else { verbose(cbs->private_data, "(%02x) %s\n", diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index fa3e9225aedc..b77db7413f8c 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -150,14 +150,12 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, goto out; d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE); if (!d->rw_image) { - u32 size = PAGE_SIZE; - - bpf_arch_text_copy(d->image, &size, sizeof(size)); - bpf_prog_pack_free((struct bpf_binary_header *)d->image); + bpf_prog_pack_free(d->image, PAGE_SIZE); d->image = NULL; goto out; } - bpf_image_ksym_add(d->image, &d->ksym); + bpf_image_ksym_init(d->image, PAGE_SIZE, &d->ksym); + bpf_image_ksym_add(&d->ksym); } prev_num_progs = d->num_progs; diff --git a/kernel/bpf/dmabuf_iter.c b/kernel/bpf/dmabuf_iter.c new file mode 100644 index 000000000000..4dd7ef7c145c --- /dev/null +++ b/kernel/bpf/dmabuf_iter.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025 Google LLC */ +#include <linux/bpf.h> +#include <linux/btf_ids.h> +#include <linux/dma-buf.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> + +static void *dmabuf_iter_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (*pos) + return NULL; + + return dma_buf_iter_begin(); +} + +static void *dmabuf_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct dma_buf *dmabuf = v; + + ++*pos; + + return dma_buf_iter_next(dmabuf); +} + +struct bpf_iter__dmabuf { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct dma_buf *, dmabuf); +}; + +static int __dmabuf_seq_show(struct seq_file *seq, void *v, bool in_stop) +{ + struct bpf_iter_meta meta = { + .seq = seq, + }; + struct bpf_iter__dmabuf ctx = { + .meta = &meta, + .dmabuf = v, + }; + struct bpf_prog *prog = bpf_iter_get_info(&meta, in_stop); + + if (prog) + return bpf_iter_run_prog(prog, &ctx); + + return 0; +} + +static int dmabuf_iter_seq_show(struct seq_file *seq, void *v) +{ + return __dmabuf_seq_show(seq, v, false); +} + +static void dmabuf_iter_seq_stop(struct seq_file *seq, void *v) +{ + struct dma_buf *dmabuf = v; + + if (dmabuf) + dma_buf_put(dmabuf); +} + +static const struct seq_operations dmabuf_iter_seq_ops = { + .start = dmabuf_iter_seq_start, + .next = dmabuf_iter_seq_next, + .stop = dmabuf_iter_seq_stop, + .show = dmabuf_iter_seq_show, +}; + +static void bpf_iter_dmabuf_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq) +{ + seq_puts(seq, "dmabuf iter\n"); +} + +static const struct bpf_iter_seq_info dmabuf_iter_seq_info = { + .seq_ops = &dmabuf_iter_seq_ops, + .init_seq_private = NULL, + .fini_seq_private = NULL, + .seq_priv_size = 0, +}; + +static struct bpf_iter_reg bpf_dmabuf_reg_info = { + .target = "dmabuf", + .feature = BPF_ITER_RESCHED, + .show_fdinfo = bpf_iter_dmabuf_show_fdinfo, + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__dmabuf, dmabuf), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &dmabuf_iter_seq_info, +}; + +DEFINE_BPF_ITER_FUNC(dmabuf, struct bpf_iter_meta *meta, struct dma_buf *dmabuf) +BTF_ID_LIST_SINGLE(bpf_dmabuf_btf_id, struct, dma_buf) + +static int __init dmabuf_iter_init(void) +{ + bpf_dmabuf_reg_info.ctx_arg_info[0].btf_id = bpf_dmabuf_btf_id[0]; + return bpf_iter_reg_target(&bpf_dmabuf_reg_info); +} + +late_initcall(dmabuf_iter_init); + +struct bpf_iter_dmabuf { + /* + * opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __aligned(8); + +/* Non-opaque version of bpf_iter_dmabuf */ +struct bpf_iter_dmabuf_kern { + struct dma_buf *dmabuf; +} __aligned(8); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_dmabuf_new(struct bpf_iter_dmabuf *it) +{ + struct bpf_iter_dmabuf_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(*kit) > sizeof(*it)); + BUILD_BUG_ON(__alignof__(*kit) != __alignof__(*it)); + + kit->dmabuf = NULL; + return 0; +} + +__bpf_kfunc struct dma_buf *bpf_iter_dmabuf_next(struct bpf_iter_dmabuf *it) +{ + struct bpf_iter_dmabuf_kern *kit = (void *)it; + + if (kit->dmabuf) + kit->dmabuf = dma_buf_iter_next(kit->dmabuf); + else + kit->dmabuf = dma_buf_iter_begin(); + + return kit->dmabuf; +} + +__bpf_kfunc void bpf_iter_dmabuf_destroy(struct bpf_iter_dmabuf *it) +{ + struct bpf_iter_dmabuf_kern *kit = (void *)it; + + if (kit->dmabuf) + dma_buf_put(kit->dmabuf); +} + +__bpf_kfunc_end_defs(); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 66bded144377..c8a9b27f8663 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -7,6 +7,7 @@ #include <linux/jhash.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> +#include <linux/rcupdate_wait.h> #include <linux/random.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> @@ -15,6 +16,7 @@ #include "bpf_lru_list.h" #include "map_in_map.h" #include <linux/bpf_mem_alloc.h> +#include <asm/rqspinlock.h> #define HTAB_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ @@ -77,7 +79,7 @@ */ struct bucket { struct hlist_nulls_head head; - raw_spinlock_t raw_lock; + rqspinlock_t raw_lock; }; #define HASHTAB_MAP_LOCK_COUNT 8 @@ -103,8 +105,6 @@ struct bpf_htab { u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ u32 hashrnd; - struct lock_class_key lockdep_key; - int __percpu *map_locked[HASHTAB_MAP_LOCK_COUNT]; }; /* each htab element is struct htab_elem + key + value */ @@ -139,42 +139,26 @@ static void htab_init_buckets(struct bpf_htab *htab) for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); - raw_spin_lock_init(&htab->buckets[i].raw_lock); - lockdep_set_class(&htab->buckets[i].raw_lock, - &htab->lockdep_key); + raw_res_spin_lock_init(&htab->buckets[i].raw_lock); cond_resched(); } } -static inline int htab_lock_bucket(const struct bpf_htab *htab, - struct bucket *b, u32 hash, - unsigned long *pflags) +static inline int htab_lock_bucket(struct bucket *b, unsigned long *pflags) { unsigned long flags; + int ret; - hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); - - preempt_disable(); - if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) { - __this_cpu_dec(*(htab->map_locked[hash])); - preempt_enable(); - return -EBUSY; - } - - raw_spin_lock_irqsave(&b->raw_lock, flags); + ret = raw_res_spin_lock_irqsave(&b->raw_lock, flags); + if (ret) + return ret; *pflags = flags; - return 0; } -static inline void htab_unlock_bucket(const struct bpf_htab *htab, - struct bucket *b, u32 hash, - unsigned long flags) +static inline void htab_unlock_bucket(struct bucket *b, unsigned long flags) { - hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); - raw_spin_unlock_irqrestore(&b->raw_lock, flags); - __this_cpu_dec(*(htab->map_locked[hash])); - preempt_enable(); + raw_res_spin_unlock_irqrestore(&b->raw_lock, flags); } static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); @@ -191,20 +175,30 @@ static bool htab_is_percpu(const struct bpf_htab *htab) htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } +static inline bool is_fd_htab(const struct bpf_htab *htab) +{ + return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS; +} + +static inline void *htab_elem_value(struct htab_elem *l, u32 key_size) +{ + return l->key + round_up(key_size, 8); +} + static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { - *(void __percpu **)(l->key + key_size) = pptr; + *(void __percpu **)htab_elem_value(l, key_size) = pptr; } static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) { - return *(void __percpu **)(l->key + key_size); + return *(void __percpu **)htab_elem_value(l, key_size); } static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l) { - return *(void **)(l->key + roundup(map->key_size, 8)); + return *(void **)htab_elem_value(l, map->key_size); } static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) @@ -212,18 +206,20 @@ static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size); } +/* Both percpu and fd htab support in-place update, so no need for + * extra elem. LRU itself can remove the least used element, so + * there is no need for an extra elem during map_update. + */ static bool htab_has_extra_elems(struct bpf_htab *htab) { - return !htab_is_percpu(htab) && !htab_is_lru(htab); + return !htab_is_percpu(htab) && !htab_is_lru(htab) && !is_fd_htab(htab); } -static void htab_free_prealloced_timers(struct bpf_htab *htab) +static void htab_free_prealloced_internal_structs(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(); @@ -231,7 +227,8 @@ 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)); + bpf_map_free_internal_structs(&htab->map, + htab_elem_value(elem, htab->map.key_size)); cond_resched(); } } @@ -249,7 +246,19 @@ static void htab_free_prealloced_fields(struct bpf_htab *htab) struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); + if (htab_is_percpu(htab)) { + void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size); + int cpu; + + for_each_possible_cpu(cpu) { + bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu)); + cond_resched(); + } + } else { + bpf_obj_free_fields(htab->map.record, + htab_elem_value(elem, htab->map.key_size)); + cond_resched(); + } cond_resched(); } } @@ -291,6 +300,7 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, struct htab_elem *l; if (node) { + bpf_map_inc_elem_count(&htab->map); l = container_of(node, struct htab_elem, lru_node); memcpy(l->key, key, htab->map.key_size); return l; @@ -411,12 +421,6 @@ static int htab_map_alloc_check(union bpf_attr *attr) BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) != offsetof(struct htab_elem, hash_node.pprev)); - if (lru && !bpf_capable()) - /* LRU implementation is much complicated than other - * maps. Hence, limit to CAP_BPF. - */ - return -EPERM; - if (zero_seed && !capable(CAP_SYS_ADMIN)) /* Guard against local DoS, and discourage production use. */ return -EPERM; @@ -449,6 +453,9 @@ static int htab_map_alloc_check(union bpf_attr *attr) * kmalloc-able later in htab_map_update_elem() */ return -E2BIG; + /* percpu map value size is bound by PCPU_MIN_UNIT_SIZE */ + if (percpu && round_up(attr->value_size, 8) > PCPU_MIN_UNIT_SIZE) + return -E2BIG; return 0; } @@ -457,8 +464,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); - bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH || - attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); /* percpu_lru means each cpu has its own LRU list. * it is different from BPF_MAP_TYPE_PERCPU_HASH where * the map's value itself is percpu. percpu_lru has @@ -467,14 +472,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; - int err, i; + int err; htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE); if (!htab) return ERR_PTR(-ENOMEM); - lockdep_register_key(&htab->lockdep_key); - bpf_map_init_from_attr(&htab->map, attr); if (percpu_lru) { @@ -489,7 +492,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) num_possible_cpus()); } - /* hash table size must be power of 2 */ + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + err = -E2BIG; + if (htab->map.max_entries > 1UL << 31) + goto free_htab; + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct htab_elem) + @@ -499,10 +508,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->elem_size += round_up(htab->map.value_size, 8); - err = -E2BIG; - /* prevent zero size kmalloc and check for u32 overflow */ - if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct bucket)) + /* check for u32 overflow */ + if (htab->n_buckets > U32_MAX / sizeof(struct bucket)) + goto free_htab; + + err = bpf_map_init_elem_count(&htab->map); + if (err) goto free_htab; err = -ENOMEM; @@ -510,16 +521,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) sizeof(struct bucket), htab->map.numa_node); if (!htab->buckets) - goto free_htab; - - for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) { - htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map, - sizeof(int), - sizeof(int), - GFP_USER); - if (!htab->map_locked[i]) - goto free_map_locked; - } + goto free_elem_count; if (htab->map.map_flags & BPF_F_ZERO_SEED) htab->hashrnd = 0; @@ -556,10 +558,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (err) goto free_map_locked; - if (!percpu && !lru) { - /* lru itself can remove the least used element, so - * there is no need for an extra elem during map_update. - */ + if (htab_has_extra_elems(htab)) { err = alloc_extra_elems(htab); if (err) goto free_prealloc; @@ -583,19 +582,20 @@ free_prealloc: free_map_locked: if (htab->use_percpu_counter) percpu_counter_destroy(&htab->pcount); - for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) - free_percpu(htab->map_locked[i]); bpf_map_area_free(htab->buckets); bpf_mem_alloc_destroy(&htab->pcpu_ma); bpf_mem_alloc_destroy(&htab->ma); +free_elem_count: + bpf_map_free_elem_count(&htab->map); free_htab: - lockdep_unregister_key(&htab->lockdep_key); bpf_map_area_free(htab); return ERR_PTR(err); } static inline u32 htab_map_hash(const void *key, u32 key_len, u32 hashrnd) { + if (likely(key_len % 4 == 0)) + return jhash2(key, key_len / 4, hashrnd); return jhash(key, key_len, hashrnd); } @@ -657,8 +657,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) struct htab_elem *l; u32 hash, key_size; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && - !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); key_size = map->key_size; @@ -676,7 +675,7 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key) struct htab_elem *l = __htab_map_lookup_elem(map, key); if (l) - return l->key + round_up(map->key_size, 8); + return htab_elem_value(l, map->key_size); return NULL; } @@ -715,7 +714,7 @@ static __always_inline void *__htab_lru_map_lookup_elem(struct bpf_map *map, if (l) { if (mark) bpf_lru_node_set_ref(&l->lru_node); - return l->key + round_up(map->key_size, 8); + return htab_elem_value(l, map->key_size); } return NULL; @@ -759,9 +758,20 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, static void check_and_free_fields(struct bpf_htab *htab, struct htab_elem *elem) { - void *map_value = elem->key + round_up(htab->map.key_size, 8); + if (IS_ERR_OR_NULL(htab->map.record)) + return; + + if (htab_is_percpu(htab)) { + void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size); + int cpu; + + for_each_possible_cpu(cpu) + bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu)); + } else { + void *map_value = htab_elem_value(elem, htab->map.key_size); - bpf_obj_free_fields(htab->map.record, map_value); + bpf_obj_free_fields(htab->map.record, map_value); + } } /* It is called from the bpf_lru_list when the LRU needs to delete @@ -781,19 +791,21 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) b = __select_bucket(htab, tgt_l->hash); head = &b->head; - ret = htab_lock_bucket(htab, b, tgt_l->hash, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) return false; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { hlist_nulls_del_rcu(&l->hash_node); - check_and_free_fields(htab, l); + bpf_map_dec_elem_count(&htab->map); break; } - htab_unlock_bucket(htab, b, tgt_l->hash, flags); + htab_unlock_bucket(b, flags); + if (l == tgt_l) + check_and_free_fields(htab, l); return l == tgt_l; } @@ -858,9 +870,10 @@ find_first_elem: static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { + check_and_free_fields(htab, l); + if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr); - check_and_free_fields(htab, l); bpf_mem_cache_free(&htab->ma, l); } @@ -871,7 +884,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) if (map->ops->map_fd_put_ptr) { ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, true); } } @@ -885,6 +898,8 @@ static bool is_map_full(struct bpf_htab *htab) static void inc_elem_count(struct bpf_htab *htab) { + bpf_map_inc_elem_count(&htab->map); + if (htab->use_percpu_counter) percpu_counter_add_batch(&htab->pcount, 1, PERCPU_COUNTER_BATCH); else @@ -893,6 +908,8 @@ static void inc_elem_count(struct bpf_htab *htab) static void dec_elem_count(struct bpf_htab *htab) { + bpf_map_dec_elem_count(&htab->map); + if (htab->use_percpu_counter) percpu_counter_add_batch(&htab->pcount, -1, PERCPU_COUNTER_BATCH); else @@ -905,8 +922,9 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { + bpf_map_dec_elem_count(&htab->map); check_and_free_fields(htab, l); - __pcpu_freelist_push(&htab->freelist, &l->fnode); + pcpu_freelist_push(&htab->freelist, &l->fnode); } else { dec_elem_count(htab); htab_elem_free(htab, l); @@ -916,16 +934,21 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, void *value, bool onallcpus) { + void *ptr; + if (!onallcpus) { /* copy true value_size bytes */ - memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + ptr = this_cpu_ptr(pptr); + copy_map_value(&htab->map, ptr, value); + bpf_obj_free_fields(htab->map.record, ptr); } else { u32 size = round_up(htab->map.value_size, 8); int off = 0, cpu; for_each_possible_cpu(cpu) { - bpf_long_memcpy(per_cpu_ptr(pptr, cpu), - value + off, size); + ptr = per_cpu_ptr(pptr, cpu); + copy_map_value_long(&htab->map, ptr, value + off); + bpf_obj_free_fields(htab->map.record, ptr); off += size; } } @@ -940,16 +963,14 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, * (onallcpus=false always when coming from bpf prog). */ if (!onallcpus) { - u32 size = round_up(htab->map.value_size, 8); int current_cpu = raw_smp_processor_id(); int cpu; for_each_possible_cpu(cpu) { if (cpu == current_cpu) - bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value, - size); - else - memset(per_cpu_ptr(pptr, cpu), 0, size); + copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value); + else /* Since elem is preallocated, we cannot touch special fields */ + zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu)); } } else { pcpu_copy_value(htab, pptr, value, onallcpus); @@ -958,8 +979,7 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) { - return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && - BITS_PER_LONG == 64; + return is_fd_htab(htab) && BITS_PER_LONG == 64; } static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, @@ -979,7 +999,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; - htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; @@ -988,6 +1007,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, if (!l) return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); + bpf_map_inc_elem_count(&htab->map); } } else { if (is_map_full(htab)) @@ -1004,8 +1024,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-ENOMEM); goto dec_count; } - check_and_init_map_value(&htab->map, - l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); @@ -1014,14 +1032,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, pptr = htab_elem_get_ptr(l_new, key_size); } else { /* alloc_percpu zero-fills */ - pptr = bpf_mem_cache_alloc(&htab->pcpu_ma); - if (!pptr) { + void *ptr = bpf_mem_cache_alloc(&htab->pcpu_ma); + + if (!ptr) { bpf_mem_cache_free(&htab->ma, l_new); l_new = ERR_PTR(-ENOMEM); goto dec_count; } - l_new->ptr_to_pptr = pptr; - pptr = *(void **)pptr; + l_new->ptr_to_pptr = ptr; + pptr = *(void __percpu **)ptr; } pcpu_init_value(htab, pptr, value, onallcpus); @@ -1030,11 +1049,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, htab_elem_set_ptr(l_new, key_size, pptr); } else if (fd_htab_map_needs_adjust(htab)) { size = round_up(size, 8); - memcpy(l_new->key + round_up(key_size, 8), value, size); + memcpy(htab_elem_value(l_new, key_size), value, size); } else { - copy_map_value(&htab->map, - l_new->key + round_up(key_size, 8), - value); + copy_map_value(&htab->map, htab_elem_value(l_new, key_size), value); } l_new->hash = hash; @@ -1059,11 +1076,11 @@ static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, } /* Called from syscall or from eBPF program */ -static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long htab_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct htab_elem *l_new = NULL, *l_old; + struct htab_elem *l_new, *l_old; struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; @@ -1074,8 +1091,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && - !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); key_size = map->key_size; @@ -1096,7 +1112,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (l_old) { /* grab the element lock and update value in place */ copy_map_value_locked(map, - l_old->key + round_up(key_size, 8), + htab_elem_value(l_old, key_size), value, false); return 0; } @@ -1106,7 +1122,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, */ } - ret = htab_lock_bucket(htab, b, hash, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) return ret; @@ -1124,7 +1140,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, * and update element in place */ copy_map_value_locked(map, - l_old->key + round_up(key_size, 8), + htab_elem_value(l_old, key_size), value, false); ret = 0; goto err; @@ -1144,25 +1160,31 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { hlist_nulls_del_rcu(&l_old->hash_node); - if (!htab_is_prealloc(htab)) - free_htab_elem(htab, l_old); - else + + /* l_old has already been stashed in htab->extra_elems, free + * its special fields before it is available for reuse. + */ + if (htab_is_prealloc(htab)) check_and_free_fields(htab, l_old); } - ret = 0; + htab_unlock_bucket(b, flags); + if (l_old && !htab_is_prealloc(htab)) + free_htab_elem(htab, l_old); + return 0; err: - htab_unlock_bucket(htab, b, hash, flags); + htab_unlock_bucket(b, flags); return ret; } static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem) { check_and_free_fields(htab, elem); + bpf_map_dec_elem_count(&htab->map); bpf_lru_push_free(&htab->lru, &elem->lru_node); } -static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new, *l_old = NULL; @@ -1176,8 +1198,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && - !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); key_size = map->key_size; @@ -1194,12 +1215,11 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, l_new = prealloc_lru_pop(htab, key, hash); if (!l_new) return -ENOMEM; - copy_map_value(&htab->map, - l_new->key + round_up(map->key_size, 8), value); + copy_map_value(&htab->map, htab_elem_value(l_new, map->key_size), value); - ret = htab_lock_bucket(htab, b, hash, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) - return ret; + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1218,8 +1238,9 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, ret = 0; err: - htab_unlock_bucket(htab, b, hash, flags); + htab_unlock_bucket(b, flags); +err_lock_bucket: if (ret) htab_lru_push_free(htab, l_new); else if (l_old) @@ -1228,13 +1249,14 @@ err: return ret; } -static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags, - bool onallcpus) +static long htab_map_update_elem_in_place(struct bpf_map *map, void *key, + void *value, u64 map_flags, + bool percpu, bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct htab_elem *l_new = NULL, *l_old; + struct htab_elem *l_new, *l_old; struct hlist_nulls_head *head; + void *old_map_ptr = NULL; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -1244,8 +1266,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && - !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); key_size = map->key_size; @@ -1254,7 +1275,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, b = __select_bucket(htab, hash); head = &b->head; - ret = htab_lock_bucket(htab, b, hash, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) return ret; @@ -1265,27 +1286,35 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, goto err; if (l_old) { - /* per-cpu hash map can update value in-place */ - pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), - value, onallcpus); + /* Update value in-place */ + if (percpu) { + pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), + value, onallcpus); + } else { + void **inner_map_pptr = htab_elem_value(l_old, key_size); + + old_map_ptr = *inner_map_pptr; + WRITE_ONCE(*inner_map_pptr, *(void **)value); + } } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true, onallcpus, NULL); + hash, percpu, onallcpus, NULL); if (IS_ERR(l_new)) { ret = PTR_ERR(l_new); goto err; } hlist_nulls_add_head_rcu(&l_new->hash_node, head); } - ret = 0; err: - htab_unlock_bucket(htab, b, hash, flags); + htab_unlock_bucket(b, flags); + if (old_map_ptr) + map->ops->map_fd_put_ptr(map, old_map_ptr, true); return ret; } -static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags, - bool onallcpus) +static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags, + bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; @@ -1299,8 +1328,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && - !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); key_size = map->key_size; @@ -1320,9 +1348,9 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, return -ENOMEM; } - ret = htab_lock_bucket(htab, b, hash, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) - return ret; + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1344,27 +1372,30 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - htab_unlock_bucket(htab, b, hash, flags); - if (l_new) + htab_unlock_bucket(b, flags); +err_lock_bucket: + if (l_new) { + bpf_map_dec_elem_count(&htab->map); bpf_lru_push_free(&htab->lru, &l_new->lru_node); + } return ret; } -static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { - return __htab_percpu_map_update_elem(map, key, value, map_flags, false); + return htab_map_update_elem_in_place(map, key, value, map_flags, true, false); } -static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { return __htab_lru_percpu_map_update_elem(map, key, value, map_flags, false); } /* Called from syscall or from eBPF program */ -static int htab_map_delete_elem(struct bpf_map *map, void *key) +static long htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; @@ -1374,8 +1405,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) u32 hash, key_size; int ret; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && - !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); key_size = map->key_size; @@ -1383,24 +1413,24 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - ret = htab_lock_bucket(htab, b, hash, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) return ret; l = lookup_elem_raw(head, hash, key, key_size); - - if (l) { + if (l) hlist_nulls_del_rcu(&l->hash_node); - free_htab_elem(htab, l); - } else { + else ret = -ENOENT; - } - htab_unlock_bucket(htab, b, hash, flags); + htab_unlock_bucket(b, flags); + + if (l) + free_htab_elem(htab, l); return ret; } -static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) +static long htab_lru_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; @@ -1410,8 +1440,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) u32 hash, key_size; int ret; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && - !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); key_size = map->key_size; @@ -1419,7 +1448,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - ret = htab_lock_bucket(htab, b, hash, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) return ret; @@ -1430,7 +1459,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) else ret = -ENOENT; - htab_unlock_bucket(htab, b, hash, flags); + htab_unlock_bucket(b, flags); if (l) htab_lru_push_free(htab, l); return ret; @@ -1440,10 +1469,9 @@ static void delete_all_elements(struct bpf_htab *htab) { int i; - /* It's called from a worker thread, so disable migration here, - * since bpf_mem_cache_free() relies on that. + /* It's called from a worker thread and migration has been disabled, + * therefore, it is OK to invoke bpf_mem_cache_free() directly. */ - migrate_disable(); for (i = 0; i < htab->n_buckets; i++) { struct hlist_nulls_head *head = select_bucket(htab, i); struct hlist_nulls_node *n; @@ -1453,11 +1481,11 @@ 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_internal_structs(struct bpf_htab *htab) { int i; @@ -1468,32 +1496,33 @@ static void htab_free_malloced_timers(struct bpf_htab *htab) struct htab_elem *l; 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)); + /* We only free internal structs on uref dropping to zero */ + bpf_map_free_internal_structs(&htab->map, + htab_elem_value(l, htab->map.key_size)); } cond_resched_rcu(); } rcu_read_unlock(); } -static void htab_map_free_timers(struct bpf_map *map) +static void htab_map_free_internal_structs(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)) + /* We only free internal structs on uref dropping to zero */ + if (!bpf_map_has_internal_structs(map)) return; - if (!htab_is_prealloc(htab)) - htab_free_malloced_timers(htab); + + if (htab_is_prealloc(htab)) + htab_free_prealloced_internal_structs(htab); else - htab_free_prealloced_timers(htab); + htab_free_malloced_internal_structs(htab); } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void htab_map_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - int i; /* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback. * bpf_free_used_maps() is called after bpf prog is no longer executing. @@ -1501,7 +1530,7 @@ 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)) { @@ -1511,15 +1540,13 @@ static void htab_map_free(struct bpf_map *map) prealloc_destroy(htab); } + bpf_map_free_elem_count(map); free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); bpf_mem_alloc_destroy(&htab->pcpu_ma); bpf_mem_alloc_destroy(&htab->ma); if (htab->use_percpu_counter) percpu_counter_destroy(&htab->pcount); - for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) - free_percpu(htab->map_locked[i]); - lockdep_unregister_key(&htab->lockdep_key); bpf_map_area_free(htab); } @@ -1539,7 +1566,7 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key, btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); seq_puts(m, ": "); btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); rcu_read_unlock(); } @@ -1562,48 +1589,48 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, b = __select_bucket(htab, hash); head = &b->head; - ret = htab_lock_bucket(htab, b, hash, &bflags); + ret = htab_lock_bucket(b, &bflags); if (ret) return ret; l = lookup_elem_raw(head, hash, key, key_size); if (!l) { ret = -ENOENT; - } else { - if (is_percpu) { - u32 roundup_value_size = round_up(map->value_size, 8); - void __percpu *pptr; - int off = 0, cpu; + goto out_unlock; + } - pptr = htab_elem_get_ptr(l, key_size); - for_each_possible_cpu(cpu) { - bpf_long_memcpy(value + off, - per_cpu_ptr(pptr, cpu), - roundup_value_size); - off += roundup_value_size; - } - } else { - u32 roundup_key_size = round_up(map->key_size, 8); + if (is_percpu) { + u32 roundup_value_size = round_up(map->value_size, 8); + void __percpu *pptr; + int off = 0, cpu; - if (flags & BPF_F_LOCK) - copy_map_value_locked(map, value, l->key + - roundup_key_size, - true); - else - copy_map_value(map, value, l->key + - roundup_key_size); - check_and_init_map_value(map, value); + pptr = htab_elem_get_ptr(l, key_size); + for_each_possible_cpu(cpu) { + copy_map_value_long(&htab->map, value + off, per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(&htab->map, value + off); + off += roundup_value_size; } + } else { + void *src = htab_elem_value(l, map->key_size); - hlist_nulls_del_rcu(&l->hash_node); - if (!is_lru_map) - free_htab_elem(htab, l); + if (flags & BPF_F_LOCK) + copy_map_value_locked(map, value, src, true); + else + copy_map_value(map, value, src); + /* Zeroing special fields in the temp buffer */ + check_and_init_map_value(map, value); } + hlist_nulls_del_rcu(&l->hash_node); - htab_unlock_bucket(htab, b, hash, bflags); +out_unlock: + htab_unlock_bucket(b, bflags); - if (is_lru_map && l) - htab_lru_push_free(htab, l); + if (l) { + if (is_lru_map) + htab_lru_push_free(htab, l); + else + free_htab_elem(htab, l); + } return ret; } @@ -1646,12 +1673,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, bool is_percpu) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - u32 bucket_cnt, total, key_size, value_size, roundup_key_size; void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val; void __user *uvalues = u64_to_user_ptr(attr->batch.values); void __user *ukeys = u64_to_user_ptr(attr->batch.keys); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); u32 batch, max_count, size, bucket_size, map_id; + u32 bucket_cnt, total, key_size, value_size; struct htab_elem *node_to_free = NULL; u64 elem_map_flags, map_flags; struct hlist_nulls_head *head; @@ -1686,7 +1713,6 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, return -ENOENT; key_size = htab->map.key_size; - roundup_key_size = round_up(htab->map.key_size, 8); value_size = htab->map.value_size; size = round_up(value_size, 8); if (is_percpu) @@ -1718,7 +1744,7 @@ again_nocopy: head = &b->head; /* do not grab the lock unless need it (bucket_cnt > 0). */ if (locked) { - ret = htab_lock_bucket(htab, b, batch, &flags); + ret = htab_lock_bucket(b, &flags); if (ret) { rcu_read_unlock(); bpf_enable_instrumentation(); @@ -1741,7 +1767,7 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - htab_unlock_bucket(htab, b, batch, flags); + htab_unlock_bucket(b, flags); rcu_read_unlock(); bpf_enable_instrumentation(); goto after_loop; @@ -1752,7 +1778,7 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - htab_unlock_bucket(htab, b, batch, flags); + htab_unlock_bucket(b, flags); rcu_read_unlock(); bpf_enable_instrumentation(); kvfree(keys); @@ -1773,13 +1799,13 @@ again_nocopy: pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { - bpf_long_memcpy(dst_val + off, - per_cpu_ptr(pptr, cpu), size); + copy_map_value_long(&htab->map, dst_val + off, per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(&htab->map, dst_val + off); off += size; } } else { - value = l->key + roundup_key_size; - if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + value = htab_elem_value(l, key_size); + if (is_fd_htab(htab)) { struct bpf_map **inner_map = value; /* Actual value is the id of the inner map */ @@ -1792,6 +1818,7 @@ again_nocopy: true); else copy_map_value(map, dst_val, value); + /* Zeroing special fields in the temp buffer */ check_and_init_map_value(map, dst_val); } if (do_delete) { @@ -1801,25 +1828,29 @@ again_nocopy: * may cause deadlock. See comments in function * prealloc_lru_pop(). Let us do bpf_lru_push_free() * after releasing the bucket lock. + * + * For htab of maps, htab_put_fd_value() in + * free_htab_elem() may acquire a spinlock with bucket + * lock being held and it violates the lock rule, so + * invoke free_htab_elem() after unlock as well. */ - if (is_lru_map) { - l->batch_flink = node_to_free; - node_to_free = l; - } else { - free_htab_elem(htab, l); - } + l->batch_flink = node_to_free; + node_to_free = l; } dst_key += key_size; dst_val += value_size; } - htab_unlock_bucket(htab, b, batch, flags); + htab_unlock_bucket(b, flags); locked = false; while (node_to_free) { l = node_to_free; node_to_free = node_to_free->batch_flink; - htab_lru_push_free(htab, l); + if (is_lru_map) + htab_lru_push_free(htab, l); + else + free_htab_elem(htab, l); } next_batch: @@ -2024,11 +2055,11 @@ static void *bpf_hash_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem) { struct bpf_iter_seq_hash_map_info *info = seq->private; - u32 roundup_key_size, roundup_value_size; struct bpf_iter__bpf_map_elem ctx = {}; struct bpf_map *map = info->map; struct bpf_iter_meta meta; int ret = 0, off = 0, cpu; + u32 roundup_value_size; struct bpf_prog *prog; void __percpu *pptr; @@ -2038,17 +2069,16 @@ static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem) ctx.meta = &meta; ctx.map = info->map; if (elem) { - roundup_key_size = round_up(map->key_size, 8); ctx.key = elem->key; if (!info->percpu_value_buf) { - ctx.value = elem->key + roundup_key_size; + ctx.value = htab_elem_value(elem, map->key_size); } else { roundup_value_size = round_up(map->value_size, 8); pptr = htab_elem_get_ptr(elem, map->key_size); for_each_possible_cpu(cpu) { - bpf_long_memcpy(info->percpu_value_buf + off, - per_cpu_ptr(pptr, cpu), - roundup_value_size); + copy_map_value_long(map, info->percpu_value_buf + off, + per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(map, info->percpu_value_buf + off); off += roundup_value_size; } ctx.value = info->percpu_value_buf; @@ -2119,14 +2149,13 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_hash_map_info), }; -static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn, - void *callback_ctx, u64 flags) +static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn, + void *callback_ctx, u64 flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; struct hlist_nulls_node *n; struct htab_elem *elem; - u32 roundup_key_size; int i, num_elems = 0; void __percpu *pptr; struct bucket *b; @@ -2134,29 +2163,29 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_f bool is_percpu; u64 ret = 0; + cant_migrate(); + if (flags != 0) return -EINVAL; is_percpu = htab_is_percpu(htab); - roundup_key_size = round_up(map->key_size, 8); - /* disable migration so percpu value prepared here will be the - * same as the one seen by the bpf program with bpf_map_lookup_elem(). + /* migration has been disabled, so percpu value prepared here will be + * the same as the one seen by the bpf program with + * bpf_map_lookup_elem(). */ - if (is_percpu) - migrate_disable(); for (i = 0; i < htab->n_buckets; i++) { b = &htab->buckets[i]; rcu_read_lock(); head = &b->head; - hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) { + hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) { key = elem->key; if (is_percpu) { /* current cpu value for percpu map */ pptr = htab_elem_get_ptr(elem, map->key_size); val = this_cpu_ptr(pptr); } else { - val = elem->key + roundup_key_size; + val = htab_elem_value(elem, map->key_size); } num_elems++; ret = callback_fn((u64)(long)map, (u64)(long)key, @@ -2170,11 +2199,47 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_f rcu_read_unlock(); } out: - if (is_percpu) - migrate_enable(); return num_elems; } +static u64 htab_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 value_size = round_up(htab->map.value_size, 8); + bool prealloc = htab_is_prealloc(htab); + bool percpu = htab_is_percpu(htab); + bool lru = htab_is_lru(htab); + u64 num_entries; + u64 usage = sizeof(struct bpf_htab); + + usage += sizeof(struct bucket) * htab->n_buckets; + usage += sizeof(int) * num_possible_cpus() * HASHTAB_MAP_LOCK_COUNT; + if (prealloc) { + num_entries = map->max_entries; + if (htab_has_extra_elems(htab)) + num_entries += num_possible_cpus(); + + usage += htab->elem_size * num_entries; + + if (percpu) + usage += value_size * num_possible_cpus() * num_entries; + else if (!lru) + usage += sizeof(struct htab_elem *) * num_possible_cpus(); + } else { +#define LLIST_NODE_SZ sizeof(struct llist_node) + + num_entries = htab->use_percpu_counter ? + percpu_counter_sum(&htab->pcount) : + atomic_read(&htab->count); + usage += (htab->elem_size + LLIST_NODE_SZ) * num_entries; + if (percpu) { + usage += (LLIST_NODE_SZ + sizeof(void *)) * num_entries; + usage += value_size * num_possible_cpus() * num_entries; + } + } + return usage; +} + BTF_ID_LIST_SINGLE(htab_map_btf_ids, struct, bpf_htab) const struct bpf_map_ops htab_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -2182,7 +2247,7 @@ 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_internal_structs, .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, @@ -2191,6 +2256,7 @@ const struct bpf_map_ops htab_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2202,7 +2268,7 @@ 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_internal_structs, .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, @@ -2212,6 +2278,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2228,6 +2295,26 @@ 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) + roundup(map->key_size, 8)); + *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; @@ -2292,8 +2379,8 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) */ pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { - bpf_long_memcpy(value + off, - per_cpu_ptr(pptr, cpu), size); + copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(map, value + off); off += size; } ret = 0; @@ -2313,8 +2400,8 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, ret = __htab_lru_percpu_map_update_elem(map, key, value, map_flags, true); else - ret = __htab_percpu_map_update_elem(map, key, value, map_flags, - true); + ret = htab_map_update_elem_in_place(map, key, value, map_flags, + true, true); rcu_read_unlock(); return ret; @@ -2342,7 +2429,7 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, seq_printf(m, "\tcpu%d: ", cpu); btf_type_seq_show(map->btf, map->btf_value_type_id, per_cpu_ptr(pptr, cpu), m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); } seq_puts(m, "}\n"); @@ -2356,6 +2443,7 @@ 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, @@ -2363,6 +2451,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_percpu), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2382,6 +2471,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru_percpu), .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, @@ -2408,7 +2498,7 @@ static void fd_htab_map_free(struct bpf_map *map) hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { void *ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); } } @@ -2435,21 +2525,26 @@ int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value) return ret; } -/* only called from syscall */ +/* Only called from syscall */ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags) { void *ptr; int ret; - u32 ufd = *(u32 *)value; - ptr = map->ops->map_fd_get_ptr(map, map_file, ufd); + ptr = map->ops->map_fd_get_ptr(map, map_file, *(int *)value); if (IS_ERR(ptr)) return PTR_ERR(ptr); - ret = htab_map_update_elem(map, key, &ptr, map_flags); + /* The htab bucket lock is always held during update operations in fd + * htab map, and the following rcu_read_lock() is only used to avoid + * the WARN_ON_ONCE in htab_map_update_elem_in_place(). + */ + rcu_read_lock(); + ret = htab_map_update_elem_in_place(map, key, &ptr, map_flags, false, false); + rcu_read_unlock(); if (ret) - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); return ret; } @@ -2519,6 +2614,7 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = htab_of_map_gen_lookup, .map_check_btf = map_check_no_btf, + .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index af30c6cbd65d..db72b96f9c8c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -18,9 +18,17 @@ #include <linux/pid_namespace.h> #include <linux/poison.h> #include <linux/proc_ns.h> +#include <linux/sched/task.h> #include <linux/security.h> #include <linux/btf_ids.h> #include <linux/bpf_mem_alloc.h> +#include <linux/kasan.h> +#include <linux/bpf_verifier.h> +#include <linux/uaccess.h> +#include <linux/verification.h> +#include <linux/task_work.h> +#include <linux/irq_work.h> +#include <linux/buildid.h> #include "../../lib/kstrtox.h" @@ -30,12 +38,12 @@ * * Different map implementations will rely on rcu in map methods * lookup/update/delete, therefore eBPF programs must run under rcu lock - * if program is allowed to access maps, so check rcu_read_lock_held in - * all three functions. + * if program is allowed to access maps, so check rcu_read_lock_held() or + * rcu_read_lock_trace_held() in all three functions. */ BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); return (unsigned long) map->ops->map_lookup_elem(map, key); } @@ -51,7 +59,7 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = { BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, void *, value, u64, flags) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); return map->ops->map_update_elem(map, key, value, flags); } @@ -68,7 +76,7 @@ const struct bpf_func_proto bpf_map_update_elem_proto = { BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); return map->ops->map_delete_elem(map, key); } @@ -106,7 +114,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) @@ -119,12 +127,12 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!bpf_rcu_lock_held()); return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu); } @@ -153,6 +161,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = { .func = bpf_get_smp_processor_id, .gpl_only = false, .ret_type = RET_INTEGER, + .allow_fastcall = true, }; BPF_CALL_0(bpf_get_numa_node_id) @@ -257,7 +266,7 @@ BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size) goto err_clear; /* Verifier guarantees that size > 0 */ - strscpy(buf, task->comm, size); + strscpy_pad(buf, task->comm, size); return 0; err_clear: memset(buf, 0, size); @@ -285,6 +294,7 @@ static inline void __bpf_spin_lock(struct bpf_spin_lock *lock) compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0"); BUILD_BUG_ON(sizeof(*l) != sizeof(__u32)); BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32)); + preempt_disable(); arch_spin_lock(l); } @@ -293,6 +303,7 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) arch_spinlock_t *l = (void *)lock; arch_spin_unlock(l); + preempt_enable(); } #else @@ -327,7 +338,7 @@ static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) __this_cpu_write(irqsave_flags, flags); } -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) { __bpf_spin_lock_irqsave(lock); return 0; @@ -350,7 +361,7 @@ static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) local_irq_restore(flags); } -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) { __bpf_spin_unlock_irqrestore(lock); return 0; @@ -510,16 +521,15 @@ static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags, } BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags, - long *, res) + s64 *, res) { long long _res; int err; + *res = 0; err = __bpf_strtoll(buf, buf_len, flags, &_res); if (err < 0) return err; - if (_res != (long)_res) - return -ERANGE; *res = _res; return err; } @@ -531,23 +541,23 @@ const struct bpf_func_proto bpf_strtol_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, + .arg4_size = sizeof(s64), }; BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags, - unsigned long *, res) + u64 *, res) { unsigned long long _res; bool is_negative; int err; + *res = 0; err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); if (err < 0) return err; if (is_negative) return -EINVAL; - if (_res != (unsigned long)_res) - return -ERANGE; *res = _res; return err; } @@ -559,7 +569,8 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, + .arg4_size = sizeof(u64), }; BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2) @@ -571,7 +582,7 @@ static const struct bpf_func_proto bpf_strncmp_proto = { .func = bpf_strncmp, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_CONST_STR, }; @@ -707,7 +718,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu) if (cpu >= nr_cpu_ids) return (unsigned long)NULL; - return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu); + return (unsigned long)per_cpu_ptr((const void __percpu *)(const uintptr_t)ptr, cpu); } const struct bpf_func_proto bpf_per_cpu_ptr_proto = { @@ -720,7 +731,7 @@ const struct bpf_func_proto bpf_per_cpu_ptr_proto = { BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr) { - return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr); + return (unsigned long)this_cpu_ptr((const void __percpu *)(const uintptr_t)percpu_ptr); } const struct bpf_func_proto bpf_this_cpu_ptr_proto = { @@ -753,22 +764,14 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, return -EINVAL; } -/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary - * arguments representation. - */ -#define MAX_BPRINTF_BUF_LEN 512 - /* Support executing three nested bprintf helper calls on a given CPU */ #define MAX_BPRINTF_NEST_LEVEL 3 -struct bpf_bprintf_buffers { - char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; -}; -static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); + +static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs); static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); -static int try_get_fmt_tmp_buf(char **tmp_buf) +int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs) { - struct bpf_bprintf_buffers *bufs; int nest_level; preempt_disable(); @@ -778,18 +781,24 @@ static int try_get_fmt_tmp_buf(char **tmp_buf) preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_bprintf_bufs); - *tmp_buf = bufs->tmp_bufs[nest_level - 1]; + *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]); return 0; } -void bpf_bprintf_cleanup(void) +void bpf_put_buffers(void) { - if (this_cpu_read(bpf_bprintf_nest_level)) { - this_cpu_dec(bpf_bprintf_nest_level); - preempt_enable(); - } + if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0)) + return; + this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); +} + +void bpf_bprintf_cleanup(struct bpf_bprintf_data *data) +{ + if (!data->bin_args && !data->buf) + return; + bpf_put_buffers(); } /* @@ -798,18 +807,20 @@ void bpf_bprintf_cleanup(void) * Returns a negative value if fmt is an invalid format string or 0 otherwise. * * This can be used in two ways: - * - Format string verification only: when bin_args is NULL + * - Format string verification only: when data->get_bin_args is false * - Arguments preparation: in addition to the above verification, it writes in - * bin_args a binary representation of arguments usable by bstr_printf where - * pointers from BPF have been sanitized. + * data->bin_args a binary representation of arguments usable by bstr_printf + * where pointers from BPF have been sanitized. * * In argument preparation mode, if 0 is returned, safe temporary buffers are * allocated and bpf_bprintf_cleanup should be called to free them after use. */ -int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, - u32 **bin_args, u32 num_args) +int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args, + u32 num_args, struct bpf_bprintf_data *data) { + bool get_buffers = (data->get_bin_args && num_args) || data->get_buf; char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end; + struct bpf_bprintf_buffers *buffers = NULL; size_t sizeof_cur_arg, sizeof_cur_ip; int err, i, num_spec = 0; u64 cur_arg; @@ -820,14 +831,19 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, return -EINVAL; fmt_size = fmt_end - fmt; - if (bin_args) { - if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) - return -EBUSY; + if (get_buffers && bpf_try_get_buffers(&buffers)) + return -EBUSY; - tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; - *bin_args = (u32 *)tmp_buf; + if (data->get_bin_args) { + if (num_args) + tmp_buf = buffers->bin_args; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS; + data->bin_args = (u32 *)tmp_buf; } + if (data->get_buf) + data->buf = buffers->buf; + for (i = 0; i < fmt_size; i++) { if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { err = -EINVAL; @@ -865,6 +881,13 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (fmt[i] == 'p') { sizeof_cur_arg = sizeof(long); + if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || + ispunct(fmt[i + 1])) { + if (tmp_buf) + cur_arg = raw_args[num_spec]; + goto nocopy_fmt; + } + if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') && fmt[i + 2] == 's') { fmt_ptype = fmt[i + 1]; @@ -872,11 +895,9 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, goto fmt_str; } - if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || - ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' || + if (fmt[i + 1] == 'K' || fmt[i + 1] == 'x' || fmt[i + 1] == 's' || fmt[i + 1] == 'S') { - /* just kernel pointers */ if (tmp_buf) cur_arg = raw_args[num_spec]; i++; @@ -1021,31 +1042,33 @@ nocopy_fmt: err = 0; out: if (err) - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(data); return err; } BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, - const void *, data, u32, data_len) + const void *, args, u32, data_len) { + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; int err, num_args; - u32 *bin_args; if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; /* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we * can safely give an unbounded size. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, data, &bin_args, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data); if (err < 0) return err; - err = bstr_printf(str, str_size, fmt, bin_args); + err = bstr_printf(str, str_size, fmt, data.bin_args); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return err + 1; } @@ -1061,11 +1084,34 @@ const struct bpf_func_proto bpf_snprintf_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +static void *map_key_from_value(struct bpf_map *map, void *value, u32 *arr_idx) +{ + if (map->map_type == BPF_MAP_TYPE_ARRAY) { + struct bpf_array *array = container_of(map, struct bpf_array, map); + + *arr_idx = ((char *)value - array->value) / array->elem_size; + return arr_idx; + } + return (void *)value - round_up(map->key_size, 8); +} + +struct bpf_async_cb { + struct bpf_map *map; + struct bpf_prog *prog; + void __rcu *callback_fn; + void *value; + union { + struct rcu_head rcu; + struct work_struct delete_work; + }; + 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. @@ -1078,16 +1124,24 @@ 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; + atomic_t cancelling; +}; + +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 */ -struct bpf_timer_kern { - struct bpf_hrtimer *timer; +/* 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. @@ -1095,19 +1149,24 @@ 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; @@ -1118,15 +1177,8 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) * bpf_map_delete_elem() on the same timer. */ this_cpu_write(hrtimer_running, t); - 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); - } + key = map_key_from_value(map, value, &idx); callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); /* The verifier checked that return value is zero. */ @@ -1136,57 +1188,163 @@ 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) { - clockid_t clockid = flags & (MAX_CLOCKS - 1); + 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; + + key = map_key_from_value(map, value, &idx); + + 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_async_cb_rcu_free(struct rcu_head *rcu) +{ + struct bpf_async_cb *cb = container_of(rcu, struct bpf_async_cb, rcu); + + kfree_nolock(cb); +} + +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); + + call_rcu(&w->cb.rcu, bpf_async_cb_rcu_free); +} + +static void bpf_timer_delete_work(struct work_struct *work) +{ + struct bpf_hrtimer *t = container_of(work, struct bpf_hrtimer, cb.delete_work); + + /* 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 + * call_rcu() right after for both preallocated and non-preallocated + * maps. The async->cb = NULL was already done and no code path can see + * address 't' anymore. Timer if armed for existing bpf_hrtimer before + * bpf_timer_cancel_and_free will have been cancelled. + */ + hrtimer_cancel(&t->timer); + call_rcu(&t->cb.rcu, bpf_async_cb_rcu_free); +} + +static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u64 flags, + enum bpf_async_type type) +{ + 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; } + + cb = bpf_map_kmalloc_nolock(map, size, 0, map->numa_node); + if (!cb) { + ret = -ENOMEM; + goto out; + } + + switch (type) { + case BPF_ASYNC_TYPE_TIMER: + clockid = flags & (MAX_CLOCKS - 1); + t = (struct bpf_hrtimer *)cb; + + atomic_set(&t->cancelling, 0); + INIT_WORK(&t->cb.delete_work, bpf_timer_delete_work); + hrtimer_setup(&t->timer, bpf_timer_cb, clockid, HRTIMER_MODE_REL_SOFT); + 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. + */ + smp_mb(); if (!atomic64_read(&map->usercnt)) { /* maps with timers must be either held by user space * or pinned in bpffs. */ + WRITE_ONCE(async->cb, NULL); + kfree_nolock(cb); ret = -EPERM; - 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) { - 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; - timer->timer = t; 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, @@ -1196,22 +1354,23 @@ 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 @@ -1220,7 +1379,7 @@ 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. @@ -1233,14 +1392,20 @@ 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, @@ -1249,22 +1414,32 @@ 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; + enum hrtimer_mode mode; if (in_nmi()) return -EOPNOTSUPP; - if (flags) + if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN)) return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; - if (!t || !t->prog) { + if (!t || !t->cb.prog) { ret = -EINVAL; goto out; } - hrtimer_start(&t->timer, ns_to_ktime(nsecs), HRTIMER_MODE_REL_SOFT); + + if (flags & BPF_F_TIMER_ABS) + mode = HRTIMER_MODE_ABS_SOFT; + else + mode = HRTIMER_MODE_REL_SOFT; + + if (flags & BPF_F_TIMER_CPU_PIN) + mode |= HRTIMER_MODE_PINNED; + + hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode); out: __bpf_spin_unlock_irqrestore(&timer->lock); return ret; @@ -1279,45 +1454,77 @@ 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; + struct bpf_hrtimer *t, *cur_t; + bool inc = false; int ret = 0; if (in_nmi()) return -EOPNOTSUPP; + rcu_read_lock(); __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { ret = -EINVAL; goto out; } - if (this_cpu_read(hrtimer_running) == t) { + + cur_t = this_cpu_read(hrtimer_running); + if (cur_t == t) { /* If bpf callback_fn is trying to bpf_timer_cancel() * its own timer the hrtimer_cancel() will deadlock - * since it waits for callback_fn to finish + * since it waits for callback_fn to finish. */ ret = -EDEADLK; goto out; } - drop_prog_refcnt(t); + + /* Only account in-flight cancellations when invoked from a timer + * callback, since we want to avoid waiting only if other _callbacks_ + * are waiting on us, to avoid introducing lockups. Non-callback paths + * are ok, since nobody would synchronously wait for their completion. + */ + if (!cur_t) + goto drop; + atomic_inc(&t->cancelling); + /* Need full barrier after relaxed atomic_inc */ + smp_mb__after_atomic(); + inc = true; + if (atomic_read(&cur_t->cancelling)) { + /* We're cancelling timer t, while some other timer callback is + * attempting to cancel us. In such a case, it might be possible + * that timer t belongs to the other callback, or some other + * callback waiting upon it (creating transitive dependencies + * upon us), and we will enter a deadlock if we continue + * cancelling and waiting for it synchronously, since it might + * do the same. Bail! + */ + ret = -EDEADLK; + goto out; + } +drop: + drop_prog_refcnt(&t->cb); out: __bpf_spin_unlock_irqrestore(&timer->lock); /* Cancel the timer and wait for associated callback to finish * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); + if (inc) + atomic_dec(&t->cancelling); + rcu_read_unlock(); return ret; } @@ -1328,57 +1535,114 @@ 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. */ - 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 - * see address 't' anymore. - * - * Check that bpf_map_delete/update_elem() wasn't called from timer - * callback_fn. In such case don't call hrtimer_cancel() (since it will - * deadlock) and don't call hrtimer_try_to_cancel() (since it will just - * return -1). Though callback_fn is still running on this cpu it's + /* We check that bpf_map_delete/update_elem() was called from timer + * callback_fn. In such case we don't call hrtimer_cancel() (since it + * will deadlock) and don't call hrtimer_try_to_cancel() (since it will + * just 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. + * + * However, it is possible the timer callback_fn calling us armed the + * timer _before_ calling us, such that failing to cancel it here will + * cause it to possibly use struct hrtimer after freeing bpf_hrtimer. + * Therefore, we _need_ to cancel any outstanding timers before we do + * call_rcu, even though no more timers can be armed. + * + * Moreover, we need to schedule work even if timer does not belong to + * the calling callback_fn, as on two different CPUs, we can end up in a + * situation where both sides run in parallel, try to cancel one + * another, and we end up waiting on both sides in hrtimer_cancel + * without making forward progress, since timer1 depends on time2 + * callback to finish, and vice versa. + * + * CPU 1 (timer1_cb) CPU 2 (timer2_cb) + * bpf_timer_cancel_and_free(timer2) bpf_timer_cancel_and_free(timer1) + * + * To avoid these issues, punt to workqueue context when we are in a + * timer callback. + */ + if (this_cpu_read(hrtimer_running)) { + queue_work(system_dfl_wq, &t->cb.delete_work); + return; + } + + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + /* If the timer is running on other CPU, also use a kworker to + * wait for the completion of the timer instead of trying to + * acquire a sleepable lock in hrtimer_cancel() to wait for its + * completion. + */ + if (hrtimer_try_to_cancel(&t->timer) >= 0) + call_rcu(&t->cb.rcu, bpf_async_cb_rcu_free); + else + queue_work(system_dfl_wq, &t->cb.delete_work); + } else { + bpf_timer_delete_work(&t->cb.delete_work); + } +} + +/* 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. */ - if (this_cpu_read(hrtimer_running) != t) - hrtimer_cancel(&t->timer); - kfree(t); + schedule_work(&work->delete_work); } -BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) +BPF_CALL_2(bpf_kptr_xchg, void *, dst, void *, ptr) { - unsigned long *kptr = map_value; + unsigned long *kptr = dst; + /* This helper may be inlined by verifier. */ return xchg(kptr, (unsigned long)ptr); } @@ -1391,11 +1655,18 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .ret_btf_id = BPF_PTR_POISON, - .arg1_type = ARG_PTR_TO_KPTR, + .arg1_type = ARG_KPTR_XCHG_DEST, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL | OBJ_RELEASE, .arg2_btf_id = BPF_PTR_POISON, }; +struct bpf_dynptr_file_impl { + struct freader freader; + /* 64 bit offset and size overriding 32 bit ones in bpf_dynptr_kern */ + u64 offset; + u64 size; +}; + /* Since the upper 8 bits of dynptr->size is reserved, the * maximum supported size is 2^24 - 1. */ @@ -1404,26 +1675,85 @@ 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; } +void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) +{ + ptr->size |= DYNPTR_RDONLY_BIT; +} + static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_type type) { ptr->size |= type << DYNPTR_TYPE_SHIFT; } -u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr) +static enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *ptr) { + return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT; +} + +u64 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr) +{ + if (bpf_dynptr_get_type(ptr) == BPF_DYNPTR_TYPE_FILE) { + struct bpf_dynptr_file_impl *df = ptr->data; + + return df->size; + } + return ptr->size & DYNPTR_SIZE_MASK; } -int bpf_dynptr_check_size(u32 size) +static void bpf_dynptr_advance_offset(struct bpf_dynptr_kern *ptr, u64 off) +{ + if (bpf_dynptr_get_type(ptr) == BPF_DYNPTR_TYPE_FILE) { + struct bpf_dynptr_file_impl *df = ptr->data; + + df->offset += off; + return; + } + ptr->offset += off; +} + +static void bpf_dynptr_set_size(struct bpf_dynptr_kern *ptr, u64 new_size) +{ + u32 metadata = ptr->size & ~DYNPTR_SIZE_MASK; + + if (bpf_dynptr_get_type(ptr) == BPF_DYNPTR_TYPE_FILE) { + struct bpf_dynptr_file_impl *df = ptr->data; + + df->size = new_size; + return; + } + ptr->size = (u32)new_size | metadata; +} + +int bpf_dynptr_check_size(u64 size) { return size > DYNPTR_MAX_SIZE ? -E2BIG : 0; } +static int bpf_file_fetch_bytes(struct bpf_dynptr_file_impl *df, u64 offset, void *buf, u64 len) +{ + const void *ptr; + + if (!buf) + return -EINVAL; + + df->freader.buf = buf; + df->freader.buf_sz = len; + ptr = freader_fetch(&df->freader, offset + df->offset, len); + if (!ptr) + return df->freader.err; + + if (ptr != buf) /* Force copying into the buffer */ + memcpy(buf, ptr, len); + + return 0; +} + void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size) { @@ -1438,17 +1768,7 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) memset(ptr, 0, sizeof(*ptr)); } -static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len) -{ - u32 size = bpf_dynptr_get_size(ptr); - - if (len > size || offset > size - len) - return -E2BIG; - - return 0; -} - -BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr) +BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u64, size, u64, flags, struct bpf_dynptr_kern *, ptr) { int err; @@ -1480,12 +1800,13 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE, }; -BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, - u32, offset, u64, flags) +static int __bpf_dynptr_read(void *dst, u64 len, const struct bpf_dynptr_kern *src, + u64 offset, u64 flags) { + enum bpf_dynptr_type type; int err; if (!src->data || flags) @@ -1495,13 +1816,36 @@ BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern if (err) return err; - /* Source and destination may possibly overlap, hence use memmove to - * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr - * pointing to overlapping PTR_TO_MAP_VALUE regions. - */ - memmove(dst, src->data + src->offset + offset, len); + type = bpf_dynptr_get_type(src); - return 0; + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + /* Source and destination may possibly overlap, hence use memmove to + * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr + * pointing to overlapping PTR_TO_MAP_VALUE regions. + */ + memmove(dst, src->data + src->offset + offset, len); + return 0; + case BPF_DYNPTR_TYPE_SKB: + return __bpf_skb_load_bytes(src->data, src->offset + offset, dst, len); + case BPF_DYNPTR_TYPE_XDP: + return __bpf_xdp_load_bytes(src->data, src->offset + offset, dst, len); + case BPF_DYNPTR_TYPE_SKB_META: + memmove(dst, bpf_skb_meta_pointer(src->data, src->offset + offset), len); + return 0; + case BPF_DYNPTR_TYPE_FILE: + return bpf_file_fetch_bytes(src->data, offset, dst, len); + default: + WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type); + return -EFAULT; + } +} + +BPF_CALL_5(bpf_dynptr_read, void *, dst, u64, len, const struct bpf_dynptr_kern *, src, + u64, offset, u64, flags) +{ + return __bpf_dynptr_read(dst, len, src, offset, flags); } static const struct bpf_func_proto bpf_dynptr_read_proto = { @@ -1515,25 +1859,52 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = { .arg5_type = ARG_ANYTHING, }; -BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src, - u32, len, u64, flags) +int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u64 offset, void *src, + u64 len, u64 flags) { + enum bpf_dynptr_type type; int err; - if (!dst->data || flags || bpf_dynptr_is_rdonly(dst)) + if (!dst->data || __bpf_dynptr_is_rdonly(dst)) return -EINVAL; err = bpf_dynptr_check_off_len(dst, offset, len); if (err) return err; - /* Source and destination may possibly overlap, hence use memmove to - * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr - * pointing to overlapping PTR_TO_MAP_VALUE regions. - */ - memmove(dst->data + dst->offset + offset, src, len); + type = bpf_dynptr_get_type(dst); - return 0; + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + if (flags) + return -EINVAL; + /* Source and destination may possibly overlap, hence use memmove to + * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr + * pointing to overlapping PTR_TO_MAP_VALUE regions. + */ + memmove(dst->data + dst->offset + offset, src, len); + return 0; + case BPF_DYNPTR_TYPE_SKB: + return __bpf_skb_store_bytes(dst->data, dst->offset + offset, src, len, + flags); + case BPF_DYNPTR_TYPE_XDP: + if (flags) + return -EINVAL; + return __bpf_xdp_store_bytes(dst->data, dst->offset + offset, src, len); + case BPF_DYNPTR_TYPE_SKB_META: + return __bpf_skb_meta_store_bytes(dst->data, dst->offset + offset, src, + len, flags); + default: + WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type); + return -EFAULT; + } +} + +BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u64, offset, void *, src, + u64, len, u64, flags) +{ + return __bpf_dynptr_write(dst, offset, src, len, flags); } static const struct bpf_func_proto bpf_dynptr_write_proto = { @@ -1547,8 +1918,9 @@ static const struct bpf_func_proto bpf_dynptr_write_proto = { .arg5_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) +BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u64, offset, u64, len) { + enum bpf_dynptr_type type; int err; if (!ptr->data) @@ -1558,10 +1930,24 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3 if (err) return 0; - if (bpf_dynptr_is_rdonly(ptr)) + if (__bpf_dynptr_is_rdonly(ptr)) return 0; - return (unsigned long)(ptr->data + ptr->offset + offset); + type = bpf_dynptr_get_type(ptr); + + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + return (unsigned long)(ptr->data + ptr->offset + offset); + case BPF_DYNPTR_TYPE_SKB: + case BPF_DYNPTR_TYPE_XDP: + case BPF_DYNPTR_TYPE_SKB_META: + /* skb and xdp dynptrs should use bpf_dynptr_slice / bpf_dynptr_slice_rdwr */ + return 0; + default: + WARN_ONCE(true, "bpf_dynptr_data: unknown dynptr type %d\n", type); + return 0; + } } static const struct bpf_func_proto bpf_dynptr_data_proto = { @@ -1580,9 +1966,15 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto __weak; const struct bpf_func_proto bpf_probe_read_kernel_proto __weak; const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; +const struct bpf_func_proto bpf_perf_event_read_proto __weak; +const struct bpf_func_proto bpf_send_signal_proto __weak; +const struct bpf_func_proto bpf_send_signal_thread_proto __weak; +const struct bpf_func_proto bpf_get_task_stack_sleepable_proto __weak; +const struct bpf_func_proto bpf_get_task_stack_proto __weak; +const struct bpf_func_proto bpf_get_branch_snapshot_proto __weak; const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1629,11 +2021,17 @@ bpf_base_func_proto(enum bpf_func_id func_id) 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; + case BPF_FUNC_get_current_uid_gid: + return &bpf_get_current_uid_gid_proto; default: break; } - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return NULL; switch (func_id) { @@ -1682,12 +2080,30 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_cgrp_storage_get_proto; case BPF_FUNC_cgrp_storage_delete: return &bpf_cgrp_storage_delete_proto; + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; + case BPF_FUNC_get_current_ancestor_cgroup_id: + return &bpf_get_current_ancestor_cgroup_id_proto; + case BPF_FUNC_current_task_under_cgroup: + return &bpf_current_task_under_cgroup_proto; #endif +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_curr_proto; +#endif + case BPF_FUNC_task_storage_get: + if (bpf_prog_check_recur(prog)) + return &bpf_task_storage_get_recur_proto; + return &bpf_task_storage_get_proto; + case BPF_FUNC_task_storage_delete: + if (bpf_prog_check_recur(prog)) + return &bpf_task_storage_delete_recur_proto; + return &bpf_task_storage_delete_proto; default: break; } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; switch (func_id) { @@ -1697,6 +2113,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_get_current_task_proto; case BPF_FUNC_get_current_task_btf: return &bpf_get_current_task_btf_proto; + case BPF_FUNC_get_current_comm: + return &bpf_get_current_comm_proto; case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: @@ -1707,6 +2125,10 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_kernel_str: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; + case BPF_FUNC_copy_from_user: + return &bpf_copy_from_user_proto; + case BPF_FUNC_copy_from_user_task: + return &bpf_copy_from_user_task_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_snprintf: @@ -1715,10 +2137,26 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_task_pt_regs_proto; case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); + case BPF_FUNC_perf_event_read_value: + return bpf_get_perf_event_read_value_proto(); + case BPF_FUNC_perf_event_read: + return &bpf_perf_event_read_proto; + case BPF_FUNC_send_signal: + return &bpf_send_signal_proto; + case BPF_FUNC_send_signal_thread: + return &bpf_send_signal_thread_proto; + case BPF_FUNC_get_task_stack: + return prog->sleepable ? &bpf_get_task_stack_sleepable_proto + : &bpf_get_task_stack_proto; + case BPF_FUNC_get_branch_snapshot: + return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_find_vma: + return &bpf_find_vma_proto; default: return NULL; } } +EXPORT_SYMBOL_GPL(bpf_base_func_proto); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock) @@ -1745,27 +2183,55 @@ unlock: while (head != orig_head) { void *obj = head; - obj -= field->list_head.node_offset; + obj -= field->graph_root.node_offset; head = head->next; /* The contained type can also have resources, including a * bpf_list_head which needs to be freed. */ - bpf_obj_free_fields(field->list_head.value_rec, obj); - /* bpf_mem_free requires migrate_disable(), since we can be - * called from map free path as well apart from BPF program (as - * part of map ops doing bpf_obj_free_fields). - */ - migrate_disable(); - bpf_mem_free(&bpf_global_ma, obj); - migrate_enable(); + __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false); } } -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +/* Like rbtree_postorder_for_each_entry_safe, but 'pos' and 'n' are + * 'rb_node *', so field name of rb_node within containing struct is not + * needed. + * + * Since bpf_rb_tree's node type has a corresponding struct btf_field with + * graph_root.node_offset, it's not necessary to know field name + * or type of node struct + */ +#define bpf_rbtree_postorder_for_each_entry_safe(pos, n, root) \ + for (pos = rb_first_postorder(root); \ + pos && ({ n = rb_next_postorder(pos); 1; }); \ + pos = n) -void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) +void bpf_rb_root_free(const struct btf_field *field, void *rb_root, + struct bpf_spin_lock *spin_lock) +{ + struct rb_root_cached orig_root, *root = rb_root; + struct rb_node *pos, *n; + void *obj; + + BUILD_BUG_ON(sizeof(struct rb_root_cached) > sizeof(struct bpf_rb_root)); + BUILD_BUG_ON(__alignof__(struct rb_root_cached) > __alignof__(struct bpf_rb_root)); + + __bpf_spin_lock_irqsave(spin_lock); + orig_root = *root; + *root = RB_ROOT_CACHED; + __bpf_spin_unlock_irqrestore(spin_lock); + + bpf_rbtree_postorder_for_each_entry_safe(pos, n, &orig_root.rb_root) { + obj = pos; + obj -= field->graph_root.node_offset; + + + __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false); + } +} + +__bpf_kfunc_start_defs(); + +__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) { struct btf_struct_meta *meta = meta__ign; u64 size = local_type_id__k; @@ -1775,139 +2241,283 @@ void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) if (!p) return NULL; if (meta) - bpf_obj_init(meta->field_offs, p); + bpf_obj_init(meta->record, p); return p; } -void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) +__bpf_kfunc void *bpf_percpu_obj_new_impl(u64 local_type_id__k, void *meta__ign) +{ + u64 size = local_type_id__k; + + /* The verifier has ensured that meta__ign must be NULL */ + return bpf_mem_alloc(&bpf_global_percpu_ma, size); +} + +/* Must be called under migrate_disable(), as required by bpf_mem_free */ +void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu) +{ + struct bpf_mem_alloc *ma; + + if (rec && rec->refcount_off >= 0 && + !refcount_dec_and_test((refcount_t *)(p + rec->refcount_off))) { + /* Object is refcounted and refcount_dec didn't result in 0 + * refcount. Return without freeing the object + */ + return; + } + + if (rec) + bpf_obj_free_fields(rec, p); + + if (percpu) + ma = &bpf_global_percpu_ma; + else + ma = &bpf_global_ma; + bpf_mem_free_rcu(ma, p); +} + +__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) { struct btf_struct_meta *meta = meta__ign; void *p = p__alloc; - if (meta) - bpf_obj_free_fields(meta->record, p); - bpf_mem_free(&bpf_global_ma, p); + __bpf_obj_drop_impl(p, meta ? meta->record : NULL, false); } -static void __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head, bool tail) +__bpf_kfunc void bpf_percpu_obj_drop_impl(void *p__alloc, void *meta__ign) { - struct list_head *n = (void *)node, *h = (void *)head; + /* The verifier has ensured that meta__ign must be NULL */ + bpf_mem_free_rcu(&bpf_global_percpu_ma, p__alloc); +} +__bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta__ign) +{ + struct btf_struct_meta *meta = meta__ign; + struct bpf_refcount *ref; + + /* Could just cast directly to refcount_t *, but need some code using + * bpf_refcount type so that it is emitted in vmlinux BTF + */ + ref = (struct bpf_refcount *)(p__refcounted_kptr + meta->record->refcount_off); + if (!refcount_inc_not_zero((refcount_t *)ref)) + return NULL; + + /* Verifier strips KF_RET_NULL if input is owned ref, see is_kfunc_ret_null + * in verifier.c + */ + return (void *)p__refcounted_kptr; +} + +static int __bpf_list_add(struct bpf_list_node_kern *node, + struct bpf_list_head *head, + bool tail, struct btf_record *rec, u64 off) +{ + struct list_head *n = &node->list_head, *h = (void *)head; + + /* If list_head was 0-initialized by map, bpf_obj_init_field wasn't + * called on its fields, so init here + */ if (unlikely(!h->next)) INIT_LIST_HEAD(h); - if (unlikely(!n->next)) - INIT_LIST_HEAD(n); + + /* node->owner != NULL implies !list_empty(n), no need to separately + * check the latter + */ + if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) { + /* Only called from BPF prog, no need to migrate_disable */ + __bpf_obj_drop_impl((void *)n - off, rec, false); + return -EINVAL; + } + tail ? list_add_tail(n, h) : list_add(n, h); + WRITE_ONCE(node->owner, head); + + return 0; } -void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) +__bpf_kfunc int bpf_list_push_front_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta__ign, u64 off) { - return __bpf_list_add(node, head, false); + struct bpf_list_node_kern *n = (void *)node; + struct btf_struct_meta *meta = meta__ign; + + return __bpf_list_add(n, head, false, meta ? meta->record : NULL, off); } -void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) +__bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta__ign, u64 off) { - return __bpf_list_add(node, head, true); + struct bpf_list_node_kern *n = (void *)node; + struct btf_struct_meta *meta = meta__ign; + + return __bpf_list_add(n, head, true, meta ? meta->record : NULL, off); } static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail) { struct list_head *n, *h = (void *)head; + struct bpf_list_node_kern *node; + /* If list_head was 0-initialized by map, bpf_obj_init_field wasn't + * called on its fields, so init here + */ if (unlikely(!h->next)) INIT_LIST_HEAD(h); if (list_empty(h)) return NULL; + n = tail ? h->prev : h->next; + node = container_of(n, struct bpf_list_node_kern, list_head); + if (WARN_ON_ONCE(READ_ONCE(node->owner) != head)) + return NULL; + list_del_init(n); + WRITE_ONCE(node->owner, NULL); return (struct bpf_list_node *)n; } -struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) +__bpf_kfunc struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) { return __bpf_list_del(head, false); } -struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) +__bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) { return __bpf_list_del(head, true); } -/** - * bpf_task_acquire - Acquire a reference to a task. A task acquired by this - * kfunc which is not stored in a map as a kptr, must be released by calling - * bpf_task_release(). - * @p: The task on which a reference is being acquired. - */ -struct task_struct *bpf_task_acquire(struct task_struct *p) +__bpf_kfunc struct bpf_list_node *bpf_list_front(struct bpf_list_head *head) { - return get_task_struct(p); + struct list_head *h = (struct list_head *)head; + + if (list_empty(h) || unlikely(!h->next)) + return NULL; + + return (struct bpf_list_node *)h->next; } -/** - * bpf_task_acquire_not_zero - Acquire a reference to a rcu task object. A task - * acquired by this kfunc which is not stored in a map as a kptr, must be - * released by calling bpf_task_release(). - * @p: The task on which a reference is being acquired. +__bpf_kfunc struct bpf_list_node *bpf_list_back(struct bpf_list_head *head) +{ + struct list_head *h = (struct list_head *)head; + + if (list_empty(h) || unlikely(!h->next)) + return NULL; + + return (struct bpf_list_node *)h->prev; +} + +__bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, + struct bpf_rb_node *node) +{ + struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node; + struct rb_root_cached *r = (struct rb_root_cached *)root; + struct rb_node *n = &node_internal->rb_node; + + /* node_internal->owner != root implies either RB_EMPTY_NODE(n) or + * n is owned by some other tree. No need to check RB_EMPTY_NODE(n) + */ + if (READ_ONCE(node_internal->owner) != root) + return NULL; + + rb_erase_cached(n, r); + RB_CLEAR_NODE(n); + WRITE_ONCE(node_internal->owner, NULL); + return (struct bpf_rb_node *)n; +} + +/* Need to copy rbtree_add_cached's logic here because our 'less' is a BPF + * program */ -struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) +static int __bpf_rbtree_add(struct bpf_rb_root *root, + struct bpf_rb_node_kern *node, + void *less, struct btf_record *rec, u64 off) { - /* For the time being this function returns NULL, as it's not currently - * possible to safely acquire a reference to a task with RCU protection - * using get_task_struct() and put_task_struct(). This is due to the - * slightly odd mechanics of p->rcu_users, and how task RCU protection - * works. - * - * A struct task_struct is refcounted by two different refcount_t - * fields: - * - * 1. p->usage: The "true" refcount field which tracks a task's - * lifetime. The task is freed as soon as this - * refcount drops to 0. - * - * 2. p->rcu_users: An "RCU users" refcount field which is statically - * initialized to 2, and is co-located in a union with - * a struct rcu_head field (p->rcu). p->rcu_users - * essentially encapsulates a single p->usage - * refcount, and when p->rcu_users goes to 0, an RCU - * callback is scheduled on the struct rcu_head which - * decrements the p->usage refcount. - * - * There are two important implications to this task refcounting logic - * described above. The first is that - * refcount_inc_not_zero(&p->rcu_users) cannot be used anywhere, as - * after the refcount goes to 0, the RCU callback being scheduled will - * cause the memory backing the refcount to again be nonzero due to the - * fields sharing a union. The other is that we can't rely on RCU to - * guarantee that a task is valid in a BPF program. This is because a - * task could have already transitioned to being in the TASK_DEAD - * state, had its rcu_users refcount go to 0, and its rcu callback - * invoked in which it drops its single p->usage reference. At this - * point the task will be freed as soon as the last p->usage reference - * goes to 0, without waiting for another RCU gp to elapse. The only - * way that a BPF program can guarantee that a task is valid is in this - * scenario is to hold a p->usage refcount itself. - * - * Until we're able to resolve this issue, either by pulling - * p->rcu_users and p->rcu out of the union, or by getting rid of - * p->usage and just using p->rcu_users for refcounting, we'll just - * return NULL here. + struct rb_node **link = &((struct rb_root_cached *)root)->rb_root.rb_node; + struct rb_node *parent = NULL, *n = &node->rb_node; + bpf_callback_t cb = (bpf_callback_t)less; + bool leftmost = true; + + /* node->owner != NULL implies !RB_EMPTY_NODE(n), no need to separately + * check the latter */ - return NULL; + if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) { + /* Only called from BPF prog, no need to migrate_disable */ + __bpf_obj_drop_impl((void *)n - off, rec, false); + return -EINVAL; + } + + while (*link) { + parent = *link; + if (cb((uintptr_t)node, (uintptr_t)parent, 0, 0, 0)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = false; + } + } + + rb_link_node(n, parent, link); + rb_insert_color_cached(n, (struct rb_root_cached *)root, leftmost); + WRITE_ONCE(node->owner, root); + return 0; +} + +__bpf_kfunc int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node, + bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b), + void *meta__ign, u64 off) +{ + struct btf_struct_meta *meta = meta__ign; + struct bpf_rb_node_kern *n = (void *)node; + + return __bpf_rbtree_add(root, n, (void *)less, meta ? meta->record : NULL, off); +} + +__bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) +{ + struct rb_root_cached *r = (struct rb_root_cached *)root; + + return (struct bpf_rb_node *)rb_first_cached(r); +} + +__bpf_kfunc struct bpf_rb_node *bpf_rbtree_root(struct bpf_rb_root *root) +{ + struct rb_root_cached *r = (struct rb_root_cached *)root; + + return (struct bpf_rb_node *)r->rb_root.rb_node; +} + +__bpf_kfunc struct bpf_rb_node *bpf_rbtree_left(struct bpf_rb_root *root, struct bpf_rb_node *node) +{ + struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node; + + if (READ_ONCE(node_internal->owner) != root) + return NULL; + + return (struct bpf_rb_node *)node_internal->rb_node.rb_left; +} + +__bpf_kfunc struct bpf_rb_node *bpf_rbtree_right(struct bpf_rb_root *root, struct bpf_rb_node *node) +{ + struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node; + + if (READ_ONCE(node_internal->owner) != root) + return NULL; + + return (struct bpf_rb_node *)node_internal->rb_node.rb_right; } /** - * bpf_task_kptr_get - Acquire a reference on a struct task_struct kptr. A task - * kptr acquired by this kfunc which is not subsequently stored in a map, must - * be released by calling bpf_task_release(). - * @pp: A pointer to a task kptr on which a reference is being acquired. + * bpf_task_acquire - Acquire a reference to a task. A task acquired by this + * kfunc which is not stored in a map as a kptr, must be released by calling + * bpf_task_release(). + * @p: The task on which a reference is being acquired. */ -struct task_struct *bpf_task_kptr_get(struct task_struct **pp) +__bpf_kfunc struct task_struct *bpf_task_acquire(struct task_struct *p) { - /* We must return NULL here until we have clarity on how to properly - * leverage RCU for ensuring a task's lifetime. See the comment above - * in bpf_task_acquire_not_zero() for more details. - */ + if (refcount_inc_not_zero(&p->rcu_users)) + return p; return NULL; } @@ -1915,13 +2525,16 @@ struct task_struct *bpf_task_kptr_get(struct task_struct **pp) * bpf_task_release - Release the reference acquired on a task. * @p: The task on which a reference is being released. */ -void bpf_task_release(struct task_struct *p) +__bpf_kfunc void bpf_task_release(struct task_struct *p) { - if (!p) - return; + put_task_struct_rcu_user(p); +} - put_task_struct(p); +__bpf_kfunc void bpf_task_release_dtor(void *p) +{ + put_task_struct_rcu_user(p); } +CFI_NOSEAL(bpf_task_release_dtor); #ifdef CONFIG_CGROUPS /** @@ -1930,41 +2543,9 @@ void bpf_task_release(struct task_struct *p) * calling bpf_cgroup_release(). * @cgrp: The cgroup on which a reference is being acquired. */ -struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) +__bpf_kfunc struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) { - cgroup_get(cgrp); - return cgrp; -} - -/** - * bpf_cgroup_kptr_get - Acquire a reference on a struct cgroup kptr. A cgroup - * kptr acquired by this kfunc which is not subsequently stored in a map, must - * be released by calling bpf_cgroup_release(). - * @cgrpp: A pointer to a cgroup kptr on which a reference is being acquired. - */ -struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) -{ - struct cgroup *cgrp; - - rcu_read_lock(); - /* Another context could remove the cgroup from the map and release it - * at any time, including after we've done the lookup above. This is - * safe because we're in an RCU read region, so the cgroup is - * guaranteed to remain valid until at least the rcu_read_unlock() - * below. - */ - cgrp = READ_ONCE(*cgrpp); - - if (cgrp && !cgroup_tryget(cgrp)) - /* If the cgroup had been removed from the map and freed as - * described above, cgroup_tryget() will return false. The - * cgroup will be freed at some point after the current RCU gp - * has ended, so just return NULL to the user. - */ - cgrp = NULL; - rcu_read_unlock(); - - return cgrp; + return cgroup_tryget(cgrp) ? cgrp : NULL; } /** @@ -1974,13 +2555,16 @@ struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) * drops to 0. * @cgrp: The cgroup on which a reference is being released. */ -void bpf_cgroup_release(struct cgroup *cgrp) +__bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp) { - if (!cgrp) - return; + cgroup_put(cgrp); +} +__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp) +{ cgroup_put(cgrp); } +CFI_NOSEAL(bpf_cgroup_release_dtor); /** * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor @@ -1989,17 +2573,98 @@ void bpf_cgroup_release(struct cgroup *cgrp) * @cgrp: The cgroup for which we're performing a lookup. * @level: The level of ancestor to look up. */ -struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) +__bpf_kfunc struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) { struct cgroup *ancestor; if (level > cgrp->level || level < 0) return NULL; + /* cgrp's refcnt could be 0 here, but ancestors can still be accessed */ ancestor = cgrp->ancestors[level]; - cgroup_get(ancestor); + if (!cgroup_tryget(ancestor)) + return NULL; return ancestor; } + +/** + * bpf_cgroup_from_id - Find a cgroup from its ID. A cgroup returned by this + * kfunc which is not subsequently stored in a map, must be released by calling + * bpf_cgroup_release(). + * @cgid: cgroup id. + */ +__bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid) +{ + struct cgroup *cgrp; + + cgrp = __cgroup_get_from_id(cgid); + if (IS_ERR(cgrp)) + return NULL; + return cgrp; +} + +/** + * bpf_task_under_cgroup - wrap task_under_cgroup_hierarchy() as a kfunc, test + * task's membership of cgroup ancestry. + * @task: the task to be tested + * @ancestor: possible ancestor of @task's cgroup + * + * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. + * It follows all the same rules as cgroup_is_descendant, and only applies + * to the default hierarchy. + */ +__bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task, + struct cgroup *ancestor) +{ + long ret; + + rcu_read_lock(); + ret = task_under_cgroup_hierarchy(task, ancestor); + rcu_read_unlock(); + return ret; +} + +BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct cgroup *cgrp; + + if (unlikely(idx >= array->map.max_entries)) + return -E2BIG; + + cgrp = READ_ONCE(array->ptrs[idx]); + if (unlikely(!cgrp)) + return -EAGAIN; + + return task_under_cgroup_hierarchy(current, cgrp); +} + +const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { + .func = bpf_current_task_under_cgroup, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; + +/** + * bpf_task_get_cgroup1 - Acquires the associated cgroup of a task within a + * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its + * hierarchy ID. + * @task: The target task + * @hierarchy_id: The ID of a cgroup1 hierarchy + * + * On success, the cgroup is returen. On failure, NULL is returned. + */ +__bpf_kfunc struct cgroup * +bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) +{ + struct cgroup *cgrp = task_get_cgroup1(task, hierarchy_id); + + if (IS_ERR(cgrp)) + return NULL; + return cgrp; +} #endif /* CONFIG_CGROUPS */ /** @@ -2008,63 +2673,1771 @@ struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) * stored in a map, or released with bpf_task_release(). * @pid: The pid of the task being looked up. */ -struct task_struct *bpf_task_from_pid(s32 pid) +__bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) { struct task_struct *p; rcu_read_lock(); p = find_task_by_pid_ns(pid, &init_pid_ns); if (p) - bpf_task_acquire(p); + p = bpf_task_acquire(p); + rcu_read_unlock(); + + return p; +} + +/** + * bpf_task_from_vpid - Find a struct task_struct from its vpid by looking it up + * in the pid namespace of the current task. If a task is returned, it must + * either be stored in a map, or released with bpf_task_release(). + * @vpid: The vpid of the task being looked up. + */ +__bpf_kfunc struct task_struct *bpf_task_from_vpid(s32 vpid) +{ + struct task_struct *p; + + rcu_read_lock(); + p = find_task_by_vpid(vpid); + if (p) + p = bpf_task_acquire(p); rcu_read_unlock(); return p; } -void *bpf_cast_to_kern_ctx(void *obj) +/** + * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data. + * @p: The dynptr whose data slice to retrieve + * @offset: Offset into the dynptr + * @buffer__opt: User-provided buffer to copy contents into. May be NULL + * @buffer__szk: Size (in bytes) of the buffer if present. This is the + * length of the requested slice. This must be a constant. + * + * For non-skb and non-xdp type dynptrs, there is no difference between + * bpf_dynptr_slice and bpf_dynptr_data. + * + * If buffer__opt is NULL, the call will fail if buffer_opt was needed. + * + * If the intention is to write to the data slice, please use + * bpf_dynptr_slice_rdwr. + * + * The user must check that the returned pointer is not null before using it. + * + * Please note that in the case of skb and xdp dynptrs, bpf_dynptr_slice + * does not change the underlying packet data pointers, so a call to + * bpf_dynptr_slice will not invalidate any ctx->data/data_end pointers in + * the bpf program. + * + * Return: NULL if the call failed (eg invalid dynptr), pointer to a read-only + * data slice (can be either direct pointer to the data or a pointer to the user + * provided buffer, with its contents containing the data, if unable to obtain + * direct pointer) + */ +__bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr *p, u64 offset, + void *buffer__opt, u64 buffer__szk) +{ + const struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + enum bpf_dynptr_type type; + u64 len = buffer__szk; + int err; + + if (!ptr->data) + return NULL; + + err = bpf_dynptr_check_off_len(ptr, offset, len); + if (err) + return NULL; + + type = bpf_dynptr_get_type(ptr); + + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + case BPF_DYNPTR_TYPE_RINGBUF: + return ptr->data + ptr->offset + offset; + case BPF_DYNPTR_TYPE_SKB: + if (buffer__opt) + return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt); + else + return skb_pointer_if_linear(ptr->data, ptr->offset + offset, len); + case BPF_DYNPTR_TYPE_XDP: + { + void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len); + if (!IS_ERR_OR_NULL(xdp_ptr)) + return xdp_ptr; + + if (!buffer__opt) + return NULL; + bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer__opt, len, false); + return buffer__opt; + } + case BPF_DYNPTR_TYPE_SKB_META: + return bpf_skb_meta_pointer(ptr->data, ptr->offset + offset); + case BPF_DYNPTR_TYPE_FILE: + err = bpf_file_fetch_bytes(ptr->data, offset, buffer__opt, buffer__szk); + return err ? NULL : buffer__opt; + default: + WARN_ONCE(true, "unknown dynptr type %d\n", type); + return NULL; + } +} + +/** + * bpf_dynptr_slice_rdwr() - Obtain a writable pointer to the dynptr data. + * @p: The dynptr whose data slice to retrieve + * @offset: Offset into the dynptr + * @buffer__opt: User-provided buffer to copy contents into. May be NULL + * @buffer__szk: Size (in bytes) of the buffer if present. This is the + * length of the requested slice. This must be a constant. + * + * For non-skb and non-xdp type dynptrs, there is no difference between + * bpf_dynptr_slice and bpf_dynptr_data. + * + * If buffer__opt is NULL, the call will fail if buffer_opt was needed. + * + * The returned pointer is writable and may point to either directly the dynptr + * data at the requested offset or to the buffer if unable to obtain a direct + * data pointer to (example: the requested slice is to the paged area of an skb + * packet). In the case where the returned pointer is to the buffer, the user + * is responsible for persisting writes through calling bpf_dynptr_write(). This + * usually looks something like this pattern: + * + * struct eth_hdr *eth = bpf_dynptr_slice_rdwr(&dynptr, 0, buffer, sizeof(buffer)); + * if (!eth) + * return TC_ACT_SHOT; + * + * // mutate eth header // + * + * if (eth == buffer) + * bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0); + * + * Please note that, as in the example above, the user must check that the + * returned pointer is not null before using it. + * + * Please also note that in the case of skb and xdp dynptrs, bpf_dynptr_slice_rdwr + * does not change the underlying packet data pointers, so a call to + * bpf_dynptr_slice_rdwr will not invalidate any ctx->data/data_end pointers in + * the bpf program. + * + * Return: NULL if the call failed (eg invalid dynptr), pointer to a + * data slice (can be either direct pointer to the data or a pointer to the user + * provided buffer, with its contents containing the data, if unable to obtain + * direct pointer) + */ +__bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u64 offset, + void *buffer__opt, u64 buffer__szk) +{ + const struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + + if (!ptr->data || __bpf_dynptr_is_rdonly(ptr)) + return NULL; + + /* 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 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 + * returned pointer is directly to skb data, and if the skb is cloned, the + * verifier will have uncloned it (see bpf_unclone_prologue()) already. + * The pointer can be directly written into. + * + * 2) Some portion of the requested slice is in the paged buffer area. + * In this case, the requested data will be copied out into the buffer + * and the returned pointer will be a pointer to the buffer. The skb + * will not be pulled. To persist the write, the user will need to call + * bpf_dynptr_write(), which will pull the skb and commit the write. + * + * Similarly for xdp programs, if the requested slice is not across xdp + * fragments, then a direct pointer will be returned, otherwise the data + * will be copied out into the buffer and the user will need to call + * bpf_dynptr_write() to commit changes. + */ + return bpf_dynptr_slice(p, offset, buffer__opt, buffer__szk); +} + +__bpf_kfunc int bpf_dynptr_adjust(const struct bpf_dynptr *p, u64 start, u64 end) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + u64 size; + + if (!ptr->data || start > end) + return -EINVAL; + + size = __bpf_dynptr_size(ptr); + + if (start > size || end > size) + return -ERANGE; + + bpf_dynptr_advance_offset(ptr, start); + bpf_dynptr_set_size(ptr, end - start); + + return 0; +} + +__bpf_kfunc bool bpf_dynptr_is_null(const struct bpf_dynptr *p) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + + return !ptr->data; +} + +__bpf_kfunc bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *p) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + + if (!ptr->data) + return false; + + return __bpf_dynptr_is_rdonly(ptr); +} + +__bpf_kfunc u64 bpf_dynptr_size(const struct bpf_dynptr *p) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + + if (!ptr->data) + return -EINVAL; + + return __bpf_dynptr_size(ptr); +} + +__bpf_kfunc int bpf_dynptr_clone(const struct bpf_dynptr *p, + struct bpf_dynptr *clone__uninit) +{ + struct bpf_dynptr_kern *clone = (struct bpf_dynptr_kern *)clone__uninit; + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + + if (!ptr->data) { + bpf_dynptr_set_null(clone); + return -EINVAL; + } + + *clone = *ptr; + + return 0; +} + +/** + * bpf_dynptr_copy() - Copy data from one dynptr to another. + * @dst_ptr: Destination dynptr - where data should be copied to + * @dst_off: Offset into the destination dynptr + * @src_ptr: Source dynptr - where data should be copied from + * @src_off: Offset into the source dynptr + * @size: Length of the data to copy from source to destination + * + * Copies data from source dynptr to destination dynptr. + * Returns 0 on success; negative error, otherwise. + */ +__bpf_kfunc int bpf_dynptr_copy(struct bpf_dynptr *dst_ptr, u64 dst_off, + struct bpf_dynptr *src_ptr, u64 src_off, u64 size) +{ + struct bpf_dynptr_kern *dst = (struct bpf_dynptr_kern *)dst_ptr; + struct bpf_dynptr_kern *src = (struct bpf_dynptr_kern *)src_ptr; + void *src_slice, *dst_slice; + char buf[256]; + u64 off; + + src_slice = bpf_dynptr_slice(src_ptr, src_off, NULL, size); + dst_slice = bpf_dynptr_slice_rdwr(dst_ptr, dst_off, NULL, size); + + if (src_slice && dst_slice) { + memmove(dst_slice, src_slice, size); + return 0; + } + + if (src_slice) + return __bpf_dynptr_write(dst, dst_off, src_slice, size, 0); + + if (dst_slice) + return __bpf_dynptr_read(dst_slice, size, src, src_off, 0); + + if (bpf_dynptr_check_off_len(dst, dst_off, size) || + bpf_dynptr_check_off_len(src, src_off, size)) + return -E2BIG; + + off = 0; + while (off < size) { + u64 chunk_sz = min_t(u64, sizeof(buf), size - off); + int err; + + err = __bpf_dynptr_read(buf, chunk_sz, src, src_off + off, 0); + if (err) + return err; + err = __bpf_dynptr_write(dst, dst_off + off, buf, chunk_sz, 0); + if (err) + return err; + + off += chunk_sz; + } + return 0; +} + +/** + * bpf_dynptr_memset() - Fill dynptr memory with a constant byte. + * @p: Destination dynptr - where data will be filled + * @offset: Offset into the dynptr to start filling from + * @size: Number of bytes to fill + * @val: Constant byte to fill the memory with + * + * Fills the @size bytes of the memory area pointed to by @p + * at @offset with the constant byte @val. + * Returns 0 on success; negative error, otherwise. + */ +__bpf_kfunc int bpf_dynptr_memset(struct bpf_dynptr *p, u64 offset, u64 size, u8 val) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + u64 chunk_sz, write_off; + char buf[256]; + void* slice; + int err; + + slice = bpf_dynptr_slice_rdwr(p, offset, NULL, size); + if (likely(slice)) { + memset(slice, val, size); + return 0; + } + + if (__bpf_dynptr_is_rdonly(ptr)) + return -EINVAL; + + err = bpf_dynptr_check_off_len(ptr, offset, size); + if (err) + return err; + + /* Non-linear data under the dynptr, write from a local buffer */ + chunk_sz = min_t(u64, sizeof(buf), size); + memset(buf, val, chunk_sz); + + for (write_off = 0; write_off < size; write_off += chunk_sz) { + chunk_sz = min_t(u64, sizeof(buf), size - write_off); + err = __bpf_dynptr_write(ptr, offset + write_off, buf, chunk_sz, 0); + if (err) + return err; + } + + return 0; +} + +__bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) { return obj; } -void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) +__bpf_kfunc void *bpf_rdonly_cast(const void *obj__ign, u32 btf_id__k) { - return obj__ign; + return (void *)obj__ign; } -void bpf_rcu_read_lock(void) +__bpf_kfunc void bpf_rcu_read_lock(void) { rcu_read_lock(); } -void bpf_rcu_read_unlock(void) +__bpf_kfunc void bpf_rcu_read_unlock(void) { rcu_read_unlock(); } -__diag_pop(); +struct bpf_throw_ctx { + struct bpf_prog_aux *aux; + u64 sp; + u64 bp; + int cnt; +}; + +static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp) +{ + struct bpf_throw_ctx *ctx = cookie; + struct bpf_prog *prog; + + /* + * The RCU read lock is held to safely traverse the latch tree, but we + * don't need its protection when accessing the prog, since it has an + * active stack frame on the current stack trace, and won't disappear. + */ + rcu_read_lock(); + prog = bpf_prog_ksym_find(ip); + rcu_read_unlock(); + if (!prog) + return !ctx->cnt; + ctx->cnt++; + if (bpf_is_subprog(prog)) + return true; + ctx->aux = prog->aux; + ctx->sp = sp; + ctx->bp = bp; + return false; +} + +__bpf_kfunc void bpf_throw(u64 cookie) +{ + struct bpf_throw_ctx ctx = {}; + + arch_bpf_stack_walk(bpf_stack_walker, &ctx); + WARN_ON_ONCE(!ctx.aux); + if (ctx.aux) + WARN_ON_ONCE(!ctx.aux->exception_boundary); + WARN_ON_ONCE(!ctx.bp); + WARN_ON_ONCE(!ctx.cnt); + /* Prevent KASAN false positives for CONFIG_KASAN_STACK by unpoisoning + * deeper stack depths than ctx.sp as we do not return from bpf_throw, + * which skips compiler generated instrumentation to do the same. + */ + kasan_unpoison_task_stack_below((void *)(long)ctx.sp); + ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0); + 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, void *value), + unsigned int flags, + void *aux__prog) +{ + struct bpf_prog_aux *aux = (struct bpf_prog_aux *)aux__prog; + 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(); +} + +struct bpf_iter_bits { + __u64 __opaque[2]; +} __aligned(8); + +#define BITS_ITER_NR_WORDS_MAX 511 + +struct bpf_iter_bits_kern { + union { + __u64 *bits; + __u64 bits_copy; + }; + int nr_bits; + int bit; +} __aligned(8); + +/* On 64-bit hosts, unsigned long and u64 have the same size, so passing + * a u64 pointer and an unsigned long pointer to find_next_bit() will + * return the same result, as both point to the same 8-byte area. + * + * For 32-bit little-endian hosts, using a u64 pointer or unsigned long + * pointer also makes no difference. This is because the first iterated + * unsigned long is composed of bits 0-31 of the u64 and the second unsigned + * long is composed of bits 32-63 of the u64. + * + * However, for 32-bit big-endian hosts, this is not the case. The first + * iterated unsigned long will be bits 32-63 of the u64, so swap these two + * ulong values within the u64. + */ +static void swap_ulong_in_u64(u64 *bits, unsigned int nr) +{ +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN) + unsigned int i; + + for (i = 0; i < nr; i++) + bits[i] = (bits[i] >> 32) | ((u64)(u32)bits[i] << 32); +#endif +} + +/** + * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area + * @it: The new bpf_iter_bits to be created + * @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over + * @nr_words: The size of the specified memory area, measured in 8-byte units. + * The maximum value of @nr_words is @BITS_ITER_NR_WORDS_MAX. This limit may be + * further reduced by the BPF memory allocator implementation. + * + * This function initializes a new bpf_iter_bits structure for iterating over + * a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It + * copies the data of the memory area to the newly created bpf_iter_bits @it for + * subsequent iteration operations. + * + * On success, 0 is returned. On failure, ERR is returned. + */ +__bpf_kfunc int +bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_words) +{ + struct bpf_iter_bits_kern *kit = (void *)it; + u32 nr_bytes = nr_words * sizeof(u64); + u32 nr_bits = BYTES_TO_BITS(nr_bytes); + int err; + + BUILD_BUG_ON(sizeof(struct bpf_iter_bits_kern) != sizeof(struct bpf_iter_bits)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_bits_kern) != + __alignof__(struct bpf_iter_bits)); + + kit->nr_bits = 0; + kit->bits_copy = 0; + kit->bit = -1; + + if (!unsafe_ptr__ign || !nr_words) + return -EINVAL; + if (nr_words > BITS_ITER_NR_WORDS_MAX) + return -E2BIG; + + /* Optimization for u64 mask */ + if (nr_bits == 64) { + err = bpf_probe_read_kernel_common(&kit->bits_copy, nr_bytes, unsafe_ptr__ign); + if (err) + return -EFAULT; + + swap_ulong_in_u64(&kit->bits_copy, nr_words); + + kit->nr_bits = nr_bits; + return 0; + } + + if (bpf_mem_alloc_check_size(false, nr_bytes)) + return -E2BIG; + + /* Fallback to memalloc */ + kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes); + if (!kit->bits) + return -ENOMEM; + + err = bpf_probe_read_kernel_common(kit->bits, nr_bytes, unsafe_ptr__ign); + if (err) { + bpf_mem_free(&bpf_global_ma, kit->bits); + return err; + } + + swap_ulong_in_u64(kit->bits, nr_words); + + kit->nr_bits = nr_bits; + return 0; +} + +/** + * bpf_iter_bits_next() - Get the next bit in a bpf_iter_bits + * @it: The bpf_iter_bits to be checked + * + * This function returns a pointer to a number representing the value of the + * next bit in the bits. + * + * If there are no further bits available, it returns NULL. + */ +__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it) +{ + struct bpf_iter_bits_kern *kit = (void *)it; + int bit = kit->bit, nr_bits = kit->nr_bits; + const void *bits; + + if (!nr_bits || bit >= nr_bits) + return NULL; + + bits = nr_bits == 64 ? &kit->bits_copy : kit->bits; + bit = find_next_bit(bits, nr_bits, bit + 1); + if (bit >= nr_bits) { + kit->bit = bit; + return NULL; + } + + kit->bit = bit; + return &kit->bit; +} + +/** + * bpf_iter_bits_destroy() - Destroy a bpf_iter_bits + * @it: The bpf_iter_bits to be destroyed + * + * Destroy the resource associated with the bpf_iter_bits. + */ +__bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it) +{ + struct bpf_iter_bits_kern *kit = (void *)it; + + if (kit->nr_bits <= 64) + return; + bpf_mem_free(&bpf_global_ma, kit->bits); +} + +/** + * bpf_copy_from_user_str() - Copy a string from an unsafe user address + * @dst: Destination address, in kernel space. This buffer must be + * at least @dst__sz bytes long. + * @dst__sz: Maximum number of bytes to copy, includes the trailing NUL. + * @unsafe_ptr__ign: Source address, in user space. + * @flags: The only supported flag is BPF_F_PAD_ZEROS + * + * Copies a NUL-terminated string from userspace to BPF space. If user string is + * too long this will still ensure zero termination in the dst buffer unless + * buffer size is 0. + * + * If BPF_F_PAD_ZEROS flag is set, memset the tail of @dst to 0 on success and + * memset all of @dst on failure. + */ +__bpf_kfunc int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void __user *unsafe_ptr__ign, u64 flags) +{ + int ret; + + if (unlikely(flags & ~BPF_F_PAD_ZEROS)) + return -EINVAL; + + if (unlikely(!dst__sz)) + return 0; + + ret = strncpy_from_user(dst, unsafe_ptr__ign, dst__sz - 1); + if (ret < 0) { + if (flags & BPF_F_PAD_ZEROS) + memset((char *)dst, 0, dst__sz); + + return ret; + } + + if (flags & BPF_F_PAD_ZEROS) + memset((char *)dst + ret, 0, dst__sz - ret); + else + ((char *)dst)[ret] = '\0'; + + return ret + 1; +} + +/** + * bpf_copy_from_user_task_str() - Copy a string from an task's address space + * @dst: Destination address, in kernel space. This buffer must be + * at least @dst__sz bytes long. + * @dst__sz: Maximum number of bytes to copy, includes the trailing NUL. + * @unsafe_ptr__ign: Source address in the task's address space. + * @tsk: The task whose address space will be used + * @flags: The only supported flag is BPF_F_PAD_ZEROS + * + * Copies a NUL terminated string from a task's address space to @dst__sz + * buffer. If user string is too long this will still ensure zero termination + * in the @dst__sz buffer unless buffer size is 0. + * + * If BPF_F_PAD_ZEROS flag is set, memset the tail of @dst__sz to 0 on success + * and memset all of @dst__sz on failure. + * + * Return: The number of copied bytes on success including the NUL terminator. + * A negative error code on failure. + */ +__bpf_kfunc int bpf_copy_from_user_task_str(void *dst, u32 dst__sz, + const void __user *unsafe_ptr__ign, + struct task_struct *tsk, u64 flags) +{ + int ret; + + if (unlikely(flags & ~BPF_F_PAD_ZEROS)) + return -EINVAL; + + if (unlikely(dst__sz == 0)) + return 0; + + ret = copy_remote_vm_str(tsk, (unsigned long)unsafe_ptr__ign, dst, dst__sz, 0); + if (ret < 0) { + if (flags & BPF_F_PAD_ZEROS) + memset(dst, 0, dst__sz); + return ret; + } + + if (flags & BPF_F_PAD_ZEROS) + memset(dst + ret, 0, dst__sz - ret); + + return ret + 1; +} + +/* Keep unsinged long in prototype so that kfunc is usable when emitted to + * vmlinux.h in BPF programs directly, but note that while in BPF prog, the + * unsigned long always points to 8-byte region on stack, the kernel may only + * read and write the 4-bytes on 32-bit. + */ +__bpf_kfunc void bpf_local_irq_save(unsigned long *flags__irq_flag) +{ + local_irq_save(*flags__irq_flag); +} + +__bpf_kfunc void bpf_local_irq_restore(unsigned long *flags__irq_flag) +{ + local_irq_restore(*flags__irq_flag); +} + +__bpf_kfunc void __bpf_trap(void) +{ +} + +/* + * Kfuncs for string operations. + * + * Since strings are not necessarily %NUL-terminated, we cannot directly call + * in-kernel implementations. Instead, we open-code the implementations using + * __get_kernel_nofault instead of plain dereference to make them safe. + */ + +static int __bpf_strcasecmp(const char *s1, const char *s2, bool ignore_case) +{ + char c1, c2; + int i; + + if (!copy_from_kernel_nofault_allowed(s1, 1) || + !copy_from_kernel_nofault_allowed(s2, 1)) { + return -ERANGE; + } + + guard(pagefault)(); + for (i = 0; i < XATTR_SIZE_MAX; i++) { + __get_kernel_nofault(&c1, s1, char, err_out); + __get_kernel_nofault(&c2, s2, char, err_out); + if (ignore_case) { + c1 = tolower(c1); + c2 = tolower(c2); + } + if (c1 != c2) + return c1 < c2 ? -1 : 1; + if (c1 == '\0') + return 0; + s1++; + s2++; + } + return -E2BIG; +err_out: + return -EFAULT; +} + +/** + * bpf_strcmp - Compare two strings + * @s1__ign: One string + * @s2__ign: Another string + * + * Return: + * * %0 - Strings are equal + * * %-1 - @s1__ign is smaller + * * %1 - @s2__ign is smaller + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of strings is too large + * * %-ERANGE - One of strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strcmp(const char *s1__ign, const char *s2__ign) +{ + return __bpf_strcasecmp(s1__ign, s2__ign, false); +} + +/** + * bpf_strcasecmp - Compare two strings, ignoring the case of the characters + * @s1__ign: One string + * @s2__ign: Another string + * + * Return: + * * %0 - Strings are equal + * * %-1 - @s1__ign is smaller + * * %1 - @s2__ign is smaller + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of strings is too large + * * %-ERANGE - One of strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strcasecmp(const char *s1__ign, const char *s2__ign) +{ + return __bpf_strcasecmp(s1__ign, s2__ign, true); +} + +/** + * bpf_strnchr - Find a character in a length limited string + * @s__ign: The string to be searched + * @count: The number of characters to be searched + * @c: The character to search for + * + * Note that the %NUL-terminator is considered part of the string, and can + * be searched for. + * + * Return: + * * >=0 - Index of the first occurrence of @c within @s__ign + * * %-ENOENT - @c not found in the first @count characters of @s__ign + * * %-EFAULT - Cannot read @s__ign + * * %-E2BIG - @s__ign is too large + * * %-ERANGE - @s__ign is outside of kernel address space + */ +__bpf_kfunc int bpf_strnchr(const char *s__ign, size_t count, char c) +{ + char sc; + int i; + + if (!copy_from_kernel_nofault_allowed(s__ign, 1)) + return -ERANGE; + + guard(pagefault)(); + for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) { + __get_kernel_nofault(&sc, s__ign, char, err_out); + if (sc == c) + return i; + if (sc == '\0') + return -ENOENT; + s__ign++; + } + return i == XATTR_SIZE_MAX ? -E2BIG : -ENOENT; +err_out: + return -EFAULT; +} + +/** + * bpf_strchr - Find the first occurrence of a character in a string + * @s__ign: The string to be searched + * @c: The character to search for + * + * Note that the %NUL-terminator is considered part of the string, and can + * be searched for. + * + * Return: + * * >=0 - The index of the first occurrence of @c within @s__ign + * * %-ENOENT - @c not found in @s__ign + * * %-EFAULT - Cannot read @s__ign + * * %-E2BIG - @s__ign is too large + * * %-ERANGE - @s__ign is outside of kernel address space + */ +__bpf_kfunc int bpf_strchr(const char *s__ign, char c) +{ + return bpf_strnchr(s__ign, XATTR_SIZE_MAX, c); +} + +/** + * bpf_strchrnul - Find and return a character in a string, or end of string + * @s__ign: The string to be searched + * @c: The character to search for + * + * Return: + * * >=0 - Index of the first occurrence of @c within @s__ign or index of + * the null byte at the end of @s__ign when @c is not found + * * %-EFAULT - Cannot read @s__ign + * * %-E2BIG - @s__ign is too large + * * %-ERANGE - @s__ign is outside of kernel address space + */ +__bpf_kfunc int bpf_strchrnul(const char *s__ign, char c) +{ + char sc; + int i; + + if (!copy_from_kernel_nofault_allowed(s__ign, 1)) + return -ERANGE; + + guard(pagefault)(); + for (i = 0; i < XATTR_SIZE_MAX; i++) { + __get_kernel_nofault(&sc, s__ign, char, err_out); + if (sc == '\0' || sc == c) + return i; + s__ign++; + } + return -E2BIG; +err_out: + return -EFAULT; +} + +/** + * bpf_strrchr - Find the last occurrence of a character in a string + * @s__ign: The string to be searched + * @c: The character to search for + * + * Return: + * * >=0 - Index of the last occurrence of @c within @s__ign + * * %-ENOENT - @c not found in @s__ign + * * %-EFAULT - Cannot read @s__ign + * * %-E2BIG - @s__ign is too large + * * %-ERANGE - @s__ign is outside of kernel address space + */ +__bpf_kfunc int bpf_strrchr(const char *s__ign, int c) +{ + char sc; + int i, last = -ENOENT; + + if (!copy_from_kernel_nofault_allowed(s__ign, 1)) + return -ERANGE; + + guard(pagefault)(); + for (i = 0; i < XATTR_SIZE_MAX; i++) { + __get_kernel_nofault(&sc, s__ign, char, err_out); + if (sc == c) + last = i; + if (sc == '\0') + return last; + s__ign++; + } + return -E2BIG; +err_out: + return -EFAULT; +} + +/** + * bpf_strnlen - Calculate the length of a length-limited string + * @s__ign: The string + * @count: The maximum number of characters to count + * + * Return: + * * >=0 - The length of @s__ign + * * %-EFAULT - Cannot read @s__ign + * * %-E2BIG - @s__ign is too large + * * %-ERANGE - @s__ign is outside of kernel address space + */ +__bpf_kfunc int bpf_strnlen(const char *s__ign, size_t count) +{ + char c; + int i; + + if (!copy_from_kernel_nofault_allowed(s__ign, 1)) + return -ERANGE; + + guard(pagefault)(); + for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) { + __get_kernel_nofault(&c, s__ign, char, err_out); + if (c == '\0') + return i; + s__ign++; + } + return i == XATTR_SIZE_MAX ? -E2BIG : i; +err_out: + return -EFAULT; +} + +/** + * bpf_strlen - Calculate the length of a string + * @s__ign: The string + * + * Return: + * * >=0 - The length of @s__ign + * * %-EFAULT - Cannot read @s__ign + * * %-E2BIG - @s__ign is too large + * * %-ERANGE - @s__ign is outside of kernel address space + */ +__bpf_kfunc int bpf_strlen(const char *s__ign) +{ + return bpf_strnlen(s__ign, XATTR_SIZE_MAX); +} -BTF_SET8_START(generic_btf_ids) -#ifdef CONFIG_KEXEC_CORE +/** + * bpf_strspn - Calculate the length of the initial substring of @s__ign which + * only contains letters in @accept__ign + * @s__ign: The string to be searched + * @accept__ign: The string to search for + * + * Return: + * * >=0 - The length of the initial substring of @s__ign which only + * contains letters from @accept__ign + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of the strings is too large + * * %-ERANGE - One of the strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strspn(const char *s__ign, const char *accept__ign) +{ + char cs, ca; + int i, j; + + if (!copy_from_kernel_nofault_allowed(s__ign, 1) || + !copy_from_kernel_nofault_allowed(accept__ign, 1)) { + return -ERANGE; + } + + guard(pagefault)(); + for (i = 0; i < XATTR_SIZE_MAX; i++) { + __get_kernel_nofault(&cs, s__ign, char, err_out); + if (cs == '\0') + return i; + for (j = 0; j < XATTR_SIZE_MAX; j++) { + __get_kernel_nofault(&ca, accept__ign + j, char, err_out); + if (cs == ca || ca == '\0') + break; + } + if (j == XATTR_SIZE_MAX) + return -E2BIG; + if (ca == '\0') + return i; + s__ign++; + } + return -E2BIG; +err_out: + return -EFAULT; +} + +/** + * bpf_strcspn - Calculate the length of the initial substring of @s__ign which + * does not contain letters in @reject__ign + * @s__ign: The string to be searched + * @reject__ign: The string to search for + * + * Return: + * * >=0 - The length of the initial substring of @s__ign which does not + * contain letters from @reject__ign + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of the strings is too large + * * %-ERANGE - One of the strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strcspn(const char *s__ign, const char *reject__ign) +{ + char cs, cr; + int i, j; + + if (!copy_from_kernel_nofault_allowed(s__ign, 1) || + !copy_from_kernel_nofault_allowed(reject__ign, 1)) { + return -ERANGE; + } + + guard(pagefault)(); + for (i = 0; i < XATTR_SIZE_MAX; i++) { + __get_kernel_nofault(&cs, s__ign, char, err_out); + if (cs == '\0') + return i; + for (j = 0; j < XATTR_SIZE_MAX; j++) { + __get_kernel_nofault(&cr, reject__ign + j, char, err_out); + if (cs == cr || cr == '\0') + break; + } + if (j == XATTR_SIZE_MAX) + return -E2BIG; + if (cr != '\0') + return i; + s__ign++; + } + return -E2BIG; +err_out: + return -EFAULT; +} + +static int __bpf_strnstr(const char *s1, const char *s2, size_t len, + bool ignore_case) +{ + char c1, c2; + int i, j; + + if (!copy_from_kernel_nofault_allowed(s1, 1) || + !copy_from_kernel_nofault_allowed(s2, 1)) { + return -ERANGE; + } + + guard(pagefault)(); + for (i = 0; i < XATTR_SIZE_MAX; i++) { + for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) { + __get_kernel_nofault(&c2, s2 + j, char, err_out); + if (c2 == '\0') + return i; + /* + * We allow reading an extra byte from s2 (note the + * `i + j <= len` above) to cover the case when s2 is + * a suffix of the first len chars of s1. + */ + if (i + j == len) + break; + __get_kernel_nofault(&c1, s1 + j, char, err_out); + + if (ignore_case) { + c1 = tolower(c1); + c2 = tolower(c2); + } + + if (c1 == '\0') + return -ENOENT; + if (c1 != c2) + break; + } + if (j == XATTR_SIZE_MAX) + return -E2BIG; + if (i + j == len) + return -ENOENT; + s1++; + } + return -E2BIG; +err_out: + return -EFAULT; +} + +/** + * bpf_strstr - Find the first substring in a string + * @s1__ign: The string to be searched + * @s2__ign: The string to search for + * + * Return: + * * >=0 - Index of the first character of the first occurrence of @s2__ign + * within @s1__ign + * * %-ENOENT - @s2__ign is not a substring of @s1__ign + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of the strings is too large + * * %-ERANGE - One of the strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strstr(const char *s1__ign, const char *s2__ign) +{ + return __bpf_strnstr(s1__ign, s2__ign, XATTR_SIZE_MAX, false); +} + +/** + * bpf_strcasestr - Find the first substring in a string, ignoring the case of + * the characters + * @s1__ign: The string to be searched + * @s2__ign: The string to search for + * + * Return: + * * >=0 - Index of the first character of the first occurrence of @s2__ign + * within @s1__ign + * * %-ENOENT - @s2__ign is not a substring of @s1__ign + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of the strings is too large + * * %-ERANGE - One of the strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strcasestr(const char *s1__ign, const char *s2__ign) +{ + return __bpf_strnstr(s1__ign, s2__ign, XATTR_SIZE_MAX, true); +} + +/** + * bpf_strnstr - Find the first substring in a length-limited string + * @s1__ign: The string to be searched + * @s2__ign: The string to search for + * @len: the maximum number of characters to search + * + * Return: + * * >=0 - Index of the first character of the first occurrence of @s2__ign + * within the first @len characters of @s1__ign + * * %-ENOENT - @s2__ign not found in the first @len characters of @s1__ign + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of the strings is too large + * * %-ERANGE - One of the strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, + size_t len) +{ + return __bpf_strnstr(s1__ign, s2__ign, len, false); +} + +/** + * bpf_strncasestr - Find the first substring in a length-limited string, + * ignoring the case of the characters + * @s1__ign: The string to be searched + * @s2__ign: The string to search for + * @len: the maximum number of characters to search + * + * Return: + * * >=0 - Index of the first character of the first occurrence of @s2__ign + * within the first @len characters of @s1__ign + * * %-ENOENT - @s2__ign not found in the first @len characters of @s1__ign + * * %-EFAULT - Cannot read one of the strings + * * %-E2BIG - One of the strings is too large + * * %-ERANGE - One of the strings is outside of kernel address space + */ +__bpf_kfunc int bpf_strncasestr(const char *s1__ign, const char *s2__ign, + size_t len) +{ + return __bpf_strnstr(s1__ign, s2__ign, len, true); +} + +#ifdef CONFIG_KEYS +/** + * bpf_lookup_user_key - lookup a key by its serial + * @serial: key handle serial number + * @flags: lookup-specific flags + * + * Search a key with a given *serial* and the provided *flags*. + * If found, increment the reference count of the key by one, and + * return it in the bpf_key structure. + * + * The bpf_key structure must be passed to bpf_key_put() when done + * with it, so that the key reference count is decremented and the + * bpf_key structure is freed. + * + * Permission checks are deferred to the time the key is used by + * one of the available key-specific kfuncs. + * + * Set *flags* with KEY_LOOKUP_CREATE, to attempt creating a requested + * special keyring (e.g. session keyring), if it doesn't yet exist. + * Set *flags* with KEY_LOOKUP_PARTIAL, to lookup a key without waiting + * for the key construction, and to retrieve uninstantiated keys (keys + * without data attached to them). + * + * Return: a bpf_key pointer with a valid key pointer if the key is found, a + * NULL pointer otherwise. + */ +__bpf_kfunc struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags) +{ + key_ref_t key_ref; + struct bpf_key *bkey; + + if (flags & ~KEY_LOOKUP_ALL) + return NULL; + + /* + * Permission check is deferred until the key is used, as the + * intent of the caller is unknown here. + */ + key_ref = lookup_user_key(serial, flags, KEY_DEFER_PERM_CHECK); + if (IS_ERR(key_ref)) + return NULL; + + bkey = kmalloc(sizeof(*bkey), GFP_KERNEL); + if (!bkey) { + key_put(key_ref_to_ptr(key_ref)); + return NULL; + } + + bkey->key = key_ref_to_ptr(key_ref); + bkey->has_ref = true; + + return bkey; +} + +/** + * bpf_lookup_system_key - lookup a key by a system-defined ID + * @id: key ID + * + * Obtain a bpf_key structure with a key pointer set to the passed key ID. + * The key pointer is marked as invalid, to prevent bpf_key_put() from + * attempting to decrement the key reference count on that pointer. The key + * pointer set in such way is currently understood only by + * verify_pkcs7_signature(). + * + * Set *id* to one of the values defined in include/linux/verification.h: + * 0 for the primary keyring (immutable keyring of system keys); + * VERIFY_USE_SECONDARY_KEYRING for both the primary and secondary keyring + * (where keys can be added only if they are vouched for by existing keys + * in those keyrings); VERIFY_USE_PLATFORM_KEYRING for the platform + * keyring (primarily used by the integrity subsystem to verify a kexec'ed + * kerned image and, possibly, the initramfs signature). + * + * Return: a bpf_key pointer with an invalid key pointer set from the + * pre-determined ID on success, a NULL pointer otherwise + */ +__bpf_kfunc struct bpf_key *bpf_lookup_system_key(u64 id) +{ + struct bpf_key *bkey; + + if (system_keyring_id_check(id) < 0) + return NULL; + + bkey = kmalloc(sizeof(*bkey), GFP_ATOMIC); + if (!bkey) + return NULL; + + bkey->key = (struct key *)(unsigned long)id; + bkey->has_ref = false; + + return bkey; +} + +/** + * bpf_key_put - decrement key reference count if key is valid and free bpf_key + * @bkey: bpf_key structure + * + * Decrement the reference count of the key inside *bkey*, if the pointer + * is valid, and free *bkey*. + */ +__bpf_kfunc void bpf_key_put(struct bpf_key *bkey) +{ + if (bkey->has_ref) + key_put(bkey->key); + + kfree(bkey); +} + +/** + * bpf_verify_pkcs7_signature - verify a PKCS#7 signature + * @data_p: data to verify + * @sig_p: signature of the data + * @trusted_keyring: keyring with keys trusted for signature verification + * + * Verify the PKCS#7 signature *sig_ptr* against the supplied *data_ptr* + * with keys in a keyring referenced by *trusted_keyring*. + * + * Return: 0 on success, a negative value on error. + */ +__bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p, + struct bpf_dynptr *sig_p, + struct bpf_key *trusted_keyring) +{ +#ifdef CONFIG_SYSTEM_DATA_VERIFICATION + struct bpf_dynptr_kern *data_ptr = (struct bpf_dynptr_kern *)data_p; + struct bpf_dynptr_kern *sig_ptr = (struct bpf_dynptr_kern *)sig_p; + const void *data, *sig; + u32 data_len, sig_len; + int ret; + + if (trusted_keyring->has_ref) { + /* + * Do the permission check deferred in bpf_lookup_user_key(). + * See bpf_lookup_user_key() for more details. + * + * A call to key_task_permission() here would be redundant, as + * it is already done by keyring_search() called by + * find_asymmetric_key(). + */ + ret = key_validate(trusted_keyring->key); + if (ret < 0) + return ret; + } + + data_len = __bpf_dynptr_size(data_ptr); + data = __bpf_dynptr_data(data_ptr, data_len); + sig_len = __bpf_dynptr_size(sig_ptr); + sig = __bpf_dynptr_data(sig_ptr, sig_len); + + return verify_pkcs7_signature(data, data_len, sig, sig_len, + trusted_keyring->key, + VERIFYING_BPF_SIGNATURE, NULL, + NULL); +#else + return -EOPNOTSUPP; +#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ +} +#endif /* CONFIG_KEYS */ + +typedef int (*bpf_task_work_callback_t)(struct bpf_map *map, void *key, void *value); + +enum bpf_task_work_state { + /* bpf_task_work is ready to be used */ + BPF_TW_STANDBY = 0, + /* irq work scheduling in progress */ + BPF_TW_PENDING, + /* task work scheduling in progress */ + BPF_TW_SCHEDULING, + /* task work is scheduled successfully */ + BPF_TW_SCHEDULED, + /* callback is running */ + BPF_TW_RUNNING, + /* associated BPF map value is deleted */ + BPF_TW_FREED, +}; + +struct bpf_task_work_ctx { + enum bpf_task_work_state state; + refcount_t refcnt; + struct callback_head work; + struct irq_work irq_work; + /* bpf_prog that schedules task work */ + struct bpf_prog *prog; + /* task for which callback is scheduled */ + struct task_struct *task; + /* the map and map value associated with this context */ + struct bpf_map *map; + void *map_val; + enum task_work_notify_mode mode; + bpf_task_work_callback_t callback_fn; + struct rcu_head rcu; +} __aligned(8); + +/* Actual type for struct bpf_task_work */ +struct bpf_task_work_kern { + struct bpf_task_work_ctx *ctx; +}; + +static void bpf_task_work_ctx_reset(struct bpf_task_work_ctx *ctx) +{ + if (ctx->prog) { + bpf_prog_put(ctx->prog); + ctx->prog = NULL; + } + if (ctx->task) { + bpf_task_release(ctx->task); + ctx->task = NULL; + } +} + +static bool bpf_task_work_ctx_tryget(struct bpf_task_work_ctx *ctx) +{ + return refcount_inc_not_zero(&ctx->refcnt); +} + +static void bpf_task_work_ctx_put(struct bpf_task_work_ctx *ctx) +{ + if (!refcount_dec_and_test(&ctx->refcnt)) + return; + + bpf_task_work_ctx_reset(ctx); + + /* bpf_mem_free expects migration to be disabled */ + migrate_disable(); + bpf_mem_free(&bpf_global_ma, ctx); + migrate_enable(); +} + +static void bpf_task_work_cancel(struct bpf_task_work_ctx *ctx) +{ + /* + * Scheduled task_work callback holds ctx ref, so if we successfully + * cancelled, we put that ref on callback's behalf. If we couldn't + * cancel, callback will inevitably run or has already completed + * running, and it would have taken care of its ctx ref itself. + */ + if (task_work_cancel(ctx->task, &ctx->work)) + bpf_task_work_ctx_put(ctx); +} + +static void bpf_task_work_callback(struct callback_head *cb) +{ + struct bpf_task_work_ctx *ctx = container_of(cb, struct bpf_task_work_ctx, work); + enum bpf_task_work_state state; + u32 idx; + void *key; + + /* Read lock is needed to protect ctx and map key/value access */ + guard(rcu_tasks_trace)(); + /* + * This callback may start running before bpf_task_work_irq() switched to + * SCHEDULED state, so handle both transition variants SCHEDULING|SCHEDULED -> RUNNING. + */ + state = cmpxchg(&ctx->state, BPF_TW_SCHEDULING, BPF_TW_RUNNING); + if (state == BPF_TW_SCHEDULED) + state = cmpxchg(&ctx->state, BPF_TW_SCHEDULED, BPF_TW_RUNNING); + if (state == BPF_TW_FREED) { + bpf_task_work_ctx_put(ctx); + return; + } + + key = (void *)map_key_from_value(ctx->map, ctx->map_val, &idx); + + migrate_disable(); + ctx->callback_fn(ctx->map, key, ctx->map_val); + migrate_enable(); + + bpf_task_work_ctx_reset(ctx); + (void)cmpxchg(&ctx->state, BPF_TW_RUNNING, BPF_TW_STANDBY); + + bpf_task_work_ctx_put(ctx); +} + +static void bpf_task_work_irq(struct irq_work *irq_work) +{ + struct bpf_task_work_ctx *ctx = container_of(irq_work, struct bpf_task_work_ctx, irq_work); + enum bpf_task_work_state state; + int err; + + guard(rcu_tasks_trace)(); + + if (cmpxchg(&ctx->state, BPF_TW_PENDING, BPF_TW_SCHEDULING) != BPF_TW_PENDING) { + bpf_task_work_ctx_put(ctx); + return; + } + + err = task_work_add(ctx->task, &ctx->work, ctx->mode); + if (err) { + bpf_task_work_ctx_reset(ctx); + /* + * try to switch back to STANDBY for another task_work reuse, but we might have + * gone to FREED already, which is fine as we already cleaned up after ourselves + */ + (void)cmpxchg(&ctx->state, BPF_TW_SCHEDULING, BPF_TW_STANDBY); + bpf_task_work_ctx_put(ctx); + return; + } + + /* + * It's technically possible for just scheduled task_work callback to + * complete running by now, going SCHEDULING -> RUNNING and then + * dropping its ctx refcount. Instead of capturing extra ref just to + * protected below ctx->state access, we rely on RCU protection to + * perform below SCHEDULING -> SCHEDULED attempt. + */ + state = cmpxchg(&ctx->state, BPF_TW_SCHEDULING, BPF_TW_SCHEDULED); + if (state == BPF_TW_FREED) + bpf_task_work_cancel(ctx); /* clean up if we switched into FREED state */ +} + +static struct bpf_task_work_ctx *bpf_task_work_fetch_ctx(struct bpf_task_work *tw, + struct bpf_map *map) +{ + struct bpf_task_work_kern *twk = (void *)tw; + struct bpf_task_work_ctx *ctx, *old_ctx; + + ctx = READ_ONCE(twk->ctx); + if (ctx) + return ctx; + + ctx = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_task_work_ctx)); + if (!ctx) + return ERR_PTR(-ENOMEM); + + memset(ctx, 0, sizeof(*ctx)); + refcount_set(&ctx->refcnt, 1); /* map's own ref */ + ctx->state = BPF_TW_STANDBY; + + old_ctx = cmpxchg(&twk->ctx, NULL, ctx); + if (old_ctx) { + /* + * tw->ctx is set by concurrent BPF program, release allocated + * memory and try to reuse already set context. + */ + bpf_mem_free(&bpf_global_ma, ctx); + return old_ctx; + } + + return ctx; /* Success */ +} + +static struct bpf_task_work_ctx *bpf_task_work_acquire_ctx(struct bpf_task_work *tw, + struct bpf_map *map) +{ + struct bpf_task_work_ctx *ctx; + + ctx = bpf_task_work_fetch_ctx(tw, map); + if (IS_ERR(ctx)) + return ctx; + + /* try to get ref for task_work callback to hold */ + if (!bpf_task_work_ctx_tryget(ctx)) + return ERR_PTR(-EBUSY); + + if (cmpxchg(&ctx->state, BPF_TW_STANDBY, BPF_TW_PENDING) != BPF_TW_STANDBY) { + /* lost acquiring race or map_release_uref() stole it from us, put ref and bail */ + bpf_task_work_ctx_put(ctx); + return ERR_PTR(-EBUSY); + } + + /* + * If no process or bpffs is holding a reference to the map, no new callbacks should be + * scheduled. This does not address any race or correctness issue, but rather is a policy + * choice: dropping user references should stop everything. + */ + if (!atomic64_read(&map->usercnt)) { + /* drop ref we just got for task_work callback itself */ + bpf_task_work_ctx_put(ctx); + /* transfer map's ref into cancel_and_free() */ + bpf_task_work_cancel_and_free(tw); + return ERR_PTR(-EBUSY); + } + + return ctx; +} + +static int bpf_task_work_schedule(struct task_struct *task, struct bpf_task_work *tw, + struct bpf_map *map, bpf_task_work_callback_t callback_fn, + struct bpf_prog_aux *aux, enum task_work_notify_mode mode) +{ + struct bpf_prog *prog; + struct bpf_task_work_ctx *ctx; + int err; + + BTF_TYPE_EMIT(struct bpf_task_work); + + prog = bpf_prog_inc_not_zero(aux->prog); + if (IS_ERR(prog)) + return -EBADF; + task = bpf_task_acquire(task); + if (!task) { + err = -EBADF; + goto release_prog; + } + + ctx = bpf_task_work_acquire_ctx(tw, map); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto release_all; + } + + ctx->task = task; + ctx->callback_fn = callback_fn; + ctx->prog = prog; + ctx->mode = mode; + ctx->map = map; + ctx->map_val = (void *)tw - map->record->task_work_off; + init_task_work(&ctx->work, bpf_task_work_callback); + init_irq_work(&ctx->irq_work, bpf_task_work_irq); + + irq_work_queue(&ctx->irq_work); + return 0; + +release_all: + bpf_task_release(task); +release_prog: + bpf_prog_put(prog); + return err; +} + +/** + * bpf_task_work_schedule_signal_impl - Schedule BPF callback using task_work_add with TWA_SIGNAL + * mode + * @task: Task struct for which callback should be scheduled + * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping + * @map__map: bpf_map that embeds struct bpf_task_work in the values + * @callback: pointer to BPF subprogram to call + * @aux__prog: user should pass NULL + * + * Return: 0 if task work has been scheduled successfully, negative error code otherwise + */ +__bpf_kfunc int bpf_task_work_schedule_signal_impl(struct task_struct *task, + struct bpf_task_work *tw, void *map__map, + bpf_task_work_callback_t callback, + void *aux__prog) +{ + return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_SIGNAL); +} + +/** + * bpf_task_work_schedule_resume_impl - Schedule BPF callback using task_work_add with TWA_RESUME + * mode + * @task: Task struct for which callback should be scheduled + * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping + * @map__map: bpf_map that embeds struct bpf_task_work in the values + * @callback: pointer to BPF subprogram to call + * @aux__prog: user should pass NULL + * + * Return: 0 if task work has been scheduled successfully, negative error code otherwise + */ +__bpf_kfunc int bpf_task_work_schedule_resume_impl(struct task_struct *task, + struct bpf_task_work *tw, void *map__map, + bpf_task_work_callback_t callback, + void *aux__prog) +{ + return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_RESUME); +} + +static int make_file_dynptr(struct file *file, u32 flags, bool may_sleep, + struct bpf_dynptr_kern *ptr) +{ + struct bpf_dynptr_file_impl *state; + + /* flags is currently unsupported */ + if (flags) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + state = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_dynptr_file_impl)); + if (!state) { + bpf_dynptr_set_null(ptr); + return -ENOMEM; + } + state->offset = 0; + state->size = U64_MAX; /* Don't restrict size, as file may change anyways */ + freader_init_from_file(&state->freader, NULL, 0, file, may_sleep); + bpf_dynptr_init(ptr, state, BPF_DYNPTR_TYPE_FILE, 0, 0); + bpf_dynptr_set_rdonly(ptr); + return 0; +} + +__bpf_kfunc int bpf_dynptr_from_file(struct file *file, u32 flags, struct bpf_dynptr *ptr__uninit) +{ + return make_file_dynptr(file, flags, false, (struct bpf_dynptr_kern *)ptr__uninit); +} + +int bpf_dynptr_from_file_sleepable(struct file *file, u32 flags, struct bpf_dynptr *ptr__uninit) +{ + return make_file_dynptr(file, flags, true, (struct bpf_dynptr_kern *)ptr__uninit); +} + +__bpf_kfunc int bpf_dynptr_file_discard(struct bpf_dynptr *dynptr) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)dynptr; + struct bpf_dynptr_file_impl *df = ptr->data; + + if (!df) + return 0; + + freader_cleanup(&df->freader); + bpf_mem_free(&bpf_global_ma, df); + bpf_dynptr_set_null(ptr); + return 0; +} + +__bpf_kfunc_end_defs(); + +static void bpf_task_work_cancel_scheduled(struct irq_work *irq_work) +{ + struct bpf_task_work_ctx *ctx = container_of(irq_work, struct bpf_task_work_ctx, irq_work); + + bpf_task_work_cancel(ctx); /* this might put task_work callback's ref */ + bpf_task_work_ctx_put(ctx); /* and here we put map's own ref that was transferred to us */ +} + +void bpf_task_work_cancel_and_free(void *val) +{ + struct bpf_task_work_kern *twk = val; + struct bpf_task_work_ctx *ctx; + enum bpf_task_work_state state; + + ctx = xchg(&twk->ctx, NULL); + if (!ctx) + return; + + state = xchg(&ctx->state, BPF_TW_FREED); + if (state == BPF_TW_SCHEDULED) { + /* run in irq_work to avoid locks in NMI */ + init_irq_work(&ctx->irq_work, bpf_task_work_cancel_scheduled); + irq_work_queue(&ctx->irq_work); + return; + } + + bpf_task_work_ctx_put(ctx); /* put bpf map's ref */ +} + +BTF_KFUNCS_START(generic_btf_ids) +#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) +BTF_ID_FLAGS(func, bpf_percpu_obj_new_impl, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE) -BTF_ID_FLAGS(func, bpf_list_push_front) -BTF_ID_FLAGS(func, bpf_list_push_back) +BTF_ID_FLAGS(func, bpf_percpu_obj_drop_impl, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL | KF_RCU) +BTF_ID_FLAGS(func, bpf_list_push_front_impl) +BTF_ID_FLAGS(func, bpf_list_push_back_impl) BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_task_acquire_not_zero, KF_ACQUIRE | KF_RCU | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_task_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_list_front, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_list_back, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_rbtree_remove, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_rbtree_add_impl) +BTF_ID_FLAGS(func, bpf_rbtree_first, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_rbtree_root, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_rbtree_left, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_rbtree_right, KF_RET_NULL) + #ifdef CONFIG_CGROUPS -BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cgroup_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE) -BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_TRUSTED_ARGS | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU) +BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) -BTF_SET8_END(generic_btf_ids) +BTF_ID_FLAGS(func, bpf_task_from_vpid, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_throw) +#ifdef CONFIG_BPF_EVENTS +BTF_ID_FLAGS(func, bpf_send_signal_task, KF_TRUSTED_ARGS) +#endif +#ifdef CONFIG_KEYS +BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE) +#ifdef CONFIG_SYSTEM_DATA_VERIFICATION +BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE) +#endif +#endif +BTF_KFUNCS_END(generic_btf_ids) static const struct btf_kfunc_id_set generic_kfunc_set = { .owner = THIS_MODULE, @@ -2074,18 +4447,101 @@ static const struct btf_kfunc_id_set generic_kfunc_set = { BTF_ID_LIST(generic_dtor_ids) BTF_ID(struct, task_struct) -BTF_ID(func, bpf_task_release) +BTF_ID(func, bpf_task_release_dtor) #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) -BTF_ID(func, bpf_cgroup_release) +BTF_ID(func, bpf_cgroup_release_dtor) #endif -BTF_SET8_START(common_btf_ids) -BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) -BTF_ID_FLAGS(func, bpf_rdonly_cast) +BTF_KFUNCS_START(common_btf_ids) +BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx, KF_FASTCALL) +BTF_ID_FLAGS(func, bpf_rdonly_cast, KF_FASTCALL) BTF_ID_FLAGS(func, bpf_rcu_read_lock) BTF_ID_FLAGS(func, bpf_rcu_read_unlock) -BTF_SET8_END(common_btf_ids) +BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW) +BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU) +BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY) +#ifdef CONFIG_CGROUPS +BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY) +#endif +BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_dynptr_adjust) +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_dynptr_copy) +BTF_ID_FLAGS(func, bpf_dynptr_memset) +#ifdef CONFIG_NET +BTF_ID_FLAGS(func, bpf_modify_return_test_tp) +#endif +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_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW) +BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_get_kmem_cache) +BTF_ID_FLAGS(func, bpf_iter_kmem_cache_new, KF_ITER_NEW | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_iter_kmem_cache_destroy, KF_ITER_DESTROY | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_local_irq_save) +BTF_ID_FLAGS(func, bpf_local_irq_restore) +#ifdef CONFIG_BPF_EVENTS +BTF_ID_FLAGS(func, bpf_probe_read_user_dynptr) +BTF_ID_FLAGS(func, bpf_probe_read_kernel_dynptr) +BTF_ID_FLAGS(func, bpf_probe_read_user_str_dynptr) +BTF_ID_FLAGS(func, bpf_probe_read_kernel_str_dynptr) +BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS) +#endif +#ifdef CONFIG_DMA_SHARED_BUFFER +BTF_ID_FLAGS(func, bpf_iter_dmabuf_new, KF_ITER_NEW | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE) +#endif +BTF_ID_FLAGS(func, __bpf_trap) +BTF_ID_FLAGS(func, bpf_strcmp); +BTF_ID_FLAGS(func, bpf_strcasecmp); +BTF_ID_FLAGS(func, bpf_strchr); +BTF_ID_FLAGS(func, bpf_strchrnul); +BTF_ID_FLAGS(func, bpf_strnchr); +BTF_ID_FLAGS(func, bpf_strrchr); +BTF_ID_FLAGS(func, bpf_strlen); +BTF_ID_FLAGS(func, bpf_strnlen); +BTF_ID_FLAGS(func, bpf_strspn); +BTF_ID_FLAGS(func, bpf_strcspn); +BTF_ID_FLAGS(func, bpf_strstr); +BTF_ID_FLAGS(func, bpf_strcasestr); +BTF_ID_FLAGS(func, bpf_strnstr); +BTF_ID_FLAGS(func, bpf_strncasestr); +#if defined(CONFIG_BPF_LSM) && defined(CONFIG_CGROUPS) +BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU) +#endif +BTF_ID_FLAGS(func, bpf_stream_vprintk_impl, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_task_work_schedule_signal_impl, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_task_work_schedule_resume_impl, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_dynptr_from_file, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_dynptr_file_discard) +BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { .owner = THIS_MODULE, @@ -2110,7 +4566,10 @@ static int __init kfunc_init(void) ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &generic_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &generic_kfunc_set); ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors, ARRAY_SIZE(generic_dtors), THIS_MODULE); @@ -2118,3 +4577,34 @@ static int __init kfunc_init(void) } late_initcall(kfunc_init); + +/* Get a pointer to dynptr data up to len bytes for read only access. If + * the dynptr doesn't have continuous data up to len bytes, return NULL. + */ +const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u64 len) +{ + const struct bpf_dynptr *p = (struct bpf_dynptr *)ptr; + + return bpf_dynptr_slice(p, 0, NULL, len); +} + +/* Get a pointer to dynptr data up to len bytes for read write access. If + * the dynptr doesn't have continuous data up to len bytes, or the dynptr + * is read only, return NULL. + */ +void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u64 len) +{ + if (__bpf_dynptr_is_rdonly(ptr)) + return NULL; + return (void *)__bpf_dynptr_data(ptr, len); +} + +void bpf_map_free_internal_structs(struct bpf_map *map, void *val) +{ + if (btf_record_has_field(map->record, BPF_TIMER)) + bpf_obj_free_timer(map->record, val); + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(map->record, val); + if (btf_record_has_field(map->record, BPF_TASK_WORK)) + bpf_obj_free_task_work(map->record, val); +} diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 4f841e16779e..9f866a010dad 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/kstrtox.h> #include "preload/bpf_preload.h" enum bpf_type { @@ -98,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -118,11 +119,9 @@ static struct inode *bpf_get_inode(struct super_block *sb, return ERR_PTR(-ENOSPC); inode->i_ino = get_next_ino(); - inode->i_atime = current_time(inode); - inode->i_mtime = inode->i_atime; - inode->i_ctime = inode->i_atime; + simple_inode_init_ts(inode); - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); return inode; } @@ -145,21 +144,19 @@ static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, struct inode *dir) { - d_instantiate(dentry, inode); - dget(dentry); + d_make_persistent(dentry, inode); - dir->i_mtime = current_time(dir); - dir->i_ctime = dir->i_mtime; + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); } -static int bpf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); if (IS_ERR(inode)) - return PTR_ERR(inode); + return ERR_CAST(inode); inode->i_op = &bpf_dir_iops; inode->i_fop = &simple_dir_operations; @@ -168,7 +165,7 @@ static int bpf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, inc_nlink(dir); bpf_dentry_finalize(dentry, inode, dir); - return 0; + return NULL; } struct map_iter { @@ -382,7 +379,7 @@ bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) return simple_lookup(dir, dentry, flags); } -static int bpf_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int bpf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *target) { char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); @@ -422,20 +419,16 @@ static int bpf_iter_link_pin_kernel(struct dentry *parent, struct dentry *dentry; int ret; - inode_lock(parent->d_inode); - dentry = lookup_one_len(name, parent, strlen(name)); - if (IS_ERR(dentry)) { - inode_unlock(parent->d_inode); + dentry = simple_start_creating(parent, name); + if (IS_ERR(dentry)) return PTR_ERR(dentry); - } ret = bpf_mkobj_ops(dentry, mode, link, &bpf_link_iops, &bpf_iter_fops); - dput(dentry); - inode_unlock(parent->d_inode); + simple_done_creating(dentry); return ret; } -static int bpf_obj_do_pin(const char __user *pathname, void *raw, +static int bpf_obj_do_pin(int path_fd, const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; @@ -444,22 +437,21 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, umode_t mode; int ret; - dentry = user_path_create(AT_FDCWD, pathname, &path, 0); + dentry = start_creating_user_path(path_fd, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); - mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); - - ret = security_path_mknod(&path, dentry, mode, 0); - if (ret) - goto out; - dir = d_inode(path.dentry); if (dir->i_op != &bpf_dir_iops) { ret = -EPERM; goto out; } + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + ret = security_path_mknod(&path, dentry, mode, 0); + if (ret) + goto out; + switch (type) { case BPF_TYPE_PROG: ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw); @@ -474,11 +466,11 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, ret = -EPERM; } out: - done_path_create(&path, dentry); + end_creating_path(&path, dentry); return ret; } -int bpf_obj_pin_user(u32 ufd, const char __user *pathname) +int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname) { enum bpf_type type; void *raw; @@ -488,14 +480,14 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) if (IS_ERR(raw)) return PTR_ERR(raw); - ret = bpf_obj_do_pin(pathname, raw, type); + ret = bpf_obj_do_pin(path_fd, pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); return ret; } -static void *bpf_obj_do_get(const char __user *pathname, +static void *bpf_obj_do_get(int path_fd, const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; @@ -503,7 +495,7 @@ static void *bpf_obj_do_get(const char __user *pathname, void *raw; int ret; - ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path); + ret = user_path_at(path_fd, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); @@ -527,7 +519,7 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname, int flags) +int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; int f_flags; @@ -538,7 +530,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) if (f_flags < 0) return f_flags; - raw = bpf_obj_do_get(pathname, &type, f_flags); + raw = bpf_obj_do_get(path_fd, pathname, &type, f_flags); if (IS_ERR(raw)) return PTR_ERR(raw); @@ -559,7 +551,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) { struct bpf_prog *prog; - int ret = inode_permission(&init_user_ns, inode, MAY_READ); + int ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ); if (ret) return ERR_PTR(ret); @@ -598,19 +590,187 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); +struct bpffs_btf_enums { + const struct btf *btf; + const struct btf_type *cmd_t; + const struct btf_type *map_t; + const struct btf_type *prog_t; + const struct btf_type *attach_t; +}; + +static int find_bpffs_btf_enums(struct bpffs_btf_enums *info) +{ + const struct btf *btf; + const struct btf_type *t; + const char *name; + int i, n; + + memset(info, 0, sizeof(*info)); + + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return PTR_ERR(btf); + if (!btf) + return -ENOENT; + + info->btf = btf; + + for (i = 1, n = btf_nr_types(btf); i < n; i++) { + t = btf_type_by_id(btf, i); + if (!btf_type_is_enum(t)) + continue; + + name = btf_name_by_offset(btf, t->name_off); + if (!name) + continue; + + if (strcmp(name, "bpf_cmd") == 0) + info->cmd_t = t; + else if (strcmp(name, "bpf_map_type") == 0) + info->map_t = t; + else if (strcmp(name, "bpf_prog_type") == 0) + info->prog_t = t; + else if (strcmp(name, "bpf_attach_type") == 0) + info->attach_t = t; + else + continue; + + if (info->cmd_t && info->map_t && info->prog_t && info->attach_t) + return 0; + } + + return -ESRCH; +} + +static bool find_btf_enum_const(const struct btf *btf, const struct btf_type *enum_t, + const char *prefix, const char *str, int *value) +{ + const struct btf_enum *e; + const char *name; + int i, n, pfx_len = strlen(prefix); + + *value = 0; + + if (!btf || !enum_t) + return false; + + for (i = 0, n = btf_vlen(enum_t); i < n; i++) { + e = &btf_enum(enum_t)[i]; + + name = btf_name_by_offset(btf, e->name_off); + if (!name || strncasecmp(name, prefix, pfx_len) != 0) + continue; + + /* match symbolic name case insensitive and ignoring prefix */ + if (strcasecmp(name + pfx_len, str) == 0) { + *value = e->val; + return true; + } + } + + return false; +} + +static void seq_print_delegate_opts(struct seq_file *m, + const char *opt_name, + const struct btf *btf, + const struct btf_type *enum_t, + const char *prefix, + u64 delegate_msk, u64 any_msk) +{ + const struct btf_enum *e; + bool first = true; + const char *name; + u64 msk; + int i, n, pfx_len = strlen(prefix); + + delegate_msk &= any_msk; /* clear unknown bits */ + + if (delegate_msk == 0) + return; + + seq_printf(m, ",%s", opt_name); + if (delegate_msk == any_msk) { + seq_printf(m, "=any"); + return; + } + + if (btf && enum_t) { + for (i = 0, n = btf_vlen(enum_t); i < n; i++) { + e = &btf_enum(enum_t)[i]; + name = btf_name_by_offset(btf, e->name_off); + if (!name || strncasecmp(name, prefix, pfx_len) != 0) + continue; + msk = 1ULL << e->val; + if (delegate_msk & msk) { + /* emit lower-case name without prefix */ + seq_putc(m, first ? '=' : ':'); + name += pfx_len; + while (*name) { + seq_putc(m, tolower(*name)); + name++; + } + + delegate_msk &= ~msk; + first = false; + } + } + } + if (delegate_msk) + seq_printf(m, "%c0x%llx", first ? '=' : ':', delegate_msk); +} + /* * Display the mount options in /proc/mounts. */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { - umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; - + struct inode *inode = d_inode(root); + umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; + struct bpf_mount_opts *opts = root->d_sb->s_fs_info; + u64 mask; + + if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, inode->i_uid)); + if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); + + if (opts->delegate_cmds || opts->delegate_maps || + opts->delegate_progs || opts->delegate_attachs) { + struct bpffs_btf_enums info; + + /* ignore errors, fallback to hex */ + (void)find_bpffs_btf_enums(&info); + + mask = (1ULL << __MAX_BPF_CMD) - 1; + seq_print_delegate_opts(m, "delegate_cmds", + info.btf, info.cmd_t, "BPF_", + opts->delegate_cmds, mask); + + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_maps", + info.btf, info.map_t, "BPF_MAP_TYPE_", + opts->delegate_maps, mask); + + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_progs", + info.btf, info.prog_t, "BPF_PROG_TYPE_", + opts->delegate_progs, mask); + + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_attachs", + info.btf, info.attach_t, "BPF_", + opts->delegate_attachs, mask); + } + return 0; } -static void bpf_free_inode(struct inode *inode) +static void bpf_destroy_inode(struct inode *inode) { enum bpf_type type; @@ -621,31 +781,41 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, .show_options = bpf_show_options, - .free_inode = bpf_free_inode, + .destroy_inode = bpf_destroy_inode, }; enum { + OPT_UID, + OPT_GID, OPT_MODE, + OPT_DELEGATE_CMDS, + OPT_DELEGATE_MAPS, + OPT_DELEGATE_PROGS, + OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { + fsparam_u32 ("uid", OPT_UID), + fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), + fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), + fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), + fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), + fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; -struct bpf_mount_opts { - umode_t mode; -}; - static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = fc->s_fs_info; struct fs_parse_result result; - int opt; + kuid_t uid; + kgid_t gid; + int opt, err; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { @@ -666,12 +836,104 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) } switch (opt) { + case OPT_UID: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + goto bad_value; + + /* + * The requested uid must be representable in the + * filesystem's idmapping. + */ + if (!kuid_has_mapping(fc->user_ns, uid)) + goto bad_value; + + opts->uid = uid; + break; + case OPT_GID: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + goto bad_value; + + /* + * The requested gid must be representable in the + * filesystem's idmapping. + */ + if (!kgid_has_mapping(fc->user_ns, gid)) + goto bad_value; + + opts->gid = gid; + break; case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; + case OPT_DELEGATE_CMDS: + case OPT_DELEGATE_MAPS: + case OPT_DELEGATE_PROGS: + case OPT_DELEGATE_ATTACHS: { + struct bpffs_btf_enums info; + const struct btf_type *enum_t; + const char *enum_pfx; + u64 *delegate_msk, msk = 0; + char *p, *str; + int val; + + /* ignore errors, fallback to hex */ + (void)find_bpffs_btf_enums(&info); + + switch (opt) { + case OPT_DELEGATE_CMDS: + delegate_msk = &opts->delegate_cmds; + enum_t = info.cmd_t; + enum_pfx = "BPF_"; + break; + case OPT_DELEGATE_MAPS: + delegate_msk = &opts->delegate_maps; + enum_t = info.map_t; + enum_pfx = "BPF_MAP_TYPE_"; + break; + case OPT_DELEGATE_PROGS: + delegate_msk = &opts->delegate_progs; + enum_t = info.prog_t; + enum_pfx = "BPF_PROG_TYPE_"; + break; + case OPT_DELEGATE_ATTACHS: + delegate_msk = &opts->delegate_attachs; + enum_t = info.attach_t; + enum_pfx = "BPF_"; + break; + default: + return -EINVAL; + } + + str = param->string; + while ((p = strsep(&str, ":"))) { + if (strcmp(p, "any") == 0) { + msk |= ~0ULL; + } else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) { + msk |= 1ULL << val; + } else { + err = kstrtou64(p, 0, &msk); + if (err) + return err; + } + } + + /* Setting delegation mount options requires privileges */ + if (msk && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + *delegate_msk |= msk; + break; + } + default: + /* ignore unknown mount options */ + break; } return 0; +bad_value: + return invalfc(fc, "Bad value for '%s'", param->key); } struct bpf_preload_ops *bpf_preload_ops; @@ -743,10 +1005,14 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; int ret; + /* Mounting an instance of BPF FS requires privileges */ + if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -754,6 +1020,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; + inode->i_uid = opts->uid; + inode->i_gid = opts->gid; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); @@ -768,7 +1036,7 @@ static int bpf_get_tree(struct fs_context *fc) static void bpf_free_fc(struct fs_context *fc) { - kfree(fc->fs_private); + kfree(fc->s_fs_info); } static const struct fs_context_operations bpf_context_ops = { @@ -789,18 +1057,35 @@ static int bpf_init_fs_context(struct fs_context *fc) return -ENOMEM; opts->mode = S_IRWXUGO; + opts->uid = current_fsuid(); + opts->gid = current_fsgid(); - fc->fs_private = opts; + /* start out with no BPF token delegation enabled */ + opts->delegate_cmds = 0; + opts->delegate_maps = 0; + opts->delegate_progs = 0; + opts->delegate_attachs = 0; + + fc->s_fs_info = opts; fc->ops = &bpf_context_ops; return 0; } +static void bpf_kill_super(struct super_block *sb) +{ + struct bpf_mount_opts *opts = sb->s_fs_info; + + kill_anon_super(sb); + kfree(opts); +} + static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, - .kill_sb = kill_litter_super, + .kill_sb = bpf_kill_super, + .fs_flags = FS_USERNS_MOUNT, }; static int __init bpf_init(void) diff --git a/kernel/bpf/kmem_cache_iter.c b/kernel/bpf/kmem_cache_iter.c new file mode 100644 index 000000000000..3ae2158d767f --- /dev/null +++ b/kernel/bpf/kmem_cache_iter.c @@ -0,0 +1,238 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Google */ +#include <linux/bpf.h> +#include <linux/btf_ids.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> + +#include "../../mm/slab.h" /* kmem_cache, slab_caches and slab_mutex */ + +/* open-coded version */ +struct bpf_iter_kmem_cache { + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +struct bpf_iter_kmem_cache_kern { + struct kmem_cache *pos; +} __attribute__((aligned(8))); + +#define KMEM_CACHE_POS_START ((void *)1L) + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_kmem_cache_new(struct bpf_iter_kmem_cache *it) +{ + struct bpf_iter_kmem_cache_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(*kit) > sizeof(*it)); + BUILD_BUG_ON(__alignof__(*kit) != __alignof__(*it)); + + kit->pos = KMEM_CACHE_POS_START; + return 0; +} + +__bpf_kfunc struct kmem_cache *bpf_iter_kmem_cache_next(struct bpf_iter_kmem_cache *it) +{ + struct bpf_iter_kmem_cache_kern *kit = (void *)it; + struct kmem_cache *prev = kit->pos; + struct kmem_cache *next; + bool destroy = false; + + if (!prev) + return NULL; + + mutex_lock(&slab_mutex); + + if (list_empty(&slab_caches)) { + mutex_unlock(&slab_mutex); + return NULL; + } + + if (prev == KMEM_CACHE_POS_START) + next = list_first_entry(&slab_caches, struct kmem_cache, list); + else if (list_last_entry(&slab_caches, struct kmem_cache, list) == prev) + next = NULL; + else + next = list_next_entry(prev, list); + + /* boot_caches have negative refcount, don't touch them */ + if (next && next->refcount > 0) + next->refcount++; + + /* Skip kmem_cache_destroy() for active entries */ + if (prev && prev != KMEM_CACHE_POS_START) { + if (prev->refcount > 1) + prev->refcount--; + else if (prev->refcount == 1) + destroy = true; + } + + mutex_unlock(&slab_mutex); + + if (destroy) + kmem_cache_destroy(prev); + + kit->pos = next; + return next; +} + +__bpf_kfunc void bpf_iter_kmem_cache_destroy(struct bpf_iter_kmem_cache *it) +{ + struct bpf_iter_kmem_cache_kern *kit = (void *)it; + struct kmem_cache *s = kit->pos; + bool destroy = false; + + if (s == NULL || s == KMEM_CACHE_POS_START) + return; + + mutex_lock(&slab_mutex); + + /* Skip kmem_cache_destroy() for active entries */ + if (s->refcount > 1) + s->refcount--; + else if (s->refcount == 1) + destroy = true; + + mutex_unlock(&slab_mutex); + + if (destroy) + kmem_cache_destroy(s); +} + +__bpf_kfunc_end_defs(); + +struct bpf_iter__kmem_cache { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct kmem_cache *, s); +}; + +union kmem_cache_iter_priv { + struct bpf_iter_kmem_cache it; + struct bpf_iter_kmem_cache_kern kit; +}; + +static void *kmem_cache_iter_seq_start(struct seq_file *seq, loff_t *pos) +{ + loff_t cnt = 0; + bool found = false; + struct kmem_cache *s; + union kmem_cache_iter_priv *p = seq->private; + + mutex_lock(&slab_mutex); + + /* Find an entry at the given position in the slab_caches list instead + * of keeping a reference (of the last visited entry, if any) out of + * slab_mutex. It might miss something if one is deleted in the middle + * while it releases the lock. But it should be rare and there's not + * much we can do about it. + */ + list_for_each_entry(s, &slab_caches, list) { + if (cnt == *pos) { + /* Make sure this entry remains in the list by getting + * a new reference count. Note that boot_cache entries + * have a negative refcount, so don't touch them. + */ + if (s->refcount > 0) + s->refcount++; + found = true; + break; + } + cnt++; + } + mutex_unlock(&slab_mutex); + + if (!found) + s = NULL; + + p->kit.pos = s; + return s; +} + +static void kmem_cache_iter_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_iter__kmem_cache ctx = { + .meta = &meta, + .s = v, + }; + union kmem_cache_iter_priv *p = seq->private; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, true); + if (prog && !ctx.s) + bpf_iter_run_prog(prog, &ctx); + + bpf_iter_kmem_cache_destroy(&p->it); +} + +static void *kmem_cache_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + union kmem_cache_iter_priv *p = seq->private; + + ++*pos; + + return bpf_iter_kmem_cache_next(&p->it); +} + +static int kmem_cache_iter_seq_show(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_iter__kmem_cache ctx = { + .meta = &meta, + .s = v, + }; + struct bpf_prog *prog; + int ret = 0; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + if (prog) + ret = bpf_iter_run_prog(prog, &ctx); + + return ret; +} + +static const struct seq_operations kmem_cache_iter_seq_ops = { + .start = kmem_cache_iter_seq_start, + .next = kmem_cache_iter_seq_next, + .stop = kmem_cache_iter_seq_stop, + .show = kmem_cache_iter_seq_show, +}; + +BTF_ID_LIST_GLOBAL_SINGLE(bpf_kmem_cache_btf_id, struct, kmem_cache) + +static const struct bpf_iter_seq_info kmem_cache_iter_seq_info = { + .seq_ops = &kmem_cache_iter_seq_ops, + .seq_priv_size = sizeof(union kmem_cache_iter_priv), +}; + +static void bpf_iter_kmem_cache_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq) +{ + seq_puts(seq, "kmem_cache iter\n"); +} + +DEFINE_BPF_ITER_FUNC(kmem_cache, struct bpf_iter_meta *meta, + struct kmem_cache *s) + +static struct bpf_iter_reg bpf_kmem_cache_reg_info = { + .target = "kmem_cache", + .feature = BPF_ITER_RESCHED, + .show_fdinfo = bpf_iter_kmem_cache_show_fdinfo, + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__kmem_cache, s), + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, + }, + .seq_info = &kmem_cache_iter_seq_info, +}; + +static int __init bpf_kmem_cache_iter_init(void) +{ + bpf_kmem_cache_reg_info.ctx_arg_info[0].btf_id = bpf_kmem_cache_btf_id[0]; + return bpf_iter_reg_target(&bpf_kmem_cache_reg_info); +} + +late_initcall(bpf_kmem_cache_iter_init); diff --git a/kernel/bpf/link_iter.c b/kernel/bpf/link_iter.c index fec8005a121c..8158e9c1af7b 100644 --- a/kernel/bpf/link_iter.c +++ b/kernel/bpf/link_iter.c @@ -78,8 +78,7 @@ static const struct seq_operations bpf_link_seq_ops = { .show = bpf_link_seq_show, }; -BTF_ID_LIST(btf_bpf_link_id) -BTF_ID(struct, bpf_link) +BTF_ID_LIST_SINGLE(btf_bpf_link_id, struct, bpf_link) static const struct bpf_iter_seq_info bpf_link_seq_info = { .seq_ops = &bpf_link_seq_ops, diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c new file mode 100644 index 000000000000..60db5d655495 --- /dev/null +++ b/kernel/bpf/liveness.c @@ -0,0 +1,753 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf_verifier.h> +#include <linux/hashtable.h> +#include <linux/jhash.h> +#include <linux/slab.h> + +/* + * This file implements live stack slots analysis. After accumulating + * stack usage data, the analysis answers queries about whether a + * particular stack slot may be read by an instruction or any of it's + * successors. This data is consumed by the verifier states caching + * mechanism to decide which stack slots are important when looking for a + * visited state corresponding to the current state. + * + * The analysis is call chain sensitive, meaning that data is collected + * and queried for tuples (call chain, subprogram instruction index). + * Such sensitivity allows identifying if some subprogram call always + * leads to writes in the caller's stack. + * + * The basic idea is as follows: + * - As the verifier accumulates a set of visited states, the analysis instance + * accumulates a conservative estimate of stack slots that can be read + * or must be written for each visited tuple (call chain, instruction index). + * - If several states happen to visit the same instruction with the same + * call chain, stack usage information for the corresponding tuple is joined: + * - "may_read" set represents a union of all possibly read slots + * (any slot in "may_read" set might be read at or after the instruction); + * - "must_write" set represents an intersection of all possibly written slots + * (any slot in "must_write" set is guaranteed to be written by the instruction). + * - The analysis is split into two phases: + * - read and write marks accumulation; + * - read and write marks propagation. + * - The propagation phase is a textbook live variable data flow analysis: + * + * state[cc, i].live_after = U [state[cc, s].live_before for s in bpf_insn_successors(i)] + * state[cc, i].live_before = + * (state[cc, i].live_after / state[cc, i].must_write) U state[i].may_read + * + * Where: + * - `U` stands for set union + * - `/` stands for set difference; + * - `cc` stands for a call chain; + * - `i` and `s` are instruction indexes; + * + * The above equations are computed for each call chain and instruction + * index until state stops changing. + * - Additionally, in order to transfer "must_write" information from a + * subprogram to call instructions invoking this subprogram, + * the "must_write_acc" set is tracked for each (cc, i) tuple. + * A set of stack slots that are guaranteed to be written by this + * instruction or any of its successors (within the subprogram). + * The equation for "must_write_acc" propagation looks as follows: + * + * state[cc, i].must_write_acc = + * ∩ [state[cc, s].must_write_acc for s in bpf_insn_successors(i)] + * U state[cc, i].must_write + * + * (An intersection of all "must_write_acc" for instruction successors + * plus all "must_write" slots for the instruction itself). + * - After the propagation phase completes for a subprogram, information from + * (cc, 0) tuple (subprogram entry) is transferred to the caller's call chain: + * - "must_write_acc" set is intersected with the call site's "must_write" set; + * - "may_read" set is added to the call site's "may_read" set. + * - Any live stack queries must be taken after the propagation phase. + * - Accumulation and propagation phases can be entered multiple times, + * at any point in time: + * - "may_read" set only grows; + * - "must_write" set only shrinks; + * - for each visited verifier state with zero branches, all relevant + * read and write marks are already recorded by the analysis instance. + * + * Technically, the analysis is facilitated by the following data structures: + * - Call chain: for given verifier state, the call chain is a tuple of call + * instruction indexes leading to the current subprogram plus the subprogram + * entry point index. + * - Function instance: for a given call chain, for each instruction in + * the current subprogram, a mapping between instruction index and a + * set of "may_read", "must_write" and other marks accumulated for this + * instruction. + * - A hash table mapping call chains to function instances. + */ + +struct callchain { + u32 callsites[MAX_CALL_FRAMES]; /* instruction pointer for each frame */ + /* cached subprog_info[*].start for functions owning the frames: + * - sp_starts[curframe] used to get insn relative index within current function; + * - sp_starts[0..current-1] used for fast callchain_frame_up(). + */ + u32 sp_starts[MAX_CALL_FRAMES]; + u32 curframe; /* depth of callsites and sp_starts arrays */ +}; + +struct per_frame_masks { + u64 may_read; /* stack slots that may be read by this instruction */ + u64 must_write; /* stack slots written by this instruction */ + u64 must_write_acc; /* stack slots written by this instruction and its successors */ + u64 live_before; /* stack slots that may be read by this insn and its successors */ +}; + +/* + * A function instance created for a specific callchain. + * Encapsulates read and write marks for each instruction in the function. + * Marks are tracked for each frame in the callchain. + */ +struct func_instance { + struct hlist_node hl_node; + struct callchain callchain; + u32 insn_cnt; /* cached number of insns in the function */ + bool updated; + bool must_write_dropped; + /* Per frame, per instruction masks, frames allocated lazily. */ + struct per_frame_masks *frames[MAX_CALL_FRAMES]; + /* For each instruction a flag telling if "must_write" had been initialized for it. */ + bool *must_write_set; +}; + +struct live_stack_query { + struct func_instance *instances[MAX_CALL_FRAMES]; /* valid in range [0..curframe] */ + u32 curframe; + u32 insn_idx; +}; + +struct bpf_liveness { + DECLARE_HASHTABLE(func_instances, 8); /* maps callchain to func_instance */ + struct live_stack_query live_stack_query; /* cache to avoid repetitive ht lookups */ + /* Cached instance corresponding to env->cur_state, avoids per-instruction ht lookup */ + struct func_instance *cur_instance; + /* + * Below fields are used to accumulate stack write marks for instruction at + * @write_insn_idx before submitting the marks to @cur_instance. + */ + u64 write_masks_acc[MAX_CALL_FRAMES]; + u32 write_insn_idx; +}; + +/* Compute callchain corresponding to state @st at depth @frameno */ +static void compute_callchain(struct bpf_verifier_env *env, struct bpf_verifier_state *st, + struct callchain *callchain, u32 frameno) +{ + struct bpf_subprog_info *subprog_info = env->subprog_info; + u32 i; + + memset(callchain, 0, sizeof(*callchain)); + for (i = 0; i <= frameno; i++) { + callchain->sp_starts[i] = subprog_info[st->frame[i]->subprogno].start; + if (i < st->curframe) + callchain->callsites[i] = st->frame[i + 1]->callsite; + } + callchain->curframe = frameno; + callchain->callsites[callchain->curframe] = callchain->sp_starts[callchain->curframe]; +} + +static u32 hash_callchain(struct callchain *callchain) +{ + return jhash2(callchain->callsites, callchain->curframe, 0); +} + +static bool same_callsites(struct callchain *a, struct callchain *b) +{ + int i; + + if (a->curframe != b->curframe) + return false; + for (i = a->curframe; i >= 0; i--) + if (a->callsites[i] != b->callsites[i]) + return false; + return true; +} + +/* + * Find existing or allocate new function instance corresponding to @callchain. + * Instances are accumulated in env->liveness->func_instances and persist + * until the end of the verification process. + */ +static struct func_instance *__lookup_instance(struct bpf_verifier_env *env, + struct callchain *callchain) +{ + struct bpf_liveness *liveness = env->liveness; + struct bpf_subprog_info *subprog; + struct func_instance *result; + u32 subprog_sz, size, key; + + key = hash_callchain(callchain); + hash_for_each_possible(liveness->func_instances, result, hl_node, key) + if (same_callsites(&result->callchain, callchain)) + return result; + + subprog = bpf_find_containing_subprog(env, callchain->sp_starts[callchain->curframe]); + subprog_sz = (subprog + 1)->start - subprog->start; + size = sizeof(struct func_instance); + result = kvzalloc(size, GFP_KERNEL_ACCOUNT); + if (!result) + return ERR_PTR(-ENOMEM); + result->must_write_set = kvcalloc(subprog_sz, sizeof(*result->must_write_set), + GFP_KERNEL_ACCOUNT); + if (!result->must_write_set) { + kvfree(result); + return ERR_PTR(-ENOMEM); + } + memcpy(&result->callchain, callchain, sizeof(*callchain)); + result->insn_cnt = subprog_sz; + hash_add(liveness->func_instances, &result->hl_node, key); + return result; +} + +static struct func_instance *lookup_instance(struct bpf_verifier_env *env, + struct bpf_verifier_state *st, + u32 frameno) +{ + struct callchain callchain; + + compute_callchain(env, st, &callchain, frameno); + return __lookup_instance(env, &callchain); +} + +int bpf_stack_liveness_init(struct bpf_verifier_env *env) +{ + env->liveness = kvzalloc(sizeof(*env->liveness), GFP_KERNEL_ACCOUNT); + if (!env->liveness) + return -ENOMEM; + hash_init(env->liveness->func_instances); + return 0; +} + +void bpf_stack_liveness_free(struct bpf_verifier_env *env) +{ + struct func_instance *instance; + struct hlist_node *tmp; + int bkt, i; + + if (!env->liveness) + return; + hash_for_each_safe(env->liveness->func_instances, bkt, tmp, instance, hl_node) { + for (i = 0; i <= instance->callchain.curframe; i++) + kvfree(instance->frames[i]); + kvfree(instance->must_write_set); + kvfree(instance); + } + kvfree(env->liveness); +} + +/* + * Convert absolute instruction index @insn_idx to an index relative + * to start of the function corresponding to @instance. + */ +static int relative_idx(struct func_instance *instance, u32 insn_idx) +{ + return insn_idx - instance->callchain.sp_starts[instance->callchain.curframe]; +} + +static struct per_frame_masks *get_frame_masks(struct func_instance *instance, + u32 frame, u32 insn_idx) +{ + if (!instance->frames[frame]) + return NULL; + + return &instance->frames[frame][relative_idx(instance, insn_idx)]; +} + +static struct per_frame_masks *alloc_frame_masks(struct bpf_verifier_env *env, + struct func_instance *instance, + u32 frame, u32 insn_idx) +{ + struct per_frame_masks *arr; + + if (!instance->frames[frame]) { + arr = kvcalloc(instance->insn_cnt, sizeof(*arr), GFP_KERNEL_ACCOUNT); + instance->frames[frame] = arr; + if (!arr) + return ERR_PTR(-ENOMEM); + } + return get_frame_masks(instance, frame, insn_idx); +} + +void bpf_reset_live_stack_callchain(struct bpf_verifier_env *env) +{ + env->liveness->cur_instance = NULL; +} + +/* If @env->liveness->cur_instance is null, set it to instance corresponding to @env->cur_state. */ +static int ensure_cur_instance(struct bpf_verifier_env *env) +{ + struct bpf_liveness *liveness = env->liveness; + struct func_instance *instance; + + if (liveness->cur_instance) + return 0; + + instance = lookup_instance(env, env->cur_state, env->cur_state->curframe); + if (IS_ERR(instance)) + return PTR_ERR(instance); + + liveness->cur_instance = instance; + return 0; +} + +/* Accumulate may_read masks for @frame at @insn_idx */ +static int mark_stack_read(struct bpf_verifier_env *env, + struct func_instance *instance, u32 frame, u32 insn_idx, u64 mask) +{ + struct per_frame_masks *masks; + u64 new_may_read; + + masks = alloc_frame_masks(env, instance, frame, insn_idx); + if (IS_ERR(masks)) + return PTR_ERR(masks); + new_may_read = masks->may_read | mask; + if (new_may_read != masks->may_read && + ((new_may_read | masks->live_before) != masks->live_before)) + instance->updated = true; + masks->may_read |= mask; + return 0; +} + +int bpf_mark_stack_read(struct bpf_verifier_env *env, u32 frame, u32 insn_idx, u64 mask) +{ + int err; + + err = ensure_cur_instance(env); + err = err ?: mark_stack_read(env, env->liveness->cur_instance, frame, insn_idx, mask); + return err; +} + +static void reset_stack_write_marks(struct bpf_verifier_env *env, + struct func_instance *instance, u32 insn_idx) +{ + struct bpf_liveness *liveness = env->liveness; + int i; + + liveness->write_insn_idx = insn_idx; + for (i = 0; i <= instance->callchain.curframe; i++) + liveness->write_masks_acc[i] = 0; +} + +int bpf_reset_stack_write_marks(struct bpf_verifier_env *env, u32 insn_idx) +{ + struct bpf_liveness *liveness = env->liveness; + int err; + + err = ensure_cur_instance(env); + if (err) + return err; + + reset_stack_write_marks(env, liveness->cur_instance, insn_idx); + return 0; +} + +void bpf_mark_stack_write(struct bpf_verifier_env *env, u32 frame, u64 mask) +{ + env->liveness->write_masks_acc[frame] |= mask; +} + +static int commit_stack_write_marks(struct bpf_verifier_env *env, + struct func_instance *instance) +{ + struct bpf_liveness *liveness = env->liveness; + u32 idx, frame, curframe, old_must_write; + struct per_frame_masks *masks; + u64 mask; + + if (!instance) + return 0; + + curframe = instance->callchain.curframe; + idx = relative_idx(instance, liveness->write_insn_idx); + for (frame = 0; frame <= curframe; frame++) { + mask = liveness->write_masks_acc[frame]; + /* avoid allocating frames for zero masks */ + if (mask == 0 && !instance->must_write_set[idx]) + continue; + masks = alloc_frame_masks(env, instance, frame, liveness->write_insn_idx); + if (IS_ERR(masks)) + return PTR_ERR(masks); + old_must_write = masks->must_write; + /* + * If instruction at this callchain is seen for a first time, set must_write equal + * to @mask. Otherwise take intersection with the previous value. + */ + if (instance->must_write_set[idx]) + mask &= old_must_write; + if (old_must_write != mask) { + masks->must_write = mask; + instance->updated = true; + } + if (old_must_write & ~mask) + instance->must_write_dropped = true; + } + instance->must_write_set[idx] = true; + liveness->write_insn_idx = 0; + return 0; +} + +/* + * Merge stack writes marks in @env->liveness->write_masks_acc + * with information already in @env->liveness->cur_instance. + */ +int bpf_commit_stack_write_marks(struct bpf_verifier_env *env) +{ + return commit_stack_write_marks(env, env->liveness->cur_instance); +} + +static char *fmt_callchain(struct bpf_verifier_env *env, struct callchain *callchain) +{ + char *buf_end = env->tmp_str_buf + sizeof(env->tmp_str_buf); + char *buf = env->tmp_str_buf; + int i; + + buf += snprintf(buf, buf_end - buf, "("); + for (i = 0; i <= callchain->curframe; i++) + buf += snprintf(buf, buf_end - buf, "%s%d", i ? "," : "", callchain->callsites[i]); + snprintf(buf, buf_end - buf, ")"); + return env->tmp_str_buf; +} + +static void log_mask_change(struct bpf_verifier_env *env, struct callchain *callchain, + char *pfx, u32 frame, u32 insn_idx, u64 old, u64 new) +{ + u64 changed_bits = old ^ new; + u64 new_ones = new & changed_bits; + u64 new_zeros = ~new & changed_bits; + + if (!changed_bits) + return; + bpf_log(&env->log, "%s frame %d insn %d ", fmt_callchain(env, callchain), frame, insn_idx); + if (new_ones) { + bpf_fmt_stack_mask(env->tmp_str_buf, sizeof(env->tmp_str_buf), new_ones); + bpf_log(&env->log, "+%s %s ", pfx, env->tmp_str_buf); + } + if (new_zeros) { + bpf_fmt_stack_mask(env->tmp_str_buf, sizeof(env->tmp_str_buf), new_zeros); + bpf_log(&env->log, "-%s %s", pfx, env->tmp_str_buf); + } + bpf_log(&env->log, "\n"); +} + +int bpf_jmp_offset(struct bpf_insn *insn) +{ + u8 code = insn->code; + + if (code == (BPF_JMP32 | BPF_JA)) + return insn->imm; + return insn->off; +} + +__diag_push(); +__diag_ignore_all("-Woverride-init", "Allow field initialization overrides for opcode_info_tbl"); + +/* + * Returns an array of instructions succ, with succ->items[0], ..., + * succ->items[n-1] with successor instructions, where n=succ->cnt + */ +inline struct bpf_iarray * +bpf_insn_successors(struct bpf_verifier_env *env, u32 idx) +{ + static const struct opcode_info { + bool can_jump; + bool can_fallthrough; + } opcode_info_tbl[256] = { + [0 ... 255] = {.can_jump = false, .can_fallthrough = true}, + #define _J(code, ...) \ + [BPF_JMP | code] = __VA_ARGS__, \ + [BPF_JMP32 | code] = __VA_ARGS__ + + _J(BPF_EXIT, {.can_jump = false, .can_fallthrough = false}), + _J(BPF_JA, {.can_jump = true, .can_fallthrough = false}), + _J(BPF_JEQ, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JNE, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JLT, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JLE, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JGT, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JGE, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JSGT, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JSGE, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JSLT, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JSLE, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JCOND, {.can_jump = true, .can_fallthrough = true}), + _J(BPF_JSET, {.can_jump = true, .can_fallthrough = true}), + #undef _J + }; + struct bpf_prog *prog = env->prog; + struct bpf_insn *insn = &prog->insnsi[idx]; + const struct opcode_info *opcode_info; + struct bpf_iarray *succ, *jt; + int insn_sz; + + jt = env->insn_aux_data[idx].jt; + if (unlikely(jt)) + return jt; + + /* pre-allocated array of size up to 2; reset cnt, as it may have been used already */ + succ = env->succ; + succ->cnt = 0; + + opcode_info = &opcode_info_tbl[BPF_CLASS(insn->code) | BPF_OP(insn->code)]; + insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; + if (opcode_info->can_fallthrough) + succ->items[succ->cnt++] = idx + insn_sz; + + if (opcode_info->can_jump) + succ->items[succ->cnt++] = idx + bpf_jmp_offset(insn) + 1; + + return succ; +} + +__diag_pop(); + +static struct func_instance *get_outer_instance(struct bpf_verifier_env *env, + struct func_instance *instance) +{ + struct callchain callchain = instance->callchain; + + /* Adjust @callchain to represent callchain one frame up */ + callchain.callsites[callchain.curframe] = 0; + callchain.sp_starts[callchain.curframe] = 0; + callchain.curframe--; + callchain.callsites[callchain.curframe] = callchain.sp_starts[callchain.curframe]; + return __lookup_instance(env, &callchain); +} + +static u32 callchain_subprog_start(struct callchain *callchain) +{ + return callchain->sp_starts[callchain->curframe]; +} + +/* + * Transfer @may_read and @must_write_acc marks from the first instruction of @instance, + * to the call instruction in function instance calling @instance. + */ +static int propagate_to_outer_instance(struct bpf_verifier_env *env, + struct func_instance *instance) +{ + struct callchain *callchain = &instance->callchain; + u32 this_subprog_start, callsite, frame; + struct func_instance *outer_instance; + struct per_frame_masks *insn; + int err; + + this_subprog_start = callchain_subprog_start(callchain); + outer_instance = get_outer_instance(env, instance); + if (IS_ERR(outer_instance)) + return PTR_ERR(outer_instance); + callsite = callchain->callsites[callchain->curframe - 1]; + + reset_stack_write_marks(env, outer_instance, callsite); + for (frame = 0; frame < callchain->curframe; frame++) { + insn = get_frame_masks(instance, frame, this_subprog_start); + if (!insn) + continue; + bpf_mark_stack_write(env, frame, insn->must_write_acc); + err = mark_stack_read(env, outer_instance, frame, callsite, insn->live_before); + if (err) + return err; + } + commit_stack_write_marks(env, outer_instance); + return 0; +} + +static inline bool update_insn(struct bpf_verifier_env *env, + struct func_instance *instance, u32 frame, u32 insn_idx) +{ + struct bpf_insn_aux_data *aux = env->insn_aux_data; + u64 new_before, new_after, must_write_acc; + struct per_frame_masks *insn, *succ_insn; + struct bpf_iarray *succ; + u32 s; + bool changed; + + succ = bpf_insn_successors(env, insn_idx); + if (succ->cnt == 0) + return false; + + changed = false; + insn = get_frame_masks(instance, frame, insn_idx); + new_before = 0; + new_after = 0; + /* + * New "must_write_acc" is an intersection of all "must_write_acc" + * of successors plus all "must_write" slots of instruction itself. + */ + must_write_acc = U64_MAX; + for (s = 0; s < succ->cnt; ++s) { + succ_insn = get_frame_masks(instance, frame, succ->items[s]); + new_after |= succ_insn->live_before; + must_write_acc &= succ_insn->must_write_acc; + } + must_write_acc |= insn->must_write; + /* + * New "live_before" is a union of all "live_before" of successors + * minus slots written by instruction plus slots read by instruction. + */ + new_before = (new_after & ~insn->must_write) | insn->may_read; + changed |= new_before != insn->live_before; + changed |= must_write_acc != insn->must_write_acc; + if (unlikely(env->log.level & BPF_LOG_LEVEL2) && + (insn->may_read || insn->must_write || + insn_idx == callchain_subprog_start(&instance->callchain) || + aux[insn_idx].prune_point)) { + log_mask_change(env, &instance->callchain, "live", + frame, insn_idx, insn->live_before, new_before); + log_mask_change(env, &instance->callchain, "written", + frame, insn_idx, insn->must_write_acc, must_write_acc); + } + insn->live_before = new_before; + insn->must_write_acc = must_write_acc; + return changed; +} + +/* Fixed-point computation of @live_before and @must_write_acc marks */ +static int update_instance(struct bpf_verifier_env *env, struct func_instance *instance) +{ + u32 i, frame, po_start, po_end, cnt, this_subprog_start; + struct callchain *callchain = &instance->callchain; + int *insn_postorder = env->cfg.insn_postorder; + struct bpf_subprog_info *subprog; + struct per_frame_masks *insn; + bool changed; + int err; + + this_subprog_start = callchain_subprog_start(callchain); + /* + * If must_write marks were updated must_write_acc needs to be reset + * (to account for the case when new must_write sets became smaller). + */ + if (instance->must_write_dropped) { + for (frame = 0; frame <= callchain->curframe; frame++) { + if (!instance->frames[frame]) + continue; + + for (i = 0; i < instance->insn_cnt; i++) { + insn = get_frame_masks(instance, frame, this_subprog_start + i); + insn->must_write_acc = 0; + } + } + } + + subprog = bpf_find_containing_subprog(env, this_subprog_start); + po_start = subprog->postorder_start; + po_end = (subprog + 1)->postorder_start; + cnt = 0; + /* repeat until fixed point is reached */ + do { + cnt++; + changed = false; + for (frame = 0; frame <= instance->callchain.curframe; frame++) { + if (!instance->frames[frame]) + continue; + + for (i = po_start; i < po_end; i++) + changed |= update_insn(env, instance, frame, insn_postorder[i]); + } + } while (changed); + + if (env->log.level & BPF_LOG_LEVEL2) + bpf_log(&env->log, "%s live stack update done in %d iterations\n", + fmt_callchain(env, callchain), cnt); + + /* transfer marks accumulated for outer frames to outer func instance (caller) */ + if (callchain->curframe > 0) { + err = propagate_to_outer_instance(env, instance); + if (err) + return err; + } + + return 0; +} + +/* + * Prepare all callchains within @env->cur_state for querying. + * This function should be called after each verifier.c:pop_stack() + * and whenever verifier.c:do_check_insn() processes subprogram exit. + * This would guarantee that visited verifier states with zero branches + * have their bpf_mark_stack_{read,write}() effects propagated in + * @env->liveness. + */ +int bpf_update_live_stack(struct bpf_verifier_env *env) +{ + struct func_instance *instance; + int err, frame; + + bpf_reset_live_stack_callchain(env); + for (frame = env->cur_state->curframe; frame >= 0; --frame) { + instance = lookup_instance(env, env->cur_state, frame); + if (IS_ERR(instance)) + return PTR_ERR(instance); + + if (instance->updated) { + err = update_instance(env, instance); + if (err) + return err; + instance->updated = false; + instance->must_write_dropped = false; + } + } + return 0; +} + +static bool is_live_before(struct func_instance *instance, u32 insn_idx, u32 frameno, u32 spi) +{ + struct per_frame_masks *masks; + + masks = get_frame_masks(instance, frameno, insn_idx); + return masks && (masks->live_before & BIT(spi)); +} + +int bpf_live_stack_query_init(struct bpf_verifier_env *env, struct bpf_verifier_state *st) +{ + struct live_stack_query *q = &env->liveness->live_stack_query; + struct func_instance *instance; + u32 frame; + + memset(q, 0, sizeof(*q)); + for (frame = 0; frame <= st->curframe; frame++) { + instance = lookup_instance(env, st, frame); + if (IS_ERR(instance)) + return PTR_ERR(instance); + q->instances[frame] = instance; + } + q->curframe = st->curframe; + q->insn_idx = st->insn_idx; + return 0; +} + +bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 spi) +{ + /* + * Slot is alive if it is read before q->st->insn_idx in current func instance, + * or if for some outer func instance: + * - alive before callsite if callsite calls callback, otherwise + * - alive after callsite + */ + struct live_stack_query *q = &env->liveness->live_stack_query; + struct func_instance *instance, *curframe_instance; + u32 i, callsite; + bool alive; + + curframe_instance = q->instances[q->curframe]; + if (is_live_before(curframe_instance, q->insn_idx, frameno, spi)) + return true; + + for (i = frameno; i < q->curframe; i++) { + callsite = curframe_instance->callchain.callsites[i]; + instance = q->instances[i]; + alive = bpf_calls_callback(env, callsite) + ? is_live_before(instance, callsite, frameno, spi) + : is_live_before(instance, callsite + 1, frameno, spi); + if (alive) + return true; + } + + return false; +} diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index e90d9f63edc5..c93a756e035c 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -141,8 +141,8 @@ static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *key) return &READ_ONCE(storage->buf)->data[0]; } -static int cgroup_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long cgroup_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; @@ -165,7 +165,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, } new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size), - __GFP_ZERO | GFP_NOWAIT | __GFP_NOWARN, + __GFP_ZERO | GFP_NOWAIT, map->numa_node); if (!new) return -ENOMEM; @@ -333,14 +333,14 @@ static void cgroup_storage_map_free(struct bpf_map *_map) struct list_head *storages = &map->list; struct bpf_cgroup_storage *storage, *stmp; - mutex_lock(&cgroup_mutex); + cgroup_lock(); list_for_each_entry_safe(storage, stmp, storages, list_map) { bpf_cgroup_storage_unlink(storage); bpf_cgroup_storage_free(storage); } - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); WARN_ON(!RB_EMPTY_ROOT(&map->root)); WARN_ON(!list_empty(&map->list)); @@ -348,7 +348,7 @@ static void cgroup_storage_map_free(struct bpf_map *_map) bpf_map_area_free(map); } -static int cgroup_storage_delete_elem(struct bpf_map *map, void *key) +static long cgroup_storage_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } @@ -394,17 +394,10 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) return -EINVAL; } else { - u32 int_data; - /* * Key is expected to be u64, which stores the cgroup_inode_id */ - - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) - return -EINVAL; - - int_data = *(u32 *)(key_type + 1); - if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data)) + if (!btf_type_is_i64(key_type)) return -EINVAL; } @@ -431,7 +424,7 @@ static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key, seq_puts(m, ": "); btf_type_seq_show(map->btf, map->btf_value_type_id, &READ_ONCE(storage->buf)->data[0], m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); } else { seq_puts(m, ": {\n"); for_each_possible_cpu(cpu) { @@ -439,13 +432,19 @@ static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key, btf_type_seq_show(map->btf, map->btf_value_type_id, per_cpu_ptr(storage->percpu_buf, cpu), m); - seq_puts(m, "\n"); + seq_putc(m, '\n'); } seq_puts(m, "}\n"); } rcu_read_unlock(); } +static u64 cgroup_storage_map_usage(const struct bpf_map *map) +{ + /* Currently the dynamically allocated elements are not counted. */ + return sizeof(struct bpf_cgroup_storage_map); +} + BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_cgroup_storage_map) const struct bpf_map_ops cgroup_storage_map_ops = { @@ -457,6 +456,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_delete_elem = cgroup_storage_delete_elem, .map_check_btf = cgroup_storage_check_btf, .map_seq_show_elem = cgroup_storage_seq_show_elem, + .map_mem_usage = cgroup_storage_map_usage, .map_btf_id = &cgroup_storage_map_btf_ids[0], }; diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c new file mode 100644 index 000000000000..a0c3b35de2ce --- /dev/null +++ b/kernel/bpf/log.c @@ -0,0 +1,865 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io + */ +#include <uapi/linux/btf.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bpf.h> +#include <linux/bpf_verifier.h> +#include <linux/math64.h> +#include <linux/string.h> + +#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) + +static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) +{ + /* ubuf and len_total should both be specified (or not) together */ + if (!!log->ubuf != !!log->len_total) + return false; + /* log buf without log_level is meaningless */ + if (log->ubuf && log->level == 0) + return false; + if (log->level & ~BPF_LOG_MASK) + return false; + if (log->len_total > UINT_MAX >> 2) + return false; + return true; +} + +int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, + char __user *log_buf, u32 log_size) +{ + log->level = log_level; + log->ubuf = log_buf; + log->len_total = log_size; + + /* log attributes have to be sane */ + if (!bpf_verifier_log_attr_valid(log)) + return -EINVAL; + + return 0; +} + +static void bpf_vlog_update_len_max(struct bpf_verifier_log *log, u32 add_len) +{ + /* add_len includes terminal \0, so no need for +1. */ + u64 len = log->end_pos + add_len; + + /* log->len_max could be larger than our current len due to + * bpf_vlog_reset() calls, so we maintain the max of any length at any + * previous point + */ + if (len > UINT_MAX) + log->len_max = UINT_MAX; + else if (len > log->len_max) + log->len_max = len; +} + +void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, + va_list args) +{ + u64 cur_pos; + u32 new_n, n; + + n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); + + if (log->level == BPF_LOG_KERNEL) { + bool newline = n > 0 && log->kbuf[n - 1] == '\n'; + + pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); + return; + } + + n += 1; /* include terminating zero */ + bpf_vlog_update_len_max(log, n); + + if (log->level & BPF_LOG_FIXED) { + /* check if we have at least something to put into user buf */ + new_n = 0; + if (log->end_pos < log->len_total) { + new_n = min_t(u32, log->len_total - log->end_pos, n); + log->kbuf[new_n - 1] = '\0'; + } + + cur_pos = log->end_pos; + log->end_pos += n - 1; /* don't count terminating '\0' */ + + if (log->ubuf && new_n && + copy_to_user(log->ubuf + cur_pos, log->kbuf, new_n)) + goto fail; + } else { + u64 new_end, new_start; + u32 buf_start, buf_end; + + new_end = log->end_pos + n; + if (new_end - log->start_pos >= log->len_total) + new_start = new_end - log->len_total; + else + new_start = log->start_pos; + + log->start_pos = new_start; + log->end_pos = new_end - 1; /* don't count terminating '\0' */ + + if (!log->ubuf) + return; + + new_n = min(n, log->len_total); + cur_pos = new_end - new_n; + div_u64_rem(cur_pos, log->len_total, &buf_start); + div_u64_rem(new_end, log->len_total, &buf_end); + /* new_end and buf_end are exclusive indices, so if buf_end is + * exactly zero, then it actually points right to the end of + * ubuf and there is no wrap around + */ + if (buf_end == 0) + buf_end = log->len_total; + + /* if buf_start > buf_end, we wrapped around; + * if buf_start == buf_end, then we fill ubuf completely; we + * can't have buf_start == buf_end to mean that there is + * nothing to write, because we always write at least + * something, even if terminal '\0' + */ + if (buf_start < buf_end) { + /* message fits within contiguous chunk of ubuf */ + if (copy_to_user(log->ubuf + buf_start, + log->kbuf + n - new_n, + buf_end - buf_start)) + goto fail; + } else { + /* message wraps around the end of ubuf, copy in two chunks */ + if (copy_to_user(log->ubuf + buf_start, + log->kbuf + n - new_n, + log->len_total - buf_start)) + goto fail; + if (copy_to_user(log->ubuf, + log->kbuf + n - buf_end, + buf_end)) + goto fail; + } + } + + return; +fail: + log->ubuf = NULL; +} + +void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos) +{ + char zero = 0; + u32 pos; + + if (WARN_ON_ONCE(new_pos > log->end_pos)) + return; + + if (!bpf_verifier_log_needed(log) || log->level == BPF_LOG_KERNEL) + return; + + /* if position to which we reset is beyond current log window, + * then we didn't preserve any useful content and should adjust + * start_pos to end up with an empty log (start_pos == end_pos) + */ + log->end_pos = new_pos; + if (log->end_pos < log->start_pos) + log->start_pos = log->end_pos; + + if (!log->ubuf) + return; + + if (log->level & BPF_LOG_FIXED) + pos = log->end_pos + 1; + else + div_u64_rem(new_pos, log->len_total, &pos); + + if (pos < log->len_total && put_user(zero, log->ubuf + pos)) + log->ubuf = NULL; +} + +static void bpf_vlog_reverse_kbuf(char *buf, int len) +{ + int i, j; + + for (i = 0, j = len - 1; i < j; i++, j--) + swap(buf[i], buf[j]); +} + +static int bpf_vlog_reverse_ubuf(struct bpf_verifier_log *log, int start, int end) +{ + /* we split log->kbuf into two equal parts for both ends of array */ + int n = sizeof(log->kbuf) / 2, nn; + char *lbuf = log->kbuf, *rbuf = log->kbuf + n; + + /* Read ubuf's section [start, end) two chunks at a time, from left + * and right side; within each chunk, swap all the bytes; after that + * reverse the order of lbuf and rbuf and write result back to ubuf. + * This way we'll end up with swapped contents of specified + * [start, end) ubuf segment. + */ + while (end - start > 1) { + nn = min(n, (end - start ) / 2); + + if (copy_from_user(lbuf, log->ubuf + start, nn)) + return -EFAULT; + if (copy_from_user(rbuf, log->ubuf + end - nn, nn)) + return -EFAULT; + + bpf_vlog_reverse_kbuf(lbuf, nn); + bpf_vlog_reverse_kbuf(rbuf, nn); + + /* we write lbuf to the right end of ubuf, while rbuf to the + * left one to end up with properly reversed overall ubuf + */ + if (copy_to_user(log->ubuf + start, rbuf, nn)) + return -EFAULT; + if (copy_to_user(log->ubuf + end - nn, lbuf, nn)) + return -EFAULT; + + start += nn; + end -= nn; + } + + return 0; +} + +int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual) +{ + u32 sublen; + int err; + + *log_size_actual = 0; + if (!log || log->level == 0 || log->level == BPF_LOG_KERNEL) + return 0; + + if (!log->ubuf) + goto skip_log_rotate; + /* If we never truncated log, there is nothing to move around. */ + if (log->start_pos == 0) + goto skip_log_rotate; + + /* Otherwise we need to rotate log contents to make it start from the + * buffer beginning and be a continuous zero-terminated string. Note + * that if log->start_pos != 0 then we definitely filled up entire log + * buffer with no gaps, and we just need to shift buffer contents to + * the left by (log->start_pos % log->len_total) bytes. + * + * Unfortunately, user buffer could be huge and we don't want to + * allocate temporary kernel memory of the same size just to shift + * contents in a straightforward fashion. Instead, we'll be clever and + * do in-place array rotation. This is a leetcode-style problem, which + * could be solved by three rotations. + * + * Let's say we have log buffer that has to be shifted left by 7 bytes + * (spaces and vertical bar is just for demonstrative purposes): + * E F G H I J K | A B C D + * + * First, we reverse entire array: + * D C B A | K J I H G F E + * + * Then we rotate first 4 bytes (DCBA) and separately last 7 bytes + * (KJIHGFE), resulting in a properly rotated array: + * A B C D | E F G H I J K + * + * We'll utilize log->kbuf to read user memory chunk by chunk, swap + * bytes, and write them back. Doing it byte-by-byte would be + * unnecessarily inefficient. Altogether we are going to read and + * write each byte twice, for total 4 memory copies between kernel and + * user space. + */ + + /* length of the chopped off part that will be the beginning; + * len(ABCD) in the example above + */ + div_u64_rem(log->start_pos, log->len_total, &sublen); + sublen = log->len_total - sublen; + + err = bpf_vlog_reverse_ubuf(log, 0, log->len_total); + err = err ?: bpf_vlog_reverse_ubuf(log, 0, sublen); + err = err ?: bpf_vlog_reverse_ubuf(log, sublen, log->len_total); + if (err) + log->ubuf = NULL; + +skip_log_rotate: + *log_size_actual = log->len_max; + + /* properly initialized log has either both ubuf!=NULL and len_total>0 + * or ubuf==NULL and len_total==0, so if this condition doesn't hold, + * we got a fault somewhere along the way, so report it back + */ + if (!!log->ubuf != !!log->len_total) + return -EFAULT; + + /* did truncation actually happen? */ + if (log->ubuf && log->len_max > log->len_total) + return -ENOSPC; + + return 0; +} + +/* log_level controls verbosity level of eBPF verifier. + * bpf_verifier_log_write() is used to dump the verification trace to the log, + * so the user can figure out what's wrong with the program + */ +__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, + const char *fmt, ...) +{ + va_list args; + + if (!bpf_verifier_log_needed(&env->log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(&env->log, fmt, args); + va_end(args); +} +EXPORT_SYMBOL_GPL(bpf_verifier_log_write); + +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...) +{ + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} +EXPORT_SYMBOL_GPL(bpf_log); + +static const struct bpf_line_info * +find_linfo(const struct bpf_verifier_env *env, u32 insn_off) +{ + const struct bpf_line_info *linfo; + const struct bpf_prog *prog; + u32 nr_linfo; + int l, r, m; + + prog = env->prog; + nr_linfo = prog->aux->nr_linfo; + + if (!nr_linfo || insn_off >= prog->len) + return NULL; + + linfo = prog->aux->linfo; + /* Loop invariant: linfo[l].insn_off <= insns_off. + * linfo[0].insn_off == 0 which always satisfies above condition. + * Binary search is searching for rightmost linfo entry that satisfies + * the above invariant, giving us the desired record that covers given + * instruction offset. + */ + l = 0; + r = nr_linfo - 1; + while (l < r) { + /* (r - l + 1) / 2 means we break a tie to the right, so if: + * l=1, r=2, linfo[l].insn_off <= insn_off, linfo[r].insn_off > insn_off, + * then m=2, we see that linfo[m].insn_off > insn_off, and so + * r becomes 1 and we exit the loop with correct l==1. + * If the tie was broken to the left, m=1 would end us up in + * an endless loop where l and m stay at 1 and r stays at 2. + */ + m = l + (r - l + 1) / 2; + if (linfo[m].insn_off <= insn_off) + l = m; + else + r = m - 1; + } + + return &linfo[l]; +} + +static const char *ltrim(const char *s) +{ + while (isspace(*s)) + s++; + + return s; +} + +__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, + u32 insn_off, + const char *prefix_fmt, ...) +{ + const struct bpf_line_info *linfo, *prev_linfo; + const struct btf *btf; + const char *s, *fname; + + if (!bpf_verifier_log_needed(&env->log)) + return; + + prev_linfo = env->prev_linfo; + linfo = find_linfo(env, insn_off); + if (!linfo || linfo == prev_linfo) + return; + + /* It often happens that two separate linfo records point to the same + * source code line, but have differing column numbers. Given verifier + * log doesn't emit column information, from user perspective we just + * end up emitting the same source code line twice unnecessarily. + * So instead check that previous and current linfo record point to + * the same file (file_name_offs match) and the same line number, and + * avoid emitting duplicated source code line in such case. + */ + if (prev_linfo && linfo->file_name_off == prev_linfo->file_name_off && + BPF_LINE_INFO_LINE_NUM(linfo->line_col) == BPF_LINE_INFO_LINE_NUM(prev_linfo->line_col)) + return; + + if (prefix_fmt) { + va_list args; + + va_start(args, prefix_fmt); + bpf_verifier_vlog(&env->log, prefix_fmt, args); + va_end(args); + } + + btf = env->prog->aux->btf; + s = ltrim(btf_name_by_offset(btf, linfo->line_off)); + verbose(env, "%s", s); /* source code line */ + + s = btf_name_by_offset(btf, linfo->file_name_off); + /* leave only file name */ + fname = strrchr(s, '/'); + fname = fname ? fname + 1 : s; + verbose(env, " @ %s:%u\n", fname, BPF_LINE_INFO_LINE_NUM(linfo->line_col)); + + env->prev_linfo = linfo; +} + +static const char *btf_type_name(const struct btf *btf, u32 id) +{ + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); +} + +/* string representation of 'enum bpf_reg_type' + * + * Note that reg_type_str() can not appear more than once in a single verbose() + * statement. + */ +const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) +{ + char postfix[16] = {0}, prefix[64] = {0}; + static const char * const str[] = { + [NOT_INIT] = "?", + [SCALAR_VALUE] = "scalar", + [PTR_TO_CTX] = "ctx", + [CONST_PTR_TO_MAP] = "map_ptr", + [PTR_TO_MAP_VALUE] = "map_value", + [PTR_TO_STACK] = "fp", + [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", + [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCK_COMMON] = "sock_common", + [PTR_TO_TCP_SOCK] = "tcp_sock", + [PTR_TO_TP_BUFFER] = "tp_buffer", + [PTR_TO_XDP_SOCK] = "xdp_sock", + [PTR_TO_BTF_ID] = "ptr_", + [PTR_TO_MEM] = "mem", + [PTR_TO_ARENA] = "arena", + [PTR_TO_BUF] = "buf", + [PTR_TO_FUNC] = "func", + [PTR_TO_INSN] = "insn", + [PTR_TO_MAP_KEY] = "map_key", + [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", + }; + + if (type & PTR_MAYBE_NULL) { + if (base_type(type) == PTR_TO_BTF_ID) + strscpy(postfix, "or_null_"); + else + strscpy(postfix, "_or_null"); + } + + snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", + type & MEM_RDONLY ? "rdonly_" : "", + type & MEM_RINGBUF ? "ringbuf_" : "", + type & MEM_USER ? "user_" : "", + type & MEM_PERCPU ? "percpu_" : "", + type & MEM_RCU ? "rcu_" : "", + type & PTR_UNTRUSTED ? "untrusted_" : "", + type & PTR_TRUSTED ? "trusted_" : "" + ); + + snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", + prefix, str[base_type(type)], postfix); + return env->tmp_str_buf; +} + +const char *dynptr_type_str(enum bpf_dynptr_type type) +{ + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + return "local"; + case BPF_DYNPTR_TYPE_RINGBUF: + return "ringbuf"; + case BPF_DYNPTR_TYPE_SKB: + return "skb"; + case BPF_DYNPTR_TYPE_XDP: + return "xdp"; + case BPF_DYNPTR_TYPE_SKB_META: + return "skb_meta"; + case BPF_DYNPTR_TYPE_FILE: + return "file"; + case BPF_DYNPTR_TYPE_INVALID: + return "<invalid>"; + default: + WARN_ONCE(1, "unknown dynptr type %d\n", type); + return "<unknown>"; + } +} + +const char *iter_type_str(const struct btf *btf, u32 btf_id) +{ + if (!btf || btf_id == 0) + return "<invalid>"; + + /* we already validated that type is valid and has conforming name */ + return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1; +} + +const char *iter_state_str(enum bpf_iter_state state) +{ + switch (state) { + case BPF_ITER_STATE_ACTIVE: + return "active"; + case BPF_ITER_STATE_DRAINED: + return "drained"; + case BPF_ITER_STATE_INVALID: + return "<invalid>"; + default: + WARN_ONCE(1, "unknown iter state %d\n", state); + return "<unknown>"; + } +} + +static char slot_type_char[] = { + [STACK_INVALID] = '?', + [STACK_SPILL] = 'r', + [STACK_MISC] = 'm', + [STACK_ZERO] = '0', + [STACK_DYNPTR] = 'd', + [STACK_ITER] = 'i', + [STACK_IRQ_FLAG] = 'f' +}; + +#define UNUM_MAX_DECIMAL U16_MAX +#define SNUM_MAX_DECIMAL S16_MAX +#define SNUM_MIN_DECIMAL S16_MIN + +static bool is_unum_decimal(u64 num) +{ + return num <= UNUM_MAX_DECIMAL; +} + +static bool is_snum_decimal(s64 num) +{ + return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL; +} + +static void verbose_unum(struct bpf_verifier_env *env, u64 num) +{ + if (is_unum_decimal(num)) + verbose(env, "%llu", num); + else + verbose(env, "%#llx", num); +} + +static void verbose_snum(struct bpf_verifier_env *env, s64 num) +{ + if (is_snum_decimal(num)) + verbose(env, "%lld", num); + else + verbose(env, "%#llx", num); +} + +int tnum_strn(char *str, size_t size, struct tnum a) +{ + /* print as a constant, if tnum is fully known */ + if (a.mask == 0) { + if (is_unum_decimal(a.value)) + return snprintf(str, size, "%llu", a.value); + else + return snprintf(str, size, "%#llx", a.value); + } + return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); +} +EXPORT_SYMBOL_GPL(tnum_strn); + +static void print_scalar_ranges(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + const char **sep) +{ + /* For signed ranges, we want to unify 64-bit and 32-bit values in the + * output as much as possible, but there is a bit of a complication. + * If we choose to print values as decimals, this is natural to do, + * because negative 64-bit and 32-bit values >= -S32_MIN have the same + * representation due to sign extension. But if we choose to print + * them in hex format (see is_snum_decimal()), then sign extension is + * misleading. + * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in + * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two + * very different numbers. + * So we avoid sign extension if we choose to print values in hex. + */ + struct { + const char *name; + u64 val; + bool omit; + } minmaxs[] = { + {"smin", reg->smin_value, reg->smin_value == S64_MIN}, + {"smax", reg->smax_value, reg->smax_value == S64_MAX}, + {"umin", reg->umin_value, reg->umin_value == 0}, + {"umax", reg->umax_value, reg->umax_value == U64_MAX}, + {"smin32", + is_snum_decimal((s64)reg->s32_min_value) + ? (s64)reg->s32_min_value + : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN}, + {"smax32", + is_snum_decimal((s64)reg->s32_max_value) + ? (s64)reg->s32_max_value + : (u32)reg->s32_max_value, reg->s32_max_value == S32_MAX}, + {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, + {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, + }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; + bool neg1, neg2; + + for (m1 = &minmaxs[0]; m1 < mend; m1++) { + if (m1->omit) + continue; + + neg1 = m1->name[0] == 's' && (s64)m1->val < 0; + + verbose(env, "%s%s=", *sep, m1->name); + *sep = ","; + + for (m2 = m1 + 2; m2 < mend; m2 += 2) { + if (m2->omit || m2->val != m1->val) + continue; + /* don't mix negatives with positives */ + neg2 = m2->name[0] == 's' && (s64)m2->val < 0; + if (neg2 != neg1) + continue; + m2->omit = true; + verbose(env, "%s=", m2->name); + } + + if (m1->name[0] == 's') + verbose_snum(env, m1->val); + else + verbose_unum(env, m1->val); + } +} + +static bool type_is_map_ptr(enum bpf_reg_type t) { + switch (base_type(t)) { + case CONST_PTR_TO_MAP: + case PTR_TO_MAP_KEY: + case PTR_TO_MAP_VALUE: + return true; + default: + return false; + } +} + +/* + * _a stands for append, was shortened to avoid multiline statements below. + * This macro is used to output a comma separated list of attributes. + */ +#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) + +static void print_reg_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state, + const struct bpf_reg_state *reg) +{ + enum bpf_reg_type t; + const char *sep = ""; + + t = reg->type; + if (t == SCALAR_VALUE && reg->precise) + verbose(env, "P"); + if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) { + verbose_snum(env, reg->var_off.value); + return; + } + + verbose(env, "%s", reg_type_str(env, t)); + if (t == PTR_TO_ARENA) + return; + if (t == PTR_TO_STACK) { + if (state->frameno != reg->frameno) + verbose(env, "[%d]", reg->frameno); + if (tnum_is_const(reg->var_off)) { + verbose_snum(env, reg->var_off.value + reg->off); + return; + } + } + if (base_type(t) == PTR_TO_BTF_ID) + verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); + verbose(env, "("); + if (reg->id) + verbose_a("id=%d", reg->id & ~BPF_ADD_CONST); + if (reg->id & BPF_ADD_CONST) + verbose(env, "%+d", reg->off); + if (reg->ref_obj_id) + verbose_a("ref_obj_id=%d", reg->ref_obj_id); + if (type_is_non_owning_ref(reg->type)) + verbose_a("%s", "non_own_ref"); + if (type_is_map_ptr(t)) { + if (reg->map_ptr->name[0]) + verbose_a("map=%s", reg->map_ptr->name); + verbose_a("ks=%d,vs=%d", + reg->map_ptr->key_size, + reg->map_ptr->value_size); + } + if (t != SCALAR_VALUE && reg->off) { + verbose_a("off="); + verbose_snum(env, reg->off); + } + if (type_is_pkt_pointer(t)) { + verbose_a("r="); + verbose_unum(env, reg->range); + } + if (base_type(t) == PTR_TO_MEM) { + verbose_a("sz="); + verbose_unum(env, reg->mem_size); + } + if (t == CONST_PTR_TO_DYNPTR) + verbose_a("type=%s", dynptr_type_str(reg->dynptr.type)); + if (tnum_is_const(reg->var_off)) { + /* a pointer register with fixed offset */ + if (reg->var_off.value) { + verbose_a("imm="); + verbose_snum(env, reg->var_off.value); + } + } else { + print_scalar_ranges(env, reg, &sep); + if (!tnum_is_unknown(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose_a("var_off=%s", tn_buf); + } + } + verbose(env, ")"); +} + +void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno, bool print_all) +{ + const struct bpf_func_state *state = vstate->frame[frameno]; + const struct bpf_reg_state *reg; + int i; + + if (state->frameno) + verbose(env, " frame%d:", state->frameno); + for (i = 0; i < MAX_BPF_REG; i++) { + reg = &state->regs[i]; + if (reg->type == NOT_INIT) + continue; + if (!print_all && !reg_scratched(env, i)) + continue; + verbose(env, " R%d", i); + verbose(env, "="); + print_reg_state(env, state, reg); + } + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + char types_buf[BPF_REG_SIZE + 1]; + const char *sep = ""; + bool valid = false; + u8 slot_type; + int j; + + if (!print_all && !stack_slot_scratched(env, i)) + continue; + + for (j = 0; j < BPF_REG_SIZE; j++) { + slot_type = state->stack[i].slot_type[j]; + if (slot_type != STACK_INVALID) + valid = true; + types_buf[j] = slot_type_char[slot_type]; + } + types_buf[BPF_REG_SIZE] = 0; + if (!valid) + continue; + + reg = &state->stack[i].spilled_ptr; + switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { + case STACK_SPILL: + /* print MISC/ZERO/INVALID slots above subreg spill */ + for (j = 0; j < BPF_REG_SIZE; j++) + if (state->stack[i].slot_type[j] == STACK_SPILL) + break; + types_buf[j] = '\0'; + + verbose(env, " fp%d=%s", (-i - 1) * BPF_REG_SIZE, types_buf); + print_reg_state(env, state, reg); + break; + case STACK_DYNPTR: + /* skip to main dynptr slot */ + i += BPF_DYNPTR_NR_SLOTS - 1; + reg = &state->stack[i].spilled_ptr; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type)); + if (reg->id) + verbose_a("id=%d", reg->id); + if (reg->ref_obj_id) + verbose_a("ref_id=%d", reg->ref_obj_id); + if (reg->dynptr_id) + verbose_a("dynptr_id=%d", reg->dynptr_id); + verbose(env, ")"); + break; + case STACK_ITER: + /* only main slot has ref_obj_id set; skip others */ + if (!reg->ref_obj_id) + continue; + + verbose(env, " fp%d=iter_%s(ref_id=%d,state=%s,depth=%u)", + (-i - 1) * BPF_REG_SIZE, + iter_type_str(reg->iter.btf, reg->iter.btf_id), + reg->ref_obj_id, iter_state_str(reg->iter.state), + reg->iter.depth); + break; + case STACK_MISC: + case STACK_ZERO: + default: + verbose(env, " fp%d=%s", (-i - 1) * BPF_REG_SIZE, types_buf); + break; + } + } + if (vstate->acquired_refs && vstate->refs[0].id) { + verbose(env, " refs=%d", vstate->refs[0].id); + for (i = 1; i < vstate->acquired_refs; i++) + if (vstate->refs[i].id) + verbose(env, ",%d", vstate->refs[i].id); + } + if (state->in_callback_fn) + verbose(env, " cb"); + if (state->in_async_callback_fn) + verbose(env, " async_cb"); + verbose(env, "\n"); + if (!print_all) + mark_verifier_state_clean(env); +} + +static inline u32 vlog_alignment(u32 pos) +{ + return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), + BPF_LOG_MIN_ALIGNMENT) - pos - 1; +} + +void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno) +{ + if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { + /* remove new line character */ + bpf_vlog_reset(&env->log, env->prev_log_pos - 1); + verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' '); + } else { + verbose(env, "%d:", env->insn_idx); + } + print_verifier_state(env, vstate, frameno, false); +} diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index d833496e9e42..be66d7e520e0 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -15,6 +15,8 @@ #include <net/ipv6.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> +#include <asm/rqspinlock.h> +#include <linux/bpf_mem_alloc.h> /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) @@ -22,7 +24,6 @@ struct lpm_trie_node; struct lpm_trie_node { - struct rcu_head rcu; struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; @@ -32,10 +33,11 @@ struct lpm_trie_node { struct lpm_trie { struct bpf_map map; struct lpm_trie_node __rcu *root; + struct bpf_mem_alloc ma; size_t n_entries; size_t max_prefixlen; size_t data_size; - spinlock_t lock; + rqspinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to @@ -155,22 +157,23 @@ 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 *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; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); - BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); + BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key_u8, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) @@ -224,12 +227,22 @@ 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) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; + + if (key->prefixlen > trie->max_prefixlen) + return NULL; /* Start walking the trie from the root node ... */ @@ -242,7 +255,7 @@ 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; @@ -276,17 +289,13 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) return found->data + trie->data_size; } -static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, +static struct lpm_trie_node *lpm_trie_node_alloc(struct lpm_trie *trie, const void *value) { struct lpm_trie_node *node; - size_t size = sizeof(struct lpm_trie_node) + trie->data_size; - if (value) - size += trie->map.value_size; + node = bpf_mem_cache_alloc(&trie->ma); - node = bpf_map_kmalloc_node(&trie->map, size, GFP_NOWAIT | __GFP_NOWARN, - trie->map.numa_node); if (!node) return NULL; @@ -299,14 +308,25 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, return node; } +static int trie_check_add_elem(struct lpm_trie *trie, u64 flags) +{ + if (flags == BPF_EXIST) + return -ENOENT; + if (trie->n_entries == trie->map.max_entries) + return -ENOSPC; + trie->n_entries++; + return 0; +} + /* Called from syscall or from eBPF program */ -static int trie_update_elem(struct bpf_map *map, - void *_key, void *value, u64 flags) +static long trie_update_elem(struct bpf_map *map, + void *_key, void *value, u64 flags) { 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 *node, *im_node, *new_node; + struct lpm_trie_node *free_node = NULL; struct lpm_trie_node __rcu **slot; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; @@ -318,22 +338,14 @@ static int trie_update_elem(struct bpf_map *map, if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - spin_lock_irqsave(&trie->lock, irq_flags); - /* Allocate and fill a new node */ - - if (trie->n_entries == trie->map.max_entries) { - ret = -ENOSPC; - goto out; - } - new_node = lpm_trie_node_alloc(trie, value); - if (!new_node) { - ret = -ENOMEM; - goto out; - } + if (!new_node) + return -ENOMEM; - trie->n_entries++; + ret = raw_res_spin_lock_irqsave(&trie->lock, irq_flags); + if (ret) + goto out_free; new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); @@ -347,13 +359,11 @@ static int trie_update_elem(struct bpf_map *map, */ slot = &trie->root; - while ((node = rcu_dereference_protected(*slot, - lockdep_is_held(&trie->lock)))) { + while ((node = rcu_dereference(*slot))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || - node->prefixlen == key->prefixlen || - node->prefixlen == trie->max_prefixlen) + node->prefixlen == key->prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); @@ -364,6 +374,10 @@ static int trie_update_elem(struct bpf_map *map, * simply assign the @new_node to that slot and be done. */ if (!node) { + ret = trie_check_add_elem(trie, flags); + if (ret) + goto out; + rcu_assign_pointer(*slot, new_node); goto out; } @@ -372,18 +386,30 @@ static int trie_update_elem(struct bpf_map *map, * which already has the correct data array set. */ if (node->prefixlen == matchlen) { + if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) { + if (flags == BPF_NOEXIST) { + ret = -EEXIST; + goto out; + } + } else { + ret = trie_check_add_elem(trie, flags); + if (ret) + goto out; + } + new_node->child[0] = node->child[0]; new_node->child[1] = node->child[1]; - if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) - trie->n_entries--; - rcu_assign_pointer(*slot, new_node); - kfree_rcu(node, rcu); + free_node = node; goto out; } + ret = trie_check_add_elem(trie, flags); + if (ret) + goto out; + /* If the new node matches the prefix completely, it must be inserted * as an ancestor. Simply insert it between @node and *@slot. */ @@ -396,6 +422,7 @@ static int trie_update_elem(struct bpf_map *map, im_node = lpm_trie_node_alloc(trie, NULL); if (!im_node) { + trie->n_entries--; ret = -ENOMEM; goto out; } @@ -417,24 +444,21 @@ static int trie_update_elem(struct bpf_map *map, rcu_assign_pointer(*slot, im_node); out: - if (ret) { - if (new_node) - trie->n_entries--; - - kfree(new_node); - kfree(im_node); - } - - spin_unlock_irqrestore(&trie->lock, irq_flags); + raw_res_spin_unlock_irqrestore(&trie->lock, irq_flags); +out_free: + if (ret) + bpf_mem_cache_free(&trie->ma, new_node); + bpf_mem_cache_free_rcu(&trie->ma, free_node); return ret; } /* Called from syscall or from eBPF program */ -static int trie_delete_elem(struct bpf_map *map, void *_key) +static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key; + 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; unsigned long irq_flags; @@ -445,7 +469,9 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - spin_lock_irqsave(&trie->lock, irq_flags); + ret = raw_res_spin_lock_irqsave(&trie->lock, irq_flags); + if (ret) + return ret; /* Walk the tree looking for an exact key/length match and keeping * track of the path we traverse. We will need to know the node @@ -456,8 +482,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) trim = &trie->root; trim2 = trim; parent = NULL; - while ((node = rcu_dereference_protected( - *trim, lockdep_is_held(&trie->lock)))) { + while ((node = rcu_dereference(*trim))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || @@ -503,8 +528,8 @@ static int 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; } @@ -518,10 +543,13 @@ static int 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); + raw_res_spin_unlock_irqrestore(&trie->lock, irq_flags); + + bpf_mem_cache_free_rcu(&trie->ma, free_parent); + bpf_mem_cache_free_rcu(&trie->ma, free_node); return ret; } @@ -533,7 +561,7 @@ out: sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 -#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X)) +#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key_u8) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) @@ -543,9 +571,8 @@ out: static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; - - if (!bpf_capable()) - return ERR_PTR(-EPERM); + size_t leaf_size; + int err; /* check sanity of attributes */ if (attr->max_entries == 0 || @@ -565,12 +592,22 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - - offsetof(struct bpf_lpm_trie_key, data); + offsetof(struct bpf_lpm_trie_key_u8, data); trie->max_prefixlen = trie->data_size * 8; - spin_lock_init(&trie->lock); + raw_res_spin_lock_init(&trie->lock); + /* Allocate intermediate and leaf nodes from the same allocator */ + leaf_size = sizeof(struct lpm_trie_node) + trie->data_size + + trie->map.value_size; + err = bpf_mem_alloc_init(&trie->ma, leaf_size, false); + if (err) + goto free_out; return &trie->map; + +free_out: + bpf_map_area_free(trie); + return ERR_PTR(err); } static void trie_free(struct bpf_map *map) @@ -602,13 +639,17 @@ static void trie_free(struct bpf_map *map) continue; } - kfree(node); + /* No bpf program may access the map, so freeing the + * node without waiting for the extra RCU GP. + */ + bpf_mem_cache_raw_free(node); RCU_INIT_POINTER(*slot, NULL); break; } } out: + bpf_mem_alloc_destroy(&trie->ma); bpf_map_area_free(trie); } @@ -616,11 +657,11 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; + struct bpf_lpm_trie_key_u8 *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; - size_t matchlen; + size_t matchlen = 0; /* The get_next_key follows postorder. For the 4 node example in * the top of this file, the trie_get_next_key() returns the following @@ -642,7 +683,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; - node_stack = kmalloc_array(trie->max_prefixlen, + node_stack = kmalloc_array(trie->max_prefixlen + 1, sizeof(struct lpm_trie_node *), GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) @@ -659,7 +700,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } - if (!node || node->prefixlen != key->prefixlen || + if (!node || node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) goto find_leftmost; @@ -703,7 +744,7 @@ find_leftmost: } do_copy: next_key->prefixlen = next_node->prefixlen; - memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), + memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key_u8, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); @@ -715,11 +756,21 @@ static int trie_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) { - /* Keys must have struct bpf_lpm_trie_key embedded. */ + /* Keys must have struct bpf_lpm_trie_key_u8 embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } +static u64 trie_mem_usage(const struct bpf_map *map) +{ + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + u64 elem_size; + + elem_size = sizeof(struct lpm_trie_node) + trie->data_size + + trie->map.value_size; + return elem_size * READ_ONCE(trie->n_entries); +} + BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie) const struct bpf_map_ops trie_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -733,5 +784,6 @@ const struct bpf_map_ops trie_map_ops = { .map_update_batch = generic_map_update_batch, .map_delete_batch = generic_map_delete_batch, .map_check_btf = trie_check_btf, + .map_mem_usage = trie_mem_usage, .map_btf_id = &trie_map_btf_ids[0], }; diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 38136ec4e095..645bd30bc9a9 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -11,35 +11,27 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) { struct bpf_map *inner_map, *inner_map_meta; u32 inner_map_meta_size; - struct fd f; - int ret; + CLASS(fd, f)(inner_map_ufd); - f = fdget(inner_map_ufd); inner_map = __bpf_map_get(f); if (IS_ERR(inner_map)) return inner_map; /* Does not support >1 level map-in-map */ - if (inner_map->inner_map_meta) { - ret = -EINVAL; - goto put; - } + if (inner_map->inner_map_meta) + return ERR_PTR(-EINVAL); - if (!inner_map->ops->map_meta_equal) { - ret = -ENOTSUPP; - goto put; - } + if (!inner_map->ops->map_meta_equal) + return ERR_PTR(-ENOTSUPP); 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); - if (!inner_map_meta) { - ret = -ENOMEM; - goto put; - } + if (!inner_map_meta) + return ERR_PTR(-ENOMEM); inner_map_meta->map_type = inner_map->map_type; inner_map_meta->key_size = inner_map->key_size; @@ -53,20 +45,9 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) * invalid/empty/valid, but ERR_PTR in case of errors. During * equality NULL or IS_ERR is equivalent. */ - ret = PTR_ERR(inner_map_meta->record); - goto free; - } - if (inner_map_meta->record) { - struct btf_field_offs *field_offs; - /* If btf_record is !IS_ERR_OR_NULL, then field_offs is always - * valid. - */ - field_offs = kmemdup(inner_map->field_offs, sizeof(*inner_map->field_offs), GFP_KERNEL | __GFP_NOWARN); - if (!field_offs) { - ret = -ENOMEM; - goto free_rec; - } - inner_map_meta->field_offs = field_offs; + struct bpf_map *ret = ERR_CAST(inner_map_meta->record); + kfree(inner_map_meta); + return ret; } /* Note: We must use the same BTF, as we also used btf_record_dup above * which relies on BTF being same for both maps, as some members like @@ -80,26 +61,20 @@ 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); + + inner_array_meta->index_mask = inner_array->index_mask; + inner_array_meta->elem_size = inner_array->elem_size; inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1; - container_of(inner_map_meta, struct bpf_array, map)->index_mask = - container_of(inner_map, struct bpf_array, map)->index_mask; } - - fdput(f); return inner_map_meta; -free_rec: - btf_record_free(inner_map_meta->record); -free: - kfree(inner_map_meta); -put: - fdput(f); - return ERR_PTR(ret); } void bpf_map_meta_free(struct bpf_map *map_meta) { - kfree(map_meta->field_offs); bpf_map_free_record(map_meta); btf_put(map_meta->btf); kfree(map_meta); @@ -121,9 +96,8 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, int ufd) { struct bpf_map *inner_map, *inner_map_meta; - struct fd f; + CLASS(fd, f)(ufd); - f = fdget(ufd); inner_map = __bpf_map_get(f); if (IS_ERR(inner_map)) return inner_map; @@ -134,16 +108,24 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, else inner_map = ERR_PTR(-EINVAL); - fdput(f); return inner_map; } -void bpf_map_fd_put_ptr(void *ptr) +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { - /* ptr->ops->map_free() has to go through one - * rcu grace period by itself. + struct bpf_map *inner_map = ptr; + + /* Defer the freeing of inner map according to the sleepable attribute + * of bpf program which owns the outer map, so unnecessary waiting for + * RCU tasks trace grace period can be avoided. */ - bpf_map_put(ptr); + if (need_defer) { + if (atomic64_read(&map->sleepable_refcnt)) + WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + else + WRITE_ONCE(inner_map->free_after_rcu_gp, true); + } + bpf_map_put(inner_map); } u32 bpf_map_fd_sys_lookup_elem(void *ptr) diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h index bcb7534afb3c..7d61602354de 100644 --- a/kernel/bpf/map_in_map.h +++ b/kernel/bpf/map_in_map.h @@ -13,7 +13,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd); void bpf_map_meta_free(struct bpf_map *map_meta); void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file, int ufd); -void bpf_map_fd_put_ptr(void *ptr); +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer); u32 bpf_map_fd_sys_lookup_elem(void *ptr); #endif diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index b0fa190b0979..9575314f40a6 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -78,8 +78,7 @@ static const struct seq_operations bpf_map_seq_ops = { .show = bpf_map_seq_show, }; -BTF_ID_LIST(btf_bpf_map_id) -BTF_ID(struct, bpf_map) +BTF_ID_LIST_GLOBAL_SINGLE(btf_bpf_map_id, struct, bpf_map) static const struct bpf_iter_seq_info bpf_map_seq_info = { .seq_ops = &bpf_map_seq_ops, @@ -93,7 +92,7 @@ static struct bpf_iter_reg bpf_map_reg_info = { .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_map, map), - PTR_TO_BTF_ID_OR_NULL }, + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .seq_info = &bpf_map_seq_info, }; @@ -193,3 +192,38 @@ static int __init bpf_map_iter_init(void) } late_initcall(bpf_map_iter_init); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map) +{ + s64 *pcount; + s64 ret = 0; + int cpu; + + if (!map || !map->elem_count) + return 0; + + for_each_possible_cpu(cpu) { + pcount = per_cpu_ptr(map->elem_count, cpu); + ret += READ_ONCE(*pcount); + } + return ret; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(bpf_map_iter_kfunc_ids) +BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS) +BTF_KFUNCS_END(bpf_map_iter_kfunc_ids) + +static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = { + .owner = THIS_MODULE, + .set = &bpf_map_iter_kfunc_ids, +}; + +static int init_subsystem(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_map_iter_kfunc_set); +} +late_initcall(init_subsystem); diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index ebcc3dd0fa19..bd45dda9dc35 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -35,6 +35,8 @@ */ #define LLIST_NODE_SZ sizeof(struct llist_node) +#define BPF_MEM_ALLOC_SIZE_MAX 4096 + /* similar to kmalloc, but sizeof == 8 bucket is gone */ static u8 size_index[24] __ro_after_init = { 3, /* 8 */ @@ -65,13 +67,13 @@ static u8 size_index[24] __ro_after_init = { static int bpf_mem_cache_idx(size_t size) { - if (!size || size > 4096) + if (!size || size > BPF_MEM_ALLOC_SIZE_MAX) return -1; if (size <= 192) return size_index[(size - 1) / 8] - 1; - return fls(size - 1) - 1; + return fls(size - 1) - 2; } #define NUM_CACHES 11 @@ -98,17 +100,31 @@ struct bpf_mem_cache { int free_cnt; int low_watermark, high_watermark, batch; int percpu_size; + bool draining; + struct bpf_mem_cache *tgt; - struct rcu_head rcu; + /* list of objects to be freed after RCU GP */ struct llist_head free_by_rcu; + struct llist_node *free_by_rcu_tail; struct llist_head waiting_for_gp; + struct llist_node *waiting_for_gp_tail; + struct rcu_head rcu; atomic_t call_rcu_in_progress; + struct llist_head free_llist_extra_rcu; + + /* list of objects to be freed after RCU tasks trace GP */ + struct llist_head free_by_rcu_ttrace; + struct llist_head waiting_for_gp_ttrace; + struct rcu_head rcu_ttrace; + atomic_t call_rcu_ttrace_in_progress; }; struct bpf_mem_caches { struct bpf_mem_cache cache[NUM_CACHES]; }; +static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; + static struct llist_node notrace *__llist_del_first(struct llist_head *head) { struct llist_node *entry, *next; @@ -121,18 +137,11 @@ static struct llist_node notrace *__llist_del_first(struct llist_head *head) return entry; } -static void *__alloc(struct bpf_mem_cache *c, int node) +static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags) { - /* Allocate, but don't deplete atomic reserves that typical - * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc - * will allocate from the current numa node which is what we - * want here. - */ - gfp_t flags = GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT; - if (c->percpu_size) { - void **obj = kmalloc_node(c->percpu_size, flags, node); - void *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags); + void __percpu **obj = kmalloc_node(c->percpu_size, flags, node); + void __percpu *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags); if (!obj || !pptr) { free_percpu(pptr); @@ -143,96 +152,132 @@ static void *__alloc(struct bpf_mem_cache *c, int node) return obj; } - return kmalloc_node(c->unit_size, flags, node); + return kmalloc_node(c->unit_size, flags | __GFP_ZERO, node); } static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c) { -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (c->objcg) return get_mem_cgroup_from_objcg(c->objcg); -#endif - -#ifdef CONFIG_MEMCG return root_mem_cgroup; #else return NULL; #endif } +static void inc_active(struct bpf_mem_cache *c, unsigned long *flags) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + /* In RT irq_work runs in per-cpu kthread, so disable + * interrupts to avoid preemption and interrupts and + * reduce the chance of bpf prog executing on this cpu + * when active counter is busy. + */ + local_irq_save(*flags); + /* alloc_bulk runs from irq_work which will not preempt a bpf + * program that does unit_alloc/unit_free since IRQs are + * disabled there. There is no race to increment 'active' + * counter. It protects free_llist from corruption in case NMI + * bpf prog preempted this loop. + */ + WARN_ON_ONCE(local_inc_return(&c->active) != 1); +} + +static void dec_active(struct bpf_mem_cache *c, unsigned long *flags) +{ + local_dec(&c->active); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_restore(*flags); +} + +static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj) +{ + unsigned long flags; + + inc_active(c, &flags); + __llist_add(obj, &c->free_llist); + c->free_cnt++; + dec_active(c, &flags); +} + /* Mostly runs from irq_work except __init phase. */ -static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node) +static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic) { struct mem_cgroup *memcg = NULL, *old_memcg; - unsigned long flags; + gfp_t gfp; void *obj; int i; - memcg = get_memcg(c); - old_memcg = set_active_memcg(memcg); + gfp = __GFP_NOWARN | __GFP_ACCOUNT; + gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL; + for (i = 0; i < cnt; i++) { /* - * free_by_rcu is only manipulated by irq work refill_work(). - * IRQ works on the same CPU are called sequentially, so it is - * safe to use __llist_del_first() here. If alloc_bulk() is - * invoked by the initial prefill, there will be no running - * refill_work(), so __llist_del_first() is fine as well. - * - * In most cases, objects on free_by_rcu are from the same CPU. - * If some objects come from other CPUs, it doesn't incur any - * harm because NUMA_NO_NODE means the preference for current - * numa node and it is not a guarantee. + * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is + * done only by one CPU == current CPU. Other CPUs might + * llist_add() and llist_del_all() in parallel. */ - obj = __llist_del_first(&c->free_by_rcu); - if (!obj) { - obj = __alloc(c, node); - if (!obj) - break; - } - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - /* In RT irq_work runs in per-cpu kthread, so disable - * interrupts to avoid preemption and interrupts and - * reduce the chance of bpf prog executing on this cpu - * when active counter is busy. - */ - local_irq_save(flags); - /* alloc_bulk runs from irq_work which will not preempt a bpf - * program that does unit_alloc/unit_free since IRQs are - * disabled there. There is no race to increment 'active' - * counter. It protects free_llist from corruption in case NMI - * bpf prog preempted this loop. + obj = llist_del_first(&c->free_by_rcu_ttrace); + if (!obj) + break; + add_obj_to_free_list(c, obj); + } + if (i >= cnt) + return; + + for (; i < cnt; i++) { + obj = llist_del_first(&c->waiting_for_gp_ttrace); + if (!obj) + break; + add_obj_to_free_list(c, obj); + } + if (i >= cnt) + return; + + memcg = get_memcg(c); + old_memcg = set_active_memcg(memcg); + for (; i < cnt; i++) { + /* Allocate, but don't deplete atomic reserves that typical + * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc + * will allocate from the current numa node which is what we + * want here. */ - WARN_ON_ONCE(local_inc_return(&c->active) != 1); - __llist_add(obj, &c->free_llist); - c->free_cnt++; - local_dec(&c->active); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - local_irq_restore(flags); + obj = __alloc(c, node, gfp); + if (!obj) + break; + add_obj_to_free_list(c, obj); } set_active_memcg(old_memcg); mem_cgroup_put(memcg); } -static void free_one(struct bpf_mem_cache *c, void *obj) +static void free_one(void *obj, bool percpu) { - if (c->percpu_size) { - free_percpu(((void **)obj)[1]); - kfree(obj); - return; - } + if (percpu) + free_percpu(((void __percpu **)obj)[1]); kfree(obj); } -static void __free_rcu(struct rcu_head *head) +static int free_all(struct llist_node *llnode, bool percpu) { - struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu); - struct llist_node *llnode = llist_del_all(&c->waiting_for_gp); struct llist_node *pos, *t; + int cnt = 0; - llist_for_each_safe(pos, t, llnode) - free_one(c, pos); - atomic_set(&c->call_rcu_in_progress, 0); + llist_for_each_safe(pos, t, llnode) { + free_one(pos, percpu); + cnt++; + } + return cnt; +} + +static void __free_rcu(struct rcu_head *head) +{ + struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace); + + free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); + atomic_set(&c->call_rcu_ttrace_in_progress, 0); } static void __free_rcu_tasks_trace(struct rcu_head *head) @@ -251,60 +296,132 @@ static void enque_to_free(struct bpf_mem_cache *c, void *obj) struct llist_node *llnode = obj; /* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work. - * Nothing races to add to free_by_rcu list. + * Nothing races to add to free_by_rcu_ttrace list. */ - __llist_add(llnode, &c->free_by_rcu); + llist_add(llnode, &c->free_by_rcu_ttrace); } -static void do_call_rcu(struct bpf_mem_cache *c) +static void do_call_rcu_ttrace(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; - if (atomic_xchg(&c->call_rcu_in_progress, 1)) + if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { + if (unlikely(READ_ONCE(c->draining))) { + llnode = llist_del_all(&c->free_by_rcu_ttrace); + free_all(llnode, !!c->percpu_size); + } return; + } + + WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); + llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace)) + llist_add(llnode, &c->waiting_for_gp_ttrace); + + if (unlikely(READ_ONCE(c->draining))) { + __free_rcu(&c->rcu_ttrace); + return; + } - WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); - llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu)) - /* There is no concurrent __llist_add(waiting_for_gp) access. - * It doesn't race with llist_del_all either. - * But there could be two concurrent llist_del_all(waiting_for_gp): - * from __free_rcu() and from drain_mem_cache(). - */ - __llist_add(llnode, &c->waiting_for_gp); /* Use call_rcu_tasks_trace() to wait for sleepable progs to finish. * If RCU Tasks Trace grace period implies RCU grace period, free * these elements directly, else use call_rcu() to wait for normal * progs to finish and finally do free_one() on each element. */ - call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace); + call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu_tasks_trace); } static void free_bulk(struct bpf_mem_cache *c) { + struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode, *t; unsigned long flags; int cnt; + WARN_ON_ONCE(tgt->unit_size != c->unit_size); + WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); + do { - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - local_irq_save(flags); - WARN_ON_ONCE(local_inc_return(&c->active) != 1); + inc_active(c, &flags); llnode = __llist_del_first(&c->free_llist); if (llnode) cnt = --c->free_cnt; else cnt = 0; - local_dec(&c->active); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - local_irq_restore(flags); + dec_active(c, &flags); if (llnode) - enque_to_free(c, llnode); + enque_to_free(tgt, llnode); } while (cnt > (c->high_watermark + c->low_watermark) / 2); /* and drain free_llist_extra */ llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra)) - enque_to_free(c, llnode); - do_call_rcu(c); + enque_to_free(tgt, llnode); + do_call_rcu_ttrace(tgt); +} + +static void __free_by_rcu(struct rcu_head *head) +{ + struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu); + struct bpf_mem_cache *tgt = c->tgt; + struct llist_node *llnode; + + WARN_ON_ONCE(tgt->unit_size != c->unit_size); + WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); + + llnode = llist_del_all(&c->waiting_for_gp); + if (!llnode) + goto out; + + llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace); + + /* Objects went through regular RCU GP. Send them to RCU tasks trace */ + do_call_rcu_ttrace(tgt); +out: + atomic_set(&c->call_rcu_in_progress, 0); +} + +static void check_free_by_rcu(struct bpf_mem_cache *c) +{ + struct llist_node *llnode, *t; + unsigned long flags; + + /* drain free_llist_extra_rcu */ + if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) { + inc_active(c, &flags); + llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu)) + if (__llist_add(llnode, &c->free_by_rcu)) + c->free_by_rcu_tail = llnode; + dec_active(c, &flags); + } + + if (llist_empty(&c->free_by_rcu)) + return; + + if (atomic_xchg(&c->call_rcu_in_progress, 1)) { + /* + * Instead of kmalloc-ing new rcu_head and triggering 10k + * call_rcu() to hit rcutree.qhimark and force RCU to notice + * the overload just ask RCU to hurry up. There could be many + * objects in free_by_rcu list. + * This hint reduces memory consumption for an artificial + * benchmark from 2 Gbyte to 150 Mbyte. + */ + rcu_request_urgent_qs_task(current); + return; + } + + WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); + + inc_active(c, &flags); + WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu)); + c->waiting_for_gp_tail = c->free_by_rcu_tail; + dec_active(c, &flags); + + if (unlikely(READ_ONCE(c->draining))) { + free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size); + atomic_set(&c->call_rcu_in_progress, 0); + } else { + call_rcu_hurry(&c->rcu, __free_by_rcu); + } } static void bpf_mem_refill(struct irq_work *work) @@ -318,9 +435,11 @@ static void bpf_mem_refill(struct irq_work *work) /* irq_work runs on this cpu and kmalloc will allocate * from the current numa node which is what we want here. */ - alloc_bulk(c, c->batch, NUMA_NO_NODE); + alloc_bulk(c, c->batch, NUMA_NO_NODE, true); else if (cnt > c->high_watermark) free_bulk(c); + + check_free_by_rcu(c); } static void notrace irq_work_raise(struct bpf_mem_cache *c) @@ -341,12 +460,17 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c) * consume ~ 11 Kbyte per cpu. * Typical case will be between 11K and 116K closer to 11K. * bpf progs can and should share bpf_mem_cache when possible. + * + * Percpu allocation is typically rare. To avoid potential unnecessary large + * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1. */ - -static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) +static void init_refill_work(struct bpf_mem_cache *c) { init_irq_work(&c->refill_work, bpf_mem_refill); - if (c->unit_size <= 256) { + if (c->percpu_size) { + c->low_watermark = 1; + c->high_watermark = 3; + } else if (c->unit_size <= 256) { c->low_watermark = 32; c->high_watermark = 96; } else { @@ -359,12 +483,20 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) c->high_watermark = max(96 * 256 / c->unit_size, 3); } c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1); +} - /* To avoid consuming memory assume that 1st run of bpf - * prog won't be doing more than 4 map_update_elem from - * irq disabled region +static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) +{ + int cnt = 1; + + /* To avoid consuming memory, for non-percpu allocation, assume that + * 1st run of bpf prog won't be doing more than 4 map_update_elem from + * irq disabled region if unit size is less than or equal to 256. + * For all other cases, let us just do one allocation. */ - alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu)); + if (!c->percpu_size && c->unit_size <= 256) + cnt = 4; + alloc_bulk(c, cnt, cpu_to_node(cpu), false); } /* When size != 0 bpf_mem_cache for each cpu. @@ -376,84 +508,179 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { - static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; - struct bpf_mem_caches *cc, __percpu *pcc; - struct bpf_mem_cache *c, __percpu *pc; + struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc; + struct bpf_mem_cache *c; struct bpf_mem_cache __percpu *pc; struct obj_cgroup *objcg = NULL; int cpu, i, unit_size, percpu_size = 0; + if (percpu && size == 0) + return -EINVAL; + + /* room for llist_node and per-cpu pointer */ + if (percpu) + percpu_size = LLIST_NODE_SZ + sizeof(void *); + ma->percpu = percpu; + if (size) { pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL); if (!pc) return -ENOMEM; - if (percpu) - /* room for llist_node and per-cpu pointer */ - percpu_size = LLIST_NODE_SZ + sizeof(void *); - else + if (!percpu) size += LLIST_NODE_SZ; /* room for llist_node */ unit_size = size; -#ifdef CONFIG_MEMCG_KMEM - objcg = get_obj_cgroup_from_current(); +#ifdef CONFIG_MEMCG + if (memcg_bpf_enabled()) + objcg = get_obj_cgroup_from_current(); #endif + ma->objcg = objcg; + for_each_possible_cpu(cpu) { c = per_cpu_ptr(pc, cpu); c->unit_size = unit_size; c->objcg = objcg; c->percpu_size = percpu_size; + c->tgt = c; + init_refill_work(c); prefill_mem_cache(c, cpu); } ma->cache = pc; return 0; } - /* size == 0 && percpu is an invalid combination */ - if (WARN_ON_ONCE(percpu)) - return -EINVAL; - pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG objcg = get_obj_cgroup_from_current(); #endif + ma->objcg = objcg; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; c->unit_size = sizes[i]; c->objcg = objcg; + c->percpu_size = percpu_size; + c->tgt = c; + + init_refill_work(c); prefill_mem_cache(c, cpu); } } + + ma->caches = pcc; + return 0; +} + +int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg) +{ + struct bpf_mem_caches __percpu *pcc; + + pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL); + if (!pcc) + return -ENOMEM; + ma->caches = pcc; + ma->objcg = objcg; + ma->percpu = true; + return 0; +} + +int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size) +{ + struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc; + int cpu, i, unit_size, percpu_size; + struct obj_cgroup *objcg; + struct bpf_mem_cache *c; + + i = bpf_mem_cache_idx(size); + if (i < 0) + return -EINVAL; + + /* room for llist_node and per-cpu pointer */ + percpu_size = LLIST_NODE_SZ + sizeof(void *); + + unit_size = sizes[i]; + objcg = ma->objcg; + pcc = ma->caches; + + for_each_possible_cpu(cpu) { + cc = per_cpu_ptr(pcc, cpu); + c = &cc->cache[i]; + if (c->unit_size) + break; + + c->unit_size = unit_size; + c->objcg = objcg; + c->percpu_size = percpu_size; + c->tgt = c; + + init_refill_work(c); + prefill_mem_cache(c, cpu); + } + return 0; } static void drain_mem_cache(struct bpf_mem_cache *c) { - struct llist_node *llnode, *t; + bool percpu = !!c->percpu_size; /* No progs are using this bpf_mem_cache, but htab_map_free() called * bpf_mem_cache_free() for all remaining elements and they can be in - * free_by_rcu or in waiting_for_gp lists, so drain those lists now. + * free_by_rcu_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now. * - * Except for waiting_for_gp list, there are no concurrent operations + * Except for waiting_for_gp_ttrace list, there are no concurrent operations * on these lists, so it is safe to use __llist_del_all(). */ - llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu)) - free_one(c, llnode); - llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp)) - free_one(c, llnode); - llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist)) - free_one(c, llnode); - llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist_extra)) - free_one(c, llnode); + free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu); + free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu); + free_all(__llist_del_all(&c->free_llist), percpu); + free_all(__llist_del_all(&c->free_llist_extra), percpu); + free_all(__llist_del_all(&c->free_by_rcu), percpu); + free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu); + free_all(llist_del_all(&c->waiting_for_gp), percpu); +} + +static void check_mem_cache(struct bpf_mem_cache *c) +{ + WARN_ON_ONCE(!llist_empty(&c->free_by_rcu_ttrace)); + WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); + WARN_ON_ONCE(!llist_empty(&c->free_llist)); + WARN_ON_ONCE(!llist_empty(&c->free_llist_extra)); + WARN_ON_ONCE(!llist_empty(&c->free_by_rcu)); + WARN_ON_ONCE(!llist_empty(&c->free_llist_extra_rcu)); + WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); +} + +static void check_leaked_objs(struct bpf_mem_alloc *ma) +{ + struct bpf_mem_caches *cc; + struct bpf_mem_cache *c; + int cpu, i; + + if (ma->cache) { + for_each_possible_cpu(cpu) { + c = per_cpu_ptr(ma->cache, cpu); + check_mem_cache(c); + } + } + if (ma->caches) { + for_each_possible_cpu(cpu) { + cc = per_cpu_ptr(ma->caches, cpu); + for (i = 0; i < NUM_CACHES; i++) { + c = &cc->cache[i]; + check_mem_cache(c); + } + } + } } static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) { + check_leaked_objs(ma); free_percpu(ma->cache); free_percpu(ma->caches); ma->cache = NULL; @@ -462,8 +689,8 @@ static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) static void free_mem_alloc(struct bpf_mem_alloc *ma) { - /* waiting_for_gp lists was drained, but __free_rcu might - * still execute. Wait for it now before we freeing percpu caches. + /* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks + * might still execute. Wait for them. * * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(), * but rcu_barrier_tasks_trace() and rcu_barrier() below are only used @@ -472,7 +699,8 @@ static void free_mem_alloc(struct bpf_mem_alloc *ma) * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by * using rcu_trace_implies_rcu_gp() as well. */ - rcu_barrier_tasks_trace(); + rcu_barrier(); /* wait for __free_by_rcu */ + rcu_barrier_tasks_trace(); /* wait for __free_rcu */ if (!rcu_trace_implies_rcu_gp()) rcu_barrier(); free_mem_alloc_no_barrier(ma); @@ -498,7 +726,7 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress) return; } - copy = kmalloc(sizeof(*ma), GFP_KERNEL); + copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL); if (!copy) { /* Slow path with inline barrier-s */ free_mem_alloc(ma); @@ -506,12 +734,9 @@ static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress) } /* Defer barriers into worker to let the rest of map memory to be freed */ - copy->cache = ma->cache; - ma->cache = NULL; - copy->caches = ma->caches; - ma->caches = NULL; + memset(ma, 0, sizeof(*ma)); INIT_WORK(©->work, free_mem_alloc_deferred); - queue_work(system_unbound_wq, ©->work); + queue_work(system_dfl_wq, ©->work); } void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) @@ -524,22 +749,13 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress = 0; for_each_possible_cpu(cpu) { c = per_cpu_ptr(ma->cache, cpu); - /* - * refill_work may be unfinished for PREEMPT_RT kernel - * in which irq work is invoked in a per-CPU RT thread. - * It is also possible for kernel with - * arch_irq_work_has_interrupt() being false and irq - * work is invoked in timer interrupt. So waiting for - * the completion of irq work to ease the handling of - * concurrency. - */ + WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); + rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } - /* objcg is the same across cpus */ - if (c->objcg) - obj_cgroup_put(c->objcg); + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { @@ -548,13 +764,14 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) cc = per_cpu_ptr(ma->caches, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; + WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); + rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } - if (c->objcg) - obj_cgroup_put(c->objcg); + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } @@ -581,16 +798,23 @@ static void notrace *unit_alloc(struct bpf_mem_cache *c) local_irq_save(flags); if (local_inc_return(&c->active) == 1) { llnode = __llist_del_first(&c->free_llist); - if (llnode) + if (llnode) { cnt = --c->free_cnt; + *(struct bpf_mem_cache **)llnode = c; + } } local_dec(&c->active); - local_irq_restore(flags); WARN_ON(cnt < 0); if (cnt < c->low_watermark) irq_work_raise(c); + /* Enable IRQ after the enqueue of irq work completes, so irq work + * will run after IRQ is enabled and free_llist may be refilled by + * irq work before other task preempts current task. + */ + local_irq_restore(flags); + return llnode; } @@ -606,6 +830,12 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr) BUILD_BUG_ON(LLIST_NODE_SZ > 8); + /* + * Remember bpf_mem_cache that allocated this object. + * The hint is not accurate. + */ + c->tgt = *(struct bpf_mem_cache **)llnode; + local_irq_save(flags); if (local_inc_return(&c->active) == 1) { __llist_add(llnode, &c->free_llist); @@ -620,11 +850,37 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr) llist_add(llnode, &c->free_llist_extra); } local_dec(&c->active); - local_irq_restore(flags); if (cnt > c->high_watermark) /* free few objects from current cpu into global kmalloc pool */ irq_work_raise(c); + /* Enable IRQ after irq_work_raise() completes, otherwise when current + * task is preempted by task which does unit_alloc(), unit_alloc() may + * return NULL unexpectedly because irq work is already pending but can + * not been triggered and free_llist can not be refilled timely. + */ + local_irq_restore(flags); +} + +static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr) +{ + struct llist_node *llnode = ptr - LLIST_NODE_SZ; + unsigned long flags; + + c->tgt = *(struct bpf_mem_cache **)llnode; + + local_irq_save(flags); + if (local_inc_return(&c->active) == 1) { + if (__llist_add(llnode, &c->free_by_rcu)) + c->free_by_rcu_tail = llnode; + } else { + llist_add(llnode, &c->free_llist_extra_rcu); + } + local_dec(&c->active); + + if (!atomic_read(&c->call_rcu_in_progress)) + irq_work_raise(c); + local_irq_restore(flags); } /* Called from BPF program or from sys_bpf syscall. @@ -636,9 +892,11 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) void *ret; if (!size) - return ZERO_SIZE_PTR; + return NULL; - idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ); + if (!ma->percpu) + size += LLIST_NODE_SZ; + idx = bpf_mem_cache_idx(size); if (idx < 0) return NULL; @@ -648,18 +906,36 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) { + struct bpf_mem_cache *c; int idx; if (!ptr) return; - idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ)); - if (idx < 0) + c = *(void **)(ptr - LLIST_NODE_SZ); + idx = bpf_mem_cache_idx(c->unit_size); + if (WARN_ON_ONCE(idx < 0)) return; unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr); } +void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr) +{ + struct bpf_mem_cache *c; + int idx; + + if (!ptr) + return; + + c = *(void **)(ptr - LLIST_NODE_SZ); + idx = bpf_mem_cache_idx(c->unit_size); + if (WARN_ON_ONCE(idx < 0)) + return; + + unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr); +} + void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma) { void *ret; @@ -675,3 +951,66 @@ void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr) unit_free(this_cpu_ptr(ma->cache), ptr); } + +void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr) +{ + if (!ptr) + return; + + unit_free_rcu(this_cpu_ptr(ma->cache), ptr); +} + +/* Directly does a kfree() without putting 'ptr' back to the free_llist + * for reuse and without waiting for a rcu_tasks_trace gp. + * The caller must first go through the rcu_tasks_trace gp for 'ptr' + * before calling bpf_mem_cache_raw_free(). + * It could be used when the rcu_tasks_trace callback does not have + * a hold on the original bpf_mem_alloc object that allocated the + * 'ptr'. This should only be used in the uncommon code path. + * Otherwise, the bpf_mem_alloc's free_llist cannot be refilled + * and may affect performance. + */ +void bpf_mem_cache_raw_free(void *ptr) +{ + if (!ptr) + return; + + kfree(ptr - LLIST_NODE_SZ); +} + +/* When flags == GFP_KERNEL, it signals that the caller will not cause + * deadlock when using kmalloc. bpf_mem_cache_alloc_flags() will use + * kmalloc if the free_llist is empty. + */ +void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) +{ + struct bpf_mem_cache *c; + void *ret; + + c = this_cpu_ptr(ma->cache); + + ret = unit_alloc(c); + if (!ret && flags == GFP_KERNEL) { + struct mem_cgroup *memcg, *old_memcg; + + memcg = get_memcg(c); + old_memcg = set_active_memcg(memcg); + ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT); + if (ret) + *(struct bpf_mem_cache **)ret = c; + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + } + + return !ret ? NULL : ret + LLIST_NODE_SZ; +} + +int bpf_mem_alloc_check_size(bool percpu, size_t size) +{ + /* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */ + if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) || + (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ)) + return -E2BIG; + + return 0; +} diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c new file mode 100644 index 000000000000..1394168062e8 --- /dev/null +++ b/kernel/bpf/mprog.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include <linux/bpf.h> +#include <linux/bpf_mprog.h> + +static int bpf_mprog_link(struct bpf_tuple *tuple, + u32 id_or_fd, u32 flags, + enum bpf_prog_type type) +{ + struct bpf_link *link = ERR_PTR(-EINVAL); + bool id = flags & BPF_F_ID; + + if (id) + link = bpf_link_by_id(id_or_fd); + else if (id_or_fd) + link = bpf_link_get_from_fd(id_or_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + if (type && link->prog->type != type) { + bpf_link_put(link); + return -EINVAL; + } + + tuple->link = link; + tuple->prog = link->prog; + return 0; +} + +static int bpf_mprog_prog(struct bpf_tuple *tuple, + u32 id_or_fd, u32 flags, + enum bpf_prog_type type) +{ + struct bpf_prog *prog = ERR_PTR(-EINVAL); + bool id = flags & BPF_F_ID; + + if (id) + prog = bpf_prog_by_id(id_or_fd); + else if (id_or_fd) + prog = bpf_prog_get(id_or_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + if (type && prog->type != type) { + bpf_prog_put(prog); + return -EINVAL; + } + + tuple->link = NULL; + tuple->prog = prog; + return 0; +} + +static int bpf_mprog_tuple_relative(struct bpf_tuple *tuple, + u32 id_or_fd, u32 flags, + enum bpf_prog_type type) +{ + bool link = flags & BPF_F_LINK; + bool id = flags & BPF_F_ID; + + memset(tuple, 0, sizeof(*tuple)); + if (link) + return bpf_mprog_link(tuple, id_or_fd, flags, type); + /* If no relevant flag is set and no id_or_fd was passed, then + * tuple link/prog is just NULLed. This is the case when before/ + * after selects first/last position without passing fd. + */ + if (!id && !id_or_fd) + return 0; + return bpf_mprog_prog(tuple, id_or_fd, flags, type); +} + +static void bpf_mprog_tuple_put(struct bpf_tuple *tuple) +{ + if (tuple->link) + bpf_link_put(tuple->link); + else if (tuple->prog) + bpf_prog_put(tuple->prog); +} + +/* The bpf_mprog_{replace,delete}() operate on exact idx position with the + * one exception that for deletion we support delete from front/back. In + * case of front idx is -1, in case of back idx is bpf_mprog_total(entry). + * Adjustment to first and last entry is trivial. The bpf_mprog_insert() + * we have to deal with the following cases: + * + * idx + before: + * + * Insert P4 before P3: idx for old array is 1, idx for new array is 2, + * hence we adjust target idx for the new array, so that memmove copies + * P1 and P2 to the new entry, and we insert P4 into idx 2. Inserting + * before P1 would have old idx -1 and new idx 0. + * + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + * + * idx + after: + * + * Insert P4 after P2: idx for old array is 2, idx for new array is 2. + * Again, memmove copies P1 and P2 to the new entry, and we insert P4 + * into idx 2. Inserting after P3 would have both old/new idx at 4 aka + * bpf_mprog_total(entry). + * + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + */ +static int bpf_mprog_replace(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_tuple *ntuple, int idx) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + struct bpf_prog *oprog; + + bpf_mprog_read(entry, idx, &fp, &cp); + oprog = READ_ONCE(fp->prog); + bpf_mprog_write(fp, cp, ntuple); + if (!ntuple->link) { + WARN_ON_ONCE(cp->link); + bpf_prog_put(oprog); + } + *entry_new = entry; + return 0; +} + +static int bpf_mprog_insert(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_tuple *ntuple, int idx, u32 flags) +{ + int total = bpf_mprog_total(entry); + struct bpf_mprog_entry *peer; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + + peer = bpf_mprog_peer(entry); + bpf_mprog_entry_copy(peer, entry); + if (idx == total) + goto insert; + else if (flags & BPF_F_BEFORE) + idx += 1; + bpf_mprog_entry_grow(peer, idx); +insert: + bpf_mprog_read(peer, idx, &fp, &cp); + bpf_mprog_write(fp, cp, ntuple); + bpf_mprog_inc(peer); + *entry_new = peer; + return 0; +} + +static int bpf_mprog_delete(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_tuple *dtuple, int idx) +{ + int total = bpf_mprog_total(entry); + struct bpf_mprog_entry *peer; + + peer = bpf_mprog_peer(entry); + bpf_mprog_entry_copy(peer, entry); + if (idx == -1) + idx = 0; + else if (idx == total) + idx = total - 1; + bpf_mprog_entry_shrink(peer, idx); + bpf_mprog_dec(peer); + bpf_mprog_mark_for_release(peer, dtuple); + *entry_new = peer; + return 0; +} + +/* In bpf_mprog_pos_*() we evaluate the target position for the BPF + * program/link that needs to be replaced, inserted or deleted for + * each "rule" independently. If all rules agree on that position + * or existing element, then enact replacement, addition or deletion. + * If this is not the case, then the request cannot be satisfied and + * we bail out with an error. + */ +static int bpf_mprog_pos_exact(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + int i; + + for (i = 0; i < bpf_mprog_total(entry); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + if (tuple->prog == READ_ONCE(fp->prog)) + return tuple->link == cp->link ? i : -EBUSY; + } + return -ENOENT; +} + +static int bpf_mprog_pos_before(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + int i; + + for (i = 0; i < bpf_mprog_total(entry); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + if (tuple->prog == READ_ONCE(fp->prog) && + (!tuple->link || tuple->link == cp->link)) + return i - 1; + } + return tuple->prog ? -ENOENT : -1; +} + +static int bpf_mprog_pos_after(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + int i; + + for (i = 0; i < bpf_mprog_total(entry); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + if (tuple->prog == READ_ONCE(fp->prog) && + (!tuple->link || tuple->link == cp->link)) + return i + 1; + } + return tuple->prog ? -ENOENT : bpf_mprog_total(entry); +} + +int bpf_mprog_attach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog_new, struct bpf_link *link, + struct bpf_prog *prog_old, + u32 flags, u32 id_or_fd, u64 revision) +{ + struct bpf_tuple rtuple, ntuple = { + .prog = prog_new, + .link = link, + }, otuple = { + .prog = prog_old, + .link = link, + }; + int ret, idx = -ERANGE, tidx; + + if (revision && revision != bpf_mprog_revision(entry)) + return -ESTALE; + if (bpf_mprog_exists(entry, prog_new)) + return -EEXIST; + ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, + flags & ~BPF_F_REPLACE, + prog_new->type); + if (ret) + return ret; + if (flags & BPF_F_REPLACE) { + tidx = bpf_mprog_pos_exact(entry, &otuple); + if (tidx < 0) { + ret = tidx; + goto out; + } + idx = tidx; + } else if (bpf_mprog_total(entry) == bpf_mprog_max()) { + ret = -ERANGE; + goto out; + } + if (flags & BPF_F_BEFORE) { + tidx = bpf_mprog_pos_before(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < -1 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (flags & BPF_F_AFTER) { + tidx = bpf_mprog_pos_after(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < 0 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (idx < -1) { + if (rtuple.prog || flags) { + ret = -EINVAL; + goto out; + } + idx = bpf_mprog_total(entry); + flags = BPF_F_AFTER; + } + if (idx >= bpf_mprog_max()) { + ret = -ERANGE; + goto out; + } + if (flags & BPF_F_REPLACE) + ret = bpf_mprog_replace(entry, entry_new, &ntuple, idx); + else + ret = bpf_mprog_insert(entry, entry_new, &ntuple, idx, flags); +out: + bpf_mprog_tuple_put(&rtuple); + return ret; +} + +static int bpf_mprog_fetch(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple, int idx) +{ + int total = bpf_mprog_total(entry); + struct bpf_mprog_cp *cp; + struct bpf_mprog_fp *fp; + struct bpf_prog *prog; + struct bpf_link *link; + + if (idx == -1) + idx = 0; + else if (idx == total) + idx = total - 1; + bpf_mprog_read(entry, idx, &fp, &cp); + prog = READ_ONCE(fp->prog); + link = cp->link; + /* The deletion request can either be without filled tuple in which + * case it gets populated here based on idx, or with filled tuple + * where the only thing we end up doing is the WARN_ON_ONCE() assert. + * If we hit a BPF link at the given index, it must not be removed + * from opts path. + */ + if (link && !tuple->link) + return -EBUSY; + WARN_ON_ONCE(tuple->prog && tuple->prog != prog); + WARN_ON_ONCE(tuple->link && tuple->link != link); + tuple->prog = prog; + tuple->link = link; + return 0; +} + +int bpf_mprog_detach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog, struct bpf_link *link, + u32 flags, u32 id_or_fd, u64 revision) +{ + struct bpf_tuple rtuple, dtuple = { + .prog = prog, + .link = link, + }; + int ret, idx = -ERANGE, tidx; + + if (flags & BPF_F_REPLACE) + return -EINVAL; + if (revision && revision != bpf_mprog_revision(entry)) + return -ESTALE; + if (!bpf_mprog_total(entry)) + return -ENOENT; + ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags, + prog ? prog->type : + BPF_PROG_TYPE_UNSPEC); + if (ret) + return ret; + if (dtuple.prog) { + tidx = bpf_mprog_pos_exact(entry, &dtuple); + if (tidx < 0) { + ret = tidx; + goto out; + } + idx = tidx; + } + if (flags & BPF_F_BEFORE) { + tidx = bpf_mprog_pos_before(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < -1 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (flags & BPF_F_AFTER) { + tidx = bpf_mprog_pos_after(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < 0 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (idx < -1) { + if (rtuple.prog || flags) { + ret = -EINVAL; + goto out; + } + idx = bpf_mprog_total(entry); + flags = BPF_F_AFTER; + } + if (idx >= bpf_mprog_max()) { + ret = -ERANGE; + goto out; + } + ret = bpf_mprog_fetch(entry, &dtuple, idx); + if (ret) + goto out; + ret = bpf_mprog_delete(entry, entry_new, &dtuple, idx); +out: + bpf_mprog_tuple_put(&rtuple); + return ret; +} + +int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, + struct bpf_mprog_entry *entry) +{ + u32 __user *uprog_flags, *ulink_flags; + u32 __user *uprog_id, *ulink_id; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + struct bpf_prog *prog; + const u32 flags = 0; + u32 id, count = 0; + u64 revision = 1; + int i, ret = 0; + + if (attr->query.query_flags || attr->query.attach_flags) + return -EINVAL; + if (entry) { + revision = bpf_mprog_revision(entry); + count = bpf_mprog_total(entry); + } + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision))) + return -EFAULT; + if (copy_to_user(&uattr->query.count, &count, sizeof(count))) + return -EFAULT; + uprog_id = u64_to_user_ptr(attr->query.prog_ids); + uprog_flags = u64_to_user_ptr(attr->query.prog_attach_flags); + ulink_id = u64_to_user_ptr(attr->query.link_ids); + ulink_flags = u64_to_user_ptr(attr->query.link_attach_flags); + if (attr->query.count == 0 || !uprog_id || !count) + return 0; + if (attr->query.count < count) { + count = attr->query.count; + ret = -ENOSPC; + } + for (i = 0; i < bpf_mprog_max(); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + prog = READ_ONCE(fp->prog); + if (!prog) + break; + id = prog->aux->id; + if (copy_to_user(uprog_id + i, &id, sizeof(id))) + return -EFAULT; + if (uprog_flags && + copy_to_user(uprog_flags + i, &flags, sizeof(flags))) + return -EFAULT; + id = cp->link ? cp->link->id : 0; + if (ulink_id && + copy_to_user(ulink_id + i, &id, sizeof(id))) + return -EFAULT; + if (ulink_flags && + copy_to_user(ulink_flags + i, &flags, sizeof(flags))) + return -EFAULT; + if (i + 1 == count) + break; + } + return ret; +} diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c index 868cc2c43899..8e88201c98bf 100644 --- a/kernel/bpf/net_namespace.c +++ b/kernel/bpf/net_namespace.c @@ -11,8 +11,6 @@ struct bpf_netns_link { struct bpf_link link; - enum bpf_attach_type type; - enum netns_bpf_attach_type netns_type; /* We don't hold a ref to net in order to auto-detach the link * when netns is going away. Instead we rely on pernet @@ -21,6 +19,7 @@ struct bpf_netns_link { */ struct net *net; struct list_head node; /* node in list of links attached to net */ + enum netns_bpf_attach_type netns_type; }; /* Protects updates to netns_bpf */ @@ -216,7 +215,7 @@ static int bpf_netns_link_fill_info(const struct bpf_link *link, mutex_unlock(&netns_bpf_mutex); info->netns.netns_ino = inum; - info->netns.attach_type = net_link->type; + info->netns.attach_type = link->attach_type; return 0; } @@ -230,7 +229,7 @@ static void bpf_netns_link_show_fdinfo(const struct bpf_link *link, "netns_ino:\t%u\n" "attach_type:\t%u\n", info.netns.netns_ino, - info.netns.attach_type); + link->attach_type); } static const struct bpf_link_ops bpf_netns_link_ops = { @@ -501,9 +500,8 @@ int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog) goto out_put_net; } bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS, - &bpf_netns_link_ops, prog); + &bpf_netns_link_ops, prog, type); net_link->net = net; - net_link->type = type; net_link->netns_type = netns_type; err = bpf_link_prime(&net_link->link, &link_primer); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 190d9f9dc987..42ae8d595c2c 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -25,6 +25,8 @@ #include <linux/rhashtable.h> #include <linux/rtnetlink.h> #include <linux/rwsem.h> +#include <net/netdev_lock.h> +#include <net/xdp.h> /* Protects offdevs, members of bpf_offload_netdev and offload members * of all progs. @@ -41,7 +43,7 @@ struct bpf_offload_dev { struct bpf_offload_netdev { struct rhash_head l; struct net_device *netdev; - struct bpf_offload_dev *offdev; + struct bpf_offload_dev *offdev; /* NULL when bound-only */ struct list_head progs; struct list_head maps; struct list_head offdev_netdevs; @@ -56,7 +58,6 @@ static const struct rhashtable_params offdevs_params = { }; static struct rhashtable offdevs; -static bool offdevs_inited; static int bpf_dev_offload_check(struct net_device *netdev) { @@ -72,58 +73,227 @@ bpf_offload_find_netdev(struct net_device *netdev) { lockdep_assert_held(&bpf_devs_lock); - if (!offdevs_inited) - return NULL; return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); } -int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) +static int __bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, + struct net_device *netdev) { struct bpf_offload_netdev *ondev; - struct bpf_prog_offload *offload; int err; - if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS && - attr->prog_type != BPF_PROG_TYPE_XDP) - return -EINVAL; + ondev = kzalloc(sizeof(*ondev), GFP_KERNEL); + if (!ondev) + return -ENOMEM; - if (attr->prog_flags) - return -EINVAL; + ondev->netdev = netdev; + ondev->offdev = offdev; + INIT_LIST_HEAD(&ondev->progs); + INIT_LIST_HEAD(&ondev->maps); + + err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params); + if (err) { + netdev_warn(netdev, "failed to register for BPF offload\n"); + goto err_free; + } + + if (offdev) + list_add(&ondev->offdev_netdevs, &offdev->netdevs); + return 0; + +err_free: + kfree(ondev); + return err; +} + +static void __bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_prog_offload *offload = prog->aux->offload; + + if (offload->dev_state) + offload->offdev->ops->destroy(prog); + + list_del_init(&offload->offloads); + kfree(offload); + prog->aux->offload = NULL; +} + +static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, + enum bpf_netdev_command cmd) +{ + struct netdev_bpf data = {}; + struct net_device *netdev; + + ASSERT_RTNL(); + + data.command = cmd; + data.offmap = offmap; + /* Caller must make sure netdev is valid */ + netdev = offmap->netdev; + + return netdev->netdev_ops->ndo_bpf(netdev, &data); +} + +static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) +{ + WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE)); + /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */ + bpf_map_free_id(&offmap->map); + list_del_init(&offmap->offloads); + offmap->netdev = NULL; +} + +static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, + struct net_device *netdev) +{ + struct bpf_offload_netdev *ondev, *altdev = NULL; + struct bpf_offloaded_map *offmap, *mtmp; + struct bpf_prog_offload *offload, *ptmp; + + ASSERT_RTNL(); + + ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); + if (WARN_ON(!ondev)) + return; + + WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); + + /* Try to move the objects to another netdev of the device */ + if (offdev) { + list_del(&ondev->offdev_netdevs); + altdev = list_first_entry_or_null(&offdev->netdevs, + struct bpf_offload_netdev, + offdev_netdevs); + } + + if (altdev) { + list_for_each_entry(offload, &ondev->progs, offloads) + offload->netdev = altdev->netdev; + list_splice_init(&ondev->progs, &altdev->progs); + + list_for_each_entry(offmap, &ondev->maps, offloads) + offmap->netdev = altdev->netdev; + list_splice_init(&ondev->maps, &altdev->maps); + } else { + list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) + __bpf_prog_offload_destroy(offload->prog); + list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) + __bpf_map_offload_destroy(offmap); + } + + WARN_ON(!list_empty(&ondev->progs)); + WARN_ON(!list_empty(&ondev->maps)); + kfree(ondev); +} + +static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *netdev) +{ + struct bpf_offload_netdev *ondev; + struct bpf_prog_offload *offload; + int err; offload = kzalloc(sizeof(*offload), GFP_USER); if (!offload) return -ENOMEM; offload->prog = prog; + offload->netdev = netdev; - offload->netdev = dev_get_by_index(current->nsproxy->net_ns, - attr->prog_ifindex); - err = bpf_dev_offload_check(offload->netdev); - if (err) - goto err_maybe_put; - - down_write(&bpf_devs_lock); ondev = bpf_offload_find_netdev(offload->netdev); - if (!ondev) { + /* When program is offloaded require presence of "true" + * bpf_offload_netdev, avoid the one created for !ondev case below. + */ + if (bpf_prog_is_offloaded(prog->aux) && (!ondev || !ondev->offdev)) { err = -EINVAL; - goto err_unlock; + goto err_free; + } + if (!ondev) { + /* When only binding to the device, explicitly + * create an entry in the hashtable. + */ + err = __bpf_offload_dev_netdev_register(NULL, offload->netdev); + if (err) + goto err_free; + ondev = bpf_offload_find_netdev(offload->netdev); } offload->offdev = ondev->offdev; prog->aux->offload = offload; list_add_tail(&offload->offloads, &ondev->progs); - dev_put(offload->netdev); - up_write(&bpf_devs_lock); return 0; -err_unlock: - up_write(&bpf_devs_lock); -err_maybe_put: - if (offload->netdev) - dev_put(offload->netdev); +err_free: kfree(offload); return err; } +int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) +{ + struct net_device *netdev; + int err; + + if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS && + attr->prog_type != BPF_PROG_TYPE_XDP) + return -EINVAL; + + if (attr->prog_flags & ~(BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_XDP_HAS_FRAGS)) + return -EINVAL; + + /* Frags are allowed only if program is dev-bound-only, but not + * if it is requesting bpf offload. + */ + if (attr->prog_flags & BPF_F_XDP_HAS_FRAGS && + !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY)) + return -EINVAL; + + if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS && + attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY) + return -EINVAL; + + netdev = dev_get_by_index(current->nsproxy->net_ns, attr->prog_ifindex); + if (!netdev) + return -EINVAL; + + err = bpf_dev_offload_check(netdev); + if (err) + goto out; + + prog->aux->offload_requested = !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY); + + down_write(&bpf_devs_lock); + err = __bpf_prog_dev_bound_init(prog, netdev); + up_write(&bpf_devs_lock); + +out: + dev_put(netdev); + return err; +} + +int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog) +{ + int err; + + if (!bpf_prog_is_dev_bound(old_prog->aux)) + return 0; + + if (bpf_prog_is_offloaded(old_prog->aux)) + return -EINVAL; + + new_prog->aux->dev_bound = old_prog->aux->dev_bound; + new_prog->aux->offload_requested = old_prog->aux->offload_requested; + + down_write(&bpf_devs_lock); + if (!old_prog->aux->offload) { + err = -EINVAL; + goto out; + } + + err = __bpf_prog_dev_bound_init(new_prog, old_prog->aux->offload->netdev); + +out: + up_write(&bpf_devs_lock); + return err; +} + int bpf_prog_offload_verifier_prep(struct bpf_prog *prog) { struct bpf_prog_offload *offload; @@ -209,24 +379,25 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) up_read(&bpf_devs_lock); } -static void __bpf_prog_offload_destroy(struct bpf_prog *prog) +void bpf_prog_dev_bound_destroy(struct bpf_prog *prog) { - struct bpf_prog_offload *offload = prog->aux->offload; - - if (offload->dev_state) - offload->offdev->ops->destroy(prog); - - list_del_init(&offload->offloads); - kfree(offload); - prog->aux->offload = NULL; -} + struct bpf_offload_netdev *ondev; + struct net_device *netdev; -void bpf_prog_offload_destroy(struct bpf_prog *prog) -{ + rtnl_lock(); down_write(&bpf_devs_lock); - if (prog->aux->offload) + if (prog->aux->offload) { + list_del_init(&prog->aux->offload->offloads); + + netdev = prog->aux->offload->netdev; __bpf_prog_offload_destroy(prog); + + ondev = bpf_offload_find_netdev(netdev); + if (!ondev->offdev && list_empty(&ondev->progs)) + __bpf_offload_dev_netdev_unregister(NULL, netdev); + } up_write(&bpf_devs_lock); + rtnl_unlock(); } static int bpf_prog_offload_translate(struct bpf_prog *prog) @@ -340,22 +511,6 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, const struct bpf_prog_ops bpf_offload_prog_ops = { }; -static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, - enum bpf_netdev_command cmd) -{ - struct netdev_bpf data = {}; - struct net_device *netdev; - - ASSERT_RTNL(); - - data.command = cmd; - data.offmap = offmap; - /* Caller must make sure netdev is valid */ - netdev = offmap->netdev; - - return netdev->netdev_ops->ndo_bpf(netdev, &data); -} - struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { struct net *net = current->nsproxy->net_ns; @@ -374,13 +529,14 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&offmap->map, attr); - rtnl_lock(); - down_write(&bpf_devs_lock); offmap->netdev = __dev_get_by_index(net, attr->map_ifindex); err = bpf_dev_offload_check(offmap->netdev); if (err) - goto err_unlock; + goto err_unlock_rtnl; + + netdev_lock_ops(offmap->netdev); + down_write(&bpf_devs_lock); ondev = bpf_offload_find_netdev(offmap->netdev); if (!ondev) { @@ -394,26 +550,20 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) list_add_tail(&offmap->offloads, &ondev->maps); up_write(&bpf_devs_lock); + netdev_unlock_ops(offmap->netdev); rtnl_unlock(); return &offmap->map; err_unlock: up_write(&bpf_devs_lock); + netdev_unlock_ops(offmap->netdev); +err_unlock_rtnl: rtnl_unlock(); bpf_map_area_free(offmap); return ERR_PTR(err); } -static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) -{ - WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE)); - /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */ - bpf_map_free_id(&offmap->map, true); - list_del_init(&offmap->offloads); - offmap->netdev = NULL; -} - void bpf_map_offload_map_free(struct bpf_map *map) { struct bpf_offloaded_map *offmap = map_to_offmap(map); @@ -428,6 +578,12 @@ void bpf_map_offload_map_free(struct bpf_map *map) bpf_map_area_free(offmap); } +u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) +{ + /* The memory dynamically allocated in netdev dev_ops is not counted */ + return sizeof(struct bpf_offloaded_map); +} + int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value) { struct bpf_offloaded_map *offmap = map_to_offmap(map); @@ -573,12 +729,28 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev) } EXPORT_SYMBOL_GPL(bpf_offload_dev_match); +bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs) +{ + bool ret; + + if (bpf_prog_is_offloaded(lhs->aux) != bpf_prog_is_offloaded(rhs->aux)) + return false; + + down_read(&bpf_devs_lock); + ret = lhs->aux->offload && rhs->aux->offload && + lhs->aux->offload->netdev && + lhs->aux->offload->netdev == rhs->aux->offload->netdev; + up_read(&bpf_devs_lock); + + return ret; +} + bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) { struct bpf_offloaded_map *offmap; bool ret; - if (!bpf_map_is_dev_bound(map)) + if (!bpf_map_is_offloaded(map)) return bpf_map_offload_neutral(map); offmap = map_to_offmap(map); @@ -592,32 +764,11 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev) { - struct bpf_offload_netdev *ondev; int err; - ondev = kzalloc(sizeof(*ondev), GFP_KERNEL); - if (!ondev) - return -ENOMEM; - - ondev->netdev = netdev; - ondev->offdev = offdev; - INIT_LIST_HEAD(&ondev->progs); - INIT_LIST_HEAD(&ondev->maps); - down_write(&bpf_devs_lock); - err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params); - if (err) { - netdev_warn(netdev, "failed to register for BPF offload\n"); - goto err_unlock_free; - } - - list_add(&ondev->offdev_netdevs, &offdev->netdevs); - up_write(&bpf_devs_lock); - return 0; - -err_unlock_free: + err = __bpf_offload_dev_netdev_register(offdev, netdev); up_write(&bpf_devs_lock); - kfree(ondev); return err; } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); @@ -625,43 +776,8 @@ EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev) { - struct bpf_offload_netdev *ondev, *altdev; - struct bpf_offloaded_map *offmap, *mtmp; - struct bpf_prog_offload *offload, *ptmp; - - ASSERT_RTNL(); - down_write(&bpf_devs_lock); - ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); - if (WARN_ON(!ondev)) - goto unlock; - - WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); - list_del(&ondev->offdev_netdevs); - - /* Try to move the objects to another netdev of the device */ - altdev = list_first_entry_or_null(&offdev->netdevs, - struct bpf_offload_netdev, - offdev_netdevs); - if (altdev) { - list_for_each_entry(offload, &ondev->progs, offloads) - offload->netdev = altdev->netdev; - list_splice_init(&ondev->progs, &altdev->progs); - - list_for_each_entry(offmap, &ondev->maps, offloads) - offmap->netdev = altdev->netdev; - list_splice_init(&ondev->maps, &altdev->maps); - } else { - list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) - __bpf_prog_offload_destroy(offload->prog); - list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) - __bpf_map_offload_destroy(offmap); - } - - WARN_ON(!list_empty(&ondev->progs)); - WARN_ON(!list_empty(&ondev->maps)); - kfree(ondev); -unlock: + __bpf_offload_dev_netdev_unregister(offdev, netdev); up_write(&bpf_devs_lock); } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); @@ -670,18 +786,6 @@ struct bpf_offload_dev * bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv) { struct bpf_offload_dev *offdev; - int err; - - down_write(&bpf_devs_lock); - if (!offdevs_inited) { - err = rhashtable_init(&offdevs, &offdevs_params); - if (err) { - up_write(&bpf_devs_lock); - return ERR_PTR(err); - } - offdevs_inited = true; - } - up_write(&bpf_devs_lock); offdev = kzalloc(sizeof(*offdev), GFP_KERNEL); if (!offdev) @@ -707,3 +811,68 @@ void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev) return offdev->priv; } EXPORT_SYMBOL_GPL(bpf_offload_dev_priv); + +void bpf_dev_bound_netdev_unregister(struct net_device *dev) +{ + struct bpf_offload_netdev *ondev; + + ASSERT_RTNL(); + + down_write(&bpf_devs_lock); + ondev = bpf_offload_find_netdev(dev); + if (ondev && !ondev->offdev) + __bpf_offload_dev_netdev_unregister(NULL, ondev->netdev); + up_write(&bpf_devs_lock); +} + +int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, + struct bpf_prog_aux *prog_aux) +{ + if (!bpf_prog_is_dev_bound(prog_aux)) { + bpf_log(log, "metadata kfuncs require device-bound program\n"); + return -EINVAL; + } + + if (bpf_prog_is_offloaded(prog_aux)) { + bpf_log(log, "metadata kfuncs can't be offloaded\n"); + return -EINVAL; + } + + return 0; +} + +void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id) +{ + const struct xdp_metadata_ops *ops; + void *p = NULL; + + /* We don't hold bpf_devs_lock while resolving several + * kfuncs and can race with the unregister_netdevice(). + * We rely on bpf_dev_bound_match() check at attach + * to render this program unusable. + */ + down_read(&bpf_devs_lock); + if (!prog->aux->offload) + goto out; + + ops = prog->aux->offload->netdev->xdp_metadata_ops; + if (!ops) + goto out; + +#define XDP_METADATA_KFUNC(name, _, __, xmo) \ + if (func_id == bpf_xdp_metadata_kfunc_id(name)) p = ops->xmo; + XDP_METADATA_KFUNC_xxx +#undef XDP_METADATA_KFUNC + +out: + up_read(&bpf_devs_lock); + + return p; +} + +static int __init bpf_offload_init(void) +{ + return rhashtable_init(&offdevs, &offdevs_params); +} + +core_initcall(bpf_offload_init); diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 034cf87b54e9..632762b57299 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -14,11 +14,9 @@ int pcpu_freelist_init(struct pcpu_freelist *s) for_each_possible_cpu(cpu) { struct pcpu_freelist_head *head = per_cpu_ptr(s->freelist, cpu); - raw_spin_lock_init(&head->lock); + raw_res_spin_lock_init(&head->lock); head->first = NULL; } - raw_spin_lock_init(&s->extralist.lock); - s->extralist.first = NULL; return 0; } @@ -34,58 +32,39 @@ static inline void pcpu_freelist_push_node(struct pcpu_freelist_head *head, WRITE_ONCE(head->first, node); } -static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, +static inline bool ___pcpu_freelist_push(struct pcpu_freelist_head *head, struct pcpu_freelist_node *node) { - raw_spin_lock(&head->lock); - pcpu_freelist_push_node(head, node); - raw_spin_unlock(&head->lock); -} - -static inline bool pcpu_freelist_try_push_extra(struct pcpu_freelist *s, - struct pcpu_freelist_node *node) -{ - if (!raw_spin_trylock(&s->extralist.lock)) + if (raw_res_spin_lock(&head->lock)) return false; - - pcpu_freelist_push_node(&s->extralist, node); - raw_spin_unlock(&s->extralist.lock); + pcpu_freelist_push_node(head, node); + raw_res_spin_unlock(&head->lock); return true; } -static inline void ___pcpu_freelist_push_nmi(struct pcpu_freelist *s, - struct pcpu_freelist_node *node) +void __pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) { - int cpu, orig_cpu; + struct pcpu_freelist_head *head; + int cpu; - orig_cpu = raw_smp_processor_id(); - while (1) { - for_each_cpu_wrap(cpu, cpu_possible_mask, orig_cpu) { - struct pcpu_freelist_head *head; + if (___pcpu_freelist_push(this_cpu_ptr(s->freelist), node)) + return; + while (true) { + for_each_cpu_wrap(cpu, cpu_possible_mask, raw_smp_processor_id()) { + if (cpu == raw_smp_processor_id()) + continue; head = per_cpu_ptr(s->freelist, cpu); - if (raw_spin_trylock(&head->lock)) { - pcpu_freelist_push_node(head, node); - raw_spin_unlock(&head->lock); - return; - } - } - - /* cannot lock any per cpu lock, try extralist */ - if (pcpu_freelist_try_push_extra(s, node)) + if (raw_res_spin_lock(&head->lock)) + continue; + pcpu_freelist_push_node(head, node); + raw_res_spin_unlock(&head->lock); return; + } } } -void __pcpu_freelist_push(struct pcpu_freelist *s, - struct pcpu_freelist_node *node) -{ - if (in_nmi()) - ___pcpu_freelist_push_nmi(s, node); - else - ___pcpu_freelist_push(this_cpu_ptr(s->freelist), node); -} - void pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { @@ -120,71 +99,29 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s) { + struct pcpu_freelist_node *node = NULL; struct pcpu_freelist_head *head; - struct pcpu_freelist_node *node; int cpu; for_each_cpu_wrap(cpu, cpu_possible_mask, raw_smp_processor_id()) { head = per_cpu_ptr(s->freelist, cpu); if (!READ_ONCE(head->first)) continue; - raw_spin_lock(&head->lock); + if (raw_res_spin_lock(&head->lock)) + continue; node = head->first; if (node) { WRITE_ONCE(head->first, node->next); - raw_spin_unlock(&head->lock); + raw_res_spin_unlock(&head->lock); return node; } - raw_spin_unlock(&head->lock); + raw_res_spin_unlock(&head->lock); } - - /* per cpu lists are all empty, try extralist */ - if (!READ_ONCE(s->extralist.first)) - return NULL; - raw_spin_lock(&s->extralist.lock); - node = s->extralist.first; - if (node) - WRITE_ONCE(s->extralist.first, node->next); - raw_spin_unlock(&s->extralist.lock); - return node; -} - -static struct pcpu_freelist_node * -___pcpu_freelist_pop_nmi(struct pcpu_freelist *s) -{ - struct pcpu_freelist_head *head; - struct pcpu_freelist_node *node; - int cpu; - - for_each_cpu_wrap(cpu, cpu_possible_mask, raw_smp_processor_id()) { - head = per_cpu_ptr(s->freelist, cpu); - if (!READ_ONCE(head->first)) - continue; - if (raw_spin_trylock(&head->lock)) { - node = head->first; - if (node) { - WRITE_ONCE(head->first, node->next); - raw_spin_unlock(&head->lock); - return node; - } - raw_spin_unlock(&head->lock); - } - } - - /* cannot pop from per cpu lists, try extralist */ - if (!READ_ONCE(s->extralist.first) || !raw_spin_trylock(&s->extralist.lock)) - return NULL; - node = s->extralist.first; - if (node) - WRITE_ONCE(s->extralist.first, node->next); - raw_spin_unlock(&s->extralist.lock); return node; } struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) { - if (in_nmi()) - return ___pcpu_freelist_pop_nmi(s); return ___pcpu_freelist_pop(s); } diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index 3c76553cfe57..914798b74967 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -5,15 +5,15 @@ #define __PERCPU_FREELIST_H__ #include <linux/spinlock.h> #include <linux/percpu.h> +#include <asm/rqspinlock.h> struct pcpu_freelist_head { struct pcpu_freelist_node *first; - raw_spinlock_t lock; + rqspinlock_t lock; }; struct pcpu_freelist { struct pcpu_freelist_head __percpu *freelist; - struct pcpu_freelist_head extralist; }; struct pcpu_freelist_node { diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig index c9d45c9d6918..aef7b0bc96d6 100644 --- a/kernel/bpf/preload/Kconfig +++ b/kernel/bpf/preload/Kconfig @@ -1,8 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -config USERMODE_DRIVER - bool - default n - menuconfig BPF_PRELOAD bool "Preload BPF file system with kernel specific program and map iterators" depends on BPF @@ -10,7 +6,6 @@ menuconfig BPF_PRELOAD # The dependency on !COMPILE_TEST prevents it from being enabled # in allmodconfig or allyesconfig configurations depends on !COMPILE_TEST - select USERMODE_DRIVER help This builds kernel module with several embedded BPF programs that are pinned into BPF FS mount point as human readable files that are diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c index 5106b5372f0c..774e5a538811 100644 --- a/kernel/bpf/preload/bpf_preload_kern.c +++ b/kernel/bpf/preload/bpf_preload_kern.c @@ -3,7 +3,11 @@ #include <linux/init.h> #include <linux/module.h> #include "bpf_preload.h" -#include "iterators/iterators.lskel.h" +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#include "iterators/iterators.lskel-little-endian.h" +#else +#include "iterators/iterators.lskel-big-endian.h" +#endif static struct bpf_link *maps_link, *progs_link; static struct iterators_bpf *skel; @@ -19,9 +23,9 @@ static void free_links_and_skel(void) static int preload(struct bpf_preload_info *obj) { - strlcpy(obj[0].link_name, "maps.debug", sizeof(obj[0].link_name)); + strscpy(obj[0].link_name, "maps.debug", sizeof(obj[0].link_name)); obj[0].link = maps_link; - strlcpy(obj[1].link_name, "progs.debug", sizeof(obj[1].link_name)); + strscpy(obj[1].link_name, "progs.debug", sizeof(obj[1].link_name)); obj[1].link = progs_link; return 0; } @@ -85,4 +89,6 @@ static void __exit fini(void) } late_initcall(load); module_exit(fini); +MODULE_IMPORT_NS("BPF_INTERNAL"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs"); diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile index 6762b1260f2f..b83c2f5e9be1 100644 --- a/kernel/bpf/preload/iterators/Makefile +++ b/kernel/bpf/preload/iterators/Makefile @@ -35,20 +35,22 @@ endif .PHONY: all clean -all: iterators.lskel.h +all: iterators.lskel-little-endian.h + +big: iterators.lskel-big-endian.h clean: $(call msg,CLEAN) $(Q)rm -rf $(OUTPUT) iterators -iterators.lskel.h: $(OUTPUT)/iterators.bpf.o | $(BPFTOOL) +iterators.lskel-%.h: $(OUTPUT)/%/iterators.bpf.o | $(BPFTOOL) $(call msg,GEN-SKEL,$@) $(Q)$(BPFTOOL) gen skeleton -L $< > $@ - -$(OUTPUT)/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) +$(OUTPUT)/%/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) $(call msg,BPF,$@) - $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + $(Q)mkdir -p $(@D) + $(Q)$(CLANG) -g -O2 --target=bpf -m$* $(INCLUDES) \ -c $(filter %.c,$^) -o $@ && \ $(LLVM_STRIP) -g $@ diff --git a/kernel/bpf/preload/iterators/README b/kernel/bpf/preload/iterators/README index 7fd6d39a9ad2..98e7c90ea012 100644 --- a/kernel/bpf/preload/iterators/README +++ b/kernel/bpf/preload/iterators/README @@ -1,4 +1,7 @@ WARNING: -If you change "iterators.bpf.c" do "make -j" in this directory to rebuild "iterators.skel.h". +If you change "iterators.bpf.c" do "make -j" in this directory to +rebuild "iterators.lskel-little-endian.h". Then, on a big-endian +machine, do "make -j big" in this directory to rebuild +"iterators.lskel-big-endian.h". Commit both resulting headers. Make sure to have clang 10 installed. See Documentation/bpf/bpf_devel_QA.rst diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c index 03af863314ea..b78968b63fab 100644 --- a/kernel/bpf/preload/iterators/iterators.bpf.c +++ b/kernel/bpf/preload/iterators/iterators.bpf.c @@ -73,6 +73,8 @@ static const char *get_name(struct btf *btf, long btf_id, const char *fallback) return str + name_off; } +__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym; + SEC("iter/bpf_map") int dump_bpf_map(struct bpf_iter__bpf_map *ctx) { @@ -84,9 +86,12 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx) return 0; if (seq_num == 0) - BPF_SEQ_PRINTF(seq, " id name max_entries\n"); + BPF_SEQ_PRINTF(seq, " id name max_entries cur_entries\n"); + + BPF_SEQ_PRINTF(seq, "%4u %-16s %10d %10lld\n", + map->id, map->name, map->max_entries, + bpf_map_sum_elem_count(map)); - BPF_SEQ_PRINTF(seq, "%4u %-16s%6d\n", map->id, map->name, map->max_entries); return 0; } diff --git a/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h b/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h new file mode 100644 index 000000000000..49b1d515a847 --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h @@ -0,0 +1,437 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ +#ifndef __ITERATORS_BPF_SKEL_H__ +#define __ITERATORS_BPF_SKEL_H__ + +#include <bpf/skel_internal.h> + +struct iterators_bpf { + struct bpf_loader_ctx ctx; + struct { + struct bpf_map_desc rodata; + } maps; + struct { + struct bpf_prog_desc dump_bpf_map; + struct bpf_prog_desc dump_bpf_prog; + } progs; + struct { + int dump_bpf_map_fd; + int dump_bpf_prog_fd; + } links; +}; + +static inline int +iterators_bpf__dump_bpf_map__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_map.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_map_fd = fd; + return fd; +} + +static inline int +iterators_bpf__dump_bpf_prog__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_prog.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_prog_fd = fd; + return fd; +} + +static inline int +iterators_bpf__attach(struct iterators_bpf *skel) +{ + int ret = 0; + + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_map__attach(skel); + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_prog__attach(skel); + return ret < 0 ? ret : 0; +} + +static inline void +iterators_bpf__detach(struct iterators_bpf *skel) +{ + skel_closenz(skel->links.dump_bpf_map_fd); + skel_closenz(skel->links.dump_bpf_prog_fd); +} +static void +iterators_bpf__destroy(struct iterators_bpf *skel) +{ + if (!skel) + return; + iterators_bpf__detach(skel); + skel_closenz(skel->progs.dump_bpf_map.prog_fd); + skel_closenz(skel->progs.dump_bpf_prog.prog_fd); + skel_closenz(skel->maps.rodata.map_fd); + skel_free(skel); +} +static inline struct iterators_bpf * +iterators_bpf__open(void) +{ + struct iterators_bpf *skel; + + skel = skel_alloc(sizeof(*skel)); + if (!skel) + goto cleanup; + skel->ctx.sz = (void *)&skel->links - (void *)skel; + return skel; +cleanup: + iterators_bpf__destroy(skel); + return NULL; +} + +static inline int +iterators_bpf__load(struct iterators_bpf *skel) +{ + struct bpf_load_and_run_opts opts = {}; + int err; + static const char opts_data[] __attribute__((__aligned__(8))) = "\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xeb\x9f\x01\0\ +\0\0\0\x18\0\0\0\0\0\0\x04\x80\0\0\x04\x80\0\0\x05\x44\0\0\0\0\x02\0\0\0\0\0\0\ +\x02\0\0\0\x01\x04\0\0\x02\0\0\0\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\ +\0\x04\0\0\0\x40\0\0\0\0\x02\0\0\0\0\0\0\x08\0\0\0\0\x02\0\0\0\0\0\0\x0d\0\0\0\ +\0\x0d\0\0\x01\0\0\0\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\x01\0\0\0\0\0\0\x04\x01\ +\0\0\x20\0\0\0\x24\x0c\0\0\x01\0\0\0\x05\0\0\0\xc3\x04\0\0\x03\0\0\0\x18\0\0\0\ +\xd1\0\0\0\x09\0\0\0\0\0\0\0\xd5\0\0\0\x0b\0\0\0\x40\0\0\0\xe0\0\0\0\x0b\0\0\0\ +\x80\0\0\0\0\x02\0\0\0\0\0\0\x0a\0\0\0\xe8\x07\0\0\0\0\0\0\0\0\0\0\xf1\x08\0\0\ +\0\0\0\0\x0c\0\0\0\xf7\x01\0\0\0\0\0\0\x08\0\0\0\x40\0\0\x01\xc1\x04\0\0\x03\0\ +\0\0\x18\0\0\x01\xc9\0\0\0\x0e\0\0\0\0\0\0\x01\xcc\0\0\0\x11\0\0\0\x20\0\0\x01\ +\xd1\0\0\0\x0e\0\0\0\xa0\0\0\x01\xdd\x08\0\0\0\0\0\0\x0f\0\0\x01\xe3\x01\0\0\0\ +\0\0\0\x04\0\0\0\x20\0\0\x01\xf0\x01\0\0\0\0\0\0\x01\x01\0\0\x08\0\0\0\0\x03\0\ +\0\0\0\0\0\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\x01\xf5\x01\0\0\0\0\0\0\x04\0\0\ +\0\x20\0\0\0\0\x0d\0\0\x01\0\0\0\x14\0\0\x05\x39\0\0\0\x04\0\0\x02\x3e\x08\0\0\ +\0\0\0\0\x15\0\0\x02\x44\x01\0\0\0\0\0\0\x08\x01\0\0\x40\0\0\x02\x4e\x0c\0\0\ +\x01\0\0\0\x13\0\0\0\0\x02\0\0\0\0\0\0\x18\0\0\x02\x65\x04\0\0\x02\0\0\0\x10\0\ +\0\0\x13\0\0\0\x03\0\0\0\0\0\0\x02\x78\0\0\0\x19\0\0\0\x40\0\0\0\0\x02\0\0\0\0\ +\0\0\x1c\0\0\0\0\x0d\0\0\x01\0\0\0\x06\0\0\0\x1c\0\0\0\x17\0\0\x02\x7d\x0c\0\0\ +\x01\0\0\0\x1a\0\0\x02\xc9\x04\0\0\x01\0\0\0\x08\0\0\x02\xd2\0\0\0\x1d\0\0\0\0\ +\0\0\0\0\x02\0\0\0\0\0\0\x1e\0\0\x03\x23\x04\0\0\x06\0\0\0\x38\0\0\x01\xc9\0\0\ +\0\x0e\0\0\0\0\0\0\x01\xcc\0\0\0\x11\0\0\0\x20\0\0\x03\x30\0\0\0\x1f\0\0\0\xc0\ +\0\0\x03\x41\0\0\0\x19\0\0\x01\0\0\0\x03\x4a\0\0\0\x21\0\0\x01\x40\0\0\x03\x54\ +\0\0\0\x22\0\0\x01\x80\0\0\0\0\x02\0\0\0\0\0\0\x20\0\0\0\0\x0a\0\0\0\0\0\0\x10\ +\0\0\0\0\x02\0\0\0\0\0\0\x23\0\0\0\0\x02\0\0\0\0\0\0\x24\0\0\x03\x9e\x04\0\0\ +\x02\0\0\0\x08\0\0\x03\xac\0\0\0\x0e\0\0\0\0\0\0\x03\xb5\0\0\0\x0e\0\0\0\x20\0\ +\0\x03\x54\x04\0\0\x03\0\0\0\x18\0\0\x03\xbf\0\0\0\x1f\0\0\0\0\0\0\x03\xc7\0\0\ +\0\x25\0\0\0\x40\0\0\x03\xcd\0\0\0\x27\0\0\0\x80\0\0\0\0\x02\0\0\0\0\0\0\x26\0\ +\0\0\0\x02\0\0\0\0\0\0\x28\0\0\x03\xd1\x04\0\0\x01\0\0\0\x04\0\0\x03\xdc\0\0\0\ +\x0e\0\0\0\0\0\0\x04\x45\x04\0\0\x01\0\0\0\x04\0\0\x04\x4e\0\0\0\x0e\0\0\0\0\0\ +\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x20\0\0\0\x12\0\0\0\x30\0\0\x04\xc4\x0e\0\0\0\0\ +\0\0\x29\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x20\0\0\0\x12\0\0\0\x1a\0\0\ +\x04\xd8\x0e\0\0\0\0\0\0\x2b\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x20\0\0\0\ +\x12\0\0\0\x20\0\0\x04\xee\x0e\0\0\0\0\0\0\x2d\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\ +\0\0\0\0\x20\0\0\0\x12\0\0\0\x11\0\0\x05\x03\x0e\0\0\0\0\0\0\x2f\0\0\0\0\0\0\0\ +\0\x03\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\x05\x1a\x0e\0\0\0\0\0\0\ +\x31\0\0\0\x01\0\0\x05\x22\x0f\0\0\x01\0\0\0\x04\0\0\0\x36\0\0\0\0\0\0\0\x04\0\ +\0\x05\x29\x0f\0\0\x04\0\0\0\x7b\0\0\0\x2a\0\0\0\0\0\0\0\x30\0\0\0\x2c\0\0\0\ +\x30\0\0\0\x1a\0\0\0\x2e\0\0\0\x4a\0\0\0\x20\0\0\0\x30\0\0\0\x6a\0\0\0\x11\0\0\ +\x05\x31\x0f\0\0\x01\0\0\0\x04\0\0\0\x32\0\0\0\0\0\0\0\x04\0\0\x05\x39\x0e\0\0\ +\0\0\0\0\x06\0\0\0\x01\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\ +\x5f\x6d\x61\x70\0\x6d\x65\x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\ +\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\ +\x66\x5f\x6d\x61\x70\0\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x32\x2f\x69\x69\x69\ +\x2f\x6c\x69\x6e\x75\x78\x2d\x6b\x65\x72\x6e\x65\x6c\x2d\x74\x6f\x6f\x6c\x63\ +\x68\x61\x69\x6e\x2f\x73\x72\x63\x2f\x6c\x69\x6e\x75\x78\x2f\x6b\x65\x72\x6e\ +\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\ +\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\ +\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\ +\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\ +\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\ +\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\ +\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\ +\x6e\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\ +\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\ +\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\ +\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\ +\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\ +\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\ +\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\ +\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\ +\x65\x73\x20\x20\x63\x75\x72\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\x6e\x22\x29\ +\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\x6d\x61\x78\ +\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\x73\x69\x67\ +\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\x52\x41\x59\ +\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\x5f\x53\x45\ +\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\ +\x25\x2d\x31\x36\x73\x20\x20\x25\x31\x30\x64\x20\x20\x20\x25\x31\x30\x6c\x6c\ +\x64\x5c\x6e\x22\x2c\0\x7d\0\x5f\x5f\x73\x36\x34\0\x6c\x6f\x6e\x67\x20\x6c\x6f\ +\x6e\x67\0\x62\x70\x66\x5f\x6d\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\x6d\x5f\ +\x63\x6f\x75\x6e\x74\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\ +\x70\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\ +\x72\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\ +\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\ +\x67\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\ +\x21\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\ +\x61\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\ +\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\ +\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\ +\x66\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\ +\x6e\x63\x5f\x6e\x61\x6d\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\ +\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\ +\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\ +\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\ +\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\ +\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\ +\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\ +\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\ +\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\ +\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\ +\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\ +\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\ +\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\ +\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\ +\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\ +\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\ +\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\ +\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\ +\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\ +\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\ +\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\ +\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\ +\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\ +\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\ +\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x6b\x73\x79\x6d\x73\0\x2e\ +\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x64\x75\x6d\x6d\x79\ +\x5f\x6b\x73\x79\x6d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x09\xdc\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x7b\0\0\0\x01\0\0\0\x80\0\0\0\0\ +\0\0\0\0\x69\x74\x65\x72\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\x74\x61\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x34\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\x69\x64\x20\x6e\x61\ +\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\ +\x65\x6e\x74\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\x6e\x74\x72\x69\x65\ +\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\x31\x30\x64\x20\x20\ +\x20\x25\x31\x30\x6c\x6c\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\ +\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x21\0\0\0\0\0\0\x79\x62\0\0\0\ +\0\0\0\x79\x71\0\x08\0\0\0\0\x15\x70\0\x1d\0\0\0\0\x79\x12\0\x10\0\0\0\0\x55\ +\x10\0\x08\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\0\0\xff\xff\xff\xe0\xbf\x16\0\0\ +\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb4\x30\0\0\0\0\0\x30\xb4\x50\0\0\ +\0\0\0\0\x85\0\0\0\0\0\0\x7e\x61\x17\0\0\0\0\0\0\x7b\xa1\xff\xe0\0\0\0\0\xb7\ +\x10\0\0\0\0\0\x04\xbf\x27\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\0\x7b\xa2\xff\xe8\0\0\ +\0\0\x61\x17\0\x14\0\0\0\0\x7b\xa1\xff\xf0\0\0\0\0\xbf\x17\0\0\0\0\0\0\x85\x02\ +\0\0\0\0\0\0\x7b\xa0\xff\xf8\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\0\0\xff\xff\ +\xff\xe0\xbf\x16\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\x30\xb4\x30\0\0\ +\0\0\0\x1a\xb4\x50\0\0\0\0\0\x20\x85\0\0\0\0\0\0\x7e\xb4\0\0\0\0\0\0\0\x95\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x9b\0\x01\x44\x1e\0\0\0\ +\x01\0\0\0\x42\0\0\0\x9b\0\x01\x44\x24\0\0\0\x02\0\0\0\x42\0\0\x01\x0e\0\x01\ +\x4c\x1d\0\0\0\x03\0\0\0\x42\0\0\x01\x2f\0\x01\x54\x06\0\0\0\x04\0\0\0\x42\0\0\ +\x01\x3e\0\x01\x48\x1d\0\0\0\x05\0\0\0\x42\0\0\x01\x63\0\x01\x60\x0e\0\0\0\x08\ +\0\0\0\x42\0\0\x01\x76\0\x01\x64\x03\0\0\0\x0e\0\0\0\x42\0\0\x02\x09\0\x01\x6c\ +\x02\0\0\0\x21\0\0\0\x42\0\0\x02\x3c\0\x01\x80\x01\0\0\0\0\0\0\0\x02\0\0\0\x3e\ +\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x02\0\0\x01\x0a\ +\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\x01\x3a\0\0\0\0\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\ +\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\x01\x0a\0\0\0\0\0\0\0\xa0\0\0\0\x0d\0\0\x01\ +\x3a\0\0\0\0\0\0\0\x1a\0\0\0\x23\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\ +\x70\0\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\ +\0\x10\0\0\0\0\0\0\0\0\0\0\0\x09\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\ +\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x62\x70\x66\x5f\x6d\x61\x70\x5f\x73\x75\ +\x6d\x5f\x65\x6c\x65\x6d\x5f\x63\x6f\x75\x6e\x74\0\0\x47\x50\x4c\0\0\0\0\0\x79\ +\x21\0\0\0\0\0\0\x79\x62\0\0\0\0\0\0\x79\x11\0\x08\0\0\0\0\x15\x10\0\x3b\0\0\0\ +\0\x79\x71\0\0\0\0\0\0\x79\x12\0\x10\0\0\0\0\x55\x10\0\x08\0\0\0\0\xbf\x4a\0\0\ +\0\0\0\0\x07\x40\0\0\xff\xff\xff\xd0\xbf\x16\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\x4a\xb4\x30\0\0\0\0\0\x20\xb4\x50\0\0\0\0\0\0\x85\0\0\0\0\0\0\x7e\ +\x7b\xa6\xff\xc8\0\0\0\0\x61\x17\0\0\0\0\0\0\x7b\xa1\xff\xd0\0\0\0\0\xb7\x30\0\ +\0\0\0\0\x04\xbf\x97\0\0\0\0\0\0\x0f\x93\0\0\0\0\0\0\x79\x17\0\x28\0\0\0\0\x79\ +\x87\0\x30\0\0\0\0\x15\x80\0\x18\0\0\0\0\xb7\x20\0\0\0\0\0\0\x0f\x12\0\0\0\0\0\ +\0\x61\x11\0\x04\0\0\0\0\x79\x38\0\x08\0\0\0\0\x67\x10\0\0\0\0\0\x03\x0f\x31\0\ +\0\0\0\0\0\x79\x68\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\xf8\ +\xb4\x20\0\0\0\0\0\x08\x85\0\0\0\0\0\0\x71\xb7\x10\0\0\0\0\0\0\x79\x3a\xff\xf8\ +\0\0\0\0\x0f\x31\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\xf4\ +\xb4\x20\0\0\0\0\0\x04\x85\0\0\0\0\0\0\x71\xb7\x30\0\0\0\0\0\x04\x61\x1a\xff\ +\xf4\0\0\0\0\x61\x28\0\x10\0\0\0\0\x3e\x12\0\x02\0\0\0\0\x0f\x61\0\0\0\0\0\0\ +\xbf\x96\0\0\0\0\0\0\x7b\xa9\xff\xd8\0\0\0\0\x79\x17\0\x18\0\0\0\0\x7b\xa1\xff\ +\xe0\0\0\0\0\x79\x17\0\x20\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x13\0\0\0\0\0\0\x7b\ +\xa1\xff\xe8\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\0\0\xff\xff\xff\xd0\x79\x1a\ +\xff\xc8\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\x6a\xb4\x30\0\0\0\0\0\x11\ +\xb4\x50\0\0\0\0\0\x20\x85\0\0\0\0\0\0\x7e\xb4\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x1b\0\0\0\0\0\0\0\x42\0\0\0\x9b\0\x01\x94\x1e\0\0\0\x01\0\0\0\ +\x42\0\0\0\x9b\0\x01\x94\x24\0\0\0\x02\0\0\0\x42\0\0\x02\x99\0\x01\x9c\x1f\0\0\ +\0\x03\0\0\0\x42\0\0\x02\xbd\0\x01\xa8\x06\0\0\0\x04\0\0\0\x42\0\0\x02\xd6\0\ +\x01\xb4\x0e\0\0\0\x05\0\0\0\x42\0\0\x01\x3e\0\x01\x98\x1d\0\0\0\x06\0\0\0\x42\ +\0\0\x01\x63\0\x01\xb8\x0e\0\0\0\x09\0\0\0\x42\0\0\x02\xe8\0\x01\xbc\x03\0\0\0\ +\x10\0\0\0\x42\0\0\x03\x58\0\x01\xc4\x02\0\0\0\x17\0\0\0\x42\0\0\x03\x93\0\x01\ +\x04\x06\0\0\0\x1a\0\0\0\x42\0\0\x03\x58\0\x01\xc4\x02\0\0\0\x1b\0\0\0\x42\0\0\ +\x03\xe4\0\x01\x10\x0f\0\0\0\x1c\0\0\0\x42\0\0\x03\xf9\0\x01\x14\x2d\0\0\0\x1e\ +\0\0\0\x42\0\0\x04\x30\0\x01\x0c\x0d\0\0\0\x21\0\0\0\x42\0\0\x03\xf9\0\x01\x14\ +\x02\0\0\0\x24\0\0\0\x42\0\0\x04\x57\0\x01\x18\x0d\0\0\0\x2b\0\0\0\x42\0\0\x04\ +\x57\0\x01\x18\x0d\0\0\0\x2c\0\0\0\x42\0\0\x04\x85\0\x01\x1c\x1b\0\0\0\x2d\0\0\ +\0\x42\0\0\x04\x85\0\x01\x1c\x0f\0\0\0\x2e\0\0\0\x42\0\0\x04\xa8\0\x01\x24\x0d\ +\0\0\0\x30\0\0\0\x42\0\0\x03\x58\0\x01\xc4\x02\0\0\0\x3f\0\0\0\x42\0\0\x02\x3c\ +\0\x01\xd4\x01\0\0\0\0\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\ +\x3e\0\0\0\0\0\0\0\x10\0\0\0\x18\0\0\x01\x0a\0\0\0\0\0\0\0\x20\0\0\0\x1c\0\0\0\ +\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\x01\x3a\0\0\0\0\0\0\0\x80\0\0\0\x1e\0\0\0\ +\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1e\0\0\x01\x0a\0\0\0\0\0\0\0\xa8\0\0\0\x1e\0\0\ +\x03\x8b\0\0\0\0\0\0\0\xb0\0\0\0\x1e\0\0\x03\x8f\0\0\0\0\0\0\0\xc0\0\0\0\x23\0\ +\0\x03\xbd\0\0\0\0\0\0\0\xd8\0\0\0\x24\0\0\x01\x0a\0\0\0\0\0\0\0\xf0\0\0\0\x24\ +\0\0\0\x3e\0\0\0\0\0\0\x01\x18\0\0\0\x28\0\0\0\x3e\0\0\0\0\0\0\x01\x50\0\0\0\ +\x1e\0\0\x01\x0a\0\0\0\0\0\0\x01\x60\0\0\0\x24\0\0\x04\x7f\0\0\0\0\0\0\x01\x88\ +\0\0\0\x1e\0\0\x01\x3a\0\0\0\0\0\0\x01\x98\0\0\0\x1e\0\0\x04\xc0\0\0\0\0\0\0\ +\x01\xa0\0\0\0\x1c\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x41\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\ +\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\ +\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x16\0\0\0\x01\0\0\0\0\0\ +\0\0\x12\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\x62\x70\x66\x5f\x69\ +\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0"; + static const char opts_insn[] __attribute__((__aligned__(8))) = "\ +\xbf\x61\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\x78\xb7\x20\0\ +\0\0\0\0\x88\xb7\x30\0\0\0\0\0\0\x85\0\0\0\0\0\0\x71\x05\0\0\x14\0\0\0\0\x61\ +\x1a\xff\x78\0\0\0\0\xd5\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x7c\ +\0\0\0\0\xd5\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x80\0\0\0\0\xd5\ +\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x84\0\0\0\0\xd5\x10\0\x01\0\ +\0\0\0\x85\0\0\0\0\0\0\xa8\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\ +\0\0\xd5\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\xbf\x07\0\0\ +\0\0\0\0\x95\0\0\0\0\0\0\0\x61\x06\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\ +\0\x0e\xf8\x63\x10\0\0\0\0\0\0\x61\x06\0\x0c\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\ +\0\0\0\x0e\xf4\x63\x10\0\0\0\0\0\0\x79\x06\0\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x0e\xe8\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x05\0\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0e\xe0\x7b\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\ +\x12\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0e\xe0\xb7\x30\0\0\0\0\0\x1c\x85\0\0\0\0\ +\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\xd4\0\0\0\0\x63\xa7\xff\x78\0\0\0\0\ +\x61\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x30\x63\x10\0\0\0\ +\0\0\0\x61\x06\0\x1c\0\0\0\0\x15\0\0\x03\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\ +\0\x0f\x0c\x63\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\ +\0\0\x0f\0\xb7\x30\0\0\0\0\0\x48\x85\0\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\ +\x70\xff\xc3\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x17\0\0\0\0\0\0\ +\x79\x36\0\x20\0\0\0\0\x15\x30\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\ +\x0f\x48\xb7\x20\0\0\0\0\0\x7b\x61\x06\0\x04\0\0\0\0\x45\0\0\x02\0\0\0\x01\x85\ +\0\0\0\0\0\0\x94\x05\0\0\x01\0\0\0\0\x85\0\0\0\0\0\0\x71\x18\x26\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x61\x02\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\xd0\x63\ +\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\xc8\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x0f\xd8\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x48\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\xe0\x7b\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\ +\x02\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0f\xd0\xb7\x30\0\0\0\0\0\x20\x85\0\0\0\0\ +\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\x9f\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x61\x02\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\xf0\x63\x10\ +\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\x16\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0f\xf0\xb7\ +\x30\0\0\0\0\0\x04\x85\0\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\x92\0\0\ +\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\xf8\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\ +\x12\x30\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\x18\x16\0\0\ +\0\0\0\0\0\0\0\0\0\0\x12\x28\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\ +\0\x11\x18\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\x70\x7b\x10\0\0\0\0\0\0\x18\x06\ +\0\0\0\0\0\0\0\0\0\0\0\0\x11\x20\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\x80\x7b\ +\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x11\xb0\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x12\xa0\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x18\ +\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\x98\x7b\x10\0\0\0\0\0\0\x61\x06\0\x08\0\0\0\0\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\x38\x63\x10\0\0\0\0\0\0\x61\x06\0\x0c\0\0\ +\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\x3c\x63\x10\0\0\0\0\0\0\x79\x06\0\x10\ +\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\x40\x7b\x10\0\0\0\0\0\0\x61\x0a\ +\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\x68\x63\x10\0\0\0\0\0\0\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\xb0\xb7\x20\0\0\0\0\0\x11\xb7\x30\0\0\0\0\ +\0\x0c\xb7\x40\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa7\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\ +\x5c\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x12\x20\x63\x07\0\x6c\0\0\0\0\x77\ +\x70\0\0\0\0\0\x20\x63\x07\0\x70\0\0\0\0\x18\x86\0\0\0\0\0\0\0\0\0\0\0\0\x10\ +\xb8\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x12\xc8\xb7\x20\0\0\0\0\0\x17\xb7\x30\0\0\ +\0\0\0\x0c\xb7\x40\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa7\xbf\x70\0\0\0\0\0\0\xc5\x70\ +\xff\x4d\0\0\0\0\x75\x70\0\x03\0\0\0\0\x62\x80\0\x04\0\0\0\0\x6a\x80\0\x02\0\0\ +\0\0\x05\0\0\x0a\0\0\0\0\x63\x87\0\x04\0\0\0\0\xbf\x97\0\0\0\0\0\0\x77\x90\0\0\ +\0\0\0\x20\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\x63\x09\0\0\0\0\0\0\x55\x90\0\ +\x02\0\0\0\0\x6a\x80\0\x02\0\0\0\0\x05\0\0\x01\0\0\0\0\x6a\x80\0\x02\0\0\0\x40\ +\xb7\x10\0\0\0\0\0\x05\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x12\x20\xb7\x30\0\0\0\0\ +\0\x8c\x85\0\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\ +\x01\0\x61\x10\0\0\0\0\0\0\xd5\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\ +\0\0\0\xa8\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x12\x90\x61\x10\0\0\0\0\0\0\xd5\x10\ +\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\xc5\x70\xff\x2c\0\0\0\0\ +\x63\xa7\xff\x80\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x12\xe0\x18\x16\0\0\0\ +\0\0\0\0\0\0\0\0\0\x17\x88\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\ +\x12\xe8\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x80\x7b\x10\0\0\0\0\0\0\x18\x06\0\ +\0\0\0\0\0\0\0\0\0\0\0\x14\xf0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\xc8\x7b\x10\ +\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x14\xf8\x18\x16\0\0\0\0\0\0\0\0\0\ +\0\0\0\x17\xd8\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x16\x58\x18\ +\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\xf8\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\xf0\x7b\x10\0\0\0\0\0\0\x61\ +\x06\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x90\x63\x10\0\0\0\0\0\0\ +\x61\x06\0\x0c\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x94\x63\x10\0\0\0\0\ +\0\0\x79\x06\0\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x98\x7b\x10\0\0\ +\0\0\0\0\x61\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\xc0\x63\ +\x10\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x18\x08\xb7\x20\0\0\0\0\0\x12\ +\xb7\x30\0\0\0\0\0\x0c\xb7\x40\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa7\xbf\x70\0\0\0\0\ +\0\0\xc5\x70\xfe\xf5\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x17\x78\x63\x07\0\ +\x6c\0\0\0\0\x77\x70\0\0\0\0\0\x20\x63\x07\0\x70\0\0\0\0\xb7\x10\0\0\0\0\0\x05\ +\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x17\x78\xb7\x30\0\0\0\0\0\x8c\x85\0\0\0\0\0\0\ +\xa6\xbf\x70\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x17\xe8\x61\x10\0\0\0\ +\0\0\0\xd5\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\xc5\x70\ +\xfe\xe3\0\0\0\0\x63\xa7\xff\x84\0\0\0\0\x61\x1a\xff\x78\0\0\0\0\xd5\x10\0\x02\ +\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x0a\xff\x80\0\0\0\0\x63\ +\x60\0\x28\0\0\0\0\x61\x0a\xff\x84\0\0\0\0\x63\x60\0\x2c\0\0\0\0\x18\x16\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\0\0\x63\x60\0\x18\0\0\0\0\xb7\0\0\0\0\0\ +\0\0\x95\0\0\0\0\0\0\0"; + + opts.ctx = (struct bpf_loader_ctx *)skel; + opts.data_sz = sizeof(opts_data) - 1; + opts.data = (void *)opts_data; + opts.insns_sz = sizeof(opts_insn) - 1; + opts.insns = (void *)opts_insn; + + err = bpf_load_and_run(&opts); + if (err < 0) + return err; + return 0; +} + +static inline struct iterators_bpf * +iterators_bpf__open_and_load(void) +{ + struct iterators_bpf *skel; + + skel = iterators_bpf__open(); + if (!skel) + return NULL; + if (iterators_bpf__load(skel)) { + iterators_bpf__destroy(skel); + return NULL; + } + return skel; +} + +__attribute__((unused)) static void +iterators_bpf__assert(struct iterators_bpf *s __attribute__((unused))) +{ +#ifdef __cplusplus +#define _Static_assert static_assert +#endif +#ifdef __cplusplus +#undef _Static_assert +#endif +} + +#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h new file mode 100644 index 000000000000..5b98ab02025e --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h @@ -0,0 +1,435 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ +#ifndef __ITERATORS_BPF_SKEL_H__ +#define __ITERATORS_BPF_SKEL_H__ + +#include <bpf/skel_internal.h> + +struct iterators_bpf { + struct bpf_loader_ctx ctx; + struct { + struct bpf_map_desc rodata; + } maps; + struct { + struct bpf_prog_desc dump_bpf_map; + struct bpf_prog_desc dump_bpf_prog; + } progs; + struct { + int dump_bpf_map_fd; + int dump_bpf_prog_fd; + } links; +}; + +static inline int +iterators_bpf__dump_bpf_map__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_map.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_map_fd = fd; + return fd; +} + +static inline int +iterators_bpf__dump_bpf_prog__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_prog.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_prog_fd = fd; + return fd; +} + +static inline int +iterators_bpf__attach(struct iterators_bpf *skel) +{ + int ret = 0; + + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_map__attach(skel); + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_prog__attach(skel); + return ret < 0 ? ret : 0; +} + +static inline void +iterators_bpf__detach(struct iterators_bpf *skel) +{ + skel_closenz(skel->links.dump_bpf_map_fd); + skel_closenz(skel->links.dump_bpf_prog_fd); +} +static void +iterators_bpf__destroy(struct iterators_bpf *skel) +{ + if (!skel) + return; + iterators_bpf__detach(skel); + skel_closenz(skel->progs.dump_bpf_map.prog_fd); + skel_closenz(skel->progs.dump_bpf_prog.prog_fd); + skel_closenz(skel->maps.rodata.map_fd); + skel_free(skel); +} +static inline struct iterators_bpf * +iterators_bpf__open(void) +{ + struct iterators_bpf *skel; + + skel = skel_alloc(sizeof(*skel)); + if (!skel) + goto cleanup; + skel->ctx.sz = (void *)&skel->links - (void *)skel; + return skel; +cleanup: + iterators_bpf__destroy(skel); + return NULL; +} + +static inline int +iterators_bpf__load(struct iterators_bpf *skel) +{ + struct bpf_load_and_run_opts opts = {}; + int err; + + opts.ctx = (struct bpf_loader_ctx *)skel; + opts.data_sz = 6208; + opts.data = (void *)"\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x9f\xeb\x01\0\ +\x18\0\0\0\0\0\0\0\x80\x04\0\0\x80\x04\0\0\x31\x05\0\0\0\0\0\0\0\0\0\x02\x02\0\ +\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\0\x04\ +\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\0\0\0\0\0\ +\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\0\0\0\x20\ +\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xb0\0\0\0\x03\0\0\x04\x18\0\0\0\xbe\0\ +\0\0\x09\0\0\0\0\0\0\0\xc2\0\0\0\x0b\0\0\0\x40\0\0\0\xcd\0\0\0\x0b\0\0\0\x80\0\ +\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd5\0\0\0\0\0\0\x07\0\0\0\0\xde\0\0\0\0\0\0\ +\x08\x0c\0\0\0\xe4\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xae\x01\0\0\x03\0\0\x04\ +\x18\0\0\0\xb6\x01\0\0\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\xbe\ +\x01\0\0\x0e\0\0\0\xa0\0\0\0\xca\x01\0\0\0\0\0\x08\x0f\0\0\0\xd0\x01\0\0\0\0\0\ +\x01\x04\0\0\0\x20\0\0\0\xdd\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\ +\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xe2\x01\0\0\0\0\0\x01\x04\0\0\0\ +\x20\0\0\0\0\0\0\0\x01\0\0\x0d\x14\0\0\0\x26\x05\0\0\x04\0\0\0\x2b\x02\0\0\0\0\ +\0\x08\x15\0\0\0\x31\x02\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\x01\x3b\x02\0\0\x01\0\ +\0\x0c\x13\0\0\0\0\0\0\0\0\0\0\x02\x18\0\0\0\x52\x02\0\0\x02\0\0\x04\x10\0\0\0\ +\x13\0\0\0\x03\0\0\0\0\0\0\0\x65\x02\0\0\x19\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\ +\x1c\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x17\0\0\0\x6a\x02\0\0\x01\0\ +\0\x0c\x1a\0\0\0\xb6\x02\0\0\x01\0\0\x04\x08\0\0\0\xbf\x02\0\0\x1d\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\x02\x1e\0\0\0\x10\x03\0\0\x06\0\0\x04\x38\0\0\0\xb6\x01\0\0\ +\x0e\0\0\0\0\0\0\0\xb9\x01\0\0\x11\0\0\0\x20\0\0\0\x1d\x03\0\0\x1f\0\0\0\xc0\0\ +\0\0\x2e\x03\0\0\x19\0\0\0\0\x01\0\0\x37\x03\0\0\x21\0\0\0\x40\x01\0\0\x41\x03\ +\0\0\x22\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\ +\0\0\0\0\0\0\0\0\0\x02\x23\0\0\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x8b\x03\0\0\x02\0\ +\0\x04\x08\0\0\0\x99\x03\0\0\x0e\0\0\0\0\0\0\0\xa2\x03\0\0\x0e\0\0\0\x20\0\0\0\ +\x41\x03\0\0\x03\0\0\x04\x18\0\0\0\xac\x03\0\0\x1f\0\0\0\0\0\0\0\xb4\x03\0\0\ +\x25\0\0\0\x40\0\0\0\xba\x03\0\0\x27\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x26\0\0\ +\0\0\0\0\0\0\0\0\x02\x28\0\0\0\xbe\x03\0\0\x01\0\0\x04\x04\0\0\0\xc9\x03\0\0\ +\x0e\0\0\0\0\0\0\0\x32\x04\0\0\x01\0\0\x04\x04\0\0\0\x3b\x04\0\0\x0e\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x30\0\0\0\xb1\x04\0\0\0\0\0\ +\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\x12\0\0\0\x1a\0\0\0\ +\xc5\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x20\0\0\0\ +\x12\0\0\0\x20\0\0\0\xdb\x04\0\0\0\0\0\x0e\x2d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\ +\0\0\0\0\x20\0\0\0\x12\0\0\0\x11\0\0\0\xf0\x04\0\0\0\0\0\x0e\x2f\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\x07\x05\0\0\0\0\0\x0e\ +\x31\0\0\0\x01\0\0\0\x0f\x05\0\0\x01\0\0\x0f\x04\0\0\0\x36\0\0\0\0\0\0\0\x04\0\ +\0\0\x16\x05\0\0\x04\0\0\x0f\x7b\0\0\0\x2a\0\0\0\0\0\0\0\x30\0\0\0\x2c\0\0\0\ +\x30\0\0\0\x1a\0\0\0\x2e\0\0\0\x4a\0\0\0\x20\0\0\0\x30\0\0\0\x6a\0\0\0\x11\0\0\ +\0\x1e\x05\0\0\x01\0\0\x0f\x04\0\0\0\x32\0\0\0\0\0\0\0\x04\0\0\0\x26\x05\0\0\0\ +\0\0\x0e\x06\0\0\0\x01\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\ +\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\ +\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\ +\x62\x70\x66\x5f\x6d\x61\x70\0\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x73\ +\x70\x73\x6b\x2f\x73\x72\x63\x2f\x62\x70\x66\x2d\x6e\x65\x78\x74\x2f\x6b\x65\ +\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\ +\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\ +\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\ +\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\ +\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\ +\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\ +\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\ +\x69\x67\x6e\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\ +\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\ +\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\ +\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\ +\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\ +\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\ +\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\ +\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\ +\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\x6e\ +\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\x6d\ +\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\x73\ +\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\x52\ +\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\x5f\ +\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\ +\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\x31\x30\x64\x20\x20\x20\x25\x31\x30\ +\x6c\x6c\x64\x5c\x6e\x22\x2c\0\x7d\0\x5f\x5f\x73\x36\x34\0\x6c\x6f\x6e\x67\x20\ +\x6c\x6f\x6e\x67\0\x62\x70\x66\x5f\x6d\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\ +\x6d\x5f\x63\x6f\x75\x6e\x74\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\ +\x66\x5f\x70\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\ +\x5f\x70\x72\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\ +\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\ +\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\ +\x20\x28\x21\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\ +\x78\0\x09\x61\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\ +\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\ +\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\ +\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\ +\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\ +\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\ +\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\ +\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\ +\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\ +\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\ +\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\ +\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\ +\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\ +\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\ +\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\ +\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\ +\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\ +\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\ +\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\ +\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\ +\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\ +\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\ +\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\ +\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\ +\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\ +\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\ +\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\ +\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\ +\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x6b\x73\x79\x6d\ +\x73\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x64\x75\x6d\ +\x6d\x79\x5f\x6b\x73\x79\x6d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\xc9\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x7b\0\0\0\x01\0\0\0\ +\x80\0\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\ +\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x34\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\ +\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x20\x20\x63\x75\x72\x5f\x65\ +\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x20\x25\ +\x31\x30\x64\x20\x20\x20\x25\x31\x30\x6c\x6c\x64\x0a\0\x20\x20\x69\x64\x20\x6e\ +\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\ +\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\ +\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\ +\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1d\0\0\0\0\0\x79\x21\ +\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe0\xff\ +\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\ +\x30\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\ +\xe0\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\ +\x7b\x2a\xe8\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\x7b\x1a\xf0\xff\0\0\0\0\xbf\x71\ +\0\0\0\0\0\0\x85\x20\0\0\0\0\0\0\x7b\x0a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\ +\x07\x04\0\0\xe0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\ +\x30\0\0\0\xb7\x03\0\0\x1a\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\ +\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\ +\x1e\x44\x01\0\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x44\x01\0\x02\0\0\0\x42\0\0\0\ +\xfb\0\0\0\x1d\x4c\x01\0\x03\0\0\0\x42\0\0\0\x1c\x01\0\0\x06\x54\x01\0\x04\0\0\ +\0\x42\0\0\0\x2b\x01\0\0\x1d\x48\x01\0\x05\0\0\0\x42\0\0\0\x50\x01\0\0\x06\x60\ +\x01\0\x07\0\0\0\x42\0\0\0\x63\x01\0\0\x03\x64\x01\0\x0e\0\0\0\x42\0\0\0\xf6\ +\x01\0\0\x02\x6c\x01\0\x21\0\0\0\x42\0\0\0\x29\x02\0\0\x01\x80\x01\0\0\0\0\0\ +\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\ +\x02\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x70\0\0\0\ +\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xf7\0\0\0\0\0\0\0\xa0\0\0\0\ +\x0d\0\0\0\x27\x01\0\0\0\0\0\0\x1a\0\0\0\x23\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\ +\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\ +\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x09\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\ +\x65\x72\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x62\x70\x66\x5f\x6d\ +\x61\x70\x5f\x73\x75\x6d\x5f\x65\x6c\x65\x6d\x5f\x63\x6f\x75\x6e\x74\0\0\x47\ +\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x11\x08\0\0\0\0\ +\0\x15\x01\x3b\0\0\0\0\0\x79\x17\0\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\ +\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\ +\x18\x62\0\0\0\0\0\0\0\0\0\0\x4a\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\ +\0\x85\0\0\0\x7e\0\0\0\x7b\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\ +\xff\0\0\0\0\xb7\x03\0\0\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\ +\x71\x28\0\0\0\0\0\x79\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\ +\0\0\x0f\x21\0\0\0\0\0\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\ +\0\x03\0\0\0\x0f\x13\0\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\ +\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\ +\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\ +\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\ +\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\ +\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\ +\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\ +\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\ +\xff\xff\xff\x79\xa1\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x6a\0\0\0\xb7\ +\x03\0\0\x11\0\0\0\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\ +\x95\0\0\0\0\0\0\0\0\0\0\0\x1b\0\0\0\0\0\0\0\x42\0\0\0\x88\0\0\0\x1e\x94\x01\0\ +\x01\0\0\0\x42\0\0\0\x88\0\0\0\x24\x94\x01\0\x02\0\0\0\x42\0\0\0\x86\x02\0\0\ +\x1f\x9c\x01\0\x03\0\0\0\x42\0\0\0\xaa\x02\0\0\x06\xa8\x01\0\x04\0\0\0\x42\0\0\ +\0\xc3\x02\0\0\x0e\xb4\x01\0\x05\0\0\0\x42\0\0\0\x2b\x01\0\0\x1d\x98\x01\0\x06\ +\0\0\0\x42\0\0\0\x50\x01\0\0\x06\xb8\x01\0\x08\0\0\0\x42\0\0\0\xd5\x02\0\0\x03\ +\xbc\x01\0\x10\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x17\0\0\0\x42\0\0\0\ +\x80\x03\0\0\x06\x04\x01\0\x1a\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x1b\0\ +\0\0\x42\0\0\0\xd1\x03\0\0\x0f\x10\x01\0\x1c\0\0\0\x42\0\0\0\xe6\x03\0\0\x2d\ +\x14\x01\0\x1e\0\0\0\x42\0\0\0\x1d\x04\0\0\x0d\x0c\x01\0\x20\0\0\0\x42\0\0\0\ +\x45\x03\0\0\x02\xc4\x01\0\x21\0\0\0\x42\0\0\0\xe6\x03\0\0\x02\x14\x01\0\x24\0\ +\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x27\0\0\0\x42\0\0\0\x45\x03\0\0\x02\ +\xc4\x01\0\x28\0\0\0\x42\0\0\0\x44\x04\0\0\x0d\x18\x01\0\x2b\0\0\0\x42\0\0\0\ +\x44\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x72\x04\0\0\x1b\x1c\x01\0\x2d\0\ +\0\0\x42\0\0\0\x72\x04\0\0\x06\x1c\x01\0\x2e\0\0\0\x42\0\0\0\x95\x04\0\0\x0d\ +\x24\x01\0\x30\0\0\0\x42\0\0\0\x45\x03\0\0\x02\xc4\x01\0\x3f\0\0\0\x42\0\0\0\ +\x29\x02\0\0\x01\xd4\x01\0\0\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\ +\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x18\0\0\0\xf7\0\0\0\0\0\0\0\x20\0\0\0\x1c\0\0\ +\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x27\x01\0\0\0\0\0\0\x80\0\0\0\x1e\0\0\ +\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1e\0\0\0\xf7\0\0\0\0\0\0\0\xa8\0\0\0\x1e\0\0\0\ +\x78\x03\0\0\0\0\0\0\xb0\0\0\0\x1e\0\0\0\x7c\x03\0\0\0\0\0\0\xc0\0\0\0\x23\0\0\ +\0\xaa\x03\0\0\0\0\0\0\xd8\0\0\0\x24\0\0\0\xf7\0\0\0\0\0\0\0\xf0\0\0\0\x24\0\0\ +\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x28\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1e\0\ +\0\0\xf7\0\0\0\0\0\0\0\x60\x01\0\0\x24\0\0\0\x6c\x04\0\0\0\0\0\0\x88\x01\0\0\ +\x1e\0\0\0\x27\x01\0\0\0\0\0\0\x98\x01\0\0\x1e\0\0\0\xad\x04\0\0\0\0\0\0\xa0\ +\x01\0\0\x1c\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x41\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\ +\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\ +\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x19\0\0\0\x01\0\0\0\0\0\0\0\ +\x12\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\ +\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0"; + opts.insns_sz = 2456; + opts.insns = (void *)"\ +\xbf\x16\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x78\xff\xff\xff\xb7\x02\0\ +\0\x88\0\0\0\xb7\x03\0\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x05\0\x14\0\0\0\0\0\x61\ +\xa1\x78\xff\0\0\0\0\xd5\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x7c\xff\ +\0\0\0\0\xd5\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x80\xff\0\0\0\0\xd5\ +\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x84\xff\0\0\0\0\xd5\x01\x01\0\0\ +\0\0\0\x85\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\ +\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xbf\x70\0\0\ +\0\0\0\0\x95\0\0\0\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ +\xe8\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\ +\0\0\xe4\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\ +\0\0\0\0\xd8\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\ +\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\ +\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xd0\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\ +\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\xd4\xff\0\0\0\0\x63\x7a\x78\xff\0\0\0\0\ +\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x0f\0\0\x63\x01\0\0\0\ +\0\0\0\x61\x60\x1c\0\0\0\0\0\x15\0\x03\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ +\xfc\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\ +\0\xf0\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\ +\xc5\x07\xc3\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x71\0\0\0\0\0\ +\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x38\ +\x0f\0\0\xb7\x02\0\0\x7b\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\ +\0\0\0\x94\0\0\0\x05\0\x01\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x18\x62\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\x63\ +\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xb8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\ +\0\0\0\xc8\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\ +\x18\x61\0\0\0\0\0\0\0\0\0\0\xd0\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\ +\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xc0\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\ +\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x9f\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\x63\ +\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\xe0\x0f\0\0\ +\xb7\x03\0\0\x04\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x92\xff\ +\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ +\x20\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xf0\x0f\0\0\x18\ +\x61\0\0\0\0\0\0\0\0\0\0\x18\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\ +\0\0\0\x08\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x60\x12\0\0\x7b\x01\0\0\0\0\0\0\ +\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x70\x12\0\ +\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xa0\x11\0\0\x18\x61\0\0\0\0\ +\0\0\0\0\0\0\x90\x12\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\ +\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x12\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\ +\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x2c\x12\0\0\x63\x01\0\0\0\0\0\0\x79\x60\ +\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x12\0\0\x7b\x01\0\0\0\0\0\0\x61\ +\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x58\x12\0\0\x63\x01\0\0\0\0\0\ +\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x12\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\ +\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\ +\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x63\x70\x6c\0\0\0\0\0\ +\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\x18\x68\0\0\0\0\0\0\0\0\0\0\xa8\ +\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x12\0\0\xb7\x02\0\0\x17\0\0\0\xb7\x03\ +\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\ +\x07\x4d\xff\0\0\0\0\x75\x07\x03\0\0\0\0\0\x62\x08\x04\0\0\0\0\0\x6a\x08\x02\0\ +\0\0\0\0\x05\0\x0a\0\0\0\0\0\x63\x78\x04\0\0\0\0\0\xbf\x79\0\0\0\0\0\0\x77\x09\ +\0\0\x20\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\x63\x90\0\0\0\0\0\0\x55\ +\x09\x02\0\0\0\0\0\x6a\x08\x02\0\0\0\0\0\x05\0\x01\0\0\0\0\0\x6a\x08\x02\0\x40\ +\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\xb7\x03\0\ +\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\ +\0\0\x01\0\0\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\ +\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x80\x12\0\0\x61\x01\0\0\0\0\0\0\ +\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x2c\xff\ +\0\0\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\x18\ +\x61\0\0\0\0\0\0\0\0\0\0\xa8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\ +\0\0\0\xd8\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xa0\x17\0\0\x7b\x01\0\0\0\0\0\0\ +\x18\x60\0\0\0\0\0\0\0\0\0\0\xe0\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe8\x17\0\ +\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x14\0\0\x18\x61\0\0\0\0\ +\0\0\0\0\0\0\xf8\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x78\ +\x16\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x10\x18\0\0\x7b\x01\0\0\ +\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x17\0\0\x63\x01\ +\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb4\x17\0\0\x63\ +\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x17\0\0\ +\x7b\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\ +\x17\0\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x18\0\0\xb7\x02\0\ +\0\x12\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\ +\x07\0\0\0\0\0\0\xc5\x07\xf5\xfe\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x17\0\ +\0\x63\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\ +\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x98\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\ +\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x08\x18\0\0\ +\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\ +\0\0\xc5\x07\xe3\xfe\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\ +\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\ +\0\0\0\0\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\ +\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\ +\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0"; + err = bpf_load_and_run(&opts); + if (err < 0) + return err; + return 0; +} + +static inline struct iterators_bpf * +iterators_bpf__open_and_load(void) +{ + struct iterators_bpf *skel; + + skel = iterators_bpf__open(); + if (!skel) + return NULL; + if (iterators_bpf__load(skel)) { + iterators_bpf__destroy(skel); + return NULL; + } + return skel; +} + +__attribute__((unused)) static void +iterators_bpf__assert(struct iterators_bpf *s __attribute__((unused))) +{ +#ifdef __cplusplus +#define _Static_assert static_assert +#endif +#ifdef __cplusplus +#undef _Static_assert +#endif +} + +#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/preload/iterators/iterators.lskel.h b/kernel/bpf/preload/iterators/iterators.lskel.h deleted file mode 100644 index 70f236a82fe1..000000000000 --- a/kernel/bpf/preload/iterators/iterators.lskel.h +++ /dev/null @@ -1,425 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -/* THIS FILE IS AUTOGENERATED! */ -#ifndef __ITERATORS_BPF_SKEL_H__ -#define __ITERATORS_BPF_SKEL_H__ - -#include <bpf/skel_internal.h> - -struct iterators_bpf { - struct bpf_loader_ctx ctx; - struct { - struct bpf_map_desc rodata; - } maps; - struct { - struct bpf_prog_desc dump_bpf_map; - struct bpf_prog_desc dump_bpf_prog; - } progs; - struct { - int dump_bpf_map_fd; - int dump_bpf_prog_fd; - } links; - struct iterators_bpf__rodata { - } *rodata; -}; - -static inline int -iterators_bpf__dump_bpf_map__attach(struct iterators_bpf *skel) -{ - int prog_fd = skel->progs.dump_bpf_map.prog_fd; - int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); - - if (fd > 0) - skel->links.dump_bpf_map_fd = fd; - return fd; -} - -static inline int -iterators_bpf__dump_bpf_prog__attach(struct iterators_bpf *skel) -{ - int prog_fd = skel->progs.dump_bpf_prog.prog_fd; - int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); - - if (fd > 0) - skel->links.dump_bpf_prog_fd = fd; - return fd; -} - -static inline int -iterators_bpf__attach(struct iterators_bpf *skel) -{ - int ret = 0; - - ret = ret < 0 ? ret : iterators_bpf__dump_bpf_map__attach(skel); - ret = ret < 0 ? ret : iterators_bpf__dump_bpf_prog__attach(skel); - return ret < 0 ? ret : 0; -} - -static inline void -iterators_bpf__detach(struct iterators_bpf *skel) -{ - skel_closenz(skel->links.dump_bpf_map_fd); - skel_closenz(skel->links.dump_bpf_prog_fd); -} -static void -iterators_bpf__destroy(struct iterators_bpf *skel) -{ - if (!skel) - return; - iterators_bpf__detach(skel); - skel_closenz(skel->progs.dump_bpf_map.prog_fd); - skel_closenz(skel->progs.dump_bpf_prog.prog_fd); - skel_free_map_data(skel->rodata, skel->maps.rodata.initial_value, 4096); - skel_closenz(skel->maps.rodata.map_fd); - skel_free(skel); -} -static inline struct iterators_bpf * -iterators_bpf__open(void) -{ - struct iterators_bpf *skel; - - skel = skel_alloc(sizeof(*skel)); - if (!skel) - goto cleanup; - skel->ctx.sz = (void *)&skel->links - (void *)skel; - skel->rodata = skel_prep_map_data((void *)"\ -\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ -\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\ -\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\ -\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\ -\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0", 4096, 98); - if (!skel->rodata) - goto cleanup; - skel->maps.rodata.initial_value = (__u64) (long) skel->rodata; - return skel; -cleanup: - iterators_bpf__destroy(skel); - return NULL; -} - -static inline int -iterators_bpf__load(struct iterators_bpf *skel) -{ - struct bpf_load_and_run_opts opts = {}; - int err; - - opts.ctx = (struct bpf_loader_ctx *)skel; - opts.data_sz = 6056; - opts.data = (void *)"\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x9f\xeb\x01\0\ -\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\xf9\x04\0\0\0\0\0\0\0\0\0\x02\x02\0\ -\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\0\x04\ -\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\0\0\0\0\0\ -\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\0\0\0\x20\ -\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\0\0\xb1\0\ -\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\0\0\x80\0\ -\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\0\0\0\0\ -\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x94\x01\0\0\x03\0\0\x04\ -\x18\0\0\0\x9c\x01\0\0\x0e\0\0\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xa4\ -\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb0\x01\0\0\0\0\0\x08\x0f\0\0\0\xb6\x01\0\0\0\0\0\ -\x01\x04\0\0\0\x20\0\0\0\xc3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\ -\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xc8\x01\0\0\0\0\0\x01\x04\0\0\0\ -\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x2c\x02\0\0\x02\0\0\x04\x10\0\0\0\x13\0\ -\0\0\x03\0\0\0\0\0\0\0\x3f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x18\0\ -\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x44\x02\0\0\x01\0\0\x0c\ -\x16\0\0\0\x90\x02\0\0\x01\0\0\x04\x08\0\0\0\x99\x02\0\0\x19\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\x02\x1a\0\0\0\xea\x02\0\0\x06\0\0\x04\x38\0\0\0\x9c\x01\0\0\x0e\0\0\ -\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xf7\x02\0\0\x1b\0\0\0\xc0\0\0\0\x08\ -\x03\0\0\x15\0\0\0\0\x01\0\0\x11\x03\0\0\x1d\0\0\0\x40\x01\0\0\x1b\x03\0\0\x1e\ -\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\0\0\0\0\ -\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x65\x03\0\0\x02\0\0\x04\ -\x08\0\0\0\x73\x03\0\0\x0e\0\0\0\0\0\0\0\x7c\x03\0\0\x0e\0\0\0\x20\0\0\0\x1b\ -\x03\0\0\x03\0\0\x04\x18\0\0\0\x86\x03\0\0\x1b\0\0\0\0\0\0\0\x8e\x03\0\0\x21\0\ -\0\0\x40\0\0\0\x94\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\0\0\0\ -\0\0\0\0\0\x02\x24\0\0\0\x98\x03\0\0\x01\0\0\x04\x04\0\0\0\xa3\x03\0\0\x0e\0\0\ -\0\0\0\0\0\x0c\x04\0\0\x01\0\0\x04\x04\0\0\0\x15\x04\0\0\x0e\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x8b\x04\0\0\0\0\0\x0e\x25\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\x9f\x04\ -\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\ -\x20\0\0\0\xb5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\ -\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xca\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe1\x04\0\0\0\0\0\x0e\x2d\0\0\ -\0\x01\0\0\0\xe9\x04\0\0\x04\0\0\x0f\x62\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\0\x28\ -\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\0\0\ -\x11\0\0\0\xf1\x04\0\0\x01\0\0\x0f\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\x62\ -\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\ -\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\x70\ -\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x30\ -\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\x65\ -\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\ -\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\ -\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\ -\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\ -\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\ -\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\ -\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\x6e\ -\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\x74\ -\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\ -\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\ -\x29\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x20\x63\ -\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\x3b\0\x30\ -\x3a\x32\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\ -\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\ -\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\ -\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\ -\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\ -\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\ -\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\ -\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\ -\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\ -\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\ -\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\ -\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\ -\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\ -\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\ -\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\ -\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\ -\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\ -\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\ -\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\ -\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\ -\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\ -\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\ -\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\ -\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\ -\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\ -\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\ -\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\ -\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\ -\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\ -\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\ -\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\ -\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\ -\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\ -\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\ -\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\ -\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\ -\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\ -\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\ -\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\ -\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\ -\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\ -\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\ -\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ -\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ -\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\ -\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\ -\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\ -\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2d\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\ -\0\x04\0\0\0\x62\0\0\0\x01\0\0\0\x80\x04\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\ -\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x2f\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\ -\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\ -\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\ -\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ -\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\ -\x25\x73\x20\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\ -\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1b\0\0\ -\0\0\0\x79\x11\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\ -\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x23\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\ -\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\ -\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\x7b\x2a\xf0\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\ -\x7b\x1a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\ -\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x23\0\0\0\xb7\x03\0\0\x0e\0\0\0\ -\xb7\x05\0\0\x18\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ -\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x3c\x01\0\x01\0\0\0\x42\0\0\ -\0\x7b\0\0\0\x24\x3c\x01\0\x02\0\0\0\x42\0\0\0\xee\0\0\0\x1d\x44\x01\0\x03\0\0\ -\0\x42\0\0\0\x0f\x01\0\0\x06\x4c\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\x40\ -\x01\0\x05\0\0\0\x42\0\0\0\x1a\x01\0\0\x1d\x40\x01\0\x06\0\0\0\x42\0\0\0\x43\ -\x01\0\0\x06\x58\x01\0\x08\0\0\0\x42\0\0\0\x56\x01\0\0\x03\x5c\x01\0\x0f\0\0\0\ -\x42\0\0\0\xdc\x01\0\0\x02\x64\x01\0\x1f\0\0\0\x42\0\0\0\x2a\x02\0\0\x01\x6c\ -\x01\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\ -\0\x10\0\0\0\x02\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\ -\x28\0\0\0\x08\0\0\0\x3f\x01\0\0\0\0\0\0\x78\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\ -\x88\0\0\0\x0d\0\0\0\xea\0\0\0\0\0\0\0\xa8\0\0\0\x0d\0\0\0\x3f\x01\0\0\0\0\0\0\ -\x1a\0\0\0\x21\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\ -\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\ -\0\0\0\0\0\x0a\0\0\0\x01\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x6d\ -\x61\x70\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\ -\0\0\0\0\x79\x12\x08\0\0\0\0\0\x15\x02\x3c\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x79\ -\x27\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\ -\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\ -\x31\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x7b\ -\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xb7\x03\0\0\ -\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\x71\x28\0\0\0\0\0\x79\ -\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\ -\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\0\x03\0\0\0\x0f\x13\0\ -\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\ -\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\ -\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\ -\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\ -\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\ -\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\ -\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\ -\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\x79\xa1\ -\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x51\0\0\0\xb7\x03\0\0\x11\0\0\0\ -\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ -\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x80\x01\0\x01\0\0\0\x42\0\0\ -\0\x7b\0\0\0\x24\x80\x01\0\x02\0\0\0\x42\0\0\0\x60\x02\0\0\x1f\x88\x01\0\x03\0\ -\0\0\x42\0\0\0\x84\x02\0\0\x06\x94\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\ -\x84\x01\0\x05\0\0\0\x42\0\0\0\x9d\x02\0\0\x0e\xa0\x01\0\x06\0\0\0\x42\0\0\0\ -\x1a\x01\0\0\x1d\x84\x01\0\x07\0\0\0\x42\0\0\0\x43\x01\0\0\x06\xa4\x01\0\x09\0\ -\0\0\x42\0\0\0\xaf\x02\0\0\x03\xa8\x01\0\x11\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\ -\xb0\x01\0\x18\0\0\0\x42\0\0\0\x5a\x03\0\0\x06\x04\x01\0\x1b\0\0\0\x42\0\0\0\0\ -\0\0\0\0\0\0\0\x1c\0\0\0\x42\0\0\0\xab\x03\0\0\x0f\x10\x01\0\x1d\0\0\0\x42\0\0\ -\0\xc0\x03\0\0\x2d\x14\x01\0\x1f\0\0\0\x42\0\0\0\xf7\x03\0\0\x0d\x0c\x01\0\x21\ -\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x22\0\0\0\x42\0\0\0\xc0\x03\0\0\x02\x14\x01\0\ -\x25\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x28\0\0\0\x42\0\0\0\0\0\0\0\0\0\ -\0\0\x29\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x1e\x04\ -\0\0\x0d\x18\x01\0\x2d\0\0\0\x42\0\0\0\x4c\x04\0\0\x1b\x1c\x01\0\x2e\0\0\0\x42\ -\0\0\0\x4c\x04\0\0\x06\x1c\x01\0\x2f\0\0\0\x42\0\0\0\x6f\x04\0\0\x0d\x24\x01\0\ -\x31\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\xb0\x01\0\x40\0\0\0\x42\0\0\0\x2a\x02\0\0\ -\x01\xc0\x01\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\ -\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x14\0\0\0\x3e\0\0\0\ -\0\0\0\0\x28\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x30\0\0\0\x08\0\0\0\x3f\x01\0\0\ -\0\0\0\0\x88\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x98\0\0\0\x1a\0\0\0\xea\0\0\0\0\ -\0\0\0\xb0\0\0\0\x1a\0\0\0\x52\x03\0\0\0\0\0\0\xb8\0\0\0\x1a\0\0\0\x56\x03\0\0\ -\0\0\0\0\xc8\0\0\0\x1f\0\0\0\x84\x03\0\0\0\0\0\0\xe0\0\0\0\x20\0\0\0\xea\0\0\0\ -\0\0\0\0\xf8\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x20\x01\0\0\x24\0\0\0\x3e\0\0\0\ -\0\0\0\0\x58\x01\0\0\x1a\0\0\0\xea\0\0\0\0\0\0\0\x68\x01\0\0\x20\0\0\0\x46\x04\ -\0\0\0\0\0\0\x90\x01\0\0\x1a\0\0\0\x3f\x01\0\0\0\0\0\0\xa0\x01\0\0\x1a\0\0\0\ -\x87\x04\0\0\0\0\0\0\xa8\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x42\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\ -\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x1a\0\ -\0\0\x01\0\0\0\0\0\0\0\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\ -\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\ -\0\0\0\0"; - opts.insns_sz = 2216; - opts.insns = (void *)"\ -\xbf\x16\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x78\xff\xff\xff\xb7\x02\0\ -\0\x88\0\0\0\xb7\x03\0\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x05\0\x14\0\0\0\0\0\x61\ -\xa1\x78\xff\0\0\0\0\xd5\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x7c\xff\ -\0\0\0\0\xd5\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x80\xff\0\0\0\0\xd5\ -\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x84\xff\0\0\0\0\xd5\x01\x01\0\0\ -\0\0\0\x85\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\ -\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xbf\x70\0\0\ -\0\0\0\0\x95\0\0\0\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ -\x48\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\ -\0\0\x44\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\ -\0\0\0\0\x38\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\ -\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\ -\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\ -\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\xd4\xff\0\0\0\0\x63\x7a\x78\xff\0\0\0\0\ -\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x0e\0\0\x63\x01\0\0\0\ -\0\0\0\x61\x60\x1c\0\0\0\0\0\x15\0\x03\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ -\x5c\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\ -\0\x50\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\ -\xc5\x07\xc3\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x71\0\0\0\0\0\ -\0\x79\x63\x20\0\0\0\0\0\x15\x03\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x98\ -\x0e\0\0\xb7\x02\0\0\x62\0\0\0\x61\x60\x04\0\0\0\0\0\x45\0\x02\0\x01\0\0\0\x85\ -\0\0\0\x94\0\0\0\x05\0\x01\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x18\x62\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\x63\ -\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\ -\0\0\x10\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x0e\0\0\ -\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\ -\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\ -\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x9f\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\x63\ -\x01\0\0\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\ -\xb7\x03\0\0\x04\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x92\xff\ -\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ -\x78\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\x18\ -\x61\0\0\0\0\0\0\0\0\0\0\x70\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\ -\0\0\0\x40\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x11\0\0\x7b\x01\0\0\0\0\0\0\ -\x18\x60\0\0\0\0\0\0\0\0\0\0\x48\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc8\x11\0\ -\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x10\0\0\x18\x61\0\0\0\0\ -\0\0\0\0\0\0\xe8\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xe0\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\ -\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x11\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\ -\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x84\x11\0\0\x63\x01\0\0\0\0\0\0\x79\x60\ -\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\ -\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x11\0\0\x63\x01\0\0\0\0\0\ -\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xf8\x11\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\ -\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\ -\x5c\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x68\x11\0\0\x63\x70\x6c\0\0\0\0\0\ -\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\ -\0\0\0\0\0\0\0\0\x68\x11\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\ -\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd8\x11\0\0\x61\x01\0\0\0\0\0\0\xd5\ -\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x4a\xff\0\0\ -\0\0\x63\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x18\x61\0\ -\0\0\0\0\0\0\0\0\0\x10\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\ -\x18\x12\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\ -\x60\0\0\0\0\0\0\0\0\0\0\x28\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x50\x17\0\0\ -\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x14\0\0\x18\x61\0\0\0\0\0\ -\0\0\0\0\0\x60\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x15\ -\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x78\x17\0\0\x7b\x01\0\0\0\0\ -\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x17\0\0\x63\x01\0\0\ -\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x1c\x17\0\0\x63\x01\ -\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\x7b\ -\x01\0\0\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x48\x17\0\ -\0\x63\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x90\x17\0\0\xb7\x02\0\0\x12\ -\0\0\0\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\ -\0\0\0\0\0\xc5\x07\x13\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\x63\ -\x70\x6c\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\ -\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\ -\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x70\x17\0\0\x61\x01\ -\0\0\0\0\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\ -\x07\x01\xff\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\xd5\x01\ -\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\0\0\0\0\ -\x63\x06\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\x18\x61\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\xb7\0\0\0\ -\0\0\0\0\x95\0\0\0\0\0\0\0"; - err = bpf_load_and_run(&opts); - if (err < 0) - return err; - skel->rodata = skel_finalize_map_data(&skel->maps.rodata.initial_value, - 4096, PROT_READ, skel->maps.rodata.map_fd); - if (!skel->rodata) - return -ENOMEM; - return 0; -} - -static inline struct iterators_bpf * -iterators_bpf__open_and_load(void) -{ - struct iterators_bpf *skel; - - skel = iterators_bpf__open(); - if (!skel) - return NULL; - if (iterators_bpf__load(skel)) { - iterators_bpf__destroy(skel); - return NULL; - } - return skel; -} - -#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/prog_iter.c b/kernel/bpf/prog_iter.c index 53a73c841c13..85d8fcb56fb7 100644 --- a/kernel/bpf/prog_iter.c +++ b/kernel/bpf/prog_iter.c @@ -78,8 +78,7 @@ static const struct seq_operations bpf_prog_seq_ops = { .show = bpf_prog_seq_show, }; -BTF_ID_LIST(btf_bpf_prog_id) -BTF_ID(struct, bpf_prog) +BTF_ID_LIST_SINGLE(btf_bpf_prog_id, struct, bpf_prog) static const struct bpf_iter_seq_info bpf_prog_seq_info = { .seq_ops = &bpf_prog_seq_ops, diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8a5e060de63b..9a5f94371e50 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -7,16 +7,16 @@ #include <linux/bpf.h> #include <linux/list.h> #include <linux/slab.h> -#include <linux/capability.h> #include <linux/btf_ids.h> #include "percpu_freelist.h" +#include <asm/rqspinlock.h> #define QUEUE_STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) struct bpf_queue_stack { struct bpf_map map; - raw_spinlock_t lock; + rqspinlock_t lock; u32 head, tail; u32 size; /* max_entries + 1 */ @@ -46,9 +46,6 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) /* Called from syscall */ static int queue_stack_map_alloc_check(union bpf_attr *attr) { - if (!bpf_capable()) - return -EPERM; - /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || attr->value_size == 0 || @@ -82,7 +79,7 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) qs->size = size; - raw_spin_lock_init(&qs->lock); + raw_res_spin_lock_init(&qs->lock); return &qs->map; } @@ -95,14 +92,15 @@ static void queue_stack_map_free(struct bpf_map *map) bpf_map_area_free(qs); } -static int __queue_map_get(struct bpf_map *map, void *value, bool delete) +static long __queue_map_get(struct bpf_map *map, void *value, bool delete) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long flags; int err = 0; void *ptr; - raw_spin_lock_irqsave(&qs->lock, flags); + if (raw_res_spin_lock_irqsave(&qs->lock, flags)) + return -EBUSY; if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -119,12 +117,12 @@ static int __queue_map_get(struct bpf_map *map, void *value, bool delete) } out: - raw_spin_unlock_irqrestore(&qs->lock, flags); + raw_res_spin_unlock_irqrestore(&qs->lock, flags); return err; } -static int __stack_map_get(struct bpf_map *map, void *value, bool delete) +static long __stack_map_get(struct bpf_map *map, void *value, bool delete) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long flags; @@ -132,7 +130,8 @@ static int __stack_map_get(struct bpf_map *map, void *value, bool delete) void *ptr; u32 index; - raw_spin_lock_irqsave(&qs->lock, flags); + if (raw_res_spin_lock_irqsave(&qs->lock, flags)) + return -EBUSY; if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -151,37 +150,37 @@ static int __stack_map_get(struct bpf_map *map, void *value, bool delete) qs->head = index; out: - raw_spin_unlock_irqrestore(&qs->lock, flags); + raw_res_spin_unlock_irqrestore(&qs->lock, flags); return err; } /* Called from syscall or from eBPF program */ -static int queue_map_peek_elem(struct bpf_map *map, void *value) +static long queue_map_peek_elem(struct bpf_map *map, void *value) { return __queue_map_get(map, value, false); } /* Called from syscall or from eBPF program */ -static int stack_map_peek_elem(struct bpf_map *map, void *value) +static long stack_map_peek_elem(struct bpf_map *map, void *value) { return __stack_map_get(map, value, false); } /* Called from syscall or from eBPF program */ -static int queue_map_pop_elem(struct bpf_map *map, void *value) +static long queue_map_pop_elem(struct bpf_map *map, void *value) { return __queue_map_get(map, value, true); } /* Called from syscall or from eBPF program */ -static int stack_map_pop_elem(struct bpf_map *map, void *value) +static long stack_map_pop_elem(struct bpf_map *map, void *value) { return __stack_map_get(map, value, true); } /* Called from syscall or from eBPF program */ -static int queue_stack_map_push_elem(struct bpf_map *map, void *value, - u64 flags) +static long queue_stack_map_push_elem(struct bpf_map *map, void *value, + u64 flags) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long irq_flags; @@ -197,7 +196,8 @@ static int queue_stack_map_push_elem(struct bpf_map *map, void *value, if (flags & BPF_NOEXIST || flags > BPF_EXIST) return -EINVAL; - raw_spin_lock_irqsave(&qs->lock, irq_flags); + if (raw_res_spin_lock_irqsave(&qs->lock, irq_flags)) + return -EBUSY; if (queue_stack_map_is_full(qs)) { if (!replace) { @@ -216,7 +216,7 @@ static int queue_stack_map_push_elem(struct bpf_map *map, void *value, qs->head = 0; out: - raw_spin_unlock_irqrestore(&qs->lock, irq_flags); + raw_res_spin_unlock_irqrestore(&qs->lock, irq_flags); return err; } @@ -227,14 +227,14 @@ static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key) } /* Called from syscall or from eBPF program */ -static int queue_stack_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long queue_stack_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { return -EINVAL; } /* Called from syscall or from eBPF program */ -static int queue_stack_map_delete_elem(struct bpf_map *map, void *key) +static long queue_stack_map_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } @@ -246,6 +246,14 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, return -EINVAL; } +static u64 queue_stack_map_mem_usage(const struct bpf_map *map) +{ + u64 usage = sizeof(struct bpf_queue_stack); + + usage += ((u64)map->max_entries + 1) * map->value_size; + return usage; +} + BTF_ID_LIST_SINGLE(queue_map_btf_ids, struct, bpf_queue_stack) const struct bpf_map_ops queue_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -259,6 +267,7 @@ const struct bpf_map_ops queue_map_ops = { .map_pop_elem = queue_map_pop_elem, .map_peek_elem = queue_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, + .map_mem_usage = queue_stack_map_mem_usage, .map_btf_id = &queue_map_btf_ids[0], }; @@ -274,5 +283,6 @@ const struct bpf_map_ops stack_map_ops = { .map_pop_elem = stack_map_pop_elem, .map_peek_elem = stack_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, + .map_mem_usage = queue_stack_map_mem_usage, .map_btf_id = &queue_map_btf_ids[0], }; diff --git a/kernel/bpf/range_tree.c b/kernel/bpf/range_tree.c new file mode 100644 index 000000000000..99c63d982c5d --- /dev/null +++ b/kernel/bpf/range_tree.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <linux/interval_tree_generic.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#include "range_tree.h" + +/* + * struct range_tree is a data structure used to allocate contiguous memory + * ranges in bpf arena. It's a large bitmap. The contiguous sequence of bits is + * represented by struct range_node or 'rn' for short. + * rn->rn_rbnode links it into an interval tree while + * rn->rb_range_size links it into a second rbtree sorted by size of the range. + * __find_range() performs binary search and best fit algorithm to find the + * range less or equal requested size. + * range_tree_clear/set() clears or sets a range of bits in this bitmap. The + * adjacent ranges are merged or split at the same time. + * + * The split/merge logic is based/borrowed from XFS's xbitmap32 added + * in commit 6772fcc8890a ("xfs: convert xbitmap to interval tree"). + * + * The implementation relies on external lock to protect rbtree-s. + * The alloc/free of range_node-s is done via kmalloc_nolock(). + * + * bpf arena is using range_tree to represent unallocated slots. + * At init time: + * range_tree_set(rt, 0, max); + * Then: + * start = range_tree_find(rt, len); + * if (start >= 0) + * range_tree_clear(rt, start, len); + * to find free range and mark slots as allocated and later: + * range_tree_set(rt, start, len); + * to mark as unallocated after use. + */ +struct range_node { + struct rb_node rn_rbnode; + struct rb_node rb_range_size; + u32 rn_start; + u32 rn_last; /* inclusive */ + u32 __rn_subtree_last; +}; + +static struct range_node *rb_to_range_node(struct rb_node *rb) +{ + return rb_entry(rb, struct range_node, rb_range_size); +} + +static u32 rn_size(struct range_node *rn) +{ + return rn->rn_last - rn->rn_start + 1; +} + +/* Find range that fits best to requested size */ +static inline struct range_node *__find_range(struct range_tree *rt, u32 len) +{ + struct rb_node *rb = rt->range_size_root.rb_root.rb_node; + struct range_node *best = NULL; + + while (rb) { + struct range_node *rn = rb_to_range_node(rb); + + if (len <= rn_size(rn)) { + best = rn; + rb = rb->rb_right; + } else { + rb = rb->rb_left; + } + } + + return best; +} + +s64 range_tree_find(struct range_tree *rt, u32 len) +{ + struct range_node *rn; + + rn = __find_range(rt, len); + if (!rn) + return -ENOENT; + return rn->rn_start; +} + +/* Insert the range into rbtree sorted by the range size */ +static inline void __range_size_insert(struct range_node *rn, + struct rb_root_cached *root) +{ + struct rb_node **link = &root->rb_root.rb_node, *rb = NULL; + u64 size = rn_size(rn); + bool leftmost = true; + + while (*link) { + rb = *link; + if (size > rn_size(rb_to_range_node(rb))) { + link = &rb->rb_left; + } else { + link = &rb->rb_right; + leftmost = false; + } + } + + rb_link_node(&rn->rb_range_size, rb, link); + rb_insert_color_cached(&rn->rb_range_size, root, leftmost); +} + +#define START(node) ((node)->rn_start) +#define LAST(node) ((node)->rn_last) + +INTERVAL_TREE_DEFINE(struct range_node, rn_rbnode, u32, + __rn_subtree_last, START, LAST, + static inline __maybe_unused, + __range_it) + +static inline __maybe_unused void +range_it_insert(struct range_node *rn, struct range_tree *rt) +{ + __range_size_insert(rn, &rt->range_size_root); + __range_it_insert(rn, &rt->it_root); +} + +static inline __maybe_unused void +range_it_remove(struct range_node *rn, struct range_tree *rt) +{ + rb_erase_cached(&rn->rb_range_size, &rt->range_size_root); + RB_CLEAR_NODE(&rn->rb_range_size); + __range_it_remove(rn, &rt->it_root); +} + +static inline __maybe_unused struct range_node * +range_it_iter_first(struct range_tree *rt, u32 start, u32 last) +{ + return __range_it_iter_first(&rt->it_root, start, last); +} + +/* Clear the range in this range tree */ +int range_tree_clear(struct range_tree *rt, u32 start, u32 len) +{ + u32 last = start + len - 1; + struct range_node *new_rn; + struct range_node *rn; + + while ((rn = range_it_iter_first(rt, start, last))) { + if (rn->rn_start < start && rn->rn_last > last) { + u32 old_last = rn->rn_last; + + /* Overlaps with the entire clearing range */ + range_it_remove(rn, rt); + rn->rn_last = start - 1; + range_it_insert(rn, rt); + + /* Add a range */ + new_rn = kmalloc_nolock(sizeof(struct range_node), 0, NUMA_NO_NODE); + if (!new_rn) + return -ENOMEM; + new_rn->rn_start = last + 1; + new_rn->rn_last = old_last; + range_it_insert(new_rn, rt); + } else if (rn->rn_start < start) { + /* Overlaps with the left side of the clearing range */ + range_it_remove(rn, rt); + rn->rn_last = start - 1; + range_it_insert(rn, rt); + } else if (rn->rn_last > last) { + /* Overlaps with the right side of the clearing range */ + range_it_remove(rn, rt); + rn->rn_start = last + 1; + range_it_insert(rn, rt); + break; + } else { + /* in the middle of the clearing range */ + range_it_remove(rn, rt); + kfree_nolock(rn); + } + } + return 0; +} + +/* Is the whole range set ? */ +int is_range_tree_set(struct range_tree *rt, u32 start, u32 len) +{ + u32 last = start + len - 1; + struct range_node *left; + + /* Is this whole range set ? */ + left = range_it_iter_first(rt, start, last); + if (left && left->rn_start <= start && left->rn_last >= last) + return 0; + return -ESRCH; +} + +/* Set the range in this range tree */ +int range_tree_set(struct range_tree *rt, u32 start, u32 len) +{ + u32 last = start + len - 1; + struct range_node *right; + struct range_node *left; + int err; + + /* Is this whole range already set ? */ + left = range_it_iter_first(rt, start, last); + if (left && left->rn_start <= start && left->rn_last >= last) + return 0; + + /* Clear out everything in the range we want to set. */ + err = range_tree_clear(rt, start, len); + if (err) + return err; + + /* Do we have a left-adjacent range ? */ + left = range_it_iter_first(rt, start - 1, start - 1); + if (left && left->rn_last + 1 != start) + return -EFAULT; + + /* Do we have a right-adjacent range ? */ + right = range_it_iter_first(rt, last + 1, last + 1); + if (right && right->rn_start != last + 1) + return -EFAULT; + + if (left && right) { + /* Combine left and right adjacent ranges */ + range_it_remove(left, rt); + range_it_remove(right, rt); + left->rn_last = right->rn_last; + range_it_insert(left, rt); + kfree_nolock(right); + } else if (left) { + /* Combine with the left range */ + range_it_remove(left, rt); + left->rn_last = last; + range_it_insert(left, rt); + } else if (right) { + /* Combine with the right range */ + range_it_remove(right, rt); + right->rn_start = start; + range_it_insert(right, rt); + } else { + left = kmalloc_nolock(sizeof(struct range_node), 0, NUMA_NO_NODE); + if (!left) + return -ENOMEM; + left->rn_start = start; + left->rn_last = last; + range_it_insert(left, rt); + } + return 0; +} + +void range_tree_destroy(struct range_tree *rt) +{ + struct range_node *rn; + + while ((rn = range_it_iter_first(rt, 0, -1U))) { + range_it_remove(rn, rt); + kfree_nolock(rn); + } +} + +void range_tree_init(struct range_tree *rt) +{ + rt->it_root = RB_ROOT_CACHED; + rt->range_size_root = RB_ROOT_CACHED; +} diff --git a/kernel/bpf/range_tree.h b/kernel/bpf/range_tree.h new file mode 100644 index 000000000000..ff0b9110eb71 --- /dev/null +++ b/kernel/bpf/range_tree.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#ifndef _RANGE_TREE_H +#define _RANGE_TREE_H 1 + +struct range_tree { + /* root of interval tree */ + struct rb_root_cached it_root; + /* root of rbtree of interval sizes */ + struct rb_root_cached range_size_root; +}; + +void range_tree_init(struct range_tree *rt); +void range_tree_destroy(struct range_tree *rt); + +int range_tree_clear(struct range_tree *rt, u32 start, u32 len); +int range_tree_set(struct range_tree *rt, u32 start, u32 len); +int is_range_tree_set(struct range_tree *rt, u32 start, u32 len); +s64 range_tree_find(struct range_tree *rt, u32 len); + +#endif diff --git a/kernel/bpf/relo_core.c b/kernel/bpf/relo_core.c new file mode 100644 index 000000000000..aa822c9fcfde --- /dev/null +++ b/kernel/bpf/relo_core.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#include "../../tools/lib/bpf/relo_core.c" diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 82c61612f382..49b8e5a0c6b4 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -59,7 +59,7 @@ static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key) } /* Called from syscall only */ -static int reuseport_array_delete_elem(struct bpf_map *map, void *key) +static long reuseport_array_delete_elem(struct bpf_map *map, void *key) { struct reuseport_array *array = reuseport_array(map); u32 index = *(u32 *)key; @@ -151,9 +151,6 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) int numa_node = bpf_map_attr_numa_node(attr); struct reuseport_array *array; - if (!bpf_capable()) - return ERR_PTR(-EPERM); - /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(struct_size(array, ptrs, attr->max_entries), numa_node); if (!array) @@ -311,7 +308,7 @@ put_file_unlock: spin_unlock_bh(&reuseport_lock); put_file: - fput(socket->file); + sockfd_put(socket); return err; } @@ -335,6 +332,13 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key, return 0; } +static u64 reuseport_array_mem_usage(const struct bpf_map *map) +{ + struct reuseport_array *array; + + return struct_size(array, ptrs, map->max_entries); +} + BTF_ID_LIST_SINGLE(reuseport_array_map_btf_ids, struct, reuseport_array) const struct bpf_map_ops reuseport_array_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -344,5 +348,6 @@ const struct bpf_map_ops reuseport_array_ops = { .map_lookup_elem = reuseport_array_lookup_elem, .map_get_next_key = reuseport_array_get_next_key, .map_delete_elem = reuseport_array_delete_elem, + .map_mem_usage = reuseport_array_mem_usage, .map_btf_id = &reuseport_array_map_btf_ids[0], }; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 80f4b4d88aaf..f6a075ffac63 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -11,33 +11,27 @@ #include <linux/kmemleak.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> +#include <asm/rqspinlock.h> -#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) +#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE | BPF_F_RB_OVERWRITE) /* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */ #define RINGBUF_PGOFF \ (offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT) /* consumer page and producer page */ #define RINGBUF_POS_PAGES 2 +#define RINGBUF_NR_META_PAGES (RINGBUF_PGOFF + RINGBUF_POS_PAGES) #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4) -/* Maximum size of ring buffer area is limited by 32-bit page offset within - * record header, counted in pages. Reserve 8 bits for extensibility, and take - * into account few extra pages for consumer/producer pages and - * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single - * ring buffer. - */ -#define RINGBUF_MAX_DATA_SZ \ - (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE) - struct bpf_ringbuf { wait_queue_head_t waitq; struct irq_work work; u64 mask; struct page **pages; int nr_pages; - spinlock_t spinlock ____cacheline_aligned_in_smp; + bool overwrite_mode; + rqspinlock_t spinlock ____cacheline_aligned_in_smp; /* For user-space producer ring buffers, an atomic_t busy bit is used * to synchronize access to the ring buffers in the kernel, rather than * the spinlock that is used for kernel-producer ring buffers. This is @@ -59,7 +53,8 @@ struct bpf_ringbuf { * This prevents a user-space application from modifying the * position and ruining in-kernel tracking. The permissions of the * pages depend on who is producing samples: user-space or the - * kernel. + * kernel. Note that the pending counter is placed in the same + * page as the producer, so that it shares the same cache line. * * Kernel-producer * --------------- @@ -78,6 +73,8 @@ struct bpf_ringbuf { */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); + unsigned long pending_pos; + unsigned long overwrite_pos; /* position after the last overwritten record */ char data[] __aligned(PAGE_SIZE); }; @@ -96,7 +93,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | __GFP_ZERO; - int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; + int nr_meta_pages = RINGBUF_NR_META_PAGES; int nr_data_pages = data_sz >> PAGE_SHIFT; int nr_pages = nr_meta_pages + nr_data_pages; struct page **pages, *page; @@ -160,7 +157,18 @@ static void bpf_ringbuf_notify(struct irq_work *work) wake_up_all(&rb->waitq); } -static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) +/* Maximum size of ring buffer area is limited by 32-bit page offset within + * record header, counted in pages. Reserve 8 bits for extensibility, and + * take into account few extra pages for consumer/producer pages and + * non-mmap()'able parts, the current maximum size would be: + * + * (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE) + * + * This gives 64GB limit, which seems plenty for single ring buffer. Now + * considering that the maximum value of data_sz is (4GB - 1), there + * will be no overflow, so just note the size limit in the comments. + */ +static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node, bool overwrite_mode) { struct bpf_ringbuf *rb; @@ -168,7 +176,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) if (!rb) return NULL; - spin_lock_init(&rb->spinlock); + raw_res_spin_lock_init(&rb->spinlock); atomic_set(&rb->busy, 0); init_waitqueue_head(&rb->waitq); init_irq_work(&rb->work, bpf_ringbuf_notify); @@ -176,35 +184,38 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) rb->mask = data_sz - 1; rb->consumer_pos = 0; rb->producer_pos = 0; + rb->pending_pos = 0; + rb->overwrite_mode = overwrite_mode; return rb; } static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { + bool overwrite_mode = false; struct bpf_ringbuf_map *rb_map; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); + if (attr->map_flags & BPF_F_RB_OVERWRITE) { + if (attr->map_type != BPF_MAP_TYPE_RINGBUF) + return ERR_PTR(-EINVAL); + overwrite_mode = true; + } + if (attr->key_size || attr->value_size || !is_power_of_2(attr->max_entries) || !PAGE_ALIGNED(attr->max_entries)) return ERR_PTR(-EINVAL); -#ifdef CONFIG_64BIT - /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ - if (attr->max_entries > RINGBUF_MAX_DATA_SZ) - return ERR_PTR(-E2BIG); -#endif - rb_map = bpf_map_area_alloc(sizeof(*rb_map), NUMA_NO_NODE); if (!rb_map) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&rb_map->map, attr); - rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); + rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node, overwrite_mode); if (!rb_map->rb) { bpf_map_area_free(rb_map); return ERR_PTR(-ENOMEM); @@ -215,6 +226,8 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) static void bpf_ringbuf_free(struct bpf_ringbuf *rb) { + irq_work_sync(&rb->work); + /* copy pages pointer and nr_pages to local variable, as we are going * to unmap rb itself with vunmap() below */ @@ -241,13 +254,13 @@ static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) return ERR_PTR(-ENOTSUPP); } -static int ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 flags) +static long ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 flags) { return -ENOTSUPP; } -static int ringbuf_map_delete_elem(struct bpf_map *map, void *key) +static long ringbuf_map_delete_elem(struct bpf_map *map, void *key) { return -ENOTSUPP; } @@ -268,8 +281,6 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma /* allow writable mapping for the consumer_pos only */ if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; - } else { - vma->vm_flags &= ~VM_MAYWRITE; } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, @@ -289,20 +300,31 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma * position, and the ring buffer data itself. */ return -EPERM; - } else { - vma->vm_flags &= ~VM_MAYWRITE; } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } +/* + * Return an estimate of the available data in the ring buffer. + * Note: the returned value can exceed the actual ring buffer size because the + * function is not synchronized with the producer. The producer acquires the + * ring buffer's spinlock, but this function does not. + */ static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) { - unsigned long cons_pos, prod_pos; + unsigned long cons_pos, prod_pos, over_pos; cons_pos = smp_load_acquire(&rb->consumer_pos); - prod_pos = smp_load_acquire(&rb->producer_pos); - return prod_pos - cons_pos; + + if (unlikely(rb->overwrite_mode)) { + over_pos = smp_load_acquire(&rb->overwrite_pos); + prod_pos = smp_load_acquire(&rb->producer_pos); + return prod_pos - max(cons_pos, over_pos); + } else { + prod_pos = smp_load_acquire(&rb->producer_pos); + return prod_pos - cons_pos; + } } static u32 ringbuf_total_data_sz(const struct bpf_ringbuf *rb) @@ -336,6 +358,21 @@ static __poll_t ringbuf_map_poll_user(struct bpf_map *map, struct file *filp, return 0; } +static u64 ringbuf_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_ringbuf *rb; + int nr_data_pages; + int nr_meta_pages; + u64 usage = sizeof(struct bpf_ringbuf_map); + + rb = container_of(map, struct bpf_ringbuf_map, map)->rb; + usage += (u64)rb->nr_pages << PAGE_SHIFT; + nr_meta_pages = RINGBUF_NR_META_PAGES; + nr_data_pages = map->max_entries >> PAGE_SHIFT; + usage += (nr_meta_pages + 2 * nr_data_pages) * sizeof(struct page *); + return usage; +} + BTF_ID_LIST_SINGLE(ringbuf_map_btf_ids, struct, bpf_ringbuf_map) const struct bpf_map_ops ringbuf_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -347,6 +384,7 @@ const struct bpf_map_ops ringbuf_map_ops = { .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, + .map_mem_usage = ringbuf_map_mem_usage, .map_btf_id = &ringbuf_map_btf_ids[0], }; @@ -361,6 +399,7 @@ const struct bpf_map_ops user_ringbuf_map_ops = { .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, + .map_mem_usage = ringbuf_map_mem_usage, .map_btf_id = &user_ringbuf_map_btf_ids[0], }; @@ -388,11 +427,43 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) return (void*)((addr & PAGE_MASK) - off); } +static bool bpf_ringbuf_has_space(const struct bpf_ringbuf *rb, + unsigned long new_prod_pos, + unsigned long cons_pos, + unsigned long pend_pos) +{ + /* + * No space if oldest not yet committed record until the newest + * record span more than (ringbuf_size - 1). + */ + if (new_prod_pos - pend_pos > rb->mask) + return false; + + /* Ok, we have space in overwrite mode */ + if (unlikely(rb->overwrite_mode)) + return true; + + /* + * No space if producer position advances more than (ringbuf_size - 1) + * ahead of consumer position when not in overwrite mode. + */ + if (new_prod_pos - cons_pos > rb->mask) + return false; + + return true; +} + +static u32 bpf_ringbuf_round_up_hdr_len(u32 hdr_len) +{ + hdr_len &= ~BPF_RINGBUF_DISCARD_BIT; + return round_up(hdr_len + BPF_RINGBUF_HDR_SZ, 8); +} + static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) { - unsigned long cons_pos, prod_pos, new_prod_pos, flags; - u32 len, pg_off; + unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, over_pos, flags; struct bpf_ringbuf_hdr *hdr; + u32 len, pg_off, hdr_len; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; @@ -403,24 +474,55 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) cons_pos = smp_load_acquire(&rb->consumer_pos); - if (in_nmi()) { - if (!spin_trylock_irqsave(&rb->spinlock, flags)) - return NULL; - } else { - spin_lock_irqsave(&rb->spinlock, flags); - } + if (raw_res_spin_lock_irqsave(&rb->spinlock, flags)) + return NULL; + pend_pos = rb->pending_pos; prod_pos = rb->producer_pos; new_prod_pos = prod_pos + len; - /* check for out of ringbuf space by ensuring producer position - * doesn't advance more than (ringbuf_size - 1) ahead - */ - if (new_prod_pos - cons_pos > rb->mask) { - spin_unlock_irqrestore(&rb->spinlock, flags); + while (pend_pos < prod_pos) { + hdr = (void *)rb->data + (pend_pos & rb->mask); + hdr_len = READ_ONCE(hdr->len); + if (hdr_len & BPF_RINGBUF_BUSY_BIT) + break; + pend_pos += bpf_ringbuf_round_up_hdr_len(hdr_len); + } + rb->pending_pos = pend_pos; + + if (!bpf_ringbuf_has_space(rb, new_prod_pos, cons_pos, pend_pos)) { + raw_res_spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } + /* + * In overwrite mode, advance overwrite_pos when the ring buffer is full. + * The key points are to stay on record boundaries and consume enough records + * to fit the new one. + */ + if (unlikely(rb->overwrite_mode)) { + over_pos = rb->overwrite_pos; + while (new_prod_pos - over_pos > rb->mask) { + hdr = (void *)rb->data + (over_pos & rb->mask); + hdr_len = READ_ONCE(hdr->len); + /* + * The bpf_ringbuf_has_space() check above ensures we won’t + * step over a record currently being worked on by another + * producer. + */ + over_pos += bpf_ringbuf_round_up_hdr_len(hdr_len); + } + /* + * smp_store_release(&rb->producer_pos, new_prod_pos) at + * the end of the function ensures that when consumer sees + * the updated rb->producer_pos, it always sees the updated + * rb->overwrite_pos, so when consumer reads overwrite_pos + * after smp_load_acquire(r->producer_pos), the overwrite_pos + * will always be valid. + */ + WRITE_ONCE(rb->overwrite_pos, over_pos); + } + hdr = (void *)rb->data + (prod_pos & rb->mask); pg_off = bpf_ringbuf_rec_pg_off(rb, hdr); hdr->len = size | BPF_RINGBUF_BUSY_BIT; @@ -429,7 +531,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) /* pairs with consumer's smp_load_acquire() */ smp_store_release(&rb->producer_pos, new_prod_pos); - spin_unlock_irqrestore(&rb->spinlock, flags); + raw_res_spin_unlock_irqrestore(&rb->spinlock, flags); return (void *)hdr + BPF_RINGBUF_HDR_SZ; } @@ -550,6 +652,8 @@ BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) return smp_load_acquire(&rb->consumer_pos); case BPF_RB_PROD_POS: return smp_load_acquire(&rb->producer_pos); + case BPF_RB_OVERWRITE_POS: + return smp_load_acquire(&rb->overwrite_pos); default: return 0; } @@ -599,7 +703,7 @@ const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) @@ -756,8 +860,7 @@ schedule_work_return: /* Prevent the clearing of the busy-bit from being reordered before the * storing of any rb consumer or producer positions. */ - smp_mb__before_atomic(); - atomic_set(&rb->busy, 0); + atomic_set_release(&rb->busy, 0); if (flags & BPF_RB_FORCE_WAKEUP) irq_work_queue(&rb->work); diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c new file mode 100644 index 000000000000..f7d0c8d4644e --- /dev/null +++ b/kernel/bpf/rqspinlock.c @@ -0,0 +1,762 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Resilient Queued Spin Lock + * + * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. + * (C) Copyright 2013-2014,2018 Red Hat, Inc. + * (C) Copyright 2015 Intel Corp. + * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP + * (C) Copyright 2024-2025 Meta Platforms, Inc. and affiliates. + * + * Authors: Waiman Long <longman@redhat.com> + * Peter Zijlstra <peterz@infradead.org> + * Kumar Kartikeya Dwivedi <memxor@gmail.com> + */ + +#include <linux/smp.h> +#include <linux/bug.h> +#include <linux/bpf.h> +#include <linux/err.h> +#include <linux/cpumask.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/mutex.h> +#include <linux/prefetch.h> +#include <asm/byteorder.h> +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#endif +#include <trace/events/lock.h> +#include <asm/rqspinlock.h> +#include <linux/timekeeping.h> + +/* + * Include queued spinlock definitions and statistics code + */ +#ifdef CONFIG_QUEUED_SPINLOCKS +#include "../locking/qspinlock.h" +#include "../locking/lock_events.h" +#include "rqspinlock.h" +#include "../locking/mcs_spinlock.h" +#endif + +/* + * The basic principle of a queue-based spinlock can best be understood + * by studying a classic queue-based spinlock implementation called the + * MCS lock. A copy of the original MCS lock paper ("Algorithms for Scalable + * Synchronization on Shared-Memory Multiprocessors by Mellor-Crummey and + * Scott") is available at + * + * https://bugzilla.kernel.org/show_bug.cgi?id=206115 + * + * This queued spinlock implementation is based on the MCS lock, however to + * make it fit the 4 bytes we assume spinlock_t to be, and preserve its + * existing API, we must modify it somehow. + * + * In particular; where the traditional MCS lock consists of a tail pointer + * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to + * unlock the next pending (next->locked), we compress both these: {tail, + * next->locked} into a single u32 value. + * + * Since a spinlock disables recursion of its own context and there is a limit + * to the contexts that can nest; namely: task, softirq, hardirq, nmi. As there + * are at most 4 nesting levels, it can be encoded by a 2-bit number. Now + * we can encode the tail by combining the 2-bit nesting level with the cpu + * number. With one byte for the lock value and 3 bytes for the tail, only a + * 32-bit word is now needed. Even though we only need 1 bit for the lock, + * we extend it to a full byte to achieve better performance for architectures + * that support atomic byte write. + * + * We also change the first spinner to spin on the lock bit instead of its + * node; whereby avoiding the need to carry a node from lock to unlock, and + * preserving existing lock API. This also makes the unlock code simpler and + * faster. + * + * N.B. The current implementation only supports architectures that allow + * atomic operations on smaller 8-bit and 16-bit data types. + * + */ + +struct rqspinlock_timeout { + u64 timeout_end; + u64 duration; + u64 cur; + u16 spin; +}; + +#define RES_TIMEOUT_VAL 2 + +DEFINE_PER_CPU_ALIGNED(struct rqspinlock_held, rqspinlock_held_locks); +EXPORT_SYMBOL_GPL(rqspinlock_held_locks); + +static bool is_lock_released(rqspinlock_t *lock, u32 mask) +{ + if (!(atomic_read_acquire(&lock->val) & (mask))) + return true; + return false; +} + +static noinline int check_deadlock_AA(rqspinlock_t *lock) +{ + struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); + int cnt = min(RES_NR_HELD, rqh->cnt); + + /* + * Return an error if we hold the lock we are attempting to acquire. + * We'll iterate over max 32 locks; no need to do is_lock_released. + */ + for (int i = 0; i < cnt - 1; i++) { + if (rqh->locks[i] == lock) + return -EDEADLK; + } + return 0; +} + +/* + * This focuses on the most common case of ABBA deadlocks (or ABBA involving + * more locks, which reduce to ABBA). This is not exhaustive, and we rely on + * timeouts as the final line of defense. + */ +static noinline int check_deadlock_ABBA(rqspinlock_t *lock, u32 mask) +{ + struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); + int rqh_cnt = min(RES_NR_HELD, rqh->cnt); + void *remote_lock; + int cpu; + + /* + * Find the CPU holding the lock that we want to acquire. If there is a + * deadlock scenario, we will read a stable set on the remote CPU and + * find the target. This would be a constant time operation instead of + * O(NR_CPUS) if we could determine the owning CPU from a lock value, but + * that requires increasing the size of the lock word. + */ + for_each_possible_cpu(cpu) { + struct rqspinlock_held *rqh_cpu = per_cpu_ptr(&rqspinlock_held_locks, cpu); + int real_cnt = READ_ONCE(rqh_cpu->cnt); + int cnt = min(RES_NR_HELD, real_cnt); + + /* + * Let's ensure to break out of this loop if the lock is available for + * us to potentially acquire. + */ + if (is_lock_released(lock, mask)) + return 0; + + /* + * Skip ourselves, and CPUs whose count is less than 2, as they need at + * least one held lock and one acquisition attempt (reflected as top + * most entry) to participate in an ABBA deadlock. + * + * If cnt is more than RES_NR_HELD, it means the current lock being + * acquired won't appear in the table, and other locks in the table are + * already held, so we can't determine ABBA. + */ + if (cpu == smp_processor_id() || real_cnt < 2 || real_cnt > RES_NR_HELD) + continue; + + /* + * Obtain the entry at the top, this corresponds to the lock the + * remote CPU is attempting to acquire in a deadlock situation, + * and would be one of the locks we hold on the current CPU. + */ + remote_lock = READ_ONCE(rqh_cpu->locks[cnt - 1]); + /* + * If it is NULL, we've raced and cannot determine a deadlock + * conclusively, skip this CPU. + */ + if (!remote_lock) + continue; + /* + * Find if the lock we're attempting to acquire is held by this CPU. + * Don't consider the topmost entry, as that must be the latest lock + * being held or acquired. For a deadlock, the target CPU must also + * attempt to acquire a lock we hold, so for this search only 'cnt - 1' + * entries are important. + */ + for (int i = 0; i < cnt - 1; i++) { + if (READ_ONCE(rqh_cpu->locks[i]) != lock) + continue; + /* + * We found our lock as held on the remote CPU. Is the + * acquisition attempt on the remote CPU for a lock held + * by us? If so, we have a deadlock situation, and need + * to recover. + */ + for (int i = 0; i < rqh_cnt - 1; i++) { + if (rqh->locks[i] == remote_lock) + return -EDEADLK; + } + /* + * Inconclusive; retry again later. + */ + return 0; + } + } + return 0; +} + +static noinline int check_timeout(rqspinlock_t *lock, u32 mask, + struct rqspinlock_timeout *ts) +{ + u64 prev = ts->cur; + u64 time; + + if (!ts->timeout_end) { + if (check_deadlock_AA(lock)) + return -EDEADLK; + ts->cur = ktime_get_mono_fast_ns(); + ts->timeout_end = ts->cur + ts->duration; + return 0; + } + + time = ktime_get_mono_fast_ns(); + if (time > ts->timeout_end) + return -ETIMEDOUT; + + /* + * A millisecond interval passed from last time? Trigger deadlock + * checks. + */ + if (prev + NSEC_PER_MSEC < time) { + ts->cur = time; + return check_deadlock_ABBA(lock, mask); + } + + return 0; +} + +/* + * Do not amortize with spins when res_smp_cond_load_acquire is defined, + * as the macro does internal amortization for us. + */ +#ifndef res_smp_cond_load_acquire +#define RES_CHECK_TIMEOUT(ts, ret, mask) \ + ({ \ + if (!(ts).spin++) \ + (ret) = check_timeout((lock), (mask), &(ts)); \ + (ret); \ + }) +#else +#define RES_CHECK_TIMEOUT(ts, ret, mask) \ + ({ (ret) = check_timeout((lock), (mask), &(ts)); }) +#endif + +/* + * Initialize the 'spin' member. + * Set spin member to 0 to trigger AA/ABBA checks immediately. + */ +#define RES_INIT_TIMEOUT(ts) ({ (ts).spin = 0; }) + +/* + * We only need to reset 'timeout_end', 'spin' will just wrap around as necessary. + * Duration is defined for each spin attempt, so set it here. + */ +#define RES_RESET_TIMEOUT(ts, _duration) ({ (ts).timeout_end = 0; (ts).duration = _duration; }) + +/* + * Provide a test-and-set fallback for cases when queued spin lock support is + * absent from the architecture. + */ +int __lockfunc resilient_tas_spin_lock(rqspinlock_t *lock) +{ + struct rqspinlock_timeout ts; + int val, ret = 0; + + RES_INIT_TIMEOUT(ts); + /* + * The fast path is not invoked for the TAS fallback, so we must grab + * the deadlock detection entry here. + */ + grab_held_lock_entry(lock); + + /* + * Since the waiting loop's time is dependent on the amount of + * contention, a short timeout unlike rqspinlock waiting loops + * isn't enough. Choose a second as the timeout value. + */ + RES_RESET_TIMEOUT(ts, NSEC_PER_SEC); +retry: + val = atomic_read(&lock->val); + + if (val || !atomic_try_cmpxchg(&lock->val, &val, 1)) { + if (RES_CHECK_TIMEOUT(ts, ret, ~0u)) + goto out; + cpu_relax(); + goto retry; + } + + return 0; +out: + release_held_lock_entry(); + return ret; +} +EXPORT_SYMBOL_GPL(resilient_tas_spin_lock); + +#ifdef CONFIG_QUEUED_SPINLOCKS + +/* + * Per-CPU queue node structures; we can never have more than 4 nested + * contexts: task, softirq, hardirq, nmi. + * + * Exactly fits one 64-byte cacheline on a 64-bit architecture. + */ +static DEFINE_PER_CPU_ALIGNED(struct qnode, rqnodes[_Q_MAX_NODES]); + +#ifndef res_smp_cond_load_acquire +#define res_smp_cond_load_acquire(v, c) smp_cond_load_acquire(v, c) +#endif + +#define res_atomic_cond_read_acquire(v, c) res_smp_cond_load_acquire(&(v)->counter, (c)) + +/** + * resilient_queued_spin_lock_slowpath - acquire the queued spinlock + * @lock: Pointer to queued spinlock structure + * @val: Current value of the queued spinlock 32-bit word + * + * Return: + * * 0 - Lock was acquired successfully. + * * -EDEADLK - Lock acquisition failed because of AA/ABBA deadlock. + * * -ETIMEDOUT - Lock acquisition failed because of timeout. + * + * (queue tail, pending bit, lock value) + * + * fast : slow : unlock + * : : + * uncontended (0,0,0) -:--> (0,0,1) ------------------------------:--> (*,*,0) + * : | ^--------.------. / : + * : v \ \ | : + * pending : (0,1,1) +--> (0,1,0) \ | : + * : | ^--' | | : + * : v | | : + * uncontended : (n,x,y) +--> (n,0,0) --' | : + * queue : | ^--' | : + * : v | : + * contended : (*,x,y) +--> (*,0,0) ---> (*,0,1) -' : + * queue : ^--' : + */ +int __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val) +{ + struct mcs_spinlock *prev, *next, *node; + struct rqspinlock_timeout ts; + int idx, ret = 0; + u32 old, tail; + + BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS)); + + if (resilient_virt_spin_lock_enabled()) + return resilient_virt_spin_lock(lock); + + RES_INIT_TIMEOUT(ts); + + /* + * Wait for in-progress pending->locked hand-overs with a bounded + * number of spins so that we guarantee forward progress. + * + * 0,1,0 -> 0,0,1 + */ + if (val == _Q_PENDING_VAL) { + int cnt = _Q_PENDING_LOOPS; + val = atomic_cond_read_relaxed(&lock->val, + (VAL != _Q_PENDING_VAL) || !cnt--); + } + + /* + * If we observe any contention; queue. + */ + if (val & ~_Q_LOCKED_MASK) + goto queue; + + /* + * trylock || pending + * + * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock + */ + val = queued_fetch_set_pending_acquire(lock); + + /* + * If we observe contention, there is a concurrent locker. + * + * Undo and queue; our setting of PENDING might have made the + * n,0,0 -> 0,0,0 transition fail and it will now be waiting + * on @next to become !NULL. + */ + if (unlikely(val & ~_Q_LOCKED_MASK)) { + + /* Undo PENDING if we set it. */ + if (!(val & _Q_PENDING_MASK)) + clear_pending(lock); + + goto queue; + } + + /* Deadlock detection entry already held after failing fast path. */ + + /* + * We're pending, wait for the owner to go away. + * + * 0,1,1 -> *,1,0 + * + * this wait loop must be a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because not all + * clear_pending_set_locked() implementations imply full + * barriers. + */ + if (val & _Q_LOCKED_MASK) { + RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT); + res_smp_cond_load_acquire(&lock->locked, !VAL || RES_CHECK_TIMEOUT(ts, ret, _Q_LOCKED_MASK)); + } + + if (ret) { + /* + * We waited for the locked bit to go back to 0, as the pending + * waiter, but timed out. We need to clear the pending bit since + * we own it. Once a stuck owner has been recovered, the lock + * must be restored to a valid state, hence removing the pending + * bit is necessary. + * + * *,1,* -> *,0,* + */ + clear_pending(lock); + lockevent_inc(rqspinlock_lock_timeout); + goto err_release_entry; + } + + /* + * take ownership and clear the pending bit. + * + * 0,1,0 -> 0,0,1 + */ + clear_pending_set_locked(lock); + lockevent_inc(lock_pending); + return 0; + + /* + * End of pending bit optimistic spinning and beginning of MCS + * queuing. + */ +queue: + /* + * Do not queue if we're a waiter and someone is attempting this lock on + * the same CPU. In case of NMIs, this prevents long timeouts where we + * interrupt the pending waiter, and the owner, that will eventually + * signal the head of our queue, both of which are logically but not + * physically part of the queue, hence outside the scope of the idx > 0 + * check above for the trylock fallback. + */ + if (check_deadlock_AA(lock)) { + ret = -EDEADLK; + goto err_release_entry; + } + + lockevent_inc(lock_slowpath); + /* Deadlock detection entry already held after failing fast path. */ + node = this_cpu_ptr(&rqnodes[0].mcs); + idx = node->count++; + tail = encode_tail(smp_processor_id(), idx); + + trace_contention_begin(lock, LCB_F_SPIN); + + /* + * 4 nodes are allocated based on the assumption that there will + * not be nested NMIs taking spinlocks. That may not be true in + * some architectures even though the chance of needing more than + * 4 nodes will still be extremely unlikely. When that happens, + * we fall back to attempting a trylock operation without using + * any MCS node. Unlike qspinlock which cannot fail, we have the + * option of failing the slow path, and under contention, such a + * trylock spinning will likely be treated unfairly due to lack of + * queueing, hence do not spin. + */ + if (unlikely(idx >= _Q_MAX_NODES || (in_nmi() && idx > 0))) { + lockevent_inc(lock_no_node); + if (!queued_spin_trylock(lock)) { + ret = -EDEADLK; + goto err_release_node; + } + goto release; + } + + node = grab_mcs_node(node, idx); + + /* + * Keep counts of non-zero index values: + */ + lockevent_cond_inc(lock_use_node2 + idx - 1, idx); + + /* + * Ensure that we increment the head node->count before initialising + * the actual node. If the compiler is kind enough to reorder these + * stores, then an IRQ could overwrite our assignments. + */ + barrier(); + + node->locked = 0; + node->next = NULL; + + /* + * We touched a (possibly) cold cacheline in the per-cpu queue node; + * attempt the trylock once more in the hope someone let go while we + * weren't watching. + */ + if (queued_spin_trylock(lock)) + goto release; + + /* + * Ensure that the initialisation of @node is complete before we + * publish the updated tail via xchg_tail() and potentially link + * @node into the waitqueue via WRITE_ONCE(prev->next, node) below. + */ + smp_wmb(); + + /* + * Publish the updated tail. + * We have already touched the queueing cacheline; don't bother with + * pending stuff. + * + * p,*,* -> n,*,* + */ + old = xchg_tail(lock, tail); + next = NULL; + + /* + * if there was a previous node; link it and wait until reaching the + * head of the waitqueue. + */ + if (old & _Q_TAIL_MASK) { + int val; + + prev = decode_tail(old, rqnodes); + + /* Link @node into the waitqueue. */ + WRITE_ONCE(prev->next, node); + + val = arch_mcs_spin_lock_contended(&node->locked); + if (val == RES_TIMEOUT_VAL) { + ret = -ETIMEDOUT; + goto waitq_timeout; + } + + /* + * While waiting for the MCS lock, the next pointer may have + * been set by another lock waiter. We optimistically load + * the next pointer & prefetch the cacheline for writing + * to reduce latency in the upcoming MCS unlock operation. + */ + next = READ_ONCE(node->next); + if (next) + prefetchw(next); + } + + /* + * we're at the head of the waitqueue, wait for the owner & pending to + * go away. + * + * *,x,y -> *,0,0 + * + * this wait loop must use a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because the set_locked() function below + * does not imply a full barrier. + * + * We use RES_DEF_TIMEOUT * 2 as the duration, as RES_DEF_TIMEOUT is + * meant to span maximum allowed time per critical section, and we may + * have both the owner of the lock and the pending bit waiter ahead of + * us. + */ + RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT * 2); + val = res_atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK) || + RES_CHECK_TIMEOUT(ts, ret, _Q_LOCKED_PENDING_MASK)); + + /* Disable queue destruction when we detect deadlocks. */ + if (ret == -EDEADLK) { + if (!next) + next = smp_cond_load_relaxed(&node->next, (VAL)); + arch_mcs_spin_unlock_contended(&next->locked); + goto err_release_node; + } + +waitq_timeout: + if (ret) { + /* + * If the tail is still pointing to us, then we are the final waiter, + * and are responsible for resetting the tail back to 0. Otherwise, if + * the cmpxchg operation fails, we signal the next waiter to take exit + * and try the same. For a waiter with tail node 'n': + * + * n,*,* -> 0,*,* + * + * When performing cmpxchg for the whole word (NR_CPUS > 16k), it is + * possible locked/pending bits keep changing and we see failures even + * when we remain the head of wait queue. However, eventually, + * pending bit owner will unset the pending bit, and new waiters + * will queue behind us. This will leave the lock owner in + * charge, and it will eventually either set locked bit to 0, or + * leave it as 1, allowing us to make progress. + * + * We terminate the whole wait queue for two reasons. Firstly, + * we eschew per-waiter timeouts with one applied at the head of + * the wait queue. This allows everyone to break out faster + * once we've seen the owner / pending waiter not responding for + * the timeout duration from the head. Secondly, it avoids + * complicated synchronization, because when not leaving in FIFO + * order, prev's next pointer needs to be fixed up etc. + */ + if (!try_cmpxchg_tail(lock, tail, 0)) { + next = smp_cond_load_relaxed(&node->next, VAL); + WRITE_ONCE(next->locked, RES_TIMEOUT_VAL); + } + lockevent_inc(rqspinlock_lock_timeout); + goto err_release_node; + } + + /* + * claim the lock: + * + * n,0,0 -> 0,0,1 : lock, uncontended + * *,*,0 -> *,*,1 : lock, contended + * + * If the queue head is the only one in the queue (lock value == tail) + * and nobody is pending, clear the tail code and grab the lock. + * Otherwise, we only need to grab the lock. + */ + + /* + * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the + * above wait condition, therefore any concurrent setting of + * PENDING will make the uncontended transition fail. + */ + if ((val & _Q_TAIL_MASK) == tail) { + if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL)) + goto release; /* No contention */ + } + + /* + * Either somebody is queued behind us or _Q_PENDING_VAL got set + * which will then detect the remaining tail and queue behind us + * ensuring we'll see a @next. + */ + set_locked(lock); + + /* + * contended path; wait for next if not observed yet, release. + */ + if (!next) + next = smp_cond_load_relaxed(&node->next, (VAL)); + + arch_mcs_spin_unlock_contended(&next->locked); + +release: + trace_contention_end(lock, 0); + + /* + * release the node + */ + __this_cpu_dec(rqnodes[0].mcs.count); + return ret; +err_release_node: + trace_contention_end(lock, ret); + __this_cpu_dec(rqnodes[0].mcs.count); +err_release_entry: + release_held_lock_entry(); + return ret; +} +EXPORT_SYMBOL_GPL(resilient_queued_spin_lock_slowpath); + +#endif /* CONFIG_QUEUED_SPINLOCKS */ + +__bpf_kfunc_start_defs(); + +static void bpf_prog_report_rqspinlock_violation(const char *str, void *lock, bool irqsave) +{ + struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); + struct bpf_stream_stage ss; + struct bpf_prog *prog; + + prog = bpf_prog_find_from_stack(); + if (!prog) + return; + bpf_stream_stage(ss, prog, BPF_STDERR, ({ + bpf_stream_printk(ss, "ERROR: %s for bpf_res_spin_lock%s\n", str, irqsave ? "_irqsave" : ""); + bpf_stream_printk(ss, "Attempted lock = 0x%px\n", lock); + bpf_stream_printk(ss, "Total held locks = %d\n", rqh->cnt); + for (int i = 0; i < min(RES_NR_HELD, rqh->cnt); i++) + bpf_stream_printk(ss, "Held lock[%2d] = 0x%px\n", i, rqh->locks[i]); + bpf_stream_dump_stack(ss); + })); +} + +#define REPORT_STR(ret) ({ (ret) == -ETIMEDOUT ? "Timeout detected" : "AA or ABBA deadlock detected"; }) + +__bpf_kfunc int bpf_res_spin_lock(struct bpf_res_spin_lock *lock) +{ + int ret; + + BUILD_BUG_ON(sizeof(rqspinlock_t) != sizeof(struct bpf_res_spin_lock)); + BUILD_BUG_ON(__alignof__(rqspinlock_t) != __alignof__(struct bpf_res_spin_lock)); + + preempt_disable(); + ret = res_spin_lock((rqspinlock_t *)lock); + if (unlikely(ret)) { + bpf_prog_report_rqspinlock_violation(REPORT_STR(ret), lock, false); + preempt_enable(); + return ret; + } + return 0; +} + +__bpf_kfunc void bpf_res_spin_unlock(struct bpf_res_spin_lock *lock) +{ + res_spin_unlock((rqspinlock_t *)lock); + preempt_enable(); +} + +__bpf_kfunc int bpf_res_spin_lock_irqsave(struct bpf_res_spin_lock *lock, unsigned long *flags__irq_flag) +{ + u64 *ptr = (u64 *)flags__irq_flag; + unsigned long flags; + int ret; + + preempt_disable(); + local_irq_save(flags); + ret = res_spin_lock((rqspinlock_t *)lock); + if (unlikely(ret)) { + bpf_prog_report_rqspinlock_violation(REPORT_STR(ret), lock, true); + local_irq_restore(flags); + preempt_enable(); + return ret; + } + *ptr = flags; + return 0; +} + +__bpf_kfunc void bpf_res_spin_unlock_irqrestore(struct bpf_res_spin_lock *lock, unsigned long *flags__irq_flag) +{ + u64 *ptr = (u64 *)flags__irq_flag; + unsigned long flags = *ptr; + + res_spin_unlock((rqspinlock_t *)lock); + local_irq_restore(flags); + preempt_enable(); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(rqspinlock_kfunc_ids) +BTF_ID_FLAGS(func, bpf_res_spin_lock, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_res_spin_unlock) +BTF_ID_FLAGS(func, bpf_res_spin_lock_irqsave, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_res_spin_unlock_irqrestore) +BTF_KFUNCS_END(rqspinlock_kfunc_ids) + +static const struct btf_kfunc_id_set rqspinlock_kfunc_set = { + .owner = THIS_MODULE, + .set = &rqspinlock_kfunc_ids, +}; + +static __init int rqspinlock_register_kfuncs(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &rqspinlock_kfunc_set); +} +late_initcall(rqspinlock_register_kfuncs); diff --git a/kernel/bpf/rqspinlock.h b/kernel/bpf/rqspinlock.h new file mode 100644 index 000000000000..5d8cb1b1aab4 --- /dev/null +++ b/kernel/bpf/rqspinlock.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Resilient Queued Spin Lock defines + * + * (C) Copyright 2024-2025 Meta Platforms, Inc. and affiliates. + * + * Authors: Kumar Kartikeya Dwivedi <memxor@gmail.com> + */ +#ifndef __LINUX_RQSPINLOCK_H +#define __LINUX_RQSPINLOCK_H + +#include "../locking/qspinlock.h" + +/* + * try_cmpxchg_tail - Return result of cmpxchg of tail word with a new value + * @lock: Pointer to queued spinlock structure + * @tail: The tail to compare against + * @new_tail: The new queue tail code word + * Return: Bool to indicate whether the cmpxchg operation succeeded + * + * This is used by the head of the wait queue to clean up the queue. + * Provides relaxed ordering, since observers only rely on initialized + * state of the node which was made visible through the xchg_tail operation, + * i.e. through the smp_wmb preceding xchg_tail. + * + * We avoid using 16-bit cmpxchg, which is not available on all architectures. + */ +static __always_inline bool try_cmpxchg_tail(struct qspinlock *lock, u32 tail, u32 new_tail) +{ + u32 old, new; + + old = atomic_read(&lock->val); + do { + /* + * Is the tail part we compare to already stale? Fail. + */ + if ((old & _Q_TAIL_MASK) != tail) + return false; + /* + * Encode latest locked/pending state for new tail. + */ + new = (old & _Q_LOCKED_PENDING_MASK) | new_tail; + } while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new)); + + return true; +} + +#endif /* __LINUX_RQSPINLOCK_H */ diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index aecea7451b61..da3d328f5c15 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -28,7 +28,7 @@ struct bpf_stack_map { void *elems; struct pcpu_freelist freelist; u32 n_buckets; - struct stack_map_bucket *buckets[]; + struct stack_map_bucket *buckets[] __counted_by(n_buckets); }; static inline bool stack_map_use_build_id(struct bpf_map *map) @@ -42,6 +42,28 @@ static inline int stack_map_data_size(struct bpf_map *map) sizeof(struct bpf_stack_build_id) : sizeof(u64); } +/** + * stack_map_calculate_max_depth - Calculate maximum allowed stack trace depth + * @size: Size of the buffer/map value in bytes + * @elem_size: Size of each stack trace element + * @flags: BPF stack trace flags (BPF_F_USER_STACK, BPF_F_USER_BUILD_ID, ...) + * + * Return: Maximum number of stack trace entries that can be safely stored + */ +static u32 stack_map_calculate_max_depth(u32 size, u32 elem_size, u64 flags) +{ + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 max_depth; + u32 curr_sysctl_max_stack = READ_ONCE(sysctl_perf_event_max_stack); + + max_depth = size / elem_size; + max_depth += skip; + if (max_depth > curr_sysctl_max_stack) + return curr_sysctl_max_stack; + + return max_depth; +} + static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { u64 elem_size = sizeof(struct stack_map_bucket) + @@ -74,9 +96,6 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) u64 cost, n_buckets; int err; - if (!bpf_capable()) - return ERR_PTR(-EPERM); - if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); @@ -94,11 +113,14 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); - /* hash table size must be power of 2 */ - n_buckets = roundup_pow_of_two(attr->max_entries); - if (!n_buckets) + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); + n_buckets = roundup_pow_of_two(attr->max_entries); + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) @@ -124,8 +146,24 @@ free_smap: return ERR_PTR(err); } +static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault) +{ + return may_fault ? build_id_parse(vma, build_id, NULL) + : build_id_parse_nofault(vma, build_id, NULL); +} + +/* + * Expects all id_offs[i].ip values to be set to correct initial IPs. + * They will be subsequently: + * - either adjusted in place to a file offset, if build ID fetching + * succeeds; in this case id_offs[i].build_id is set to correct build ID, + * and id_offs[i].status is set to BPF_STACK_BUILD_ID_VALID; + * - or IP will be kept intact, if build ID fetching failed; in this case + * id_offs[i].build_id is zeroed out and id_offs[i].status is set to + * BPF_STACK_BUILD_ID_IP. + */ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, - u64 *ips, u32 trace_nr, bool user) + u32 trace_nr, bool user, bool may_fault) { int i; struct mmap_unlock_irq_work *work = NULL; @@ -142,30 +180,28 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; - id_offs[i].ip = ips[i]; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); } return; } for (i = 0; i < trace_nr; i++) { - if (range_in_vma(prev_vma, ips[i], ips[i])) { + u64 ip = READ_ONCE(id_offs[i].ip); + + if (range_in_vma(prev_vma, ip, ip)) { vma = prev_vma; - memcpy(id_offs[i].build_id, prev_build_id, - BUILD_ID_SIZE_MAX); + memcpy(id_offs[i].build_id, prev_build_id, BUILD_ID_SIZE_MAX); goto build_id_valid; } - vma = find_vma(current->mm, ips[i]); - if (!vma || build_id_parse(vma, id_offs[i].build_id, NULL)) { + vma = find_vma(current->mm, ip); + if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) { /* per entry fall back to ips */ id_offs[i].status = BPF_STACK_BUILD_ID_IP; - id_offs[i].ip = ips[i]; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); continue; } build_id_valid: - id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i] - - vma->vm_start; + id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ip - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; prev_vma = vma; prev_build_id = id_offs[i].build_id; @@ -215,8 +251,8 @@ static long __bpf_get_stackid(struct bpf_map *map, { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *new_bucket, *old_bucket; + u32 hash, id, trace_nr, trace_len, i, max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; - u32 hash, id, trace_nr, trace_len; bool user = flags & BPF_F_USER_STACK; u64 *ips; bool hash_matches; @@ -225,7 +261,8 @@ static long __bpf_get_stackid(struct bpf_map *map, /* skipping more than usable stack trace */ return -EFAULT; - trace_nr = trace->nr - skip; + max_depth = stack_map_calculate_max_depth(map->value_size, stack_map_data_size(map), flags); + trace_nr = min_t(u32, trace->nr - skip, max_depth - skip); trace_len = trace_nr * sizeof(u64); ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); @@ -238,15 +275,18 @@ static long __bpf_get_stackid(struct bpf_map *map, return id; if (stack_map_use_build_id(map)) { + struct bpf_stack_build_id *id_offs; + /* for build_id+offset, pop a bucket before slow cmp */ new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; new_bucket->nr = trace_nr; - stack_map_get_build_id_offset( - (struct bpf_stack_build_id *)new_bucket->data, - ips, trace_nr, user); + id_offs = (struct bpf_stack_build_id *)new_bucket->data; + for (i = 0; i < trace_nr; i++) + id_offs[i].ip = ips[i]; + stack_map_get_build_id_offset(id_offs, trace_nr, user, false /* !may_fault */); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { @@ -283,22 +323,19 @@ static long __bpf_get_stackid(struct bpf_map *map, BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { - u32 max_depth = map->value_size / stack_map_data_size(map); - u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 elem_size = stack_map_data_size(map); bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; + u32 max_depth; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; - max_depth += skip; - if (max_depth > sysctl_perf_event_max_stack) - max_depth = sysctl_perf_event_max_stack; - - trace = get_perf_callchain(regs, 0, kernel, user, max_depth, - false, false); + max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags); + trace = get_perf_callchain(regs, kernel, user, max_depth, + false, false, 0); if (unlikely(!trace)) /* couldn't fetch the stack trace */ @@ -354,15 +391,11 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, return -EFAULT; nr_kernel = count_kernel_ip(trace); + __u64 nr = trace->nr; /* save original */ if (kernel) { - __u64 nr = trace->nr; - trace->nr = nr_kernel; ret = __bpf_get_stackid(map, trace, flags); - - /* restore nr */ - trace->nr = nr; } else { /* user */ u64 skip = flags & BPF_F_SKIP_FIELD_MASK; @@ -373,6 +406,10 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; ret = __bpf_get_stackid(map, trace, flags); } + + /* restore nr */ + trace->nr = nr; + return ret; } @@ -387,10 +424,11 @@ const struct bpf_func_proto bpf_get_stackid_proto_pe = { static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, - void *buf, u32 size, u64 flags) + void *buf, u32 size, u64 flags, bool may_fault) { - u32 trace_nr, copy_len, elem_size, num_elem, max_depth; + u32 trace_nr, copy_len, elem_size, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; + bool crosstask = task && task != current; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; @@ -404,8 +442,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (kernel && user_build_id) goto clear; - elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id) - : sizeof(u64); + elem_size = user_build_id ? sizeof(struct bpf_stack_build_id) : sizeof(u64); if (unlikely(size % elem_size)) goto clear; @@ -413,33 +450,55 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (task && user && !user_mode(regs)) goto err_fault; - num_elem = size / elem_size; - max_depth = num_elem + skip; - if (sysctl_perf_event_max_stack < max_depth) - max_depth = sysctl_perf_event_max_stack; + /* get_perf_callchain does not support crosstask user stack walking + * but returns an empty stack instead of NULL. + */ + if (crosstask && user) { + err = -EOPNOTSUPP; + goto clear; + } + + max_depth = stack_map_calculate_max_depth(size, elem_size, flags); + + if (may_fault) + rcu_read_lock(); /* need RCU for perf's callchain below */ - if (trace_in) + if (trace_in) { trace = trace_in; - else if (kernel && task) + trace->nr = min_t(u32, trace->nr, max_depth); + } else if (kernel && task) { trace = get_callchain_entry_for_task(task, max_depth); - else - trace = get_perf_callchain(regs, 0, kernel, user, max_depth, - false, false); - if (unlikely(!trace)) - goto err_fault; + } else { + trace = get_perf_callchain(regs, kernel, user, max_depth, + crosstask, false, 0); + } - if (trace->nr < skip) + if (unlikely(!trace) || trace->nr < skip) { + if (may_fault) + rcu_read_unlock(); goto err_fault; + } trace_nr = trace->nr - skip; - trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; copy_len = trace_nr * elem_size; ips = trace->ip + skip; - if (user && user_build_id) - stack_map_get_build_id_offset(buf, ips, trace_nr, user); - else + if (user_build_id) { + struct bpf_stack_build_id *id_offs = buf; + u32 i; + + for (i = 0; i < trace_nr; i++) + id_offs[i].ip = ips[i]; + } else { memcpy(buf, ips, copy_len); + } + + /* trace/ips should not be dereferenced after this point */ + if (may_fault) + rcu_read_unlock(); + + if (user_build_id) + stack_map_get_build_id_offset(buf, trace_nr, user, may_fault); if (size > copy_len) memset(buf + copy_len, 0, size - copy_len); @@ -455,7 +514,7 @@ clear: BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, u64, flags) { - return __bpf_get_stack(regs, NULL, NULL, buf, size, flags); + return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */); } const struct bpf_func_proto bpf_get_stack_proto = { @@ -468,8 +527,24 @@ const struct bpf_func_proto bpf_get_stack_proto = { .arg4_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, - u32, size, u64, flags) +BPF_CALL_4(bpf_get_stack_sleepable, struct pt_regs *, regs, void *, buf, u32, size, + u64, flags) +{ + return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, true /* may_fault */); +} + +const struct bpf_func_proto bpf_get_stack_sleepable_proto = { + .func = bpf_get_stack_sleepable, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + +static long __bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, + u64 flags, bool may_fault) { struct pt_regs *regs; long res = -EINVAL; @@ -479,12 +554,18 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, regs = task_pt_regs(task); if (regs) - res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + res = __bpf_get_stack(regs, task, NULL, buf, size, flags, may_fault); put_task_stack(task); return res; } +BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, + u32, size, u64, flags) +{ + return __bpf_get_task_stack(task, buf, size, flags, false /* !may_fault */); +} + const struct bpf_func_proto bpf_get_task_stack_proto = { .func = bpf_get_task_stack, .gpl_only = false, @@ -496,6 +577,23 @@ const struct bpf_func_proto bpf_get_task_stack_proto = { .arg4_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_task_stack_sleepable, struct task_struct *, task, void *, buf, + u32, size, u64, flags) +{ + return __bpf_get_task_stack(task, buf, size, flags, true /* !may_fault */); +} + +const struct bpf_func_proto bpf_get_task_stack_sleepable_proto = { + .func = bpf_get_task_stack_sleepable, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { @@ -507,7 +605,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, __u64 nr_kernel; if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) - return __bpf_get_stack(regs, NULL, NULL, buf, size, flags); + return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */); if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_USER_BUILD_ID))) @@ -527,7 +625,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, __u64 nr = trace->nr; trace->nr = nr_kernel; - err = __bpf_get_stack(regs, NULL, trace, buf, size, flags); + err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */); /* restore nr */ trace->nr = nr; @@ -539,7 +637,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, goto clear; flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; - err = __bpf_get_stack(regs, NULL, trace, buf, size, flags); + err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */); } return err; @@ -566,7 +664,15 @@ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) } /* Called from syscall */ -int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) +static int stack_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return bpf_stackmap_extract(map, key, value, true); +} + +/* Called from syscall */ +int bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, + bool delete) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *old_bucket; @@ -583,7 +689,10 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) memcpy(value, bucket->data, trace_len); memset(value + trace_len, 0, map->value_size - trace_len); - old_bucket = xchg(&smap->buckets[id], bucket); + if (delete) + old_bucket = bucket; + else + old_bucket = xchg(&smap->buckets[id], bucket); if (old_bucket) pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return 0; @@ -618,14 +727,14 @@ static int stack_map_get_next_key(struct bpf_map *map, void *key, return 0; } -static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long stack_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { return -EINVAL; } /* Called from syscall or from eBPF program */ -static int stack_map_delete_elem(struct bpf_map *map, void *key) +static long stack_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *old_bucket; @@ -654,6 +763,19 @@ static void stack_map_free(struct bpf_map *map) put_callchain_buffers(); } +static u64 stack_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + u64 value_size = map->value_size; + u64 n_buckets = smap->n_buckets; + u64 enties = map->max_entries; + u64 usage = sizeof(*smap); + + usage += n_buckets * sizeof(struct stack_map_bucket *); + usage += enties * (sizeof(struct stack_map_bucket) + value_size); + return usage; +} + BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map) const struct bpf_map_ops stack_trace_map_ops = { .map_meta_equal = bpf_map_meta_equal, @@ -661,8 +783,10 @@ const struct bpf_map_ops stack_trace_map_ops = { .map_free = stack_map_free, .map_get_next_key = stack_map_get_next_key, .map_lookup_elem = stack_map_lookup_elem, + .map_lookup_and_delete_elem = stack_map_lookup_and_delete_elem, .map_update_elem = stack_map_update_elem, .map_delete_elem = stack_map_delete_elem, .map_check_btf = map_check_no_btf, + .map_mem_usage = stack_map_mem_usage, .map_btf_id = &stack_trace_map_btf_ids[0], }; diff --git a/kernel/bpf/stream.c b/kernel/bpf/stream.c new file mode 100644 index 000000000000..0b6bc3f30335 --- /dev/null +++ b/kernel/bpf/stream.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/bpf_mem_alloc.h> +#include <linux/gfp.h> +#include <linux/memory.h> +#include <linux/mutex.h> + +static void bpf_stream_elem_init(struct bpf_stream_elem *elem, int len) +{ + init_llist_node(&elem->node); + elem->total_len = len; + elem->consumed_len = 0; +} + +static struct bpf_stream_elem *bpf_stream_elem_alloc(int len) +{ + const int max_len = ARRAY_SIZE((struct bpf_bprintf_buffers){}.buf); + struct bpf_stream_elem *elem; + size_t alloc_size; + + /* + * Length denotes the amount of data to be written as part of stream element, + * thus includes '\0' byte. We're capped by how much bpf_bprintf_buffers can + * accomodate, therefore deny allocations that won't fit into them. + */ + if (len < 0 || len > max_len) + return NULL; + + alloc_size = offsetof(struct bpf_stream_elem, str[len]); + elem = kmalloc_nolock(alloc_size, __GFP_ZERO, -1); + if (!elem) + return NULL; + + bpf_stream_elem_init(elem, len); + + return elem; +} + +static int __bpf_stream_push_str(struct llist_head *log, const char *str, int len) +{ + struct bpf_stream_elem *elem = NULL; + + /* + * Allocate a bpf_prog_stream_elem and push it to the bpf_prog_stream + * log, elements will be popped at once and reversed to print the log. + */ + elem = bpf_stream_elem_alloc(len); + if (!elem) + return -ENOMEM; + + memcpy(elem->str, str, len); + llist_add(&elem->node, log); + + return 0; +} + +static int bpf_stream_consume_capacity(struct bpf_stream *stream, int len) +{ + if (atomic_read(&stream->capacity) >= BPF_STREAM_MAX_CAPACITY) + return -ENOSPC; + if (atomic_add_return(len, &stream->capacity) >= BPF_STREAM_MAX_CAPACITY) { + atomic_sub(len, &stream->capacity); + return -ENOSPC; + } + return 0; +} + +static void bpf_stream_release_capacity(struct bpf_stream *stream, struct bpf_stream_elem *elem) +{ + int len = elem->total_len; + + atomic_sub(len, &stream->capacity); +} + +static int bpf_stream_push_str(struct bpf_stream *stream, const char *str, int len) +{ + int ret = bpf_stream_consume_capacity(stream, len); + + return ret ?: __bpf_stream_push_str(&stream->log, str, len); +} + +static struct bpf_stream *bpf_stream_get(enum bpf_stream_id stream_id, struct bpf_prog_aux *aux) +{ + if (stream_id != BPF_STDOUT && stream_id != BPF_STDERR) + return NULL; + return &aux->stream[stream_id - 1]; +} + +static void bpf_stream_free_elem(struct bpf_stream_elem *elem) +{ + kfree_nolock(elem); +} + +static void bpf_stream_free_list(struct llist_node *list) +{ + struct bpf_stream_elem *elem, *tmp; + + llist_for_each_entry_safe(elem, tmp, list, node) + bpf_stream_free_elem(elem); +} + +static struct llist_node *bpf_stream_backlog_peek(struct bpf_stream *stream) +{ + return stream->backlog_head; +} + +static struct llist_node *bpf_stream_backlog_pop(struct bpf_stream *stream) +{ + struct llist_node *node; + + node = stream->backlog_head; + if (stream->backlog_head == stream->backlog_tail) + stream->backlog_head = stream->backlog_tail = NULL; + else + stream->backlog_head = node->next; + return node; +} + +static void bpf_stream_backlog_fill(struct bpf_stream *stream) +{ + struct llist_node *head, *tail; + + if (llist_empty(&stream->log)) + return; + tail = llist_del_all(&stream->log); + if (!tail) + return; + head = llist_reverse_order(tail); + + if (!stream->backlog_head) { + stream->backlog_head = head; + stream->backlog_tail = tail; + } else { + stream->backlog_tail->next = head; + stream->backlog_tail = tail; + } + + return; +} + +static bool bpf_stream_consume_elem(struct bpf_stream_elem *elem, int *len) +{ + int rem = elem->total_len - elem->consumed_len; + int used = min(rem, *len); + + elem->consumed_len += used; + *len -= used; + + return elem->consumed_len == elem->total_len; +} + +static int bpf_stream_read(struct bpf_stream *stream, void __user *buf, int len) +{ + int rem_len = len, cons_len, ret = 0; + struct bpf_stream_elem *elem = NULL; + struct llist_node *node; + + mutex_lock(&stream->lock); + + while (rem_len) { + int pos = len - rem_len; + bool cont; + + node = bpf_stream_backlog_peek(stream); + if (!node) { + bpf_stream_backlog_fill(stream); + node = bpf_stream_backlog_peek(stream); + } + if (!node) + break; + elem = container_of(node, typeof(*elem), node); + + cons_len = elem->consumed_len; + cont = bpf_stream_consume_elem(elem, &rem_len) == false; + + ret = copy_to_user(buf + pos, elem->str + cons_len, + elem->consumed_len - cons_len); + /* Restore in case of error. */ + if (ret) { + ret = -EFAULT; + elem->consumed_len = cons_len; + break; + } + + if (cont) + continue; + bpf_stream_backlog_pop(stream); + bpf_stream_release_capacity(stream, elem); + bpf_stream_free_elem(elem); + } + + mutex_unlock(&stream->lock); + return ret ? ret : len - rem_len; +} + +int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len) +{ + struct bpf_stream *stream; + + stream = bpf_stream_get(stream_id, prog->aux); + if (!stream) + return -ENOENT; + return bpf_stream_read(stream, buf, len); +} + +__bpf_kfunc_start_defs(); + +/* + * Avoid using enum bpf_stream_id so that kfunc users don't have to pull in the + * enum in headers. + */ +__bpf_kfunc int bpf_stream_vprintk_impl(int stream_id, const char *fmt__str, const void *args, + u32 len__sz, void *aux__prog) +{ + struct bpf_bprintf_data data = { + .get_bin_args = true, + .get_buf = true, + }; + struct bpf_prog_aux *aux = aux__prog; + u32 fmt_size = strlen(fmt__str) + 1; + struct bpf_stream *stream; + u32 data_len = len__sz; + int ret, num_args; + + stream = bpf_stream_get(stream_id, aux); + if (!stream) + return -ENOENT; + + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || + (data_len && !args)) + return -EINVAL; + num_args = data_len / 8; + + ret = bpf_bprintf_prepare(fmt__str, fmt_size, args, num_args, &data); + if (ret < 0) + return ret; + + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt__str, data.bin_args); + /* Exclude NULL byte during push. */ + ret = bpf_stream_push_str(stream, data.buf, ret); + bpf_bprintf_cleanup(&data); + + return ret; +} + +__bpf_kfunc_end_defs(); + +/* Added kfunc to common_btf_ids */ + +void bpf_prog_stream_init(struct bpf_prog *prog) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { + atomic_set(&prog->aux->stream[i].capacity, 0); + init_llist_head(&prog->aux->stream[i].log); + mutex_init(&prog->aux->stream[i].lock); + prog->aux->stream[i].backlog_head = NULL; + prog->aux->stream[i].backlog_tail = NULL; + } +} + +void bpf_prog_stream_free(struct bpf_prog *prog) +{ + struct llist_node *list; + int i; + + for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { + list = llist_del_all(&prog->aux->stream[i].log); + bpf_stream_free_list(list); + bpf_stream_free_list(prog->aux->stream[i].backlog_head); + } +} + +void bpf_stream_stage_init(struct bpf_stream_stage *ss) +{ + init_llist_head(&ss->log); + ss->len = 0; +} + +void bpf_stream_stage_free(struct bpf_stream_stage *ss) +{ + struct llist_node *node; + + node = llist_del_all(&ss->log); + bpf_stream_free_list(node); +} + +int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...) +{ + struct bpf_bprintf_buffers *buf; + va_list args; + int ret; + + if (bpf_try_get_buffers(&buf)) + return -EBUSY; + + va_start(args, fmt); + ret = vsnprintf(buf->buf, ARRAY_SIZE(buf->buf), fmt, args); + va_end(args); + ss->len += ret; + /* Exclude NULL byte during push. */ + ret = __bpf_stream_push_str(&ss->log, buf->buf, ret); + bpf_put_buffers(); + return ret; +} + +int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog, + enum bpf_stream_id stream_id) +{ + struct llist_node *list, *head, *tail; + struct bpf_stream *stream; + int ret; + + stream = bpf_stream_get(stream_id, prog->aux); + if (!stream) + return -EINVAL; + + ret = bpf_stream_consume_capacity(stream, ss->len); + if (ret) + return ret; + + list = llist_del_all(&ss->log); + head = tail = list; + + if (!list) + return 0; + while (llist_next(list)) { + tail = llist_next(list); + list = tail; + } + llist_add_batch(head, tail, &stream->log); + return 0; +} + +struct dump_stack_ctx { + struct bpf_stream_stage *ss; + int err; +}; + +static bool dump_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp) +{ + struct dump_stack_ctx *ctxp = cookie; + const char *file = "", *line = ""; + struct bpf_prog *prog; + int num, ret; + + rcu_read_lock(); + prog = bpf_prog_ksym_find(ip); + rcu_read_unlock(); + if (prog) { + ret = bpf_prog_get_file_line(prog, ip, &file, &line, &num); + if (ret < 0) + goto end; + ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n %s @ %s:%d\n", + (void *)(long)ip, line, file, num); + return !ctxp->err; + } +end: + ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n", (void *)(long)ip); + return !ctxp->err; +} + +int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss) +{ + struct dump_stack_ctx ctx = { .ss = ss }; + int ret; + + ret = bpf_stream_stage_printk(ss, "CPU: %d UID: %d PID: %d Comm: %s\n", + raw_smp_processor_id(), __kuid_val(current_real_cred()->euid), + current->pid, current->comm); + if (ret) + return ret; + ret = bpf_stream_stage_printk(ss, "Call trace:\n"); + if (ret) + return ret; + arch_bpf_stack_walk(dump_stack_cb, &ctx); + if (ctx.err) + return ctx.err; + return bpf_stream_stage_printk(ss, "\n"); +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ecca9366c7a6..4ff82144f885 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ +#include <crypto/sha2.h> #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> @@ -35,6 +36,14 @@ #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #include <linux/trace_events.h> +#include <linux/tracepoint.h> +#include <linux/overflow.h> +#include <linux/cookie.h> +#include <linux/verification.h> + +#include <net/netfilter/nf_bpf_link.h> +#include <net/netkit.h> +#include <net/tcx.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -47,6 +56,7 @@ #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); +DEFINE_COOKIE(bpf_map_cookie); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); @@ -105,37 +115,9 @@ const struct bpf_map_ops bpf_map_offload_ops = { .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, + .map_mem_usage = bpf_map_offload_map_mem_usage, }; -static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) -{ - const struct bpf_map_ops *ops; - u32 type = attr->map_type; - struct bpf_map *map; - int err; - - if (type >= ARRAY_SIZE(bpf_map_types)) - return ERR_PTR(-EINVAL); - type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types)); - ops = bpf_map_types[type]; - if (!ops) - return ERR_PTR(-EINVAL); - - if (ops->map_alloc_check) { - err = ops->map_alloc_check(attr); - if (err) - return ERR_PTR(err); - } - if (attr->map_ifindex) - ops = &bpf_map_offload_ops; - map = ops->map_alloc(attr); - if (IS_ERR(map)) - return map; - map->ops = ops; - map->map_type = type; - return map; -} - static void bpf_map_write_active_inc(struct bpf_map *map) { atomic64_inc(&map->writecnt); @@ -166,13 +148,100 @@ static u32 bpf_map_value_size(const struct bpf_map *map) static void maybe_wait_bpf_programs(struct bpf_map *map) { - /* Wait for any running BPF programs to complete so that - * userspace, when we return to it, knows that all programs - * that could be running use the new map value. + /* Wait for any running non-sleepable BPF programs to complete so that + * userspace, when we return to it, knows that all non-sleepable + * programs that could be running use the new map value. For sleepable + * BPF programs, synchronize_rcu_tasks_trace() should be used to wait + * for the completions of these programs, but considering the waiting + * time can be very long and userspace may think it will hang forever, + * so don't handle sleepable BPF programs now. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) - synchronize_rcu(); + synchronize_rcu_expedited(); +} + +static void unpin_uptr_kaddr(void *kaddr) +{ + if (kaddr) + unpin_user_page(virt_to_page(kaddr)); +} + +static void __bpf_obj_unpin_uptrs(struct btf_record *rec, u32 cnt, void *obj) +{ + const struct btf_field *field; + void **uptr_addr; + int i; + + for (i = 0, field = rec->fields; i < cnt; i++, field++) { + if (field->type != BPF_UPTR) + continue; + + uptr_addr = obj + field->offset; + unpin_uptr_kaddr(*uptr_addr); + } +} + +static void bpf_obj_unpin_uptrs(struct btf_record *rec, void *obj) +{ + if (!btf_record_has_field(rec, BPF_UPTR)) + return; + + __bpf_obj_unpin_uptrs(rec, rec->cnt, obj); +} + +static int bpf_obj_pin_uptrs(struct btf_record *rec, void *obj) +{ + const struct btf_field *field; + const struct btf_type *t; + unsigned long start, end; + struct page *page; + void **uptr_addr; + int i, err; + + if (!btf_record_has_field(rec, BPF_UPTR)) + return 0; + + for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { + if (field->type != BPF_UPTR) + continue; + + uptr_addr = obj + field->offset; + start = *(unsigned long *)uptr_addr; + if (!start) + continue; + + t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); + /* t->size was checked for zero before */ + if (check_add_overflow(start, t->size - 1, &end)) { + err = -EFAULT; + goto unpin_all; + } + + /* The uptr's struct cannot span across two pages */ + if ((start & PAGE_MASK) != (end & PAGE_MASK)) { + err = -EOPNOTSUPP; + goto unpin_all; + } + + err = pin_user_pages_fast(start, 1, FOLL_LONGTERM | FOLL_WRITE, &page); + if (err != 1) + goto unpin_all; + + if (PageHighMem(page)) { + err = -EOPNOTSUPP; + unpin_user_page(page); + goto unpin_all; + } + + *uptr_addr = page_address(page) + offset_in_page(start); + } + + return 0; + +unpin_all: + __bpf_obj_unpin_uptrs(rec, i, obj); + return err; } static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, @@ -181,9 +250,10 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, int err; /* Need to create a kthread, thus must support schedule */ - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || @@ -204,15 +274,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { - rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); - rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - rcu_read_lock(); err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); - rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, @@ -222,12 +288,16 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { - rcu_read_lock(); - err = map->ops->map_update_elem(map, key, value, flags); - rcu_read_unlock(); + err = bpf_obj_pin_uptrs(map->record, value); + if (!err) { + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, flags); + rcu_read_unlock(); + if (err) + bpf_obj_unpin_uptrs(map->record, value); + } } bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); return err; } @@ -238,7 +308,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, void *ptr; int err; - if (bpf_map_is_dev_bound(map)) + if (bpf_map_is_offloaded(map)) return bpf_map_offload_lookup_elem(map, key, value); bpf_disable_instrumentation(); @@ -250,7 +320,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { - err = bpf_stackmap_copy(map, key, value); + err = bpf_stackmap_extract(map, key, value, false); } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { @@ -288,7 +358,6 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); return err; } @@ -309,7 +378,7 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT; + gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO); unsigned int flags = 0; unsigned long align = 1; void *area; @@ -390,7 +459,7 @@ static int bpf_map_alloc_id(struct bpf_map *map) return id > 0 ? 0 : id; } -void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +void bpf_map_free_id(struct bpf_map *map) { unsigned long flags; @@ -402,21 +471,15 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) if (!map->id) return; - if (do_idr_lock) - spin_lock_irqsave(&map_idr_lock, flags); - else - __acquire(&map_idr_lock); + spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; - if (do_idr_lock) - spin_unlock_irqrestore(&map_idr_lock, flags); - else - __release(&map_idr_lock); + spin_unlock_irqrestore(&map_idr_lock, flags); } -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG static void bpf_map_save_memcg(struct bpf_map *map) { /* Currently if a map is created by a process belonging to the root @@ -424,7 +487,8 @@ static void bpf_map_save_memcg(struct bpf_map *map) * So we have to check map->objcg for being NULL each time it's * being used. */ - map->objcg = get_obj_cgroup_from_current(); + if (memcg_bpf_enabled()) + map->objcg = get_obj_cgroup_from_current(); } static void bpf_map_release_memcg(struct bpf_map *map) @@ -456,6 +520,21 @@ void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, return ptr; } +void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags, + int node) +{ + struct mem_cgroup *memcg, *old_memcg; + void *ptr; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = kmalloc_nolock(size, flags | __GFP_ACCOUNT, node); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; +} + void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; @@ -470,6 +549,21 @@ void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) return ptr; } +void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, + gfp_t flags) +{ + struct mem_cgroup *memcg, *old_memcg; + void *ptr; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; +} + void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { @@ -495,6 +589,56 @@ static void bpf_map_release_memcg(struct bpf_map *map) } #endif +static bool can_alloc_pages(void) +{ + return preempt_count() == 0 && !irqs_disabled() && + !IS_ENABLED(CONFIG_PREEMPT_RT); +} + +static struct page *__bpf_alloc_page(int nid) +{ + if (!can_alloc_pages()) + return alloc_pages_nolock(__GFP_ACCOUNT, nid, 0); + + return alloc_pages_node(nid, + GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT + | __GFP_NOWARN, + 0); +} + +int bpf_map_alloc_pages(const struct bpf_map *map, int nid, + unsigned long nr_pages, struct page **pages) +{ + unsigned long i, j; + struct page *pg; + int ret = 0; +#ifdef CONFIG_MEMCG + struct mem_cgroup *memcg, *old_memcg; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); +#endif + for (i = 0; i < nr_pages; i++) { + pg = __bpf_alloc_page(nid); + + if (pg) { + pages[i] = pg; + continue; + } + for (j = 0; j < i; j++) + free_pages_nolock(pages[j], 0); + ret = -ENOMEM; + break; + } + +#ifdef CONFIG_MEMCG + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); +#endif + return ret; +} + + static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; @@ -507,14 +651,14 @@ static int btf_field_cmp(const void *a, const void *b) } struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, - enum btf_field_type type) + u32 field_mask) { struct btf_field *field; - if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & type)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & field_mask)) return NULL; field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); - if (!field || !(field->type & type)) + if (!field || !(field->type & field_mask)) return NULL; return field; } @@ -527,18 +671,26 @@ void btf_record_free(struct btf_record *rec) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: + case BPF_UPTR: if (rec->fields[i].kptr.module) module_put(rec->fields[i].kptr.module); - btf_put(rec->fields[i].kptr.btf); + if (btf_is_kernel(rec->fields[i].kptr.btf)) + btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: - /* Nothing to release for bpf_list_head */ + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_RES_SPIN_LOCK: + case BPF_TIMER: + case BPF_REFCOUNT: + case BPF_WORKQUEUE: + case BPF_TASK_WORK: + /* Nothing to release */ break; default: WARN_ON_ONCE(1); @@ -562,7 +714,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) if (IS_ERR_OR_NULL(rec)) return NULL; - size = offsetof(struct btf_record, fields[rec->cnt]); + size = struct_size(rec, fields, rec->cnt); new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); if (!new_rec) return ERR_PTR(-ENOMEM); @@ -571,12 +723,12 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: - btf_get(fields[i].kptr.btf); + case BPF_KPTR_PERCPU: + case BPF_UPTR: + if (btf_is_kernel(fields[i].kptr.btf)) + btf_get(fields[i].kptr.btf); if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { ret = -ENXIO; goto free; @@ -584,7 +736,15 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) break; case BPF_LIST_HEAD: case BPF_LIST_NODE: - /* Nothing to acquire for bpf_list_head */ + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_RES_SPIN_LOCK: + case BPF_TIMER: + case BPF_REFCOUNT: + case BPF_WORKQUEUE: + case BPF_TASK_WORK: + /* Nothing to acquire */ break; default: ret = -EFAULT; @@ -610,7 +770,7 @@ bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *r return false; if (rec_a->cnt != rec_b->cnt) return false; - size = offsetof(struct btf_record, fields[rec_a->cnt]); + size = struct_size(rec_a, fields, rec_a->cnt); /* btf_parse_fields uses kzalloc to allocate a btf_record, so unused * members are zeroed out. So memcmp is safe to do without worrying * about padding/unused fields. @@ -635,6 +795,20 @@ 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_task_work(const struct btf_record *rec, void *obj) +{ + if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TASK_WORK))) + return; + bpf_task_work_cancel_and_free(obj + rec->task_work_off); +} + void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; @@ -644,27 +818,60 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) return; fields = rec->fields; for (i = 0; i < rec->cnt; i++) { + struct btf_struct_meta *pointee_struct_meta; const struct btf_field *field = &fields[i]; void *field_ptr = obj + field->offset; + void *xchgd_field; switch (fields[i].type) { case BPF_SPIN_LOCK: + case BPF_RES_SPIN_LOCK: break; case BPF_TIMER: bpf_timer_cancel_and_free(field_ptr); break; + case BPF_WORKQUEUE: + bpf_wq_cancel_and_free(field_ptr); + break; + case BPF_TASK_WORK: + bpf_task_work_cancel_and_free(field_ptr); + break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; case BPF_KPTR_REF: - field->kptr.dtor((void *)xchg((unsigned long *)field_ptr, 0)); + case BPF_KPTR_PERCPU: + xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0); + if (!xchgd_field) + break; + + if (!btf_is_kernel(field->kptr.btf)) { + pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, + field->kptr.btf_id); + __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? + pointee_struct_meta->record : NULL, + fields[i].type == BPF_KPTR_PERCPU); + } else { + field->kptr.dtor(xchgd_field); + } + break; + case BPF_UPTR: + /* The caller ensured that no one is using the uptr */ + unpin_uptr_kaddr(*(void **)field_ptr); break; case BPF_LIST_HEAD: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; + case BPF_RB_ROOT: + if (WARN_ON_ONCE(rec->spin_lock_off < 0)) + continue; + bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off); + break; case BPF_LIST_NODE: + case BPF_RB_NODE: + case BPF_REFCOUNT: break; default: WARN_ON_ONCE(1); @@ -673,18 +880,21 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) } } -/* called from workqueue */ -static void bpf_map_free_deferred(struct work_struct *work) +static void bpf_map_free(struct bpf_map *map) { - struct bpf_map *map = container_of(work, struct bpf_map, work); - struct btf_field_offs *foffs = map->field_offs; struct btf_record *rec = map->record; + struct btf *btf = map->btf; - security_bpf_map_free(map); - bpf_map_release_memcg(map); - /* implementation dependent freeing */ + /* implementation dependent freeing. Disabling migration to simplify + * the free of values or special fields allocated from bpf memory + * allocator. + */ + kfree(map->excl_prog_sha); + migrate_disable(); map->ops->map_free(map); - /* Delay freeing of field_offs and btf_record for maps, as map_free + migrate_enable(); + + /* Delay freeing of btf_record for maps, as map_free * callback usually needs access to them. It is better to do it here * than require each callback to do the free itself manually. * @@ -693,8 +903,22 @@ static void bpf_map_free_deferred(struct work_struct *work) * eventually calls bpf_map_free_meta, since inner_map_meta is only a * template bpf_map struct used during verification. */ - kfree(foffs); btf_record_free(rec); + /* Delay freeing of btf for maps, as map_free callback may need + * struct_meta info which will be freed with btf_put(). + */ + btf_put(btf); +} + +/* called from workqueue */ +static void bpf_map_free_deferred(struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + + security_bpf_map_free(map); + bpf_map_release_memcg(map); + bpf_map_owner_free(map); + bpf_map_free(map); } static void bpf_map_put_uref(struct bpf_map *map) @@ -705,26 +929,45 @@ static void bpf_map_put_uref(struct bpf_map *map) } } +static void bpf_map_free_in_work(struct bpf_map *map) +{ + INIT_WORK(&map->work, bpf_map_free_deferred); + /* Avoid spawning kworkers, since they all might contend + * for the same mutex like slab_mutex. + */ + queue_work(system_dfl_wq, &map->work); +} + +static void bpf_map_free_rcu_gp(struct rcu_head *rcu) +{ + bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); +} + +static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_map_free_rcu_gp(rcu); + else + call_rcu(rcu, bpf_map_free_rcu_gp); +} + /* decrement map refcnt and schedule it for freeing via workqueue - * (unrelying map implementation ops->map_free() might sleep) + * (underlying map implementation ops->map_free() might sleep) */ -static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) +void bpf_map_put(struct bpf_map *map) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ - bpf_map_free_id(map, do_idr_lock); - btf_put(map->btf); - INIT_WORK(&map->work, bpf_map_free_deferred); - /* Avoid spawning kworkers, since they all might contend - * for the same mutex like slab_mutex. - */ - queue_work(system_unbound_wq, &map->work); - } -} + bpf_map_free_id(map); -void bpf_map_put(struct bpf_map *map) -{ - __bpf_map_put(map, true); + WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); + if (READ_ONCE(map->free_after_mult_rcu_gp)) + call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); + else if (READ_ONCE(map->free_after_rcu_gp)) + call_rcu(&map->rcu, bpf_map_free_rcu_gp); + else + bpf_map_free_in_work(map); + } } EXPORT_SYMBOL_GPL(bpf_map_put); @@ -747,7 +990,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp) static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) { - fmode_t mode = f.file->f_mode; + fmode_t mode = fd_file(f)->f_mode; /* Our file permissions may have been overridden by global * map permissions facing syscall side. @@ -758,17 +1001,10 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) } #ifdef CONFIG_PROC_FS -/* Provides an approximation of the map's memory footprint. - * Used only to provide a backward compatibility and display - * a reasonable "memlock" info. - */ -static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) +/* Show the memory usage of a bpf map */ +static u64 bpf_map_memory_usage(const struct bpf_map *map) { - unsigned long size; - - size = round_up(map->key_size + bpf_map_value_size(map), 8); - - return round_up(map->max_entries * size, PAGE_SIZE); + return map->ops->map_mem_usage(map); } static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) @@ -776,12 +1012,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; - if (map_type_contains_progs(map)) { - spin_lock(&map->owner.lock); - type = map->owner.type; - jited = map->owner.jited; - spin_unlock(&map->owner.lock); + spin_lock(&map->owner_lock); + if (map->owner) { + type = map->owner->type; + jited = map->owner->jited; } + spin_unlock(&map->owner_lock); seq_printf(m, "map_type:\t%u\n" @@ -790,7 +1026,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "max_entries:\t%u\n" "map_flags:\t%#x\n" "map_extra:\t%#llx\n" - "memlock:\t%lu\n" + "memlock:\t%llu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, @@ -799,7 +1035,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->max_entries, map->map_flags, (unsigned long long)map->map_extra, - bpf_map_memory_footprint(map), + bpf_map_memory_usage(map), map->id, READ_ONCE(map->frozen)); if (type) { @@ -853,7 +1089,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = { static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; - int err; + int err = 0; if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; @@ -877,24 +1113,33 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) err = -EACCES; goto out; } + bpf_map_write_active_inc(map); } +out: + mutex_unlock(&map->freeze_mutex); + if (err) + return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; - vma->vm_flags &= ~VM_MAYEXEC; + vm_flags_clear(vma, VM_MAYEXEC); + /* If mapping is read-only, then disallow potentially re-mapping with + * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing + * means that as far as BPF map's memory-mapped VMAs are concerned, + * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, + * both should be set, so we can forget about VM_MAYWRITE and always + * check just VM_WRITE + */ if (!(vma->vm_flags & VM_WRITE)) - /* disallow re-mapping with PROT_WRITE */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); - if (err) - goto out; + if (err) { + if (vma->vm_flags & VM_WRITE) + bpf_map_write_active_dec(map); + } - if (vma->vm_flags & VM_MAYWRITE) - bpf_map_write_active_inc(map); -out: - mutex_unlock(&map->freeze_mutex); return err; } @@ -908,6 +1153,21 @@ static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) return EPOLLERR; } +static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct bpf_map *map = filp->private_data; + + if (map->ops->map_get_unmapped_area) + return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); +#ifdef CONFIG_MMU + return mm_get_unmapped_area(filp, addr, len, pgoff, flags); +#else + return addr; +#endif +} + const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, @@ -917,6 +1177,7 @@ const struct file_operations bpf_map_fops = { .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, + .get_unmapped_area = bpf_get_unmapped_area, }; int bpf_map_new_fd(struct bpf_map *map, int flags) @@ -973,6 +1234,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) return src - orig_src; } +EXPORT_SYMBOL_GPL(bpf_obj_name_cpy); int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, @@ -982,8 +1244,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1005,12 +1267,14 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EINVAL; map->record = btf_parse_fields(btf, value_type, - BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD, + BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | + BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR | + BPF_TASK_WORK, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1023,6 +1287,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, case 0: continue; case BPF_SPIN_LOCK: + case BPF_RES_SPIN_LOCK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && @@ -1035,6 +1300,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } break; case BPF_TIMER: + case BPF_WORKQUEUE: + case BPF_TASK_WORK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { @@ -1044,15 +1311,30 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: + case BPF_REFCOUNT: if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { + map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && + map->map_type != BPF_MAP_TYPE_SK_STORAGE && + map->map_type != BPF_MAP_TYPE_INODE_STORAGE && + map->map_type != BPF_MAP_TYPE_TASK_STORAGE && + map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; + case BPF_UPTR: + if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_LIST_HEAD: + case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { @@ -1084,13 +1366,21 @@ free_map_tab: return ret; } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +static bool bpf_net_capable(void) +{ + return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); +} + +#define BPF_MAP_CREATE_LAST_FIELD excl_prog_hash_size /* called via syscall */ -static int map_create(union bpf_attr *attr) +static int map_create(union bpf_attr *attr, bpfptr_t uattr) { + const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); - struct btf_field_offs *foffs; + u32 map_type = attr->map_type; struct bpf_map *map; + bool token_flag; int f_flags; int err; @@ -1098,6 +1388,12 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it + * to avoid per-map type checks tripping on unknown flag + */ + token_flag = attr->map_flags & BPF_F_TOKEN_FD; + attr->map_flags &= ~BPF_F_TOKEN_FD; + if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) @@ -1107,6 +1403,7 @@ static int map_create(union bpf_attr *attr) } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; @@ -1120,19 +1417,121 @@ static int map_create(union bpf_attr *attr) return -EINVAL; /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ - map = find_and_alloc_map(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + map_type = attr->map_type; + if (map_type >= ARRAY_SIZE(bpf_map_types)) + return -EINVAL; + map_type = array_index_nospec(map_type, ARRAY_SIZE(bpf_map_types)); + ops = bpf_map_types[map_type]; + if (!ops) + return -EINVAL; + + if (ops->map_alloc_check) { + err = ops->map_alloc_check(attr); + if (err) + return err; + } + if (attr->map_ifindex) + ops = &bpf_map_offload_ops; + if (!ops->map_mem_usage) + return -EINVAL; + + if (token_flag) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + + /* Intent here is for unprivileged_bpf_disabled to block BPF map + * creation for unprivileged users; other actions depend + * on fd availability and access to bpffs, so are dependent on + * object creation success. Even with unprivileged BPF disabled, + * capability checks are still carried out. + */ + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; + + /* check privileged map type permissions */ + switch (map_type) { + case BPF_MAP_TYPE_ARRAY: + case BPF_MAP_TYPE_PERCPU_ARRAY: + case BPF_MAP_TYPE_PROG_ARRAY: + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_PERCPU_HASH: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_RINGBUF: + case BPF_MAP_TYPE_USER_RINGBUF: + case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: + /* unprivileged */ + break; + case BPF_MAP_TYPE_SK_STORAGE: + case BPF_MAP_TYPE_INODE_STORAGE: + case BPF_MAP_TYPE_TASK_STORAGE: + case BPF_MAP_TYPE_CGRP_STORAGE: + case BPF_MAP_TYPE_BLOOM_FILTER: + case BPF_MAP_TYPE_LPM_TRIE: + case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_LRU_HASH: + case BPF_MAP_TYPE_LRU_PERCPU_HASH: + case BPF_MAP_TYPE_STRUCT_OPS: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_ARENA: + case BPF_MAP_TYPE_INSN_ARRAY: + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; + break; + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_XSKMAP: + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + break; + default: + WARN(1, "unsupported map type %d", map_type); + goto put_token; + } + + map = ops->map_alloc(attr); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } + map->ops = ops; + map->map_type = map_type; err = bpf_obj_name_cpy(map->name, attr->map_name, sizeof(attr->map_name)); if (err < 0) goto free_map; + preempt_disable(); + map->cookie = gen_cookie_next(&bpf_map_cookie); + preempt_enable(); + atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); - spin_lock_init(&map->owner.lock); + spin_lock_init(&map->owner_lock); if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, @@ -1157,7 +1556,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1169,23 +1568,39 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } + if (attr->excl_prog_hash) { + bpfptr_t uprog_hash = make_bpfptr(attr->excl_prog_hash, uattr.is_kernel); - foffs = btf_parse_field_offs(map->record); - if (IS_ERR(foffs)) { - err = PTR_ERR(foffs); + if (attr->excl_prog_hash_size != SHA256_DIGEST_SIZE) { + err = -EINVAL; + goto free_map; + } + + map->excl_prog_sha = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL); + if (!map->excl_prog_sha) { + err = -ENOMEM; + goto free_map; + } + + if (copy_from_bpfptr(map->excl_prog_sha, uprog_hash, SHA256_DIGEST_SIZE)) { + err = -EFAULT; + goto free_map; + } + } else if (attr->excl_prog_hash_size) { + err = -EINVAL; goto free_map; } - map->field_offs = foffs; - err = security_bpf_map_alloc(map); + err = security_bpf_map_create(map, attr, token, uattr.is_kernel); if (err) - goto free_map_field_offs; + goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1203,29 +1618,13 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); -free_map_field_offs: - kfree(map->field_offs); free_map: - btf_put(map->btf); - map->ops->map_free(map); + bpf_map_free(map); +put_token: + bpf_token_put(token); return err; } -/* if error is returned, fd is released. - * On success caller should complete fd access with matching fdput() - */ -struct bpf_map *__bpf_map_get(struct fd f) -{ - if (!f.file) - return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_map_fops) { - fdput(f); - return ERR_PTR(-EINVAL); - } - - return f.file->private_data; -} - void bpf_map_inc(struct bpf_map *map) { atomic64_inc(&map->refcnt); @@ -1241,37 +1640,31 @@ EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); struct bpf_map *bpf_map_get(u32 ufd) { - struct fd f = fdget(ufd); - struct bpf_map *map; - - map = __bpf_map_get(f); - if (IS_ERR(map)) - return map; + CLASS(fd, f)(ufd); + struct bpf_map *map = __bpf_map_get(f); - bpf_map_inc(map); - fdput(f); + if (!IS_ERR(map)) + bpf_map_inc(map); return map; } -EXPORT_SYMBOL(bpf_map_get); +EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL"); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { - struct fd f = fdget(ufd); - struct bpf_map *map; - - map = __bpf_map_get(f); - if (IS_ERR(map)) - return map; + CLASS(fd, f)(ufd); + struct bpf_map *map = __bpf_map_get(f); - bpf_map_inc_with_uref(map); - fdput(f); + if (!IS_ERR(map)) + bpf_map_inc_with_uref(map); return map; } -/* map_idr_lock should have been held */ -static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) +/* map_idr_lock should have been held or the map should have been + * protected by rcu read lock. + */ +struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; @@ -1286,15 +1679,13 @@ static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { - spin_lock_bh(&map_idr_lock); - map = __bpf_map_inc_not_zero(map, false); - spin_unlock_bh(&map_idr_lock); - - return map; + lockdep_assert(rcu_read_lock_held()); + return __bpf_map_inc_not_zero(map, false); } EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); -int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) +int __weak bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, + bool delete) { return -ENOTSUPP; } @@ -1328,39 +1719,28 @@ static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; - if (attr->flags & ~BPF_F_LOCK) - return -EINVAL; - - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { - err = -EPERM; - goto err_put; - } + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) + return -EPERM; - if ((attr->flags & BPF_F_LOCK) && - !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { - err = -EINVAL; - goto err_put; - } + err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK); + if (err) + return err; key = __bpf_copy_key(ukey, map->key_size); - if (IS_ERR(key)) { - err = PTR_ERR(key); - goto err_put; - } + if (IS_ERR(key)) + return PTR_ERR(key); value_size = bpf_map_value_size(map); @@ -1391,8 +1771,6 @@ free_value: kvfree(value); free_key: kvfree(key); -err_put: - fdput(f); return err; } @@ -1403,17 +1781,15 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -1423,11 +1799,9 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) goto err_put; } - if ((attr->flags & BPF_F_LOCK) && - !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { - err = -EINVAL; + err = bpf_map_check_op_flags(map, attr->flags, ~0); + if (err) goto err_put; - } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { @@ -1442,14 +1816,15 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) goto free_key; } - err = bpf_map_update_value(map, f.file, key, value, attr->flags); + err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags); + if (!err) + maybe_wait_bpf_programs(map); kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); - fdput(f); return err; } @@ -1458,16 +1833,14 @@ err_put: static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); - int ufd = attr->map_fd; struct bpf_map *map; - struct fd f; void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -1483,7 +1856,7 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) goto err_put; } - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; } else if (IS_FD_PROG_ARRAY(map) || @@ -1498,12 +1871,12 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); + if (!err) + maybe_wait_bpf_programs(map); out: kvfree(key); err_put: bpf_map_write_active_dec(map); - fdput(f); return err; } @@ -1514,30 +1887,24 @@ static int map_get_next_key(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *unext_key = u64_to_user_ptr(attr->next_key); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *next_key; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { - err = -EPERM; - goto err_put; - } + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) + return -EPERM; if (ukey) { key = __bpf_copy_key(ukey, map->key_size); - if (IS_ERR(key)) { - err = PTR_ERR(key); - goto err_put; - } + if (IS_ERR(key)) + return PTR_ERR(key); } else { key = NULL; } @@ -1547,7 +1914,7 @@ static int map_get_next_key(union bpf_attr *attr) if (!next_key) goto free_key; - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); goto out; } @@ -1569,8 +1936,6 @@ free_next_key: kvfree(next_key); free_key: kvfree(key); -err_put: - fdput(f); return err; } @@ -1595,6 +1960,9 @@ int generic_map_delete_batch(struct bpf_map *map, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1605,7 +1973,7 @@ int generic_map_delete_batch(struct bpf_map *map, map->key_size)) break; - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); break; } @@ -1624,7 +1992,6 @@ int generic_map_delete_batch(struct bpf_map *map, kvfree(key); - maybe_wait_bpf_programs(map); return err; } @@ -1638,13 +2005,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, void *key, *value; int err = 0; - if (attr->batch.elem_flags & ~BPF_F_LOCK) - return -EINVAL; - - if ((attr->batch.elem_flags & BPF_F_LOCK) && - !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { - return -EINVAL; - } + err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK); + if (err) + return err; value_size = bpf_map_value_size(map); @@ -1652,6 +2015,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1682,11 +2048,10 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, kvfree(value); kvfree(key); + return err; } -#define MAP_LOOKUP_RETRIES 3 - int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -1696,15 +2061,12 @@ int generic_map_lookup_batch(struct bpf_map *map, void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; - int err, retry = MAP_LOOKUP_RETRIES; u32 value_size, cp, max_count; + int err; - if (attr->batch.elem_flags & ~BPF_F_LOCK) - return -EINVAL; - - if ((attr->batch.elem_flags & BPF_F_LOCK) && - !btf_record_has_field(map->record, BPF_SPIN_LOCK)) - return -EINVAL; + err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK); + if (err) + return err; value_size = bpf_map_value_size(map); @@ -1743,14 +2105,8 @@ int generic_map_lookup_batch(struct bpf_map *map, err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); - if (err == -ENOENT) { - if (retry) { - retry--; - continue; - } - err = -EINTR; - break; - } + if (err == -ENOENT) + goto next_key; if (err) goto free_buf; @@ -1765,12 +2121,12 @@ int generic_map_lookup_batch(struct bpf_map *map, goto free_buf; } + cp++; +next_key: if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); - retry = MAP_LOOKUP_RETRIES; - cp++; cond_resched(); } @@ -1793,11 +2149,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); - int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; - struct fd f; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) @@ -1806,7 +2160,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (attr->flags & ~BPF_F_LOCK) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -1850,8 +2204,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) } else if (map->map_type == BPF_MAP_TYPE_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - if (!bpf_map_is_dev_bound(map)) { + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_STACK_TRACE) { + if (!bpf_map_is_offloaded(map)) { bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); @@ -1876,7 +2231,6 @@ free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); - fdput(f); return err; } @@ -1884,22 +2238,22 @@ err_put: static int map_freeze(const union bpf_attr *attr) { - int err = 0, ufd = attr->map_fd; + int err = 0; struct bpf_map *map; - struct fd f; if (CHECK_ATTR(BPF_MAP_FREEZE)) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) { - fdput(f); + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; - } + + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) + return -EPERM; mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { @@ -1910,15 +2264,10 @@ static int map_freeze(const union bpf_attr *attr) err = -EBUSY; goto err_put; } - if (!bpf_capable()) { - err = -EPERM; - goto err_put; - } WRITE_ONCE(map->frozen, true); err_put: mutex_unlock(&map->freeze_mutex); - fdput(f); return err; } @@ -1944,7 +2293,7 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) if (!ops) return -EINVAL; - if (!bpf_prog_is_dev_bound(prog->aux)) + if (!bpf_prog_is_offloaded(prog->aux)) prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; @@ -1972,7 +2321,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) return; if (audit_enabled == AUDIT_OFF) return; - if (!in_irq() && !irqs_disabled()) + if (!in_hardirq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) @@ -2026,7 +2375,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); - security_bpf_prog_free(aux); + security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } @@ -2034,14 +2383,16 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); + module_put(prog->aux->mod); kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); + kfree(prog->aux->ctx_arg_info); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); if (deferred) { - if (prog->aux->sleepable) + if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); @@ -2068,7 +2419,7 @@ static void __bpf_prog_put(struct bpf_prog *prog) struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { - if (in_irq() || irqs_disabled()) { + if (in_hardirq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); } else { @@ -2102,6 +2453,9 @@ void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) struct bpf_prog_stats *stats; unsigned int flags; + if (unlikely(!prog->stats)) + return; + stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); @@ -2187,18 +2541,6 @@ int bpf_prog_new_fd(struct bpf_prog *prog) O_RDWR | O_CLOEXEC); } -static struct bpf_prog *____bpf_prog_get(struct fd f) -{ - if (!f.file) - return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_prog_fops) { - fdput(f); - return ERR_PTR(-EINVAL); - } - - return f.file->private_data; -} - void bpf_prog_add(struct bpf_prog *prog, int i) { atomic64_add(i, &prog->aux->refcnt); @@ -2245,7 +2587,7 @@ bool bpf_prog_get_ok(struct bpf_prog *prog, if (prog->type != *attach_type) return false; - if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv) + if (bpf_prog_is_offloaded(prog->aux) && !attach_drv) return false; return true; @@ -2254,20 +2596,19 @@ bool bpf_prog_get_ok(struct bpf_prog *prog, static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, bool attach_drv) { - struct fd f = fdget(ufd); + CLASS(fd, f)(ufd); struct bpf_prog *prog; - prog = ____bpf_prog_get(f); - if (IS_ERR(prog)) - return prog; - if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) { - prog = ERR_PTR(-EINVAL); - goto out; - } + if (fd_empty(f)) + return ERR_PTR(-EBADF); + if (fd_file(f)->f_op != &bpf_prog_fops) + return ERR_PTR(-EINVAL); + + prog = fd_file(f)->private_data; + if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) + return ERR_PTR(-EINVAL); bpf_prog_inc(prog); -out: - fdput(f); return prog; } @@ -2362,14 +2703,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; @@ -2402,6 +2748,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_NETFILTER: + if (expected_attach_type == BPF_NETFILTER) + return 0; + return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) @@ -2424,7 +2774,6 @@ static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: - case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SOCK: @@ -2433,6 +2782,7 @@ static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_EXT: /* extends any prog */ + case BPF_PROG_TYPE_NETFILTER: return true; case BPF_PROG_TYPE_CGROUP_SKB: /* always unpriv */ @@ -2461,17 +2811,71 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } } +static int bpf_prog_verify_signature(struct bpf_prog *prog, union bpf_attr *attr, + bool is_kernel) +{ + bpfptr_t usig = make_bpfptr(attr->signature, is_kernel); + struct bpf_dynptr_kern sig_ptr, insns_ptr; + struct bpf_key *key = NULL; + void *sig; + int err = 0; + + if (system_keyring_id_check(attr->keyring_id) == 0) + key = bpf_lookup_system_key(attr->keyring_id); + else + key = bpf_lookup_user_key(attr->keyring_id, 0); + + if (!key) + return -EINVAL; + + sig = kvmemdup_bpfptr(usig, attr->signature_size); + if (IS_ERR(sig)) { + bpf_key_put(key); + return -ENOMEM; + } + + bpf_dynptr_init(&sig_ptr, sig, BPF_DYNPTR_TYPE_LOCAL, 0, + attr->signature_size); + bpf_dynptr_init(&insns_ptr, prog->insnsi, BPF_DYNPTR_TYPE_LOCAL, 0, + prog->len * sizeof(struct bpf_insn)); + + err = bpf_verify_pkcs7_signature((struct bpf_dynptr *)&insns_ptr, + (struct bpf_dynptr *)&sig_ptr, key); + + bpf_key_put(key); + kvfree(sig); + return err; +} + +static int bpf_prog_mark_insn_arrays_ready(struct bpf_prog *prog) +{ + int err; + int i; + + for (i = 0; i < prog->aux->used_map_cnt; i++) { + if (prog->aux->used_maps[i]->map_type != BPF_MAP_TYPE_INSN_ARRAY) + continue; + + err = bpf_insn_array_ready(prog->aux->used_maps[i]); + if (err) + return err; + } + + return 0; +} + /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size +#define BPF_PROG_LOAD_LAST_FIELD keyring_id -static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) +static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; - bool is_gpl; if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; @@ -2481,36 +2885,62 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | - BPF_F_XDP_HAS_FRAGS)) + BPF_F_XDP_HAS_FRAGS | + BPF_F_XDP_DEV_BOUND_ONLY | + BPF_F_TEST_REG_INVARIANTS | + BPF_F_TOKEN_FD)) return -EINVAL; - if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && - (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + bpf_prog_load_fixup_attach_type(attr); - /* copy eBPF program license from user space */ - if (strncpy_from_bpfptr(license, - make_bpfptr(attr->license, uattr.is_kernel), - sizeof(license) - 1) < 0) - return -EFAULT; - license[sizeof(license) - 1] = 0; + if (attr->prog_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } - /* eBPF programs must be GPL compatible to use GPL-ed functions */ - is_gpl = license_is_gpl_compatible(license); + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && + (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && + !bpf_cap) + goto put_token; + + /* Intent here is for unprivileged_bpf_disabled to block BPF program + * creation for unprivileged users; other actions depend + * on fd availability and access to bpffs, so are dependent on + * object creation success. Even with unprivileged BPF disabled, + * capability checks are still carried out for these + * and other operations. + */ + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2520,27 +2950,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2548,7 +2984,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2558,20 +2995,21 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; + prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; - prog->aux->offload_requested = !!attr->prog_ifindex; - prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; + prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; - err = security_bpf_prog_alloc(prog->aux); - if (err) - goto free_prog; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; @@ -2580,33 +3018,74 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) - goto free_prog_sec; + goto free_prog; + /* copy eBPF program license from user space */ + if (strncpy_from_bpfptr(license, + make_bpfptr(attr->license, uattr.is_kernel), + sizeof(license) - 1) < 0) + goto free_prog; + license[sizeof(license) - 1] = 0; + + /* eBPF programs must be GPL compatible to use GPL-ed functions */ + prog->gpl_compatible = license_is_gpl_compatible(license) ? 1 : 0; + + if (attr->signature) { + err = bpf_prog_verify_signature(prog, attr, uattr.is_kernel); + if (err) + goto free_prog; + } prog->orig_prog = NULL; prog->jited = 0; atomic64_set(&prog->aux->refcnt, 1); - prog->gpl_compatible = is_gpl ? 1 : 0; if (bpf_prog_is_dev_bound(prog->aux)) { - err = bpf_prog_offload_init(prog, attr); + err = bpf_prog_dev_bound_init(prog, attr); + if (err) + goto free_prog; + } + + if (type == BPF_PROG_TYPE_EXT && dst_prog && + bpf_prog_is_dev_bound(dst_prog->aux)) { + err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) - goto free_prog_sec; + goto free_prog; + } + + /* + * Bookkeeping for managing the program attachment chain. + * + * It might be tempting to set attach_tracing_prog flag at the attachment + * time, but this will not prevent from loading bunch of tracing prog + * first, then attach them one to another. + * + * The flag attach_tracing_prog is set for the whole program lifecycle, and + * doesn't have to be cleared in bpf_tracing_link_release, since tracing + * programs cannot change attachment target. + */ + if (type == BPF_PROG_TYPE_TRACING && dst_prog && + dst_prog->type == BPF_PROG_TYPE_TRACING) { + prog->aux->attach_tracing_prog = true; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog_sec; + goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) + goto free_prog; + + err = security_bpf_prog_load(prog, attr, token, uattr.is_kernel); + if (err) goto free_prog_sec; /* run eBPF verifier */ - err = bpf_check(&prog, attr, uattr); + err = bpf_check(&prog, attr, uattr, uattr_size); if (err < 0) goto free_used_maps; @@ -2614,6 +3093,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) if (err < 0) goto free_used_maps; + err = bpf_prog_mark_insn_arrays_ready(prog); + if (err < 0) + goto free_used_maps; + err = bpf_prog_alloc_id(prog); if (err) goto free_used_maps; @@ -2646,46 +3129,83 @@ free_used_maps: * period before we can tear down JIT memory since symbols * are already exposed under kallsyms. */ - __bpf_prog_put_noref(prog, prog->aux->func_cnt); + __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; + free_prog_sec: - free_uid(prog->aux->user); - security_bpf_prog_free(prog->aux); + security_bpf_prog_free(prog); free_prog: + free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } -#define BPF_OBJ_LAST_FIELD file_flags +#define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) + int path_fd; + + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags & ~BPF_F_PATH_FD) return -EINVAL; - return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); + /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ + if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) + return -EINVAL; + + path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; + return bpf_obj_pin_user(attr->bpf_fd, path_fd, + u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { + int path_fd; + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || - attr->file_flags & ~BPF_OBJ_FLAG_MASK) + attr->file_flags & ~(BPF_OBJ_FLAG_MASK | BPF_F_PATH_FD)) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ + if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) + return -EINVAL; + + path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; + return bpf_obj_get_user(path_fd, u64_to_user_ptr(attr->pathname), attr->file_flags); } -void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, - const struct bpf_link_ops *ops, struct bpf_prog *prog) +/* bpf_link_init_sleepable() allows to specify whether BPF link itself has + * "sleepable" semantics, which normally would mean that BPF link's attach + * hook can dereference link or link's underlying program for some time after + * detachment due to RCU Tasks Trace-based lifetime protection scheme. + * BPF program itself can be non-sleepable, yet, because it's transitively + * reachable through BPF link, its freeing has to be delayed until after RCU + * Tasks Trace GP. + */ +void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, struct bpf_prog *prog, + enum bpf_attach_type attach_type, bool sleepable) { + WARN_ON(ops->dealloc && ops->dealloc_deferred); atomic64_set(&link->refcnt, 1); link->type = type; + link->sleepable = sleepable; link->id = 0; link->ops = ops; link->prog = prog; + link->attach_type = attach_type; +} + +void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, struct bpf_prog *prog, + enum bpf_attach_type attach_type) +{ + bpf_link_init_sleepable(link, type, ops, prog, attach_type, false); } static void bpf_link_free_id(int id) @@ -2700,10 +3220,12 @@ static void bpf_link_free_id(int id) /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred - * anon_inode's release() call. This helper marksbpf_link as + * anon_inode's release() call. This helper marks bpf_link as * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt * is not decremented, it's the responsibility of a calling code that failed * to complete bpf_link initialization. + * This helper eventually calls link's dealloc callback, but does not call + * link's release callback. */ void bpf_link_cleanup(struct bpf_link_primer *primer) { @@ -2718,17 +3240,59 @@ void bpf_link_inc(struct bpf_link *link) atomic64_inc(&link->refcnt); } +static void bpf_link_dealloc(struct bpf_link *link) +{ + /* now that we know that bpf_link itself can't be reached, put underlying BPF program */ + if (link->prog) + bpf_prog_put(link->prog); + + /* free bpf_link and its containing memory */ + if (link->ops->dealloc_deferred) + link->ops->dealloc_deferred(link); + else + link->ops->dealloc(link); +} + +static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) +{ + struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); + + bpf_link_dealloc(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) { + const struct bpf_link_ops *ops = link->ops; + bpf_link_free_id(link->id); - if (link->prog) { - /* detach BPF program, clean up used resources */ - link->ops->release(link); - bpf_prog_put(link->prog); + /* detach BPF program, clean up used resources */ + if (link->prog) + ops->release(link); + if (ops->dealloc_deferred) { + /* Schedule BPF link deallocation, which will only then + * trigger putting BPF program refcount. + * If underlying BPF program is sleepable or BPF link's target + * attach hookpoint is sleepable or otherwise requires RCU GPs + * to ensure link and its underlying BPF program is not + * reachable anymore, we need to first wait for RCU tasks + * trace sync, and then go through "classic" RCU grace period + */ + if (link->sleepable || (link->prog && link->prog->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); + } else if (ops->dealloc) { + bpf_link_dealloc(link); } - /* free bpf_link and its containing memory */ - link->ops->dealloc(link); } static void bpf_link_put_deferred(struct work_struct *work) @@ -2738,28 +3302,31 @@ static void bpf_link_put_deferred(struct work_struct *work) bpf_link_free(link); } -/* bpf_link_put can be called from atomic context, but ensures that resources - * are freed from process context +/* bpf_link_put might be called from atomic context. It needs to be called + * from sleepable context in order to acquire sleeping locks during the process. */ void bpf_link_put(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; - if (in_atomic()) { - INIT_WORK(&link->work, bpf_link_put_deferred); - schedule_work(&link->work); - } else { - bpf_link_free(link); - } + INIT_WORK(&link->work, bpf_link_put_deferred); + schedule_work(&link->work); } EXPORT_SYMBOL(bpf_link_put); +static void bpf_link_put_direct(struct bpf_link *link) +{ + if (!atomic64_dec_and_test(&link->refcnt)) + return; + bpf_link_free(link); +} + static int bpf_link_release(struct inode *inode, struct file *filp) { struct bpf_link *link = filp->private_data; - bpf_link_put(link); + bpf_link_put_direct(link); return 0; } @@ -2779,23 +3346,44 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; + enum bpf_link_type type = link->type; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); - seq_printf(m, - "link_type:\t%s\n" - "link_id:\t%u\n" - "prog_tag:\t%s\n" - "prog_id:\t%u\n", - bpf_link_type_strs[link->type], - link->id, - prog_tag, - prog->aux->id); + if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) { + if (link->type == BPF_LINK_TYPE_KPROBE_MULTI) + seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_KPROBE_MULTI_RETURN ? + "kretprobe_multi" : "kprobe_multi"); + else if (link->type == BPF_LINK_TYPE_UPROBE_MULTI) + seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_UPROBE_MULTI_RETURN ? + "uretprobe_multi" : "uprobe_multi"); + else + seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]); + } else { + WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type); + seq_printf(m, "link_type:\t<%u>\n", type); + } + seq_printf(m, "link_id:\t%u\n", link->id); + + if (prog) { + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); + seq_printf(m, + "prog_tag:\t%s\n" + "prog_id:\t%u\n", + prog_tag, + prog->aux->id); + } if (link->ops->show_fdinfo) link->ops->show_fdinfo(link, m); } #endif +static __poll_t bpf_link_poll(struct file *file, struct poll_table_struct *pts) +{ + struct bpf_link *link = file->private_data; + + return link->ops->poll(file, pts); +} + static const struct file_operations bpf_link_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, @@ -2805,6 +3393,16 @@ static const struct file_operations bpf_link_fops = { .write = bpf_dummy_write, }; +static const struct file_operations bpf_link_fops_poll = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = bpf_link_show_fdinfo, +#endif + .release = bpf_link_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, + .poll = bpf_link_poll, +}; + static int bpf_link_alloc_id(struct bpf_link *link) { int id; @@ -2847,7 +3445,9 @@ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) return id; } - file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC); + file = anon_inode_getfile("bpf_link", + link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, + link, O_CLOEXEC); if (IS_ERR(file)) { bpf_link_free_id(id); put_unused_fd(fd); @@ -2875,28 +3475,26 @@ int bpf_link_settle(struct bpf_link_primer *primer) int bpf_link_new_fd(struct bpf_link *link) { - return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); + return anon_inode_getfd("bpf-link", + link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, + link, O_CLOEXEC); } struct bpf_link *bpf_link_get_from_fd(u32 ufd) { - struct fd f = fdget(ufd); + CLASS(fd, f)(ufd); struct bpf_link *link; - if (!f.file) + if (fd_empty(f)) return ERR_PTR(-EBADF); - if (f.file->f_op != &bpf_link_fops) { - fdput(f); + if (fd_file(f)->f_op != &bpf_link_fops && fd_file(f)->f_op != &bpf_link_fops_poll) return ERR_PTR(-EINVAL); - } - link = f.file->private_data; + link = fd_file(f)->private_data; bpf_link_inc(link); - fdput(f); - return link; } -EXPORT_SYMBOL(bpf_link_get_from_fd); +EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL"); static void bpf_tracing_link_release(struct bpf_link *link) { @@ -2904,7 +3502,8 @@ static void bpf_tracing_link_release(struct bpf_link *link) container_of(link, struct bpf_tracing_link, link.link); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, - tr_link->trampoline)); + tr_link->trampoline, + tr_link->tgt_prog)); bpf_trampoline_put(tr_link->trampoline); @@ -2926,10 +3525,19 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); + u32 target_btf_id, target_obj_id; + bpf_trampoline_unpack_key(tr_link->trampoline->key, + &target_obj_id, &target_btf_id); seq_printf(seq, - "attach_type:\t%d\n", - tr_link->attach_type); + "attach_type:\t%d\n" + "target_obj_id:\t%u\n" + "target_btf_id:\t%u\n" + "cookie:\t%llu\n", + link->attach_type, + target_obj_id, + target_btf_id, + tr_link->link.cookie); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, @@ -2938,7 +3546,8 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); - info->tracing.attach_type = tr_link->attach_type; + info->tracing.attach_type = link->attach_type; + info->tracing.cookie = tr_link->link.cookie; bpf_trampoline_unpack_key(tr_link->trampoline->key, &info->tracing.target_obj_id, &info->tracing.target_btf_id); @@ -2956,7 +3565,8 @@ static const struct bpf_link_ops bpf_tracing_link_lops = { static int bpf_tracing_prog_attach(struct bpf_prog *prog, int tgt_prog_fd, u32 btf_id, - u64 bpf_cookie) + u64 bpf_cookie, + enum bpf_attach_type attach_type) { struct bpf_link_primer link_primer; struct bpf_prog *tgt_prog = NULL; @@ -2997,7 +3607,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, } if (tgt_prog_fd) { - /* For now we only allow new targets for BPF_PROG_TYPE_EXT */ + /* + * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this + * part would be changed to implement the same for + * BPF_PROG_TYPE_TRACING, do not forget to update the way how + * attach_tracing_prog flag is set. + */ if (prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; @@ -3019,8 +3634,8 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, goto out_put_prog; } bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, - &bpf_tracing_link_lops, prog); - link->attach_type = prog->expected_attach_type; + &bpf_tracing_link_lops, prog, attach_type); + link->link.cookie = bpf_cookie; mutex_lock(&prog->aux->dst_mutex); @@ -3032,7 +3647,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, * in prog->aux * * - if prog->aux->dst_trampoline is NULL, the program has already been - * attached to a target and its initial target was cleared (below) + * attached to a target and its initial target was cleared (below) * * - if tgt_prog != NULL, the caller specified tgt_prog_fd + * target_btf_id using the link_create API. @@ -3042,6 +3657,10 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, * * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program * was detached and is going for re-attachment. + * + * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf + * are NULL, then program was already attached and user did not provide + * tgt_prog_fd so we have no way to find out or create trampoline */ if (!prog->aux->dst_trampoline && !tgt_prog) { /* @@ -3055,6 +3674,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, err = -EINVAL; goto out_unlock; } + /* We can allow re-attach only if we have valid attach_btf. */ + if (!prog->aux->attach_btf) { + err = -EINVAL; + goto out_unlock; + } btf_id = prog->aux->attach_btf_id; key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); } @@ -3072,6 +3696,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, if (err) goto out_unlock; + if (tgt_info.tgt_mod) { + module_put(prog->aux->mod); + prog->aux->mod = tgt_info.tgt_mod; + } + tr = bpf_trampoline_get(key, &tgt_info); if (!tr) { err = -ENOMEM; @@ -3093,7 +3722,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, if (err) goto out_unlock; - err = bpf_trampoline_link_prog(&link->link, tr); + err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog); if (err) { bpf_link_cleanup(&link_primer); link = NULL; @@ -3131,17 +3760,12 @@ 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); } @@ -3160,8 +3784,29 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, container_of(link, struct bpf_raw_tp_link, link); seq_printf(seq, - "tp_name:\t%s\n", - raw_tp_link->btp->tp->name); + "tp_name:\t%s\n" + "cookie:\t%llu\n", + raw_tp_link->btp->tp->name, + raw_tp_link->cookie); +} + +static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen, + u32 len) +{ + if (ulen >= len + 1) { + if (copy_to_user(ubuf, buf, len + 1)) + return -EFAULT; + } else { + char zero = '\0'; + + if (copy_to_user(ubuf, buf, ulen - 1)) + return -EFAULT; + if (put_user(zero, ubuf + ulen - 1)) + return -EFAULT; + return -ENOSPC; + } + + return 0; } static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, @@ -3178,29 +3823,17 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; + info->raw_tracepoint.cookie = raw_tp_link->cookie; if (!ubuf) return 0; - if (ulen >= tp_len + 1) { - if (copy_to_user(ubuf, tp_name, tp_len + 1)) - return -EFAULT; - } else { - char zero = '\0'; - - if (copy_to_user(ubuf, tp_name, ulen - 1)) - return -EFAULT; - if (put_user(zero, ubuf + ulen - 1)) - return -EFAULT; - return -ENOSPC; - } - - return 0; + return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len); } 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, }; @@ -3227,9 +3860,296 @@ static void bpf_perf_link_dealloc(struct bpf_link *link) kfree(perf_link); } +static int bpf_perf_link_fill_common(const struct perf_event *event, + char __user *uname, u32 *ulenp, + u64 *probe_offset, u64 *probe_addr, + u32 *fd_type, unsigned long *missed) +{ + const char *buf; + u32 prog_id, ulen; + size_t len; + int err; + + ulen = *ulenp; + if (!ulen ^ !uname) + return -EINVAL; + + err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, + probe_offset, probe_addr, missed); + if (err) + return err; + + if (buf) { + len = strlen(buf); + *ulenp = len + 1; + } else { + *ulenp = 1; + } + if (!uname) + return 0; + + if (buf) { + err = bpf_copy_to_user(uname, buf, ulen, len); + if (err) + return err; + } else { + char zero = '\0'; + + if (put_user(zero, uname)) + return -EFAULT; + } + return 0; +} + +#ifdef CONFIG_KPROBE_EVENTS +static int bpf_perf_link_fill_kprobe(const struct perf_event *event, + struct bpf_link_info *info) +{ + unsigned long missed; + char __user *uname; + u64 addr, offset; + u32 ulen, type; + int err; + + uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); + ulen = info->perf_event.kprobe.name_len; + err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, + &type, &missed); + if (err) + return err; + if (type == BPF_FD_TYPE_KRETPROBE) + info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; + else + info->perf_event.type = BPF_PERF_EVENT_KPROBE; + info->perf_event.kprobe.name_len = ulen; + info->perf_event.kprobe.offset = offset; + info->perf_event.kprobe.missed = missed; + if (!kallsyms_show_value(current_cred())) + addr = 0; + info->perf_event.kprobe.addr = addr; + info->perf_event.kprobe.cookie = event->bpf_cookie; + return 0; +} + +static void bpf_perf_link_fdinfo_kprobe(const struct perf_event *event, + struct seq_file *seq) +{ + const char *name; + int err; + u32 prog_id, type; + u64 offset, addr; + unsigned long missed; + + err = bpf_get_perf_event_info(event, &prog_id, &type, &name, + &offset, &addr, &missed); + if (err) + return; + + seq_printf(seq, + "name:\t%s\n" + "offset:\t%#llx\n" + "missed:\t%lu\n" + "addr:\t%#llx\n" + "event_type:\t%s\n" + "cookie:\t%llu\n", + name, offset, missed, addr, + type == BPF_FD_TYPE_KRETPROBE ? "kretprobe" : "kprobe", + event->bpf_cookie); +} +#endif + +#ifdef CONFIG_UPROBE_EVENTS +static int bpf_perf_link_fill_uprobe(const struct perf_event *event, + struct bpf_link_info *info) +{ + u64 ref_ctr_offset, offset; + char __user *uname; + u32 ulen, type; + int err; + + uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); + ulen = info->perf_event.uprobe.name_len; + err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &ref_ctr_offset, + &type, NULL); + if (err) + return err; + + if (type == BPF_FD_TYPE_URETPROBE) + info->perf_event.type = BPF_PERF_EVENT_URETPROBE; + else + info->perf_event.type = BPF_PERF_EVENT_UPROBE; + info->perf_event.uprobe.name_len = ulen; + info->perf_event.uprobe.offset = offset; + info->perf_event.uprobe.cookie = event->bpf_cookie; + info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset; + return 0; +} + +static void bpf_perf_link_fdinfo_uprobe(const struct perf_event *event, + struct seq_file *seq) +{ + const char *name; + int err; + u32 prog_id, type; + u64 offset, ref_ctr_offset; + unsigned long missed; + + err = bpf_get_perf_event_info(event, &prog_id, &type, &name, + &offset, &ref_ctr_offset, &missed); + if (err) + return; + + seq_printf(seq, + "name:\t%s\n" + "offset:\t%#llx\n" + "ref_ctr_offset:\t%#llx\n" + "event_type:\t%s\n" + "cookie:\t%llu\n", + name, offset, ref_ctr_offset, + type == BPF_FD_TYPE_URETPROBE ? "uretprobe" : "uprobe", + event->bpf_cookie); +} +#endif + +static int bpf_perf_link_fill_probe(const struct perf_event *event, + struct bpf_link_info *info) +{ +#ifdef CONFIG_KPROBE_EVENTS + if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) + return bpf_perf_link_fill_kprobe(event, info); +#endif +#ifdef CONFIG_UPROBE_EVENTS + if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) + return bpf_perf_link_fill_uprobe(event, info); +#endif + return -EOPNOTSUPP; +} + +static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, + struct bpf_link_info *info) +{ + char __user *uname; + u32 ulen; + int err; + + uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); + ulen = info->perf_event.tracepoint.name_len; + err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL); + if (err) + return err; + + info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; + info->perf_event.tracepoint.name_len = ulen; + info->perf_event.tracepoint.cookie = event->bpf_cookie; + return 0; +} + +static int bpf_perf_link_fill_perf_event(const struct perf_event *event, + struct bpf_link_info *info) +{ + info->perf_event.event.type = event->attr.type; + info->perf_event.event.config = event->attr.config; + info->perf_event.event.cookie = event->bpf_cookie; + info->perf_event.type = BPF_PERF_EVENT_EVENT; + return 0; +} + +static int bpf_perf_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_perf_link *perf_link; + const struct perf_event *event; + + perf_link = container_of(link, struct bpf_perf_link, link); + event = perf_get_event(perf_link->perf_file); + if (IS_ERR(event)) + return PTR_ERR(event); + + switch (event->prog->type) { + case BPF_PROG_TYPE_PERF_EVENT: + return bpf_perf_link_fill_perf_event(event, info); + case BPF_PROG_TYPE_TRACEPOINT: + return bpf_perf_link_fill_tracepoint(event, info); + case BPF_PROG_TYPE_KPROBE: + return bpf_perf_link_fill_probe(event, info); + default: + return -EOPNOTSUPP; + } +} + +static void bpf_perf_event_link_show_fdinfo(const struct perf_event *event, + struct seq_file *seq) +{ + seq_printf(seq, + "type:\t%u\n" + "config:\t%llu\n" + "event_type:\t%s\n" + "cookie:\t%llu\n", + event->attr.type, event->attr.config, + "event", event->bpf_cookie); +} + +static void bpf_tracepoint_link_show_fdinfo(const struct perf_event *event, + struct seq_file *seq) +{ + int err; + const char *name; + u32 prog_id; + + err = bpf_get_perf_event_info(event, &prog_id, NULL, &name, NULL, + NULL, NULL); + if (err) + return; + + seq_printf(seq, + "tp_name:\t%s\n" + "event_type:\t%s\n" + "cookie:\t%llu\n", + name, "tracepoint", event->bpf_cookie); +} + +static void bpf_probe_link_show_fdinfo(const struct perf_event *event, + struct seq_file *seq) +{ +#ifdef CONFIG_KPROBE_EVENTS + if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) + return bpf_perf_link_fdinfo_kprobe(event, seq); +#endif + +#ifdef CONFIG_UPROBE_EVENTS + if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) + return bpf_perf_link_fdinfo_uprobe(event, seq); +#endif +} + +static void bpf_perf_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_perf_link *perf_link; + const struct perf_event *event; + + perf_link = container_of(link, struct bpf_perf_link, link); + event = perf_get_event(perf_link->perf_file); + if (IS_ERR(event)) + return; + + switch (event->prog->type) { + case BPF_PROG_TYPE_PERF_EVENT: + return bpf_perf_event_link_show_fdinfo(event, seq); + case BPF_PROG_TYPE_TRACEPOINT: + return bpf_tracepoint_link_show_fdinfo(event, seq); + case BPF_PROG_TYPE_KPROBE: + return bpf_probe_link_show_fdinfo(event, seq); + default: + return; + } +} + static const struct bpf_link_ops bpf_perf_link_lops = { .release = bpf_perf_link_release, .dealloc = bpf_perf_link_dealloc, + .fill_link_info = bpf_perf_link_fill_link_info, + .show_fdinfo = bpf_perf_link_show_fdinfo, }; static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) @@ -3252,7 +4172,8 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro err = -ENOMEM; goto out_put_file; } - bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog); + bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog, + attr->link_create.attach_type); link->perf_file = perf_file; err = bpf_link_prime(&link->link, &link_primer); @@ -3284,7 +4205,8 @@ 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, + enum bpf_attach_type attach_type) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; @@ -3307,7 +4229,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, tp_name = prog->aux->attach_func_name; break; } - return bpf_tracing_prog_attach(prog, 0, 0, 0); + return bpf_tracing_prog_attach(prog, 0, 0, 0, attach_type); case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) @@ -3328,9 +4250,11 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, err = -ENOMEM; goto out_put_btp; } - bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, - &bpf_raw_tp_link_lops, prog); + bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, + &bpf_raw_tp_link_lops, prog, attach_type, + tracepoint_is_faultable(btp->tp)); link->btp = btp; + link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -3338,7 +4262,7 @@ 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; @@ -3351,11 +4275,13 @@ 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)) @@ -3365,35 +4291,14 @@ 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, prog->expected_attach_type); if (fd < 0) bpf_prog_put(prog); return fd; } -static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, - enum bpf_attach_type attach_type) -{ - switch (prog->type) { - case BPF_PROG_TYPE_CGROUP_SOCK: - case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: - case BPF_PROG_TYPE_SK_LOOKUP: - return attach_type == prog->expected_attach_type ? 0 : -EINVAL; - case BPF_PROG_TYPE_CGROUP_SKB: - if (!capable(CAP_NET_ADMIN)) - /* cg-skb progs can be loaded by unpriv user. - * check permissions at attach time. - */ - return -EPERM; - return prog->enforce_expected_attach_type && - prog->expected_attach_type != attach_type ? - -EINVAL : 0; - default: - return 0; - } -} - static enum bpf_prog_type attach_type_to_prog_type(enum bpf_attach_type attach_type) { @@ -3410,14 +4315,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; @@ -3452,15 +4362,120 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) return BPF_PROG_TYPE_XDP; case BPF_LSM_CGROUP: return BPF_PROG_TYPE_LSM; + case BPF_TCX_INGRESS: + case BPF_TCX_EGRESS: + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; } } -#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd +static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, + enum bpf_attach_type attach_type) +{ + enum bpf_prog_type ptype; + + switch (prog->type) { + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_SK_LOOKUP: + return attach_type == prog->expected_attach_type ? 0 : -EINVAL; + case BPF_PROG_TYPE_CGROUP_SKB: + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) + /* cg-skb progs can be loaded by unpriv user. + * 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; + case BPF_PROG_TYPE_EXT: + return 0; + case BPF_PROG_TYPE_NETFILTER: + if (attach_type != BPF_NETFILTER) + return -EINVAL; + return 0; + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_TRACEPOINT: + if (attach_type != BPF_PERF_EVENT) + return -EINVAL; + return 0; + case BPF_PROG_TYPE_KPROBE: + 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 (prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION && + attach_type != BPF_TRACE_UPROBE_SESSION) + 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 && + attach_type != BPF_TRACE_UPROBE_SESSION) + return -EINVAL; + return 0; + case BPF_PROG_TYPE_SCHED_CLS: + if (attach_type != BPF_TCX_INGRESS && + attach_type != BPF_TCX_EGRESS && + attach_type != BPF_NETKIT_PRIMARY && + attach_type != BPF_NETKIT_PEER) + return -EINVAL; + return 0; + default: + ptype = attach_type_to_prog_type(attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) + return -EINVAL; + return 0; + } +} + +static bool is_cgroup_prog_type(enum bpf_prog_type ptype, enum bpf_attach_type atype, + bool check_atype) +{ + switch (ptype) { + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_SOCK_OPS: + return true; + case BPF_PROG_TYPE_LSM: + return check_atype ? atype == BPF_LSM_CGROUP : true; + default: + return false; + } +} + +#define BPF_PROG_ATTACH_LAST_FIELD expected_revision + +#define BPF_F_ATTACH_MASK_BASE \ + (BPF_F_ALLOW_OVERRIDE | \ + BPF_F_ALLOW_MULTI | \ + BPF_F_REPLACE | \ + BPF_F_PREORDER) -#define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) +#define BPF_F_ATTACH_MASK_MPROG \ + (BPF_F_REPLACE | \ + BPF_F_BEFORE | \ + BPF_F_AFTER | \ + BPF_F_ID | \ + BPF_F_LINK) static int bpf_prog_attach(const union bpf_attr *attr) { @@ -3471,12 +4486,22 @@ static int bpf_prog_attach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; - if (attr->attach_flags & ~BPF_F_ATTACH_MASK) - return -EINVAL; - ptype = attach_type_to_prog_type(attr->attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; + if (bpf_mprog_supported(ptype)) { + if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) + return -EINVAL; + } else if (is_cgroup_prog_type(ptype, 0, false)) { + if (attr->attach_flags & ~(BPF_F_ATTACH_MASK_BASE | BPF_F_ATTACH_MASK_MPROG)) + return -EINVAL; + } else { + if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE) + return -EINVAL; + if (attr->relative_fd || + attr->expected_revision) + return -EINVAL; + } prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) @@ -3487,6 +4512,11 @@ static int bpf_prog_attach(const union bpf_attr *attr) return -EINVAL; } + if (is_cgroup_prog_type(ptype, prog->expected_attach_type, true)) { + ret = cgroup_bpf_prog_attach(attr, ptype, prog); + goto out; + } + switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: @@ -3498,48 +4528,64 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_attach(attr, prog); break; - case BPF_PROG_TYPE_CGROUP_DEVICE: - case BPF_PROG_TYPE_CGROUP_SKB: - case BPF_PROG_TYPE_CGROUP_SOCK: - case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: - case BPF_PROG_TYPE_CGROUP_SYSCTL: - case BPF_PROG_TYPE_SOCK_OPS: - case BPF_PROG_TYPE_LSM: - if (ptype == BPF_PROG_TYPE_LSM && - prog->expected_attach_type != BPF_LSM_CGROUP) - ret = -EINVAL; + case BPF_PROG_TYPE_SCHED_CLS: + if (attr->attach_type == BPF_TCX_INGRESS || + attr->attach_type == BPF_TCX_EGRESS) + ret = tcx_prog_attach(attr, prog); else - ret = cgroup_bpf_prog_attach(attr, ptype, prog); + ret = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; } - +out: if (ret) bpf_prog_put(prog); return ret; } -#define BPF_PROG_DETACH_LAST_FIELD attach_type +#define BPF_PROG_DETACH_LAST_FIELD expected_revision static int bpf_prog_detach(const union bpf_attr *attr) { + struct bpf_prog *prog = NULL; enum bpf_prog_type ptype; + int ret; if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); + if (bpf_mprog_supported(ptype)) { + if (ptype == BPF_PROG_TYPE_UNSPEC) + return -EINVAL; + if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) + return -EINVAL; + if (attr->attach_bpf_fd) { + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + } else if (is_cgroup_prog_type(ptype, 0, false)) { + if (attr->attach_flags || attr->relative_fd) + return -EINVAL; + } else if (attr->attach_flags || + attr->relative_fd || + attr->expected_revision) { + return -EINVAL; + } switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: - return sock_map_prog_detach(attr, ptype); + ret = sock_map_prog_detach(attr, ptype); + break; case BPF_PROG_TYPE_LIRC_MODE2: - return lirc_prog_detach(attr); + ret = lirc_prog_detach(attr); + break; case BPF_PROG_TYPE_FLOW_DISSECTOR: - return netns_bpf_prog_detach(attr, ptype); + ret = netns_bpf_prog_detach(attr, ptype); + break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: @@ -3548,18 +4594,30 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: - return cgroup_bpf_prog_detach(attr, ptype); + ret = cgroup_bpf_prog_detach(attr, ptype); + break; + case BPF_PROG_TYPE_SCHED_CLS: + if (attr->attach_type == BPF_TCX_INGRESS || + attr->attach_type == BPF_TCX_EGRESS) + ret = tcx_prog_detach(attr, prog); + else + ret = netkit_prog_detach(attr, prog); + break; default: - return -EINVAL; + ret = -EINVAL; } + + if (prog) + bpf_prog_put(prog); + return ret; } -#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags +#define BPF_PROG_QUERY_LAST_FIELD query.revision static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - if (!capable(CAP_NET_ADMIN)) + if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; @@ -3577,14 +4635,19 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: @@ -3602,6 +4665,12 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_SK_MSG_VERDICT: case BPF_SK_SKB_VERDICT: return sock_map_bpf_prog_query(attr, uattr); + case BPF_TCX_INGRESS: + case BPF_TCX_EGRESS: + return tcx_prog_query(attr, uattr); + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + return netkit_prog_query(attr, uattr); default: return -EINVAL; } @@ -3847,6 +4916,12 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, continue; } + if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX || + BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) { + insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM; + continue; + } + if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; @@ -3954,6 +5029,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.recursion_misses = stats.misses; info.verified_insns = prog->aux->verified_insns; + if (prog->aux->btf) + info.btf_id = btf_obj_id(prog->aux->btf); if (!bpf_capable()) { info.jited_prog_len = 0; @@ -3972,22 +5049,22 @@ static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_insn *insns_sanitized; bool fault; - if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) { + if (!prog->blinded || bpf_dump_raw_ok(file->f_cred)) { + insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); + if (!insns_sanitized) + return -ENOMEM; + uinsns = u64_to_user_ptr(info.xlated_prog_insns); + ulen = min_t(u32, info.xlated_prog_len, ulen); + fault = copy_to_user(uinsns, insns_sanitized, ulen); + kfree(insns_sanitized); + if (fault) + return -EFAULT; + } else { info.xlated_prog_insns = 0; - goto done; } - insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); - if (!insns_sanitized) - return -ENOMEM; - uinsns = u64_to_user_ptr(info.xlated_prog_insns); - ulen = min_t(u32, info.xlated_prog_len, ulen); - fault = copy_to_user(uinsns, insns_sanitized, ulen); - kfree(insns_sanitized); - if (fault) - return -EFAULT; } - if (bpf_prog_is_dev_bound(prog->aux)) { + if (bpf_prog_is_offloaded(prog->aux)) { err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; @@ -4100,8 +5177,6 @@ static int bpf_prog_get_info_by_fd(struct file *file, } } - if (prog->aux->btf) - info.btf_id = btf_obj_id(prog->aux->btf); info.attach_btf_id = prog->aux->attach_btf_id; if (attach_btf) info.attach_btf_obj_id = btf_obj_id(attach_btf); @@ -4199,6 +5274,9 @@ static int bpf_map_get_info_by_fd(struct file *file, info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); + if (copy_from_user(&info, uinfo, info_len)) + return -EFAULT; + info.type = map->map_type; info.id = map->id; info.key_size = map->key_size; @@ -4214,13 +5292,34 @@ static int bpf_map_get_info_by_fd(struct file *file, info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) + bpf_map_struct_ops_info_fill(&info, map); - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) return err; } + if (info.hash) { + char __user *uhash = u64_to_user_ptr(info.hash); + + if (!map->ops->map_get_hash) + return -EINVAL; + + if (info.hash_size != SHA256_DIGEST_SIZE) + return -EINVAL; + + err = map->ops->map_get_hash(map, SHA256_DIGEST_SIZE, map->sha); + if (err != 0) + return err; + + if (copy_to_user(uhash, map->sha, SHA256_DIGEST_SIZE) != 0) + return -EFAULT; + } else if (info.hash_size) { + return -EINVAL; + } + if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; @@ -4265,7 +5364,8 @@ static int bpf_link_get_info_by_fd(struct file *file, info.type = link->type; info.id = link->id; - info.prog_id = link->prog->aux->id; + if (link->prog) + info.prog_id = link->prog->aux->id; if (link->ops->fill_link_info) { err = link->ops->fill_link_info(link, &info); @@ -4281,62 +5381,110 @@ static int bpf_link_get_info_by_fd(struct file *file, } +static int token_get_info_by_fd(struct file *file, + struct bpf_token *token, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info); + u32 info_len = attr->info.info_len; + int err; + + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); + if (err) + return err; + return bpf_token_get_info_by_fd(token, attr, uattr); +} + #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, union bpf_attr __user *uattr) { - int ufd = attr->info.bpf_fd; - struct fd f; - int err; - if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) return -EINVAL; - f = fdget(ufd); - if (!f.file) + CLASS(fd, f)(attr->info.bpf_fd); + if (fd_empty(f)) return -EBADFD; - if (f.file->f_op == &bpf_prog_fops) - err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr, + if (fd_file(f)->f_op == &bpf_prog_fops) + return bpf_prog_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); - else if (f.file->f_op == &bpf_map_fops) - err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr, + else if (fd_file(f)->f_op == &bpf_map_fops) + return bpf_map_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); - else if (f.file->f_op == &btf_fops) - err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr); - else if (f.file->f_op == &bpf_link_fops) - err = bpf_link_get_info_by_fd(f.file, f.file->private_data, + else if (fd_file(f)->f_op == &btf_fops) + return bpf_btf_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); + else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll) + return bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); - else - err = -EINVAL; - - fdput(f); - return err; + else if (fd_file(f)->f_op == &bpf_token_fops) + return token_get_info_by_fd(fd_file(f), fd_file(f)->private_data, + attr, uattr); + return -EINVAL; } -#define BPF_BTF_LOAD_LAST_FIELD btf_log_level +#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd -static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr) +static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (!bpf_capable()) + if (attr->btf_flags & ~BPF_F_TOKEN_FD) + return -EINVAL; + + if (attr->btf_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->btf_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_BPF)) { + bpf_token_put(token); return -EPERM; + } - return btf_new_fd(attr, uattr); + bpf_token_put(token); + + return btf_new_fd(attr, uattr, uattr_size); } -#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id +#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD fd_by_id_token_fd static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) + if (attr->open_flags & ~BPF_F_TOKEN_FD) + return -EINVAL; + + if (attr->open_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->fd_by_id_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_GET_FD_BY_ID)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_SYS_ADMIN)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_get_fd_by_id(attr->btf_id); } @@ -4361,21 +5509,10 @@ static int bpf_task_fd_query_copy(const union bpf_attr *attr, if (put_user(zero, ubuf)) return -EFAULT; - } else if (input_len >= len + 1) { - /* ubuf can hold the string with NULL terminator */ - if (copy_to_user(ubuf, buf, len + 1)) - return -EFAULT; } else { - /* ubuf cannot hold the string with NULL terminator, - * do a partial copy with NULL terminator. - */ - char zero = '\0'; - - err = -ENOSPC; - if (copy_to_user(ubuf, buf, input_len - 1)) - return -EFAULT; - if (put_user(zero, ubuf + input_len - 1)) - return -EFAULT; + err = bpf_copy_to_user(ubuf, buf, input_len, len); + if (err == -EFAULT) + return err; } } @@ -4421,7 +5558,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, if (!file) return -EBADF; - if (file->f_op == &bpf_link_fops) { + if (file->f_op == &bpf_link_fops || file->f_op == &bpf_link_fops_poll) { struct bpf_link *link = file->private_data; if (link->ops == &bpf_raw_tp_link_lops) { @@ -4446,7 +5583,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, - &probe_addr); + &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, @@ -4481,14 +5618,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; - int err, ufd; - struct fd f; + int err; if (CHECK_ATTR(BPF_MAP_BATCH)) return -EINVAL; - ufd = attr->batch.map_fd; - f = fdget(ufd); + CLASS(fd, f)(attr->batch.map_fd); + map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -4508,26 +5644,29 @@ static int bpf_map_do_batch(const union bpf_attr *attr, else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr); else if (cmd == BPF_MAP_UPDATE_BATCH) - BPF_DO_BATCH(map->ops->map_update_batch, map, f.file, attr, uattr); + BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr); else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: - if (has_write) + if (has_write) { + maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); - fdput(f); + } return err; } -#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies +#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid static int link_create(union bpf_attr *attr, bpfptr_t uattr) { - enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; + if (attr->link_create.attach_type == BPF_STRUCT_OPS) + return bpf_struct_ops_link_create(attr); + prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); @@ -4538,32 +5677,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) goto out; switch (prog->type) { - case BPF_PROG_TYPE_EXT: - break; - case BPF_PROG_TYPE_PERF_EVENT: - case BPF_PROG_TYPE_TRACEPOINT: - if (attr->link_create.attach_type != BPF_PERF_EVENT) { - ret = -EINVAL; - goto out; - } - break; - case BPF_PROG_TYPE_KPROBE: - if (attr->link_create.attach_type != BPF_PERF_EVENT && - attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) { - ret = -EINVAL; - goto out; - } - break; - default: - ptype = attach_type_to_prog_type(attr->link_create.attach_type); - if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) { - ret = -EINVAL; - goto out; - } - break; - } - - switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: @@ -4577,7 +5690,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, - attr->link_create.tracing.cookie); + attr->link_create.tracing.cookie, + attr->link_create.attach_type); break; case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_TRACING: @@ -4586,7 +5700,8 @@ 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, + attr->link_create.attach_type); 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) @@ -4595,16 +5710,31 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, - attr->link_create.tracing.cookie); + attr->link_create.tracing.cookie, + attr->link_create.attach_type); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: 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); break; + case BPF_PROG_TYPE_SCHED_CLS: + if (attr->link_create.attach_type == BPF_TCX_INGRESS || + attr->link_create.attach_type == BPF_TCX_EGRESS) + ret = tcx_link_attach(attr, prog); + else + ret = netkit_link_attach(attr, prog); + break; + case BPF_PROG_TYPE_NETFILTER: + ret = bpf_nf_link_attach(attr, prog); + break; #endif case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: @@ -4613,8 +5743,12 @@ 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 + 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 || + attr->link_create.attach_type == BPF_TRACE_UPROBE_SESSION) + ret = bpf_uprobe_multi_link_attach(attr, prog); break; default: ret = -EINVAL; @@ -4626,6 +5760,35 @@ out: return ret; } +static int link_update_map(struct bpf_link *link, union bpf_attr *attr) +{ + struct bpf_map *new_map, *old_map = NULL; + int ret; + + new_map = bpf_map_get(attr->link_update.new_map_fd); + if (IS_ERR(new_map)) + return PTR_ERR(new_map); + + if (attr->link_update.flags & BPF_F_REPLACE) { + old_map = bpf_map_get(attr->link_update.old_map_fd); + if (IS_ERR(old_map)) { + ret = PTR_ERR(old_map); + goto out_put; + } + } else if (attr->link_update.old_map_fd) { + ret = -EINVAL; + goto out_put; + } + + ret = link->ops->update_map(link, new_map, old_map); + + if (old_map) + bpf_map_put(old_map); +out_put: + bpf_map_put(new_map); + return ret; +} + #define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd static int link_update(union bpf_attr *attr) @@ -4646,6 +5809,11 @@ static int link_update(union bpf_attr *attr) if (IS_ERR(link)) return PTR_ERR(link); + if (link->ops->update_map) { + ret = link_update_map(link, attr); + goto out_put_link; + } + new_prog = bpf_prog_get(attr->link_update.new_prog_fd); if (IS_ERR(new_prog)) { ret = PTR_ERR(new_prog); @@ -4675,7 +5843,7 @@ out_put_progs: if (ret) bpf_prog_put(new_prog); out_put_link: - bpf_link_put(link); + bpf_link_put_direct(link); return ret; } @@ -4698,14 +5866,15 @@ static int link_detach(union bpf_attr *attr) else ret = -EOPNOTSUPP; - bpf_link_put(link); + bpf_link_put_direct(link); return ret; } -static struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) +struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); } +EXPORT_SYMBOL(bpf_link_inc_not_zero); struct bpf_link *bpf_link_by_id(u32 id) { @@ -4768,7 +5937,7 @@ static int bpf_link_get_fd_by_id(const union bpf_attr *attr) fd = bpf_link_new_fd(link); if (fd < 0) - bpf_link_put(link); + bpf_link_put_direct(link); return fd; } @@ -4845,7 +6014,7 @@ static int bpf_iter_create(union bpf_attr *attr) return PTR_ERR(link); err = bpf_iter_new_fd(link); - bpf_link_put(link); + bpf_link_put_direct(link); return err; } @@ -4893,6 +6062,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr) goto out_unlock; } + /* The bpf program will not access the bpf map, but for the sake of + * simplicity, increase sleepable_refcnt for sleepable program as well. + */ + if (prog->sleepable) + atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; @@ -4912,25 +6086,46 @@ out_prog_put: return ret; } -static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) { - union bpf_attr attr; - bool capable; - int err; + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; - capable = bpf_capable() || !sysctl_unprivileged_bpf_disabled; + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; - /* Intent here is for unprivileged_bpf_disabled to block key object - * creation commands for unprivileged users; other actions depend - * of fd availability and access to bpffs, so are dependent on - * object creation success. Capabilities are later verified for - * operations such as load and map create, so even with unprivileged - * BPF disabled, capability checks are still carried out for these - * and other operations. - */ - if (!capable && - (cmd == BPF_MAP_CREATE || cmd == BPF_PROG_LOAD)) - return -EPERM; + return bpf_token_create(attr); +} + +#define BPF_PROG_STREAM_READ_BY_FD_LAST_FIELD prog_stream_read.prog_fd + +static int prog_stream_read(union bpf_attr *attr) +{ + char __user *buf = u64_to_user_ptr(attr->prog_stream_read.stream_buf); + u32 len = attr->prog_stream_read.stream_buf_len; + struct bpf_prog *prog; + int ret; + + if (CHECK_ATTR(BPF_PROG_STREAM_READ_BY_FD)) + return -EINVAL; + + prog = bpf_prog_get(attr->prog_stream_read.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + ret = bpf_prog_stream_read(prog, attr->prog_stream_read.stream_id, buf, len); + bpf_prog_put(prog); + + return ret; +} + +static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) +{ + union bpf_attr attr; + int err; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) @@ -4942,13 +6137,13 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; - err = security_bpf(cmd, &attr, size); + err = security_bpf(cmd, &attr, size, uattr.is_kernel); if (err < 0) return err; switch (cmd) { case BPF_MAP_CREATE: - err = map_create(&attr); + err = map_create(&attr, uattr); break; case BPF_MAP_LOOKUP_ELEM: err = map_lookup_elem(&attr); @@ -4966,7 +6161,7 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) err = map_freeze(&attr); break; case BPF_PROG_LOAD: - err = bpf_prog_load(&attr, uattr); + err = bpf_prog_load(&attr, uattr, size); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); @@ -5011,7 +6206,7 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: - err = bpf_btf_load(&attr, uattr); + err = bpf_btf_load(&attr, uattr, size); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); @@ -5060,6 +6255,12 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; + case BPF_PROG_STREAM_READ_BY_FD: + err = prog_stream_read(&attr); + break; default: err = -EINVAL; break; @@ -5136,9 +6337,9 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) } run_ctx.bpf_cookie = 0; - run_ctx.saved_run_ctx = NULL; if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ + __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx); bpf_prog_put(prog); return -EBUSY; } @@ -5152,7 +6353,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) return ____bpf_sys_bpf(cmd, attr, size); } } -EXPORT_SYMBOL(kern_sys_bpf); +EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL"); static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, @@ -5166,7 +6367,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) @@ -5188,6 +6389,7 @@ static const struct bpf_func_proto bpf_sys_close_proto = { BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) { + *res = 0; if (flags) return -EINVAL; @@ -5208,7 +6410,8 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, + .arg4_size = sizeof(u64), }; static const struct bpf_func_proto * @@ -5216,7 +6419,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; + return !bpf_token_capable(prog->aux->token, CAP_PERFMON) + ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: @@ -5238,7 +6442,7 @@ const struct bpf_prog_ops bpf_syscall_prog_ops = { }; #ifdef CONFIG_SYSCTL -static int bpf_stats_handler(struct ctl_table *table, int write, +static int bpf_stats_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; @@ -5273,7 +6477,7 @@ void __weak unpriv_ebpf_notify(int new_state) { } -static int bpf_unpriv_handler(struct ctl_table *table, int write, +static int bpf_unpriv_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, unpriv_enable = *(int *)table->data; @@ -5291,12 +6495,13 @@ static int bpf_unpriv_handler(struct ctl_table *table, int write, *(int *)table->data = unpriv_enable; } - unpriv_ebpf_notify(unpriv_enable); + if (write) + unpriv_ebpf_notify(unpriv_enable); return ret; } -static struct ctl_table bpf_syscall_table[] = { +static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, @@ -5309,11 +6514,9 @@ static struct ctl_table bpf_syscall_table[] = { { .procname = "bpf_stats_enabled", .data = &bpf_stats_enabled_key.key, - .maxlen = sizeof(bpf_stats_enabled_key), .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..9cbe15ce3540 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -7,32 +7,56 @@ #include <linux/kobject.h> #include <linux/init.h> #include <linux/sysfs.h> +#include <linux/mm.h> +#include <linux/io.h> +#include <linux/btf.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, - struct bin_attribute *bin_attr, - char *buf, loff_t off, size_t len) +static int btf_sysfs_vmlinux_mmap(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + struct vm_area_struct *vma) { - memcpy(buf, __start_BTF + off, len); - return len; + unsigned long pages = PAGE_ALIGN(attr->size) >> PAGE_SHIFT; + size_t vm_size = vma->vm_end - vma->vm_start; + phys_addr_t addr = __pa_symbol(__start_BTF); + unsigned long pfn = addr >> PAGE_SHIFT; + + if (attr->private != __start_BTF || !PAGE_ALIGNED(addr)) + return -EINVAL; + + if (vma->vm_pgoff) + return -EINVAL; + + if (vma->vm_flags & (VM_WRITE | VM_EXEC | VM_MAYSHARE)) + return -EACCES; + + if (pfn + pages < pfn) + return -EINVAL; + + if ((vm_size >> PAGE_SHIFT) > pages) + return -EINVAL; + + vm_flags_mod(vma, VM_DONTDUMP, VM_MAYEXEC | VM_MAYWRITE); + return remap_pfn_range(vma, vma->vm_start, pfn, vm_size, vma->vm_page_prot); } static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = { .attr = { .name = "vmlinux", .mode = 0444, }, - .read = btf_vmlinux_read, + .read = sysfs_bin_attr_simple_read, + .mmap = btf_sysfs_vmlinux_mmap, }; struct kobject *btf_kobj; static int __init btf_vmlinux_init(void) { + bin_attr_btf_vmlinux.private = __start_BTF; 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/task_iter.c b/kernel/bpf/task_iter.c index c4ab9d6cdbe9..98d9b4c0daff 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -5,9 +5,10 @@ #include <linux/namei.h> #include <linux/pid_namespace.h> #include <linux/fs.h> -#include <linux/fdtable.h> #include <linux/filter.h> +#include <linux/bpf_mem_alloc.h> #include <linux/btf_ids.h> +#include <linux/mm_types.h> #include "mmap_unlock_work.h" static const char * const iter_task_type_names[] = { @@ -35,16 +36,13 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm u32 *tid, bool skip_if_dup_files) { - struct task_struct *task, *next_task; + struct task_struct *task; struct pid *pid; - u32 saved_tid; + u32 next_tid; if (!*tid) { /* The first time, the iterator calls this function. */ pid = find_pid_ns(common->pid, common->ns); - if (!pid) - return NULL; - task = get_pid_task(pid, PIDTYPE_TGID); if (!task) return NULL; @@ -66,44 +64,25 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm return task; } - pid = find_pid_ns(common->pid_visiting, common->ns); - if (!pid) - return NULL; - - task = get_pid_task(pid, PIDTYPE_PID); + task = find_task_by_pid_ns(common->pid_visiting, common->ns); if (!task) return NULL; retry: - if (!pid_alive(task)) { - put_task_struct(task); - return NULL; - } - - next_task = next_thread(task); - put_task_struct(task); - if (!next_task) + task = __next_thread(task); + if (!task) return NULL; - saved_tid = *tid; - *tid = __task_pid_nr_ns(next_task, PIDTYPE_PID, common->ns); - if (!*tid || *tid == common->pid) { - /* Run out of tasks of a process. The tasks of a - * thread_group are linked as circular linked list. - */ - *tid = saved_tid; - return NULL; - } - - get_task_struct(next_task); - common->pid_visiting = *tid; + next_tid = __task_pid_nr_ns(task, PIDTYPE_PID, common->ns); + if (!next_tid) + goto retry; - if (skip_if_dup_files && task->files == task->group_leader->files) { - task = next_task; + if (skip_if_dup_files && task->files == task->group_leader->files) goto retry; - } - return next_task; + *tid = common->pid_visiting = next_tid; + get_task_struct(task); + return task; } static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common, @@ -119,7 +98,7 @@ static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *co rcu_read_lock(); pid = find_pid_ns(common->pid, common->ns); if (pid) { - task = get_pid_task(pid, PIDTYPE_TGID); + task = get_pid_task(pid, PIDTYPE_PID); *tid = common->pid; } rcu_read_unlock(); @@ -281,6 +260,7 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info) u32 saved_tid = info->tid; struct task_struct *curr_task; unsigned int curr_fd = info->fd; + struct file *f; /* If this function returns a non-NULL file object, * it held a reference to the task/file. @@ -305,23 +285,14 @@ again: curr_fd = 0; } - rcu_read_lock(); - for (;; curr_fd++) { - struct file *f; - f = task_lookup_next_fd_rcu(curr_task, &curr_fd); - if (!f) - break; - if (!get_file_rcu(f)) - continue; - + f = fget_task_next(curr_task, &curr_fd); + if (f) { /* set info->fd */ info->fd = curr_fd; - rcu_read_unlock(); return f; } /* the current task is done, go to the next task */ - rcu_read_unlock(); put_task_struct(curr_task); if (info->common.type == BPF_TASK_ITER_TID) { @@ -724,7 +695,7 @@ static struct bpf_iter_reg task_reg_info = { .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__task, task), - PTR_TO_BTF_ID_OR_NULL }, + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .seq_info = &task_seq_info, .fill_link_info = bpf_iter_fill_link_info, @@ -823,6 +794,241 @@ const struct bpf_func_proto bpf_find_vma_proto = { .arg5_type = ARG_ANYTHING, }; +struct bpf_iter_task_vma_kern_data { + struct task_struct *task; + struct mm_struct *mm; + struct mmap_unlock_irq_work *work; + struct vma_iterator vmi; +}; + +struct bpf_iter_task_vma { + /* opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +/* Non-opaque version of bpf_iter_task_vma */ +struct bpf_iter_task_vma_kern { + struct bpf_iter_task_vma_kern_data *data; +} __attribute__((aligned(8))); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, + struct task_struct *task, u64 addr) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + bool irq_work_busy = false; + int err; + + BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma)); + + /* is_iter_reg_valid_uninit guarantees that kit hasn't been initialized + * before, so non-NULL kit->data doesn't point to previously + * bpf_mem_alloc'd bpf_iter_task_vma_kern_data + */ + kit->data = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_iter_task_vma_kern_data)); + if (!kit->data) + return -ENOMEM; + + kit->data->task = get_task_struct(task); + kit->data->mm = task->mm; + if (!kit->data->mm) { + err = -ENOENT; + goto err_cleanup_iter; + } + + /* kit->data->work == NULL is valid after bpf_mmap_unlock_get_irq_work */ + irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work); + if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) { + err = -EBUSY; + goto err_cleanup_iter; + } + + vma_iter_init(&kit->data->vmi, kit->data->mm, addr); + return 0; + +err_cleanup_iter: + if (kit->data->task) + put_task_struct(kit->data->task); + bpf_mem_free(&bpf_global_ma, kit->data); + /* NULL kit->data signals failed bpf_iter_task_vma initialization */ + kit->data = NULL; + return err; +} + +__bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + + if (!kit->data) /* bpf_iter_task_vma_new failed */ + return NULL; + return vma_next(&kit->data->vmi); +} + +__bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + + if (kit->data) { + bpf_mmap_unlock_mm(kit->data->work, kit->data->mm); + put_task_struct(kit->data->task); + bpf_mem_free(&bpf_global_ma, kit->data); + } +} + +__bpf_kfunc_end_defs(); + +#ifdef CONFIG_CGROUPS + +struct bpf_iter_css_task { + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_task_kern { + struct css_task_iter *css_it; +} __attribute__((aligned(8))); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) != + __alignof__(struct bpf_iter_css_task)); + kit->css_it = NULL; + switch (flags) { + case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED: + case CSS_TASK_ITER_PROCS: + case 0: + break; + default: + return -EINVAL; + } + + kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter)); + if (!kit->css_it) + return -ENOMEM; + css_task_iter_start(css, flags, kit->css_it); + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return NULL; + return css_task_iter_next(kit->css_it); +} + +__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return; + css_task_iter_end(kit->css_it); + bpf_mem_free(&bpf_global_ma, kit->css_it); +} + +__bpf_kfunc_end_defs(); + +#endif /* CONFIG_CGROUPS */ + +struct bpf_iter_task { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_task_kern { + struct task_struct *task; + struct task_struct *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +enum { + /* all process in the system */ + BPF_TASK_ITER_ALL_PROCS, + /* all threads in the system */ + BPF_TASK_ITER_ALL_THREADS, + /* all threads of a specific process */ + BPF_TASK_ITER_PROC_THREADS +}; + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task__nullable, unsigned int flags) +{ + struct bpf_iter_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != + __alignof__(struct bpf_iter_task)); + + kit->pos = NULL; + + switch (flags) { + case BPF_TASK_ITER_ALL_THREADS: + case BPF_TASK_ITER_ALL_PROCS: + break; + case BPF_TASK_ITER_PROC_THREADS: + if (!task__nullable) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (flags == BPF_TASK_ITER_PROC_THREADS) + kit->task = task__nullable; + else + kit->task = &init_task; + kit->pos = kit->task; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) +{ + struct bpf_iter_task_kern *kit = (void *)it; + struct task_struct *pos; + unsigned int flags; + + flags = kit->flags; + pos = kit->pos; + + if (!pos) + return pos; + + if (flags == BPF_TASK_ITER_ALL_PROCS) + goto get_next_task; + + kit->pos = __next_thread(kit->pos); + if (kit->pos || flags == BPF_TASK_ITER_PROC_THREADS) + return pos; + +get_next_task: + kit->task = next_task(kit->task); + if (kit->task == &init_task) + kit->pos = NULL; + else + kit->pos = kit->task; + + return pos; +} + +__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it) +{ +} + +__bpf_kfunc_end_defs(); + DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); static void do_mmap_read_unlock(struct irq_work *entry) diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c new file mode 100644 index 000000000000..efd987ea6872 --- /dev/null +++ b/kernel/bpf/tcx.c @@ -0,0 +1,346 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include <linux/bpf.h> +#include <linux/bpf_mprog.h> +#include <linux/netdevice.h> + +#include <net/tcx.h> + +int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + bool created, ingress = attr->attach_type == BPF_TCX_INGRESS; + struct net *net = current->nsproxy->net_ns; + struct bpf_mprog_entry *entry, *entry_new; + struct bpf_prog *replace_prog = NULL; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + if (attr->attach_flags & BPF_F_REPLACE) { + replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, + prog->type); + if (IS_ERR(replace_prog)) { + ret = PTR_ERR(replace_prog); + replace_prog = NULL; + goto out; + } + } + entry = tcx_entry_fetch_or_create(dev, ingress, &created); + if (!entry) { + ret = -ENOMEM; + goto out; + } + ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog, + attr->attach_flags, attr->relative_fd, + attr->expected_revision); + if (!ret) { + if (entry != entry_new) { + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_inc(ingress); + } + bpf_mprog_commit(entry); + } else if (created) { + tcx_entry_free(entry); + } +out: + if (replace_prog) + bpf_prog_put(replace_prog); + rtnl_unlock(); + return ret; +} + +int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + bool ingress = attr->attach_type == BPF_TCX_INGRESS; + struct net *net = current->nsproxy->net_ns; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + entry = tcx_entry_fetch(dev, ingress); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags, + attr->relative_fd, attr->expected_revision); + if (!ret) { + if (!tcx_entry_is_active(entry_new)) + entry_new = NULL; + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_dec(ingress); + bpf_mprog_commit(entry); + if (!entry_new) + tcx_entry_free(entry); + } +out: + rtnl_unlock(); + return ret; +} + +void tcx_uninstall(struct net_device *dev, bool ingress) +{ + struct bpf_mprog_entry *entry, *entry_new = NULL; + struct bpf_tuple tuple = {}; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + bool active; + + entry = tcx_entry_fetch(dev, ingress); + if (!entry) + return; + active = tcx_entry(entry)->miniq_active; + if (active) + bpf_mprog_clear_all(entry, &entry_new); + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + bpf_mprog_foreach_tuple(entry, fp, cp, tuple) { + if (tuple.link) + tcx_link(tuple.link)->dev = NULL; + else + bpf_prog_put(tuple.prog); + tcx_skeys_dec(ingress); + } + if (!active) + tcx_entry_free(entry); +} + +int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) +{ + bool ingress = attr->query.attach_type == BPF_TCX_INGRESS; + struct net *net = current->nsproxy->net_ns; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->query.target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + ret = bpf_mprog_query(attr, uattr, tcx_entry_fetch(dev, ingress)); +out: + rtnl_unlock(); + return ret; +} + +static int tcx_link_prog_attach(struct bpf_link *link, u32 flags, u32 id_or_fd, + u64 revision) +{ + struct tcx_link *tcx = tcx_link(link); + bool created, ingress = link->attach_type == BPF_TCX_INGRESS; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev = tcx->dev; + int ret; + + ASSERT_RTNL(); + entry = tcx_entry_fetch_or_create(dev, ingress, &created); + if (!entry) + return -ENOMEM; + ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags, + id_or_fd, revision); + if (!ret) { + if (entry != entry_new) { + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_inc(ingress); + } + bpf_mprog_commit(entry); + } else if (created) { + tcx_entry_free(entry); + } + return ret; +} + +static void tcx_link_release(struct bpf_link *link) +{ + struct tcx_link *tcx = tcx_link(link); + bool ingress = link->attach_type == BPF_TCX_INGRESS; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = tcx->dev; + if (!dev) + goto out; + entry = tcx_entry_fetch(dev, ingress); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0); + if (!ret) { + if (!tcx_entry_is_active(entry_new)) + entry_new = NULL; + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_dec(ingress); + bpf_mprog_commit(entry); + if (!entry_new) + tcx_entry_free(entry); + tcx->dev = NULL; + } +out: + WARN_ON_ONCE(ret); + rtnl_unlock(); +} + +static int tcx_link_update(struct bpf_link *link, struct bpf_prog *nprog, + struct bpf_prog *oprog) +{ + struct tcx_link *tcx = tcx_link(link); + bool ingress = link->attach_type == BPF_TCX_INGRESS; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = tcx->dev; + if (!dev) { + ret = -ENOLINK; + goto out; + } + if (oprog && link->prog != oprog) { + ret = -EPERM; + goto out; + } + oprog = link->prog; + if (oprog == nprog) { + bpf_prog_put(nprog); + goto out; + } + entry = tcx_entry_fetch(dev, ingress); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog, + BPF_F_REPLACE | BPF_F_ID, + link->prog->aux->id, 0); + if (!ret) { + WARN_ON_ONCE(entry != entry_new); + oprog = xchg(&link->prog, nprog); + bpf_prog_put(oprog); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +static void tcx_link_dealloc(struct bpf_link *link) +{ + kfree(tcx_link(link)); +} + +static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) +{ + const struct tcx_link *tcx = tcx_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (tcx->dev) + ifindex = tcx->dev->ifindex; + rtnl_unlock(); + + seq_printf(seq, "ifindex:\t%u\n", ifindex); + seq_printf(seq, "attach_type:\t%u (%s)\n", + link->attach_type, + link->attach_type == BPF_TCX_INGRESS ? "ingress" : "egress"); +} + +static int tcx_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct tcx_link *tcx = tcx_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (tcx->dev) + ifindex = tcx->dev->ifindex; + rtnl_unlock(); + + info->tcx.ifindex = ifindex; + info->tcx.attach_type = link->attach_type; + return 0; +} + +static int tcx_link_detach(struct bpf_link *link) +{ + tcx_link_release(link); + return 0; +} + +static const struct bpf_link_ops tcx_link_lops = { + .release = tcx_link_release, + .detach = tcx_link_detach, + .dealloc = tcx_link_dealloc, + .update_prog = tcx_link_update, + .show_fdinfo = tcx_link_fdinfo, + .fill_link_info = tcx_link_fill_info, +}; + +static int tcx_link_init(struct tcx_link *tcx, + struct bpf_link_primer *link_primer, + const union bpf_attr *attr, + struct net_device *dev, + struct bpf_prog *prog) +{ + bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog, + attr->link_create.attach_type); + tcx->dev = dev; + return bpf_link_prime(&tcx->link, link_primer); +} + +int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_link_primer link_primer; + struct net_device *dev; + struct tcx_link *tcx; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->link_create.target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + tcx = kzalloc(sizeof(*tcx), GFP_USER); + if (!tcx) { + ret = -ENOMEM; + goto out; + } + ret = tcx_link_init(tcx, &link_primer, attr, dev, prog); + if (ret) { + kfree(tcx); + goto out; + } + ret = tcx_link_prog_attach(&tcx->link, attr->link_create.flags, + attr->link_create.tcx.relative_fd, + attr->link_create.tcx.expected_revision); + if (ret) { + tcx->dev = NULL; + bpf_link_cleanup(&link_primer); + goto out; + } + ret = bpf_link_settle(&link_primer); +out: + rtnl_unlock(); + return ret; +} diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index 3d7127f439a1..f8e70e9c3998 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -83,6 +83,11 @@ struct tnum tnum_sub(struct tnum a, struct tnum b) return TNUM(dv & ~mu, mu); } +struct tnum tnum_neg(struct tnum a) +{ + return tnum_sub(TNUM(0, 0), a); +} + struct tnum tnum_and(struct tnum a, struct tnum b) { u64 alpha, beta, v; @@ -111,31 +116,55 @@ struct tnum tnum_xor(struct tnum a, struct tnum b) return TNUM(v & ~mu, mu); } -/* Generate partial products by multiplying each bit in the multiplier (tnum a) - * with the multiplicand (tnum b), and add the partial products after - * appropriately bit-shifting them. Instead of directly performing tnum addition - * on the generated partial products, equivalenty, decompose each partial - * product into two tnums, consisting of the value-sum (acc_v) and the - * mask-sum (acc_m) and then perform tnum addition on them. The following paper - * explains the algorithm in more detail: https://arxiv.org/abs/2105.05398. +/* Perform long multiplication, iterating through the bits in a using rshift: + * - if LSB(a) is a known 0, keep current accumulator + * - if LSB(a) is a known 1, add b to current accumulator + * - if LSB(a) is unknown, take a union of the above cases. + * + * For example: + * + * acc_0: acc_1: + * + * 11 * -> 11 * -> 11 * -> union(0011, 1001) == x0x1 + * x1 01 11 + * ------ ------ ------ + * 11 11 11 + * xx 00 11 + * ------ ------ ------ + * ???? 0011 1001 */ struct tnum tnum_mul(struct tnum a, struct tnum b) { - u64 acc_v = a.value * b.value; - struct tnum acc_m = TNUM(0, 0); + struct tnum acc = TNUM(0, 0); while (a.value || a.mask) { /* LSB of tnum a is a certain 1 */ if (a.value & 1) - acc_m = tnum_add(acc_m, TNUM(0, b.mask)); + acc = tnum_add(acc, b); /* LSB of tnum a is uncertain */ - else if (a.mask & 1) - acc_m = tnum_add(acc_m, TNUM(0, b.value | b.mask)); + else if (a.mask & 1) { + /* acc = tnum_union(acc_0, acc_1), where acc_0 and + * acc_1 are partial accumulators for cases + * LSB(a) = certain 0 and LSB(a) = certain 1. + * acc_0 = acc + 0 * b = acc. + * acc_1 = acc + 1 * b = tnum_add(acc, b). + */ + + acc = tnum_union(acc, tnum_add(acc, b)); + } /* Note: no case for LSB is certain 0 */ a = tnum_rshift(a, 1); b = tnum_lshift(b, 1); } - return tnum_add(TNUM(acc_v, 0), acc_m); + return acc; +} + +bool tnum_overlap(struct tnum a, struct tnum b) +{ + u64 mu; + + mu = ~a.mask & ~b.mask; + return (a.value & mu) == (b.value & mu); } /* Note that if a and b disagree - i.e. one has a 'known 1' where the other has @@ -150,6 +179,19 @@ struct tnum tnum_intersect(struct tnum a, struct tnum b) return TNUM(v & ~mu, mu); } +/* Returns a tnum with the uncertainty from both a and b, and in addition, new + * uncertainty at any position that a and b disagree. This represents a + * superset of the union of the concrete sets of both a and b. Despite the + * overapproximation, it is optimal. + */ +struct tnum tnum_union(struct tnum a, struct tnum b) +{ + u64 v = a.value & b.value; + u64 mu = (a.value ^ b.value) | a.mask | b.mask; + + return TNUM(v & ~mu, mu); +} + struct tnum tnum_cast(struct tnum a, u8 size) { a.value &= (1ULL << (size * 8)) - 1; @@ -172,12 +214,6 @@ bool tnum_in(struct tnum a, struct tnum b) return a.value == b.value; } -int tnum_strn(char *str, size_t size, struct tnum a) -{ - return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); -} -EXPORT_SYMBOL_GPL(tnum_strn); - int tnum_sbin(char *str, size_t size, struct tnum a) { size_t n; @@ -208,7 +244,12 @@ struct tnum tnum_clear_subreg(struct tnum a) return tnum_lshift(tnum_rshift(a, 32), 32); } +struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg) +{ + return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg)); +} + struct tnum tnum_const_subreg(struct tnum a, u32 value) { - return tnum_or(tnum_clear_subreg(a), tnum_const(value)); + return tnum_with_subreg(a, tnum_const(value)); } diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..feecd8f4dbf9 --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,261 @@ +#include <linux/bpf.h> +#include <linux/vmalloc.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/idr.h> +#include <linux/namei.h> +#include <linux/user_namespace.h> +#include <linux/security.h> + +static bool bpf_ns_capable(struct user_namespace *ns, int cap) +{ + return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); +} + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + struct user_namespace *userns; + + /* BPF token allows ns_capable() level of capabilities */ + userns = token ? token->userns : &init_user_ns; + if (!bpf_ns_capable(userns, cap)) + return false; + if (token && security_bpf_token_capable(token, cap) < 0) + return false; + return true; +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + security_bpf_token_free(token); + put_user_ns(token->userns); + kfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = BIT_ULL(__MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = BIT_ULL(__MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = BIT_ULL(__MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = BIT_ULL(__MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_token *token __free(kfree) = NULL; + struct bpf_mount_opts *mnt_opts; + struct user_namespace *userns; + struct inode *inode; + CLASS(fd, f)(attr->token_create.bpffs_fd); + struct path path; + struct super_block *sb; + umode_t mode; + int err; + + if (fd_empty(f)) + return -EBADF; + + path = fd_file(f)->f_path; + sb = path.dentry->d_sb; + + if (path.dentry != sb->s_root) + return -EINVAL; + if (sb->s_op != &bpf_super_ops) + return -EINVAL; + err = path_permission(&path, MAY_ACCESS); + if (err) + return err; + + userns = sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) + return -EPERM; + if (!ns_capable(userns, CAP_BPF)) + return -EPERM; + + /* Creating BPF token in init_user_ns doesn't make much sense. */ + if (current_user_ns() == &init_user_ns) + return -EOPNOTSUPP; + + mnt_opts = sb->s_fs_info; + if (mnt_opts->delegate_cmds == 0 && + mnt_opts->delegate_maps == 0 && + mnt_opts->delegate_progs == 0 && + mnt_opts->delegate_attachs == 0) + return -ENOENT; /* no BPF token delegation is set up */ + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(sb, NULL, mode); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + FD_PREPARE(fdf, O_CLOEXEC, + alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, + O_RDWR, &bpf_token_fops)); + if (fdf.err) + return fdf.err; + + token = kzalloc(sizeof(*token), GFP_USER); + if (!token) + return -ENOMEM; + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks. */ + token->userns = userns; + token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; + + err = security_bpf_token_create(token, attr, &path); + if (err) + return err; + + get_user_ns(token->userns); + fd_prepare_file(fdf)->private_data = no_free_ptr(token); + return fd_publish(fdf); +} + +int bpf_token_get_info_by_fd(struct bpf_token *token, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct bpf_token_info info; + u32 info_len = attr->info.info_len; + + info_len = min_t(u32, info_len, sizeof(info)); + memset(&info, 0, sizeof(info)); + + info.allowed_cmds = token->allowed_cmds; + info.allowed_maps = token->allowed_maps; + info.allowed_progs = token->allowed_progs; + info.allowed_attachs = token->allowed_attachs; + + if (copy_to_user(uinfo, &info, info_len) || + put_user(info_len, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + CLASS(fd, f)(ufd); + struct bpf_token *token; + + if (fd_empty(f)) + return ERR_PTR(-EBADF); + if (fd_file(f)->f_op != &bpf_token_fops) + return ERR_PTR(-EINVAL); + + token = fd_file(f)->private_data; + bpf_token_inc(token); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + if (!token) + return false; + if (!(token->allowed_cmds & BIT_ULL(cmd))) + return false; + return security_bpf_token_cmd(token, cmd) == 0; +} + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & BIT_ULL(type); +} + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & BIT_ULL(prog_type)) && + (token->allowed_attachs & BIT_ULL(attach_type)); +} diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index d0ed7d6f5eec..976d89011b15 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -9,7 +9,6 @@ #include <linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> -#include <linux/module.h> #include <linux/static_call.h> #include <linux/bpf_verifier.h> #include <linux/bpf_lsm.h> @@ -45,8 +44,8 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, enum ftrace_ops_cmd lockdep_assert_held_once(&tr->mutex); /* Instead of updating the trampoline here, we propagate - * -EAGAIN to register_ftrace_direct_multi(). Then we can - * retry register_ftrace_direct_multi() after updating the + * -EAGAIN to register_ftrace_direct(). Then we can + * retry register_ftrace_direct() after updating the * trampoline. */ if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) && @@ -116,10 +115,14 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog) (ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC); } -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym) +void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym) { ksym->start = (unsigned long) data; - ksym->end = ksym->start + PAGE_SIZE; + ksym->end = ksym->start + size; +} + +void bpf_image_ksym_add(struct bpf_ksym *ksym) +{ bpf_ksym_add(ksym); perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, PAGE_SIZE, false, ksym->name); @@ -172,54 +175,52 @@ out: return tr; } -static int bpf_trampoline_module_get(struct bpf_trampoline *tr) +static int bpf_trampoline_update_fentry(struct bpf_trampoline *tr, u32 orig_flags, + void *old_addr, void *new_addr) { - struct module *mod; - int err = 0; + enum bpf_text_poke_type new_t = BPF_MOD_CALL, old_t = BPF_MOD_CALL; + void *ip = tr->func.addr; - preempt_disable(); - mod = __module_text_address((unsigned long) tr->func.addr); - if (mod && !try_module_get(mod)) - err = -ENOENT; - preempt_enable(); - tr->mod = mod; - return err; -} + if (!new_addr) + new_t = BPF_MOD_NOP; + else if (bpf_trampoline_use_jmp(tr->flags)) + new_t = BPF_MOD_JUMP; -static void bpf_trampoline_module_put(struct bpf_trampoline *tr) -{ - module_put(tr->mod); - tr->mod = NULL; + if (!old_addr) + old_t = BPF_MOD_NOP; + else if (bpf_trampoline_use_jmp(orig_flags)) + old_t = BPF_MOD_JUMP; + + return bpf_arch_text_poke(ip, old_t, new_t, old_addr, new_addr); } -static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) +static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags, + void *old_addr) { - void *ip = tr->func.addr; int ret; if (tr->func.ftrace_managed) - ret = unregister_ftrace_direct_multi(tr->fops, (long)old_addr); + ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false); else - ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); + ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr, NULL); - if (!ret) - bpf_trampoline_module_put(tr); return ret; } -static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr, +static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags, + void *old_addr, void *new_addr, bool lock_direct_mutex) { - void *ip = tr->func.addr; int ret; if (tr->func.ftrace_managed) { if (lock_direct_mutex) - ret = modify_ftrace_direct_multi(tr->fops, (long)new_addr); + ret = modify_ftrace_direct(tr->fops, (long)new_addr); else - ret = modify_ftrace_direct_multi_nolock(tr->fops, (long)new_addr); + ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr); } else { - ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr); + ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr, + new_addr); } return ret; } @@ -238,18 +239,15 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) tr->func.ftrace_managed = true; } - if (bpf_trampoline_module_get(tr)) - return -ENOENT; - if (tr->func.ftrace_managed) { - ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1); - ret = register_ftrace_direct_multi(tr->fops, (long)new_addr); + ret = ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1); + if (ret) + return ret; + ret = register_ftrace_direct(tr->fops, (long)new_addr); } else { - ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + ret = bpf_trampoline_update_fentry(tr, 0, NULL, new_addr); } - if (ret) - bpf_trampoline_module_put(tr); return ret; } @@ -279,16 +277,21 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a return tlinks; } +static void bpf_tramp_image_free(struct bpf_tramp_image *im) +{ + bpf_image_ksym_del(&im->ksym); + arch_free_bpf_trampoline(im->image, im->size); + bpf_jit_uncharge_modmem(im->size); + percpu_ref_exit(&im->pcref); + kfree_rcu(im, rcu); +} + static void __bpf_tramp_image_put_deferred(struct work_struct *work) { struct bpf_tramp_image *im; im = container_of(work, struct bpf_tramp_image, work); - bpf_image_ksym_del(&im->ksym); - bpf_jit_free_exec(im->image); - bpf_jit_uncharge_modmem(PAGE_SIZE); - percpu_ref_exit(&im->pcref); - kfree_rcu(im, rcu); + bpf_tramp_image_free(im); } /* callback, fexit step 3 or fentry step 2 */ @@ -353,10 +356,11 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) * call_rcu_tasks() is not necessary. */ if (im->ip_after_call) { - int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP, - NULL, im->ip_epilogue); + int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_NOP, + 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); @@ -372,7 +376,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); } -static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size) { struct bpf_tramp_image *im; struct bpf_ksym *ksym; @@ -383,15 +387,15 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) if (!im) goto out; - err = bpf_jit_charge_modmem(PAGE_SIZE); + err = bpf_jit_charge_modmem(size); if (err) goto out_free_im; + im->size = size; err = -ENOMEM; - im->image = image = bpf_jit_alloc_exec(PAGE_SIZE); + im->image = image = arch_alloc_bpf_trampoline(size); if (!image) goto out_uncharge; - set_vm_flush_reset_perms(image); err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL); if (err) @@ -399,14 +403,15 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) ksym = &im->ksym; INIT_LIST_HEAD_RCU(&ksym->lnode); - snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx); - bpf_image_ksym_add(image, ksym); + snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key); + bpf_image_ksym_init(image, size, ksym); + bpf_image_ksym_add(ksym); return im; out_free_image: - bpf_jit_free_exec(im->image); + arch_free_bpf_trampoline(im->image, im->size); out_uncharge: - bpf_jit_uncharge_modmem(PAGE_SIZE); + bpf_jit_uncharge_modmem(size); out_free_im: kfree(im); out: @@ -419,28 +424,21 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut struct bpf_tramp_links *tlinks; u32 orig_flags = tr->flags; bool ip_arg = false; - int err, total; + int err, total, size; tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg); if (IS_ERR(tlinks)) return PTR_ERR(tlinks); if (total == 0) { - err = unregister_fentry(tr, tr->cur_image->image); + err = unregister_fentry(tr, orig_flags, tr->cur_image->image); bpf_tramp_image_put(tr->cur_image); tr->cur_image = NULL; - tr->selector = 0; - goto out; - } - - im = bpf_tramp_image_alloc(tr->key, tr->selector); - if (IS_ERR(im)) { - err = PTR_ERR(im); goto out; } - /* clear all bits except SHARE_IPMODIFY */ - tr->flags &= BPF_TRAMP_F_SHARE_IPMODIFY; + /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */ + tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX); if (tlinks[BPF_TRAMP_FEXIT].nr_links || tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) { @@ -457,24 +455,62 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS again: - if ((tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) && - (tr->flags & BPF_TRAMP_F_CALL_ORIG)) - tr->flags |= BPF_TRAMP_F_ORIG_STACK; + if (tr->flags & BPF_TRAMP_F_CALL_ORIG) { + if (tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) { + /* The BPF_TRAMP_F_SKIP_FRAME can be cleared in the + * first try, reset it in the second try. + */ + tr->flags |= BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SKIP_FRAME; + } else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_JMP)) { + /* Use "jmp" instead of "call" for the trampoline + * in the origin call case, and we don't need to + * skip the frame. + */ + tr->flags &= ~BPF_TRAMP_F_SKIP_FRAME; + } + } #endif - err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, + size = arch_bpf_trampoline_size(&tr->func.model, tr->flags, + tlinks, tr->func.addr); + if (size < 0) { + err = size; + goto out; + } + + if (size > PAGE_SIZE) { + err = -E2BIG; + goto out; + } + + im = bpf_tramp_image_alloc(tr->key, size); + if (IS_ERR(im)) { + err = PTR_ERR(im); + goto out; + } + + err = arch_prepare_bpf_trampoline(im, im->image, im->image + size, &tr->func.model, tr->flags, tlinks, tr->func.addr); if (err < 0) - goto out; + goto out_free; - set_memory_rox((long)im->image, 1); + err = arch_protect_bpf_trampoline(im->image, im->size); + if (err) + goto out_free; + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP + if (bpf_trampoline_use_jmp(tr->flags)) + tr->fops->flags |= FTRACE_OPS_FL_JMP; + else + tr->fops->flags &= ~FTRACE_OPS_FL_JMP; +#endif - WARN_ON(tr->cur_image && tr->selector == 0); - WARN_ON(!tr->cur_image && tr->selector); + WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) /* progs already running at this address */ - err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex); + err = modify_fentry(tr, orig_flags, tr->cur_image->image, + im->image, lock_direct_mutex); else /* first time registering */ err = register_fentry(tr, im->image); @@ -485,29 +521,33 @@ again: * BPF_TRAMP_F_SHARE_IPMODIFY is set, we can generate the * trampoline again, and retry register. */ - /* reset fops->func and fops->trampoline for re-register */ - tr->fops->func = NULL; - tr->fops->trampoline = 0; - - /* reset im->image memory attr for arch_prepare_bpf_trampoline */ - set_memory_nx((long)im->image, 1); - set_memory_rw((long)im->image, 1); + bpf_tramp_image_free(im); goto again; } #endif if (err) - goto out; + goto out_free; if (tr->cur_image) bpf_tramp_image_put(tr->cur_image); tr->cur_image = im; - tr->selector++; out: /* If any error happens, restore previous flags */ - if (err) + if (err) { tr->flags = orig_flags; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP + if (bpf_trampoline_use_jmp(tr->flags)) + tr->fops->flags |= FTRACE_OPS_FL_JMP; + else + tr->fops->flags &= ~FTRACE_OPS_FL_JMP; +#endif + } kfree(tlinks); return err; + +out_free: + bpf_tramp_image_free(im); + goto out; } static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) @@ -532,7 +572,27 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) } } -static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog) +{ + struct bpf_prog_aux *aux = tgt_prog->aux; + + guard(mutex)(&aux->ext_mutex); + if (aux->prog_array_member_cnt) + /* Program extensions can not extend target prog when the target + * prog has been updated to any prog_array map as tail callee. + * It's to prevent a potential infinite loop like: + * tgt prog entry -> tgt prog subprog -> freplace prog entry + * --tailcall-> tgt prog entry. + */ + return -EBUSY; + + aux->is_extended = true; + return 0; +} + +static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { enum bpf_tramp_prog_type kind; struct bpf_tramp_link *link_exiting; @@ -553,8 +613,12 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_tr /* Cannot attach extension if fentry/fexit are in use. */ if (cnt) return -EBUSY; + err = bpf_freplace_check_tgt_prog(tgt_prog); + if (err) + return err; tr->extension_prog = link->link.prog; - return bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL, + return bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP, + BPF_MOD_JUMP, NULL, link->link.prog->bpf_func); } if (cnt >= BPF_MAX_TRAMP_LINKS) @@ -579,17 +643,21 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_tr return err; } -int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { int err; mutex_lock(&tr->mutex); - err = __bpf_trampoline_link_prog(link, tr); + err = __bpf_trampoline_link_prog(link, tr, tgt_prog); mutex_unlock(&tr->mutex); return err; } -static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { enum bpf_tramp_prog_type kind; int err; @@ -598,8 +666,11 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_ if (kind == BPF_TRAMP_REPLACE) { WARN_ON_ONCE(!tr->extension_prog); err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, + BPF_MOD_NOP, tr->extension_prog->bpf_func, NULL); tr->extension_prog = NULL; + guard(mutex)(&tgt_prog->aux->ext_mutex); + tgt_prog->aux->is_extended = false; return err; } hlist_del_init(&link->tramp_hlist); @@ -608,12 +679,14 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_ } /* bpf_trampoline_unlink_prog() should never fail. */ -int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { int err; mutex_lock(&tr->mutex); - err = __bpf_trampoline_unlink_prog(link, tr); + err = __bpf_trampoline_unlink_prog(link, tr, tgt_prog); mutex_unlock(&tr->mutex); return err; } @@ -628,7 +701,7 @@ static void bpf_shim_tramp_link_release(struct bpf_link *link) if (!shim_link->trampoline) return; - WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline)); + WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); bpf_trampoline_put(shim_link->trampoline); } @@ -647,7 +720,8 @@ static const struct bpf_link_ops bpf_shim_tramp_link_lops = { static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog, bpf_func_t bpf_func, - int cgroup_atype) + int cgroup_atype, + enum bpf_attach_type attach_type) { struct bpf_shim_tramp_link *shim_link = NULL; struct bpf_prog *p; @@ -674,7 +748,7 @@ static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog p->expected_attach_type = BPF_LSM_MAC; bpf_prog_inc(p); bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC, - &bpf_shim_tramp_link_lops, p); + &bpf_shim_tramp_link_lops, p, attach_type); bpf_cgroup_atype_get(p->aux->attach_btf_id, cgroup_atype); return shim_link; @@ -699,7 +773,8 @@ static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr, } int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, - int cgroup_atype) + int cgroup_atype, + enum bpf_attach_type attach_type) { struct bpf_shim_tramp_link *shim_link = NULL; struct bpf_attach_target_info tgt_info = {}; @@ -736,13 +811,13 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, /* Allocate and install new shim. */ - shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype); + shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype, attach_type); if (!shim_link) { err = -ENOMEM; goto err; } - err = __bpf_trampoline_link_prog(&shim_link->link, tr); + err = __bpf_trampoline_link_prog(&shim_link->link, tr, NULL); if (err) goto err; @@ -870,38 +945,45 @@ static __always_inline u64 notrace bpf_prog_start_time(void) static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { - rcu_read_lock(); - migrate_disable(); + rcu_read_lock_dont_migrate(); run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); + if (prog->aux->recursion_detected) + prog->aux->recursion_detected(prog); return 0; } return bpf_prog_start_time(); } -static void notrace update_prog_stats(struct bpf_prog *prog, - u64 start) +static void notrace __update_prog_stats(struct bpf_prog *prog, u64 start) { struct bpf_prog_stats *stats; + unsigned long flags; + u64 duration; - if (static_branch_unlikely(&bpf_stats_enabled_key) && - /* static_key could be enabled in __bpf_prog_enter* - * and disabled in __bpf_prog_exit*. - * And vice versa. - * Hence check that 'start' is valid. - */ - start > NO_START_TIME) { - 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_update_end_irqrestore(&stats->syncp, flags); - } + /* + * static_key could be enabled in __bpf_prog_enter* and disabled in + * __bpf_prog_exit*. And vice versa. Check that 'start' is valid. + */ + if (start <= NO_START_TIME) + return; + + duration = sched_clock() - start; + stats = this_cpu_ptr(prog->stats); + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, duration); + u64_stats_update_end_irqrestore(&stats->syncp, flags); +} + +static __always_inline void notrace update_prog_stats(struct bpf_prog *prog, + u64 start) +{ + if (static_branch_unlikely(&bpf_stats_enabled_key)) + __update_prog_stats(prog, start); } static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start, @@ -912,8 +994,7 @@ static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start, update_prog_stats(prog, start); this_cpu_dec(*(prog->active)); - migrate_enable(); - rcu_read_unlock(); + rcu_read_unlock_migrate(); } static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, @@ -923,8 +1004,7 @@ static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, /* Runtime stats are exported via actual BPF_LSM_CGROUP * programs, not the shims. */ - rcu_read_lock(); - migrate_disable(); + rcu_read_lock_dont_migrate(); run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); @@ -937,8 +1017,7 @@ static void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, { bpf_reset_run_ctx(run_ctx->saved_run_ctx); - migrate_enable(); - rcu_read_unlock(); + rcu_read_unlock_migrate(); } u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, @@ -948,13 +1027,14 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, migrate_disable(); might_fault(); + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); + if (prog->aux->recursion_detected) + prog->aux->recursion_detected(prog); return 0; } - - run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); - return bpf_prog_start_time(); } @@ -995,8 +1075,7 @@ static u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { - rcu_read_lock(); - migrate_disable(); + rcu_read_lock_dont_migrate(); run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); @@ -1010,8 +1089,7 @@ static void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, bpf_reset_run_ctx(run_ctx->saved_run_ctx); update_prog_stats(prog, start); - migrate_enable(); - rcu_read_unlock(); + rcu_read_unlock_migrate(); } void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr) @@ -1026,7 +1104,7 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) { - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; if (bpf_prog_check_recur(prog)) return sleepable ? __bpf_prog_enter_sleepable_recur : @@ -1041,7 +1119,7 @@ bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) { - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; if (bpf_prog_check_recur(prog)) return sleepable ? __bpf_prog_exit_sleepable_recur : @@ -1055,10 +1133,43 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) } int __weak -arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call) + void *func_addr) +{ + return -ENOTSUPP; +} + +void * __weak arch_alloc_bpf_trampoline(unsigned int size) +{ + void *image; + + if (WARN_ON_ONCE(size > PAGE_SIZE)) + return NULL; + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (image) + set_vm_flush_reset_perms(image); + return image; +} + +void __weak arch_free_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + /* bpf_jit_free_exec doesn't need "size", but + * bpf_prog_pack_free() needs it. + */ + bpf_jit_free_exec(image); +} + +int __weak arch_protect_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + return set_memory_rox((long)image, 1); +} + +int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) { return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index dbef0b0967ae..f0ca69f888fa 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -24,6 +24,12 @@ #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/poison.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/bpf_mem_alloc.h> +#include <net/xdp.h> +#include <linux/trace_events.h> +#include <linux/kallsyms.h> #include "disasm.h" @@ -38,6 +44,15 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #undef BPF_LINK_TYPE }; +enum bpf_features { + BPF_FEAT_RDONLY_CAST_TO_VOID = 0, + BPF_FEAT_STREAMS = 1, + __MAX_BPF_FEAT, +}; + +struct bpf_mem_alloc bpf_global_percpu_ma; +static bool bpf_global_percpu_ma_set; + /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. @@ -165,7 +180,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { /* 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' */ @@ -183,31 +198,37 @@ 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); +#define BPF_PRIV_STACK_MIN_SIZE 64 + +static int acquire_reference(struct bpf_verifier_env *env, int insn_idx); +static int release_reference_nomark(struct bpf_verifier_state *state, int ref_obj_id); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); +static void invalidate_non_owning_refs(struct bpf_verifier_env *env); +static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env); +static int ref_set_non_owning(struct bpf_verifier_env *env, + struct bpf_reg_state *reg); +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) @@ -233,6 +254,12 @@ static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } +static bool bpf_helper_call(const struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_CALL) && + insn->src_reg == 0; +} + static bool bpf_pseudo_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && @@ -255,6 +282,7 @@ struct bpf_call_arg_meta { int mem_size; u64 msize_max_value; int ref_obj_id; + int dynptr_id; int map_uid; int func_id; struct btf *btf; @@ -263,88 +291,74 @@ struct bpf_call_arg_meta { u32 ret_btf_id; u32 subprogno; struct btf_field *kptr_field; - u8 uninit_dynptr_regno; + s64 const_map_key; }; -struct btf *btf_vmlinux; - -static DEFINE_MUTEX(bpf_verifier_lock); - -static const struct bpf_line_info * -find_linfo(const struct bpf_verifier_env *env, u32 insn_off) -{ - const struct bpf_line_info *linfo; - const struct bpf_prog *prog; - u32 i, nr_linfo; - - prog = env->prog; - nr_linfo = prog->aux->nr_linfo; - - if (!nr_linfo || insn_off >= prog->len) - return NULL; - - linfo = prog->aux->linfo; - for (i = 1; i < nr_linfo; i++) - if (insn_off < linfo[i].insn_off) - break; - - return &linfo[i - 1]; -} - -void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, - va_list args) -{ - unsigned int n; - - n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); - - WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, - "verifier log line truncated - local buffer too short\n"); +struct bpf_kfunc_call_arg_meta { + /* In parameters */ + struct btf *btf; + u32 func_id; + u32 kfunc_flags; + const struct btf_type *func_proto; + const char *func_name; + /* Out parameters */ + u32 ref_obj_id; + u8 release_regno; + bool r0_rdonly; + u32 ret_btf_id; + u64 r0_size; + u32 subprogno; + struct { + u64 value; + bool found; + } arg_constant; - if (log->level == BPF_LOG_KERNEL) { - bool newline = n > 0 && log->kbuf[n - 1] == '\n'; + /* arg_{btf,btf_id,owning_ref} are used by kfunc-specific handling, + * generally to pass info about user-defined local kptr types to later + * verification logic + * bpf_obj_drop/bpf_percpu_obj_drop + * Record the local kptr type to be drop'd + * bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type) + * Record the local kptr type to be refcount_incr'd and use + * arg_owning_ref to determine whether refcount_acquire should be + * fallible + */ + struct btf *arg_btf; + u32 arg_btf_id; + bool arg_owning_ref; + bool arg_prog; - pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); - return; - } + struct { + struct btf_field *field; + } arg_list_head; + struct { + struct btf_field *field; + } arg_rbtree_root; + struct { + enum bpf_dynptr_type type; + u32 id; + u32 ref_obj_id; + } initialized_dynptr; + struct { + u8 spi; + u8 frameno; + } iter; + struct { + struct bpf_map *ptr; + int uid; + } map; + u64 mem_size; +}; - n = min(log->len_total - log->len_used - 1, n); - log->kbuf[n] = '\0'; - if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) - log->len_used += n; - else - log->ubuf = NULL; -} +struct btf *btf_vmlinux; -static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos) +static const char *btf_type_name(const struct btf *btf, u32 id) { - char zero = 0; - - if (!bpf_verifier_log_needed(log)) - return; - - log->len_used = new_pos; - if (put_user(zero, log->ubuf + new_pos)) - log->ubuf = NULL; + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } -/* log_level controls verbosity level of eBPF verifier. - * bpf_verifier_log_write() is used to dump the verification trace to the log, - * so the user can figure out what's wrong with the program - */ -__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, - const char *fmt, ...) -{ - va_list args; - - if (!bpf_verifier_log_needed(&env->log)) - return; - - va_start(args, fmt); - bpf_verifier_vlog(&env->log, fmt, args); - va_end(args); -} -EXPORT_SYMBOL_GPL(bpf_verifier_log_write); +static DEFINE_MUTEX(bpf_verifier_lock); +static DEFINE_MUTEX(bpf_percpu_ma_lock); __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { @@ -359,101 +373,44 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) va_end(args); } -__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, - const char *fmt, ...) -{ - va_list args; - - if (!bpf_verifier_log_needed(log)) - return; - - va_start(args, fmt); - bpf_verifier_vlog(log, fmt, args); - va_end(args); -} -EXPORT_SYMBOL_GPL(bpf_log); - -static const char *ltrim(const char *s) -{ - while (isspace(*s)) - s++; - - return s; -} - -__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env, - u32 insn_off, - const char *prefix_fmt, ...) -{ - const struct bpf_line_info *linfo; - - if (!bpf_verifier_log_needed(&env->log)) - return; - - linfo = find_linfo(env, insn_off); - if (!linfo || linfo == env->prev_linfo) - return; - - if (prefix_fmt) { - va_list args; - - va_start(args, prefix_fmt); - bpf_verifier_vlog(&env->log, prefix_fmt, args); - va_end(args); - } - - verbose(env, "%s\n", - ltrim(btf_name_by_offset(env->prog->aux->btf, - linfo->line_off))); - - env->prev_linfo = linfo; -} - static void verbose_invalid_scalar(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - struct tnum *range, const char *ctx, + struct bpf_retval_range range, const char *ctx, const char *reg_name) { - char tn_buf[48]; + bool unknown = true; - verbose(env, "At %s the register %s ", ctx, reg_name); - if (!tnum_is_unknown(reg->var_off)) { - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "has value %s", tn_buf); - } else { - verbose(env, "has unknown scalar value"); + verbose(env, "%s the register %s has", ctx, reg_name); + if (reg->smin_value > S64_MIN) { + verbose(env, " smin=%lld", reg->smin_value); + unknown = false; + } + if (reg->smax_value < S64_MAX) { + verbose(env, " smax=%lld", reg->smax_value); + unknown = false; } - tnum_strn(tn_buf, sizeof(tn_buf), *range); - verbose(env, " should have been in %s\n", tn_buf); + if (unknown) + verbose(env, " unknown scalar value"); + verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval); } -static bool type_is_pkt_pointer(enum bpf_reg_type type) +static bool reg_not_null(const struct bpf_reg_state *reg) { - type = base_type(type); - return type == PTR_TO_PACKET || - type == PTR_TO_PACKET_META; -} + enum bpf_reg_type type; -static bool type_is_sk_pointer(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET || - type == PTR_TO_SOCK_COMMON || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_XDP_SOCK; -} + type = reg->type; + if (type_may_be_null(type)) + return false; -static bool reg_type_not_null(enum bpf_reg_type type) -{ + type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || type == PTR_TO_MAP_KEY || - type == PTR_TO_SOCK_COMMON; -} - -static bool type_is_ptr_alloc_obj(u32 type) -{ - return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; + type == PTR_TO_SOCK_COMMON || + (type == PTR_TO_BTF_ID && is_trusted_reg(reg)) || + (type == PTR_TO_MEM && !(reg->type & PTR_UNTRUSTED)) || + type == CONST_PTR_TO_MAP; } static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) @@ -471,19 +428,46 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) return rec; } -static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) +static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) { - return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); + struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; + + return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL; } -static bool type_is_rdonly_mem(u32 type) +static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) { - return type & MEM_RDONLY; + struct bpf_func_info *info; + + if (!env->prog->aux->func_info) + return ""; + + info = &env->prog->aux->func_info[subprog]; + return btf_type_name(env->prog->aux->btf, info->type_id); +} + +static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog) +{ + struct bpf_subprog_info *info = subprog_info(env, subprog); + + info->is_cb = true; + info->is_async_cb = true; + info->is_exception_cb = true; } -static bool type_may_be_null(u32 type) +static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog) { - return type & PTR_MAYBE_NULL; + return subprog_info(env, subprog)->is_exception_cb; +} + +static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) +{ + return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK); +} + +static bool type_is_rdonly_mem(u32 type) +{ + return type & MEM_RDONLY; } static bool is_acquire_function(enum bpf_func_id func_id, @@ -523,15 +507,70 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_dynptr_data; } -static bool is_callback_calling_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_task_work_add_kfunc(u32 func_id); + +static bool is_sync_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || - func_id == BPF_FUNC_timer_set_callback || func_id == BPF_FUNC_find_vma || func_id == BPF_FUNC_loop || func_id == BPF_FUNC_user_ringbuf_drain; } +static bool is_async_callback_calling_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_timer_set_callback; +} + +static bool is_callback_calling_function(enum bpf_func_id func_id) +{ + return is_sync_callback_calling_function(func_id) || + is_async_callback_calling_function(func_id); +} + +static bool is_sync_callback_calling_insn(struct bpf_insn *insn) +{ + return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) || + (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); +} + +static bool is_async_callback_calling_insn(struct bpf_insn *insn) +{ + 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_async_cb_sleepable(struct bpf_verifier_env *env, struct bpf_insn *insn) +{ + /* bpf_timer callbacks are never sleepable. */ + if (bpf_helper_call(insn) && insn->imm == BPF_FUNC_timer_set_callback) + return false; + + /* bpf_wq and bpf_task_work callbacks are always sleepable. */ + if (bpf_pseudo_kfunc_call(insn) && insn->off == 0 && + (is_bpf_wq_set_callback_impl_kfunc(insn->imm) || is_task_work_add_kfunc(insn->imm))) + return true; + + verifier_bug(env, "unhandled async callback in is_async_cb_sleepable"); + return false; +} + +static bool is_may_goto_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO; +} + +static bool is_may_goto_insn_at(struct bpf_verifier_env *env, int insn_idx) +{ + return is_may_goto_insn(&env->prog->insnsi[insn_idx]); +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -562,101 +601,18 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) insn->imm == BPF_CMPXCHG; } -/* string representation of 'enum bpf_reg_type' - * - * Note that reg_type_str() can not appear more than once in a single verbose() - * statement. - */ -static const char *reg_type_str(struct bpf_verifier_env *env, - enum bpf_reg_type type) -{ - char postfix[16] = {0}, prefix[64] = {0}; - static const char * const str[] = { - [NOT_INIT] = "?", - [SCALAR_VALUE] = "scalar", - [PTR_TO_CTX] = "ctx", - [CONST_PTR_TO_MAP] = "map_ptr", - [PTR_TO_MAP_VALUE] = "map_value", - [PTR_TO_STACK] = "fp", - [PTR_TO_PACKET] = "pkt", - [PTR_TO_PACKET_META] = "pkt_meta", - [PTR_TO_PACKET_END] = "pkt_end", - [PTR_TO_FLOW_KEYS] = "flow_keys", - [PTR_TO_SOCKET] = "sock", - [PTR_TO_SOCK_COMMON] = "sock_common", - [PTR_TO_TCP_SOCK] = "tcp_sock", - [PTR_TO_TP_BUFFER] = "tp_buffer", - [PTR_TO_XDP_SOCK] = "xdp_sock", - [PTR_TO_BTF_ID] = "ptr_", - [PTR_TO_MEM] = "mem", - [PTR_TO_BUF] = "buf", - [PTR_TO_FUNC] = "func", - [PTR_TO_MAP_KEY] = "map_key", - [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", - }; - - if (type & PTR_MAYBE_NULL) { - if (base_type(type) == PTR_TO_BTF_ID) - strncpy(postfix, "or_null_", 16); - else - strncpy(postfix, "_or_null", 16); - } - - snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", - type & MEM_RDONLY ? "rdonly_" : "", - type & MEM_RINGBUF ? "ringbuf_" : "", - type & MEM_USER ? "user_" : "", - type & MEM_PERCPU ? "percpu_" : "", - type & MEM_RCU ? "rcu_" : "", - type & PTR_UNTRUSTED ? "untrusted_" : "", - type & PTR_TRUSTED ? "trusted_" : "" - ); - - snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", - prefix, str[base_type(type)], postfix); - return env->type_str_buf; -} - -static char slot_type_char[] = { - [STACK_INVALID] = '?', - [STACK_SPILL] = 'r', - [STACK_MISC] = 'm', - [STACK_ZERO] = '0', - [STACK_DYNPTR] = 'd', -}; - -static void print_liveness(struct bpf_verifier_env *env, - enum bpf_reg_liveness live) +static bool is_atomic_load_insn(const struct bpf_insn *insn) { - if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) - verbose(env, "_"); - if (live & REG_LIVE_READ) - verbose(env, "r"); - if (live & REG_LIVE_WRITTEN) - verbose(env, "w"); - if (live & REG_LIVE_DONE) - verbose(env, "D"); + return BPF_CLASS(insn->code) == BPF_STX && + BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_LOAD_ACQ; } -static int get_spi(s32 off) +static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; } -static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots) -{ - int allocated_slots = state->allocated_stack / BPF_REG_SIZE; - - /* We need to check that slots between [spi - nr_slots + 1, spi] are - * within [0, allocated_stack). - * - * Please note that the spi grows downwards. For example, a dynptr - * takes the size of two stack slots; the first slot will be at - * spi and the second slot will be at spi - 1. - */ - return spi - nr_slots + 1 >= 0 && spi < allocated_slots; -} - static struct bpf_func_state *func(struct bpf_verifier_env *env, const struct bpf_reg_state *reg) { @@ -665,47 +621,60 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env, return cur->frame[reg->frameno]; } -static const char *kernel_type_name(const struct btf* btf, u32 id) +static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots) { - return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); -} + int allocated_slots = state->allocated_stack / BPF_REG_SIZE; -static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) -{ - env->scratched_regs |= 1U << regno; + /* We need to check that slots between [spi - nr_slots + 1, spi] are + * within [0, allocated_stack). + * + * Please note that the spi grows downwards. For example, a dynptr + * takes the size of two stack slots; the first slot will be at + * spi and the second slot will be at spi - 1. + */ + return spi - nr_slots + 1 >= 0 && spi < allocated_slots; } -static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) +static int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + const char *obj_kind, int nr_slots) { - env->scratched_stack_slots |= 1ULL << spi; -} + int off, spi; -static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) -{ - return (env->scratched_regs >> regno) & 1; -} + if (!tnum_is_const(reg->var_off)) { + verbose(env, "%s has to be at a constant offset\n", obj_kind); + return -EINVAL; + } -static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) -{ - return (env->scratched_stack_slots >> regno) & 1; + off = reg->off + reg->var_off.value; + if (off % BPF_REG_SIZE) { + verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); + return -EINVAL; + } + + spi = __get_spi(off); + if (spi + 1 < nr_slots) { + verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); + return -EINVAL; + } + + if (!is_spi_bounds_valid(func(env, reg), spi, nr_slots)) + return -ERANGE; + return spi; } -static bool verifier_state_scratched(const struct bpf_verifier_env *env) +static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - return env->scratched_regs || env->scratched_stack_slots; + return stack_slot_obj_get_spi(env, reg, "dynptr", BPF_DYNPTR_NR_SLOTS); } -static void mark_verifier_state_clean(struct bpf_verifier_env *env) +static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { - env->scratched_regs = 0U; - env->scratched_stack_slots = 0ULL; + return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); } -/* Used for printing the entire verifier state. */ -static void mark_verifier_state_scratched(struct bpf_verifier_env *env) +static int irq_flag_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - env->scratched_regs = ~0U; - env->scratched_stack_slots = ~0ULL; + return stack_slot_obj_get_spi(env, reg, "irq_flag", 1); } static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) @@ -715,49 +684,98 @@ static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) return BPF_DYNPTR_TYPE_LOCAL; case DYNPTR_TYPE_RINGBUF: return BPF_DYNPTR_TYPE_RINGBUF; + case DYNPTR_TYPE_SKB: + return BPF_DYNPTR_TYPE_SKB; + case DYNPTR_TYPE_XDP: + return BPF_DYNPTR_TYPE_XDP; + case DYNPTR_TYPE_SKB_META: + return BPF_DYNPTR_TYPE_SKB_META; + case DYNPTR_TYPE_FILE: + return BPF_DYNPTR_TYPE_FILE; default: return BPF_DYNPTR_TYPE_INVALID; } } +static enum bpf_type_flag get_dynptr_type_flag(enum bpf_dynptr_type type) +{ + switch (type) { + case BPF_DYNPTR_TYPE_LOCAL: + return DYNPTR_TYPE_LOCAL; + case BPF_DYNPTR_TYPE_RINGBUF: + return DYNPTR_TYPE_RINGBUF; + case BPF_DYNPTR_TYPE_SKB: + return DYNPTR_TYPE_SKB; + case BPF_DYNPTR_TYPE_XDP: + return DYNPTR_TYPE_XDP; + case BPF_DYNPTR_TYPE_SKB_META: + return DYNPTR_TYPE_SKB_META; + case BPF_DYNPTR_TYPE_FILE: + return DYNPTR_TYPE_FILE; + default: + return 0; + } +} + static bool dynptr_type_refcounted(enum bpf_dynptr_type type) { - return type == BPF_DYNPTR_TYPE_RINGBUF; + return type == BPF_DYNPTR_TYPE_RINGBUF || type == BPF_DYNPTR_TYPE_FILE; } static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, - bool first_slot); + bool first_slot, int dynptr_id); static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); -static void mark_dynptr_stack_regs(struct bpf_reg_state *sreg1, +static void mark_dynptr_stack_regs(struct bpf_verifier_env *env, + struct bpf_reg_state *sreg1, struct bpf_reg_state *sreg2, enum bpf_dynptr_type type) { - __mark_dynptr_reg(sreg1, type, true); - __mark_dynptr_reg(sreg2, type, false); + int id = ++env->id_gen; + + __mark_dynptr_reg(sreg1, type, true, id); + __mark_dynptr_reg(sreg2, type, false, id); } -static void mark_dynptr_cb_reg(struct bpf_reg_state *reg, +static void mark_dynptr_cb_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, enum bpf_dynptr_type type) { - __mark_dynptr_reg(reg, type, true); + __mark_dynptr_reg(reg, type, true, ++env->id_gen); } +static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, + struct bpf_func_state *state, int spi); static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - enum bpf_arg_type arg_type, int insn_idx) + enum bpf_arg_type arg_type, int insn_idx, int clone_ref_obj_id) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type type; - int spi, i, id; - - spi = get_spi(reg->off); - - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) - return -EINVAL; + int spi, i, err; + + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + + /* We cannot assume both spi and spi - 1 belong to the same dynptr, + * hence we need to call destroy_if_dynptr_stack_slot twice for both, + * to ensure that for the following example: + * [d1][d1][d2][d2] + * spi 3 2 1 0 + * So marking spi = 2 should lead to destruction of both d1 and d2. In + * case they do belong to same dynptr, second call won't see slot_type + * as STACK_DYNPTR and will simply skip destruction. + */ + err = destroy_if_dynptr_stack_slot(env, state, spi); + if (err) + return err; + err = destroy_if_dynptr_stack_slot(env, state, spi - 1); + if (err) + return err; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_DYNPTR; @@ -768,12 +786,18 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (type == BPF_DYNPTR_TYPE_INVALID) return -EINVAL; - mark_dynptr_stack_regs(&state->stack[spi].spilled_ptr, + mark_dynptr_stack_regs(env, &state->stack[spi].spilled_ptr, &state->stack[spi - 1].spilled_ptr, type); if (dynptr_type_refcounted(type)) { /* The id is used to track proper releasing */ - id = acquire_reference_state(env, insn_idx); + int id; + + if (clone_ref_obj_id) + id = clone_ref_obj_id; + else + id = acquire_reference(env, insn_idx); + if (id < 0) return id; @@ -781,67 +805,192 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ state->stack[spi - 1].spilled_ptr.ref_obj_id = id; } + bpf_mark_stack_write(env, state->frameno, BIT(spi - 1) | BIT(spi)); + return 0; } +static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) +{ + int i; + + for (i = 0; i < BPF_REG_SIZE; i++) { + state->stack[spi].slot_type[i] = STACK_INVALID; + state->stack[spi - 1].slot_type[i] = STACK_INVALID; + } + + __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); + __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); + + bpf_mark_stack_write(env, state->frameno, BIT(spi - 1) | BIT(spi)); +} + static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi, i; + int spi, ref_obj_id, i; + + /* + * This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot + * be released by any dynptr helper. Hence, unmark_stack_slots_dynptr + * is safe to do directly. + */ + if (reg->type == CONST_PTR_TO_DYNPTR) { + verifier_bug(env, "CONST_PTR_TO_DYNPTR cannot be released"); + return -EFAULT; + } + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + + if (!dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { + invalidate_dynptr(env, state, spi); + return 0; + } + + ref_obj_id = state->stack[spi].spilled_ptr.ref_obj_id; + + /* If the dynptr has a ref_obj_id, then we need to invalidate + * two things: + * + * 1) Any dynptrs with a matching ref_obj_id (clones) + * 2) Any slices derived from this dynptr. + */ + + /* Invalidate any slices associated with this dynptr */ + WARN_ON_ONCE(release_reference(env, ref_obj_id)); + + /* Invalidate any dynptr clones */ + for (i = 1; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].spilled_ptr.ref_obj_id != ref_obj_id) + continue; + + /* it should always be the case that if the ref obj id + * matches then the stack slot also belongs to a + * dynptr + */ + if (state->stack[i].slot_type[0] != STACK_DYNPTR) { + verifier_bug(env, "misconfigured ref_obj_id"); + return -EFAULT; + } + if (state->stack[i].spilled_ptr.dynptr.first_slot) + invalidate_dynptr(env, state, i); + } + + return 0; +} + +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); + +static void mark_reg_invalid(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + if (!env->allow_ptr_leaks) + __mark_reg_not_init(env, reg); + else + __mark_reg_unknown(env, reg); +} - spi = get_spi(reg->off); +static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, + struct bpf_func_state *state, int spi) +{ + struct bpf_func_state *fstate; + struct bpf_reg_state *dreg; + int i, dynptr_id; - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) + /* We always ensure that STACK_DYNPTR is never set partially, + * hence just checking for slot_type[0] is enough. This is + * different for STACK_SPILL, where it may be only set for + * 1 byte, so code has to use is_spilled_reg. + */ + if (state->stack[spi].slot_type[0] != STACK_DYNPTR) + return 0; + + /* Reposition spi to first slot */ + if (!state->stack[spi].spilled_ptr.dynptr.first_slot) + spi = spi + 1; + + if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { + verbose(env, "cannot overwrite referenced dynptr\n"); return -EINVAL; + } + mark_stack_slot_scratched(env, spi); + mark_stack_slot_scratched(env, spi - 1); + + /* Writing partially to one dynptr stack slot destroys both. */ for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; state->stack[spi - 1].slot_type[i] = STACK_INVALID; } + dynptr_id = state->stack[spi].spilled_ptr.id; /* Invalidate any slices associated with this dynptr */ - if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) - WARN_ON_ONCE(release_reference(env, state->stack[spi].spilled_ptr.ref_obj_id)); + bpf_for_each_reg_in_vstate(env->cur_state, fstate, dreg, ({ + /* Dynptr slices are only PTR_TO_MEM_OR_NULL and PTR_TO_MEM */ + if (dreg->type != (PTR_TO_MEM | PTR_MAYBE_NULL) && dreg->type != PTR_TO_MEM) + continue; + if (dreg->dynptr_id == dynptr_id) + mark_reg_invalid(env, dreg); + })); + /* Do not release reference state, we are destroying dynptr on stack, + * not using some helper to release it. Just reset register. + */ __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); + + bpf_mark_stack_write(env, state->frameno, BIT(spi - 1) | BIT(spi)); + return 0; } static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - struct bpf_func_state *state = func(env, reg); - int spi, i; + int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return false; - spi = get_spi(reg->off); - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) - return true; + spi = dynptr_get_spi(env, reg); - for (i = 0; i < BPF_REG_SIZE; i++) { - if (state->stack[spi].slot_type[i] == STACK_DYNPTR || - state->stack[spi - 1].slot_type[i] == STACK_DYNPTR) - return false; - } + /* -ERANGE (i.e. spi not falling into allocated stack slots) isn't an + * error because this just means the stack state hasn't been updated yet. + * We will do check_mem_access to check and update stack bounds later. + */ + if (spi < 0 && spi != -ERANGE) + return false; + /* We don't need to check if the stack slots are marked by previous + * dynptr initializations because we allow overwriting existing unreferenced + * STACK_DYNPTR slots, see mark_stack_slots_dynptr which calls + * destroy_if_dynptr_stack_slot to ensure dynptr objects at the slots we are + * touching are completely destructed before we reinitialize them for a new + * one. For referenced ones, destroy_if_dynptr_stack_slot returns an error early + * instead of delaying it until the end where the user will get "Unreleased + * reference" error. + */ return true; } static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi; - int i; + int i, spi; - /* This already represents first slot of initialized bpf_dynptr */ + /* This already represents first slot of initialized bpf_dynptr. + * + * CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to + * check_func_arg_reg_off's logic, so we don't need to check its + * offset and alignment. + */ if (reg->type == CONST_PTR_TO_DYNPTR) return true; - spi = get_spi(reg->off); - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || - !state->stack[spi].spilled_ptr.dynptr.first_slot) + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return false; + if (!state->stack[spi].spilled_ptr.dynptr.first_slot) return false; for (i = 0; i < BPF_REG_SIZE; i++) { @@ -868,181 +1017,355 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg if (reg->type == CONST_PTR_TO_DYNPTR) { return reg->dynptr.type == dynptr_type; } else { - spi = get_spi(reg->off); + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return false; return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; } } -/* The reg state of a pointer or a bounded scalar was saved when - * it was spilled to the stack. - */ -static bool is_spilled_reg(const struct bpf_stack_state *stack) +static void __mark_reg_known_zero(struct bpf_reg_state *reg); + +static bool in_rcu_cs(struct bpf_verifier_env *env); + +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta); + +static int mark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, + struct bpf_reg_state *reg, int insn_idx, + struct btf *btf, u32 btf_id, int nr_slots) { - return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; + struct bpf_func_state *state = func(env, reg); + int spi, i, j, id; + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return spi; + + id = acquire_reference(env, insn_idx); + if (id < 0) + return id; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + struct bpf_reg_state *st = &slot->spilled_ptr; + + __mark_reg_known_zero(st); + st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + if (is_kfunc_rcu_protected(meta)) { + if (in_rcu_cs(env)) + st->type |= MEM_RCU; + else + st->type |= PTR_UNTRUSTED; + } + st->ref_obj_id = i == 0 ? id : 0; + st->iter.btf = btf; + st->iter.btf_id = btf_id; + st->iter.state = BPF_ITER_STATE_ACTIVE; + st->iter.depth = 0; + + for (j = 0; j < BPF_REG_SIZE; j++) + slot->slot_type[j] = STACK_ITER; + + bpf_mark_stack_write(env, state->frameno, BIT(spi - i)); + mark_stack_slot_scratched(env, spi - i); + } + + return 0; } -static void scrub_spilled_slot(u8 *stype) +static int unmark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int nr_slots) { - if (*stype != STACK_INVALID) - *stype = STACK_MISC; + struct bpf_func_state *state = func(env, reg); + int spi, i, j; + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return spi; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + struct bpf_reg_state *st = &slot->spilled_ptr; + + if (i == 0) + WARN_ON_ONCE(release_reference(env, st->ref_obj_id)); + + __mark_reg_not_init(env, st); + + for (j = 0; j < BPF_REG_SIZE; j++) + slot->slot_type[j] = STACK_INVALID; + + bpf_mark_stack_write(env, state->frameno, BIT(spi - i)); + mark_stack_slot_scratched(env, spi - i); + } + + return 0; } -static void print_verifier_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state, - bool print_all) +static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int nr_slots) { - const struct bpf_reg_state *reg; - enum bpf_reg_type t; - int i; + struct bpf_func_state *state = func(env, reg); + int spi, i, j; - if (state->frameno) - verbose(env, " frame%d:", state->frameno); - for (i = 0; i < MAX_BPF_REG; i++) { - reg = &state->regs[i]; - t = reg->type; - if (t == NOT_INIT) - continue; - if (!print_all && !reg_scratched(env, i)) - continue; - verbose(env, " R%d", i); - print_liveness(env, reg->live); - verbose(env, "="); - if (t == SCALAR_VALUE && reg->precise) - verbose(env, "P"); - if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && - tnum_is_const(reg->var_off)) { - /* reg->off should be 0 for SCALAR_VALUE */ - verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t)); - verbose(env, "%lld", reg->var_off.value + reg->off); - } else { - const char *sep = ""; + /* For -ERANGE (i.e. spi not falling into allocated stack slots), we + * will do check_mem_access to check and update stack bounds later, so + * return true for that case. + */ + spi = iter_get_spi(env, reg, nr_slots); + if (spi == -ERANGE) + return true; + if (spi < 0) + return false; - verbose(env, "%s", reg_type_str(env, t)); - if (base_type(t) == PTR_TO_BTF_ID) - verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); - verbose(env, "("); -/* - * _a stands for append, was shortened to avoid multiline statements below. - * This macro is used to output a comma separated list of attributes. - */ -#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; }) - - if (reg->id) - verbose_a("id=%d", reg->id); - if (reg->ref_obj_id) - verbose_a("ref_obj_id=%d", reg->ref_obj_id); - if (t != SCALAR_VALUE) - verbose_a("off=%d", reg->off); - if (type_is_pkt_pointer(t)) - verbose_a("r=%d", reg->range); - else if (base_type(t) == CONST_PTR_TO_MAP || - base_type(t) == PTR_TO_MAP_KEY || - base_type(t) == PTR_TO_MAP_VALUE) - verbose_a("ks=%d,vs=%d", - reg->map_ptr->key_size, - reg->map_ptr->value_size); - if (tnum_is_const(reg->var_off)) { - /* Typically an immediate SCALAR_VALUE, but - * could be a pointer whose offset is too big - * for reg->off - */ - verbose_a("imm=%llx", reg->var_off.value); - } else { - if (reg->smin_value != reg->umin_value && - reg->smin_value != S64_MIN) - verbose_a("smin=%lld", (long long)reg->smin_value); - if (reg->smax_value != reg->umax_value && - reg->smax_value != S64_MAX) - verbose_a("smax=%lld", (long long)reg->smax_value); - if (reg->umin_value != 0) - verbose_a("umin=%llu", (unsigned long long)reg->umin_value); - if (reg->umax_value != U64_MAX) - verbose_a("umax=%llu", (unsigned long long)reg->umax_value); - if (!tnum_is_unknown(reg->var_off)) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose_a("var_off=%s", tn_buf); - } - if (reg->s32_min_value != reg->smin_value && - reg->s32_min_value != S32_MIN) - verbose_a("s32_min=%d", (int)(reg->s32_min_value)); - if (reg->s32_max_value != reg->smax_value && - reg->s32_max_value != S32_MAX) - verbose_a("s32_max=%d", (int)(reg->s32_max_value)); - if (reg->u32_min_value != reg->umin_value && - reg->u32_min_value != U32_MIN) - verbose_a("u32_min=%d", (int)(reg->u32_min_value)); - if (reg->u32_max_value != reg->umax_value && - reg->u32_max_value != U32_MAX) - verbose_a("u32_max=%d", (int)(reg->u32_max_value)); - } -#undef verbose_a + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; - verbose(env, ")"); - } + for (j = 0; j < BPF_REG_SIZE; j++) + if (slot->slot_type[j] == STACK_ITER) + return false; } - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - char types_buf[BPF_REG_SIZE + 1]; - bool valid = false; - int j; - for (j = 0; j < BPF_REG_SIZE; j++) { - if (state->stack[i].slot_type[j] != STACK_INVALID) - valid = true; - types_buf[j] = slot_type_char[ - state->stack[i].slot_type[j]]; - } - types_buf[BPF_REG_SIZE] = 0; - if (!valid) - continue; - if (!print_all && !stack_slot_scratched(env, i)) - continue; - verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); - print_liveness(env, state->stack[i].spilled_ptr.live); - if (is_spilled_reg(&state->stack[i])) { - reg = &state->stack[i].spilled_ptr; - t = reg->type; - verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t)); - if (t == SCALAR_VALUE && reg->precise) - verbose(env, "P"); - if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) - verbose(env, "%lld", reg->var_off.value + reg->off); - } else { - verbose(env, "=%s", types_buf); - } + return true; +} + +static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + struct btf *btf, u32 btf_id, int nr_slots) +{ + struct bpf_func_state *state = func(env, reg); + int spi, i, j; + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return -EINVAL; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + struct bpf_reg_state *st = &slot->spilled_ptr; + + if (st->type & PTR_UNTRUSTED) + return -EPROTO; + /* only main (first) slot has ref_obj_id set */ + if (i == 0 && !st->ref_obj_id) + return -EINVAL; + if (i != 0 && st->ref_obj_id) + return -EINVAL; + if (st->iter.btf != btf || st->iter.btf_id != btf_id) + return -EINVAL; + + for (j = 0; j < BPF_REG_SIZE; j++) + if (slot->slot_type[j] != STACK_ITER) + return -EINVAL; + } + + return 0; +} + +static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx); +static int release_irq_state(struct bpf_verifier_state *state, int id); + +static int mark_stack_slot_irq_flag(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, + struct bpf_reg_state *reg, int insn_idx, + int kfunc_class) +{ + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + struct bpf_reg_state *st; + int spi, i, id; + + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return spi; + + id = acquire_irq_state(env, insn_idx); + if (id < 0) + return id; + + slot = &state->stack[spi]; + st = &slot->spilled_ptr; + + bpf_mark_stack_write(env, reg->frameno, BIT(spi)); + __mark_reg_known_zero(st); + st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + st->ref_obj_id = id; + st->irq.kfunc_class = kfunc_class; + + for (i = 0; i < BPF_REG_SIZE; i++) + slot->slot_type[i] = STACK_IRQ_FLAG; + + mark_stack_slot_scratched(env, spi); + return 0; +} + +static int unmark_stack_slot_irq_flag(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int kfunc_class) +{ + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + struct bpf_reg_state *st; + int spi, i, err; + + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return spi; + + slot = &state->stack[spi]; + st = &slot->spilled_ptr; + + if (st->irq.kfunc_class != kfunc_class) { + const char *flag_kfunc = st->irq.kfunc_class == IRQ_NATIVE_KFUNC ? "native" : "lock"; + const char *used_kfunc = kfunc_class == IRQ_NATIVE_KFUNC ? "native" : "lock"; + + verbose(env, "irq flag acquired by %s kfuncs cannot be restored with %s kfuncs\n", + flag_kfunc, used_kfunc); + return -EINVAL; } - if (state->acquired_refs && state->refs[0].id) { - verbose(env, " refs=%d", state->refs[0].id); - for (i = 1; i < state->acquired_refs; i++) - if (state->refs[i].id) - verbose(env, ",%d", state->refs[i].id); + + err = release_irq_state(env->cur_state, st->ref_obj_id); + WARN_ON_ONCE(err && err != -EACCES); + if (err) { + int insn_idx = 0; + + for (int i = 0; i < env->cur_state->acquired_refs; i++) { + if (env->cur_state->refs[i].id == env->cur_state->active_irq_id) { + insn_idx = env->cur_state->refs[i].insn_idx; + break; + } + } + + verbose(env, "cannot restore irq state out of order, expected id=%d acquired at insn_idx=%d\n", + env->cur_state->active_irq_id, insn_idx); + return err; } - if (state->in_callback_fn) - verbose(env, " cb"); - if (state->in_async_callback_fn) - verbose(env, " async_cb"); - verbose(env, "\n"); - mark_verifier_state_clean(env); + + __mark_reg_not_init(env, st); + + bpf_mark_stack_write(env, reg->frameno, BIT(spi)); + + for (i = 0; i < BPF_REG_SIZE; i++) + slot->slot_type[i] = STACK_INVALID; + + mark_stack_slot_scratched(env, spi); + return 0; } -static inline u32 vlog_alignment(u32 pos) +static bool is_irq_flag_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), - BPF_LOG_MIN_ALIGNMENT) - pos - 1; + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + int spi, i; + + /* For -ERANGE (i.e. spi not falling into allocated stack slots), we + * will do check_mem_access to check and update stack bounds later, so + * return true for that case. + */ + spi = irq_flag_get_spi(env, reg); + if (spi == -ERANGE) + return true; + if (spi < 0) + return false; + + slot = &state->stack[spi]; + + for (i = 0; i < BPF_REG_SIZE; i++) + if (slot->slot_type[i] == STACK_IRQ_FLAG) + return false; + return true; } -static void print_insn_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state) +static int is_irq_flag_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - if (env->prev_log_len && env->prev_log_len == env->log.len_used) { - /* remove new line character */ - bpf_vlog_reset(&env->log, env->prev_log_len - 1); - verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' '); - } else { - verbose(env, "%d:", env->insn_idx); + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + struct bpf_reg_state *st; + int spi, i; + + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return -EINVAL; + + slot = &state->stack[spi]; + st = &slot->spilled_ptr; + + if (!st->ref_obj_id) + return -EINVAL; + + for (i = 0; i < BPF_REG_SIZE; i++) + if (slot->slot_type[i] != STACK_IRQ_FLAG) + return -EINVAL; + return 0; +} + +/* Check if given stack slot is "special": + * - spilled register state (STACK_SPILL); + * - dynptr state (STACK_DYNPTR); + * - iter state (STACK_ITER). + * - irq flag state (STACK_IRQ_FLAG) + */ +static bool is_stack_slot_special(const struct bpf_stack_state *stack) +{ + enum bpf_stack_slot_type type = stack->slot_type[BPF_REG_SIZE - 1]; + + switch (type) { + case STACK_SPILL: + case STACK_DYNPTR: + case STACK_ITER: + case STACK_IRQ_FLAG: + return true; + case STACK_INVALID: + case STACK_MISC: + case STACK_ZERO: + return false; + default: + WARN_ONCE(1, "unknown stack slot type %d\n", type); + return true; } - print_verifier_state(env, state, false); +} + +/* The reg state of a pointer or a bounded scalar was saved when + * it was spilled to the stack. + */ +static bool is_spilled_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; +} + +static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL && + stack->spilled_ptr.type == SCALAR_VALUE; +} + +static bool is_spilled_scalar_reg64(const struct bpf_stack_state *stack) +{ + return stack->slot_type[0] == STACK_SPILL && + stack->spilled_ptr.type == SCALAR_VALUE; +} + +/* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which + * case they are equivalent, or it's STACK_ZERO, in which case we preserve + * more precise STACK_ZERO. + * Regardless of allow_ptr_leaks setting (i.e., privileged or unprivileged + * mode), we won't promote STACK_INVALID to STACK_MISC. In privileged case it is + * unnecessary as both are considered equivalent when loading data and pruning, + * in case of unprivileged mode it will be incorrect to allow reads of invalid + * slots. + */ +static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype) +{ + if (*stype == STACK_ZERO) + return; + if (*stype == STACK_INVALID) + return; + *stype = STACK_MISC; +} + +static void scrub_spilled_slot(u8 *stype) +{ + if (*stype != STACK_INVALID) + *stype = STACK_MISC; } /* copy array src of length n * size bytes to dst. dst is reallocated if it's too @@ -1090,7 +1413,7 @@ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) goto out; alloc_size = kmalloc_size_roundup(size_mul(new_n, size)); - new_arr = krealloc(arr, alloc_size, GFP_KERNEL); + new_arr = krealloc(arr, alloc_size, GFP_KERNEL_ACCOUNT); if (!new_arr) { kfree(arr); return NULL; @@ -1104,14 +1427,20 @@ out: return arr ? arr : ZERO_SIZE_PTR; } -static int copy_reference_state(struct bpf_func_state *dst, const struct bpf_func_state *src) +static int copy_reference_state(struct bpf_verifier_state *dst, const struct bpf_verifier_state *src) { dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs, - sizeof(struct bpf_reference_state), GFP_KERNEL); + sizeof(struct bpf_reference_state), GFP_KERNEL_ACCOUNT); if (!dst->refs) return -ENOMEM; dst->acquired_refs = src->acquired_refs; + dst->active_locks = src->active_locks; + dst->active_preempt_locks = src->active_preempt_locks; + dst->active_rcu_locks = src->active_rcu_locks; + dst->active_irq_id = src->active_irq_id; + dst->active_lock_id = src->active_lock_id; + dst->active_lock_ptr = src->active_lock_ptr; return 0; } @@ -1120,7 +1449,7 @@ static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_st size_t n = src->allocated_stack / BPF_REG_SIZE; dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!dst->stack) return -ENOMEM; @@ -1128,7 +1457,7 @@ static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_st return 0; } -static int resize_reference_state(struct bpf_func_state *state, size_t n) +static int resize_reference_state(struct bpf_verifier_state *state, size_t n) { state->refs = realloc_array(state->refs, state->acquired_refs, n, sizeof(struct bpf_reference_state)); @@ -1139,9 +1468,16 @@ static int resize_reference_state(struct bpf_func_state *state, size_t n) return 0; } -static int grow_stack_state(struct bpf_func_state *state, int size) +/* Possibly update state->allocated_stack to be at least size bytes. Also + * possibly update the function's high-water mark in its bpf_subprog_info. + */ +static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size) { - size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE; + size_t old_n = state->allocated_stack / BPF_REG_SIZE, n; + + /* The stack size is always a multiple of BPF_REG_SIZE. */ + size = round_up(size, BPF_REG_SIZE); + n = size / BPF_REG_SIZE; if (old_n >= n) return 0; @@ -1151,6 +1487,11 @@ static int grow_stack_state(struct bpf_func_state *state, int size) return -ENOMEM; state->allocated_stack = size; + + /* update known max for given subprogram */ + if (env->subprog_info[state->subprogno].stack_depth < size) + env->subprog_info[state->subprogno].stack_depth = size; + return 0; } @@ -1159,50 +1500,171 @@ static int grow_stack_state(struct bpf_func_state *state, int size) * On success, returns a valid pointer id to associate with the register * On failure, returns a negative errno. */ -static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) +static struct bpf_reference_state *acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) { - struct bpf_func_state *state = cur_func(env); + struct bpf_verifier_state *state = env->cur_state; int new_ofs = state->acquired_refs; - int id, err; + int err; err = resize_reference_state(state, state->acquired_refs + 1); if (err) - return err; - id = ++env->id_gen; - state->refs[new_ofs].id = id; + return NULL; state->refs[new_ofs].insn_idx = insn_idx; - state->refs[new_ofs].callback_ref = state->in_callback_fn ? state->frameno : 0; - return id; + return &state->refs[new_ofs]; +} + +static int acquire_reference(struct bpf_verifier_env *env, int insn_idx) +{ + struct bpf_reference_state *s; + + s = acquire_reference_state(env, insn_idx); + if (!s) + return -ENOMEM; + s->type = REF_TYPE_PTR; + s->id = ++env->id_gen; + return s->id; +} + +static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum ref_state_type type, + int id, void *ptr) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_reference_state *s; + + s = acquire_reference_state(env, insn_idx); + if (!s) + return -ENOMEM; + s->type = type; + s->id = id; + s->ptr = ptr; + + state->active_locks++; + state->active_lock_id = id; + state->active_lock_ptr = ptr; + return 0; } -/* release function corresponding to acquire_reference_state(). Idempotent. */ -static int release_reference_state(struct bpf_func_state *state, int ptr_id) +static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx) { - int i, last_idx; + struct bpf_verifier_state *state = env->cur_state; + struct bpf_reference_state *s; + + s = acquire_reference_state(env, insn_idx); + if (!s) + return -ENOMEM; + s->type = REF_TYPE_IRQ; + s->id = ++env->id_gen; + state->active_irq_id = s->id; + return s->id; +} + +static void release_reference_state(struct bpf_verifier_state *state, int idx) +{ + int last_idx; + size_t rem; + + /* IRQ state requires the relative ordering of elements remaining the + * same, since it relies on the refs array to behave as a stack, so that + * it can detect out-of-order IRQ restore. Hence use memmove to shift + * the array instead of swapping the final element into the deleted idx. + */ last_idx = state->acquired_refs - 1; + rem = state->acquired_refs - idx - 1; + if (last_idx && idx != last_idx) + memmove(&state->refs[idx], &state->refs[idx + 1], sizeof(*state->refs) * rem); + memset(&state->refs[last_idx], 0, sizeof(*state->refs)); + state->acquired_refs--; + return; +} + +static bool find_reference_state(struct bpf_verifier_state *state, int ptr_id) +{ + int i; + + for (i = 0; i < state->acquired_refs; i++) + if (state->refs[i].id == ptr_id) + return true; + + return false; +} + +static int release_lock_state(struct bpf_verifier_state *state, int type, int id, void *ptr) +{ + void *prev_ptr = NULL; + u32 prev_id = 0; + int i; + for (i = 0; i < state->acquired_refs; i++) { - if (state->refs[i].id == ptr_id) { - /* Cannot release caller references in callbacks */ - if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno) - return -EINVAL; - if (last_idx && i != last_idx) - memcpy(&state->refs[i], &state->refs[last_idx], - sizeof(*state->refs)); - memset(&state->refs[last_idx], 0, sizeof(*state->refs)); - state->acquired_refs--; + if (state->refs[i].type == type && state->refs[i].id == id && + state->refs[i].ptr == ptr) { + release_reference_state(state, i); + state->active_locks--; + /* Reassign active lock (id, ptr). */ + state->active_lock_id = prev_id; + state->active_lock_ptr = prev_ptr; return 0; } + if (state->refs[i].type & REF_TYPE_LOCK_MASK) { + prev_id = state->refs[i].id; + prev_ptr = state->refs[i].ptr; + } } return -EINVAL; } +static int release_irq_state(struct bpf_verifier_state *state, int id) +{ + u32 prev_id = 0; + int i; + + if (id != state->active_irq_id) + return -EACCES; + + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].type != REF_TYPE_IRQ) + continue; + if (state->refs[i].id == id) { + release_reference_state(state, i); + state->active_irq_id = prev_id; + return 0; + } else { + prev_id = state->refs[i].id; + } + } + return -EINVAL; +} + +static struct bpf_reference_state *find_lock_state(struct bpf_verifier_state *state, enum ref_state_type type, + int id, void *ptr) +{ + int i; + + for (i = 0; i < state->acquired_refs; i++) { + struct bpf_reference_state *s = &state->refs[i]; + + if (!(s->type & type)) + continue; + + if (s->id == id && s->ptr == ptr) + return s; + } + return NULL; +} + +static void update_peak_states(struct bpf_verifier_env *env) +{ + u32 cur_states; + + cur_states = env->explored_states_size + env->free_list_size + env->num_backedges; + env->peak_states = max(env->peak_states, cur_states); +} + static void free_func_state(struct bpf_func_state *state) { if (!state) return; - kfree(state->refs); kfree(state->stack); kfree(state); } @@ -1223,23 +1685,50 @@ static void free_verifier_state(struct bpf_verifier_state *state, free_func_state(state->frame[i]); state->frame[i] = NULL; } + kfree(state->refs); clear_jmp_history(state); if (free_self) kfree(state); } +/* struct bpf_verifier_state->parent refers to states + * that are in either of env->{expored_states,free_list}. + * In both cases the state is contained in struct bpf_verifier_state_list. + */ +static struct bpf_verifier_state_list *state_parent_as_list(struct bpf_verifier_state *st) +{ + if (st->parent) + return container_of(st->parent, struct bpf_verifier_state_list, state); + return NULL; +} + +static bool incomplete_read_marks(struct bpf_verifier_env *env, + struct bpf_verifier_state *st); + +/* A state can be freed if it is no longer referenced: + * - is in the env->free_list; + * - has no children states; + */ +static void maybe_free_verifier_state(struct bpf_verifier_env *env, + struct bpf_verifier_state_list *sl) +{ + if (!sl->in_free_list + || sl->state.branches != 0 + || incomplete_read_marks(env, &sl->state)) + return; + list_del(&sl->node); + free_verifier_state(&sl->state, false); + kfree(sl); + env->free_list_size--; +} + /* copy verifier state from src to dst growing dst stack space * when necessary to accommodate larger src stack */ static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { - int err; - - memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); - err = copy_reference_state(dst, src); - if (err) - return err; + memcpy(dst, src, offsetof(struct bpf_func_state, stack)); return copy_stack_state(dst, src); } @@ -1250,30 +1739,38 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, int i, err; dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history, - src->jmp_history_cnt, sizeof(struct bpf_idx_pair), - GFP_USER); + src->jmp_history_cnt, sizeof(*dst_state->jmp_history), + GFP_KERNEL_ACCOUNT); if (!dst_state->jmp_history) return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; - /* if dst has more stack frames then src frame, free them */ + /* if dst has more stack frames then src frame, free them, this is also + * necessary in case of exceptional exits using bpf_throw. + */ for (i = src->curframe + 1; i <= dst_state->curframe; i++) { free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } + err = copy_reference_state(dst_state, src); + if (err) + return err; dst_state->speculative = src->speculative; - dst_state->active_rcu_lock = src->active_rcu_lock; + dst_state->in_sleepable = src->in_sleepable; + dst_state->cleaned = src->cleaned; dst_state->curframe = src->curframe; - dst_state->active_lock.ptr = src->active_lock.ptr; - dst_state->active_lock.id = src->active_lock.id; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; + dst_state->dfs_depth = src->dfs_depth; + dst_state->callback_unroll_depth = src->callback_unroll_depth; + dst_state->may_goto_depth = src->may_goto_depth; + dst_state->equal_state = src->equal_state; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { - dst = kzalloc(sizeof(*dst), GFP_KERNEL); + dst = kzalloc(sizeof(*dst), GFP_KERNEL_ACCOUNT); if (!dst) return -ENOMEM; dst_state->frame[i] = dst; @@ -1285,21 +1782,291 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, return 0; } -static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) +static u32 state_htab_size(struct bpf_verifier_env *env) +{ + return env->prog->len; +} + +static struct list_head *explored_state(struct bpf_verifier_env *env, int idx) +{ + struct bpf_verifier_state *cur = env->cur_state; + struct bpf_func_state *state = cur->frame[cur->curframe]; + + return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; +} + +static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_state *b) +{ + int fr; + + if (a->curframe != b->curframe) + return false; + + for (fr = a->curframe; fr >= 0; fr--) + if (a->frame[fr]->callsite != b->frame[fr]->callsite) + return false; + + return true; +} + +/* Return IP for a given frame in a call stack */ +static u32 frame_insn_idx(struct bpf_verifier_state *st, u32 frame) +{ + return frame == st->curframe + ? st->insn_idx + : st->frame[frame + 1]->callsite; +} + +/* For state @st look for a topmost frame with frame_insn_idx() in some SCC, + * if such frame exists form a corresponding @callchain as an array of + * call sites leading to this frame and SCC id. + * E.g.: + * + * void foo() { A: loop {... SCC#1 ...}; } + * void bar() { B: loop { C: foo(); ... SCC#2 ... } + * D: loop { E: foo(); ... SCC#3 ... } } + * void main() { F: bar(); } + * + * @callchain at (A) would be either (F,SCC#2) or (F,SCC#3) depending + * on @st frame call sites being (F,C,A) or (F,E,A). + */ +static bool compute_scc_callchain(struct bpf_verifier_env *env, + struct bpf_verifier_state *st, + struct bpf_scc_callchain *callchain) +{ + u32 i, scc, insn_idx; + + memset(callchain, 0, sizeof(*callchain)); + for (i = 0; i <= st->curframe; i++) { + insn_idx = frame_insn_idx(st, i); + scc = env->insn_aux_data[insn_idx].scc; + if (scc) { + callchain->scc = scc; + break; + } else if (i < st->curframe) { + callchain->callsites[i] = insn_idx; + } else { + return false; + } + } + return true; +} + +/* Check if bpf_scc_visit instance for @callchain exists. */ +static struct bpf_scc_visit *scc_visit_lookup(struct bpf_verifier_env *env, + struct bpf_scc_callchain *callchain) +{ + struct bpf_scc_info *info = env->scc_info[callchain->scc]; + struct bpf_scc_visit *visits = info->visits; + u32 i; + + if (!info) + return NULL; + for (i = 0; i < info->num_visits; i++) + if (memcmp(callchain, &visits[i].callchain, sizeof(*callchain)) == 0) + return &visits[i]; + return NULL; +} + +/* Allocate a new bpf_scc_visit instance corresponding to @callchain. + * Allocated instances are alive for a duration of the do_check_common() + * call and are freed by free_states(). + */ +static struct bpf_scc_visit *scc_visit_alloc(struct bpf_verifier_env *env, + struct bpf_scc_callchain *callchain) +{ + struct bpf_scc_visit *visit; + struct bpf_scc_info *info; + u32 scc, num_visits; + u64 new_sz; + + scc = callchain->scc; + info = env->scc_info[scc]; + num_visits = info ? info->num_visits : 0; + new_sz = sizeof(*info) + sizeof(struct bpf_scc_visit) * (num_visits + 1); + info = kvrealloc(env->scc_info[scc], new_sz, GFP_KERNEL_ACCOUNT); + if (!info) + return NULL; + env->scc_info[scc] = info; + info->num_visits = num_visits + 1; + visit = &info->visits[num_visits]; + memset(visit, 0, sizeof(*visit)); + memcpy(&visit->callchain, callchain, sizeof(*callchain)); + return visit; +} + +/* Form a string '(callsite#1,callsite#2,...,scc)' in env->tmp_str_buf */ +static char *format_callchain(struct bpf_verifier_env *env, struct bpf_scc_callchain *callchain) +{ + char *buf = env->tmp_str_buf; + int i, delta = 0; + + delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "("); + for (i = 0; i < ARRAY_SIZE(callchain->callsites); i++) { + if (!callchain->callsites[i]) + break; + delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u,", + callchain->callsites[i]); + } + delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u)", callchain->scc); + return env->tmp_str_buf; +} + +/* If callchain for @st exists (@st is in some SCC), ensure that + * bpf_scc_visit instance for this callchain exists. + * If instance does not exist or is empty, assign visit->entry_state to @st. + */ +static int maybe_enter_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st) +{ + struct bpf_scc_callchain *callchain = &env->callchain_buf; + struct bpf_scc_visit *visit; + + if (!compute_scc_callchain(env, st, callchain)) + return 0; + visit = scc_visit_lookup(env, callchain); + visit = visit ?: scc_visit_alloc(env, callchain); + if (!visit) + return -ENOMEM; + if (!visit->entry_state) { + visit->entry_state = st; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "SCC enter %s\n", format_callchain(env, callchain)); + } + return 0; +} + +static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit); + +/* If callchain for @st exists (@st is in some SCC), make it empty: + * - set visit->entry_state to NULL; + * - flush accumulated backedges. + */ +static int maybe_exit_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st) +{ + struct bpf_scc_callchain *callchain = &env->callchain_buf; + struct bpf_scc_visit *visit; + + if (!compute_scc_callchain(env, st, callchain)) + return 0; + visit = scc_visit_lookup(env, callchain); + if (!visit) { + /* + * If path traversal stops inside an SCC, corresponding bpf_scc_visit + * must exist for non-speculative paths. For non-speculative paths + * traversal stops when: + * a. Verification error is found, maybe_exit_scc() is not called. + * b. Top level BPF_EXIT is reached. Top level BPF_EXIT is not a member + * of any SCC. + * c. A checkpoint is reached and matched. Checkpoints are created by + * is_state_visited(), which calls maybe_enter_scc(), which allocates + * bpf_scc_visit instances for checkpoints within SCCs. + * (c) is the only case that can reach this point. + */ + if (!st->speculative) { + verifier_bug(env, "scc exit: no visit info for call chain %s", + format_callchain(env, callchain)); + return -EFAULT; + } + return 0; + } + if (visit->entry_state != st) + return 0; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "SCC exit %s\n", format_callchain(env, callchain)); + visit->entry_state = NULL; + env->num_backedges -= visit->num_backedges; + visit->num_backedges = 0; + update_peak_states(env); + return propagate_backedges(env, visit); +} + +/* Lookup an bpf_scc_visit instance corresponding to @st callchain + * and add @backedge to visit->backedges. @st callchain must exist. + */ +static int add_scc_backedge(struct bpf_verifier_env *env, + struct bpf_verifier_state *st, + struct bpf_scc_backedge *backedge) +{ + struct bpf_scc_callchain *callchain = &env->callchain_buf; + struct bpf_scc_visit *visit; + + if (!compute_scc_callchain(env, st, callchain)) { + verifier_bug(env, "add backedge: no SCC in verification path, insn_idx %d", + st->insn_idx); + return -EFAULT; + } + visit = scc_visit_lookup(env, callchain); + if (!visit) { + verifier_bug(env, "add backedge: no visit info for call chain %s", + format_callchain(env, callchain)); + return -EFAULT; + } + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "SCC backedge %s\n", format_callchain(env, callchain)); + backedge->next = visit->backedges; + visit->backedges = backedge; + visit->num_backedges++; + env->num_backedges++; + update_peak_states(env); + return 0; +} + +/* bpf_reg_state->live marks for registers in a state @st are incomplete, + * if state @st is in some SCC and not all execution paths starting at this + * SCC are fully explored. + */ +static bool incomplete_read_marks(struct bpf_verifier_env *env, + struct bpf_verifier_state *st) +{ + struct bpf_scc_callchain *callchain = &env->callchain_buf; + struct bpf_scc_visit *visit; + + if (!compute_scc_callchain(env, st, callchain)) + return false; + visit = scc_visit_lookup(env, callchain); + if (!visit) + return false; + return !!visit->backedges; +} + +static void free_backedges(struct bpf_scc_visit *visit) +{ + struct bpf_scc_backedge *backedge, *next; + + for (backedge = visit->backedges; backedge; backedge = next) { + free_verifier_state(&backedge->state, false); + next = backedge->next; + kfree(backedge); + } + visit->backedges = NULL; +} + +static int update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { + struct bpf_verifier_state_list *sl = NULL, *parent_sl; + struct bpf_verifier_state *parent; + int err; + while (st) { u32 br = --st->branches; - /* WARN_ON(br > 1) technically makes sense here, + /* verifier_bug_if(br > 1, ...) technically makes sense here, * but see comment in push_stack(), hence: */ - WARN_ONCE((int)br < 0, - "BUG update_branch_counts:branches_to_explore=%d\n", - br); + verifier_bug_if((int)br < 0, env, "%s:branches_to_explore=%d", __func__, br); if (br) break; - st = st->parent; + err = maybe_exit_scc(env, st); + if (err) + return err; + parent = st->parent; + parent_sl = state_parent_as_list(st); + if (sl) + maybe_free_verifier_state(env, sl); + st = parent; + sl = parent_sl; } + return 0; } static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, @@ -1331,6 +2098,18 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, return 0; } +static bool error_recoverable_with_nospec(int err) +{ + /* Should only return true for non-fatal errors that are allowed to + * occur during speculative verification. For these we can insert a + * nospec and the program might still be accepted. Do not include + * something like ENOMEM because it is likely to re-occur for the next + * architectural path once it has been recovered-from in all speculative + * paths. + */ + return err == -EPERM || err == -EACCES || err == -EINVAL; +} + static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, bool speculative) @@ -1339,24 +2118,24 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, struct bpf_verifier_stack_elem *elem; int err; - elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); + elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL_ACCOUNT); if (!elem) - goto err; + return ERR_PTR(-ENOMEM); elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; - elem->log_pos = env->log.len_used; + elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; err = copy_verifier_state(&elem->st, cur); if (err) - goto err; + return ERR_PTR(-ENOMEM); elem->st.speculative |= speculative; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex.\n", env->stack_size); - goto err; + return ERR_PTR(-E2BIG); } if (elem->st.parent) { ++elem->st.parent->branches; @@ -1371,12 +2150,6 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, */ } return &elem->st; -err: - free_verifier_state(env->cur_state, true); - env->cur_state = NULL; - /* pop all elements and return */ - while (!pop_stack(env, NULL, NULL, false)); - return NULL; } #define CALLER_SAVED_REGS 6 @@ -1404,9 +2177,11 @@ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { - /* Clear id, off, and union(map_ptr, range) */ + /* Clear off and union(map_ptr, range) */ memset(((u8 *)reg) + sizeof(reg->type), 0, offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); + reg->id = 0; + reg->ref_obj_id = 0; ___mark_reg_known(reg, imm); } @@ -1427,10 +2202,14 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) __mark_reg_known(reg, 0); } -static void __mark_reg_const_zero(struct bpf_reg_state *reg) +static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); reg->type = SCALAR_VALUE; + /* all scalars are assumed imprecise initially (unless unprivileged, + * in which case everything is forced to be precise) + */ + reg->precise = !env->bpf_capable; } static void mark_reg_known_zero(struct bpf_verifier_env *env, @@ -1447,7 +2226,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, } static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, - bool first_slot) + bool first_slot, int dynptr_id) { /* reg->type has no meaning for STACK_DYNPTR, but when we set reg for * callback arguments, it does need to be CONST_PTR_TO_DYNPTR, so simply @@ -1455,6 +2234,8 @@ static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type ty */ __mark_reg_known_zero(reg); reg->type = CONST_PTR_TO_DYNPTR; + /* Give each dynptr a unique id to uniquely associate slices to it. */ + reg->id = dynptr_id; reg->dynptr.type = type; reg->dynptr.first_slot = first_slot; } @@ -1470,8 +2251,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - if (btf_record_has_field(map->inner_map_meta->record, BPF_TIMER)) + if (btf_record_has_field(map->inner_map_meta->record, + BPF_TIMER | BPF_WORKQUEUE | BPF_TASK_WORK)) { 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 || @@ -1486,6 +2269,16 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) reg->type &= ~PTR_MAYBE_NULL; } +static void mark_reg_graph_node(struct bpf_reg_state *regs, u32 regno, + struct btf_field_graph_root *ds_head) +{ + __mark_reg_known_zero(®s[regno]); + regs[regno].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[regno].btf = ds_head->btf; + regs[regno].btf_id = ds_head->value_btf_id; + regs[regno].off = ds_head->node_offset; +} + static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) { return type_is_pkt_pointer(reg->type); @@ -1497,6 +2290,13 @@ static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) reg->type == PTR_TO_PACKET_END; } +static bool reg_is_dynptr_slice_pkt(const struct bpf_reg_state *reg) +{ + return base_type(reg->type) == PTR_TO_MEM && + (reg->type & + (DYNPTR_TYPE_SKB | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META)); +} + /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, enum bpf_reg_type which) @@ -1578,69 +2378,290 @@ static void __update_reg_bounds(struct bpf_reg_state *reg) /* Uses signed min/max values to inform unsigned, and vice-versa */ static void __reg32_deduce_bounds(struct bpf_reg_state *reg) { - /* Learn sign from signed bounds. - * If we cannot cross the sign boundary, then signed and unsigned bounds - * are the same, so combine. This works even in the negative case, e.g. - * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. + /* If upper 32 bits of u64/s64 range don't change, we can use lower 32 + * bits to improve our u32/s32 boundaries. + * + * E.g., the case where we have upper 32 bits as zero ([10, 20] in + * u64) is pretty trivial, it's obvious that in u32 we'll also have + * [10, 20] range. But this property holds for any 64-bit range as + * long as upper 32 bits in that entire range of values stay the same. + * + * E.g., u64 range [0x10000000A, 0x10000000F] ([4294967306, 4294967311] + * in decimal) has the same upper 32 bits throughout all the values in + * that range. As such, lower 32 bits form a valid [0xA, 0xF] ([10, 15]) + * range. + * + * Note also, that [0xA, 0xF] is a valid range both in u32 and in s32, + * following the rules outlined below about u64/s64 correspondence + * (which equally applies to u32 vs s32 correspondence). In general it + * depends on actual hexadecimal values of 32-bit range. They can form + * only valid u32, or only valid s32 ranges in some cases. + * + * So we use all these insights to derive bounds for subregisters here. */ - if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) { - reg->s32_min_value = reg->u32_min_value = - max_t(u32, reg->s32_min_value, reg->u32_min_value); - reg->s32_max_value = reg->u32_max_value = - min_t(u32, reg->s32_max_value, reg->u32_max_value); - return; + if ((reg->umin_value >> 32) == (reg->umax_value >> 32)) { + /* u64 to u32 casting preserves validity of low 32 bits as + * a range, if upper 32 bits are the same + */ + reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->umin_value); + reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->umax_value); + + if ((s32)reg->umin_value <= (s32)reg->umax_value) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); + } + } + if ((reg->smin_value >> 32) == (reg->smax_value >> 32)) { + /* low 32 bits should form a proper u32 range */ + if ((u32)reg->smin_value <= (u32)reg->smax_value) { + reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->smin_value); + reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->smax_value); + } + /* low 32 bits should form a proper s32 range */ + if ((s32)reg->smin_value <= (s32)reg->smax_value) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); + } + } + /* Special case where upper bits form a small sequence of two + * sequential numbers (in 32-bit unsigned space, so 0xffffffff to + * 0x00000000 is also valid), while lower bits form a proper s32 range + * going from negative numbers to positive numbers. E.g., let's say we + * have s64 range [-1, 1] ([0xffffffffffffffff, 0x0000000000000001]). + * Possible s64 values are {-1, 0, 1} ({0xffffffffffffffff, + * 0x0000000000000000, 0x00000000000001}). Ignoring upper 32 bits, + * we still get a valid s32 range [-1, 1] ([0xffffffff, 0x00000001]). + * Note that it doesn't have to be 0xffffffff going to 0x00000000 in + * upper 32 bits. As a random example, s64 range + * [0xfffffff0fffffff0; 0xfffffff100000010], forms a valid s32 range + * [-16, 16] ([0xfffffff0; 0x00000010]) in its 32 bit subregister. + */ + if ((u32)(reg->umin_value >> 32) + 1 == (u32)(reg->umax_value >> 32) && + (s32)reg->umin_value < 0 && (s32)reg->umax_value >= 0) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); + } + if ((u32)(reg->smin_value >> 32) + 1 == (u32)(reg->smax_value >> 32) && + (s32)reg->smin_value < 0 && (s32)reg->smax_value >= 0) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); + } + /* if u32 range forms a valid s32 range (due to matching sign bit), + * try to learn from that + */ + if ((s32)reg->u32_min_value <= (s32)reg->u32_max_value) { + reg->s32_min_value = max_t(s32, reg->s32_min_value, reg->u32_min_value); + reg->s32_max_value = min_t(s32, reg->s32_max_value, reg->u32_max_value); } - /* Learn sign from unsigned bounds. Signed bounds cross the sign - * boundary, so we must be careful. + /* If we cannot cross the sign boundary, then signed and unsigned bounds + * are the same, so combine. This works even in the negative case, e.g. + * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ - if ((s32)reg->u32_max_value >= 0) { - /* Positive. We can't learn anything from the smin, but smax - * is positive, hence safe. - */ - reg->s32_min_value = reg->u32_min_value; - reg->s32_max_value = reg->u32_max_value = - min_t(u32, reg->s32_max_value, reg->u32_max_value); - } else if ((s32)reg->u32_min_value < 0) { - /* Negative. We can't learn anything from the smax, but smin - * is negative, hence safe. - */ - reg->s32_min_value = reg->u32_min_value = - max_t(u32, reg->s32_min_value, reg->u32_min_value); - reg->s32_max_value = reg->u32_max_value; + if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { + reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); + reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); } } static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { - /* Learn sign from signed bounds. - * If we cannot cross the sign boundary, then signed and unsigned bounds + /* If u64 range forms a valid s64 range (due to matching sign bit), + * try to learn from that. Let's do a bit of ASCII art to see when + * this is happening. Let's take u64 range first: + * + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * + * Valid u64 range is formed when umin and umax are anywhere in the + * range [0, U64_MAX], and umin <= umax. u64 case is simple and + * straightforward. Let's see how s64 range maps onto the same range + * of values, annotated below the line for comparison: + * + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * 0 S64_MAX S64_MIN -1 + * + * So s64 values basically start in the middle and they are logically + * contiguous to the right of it, wrapping around from -1 to 0, and + * then finishing as S64_MAX (0x7fffffffffffffff) right before + * S64_MIN. We can try drawing the continuity of u64 vs s64 values + * more visually as mapped to sign-agnostic range of hex values. + * + * u64 start u64 end + * _______________________________________________________________ + * / \ + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * 0 S64_MAX S64_MIN -1 + * / \ + * >------------------------------ -------------------------------> + * s64 continues... s64 end s64 start s64 "midpoint" + * + * What this means is that, in general, we can't always derive + * something new about u64 from any random s64 range, and vice versa. + * + * But we can do that in two particular cases. One is when entire + * u64/s64 range is *entirely* contained within left half of the above + * diagram or when it is *entirely* contained in the right half. I.e.: + * + * |-------------------------------|--------------------------------| + * ^ ^ ^ ^ + * A B C D + * + * [A, B] and [C, D] are contained entirely in their respective halves + * and form valid contiguous ranges as both u64 and s64 values. [A, B] + * will be non-negative both as u64 and s64 (and in fact it will be + * identical ranges no matter the signedness). [C, D] treated as s64 + * will be a range of negative values, while in u64 it will be + * non-negative range of values larger than 0x8000000000000000. + * + * Now, any other range here can't be represented in both u64 and s64 + * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid + * contiguous u64 ranges, but they are discontinuous in s64. [B, C] + * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX], + * for example. Similarly, valid s64 range [D, A] (going from negative + * to positive values), would be two separate [D, U64_MAX] and [0, A] + * ranges as u64. Currently reg_state can't represent two segments per + * numeric domain, so in such situations we can only derive maximal + * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64). + * + * So we use these facts to derive umin/umax from smin/smax and vice + * versa only if they stay within the same "half". This is equivalent + * to checking sign bit: lower half will have sign bit as zero, upper + * half have sign bit 1. Below in code we simplify this by just + * casting umin/umax as smin/smax and checking if they form valid + * range, and vice versa. Those are equivalent checks. + */ + if ((s64)reg->umin_value <= (s64)reg->umax_value) { + reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value); + reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value); + } + /* If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ - if (reg->smin_value >= 0 || reg->smax_value < 0) { - reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, - reg->umin_value); - reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, - reg->umax_value); - return; + if ((u64)reg->smin_value <= (u64)reg->smax_value) { + reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); + reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); + } else { + /* If the s64 range crosses the sign boundary, then it's split + * between the beginning and end of the U64 domain. In that + * case, we can derive new bounds if the u64 range overlaps + * with only one end of the s64 range. + * + * In the following example, the u64 range overlaps only with + * positive portion of the s64 range. + * + * 0 U64_MAX + * | [xxxxxxxxxxxxxx u64 range xxxxxxxxxxxxxx] | + * |----------------------------|----------------------------| + * |xxxxx s64 range xxxxxxxxx] [xxxxxxx| + * 0 S64_MAX S64_MIN -1 + * + * We can thus derive the following new s64 and u64 ranges. + * + * 0 U64_MAX + * | [xxxxxx u64 range xxxxx] | + * |----------------------------|----------------------------| + * | [xxxxxx s64 range xxxxx] | + * 0 S64_MAX S64_MIN -1 + * + * If they overlap in two places, we can't derive anything + * because reg_state can't represent two ranges per numeric + * domain. + * + * 0 U64_MAX + * | [xxxxxxxxxxxxxxxxx u64 range xxxxxxxxxxxxxxxxx] | + * |----------------------------|----------------------------| + * |xxxxx s64 range xxxxxxxxx] [xxxxxxxxxx| + * 0 S64_MAX S64_MIN -1 + * + * The first condition below corresponds to the first diagram + * above. + */ + if (reg->umax_value < (u64)reg->smin_value) { + reg->smin_value = (s64)reg->umin_value; + reg->umax_value = min_t(u64, reg->umax_value, reg->smax_value); + } else if ((u64)reg->smax_value < reg->umin_value) { + /* This second condition considers the case where the u64 range + * overlaps with the negative portion of the s64 range: + * + * 0 U64_MAX + * | [xxxxxxxxxxxxxx u64 range xxxxxxxxxxxxxx] | + * |----------------------------|----------------------------| + * |xxxxxxxxx] [xxxxxxxxxxxx s64 range | + * 0 S64_MAX S64_MIN -1 + */ + reg->smax_value = (s64)reg->umax_value; + reg->umin_value = max_t(u64, reg->umin_value, reg->smin_value); + } } - /* Learn sign from unsigned bounds. Signed bounds cross the sign - * boundary, so we must be careful. +} + +static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg) +{ + /* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit + * values on both sides of 64-bit range in hope to have 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 + * (0x100000000 -> 0x100000001) and 0x7fffffff as low 32-bits of + * _high_ 64-bit bound (0x380000000 -> 0x37fffffff) and arrive at a + * better overall bounds for r1 as [0x1'000000001; 0x3'7fffffff]. + * We just need to make sure that derived bounds we are intersecting + * with are well-formed ranges in respective s64 or u64 domain, just + * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments. */ - if ((s64)reg->umax_value >= 0) { - /* Positive. We can't learn anything from the smin, but smax - * is positive, hence safe. - */ - reg->smin_value = reg->umin_value; - reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, - reg->umax_value); - } else if ((s64)reg->umin_value < 0) { - /* Negative. We can't learn anything from the smax, but smin - * is negative, hence safe. - */ - reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, - reg->umin_value); - reg->smax_value = reg->umax_value; + __u64 new_umin, new_umax; + __s64 new_smin, new_smax; + + /* u32 -> u64 tightening, it's always well-formed */ + new_umin = (reg->umin_value & ~0xffffffffULL) | reg->u32_min_value; + new_umax = (reg->umax_value & ~0xffffffffULL) | reg->u32_max_value; + reg->umin_value = max_t(u64, reg->umin_value, new_umin); + reg->umax_value = min_t(u64, reg->umax_value, new_umax); + /* u32 -> s64 tightening, u32 range embedded into s64 preserves range validity */ + new_smin = (reg->smin_value & ~0xffffffffULL) | reg->u32_min_value; + new_smax = (reg->smax_value & ~0xffffffffULL) | reg->u32_max_value; + reg->smin_value = max_t(s64, reg->smin_value, new_smin); + reg->smax_value = min_t(s64, reg->smax_value, new_smax); + + /* Here we would like to handle a special case after sign extending load, + * when upper bits for a 64-bit range are all 1s or all 0s. + * + * Upper bits are all 1s when register is in a range: + * [0xffff_ffff_0000_0000, 0xffff_ffff_ffff_ffff] + * Upper bits are all 0s when register is in a range: + * [0x0000_0000_0000_0000, 0x0000_0000_ffff_ffff] + * Together this forms are continuous range: + * [0xffff_ffff_0000_0000, 0x0000_0000_ffff_ffff] + * + * Now, suppose that register range is in fact tighter: + * [0xffff_ffff_8000_0000, 0x0000_0000_ffff_ffff] (R) + * Also suppose that it's 32-bit range is positive, + * meaning that lower 32-bits of the full 64-bit register + * are in the range: + * [0x0000_0000, 0x7fff_ffff] (W) + * + * If this happens, then any value in a range: + * [0xffff_ffff_0000_0000, 0xffff_ffff_7fff_ffff] + * is smaller than a lowest bound of the range (R): + * 0xffff_ffff_8000_0000 + * which means that upper bits of the full 64-bit register + * can't be all 1s, when lower bits are in range (W). + * + * Note that: + * - 0xffff_ffff_8000_0000 == (s64)S32_MIN + * - 0x0000_0000_7fff_ffff == (s64)S32_MAX + * These relations are used in the conditions below. + */ + if (reg->s32_min_value >= 0 && reg->smin_value >= S32_MIN && reg->smax_value <= S32_MAX) { + reg->smin_value = reg->s32_min_value; + reg->smax_value = reg->s32_max_value; + reg->umin_value = reg->s32_min_value; + reg->umax_value = reg->s32_max_value; + reg->var_off = tnum_intersect(reg->var_off, + tnum_range(reg->smin_value, reg->smax_value)); } } @@ -1648,6 +2669,7 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg) { __reg32_deduce_bounds(reg); __reg64_deduce_bounds(reg); + __reg_deduce_mixed_bounds(reg); } /* Attempts to improve var_off based on unsigned min/max information */ @@ -1656,9 +2678,9 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) struct tnum var64_off = tnum_intersect(reg->var_off, tnum_range(reg->umin_value, reg->umax_value)); - struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off), - tnum_range(reg->u32_min_value, - reg->u32_max_value)); + struct tnum var32_off = tnum_intersect(tnum_subreg(var64_off), + tnum_range(reg->u32_min_value, + reg->u32_max_value)); reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } @@ -1669,6 +2691,8 @@ static void reg_bounds_sync(struct bpf_reg_state *reg) __update_reg_bounds(reg); /* We might have learned something about the sign bit. */ __reg_deduce_bounds(reg); + __reg_deduce_bounds(reg); + __reg_deduce_bounds(reg); /* We might have learned some bits from the bounds. */ __reg_bound_offset(reg); /* Intersecting with the old var_off might have improved our bounds @@ -1678,6 +2702,56 @@ static void reg_bounds_sync(struct bpf_reg_state *reg) __update_reg_bounds(reg); } +static int reg_bounds_sanity_check(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, const char *ctx) +{ + const char *msg; + + if (reg->umin_value > reg->umax_value || + reg->smin_value > reg->smax_value || + reg->u32_min_value > reg->u32_max_value || + reg->s32_min_value > reg->s32_max_value) { + msg = "range bounds violation"; + goto out; + } + + if (tnum_is_const(reg->var_off)) { + u64 uval = reg->var_off.value; + s64 sval = (s64)uval; + + if (reg->umin_value != uval || reg->umax_value != uval || + reg->smin_value != sval || reg->smax_value != sval) { + msg = "const tnum out of sync with range bounds"; + goto out; + } + } + + if (tnum_subreg_is_const(reg->var_off)) { + u32 uval32 = tnum_subreg(reg->var_off).value; + s32 sval32 = (s32)uval32; + + if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 || + reg->s32_min_value != sval32 || reg->s32_max_value != sval32) { + msg = "const subreg tnum out of sync with range bounds"; + goto out; + } + } + + return 0; +out: + verifier_bug(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] " + "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)", + ctx, msg, reg->umin_value, reg->umax_value, + reg->smin_value, reg->smax_value, + reg->u32_min_value, reg->u32_max_value, + reg->s32_min_value, reg->s32_max_value, + reg->var_off.value, reg->var_off.mask); + if (env->test_reg_invariants) + return -EFAULT; + __mark_reg_unbounded(reg); + return 0; +} + static bool __reg32_bound_s64(s32 a) { return a >= 0 && a <= S32_MAX; @@ -1702,67 +2776,33 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg) } } -static void __reg_combine_32_into_64(struct bpf_reg_state *reg) -{ - /* special case when 64-bit register has upper 32-bit register - * zeroed. Typically happens after zext or <<32, >>32 sequence - * allowing us to use 32-bit bounds directly, - */ - if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) { - __reg_assign_32_into_64(reg); - } else { - /* Otherwise the best we can do is push lower 32bit known and - * unknown bits into register (var_off set from jmp logic) - * then learn as much as possible from the 64-bit tnum - * known and unknown bits. The previous smin/smax bounds are - * invalid here because of jmp32 compare so mark them unknown - * so they do not impact tnum bounds calculation. - */ - __mark_reg64_unbounded(reg); - } - reg_bounds_sync(reg); -} - -static bool __reg64_bound_s32(s64 a) -{ - return a >= S32_MIN && a <= S32_MAX; -} - -static bool __reg64_bound_u32(u64 a) -{ - return a >= U32_MIN && a <= U32_MAX; -} - -static void __reg_combine_64_into_32(struct bpf_reg_state *reg) -{ - __mark_reg32_unbounded(reg); - if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) { - reg->s32_min_value = (s32)reg->smin_value; - reg->s32_max_value = (s32)reg->smax_value; - } - if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) { - reg->u32_min_value = (u32)reg->umin_value; - reg->u32_max_value = (u32)reg->umax_value; - } - reg_bounds_sync(reg); -} - /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(const struct bpf_verifier_env *env, - struct bpf_reg_state *reg) +static void __mark_reg_unknown_imprecise(struct bpf_reg_state *reg) { /* - * Clear type, id, off, and union(map_ptr, range) and + * Clear type, off, and union(map_ptr, range) and * padding between 'type' and union */ memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; + reg->id = 0; + reg->ref_obj_id = 0; reg->var_off = tnum_unknown; reg->frameno = 0; - reg->precise = !env->bpf_capable; + reg->precise = false; __mark_reg_unbounded(reg); } +/* Mark a register as having a completely unknown (scalar) value, + * initialize .precise as true when not bpf capable. + */ +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) +{ + __mark_reg_unknown_imprecise(reg); + reg->precise = !env->bpf_capable; +} + static void mark_reg_unknown(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { @@ -1776,6 +2816,25 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, __mark_reg_unknown(env, regs + regno); } +static int __mark_reg_s32_range(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, + u32 regno, + s32 s32_min, + s32 s32_max) +{ + struct bpf_reg_state *reg = regs + regno; + + reg->s32_min_value = max_t(s32, reg->s32_min_value, s32_min); + reg->s32_max_value = min_t(s32, reg->s32_max_value, s32_max); + + reg->smin_value = max_t(s64, reg->smin_value, s32_min); + reg->smax_value = min_t(s64, reg->smax_value, s32_max); + + reg_bounds_sync(reg); + + return reg_bounds_sanity_check(env, reg, "s32_range"); +} + static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { @@ -1796,20 +2855,33 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, __mark_reg_not_init(env, regs + regno); } -static void mark_btf_ld_reg(struct bpf_verifier_env *env, - struct bpf_reg_state *regs, u32 regno, - enum bpf_reg_type reg_type, - struct btf *btf, u32 btf_id, - enum bpf_type_flag flag) +static int mark_btf_ld_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno, + enum bpf_reg_type reg_type, + struct btf *btf, u32 btf_id, + enum bpf_type_flag flag) { - if (reg_type == SCALAR_VALUE) { + switch (reg_type) { + case SCALAR_VALUE: mark_reg_unknown(env, regs, regno); - return; + return 0; + case PTR_TO_BTF_ID: + mark_reg_known_zero(env, regs, regno); + 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; + return 0; + case PTR_TO_MEM: + mark_reg_known_zero(env, regs, regno); + regs[regno].type = PTR_TO_MEM | flag; + regs[regno].mem_size = 0; + return 0; + default: + verifier_bug(env, "unexpected reg_type %d in %s\n", reg_type, __func__); + return -EFAULT; } - mark_reg_known_zero(env, regs, regno); - regs[regno].type = PTR_TO_BTF_ID | flag; - regs[regno].btf = btf; - regs[regno].btf_id = btf_id; } #define DEF_NOT_SUBREG (0) @@ -1821,8 +2893,6 @@ static void init_reg_state(struct bpf_verifier_env *env, for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); - regs[i].live = REG_LIVE_NONE; - regs[i].parent = NULL; regs[i].subreg_def = DEF_NOT_SUBREG; } @@ -1832,6 +2902,11 @@ static void init_reg_state(struct bpf_verifier_env *env, regs[BPF_REG_FP].frameno = state->frameno; } +static struct bpf_retval_range retval_range(s32 minval, s32 maxval) +{ + return (struct bpf_retval_range){ minval, maxval }; +} + #define BPF_MAIN_FUNC (-1) static void init_func_state(struct bpf_verifier_env *env, struct bpf_func_state *state, @@ -1840,7 +2915,7 @@ static void init_func_state(struct bpf_verifier_env *env, state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; - state->callback_ret_range = tnum_range(0, 0); + state->callback_ret_range = retval_range(0, 0); init_reg_state(env, state); mark_verifier_state_scratched(env); } @@ -1848,26 +2923,26 @@ 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; - elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); + elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL_ACCOUNT); if (!elem) - goto err; + return ERR_PTR(-ENOMEM); elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; - elem->log_pos = env->log.len_used; + elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex for async cb.\n", env->stack_size); - goto err; + return ERR_PTR(-E2BIG); } /* Unlike push_stack() do not copy_verifier_state(). * The caller state doesn't matter. @@ -1875,21 +2950,16 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, * Initialize it similar to do_check_common(). */ elem->st.branches = 1; - frame = kzalloc(sizeof(*frame), GFP_KERNEL); + elem->st.in_sleepable = is_sleepable; + frame = kzalloc(sizeof(*frame), GFP_KERNEL_ACCOUNT); if (!frame) - goto err; + return ERR_PTR(-ENOMEM); init_func_state(env, frame, BPF_MAIN_FUNC /* callsite */, 0 /* frameno within this callchain */, subprog /* subprog number within this prog */); elem->st.frame[0] = frame; return &elem->st; -err: - free_verifier_state(env->cur_state, true); - env->cur_state = NULL; - /* pop all elements and return */ - while (!pop_stack(env, NULL, NULL, false)); - return NULL; } @@ -1905,16 +2975,36 @@ static int cmp_subprogs(const void *a, const void *b) ((struct bpf_subprog_info *)b)->start; } +/* Find subprogram that contains instruction at 'off' */ +struct bpf_subprog_info *bpf_find_containing_subprog(struct bpf_verifier_env *env, int off) +{ + struct bpf_subprog_info *vals = env->subprog_info; + int l, r, m; + + if (off >= env->prog->len || off < 0 || env->subprog_cnt == 0) + return NULL; + + l = 0; + r = env->subprog_cnt - 1; + while (l < r) { + m = l + (r - l + 1) / 2; + if (vals[m].start <= off) + l = m; + else + r = m - 1; + } + return &vals[l]; +} + +/* Find subprogram that starts exactly at 'off' */ static int find_subprog(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *p; - p = bsearch(&off, env->subprog_info, env->subprog_cnt, - sizeof(env->subprog_info[0]), cmp_subprogs); - if (!p) + p = bpf_find_containing_subprog(env, off); + if (!p || p->start != off) return -ENOENT; return p - env->subprog_info; - } static int add_subprog(struct bpf_verifier_env *env, int off) @@ -1940,6 +3030,68 @@ static int add_subprog(struct bpf_verifier_env *env, int off) return env->subprog_cnt - 1; } +static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env) +{ + struct bpf_prog_aux *aux = env->prog->aux; + struct btf *btf = aux->btf; + const struct btf_type *t; + u32 main_btf_id, id; + const char *name; + int ret, i; + + /* Non-zero func_info_cnt implies valid btf */ + if (!aux->func_info_cnt) + return 0; + main_btf_id = aux->func_info[0].type_id; + + t = btf_type_by_id(btf, main_btf_id); + if (!t) { + verbose(env, "invalid btf id for main subprog in func_info\n"); + return -EINVAL; + } + + name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:"); + if (IS_ERR(name)) { + ret = PTR_ERR(name); + /* If there is no tag present, there is no exception callback */ + if (ret == -ENOENT) + ret = 0; + else if (ret == -EEXIST) + verbose(env, "multiple exception callback tags for main subprog\n"); + return ret; + } + + ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC); + if (ret < 0) { + verbose(env, "exception callback '%s' could not be found in BTF\n", name); + return ret; + } + id = ret; + t = btf_type_by_id(btf, id); + if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) { + verbose(env, "exception callback '%s' must have global linkage\n", name); + return -EINVAL; + } + ret = 0; + for (i = 0; i < aux->func_info_cnt; i++) { + if (aux->func_info[i].type_id != id) + continue; + ret = aux->func_info[i].insn_off; + /* Further func_info and subprog checks will also happen + * later, so assume this is the right insn_off for now. + */ + if (!ret) { + verbose(env, "invalid exception callback insn_off in func_info: 0\n"); + ret = -EINVAL; + } + } + if (!ret) { + verbose(env, "exception callback type id not found in func_info\n"); + ret = -EINVAL; + } + return ret; +} + #define MAX_KFUNC_DESCS 256 #define MAX_KFUNC_BTFS 256 @@ -1948,6 +3100,7 @@ struct bpf_kfunc_desc { u32 func_id; s32 imm; u16 offset; + unsigned long addr; }; struct bpf_kfunc_btf { @@ -1957,6 +3110,11 @@ struct bpf_kfunc_btf { }; struct bpf_kfunc_desc_tab { + /* Sorted by func_id (BTF ID) and offset (fd_array offset) during + * verification. JITs do lookups by bpf_insn, where func_id may not be + * available, therefore at the end of verification do_misc_fixups() + * sorts this by imm and offset. + */ struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS]; u32 nr_descs; }; @@ -1966,6 +3124,9 @@ struct bpf_kfunc_btf_tab { u32 nr_descs; }; +static int specialize_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_desc *desc, + int insn_idx); + static int kfunc_desc_cmp_by_id_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; @@ -1983,7 +3144,7 @@ static int kfunc_btf_cmp_by_off(const void *a, const void *b) return d0->offset - d1->offset; } -static const struct bpf_kfunc_desc * +static struct bpf_kfunc_desc * find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) { struct bpf_kfunc_desc desc = { @@ -1997,6 +3158,19 @@ find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off); } +int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, + u16 btf_fd_idx, u8 **func_addr) +{ + const struct bpf_kfunc_desc *desc; + + desc = find_kfunc_desc(prog, func_id, btf_fd_idx); + if (!desc) + return -EFAULT; + + *func_addr = (u8 *)desc->addr; + return 0; +} + static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { @@ -2049,10 +3223,16 @@ static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, b->module = mod; b->offset = offset; + /* sort() reorders entries by value, so b may no longer point + * to the right entry after this + */ sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); + } else { + btf = b->btf; } - return b->btf; + + return btf; } void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) @@ -2087,12 +3267,12 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) { const struct btf_type *func, *func_proto; struct bpf_kfunc_btf_tab *btf_tab; + struct btf_func_model func_model; struct bpf_kfunc_desc_tab *tab; struct bpf_prog_aux *prog_aux; struct bpf_kfunc_desc *desc; const char *func_name; struct btf *desc_btf; - unsigned long call_imm; unsigned long addr; int err; @@ -2120,7 +3300,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) return -EINVAL; } - tab = kzalloc(sizeof(*tab), GFP_KERNEL); + tab = kzalloc(sizeof(*tab), GFP_KERNEL_ACCOUNT); if (!tab) return -ENOMEM; prog_aux->kfunc_tab = tab; @@ -2136,7 +3316,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) return 0; if (!btf_tab && offset) { - btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL); + btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL_ACCOUNT); if (!btf_tab) return -ENOMEM; prog_aux->kfunc_btf_tab = btf_tab; @@ -2177,49 +3357,77 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) return -EINVAL; } - call_imm = BPF_CALL_IMM(addr); - /* Check whether or not the relative offset overflows desc->imm */ - if ((unsigned long)(s32)call_imm != call_imm) { - verbose(env, "address of kernel function %s is out of range\n", - func_name); - return -EINVAL; + if (bpf_dev_bound_kfunc_id(func_id)) { + err = bpf_dev_bound_kfunc_check(&env->log, prog_aux); + if (err) + return err; } + err = btf_distill_func_proto(&env->log, desc_btf, + func_proto, func_name, + &func_model); + if (err) + return err; + desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; - desc->imm = call_imm; desc->offset = offset; - err = btf_distill_func_proto(&env->log, desc_btf, - func_proto, func_name, - &desc->func_model); - if (!err) - sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), - kfunc_desc_cmp_by_id_off, NULL); - return err; + desc->addr = addr; + desc->func_model = func_model; + sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), + kfunc_desc_cmp_by_id_off, NULL); + return 0; } -static int kfunc_desc_cmp_by_imm(const void *a, const void *b) +static int kfunc_desc_cmp_by_imm_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; - if (d0->imm > d1->imm) - return 1; - else if (d0->imm < d1->imm) - return -1; + if (d0->imm != d1->imm) + return d0->imm < d1->imm ? -1 : 1; + if (d0->offset != d1->offset) + return d0->offset < d1->offset ? -1 : 1; return 0; } -static void sort_kfunc_descs_by_imm(struct bpf_prog *prog) +static int set_kfunc_desc_imm(struct bpf_verifier_env *env, struct bpf_kfunc_desc *desc) +{ + unsigned long call_imm; + + if (bpf_jit_supports_far_kfunc_call()) { + call_imm = desc->func_id; + } else { + call_imm = BPF_CALL_IMM(desc->addr); + /* Check whether the relative offset overflows desc->imm */ + if ((unsigned long)(s32)call_imm != call_imm) { + verbose(env, "address of kernel func_id %u is out of range\n", + desc->func_id); + return -EINVAL; + } + } + desc->imm = call_imm; + return 0; +} + +static int sort_kfunc_descs_by_imm_off(struct bpf_verifier_env *env) { struct bpf_kfunc_desc_tab *tab; + int i, err; - tab = prog->aux->kfunc_tab; + tab = env->prog->aux->kfunc_tab; if (!tab) - return; + return 0; + + for (i = 0; i < tab->nr_descs; i++) { + err = set_kfunc_desc_imm(env, &tab->descs[i]); + if (err) + return err; + } sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), - kfunc_desc_cmp_by_imm, NULL); + kfunc_desc_cmp_by_imm_off, NULL); + return 0; } bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) @@ -2233,22 +3441,38 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, { const struct bpf_kfunc_desc desc = { .imm = insn->imm, + .offset = insn->off, }; const struct bpf_kfunc_desc *res; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; res = bsearch(&desc, tab->descs, tab->nr_descs, - sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm); + sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm_off); return res ? &res->func_model : NULL; } +static int add_kfunc_in_insns(struct bpf_verifier_env *env, + struct bpf_insn *insn, int cnt) +{ + int i, ret; + + for (i = 0; i < cnt; i++, insn++) { + if (bpf_pseudo_kfunc_call(insn)) { + ret = add_kfunc_call(env, insn->imm, insn->off); + if (ret < 0) + return ret; + } + } + return 0; +} + static int add_subprog_and_kfunc(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; + int i, ret, insn_cnt = env->prog->len, ex_cb_insn; struct bpf_insn *insn = env->prog->insnsi; - int i, ret, insn_cnt = env->prog->len; /* Add entry function. */ ret = add_subprog(env, 0); @@ -2274,6 +3498,27 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) return ret; } + ret = bpf_find_exception_callback_insn_off(env); + if (ret < 0) + return ret; + ex_cb_insn = ret; + + /* If ex_cb_insn > 0, this means that the main program has a subprog + * marked using BTF decl tag to serve as the exception callback. + */ + if (ex_cb_insn) { + ret = add_subprog(env, ex_cb_insn); + if (ret < 0) + return ret; + for (i = 1; i < env->subprog_cnt; i++) { + if (env->subprog_info[i].start != ex_cb_insn) + continue; + env->exception_callback_subprog = i; + mark_subprog_exc_cb(env, i); + break; + } + } + /* Add a fake 'exit' subprog which could simplify subprog iteration * logic. 'subprog_cnt' should not be increased. */ @@ -2300,17 +3545,23 @@ static int check_subprogs(struct bpf_verifier_env *env) u8 code = insn[i].code; if (code == (BPF_JMP | BPF_CALL) && - insn[i].imm == BPF_FUNC_tail_call && - insn[i].src_reg != BPF_PSEUDO_CALL) + insn[i].src_reg == 0 && + insn[i].imm == BPF_FUNC_tail_call) { subprog[cur_subprog].has_tail_call = true; + subprog[cur_subprog].tail_call_reachable = true; + } if (BPF_CLASS(code) == BPF_LD && (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND)) subprog[cur_subprog].has_ld_abs = true; if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) goto next; - if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) + if (BPF_OP(code) == BPF_CALL) goto next; - off = i + insn[i].off + 1; + if (BPF_OP(code) == BPF_EXIT) { + subprog[cur_subprog].exit_idx = i; + goto next; + } + off = i + bpf_jmp_offset(&insn[i]) + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; @@ -2319,9 +3570,10 @@ next: if (i == subprog_end - 1) { /* to avoid fall-through from one subprog into another * the last insn of the subprog should be either exit - * or unconditional jump back + * or unconditional jump back or bpf_throw call */ if (code != (BPF_JMP | BPF_EXIT) && + code != (BPF_JMP32 | BPF_JA) && code != (BPF_JMP | BPF_JA)) { verbose(env, "last insn is not an exit or jmp\n"); return -EINVAL; @@ -2335,62 +3587,61 @@ next: return 0; } -/* Parentage chain of this register (or stack slot) should take care of all - * issues like callee-saved registers, stack slot allocation time, etc. - */ -static int mark_reg_read(struct bpf_verifier_env *env, - const struct bpf_reg_state *state, - struct bpf_reg_state *parent, u8 flag) +static int mark_stack_slot_obj_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int spi, int nr_slots) { - bool writes = parent == state->parent; /* Observe write marks */ - int cnt = 0; + int err, i; - while (parent) { - /* if read wasn't screened by an earlier write ... */ - if (writes && state->live & REG_LIVE_WRITTEN) - break; - if (parent->live & REG_LIVE_DONE) { - verbose(env, "verifier BUG type %s var_off %lld off %d\n", - reg_type_str(env, parent->type), - parent->var_off.value, parent->off); - return -EFAULT; - } - /* The first condition is more likely to be true than the - * second, checked it first. - */ - if ((parent->live & REG_LIVE_READ) == flag || - parent->live & REG_LIVE_READ64) - /* The parentage chain never changes and - * this parent was already marked as LIVE_READ. - * There is no need to keep walking the chain again and - * keep re-marking all parents as LIVE_READ. - * This case happens when the same register is read - * multiple times without writes into it in-between. - * Also, if parent has the stronger REG_LIVE_READ64 set, - * then no need to set the weak REG_LIVE_READ32. - */ - break; - /* ... then we depend on parent's value */ - parent->live |= flag; - /* REG_LIVE_READ64 overrides REG_LIVE_READ32. */ - if (flag == REG_LIVE_READ64) - parent->live &= ~REG_LIVE_READ32; - state = parent; - parent = state->parent; - writes = true; - cnt++; - } - - if (env->longest_mark_read_walk < cnt) - env->longest_mark_read_walk = cnt; + for (i = 0; i < nr_slots; i++) { + err = bpf_mark_stack_read(env, reg->frameno, env->insn_idx, BIT(spi - i)); + if (err) + return err; + mark_stack_slot_scratched(env, spi - i); + } return 0; } +static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + int spi; + + /* For CONST_PTR_TO_DYNPTR, it must have already been done by + * check_reg_arg in check_helper_call and mark_btf_func_reg_size in + * check_kfunc_call. + */ + if (reg->type == CONST_PTR_TO_DYNPTR) + return 0; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + /* Caller ensures dynptr is valid and initialized, which means spi is in + * bounds and spi is the first dynptr slot. Simply mark stack slot as + * read. + */ + return mark_stack_slot_obj_read(env, reg, spi, BPF_DYNPTR_NR_SLOTS); +} + +static int mark_iter_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int spi, int nr_slots) +{ + return mark_stack_slot_obj_read(env, reg, spi, nr_slots); +} + +static int mark_irq_flag_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + int spi; + + spi = irq_flag_get_spi(env, reg); + if (spi < 0) + return spi; + return mark_stack_slot_obj_read(env, reg, spi, 1); +} + /* This function is supposed to be used by the following 32-bit optimization * code only. It returns TRUE if the source or destination register operates * on 64-bit, otherwise return FALSE. */ -static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, +static bool is_reg64(struct bpf_insn *insn, u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t) { u8 code, class, op; @@ -2422,8 +3673,10 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, } } + if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32)) + return false; + if (class == BPF_ALU64 || class == BPF_JMP || - /* BPF_END always use BPF_ALU class. */ (class == BPF_ALU && op == BPF_END && insn->imm == 64)) return true; @@ -2432,13 +3685,13 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, if (class == BPF_LDX) { if (t != SRC_OP) - return BPF_SIZE(code) == BPF_DW; + return BPF_SIZE(code) == BPF_DW || BPF_MODE(code) == BPF_MEMSX; /* LDX source must be ptr. */ return true; } if (class == BPF_STX) { - /* BPF_STX (including atomic variants) has multiple source + /* BPF_STX (including atomic variants) has one or more source * operands, one of which is a ptr. Check whether the caller is * asking about it. */ @@ -2483,29 +3736,30 @@ static int insn_def_regno(const struct bpf_insn *insn) case BPF_ST: return -1; case BPF_STX: - if (BPF_MODE(insn->code) == BPF_ATOMIC && - (insn->imm & BPF_FETCH)) { + if (BPF_MODE(insn->code) == BPF_ATOMIC || + BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) { if (insn->imm == BPF_CMPXCHG) return BPF_REG_0; - else + else if (insn->imm == BPF_LOAD_ACQ) + return insn->dst_reg; + else if (insn->imm & BPF_FETCH) return insn->src_reg; - } else { - return -1; } + return -1; default: return insn->dst_reg; } } /* Return TRUE if INSN has defined any 32-bit value explicitly. */ -static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn) +static bool insn_has_def32(struct bpf_insn *insn) { int dst_reg = insn_def_regno(insn); if (dst_reg == -1) return false; - return !is_reg64(env, insn, dst_reg, NULL, DST_OP); + return !is_reg64(insn, dst_reg, NULL, DST_OP); } static void mark_insn_zext(struct bpf_verifier_env *env, @@ -2521,13 +3775,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env, reg->subreg_def = DEF_NOT_SUBREG; } -static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, - enum reg_arg_type t) +static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, + enum reg_arg_type t) { - struct bpf_verifier_state *vstate = env->cur_state; - struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; - struct bpf_reg_state *reg, *regs = state->regs; + struct bpf_reg_state *reg; bool rw64; if (regno >= MAX_BPF_REG) { @@ -2538,7 +3790,7 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, mark_reg_scratched(env, regno); reg = ®s[regno]; - rw64 = is_reg64(env, insn, regno, reg, t); + rw64 = is_reg64(insn, regno, reg, t); if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (reg->type == NOT_INIT) { @@ -2552,15 +3804,13 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, if (rw64) mark_insn_zext(env, reg); - return mark_reg_read(env, reg, reg->parent, - rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32); + return 0; } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { verbose(env, "frame pointer is read only\n"); return -EACCES; } - reg->live |= REG_LIVE_WRITTEN; reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1; if (t == DST_OP) mark_reg_unknown(env, regs, regno); @@ -2568,6 +3818,30 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return 0; } +static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, + enum reg_arg_type t) +{ + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + + return __check_reg_arg(env, state->regs, regno, t); +} + +static int insn_stack_access_flags(int frameno, int spi) +{ + return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno; +} + +static int insn_stack_access_spi(int insn_flags) +{ + return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK; +} + +static int insn_stack_access_frameno(int insn_flags) +{ + return insn_flags & INSN_F_FRAMENO_MASK; +} + static void mark_jmp_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].jmp_point = true; @@ -2578,37 +3852,160 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) return env->insn_aux_data[insn_idx].jmp_point; } +#define LR_FRAMENO_BITS 3 +#define LR_SPI_BITS 6 +#define LR_ENTRY_BITS (LR_SPI_BITS + LR_FRAMENO_BITS + 1) +#define LR_SIZE_BITS 4 +#define LR_FRAMENO_MASK ((1ull << LR_FRAMENO_BITS) - 1) +#define LR_SPI_MASK ((1ull << LR_SPI_BITS) - 1) +#define LR_SIZE_MASK ((1ull << LR_SIZE_BITS) - 1) +#define LR_SPI_OFF LR_FRAMENO_BITS +#define LR_IS_REG_OFF (LR_SPI_BITS + LR_FRAMENO_BITS) +#define LINKED_REGS_MAX 6 + +struct linked_reg { + u8 frameno; + union { + u8 spi; + u8 regno; + }; + bool is_reg; +}; + +struct linked_regs { + int cnt; + struct linked_reg entries[LINKED_REGS_MAX]; +}; + +static struct linked_reg *linked_regs_push(struct linked_regs *s) +{ + if (s->cnt < LINKED_REGS_MAX) + return &s->entries[s->cnt++]; + + return NULL; +} + +/* Use u64 as a vector of 6 10-bit values, use first 4-bits to track + * number of elements currently in stack. + * Pack one history entry for linked registers as 10 bits in the following format: + * - 3-bits frameno + * - 6-bits spi_or_reg + * - 1-bit is_reg + */ +static u64 linked_regs_pack(struct linked_regs *s) +{ + u64 val = 0; + int i; + + for (i = 0; i < s->cnt; ++i) { + struct linked_reg *e = &s->entries[i]; + u64 tmp = 0; + + tmp |= e->frameno; + tmp |= e->spi << LR_SPI_OFF; + tmp |= (e->is_reg ? 1 : 0) << LR_IS_REG_OFF; + + val <<= LR_ENTRY_BITS; + val |= tmp; + } + val <<= LR_SIZE_BITS; + val |= s->cnt; + return val; +} + +static void linked_regs_unpack(u64 val, struct linked_regs *s) +{ + int i; + + s->cnt = val & LR_SIZE_MASK; + val >>= LR_SIZE_BITS; + + for (i = 0; i < s->cnt; ++i) { + struct linked_reg *e = &s->entries[i]; + + e->frameno = val & LR_FRAMENO_MASK; + e->spi = (val >> LR_SPI_OFF) & LR_SPI_MASK; + e->is_reg = (val >> LR_IS_REG_OFF) & 0x1; + val >>= LR_ENTRY_BITS; + } +} + /* for any branch, call, exit record the history of jmps in the given state */ -static int push_jmp_history(struct bpf_verifier_env *env, - struct bpf_verifier_state *cur) +static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, + int insn_flags, u64 linked_regs) { u32 cnt = cur->jmp_history_cnt; - struct bpf_idx_pair *p; + struct bpf_jmp_history_entry *p; size_t alloc_size; - if (!is_jmp_point(env, env->insn_idx)) + /* combine instruction flags if we already recorded this instruction */ + if (env->cur_hist_ent) { + /* atomic instructions push insn_flags twice, for READ and + * WRITE sides, but they should agree on stack slot + */ + verifier_bug_if((env->cur_hist_ent->flags & insn_flags) && + (env->cur_hist_ent->flags & insn_flags) != insn_flags, + env, "insn history: insn_idx %d cur flags %x new flags %x", + env->insn_idx, env->cur_hist_ent->flags, insn_flags); + env->cur_hist_ent->flags |= insn_flags; + verifier_bug_if(env->cur_hist_ent->linked_regs != 0, env, + "insn history: insn_idx %d linked_regs: %#llx", + env->insn_idx, env->cur_hist_ent->linked_regs); + env->cur_hist_ent->linked_regs = linked_regs; return 0; + } cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); - p = krealloc(cur->jmp_history, alloc_size, GFP_USER); + p = krealloc(cur->jmp_history, alloc_size, GFP_KERNEL_ACCOUNT); if (!p) return -ENOMEM; - p[cnt - 1].idx = env->insn_idx; - p[cnt - 1].prev_idx = env->prev_insn_idx; cur->jmp_history = p; + + p = &cur->jmp_history[cnt - 1]; + p->idx = env->insn_idx; + p->prev_idx = env->prev_insn_idx; + p->flags = insn_flags; + p->linked_regs = linked_regs; cur->jmp_history_cnt = cnt; + env->cur_hist_ent = p; + return 0; } +static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st, + u32 hist_end, int insn_idx) +{ + if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx) + return &st->jmp_history[hist_end - 1]; + return NULL; +} + /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. + * Return -ENOENT if we exhausted all instructions within given state. + * + * It's legal to have a bit of a looping with the same starting and ending + * insn index within the same state, e.g.: 3->4->5->3, so just because current + * instruction index is the same as state's first_idx doesn't mean we are + * done. If there is still some jump history left, we should keep going. We + * need to take into account that we might have a jump history between given + * state's parent and itself, due to checkpointing. In this case, we'll have + * history entry recording a jump from last instruction of parent state and + * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; + if (i == st->first_insn_idx) { + if (cnt == 0) + return -ENOENT; + if (cnt == 1 && st->jmp_history[0].idx == i) + return -ENOENT; + } + if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; @@ -2634,45 +4031,256 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) return btf_name_by_offset(desc_btf, func->name_off); } -/* For given verifier state backtrack_insn() is called from the last insn to - * the first insn. Its purpose is to compute a bitmask of registers and - * stack slots that needs precision in the parent verifier state. - */ -static int backtrack_insn(struct bpf_verifier_env *env, int idx, - u32 *reg_mask, u64 *stack_mask) +static void verbose_insn(struct bpf_verifier_env *env, struct bpf_insn *insn) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, .cb_print = verbose, .private_data = env, }; + + print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); +} + +static inline void bt_init(struct backtrack_state *bt, u32 frame) +{ + bt->frame = frame; +} + +static inline void bt_reset(struct backtrack_state *bt) +{ + struct bpf_verifier_env *env = bt->env; + + memset(bt, 0, sizeof(*bt)); + bt->env = env; +} + +static inline u32 bt_empty(struct backtrack_state *bt) +{ + u64 mask = 0; + int i; + + for (i = 0; i <= bt->frame; i++) + mask |= bt->reg_masks[i] | bt->stack_masks[i]; + + return mask == 0; +} + +static inline int bt_subprog_enter(struct backtrack_state *bt) +{ + if (bt->frame == MAX_CALL_FRAMES - 1) { + verifier_bug(bt->env, "subprog enter from frame %d", bt->frame); + return -EFAULT; + } + bt->frame++; + return 0; +} + +static inline int bt_subprog_exit(struct backtrack_state *bt) +{ + if (bt->frame == 0) { + verifier_bug(bt->env, "subprog exit from frame 0"); + return -EFAULT; + } + bt->frame--; + return 0; +} + +static inline void bt_set_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) +{ + bt->reg_masks[frame] |= 1 << reg; +} + +static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) +{ + bt->reg_masks[frame] &= ~(1 << reg); +} + +static inline void bt_set_reg(struct backtrack_state *bt, u32 reg) +{ + bt_set_frame_reg(bt, bt->frame, reg); +} + +static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg) +{ + bt_clear_frame_reg(bt, bt->frame, reg); +} + +static inline void bt_set_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) +{ + bt->stack_masks[frame] |= 1ull << slot; +} + +static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) +{ + bt->stack_masks[frame] &= ~(1ull << slot); +} + +static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) +{ + return bt->reg_masks[frame]; +} + +static inline u32 bt_reg_mask(struct backtrack_state *bt) +{ + return bt->reg_masks[bt->frame]; +} + +static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame) +{ + return bt->stack_masks[frame]; +} + +static inline u64 bt_stack_mask(struct backtrack_state *bt) +{ + return bt->stack_masks[bt->frame]; +} + +static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) +{ + return bt->reg_masks[bt->frame] & (1 << reg); +} + +static inline bool bt_is_frame_reg_set(struct backtrack_state *bt, u32 frame, u32 reg) +{ + return bt->reg_masks[frame] & (1 << reg); +} + +static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot) +{ + return bt->stack_masks[frame] & (1ull << slot); +} + +/* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ +static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask) +{ + DECLARE_BITMAP(mask, 64); + bool first = true; + int i, n; + + buf[0] = '\0'; + + bitmap_from_u64(mask, reg_mask); + for_each_set_bit(i, mask, 32) { + n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i); + first = false; + buf += n; + buf_sz -= n; + if (buf_sz < 0) + break; + } +} +/* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */ +void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) +{ + DECLARE_BITMAP(mask, 64); + bool first = true; + int i, n; + + buf[0] = '\0'; + + bitmap_from_u64(mask, stack_mask); + for_each_set_bit(i, mask, 64) { + n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8); + first = false; + buf += n; + buf_sz -= n; + if (buf_sz < 0) + break; + } +} + +/* If any register R in hist->linked_regs is marked as precise in bt, + * do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs. + */ +static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist) +{ + struct linked_regs linked_regs; + bool some_precise = false; + int i; + + if (!hist || hist->linked_regs == 0) + return; + + linked_regs_unpack(hist->linked_regs, &linked_regs); + for (i = 0; i < linked_regs.cnt; ++i) { + struct linked_reg *e = &linked_regs.entries[i]; + + if ((e->is_reg && bt_is_frame_reg_set(bt, e->frameno, e->regno)) || + (!e->is_reg && bt_is_frame_slot_set(bt, e->frameno, e->spi))) { + some_precise = true; + break; + } + } + + if (!some_precise) + return; + + for (i = 0; i < linked_regs.cnt; ++i) { + struct linked_reg *e = &linked_regs.entries[i]; + + if (e->is_reg) + bt_set_frame_reg(bt, e->frameno, e->regno); + else + bt_set_frame_slot(bt, e->frameno, e->spi); + } +} + +/* For given verifier state backtrack_insn() is called from the last insn to + * the first insn. Its purpose is to compute a bitmask of registers and + * stack slots that needs precision in the parent verifier state. + * + * @idx is an index of the instruction we are currently processing; + * @subseq_idx is an index of the subsequent instruction that: + * - *would be* executed next, if jump history is viewed in forward order; + * - *was* processed previously during backtracking. + */ +static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, + struct bpf_jmp_history_entry *hist, struct backtrack_state *bt) +{ struct bpf_insn *insn = env->prog->insnsi + idx; u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); - u32 dreg = 1u << insn->dst_reg; - u32 sreg = 1u << insn->src_reg; - u32 spi; + u32 dreg = insn->dst_reg; + u32 sreg = insn->src_reg; + u32 spi, i, fr; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { - verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); + fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt)); + verbose(env, "mark_precise: frame%d: regs=%s ", + bt->frame, env->tmp_str_buf); + bpf_fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt)); + verbose(env, "stack=%s before ", env->tmp_str_buf); verbose(env, "%d: ", idx); - print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); + verbose_insn(env, insn); } + /* If there is a history record that some registers gained range at this insn, + * propagate precision marks to those registers, so that bt_is_reg_set() + * accounts for these registers. + */ + bt_sync_linked_regs(bt, hist); + if (class == BPF_ALU || class == BPF_ALU64) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; - if (opcode == BPF_MOV) { + if (opcode == BPF_END || opcode == BPF_NEG) { + /* sreg is reserved and unused + * dreg still need precision before this insn + */ + return 0; + } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { - /* dreg = sreg + /* dreg = sreg or dreg = (s8, s16, s32)sreg * dreg needs precision after this insn * sreg needs precision before this insn */ - *reg_mask &= ~dreg; - *reg_mask |= sreg; + bt_clear_reg(bt, dreg); + if (sreg != BPF_REG_FP) + bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. @@ -2680,7 +4288,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * as precise=true in this verifier state. * No further markings in parent are necessary */ - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); } } else { if (BPF_SRC(insn->code) == BPF_X) { @@ -2688,15 +4296,16 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * both dreg and sreg need precision * before this insn */ - *reg_mask |= sreg; + if (sreg != BPF_REG_FP) + bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ } - } else if (class == BPF_LDX) { - if (!(*reg_mask & dreg)) + } else if (class == BPF_LDX || is_atomic_load_insn(insn)) { + if (!bt_is_reg_set(bt, dreg)) return 0; - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. @@ -2704,50 +4313,119 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ - if (insn->src_reg != BPF_REG_FP) + if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; - /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ - spi = (-insn->off - 1) / BPF_REG_SIZE; - if (spi >= 64) { - verbose(env, "BUG spi %d\n", spi); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; - } - *stack_mask |= 1ull << spi; + spi = insn_stack_access_spi(hist->flags); + fr = insn_stack_access_frameno(hist->flags); + bt_set_frame_slot(bt, fr, spi); } else if (class == BPF_STX || class == BPF_ST) { - if (*reg_mask & dreg) + if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ return -ENOTSUPP; /* scalars can only be spilled into stack */ - if (insn->dst_reg != BPF_REG_FP) + if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; - spi = (-insn->off - 1) / BPF_REG_SIZE; - if (spi >= 64) { - verbose(env, "BUG spi %d\n", spi); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; - } - if (!(*stack_mask & (1ull << spi))) + spi = insn_stack_access_spi(hist->flags); + fr = insn_stack_access_frameno(hist->flags); + if (!bt_is_frame_slot_set(bt, fr, spi)) return 0; - *stack_mask &= ~(1ull << spi); + bt_clear_frame_slot(bt, fr, spi); if (class == BPF_STX) - *reg_mask |= sreg; + bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { - if (opcode == BPF_CALL) { - if (insn->src_reg == BPF_PSEUDO_CALL) - return -ENOTSUPP; - /* BPF helpers that invoke callback subprogs are - * equivalent to BPF_PSEUDO_CALL above + if (bpf_pseudo_call(insn)) { + int subprog_insn_idx, subprog; + + subprog_insn_idx = idx + insn->imm + 1; + subprog = find_subprog(env, subprog_insn_idx); + if (subprog < 0) + return -EFAULT; + + if (subprog_is_global(env, subprog)) { + /* check that jump history doesn't have any + * extra instructions from subprog; the next + * instruction after call to global subprog + * should be literally next instruction in + * caller program + */ + verifier_bug_if(idx + 1 != subseq_idx, env, + "extra insn from subprog"); + /* r1-r5 are invalidated after subprog call, + * so for global func call it shouldn't be set + * anymore + */ + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { + verifier_bug(env, "global subprog unexpected regs %x", + bt_reg_mask(bt)); + return -EFAULT; + } + /* global subprog always sets R0 */ + bt_clear_reg(bt, BPF_REG_0); + return 0; + } else { + /* static subprog call instruction, which + * means that we are exiting current subprog, + * so only r1-r5 could be still requested as + * precise, r0 and r6-r10 or any stack slot in + * the current frame should be zero by now + */ + if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { + verifier_bug(env, "static subprog unexpected regs %x", + bt_reg_mask(bt)); + return -EFAULT; + } + /* we are now tracking register spills correctly, + * so any instance of leftover slots is a bug + */ + if (bt_stack_mask(bt) != 0) { + verifier_bug(env, + "static subprog leftover stack slots %llx", + bt_stack_mask(bt)); + return -EFAULT; + } + /* propagate r1-r5 to the caller */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) { + if (bt_is_reg_set(bt, i)) { + bt_clear_reg(bt, i); + bt_set_frame_reg(bt, bt->frame - 1, i); + } + } + if (bt_subprog_exit(bt)) + return -EFAULT; + return 0; + } + } else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) { + /* exit from callback subprog to callback-calling helper or + * kfunc call. Use idx/subseq_idx check to discern it from + * straight line code backtracking. + * Unlike the subprog call handling above, we shouldn't + * propagate precision of r1-r5 (if any requested), as they are + * not actually arguments passed directly to callback subprogs */ - if (insn->src_reg == 0 && is_callback_calling_function(insn->imm)) - return -ENOTSUPP; + if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { + verifier_bug(env, "callback unexpected regs %x", + bt_reg_mask(bt)); + return -EFAULT; + } + if (bt_stack_mask(bt) != 0) { + verifier_bug(env, "callback leftover stack slots %llx", + bt_stack_mask(bt)); + return -EFAULT; + } + /* clear r1-r5 in callback subprog's mask */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + bt_clear_reg(bt, i); + if (bt_subprog_exit(bt)) + return -EFAULT; + return 0; + } else if (opcode == BPF_CALL) { /* kfunc with imm==0 is invalid and fixup_kfunc_call will * catch this error later. Make backtracking conservative * with ENOTSUPP. @@ -2755,22 +4433,86 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) return -ENOTSUPP; /* regular helper call sets R0 */ - *reg_mask &= ~1; - if (*reg_mask & 0x3f) { - /* if backtracing was looking for registers R1-R5 + bt_clear_reg(bt, BPF_REG_0); + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { + /* if backtracking was looking for registers R1-R5 * they should have been found already. */ - verbose(env, "BUG regs %x\n", *reg_mask); - WARN_ONCE(1, "verifier backtracking bug"); + verifier_bug(env, "backtracking call unexpected regs %x", + bt_reg_mask(bt)); return -EFAULT; } + if (insn->src_reg == BPF_REG_0 && insn->imm == BPF_FUNC_tail_call + && subseq_idx - idx != 1) { + if (bt_subprog_enter(bt)) + return -EFAULT; + } } else if (opcode == BPF_EXIT) { - return -ENOTSUPP; + bool r0_precise; + + /* Backtracking to a nested function call, 'idx' is a part of + * the inner frame 'subseq_idx' is a part of the outer frame. + * In case of a regular function call, instructions giving + * precision to registers R1-R5 should have been found already. + * In case of a callback, it is ok to have R1-R5 marked for + * backtracking, as these registers are set by the function + * invoking callback. + */ + if (subseq_idx >= 0 && bpf_calls_callback(env, subseq_idx)) + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + bt_clear_reg(bt, i); + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { + verifier_bug(env, "backtracking exit unexpected regs %x", + bt_reg_mask(bt)); + return -EFAULT; + } + + /* BPF_EXIT in subprog or callback always returns + * right after the call instruction, so by checking + * whether the instruction at subseq_idx-1 is subprog + * call or not we can distinguish actual exit from + * *subprog* from exit from *callback*. In the former + * case, we need to propagate r0 precision, if + * necessary. In the former we never do that. + */ + r0_precise = subseq_idx - 1 >= 0 && + bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) && + bt_is_reg_set(bt, BPF_REG_0); + + bt_clear_reg(bt, BPF_REG_0); + if (bt_subprog_enter(bt)) + return -EFAULT; + + if (r0_precise) + bt_set_reg(bt, BPF_REG_0); + /* r6-r9 and stack slots will stay set in caller frame + * bitmasks until we return back from callee(s) + */ + return 0; + } else if (BPF_SRC(insn->code) == BPF_X) { + if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg)) + return 0; + /* dreg <cond> sreg + * Both dreg and sreg need precision before + * this insn. If only sreg was marked precise + * before it would be equally necessary to + * propagate it to dreg. + */ + if (!hist || !(hist->flags & INSN_F_SRC_REG_STACK)) + bt_set_reg(bt, sreg); + if (!hist || !(hist->flags & INSN_F_DST_REG_STACK)) + bt_set_reg(bt, dreg); + } else if (BPF_SRC(insn->code) == BPF_K) { + /* dreg <cond> K + * Only dreg still needs precision before + * this insn, so for the K-based conditional + * there is nothing new to be marked. + */ } } else if (class == BPF_LD) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary @@ -2779,6 +4521,10 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, /* to be analyzed */ return -ENOTSUPP; } + /* Propagate precision marks to linked registers, to account for + * registers marked as precise in this function. + */ + bt_sync_linked_regs(bt, hist); return 0; } @@ -2790,7 +4536,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * . if (scalar cond K|scalar) * . helper_call(.., scalar, ...) where ARG_CONST is expected * backtrack through the verifier states and mark all registers and - * stack slots with spilled constants that these scalar regisers + * stack slots with spilled constants that these scalar registers * should be precise. * . during state pruning two registers (or spilled stack slots) * are equivalent if both are not precise. @@ -2841,6 +4587,11 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_reg_state *reg; int i, j; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n", + st->curframe); + } + /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. * We also skip current state and go straight to first parent state, @@ -2852,17 +4603,25 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "force_precise: frame%d: forcing r%d to be precise\n", + i, j); + } } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n", + i, -(j + 1) * 8); + } } } } @@ -2980,62 +4739,54 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_ * mark_all_scalars_imprecise() to hopefully get more permissive and generic * finalized states which help in short circuiting more future states. */ -static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno, - int spi) +static int __mark_chain_precision(struct bpf_verifier_env *env, + struct bpf_verifier_state *starting_state, + int regno, + bool *changed) { - struct bpf_verifier_state *st = env->cur_state; + struct bpf_verifier_state *st = starting_state; + struct backtrack_state *bt = &env->bt; int first_idx = st->first_insn_idx; - int last_idx = env->insn_idx; + int last_idx = starting_state->insn_idx; + int subseq_idx = -1; struct bpf_func_state *func; + bool tmp, skip_first = true; struct bpf_reg_state *reg; - u32 reg_mask = regno >= 0 ? 1u << regno : 0; - u64 stack_mask = spi >= 0 ? 1ull << spi : 0; - bool skip_first = true; - bool new_marks = false; - int i, err; + int i, fr, err; if (!env->bpf_capable) return 0; + changed = changed ?: &tmp; + /* set frame number from which we are starting to backtrack */ + bt_init(bt, starting_state->curframe); + /* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. */ - func = st->frame[frame]; + func = st->frame[bt->frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { - WARN_ONCE(1, "backtracing misuse"); + verifier_bug(env, "backtracking misuse"); return -EFAULT; } - new_marks = true; - } - - while (spi >= 0) { - if (!is_spilled_reg(&func->stack[spi])) { - stack_mask = 0; - break; - } - reg = &func->stack[spi].spilled_ptr; - if (reg->type != SCALAR_VALUE) { - stack_mask = 0; - break; - } - new_marks = true; - break; + bt_set_reg(bt, regno); } - if (!new_marks) - return 0; - if (!reg_mask && !stack_mask) + if (bt_empty(bt)) return 0; for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; + struct bpf_jmp_history_entry *hist; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", + bt->frame, last_idx, first_idx, subseq_idx); + } if (last_idx < 0) { /* we are at the entry into subprog, which @@ -3046,22 +4797,22 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r if (st->curframe == 0 && st->frame[0]->subprogno > 0 && st->frame[0]->callsite == BPF_MAIN_FUNC && - stack_mask == 0 && (reg_mask & ~0x3e) == 0) { - bitmap_from_u64(mask, reg_mask); + bt_stack_mask(bt) == 0 && + (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) { + bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; - if (reg->type != SCALAR_VALUE) { - reg_mask &= ~(1u << i); - continue; + bt_clear_reg(bt, i); + if (reg->type == SCALAR_VALUE) { + reg->precise = true; + *changed = true; } - reg->precise = true; } return 0; } - verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n", - st->frame[0]->subprogno, reg_mask, stack_mask); - WARN_ONCE(1, "verifier backtracking bug"); + verifier_bug(env, "backtracking func entry subprog %d reg_mask %x stack_mask %llx", + st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt)); return -EFAULT; } @@ -3070,23 +4821,26 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r err = 0; skip_first = false; } else { - err = backtrack_insn(env, i, ®_mask, &stack_mask); + hist = get_jmp_hist_entry(st, history, i); + err = backtrack_insn(env, i, subseq_idx, hist, bt); } if (err == -ENOTSUPP) { - mark_all_scalars_precise(env, st); + mark_all_scalars_precise(env, starting_state); + bt_reset(bt); return 0; } else if (err) { return err; } - if (!reg_mask && !stack_mask) + if (bt_empty(bt)) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. */ return 0; - if (i == first_idx) - break; + subseq_idx = i; i = get_prev_insn_idx(st, i, &history); + if (i == -ENOENT) + break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask @@ -3094,8 +4848,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r * It means the backtracking missed the spot where * particular register was initialized with a constant. */ - verbose(env, "BUG backtracking idx %d\n", i); - WARN_ONCE(1, "verifier backtracking bug"); + verifier_bug(env, "backtracking idx %d", i); return -EFAULT; } } @@ -3103,84 +4856,86 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r if (!st) break; - new_marks = false; - func = st->frame[frame]; - bitmap_from_u64(mask, reg_mask); - for_each_set_bit(i, mask, 32) { - reg = &func->regs[i]; - if (reg->type != SCALAR_VALUE) { - reg_mask &= ~(1u << i); - continue; - } - if (!reg->precise) - new_marks = true; - reg->precise = true; - } - - bitmap_from_u64(mask, stack_mask); - for_each_set_bit(i, mask, 64) { - if (i >= func->allocated_stack / BPF_REG_SIZE) { - /* the sequence of instructions: - * 2: (bf) r3 = r10 - * 3: (7b) *(u64 *)(r3 -8) = r0 - * 4: (79) r4 = *(u64 *)(r10 -8) - * doesn't contain jmps. It's backtracked - * as a single block. - * During backtracking insn 3 is not recognized as - * stack access, so at the end of backtracking - * stack slot fp-8 is still marked in stack_mask. - * However the parent state may not have accessed - * fp-8 and it's "unallocated" stack space. - * In such case fallback to conservative. - */ - mark_all_scalars_precise(env, st); - return 0; + for (fr = bt->frame; fr >= 0; fr--) { + func = st->frame[fr]; + bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr)); + for_each_set_bit(i, mask, 32) { + reg = &func->regs[i]; + if (reg->type != SCALAR_VALUE) { + bt_clear_frame_reg(bt, fr, i); + continue; + } + if (reg->precise) { + bt_clear_frame_reg(bt, fr, i); + } else { + reg->precise = true; + *changed = true; + } } - if (!is_spilled_reg(&func->stack[i])) { - stack_mask &= ~(1ull << i); - continue; + bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); + for_each_set_bit(i, mask, 64) { + if (verifier_bug_if(i >= func->allocated_stack / BPF_REG_SIZE, + env, "stack slot %d, total slots %d", + i, func->allocated_stack / BPF_REG_SIZE)) + return -EFAULT; + + if (!is_spilled_scalar_reg(&func->stack[i])) { + bt_clear_frame_slot(bt, fr, i); + continue; + } + reg = &func->stack[i].spilled_ptr; + if (reg->precise) { + bt_clear_frame_slot(bt, fr, i); + } else { + reg->precise = true; + *changed = true; + } } - reg = &func->stack[i].spilled_ptr; - if (reg->type != SCALAR_VALUE) { - stack_mask &= ~(1ull << i); - continue; + if (env->log.level & BPF_LOG_LEVEL2) { + fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, + bt_frame_reg_mask(bt, fr)); + verbose(env, "mark_precise: frame%d: parent state regs=%s ", + fr, env->tmp_str_buf); + bpf_fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, + bt_frame_stack_mask(bt, fr)); + verbose(env, "stack=%s: ", env->tmp_str_buf); + print_verifier_state(env, st, fr, true); } - if (!reg->precise) - new_marks = true; - reg->precise = true; - } - if (env->log.level & BPF_LOG_LEVEL2) { - verbose(env, "parent %s regs=%x stack=%llx marks:", - new_marks ? "didn't have" : "already had", - reg_mask, stack_mask); - print_verifier_state(env, func, true); } - if (!reg_mask && !stack_mask) - break; - if (!new_marks) - break; + if (bt_empty(bt)) + return 0; + subseq_idx = first_idx; last_idx = st->last_insn_idx; first_idx = st->first_insn_idx; } + + /* if we still have requested precise regs or slots, we missed + * something (e.g., stack access through non-r10 register), so + * fallback to marking all precise + */ + if (!bt_empty(bt)) { + mark_all_scalars_precise(env, starting_state); + bt_reset(bt); + } + return 0; } int mark_chain_precision(struct bpf_verifier_env *env, int regno) { - return __mark_chain_precision(env, env->cur_state->curframe, regno, -1); -} - -static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno) -{ - return __mark_chain_precision(env, frame, regno, -1); + return __mark_chain_precision(env, env->cur_state, regno, NULL); } -static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi) +/* mark_chain_precision_batch() assumes that env->bt is set in the caller to + * desired reg and stack masks across all relevant frames + */ +static int mark_chain_precision_batch(struct bpf_verifier_env *env, + struct bpf_verifier_state *starting_state) { - return __mark_chain_precision(env, frame, -1, spi); + return __mark_chain_precision(env, starting_state, -1, NULL); } static bool is_spillable_regtype(enum bpf_reg_type type) @@ -3203,6 +4958,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_MEM: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: + case PTR_TO_ARENA: return true; default: return false; @@ -3215,23 +4971,17 @@ static bool register_is_null(struct bpf_reg_state *reg) return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); } -static bool register_is_const(struct bpf_reg_state *reg) +/* check if register is a constant scalar value */ +static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32) { - return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off); + return reg->type == SCALAR_VALUE && + tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off); } -static bool __is_scalar_unbounded(struct bpf_reg_state *reg) +/* assuming is_reg_const() is true, return constant value of a register */ +static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32) { - return tnum_is_unknown(reg->var_off) && - reg->smin_value == S64_MIN && reg->smax_value == S64_MAX && - reg->umin_value == 0 && reg->umax_value == U64_MAX && - reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX && - reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX; -} - -static bool register_is_bounded(struct bpf_reg_state *reg) -{ - return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg); + return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value; } static bool __is_pointer_value(bool allow_ptr_leaks, @@ -3243,22 +4993,86 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } -static void save_register_state(struct bpf_func_state *state, +static void assign_scalar_id_before_mov(struct bpf_verifier_env *env, + struct bpf_reg_state *src_reg) +{ + if (src_reg->type != SCALAR_VALUE) + return; + + if (src_reg->id & BPF_ADD_CONST) { + /* + * The verifier is processing rX = rY insn and + * rY->id has special linked register already. + * Cleared it, since multiple rX += const are not supported. + */ + src_reg->id = 0; + src_reg->off = 0; + } + + if (!src_reg->id && !tnum_is_const(src_reg->var_off)) + /* Ensure that src_reg has a valid ID that will be copied to + * dst_reg and then will be used by sync_linked_regs() to + * propagate min/max range. + */ + src_reg->id = ++env->id_gen; +} + +/* Copy src state preserving dst->parent and dst->live fields */ +static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) +{ + *dst = *src; +} + +static void save_register_state(struct bpf_verifier_env *env, + struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; - state->stack[spi].spilled_ptr = *reg; - if (size == BPF_REG_SIZE) - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + copy_register_state(&state->stack[spi].spilled_ptr, reg); for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) state->stack[spi].slot_type[i - 1] = STACK_SPILL; /* size < 8 bytes spill */ for (; i; i--) - scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); + mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]); +} + +static bool is_bpf_st_mem(struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; +} + +static int get_reg_width(struct bpf_reg_state *reg) +{ + return fls64(reg->umax_value); +} + +/* See comment for mark_fastcall_pattern_for_call() */ +static void check_fastcall_stack_contract(struct bpf_verifier_env *env, + struct bpf_func_state *state, int insn_idx, int off) +{ + struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno]; + struct bpf_insn_aux_data *aux = env->insn_aux_data; + int i; + + if (subprog->fastcall_stack_off <= off || aux[insn_idx].fastcall_pattern) + return; + /* access to the region [max_stack_depth .. fastcall_stack_off) + * from something that is not a part of the fastcall pattern, + * disable fastcall rewrites for current subprogram by setting + * fastcall_stack_off to a value smaller than any possible offset. + */ + subprog->fastcall_stack_off = S16_MIN; + /* reset fastcall aux flags within subprogram, + * happens at most once per subprogram + */ + for (i = subprog->start; i < (subprog + 1)->start; ++i) { + aux[i].fastcall_spills_num = 0; + aux[i].fastcall_pattern = 0; + } } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, @@ -3272,17 +5086,16 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; - u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg; + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; + int insn_flags = insn_stack_access_flags(state->frameno, spi); - err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE)); - if (err) - return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ if (!env->allow_ptr_leaks && - state->stack[spi].slot_type[0] == STACK_SPILL && + is_spilled_reg(&state->stack[spi]) && + !is_spilled_scalar_reg(&state->stack[spi]) && size != BPF_REG_SIZE) { verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; @@ -3304,24 +5117,46 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, } if (sanitize) - env->insn_aux_data[insn_idx].sanitize_stack_spill = true; + env->insn_aux_data[insn_idx].nospec_result = true; } + err = destroy_if_dynptr_stack_slot(env, state, spi); + if (err) + return err; + + if (!(off % BPF_REG_SIZE) && size == BPF_REG_SIZE) { + /* only mark the slot as written if all 8 bytes were written + * otherwise read propagation may incorrectly stop too soon + * when stack slots are partially written. + * This heuristic means that read propagation will be + * conservative, since it will add reg_live_read marks + * to stack slots all the way to first state when programs + * writes+reads less than 8 bytes + */ + bpf_mark_stack_write(env, state->frameno, BIT(spi)); + } + + check_fastcall_stack_contract(env, state, insn_idx, off); mark_stack_slot_scratched(env, spi); - if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && - !register_is_null(reg) && env->bpf_capable) { - if (dst_reg != BPF_REG_FP) { - /* The backtracking logic can only recognize explicit - * stack slot address like [fp - 8]. Other spill of - * scalar via different register has to be conservative. - * Backtrack from here and mark all registers as precise - * that contributed into 'reg' being a constant. - */ - err = mark_chain_precision(env, value_regno); - if (err) - return err; - } - save_register_state(state, spi, reg, size); + if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) { + bool reg_value_fits; + + reg_value_fits = get_reg_width(reg) <= BITS_PER_BYTE * size; + /* Make sure that reg had an ID to build a relation on spill. */ + if (reg_value_fits) + assign_scalar_id_before_mov(env, reg); + save_register_state(env, state, spi, reg, size); + /* Break the relation on a narrowing spill. */ + if (!reg_value_fits) + state->stack[spi].spilled_ptr.id = 0; + } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && + env->bpf_capable) { + struct bpf_reg_state *tmp_reg = &env->fake_reg[0]; + + memset(tmp_reg, 0, sizeof(*tmp_reg)); + __mark_reg_known(tmp_reg, insn->imm); + tmp_reg->type = SCALAR_VALUE; + save_register_state(env, state, spi, tmp_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -3333,31 +5168,26 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - save_register_state(state, spi, reg, size); + save_register_state(env, state, spi, reg, size); } else { u8 type = STACK_MISC; /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; - /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ - if (is_spilled_reg(&state->stack[spi])) + /* Mark slots as STACK_MISC if they belonged to spilled ptr/dynptr/iter. */ + if (is_stack_slot_special(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) scrub_spilled_slot(&state->stack[spi].slot_type[i]); - /* only mark the slot as written if all 8 bytes were written - * otherwise read propagation may incorrectly stop too soon - * when stack slots are partially written. - * This heuristic means that read propagation will be - * conservative, since it will add reg_live_read marks - * to stack slots all the way to first state when programs - * writes+reads less than 8 bytes - */ - if (size == BPF_REG_SIZE) - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; - /* when we zero initialize stack slots mark them as such */ - if (reg && register_is_null(reg)) { - /* backtracking doesn't work for STACK_ZERO yet. */ + if ((reg && register_is_null(reg)) || + (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { + /* STACK_ZERO case happened because register spill + * wasn't properly aligned at the stack slot boundary, + * so it's not a register spill anymore; force + * originating register to be precise to make + * STACK_ZERO correct for subsequent states + */ err = mark_chain_precision(env, value_regno); if (err) return err; @@ -3366,9 +5196,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) - state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = - type; + state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; + insn_flags = 0; /* not a register spill */ } + + if (insn_flags) + return push_jmp_history(env, env->cur_state, insn_flags, 0); return 0; } @@ -3401,6 +5234,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, int min_off, max_off; int i, err; struct bpf_reg_state *ptr_reg = NULL, *value_reg = NULL; + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; bool writing_zero = false; /* set if the fact that we're writing a zero is used to let any * stack slots remain STACK_ZERO @@ -3413,14 +5247,20 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, max_off = ptr_reg->smax_value + off + size; if (value_regno >= 0) value_reg = &cur->regs[value_regno]; - if (value_reg && register_is_null(value_reg)) + if ((value_reg && register_is_null(value_reg)) || + (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0)) writing_zero = true; - err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE)); - if (err) - return err; + for (i = min_off; i < max_off; i++) { + int spi; + spi = __get_spi(i); + err = destroy_if_dynptr_stack_slot(env, state, spi); + if (err) + return err; + } + check_fastcall_stack_contract(env, state, insn_idx, min_off); /* Variable offset writes destroy any spilled pointers in range. */ for (i = min_off; i < max_off; i++) { u8 new_type, *stype; @@ -3448,7 +5288,20 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, return -EINVAL; } - /* Erase all spilled pointers. */ + /* If writing_zero and the spi slot contains a spill of value 0, + * maintain the spill type. + */ + if (writing_zero && *stype == STACK_SPILL && + is_spilled_scalar_reg(&state->stack[spi])) { + struct bpf_reg_state *spill_reg = &state->stack[spi].spilled_ptr; + + if (tnum_is_const(spill_reg->var_off) && spill_reg->var_off.value == 0) { + zero_used = true; + continue; + } + } + + /* Erase all other spilled pointers. */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Update the slot type. */ @@ -3503,32 +5356,21 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env, for (i = min_off; i < max_off; i++) { slot = -i - 1; spi = slot / BPF_REG_SIZE; + mark_stack_slot_scratched(env, spi); stype = ptr_state->stack[spi].slot_type; if (stype[slot % BPF_REG_SIZE] != STACK_ZERO) break; zeros++; } if (zeros == max_off - min_off) { - /* any access_size read into register is zero extended, - * so the whole register == const_zero - */ - __mark_reg_const_zero(&state->regs[dst_regno]); - /* backtracking doesn't support STACK_ZERO yet, - * so mark it precise here, so that later - * backtracking can stop here. - * Backtracking may not need this if this register - * doesn't participate in pointer adjustment. - * Forward propagation of precise flag is not - * necessary either. This mark is only to stop - * backtracking. Any register that contributed - * to const 0 was marked precise before spill. + /* Any access_size read into register is zero extended, + * so the whole register == const_zero. */ - state->regs[dst_regno].precise = true; + __mark_reg_const_zero(env, &state->regs[dst_regno]); } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, dst_regno); } - state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } /* Read the stack at 'off' and put the results into the register indicated by @@ -3550,10 +5392,18 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; u8 *stype, type; + int insn_flags = insn_stack_access_flags(reg_state->frameno, spi); + int err; stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; + mark_stack_slot_scratched(env, spi); + check_fastcall_stack_contract(env, state, env->insn_idx, off); + err = bpf_mark_stack_read(env, reg_state->frameno, env->insn_idx, BIT(spi)); + if (err) + return err; + if (is_spilled_reg(®_state->stack[spi])) { u8 spill_size = 1; @@ -3567,43 +5417,66 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, return -EACCES; } - mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno < 0) return 0; - if (!(off % BPF_REG_SIZE) && size == spill_size) { + if (size <= spill_size && + bpf_stack_narrow_access_ok(off, size, spill_size)) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ s32 subreg_def = state->regs[dst_regno].subreg_def; - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; + + /* Break the relation on a narrowing fill. + * coerce_reg_to_size will adjust the boundaries. + */ + if (get_reg_width(reg) > size * BITS_PER_BYTE) + state->regs[dst_regno].id = 0; } else { + int spill_cnt = 0, zero_cnt = 0; + for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; - if (type == STACK_SPILL) + if (type == STACK_SPILL) { + spill_cnt++; continue; + } if (type == STACK_MISC) continue; + if (type == STACK_ZERO) { + zero_cnt++; + continue; + } + if (type == STACK_INVALID && env->allow_uninit_stack) + continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } - mark_reg_unknown(env, state->regs, dst_regno); - } - state->regs[dst_regno].live |= REG_LIVE_WRITTEN; - return 0; - } - if (dst_regno >= 0) { + if (spill_cnt == size && + tnum_is_const(reg->var_off) && reg->var_off.value == 0) { + __mark_reg_const_zero(env, &state->regs[dst_regno]); + /* this IS register fill, so keep insn_flags */ + } else if (zero_cnt == size) { + /* similarly to mark_reg_stack_read(), preserve zeroes */ + __mark_reg_const_zero(env, &state->regs[dst_regno]); + insn_flags = 0; /* not restoring original register state */ + } else { + mark_reg_unknown(env, state->regs, dst_regno); + insn_flags = 0; /* not restoring original register state */ + } + } + } else if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions */ - state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) { /* If dst_regno==-1, the caller is asking us whether * it is acceptable to use this value as a SCALAR_VALUE @@ -3615,7 +5488,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, off); return -EACCES; } - mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; @@ -3623,14 +5495,18 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, continue; if (type == STACK_ZERO) continue; + if (type == STACK_INVALID && env->allow_uninit_stack) + continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } - mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno >= 0) mark_reg_stack_read(env, reg_state, off, off + size, dst_regno); + insn_flags = 0; /* we are not restoring spilled register */ } + if (insn_flags) + return push_jmp_history(env, env->cur_state, insn_flags, 0); return 0; } @@ -3642,7 +5518,7 @@ enum bpf_access_src { static int check_stack_range_initialized(struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, - enum bpf_access_src type, + enum bpf_access_type type, struct bpf_call_arg_meta *meta); static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) @@ -3675,13 +5551,14 @@ static int check_stack_read_var_off(struct bpf_verifier_env *env, /* Note that we pass a NULL meta, so raw access will not be permitted. */ err = check_stack_range_initialized(env, ptr_regno, off, size, - false, ACCESS_DIRECT, NULL); + false, BPF_READ, NULL); if (err) return err; min_off = reg->smin_value + off; max_off = reg->smax_value + off; mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno); + check_fastcall_stack_contract(env, ptr_state, env->insn_idx, min_off); return 0; } @@ -3718,17 +5595,13 @@ static int check_stack_read(struct bpf_verifier_env *env, } /* Variable offset is prohibited for unprivileged mode for simplicity * since it requires corresponding support in Spectre masking for stack - * ALU. See also retrieve_ptr_limit(). + * ALU. See also retrieve_ptr_limit(). The check in + * check_stack_access_for_ptr_arithmetic() called by + * adjust_ptr_min_max_vals() prevents users from creating stack pointers + * with variable offsets, therefore no check is required here. Further, + * just checking it here would be insufficient as speculative stack + * writes could still lead to unsafe speculative behaviour. */ - if (!env->bypass_spec_v1 && var_off) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n", - ptr_regno, tn_buf); - return -EACCES; - } - if (!var_off) { off += reg->var_off.value; err = check_stack_read_fixed_off(env, state, off, size, @@ -3924,8 +5797,8 @@ static int __check_ptr_off_reg(struct bpf_verifier_env *env, return 0; } -int check_ptr_off_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +static int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) { return __check_ptr_off_reg(env, reg, regno, false); } @@ -3934,23 +5807,27 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, struct btf_field *kptr_field, struct bpf_reg_state *reg, u32 regno) { - const char *targ_name = kernel_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); - int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED; + const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); + int perm_flags; const char *reg_name = ""; - /* Only unreferenced case accepts untrusted pointers */ - if (kptr_field->type == BPF_KPTR_UNREF) - perm_flags |= PTR_UNTRUSTED; + if (btf_is_kernel(reg->btf)) { + perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU; + + /* Only unreferenced case accepts untrusted pointers */ + if (kptr_field->type == BPF_KPTR_UNREF) + perm_flags |= PTR_UNTRUSTED; + } else { + perm_flags = PTR_MAYBE_NULL | MEM_ALLOC; + if (kptr_field->type == BPF_KPTR_PERCPU) + perm_flags |= MEM_PERCPU; + } if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags)) goto bad_type; - if (!btf_is_kernel(reg->btf)) { - verbose(env, "R%d must point to kernel BTF\n", regno); - return -EINVAL; - } /* We need to verify reg->type and reg->btf, before accessing reg->btf */ - reg_name = kernel_type_name(reg->btf, reg->btf_id); + reg_name = btf_type_name(reg->btf, reg->btf_id); /* For ref_ptr case, release function check should ensure we get one * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the @@ -3961,7 +5838,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, if (__check_ptr_off_reg(env, reg, regno, true)) return -EACCES; - /* A full type match is needed, as BTF can be vmlinux or module BTF, and + /* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and * we also need to take into account the reg->off. * * We want to support cases like: @@ -3987,7 +5864,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, */ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, kptr_field->kptr.btf, kptr_field->kptr.btf_id, - kptr_field->type == BPF_KPTR_REF)) + kptr_field->type != BPF_KPTR_UNREF)) goto bad_type; return 0; bad_type: @@ -4002,6 +5879,105 @@ bad_type: return -EINVAL; } +static bool in_sleepable(struct bpf_verifier_env *env) +{ + return env->cur_state->in_sleepable; +} + +/* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() + * can dereference RCU protected pointers and result is PTR_TRUSTED. + */ +static bool in_rcu_cs(struct bpf_verifier_env *env) +{ + return env->cur_state->active_rcu_locks || + env->cur_state->active_locks || + !in_sleepable(env); +} + +/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ +BTF_SET_START(rcu_protected_types) +#ifdef CONFIG_NET +BTF_ID(struct, prog_test_ref_kfunc) +#endif +#ifdef CONFIG_CGROUPS +BTF_ID(struct, cgroup) +#endif +#ifdef CONFIG_BPF_JIT +BTF_ID(struct, bpf_cpumask) +#endif +BTF_ID(struct, task_struct) +#ifdef CONFIG_CRYPTO +BTF_ID(struct, bpf_crypto_ctx) +#endif +BTF_SET_END(rcu_protected_types) + +static bool rcu_protected_object(const struct btf *btf, u32 btf_id) +{ + if (!btf_is_kernel(btf)) + return true; + return btf_id_set_contains(&rcu_protected_types, btf_id); +} + +static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field) +{ + struct btf_struct_meta *meta; + + if (btf_is_kernel(kptr_field->kptr.btf)) + return NULL; + + meta = btf_find_struct_meta(kptr_field->kptr.btf, + kptr_field->kptr.btf_id); + + return meta ? meta->record : NULL; +} + +static bool rcu_safe_kptr(const struct btf_field *field) +{ + const struct btf_field_kptr *kptr = &field->kptr; + + return field->type == BPF_KPTR_PERCPU || + (field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id)); +} + +static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field) +{ + struct btf_record *rec; + u32 ret; + + ret = PTR_MAYBE_NULL; + if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) { + ret |= MEM_RCU; + if (kptr_field->type == BPF_KPTR_PERCPU) + ret |= MEM_PERCPU; + else if (!btf_is_kernel(kptr_field->kptr.btf)) + ret |= MEM_ALLOC; + + rec = kptr_pointee_btf_record(kptr_field); + if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE)) + ret |= NON_OWN_REF; + } else { + ret |= PTR_UNTRUSTED; + } + + return ret; +} + +static int mark_uptr_ld_reg(struct bpf_verifier_env *env, u32 regno, + struct btf_field *field) +{ + struct bpf_reg_state *reg; + const struct btf_type *t; + + t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); + mark_reg_known_zero(env, cur_regs(env), regno); + reg = reg_state(env, regno); + reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; + reg->mem_size = t->size; + reg->id = ++env->id_gen; + + return 0; +} + static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, struct btf_field *kptr_field) @@ -4009,6 +5985,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int class = BPF_CLASS(insn->code); struct bpf_reg_state *val_reg; + int ret; /* Things we already checked for in check_map_access and caller: * - Reject cases where variable offset may touch kptr @@ -4025,20 +6002,28 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, /* We only allow loading referenced kptr, since it will be marked as * untrusted, similar to unreferenced kptr. */ - if (class != BPF_LDX && kptr_field->type == BPF_KPTR_REF) { + if (class != BPF_LDX && + (kptr_field->type == BPF_KPTR_REF || kptr_field->type == BPF_KPTR_PERCPU)) { verbose(env, "store to referenced kptr disallowed\n"); return -EACCES; } + if (class != BPF_LDX && kptr_field->type == BPF_UPTR) { + verbose(env, "store to uptr disallowed\n"); + return -EACCES; + } if (class == BPF_LDX) { - val_reg = reg_state(env, value_regno); + if (kptr_field->type == BPF_UPTR) + return mark_uptr_ld_reg(env, value_regno, kptr_field); + /* We can simply mark the value_regno receiving the pointer * value from map as PTR_TO_BTF_ID, with the correct type. */ - mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, - kptr_field->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); - /* For mark_ptr_or_null_reg */ - val_reg->id = ++env->id_gen; + ret = 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)); + if (ret < 0) + return ret; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && @@ -4057,6 +6042,18 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, return 0; } +/* + * Return the size of the memory region accessible from a pointer to map value. + * For INSN_ARRAY maps whole bpf_insn_array->ips array is accessible. + */ +static u32 map_mem_size(const struct bpf_map *map) +{ + if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) + return map->max_entries * sizeof(long); + + return map->value_size; +} + /* check read/write into a map element with possible variable offset */ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed, @@ -4066,11 +6063,11 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; + u32 mem_size = map_mem_size(map); struct btf_record *rec; int err, i; - err = check_mem_region_access(env, regno, off, size, map->value_size, - zero_size_allowed); + err = check_mem_region_access(env, regno, off, size, mem_size, zero_size_allowed); if (err) return err; @@ -4085,26 +6082,32 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * this program. To check that [x1, x2) overlaps with [y1, y2), * it is sufficient to check x1 < y2 && y1 < x2. */ - if (reg->smin_value + off < p + btf_field_type_size(field->type) && + if (reg->smin_value + off < p + field->size && p < reg->umax_value + off + size) { switch (field->type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: + case BPF_UPTR: if (src != ACCESS_DIRECT) { - verbose(env, "kptr cannot be accessed indirectly by helper\n"); + verbose(env, "%s cannot be accessed indirectly by helper\n", + btf_field_type_name(field->type)); return -EACCES; } if (!tnum_is_const(reg->var_off)) { - verbose(env, "kptr access cannot have variable offset\n"); + verbose(env, "%s access cannot have variable offset\n", + btf_field_type_name(field->type)); return -EACCES; } if (p != off + reg->var_off.value) { - verbose(env, "kptr access misaligned expected=%u off=%llu\n", + verbose(env, "%s access misaligned expected=%u off=%llu\n", + btf_field_type_name(field->type), p, off + reg->var_off.value); return -EACCES; } if (size != bpf_size_to_bytes(BPF_DW)) { - verbose(env, "kptr access size must be BPF_DW\n"); + verbose(env, "%s access size must be BPF_DW\n", + btf_field_type_name(field->type)); return -EACCES; } break; @@ -4206,16 +6209,10 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, - enum bpf_access_type t, enum bpf_reg_type *reg_type, - struct btf **btf, u32 *btf_id) + enum bpf_access_type t, struct bpf_insn_access_aux *info) { - struct bpf_insn_access_aux info = { - .reg_type = *reg_type, - .log = &env->log, - }; - if (env->ops->is_valid_access && - env->ops->is_valid_access(off, size, t, env->prog, &info)) { + env->ops->is_valid_access(off, size, t, env->prog, info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -4223,13 +6220,15 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, * will only allow for whole field access and rejects any other * type of narrower access. */ - *reg_type = info.reg_type; - - if (base_type(*reg_type) == PTR_TO_BTF_ID) { - *btf = info.btf; - *btf_id = info.btf_id; + if (base_type(info->reg_type) == PTR_TO_BTF_ID) { + if (info->ref_obj_id && + !find_reference_state(env->cur_state, info->ref_obj_id)) { + verbose(env, "invalid bpf_context access off=%d. Reference may already be released\n", + off); + return -EACCES; + } } else { - env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + env->insn_aux_data[insn_idx].ctx_field_size = info->ctx_field_size; } /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) @@ -4332,12 +6331,53 @@ 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; +} + +/* Return false if @regno contains a pointer whose type isn't supported for + * atomic instruction @insn. + */ +static bool atomic_ptr_type_ok(struct bpf_verifier_env *env, int regno, + struct bpf_insn *insn) +{ + if (is_ctx_reg(env, regno)) + return false; + if (is_pkt_reg(env, regno)) + return false; + if (is_flow_key_reg(env, regno)) + return false; + if (is_sk_reg(env, regno)) + return false; + if (is_arena_reg(env, regno)) + return bpf_jit_supports_insn(insn, true); + + return true; +} + +static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { +#ifdef CONFIG_NET + [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], + [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], +#endif + [CONST_PTR_TO_MAP] = btf_bpf_map_id, +}; + static bool is_trusted_reg(const struct bpf_reg_state *reg) { /* A referenced register is always trusted. */ if (reg->ref_obj_id) return true; + /* Types listed in the reg2btf_ids are always trusted */ + 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 * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the * other type modifiers may be safe, but we elect to take an opt-in @@ -4356,6 +6396,11 @@ static bool is_rcu_reg(const struct bpf_reg_state *reg) return reg->type & MEM_RCU; } +static void clear_trusted_flags(enum bpf_type_flag *flag) +{ + *flag &= ~(BPF_REG_TRUSTED_MODIFIERS | MEM_RCU); +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -4437,6 +6482,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; + if (reg->map_ptr->map_type == BPF_MAP_TYPE_INSN_ARRAY) + strict = true; break; case PTR_TO_CTX: pointer_desc = "context "; @@ -4461,6 +6508,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; + case PTR_TO_ARENA: + return 0; default: break; } @@ -4468,18 +6517,43 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, strict); } -static int update_stack_depth(struct bpf_verifier_env *env, - const struct bpf_func_state *func, - int off) +static enum priv_stack_mode bpf_enable_priv_stack(struct bpf_prog *prog) { - u16 stack = env->subprog_info[func->subprogno].stack_depth; + if (!bpf_jit_supports_private_stack()) + return NO_PRIV_STACK; - if (stack >= -off) - return 0; + /* bpf_prog_check_recur() checks all prog types that use bpf trampoline + * while kprobe/tp/perf_event/raw_tp don't use trampoline hence checked + * explicitly. + */ + switch (prog->type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + return PRIV_STACK_ADAPTIVE; + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + if (prog->aux->priv_stack_requested || bpf_prog_check_recur(prog)) + return PRIV_STACK_ADAPTIVE; + fallthrough; + default: + break; + } - /* update known max for given subprogram */ - env->subprog_info[func->subprogno].stack_depth = -off; - return 0; + return NO_PRIV_STACK; +} + +static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth) +{ + if (env->prog->jit_requested) + return round_up(stack_depth, 16); + + /* round up to 32-bytes, since this is granularity + * of interpreter stack size + */ + return round_up(max_t(u32, stack_depth, 1), 32); } /* starting from main bpf function walk all instructions of the function @@ -4488,16 +6562,20 @@ static int update_stack_depth(struct bpf_verifier_env *env, * Since recursion is prevented by check_cfg() this algorithm * only needs a local stack of MAX_CALL_FRAMES to remember callsites */ -static int check_max_stack_depth(struct bpf_verifier_env *env) +static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx, + bool priv_stack_supported) { - int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; + int depth = 0, frame = 0, i, subprog_end, subprog_depth; bool tail_call_reachable = false; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; int j; + i = subprog[idx].start; + if (!priv_stack_supported) + subprog[idx].priv_stack_mode = NO_PRIV_STACK; process_func: /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack @@ -4524,19 +6602,57 @@ process_func: depth); return -EACCES; } - /* round up to 32-bytes, since this is granularity - * of interpreter stack size - */ - depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); - if (depth > MAX_BPF_STACK) { - verbose(env, "combined stack size of %d calls is %d. Too large\n", - frame + 1, depth); - return -EACCES; + + subprog_depth = round_up_stack_depth(env, subprog[idx].stack_depth); + if (priv_stack_supported) { + /* Request private stack support only if the subprog stack + * depth is no less than BPF_PRIV_STACK_MIN_SIZE. This is to + * avoid jit penalty if the stack usage is small. + */ + if (subprog[idx].priv_stack_mode == PRIV_STACK_UNKNOWN && + subprog_depth >= BPF_PRIV_STACK_MIN_SIZE) + subprog[idx].priv_stack_mode = PRIV_STACK_ADAPTIVE; + } + + if (subprog[idx].priv_stack_mode == PRIV_STACK_ADAPTIVE) { + if (subprog_depth > MAX_BPF_STACK) { + verbose(env, "stack size of subprog %d is %d. Too large\n", + idx, subprog_depth); + return -EACCES; + } + } else { + depth += subprog_depth; + if (depth > MAX_BPF_STACK) { + verbose(env, "combined stack size of %d calls is %d. Too large\n", + frame + 1, depth); + return -EACCES; + } } continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { - int next_insn; + int next_insn, sidx; + + if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) { + bool err = false; + + if (!is_bpf_throw_kfunc(insn + i)) + continue; + if (subprog[idx].is_cb) + err = true; + for (int c = 0; c < frame && !err; c++) { + if (subprog[ret_prog[c]].is_cb) { + err = true; + break; + } + } + if (!err) + continue; + verbose(env, + "bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n", + i, idx); + return -EINVAL; + } if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; @@ -4546,21 +6662,26 @@ continue_func: /* find the callee */ next_insn = i + insn[i].imm + 1; - idx = find_subprog(env, next_insn); - if (idx < 0) { - WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", - next_insn); + sidx = find_subprog(env, next_insn); + if (verifier_bug_if(sidx < 0, env, "callee not found at insn %d", next_insn)) return -EFAULT; - } - if (subprog[idx].is_async_cb) { - if (subprog[idx].has_tail_call) { - verbose(env, "verifier bug. subprog has tail_call and async cb\n"); + if (subprog[sidx].is_async_cb) { + if (subprog[sidx].has_tail_call) { + verifier_bug(env, "subprog has tail_call and async cb"); return -EFAULT; } - /* async callbacks don't increase bpf prog stack size */ - continue; + /* async callbacks don't increase bpf prog stack size unless called directly */ + if (!bpf_pseudo_call(insn + i)) + continue; + if (subprog[sidx].is_exception_cb) { + verbose(env, "insn %d cannot call exception cb directly", i); + return -EINVAL; + } } i = next_insn; + idx = sidx; + if (!priv_stack_supported) + subprog[idx].priv_stack_mode = NO_PRIV_STACK; if (subprog[idx].has_tail_call) tail_call_reachable = true; @@ -4579,8 +6700,13 @@ continue_func: * tail call counter throughout bpf2bpf calls combined with tailcalls */ if (tail_call_reachable) - for (j = 0; j < frame; j++) + for (j = 0; j < frame; j++) { + if (subprog[ret_prog[j]].is_exception_cb) { + verbose(env, "cannot tail call within exception cb\n"); + return -EINVAL; + } subprog[ret_prog[j]].tail_call_reachable = true; + } if (subprog[0].tail_call_reachable) env->prog->aux->tail_call_reachable = true; @@ -4589,13 +6715,58 @@ continue_func: */ if (frame == 0) return 0; - depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); + if (subprog[idx].priv_stack_mode != PRIV_STACK_ADAPTIVE) + depth -= round_up_stack_depth(env, subprog[idx].stack_depth); frame--; i = ret_insn[frame]; idx = ret_prog[frame]; goto continue_func; } +static int check_max_stack_depth(struct bpf_verifier_env *env) +{ + enum priv_stack_mode priv_stack_mode = PRIV_STACK_UNKNOWN; + struct bpf_subprog_info *si = env->subprog_info; + bool priv_stack_supported; + int ret; + + for (int i = 0; i < env->subprog_cnt; i++) { + if (si[i].has_tail_call) { + priv_stack_mode = NO_PRIV_STACK; + break; + } + } + + if (priv_stack_mode == PRIV_STACK_UNKNOWN) + priv_stack_mode = bpf_enable_priv_stack(env->prog); + + /* All async_cb subprogs use normal kernel stack. If a particular + * subprog appears in both main prog and async_cb subtree, that + * subprog will use normal kernel stack to avoid potential nesting. + * The reverse subprog traversal ensures when main prog subtree is + * checked, the subprogs appearing in async_cb subtrees are already + * marked as using normal kernel stack, so stack size checking can + * be done properly. + */ + for (int i = env->subprog_cnt - 1; i >= 0; i--) { + if (!i || si[i].is_async_cb) { + priv_stack_supported = !i && priv_stack_mode == PRIV_STACK_ADAPTIVE; + ret = check_max_stack_depth_subprog(env, i, priv_stack_supported); + if (ret < 0) + return ret; + } + } + + for (int i = 0; i < env->subprog_cnt; i++) { + if (si[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) { + env->prog->aux->jits_use_priv_stack = true; + break; + } + } + + return 0; +} + #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) @@ -4603,11 +6774,8 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, int start = idx + insn->imm + 1, subprog; subprog = find_subprog(env, start); - if (subprog < 0) { - WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", - start); + if (verifier_bug_if(subprog < 0, env, "get stack depth: no program at insn %d", start)) return -EFAULT; - } return env->subprog_info[subprog].stack_depth; } #endif @@ -4704,9 +6872,153 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ - if (size >= 4) + if (size < 4) + __mark_reg32_unbounded(reg); + + reg_bounds_sync(reg); +} + +static void set_sext64_default_val(struct bpf_reg_state *reg, int size) +{ + if (size == 1) { + reg->smin_value = reg->s32_min_value = S8_MIN; + reg->smax_value = reg->s32_max_value = S8_MAX; + } else if (size == 2) { + reg->smin_value = reg->s32_min_value = S16_MIN; + reg->smax_value = reg->s32_max_value = S16_MAX; + } else { + /* size == 4 */ + reg->smin_value = reg->s32_min_value = S32_MIN; + reg->smax_value = reg->s32_max_value = S32_MAX; + } + reg->umin_value = reg->u32_min_value = 0; + reg->umax_value = U64_MAX; + reg->u32_max_value = U32_MAX; + reg->var_off = tnum_unknown; +} + +static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size) +{ + s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval; + u64 top_smax_value, top_smin_value; + u64 num_bits = size * 8; + + if (tnum_is_const(reg->var_off)) { + u64_cval = reg->var_off.value; + if (size == 1) + reg->var_off = tnum_const((s8)u64_cval); + else if (size == 2) + reg->var_off = tnum_const((s16)u64_cval); + else + /* size == 4 */ + reg->var_off = tnum_const((s32)u64_cval); + + u64_cval = reg->var_off.value; + reg->smax_value = reg->smin_value = u64_cval; + reg->umax_value = reg->umin_value = u64_cval; + reg->s32_max_value = reg->s32_min_value = u64_cval; + reg->u32_max_value = reg->u32_min_value = u64_cval; + return; + } + + top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits; + top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits; + + if (top_smax_value != top_smin_value) + goto out; + + /* find the s64_min and s64_min after sign extension */ + if (size == 1) { + init_s64_max = (s8)reg->smax_value; + init_s64_min = (s8)reg->smin_value; + } else if (size == 2) { + init_s64_max = (s16)reg->smax_value; + init_s64_min = (s16)reg->smin_value; + } else { + init_s64_max = (s32)reg->smax_value; + init_s64_min = (s32)reg->smin_value; + } + + s64_max = max(init_s64_max, init_s64_min); + s64_min = min(init_s64_max, init_s64_min); + + /* both of s64_max/s64_min positive or negative */ + if ((s64_max >= 0) == (s64_min >= 0)) { + reg->s32_min_value = reg->smin_value = s64_min; + reg->s32_max_value = reg->smax_value = s64_max; + reg->u32_min_value = reg->umin_value = s64_min; + reg->u32_max_value = reg->umax_value = s64_max; + reg->var_off = tnum_range(s64_min, s64_max); return; - __reg_combine_64_into_32(reg); + } + +out: + set_sext64_default_val(reg, size); +} + +static void set_sext32_default_val(struct bpf_reg_state *reg, int size) +{ + if (size == 1) { + reg->s32_min_value = S8_MIN; + reg->s32_max_value = S8_MAX; + } else { + /* size == 2 */ + reg->s32_min_value = S16_MIN; + reg->s32_max_value = S16_MAX; + } + reg->u32_min_value = 0; + reg->u32_max_value = U32_MAX; + reg->var_off = tnum_subreg(tnum_unknown); +} + +static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size) +{ + s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val; + u32 top_smax_value, top_smin_value; + u32 num_bits = size * 8; + + if (tnum_is_const(reg->var_off)) { + u32_val = reg->var_off.value; + if (size == 1) + reg->var_off = tnum_const((s8)u32_val); + else + reg->var_off = tnum_const((s16)u32_val); + + u32_val = reg->var_off.value; + reg->s32_min_value = reg->s32_max_value = u32_val; + reg->u32_min_value = reg->u32_max_value = u32_val; + return; + } + + top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits; + top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits; + + if (top_smax_value != top_smin_value) + goto out; + + /* find the s32_min and s32_min after sign extension */ + if (size == 1) { + init_s32_max = (s8)reg->s32_max_value; + init_s32_min = (s8)reg->s32_min_value; + } else { + /* size == 2 */ + init_s32_max = (s16)reg->s32_max_value; + init_s32_min = (s16)reg->s32_min_value; + } + s32_max = max(init_s32_max, init_s32_min); + s32_min = min(init_s32_max, init_s32_min); + + if ((s32_min >= 0) == (s32_max >= 0)) { + reg->s32_min_value = s32_min; + reg->s32_max_value = s32_max; + reg->u32_min_value = (u32)s32_min; + reg->u32_max_value = (u32)s32_max; + reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max)); + return; + } + +out: + set_sext32_default_val(reg, size); } static bool bpf_map_is_rdonly(const struct bpf_map *map) @@ -4729,7 +7041,8 @@ static bool bpf_map_is_rdonly(const struct bpf_map *map) !bpf_map_write_active(map); } -static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) +static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, + bool is_ldsx) { void *ptr; u64 addr; @@ -4742,13 +7055,13 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) switch (size) { case sizeof(u8): - *val = (u64)*(u8 *)ptr; + *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr; break; case sizeof(u16): - *val = (u64)*(u16 *)ptr; + *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr; break; case sizeof(u32): - *val = (u64)*(u32 *)ptr; + *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr; break; case sizeof(u64): *val = *(u64 *)ptr; @@ -4759,6 +7072,135 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) return 0; } +#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. + * This logic doesn't allow mix tagging and will be removed once GCC supports + * btf_type_tag. + */ + +/* RCU trusted: these fields are trusted in RCU CS and never NULL */ +BTF_TYPE_SAFE_RCU(struct task_struct) { + const cpumask_t *cpus_ptr; + struct css_set __rcu *cgroups; + struct task_struct __rcu *real_parent; + struct task_struct *group_leader; +}; + +BTF_TYPE_SAFE_RCU(struct cgroup) { + /* cgrp->kn is always accessible as documented in kernel/cgroup/cgroup.c */ + struct kernfs_node *kn; +}; + +BTF_TYPE_SAFE_RCU(struct css_set) { + struct cgroup *dfl_cgrp; +}; + +BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state) { + struct cgroup *cgroup; +}; + +/* RCU trusted: these fields are trusted in RCU CS and can be NULL */ +BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct) { + struct file __rcu *exe_file; +#ifdef CONFIG_MEMCG + struct task_struct __rcu *owner; +#endif +}; + +/* skb->sk, req->sk are not RCU protected, but we mark them as such + * because bpf prog accessible sockets are SOCK_RCU_FREE. + */ +BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff) { + struct sock *sk; +}; + +BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock) { + struct sock *sk; +}; + +/* full trusted: these fields are trusted even outside of RCU CS and never NULL */ +BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta) { + struct seq_file *seq; +}; + +BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task) { + struct bpf_iter_meta *meta; + struct task_struct *task; +}; + +BTF_TYPE_SAFE_TRUSTED(struct linux_binprm) { + struct file *file; +}; + +BTF_TYPE_SAFE_TRUSTED(struct file) { + struct inode *f_inode; +}; + +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry) { + struct inode *d_inode; +}; + +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) { + struct sock *sk; +}; + +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct vm_area_struct) { + struct mm_struct *vm_mm; + struct file *vm_file; +}; + +static bool type_is_rcu(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const char *field_name, u32 btf_id) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct task_struct)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct css_set)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu"); +} + +static bool type_is_rcu_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_RCU_OR_NULL(struct mm_struct)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu_or_null"); +} + +static bool type_is_trusted(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const char *field_name, u32 btf_id) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); + + 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)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct vm_area_struct)); + + 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, @@ -4768,8 +7210,9 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg = regs + regno; const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); const char *tname = btf_name_by_offset(reg->btf, t->name_off); + const char *field_name = NULL; enum bpf_type_flag flag = 0; - u32 btf_id; + u32 btf_id = 0; int ret; if (!env->allow_ptr_leaks) { @@ -4814,65 +7257,99 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - if (env->ops->btf_struct_access && !type_is_alloc(reg->type)) { + if (env->ops->btf_struct_access && !type_is_alloc(reg->type) && atype == BPF_WRITE) { if (!btf_is_kernel(reg->btf)) { - verbose(env, "verifier internal error: reg->btf must be kernel btf\n"); + verifier_bug(env, "reg->btf must be kernel btf"); return -EFAULT; } - ret = env->ops->btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); + ret = env->ops->btf_struct_access(&env->log, reg, off, size); } else { /* Writes are permitted with default btf_struct_access for * program allocated objects (which always have ref_obj_id > 0), * but not for untrusted PTR_TO_BTF_ID | MEM_ALLOC. */ - if (atype != BPF_READ && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + if (atype != BPF_READ && !type_is_ptr_alloc_obj(reg->type)) { verbose(env, "only read is supported\n"); return -EACCES; } - if (type_is_alloc(reg->type) && !reg->ref_obj_id) { - verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n"); + if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) && + !(reg->type & MEM_RCU) && !reg->ref_obj_id) { + verifier_bug(env, "ref_obj_id for allocated object must be non-zero"); return -EFAULT; } - ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); + ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag, &field_name); } if (ret < 0) return ret; - /* If this is an untrusted pointer, all pointers formed by walking it - * also inherit the untrusted flag. - */ - if (type_flag(reg->type) & PTR_UNTRUSTED) - flag |= PTR_UNTRUSTED; + if (ret != PTR_TO_BTF_ID) { + /* just mark; */ - /* By default any pointer obtained from walking a trusted pointer is - * no longer trusted except the rcu case below. - */ - flag &= ~PTR_TRUSTED; - - if (flag & MEM_RCU) { - /* Mark value register as MEM_RCU only if it is protected by - * bpf_rcu_read_lock() and the ptr reg is rcu or trusted. MEM_RCU - * itself can already indicate trustedness inside the rcu - * read lock region. Also mark rcu pointer as PTR_MAYBE_NULL since - * it could be null in some cases. + } else if (type_flag(reg->type) & PTR_UNTRUSTED) { + /* If this is an untrusted pointer, all pointers formed by walking it + * also inherit the untrusted flag. */ - if (!env->cur_state->active_rcu_lock || - !(is_trusted_reg(reg) || is_rcu_reg(reg))) - flag &= ~MEM_RCU; - else - flag |= PTR_MAYBE_NULL; - } else if (reg->type & MEM_RCU) { - /* ptr (reg) is marked as MEM_RCU, but the struct field is not tagged - * with __rcu. Mark the flag as PTR_UNTRUSTED conservatively. + flag = PTR_UNTRUSTED; + + } else if (is_trusted_reg(reg) || is_rcu_reg(reg)) { + /* By default any pointer obtained from walking a trusted pointer is no + * longer trusted, unless the field being accessed has explicitly been + * marked as inheriting its parent's state of trust (either full or RCU). + * For example: + * 'cgroups' pointer is untrusted if task->cgroups dereference + * happened in a sleepable program outside of bpf_rcu_read_lock() + * section. In a non-sleepable program it's trusted while in RCU CS (aka MEM_RCU). + * Note bpf_rcu_read_unlock() converts MEM_RCU pointers to PTR_UNTRUSTED. + * + * A regular RCU-protected pointer with __rcu tag can also be deemed + * trusted if we are in an RCU CS. Such pointer can be NULL. */ - flag |= PTR_UNTRUSTED; + 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 */ + flag |= MEM_RCU; + } else if (flag & MEM_RCU || + type_is_rcu_or_null(env, reg, field_name, btf_id)) { + /* __rcu tagged pointers can be NULL */ + flag |= MEM_RCU | PTR_MAYBE_NULL; + + /* We always trust them */ + if (type_is_rcu_or_null(env, reg, field_name, btf_id) && + flag & PTR_UNTRUSTED) + flag &= ~PTR_UNTRUSTED; + } else if (flag & (MEM_PERCPU | MEM_USER)) { + /* keep as-is */ + } else { + /* walking unknown pointers yields old deprecated PTR_TO_BTF_ID */ + clear_trusted_flags(&flag); + } + } else { + /* + * If not in RCU CS or MEM_RCU pointer can be NULL then + * aggressively mark as untrusted otherwise such + * pointers will be plain PTR_TO_BTF_ID without flags + * and will be allowed to be passed into helpers for + * compat reasons. + */ + flag = PTR_UNTRUSTED; + } + } else { + /* Old compat. Deprecated */ + clear_trusted_flags(&flag); } - if (atype == BPF_READ && value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); + if (atype == BPF_READ && value_regno >= 0) { + ret = mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); + if (ret < 0) + return ret; + } return 0; } @@ -4926,13 +7403,19 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, /* Simulate access to a PTR_TO_BTF_ID */ memset(&map_reg, 0, sizeof(map_reg)); - mark_btf_ld_reg(env, &map_reg, 0, PTR_TO_BTF_ID, btf_vmlinux, *map->ops->map_btf_id, 0); - ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag); + ret = mark_btf_ld_reg(env, &map_reg, 0, PTR_TO_BTF_ID, + btf_vmlinux, *map->ops->map_btf_id, 0); + if (ret < 0) + return ret; + ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag, NULL); if (ret < 0) return ret; - if (value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag); + if (value_regno >= 0) { + ret = mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag); + if (ret < 0) + return ret; + } return 0; } @@ -4943,13 +7426,14 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, * The minimum valid offset is -MAX_BPF_STACK for writes, and * -state->allocated_stack for reads. */ -static int check_stack_slot_within_bounds(int off, - struct bpf_func_state *state, - enum bpf_access_type t) +static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, + s64 off, + struct bpf_func_state *state, + enum bpf_access_type t) { int min_valid_off; - if (t == BPF_WRITE) + if (t == BPF_WRITE || env->allow_uninit_stack) min_valid_off = -MAX_BPF_STACK; else min_valid_off = -state->allocated_stack; @@ -4967,29 +7451,23 @@ static int check_stack_slot_within_bounds(int off, static int check_stack_access_within_bounds( struct bpf_verifier_env *env, int regno, int off, int access_size, - enum bpf_access_src src, enum bpf_access_type type) + enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; struct bpf_func_state *state = func(env, reg); - int min_off, max_off; + s64 min_off, max_off; int err; char *err_extra; - if (src == ACCESS_HELPER) - /* We don't know if helpers are reading or writing (or both). */ - err_extra = " indirect access to"; - else if (type == BPF_READ) + if (type == BPF_READ) err_extra = " read from"; else err_extra = " write to"; if (tnum_is_const(reg->var_off)) { - min_off = reg->var_off.value + off; - if (access_size > 0) - max_off = min_off + access_size - 1; - else - max_off = min_off; + min_off = (s64)reg->var_off.value + off; + max_off = min_off + access_size; } else { if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smin_value <= -BPF_MAX_VAR_OFF) { @@ -4998,15 +7476,17 @@ static int check_stack_access_within_bounds( return -EACCES; } min_off = reg->smin_value + off; - if (access_size > 0) - max_off = reg->smax_value + off + access_size - 1; - else - max_off = min_off; + max_off = reg->smax_value + off + access_size; } - err = check_stack_slot_within_bounds(min_off, state, type); - if (!err) - err = check_stack_slot_within_bounds(max_off, state, type); + 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)) { @@ -5016,11 +7496,27 @@ static int check_stack_access_within_bounds( char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n", - err_extra, regno, tn_buf, access_size); + verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n", + err_extra, regno, tn_buf, off, access_size); } + return err; } - return err; + + /* Note that there is no stack access with offset zero, so the needed stack + * size is -min_off, not -min_off+1. + */ + return grow_stack_state(env, state, -min_off /* size */); +} + +static bool get_func_retval_range(struct bpf_prog *prog, + struct bpf_retval_range *range) +{ + if (prog->type == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_MAC && + !bpf_lsm_get_retval_range(prog, range)) { + return true; + } + return false; } /* check whether memory at (regno + off) is accessible for t = (read | write) @@ -5031,11 +7527,10 @@ static int check_stack_access_within_bounds( */ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, - int value_regno, bool strict_alignment_once) + int value_regno, bool strict_alignment_once, bool is_ldsx) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; - struct bpf_func_state *state; int size, err = 0; size = bpf_size_to_bytes(bpf_size); @@ -5078,32 +7573,45 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return err; if (tnum_is_const(reg->var_off)) kptr_field = btf_record_find(reg->map_ptr->record, - off + reg->var_off.value, BPF_KPTR); + off + reg->var_off.value, BPF_KPTR | BPF_UPTR); if (kptr_field) { err = check_map_kptr_access(env, regno, value_regno, insn_idx, kptr_field); } else if (t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; - /* if map is read-only, track its contents as scalars */ + /* + * If map is read-only, track its contents as scalars, + * unless it is an insn array (see the special case below) + */ if (tnum_is_const(reg->var_off) && bpf_map_is_rdonly(map) && - map->ops->map_direct_value_addr) { + map->ops->map_direct_value_addr && + map->map_type != BPF_MAP_TYPE_INSN_ARRAY) { int map_off = off + reg->var_off.value; u64 val = 0; err = bpf_map_direct_read(map, map_off, size, - &val); + &val, is_ldsx); if (err) return err; regs[value_regno].type = SCALAR_VALUE; __mark_reg_known(®s[value_regno], val); + } else if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) { + if (bpf_size != BPF_DW) { + verbose(env, "Invalid read of %d bytes from insn_array\n", + size); + return -EACCES; + } + copy_register_state(®s[value_regno], reg); + regs[value_regno].type = PTR_TO_INSN; } else { mark_reg_unknown(env, regs, value_regno); } } } else if (base_type(reg->type) == PTR_TO_MEM) { bool rdonly_mem = type_is_rdonly_mem(reg->type); + bool rdonly_untrusted = rdonly_mem && (reg->type & PTR_UNTRUSTED); if (type_may_be_null(reg->type)) { verbose(env, "R%d invalid mem access '%s'\n", regno, @@ -5123,14 +7631,22 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return -EACCES; } - err = check_mem_region_access(env, regno, off, size, - reg->mem_size, false); + /* + * Accesses to untrusted PTR_TO_MEM are done through probe + * instructions, hence no need to check bounds in that case. + */ + if (!rdonly_untrusted) + err = check_mem_region_access(env, regno, off, size, + reg->mem_size, false); if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { - enum bpf_reg_type reg_type = SCALAR_VALUE; - struct btf *btf = NULL; - u32 btf_id = 0; + struct bpf_retval_range range; + struct bpf_insn_access_aux info = { + .reg_type = SCALAR_VALUE, + .is_ldsx = is_ldsx, + .log = &env->log, + }; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { @@ -5142,8 +7658,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, - &btf_id); + err = check_ctx_access(env, insn_idx, off, size, t, &info); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { @@ -5151,12 +7666,19 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ - if (reg_type == SCALAR_VALUE) { - mark_reg_unknown(env, regs, value_regno); + if (info.reg_type == SCALAR_VALUE) { + if (info.is_retval && get_func_retval_range(env->prog, &range)) { + err = __mark_reg_s32_range(env, regs, value_regno, + range.minval, range.maxval); + if (err) + return err; + } else { + mark_reg_unknown(env, regs, value_regno); + } } else { mark_reg_known_zero(env, regs, value_regno); - if (type_may_be_null(reg_type)) + if (type_may_be_null(info.reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the @@ -5164,22 +7686,18 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; - if (base_type(reg_type) == PTR_TO_BTF_ID) { - regs[value_regno].btf = btf; - regs[value_regno].btf_id = btf_id; + if (base_type(info.reg_type) == PTR_TO_BTF_ID) { + regs[value_regno].btf = info.btf; + regs[value_regno].btf_id = info.btf_id; + regs[value_regno].ref_obj_id = info.ref_obj_id; } } - regs[value_regno].type = reg_type; + regs[value_regno].type = info.reg_type; } } else if (reg->type == PTR_TO_STACK) { /* Basic bounds checks. */ - err = check_stack_access_within_bounds(env, regno, off, size, ACCESS_DIRECT, t); - if (err) - return err; - - state = func(env, reg); - err = update_stack_depth(env, state, off); + err = check_stack_access_within_bounds(env, regno, off, size, t); if (err) return err; @@ -5254,6 +7772,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_ARENA) { + if (t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); @@ -5262,33 +7783,84 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && regs[value_regno].type == SCALAR_VALUE) { - /* b/h/w load zero-extends, mark upper bits as known 0 */ - coerce_reg_to_size(®s[value_regno], size); + if (!is_ldsx) + /* b/h/w load zero-extends, mark upper bits as known 0 */ + coerce_reg_to_size(®s[value_regno], size); + else + coerce_reg_to_size_sx(®s[value_regno], size); } return err; } -static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) +static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, + bool allow_trust_mismatch); + +static int check_load_mem(struct bpf_verifier_env *env, struct bpf_insn *insn, + bool strict_alignment_once, bool is_ldsx, + bool allow_trust_mismatch, const char *ctx) { - int load_reg; + struct bpf_reg_state *regs = cur_regs(env); + enum bpf_reg_type src_reg_type; int err; - switch (insn->imm) { - case BPF_ADD: - case BPF_ADD | BPF_FETCH: - case BPF_AND: - case BPF_AND | BPF_FETCH: - case BPF_OR: - case BPF_OR | BPF_FETCH: - case BPF_XOR: - case BPF_XOR | BPF_FETCH: - case BPF_XCHG: - case BPF_CMPXCHG: - break; - default: - verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); - return -EINVAL; - } + /* check src operand */ + err = check_reg_arg(env, insn->src_reg, SRC_OP); + if (err) + return err; + + /* check dst operand */ + err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); + if (err) + return err; + + src_reg_type = regs[insn->src_reg].type; + + /* Check if (src_reg + off) is readable. The state of dst_reg will be + * updated by this call. + */ + err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, + strict_alignment_once, is_ldsx); + err = err ?: save_aux_ptr_type(env, src_reg_type, + allow_trust_mismatch); + err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], ctx); + + return err; +} + +static int check_store_reg(struct bpf_verifier_env *env, struct bpf_insn *insn, + bool strict_alignment_once) +{ + struct bpf_reg_state *regs = cur_regs(env); + enum bpf_reg_type dst_reg_type; + int err; + + /* check src1 operand */ + err = check_reg_arg(env, insn->src_reg, SRC_OP); + if (err) + return err; + + /* check src2 operand */ + err = check_reg_arg(env, insn->dst_reg, SRC_OP); + if (err) + return err; + + dst_reg_type = regs[insn->dst_reg].type; + + /* Check if (dst_reg + off) is writeable. */ + err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg, + strict_alignment_once, false); + err = err ?: save_aux_ptr_type(env, dst_reg_type, false); + + return err; +} + +static int check_atomic_rmw(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + int load_reg; + int err; if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid atomic operand size\n"); @@ -5324,10 +7896,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i return -EACCES; } - 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)) { + if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) { 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)); @@ -5354,27 +7923,105 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i /* Check whether we can read the memory, with second call for fetch * case to simulate the register fill. */ - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, -1, true); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, -1, true, false); if (!err && load_reg >= 0) - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, load_reg, - true); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, + insn->off, BPF_SIZE(insn->code), + BPF_READ, load_reg, true, false); 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); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); + if (err) + return err; + return 0; +} + +static int check_atomic_load(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + int err; + + err = check_load_mem(env, insn, true, false, false, "atomic_load"); if (err) return err; + if (!atomic_ptr_type_ok(env, insn->src_reg, insn)) { + verbose(env, "BPF_ATOMIC loads from R%d %s is not allowed\n", + insn->src_reg, + reg_type_str(env, reg_state(env, insn->src_reg)->type)); + return -EACCES; + } + + return 0; +} + +static int check_atomic_store(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + int err; + + err = check_store_reg(env, insn, true); + if (err) + return err; + + if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) { + 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)); + return -EACCES; + } + return 0; } +static int check_atomic(struct bpf_verifier_env *env, struct bpf_insn *insn) +{ + switch (insn->imm) { + case BPF_ADD: + case BPF_ADD | BPF_FETCH: + case BPF_AND: + case BPF_AND | BPF_FETCH: + case BPF_OR: + case BPF_OR | BPF_FETCH: + case BPF_XOR: + case BPF_XOR | BPF_FETCH: + case BPF_XCHG: + case BPF_CMPXCHG: + return check_atomic_rmw(env, insn); + case BPF_LOAD_ACQ: + if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { + verbose(env, + "64-bit load-acquires are only supported on 64-bit arches\n"); + return -EOPNOTSUPP; + } + return check_atomic_load(env, insn); + case BPF_STORE_REL: + if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { + verbose(env, + "64-bit store-releases are only supported on 64-bit arches\n"); + return -EOPNOTSUPP; + } + return check_atomic_store(env, insn); + default: + verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", + insn->imm); + return -EINVAL; + } +} + /* When register 'regno' is used to read the stack (either directly or through * a helper function) make sure that it's within stack boundary and, depending - * on the access type, that all elements of the stack are initialized. + * on the access type and privileges, that all elements of the stack are + * initialized. * * 'off' includes 'regno->off', but not its dynamic part (if any). * @@ -5384,13 +8031,11 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i static int check_stack_range_initialized( struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, - enum bpf_access_src type, struct bpf_call_arg_meta *meta) + enum bpf_access_type type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); int err, min_off, max_off, i, j, slot, spi; - char *err_extra = type == ACCESS_HELPER ? " indirect" : ""; - enum bpf_access_type bounds_check_type; /* Some accesses can write anything into the stack, others are * read-only. */ @@ -5401,18 +8046,10 @@ static int check_stack_range_initialized( return -EACCES; } - if (type == ACCESS_HELPER) { - /* The bounds checks for writes are more permissive than for - * reads. However, if raw_mode is not set, we'll do extra - * checks below. - */ - bounds_check_type = BPF_WRITE; + if (type == BPF_WRITE) clobber = true; - } else { - bounds_check_type = BPF_READ; - } - err = check_stack_access_within_bounds(env, regno, off, access_size, - type, bounds_check_type); + + err = check_stack_access_within_bounds(env, regno, off, access_size, type); if (err) return err; @@ -5429,8 +8066,8 @@ static int check_stack_range_initialized( char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "R%d%s variable offset stack access prohibited for !root, var_off=%s\n", - regno, err_extra, tn_buf); + verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n", + regno, tn_buf); return -EACCES; } /* Only initialized buffer on stack is allowed to be accessed @@ -5447,6 +8084,31 @@ static int check_stack_range_initialized( } if (meta && meta->raw_mode) { + /* Ensure we won't be overwriting dynptrs when simulating byte + * by byte access in check_helper_call using meta.access_size. + * This would be a problem if we have a helper in the future + * which takes: + * + * helper(uninit_mem, len, dynptr) + * + * Now, uninint_mem may overlap with dynptr pointer. Hence, it + * may end up writing to dynptr itself when touching memory from + * arg 1. This can be relaxed on a case by case basis for known + * safe cases, but reject due to the possibilitiy of aliasing by + * default. + */ + for (i = min_off; i < max_off + access_size; i++) { + int stack_off = -i - 1; + + spi = __get_spi(i); + /* raw_mode may write past allocated_stack */ + if (state->allocated_stack <= stack_off) + continue; + if (state->stack[spi].slot_type[stack_off % BPF_REG_SIZE] == STACK_DYNPTR) { + verbose(env, "potential write to dynptr at off=%d disallowed\n", i); + return -EACCES; + } + } meta->access_size = access_size; meta->regno = regno; return 0; @@ -5457,12 +8119,16 @@ static int check_stack_range_initialized( slot = -i - 1; spi = slot / BPF_REG_SIZE; - if (state->allocated_stack <= slot) - goto err; + if (state->allocated_stack <= slot) { + verbose(env, "allocated_stack too small\n"); + return -EFAULT; + } + stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; if (*stype == STACK_MISC) goto mark; - if (*stype == STACK_ZERO) { + if ((*stype == STACK_ZERO) || + (*stype == STACK_INVALID && env->allow_uninit_stack)) { if (clobber) { /* helper can write anything into the stack */ *stype = STACK_MISC; @@ -5481,36 +8147,36 @@ static int check_stack_range_initialized( goto mark; } -err: if (tnum_is_const(reg->var_off)) { - verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n", - err_extra, regno, min_off, i - min_off, access_size); + verbose(env, "invalid read from stack R%d off %d+%d size %d\n", + regno, min_off, i - min_off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "invalid%s read from stack R%d var_off %s+%d size %d\n", - err_extra, regno, tn_buf, i - min_off, access_size); + verbose(env, "invalid read from stack R%d var_off %s+%d size %d\n", + regno, tn_buf, i - min_off, access_size); } return -EACCES; mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ - mark_reg_read(env, &state->stack[spi].spilled_ptr, - state->stack[spi].spilled_ptr.parent, - REG_LIVE_READ64); - /* We do not set REG_LIVE_WRITTEN for stack slot, as we can not + err = bpf_mark_stack_read(env, reg->frameno, env->insn_idx, BIT(spi)); + if (err) + return err; + /* We do not call bpf_mark_stack_write(), as we can not * be sure that whether stack slot is written to or not. Hence, * we must still conservatively propagate reads upwards even if * helper may write to the entire memory range. */ } - return update_stack_depth(env, state, min_off); + return 0; } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, - int access_size, bool zero_size_allowed, + int access_size, enum bpf_access_type access_type, + bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; @@ -5522,7 +8188,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -5530,15 +8196,13 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: - if (check_map_access_type(env, regno, reg->off, access_size, - meta && meta->raw_mode ? BPF_WRITE : - BPF_READ)) + if (check_map_access_type(env, regno, reg->off, access_size, access_type)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -5549,7 +8213,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -5566,7 +8230,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_stack_range_initialized( env, regno, reg->off, access_size, - zero_size_allowed, ACCESS_HELPER, meta); + zero_size_allowed, access_type, meta); + case PTR_TO_BTF_ID: + return check_ptr_to_btf_access(env, regs, regno, reg->off, + access_size, BPF_READ, -1); case PTR_TO_CTX: /* in case the function doesn't know how to access the context, * (because we are in a program of type SYSCALL for example), we @@ -5574,7 +8241,6 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, * Dynamically check it now. */ if (!env->ops->convert_ctx_access) { - enum bpf_access_type atype = meta && meta->raw_mode ? BPF_WRITE : BPF_READ; int offset = access_size - 1; /* Allow zero-byte read from PTR_TO_CTX */ @@ -5582,7 +8248,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return zero_size_allowed ? 0 : -EACCES; return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, - atype, -1, false); + access_type, -1, false, false); } fallthrough; @@ -5599,8 +8265,15 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +/* verify arguments to helpers or kfuncs consisting of a pointer and an access + * size. + * + * @regno is the register containing the access size. regno-1 is the register + * containing the pointer. + */ static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, + enum bpf_access_type access_type, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { @@ -5616,15 +8289,12 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, */ meta->msize_max_value = reg->umax_value; - /* The register is SCALAR_VALUE; the access check - * happens using its boundaries. + /* The register is SCALAR_VALUE; the access check happens using + * its boundaries. For unprivileged variable accesses, disable + * raw mode so that the program is required to initialize all + * the memory that the helper could just partially fill up. */ if (!tnum_is_const(reg->var_off)) - /* For unprivileged variable accesses, disable raw - * mode so that the program is required to - * initialize all the memory that the helper could - * just partially fill up. - */ meta = NULL; if (reg->smin_value < 0) { @@ -5633,12 +8303,10 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, return -EACCES; } - if (reg->umin_value == 0) { - err = check_helper_mem_access(env, regno - 1, 0, - zero_size_allowed, - meta); - if (err) - return err; + if (reg->umin_value == 0 && !zero_size_allowed) { + verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n", + regno, reg->umin_value, reg->umax_value); + return -EACCES; } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { @@ -5646,26 +8314,23 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, regno); return -EACCES; } - err = check_helper_mem_access(env, regno - 1, - reg->umax_value, - zero_size_allowed, meta); + err = check_helper_mem_access(env, regno - 1, reg->umax_value, + access_type, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); return err; } -int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno, u32 mem_size) +static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno, u32 mem_size) { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; - struct bpf_call_arg_meta meta; int err; if (register_is_null(reg)) return 0; - memset(&meta, 0, sizeof(meta)); /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. @@ -5675,10 +8340,8 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, mark_ptr_not_null_reg(reg); } - err = check_helper_mem_access(env, regno, mem_size, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); + err = check_helper_mem_access(env, regno, mem_size, BPF_READ, true, NULL); + err = err ?: check_helper_mem_access(env, regno, mem_size, BPF_WRITE, true, NULL); if (may_be_null) *reg = saved_reg; @@ -5704,16 +8367,21 @@ static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg mark_ptr_not_null_reg(mem_reg); } - err = check_mem_size_reg(env, reg, regno, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); + err = check_mem_size_reg(env, reg, regno, BPF_READ, true, &meta); + err = err ?: check_mem_size_reg(env, reg, regno, BPF_WRITE, true, &meta); if (may_be_null) *mem_reg = saved_reg; + return err; } +enum { + PROCESS_SPIN_LOCK = (1 << 0), + PROCESS_RES_LOCK = (1 << 1), + PROCESS_LOCK_IRQ = (1 << 2), +}; + /* Implementation details: * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL. * bpf_obj_new returns PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL. @@ -5733,32 +8401,36 @@ static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. - * cur_state->active_lock remembers which map value element or allocated + * env->cur_state->active_locks remembers which map value element or allocated * object got locked and clears it after bpf_spin_unlock. */ -static int process_spin_lock(struct bpf_verifier_env *env, int regno, - bool is_lock) +static int process_spin_lock(struct bpf_verifier_env *env, int regno, int flags) { + bool is_lock = flags & PROCESS_SPIN_LOCK, is_res_lock = flags & PROCESS_RES_LOCK; + const char *lock_str = is_res_lock ? "bpf_res_spin" : "bpf_spin"; struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_verifier_state *cur = env->cur_state; bool is_const = tnum_is_const(reg->var_off); + bool is_irq = flags & PROCESS_LOCK_IRQ; u64 val = reg->var_off.value; struct bpf_map *map = NULL; struct btf *btf = NULL; struct btf_record *rec; + u32 spin_lock_off; + int err; if (!is_const) { verbose(env, - "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", - regno); + "R%d doesn't have constant offset. %s_lock has to be at the constant offset\n", + regno, lock_str); return -EINVAL; } if (reg->type == PTR_TO_MAP_VALUE) { map = reg->map_ptr; if (!map->btf) { verbose(env, - "map '%s' has to have BTF in order to use bpf_spin_lock\n", - map->name); + "map '%s' has to have BTF in order to use %s_lock\n", + map->name, lock_str); return -EINVAL; } } else { @@ -5766,138 +8438,242 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, } rec = reg_btf_record(reg); - if (!btf_record_has_field(rec, BPF_SPIN_LOCK)) { - verbose(env, "%s '%s' has no valid bpf_spin_lock\n", map ? "map" : "local", - map ? map->name : "kptr"); + if (!btf_record_has_field(rec, is_res_lock ? BPF_RES_SPIN_LOCK : BPF_SPIN_LOCK)) { + verbose(env, "%s '%s' has no valid %s_lock\n", map ? "map" : "local", + map ? map->name : "kptr", lock_str); return -EINVAL; } - if (rec->spin_lock_off != val + reg->off) { - verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock' that is at %d\n", - val + reg->off, rec->spin_lock_off); + spin_lock_off = is_res_lock ? rec->res_spin_lock_off : rec->spin_lock_off; + if (spin_lock_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct %s_lock' that is at %d\n", + val + reg->off, lock_str, spin_lock_off); return -EINVAL; } if (is_lock) { - if (cur->active_lock.ptr) { - verbose(env, - "Locking two bpf_spin_locks are not allowed\n"); - return -EINVAL; - } + void *ptr; + int type; + if (map) - cur->active_lock.ptr = map; + ptr = map; + else + ptr = btf; + + if (!is_res_lock && cur->active_locks) { + if (find_lock_state(env->cur_state, REF_TYPE_LOCK, 0, NULL)) { + verbose(env, + "Locking two bpf_spin_locks are not allowed\n"); + return -EINVAL; + } + } else if (is_res_lock && cur->active_locks) { + if (find_lock_state(env->cur_state, REF_TYPE_RES_LOCK | REF_TYPE_RES_LOCK_IRQ, reg->id, ptr)) { + verbose(env, "Acquiring the same lock again, AA deadlock detected\n"); + return -EINVAL; + } + } + + if (is_res_lock && is_irq) + type = REF_TYPE_RES_LOCK_IRQ; + else if (is_res_lock) + type = REF_TYPE_RES_LOCK; else - cur->active_lock.ptr = btf; - cur->active_lock.id = reg->id; + type = REF_TYPE_LOCK; + err = acquire_lock_state(env, env->insn_idx, type, reg->id, ptr); + if (err < 0) { + verbose(env, "Failed to acquire lock state\n"); + return err; + } } else { - struct bpf_func_state *fstate = cur_func(env); void *ptr; - int i; + int type; if (map) ptr = map; else ptr = btf; - if (!cur->active_lock.ptr) { - verbose(env, "bpf_spin_unlock without taking a lock\n"); + if (!cur->active_locks) { + verbose(env, "%s_unlock without taking a lock\n", lock_str); return -EINVAL; } - if (cur->active_lock.ptr != ptr || - cur->active_lock.id != reg->id) { - verbose(env, "bpf_spin_unlock of different lock\n"); + + if (is_res_lock && is_irq) + type = REF_TYPE_RES_LOCK_IRQ; + else if (is_res_lock) + type = REF_TYPE_RES_LOCK; + else + type = REF_TYPE_LOCK; + if (!find_lock_state(cur, type, reg->id, ptr)) { + verbose(env, "%s_unlock of different lock\n", lock_str); return -EINVAL; } - cur->active_lock.ptr = NULL; - cur->active_lock.id = 0; - - for (i = fstate->acquired_refs - 1; i >= 0; i--) { - int err; - - /* Complain on error because this reference state cannot - * be freed before this point, as bpf_spin_lock critical - * section does not allow functions that release the - * allocated object immediately. - */ - if (!fstate->refs[i].release_on_unlock) - continue; - err = release_reference(env, fstate->refs[i].id); - if (err) { - verbose(env, "failed to release release_on_unlock reference"); - return err; - } + if (reg->id != cur->active_lock_id || ptr != cur->active_lock_ptr) { + verbose(env, "%s_unlock cannot be out of order\n", lock_str); + return -EINVAL; + } + if (release_lock_state(cur, type, reg->id, ptr)) { + verbose(env, "%s_unlock of different lock\n", lock_str); + return -EINVAL; } + + invalidate_non_owning_refs(env); } return 0; } -static int process_timer_func(struct bpf_verifier_env *env, int regno, - struct bpf_call_arg_meta *meta) +/* Check if @regno is a pointer to a specific field in a map value */ +static int check_map_field_pointer(struct bpf_verifier_env *env, u32 regno, + enum btf_field_type field_type) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; bool is_const = tnum_is_const(reg->var_off); struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; + const char *struct_name = btf_field_type_name(field_type); + int field_off = -1; if (!is_const) { verbose(env, - "R%d doesn't have constant offset. bpf_timer has to be at the constant offset\n", - regno); + "R%d doesn't have constant offset. %s has to be at the constant offset\n", + regno, struct_name); return -EINVAL; } if (!map->btf) { - verbose(env, "map '%s' has to have BTF in order to use bpf_timer\n", - map->name); + verbose(env, "map '%s' has to have BTF in order to use %s\n", map->name, + struct_name); return -EINVAL; } - if (!btf_record_has_field(map->record, BPF_TIMER)) { - verbose(env, "map '%s' has no valid bpf_timer\n", map->name); + if (!btf_record_has_field(map->record, field_type)) { + verbose(env, "map '%s' has no valid %s\n", map->name, struct_name); return -EINVAL; } - if (map->record->timer_off != val + reg->off) { - verbose(env, "off %lld doesn't point to 'struct bpf_timer' that is at %d\n", - val + reg->off, map->record->timer_off); + switch (field_type) { + case BPF_TIMER: + field_off = map->record->timer_off; + break; + case BPF_TASK_WORK: + field_off = map->record->task_work_off; + break; + case BPF_WORKQUEUE: + field_off = map->record->wq_off; + break; + default: + verifier_bug(env, "unsupported BTF field type: %s\n", struct_name); + return -EINVAL; + } + if (field_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct %s' that is at %d\n", + val + reg->off, struct_name, field_off); return -EINVAL; } + return 0; +} + +static int process_timer_func(struct bpf_verifier_env *env, int regno, + struct bpf_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + struct bpf_map *map = reg->map_ptr; + int err; + + err = check_map_field_pointer(env, regno, BPF_TIMER); + if (err) + return err; + if (meta->map_ptr) { - verbose(env, "verifier bug. Two map pointers in a timer helper\n"); + verifier_bug(env, "Two map pointers in a timer helper"); return -EFAULT; } + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n"); + return -EOPNOTSUPP; + } meta->map_uid = reg->map_uid; meta->map_ptr = map; 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; + int err; + + err = check_map_field_pointer(env, regno, BPF_WORKQUEUE); + if (err) + return err; + + if (meta->map.ptr) { + verifier_bug(env, "Two map pointers in a bpf_wq helper"); + return -EFAULT; + } + + meta->map.uid = reg->map_uid; + meta->map.ptr = map; + return 0; +} + +static int process_task_work_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; + int err; + + err = check_map_field_pointer(env, regno, BPF_TASK_WORK); + if (err) + return err; + + if (meta->map.ptr) { + verifier_bug(env, "Two map pointers in a bpf_task_work helper"); + return -EFAULT; + } + 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) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; - struct bpf_map *map_ptr = reg->map_ptr; struct btf_field *kptr_field; + struct bpf_map *map_ptr; + struct btf_record *rec; u32 kptr_off; + if (type_is_ptr_alloc_obj(reg->type)) { + rec = reg_btf_record(reg); + } else { /* PTR_TO_MAP_VALUE */ + map_ptr = reg->map_ptr; + if (!map_ptr->btf) { + verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n", + map_ptr->name); + return -EINVAL; + } + rec = map_ptr->record; + meta->map_ptr = map_ptr; + } + if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. kptr has to be at the constant offset\n", regno); return -EINVAL; } - if (!map_ptr->btf) { - verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n", - map_ptr->name); - return -EINVAL; - } - if (!btf_record_has_field(map_ptr->record, BPF_KPTR)) { - verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); + + if (!btf_record_has_field(rec, BPF_KPTR)) { + verbose(env, "R%d has no valid kptr\n", regno); return -EINVAL; } - meta->map_ptr = map_ptr; kptr_off = reg->off + reg->var_off.value; - kptr_field = btf_record_find(map_ptr->record, kptr_off, BPF_KPTR); + kptr_field = btf_record_find(rec, kptr_off, BPF_KPTR); if (!kptr_field) { verbose(env, "off=%d doesn't point to kptr\n", kptr_off); return -EACCES; } - if (kptr_field->type != BPF_KPTR_REF) { + if (kptr_field->type != BPF_KPTR_REF && kptr_field->type != BPF_KPTR_PERCPU) { verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); return -EACCES; } @@ -5930,26 +8706,27 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, * Helpers which do not mutate the bpf_dynptr set MEM_RDONLY in their argument * type, and declare it as 'const struct bpf_dynptr *' in their prototype. */ -int process_dynptr_func(struct bpf_verifier_env *env, int regno, - enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) +static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn_idx, + enum bpf_arg_type arg_type, int clone_ref_obj_id) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + int err; + + if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) { + verbose(env, + "arg#%d expected pointer to stack or const struct bpf_dynptr\n", + regno - 1); + return -EINVAL; + } /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*): */ if ((arg_type & (MEM_UNINIT | MEM_RDONLY)) == (MEM_UNINIT | MEM_RDONLY)) { - verbose(env, "verifier internal error: misconfigured dynptr helper type flags\n"); + verifier_bug(env, "misconfigured dynptr helper type flags"); return -EFAULT; } - /* CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to - * check_func_arg_reg_off's logic. We only need to check offset - * alignment for PTR_TO_STACK. - */ - if (reg->type == PTR_TO_STACK && (reg->off % BPF_REG_SIZE)) { - verbose(env, "cannot pass in dynptr at an offset=%d\n", reg->off); - return -EINVAL; - } + /* MEM_UNINIT - Points to memory that is an appropriate candidate for * constructing a mutable bpf_dynptr object. * @@ -5966,20 +8743,22 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, * to. */ if (arg_type & MEM_UNINIT) { + int i; + if (!is_dynptr_reg_valid_uninit(env, reg)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); return -EINVAL; } - /* We only support one dynptr being uninitialized at the moment, - * which is sufficient for the helper functions we have right now. - */ - if (meta->uninit_dynptr_regno) { - verbose(env, "verifier internal error: multiple uninitialized dynptr args\n"); - return -EFAULT; + /* we write BPF_DW bits (8 bytes) at a time */ + for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { + err = check_mem_access(env, insn_idx, regno, + i, BPF_DW, BPF_WRITE, -1, false, false); + if (err) + return err; } - meta->uninit_dynptr_regno = regno; + err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx, clone_ref_obj_id); } else /* MEM_RDONLY and None case from above */ { /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { @@ -5990,31 +8769,367 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", - regno); + regno - 1); return -EINVAL; } /* Fold modifiers (in this case, MEM_RDONLY) when checking expected type */ if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { - const char *err_extra = ""; - - switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { - case DYNPTR_TYPE_LOCAL: - err_extra = "local"; - break; - case DYNPTR_TYPE_RINGBUF: - err_extra = "ringbuf"; - break; - default: - err_extra = "<unknown>"; - break; - } verbose(env, "Expected a dynptr of type %s as arg #%d\n", - err_extra, regno); + dynptr_type_str(arg_to_dynptr_type(arg_type)), regno - 1); + return -EINVAL; + } + + err = mark_dynptr_read(env, reg); + } + return err; +} + +static u32 iter_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi) +{ + struct bpf_func_state *state = func(env, reg); + + return state->stack[spi].spilled_ptr.ref_obj_id; +} + +static bool is_iter_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); +} + +static bool is_iter_new_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ITER_NEW; +} + +static bool is_iter_next_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ITER_NEXT; +} + +static bool is_iter_destroy_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ITER_DESTROY; +} + +static bool is_kfunc_arg_iter(struct bpf_kfunc_call_arg_meta *meta, int arg_idx, + const struct btf_param *arg) +{ + /* btf_check_iter_kfuncs() guarantees that first argument of any iter + * kfunc is iter state pointer + */ + if (is_iter_kfunc(meta)) + return arg_idx == 0; + + /* iter passed as an argument to a generic kfunc */ + return btf_param_match_suffix(meta->btf, arg, "__iter"); +} + +static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_idx, + struct bpf_kfunc_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + const struct btf_type *t; + int spi, err, i, nr_slots, btf_id; + + if (reg->type != PTR_TO_STACK) { + verbose(env, "arg#%d expected pointer to an iterator on stack\n", regno - 1); + return -EINVAL; + } + + /* For iter_{new,next,destroy} functions, btf_check_iter_kfuncs() + * ensures struct convention, so we wouldn't need to do any BTF + * validation here. But given iter state can be passed as a parameter + * to any kfunc, if arg has "__iter" suffix, we need to be a bit more + * conservative here. + */ + btf_id = btf_check_iter_arg(meta->btf, meta->func_proto, regno - 1); + if (btf_id < 0) { + verbose(env, "expected valid iter pointer as arg #%d\n", regno - 1); + return -EINVAL; + } + t = btf_type_by_id(meta->btf, btf_id); + nr_slots = t->size / BPF_REG_SIZE; + + if (is_iter_new_kfunc(meta)) { + /* bpf_iter_<type>_new() expects pointer to uninit iter state */ + if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) { + verbose(env, "expected uninitialized iter_%s as arg #%d\n", + iter_type_str(meta->btf, btf_id), regno - 1); return -EINVAL; } + + for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) { + err = check_mem_access(env, insn_idx, regno, + i, BPF_DW, BPF_WRITE, -1, false, false); + if (err) + return err; + } + + err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots); + if (err) + return err; + } else { + /* iter_next() or iter_destroy(), as well as any kfunc + * accepting iter argument, expect initialized iter state + */ + err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots); + switch (err) { + case 0: + break; + case -EINVAL: + verbose(env, "expected an initialized iter_%s as arg #%d\n", + iter_type_str(meta->btf, btf_id), regno - 1); + return err; + case -EPROTO: + verbose(env, "expected an RCU CS when using %s\n", meta->func_name); + return err; + default: + return err; + } + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return spi; + + err = mark_iter_read(env, reg, spi, nr_slots); + if (err) + return err; + + /* remember meta->iter info for process_iter_next_call() */ + meta->iter.spi = spi; + meta->iter.frameno = reg->frameno; + meta->ref_obj_id = iter_ref_obj_id(env, reg, spi); + + if (is_iter_destroy_kfunc(meta)) { + err = unmark_stack_slots_iter(env, reg, nr_slots); + if (err) + return err; + } + } + + return 0; +} + +/* Look for a previous loop entry at insn_idx: nearest parent state + * stopped at insn_idx with callsites matching those in cur->frame. + */ +static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env, + struct bpf_verifier_state *cur, + int insn_idx) +{ + struct bpf_verifier_state_list *sl; + struct bpf_verifier_state *st; + struct list_head *pos, *head; + + /* Explored states are pushed in stack order, most recent states come first */ + head = explored_state(env, insn_idx); + list_for_each(pos, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); + /* If st->branches != 0 state is a part of current DFS verification path, + * hence cur & st for a loop. + */ + st = &sl->state; + if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) && + st->dfs_depth < cur->dfs_depth) + return st; + } + + return NULL; +} + +static void reset_idmap_scratch(struct bpf_verifier_env *env); +static bool regs_exact(const struct bpf_reg_state *rold, + const struct bpf_reg_state *rcur, + struct bpf_idmap *idmap); + +static void maybe_widen_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *rold, struct bpf_reg_state *rcur, + struct bpf_idmap *idmap) +{ + if (rold->type != SCALAR_VALUE) + return; + if (rold->type != rcur->type) + return; + if (rold->precise || rcur->precise || regs_exact(rold, rcur, idmap)) + return; + __mark_reg_unknown(env, rcur); +} + +static int widen_imprecise_scalars(struct bpf_verifier_env *env, + struct bpf_verifier_state *old, + struct bpf_verifier_state *cur) +{ + struct bpf_func_state *fold, *fcur; + int i, fr, num_slots; + + reset_idmap_scratch(env); + for (fr = old->curframe; fr >= 0; fr--) { + fold = old->frame[fr]; + fcur = cur->frame[fr]; + + for (i = 0; i < MAX_BPF_REG; i++) + maybe_widen_reg(env, + &fold->regs[i], + &fcur->regs[i], + &env->idmap_scratch); + + num_slots = min(fold->allocated_stack / BPF_REG_SIZE, + fcur->allocated_stack / BPF_REG_SIZE); + for (i = 0; i < num_slots; i++) { + if (!is_spilled_reg(&fold->stack[i]) || + !is_spilled_reg(&fcur->stack[i])) + continue; + + maybe_widen_reg(env, + &fold->stack[i].spilled_ptr, + &fcur->stack[i].spilled_ptr, + &env->idmap_scratch); + } + } + return 0; +} + +static struct bpf_reg_state *get_iter_from_state(struct bpf_verifier_state *cur_st, + struct bpf_kfunc_call_arg_meta *meta) +{ + int iter_frameno = meta->iter.frameno; + int iter_spi = meta->iter.spi; + + return &cur_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr; +} + +/* process_iter_next_call() is called when verifier gets to iterator's next + * "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer + * to it as just "iter_next()" in comments below. + * + * BPF verifier relies on a crucial contract for any iter_next() + * implementation: it should *eventually* return NULL, and once that happens + * it should keep returning NULL. That is, once iterator exhausts elements to + * iterate, it should never reset or spuriously return new elements. + * + * With the assumption of such contract, process_iter_next_call() simulates + * a fork in the verifier state to validate loop logic correctness and safety + * without having to simulate infinite amount of iterations. + * + * In current state, we first assume that iter_next() returned NULL and + * iterator state is set to DRAINED (BPF_ITER_STATE_DRAINED). In such + * conditions we should not form an infinite loop and should eventually reach + * exit. + * + * Besides that, we also fork current state and enqueue it for later + * verification. In a forked state we keep iterator state as ACTIVE + * (BPF_ITER_STATE_ACTIVE) and assume non-NULL return from iter_next(). We + * also bump iteration depth to prevent erroneous infinite loop detection + * later on (see iter_active_depths_differ() comment for details). In this + * state we assume that we'll eventually loop back to another iter_next() + * calls (it could be in exactly same location or in some other instruction, + * it doesn't matter, we don't make any unnecessary assumptions about this, + * everything revolves around iterator state in a stack slot, not which + * instruction is calling iter_next()). When that happens, we either will come + * to iter_next() with equivalent state and can conclude that next iteration + * will proceed in exactly the same way as we just verified, so it's safe to + * assume that loop converges. If not, we'll go on another iteration + * simulation with a different input state, until all possible starting states + * are validated or we reach maximum number of instructions limit. + * + * This way, we will either exhaustively discover all possible input states + * that iterator loop can start with and eventually will converge, or we'll + * effectively regress into bounded loop simulation logic and either reach + * maximum number of instructions if loop is not provably convergent, or there + * is some statically known limit on number of iterations (e.g., if there is + * an explicit `if n > 100 then break;` statement somewhere in the loop). + * + * Iteration convergence logic in is_state_visited() relies on exact + * states comparison, which ignores read and precision marks. + * This is necessary because read and precision marks are not finalized + * while in the loop. Exact comparison might preclude convergence for + * simple programs like below: + * + * i = 0; + * while(iter_next(&it)) + * i++; + * + * At each iteration step i++ would produce a new distinct state and + * eventually instruction processing limit would be reached. + * + * To avoid such behavior speculatively forget (widen) range for + * imprecise scalar registers, if those registers were not precise at the + * end of the previous iteration and do not match exactly. + * + * This is a conservative heuristic that allows to verify wide range of programs, + * however it precludes verification of programs that conjure an + * imprecise value on the first loop iteration and use it as precise on a second. + * For example, the following safe program would fail to verify: + * + * struct bpf_num_iter it; + * int arr[10]; + * int i = 0, a = 0; + * bpf_iter_num_new(&it, 0, 10); + * while (bpf_iter_num_next(&it)) { + * if (a == 0) { + * a = 1; + * i = 7; // Because i changed verifier would forget + * // it's range on second loop entry. + * } else { + * arr[i] = 42; // This would fail to verify. + * } + * } + * bpf_iter_num_destroy(&it); + */ +static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, + struct bpf_kfunc_call_arg_meta *meta) +{ + struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; + struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr; + struct bpf_reg_state *cur_iter, *queued_iter; + + BTF_TYPE_EMIT(struct bpf_iter); + + cur_iter = get_iter_from_state(cur_st, meta); + + if (cur_iter->iter.state != BPF_ITER_STATE_ACTIVE && + cur_iter->iter.state != BPF_ITER_STATE_DRAINED) { + verifier_bug(env, "unexpected iterator state %d (%s)", + cur_iter->iter.state, iter_state_str(cur_iter->iter.state)); + return -EFAULT; + } + + if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) { + /* Because iter_next() call is a checkpoint is_state_visitied() + * should guarantee parent state with same call sites and insn_idx. + */ + if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx || + !same_callsites(cur_st->parent, cur_st)) { + verifier_bug(env, "bad parent state for iter next call"); + return -EFAULT; + } + /* Note cur_st->parent in the call below, it is necessary to skip + * checkpoint created for cur_st by is_state_visited() + * right at this instruction. + */ + prev_st = find_prev_entry(env, cur_st->parent, insn_idx); + /* branch out active iter state */ + queued_st = push_stack(env, insn_idx + 1, insn_idx, false); + if (IS_ERR(queued_st)) + return PTR_ERR(queued_st); + + queued_iter = get_iter_from_state(queued_st, meta); + queued_iter->iter.state = BPF_ITER_STATE_ACTIVE; + queued_iter->iter.depth++; + if (prev_st) + widen_imprecise_scalars(env, prev_st, queued_st); + + queued_fr = queued_st->frame[queued_st->curframe]; + mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]); } + + /* switch to DRAINED state, but keep the depth unchanged */ + /* mark current iter state as drained and assume returned NULL */ + cur_iter->iter.state = BPF_ITER_STATE_DRAINED; + __mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]); + return 0; } @@ -6024,6 +9139,12 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type) type == ARG_CONST_SIZE_OR_ZERO; } +static bool arg_type_is_raw_mem(enum bpf_arg_type type) +{ + return base_type(type) == ARG_PTR_TO_MEM && + type & MEM_UNINIT; +} + static bool arg_type_is_release(enum bpf_arg_type type) { return type & OBJ_RELEASE; @@ -6034,24 +9155,14 @@ static bool arg_type_is_dynptr(enum bpf_arg_type type) return base_type(type) == ARG_PTR_TO_DYNPTR; } -static int int_ptr_type_to_size(enum bpf_arg_type type) -{ - if (type == ARG_PTR_TO_INT) - return sizeof(u32); - else if (type == ARG_PTR_TO_LONG) - return sizeof(u64); - - return -EINVAL; -} - static int resolve_map_arg_type(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_arg_type *arg_type) { if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ - verbose(env, "invalid map_ptr to access map->type\n"); - return -EACCES; + verifier_bug(env, "invalid map_ptr to access map->type"); + return -EFAULT; } switch (meta->map_ptr->map_type) { @@ -6112,16 +9223,7 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MEM, PTR_TO_MEM | MEM_RINGBUF, PTR_TO_BUF, - }, -}; - -static const struct bpf_reg_types int_ptr_types = { - .types = { - PTR_TO_STACK, - PTR_TO_PACKET, - PTR_TO_PACKET_META, - PTR_TO_MAP_KEY, - PTR_TO_MAP_VALUE, + PTR_TO_BTF_ID | PTR_TRUSTED, }, }; @@ -6147,6 +9249,7 @@ static const struct bpf_reg_types btf_ptr_types = { static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU, + PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU, PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED, } }; @@ -6154,7 +9257,12 @@ static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; -static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } }; +static const struct bpf_reg_types kptr_xchg_dest_types = { + .types = { + PTR_TO_MAP_VALUE, + PTR_TO_BTF_ID | MEM_ALLOC + } +}; static const struct bpf_reg_types dynptr_types = { .types = { PTR_TO_STACK, @@ -6179,14 +9287,12 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, [ARG_PTR_TO_RINGBUF_MEM] = &ringbuf_mem_types, - [ARG_PTR_TO_INT] = &int_ptr_types, - [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, - [ARG_PTR_TO_KPTR] = &kptr_types, + [ARG_KPTR_XCHG_DEST] = &kptr_xchg_dest_types, [ARG_PTR_TO_DYNPTR] = &dynptr_types, }; @@ -6202,7 +9308,7 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, compatible = compatible_reg_types[base_type(arg_type)]; if (!compatible) { - verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type); + verifier_bug(env, "unsupported arg type %d", arg_type); return -EFAULT; } @@ -6214,12 +9320,22 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL * + * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type. + * * Therefore we fold these flags depending on the arg_type before comparison. */ if (arg_type & MEM_RDONLY) type &= ~MEM_RDONLY; if (arg_type & PTR_MAYBE_NULL) type &= ~PTR_MAYBE_NULL; + if (base_type(arg_type) == ARG_PTR_TO_MEM) + type &= ~DYNPTR_TYPE_FLAG_MASK; + + /* Local kptr types are allowed as the source argument of bpf_kptr_xchg */ + if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type) && regno == BPF_REG_2) { + type &= ~MEM_ALLOC; + type &= ~MEM_PERCPU; + } for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; @@ -6237,7 +9353,28 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, return -EACCES; found: - if (reg->type == PTR_TO_BTF_ID || reg->type & PTR_TRUSTED) { + if (base_type(reg->type) != PTR_TO_BTF_ID) + return 0; + + if (compatible == &mem_types) { + if (!(arg_type & MEM_RDONLY)) { + verbose(env, + "%s() may write into memory pointed by R%d type=%s\n", + func_id_name(meta->func_id), + regno, reg_type_str(env, reg->type)); + return -EACCES; + } + return 0; + } + + switch ((int)reg->type) { + case PTR_TO_BTF_ID: + case PTR_TO_BTF_ID | PTR_TRUSTED: + case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: + case PTR_TO_BTF_ID | MEM_RCU: + case PTR_TO_BTF_ID | PTR_MAYBE_NULL: + case PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU: + { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This * allows bpf_sk_release to work for multiple socket types. @@ -6245,9 +9382,15 @@ found: bool strict_type_match = arg_type_is_release(arg_type) && meta->func_id != BPF_FUNC_sk_release; + if (type_may_be_null(reg->type) && + (!type_may_be_null(arg_type) || arg_type_is_release(arg_type))) { + verbose(env, "Possibly NULL pointer passed to helper arg%d\n", regno); + return -EACCES; + } + if (!arg_btf_id) { if (!compatible->btf_id) { - verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); + verifier_bug(env, "missing arg compatible BTF ID"); return -EFAULT; } arg_btf_id = compatible->btf_id; @@ -6268,24 +9411,58 @@ found: btf_vmlinux, *arg_btf_id, strict_type_match)) { verbose(env, "R%d is of type %s but %s is expected\n", - regno, kernel_type_name(reg->btf, reg->btf_id), - kernel_type_name(btf_vmlinux, *arg_btf_id)); + regno, btf_type_name(reg->btf, reg->btf_id), + btf_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } } - } else if (type_is_alloc(reg->type)) { - if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock) { - verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n"); + break; + } + case PTR_TO_BTF_ID | MEM_ALLOC: + case PTR_TO_BTF_ID | MEM_PERCPU | MEM_ALLOC: + if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock && + meta->func_id != BPF_FUNC_kptr_xchg) { + verifier_bug(env, "unimplemented handling of MEM_ALLOC"); return -EFAULT; } + /* Check if local kptr in src arg matches kptr in dst arg */ + if (meta->func_id == BPF_FUNC_kptr_xchg && regno == BPF_REG_2) { + if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) + return -EACCES; + } + break; + case PTR_TO_BTF_ID | MEM_PERCPU: + case PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU: + case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED: + /* Handled by helper specific checks */ + break; + default: + verifier_bug(env, "invalid PTR_TO_BTF_ID register for type match"); + return -EFAULT; } - return 0; } -int check_func_arg_reg_off(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type) +static struct btf_field * +reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields) +{ + struct btf_field *field; + struct btf_record *rec; + + rec = reg_btf_record(reg); + if (!rec) + return NULL; + + field = btf_record_find(rec, off, fields); + if (!field) + return NULL; + + return field; +} + +static int check_func_arg_reg_off(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + enum bpf_arg_type arg_type) { u32 type = reg->type; @@ -6304,6 +9481,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, */ if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK) return 0; + /* Doing check_ptr_off_reg check for the offset will catch this * because fixed_off_ok is false, but checking here allows us * to give the user a better error message. @@ -6328,6 +9506,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_MEM | MEM_RINGBUF: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: + case PTR_TO_ARENA: case SCALAR_VALUE: return 0; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows @@ -6337,7 +9516,8 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_RCU: - case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF: + case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU: /* When referenced PTR_TO_BTF_ID is passed to release function, * its fixed offset must be 0. In the other cases, fixed offset * can be non-zero. This was already checked above. So pass @@ -6351,27 +9531,194 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, } } -static u32 dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static struct bpf_reg_state *get_dynptr_arg_reg(struct bpf_verifier_env *env, + const struct bpf_func_proto *fn, + struct bpf_reg_state *regs) +{ + struct bpf_reg_state *state = NULL; + int i; + + for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) + if (arg_type_is_dynptr(fn->arg_type[i])) { + if (state) { + verbose(env, "verifier internal error: multiple dynptr args\n"); + return NULL; + } + state = ®s[BPF_REG_1 + i]; + } + + if (!state) + verbose(env, "verifier internal error: no dynptr arg found\n"); + + return state; +} + +static int dynptr_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) - return reg->ref_obj_id; + return reg->id; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + return state->stack[spi].spilled_ptr.id; +} - spi = get_spi(reg->off); +static int dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return reg->ref_obj_id; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; return state->stack[spi].spilled_ptr.ref_obj_id; } +static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env, + struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return reg->dynptr.type; + + spi = __get_spi(reg->off); + if (spi < 0) { + verbose(env, "verifier internal error: invalid spi when querying dynptr type\n"); + return BPF_DYNPTR_TYPE_INVALID; + } + + return state->stack[spi].spilled_ptr.dynptr.type; +} + +static int check_reg_const_str(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno) +{ + struct bpf_map *map = reg->map_ptr; + int err; + int map_off; + u64 map_addr; + char *str_ptr; + + if (reg->type != PTR_TO_MAP_VALUE) + return -EINVAL; + + if (!bpf_map_is_rdonly(map)) { + verbose(env, "R%d does not point to a readonly map'\n", regno); + return -EACCES; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d is not a constant address'\n", regno); + return -EACCES; + } + + if (!map->ops->map_direct_value_addr) { + verbose(env, "no direct value access support for this map type\n"); + return -EACCES; + } + + err = check_map_access(env, regno, reg->off, + map->value_size - reg->off, false, + ACCESS_HELPER); + if (err) + return err; + + map_off = reg->off + reg->var_off.value; + err = map->ops->map_direct_value_addr(map, &map_addr, map_off); + if (err) { + verbose(env, "direct value access on string failed\n"); + return err; + } + + str_ptr = (char *)(long)(map_addr); + if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) { + verbose(env, "string is not zero-terminated\n"); + return -EINVAL; + } + return 0; +} + +/* Returns constant key value in `value` if possible, else negative error */ +static int get_constant_map_key(struct bpf_verifier_env *env, + struct bpf_reg_state *key, + u32 key_size, + s64 *value) +{ + struct bpf_func_state *state = func(env, key); + struct bpf_reg_state *reg; + int slot, spi, off; + int spill_size = 0; + int zero_size = 0; + int stack_off; + int i, err; + u8 *stype; + + if (!env->bpf_capable) + return -EOPNOTSUPP; + if (key->type != PTR_TO_STACK) + return -EOPNOTSUPP; + if (!tnum_is_const(key->var_off)) + return -EOPNOTSUPP; + + stack_off = key->off + key->var_off.value; + slot = -stack_off - 1; + spi = slot / BPF_REG_SIZE; + off = slot % BPF_REG_SIZE; + stype = state->stack[spi].slot_type; + + /* First handle precisely tracked STACK_ZERO */ + for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--) + zero_size++; + if (zero_size >= key_size) { + *value = 0; + return 0; + } + + /* Check that stack contains a scalar spill of expected size */ + if (!is_spilled_scalar_reg(&state->stack[spi])) + return -EOPNOTSUPP; + for (i = off; i >= 0 && stype[i] == STACK_SPILL; i--) + spill_size++; + if (spill_size != key_size) + return -EOPNOTSUPP; + + reg = &state->stack[spi].spilled_ptr; + if (!tnum_is_const(reg->var_off)) + /* Stack value not statically known */ + return -EOPNOTSUPP; + + /* We are relying on a constant value. So mark as precise + * to prevent pruning on it. + */ + bt_set_frame_slot(&env->bt, key->frameno, spi); + err = mark_chain_precision_batch(env, env->cur_state); + if (err < 0) + return err; + + *value = reg->var_off.value; + return 0; +} + +static bool can_elide_value_nullness(enum bpf_map_type type); + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, - const struct bpf_func_proto *fn) + const struct bpf_func_proto *fn, + int insn_idx) { u32 regno = BPF_REG_1 + arg; struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_arg_type arg_type = fn->arg_type[arg]; enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; + u32 key_size; int err = 0; if (arg_type == ARG_DONTCARE) @@ -6433,9 +9780,8 @@ skip_type_check: * PTR_TO_STACK. */ if (reg->type == PTR_TO_STACK) { - spi = get_spi(reg->off); - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || - !state->stack[spi].spilled_ptr.ref_obj_id) { + spi = dynptr_get_spi(env, reg); + if (spi < 0 || !state->stack[spi].spilled_ptr.ref_obj_id) { verbose(env, "arg %d is an unacquired reference\n", regno); return -EINVAL; } @@ -6449,18 +9795,18 @@ skip_type_check: return -EINVAL; } if (meta->release_regno) { - verbose(env, "verifier internal error: more than one release argument\n"); + verifier_bug(env, "more than one release argument"); return -EFAULT; } meta->release_regno = regno; } - if (reg->ref_obj_id) { + if (reg->ref_obj_id && base_type(arg_type) != ARG_KPTR_XCHG_DEST) { if (meta->ref_obj_id) { - verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + verbose(env, "more than one arg with ref_obj_id R%d %u %u", regno, reg->ref_obj_id, meta->ref_obj_id); - return -EFAULT; + return -EACCES; } meta->ref_obj_id = reg->ref_obj_id; } @@ -6503,12 +9849,23 @@ skip_type_check: * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ - verbose(env, "invalid map_ptr to access map->key\n"); - return -EACCES; + verifier_bug(env, "invalid map_ptr to access map->key"); + return -EFAULT; + } + key_size = meta->map_ptr->key_size; + err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL); + if (err) + return err; + if (can_elide_value_nullness(meta->map_ptr->map_type)) { + err = get_constant_map_key(env, reg, key_size, &meta->const_map_key); + if (err < 0) { + meta->const_map_key = -1; + if (err == -EOPNOTSUPP) + err = 0; + else + return err; + } } - err = check_helper_mem_access(env, regno, - meta->map_ptr->key_size, false, - NULL); break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) @@ -6519,13 +9876,13 @@ skip_type_check: */ if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ - verbose(env, "invalid map_ptr to access map->value\n"); - return -EACCES; + verifier_bug(env, "invalid map_ptr to access map->value"); + return -EFAULT; } meta->raw_mode = arg_type & MEM_UNINIT; - err = check_helper_mem_access(env, regno, - meta->map_ptr->value_size, false, - meta); + err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); break; case ARG_PTR_TO_PERCPU_BTF_ID: if (!reg->btf_id) { @@ -6536,16 +9893,20 @@ skip_type_check: meta->ret_btf_id = reg->btf_id; break; case ARG_PTR_TO_SPIN_LOCK: + if (in_rbtree_lock_required_cb(env)) { + verbose(env, "can't spin_{lock,unlock} in rbtree cb\n"); + return -EACCES; + } if (meta->func_id == BPF_FUNC_spin_lock) { - err = process_spin_lock(env, regno, true); + err = process_spin_lock(env, regno, PROCESS_SPIN_LOCK); if (err) return err; } else if (meta->func_id == BPF_FUNC_spin_unlock) { - err = process_spin_lock(env, regno, false); + err = process_spin_lock(env, regno, 0); if (err) return err; } else { - verbose(env, "verifier internal error\n"); + verifier_bug(env, "spin lock arg on unexpected helper"); return -EFAULT; } break; @@ -6563,19 +9924,29 @@ skip_type_check: */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { - err = check_helper_mem_access(env, regno, - fn->arg_size[arg], false, - meta); + err = check_helper_mem_access(env, regno, fn->arg_size[arg], + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); + if (err) + return err; + if (arg_type & MEM_ALIGNED) + err = check_ptr_alignment(env, reg, 0, fn->arg_size[arg], true); } break; case ARG_CONST_SIZE: - err = check_mem_size_reg(env, reg, regno, false, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + false, meta); break; case ARG_CONST_SIZE_OR_ZERO: - err = check_mem_size_reg(env, reg, regno, true, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + true, meta); break; case ARG_PTR_TO_DYNPTR: - err = process_dynptr_func(env, regno, arg_type, meta); + err = process_dynptr_func(env, regno, insn_idx, arg_type, 0); if (err) return err; break; @@ -6590,60 +9961,14 @@ skip_type_check: if (err) return err; break; - case ARG_PTR_TO_INT: - case ARG_PTR_TO_LONG: - { - int size = int_ptr_type_to_size(arg_type); - - err = check_helper_mem_access(env, regno, size, false, meta); - if (err) - return err; - err = check_ptr_alignment(env, reg, 0, size, true); - break; - } case ARG_PTR_TO_CONST_STR: { - struct bpf_map *map = reg->map_ptr; - int map_off; - u64 map_addr; - char *str_ptr; - - if (!bpf_map_is_rdonly(map)) { - verbose(env, "R%d does not point to a readonly map'\n", regno); - return -EACCES; - } - - if (!tnum_is_const(reg->var_off)) { - verbose(env, "R%d is not a constant address'\n", regno); - return -EACCES; - } - - if (!map->ops->map_direct_value_addr) { - verbose(env, "no direct value access support for this map type\n"); - return -EACCES; - } - - err = check_map_access(env, regno, reg->off, - map->value_size - reg->off, false, - ACCESS_HELPER); + err = check_reg_const_str(env, reg, regno); if (err) return err; - - map_off = reg->off + reg->var_off.value; - err = map->ops->map_direct_value_addr(map, &map_addr, map_off); - if (err) { - verbose(env, "direct value access on string failed\n"); - return err; - } - - str_ptr = (char *)(long)(map_addr); - if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) { - verbose(env, "string is not zero-terminated\n"); - return -EINVAL; - } break; } - case ARG_PTR_TO_KPTR: + case ARG_KPTR_XCHG_DEST: err = process_kptr_func(env, regno, meta); if (err) return err; @@ -6658,7 +9983,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); - if (func_id != BPF_FUNC_map_update_elem) + if (func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these @@ -6669,6 +9995,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) if (eatype == BPF_TRACE_ITER) return true; break; + case BPF_PROG_TYPE_SOCK_OPS: + /* map_update allowed only via dedicated helpers with event type checks */ + if (func_id == BPF_FUNC_map_delete_elem) + return true; + break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: @@ -6764,7 +10095,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -6774,7 +10104,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -6794,22 +10123,26 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_MAP_TYPE_SK_STORAGE: if (func_id != BPF_FUNC_sk_storage_get && - func_id != BPF_FUNC_sk_storage_delete) + func_id != BPF_FUNC_sk_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_INODE_STORAGE: if (func_id != BPF_FUNC_inode_storage_get && - func_id != BPF_FUNC_inode_storage_delete) + func_id != BPF_FUNC_inode_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_TASK_STORAGE: if (func_id != BPF_FUNC_task_storage_get && - func_id != BPF_FUNC_task_storage_delete) + func_id != BPF_FUNC_task_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_CGRP_STORAGE: if (func_id != BPF_FUNC_cgrp_storage_get && - func_id != BPF_FUNC_cgrp_storage_delete) + func_id != BPF_FUNC_cgrp_storage_delete && + func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_BLOOM_FILTER: @@ -6817,6 +10150,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_map_push_elem) goto error; break; + case BPF_MAP_TYPE_INSN_ARRAY: + goto error; default: break; } @@ -6827,7 +10162,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) { - verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); + verbose(env, "mixing of tail_calls and bpf-to-bpf calls is not supported\n"); return -EINVAL; } break; @@ -6944,15 +10279,15 @@ static bool check_raw_mode_ok(const struct bpf_func_proto *fn) { int count = 0; - if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM) + if (arg_type_is_raw_mem(fn->arg1_type)) count++; - if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM) + if (arg_type_is_raw_mem(fn->arg2_type)) count++; - if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM) + if (arg_type_is_raw_mem(fn->arg3_type)) count++; - if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM) + if (arg_type_is_raw_mem(fn->arg4_type)) count++; - if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM) + if (arg_type_is_raw_mem(fn->arg5_type)) count++; /* We only support one arg being in raw mode at the moment, @@ -7023,6 +10358,9 @@ static int check_func_proto(const struct bpf_func_proto *fn, int func_id) /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. + * + * This also applies to dynptr slices belonging to skb and xdp dynptrs, + * since these slices point to packet data. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -7030,8 +10368,8 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(env, reg); + if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) + mark_reg_invalid(env, reg); })); } @@ -7061,32 +10399,56 @@ static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range reg->range = AT_PKT_END; } +static int release_reference_nomark(struct bpf_verifier_state *state, int ref_obj_id) +{ + int i; + + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].type != REF_TYPE_PTR) + continue; + if (state->refs[i].id == ref_obj_id) { + release_reference_state(state, i); + return 0; + } + } + return -EINVAL; +} + /* The pointer with the specified id has released its reference to kernel * resources. Identify all copies of the same pointer and clear the reference. + * + * This is the release function corresponding to acquire_reference(). Idempotent. */ -static int release_reference(struct bpf_verifier_env *env, - int ref_obj_id) +static int release_reference(struct bpf_verifier_env *env, int ref_obj_id) { + struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state; struct bpf_reg_state *reg; int err; - err = release_reference_state(cur_func(env), ref_obj_id); + err = release_reference_nomark(vstate, ref_obj_id); if (err) return err; - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg->ref_obj_id == ref_obj_id) { - if (!env->allow_ptr_leaks) - __mark_reg_not_init(env, reg); - else - __mark_reg_unknown(env, reg); - } + bpf_for_each_reg_in_vstate(vstate, state, reg, ({ + if (reg->ref_obj_id == ref_obj_id) + mark_reg_invalid(env, reg); })); return 0; } +static void invalidate_non_owning_refs(struct bpf_verifier_env *env) +{ + struct bpf_func_state *unused; + struct bpf_reg_state *reg; + + bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ + if (type_is_non_owning_ref(reg->type)) + mark_reg_invalid(env, reg); + })); +} + static void clear_caller_saved_regs(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { @@ -7095,7 +10457,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env, /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); - check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + __check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK); } } @@ -7108,15 +10470,12 @@ static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); -static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx, int subprog, - set_callee_state_fn set_callee_state_cb) +static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite, + set_callee_state_fn set_callee_state_cb, + struct bpf_verifier_state *state) { - struct bpf_verifier_state *state = env->cur_state; - struct bpf_func_info_aux *func_info_aux; struct bpf_func_state *caller, *callee; int err; - bool is_global = false; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -7124,120 +10483,319 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -E2BIG; } - caller = state->frame[state->curframe]; if (state->frame[state->curframe + 1]) { - verbose(env, "verifier bug. Frame %d already allocated\n", - state->curframe + 1); + verifier_bug(env, "Frame %d already allocated", state->curframe + 1); return -EFAULT; } - func_info_aux = env->prog->aux->func_info_aux; - if (func_info_aux) - is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_subprog_call(env, subprog, caller->regs); - if (err == -EFAULT) - return err; - if (is_global) { - if (err) { - verbose(env, "Caller passes invalid args into func#%d\n", - subprog); - return err; - } else { - if (env->log.level & BPF_LOG_LEVEL) - verbose(env, - "Func#%d is global and valid. Skipping.\n", - subprog); - clear_caller_saved_regs(env, caller->regs); + caller = state->frame[state->curframe]; + callee = kzalloc(sizeof(*callee), GFP_KERNEL_ACCOUNT); + if (!callee) + return -ENOMEM; + state->frame[state->curframe + 1] = callee; - /* All global functions return a 64-bit SCALAR_VALUE */ - mark_reg_unknown(env, caller->regs, BPF_REG_0); - caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; + /* callee cannot access r0, r6 - r9 for reading and has to write + * into its own stack before reading from it. + * callee can read/write into caller's stack + */ + init_func_state(env, callee, + /* remember the callsite, it will be used by bpf_exit */ + callsite, + state->curframe + 1 /* frameno within this callchain */, + subprog /* subprog number within this prog */); + err = set_callee_state_cb(env, caller, callee, callsite); + if (err) + goto err_out; - /* continue with next insn after call */ - return 0; + /* only increment it after check_reg_arg() finished */ + state->curframe++; + + return 0; + +err_out: + free_func_state(callee); + state->frame[state->curframe + 1] = NULL; + return err; +} + +static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, + const struct btf *btf, + struct bpf_reg_state *regs) +{ + struct bpf_subprog_info *sub = subprog_info(env, subprog); + struct bpf_verifier_log *log = &env->log; + u32 i; + int ret; + + ret = btf_prepare_func_args(env, subprog); + if (ret) + return ret; + + /* check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < sub->arg_cnt; i++) { + u32 regno = i + 1; + struct bpf_reg_state *reg = ®s[regno]; + struct bpf_subprog_arg_info *arg = &sub->args[i]; + + if (arg->arg_type == ARG_ANYTHING) { + if (reg->type != SCALAR_VALUE) { + bpf_log(log, "R%d is not a scalar\n", regno); + return -EINVAL; + } + } else if (arg->arg_type & PTR_UNTRUSTED) { + /* + * Anything is allowed for untrusted arguments, as these are + * read-only and probe read instructions would protect against + * invalid memory access. + */ + } else if (arg->arg_type == ARG_PTR_TO_CTX) { + ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); + if (ret < 0) + return ret; + /* If function expects ctx type in BTF check that caller + * is passing PTR_TO_CTX. + */ + if (reg->type != PTR_TO_CTX) { + bpf_log(log, "arg#%d expects pointer to ctx\n", i); + return -EINVAL; + } + } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { + ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); + if (ret < 0) + return ret; + if (check_mem_reg(env, reg, regno, arg->mem_size)) + return -EINVAL; + if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) { + bpf_log(log, "arg#%d is expected to be non-NULL\n", i); + return -EINVAL; + } + } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { + /* + * Can pass any value and the kernel won't crash, but + * only PTR_TO_ARENA or SCALAR make sense. Everything + * else is a bug in the bpf program. Point it out to + * the user at the verification time instead of + * run-time debug nightmare. + */ + if (reg->type != PTR_TO_ARENA && reg->type != SCALAR_VALUE) { + bpf_log(log, "R%d is not a pointer to arena or scalar.\n", regno); + return -EINVAL; + } + } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { + ret = check_func_arg_reg_off(env, reg, regno, ARG_PTR_TO_DYNPTR); + if (ret) + return ret; + + ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); + if (ret) + return ret; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + struct bpf_call_arg_meta meta; + int err; + + if (register_is_null(reg) && type_may_be_null(arg->arg_type)) + continue; + + memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ + err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); + err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); + if (err) + return err; + } else { + verifier_bug(env, "unrecognized arg#%d type %d", i, arg->arg_type); + return -EFAULT; } } + return 0; +} + +/* Compare BTF of a function call with given bpf_reg_state. + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - there is a type mismatch or BTF is not available. + * 0 - BTF matches with what bpf_reg_state expects. + * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. + */ +static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *regs) +{ + struct bpf_prog *prog = env->prog; + struct btf *btf = prog->aux->btf; + u32 btf_id; + int err; + + if (!prog->aux->func_info) + return -EINVAL; + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) + return -EFAULT; + + if (prog->aux->func_info_aux[subprog].unreliable) + return -EINVAL; + + err = btf_check_func_arg_match(env, subprog, btf, regs); + /* Compiler optimizations can remove arguments from static functions + * or mismatched type can be passed into a global function. + * In such cases mark the function as unreliable from BTF point of view. + */ + if (err) + prog->aux->func_info_aux[subprog].unreliable = true; + return err; +} + +static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int insn_idx, int subprog, + set_callee_state_fn set_callee_state_cb) +{ + struct bpf_verifier_state *state = env->cur_state, *callback_state; + struct bpf_func_state *caller, *callee; + int err; + + caller = state->frame[state->curframe]; + err = btf_check_subprog_call(env, subprog, caller->regs); + if (err == -EFAULT) + return err; + /* set_callee_state is used for direct subprog calls, but we are * interested in validating only BPF helpers that can call subprogs as * callbacks */ - if (set_callee_state_cb != set_callee_state && !is_callback_calling_function(insn->imm)) { - verbose(env, "verifier bug: helper %s#%d is not marked as callback-calling\n", - func_id_name(insn->imm), insn->imm); + env->subprog_info[subprog].is_cb = true; + if (bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_kfunc(insn->imm)) { + verifier_bug(env, "kfunc %s#%d not marked as callback-calling", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } else if (!bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_function(insn->imm)) { /* helper */ + verifier_bug(env, "helper %s#%d not marked as callback-calling", + func_id_name(insn->imm), insn->imm); return -EFAULT; } - if (insn->code == (BPF_JMP | BPF_CALL) && - insn->src_reg == 0 && - insn->imm == BPF_FUNC_timer_set_callback) { + 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); - if (!async_cb) - return -EFAULT; + insn_idx, subprog, + is_async_cb_sleepable(env, insn)); + if (IS_ERR(async_cb)) + return PTR_ERR(async_cb); callee = async_cb->frame[0]; callee->async_entry_cnt = caller->async_entry_cnt + 1; /* Convert bpf_timer_set_callback() args into timer callback args */ - err = set_callee_state_cb(env, caller, callee, *insn_idx); + err = set_callee_state_cb(env, caller, callee, insn_idx); if (err) return err; + return 0; + } + + /* for callback functions enqueue entry to callback and + * proceed with next instruction within current frame. + */ + callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false); + if (IS_ERR(callback_state)) + return PTR_ERR(callback_state); + + err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb, + callback_state); + if (err) + return err; + + callback_state->callback_unroll_depth++; + callback_state->frame[callback_state->curframe - 1]->callback_depth++; + caller->callback_depth = 0; + return 0; +} + +static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *caller; + int err, subprog, target_insn; + + target_insn = *insn_idx + insn->imm + 1; + subprog = find_subprog(env, target_insn); + if (verifier_bug_if(subprog < 0, env, "target of func call at insn %d is not a program", + target_insn)) + return -EFAULT; + + caller = state->frame[state->curframe]; + err = btf_check_subprog_call(env, subprog, caller->regs); + if (err == -EFAULT) + return err; + if (subprog_is_global(env, subprog)) { + const char *sub_name = subprog_name(env, subprog); + + if (env->cur_state->active_locks) { + verbose(env, "global function calls are not allowed while holding a lock,\n" + "use static function instead\n"); + return -EINVAL; + } + + if (env->subprog_info[subprog].might_sleep && + (env->cur_state->active_rcu_locks || env->cur_state->active_preempt_locks || + env->cur_state->active_irq_id || !in_sleepable(env))) { + verbose(env, "global functions that may sleep are not allowed in non-sleepable context,\n" + "i.e., in a RCU/IRQ/preempt-disabled section, or in\n" + "a non-sleepable BPF program context\n"); + return -EINVAL; + } + + if (err) { + verbose(env, "Caller passes invalid args into func#%d ('%s')\n", + subprog, sub_name); + return err; + } + + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, "Func#%d ('%s') is global and assumed valid.\n", + subprog, sub_name); + if (env->subprog_info[subprog].changes_pkt_data) + clear_all_pkt_pointers(env); + /* mark global subprog for verifying after main prog */ + subprog_aux(env, subprog)->called = true; clear_caller_saved_regs(env, caller->regs); + + /* All global functions return a 64-bit SCALAR_VALUE */ mark_reg_unknown(env, caller->regs, BPF_REG_0); caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; + /* continue with next insn after call */ return 0; } - callee = kzalloc(sizeof(*callee), GFP_KERNEL); - if (!callee) - return -ENOMEM; - state->frame[state->curframe + 1] = callee; - - /* callee cannot access r0, r6 - r9 for reading and has to write - * into its own stack before reading from it. - * callee can read/write into caller's stack + /* for regular function entry setup new frame and continue + * from that frame. */ - init_func_state(env, callee, - /* remember the callsite, it will be used by bpf_exit */ - *insn_idx /* callsite */, - state->curframe + 1 /* frameno within this callchain */, - subprog /* subprog number within this prog */); - - /* Transfer references to the callee */ - err = copy_reference_state(callee, caller); - if (err) - goto err_out; - - err = set_callee_state_cb(env, caller, callee, *insn_idx); + err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state); if (err) - goto err_out; + return err; clear_caller_saved_regs(env, caller->regs); - /* only increment it after check_reg_arg() finished */ - state->curframe++; - /* and go analyze first insn of the callee */ *insn_idx = env->subprog_info[subprog].start - 1; + bpf_reset_live_stack_callchain(env); + if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); - print_verifier_state(env, caller, true); + print_verifier_state(env, state, caller->frameno, true); verbose(env, "callee:\n"); - print_verifier_state(env, callee, true); + print_verifier_state(env, state, state->curframe, true); } - return 0; -err_out: - free_func_state(callee); - state->frame[state->curframe + 1] = NULL; - return err; + return 0; } int map_set_for_each_callback_args(struct bpf_verifier_env *env, @@ -7281,22 +10839,6 @@ static int set_callee_state(struct bpf_verifier_env *env, return 0; } -static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx) -{ - int subprog, target_insn; - - target_insn = *insn_idx + insn->imm + 1; - subprog = find_subprog(env, target_insn); - if (subprog < 0) { - verbose(env, "verifier bug. No program starts at insn %d\n", - target_insn); - return -EFAULT; - } - - return __check_func_call(env, insn, insn_idx, subprog, set_callee_state); -} - static int set_map_elem_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, @@ -7306,12 +10848,8 @@ 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"); @@ -7323,7 +10861,7 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return err; callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -7334,7 +10872,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env, { /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, * u64 flags); - * callback_fn(u32 index, void *callback_ctx); + * callback_fn(u64 index, void *callback_ctx); */ callee->regs[BPF_REG_1].type = SCALAR_VALUE; callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; @@ -7345,7 +10883,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -7375,7 +10913,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_async_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 0); return 0; } @@ -7394,7 +10932,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].btf = btf_vmlinux; - callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA], + callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; /* pointer to stack or null */ callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; @@ -7403,7 +10941,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -7417,7 +10955,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, * callback_fn(const struct bpf_dynptr_t* dynptr, void *callback_ctx); */ __mark_reg_not_init(env, &callee->regs[BPF_REG_0]); - mark_dynptr_cb_reg(&callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); + mark_dynptr_cb_reg(env, &callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ @@ -7426,17 +10964,118 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } -static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) +static int set_rbtree_add_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* void bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node, + * bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b)); + * + * 'struct bpf_rb_node *node' arg to bpf_rbtree_add_impl is the same PTR_TO_BTF_ID w/ offset + * that 'less' callback args will be receiving. However, 'node' arg was release_reference'd + * by this point, so look at 'root' + */ + struct btf_field *field; + + field = reg_find_field_offset(&caller->regs[BPF_REG_1], caller->regs[BPF_REG_1].off, + BPF_RB_ROOT); + if (!field || !field->graph_root.value_btf_id) + return -EFAULT; + + mark_reg_graph_node(callee->regs, BPF_REG_1, &field->graph_root); + ref_set_non_owning(env, &callee->regs[BPF_REG_1]); + mark_reg_graph_node(callee->regs, BPF_REG_2, &field->graph_root); + ref_set_non_owning(env, &callee->regs[BPF_REG_2]); + + __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_callback_fn = true; + callee->callback_ret_range = retval_range(0, 1); + return 0; +} + +static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + struct bpf_map *map_ptr = caller->regs[BPF_REG_3].map_ptr; + + /* + * callback_fn(struct bpf_map *map, void *key, void *value); + */ + callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; + __mark_reg_known_zero(&callee->regs[BPF_REG_1]); + callee->regs[BPF_REG_1].map_ptr = map_ptr; + + callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; + __mark_reg_known_zero(&callee->regs[BPF_REG_2]); + callee->regs[BPF_REG_2].map_ptr = map_ptr; + + callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; + __mark_reg_known_zero(&callee->regs[BPF_REG_3]); + callee->regs[BPF_REG_3].map_ptr = map_ptr; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_async_callback_fn = true; + callee->callback_ret_range = retval_range(S32_MIN, S32_MAX); + return 0; +} + +static bool is_rbtree_lock_required_kfunc(u32 btf_id); + +/* Are we currently verifying the callback for a rbtree helper that must + * be called with lock held? If so, no need to complain about unreleased + * lock + */ +static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) { struct bpf_verifier_state *state = env->cur_state; + struct bpf_insn *insn = env->prog->insnsi; + struct bpf_func_state *callee; + int kfunc_btf_id; + + if (!state->curframe) + return false; + + callee = state->frame[state->curframe]; + + if (!callee->in_callback_fn) + return false; + + kfunc_btf_id = insn[callee->callsite].imm; + return is_rbtree_lock_required_kfunc(kfunc_btf_id); +} + +static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg, + bool return_32bit) +{ + if (return_32bit) + return range.minval <= reg->s32_min_value && reg->s32_max_value <= range.maxval; + else + return range.minval <= reg->smin_value && reg->smax_value <= range.maxval; +} + +static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) +{ + struct bpf_verifier_state *state = env->cur_state, *prev_st; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; + bool in_callback_fn; int err; + err = bpf_update_live_stack(env); + if (err) + return err; + callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; if (r0->type == PTR_TO_STACK) { @@ -7452,66 +11091,109 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) caller = state->frame[state->curframe - 1]; if (callee->in_callback_fn) { - /* enforce R0 return value range [0, 1]. */ - struct tnum range = callee->callback_ret_range; - if (r0->type != SCALAR_VALUE) { verbose(env, "R0 not a scalar value\n"); return -EACCES; } - if (!tnum_in(range, r0->var_off)) { - verbose_invalid_scalar(env, r0, &range, "callback return", "R0"); + + /* we are going to rely on register's precise value */ + err = mark_chain_precision(env, BPF_REG_0); + if (err) + return err; + + /* enforce R0 return value range, and bpf_callback_t returns 64bit */ + if (!retval_range_within(callee->callback_ret_range, r0, false)) { + verbose_invalid_scalar(env, r0, callee->callback_ret_range, + "At callback return", "R0"); return -EINVAL; } + if (!bpf_calls_callback(env, callee->callsite)) { + verifier_bug(env, "in callback at %d, callsite %d !calls_callback", + *insn_idx, callee->callsite); + return -EFAULT; + } } else { /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; } - /* callback_fn frame should have released its own additions to parent's - * reference state at this point, or check_reference_leak would - * complain, hence it must be the same as the caller. There is no need - * to copy it back. + /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite, + * there function call logic would reschedule callback visit. If iteration + * converges is_state_visited() would prune that visit eventually. */ - if (!callee->in_callback_fn) { - /* Transfer references to the caller */ - err = copy_reference_state(caller, callee); - if (err) - return err; - } + in_callback_fn = callee->in_callback_fn; + if (in_callback_fn) + *insn_idx = callee->callsite; + else + *insn_idx = callee->callsite + 1; - *insn_idx = callee->callsite + 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); - print_verifier_state(env, callee, true); + print_verifier_state(env, state, callee->frameno, true); verbose(env, "to caller at %d:\n", *insn_idx); - print_verifier_state(env, caller, true); + print_verifier_state(env, state, caller->frameno, true); } - /* clear everything in the callee */ + /* clear everything in the callee. In case of exceptional exits using + * bpf_throw, this will be done by copy_verifier_state for extra frames. */ free_func_state(callee); state->frame[state->curframe--] = NULL; + + /* for callbacks widen imprecise scalars to make programs like below verify: + * + * struct ctx { int i; } + * void cb(int idx, struct ctx *ctx) { ctx->i++; ... } + * ... + * struct ctx = { .i = 0; } + * bpf_loop(100, cb, &ctx, 0); + * + * This is similar to what is done in process_iter_next_call() for open + * coded iterators. + */ + prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL; + if (prev_st) { + err = widen_imprecise_scalars(env, prev_st, state); + if (err) + return err; + } return 0; } -static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, - int func_id, - struct bpf_call_arg_meta *meta) +static int do_refine_retval_range(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, int ret_type, + int func_id, + struct bpf_call_arg_meta *meta) { struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; - if (ret_type != RET_INTEGER || - (func_id != BPF_FUNC_get_stack && - func_id != BPF_FUNC_get_task_stack && - func_id != BPF_FUNC_probe_read_str && - func_id != BPF_FUNC_probe_read_kernel_str && - func_id != BPF_FUNC_probe_read_user_str)) - return; + if (ret_type != RET_INTEGER) + return 0; + + switch (func_id) { + case BPF_FUNC_get_stack: + case BPF_FUNC_get_task_stack: + case BPF_FUNC_probe_read_str: + case BPF_FUNC_probe_read_kernel_str: + case BPF_FUNC_probe_read_user_str: + ret_reg->smax_value = meta->msize_max_value; + ret_reg->s32_max_value = meta->msize_max_value; + ret_reg->smin_value = -MAX_ERRNO; + ret_reg->s32_min_value = -MAX_ERRNO; + reg_bounds_sync(ret_reg); + break; + case BPF_FUNC_get_smp_processor_id: + ret_reg->umax_value = nr_cpu_ids - 1; + ret_reg->u32_max_value = nr_cpu_ids - 1; + ret_reg->smax_value = nr_cpu_ids - 1; + ret_reg->s32_max_value = nr_cpu_ids - 1; + ret_reg->umin_value = 0; + ret_reg->u32_min_value = 0; + ret_reg->smin_value = 0; + ret_reg->s32_min_value = 0; + reg_bounds_sync(ret_reg); + break; + } - ret_reg->smax_value = meta->msize_max_value; - ret_reg->s32_max_value = meta->msize_max_value; - ret_reg->smin_value = -MAX_ERRNO; - ret_reg->s32_min_value = -MAX_ERRNO; - reg_bounds_sync(ret_reg); + return reg_bounds_sanity_check(env, ret_reg, "retval"); } static int @@ -7534,8 +11216,8 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; if (map == NULL) { - verbose(env, "kernel subsystem misconfigured verifier\n"); - return -EINVAL; + verifier_bug(env, "expected map for helper call"); + return -EFAULT; } /* In case of read-only, some additional restrictions @@ -7551,12 +11233,12 @@ 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; } @@ -7573,7 +11255,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, if (func_id != BPF_FUNC_tail_call) return 0; if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) { - verbose(env, "kernel subsystem misconfigured verifier\n"); + verbose(env, "expected prog array map for tail call"); return -EINVAL; } @@ -7581,7 +11263,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, val = reg->var_off.value; max = map->max_entries; - if (!(register_is_const(reg) && val < max)) { + if (!(is_reg_const(reg, false) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } @@ -7597,17 +11279,25 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } -static int check_reference_leak(struct bpf_verifier_env *env) +static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit) { - struct bpf_func_state *state = cur_func(env); + struct bpf_verifier_state *state = env->cur_state; + enum bpf_prog_type type = resolve_prog_type(env->prog); + struct bpf_reg_state *reg = reg_state(env, BPF_REG_0); bool refs_lingering = false; int i; - if (state->frameno && !state->in_callback_fn) + if (!exception_exit && cur_func(env)->frameno) return 0; for (i = 0; i < state->acquired_refs; i++) { - if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno) + if (state->refs[i].type != REF_TYPE_PTR) + continue; + /* Allow struct_ops programs to return a referenced kptr back to + * kernel. Type checks are performed later in check_return_code. + */ + if (type == BPF_PROG_TYPE_STRUCT_OPS && !exception_exit && + reg->ref_obj_id == state->refs[i].id) continue; verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); @@ -7616,12 +11306,46 @@ static int check_reference_leak(struct bpf_verifier_env *env) return refs_lingering ? -EINVAL : 0; } +static int check_resource_leak(struct bpf_verifier_env *env, bool exception_exit, bool check_lock, const char *prefix) +{ + int err; + + if (check_lock && env->cur_state->active_locks) { + verbose(env, "%s cannot be used inside bpf_spin_lock-ed region\n", prefix); + return -EINVAL; + } + + err = check_reference_leak(env, exception_exit); + if (err) { + verbose(env, "%s would lead to reference leak\n", prefix); + return err; + } + + if (check_lock && env->cur_state->active_irq_id) { + verbose(env, "%s cannot be used inside bpf_local_irq_save-ed region\n", prefix); + return -EINVAL; + } + + if (check_lock && env->cur_state->active_rcu_locks) { + verbose(env, "%s cannot be used inside bpf_rcu_read_lock-ed region\n", prefix); + return -EINVAL; + } + + if (check_lock && env->cur_state->active_preempt_locks) { + verbose(env, "%s cannot be used inside bpf_preempt_disable-ed region\n", prefix); + return -EINVAL; + } + + return 0; +} + static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5]; struct bpf_map *fmt_map = fmt_reg->map_ptr; + struct bpf_bprintf_data data = {}; int err, fmt_map_off, num_args; u64 fmt_addr; char *fmt; @@ -7638,7 +11362,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr, fmt_map_off); if (err) { - verbose(env, "verifier bug\n"); + verbose(env, "failed to retrieve map value address\n"); return -EFAULT; } fmt = (char *)(long)fmt_addr + fmt_map_off; @@ -7646,7 +11370,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, /* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we * can focus on validating the format specifiers. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data); if (err < 0) verbose(env, "Invalid format string\n"); @@ -7674,7 +11398,7 @@ static int check_get_func_ip(struct bpf_verifier_env *env) return -ENOTSUPP; } -static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) +static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env) { return &env->insn_aux_data[env->insn_idx]; } @@ -7709,10 +11433,48 @@ static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno state->callback_subprogno == subprogno); } +/* Returns whether or not the given map type can potentially elide + * lookup return value nullness check. This is possible if the key + * is statically known. + */ +static bool can_elide_value_nullness(enum bpf_map_type type) +{ + switch (type) { + case BPF_MAP_TYPE_ARRAY: + case BPF_MAP_TYPE_PERCPU_ARRAY: + return true; + default: + return false; + } +} + +static int get_helper_proto(struct bpf_verifier_env *env, int func_id, + const struct bpf_func_proto **ptr) +{ + if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) + return -ERANGE; + + if (!env->ops->get_func_proto) + return -EINVAL; + + *ptr = env->ops->get_func_proto(func_id, env->prog); + return *ptr && (*ptr)->func ? 0 : -EINVAL; +} + +/* Check if we're in a sleepable context. */ +static inline bool in_sleepable_context(struct bpf_verifier_env *env) +{ + return !env->cur_state->active_rcu_locks && + !env->cur_state->active_preempt_locks && + !env->cur_state->active_irq_id && + in_sleepable(env); +} + static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); + bool returns_cpu_specific_alloc_ptr = false; const struct bpf_func_proto *fn = NULL; enum bpf_return_type ret_type; enum bpf_type_flag ret_flag; @@ -7724,18 +11486,16 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn /* find function prototype */ func_id = insn->imm; - if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { - verbose(env, "invalid func %s#%d\n", func_id_name(func_id), - func_id); + err = get_helper_proto(env, insn->imm, &fn); + if (err == -ERANGE) { + verbose(env, "invalid func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } - 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); - return -EINVAL; + if (err) { + verbose(env, "program of this type cannot use helper %s#%d\n", + func_id_name(func_id), func_id); + return err; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ @@ -7749,17 +11509,16 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (!env->prog->aux->sleepable && fn->might_sleep) { + if (!in_sleepable(env) && fn->might_sleep) { verbose(env, "helper call might sleep in a non-sleepable prog\n"); return -EINVAL; } /* With LD_ABS/IND some JITs save/restore skb from r1. */ - changes_data = bpf_helper_changes_pkt_data(fn->func); + changes_data = bpf_helper_changes_pkt_data(func_id); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { - verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n", - func_id_name(func_id), func_id); - return -EINVAL; + verifier_bug(env, "func %s#%d: r1 != ctx", func_id_name(func_id), func_id); + return -EFAULT; } memset(&meta, 0, sizeof(meta)); @@ -7767,26 +11526,42 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn err = check_func_proto(fn, func_id); if (err) { - verbose(env, "kernel subsystem misconfigured func %s#%d\n", - func_id_name(func_id), func_id); + verifier_bug(env, "incorrect func proto %s#%d", func_id_name(func_id), func_id); return err; } - if (env->cur_state->active_rcu_lock) { + if (env->cur_state->active_rcu_locks) { if (fn->might_sleep) { verbose(env, "sleepable helper %s#%d in rcu_read_lock region\n", func_id_name(func_id), func_id); return -EINVAL; } + } + + if (env->cur_state->active_preempt_locks) { + 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 (env->prog->aux->sleepable && is_storage_get_function(func_id)) - env->insn_aux_data[insn_idx].storage_get_func_atomic = true; + if (env->cur_state->active_irq_id) { + if (fn->might_sleep) { + verbose(env, "sleepable helper %s#%d in IRQ-disabled region\n", + func_id_name(func_id), func_id); + return -EINVAL; + } } + /* Track non-sleepable context for helpers. */ + if (!in_sleepable_context(env)) + env->insn_aux_data[insn_idx].non_sleepable = true; + meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { - err = check_func_arg(env, i, &meta, fn); + err = check_func_arg(env, i, &meta, fn, insn_idx); if (err) return err; } @@ -7804,49 +11579,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn */ for (i = 0; i < meta.access_size; i++) { err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, - BPF_WRITE, -1, false); + BPF_WRITE, -1, false, false); if (err) return err; } regs = cur_regs(env); - /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot - * be reinitialized by any dynptr helper. Hence, mark_stack_slots_dynptr - * is safe to do directly. - */ - if (meta.uninit_dynptr_regno) { - if (regs[meta.uninit_dynptr_regno].type == CONST_PTR_TO_DYNPTR) { - verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be initialized\n"); - return -EFAULT; - } - /* we write BPF_DW bits (8 bytes) at a time */ - for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { - err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno, - i, BPF_DW, BPF_WRITE, -1, false); - if (err) - return err; - } - - err = mark_stack_slots_dynptr(env, ®s[meta.uninit_dynptr_regno], - fn->arg_type[meta.uninit_dynptr_regno - BPF_REG_1], - insn_idx); - if (err) - return err; - } - if (meta.release_regno) { err = -EINVAL; - /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot - * be released by any dynptr helper. Hence, unmark_stack_slots_dynptr - * is safe to do directly. - */ if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) { - if (regs[meta.release_regno].type == CONST_PTR_TO_DYNPTR) { - verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be released\n"); - return -EFAULT; - } err = unmark_stack_slots_dynptr(env, ®s[meta.release_regno]); + } else if (func_id == BPF_FUNC_kptr_xchg && meta.ref_obj_id) { + u32 ref_obj_id = meta.ref_obj_id; + bool in_rcu = in_rcu_cs(env); + struct bpf_func_state *state; + struct bpf_reg_state *reg; + + err = release_reference_nomark(env->cur_state, ref_obj_id); + if (!err) { + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + if (reg->ref_obj_id == ref_obj_id) { + if (in_rcu && (reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU)) { + reg->ref_obj_id = 0; + reg->type &= ~MEM_ALLOC; + reg->type |= MEM_RCU; + } else { + mark_reg_invalid(env, reg); + } + } + })); + } } else if (meta.ref_obj_id) { err = release_reference(env, meta.ref_obj_id); } else if (register_is_null(®s[meta.release_regno])) { @@ -7864,11 +11627,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn switch (func_id) { case BPF_FUNC_tail_call: - err = check_reference_leak(env); - if (err) { - verbose(env, "tail_call would lead to reference leak\n"); + err = check_resource_leak(env, false, true, "tail_call"); + if (err) return err; - } break; case BPF_FUNC_get_local_storage: /* check that flags argument in get_local_storage(map, flags) is 0, @@ -7880,24 +11641,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } break; case BPF_FUNC_for_each_map_elem: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_map_elem_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_map_elem_callback_state); break; case BPF_FUNC_timer_set_callback: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_timer_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_timer_callback_state); break; case BPF_FUNC_find_vma: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_find_vma_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_find_vma_callback_state); break; case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: update_loop_inline_state(env, meta.subprogno); - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_loop_callback_state); + /* Verifier relies on R1 value to determine if bpf_loop() iteration + * is finished, thus mark it precise. + */ + err = mark_chain_precision(env, BPF_REG_1); + if (err) + return err; + if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_loop_callback_state); + } else { + cur_func(env)->callback_depth = 0; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "frame%d bpf_loop iteration limit reached\n", + env->cur_state->curframe); + } break; case BPF_FUNC_dynptr_from_mem: if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) { @@ -7919,27 +11693,83 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } break; case BPF_FUNC_dynptr_data: - for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { - if (arg_type_is_dynptr(fn->arg_type[i])) { - struct bpf_reg_state *reg = ®s[BPF_REG_1 + i]; + { + struct bpf_reg_state *reg; + int id, ref_obj_id; - if (meta.ref_obj_id) { - verbose(env, "verifier internal error: meta.ref_obj_id already set\n"); - return -EFAULT; - } + reg = get_dynptr_arg_reg(env, fn, regs); + if (!reg) + return -EFAULT; - meta.ref_obj_id = dynptr_ref_obj_id(env, reg); - break; - } + + if (meta.dynptr_id) { + verifier_bug(env, "meta.dynptr_id already set"); + return -EFAULT; + } + if (meta.ref_obj_id) { + verifier_bug(env, "meta.ref_obj_id already set"); + return -EFAULT; } - if (i == MAX_BPF_FUNC_REG_ARGS) { - verbose(env, "verifier internal error: no dynptr in bpf_dynptr_data()\n"); + + id = dynptr_id(env, reg); + if (id < 0) { + verifier_bug(env, "failed to obtain dynptr id"); + return id; + } + + ref_obj_id = dynptr_ref_obj_id(env, reg); + if (ref_obj_id < 0) { + verifier_bug(env, "failed to obtain dynptr ref_obj_id"); + return ref_obj_id; + } + + meta.dynptr_id = id; + meta.ref_obj_id = ref_obj_id; + + break; + } + case BPF_FUNC_dynptr_write: + { + enum bpf_dynptr_type dynptr_type; + struct bpf_reg_state *reg; + + reg = get_dynptr_arg_reg(env, fn, regs); + if (!reg) + return -EFAULT; + + dynptr_type = dynptr_get_type(env, reg); + if (dynptr_type == BPF_DYNPTR_TYPE_INVALID) return -EFAULT; + + if (dynptr_type == BPF_DYNPTR_TYPE_SKB || + dynptr_type == BPF_DYNPTR_TYPE_SKB_META) + /* this will trigger clear_all_pkt_pointers(), which will + * invalidate all dynptr slices associated with the skb + */ + changes_data = true; + + break; + } + case BPF_FUNC_per_cpu_ptr: + case BPF_FUNC_this_cpu_ptr: + { + struct bpf_reg_state *reg = ®s[BPF_REG_1]; + const struct btf_type *type; + + if (reg->type & MEM_RCU) { + type = btf_type_by_id(reg->btf, reg->btf_id); + if (!type || !btf_type_is_struct(type)) { + verbose(env, "Helper has invalid btf/btf_id in R1\n"); + return -EFAULT; + } + returns_cpu_specific_alloc_ptr = true; + env->insn_aux_data[insn_idx].call_with_percpu_alloc_ptr = true; } break; + } case BPF_FUNC_user_ringbuf_drain: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_user_ringbuf_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_user_ringbuf_callback_state); break; } @@ -7975,15 +11805,21 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn * to map element returned from bpf_map_lookup_elem() */ if (meta.map_ptr == NULL) { - verbose(env, - "kernel subsystem misconfigured verifier\n"); - return -EINVAL; + verifier_bug(env, "unexpected null map_ptr"); + return -EFAULT; } + + if (func_id == BPF_FUNC_map_lookup_elem && + can_elide_value_nullness(meta.map_ptr->map_type) && + meta.const_map_key >= 0 && + meta.const_map_key < meta.map_ptr->max_entries) + ret_flag &= ~PTR_MAYBE_NULL; + regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; - if (!type_may_be_null(ret_type) && - btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK)) { + if (!type_may_be_null(ret_flag) && + btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK)) { regs[BPF_REG_0].id = ++env->id_gen; } break; @@ -8026,14 +11862,18 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = tsize; } else { - /* MEM_RDONLY may be carried from ret_flag, but it - * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise - * it will confuse the check of PTR_TO_BTF_ID in - * check_mem_access(). - */ - ret_flag &= ~MEM_RDONLY; + if (returns_cpu_specific_alloc_ptr) { + regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU; + } else { + /* MEM_RDONLY may be carried from ret_flag, but it + * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise + * it will confuse the check of PTR_TO_BTF_ID in + * check_mem_access(). + */ + ret_flag &= ~MEM_RDONLY; + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; + } - regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } @@ -8049,12 +11889,16 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (func_id == BPF_FUNC_kptr_xchg) { ret_btf = meta.kptr_field->kptr.btf; ret_btf_id = meta.kptr_field->kptr.btf_id; + if (!btf_is_kernel(ret_btf)) { + regs[BPF_REG_0].type |= MEM_ALLOC; + if (meta.kptr_field->type == BPF_KPTR_PERCPU) + regs[BPF_REG_0].type |= MEM_PERCPU; + } } else { if (fn->ret_btf_id == BPF_PTR_POISON) { - verbose(env, "verifier internal error:"); - verbose(env, "func %s has non-overwritten BPF_PTR_POISON return type\n", - func_id_name(func_id)); - return -EINVAL; + verifier_bug(env, "func %s has non-overwritten BPF_PTR_POISON return type", + func_id_name(func_id)); + return -EFAULT; } ret_btf = btf_vmlinux; ret_btf_id = *fn->ret_btf_id; @@ -8079,16 +11923,19 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].id = ++env->id_gen; if (helper_multiple_ref_obj_use(func_id, meta.map_ptr)) { - verbose(env, "verifier internal error: func %s#%d sets ref_obj_id more than once\n", - func_id_name(func_id), func_id); + verifier_bug(env, "func %s#%d sets ref_obj_id more than once", + func_id_name(func_id), func_id); return -EFAULT; } + if (is_dynptr_ref_function(func_id)) + regs[BPF_REG_0].dynptr_id = meta.dynptr_id; + if (is_ptr_cast_function(func_id) || is_dynptr_ref_function(func_id)) { /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else if (is_acquire_function(func_id, meta.map_ptr)) { - int id = acquire_reference_state(env, insn_idx); + int id = acquire_reference(env, insn_idx); if (id < 0) return id; @@ -8098,7 +11945,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].ref_obj_id = id; } - do_refine_retval_range(regs, fn->ret_type, func_id, &meta); + err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta); + if (err) + return err; err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) @@ -8133,6 +11982,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn env->prog->call_get_func_ip = true; } + if (func_id == BPF_FUNC_tail_call) { + if (env->cur_state->curframe) { + struct bpf_verifier_state *branch; + + mark_reg_scratched(env, BPF_REG_0); + branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); + if (IS_ERR(branch)) + return PTR_ERR(branch); + clear_all_pkt_pointers(env); + mark_reg_unknown(env, regs, BPF_REG_0); + err = prepare_func_exit(env, &env->insn_idx); + if (err) + return err; + env->insn_idx--; + } else { + changes_data = false; + } + } + if (changes_data) clear_all_pkt_pointers(env); return 0; @@ -8141,61 +12009,30 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn /* mark_btf_func_reg_size() is used when the reg size is determined by * the BTF func_proto's return value size and argument. */ -static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, - size_t reg_size) +static void __mark_btf_func_reg_size(struct bpf_verifier_env *env, struct bpf_reg_state *regs, + u32 regno, size_t reg_size) { - struct bpf_reg_state *reg = &cur_regs(env)[regno]; + struct bpf_reg_state *reg = ®s[regno]; if (regno == BPF_REG_0) { /* Function return value */ - reg->live |= REG_LIVE_WRITTEN; reg->subreg_def = reg_size == sizeof(u64) ? DEF_NOT_SUBREG : env->insn_idx + 1; - } else { + } else if (reg_size == sizeof(u64)) { /* Function argument */ - if (reg_size == sizeof(u64)) { - mark_insn_zext(env, reg); - mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); - } else { - mark_reg_read(env, reg, reg->parent, REG_LIVE_READ32); - } + mark_insn_zext(env, reg); } } -struct bpf_kfunc_call_arg_meta { - /* In parameters */ - struct btf *btf; - u32 func_id; - u32 kfunc_flags; - const struct btf_type *func_proto; - const char *func_name; - /* Out parameters */ - u32 ref_obj_id; - u8 release_regno; - bool r0_rdonly; - u32 ret_btf_id; - u64 r0_size; - struct { - u64 value; - bool found; - } arg_constant; - struct { - struct btf *btf; - u32 btf_id; - } arg_obj_drop; - struct { - struct btf_field *field; - } arg_list_head; -}; - -static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) +static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, + size_t reg_size) { - return meta->kfunc_flags & KF_ACQUIRE; + return __mark_btf_func_reg_size(env, cur_regs(env), regno, reg_size); } -static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) +static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) { - return meta->kfunc_flags & KF_RET_NULL; + return meta->kfunc_flags & KF_ACQUIRE; } static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) @@ -8205,7 +12042,7 @@ static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) static bool is_kfunc_trusted_args(struct bpf_kfunc_call_arg_meta *meta) { - return meta->kfunc_flags & KF_TRUSTED_ARGS; + return (meta->kfunc_flags & KF_TRUSTED_ARGS) || is_kfunc_release(meta); } static bool is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) @@ -8223,32 +12060,27 @@ static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_RCU; } -static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg) +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) { - return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET); + return meta->kfunc_flags & KF_RCU_PROTECTED; } -static bool __kfunc_param_match_suffix(const struct btf *btf, - const struct btf_param *arg, - const char *suffix) +static bool is_kfunc_arg_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) { - int suffix_len = strlen(suffix), len; - const char *param_name; + const struct btf_type *t; - /* In the future, this can be ported to use BTF tagging */ - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len < suffix_len) + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - param_name += len - suffix_len; - return !strncmp(param_name, suffix, suffix_len); + + return btf_param_match_suffix(btf, arg, "__sz"); } -static bool is_kfunc_arg_mem_size(const struct btf *btf, - const struct btf_param *arg, - const struct bpf_reg_state *reg) +static bool is_kfunc_arg_const_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) { const struct btf_type *t; @@ -8256,22 +12088,62 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__sz"); + return btf_param_match_suffix(btf, arg, "__szk"); +} + +static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__opt"); } static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__k"); + return btf_param_match_suffix(btf, arg, "__k"); } static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__ign"); + return btf_param_match_suffix(btf, arg, "__ign"); +} + +static bool is_kfunc_arg_map(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__map"); } static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__alloc"); + return btf_param_match_suffix(btf, arg, "__alloc"); +} + +static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__uninit"); +} + +static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); +} + +static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__nullable"); +} + +static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__str"); +} + +static bool is_kfunc_arg_irq_flag(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__irq_flag"); +} + +static bool is_kfunc_arg_prog(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__prog"); } static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, @@ -8297,12 +12169,22 @@ enum { KF_ARG_DYNPTR_ID, KF_ARG_LIST_HEAD_ID, KF_ARG_LIST_NODE_ID, + KF_ARG_RB_ROOT_ID, + KF_ARG_RB_NODE_ID, + KF_ARG_WORKQUEUE_ID, + KF_ARG_RES_SPIN_LOCK_ID, + KF_ARG_TASK_WORK_ID, }; BTF_ID_LIST(kf_arg_btf_ids) -BTF_ID(struct, bpf_dynptr_kern) +BTF_ID(struct, bpf_dynptr) 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) +BTF_ID(struct, bpf_res_spin_lock) +BTF_ID(struct, bpf_task_work) static bool __is_kfunc_ptr_arg_type(const struct btf *btf, const struct btf_param *arg, int type) @@ -8336,6 +12218,53 @@ static bool is_kfunc_arg_list_node(const struct btf *btf, const struct btf_param return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_NODE_ID); } +static bool is_kfunc_arg_rbtree_root(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_ROOT_ID); +} + +static bool is_kfunc_arg_rbtree_node(const struct btf *btf, const struct btf_param *arg) +{ + 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_task_work(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_TASK_WORK_ID); +} + +static bool is_kfunc_arg_res_spin_lock(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RES_SPIN_LOCK_ID); +} + +static bool is_rbtree_node_type(const struct btf_type *t) +{ + return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_RB_NODE_ID]); +} + +static bool is_list_node_type(const struct btf_type *t) +{ + return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_LIST_NODE_ID]); +} + +static bool is_kfunc_arg_callback(struct bpf_verifier_env *env, const struct btf *btf, + const struct btf_param *arg) +{ + const struct btf_type *t; + + t = btf_type_resolve_func_ptr(btf, arg->type, NULL); + if (!t) + return false; + + return true; +} + /* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, const struct btf *btf, @@ -8376,62 +12305,171 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, return true; } - -static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { -#ifdef CONFIG_NET - [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], - [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], - [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], -#endif -}; - enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_CTX, - KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */ - KF_ARG_PTR_TO_KPTR, /* PTR_TO_KPTR but type specific */ + KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */ + KF_ARG_PTR_TO_REFCOUNTED_KPTR, /* Refcounted local kptr */ KF_ARG_PTR_TO_DYNPTR, + KF_ARG_PTR_TO_ITER, KF_ARG_PTR_TO_LIST_HEAD, KF_ARG_PTR_TO_LIST_NODE, - KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ + KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ KF_ARG_PTR_TO_MEM, - KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ + KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ + KF_ARG_PTR_TO_CALLBACK, + KF_ARG_PTR_TO_RB_ROOT, + KF_ARG_PTR_TO_RB_NODE, + KF_ARG_PTR_TO_NULL, + KF_ARG_PTR_TO_CONST_STR, + KF_ARG_PTR_TO_MAP, + KF_ARG_PTR_TO_WORKQUEUE, + KF_ARG_PTR_TO_IRQ_FLAG, + KF_ARG_PTR_TO_RES_SPIN_LOCK, + KF_ARG_PTR_TO_TASK_WORK, }; enum special_kfunc_type { KF_bpf_obj_new_impl, KF_bpf_obj_drop_impl, - KF_bpf_list_push_front, - KF_bpf_list_push_back, + KF_bpf_refcount_acquire_impl, + KF_bpf_list_push_front_impl, + KF_bpf_list_push_back_impl, KF_bpf_list_pop_front, KF_bpf_list_pop_back, + KF_bpf_list_front, + KF_bpf_list_back, KF_bpf_cast_to_kern_ctx, KF_bpf_rdonly_cast, KF_bpf_rcu_read_lock, KF_bpf_rcu_read_unlock, + KF_bpf_rbtree_remove, + KF_bpf_rbtree_add_impl, + KF_bpf_rbtree_first, + KF_bpf_rbtree_root, + KF_bpf_rbtree_left, + KF_bpf_rbtree_right, + KF_bpf_dynptr_from_skb, + KF_bpf_dynptr_from_xdp, + KF_bpf_dynptr_from_skb_meta, + KF_bpf_xdp_pull_data, + KF_bpf_dynptr_slice, + KF_bpf_dynptr_slice_rdwr, + KF_bpf_dynptr_clone, + 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, + KF_bpf_get_kmem_cache, + KF_bpf_local_irq_save, + KF_bpf_local_irq_restore, + KF_bpf_iter_num_new, + KF_bpf_iter_num_next, + KF_bpf_iter_num_destroy, + KF_bpf_set_dentry_xattr, + KF_bpf_remove_dentry_xattr, + KF_bpf_res_spin_lock, + KF_bpf_res_spin_unlock, + KF_bpf_res_spin_lock_irqsave, + KF_bpf_res_spin_unlock_irqrestore, + KF_bpf_dynptr_from_file, + KF_bpf_dynptr_file_discard, + KF___bpf_trap, + KF_bpf_task_work_schedule_signal_impl, + KF_bpf_task_work_schedule_resume_impl, }; -BTF_SET_START(special_kfunc_set) -BTF_ID(func, bpf_obj_new_impl) -BTF_ID(func, bpf_obj_drop_impl) -BTF_ID(func, bpf_list_push_front) -BTF_ID(func, bpf_list_push_back) -BTF_ID(func, bpf_list_pop_front) -BTF_ID(func, bpf_list_pop_back) -BTF_ID(func, bpf_cast_to_kern_ctx) -BTF_ID(func, bpf_rdonly_cast) -BTF_SET_END(special_kfunc_set) - BTF_ID_LIST(special_kfunc_list) BTF_ID(func, bpf_obj_new_impl) BTF_ID(func, bpf_obj_drop_impl) -BTF_ID(func, bpf_list_push_front) -BTF_ID(func, bpf_list_push_back) +BTF_ID(func, bpf_refcount_acquire_impl) +BTF_ID(func, bpf_list_push_front_impl) +BTF_ID(func, bpf_list_push_back_impl) BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) +BTF_ID(func, bpf_list_front) +BTF_ID(func, bpf_list_back) BTF_ID(func, bpf_cast_to_kern_ctx) BTF_ID(func, bpf_rdonly_cast) BTF_ID(func, bpf_rcu_read_lock) BTF_ID(func, bpf_rcu_read_unlock) +BTF_ID(func, bpf_rbtree_remove) +BTF_ID(func, bpf_rbtree_add_impl) +BTF_ID(func, bpf_rbtree_first) +BTF_ID(func, bpf_rbtree_root) +BTF_ID(func, bpf_rbtree_left) +BTF_ID(func, bpf_rbtree_right) +#ifdef CONFIG_NET +BTF_ID(func, bpf_dynptr_from_skb) +BTF_ID(func, bpf_dynptr_from_xdp) +BTF_ID(func, bpf_dynptr_from_skb_meta) +BTF_ID(func, bpf_xdp_pull_data) +#else +BTF_ID_UNUSED +BTF_ID_UNUSED +BTF_ID_UNUSED +BTF_ID_UNUSED +#endif +BTF_ID(func, bpf_dynptr_slice) +BTF_ID(func, bpf_dynptr_slice_rdwr) +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 +#ifdef CONFIG_BPF_EVENTS +BTF_ID(func, bpf_session_cookie) +#else +BTF_ID_UNUSED +#endif +BTF_ID(func, bpf_get_kmem_cache) +BTF_ID(func, bpf_local_irq_save) +BTF_ID(func, bpf_local_irq_restore) +BTF_ID(func, bpf_iter_num_new) +BTF_ID(func, bpf_iter_num_next) +BTF_ID(func, bpf_iter_num_destroy) +#ifdef CONFIG_BPF_LSM +BTF_ID(func, bpf_set_dentry_xattr) +BTF_ID(func, bpf_remove_dentry_xattr) +#else +BTF_ID_UNUSED +BTF_ID_UNUSED +#endif +BTF_ID(func, bpf_res_spin_lock) +BTF_ID(func, bpf_res_spin_unlock) +BTF_ID(func, bpf_res_spin_lock_irqsave) +BTF_ID(func, bpf_res_spin_unlock_irqrestore) +BTF_ID(func, bpf_dynptr_from_file) +BTF_ID(func, bpf_dynptr_file_discard) +BTF_ID(func, __bpf_trap) +BTF_ID(func, bpf_task_work_schedule_signal_impl) +BTF_ID(func, bpf_task_work_schedule_resume_impl) + +static bool is_task_work_add_kfunc(u32 func_id) +{ + return func_id == special_kfunc_list[KF_bpf_task_work_schedule_signal_impl] || + func_id == special_kfunc_list[KF_bpf_task_work_schedule_resume_impl]; +} + +static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) +{ + if (meta->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] && + meta->arg_owning_ref) { + return false; + } + + return meta->kfunc_flags & KF_RET_NULL; +} static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta) { @@ -8443,6 +12481,21 @@ 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 bool is_kfunc_pkt_changing(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_xdp_pull_data]; +} + static enum kfunc_ptr_arg_type get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, @@ -8463,36 +12516,54 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, * type to our caller. When a set of conditions hold in the BTF type of * arguments, we resolve it to a known kfunc_ptr_arg_type. */ - if (btf_get_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) + if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) return KF_ARG_PTR_TO_CTX; + if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg)) + return KF_ARG_PTR_TO_NULL; + if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno])) return KF_ARG_PTR_TO_ALLOC_BTF_ID; - if (is_kfunc_arg_kptr_get(meta, argno)) { - if (!btf_type_is_ptr(ref_t)) { - verbose(env, "arg#0 BTF type must be a double pointer for kptr_get kfunc\n"); - return -EINVAL; - } - ref_t = btf_type_by_id(meta->btf, ref_t->type); - ref_tname = btf_name_by_offset(meta->btf, ref_t->name_off); - if (!btf_type_is_struct(ref_t)) { - verbose(env, "kernel function %s args#0 pointer type %s %s is not supported\n", - meta->func_name, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } - return KF_ARG_PTR_TO_KPTR; - } + if (is_kfunc_arg_refcounted_kptr(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_REFCOUNTED_KPTR; if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) return KF_ARG_PTR_TO_DYNPTR; + if (is_kfunc_arg_iter(meta, argno, &args[argno])) + return KF_ARG_PTR_TO_ITER; + if (is_kfunc_arg_list_head(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_HEAD; if (is_kfunc_arg_list_node(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_NODE; + if (is_kfunc_arg_rbtree_root(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_RB_ROOT; + + if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_RB_NODE; + + if (is_kfunc_arg_const_str(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_CONST_STR; + + if (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 (is_kfunc_arg_task_work(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_TASK_WORK; + + if (is_kfunc_arg_irq_flag(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_IRQ_FLAG; + + if (is_kfunc_arg_res_spin_lock(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_RES_SPIN_LOCK; + 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", @@ -8502,7 +12573,12 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, return KF_ARG_PTR_TO_BTF_ID; } - if (argno + 1 < nargs && is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1])) + if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) + return KF_ARG_PTR_TO_CALLBACK; + + if (argno + 1 < nargs && + (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]) || + is_kfunc_arg_const_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]))) arg_mem_size = true; /* This is the catch all argument type of register types supported by @@ -8530,6 +12606,8 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, bool strict_type_match = false; const struct btf *reg_btf; const char *reg_ref_tname; + bool taking_projection; + bool struct_same; u32 reg_ref_id; if (base_type(reg->type) == PTR_TO_BTF_ID) { @@ -8540,12 +12618,47 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, reg_ref_id = *reg2btf_ids[base_type(reg->type)]; } - if (is_kfunc_trusted_args(meta) || (is_kfunc_release(meta) && reg->ref_obj_id)) + /* Enforce strict type matching for calls to kfuncs that are acquiring + * or releasing a reference, or are no-cast aliases. We do _not_ + * enforce strict matching for plain KF_TRUSTED_ARGS kfuncs by default, + * as we want to enable BPF programs to pass types that are bitwise + * equivalent without forcing them to explicitly cast with something + * like bpf_cast_to_kern_ctx(). + * + * For example, say we had a type like the following: + * + * struct bpf_cpumask { + * cpumask_t cpumask; + * refcount_t usage; + * }; + * + * Note that as specified in <linux/cpumask.h>, cpumask_t is typedef'ed + * to a struct cpumask, so it would be safe to pass a struct + * bpf_cpumask * to a kfunc expecting a struct cpumask *. + * + * The philosophy here is similar to how we allow scalars of different + * types to be passed to kfuncs as long as the size is the same. The + * only difference here is that we're simply allowing + * btf_struct_ids_match() to walk the struct at the 0th offset, and + * resolve types. + */ + if ((is_kfunc_release(meta) && reg->ref_obj_id) || + btf_type_ids_nocast_alias(&env->log, reg_btf, reg_ref_id, meta->btf, ref_id)) strict_type_match = true; + WARN_ON_ONCE(is_kfunc_release(meta) && + (reg->off || !tnum_is_const(reg->var_off) || + reg->var_off.value)); + reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); - if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) { + struct_same = btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match); + /* If kfunc is accepting a projection type (ie. __sk_buff), it cannot + * actually use it -- it must cast to the underlying type. So we allow + * caller to pass in the underlying type. + */ + taking_projection = btf_is_projection_of(ref_tname, reg_ref_tname); + if (!taking_projection && !struct_same) { verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1, btf_type_str(reg_ref_t), reg_ref_tname); @@ -8554,73 +12667,110 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, return 0; } -static int process_kf_arg_ptr_to_kptr(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, - const struct btf_type *ref_t, - const char *ref_tname, - struct bpf_kfunc_call_arg_meta *meta, - int argno) +static int process_irq_flag(struct bpf_verifier_env *env, int regno, + struct bpf_kfunc_call_arg_meta *meta) { - struct btf_field *kptr_field; + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + int err, kfunc_class = IRQ_NATIVE_KFUNC; + bool irq_save; + + if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_save] || + meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave]) { + irq_save = true; + if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave]) + kfunc_class = IRQ_LOCK_KFUNC; + } else if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_restore] || + meta->func_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]) { + irq_save = false; + if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]) + kfunc_class = IRQ_LOCK_KFUNC; + } else { + verifier_bug(env, "unknown irq flags kfunc"); + return -EFAULT; + } - /* check_func_arg_reg_off allows var_off for - * PTR_TO_MAP_VALUE, but we need fixed offset to find - * off_desc. - */ - if (!tnum_is_const(reg->var_off)) { - verbose(env, "arg#0 must have constant offset\n"); - return -EINVAL; + if (irq_save) { + if (!is_irq_flag_reg_valid_uninit(env, reg)) { + verbose(env, "expected uninitialized irq flag as arg#%d\n", regno - 1); + return -EINVAL; + } + + err = check_mem_access(env, env->insn_idx, regno, 0, BPF_DW, BPF_WRITE, -1, false, false); + if (err) + return err; + + err = mark_stack_slot_irq_flag(env, meta, reg, env->insn_idx, kfunc_class); + if (err) + return err; + } else { + err = is_irq_flag_reg_valid_init(env, reg); + if (err) { + verbose(env, "expected an initialized irq flag as arg#%d\n", regno - 1); + return err; + } + + err = mark_irq_flag_read(env, reg); + if (err) + return err; + + err = unmark_stack_slot_irq_flag(env, reg, kfunc_class); + if (err) + return err; } + return 0; +} - kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); - if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { - verbose(env, "arg#0 no referenced kptr at map value offset=%llu\n", - reg->off + reg->var_off.value); - return -EINVAL; + +static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct btf_record *rec = reg_btf_record(reg); + + if (!env->cur_state->active_locks) { + verifier_bug(env, "%s w/o active lock", __func__); + return -EFAULT; } - if (!btf_struct_ids_match(&env->log, meta->btf, ref_t->type, 0, kptr_field->kptr.btf, - kptr_field->kptr.btf_id, true)) { - verbose(env, "kernel function %s args#%d expected pointer to %s %s\n", - meta->func_name, argno, btf_type_str(ref_t), ref_tname); - return -EINVAL; + if (type_flag(reg->type) & NON_OWN_REF) { + verifier_bug(env, "NON_OWN_REF already set"); + return -EFAULT; } + + reg->type |= NON_OWN_REF; + if (rec->refcount_off >= 0) + reg->type |= MEM_RCU; + return 0; } -static int ref_set_release_on_unlock(struct bpf_verifier_env *env, u32 ref_obj_id) +static int ref_convert_owning_non_owning(struct bpf_verifier_env *env, u32 ref_obj_id) { - struct bpf_func_state *state = cur_func(env); + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *unused; struct bpf_reg_state *reg; int i; - /* bpf_spin_lock only allows calling list_push and list_pop, no BPF - * subprogs, no global functions. This means that the references would - * not be released inside the critical section but they may be added to - * the reference state, and the acquired_refs are never copied out for a - * different frame as BPF to BPF calls don't work in bpf_spin_lock - * critical sections. - */ if (!ref_obj_id) { - verbose(env, "verifier internal error: ref_obj_id is zero for release_on_unlock\n"); + verifier_bug(env, "ref_obj_id is zero for owning -> non-owning conversion"); return -EFAULT; } + for (i = 0; i < state->acquired_refs; i++) { - if (state->refs[i].id == ref_obj_id) { - if (state->refs[i].release_on_unlock) { - verbose(env, "verifier internal error: expected false release_on_unlock"); - return -EFAULT; + if (state->refs[i].id != ref_obj_id) + continue; + + /* Clear ref_obj_id here so release_reference doesn't clobber + * the whole reg + */ + bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ + if (reg->ref_obj_id == ref_obj_id) { + reg->ref_obj_id = 0; + ref_set_non_owning(env, reg); } - state->refs[i].release_on_unlock = true; - /* Now mark everyone sharing same ref_obj_id as untrusted */ - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg->ref_obj_id == ref_obj_id) - reg->type |= PTR_UNTRUSTED; - })); - return 0; - } + })); + return 0; } - verbose(env, "verifier internal error: ref state missing for ref_obj_id\n"); + + verifier_bug(env, "ref state missing for ref_obj_id"); return -EFAULT; } @@ -8670,6 +12820,7 @@ static int ref_set_release_on_unlock(struct bpf_verifier_env *env, u32 ref_obj_i */ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { + struct bpf_reference_state *s; void *ptr; u32 id; @@ -8678,19 +12829,18 @@ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_ ptr = reg->map_ptr; break; case PTR_TO_BTF_ID | MEM_ALLOC: - case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: ptr = reg->btf; break; default: - verbose(env, "verifier internal error: unknown reg type for lock check\n"); + verifier_bug(env, "unknown reg type for lock check"); return -EFAULT; } id = reg->id; - if (!env->cur_state->active_lock.ptr) + if (!env->cur_state->active_locks) return -EINVAL; - if (env->cur_state->active_lock.ptr != ptr || - env->cur_state->active_lock.id != id) { + s = find_lock_state(env->cur_state, REF_TYPE_LOCK_MASK, id, ptr); + if (!s) { verbose(env, "held lock and object are not in the same allocation\n"); return -EINVAL; } @@ -8699,114 +12849,317 @@ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_ static bool is_bpf_list_api_kfunc(u32 btf_id) { - return btf_id == special_kfunc_list[KF_bpf_list_push_front] || - btf_id == special_kfunc_list[KF_bpf_list_push_back] || + return btf_id == special_kfunc_list[KF_bpf_list_push_front_impl] || + btf_id == special_kfunc_list[KF_bpf_list_push_back_impl] || btf_id == special_kfunc_list[KF_bpf_list_pop_front] || - btf_id == special_kfunc_list[KF_bpf_list_pop_back]; + btf_id == special_kfunc_list[KF_bpf_list_pop_back] || + btf_id == special_kfunc_list[KF_bpf_list_front] || + btf_id == special_kfunc_list[KF_bpf_list_back]; } -static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, u32 regno, - struct bpf_kfunc_call_arg_meta *meta) +static bool is_bpf_rbtree_api_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl] || + btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || + btf_id == special_kfunc_list[KF_bpf_rbtree_first] || + btf_id == special_kfunc_list[KF_bpf_rbtree_root] || + btf_id == special_kfunc_list[KF_bpf_rbtree_left] || + btf_id == special_kfunc_list[KF_bpf_rbtree_right]; +} + +static bool is_bpf_iter_num_api_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_iter_num_new] || + btf_id == special_kfunc_list[KF_bpf_iter_num_next] || + btf_id == special_kfunc_list[KF_bpf_iter_num_destroy]; +} + +static bool is_bpf_graph_api_kfunc(u32 btf_id) +{ + return is_bpf_list_api_kfunc(btf_id) || is_bpf_rbtree_api_kfunc(btf_id) || + btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]; +} + +static bool is_bpf_res_spin_lock_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_res_spin_lock] || + btf_id == special_kfunc_list[KF_bpf_res_spin_unlock] || + btf_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave] || + btf_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]; +} + +static bool kfunc_spin_allowed(u32 btf_id) +{ + return is_bpf_graph_api_kfunc(btf_id) || is_bpf_iter_num_api_kfunc(btf_id) || + is_bpf_res_spin_lock_kfunc(btf_id); +} + +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] || + is_task_work_add_kfunc(btf_id); +} + +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); +} + +static bool check_kfunc_is_graph_root_api(struct bpf_verifier_env *env, + enum btf_field_type head_field_type, + u32 kfunc_btf_id) +{ + bool ret; + + switch (head_field_type) { + case BPF_LIST_HEAD: + ret = is_bpf_list_api_kfunc(kfunc_btf_id); + break; + case BPF_RB_ROOT: + ret = is_bpf_rbtree_api_kfunc(kfunc_btf_id); + break; + default: + verbose(env, "verifier internal error: unexpected graph root argument type %s\n", + btf_field_type_name(head_field_type)); + return false; + } + + if (!ret) + verbose(env, "verifier internal error: %s head arg for unknown kfunc\n", + btf_field_type_name(head_field_type)); + return ret; +} + +static bool check_kfunc_is_graph_node_api(struct bpf_verifier_env *env, + enum btf_field_type node_field_type, + u32 kfunc_btf_id) +{ + bool ret; + + switch (node_field_type) { + case BPF_LIST_NODE: + ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_front_impl] || + kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_back_impl]); + break; + case BPF_RB_NODE: + ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || + kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl] || + kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_left] || + kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_right]); + break; + default: + verbose(env, "verifier internal error: unexpected graph node argument type %s\n", + btf_field_type_name(node_field_type)); + return false; + } + + if (!ret) + verbose(env, "verifier internal error: %s node arg for unknown kfunc\n", + btf_field_type_name(node_field_type)); + return ret; +} + +static int +__process_kf_arg_ptr_to_graph_root(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta, + enum btf_field_type head_field_type, + struct btf_field **head_field) +{ + const char *head_type_name; struct btf_field *field; struct btf_record *rec; - u32 list_head_off; + u32 head_off; - if (meta->btf != btf_vmlinux || !is_bpf_list_api_kfunc(meta->func_id)) { - verbose(env, "verifier internal error: bpf_list_head argument for unknown kfunc\n"); + if (meta->btf != btf_vmlinux) { + verifier_bug(env, "unexpected btf mismatch in kfunc call"); return -EFAULT; } + if (!check_kfunc_is_graph_root_api(env, head_field_type, meta->func_id)) + return -EFAULT; + + head_type_name = btf_field_type_name(head_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, - "R%d doesn't have constant offset. bpf_list_head has to be at the constant offset\n", - regno); + "R%d doesn't have constant offset. %s has to be at the constant offset\n", + regno, head_type_name); return -EINVAL; } rec = reg_btf_record(reg); - list_head_off = reg->off + reg->var_off.value; - field = btf_record_find(rec, list_head_off, BPF_LIST_HEAD); + head_off = reg->off + reg->var_off.value; + field = btf_record_find(rec, head_off, head_field_type); if (!field) { - verbose(env, "bpf_list_head not found at offset=%u\n", list_head_off); + verbose(env, "%s not found at offset=%u\n", head_type_name, head_off); return -EINVAL; } /* All functions require bpf_list_head to be protected using a bpf_spin_lock */ if (check_reg_allocation_locked(env, reg)) { - verbose(env, "bpf_spin_lock at off=%d must be held for bpf_list_head\n", - rec->spin_lock_off); + verbose(env, "bpf_spin_lock at off=%d must be held for %s\n", + rec->spin_lock_off, head_type_name); return -EINVAL; } - if (meta->arg_list_head.field) { - verbose(env, "verifier internal error: repeating bpf_list_head arg\n"); + if (*head_field) { + verifier_bug(env, "repeating %s arg", head_type_name); return -EFAULT; } - meta->arg_list_head.field = field; + *head_field = field; return 0; } -static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, +static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { + return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_LIST_HEAD, + &meta->arg_list_head.field); +} + +static int process_kf_arg_ptr_to_rbtree_root(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_RB_ROOT, + &meta->arg_rbtree_root.field); +} + +static int +__process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta, + enum btf_field_type head_field_type, + enum btf_field_type node_field_type, + struct btf_field **node_field) +{ + const char *node_type_name; const struct btf_type *et, *t; struct btf_field *field; - struct btf_record *rec; - u32 list_node_off; + u32 node_off; - if (meta->btf != btf_vmlinux || - (meta->func_id != special_kfunc_list[KF_bpf_list_push_front] && - meta->func_id != special_kfunc_list[KF_bpf_list_push_back])) { - verbose(env, "verifier internal error: bpf_list_node argument for unknown kfunc\n"); + if (meta->btf != btf_vmlinux) { + verifier_bug(env, "unexpected btf mismatch in kfunc call"); return -EFAULT; } + if (!check_kfunc_is_graph_node_api(env, node_field_type, meta->func_id)) + return -EFAULT; + + node_type_name = btf_field_type_name(node_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, - "R%d doesn't have constant offset. bpf_list_node has to be at the constant offset\n", - regno); + "R%d doesn't have constant offset. %s has to be at the constant offset\n", + regno, node_type_name); return -EINVAL; } - rec = reg_btf_record(reg); - list_node_off = reg->off + reg->var_off.value; - field = btf_record_find(rec, list_node_off, BPF_LIST_NODE); - if (!field || field->offset != list_node_off) { - verbose(env, "bpf_list_node not found at offset=%u\n", list_node_off); + node_off = reg->off + reg->var_off.value; + field = reg_find_field_offset(reg, node_off, node_field_type); + if (!field) { + verbose(env, "%s not found at offset=%u\n", node_type_name, node_off); return -EINVAL; } - field = meta->arg_list_head.field; + field = *node_field; - et = btf_type_by_id(field->list_head.btf, field->list_head.value_btf_id); + et = btf_type_by_id(field->graph_root.btf, field->graph_root.value_btf_id); t = btf_type_by_id(reg->btf, reg->btf_id); - if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->list_head.btf, - field->list_head.value_btf_id, true)) { - verbose(env, "operation on bpf_list_head expects arg#1 bpf_list_node at offset=%d " + if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->graph_root.btf, + field->graph_root.value_btf_id, true)) { + verbose(env, "operation on %s expects arg#1 %s at offset=%d " "in struct %s, but arg is at offset=%d in struct %s\n", - field->list_head.node_offset, btf_name_by_offset(field->list_head.btf, et->name_off), - list_node_off, btf_name_by_offset(reg->btf, t->name_off)); + btf_field_type_name(head_field_type), + btf_field_type_name(node_field_type), + field->graph_root.node_offset, + btf_name_by_offset(field->graph_root.btf, et->name_off), + node_off, btf_name_by_offset(reg->btf, t->name_off)); return -EINVAL; } + meta->arg_btf = reg->btf; + meta->arg_btf_id = reg->btf_id; - if (list_node_off != field->list_head.node_offset) { - verbose(env, "arg#1 offset=%d, but expected bpf_list_node at offset=%d in struct %s\n", - list_node_off, field->list_head.node_offset, - btf_name_by_offset(field->list_head.btf, et->name_off)); + if (node_off != field->graph_root.node_offset) { + verbose(env, "arg#1 offset=%d, but expected %s at offset=%d in struct %s\n", + node_off, btf_field_type_name(node_field_type), + field->graph_root.node_offset, + btf_name_by_offset(field->graph_root.btf, et->name_off)); return -EINVAL; } - /* Set arg#1 for expiration after unlock */ - return ref_set_release_on_unlock(env, reg->ref_obj_id); + + return 0; +} + +static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, + BPF_LIST_HEAD, BPF_LIST_NODE, + &meta->arg_list_head.field); +} + +static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, + BPF_RB_ROOT, BPF_RB_NODE, + &meta->arg_rbtree_root.field); } -static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) +/* + * css_task iter allowlist is needed to avoid dead locking on css_set_lock. + * LSM hooks and iters (both sleepable and non-sleepable) are safe. + * Any sleepable progs are also safe since bpf_check_attach_target() enforce + * them can only be attached to some specific hook points. + */ +static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) +{ + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); + + switch (prog_type) { + case BPF_PROG_TYPE_LSM: + return true; + case BPF_PROG_TYPE_TRACING: + if (env->prog->expected_attach_type == BPF_TRACE_ITER) + return true; + fallthrough; + default: + return in_sleepable(env); + } +} + +static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, + int insn_idx) { const char *func_name = meta->func_name, *ref_tname; const struct btf *btf = meta->btf; const struct btf_param *args; + struct btf_record *rec; u32 i, nargs; int ret; @@ -8834,6 +13187,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (is_kfunc_arg_ignore(btf, &args[i])) continue; + if (is_kfunc_arg_prog(btf, &args[i])) { + /* Used to reject repeated use of __prog. */ + if (meta->arg_prog) { + verifier_bug(env, "Only 1 prog->aux argument supported per-kfunc"); + return -EFAULT; + } + meta->arg_prog = true; + cur_aux(env)->arg_prog = regno; + continue; + } + if (btf_type_is_scalar(t)) { if (reg->type != SCALAR_VALUE) { verbose(env, "R%d is not a scalar\n", regno); @@ -8842,7 +13206,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (is_kfunc_arg_constant(meta->btf, &args[i])) { if (meta->arg_constant.found) { - verbose(env, "verifier internal error: only one constant argument permitted\n"); + verifier_bug(env, "only one constant argument permitted"); return -EFAULT; } if (!tnum_is_const(reg->var_off)) { @@ -8885,11 +13249,18 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return -EINVAL; } + if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && + (register_is_null(reg) || type_may_be_null(reg->type)) && + !is_kfunc_arg_nullable(meta->btf, &args[i])) { + verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); + return -EACCES; + } + if (reg->ref_obj_id) { if (is_kfunc_release(meta) && meta->ref_obj_id) { - verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", - regno, reg->ref_obj_id, - meta->ref_obj_id); + verifier_bug(env, "more than one arg with ref_obj_id R%d %u %u", + regno, reg->ref_obj_id, + meta->ref_obj_id); return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; @@ -8905,6 +13276,44 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return kf_arg_type; switch (kf_arg_type) { + 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 || + reg->map_ptr->record->task_work_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) { + if (reg->map_ptr->record->task_work_off >= 0) { + verbose(env, + "bpf_task_work pointer in R2 map_uid=%d doesn't match map pointer in R3 map_uid=%d\n", + meta->map.uid, reg->map_uid); + return -EINVAL; + } + 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)) @@ -8920,22 +13329,26 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return -EINVAL; } } - fallthrough; case KF_ARG_PTR_TO_CTX: - /* Trusted arguments have the same offset checks as release arguments */ - arg_type |= OBJ_RELEASE; - break; - case KF_ARG_PTR_TO_KPTR: case KF_ARG_PTR_TO_DYNPTR: + case KF_ARG_PTR_TO_ITER: case KF_ARG_PTR_TO_LIST_HEAD: case KF_ARG_PTR_TO_LIST_NODE: + case KF_ARG_PTR_TO_RB_ROOT: + case KF_ARG_PTR_TO_RB_NODE: case KF_ARG_PTR_TO_MEM: case KF_ARG_PTR_TO_MEM_SIZE: - /* Trusted by default */ + 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: + case KF_ARG_PTR_TO_TASK_WORK: + case KF_ARG_PTR_TO_IRQ_FLAG: + case KF_ARG_PTR_TO_RES_SPIN_LOCK: break; default: - WARN_ON_ONCE(1); + verifier_bug(env, "unknown kfunc arg type %d", kf_arg_type); return -EFAULT; } @@ -8948,7 +13361,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ switch (kf_arg_type) { case KF_ARG_PTR_TO_CTX: if (reg->type != PTR_TO_CTX) { - verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); + verbose(env, "arg#%d expected pointer to ctx, but got %s\n", + i, reg_type_str(env, reg->type)); return -EINVAL; } @@ -8960,7 +13374,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ } break; case KF_ARG_PTR_TO_ALLOC_BTF_ID: - if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) { + if (meta->func_id != special_kfunc_list[KF_bpf_obj_drop_impl]) { + verbose(env, "arg#%d expected for bpf_obj_drop_impl()\n", i); + return -EINVAL; + } + } else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU)) { + if (meta->func_id != special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) { + verbose(env, "arg#%d expected for bpf_percpu_obj_drop_impl()\n", i); + return -EINVAL; + } + } else { verbose(env, "arg#%d expected pointer to allocated object\n", i); return -EINVAL; } @@ -8968,29 +13392,76 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ verbose(env, "allocated object must be referenced\n"); return -EINVAL; } - if (meta->btf == btf_vmlinux && - meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { - meta->arg_obj_drop.btf = reg->btf; - meta->arg_obj_drop.btf_id = reg->btf_id; + if (meta->btf == btf_vmlinux) { + meta->arg_btf = reg->btf; + meta->arg_btf_id = reg->btf_id; } break; - case KF_ARG_PTR_TO_KPTR: - if (reg->type != PTR_TO_MAP_VALUE) { - verbose(env, "arg#0 expected pointer to map value\n"); - return -EINVAL; + case KF_ARG_PTR_TO_DYNPTR: + { + enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR; + int clone_ref_obj_id = 0; + + if (reg->type == CONST_PTR_TO_DYNPTR) + dynptr_arg_type |= MEM_RDONLY; + + if (is_kfunc_arg_uninit(btf, &args[i])) + dynptr_arg_type |= MEM_UNINIT; + + if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { + dynptr_arg_type |= DYNPTR_TYPE_SKB; + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) { + dynptr_arg_type |= DYNPTR_TYPE_XDP; + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb_meta]) { + dynptr_arg_type |= DYNPTR_TYPE_SKB_META; + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_file]) { + dynptr_arg_type |= DYNPTR_TYPE_FILE; + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_file_discard]) { + dynptr_arg_type |= DYNPTR_TYPE_FILE; + meta->release_regno = regno; + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_clone] && + (dynptr_arg_type & MEM_UNINIT)) { + enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type; + + if (parent_type == BPF_DYNPTR_TYPE_INVALID) { + verifier_bug(env, "no dynptr type for parent of clone"); + return -EFAULT; + } + + dynptr_arg_type |= (unsigned int)get_dynptr_type_flag(parent_type); + clone_ref_obj_id = meta->initialized_dynptr.ref_obj_id; + if (dynptr_type_refcounted(parent_type) && !clone_ref_obj_id) { + verifier_bug(env, "missing ref obj id for parent of clone"); + return -EFAULT; + } } - ret = process_kf_arg_ptr_to_kptr(env, reg, ref_t, ref_tname, meta, i); + + ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type, clone_ref_obj_id); if (ret < 0) return ret; - break; - case KF_ARG_PTR_TO_DYNPTR: - if (reg->type != PTR_TO_STACK && - reg->type != CONST_PTR_TO_DYNPTR) { - verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i); - return -EINVAL; + + if (!(dynptr_arg_type & MEM_UNINIT)) { + int id = dynptr_id(env, reg); + + if (id < 0) { + verifier_bug(env, "failed to obtain dynptr id"); + return id; + } + meta->initialized_dynptr.id = id; + meta->initialized_dynptr.type = dynptr_get_type(env, reg); + meta->initialized_dynptr.ref_obj_id = dynptr_ref_obj_id(env, reg); } - ret = process_dynptr_func(env, regno, ARG_PTR_TO_DYNPTR | MEM_RDONLY, NULL); + break; + } + case KF_ARG_PTR_TO_ITER: + if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) { + if (!check_css_task_iter_allowlist(env)) { + verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n"); + return -EINVAL; + } + } + ret = process_iter_arg(env, regno, insn_idx, meta); if (ret < 0) return ret; break; @@ -9008,6 +13479,20 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (ret < 0) return ret; break; + case KF_ARG_PTR_TO_RB_ROOT: + if (reg->type != PTR_TO_MAP_VALUE && + reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d expected pointer to map value or allocated object\n", i); + return -EINVAL; + } + if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) && !reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_rbtree_root(env, reg, regno, meta); + if (ret < 0) + return ret; + break; case KF_ARG_PTR_TO_LIST_NODE: if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to allocated object\n", i); @@ -9021,6 +13506,37 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (ret < 0) return ret; break; + case KF_ARG_PTR_TO_RB_NODE: + if (meta->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { + if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d expected pointer to allocated object\n", i); + return -EINVAL; + } + if (!reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + } else { + if (!type_is_non_owning_ref(reg->type) && !reg->ref_obj_id) { + verbose(env, "%s can only take non-owning or refcounted bpf_rb_node pointer\n", func_name); + return -EINVAL; + } + if (in_rbtree_lock_required_cb(env)) { + verbose(env, "%s not allowed in rbtree cb\n", func_name); + return -EINVAL; + } + } + + ret = process_kf_arg_ptr_to_rbtree_node(env, reg, regno, meta); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MAP: + /* If argument has '__map' suffix expect 'struct bpf_map *' */ + ref_id = *reg2btf_ids[CONST_PTR_TO_MAP]; + ref_t = btf_type_by_id(btf_vmlinux, ref_id); + ref_tname = btf_name_by_offset(btf, ref_t->name_off); + fallthrough; case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || @@ -9048,15 +13564,125 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return ret; break; case KF_ARG_PTR_TO_MEM_SIZE: - ret = check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1); - if (ret < 0) { - verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); - return ret; + { + struct bpf_reg_state *buff_reg = ®s[regno]; + const struct btf_param *buff_arg = &args[i]; + struct bpf_reg_state *size_reg = ®s[regno + 1]; + const struct btf_param *size_arg = &args[i + 1]; + + if (!register_is_null(buff_reg) || !is_kfunc_arg_optional(meta->btf, buff_arg)) { + ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); + if (ret < 0) { + verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); + return ret; + } + } + + if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) { + if (meta->arg_constant.found) { + verifier_bug(env, "only one constant argument permitted"); + return -EFAULT; + } + if (!tnum_is_const(size_reg->var_off)) { + verbose(env, "R%d must be a known constant\n", regno + 1); + return -EINVAL; + } + meta->arg_constant.found = true; + meta->arg_constant.value = size_reg->var_off.value; } - /* Skip next '__sz' argument */ + + /* Skip next '__sz' or '__szk' argument */ i++; break; } + case KF_ARG_PTR_TO_CALLBACK: + if (reg->type != PTR_TO_FUNC) { + verbose(env, "arg%d expected pointer to func\n", i); + return -EINVAL; + } + meta->subprogno = reg->subprogno; + break; + case KF_ARG_PTR_TO_REFCOUNTED_KPTR: + if (!type_is_ptr_alloc_obj(reg->type)) { + verbose(env, "arg#%d is neither owning or non-owning ref\n", i); + return -EINVAL; + } + if (!type_is_non_owning_ref(reg->type)) + meta->arg_owning_ref = true; + + rec = reg_btf_record(reg); + if (!rec) { + verifier_bug(env, "Couldn't find btf_record"); + return -EFAULT; + } + + if (rec->refcount_off < 0) { + verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i); + return -EINVAL; + } + + meta->arg_btf = reg->btf; + meta->arg_btf_id = reg->btf_id; + break; + case KF_ARG_PTR_TO_CONST_STR: + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "arg#%d doesn't point to a const string\n", i); + return -EINVAL; + } + ret = check_reg_const_str(env, reg, regno); + if (ret) + return ret; + break; + 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; + case KF_ARG_PTR_TO_TASK_WORK: + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "arg#%d doesn't point to a map value\n", i); + return -EINVAL; + } + ret = process_task_work_func(env, regno, meta); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_IRQ_FLAG: + if (reg->type != PTR_TO_STACK) { + verbose(env, "arg#%d doesn't point to an irq flag on stack\n", i); + return -EINVAL; + } + ret = process_irq_flag(env, regno, meta); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_RES_SPIN_LOCK: + { + int flags = PROCESS_RES_LOCK; + + if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d doesn't point to map value or allocated object\n", i); + return -EINVAL; + } + + if (!is_bpf_res_spin_lock_kfunc(meta->func_id)) + return -EFAULT; + if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock] || + meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave]) + flags |= PROCESS_SPIN_LOCK; + if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave] || + meta->func_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]) + flags |= PROCESS_LOCK_IRQ; + ret = process_spin_lock(env, regno, flags); + if (ret < 0) + return ret; + break; + } + } } if (is_kfunc_release(meta) && !meta->release_regno) { @@ -9068,24 +13694,21 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return 0; } -static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx_p) +static int fetch_kfunc_meta(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_kfunc_call_arg_meta *meta, + const char **kfunc_name) { - const struct btf_type *t, *func, *func_proto, *ptr_type; - struct bpf_reg_state *regs = cur_regs(env); - const char *func_name, *ptr_type_name; - bool sleepable, rcu_lock, rcu_unlock; - struct bpf_kfunc_call_arg_meta meta; - u32 i, nargs, func_id, ptr_type_id; - int err, insn_idx = *insn_idx_p; - const struct btf_param *args; - const struct btf_type *ret_t; + const struct btf_type *func, *func_proto; + u32 func_id, *kfunc_flags; + const char *func_name; struct btf *desc_btf; - u32 *kfunc_flags; - /* skip for now, but return error when we find this in fixup_kfunc_call */ + if (kfunc_name) + *kfunc_name = NULL; + if (!insn->imm) - return 0; + return -EINVAL; desc_btf = find_kfunc_desc_btf(env, insn->off); if (IS_ERR(desc_btf)) @@ -9094,22 +13717,264 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, func_id = insn->imm; func = btf_type_by_id(desc_btf, func_id); func_name = btf_name_by_offset(desc_btf, func->name_off); + if (kfunc_name) + *kfunc_name = func_name; func_proto = btf_type_by_id(desc_btf, func->type); - kfunc_flags = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), func_id); + kfunc_flags = btf_kfunc_id_set_contains(desc_btf, func_id, env->prog); if (!kfunc_flags) { - verbose(env, "calling kernel function %s is not allowed\n", - func_name); return -EACCES; } - /* Prepare kfunc call metadata */ - memset(&meta, 0, sizeof(meta)); - meta.btf = desc_btf; - meta.func_id = func_id; - meta.kfunc_flags = *kfunc_flags; - meta.func_proto = func_proto; - meta.func_name = func_name; + memset(meta, 0, sizeof(*meta)); + meta->btf = desc_btf; + meta->func_id = func_id; + meta->kfunc_flags = *kfunc_flags; + meta->func_proto = func_proto; + meta->func_name = func_name; + + return 0; +} + +/* check special kfuncs and return: + * 1 - not fall-through to 'else' branch, continue verification + * 0 - fall-through to 'else' branch + * < 0 - not fall-through to 'else' branch, return error + */ +static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, + struct bpf_reg_state *regs, struct bpf_insn_aux_data *insn_aux, + const struct btf_type *ptr_type, struct btf *desc_btf) +{ + const struct btf_type *ret_t; + int err = 0; + + if (meta->btf != btf_vmlinux) + return 0; + + if (meta->func_id == special_kfunc_list[KF_bpf_obj_new_impl] || + meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { + struct btf_struct_meta *struct_meta; + struct btf *ret_btf; + u32 ret_btf_id; + + if (meta->func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set) + return -ENOMEM; + + if (((u64)(u32)meta->arg_constant.value) != meta->arg_constant.value) { + verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); + return -EINVAL; + } + + ret_btf = env->prog->aux->btf; + ret_btf_id = meta->arg_constant.value; + + /* This may be NULL due to user not supplying a BTF */ + if (!ret_btf) { + verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n"); + return -EINVAL; + } + + ret_t = btf_type_by_id(ret_btf, ret_btf_id); + if (!ret_t || !__btf_type_is_struct(ret_t)) { + verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n"); + return -EINVAL; + } + + if (meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { + if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) { + verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n", + ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE); + return -EINVAL; + } + + if (!bpf_global_percpu_ma_set) { + mutex_lock(&bpf_percpu_ma_lock); + if (!bpf_global_percpu_ma_set) { + /* Charge memory allocated with bpf_global_percpu_ma to + * root memcg. The obj_cgroup for root memcg is NULL. + */ + err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL); + if (!err) + bpf_global_percpu_ma_set = true; + } + mutex_unlock(&bpf_percpu_ma_lock); + if (err) + return err; + } + + mutex_lock(&bpf_percpu_ma_lock); + err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size); + mutex_unlock(&bpf_percpu_ma_lock); + if (err) + return err; + } + + struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id); + if (meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { + if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) { + verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n"); + return -EINVAL; + } + + if (struct_meta) { + verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n"); + return -EINVAL; + } + } + + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[BPF_REG_0].btf = ret_btf; + regs[BPF_REG_0].btf_id = ret_btf_id; + if (meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) + regs[BPF_REG_0].type |= MEM_PERCPU; + + insn_aux->obj_new_size = ret_t->size; + insn_aux->kptr_struct_meta = struct_meta; + } else if (meta->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[BPF_REG_0].btf = meta->arg_btf; + regs[BPF_REG_0].btf_id = meta->arg_btf_id; + + insn_aux->kptr_struct_meta = + btf_find_struct_meta(meta->arg_btf, + meta->arg_btf_id); + } else if (is_list_node_type(ptr_type)) { + struct btf_field *field = meta->arg_list_head.field; + + mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); + } else if (is_rbtree_node_type(ptr_type)) { + struct btf_field *field = meta->arg_rbtree_root.field; + + mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); + } else if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED; + regs[BPF_REG_0].btf = desc_btf; + regs[BPF_REG_0].btf_id = meta->ret_btf_id; + } else if (meta->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { + ret_t = btf_type_by_id(desc_btf, meta->arg_constant.value); + if (!ret_t) { + verbose(env, "Unknown type ID %lld passed to kfunc bpf_rdonly_cast\n", + meta->arg_constant.value); + return -EINVAL; + } else if (btf_type_is_struct(ret_t)) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED; + regs[BPF_REG_0].btf = desc_btf; + regs[BPF_REG_0].btf_id = meta->arg_constant.value; + } else if (btf_type_is_void(ret_t)) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED; + regs[BPF_REG_0].mem_size = 0; + } else { + verbose(env, + "kfunc bpf_rdonly_cast type ID argument must be of a struct or void\n"); + return -EINVAL; + } + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice] || + meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) { + enum bpf_type_flag type_flag = get_dynptr_type_flag(meta->initialized_dynptr.type); + + mark_reg_known_zero(env, regs, BPF_REG_0); + + if (!meta->arg_constant.found) { + verifier_bug(env, "bpf_dynptr_slice(_rdwr) no constant size"); + return -EFAULT; + } + + regs[BPF_REG_0].mem_size = meta->arg_constant.value; + + /* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */ + regs[BPF_REG_0].type = PTR_TO_MEM | type_flag; + + if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice]) { + regs[BPF_REG_0].type |= MEM_RDONLY; + } else { + /* this will set env->seen_direct_write to true */ + if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) { + verbose(env, "the prog does not allow writes to packet data\n"); + return -EINVAL; + } + } + + if (!meta->initialized_dynptr.id) { + verifier_bug(env, "no dynptr id"); + return -EFAULT; + } + regs[BPF_REG_0].dynptr_id = meta->initialized_dynptr.id; + + /* we don't need to set BPF_REG_0's ref obj id + * because packet slices are not refcounted (see + * dynptr_type_refcounted) + */ + } else { + return 0; + } + + return 1; +} + +static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name); + +static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx_p) +{ + 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; + 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; + const struct btf_param *args; + struct btf *desc_btf; + + /* skip for now, but return error when we find this in fixup_kfunc_call */ + if (!insn->imm) + return 0; + + err = fetch_kfunc_meta(env, insn, &meta, &func_name); + if (err == -EACCES && func_name) + verbose(env, "calling kernel function %s is not allowed\n", func_name); + if (err) + return err; + desc_btf = meta.btf; + insn_aux = &env->insn_aux_data[insn_idx]; + + insn_aux->is_iter_next = is_iter_next_kfunc(&meta); + + if (!insn->off && + (insn->imm == special_kfunc_list[KF_bpf_res_spin_lock] || + insn->imm == special_kfunc_list[KF_bpf_res_spin_lock_irqsave])) { + struct bpf_verifier_state *branch; + struct bpf_reg_state *regs; + + branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); + if (IS_ERR(branch)) { + verbose(env, "failed to push state for failed lock acquisition\n"); + return PTR_ERR(branch); + } + + regs = branch->frame[branch->curframe]->regs; + + /* Clear r0-r5 registers in forked state */ + for (i = 0; i < CALLER_SAVED_REGS; i++) + mark_reg_not_init(env, regs, caller_saved[i]); + + mark_reg_unknown(env, regs, BPF_REG_0); + err = __mark_reg_s32_range(env, regs, BPF_REG_0, -MAX_ERRNO, -1); + if (err) { + verbose(env, "failed to mark s32 range for retval in forked state for lock\n"); + return err; + } + __mark_btf_func_reg_size(env, regs, BPF_REG_0, sizeof(u32)); + } else if (!insn->off && insn->imm == special_kfunc_list[KF___bpf_trap]) { + verbose(env, "unexpected __bpf_trap() due to uninitialized variable?\n"); + return -EFAULT; + } if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); @@ -9117,69 +13982,185 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } sleepable = is_kfunc_sleepable(&meta); - if (sleepable && !env->prog->aux->sleepable) { + if (sleepable && !in_sleepable(env)) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); return -EACCES; } + /* Track non-sleepable context for kfuncs, same as for helpers. */ + if (!in_sleepable_context(env)) + insn_aux->non_sleepable = true; + + /* Check the arguments */ + err = check_kfunc_args(env, &meta, insn_idx); + if (err < 0) + return err; + + if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_rbtree_add_callback_state); + if (err) { + verbose(env, "kfunc %s#%d failed callback verification\n", + func_name, meta.func_id); + return err; + } + } + + 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; + } + } + + if (is_task_work_add_kfunc(meta.func_id)) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_task_work_schedule_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); - if ((rcu_lock || rcu_unlock) && !env->rcu_tag_supported) { - verbose(env, "no vmlinux btf rcu tag support for kfunc %s\n", func_name); - return -EACCES; - } - if (env->cur_state->active_rcu_lock) { + preempt_disable = is_kfunc_bpf_preempt_disable(&meta); + preempt_enable = is_kfunc_bpf_preempt_enable(&meta); + + if (rcu_lock) { + env->cur_state->active_rcu_locks++; + } else if (rcu_unlock) { struct bpf_func_state *state; struct bpf_reg_state *reg; + u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER); - if (rcu_lock) { - verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); + if (env->cur_state->active_rcu_locks == 0) { + verbose(env, "unmatched rcu read unlock (kernel function %s)\n", func_name); return -EINVAL; - } else if (rcu_unlock) { - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + } + if (--env->cur_state->active_rcu_locks == 0) { + bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({ if (reg->type & MEM_RCU) { reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; } })); - env->cur_state->active_rcu_lock = false; + } + } else if (sleepable && env->cur_state->active_rcu_locks) { + verbose(env, "kernel func %s is sleepable within rcu_read_lock region\n", func_name); + return -EACCES; + } + + if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) { + verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n"); + return -EACCES; + } + + if (env->cur_state->active_preempt_locks) { + if (preempt_disable) { + env->cur_state->active_preempt_locks++; + } else if (preempt_enable) { + env->cur_state->active_preempt_locks--; } else if (sleepable) { - verbose(env, "kernel func %s is sleepable within rcu_read_lock region\n", func_name); + verbose(env, "kernel func %s is sleepable within non-preemptible region\n", func_name); return -EACCES; } - } else if (rcu_lock) { - env->cur_state->active_rcu_lock = true; - } else if (rcu_unlock) { - verbose(env, "unmatched rcu read unlock (kernel function %s)\n", func_name); + } else if (preempt_disable) { + env->cur_state->active_preempt_locks++; + } else if (preempt_enable) { + verbose(env, "unmatched attempt to enable preemption (kernel function %s)\n", func_name); return -EINVAL; } - /* Check the arguments */ - err = check_kfunc_args(env, &meta); - if (err < 0) - return err; + if (env->cur_state->active_irq_id && sleepable) { + verbose(env, "kernel func %s is sleepable within IRQ-disabled region\n", func_name); + return -EACCES; + } + + if (is_kfunc_rcu_protected(&meta) && !in_rcu_cs(env)) { + verbose(env, "kernel func %s requires RCU critical section protection\n", func_name); + return -EACCES; + } + /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ if (meta.release_regno) { - err = release_reference(env, regs[meta.release_regno].ref_obj_id); + struct bpf_reg_state *reg = ®s[meta.release_regno]; + + if (meta.initialized_dynptr.ref_obj_id) { + err = unmark_stack_slots_dynptr(env, reg); + } else { + err = release_reference(env, reg->ref_obj_id); + if (err) + verbose(env, "kfunc %s#%d reference has not been acquired before\n", + func_name, meta.func_id); + } + if (err) + return err; + } + + if (meta.func_id == special_kfunc_list[KF_bpf_list_push_front_impl] || + meta.func_id == special_kfunc_list[KF_bpf_list_push_back_impl] || + meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { + release_ref_obj_id = regs[BPF_REG_2].ref_obj_id; + insn_aux->insert_off = regs[BPF_REG_2].off; + insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id); + err = ref_convert_owning_non_owning(env, release_ref_obj_id); + if (err) { + verbose(env, "kfunc %s#%d conversion of owning ref to non-owning failed\n", + func_name, meta.func_id); + return err; + } + + err = release_reference(env, release_ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", - func_name, func_id); + func_name, meta.func_id); return err; } } + if (meta.func_id == special_kfunc_list[KF_bpf_throw]) { + if (!bpf_jit_supports_exceptions()) { + verbose(env, "JIT does not support calling kfunc %s#%d\n", + func_name, meta.func_id); + return -ENOTSUPP; + } + env->seen_exception = true; + + /* In the case of the default callback, the cookie value passed + * to bpf_throw becomes the return value of the program. + */ + if (!env->exception_callback_subprog) { + err = check_return_code(env, BPF_REG_1, "R1"); + if (err < 0) + return err; + } + } + for (i = 0; i < CALLER_SAVED_REGS; i++) mark_reg_not_init(env, regs, caller_saved[i]); /* Check return type */ - t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); + t = btf_type_skip_modifiers(desc_btf, meta.func_proto->type, NULL); if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { /* Only exception is bpf_obj_new_impl */ - if (meta.btf != btf_vmlinux || meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl]) { + if (meta.btf != btf_vmlinux || + (meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl] && + meta.func_id != special_kfunc_list[KF_bpf_percpu_obj_new_impl] && + meta.func_id != special_kfunc_list[KF_bpf_refcount_acquire_impl])) { verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); return -EINVAL; } @@ -9187,82 +14168,28 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); + if (meta.btf == btf_vmlinux && (meta.func_id == special_kfunc_list[KF_bpf_res_spin_lock] || + meta.func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave])) + __mark_reg_const_zero(env, ®s[BPF_REG_0]); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); + err = check_special_kfunc(env, &meta, regs, insn_aux, ptr_type, desc_btf); + if (err) { + if (err < 0) + return err; + } else if (btf_type_is_void(ptr_type)) { + /* kfunc returning 'void *' is equivalent to returning scalar */ + mark_reg_unknown(env, regs, BPF_REG_0); + } else if (!__btf_type_is_struct(ptr_type)) { + if (!meta.r0_size) { + __u32 sz; - if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { - if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { - struct btf *ret_btf; - u32 ret_btf_id; - - if (unlikely(!bpf_global_ma_set)) - return -ENOMEM; - - if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { - verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); - return -EINVAL; - } - - ret_btf = env->prog->aux->btf; - ret_btf_id = meta.arg_constant.value; - - /* This may be NULL due to user not supplying a BTF */ - if (!ret_btf) { - verbose(env, "bpf_obj_new requires prog BTF\n"); - return -EINVAL; - } - - ret_t = btf_type_by_id(ret_btf, ret_btf_id); - if (!ret_t || !__btf_type_is_struct(ret_t)) { - verbose(env, "bpf_obj_new type ID argument must be of a struct\n"); - return -EINVAL; - } - - mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; - regs[BPF_REG_0].btf = ret_btf; - regs[BPF_REG_0].btf_id = ret_btf_id; - - env->insn_aux_data[insn_idx].obj_new_size = ret_t->size; - env->insn_aux_data[insn_idx].kptr_struct_meta = - btf_find_struct_meta(ret_btf, ret_btf_id); - } else if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { - env->insn_aux_data[insn_idx].kptr_struct_meta = - btf_find_struct_meta(meta.arg_obj_drop.btf, - meta.arg_obj_drop.btf_id); - } else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] || - meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) { - struct btf_field *field = meta.arg_list_head.field; - - mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; - regs[BPF_REG_0].btf = field->list_head.btf; - regs[BPF_REG_0].btf_id = field->list_head.value_btf_id; - regs[BPF_REG_0].off = field->list_head.node_offset; - } else if (meta.func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { - mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED; - regs[BPF_REG_0].btf = desc_btf; - regs[BPF_REG_0].btf_id = meta.ret_btf_id; - } else if (meta.func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { - ret_t = btf_type_by_id(desc_btf, meta.arg_constant.value); - if (!ret_t || !btf_type_is_struct(ret_t)) { - verbose(env, - "kfunc bpf_rdonly_cast type ID argument must be of a struct\n"); - return -EINVAL; + if (!IS_ERR(btf_resolve_size(desc_btf, ptr_type, &sz))) { + meta.r0_size = sz; + meta.r0_rdonly = true; } - - mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED; - regs[BPF_REG_0].btf = desc_btf; - regs[BPF_REG_0].btf_id = meta.arg_constant.value; - } else { - verbose(env, "kernel function %s unhandled dynamic return type\n", - meta.func_name); - return -EFAULT; } - } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); @@ -9284,11 +14211,30 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* Ensures we don't access the memory after a release_reference() */ if (meta.ref_obj_id) regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; + + if (is_kfunc_rcu_protected(&meta)) + regs[BPF_REG_0].type |= MEM_RCU; } else { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; + + if (meta.func_id == special_kfunc_list[KF_bpf_get_kmem_cache]) + regs[BPF_REG_0].type |= PTR_UNTRUSTED; + else if (is_kfunc_rcu_protected(&meta)) + regs[BPF_REG_0].type |= MEM_RCU; + + if (is_iter_next_kfunc(&meta)) { + struct bpf_reg_state *cur_iter; + + cur_iter = get_iter_from_state(env->cur_state, &meta); + + if (cur_iter->type & MEM_RCU) /* KF_RCU_PROTECTED */ + regs[BPF_REG_0].type |= MEM_RCU; + else + regs[BPF_REG_0].type |= PTR_TRUSTED; + } } if (is_kfunc_ret_null(&meta)) { @@ -9298,20 +14244,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); if (is_kfunc_acquire(&meta)) { - int id = acquire_reference_state(env, insn_idx); + int id = acquire_reference(env, insn_idx); if (id < 0) return id; if (is_kfunc_ret_null(&meta)) regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; + } else if (is_rbtree_node_type(ptr_type) || is_list_node_type(ptr_type)) { + ref_set_non_owning(env, ®s[BPF_REG_0]); } + if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) regs[BPF_REG_0].id = ++env->id_gen; - } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ + } else if (btf_type_is_void(t)) { + if (meta.btf == btf_vmlinux) { + if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl] || + meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) { + insn_aux->kptr_struct_meta = + btf_find_struct_meta(meta.arg_btf, + meta.arg_btf_id); + } + } + } - nargs = btf_type_vlen(func_proto); - args = (const struct btf_param *)(func_proto + 1); + if (is_kfunc_pkt_changing(&meta)) + clear_all_pkt_pointers(env); + + nargs = btf_type_vlen(meta.func_proto); + args = (const struct btf_param *)(meta.func_proto + 1); for (i = 0; i < nargs; i++) { u32 regno = i + 1; @@ -9323,47 +14284,13 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, mark_btf_func_reg_size(env, regno, t->size); } - return 0; -} - -static bool signed_add_overflows(s64 a, s64 b) -{ - /* Do the add in u64, where overflow is well-defined */ - s64 res = (s64)((u64)a + (u64)b); - - if (b < 0) - return res > a; - return res < a; -} - -static bool signed_add32_overflows(s32 a, s32 b) -{ - /* Do the add in u32, where overflow is well-defined */ - s32 res = (s32)((u32)a + (u32)b); - - if (b < 0) - return res > a; - return res < a; -} - -static bool signed_sub_overflows(s64 a, s64 b) -{ - /* Do the sub in u64, where overflow is well-defined */ - s64 res = (s64)((u64)a - (u64)b); - - if (b < 0) - return res < a; - return res > a; -} - -static bool signed_sub32_overflows(s32 a, s32 b) -{ - /* Do the sub in u32, where overflow is well-defined */ - s32 res = (s32)((u32)a - (u32)b); + if (is_iter_next_kfunc(&meta)) { + err = process_iter_next_call(env, insn_idx, &meta); + if (err) + return err; + } - if (b < 0) - return res < a; - return res > a; + return 0; } static bool check_reg_sane_offset(struct bpf_verifier_env *env, @@ -9443,7 +14370,9 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { - return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K; + return env->bypass_spec_v1 || + BPF_SRC(insn->code) == BPF_K || + cur_aux(env)->nospec; } static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, @@ -9484,16 +14413,15 @@ struct bpf_sanitize_info { bool mask_to_left; }; -static struct bpf_verifier_state * -sanitize_speculative_path(struct bpf_verifier_env *env, - const struct bpf_insn *insn, - u32 next_idx, u32 curr_idx) +static int sanitize_speculative_path(struct bpf_verifier_env *env, + const struct bpf_insn *insn, + u32 next_idx, u32 curr_idx) { struct bpf_verifier_state *branch; struct bpf_reg_state *regs; branch = push_stack(env, next_idx, curr_idx, true); - if (branch && insn) { + if (!IS_ERR(branch) && insn) { regs = branch->frame[branch->curframe]->regs; if (BPF_SRC(insn->code) == BPF_K) { mark_reg_unknown(env, regs, insn->dst_reg); @@ -9502,7 +14430,7 @@ sanitize_speculative_path(struct bpf_verifier_env *env, mark_reg_unknown(env, regs, insn->src_reg); } } - return branch; + return PTR_ERR_OR_ZERO(branch); } static int sanitize_ptr_alu(struct bpf_verifier_env *env, @@ -9521,7 +14449,6 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, u8 opcode = BPF_OP(insn->code); u32 alu_state, alu_limit; struct bpf_reg_state tmp; - bool ret; int err; if (can_skip_alu_sanitation(env, insn)) @@ -9592,13 +14519,14 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } - ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, - env->insn_idx); - if (!ptr_is_dst_reg && ret) + err = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); + if (err < 0) + return REASON_STACK; + if (!ptr_is_dst_reg) *dst_reg = tmp; - return !ret ? REASON_STACK : 0; + return 0; } static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) @@ -9643,10 +14571,9 @@ static int sanitize_err(struct bpf_verifier_env *env, case REASON_STACK: verbose(env, "R%d could not be pushed for speculative verification, %s\n", dst, err); - break; + return -ENOMEM; default: - verbose(env, "verifier internal error: unknown reason (%d)\n", - reason); + verifier_bug(env, "unknown reason (%d)", reason); break; } @@ -9713,7 +14640,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env, } break; default: - break; + return -EOPNOTSUPP; } return 0; @@ -9740,7 +14667,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; - int ret; + int ret, bounds_ret; dst_reg = ®s[dst]; @@ -9772,22 +14699,40 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } + /* + * Accesses to untrusted PTR_TO_MEM are done through probe + * instructions, hence no need to track offsets. + */ + if (base_type(ptr_reg->type) == PTR_TO_MEM && (ptr_reg->type & PTR_UNTRUSTED)) + return 0; + switch (base_type(ptr_reg->type)) { + case PTR_TO_CTX: + case PTR_TO_MAP_VALUE: + case PTR_TO_MAP_KEY: + case PTR_TO_STACK: + case PTR_TO_PACKET_META: + case PTR_TO_PACKET: + case PTR_TO_TP_BUFFER: + case PTR_TO_BTF_ID: + case PTR_TO_MEM: + case PTR_TO_BUF: + case PTR_TO_FUNC: + case CONST_PTR_TO_DYNPTR: + break; + case PTR_TO_FLOW_KEYS: + if (known) + break; + fallthrough; case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) break; fallthrough; - case PTR_TO_PACKET_END: - case PTR_TO_SOCKET: - case PTR_TO_SOCK_COMMON: - case PTR_TO_TCP_SOCK: - case PTR_TO_XDP_SOCK: + default: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; - default: - break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. @@ -9836,21 +14781,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, * added into the variable offset, and we copy the fixed offset * from ptr_reg. */ - if (signed_add_overflows(smin_ptr, smin_val) || - signed_add_overflows(smax_ptr, smax_val)) { + if (check_add_overflow(smin_ptr, smin_val, &dst_reg->smin_value) || + check_add_overflow(smax_ptr, smax_val, &dst_reg->smax_value)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value = smin_ptr + smin_val; - dst_reg->smax_value = smax_ptr + smax_val; } - if (umin_ptr + umin_val < umin_ptr || - umax_ptr + umax_val < umax_ptr) { + if (check_add_overflow(umin_ptr, umin_val, &dst_reg->umin_value) || + check_add_overflow(umax_ptr, umax_val, &dst_reg->umax_value)) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; - } else { - dst_reg->umin_value = umin_ptr + umin_val; - dst_reg->umax_value = umax_ptr + umax_val; } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; @@ -9893,14 +14832,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* A new variable offset is created. If the subtrahend is known * nonnegative, then any reg->range we had before is still good. */ - if (signed_sub_overflows(smin_ptr, smax_val) || - signed_sub_overflows(smax_ptr, smin_val)) { + if (check_sub_overflow(smin_ptr, smax_val, &dst_reg->smin_value) || + check_sub_overflow(smax_ptr, smin_val, &dst_reg->smax_value)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value = smin_ptr - smax_val; - dst_reg->smax_value = smax_ptr - smin_val; } if (umin_ptr < umax_val) { /* Overflow possible, we know nothing */ @@ -9938,11 +14874,19 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type)) return -EINVAL; reg_bounds_sync(dst_reg); - if (sanitize_check_bounds(env, insn, dst_reg) < 0) - return -EACCES; + bounds_ret = sanitize_check_bounds(env, insn, dst_reg); + if (bounds_ret == -EACCES) + return bounds_ret; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, &info, true); + if (verifier_bug_if(!can_skip_alu_sanitation(env, insn) + && !env->cur_state->speculative + && bounds_ret + && !ret, + env, "Pointer type unsupported by sanitize_check_bounds() not rejected by retrieve_ptr_limit() as required")) { + return -EFAULT; + } if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -9953,172 +14897,182 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s32 smin_val = src_reg->s32_min_value; - s32 smax_val = src_reg->s32_max_value; + s32 *dst_smin = &dst_reg->s32_min_value; + s32 *dst_smax = &dst_reg->s32_max_value; + u32 *dst_umin = &dst_reg->u32_min_value; + u32 *dst_umax = &dst_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; + bool min_overflow, max_overflow; - if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) || - signed_add32_overflows(dst_reg->s32_max_value, smax_val)) { - dst_reg->s32_min_value = S32_MIN; - dst_reg->s32_max_value = S32_MAX; - } else { - dst_reg->s32_min_value += smin_val; - dst_reg->s32_max_value += smax_val; + if (check_add_overflow(*dst_smin, src_reg->s32_min_value, dst_smin) || + check_add_overflow(*dst_smax, src_reg->s32_max_value, dst_smax)) { + *dst_smin = S32_MIN; + *dst_smax = S32_MAX; } - if (dst_reg->u32_min_value + umin_val < umin_val || - dst_reg->u32_max_value + umax_val < umax_val) { - dst_reg->u32_min_value = 0; - dst_reg->u32_max_value = U32_MAX; - } else { - dst_reg->u32_min_value += umin_val; - dst_reg->u32_max_value += umax_val; + + /* If either all additions overflow or no additions overflow, then + * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax = + * dst_umax + src_umax. Otherwise (some additions overflow), set + * the output bounds to unbounded. + */ + min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin); + max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax); + + if (!min_overflow && max_overflow) { + *dst_umin = 0; + *dst_umax = U32_MAX; } } static void scalar_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s64 smin_val = src_reg->smin_value; - s64 smax_val = src_reg->smax_value; + s64 *dst_smin = &dst_reg->smin_value; + s64 *dst_smax = &dst_reg->smax_value; + u64 *dst_umin = &dst_reg->umin_value; + u64 *dst_umax = &dst_reg->umax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; + bool min_overflow, max_overflow; - if (signed_add_overflows(dst_reg->smin_value, smin_val) || - signed_add_overflows(dst_reg->smax_value, smax_val)) { - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value += smin_val; - dst_reg->smax_value += smax_val; + if (check_add_overflow(*dst_smin, src_reg->smin_value, dst_smin) || + check_add_overflow(*dst_smax, src_reg->smax_value, dst_smax)) { + *dst_smin = S64_MIN; + *dst_smax = S64_MAX; } - if (dst_reg->umin_value + umin_val < umin_val || - dst_reg->umax_value + umax_val < umax_val) { - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - dst_reg->umin_value += umin_val; - dst_reg->umax_value += umax_val; + + /* If either all additions overflow or no additions overflow, then + * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax = + * dst_umax + src_umax. Otherwise (some additions overflow), set + * the output bounds to unbounded. + */ + min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin); + max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax); + + if (!min_overflow && max_overflow) { + *dst_umin = 0; + *dst_umax = U64_MAX; } } static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s32 smin_val = src_reg->s32_min_value; - s32 smax_val = src_reg->s32_max_value; + s32 *dst_smin = &dst_reg->s32_min_value; + s32 *dst_smax = &dst_reg->s32_max_value; + u32 *dst_umin = &dst_reg->u32_min_value; + u32 *dst_umax = &dst_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; + bool min_underflow, max_underflow; - if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) || - signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) { + if (check_sub_overflow(*dst_smin, src_reg->s32_max_value, dst_smin) || + check_sub_overflow(*dst_smax, src_reg->s32_min_value, dst_smax)) { /* Overflow possible, we know nothing */ - dst_reg->s32_min_value = S32_MIN; - dst_reg->s32_max_value = S32_MAX; - } else { - dst_reg->s32_min_value -= smax_val; - dst_reg->s32_max_value -= smin_val; + *dst_smin = S32_MIN; + *dst_smax = S32_MAX; } - if (dst_reg->u32_min_value < umax_val) { - /* Overflow possible, we know nothing */ - dst_reg->u32_min_value = 0; - dst_reg->u32_max_value = U32_MAX; - } else { - /* Cannot overflow (as long as bounds are consistent) */ - dst_reg->u32_min_value -= umax_val; - dst_reg->u32_max_value -= umin_val; + + /* If either all subtractions underflow or no subtractions + * underflow, it is okay to set: dst_umin = dst_umin - src_umax, + * dst_umax = dst_umax - src_umin. Otherwise (some subtractions + * underflow), set the output bounds to unbounded. + */ + min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin); + max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax); + + if (min_underflow && !max_underflow) { + *dst_umin = 0; + *dst_umax = U32_MAX; } } static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s64 smin_val = src_reg->smin_value; - s64 smax_val = src_reg->smax_value; + s64 *dst_smin = &dst_reg->smin_value; + s64 *dst_smax = &dst_reg->smax_value; + u64 *dst_umin = &dst_reg->umin_value; + u64 *dst_umax = &dst_reg->umax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; + bool min_underflow, max_underflow; - if (signed_sub_overflows(dst_reg->smin_value, smax_val) || - signed_sub_overflows(dst_reg->smax_value, smin_val)) { + if (check_sub_overflow(*dst_smin, src_reg->smax_value, dst_smin) || + check_sub_overflow(*dst_smax, src_reg->smin_value, dst_smax)) { /* Overflow possible, we know nothing */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value -= smax_val; - dst_reg->smax_value -= smin_val; + *dst_smin = S64_MIN; + *dst_smax = S64_MAX; } - if (dst_reg->umin_value < umax_val) { - /* Overflow possible, we know nothing */ - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - /* Cannot overflow (as long as bounds are consistent) */ - dst_reg->umin_value -= umax_val; - dst_reg->umax_value -= umin_val; + + /* If either all subtractions underflow or no subtractions + * underflow, it is okay to set: dst_umin = dst_umin - src_umax, + * dst_umax = dst_umax - src_umin. Otherwise (some subtractions + * underflow), set the output bounds to unbounded. + */ + min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin); + max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax); + + if (min_underflow && !max_underflow) { + *dst_umin = 0; + *dst_umax = U64_MAX; } } static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s32 smin_val = src_reg->s32_min_value; - u32 umin_val = src_reg->u32_min_value; - u32 umax_val = src_reg->u32_max_value; + s32 *dst_smin = &dst_reg->s32_min_value; + s32 *dst_smax = &dst_reg->s32_max_value; + u32 *dst_umin = &dst_reg->u32_min_value; + u32 *dst_umax = &dst_reg->u32_max_value; + s32 tmp_prod[4]; - if (smin_val < 0 || dst_reg->s32_min_value < 0) { - /* Ain't nobody got time to multiply that sign */ - __mark_reg32_unbounded(dst_reg); - return; - } - /* Both values are positive, so we can work with unsigned and - * copy the result to signed (unless it exceeds S32_MAX). - */ - if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) { - /* Potential overflow, we know nothing */ - __mark_reg32_unbounded(dst_reg); - return; + if (check_mul_overflow(*dst_umax, src_reg->u32_max_value, dst_umax) || + check_mul_overflow(*dst_umin, src_reg->u32_min_value, dst_umin)) { + /* Overflow possible, we know nothing */ + *dst_umin = 0; + *dst_umax = U32_MAX; } - dst_reg->u32_min_value *= umin_val; - dst_reg->u32_max_value *= umax_val; - if (dst_reg->u32_max_value > S32_MAX) { + if (check_mul_overflow(*dst_smin, src_reg->s32_min_value, &tmp_prod[0]) || + check_mul_overflow(*dst_smin, src_reg->s32_max_value, &tmp_prod[1]) || + check_mul_overflow(*dst_smax, src_reg->s32_min_value, &tmp_prod[2]) || + check_mul_overflow(*dst_smax, src_reg->s32_max_value, &tmp_prod[3])) { /* Overflow possible, we know nothing */ - dst_reg->s32_min_value = S32_MIN; - dst_reg->s32_max_value = S32_MAX; + *dst_smin = S32_MIN; + *dst_smax = S32_MAX; } else { - dst_reg->s32_min_value = dst_reg->u32_min_value; - dst_reg->s32_max_value = dst_reg->u32_max_value; + *dst_smin = min_array(tmp_prod, 4); + *dst_smax = max_array(tmp_prod, 4); } } static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { - s64 smin_val = src_reg->smin_value; - u64 umin_val = src_reg->umin_value; - u64 umax_val = src_reg->umax_value; + s64 *dst_smin = &dst_reg->smin_value; + s64 *dst_smax = &dst_reg->smax_value; + u64 *dst_umin = &dst_reg->umin_value; + u64 *dst_umax = &dst_reg->umax_value; + s64 tmp_prod[4]; - if (smin_val < 0 || dst_reg->smin_value < 0) { - /* Ain't nobody got time to multiply that sign */ - __mark_reg64_unbounded(dst_reg); - return; - } - /* Both values are positive, so we can work with unsigned and - * copy the result to signed (unless it exceeds S64_MAX). - */ - if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { - /* Potential overflow, we know nothing */ - __mark_reg64_unbounded(dst_reg); - return; + if (check_mul_overflow(*dst_umax, src_reg->umax_value, dst_umax) || + check_mul_overflow(*dst_umin, src_reg->umin_value, dst_umin)) { + /* Overflow possible, we know nothing */ + *dst_umin = 0; + *dst_umax = U64_MAX; } - dst_reg->umin_value *= umin_val; - dst_reg->umax_value *= umax_val; - if (dst_reg->umax_value > S64_MAX) { + if (check_mul_overflow(*dst_smin, src_reg->smin_value, &tmp_prod[0]) || + check_mul_overflow(*dst_smin, src_reg->smax_value, &tmp_prod[1]) || + check_mul_overflow(*dst_smax, src_reg->smin_value, &tmp_prod[2]) || + check_mul_overflow(*dst_smax, src_reg->smax_value, &tmp_prod[3])) { /* Overflow possible, we know nothing */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; + *dst_smin = S64_MIN; + *dst_smax = S64_MAX; } else { - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; + *dst_smin = min_array(tmp_prod, 4); + *dst_smax = max_array(tmp_prod, 4); } } @@ -10128,7 +15082,6 @@ 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) { @@ -10141,18 +15094,16 @@ 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; } } @@ -10161,7 +15112,6 @@ 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) { @@ -10174,18 +15124,16 @@ 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); @@ -10197,7 +15145,6 @@ 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) { @@ -10210,18 +15157,16 @@ 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; } } @@ -10230,7 +15175,6 @@ 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) { @@ -10243,18 +15187,16 @@ 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); @@ -10266,7 +15208,6 @@ 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); @@ -10277,10 +15218,10 @@ 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 { @@ -10294,7 +15235,6 @@ 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 */ @@ -10306,10 +15246,10 @@ 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 { @@ -10517,6 +15457,47 @@ 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_NEG: + 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. @@ -10526,53 +15507,11 @@ 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; } @@ -10608,6 +15547,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; + case BPF_NEG: + env->fake_reg[0] = *dst_reg; + __mark_reg_known(dst_reg, 0); + scalar32_min_max_sub(dst_reg, &env->fake_reg[0]); + scalar_min_max_sub(dst_reg, &env->fake_reg[0]); + dst_reg->var_off = tnum_neg(env->fake_reg[0].var_off); + break; case BPF_MUL: dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); scalar32_min_max_mul(dst_reg, &src_reg); @@ -10629,46 +15575,24 @@ 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; } @@ -10689,18 +15613,30 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; + bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); u8 opcode = BPF_OP(insn->code); int err; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; + + if (dst_reg->type == PTR_TO_ARENA) { + struct bpf_insn_aux_data *aux = cur_aux(env); + + if (BPF_CLASS(insn->code) == BPF_ALU64) + /* + * 32-bit operations zero upper bits automatically. + * 64-bit operations need to be converted to 32. + */ + aux->needs_zext = true; + + /* Any arithmetic operations are allowed on arena pointers */ + return 0; + } + if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; - else - /* Make sure ID is cleared otherwise dst_reg min/max could be - * incorrectly propagated into other registers by find_equal_scalars() - */ - dst_reg->id = 0; + if (BPF_SRC(insn->code) == BPF_X) { src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { @@ -10755,16 +15691,53 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(env, state, true); + print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); - return -EINVAL; + return -EFAULT; } if (WARN_ON(!src_reg)) { - print_verifier_state(env, state, true); + print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: no src_reg\n"); - return -EINVAL; + return -EFAULT; } - return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); + err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); + if (err) + return err; + /* + * Compilers can generate the code + * r1 = r2 + * r1 += 0x1 + * if r2 < 1000 goto ... + * use r1 in memory access + * So for 64-bit alu remember constant delta between r2 and r1 and + * update r1 after 'if' condition. + */ + if (env->bpf_capable && + BPF_OP(insn->code) == BPF_ADD && !alu32 && + dst_reg->id && is_reg_const(src_reg, false)) { + u64 val = reg_const_value(src_reg, false); + + if ((dst_reg->id & BPF_ADD_CONST) || + /* prevent overflow in sync_linked_regs() later */ + val > (u32)S32_MAX) { + /* + * If the register already went through rX += val + * we cannot accumulate another val into rx->off. + */ + dst_reg->off = 0; + dst_reg->id = 0; + } else { + dst_reg->id |= BPF_ADD_CONST; + dst_reg->off = val; + } + } else { + /* + * Make sure ID is cleared otherwise dst_reg min/max could be + * incorrectly propagated into other registers by sync_linked_regs() + */ + dst_reg->id = 0; + } + return 0; } /* check validity of 32-bit and 64-bit arithmetic operations */ @@ -10785,7 +15758,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || - BPF_CLASS(insn->code) == BPF_ALU64) { + (BPF_CLASS(insn->code) == BPF_ALU64 && + BPF_SRC(insn->code) != BPF_TO_LE)) { verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } @@ -10803,16 +15777,42 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check dest operand */ - err = check_reg_arg(env, insn->dst_reg, DST_OP); + if (opcode == BPF_NEG && + regs[insn->dst_reg].type == SCALAR_VALUE) { + err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); + err = err ?: adjust_scalar_min_max_vals(env, insn, + ®s[insn->dst_reg], + regs[insn->dst_reg]); + } else { + err = check_reg_arg(env, insn->dst_reg, DST_OP); + } if (err) return err; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { - if (insn->imm != 0 || insn->off != 0) { - verbose(env, "BPF_MOV uses reserved fields\n"); - return -EINVAL; + if (BPF_CLASS(insn->code) == BPF_ALU) { + if ((insn->off != 0 && insn->off != 8 && insn->off != 16) || + insn->imm) { + verbose(env, "BPF_MOV uses reserved fields\n"); + return -EINVAL; + } + } else if (insn->off == BPF_ADDR_SPACE_CAST) { + if (insn->imm != 1 && insn->imm != 1u << 16) { + 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) { + verbose(env, "BPF_MOV uses reserved fields\n"); + return -EINVAL; + } } /* check src operand */ @@ -10836,18 +15836,43 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) struct bpf_reg_state *dst_reg = regs + insn->dst_reg; if (BPF_CLASS(insn->code) == BPF_ALU64) { - /* case: R1 = R2 - * copy register state to dest reg - */ - if (src_reg->type == SCALAR_VALUE && !src_reg->id) - /* Assign src and dst registers the same ID - * that will be used by find_equal_scalars() - * to propagate min/max range. + 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) */ + 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 */ - src_reg->id = ++env->id_gen; - *dst_reg = *src_reg; - dst_reg->live |= REG_LIVE_WRITTEN; - dst_reg->subreg_def = DEF_NOT_SUBREG; + assign_scalar_id_before_mov(env, src_reg); + copy_register_state(dst_reg, src_reg); + dst_reg->subreg_def = DEF_NOT_SUBREG; + } else { + /* case: R1 = (s8, s16 s32)R2 */ + if (is_pointer_value(env, insn->src_reg)) { + verbose(env, + "R%d sign-extension part of pointer\n", + insn->src_reg); + return -EACCES; + } else if (src_reg->type == SCALAR_VALUE) { + bool no_sext; + + no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); + if (no_sext) + assign_scalar_id_before_mov(env, src_reg); + copy_register_state(dst_reg, src_reg); + if (!no_sext) + dst_reg->id = 0; + coerce_reg_to_size_sx(dst_reg, insn->off >> 3); + dst_reg->subreg_def = DEF_NOT_SUBREG; + } else { + mark_reg_unknown(env, regs, insn->dst_reg); + } + } } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { @@ -10856,14 +15881,31 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { - *dst_reg = *src_reg; - /* Make sure ID is cleared otherwise - * dst_reg min/max could be incorrectly - * propagated into src_reg by find_equal_scalars() - */ - dst_reg->id = 0; - dst_reg->live |= REG_LIVE_WRITTEN; - dst_reg->subreg_def = env->insn_idx + 1; + if (insn->off == 0) { + bool is_src_reg_u32 = get_reg_width(src_reg) <= 32; + + if (is_src_reg_u32) + assign_scalar_id_before_mov(env, src_reg); + copy_register_state(dst_reg, src_reg); + /* Make sure ID is cleared if src_reg is not in u32 + * range otherwise dst_reg min/max could be incorrectly + * propagated into src_reg by sync_linked_regs() + */ + if (!is_src_reg_u32) + dst_reg->id = 0; + dst_reg->subreg_def = env->insn_idx + 1; + } else { + /* case: W1 = (s8, s16)W2 */ + bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); + + if (no_sext) + assign_scalar_id_before_mov(env, src_reg); + copy_register_state(dst_reg, src_reg); + if (!no_sext) + dst_reg->id = 0; + dst_reg->subreg_def = env->insn_idx + 1; + coerce_subreg_to_size_sx(dst_reg, insn->off >> 3); + } } else { mark_reg_unknown(env, regs, insn->dst_reg); @@ -10894,7 +15936,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { - if (insn->imm != 0 || insn->off != 0) { + if (insn->imm != 0 || (insn->off != 0 && insn->off != 1) || + (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } @@ -10903,7 +15946,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; } else { - if (insn->src_reg != BPF_REG_0 || insn->off != 0) { + if (insn->src_reg != BPF_REG_0 || (insn->off != 0 && insn->off != 1) || + (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } @@ -10932,13 +15976,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); + err = err ?: adjust_reg_min_max_vals(env, insn); if (err) return err; - - return adjust_reg_min_max_vals(env, insn); } - return 0; + return reg_bounds_sanity_check(env, ®s[insn->dst_reg], "alu"); } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, @@ -11020,145 +16063,158 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, })); } -static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) -{ - struct tnum subreg = tnum_subreg(reg->var_off); - s32 sval = (s32)val; +/* + * <reg1> <op> <reg2>, currently assuming reg2 is a constant + */ +static int is_scalar_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, + u8 opcode, bool is_jmp32) +{ + struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off; + struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off; + u64 umin1 = is_jmp32 ? (u64)reg1->u32_min_value : reg1->umin_value; + u64 umax1 = is_jmp32 ? (u64)reg1->u32_max_value : reg1->umax_value; + s64 smin1 = is_jmp32 ? (s64)reg1->s32_min_value : reg1->smin_value; + s64 smax1 = is_jmp32 ? (s64)reg1->s32_max_value : reg1->smax_value; + u64 umin2 = is_jmp32 ? (u64)reg2->u32_min_value : reg2->umin_value; + u64 umax2 = is_jmp32 ? (u64)reg2->u32_max_value : reg2->umax_value; + s64 smin2 = is_jmp32 ? (s64)reg2->s32_min_value : reg2->smin_value; + s64 smax2 = is_jmp32 ? (s64)reg2->s32_max_value : reg2->smax_value; + + if (reg1 == reg2) { + switch (opcode) { + case BPF_JGE: + case BPF_JLE: + case BPF_JSGE: + case BPF_JSLE: + case BPF_JEQ: + return 1; + case BPF_JGT: + case BPF_JLT: + case BPF_JSGT: + case BPF_JSLT: + case BPF_JNE: + return 0; + case BPF_JSET: + if (tnum_is_const(t1)) + return t1.value != 0; + else + return (smin1 <= 0 && smax1 >= 0) ? -1 : 1; + default: + return -1; + } + } switch (opcode) { case BPF_JEQ: - if (tnum_is_const(subreg)) - return !!tnum_equals_const(subreg, val); - break; - case BPF_JNE: - if (tnum_is_const(subreg)) - return !tnum_equals_const(subreg, val); - break; - case BPF_JSET: - if ((~subreg.mask & subreg.value) & val) - return 1; - if (!((subreg.mask | subreg.value) & val)) - return 0; - break; - case BPF_JGT: - if (reg->u32_min_value > val) - return 1; - else if (reg->u32_max_value <= val) + /* constants, umin/umax and smin/smax checks would be + * redundant in this case because they all should match + */ + if (tnum_is_const(t1) && tnum_is_const(t2)) + return t1.value == t2.value; + if (!tnum_overlap(t1, t2)) return 0; - break; - case BPF_JSGT: - if (reg->s32_min_value > sval) - return 1; - else if (reg->s32_max_value <= sval) + /* non-overlapping ranges */ + if (umin1 > umax2 || umax1 < umin2) return 0; - break; - case BPF_JLT: - if (reg->u32_max_value < val) - return 1; - else if (reg->u32_min_value >= val) - return 0; - break; - case BPF_JSLT: - if (reg->s32_max_value < sval) - return 1; - else if (reg->s32_min_value >= sval) - return 0; - break; - case BPF_JGE: - if (reg->u32_min_value >= val) - return 1; - else if (reg->u32_max_value < val) + if (smin1 > smax2 || smax1 < smin2) return 0; + if (!is_jmp32) { + /* if 64-bit ranges are inconclusive, see if we can + * utilize 32-bit subrange knowledge to eliminate + * branches that can't be taken a priori + */ + if (reg1->u32_min_value > reg2->u32_max_value || + reg1->u32_max_value < reg2->u32_min_value) + return 0; + if (reg1->s32_min_value > reg2->s32_max_value || + reg1->s32_max_value < reg2->s32_min_value) + return 0; + } break; - case BPF_JSGE: - if (reg->s32_min_value >= sval) + case BPF_JNE: + /* constants, umin/umax and smin/smax checks would be + * redundant in this case because they all should match + */ + if (tnum_is_const(t1) && tnum_is_const(t2)) + return t1.value != t2.value; + if (!tnum_overlap(t1, t2)) return 1; - else if (reg->s32_max_value < sval) - return 0; - break; - case BPF_JLE: - if (reg->u32_max_value <= val) + /* non-overlapping ranges */ + if (umin1 > umax2 || umax1 < umin2) return 1; - else if (reg->u32_min_value > val) - return 0; - break; - case BPF_JSLE: - if (reg->s32_max_value <= sval) + if (smin1 > smax2 || smax1 < smin2) return 1; - else if (reg->s32_min_value > sval) - return 0; - break; - } - - return -1; -} - - -static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) -{ - s64 sval = (s64)val; - - switch (opcode) { - case BPF_JEQ: - if (tnum_is_const(reg->var_off)) - return !!tnum_equals_const(reg->var_off, val); - break; - case BPF_JNE: - if (tnum_is_const(reg->var_off)) - return !tnum_equals_const(reg->var_off, val); + if (!is_jmp32) { + /* if 64-bit ranges are inconclusive, see if we can + * utilize 32-bit subrange knowledge to eliminate + * branches that can't be taken a priori + */ + if (reg1->u32_min_value > reg2->u32_max_value || + reg1->u32_max_value < reg2->u32_min_value) + return 1; + if (reg1->s32_min_value > reg2->s32_max_value || + reg1->s32_max_value < reg2->s32_min_value) + return 1; + } break; case BPF_JSET: - if ((~reg->var_off.mask & reg->var_off.value) & val) + if (!is_reg_const(reg2, is_jmp32)) { + swap(reg1, reg2); + swap(t1, t2); + } + if (!is_reg_const(reg2, is_jmp32)) + return -1; + if ((~t1.mask & t1.value) & t2.value) return 1; - if (!((reg->var_off.mask | reg->var_off.value) & val)) + if (!((t1.mask | t1.value) & t2.value)) return 0; break; case BPF_JGT: - if (reg->umin_value > val) + if (umin1 > umax2) return 1; - else if (reg->umax_value <= val) + else if (umax1 <= umin2) return 0; break; case BPF_JSGT: - if (reg->smin_value > sval) + if (smin1 > smax2) return 1; - else if (reg->smax_value <= sval) + else if (smax1 <= smin2) return 0; break; case BPF_JLT: - if (reg->umax_value < val) + if (umax1 < umin2) return 1; - else if (reg->umin_value >= val) + else if (umin1 >= umax2) return 0; break; case BPF_JSLT: - if (reg->smax_value < sval) + if (smax1 < smin2) return 1; - else if (reg->smin_value >= sval) + else if (smin1 >= smax2) return 0; break; case BPF_JGE: - if (reg->umin_value >= val) + if (umin1 >= umax2) return 1; - else if (reg->umax_value < val) + else if (umax1 < umin2) return 0; break; case BPF_JSGE: - if (reg->smin_value >= sval) + if (smin1 >= smax2) return 1; - else if (reg->smax_value < sval) + else if (smax1 < smin2) return 0; break; case BPF_JLE: - if (reg->umax_value <= val) + if (umax1 <= umin2) return 1; - else if (reg->umin_value > val) + else if (umin1 > umax2) return 0; break; case BPF_JSLE: - if (reg->smax_value <= sval) + if (smax1 <= smin2) return 1; - else if (reg->smin_value > sval) + else if (smin1 > smax2) return 0; break; } @@ -11166,41 +16222,6 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) return -1; } -/* compute branch direction of the expression "if (reg opcode val) goto target;" - * and return: - * 1 - branch will be taken and "goto target" will be executed - * 0 - branch will not be taken and fall-through to next insn - * -1 - unknown. Example: "if (reg < 5)" is unknown when register value - * range [0,10] - */ -static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, - bool is_jmp32) -{ - if (__is_pointer_value(false, reg)) { - if (!reg_type_not_null(reg->type)) - return -1; - - /* If pointer is valid tests against zero will fail so we can - * use this to direct branch taken. - */ - if (val != 0) - return -1; - - switch (opcode) { - case BPF_JEQ: - return 0; - case BPF_JNE: - return 1; - default: - return -1; - } - } - - if (is_jmp32) - return is_branch32_taken(reg, val, opcode); - return is_branch64_taken(reg, val, opcode); -} - static int flip_opcode(u32 opcode) { /* How can we transform "a <op> b" into "b <op> a"? */ @@ -11262,216 +16283,295 @@ static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg, return -1; } -/* Adjusts the register min/max values in the case that the dst_reg is the - * variable register that we are working on, and src_reg is a constant or we're - * simply doing a BPF_K check. - * In JEQ/JNE cases we also adjust the var_off values. +/* compute branch direction of the expression "if (<reg1> opcode <reg2>) goto target;" + * and return: + * 1 - branch will be taken and "goto target" will be executed + * 0 - branch will not be taken and fall-through to next insn + * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value + * range [0,10] */ -static void reg_set_min_max(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, - u64 val, u32 val32, - u8 opcode, bool is_jmp32) -{ - struct tnum false_32off = tnum_subreg(false_reg->var_off); - struct tnum false_64off = false_reg->var_off; - struct tnum true_32off = tnum_subreg(true_reg->var_off); - struct tnum true_64off = true_reg->var_off; - s64 sval = (s64)val; - s32 sval32 = (s32)val32; - - /* If the dst_reg is a pointer, we can't learn anything about its - * variable offset from the compare (unless src_reg were a pointer into - * the same object, but we don't bother with that. - * Since false_reg and true_reg have the same type by construction, we - * only need to check one of them for pointerness. - */ - if (__is_pointer_value(false, false_reg)) - return; +static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, + u8 opcode, bool is_jmp32) +{ + if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32) + return is_pkt_ptr_branch_taken(reg1, reg2, opcode); + + if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) { + u64 val; + + /* arrange that reg2 is a scalar, and reg1 is a pointer */ + if (!is_reg_const(reg2, is_jmp32)) { + opcode = flip_opcode(opcode); + swap(reg1, reg2); + } + /* and ensure that reg2 is a constant */ + if (!is_reg_const(reg2, is_jmp32)) + return -1; + + if (!reg_not_null(reg1)) + return -1; + + /* If pointer is valid tests against zero will fail so we can + * use this to direct branch taken. + */ + val = reg_const_value(reg2, is_jmp32); + if (val != 0) + return -1; + + switch (opcode) { + case BPF_JEQ: + return 0; + case BPF_JNE: + return 1; + default: + return -1; + } + } + + /* now deal with two scalars, but not necessarily constants */ + return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32); +} +/* Opcode that corresponds to a *false* branch condition. + * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2 + */ +static u8 rev_opcode(u8 opcode) +{ switch (opcode) { - /* JEQ/JNE comparison doesn't change the register equivalence. - * - * r1 = r2; - * if (r1 == 42) goto label; - * ... - * label: // here both r1 and r2 are known to be 42. - * - * Hence when marking register as known preserve it's ID. + case BPF_JEQ: return BPF_JNE; + case BPF_JNE: return BPF_JEQ; + /* JSET doesn't have it's reverse opcode in BPF, so add + * BPF_X flag to denote the reverse of that operation */ + case BPF_JSET: return BPF_JSET | BPF_X; + case BPF_JSET | BPF_X: return BPF_JSET; + case BPF_JGE: return BPF_JLT; + case BPF_JGT: return BPF_JLE; + case BPF_JLE: return BPF_JGT; + case BPF_JLT: return BPF_JGE; + case BPF_JSGE: return BPF_JSLT; + case BPF_JSGT: return BPF_JSLE; + case BPF_JSLE: return BPF_JSGT; + case BPF_JSLT: return BPF_JSGE; + default: return 0; + } +} + +/* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */ +static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, + u8 opcode, bool is_jmp32) +{ + struct tnum t; + u64 val; + + /* 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) { - __mark_reg32_known(true_reg, val32); - true_32off = tnum_subreg(true_reg->var_off); + reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); + reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); + reg2->u32_min_value = reg1->u32_min_value; + reg2->u32_max_value = reg1->u32_max_value; + reg2->s32_min_value = reg1->s32_min_value; + reg2->s32_max_value = reg1->s32_max_value; + + t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); + reg2->var_off = tnum_with_subreg(reg2->var_off, t); } else { - ___mark_reg_known(true_reg, val); - true_64off = true_reg->var_off; + reg1->umin_value = max(reg1->umin_value, reg2->umin_value); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value); + reg1->smin_value = max(reg1->smin_value, reg2->smin_value); + reg1->smax_value = min(reg1->smax_value, reg2->smax_value); + reg2->umin_value = reg1->umin_value; + reg2->umax_value = reg1->umax_value; + reg2->smin_value = reg1->smin_value; + reg2->smax_value = reg1->smax_value; + + reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off); + reg2->var_off = reg1->var_off; } break; case BPF_JNE: + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + + /* try to recompute the bound of reg1 if reg2 is a const and + * is exactly the edge of reg1. + */ + val = reg_const_value(reg2, is_jmp32); if (is_jmp32) { - __mark_reg32_known(false_reg, val32); - false_32off = tnum_subreg(false_reg->var_off); + /* u32_min_value is not equal to 0xffffffff at this point, + * because otherwise u32_max_value is 0xffffffff as well, + * in such a case both reg1 and reg2 would be constants, + * jump would be predicted and reg_set_min_max() won't + * be called. + * + * Same reasoning works for all {u,s}{min,max}{32,64} cases + * below. + */ + if (reg1->u32_min_value == (u32)val) + reg1->u32_min_value++; + if (reg1->u32_max_value == (u32)val) + reg1->u32_max_value--; + if (reg1->s32_min_value == (s32)val) + reg1->s32_min_value++; + if (reg1->s32_max_value == (s32)val) + reg1->s32_max_value--; } else { - ___mark_reg_known(false_reg, val); - false_64off = false_reg->var_off; + if (reg1->umin_value == (u64)val) + reg1->umin_value++; + if (reg1->umax_value == (u64)val) + reg1->umax_value--; + if (reg1->smin_value == (s64)val) + reg1->smin_value++; + if (reg1->smax_value == (s64)val) + reg1->smax_value--; } break; case BPF_JSET: + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + val = reg_const_value(reg2, is_jmp32); + /* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X) + * requires single bit to learn something useful. E.g., if we + * know that `r1 & 0x3` is true, then which bits (0, 1, or both) + * are actually set? We can learn something definite only if + * it's a single-bit value to begin with. + * + * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have + * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor + * bit 1 is set, which we can readily use in adjustments. + */ + if (!is_power_of_2(val)) + break; if (is_jmp32) { - false_32off = tnum_and(false_32off, tnum_const(~val32)); - if (is_power_of_2(val32)) - true_32off = tnum_or(true_32off, - tnum_const(val32)); + t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { - false_64off = tnum_and(false_64off, tnum_const(~val)); - if (is_power_of_2(val)) - true_64off = tnum_or(true_64off, - tnum_const(val)); + reg1->var_off = tnum_or(reg1->var_off, tnum_const(val)); } break; - case BPF_JGE: - case BPF_JGT: - { + case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */ + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + val = reg_const_value(reg2, is_jmp32); + /* Forget the ranges before narrowing tnums, to avoid invariant + * violations if we're on a dead branch. + */ + __mark_reg_unbounded(reg1); if (is_jmp32) { - u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1; - u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32; - - false_reg->u32_max_value = min(false_reg->u32_max_value, - false_umax); - true_reg->u32_min_value = max(true_reg->u32_min_value, - true_umin); + t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { - u64 false_umax = opcode == BPF_JGT ? val : val - 1; - u64 true_umin = opcode == BPF_JGT ? val + 1 : val; - - false_reg->umax_value = min(false_reg->umax_value, false_umax); - true_reg->umin_value = max(true_reg->umin_value, true_umin); + reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val)); } break; - } - case BPF_JSGE: - case BPF_JSGT: - { + case BPF_JLE: if (is_jmp32) { - s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1; - s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32; - - false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax); - true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); + reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); } else { - s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; - s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; - - false_reg->smax_value = min(false_reg->smax_value, false_smax); - true_reg->smin_value = max(true_reg->smin_value, true_smin); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value); + reg2->umin_value = max(reg1->umin_value, reg2->umin_value); } break; - } - case BPF_JLE: case BPF_JLT: - { if (is_jmp32) { - u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1; - u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32; - - false_reg->u32_min_value = max(false_reg->u32_min_value, - false_umin); - true_reg->u32_max_value = min(true_reg->u32_max_value, - true_umax); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1); + reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value); } else { - u64 false_umin = opcode == BPF_JLT ? val : val + 1; - u64 true_umax = opcode == BPF_JLT ? val - 1 : val; - - false_reg->umin_value = max(false_reg->umin_value, false_umin); - true_reg->umax_value = min(true_reg->umax_value, true_umax); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1); + reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value); } break; - } case BPF_JSLE: + if (is_jmp32) { + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); + reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); + } else { + reg1->smax_value = min(reg1->smax_value, reg2->smax_value); + reg2->smin_value = max(reg1->smin_value, reg2->smin_value); + } + break; case BPF_JSLT: - { if (is_jmp32) { - s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1; - s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32; - - false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin); - true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax); + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1); + reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value); } else { - s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; - s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; - - false_reg->smin_value = max(false_reg->smin_value, false_smin); - true_reg->smax_value = min(true_reg->smax_value, true_smax); + reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1); + reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value); } break; - } default: return; } - - if (is_jmp32) { - false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off), - tnum_subreg(false_32off)); - true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off), - tnum_subreg(true_32off)); - __reg_combine_32_into_64(false_reg); - __reg_combine_32_into_64(true_reg); - } else { - false_reg->var_off = false_64off; - true_reg->var_off = true_64off; - __reg_combine_64_into_32(false_reg); - __reg_combine_64_into_32(true_reg); - } } -/* Same as above, but for the case that dst_reg holds a constant and src_reg is - * the variable reg. +/* Adjusts the register min/max values in the case that the dst_reg and + * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K + * check, in which case we 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. */ -static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, - u64 val, u32 val32, - u8 opcode, bool is_jmp32) +static int reg_set_min_max(struct bpf_verifier_env *env, + struct bpf_reg_state *true_reg1, + struct bpf_reg_state *true_reg2, + struct bpf_reg_state *false_reg1, + struct bpf_reg_state *false_reg2, + u8 opcode, bool is_jmp32) { - opcode = flip_opcode(opcode); - /* This uses zero as "not present in table"; luckily the zero opcode, - * BPF_JA, can't get here. + int err; + + /* If either register is a pointer, we can't learn anything about its + * variable offset from the compare (unless they were a pointer into + * the same object, but we don't bother with that). */ - if (opcode) - reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32); -} - -/* Regs are known to be equal, so intersect their min/max/var_off */ -static void __reg_combine_min_max(struct bpf_reg_state *src_reg, - struct bpf_reg_state *dst_reg) -{ - src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value, - dst_reg->umin_value); - src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value, - dst_reg->umax_value); - src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value, - dst_reg->smin_value); - src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value, - dst_reg->smax_value); - src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off, - dst_reg->var_off); - reg_bounds_sync(src_reg); - reg_bounds_sync(dst_reg); -} + if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE) + return 0; -static void reg_combine_min_max(struct bpf_reg_state *true_src, - struct bpf_reg_state *true_dst, - struct bpf_reg_state *false_src, - struct bpf_reg_state *false_dst, - u8 opcode) -{ - switch (opcode) { - case BPF_JEQ: - __reg_combine_min_max(true_src, true_dst); - break; - case BPF_JNE: - __reg_combine_min_max(false_src, false_dst); - break; - } + /* We compute branch direction for same SCALAR_VALUE registers in + * is_scalar_branch_taken(). For unknown branch directions (e.g., BPF_JSET) + * on the same registers, we don't need to adjust the min/max values. + */ + if (false_reg1 == false_reg2) + return 0; + + /* fallthrough (FALSE) branch */ + regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32); + reg_bounds_sync(false_reg1); + reg_bounds_sync(false_reg2); + + /* jump (TRUE) branch */ + regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32); + reg_bounds_sync(true_reg1); + reg_bounds_sync(true_reg2); + + err = reg_bounds_sanity_check(env, true_reg1, "true_reg1"); + err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2"); + err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1"); + err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2"); + return err; } static void mark_ptr_or_null_reg(struct bpf_func_state *state, @@ -11491,8 +16591,10 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, */ if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0))) return; - if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL) && WARN_ON_ONCE(reg->off)) + if (!(type_is_ptr_alloc_obj(reg->type) || type_is_non_owning_ref(reg->type)) && + WARN_ON_ONCE(reg->off)) return; + if (is_null) { reg->type = SCALAR_VALUE; /* We don't need id and ref_obj_id from this point @@ -11535,7 +16637,7 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, * No one could have freed the reference state before * doing the NULL check. */ - WARN_ON_ONCE(release_reference_state(state, id)); + WARN_ON_ONCE(release_reference_nomark(vstate, id)); bpf_for_each_reg_in_vstate(vstate, state, reg, ({ mark_ptr_or_null_reg(state, reg, id, is_null); @@ -11647,16 +16749,97 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, return true; } -static void find_equal_scalars(struct bpf_verifier_state *vstate, - struct bpf_reg_state *known_reg) +static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_state *reg, + u32 id, u32 frameno, u32 spi_or_reg, bool is_reg) { - struct bpf_func_state *state; + struct linked_reg *e; + + if (reg->type != SCALAR_VALUE || (reg->id & ~BPF_ADD_CONST) != id) + return; + + e = linked_regs_push(reg_set); + if (e) { + e->frameno = frameno; + e->is_reg = is_reg; + e->regno = spi_or_reg; + } else { + reg->id = 0; + } +} + +/* For all R being scalar registers or spilled scalar registers + * in verifier state, save R in linked_regs if R->id == id. + * If there are too many Rs sharing same id, reset id for leftover Rs. + */ +static void collect_linked_regs(struct bpf_verifier_state *vstate, u32 id, + struct linked_regs *linked_regs) +{ + struct bpf_func_state *func; struct bpf_reg_state *reg; + int i, j; - bpf_for_each_reg_in_vstate(vstate, state, reg, ({ - if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; - })); + id = id & ~BPF_ADD_CONST; + for (i = vstate->curframe; i >= 0; i--) { + func = vstate->frame[i]; + for (j = 0; j < BPF_REG_FP; j++) { + reg = &func->regs[j]; + __collect_linked_regs(linked_regs, reg, id, i, j, true); + } + for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { + if (!is_spilled_reg(&func->stack[j])) + continue; + reg = &func->stack[j].spilled_ptr; + __collect_linked_regs(linked_regs, reg, id, i, j, false); + } + } +} + +/* For all R in linked_regs, copy known_reg range into R + * if R->id == known_reg->id. + */ +static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_state *known_reg, + struct linked_regs *linked_regs) +{ + struct bpf_reg_state fake_reg; + struct bpf_reg_state *reg; + struct linked_reg *e; + int i; + + for (i = 0; i < linked_regs->cnt; ++i) { + e = &linked_regs->entries[i]; + reg = e->is_reg ? &vstate->frame[e->frameno]->regs[e->regno] + : &vstate->frame[e->frameno]->stack[e->spi].spilled_ptr; + if (reg->type != SCALAR_VALUE || reg == known_reg) + continue; + if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST)) + continue; + if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) || + reg->off == known_reg->off) { + s32 saved_subreg_def = reg->subreg_def; + + copy_register_state(reg, known_reg); + reg->subreg_def = saved_subreg_def; + } else { + s32 saved_subreg_def = reg->subreg_def; + s32 saved_off = reg->off; + + fake_reg.type = SCALAR_VALUE; + __mark_reg_known(&fake_reg, (s32)reg->off - (s32)known_reg->off); + + /* reg = known_reg; reg += delta */ + copy_register_state(reg, known_reg); + /* + * Must preserve off, id and add_const flag, + * otherwise another sync_linked_regs() will be incorrect. + */ + reg->off = saved_off; + reg->subreg_def = saved_subreg_def; + + scalar32_min_max_add(reg, &fake_reg); + scalar_min_max_add(reg, &fake_reg); + reg->var_off = tnum_add(reg->var_off, fake_reg.var_off); + } + } } static int check_cond_jmp_op(struct bpf_verifier_env *env, @@ -11667,17 +16850,49 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; + struct linked_regs linked_regs = {}; u8 opcode = BPF_OP(insn->code); + int insn_flags = 0; bool is_jmp32; int pred = -1; int err; /* Only conditional jumps are expected to reach here. */ - if (opcode == BPF_JA || opcode > BPF_JSLE) { + if (opcode == BPF_JA || opcode > BPF_JCOND) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } + if (opcode == BPF_JCOND) { + struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; + int idx = *insn_idx; + + if (insn->code != (BPF_JMP | BPF_JCOND) || + insn->src_reg != BPF_MAY_GOTO || + insn->dst_reg || insn->imm) { + verbose(env, "invalid may_goto imm %d\n", insn->imm); + return -EINVAL; + } + prev_st = find_prev_entry(env, cur_st->parent, idx); + + /* branch out 'fallthrough' insn as a new state to explore */ + queued_st = push_stack(env, idx + 1, idx, false); + if (IS_ERR(queued_st)) + return PTR_ERR(queued_st); + + queued_st->may_goto_depth++; + if (prev_st) + widen_imprecise_scalars(env, prev_st, queued_st); + *insn_idx += insn->off; + return 0; + } + + /* check src2 operand */ + err = check_reg_arg(env, insn->dst_reg, SRC_OP); + if (err) + return err; + + dst_reg = ®s[insn->dst_reg]; if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); @@ -11689,47 +16904,40 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (err) return err; - if (is_pointer_value(env, insn->src_reg)) { + src_reg = ®s[insn->src_reg]; + if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) && + is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } - src_reg = ®s[insn->src_reg]; + + if (src_reg->type == PTR_TO_STACK) + insn_flags |= INSN_F_SRC_REG_STACK; + if (dst_reg->type == PTR_TO_STACK) + insn_flags |= INSN_F_DST_REG_STACK; } else { if (insn->src_reg != BPF_REG_0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } - } + src_reg = &env->fake_reg[0]; + memset(src_reg, 0, sizeof(*src_reg)); + src_reg->type = SCALAR_VALUE; + __mark_reg_known(src_reg, insn->imm); - /* check src2 operand */ - err = check_reg_arg(env, insn->dst_reg, SRC_OP); - if (err) - return err; - - dst_reg = ®s[insn->dst_reg]; - is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; + if (dst_reg->type == PTR_TO_STACK) + insn_flags |= INSN_F_DST_REG_STACK; + } - if (BPF_SRC(insn->code) == BPF_K) { - pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32); - } else if (src_reg->type == SCALAR_VALUE && - is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) { - pred = is_branch_taken(dst_reg, - tnum_subreg(src_reg->var_off).value, - opcode, - is_jmp32); - } else if (src_reg->type == SCALAR_VALUE && - !is_jmp32 && tnum_is_const(src_reg->var_off)) { - pred = is_branch_taken(dst_reg, - src_reg->var_off.value, - opcode, - is_jmp32); - } else if (reg_is_pkt_pointer_any(dst_reg) && - reg_is_pkt_pointer_any(src_reg) && - !is_jmp32) { - pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode); + if (insn_flags) { + err = push_jmp_history(env, this_branch, insn_flags, 0); + if (err) + return err; } + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; + pred = is_branch_taken(dst_reg, src_reg, opcode, is_jmp32); if (pred >= 0) { /* If we get here with a dst_reg pointer type it is because * above is_branch_taken() special cased the 0 comparison. @@ -11748,10 +16956,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * the fall-through branch for simulation under speculative * execution. */ - if (!env->bypass_spec_v1 && - !sanitize_speculative_path(env, insn, *insn_idx + 1, - *insn_idx)) - return -EFAULT; + if (!env->bypass_spec_v1) { + err = sanitize_speculative_path(env, insn, *insn_idx + 1, *insn_idx); + if (err < 0) + return err; + } + if (env->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch, this_branch->curframe); *insn_idx += insn->off; return 0; } else if (pred == 0) { @@ -11759,71 +16970,68 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * program will go. If needed, push the goto branch for * simulation under speculative execution. */ - if (!env->bypass_spec_v1 && - !sanitize_speculative_path(env, insn, - *insn_idx + insn->off + 1, - *insn_idx)) - return -EFAULT; + if (!env->bypass_spec_v1) { + err = sanitize_speculative_path(env, insn, *insn_idx + insn->off + 1, + *insn_idx); + if (err < 0) + return err; + } + if (env->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch, this_branch->curframe); return 0; } - other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, - false); - if (!other_branch) - return -EFAULT; + /* Push scalar registers sharing same ID to jump history, + * do this before creating 'other_branch', so that both + * 'this_branch' and 'other_branch' share this history + * if parent state is created. + */ + if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) + collect_linked_regs(this_branch, src_reg->id, &linked_regs); + if (dst_reg->type == SCALAR_VALUE && dst_reg->id) + collect_linked_regs(this_branch, dst_reg->id, &linked_regs); + if (linked_regs.cnt > 1) { + err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs)); + if (err) + return err; + } + + other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, false); + if (IS_ERR(other_branch)) + return PTR_ERR(other_branch); other_branch_regs = other_branch->frame[other_branch->curframe]->regs; - /* detect if we are comparing against a constant value so we can adjust - * our min/max values for our dst register. - * this is only legit if both are scalars (or pointers to the same - * object, I suppose, see the PTR_MAYBE_NULL related if block below), - * because otherwise the different base pointers mean the offsets aren't - * comparable. - */ if (BPF_SRC(insn->code) == BPF_X) { - struct bpf_reg_state *src_reg = ®s[insn->src_reg]; - - if (dst_reg->type == SCALAR_VALUE && - src_reg->type == SCALAR_VALUE) { - if (tnum_is_const(src_reg->var_off) || - (is_jmp32 && - tnum_is_const(tnum_subreg(src_reg->var_off)))) - reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, - src_reg->var_off.value, - tnum_subreg(src_reg->var_off).value, - opcode, is_jmp32); - else if (tnum_is_const(dst_reg->var_off) || - (is_jmp32 && - tnum_is_const(tnum_subreg(dst_reg->var_off)))) - reg_set_min_max_inv(&other_branch_regs[insn->src_reg], - src_reg, - dst_reg->var_off.value, - tnum_subreg(dst_reg->var_off).value, - opcode, is_jmp32); - else if (!is_jmp32 && - (opcode == BPF_JEQ || opcode == BPF_JNE)) - /* Comparing for equality, we can combine knowledge */ - reg_combine_min_max(&other_branch_regs[insn->src_reg], - &other_branch_regs[insn->dst_reg], - src_reg, dst_reg, opcode); - if (src_reg->id && - !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { - find_equal_scalars(this_branch, src_reg); - find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]); - } - - } - } else if (dst_reg->type == SCALAR_VALUE) { - reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, insn->imm, (u32)insn->imm, - opcode, is_jmp32); + err = reg_set_min_max(env, + &other_branch_regs[insn->dst_reg], + &other_branch_regs[insn->src_reg], + dst_reg, src_reg, opcode, is_jmp32); + } else /* BPF_SRC(insn->code) == BPF_K */ { + /* reg_set_min_max() can mangle the fake_reg. Make a copy + * so that these are two different memory locations. The + * src_reg is not used beyond here in context of K. + */ + memcpy(&env->fake_reg[1], &env->fake_reg[0], + sizeof(env->fake_reg[0])); + err = reg_set_min_max(env, + &other_branch_regs[insn->dst_reg], + &env->fake_reg[0], + dst_reg, &env->fake_reg[1], + opcode, is_jmp32); } + if (err) + return err; + if (BPF_SRC(insn->code) == BPF_X && + src_reg->type == SCALAR_VALUE && src_reg->id && + !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { + sync_linked_regs(this_branch, src_reg, &linked_regs); + sync_linked_regs(other_branch, &other_branch_regs[insn->src_reg], &linked_regs); + } if (dst_reg->type == SCALAR_VALUE && dst_reg->id && !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) { - find_equal_scalars(this_branch, dst_reg); - find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]); + sync_linked_regs(this_branch, dst_reg, &linked_regs); + sync_linked_regs(other_branch, &other_branch_regs[insn->dst_reg], &linked_regs); } /* if one pointer register is compared to another pointer @@ -11885,7 +17093,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) - print_insn_state(env, this_branch->frame[this_branch->curframe]); + print_insn_state(env, this_branch, this_branch->curframe); return 0; } @@ -11937,7 +17145,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) dst_reg->btf_id = aux->btf_var.btf_id; break; default: - verbose(env, "bpf verifier is misconfigured\n"); + verifier_bug(env, "pseudo btf id: unexpected dst reg type"); return -EFAULT; } return 0; @@ -11967,16 +17175,21 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { + if (map->map_type == BPF_MAP_TYPE_ARENA) { + __mark_reg_unknown(env, dst_reg); + return 0; + } dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; - WARN_ON_ONCE(map->max_entries != 1); + WARN_ON_ONCE(map->map_type != BPF_MAP_TYPE_INSN_ARRAY && + map->max_entries != 1); /* We want reg->id to be same (0) as map_value is not distinct */ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; } else { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + verifier_bug(env, "unexpected src reg value for ldimm64"); + return -EFAULT; } return 0; @@ -12022,8 +17235,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } if (!env->ops->gen_ld_abs) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + verifier_bug(env, "gen_ld_abs is null"); + return -EFAULT; } if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || @@ -12042,21 +17255,9 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) * gen_ld_abs() may terminate the program at runtime, leading to * reference leak. */ - err = check_reference_leak(env); - if (err) { - verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); + err = check_resource_leak(env, false, true, "BPF_LD_[ABS|IND]"); + if (err) return err; - } - - if (env->cur_state->active_lock.ptr) { - verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); - return -EINVAL; - } - - if (env->cur_state->active_rcu_lock) { - verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_rcu_read_lock-ed region\n"); - return -EINVAL; - } if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, @@ -12091,28 +17292,47 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } -static int check_return_code(struct bpf_verifier_env *env) +static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name) { + const char *exit_ctx = "At program exit"; struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; - struct bpf_reg_state *reg; - struct tnum range = tnum_range(0, 1); + struct bpf_reg_state *reg = reg_state(env, regno); + struct bpf_retval_range range = retval_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; struct bpf_func_state *frame = env->cur_state->frame[0]; const bool is_subprog = frame->subprogno; + bool return_32bit = false; + const struct btf_type *reg_type, *ret_type = NULL; /* LSM and struct_ops func-ptr's return type could be "void" */ - if (!is_subprog) { + if (!is_subprog || frame->in_exception_callback_fn) { switch (prog_type) { case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type == BPF_LSM_CGROUP) /* See below, can be 0 or 0-1 depending on hook. */ break; - fallthrough; + if (!prog->aux->attach_func_proto->type) + return 0; + break; case BPF_PROG_TYPE_STRUCT_OPS: if (!prog->aux->attach_func_proto->type) return 0; + + if (frame->in_exception_callback_fn) + break; + + /* Allow a struct_ops program to return a referenced kptr if it + * matches the operator's return type and is in its unmodified + * form. A scalar zero (i.e., a null pointer) is also allowed. + */ + reg_type = reg->btf ? btf_type_by_id(reg->btf, reg->btf_id) : NULL; + ret_type = btf_type_resolve_ptr(prog->aux->attach_btf, + prog->aux->attach_func_proto->type, + NULL); + if (ret_type && ret_type == reg_type && reg->ref_obj_id) + return __check_ptr_off_reg(env, reg, regno, false); break; default: break; @@ -12125,36 +17345,25 @@ static int check_return_code(struct bpf_verifier_env *env) * of bpf_exit, which means that program wrote * something into it earlier */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); + err = check_reg_arg(env, regno, SRC_OP); if (err) return err; - if (is_pointer_value(env, BPF_REG_0)) { - verbose(env, "R0 leaks addr as return value\n"); + if (is_pointer_value(env, regno)) { + verbose(env, "R%d leaks addr as return value\n", regno); return -EACCES; } - reg = cur_regs(env) + BPF_REG_0; - if (frame->in_async_callback_fn) { - /* enforce return zero from async callbacks like timer */ - if (reg->type != SCALAR_VALUE) { - verbose(env, "In async callback the register R0 is not a known value (%s)\n", - reg_type_str(env, reg->type)); - return -EINVAL; - } - - if (!tnum_in(tnum_const(0), reg->var_off)) { - verbose_invalid_scalar(env, reg, &range, "async callback", "R0"); - return -EINVAL; - } - return 0; + exit_ctx = "At async callback return"; + range = frame->callback_ret_range; + goto enforce_retval; } - if (is_subprog) { + if (is_subprog && !frame->in_exception_callback_fn) { if (reg->type != SCALAR_VALUE) { - verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", - reg_type_str(env, reg->type)); + verbose(env, "At subprogram exit the register R%d is not a scalar value (%s)\n", + regno, reg_type_str(env, reg->type)); return -EINVAL; } return 0; @@ -12164,18 +17373,21 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || - env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) - range = tnum_range(1, 1); + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME) + range = retval_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) - range = tnum_range(0, 3); + range = retval_range(0, 3); break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { - range = tnum_range(0, 3); + range = retval_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } break; @@ -12188,13 +17400,13 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_RAW_TRACEPOINT: if (!env->prog->aux->attach_btf_id) return 0; - range = tnum_const(0); + range = retval_range(0, 0); break; case BPF_PROG_TYPE_TRACING: switch (env->prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: - range = tnum_const(0); + range = retval_range(0, 0); break; case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: @@ -12205,25 +17417,45 @@ static int check_return_code(struct bpf_verifier_env *env) return -ENOTSUPP; } break; + case BPF_PROG_TYPE_KPROBE: + switch (env->prog->expected_attach_type) { + case BPF_TRACE_KPROBE_SESSION: + case BPF_TRACE_UPROBE_SESSION: + range = retval_range(0, 1); + break; + default: + return 0; + } + break; case BPF_PROG_TYPE_SK_LOOKUP: - range = tnum_range(SK_DROP, SK_PASS); + range = retval_range(SK_DROP, SK_PASS); break; case BPF_PROG_TYPE_LSM: if (env->prog->expected_attach_type != BPF_LSM_CGROUP) { - /* Regular BPF_PROG_TYPE_LSM programs can return - * any value. - */ - return 0; - } - if (!env->prog->aux->attach_func_proto->type) { + /* no range found, any return value is allowed */ + if (!get_func_retval_range(env->prog, &range)) + return 0; + /* no restricted range, any return value is allowed */ + if (range.minval == S32_MIN && range.maxval == S32_MAX) + return 0; + return_32bit = true; + } else if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ - range = tnum_range(1, 1); + range = retval_range(1, 1); } break; + case BPF_PROG_TYPE_NETFILTER: + range = retval_range(NF_DROP, NF_ACCEPT); + break; + case BPF_PROG_TYPE_STRUCT_OPS: + if (!ret_type) + return 0; + range = retval_range(0, 0); + break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value * depends on the to-be-replaced kernel func or bpf program. @@ -12232,15 +17464,21 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; } +enforce_retval: if (reg->type != SCALAR_VALUE) { - verbose(env, "At program exit the register R0 is not a known value (%s)\n", - reg_type_str(env, reg->type)); + verbose(env, "%s the register R%d is not a known value (%s)\n", + exit_ctx, regno, reg_type_str(env, reg->type)); return -EINVAL; } - if (!tnum_in(range, reg->var_off)) { - verbose_invalid_scalar(env, reg, &range, "program exit", "R0"); - if (prog->expected_attach_type == BPF_LSM_CGROUP && + err = mark_chain_precision(env, regno); + if (err) + return err; + + if (!retval_range_within(range, reg, return_32bit)) { + verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name); + if (!is_subprog && + prog->expected_attach_type == BPF_LSM_CGROUP && prog_type == BPF_PROG_TYPE_LSM && !prog->aux->attach_func_proto->type) verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); @@ -12253,6 +17491,38 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; } +static void mark_subprog_changes_pkt_data(struct bpf_verifier_env *env, int off) +{ + struct bpf_subprog_info *subprog; + + subprog = bpf_find_containing_subprog(env, off); + subprog->changes_pkt_data = true; +} + +static void mark_subprog_might_sleep(struct bpf_verifier_env *env, int off) +{ + struct bpf_subprog_info *subprog; + + subprog = bpf_find_containing_subprog(env, off); + subprog->might_sleep = true; +} + +/* 't' is an index of a call-site. + * 'w' is a callee entry point. + * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED. + * Rely on DFS traversal order and absence of recursive calls to guarantee that + * callee's change_pkt_data marks would be correct at that moment. + */ +static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w) +{ + struct bpf_subprog_info *caller, *callee; + + caller = bpf_find_containing_subprog(env, t); + callee = bpf_find_containing_subprog(env, w); + caller->changes_pkt_data |= callee->changes_pkt_data; + caller->might_sleep |= callee->might_sleep; +} + /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered @@ -12293,29 +17563,34 @@ enum { BRANCH = 2, }; -static u32 state_htab_size(struct bpf_verifier_env *env) +static void mark_prune_point(struct bpf_verifier_env *env, int idx) { - return env->prog->len; + env->insn_aux_data[idx].prune_point = true; } -static struct bpf_verifier_state_list **explored_state( - struct bpf_verifier_env *env, - int idx) +static bool is_prune_point(struct bpf_verifier_env *env, int insn_idx) { - struct bpf_verifier_state *cur = env->cur_state; - struct bpf_func_state *state = cur->frame[cur->curframe]; + return env->insn_aux_data[insn_idx].prune_point; +} - return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; +static void mark_force_checkpoint(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].force_checkpoint = true; } -static void mark_prune_point(struct bpf_verifier_env *env, int idx) +static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx) { - env->insn_aux_data[idx].prune_point = true; + return env->insn_aux_data[insn_idx].force_checkpoint; } -static bool is_prune_point(struct bpf_verifier_env *env, int insn_idx) +static void mark_calls_callback(struct bpf_verifier_env *env, int idx) { - return env->insn_aux_data[insn_idx].prune_point; + env->insn_aux_data[idx].calls_callback = true; +} + +bool bpf_calls_callback(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].calls_callback; } enum { @@ -12328,8 +17603,7 @@ enum { * w - next instruction * e - edge */ -static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, - bool loop_ok) +static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; @@ -12361,7 +17635,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, insn_stack[env->cfg.cur_stack++] = w; return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { - if (loop_ok && env->bpf_capable) + if (env->bpf_capable) return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); @@ -12371,7 +17645,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { - verbose(env, "insn state internal bug\n"); + verifier_bug(env, "insn state internal bug"); return -EFAULT; } return DONE_EXPLORING; @@ -12381,28 +17655,526 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { - int ret; + int ret, insn_sz; + int w; - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); + insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; + ret = push_insn(t, t + insn_sz, FALLTHROUGH, env); if (ret) return ret; - mark_prune_point(env, t + 1); + mark_prune_point(env, t + insn_sz); /* when we exit from subprog, we need to record non-linear history */ - mark_jmp_point(env, t + 1); + mark_jmp_point(env, t + insn_sz); if (visit_callee) { + w = t + insns[t].imm + 1; mark_prune_point(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, - /* It's ok to allow recursion from CFG point of - * view. __check_func_call() will do the actual - * check. - */ - bpf_pseudo_func(insns + t)); + merge_callee_effects(env, t, w); + ret = push_insn(t, w, BRANCH, env); } return ret; } +/* Bitmask with 1s for all caller saved registers */ +#define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) + +/* True if do_misc_fixups() replaces calls to helper number 'imm', + * replacement patch is presumed to follow bpf_fastcall contract + * (see mark_fastcall_pattern_for_call() below). + */ +static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) +{ + switch (imm) { +#ifdef CONFIG_X86_64 + case BPF_FUNC_get_smp_processor_id: + return env->prog->jit_requested && bpf_jit_supports_percpu_insn(); +#endif + default: + return false; + } +} + +struct call_summary { + u8 num_params; + bool is_void; + bool fastcall; +}; + +/* If @call is a kfunc or helper call, fills @cs and returns true, + * otherwise returns false. + */ +static bool get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call, + struct call_summary *cs) +{ + struct bpf_kfunc_call_arg_meta meta; + const struct bpf_func_proto *fn; + int i; + + if (bpf_helper_call(call)) { + + if (get_helper_proto(env, call->imm, &fn) < 0) + /* error would be reported later */ + return false; + cs->fastcall = fn->allow_fastcall && + (verifier_inlines_helper_call(env, call->imm) || + bpf_jit_inlines_helper_call(call->imm)); + cs->is_void = fn->ret_type == RET_VOID; + cs->num_params = 0; + for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i) { + if (fn->arg_type[i] == ARG_DONTCARE) + break; + cs->num_params++; + } + return true; + } + + if (bpf_pseudo_kfunc_call(call)) { + int err; + + err = fetch_kfunc_meta(env, call, &meta, NULL); + if (err < 0) + /* error would be reported later */ + return false; + cs->num_params = btf_type_vlen(meta.func_proto); + cs->fastcall = meta.kfunc_flags & KF_FASTCALL; + cs->is_void = btf_type_is_void(btf_type_by_id(meta.btf, meta.func_proto->type)); + return true; + } + + return false; +} + +/* LLVM define a bpf_fastcall function attribute. + * This attribute means that function scratches only some of + * the caller saved registers defined by ABI. + * For BPF the set of such registers could be defined as follows: + * - R0 is scratched only if function is non-void; + * - R1-R5 are scratched only if corresponding parameter type is defined + * in the function prototype. + * + * The contract between kernel and clang allows to simultaneously use + * such functions and maintain backwards compatibility with old + * kernels that don't understand bpf_fastcall calls: + * + * - for bpf_fastcall calls clang allocates registers as-if relevant r0-r5 + * registers are not scratched by the call; + * + * - as a post-processing step, clang visits each bpf_fastcall call and adds + * spill/fill for every live r0-r5; + * + * - stack offsets used for the spill/fill are allocated as lowest + * stack offsets in whole function and are not used for any other + * purposes; + * + * - when kernel loads a program, it looks for such patterns + * (bpf_fastcall function surrounded by spills/fills) and checks if + * spill/fill stack offsets are used exclusively in fastcall patterns; + * + * - if so, and if verifier or current JIT inlines the call to the + * bpf_fastcall function (e.g. a helper call), kernel removes unnecessary + * spill/fill pairs; + * + * - when old kernel loads a program, presence of spill/fill pairs + * keeps BPF program valid, albeit slightly less efficient. + * + * For example: + * + * r1 = 1; + * r2 = 2; + * *(u64 *)(r10 - 8) = r1; r1 = 1; + * *(u64 *)(r10 - 16) = r2; r2 = 2; + * call %[to_be_inlined] --> call %[to_be_inlined] + * r2 = *(u64 *)(r10 - 16); r0 = r1; + * r1 = *(u64 *)(r10 - 8); r0 += r2; + * r0 = r1; exit; + * r0 += r2; + * exit; + * + * The purpose of mark_fastcall_pattern_for_call is to: + * - look for such patterns; + * - mark spill and fill instructions in env->insn_aux_data[*].fastcall_pattern; + * - mark set env->insn_aux_data[*].fastcall_spills_num for call instruction; + * - update env->subprog_info[*]->fastcall_stack_off to find an offset + * at which bpf_fastcall spill/fill stack slots start; + * - update env->subprog_info[*]->keep_fastcall_stack. + * + * The .fastcall_pattern and .fastcall_stack_off are used by + * check_fastcall_stack_contract() to check if every stack access to + * fastcall spill/fill stack slot originates from spill/fill + * instructions, members of fastcall patterns. + * + * If such condition holds true for a subprogram, fastcall patterns could + * be rewritten by remove_fastcall_spills_fills(). + * Otherwise bpf_fastcall patterns are not changed in the subprogram + * (code, presumably, generated by an older clang version). + * + * For example, it is *not* safe to remove spill/fill below: + * + * r1 = 1; + * *(u64 *)(r10 - 8) = r1; r1 = 1; + * call %[to_be_inlined] --> call %[to_be_inlined] + * r1 = *(u64 *)(r10 - 8); r0 = *(u64 *)(r10 - 8); <---- wrong !!! + * r0 = *(u64 *)(r10 - 8); r0 += r1; + * r0 += r1; exit; + * exit; + */ +static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, + struct bpf_subprog_info *subprog, + int insn_idx, s16 lowest_off) +{ + struct bpf_insn *insns = env->prog->insnsi, *stx, *ldx; + struct bpf_insn *call = &env->prog->insnsi[insn_idx]; + u32 clobbered_regs_mask; + struct call_summary cs; + u32 expected_regs_mask; + s16 off; + int i; + + if (!get_call_summary(env, call, &cs)) + return; + + /* A bitmask specifying which caller saved registers are clobbered + * by a call to a helper/kfunc *as if* this helper/kfunc follows + * bpf_fastcall contract: + * - includes R0 if function is non-void; + * - includes R1-R5 if corresponding parameter has is described + * in the function prototype. + */ + clobbered_regs_mask = GENMASK(cs.num_params, cs.is_void ? 1 : 0); + /* e.g. if helper call clobbers r{0,1}, expect r{2,3,4,5} in the pattern */ + expected_regs_mask = ~clobbered_regs_mask & ALL_CALLER_SAVED_REGS; + + /* match pairs of form: + * + * *(u64 *)(r10 - Y) = rX (where Y % 8 == 0) + * ... + * call %[to_be_inlined] + * ... + * rX = *(u64 *)(r10 - Y) + */ + for (i = 1, off = lowest_off; i <= ARRAY_SIZE(caller_saved); ++i, off += BPF_REG_SIZE) { + if (insn_idx - i < 0 || insn_idx + i >= env->prog->len) + break; + stx = &insns[insn_idx - i]; + ldx = &insns[insn_idx + i]; + /* must be a stack spill/fill pair */ + if (stx->code != (BPF_STX | BPF_MEM | BPF_DW) || + ldx->code != (BPF_LDX | BPF_MEM | BPF_DW) || + stx->dst_reg != BPF_REG_10 || + ldx->src_reg != BPF_REG_10) + break; + /* must be a spill/fill for the same reg */ + if (stx->src_reg != ldx->dst_reg) + break; + /* must be one of the previously unseen registers */ + if ((BIT(stx->src_reg) & expected_regs_mask) == 0) + break; + /* must be a spill/fill for the same expected offset, + * no need to check offset alignment, BPF_DW stack access + * is always 8-byte aligned. + */ + if (stx->off != off || ldx->off != off) + break; + expected_regs_mask &= ~BIT(stx->src_reg); + env->insn_aux_data[insn_idx - i].fastcall_pattern = 1; + env->insn_aux_data[insn_idx + i].fastcall_pattern = 1; + } + if (i == 1) + return; + + /* Conditionally set 'fastcall_spills_num' to allow forward + * compatibility when more helper functions are marked as + * bpf_fastcall at compile time than current kernel supports, e.g: + * + * 1: *(u64 *)(r10 - 8) = r1 + * 2: call A ;; assume A is bpf_fastcall for current kernel + * 3: r1 = *(u64 *)(r10 - 8) + * 4: *(u64 *)(r10 - 8) = r1 + * 5: call B ;; assume B is not bpf_fastcall for current kernel + * 6: r1 = *(u64 *)(r10 - 8) + * + * There is no need to block bpf_fastcall rewrite for such program. + * Set 'fastcall_pattern' for both calls to keep check_fastcall_stack_contract() happy, + * don't set 'fastcall_spills_num' for call B so that remove_fastcall_spills_fills() + * does not remove spill/fill pair {4,6}. + */ + if (cs.fastcall) + env->insn_aux_data[insn_idx].fastcall_spills_num = i - 1; + else + subprog->keep_fastcall_stack = 1; + subprog->fastcall_stack_off = min(subprog->fastcall_stack_off, off); +} + +static int mark_fastcall_patterns(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *subprog = env->subprog_info; + struct bpf_insn *insn; + s16 lowest_off; + int s, i; + + for (s = 0; s < env->subprog_cnt; ++s, ++subprog) { + /* find lowest stack spill offset used in this subprog */ + lowest_off = 0; + for (i = subprog->start; i < (subprog + 1)->start; ++i) { + insn = env->prog->insnsi + i; + if (insn->code != (BPF_STX | BPF_MEM | BPF_DW) || + insn->dst_reg != BPF_REG_10) + continue; + lowest_off = min(lowest_off, insn->off); + } + /* use this offset to find fastcall patterns */ + for (i = subprog->start; i < (subprog + 1)->start; ++i) { + insn = env->prog->insnsi + i; + if (insn->code != (BPF_JMP | BPF_CALL)) + continue; + mark_fastcall_pattern_for_call(env, subprog, i, lowest_off); + } + } + return 0; +} + +static struct bpf_iarray *iarray_realloc(struct bpf_iarray *old, size_t n_elem) +{ + size_t new_size = sizeof(struct bpf_iarray) + n_elem * sizeof(old->items[0]); + struct bpf_iarray *new; + + new = kvrealloc(old, new_size, GFP_KERNEL_ACCOUNT); + if (!new) { + /* this is what callers always want, so simplify the call site */ + kvfree(old); + return NULL; + } + + new->cnt = n_elem; + return new; +} + +static int copy_insn_array(struct bpf_map *map, u32 start, u32 end, u32 *items) +{ + struct bpf_insn_array_value *value; + u32 i; + + for (i = start; i <= end; i++) { + value = map->ops->map_lookup_elem(map, &i); + /* + * map_lookup_elem of an array map will never return an error, + * but not checking it makes some static analysers to worry + */ + if (IS_ERR(value)) + return PTR_ERR(value); + else if (!value) + return -EINVAL; + items[i - start] = value->xlated_off; + } + return 0; +} + +static int cmp_ptr_to_u32(const void *a, const void *b) +{ + return *(u32 *)a - *(u32 *)b; +} + +static int sort_insn_array_uniq(u32 *items, int cnt) +{ + int unique = 1; + int i; + + sort(items, cnt, sizeof(items[0]), cmp_ptr_to_u32, NULL); + + for (i = 1; i < cnt; i++) + if (items[i] != items[unique - 1]) + items[unique++] = items[i]; + + return unique; +} + +/* + * sort_unique({map[start], ..., map[end]}) into off + */ +static int copy_insn_array_uniq(struct bpf_map *map, u32 start, u32 end, u32 *off) +{ + u32 n = end - start + 1; + int err; + + err = copy_insn_array(map, start, end, off); + if (err) + return err; + + return sort_insn_array_uniq(off, n); +} + +/* + * Copy all unique offsets from the map + */ +static struct bpf_iarray *jt_from_map(struct bpf_map *map) +{ + struct bpf_iarray *jt; + int err; + int n; + + jt = iarray_realloc(NULL, map->max_entries); + if (!jt) + return ERR_PTR(-ENOMEM); + + n = copy_insn_array_uniq(map, 0, map->max_entries - 1, jt->items); + if (n < 0) { + err = n; + goto err_free; + } + if (n == 0) { + err = -EINVAL; + goto err_free; + } + jt->cnt = n; + return jt; + +err_free: + kvfree(jt); + return ERR_PTR(err); +} + +/* + * Find and collect all maps which fit in the subprog. Return the result as one + * combined jump table in jt->items (allocated with kvcalloc) + */ +static struct bpf_iarray *jt_from_subprog(struct bpf_verifier_env *env, + int subprog_start, int subprog_end) +{ + struct bpf_iarray *jt = NULL; + struct bpf_map *map; + struct bpf_iarray *jt_cur; + int i; + + for (i = 0; i < env->insn_array_map_cnt; i++) { + /* + * TODO (when needed): collect only jump tables, not static keys + * or maps for indirect calls + */ + map = env->insn_array_maps[i]; + + jt_cur = jt_from_map(map); + if (IS_ERR(jt_cur)) { + kvfree(jt); + return jt_cur; + } + + /* + * This is enough to check one element. The full table is + * checked to fit inside the subprog later in create_jt() + */ + if (jt_cur->items[0] >= subprog_start && jt_cur->items[0] < subprog_end) { + u32 old_cnt = jt ? jt->cnt : 0; + jt = iarray_realloc(jt, old_cnt + jt_cur->cnt); + if (!jt) { + kvfree(jt_cur); + return ERR_PTR(-ENOMEM); + } + memcpy(jt->items + old_cnt, jt_cur->items, jt_cur->cnt << 2); + } + + kvfree(jt_cur); + } + + if (!jt) { + verbose(env, "no jump tables found for subprog starting at %u\n", subprog_start); + return ERR_PTR(-EINVAL); + } + + jt->cnt = sort_insn_array_uniq(jt->items, jt->cnt); + return jt; +} + +static struct bpf_iarray * +create_jt(int t, struct bpf_verifier_env *env) +{ + static struct bpf_subprog_info *subprog; + int subprog_start, subprog_end; + struct bpf_iarray *jt; + int i; + + subprog = bpf_find_containing_subprog(env, t); + subprog_start = subprog->start; + subprog_end = (subprog + 1)->start; + jt = jt_from_subprog(env, subprog_start, subprog_end); + if (IS_ERR(jt)) + return jt; + + /* Check that the every element of the jump table fits within the given subprogram */ + for (i = 0; i < jt->cnt; i++) { + if (jt->items[i] < subprog_start || jt->items[i] >= subprog_end) { + verbose(env, "jump table for insn %d points outside of the subprog [%u,%u]\n", + t, subprog_start, subprog_end); + kvfree(jt); + return ERR_PTR(-EINVAL); + } + } + + return jt; +} + +/* "conditional jump with N edges" */ +static int visit_gotox_insn(int t, struct bpf_verifier_env *env) +{ + int *insn_stack = env->cfg.insn_stack; + int *insn_state = env->cfg.insn_state; + bool keep_exploring = false; + struct bpf_iarray *jt; + int i, w; + + jt = env->insn_aux_data[t].jt; + if (!jt) { + jt = create_jt(t, env); + if (IS_ERR(jt)) + return PTR_ERR(jt); + + env->insn_aux_data[t].jt = jt; + } + + mark_prune_point(env, t); + for (i = 0; i < jt->cnt; i++) { + w = jt->items[i]; + if (w < 0 || w >= env->prog->len) { + verbose(env, "indirect jump out of range from insn %d to %d\n", t, w); + return -EINVAL; + } + + mark_jmp_point(env, w); + + /* EXPLORED || DISCOVERED */ + if (insn_state[w]) + continue; + + if (env->cfg.cur_stack >= env->prog->len) + return -E2BIG; + + insn_stack[env->cfg.cur_stack++] = w; + insn_state[w] |= DISCOVERED; + keep_exploring = true; + } + + return keep_exploring ? KEEP_EXPLORING : DONE_EXPLORING; +} + +static int visit_tailcall_insn(struct bpf_verifier_env *env, int t) +{ + static struct bpf_subprog_info *subprog; + struct bpf_iarray *jt; + + if (env->insn_aux_data[t].jt) + return 0; + + jt = iarray_realloc(NULL, 2); + if (!jt) + return -ENOMEM; + + subprog = bpf_find_containing_subprog(env, t); + jt->items[0] = t + 1; + jt->items[1] = subprog->exit_idx; + env->insn_aux_data[t].jt = jt; + return 0; +} + /* Visits the instruction at index t and returns one of the following: * < 0 - an error occurred * DONE_EXPLORING - the instruction was fully explored @@ -12410,56 +18182,122 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, */ static int visit_insn(int t, struct bpf_verifier_env *env) { - struct bpf_insn *insns = env->prog->insnsi; - int ret; + struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; + int ret, off, insn_sz; - if (bpf_pseudo_func(insns + t)) + if (bpf_pseudo_func(insn)) return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ - if (BPF_CLASS(insns[t].code) != BPF_JMP && - BPF_CLASS(insns[t].code) != BPF_JMP32) - return push_insn(t, t + 1, FALLTHROUGH, env, false); + if (BPF_CLASS(insn->code) != BPF_JMP && + BPF_CLASS(insn->code) != BPF_JMP32) { + insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; + return push_insn(t, t + insn_sz, FALLTHROUGH, env); + } - switch (BPF_OP(insns[t].code)) { + switch (BPF_OP(insn->code)) { case BPF_EXIT: return DONE_EXPLORING; case BPF_CALL: - if (insns[t].imm == BPF_FUNC_timer_set_callback) + if (is_async_callback_calling_insn(insn)) /* Mark this call insn as a prune point to trigger * is_state_visited() check before call itself is * processed by __check_func_call(). Otherwise new * async state will be pushed for further exploration. */ mark_prune_point(env, t); - return visit_func_call_insn(t, insns, env, - insns[t].src_reg == BPF_PSEUDO_CALL); + /* For functions that invoke callbacks it is not known how many times + * callback would be called. Verifier models callback calling functions + * by repeatedly visiting callback bodies and returning to origin call + * instruction. + * In order to stop such iteration verifier needs to identify when a + * state identical some state from a previous iteration is reached. + * Check below forces creation of checkpoint before callback calling + * instruction to allow search for such identical states. + */ + if (is_sync_callback_calling_insn(insn)) { + mark_calls_callback(env, t); + mark_force_checkpoint(env, t); + mark_prune_point(env, t); + mark_jmp_point(env, t); + } + if (bpf_helper_call(insn)) { + const struct bpf_func_proto *fp; + + ret = get_helper_proto(env, insn->imm, &fp); + /* If called in a non-sleepable context program will be + * rejected anyway, so we should end up with precise + * sleepable marks on subprogs, except for dead code + * elimination. + */ + if (ret == 0 && fp->might_sleep) + mark_subprog_might_sleep(env, t); + if (bpf_helper_changes_pkt_data(insn->imm)) + mark_subprog_changes_pkt_data(env, t); + if (insn->imm == BPF_FUNC_tail_call) + visit_tailcall_insn(env, t); + } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + struct bpf_kfunc_call_arg_meta meta; + + ret = fetch_kfunc_meta(env, insn, &meta, NULL); + if (ret == 0 && is_iter_next_kfunc(&meta)) { + mark_prune_point(env, t); + /* Checking and saving state checkpoints at iter_next() call + * is crucial for fast convergence of open-coded iterator loop + * logic, so we need to force it. If we don't do that, + * is_state_visited() might skip saving a checkpoint, causing + * unnecessarily long sequence of not checkpointed + * instructions and jumps, leading to exhaustion of jump + * history buffer, and potentially other undesired outcomes. + * It is expected that with correct open-coded iterators + * convergence will happen quickly, so we don't run a risk of + * exhausting memory. + */ + mark_force_checkpoint(env, t); + } + /* Same as helpers, if called in a non-sleepable context + * program will be rejected anyway, so we should end up + * with precise sleepable marks on subprogs, except for + * dead code elimination. + */ + if (ret == 0 && is_kfunc_sleepable(&meta)) + mark_subprog_might_sleep(env, t); + if (ret == 0 && is_kfunc_pkt_changing(&meta)) + mark_subprog_changes_pkt_data(env, t); + } + return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); case BPF_JA: - if (BPF_SRC(insns[t].code) != BPF_K) - return -EINVAL; + if (BPF_SRC(insn->code) == BPF_X) + return visit_gotox_insn(t, env); + + if (BPF_CLASS(insn->code) == BPF_JMP) + off = insn->off; + else + off = insn->imm; /* unconditional jump with single edge */ - ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, - true); + ret = push_insn(t, t + off + 1, FALLTHROUGH, env); if (ret) return ret; - mark_prune_point(env, t + insns[t].off + 1); - mark_jmp_point(env, t + insns[t].off + 1); + mark_prune_point(env, t + off + 1); + mark_jmp_point(env, t + off + 1); return ret; default: /* conditional jump with two edges */ mark_prune_point(env, t); + if (is_may_goto_insn(insn)) + mark_force_checkpoint(env, t); - ret = push_insn(t, t + 1, FALLTHROUGH, env, true); + ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) return ret; - return push_insn(t, t + insns[t].off + 1, BRANCH, env, true); + return push_insn(t, t + insn->off + 1, BRANCH, env); } } @@ -12470,23 +18308,27 @@ static int check_cfg(struct bpf_verifier_env *env) { int insn_cnt = env->prog->len; int *insn_stack, *insn_state; - int ret = 0; - int i; + int ex_insn_beg, i, ret = 0; - insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); if (!insn_state) return -ENOMEM; - insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); if (!insn_stack) { kvfree(insn_state); return -ENOMEM; } + ex_insn_beg = env->exception_callback_subprog + ? env->subprog_info[env->exception_callback_subprog].start + : 0; + insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; +walk_cfg: while (env->cfg.cur_stack > 0) { int t = insn_stack[env->cfg.cur_stack - 1]; @@ -12500,7 +18342,7 @@ static int check_cfg(struct bpf_verifier_env *env) break; default: if (ret > 0) { - verbose(env, "visit_insn internal bug\n"); + verifier_bug(env, "visit_insn internal bug"); ret = -EFAULT; } goto err_free; @@ -12508,19 +18350,38 @@ static int check_cfg(struct bpf_verifier_env *env) } if (env->cfg.cur_stack < 0) { - verbose(env, "pop stack internal bug\n"); + verifier_bug(env, "pop stack internal bug"); ret = -EFAULT; goto err_free; } + if (ex_insn_beg && insn_state[ex_insn_beg] != EXPLORED) { + insn_state[ex_insn_beg] = DISCOVERED; + insn_stack[0] = ex_insn_beg; + env->cfg.cur_stack = 1; + goto walk_cfg; + } + for (i = 0; i < insn_cnt; i++) { + struct bpf_insn *insn = &env->prog->insnsi[i]; + if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } + if (bpf_is_ldimm64(insn)) { + if (insn_state[i + 1] != 0) { + verbose(env, "jump into the middle of ldimm64 insn %d\n", i); + ret = -EINVAL; + goto err_free; + } + i++; /* skip second half of ldimm64 */ + } } ret = 0; /* cfg looks good */ + env->prog->aux->changes_pkt_data = env->subprog_info[0].changes_pkt_data; + env->prog->aux->might_sleep = env->subprog_info[0].might_sleep; err_free: kvfree(insn_state); @@ -12529,6 +18390,57 @@ err_free: return ret; } +/* + * For each subprogram 'i' fill array env->cfg.insn_subprogram sub-range + * [env->subprog_info[i].postorder_start, env->subprog_info[i+1].postorder_start) + * with indices of 'i' instructions in postorder. + */ +static int compute_postorder(struct bpf_verifier_env *env) +{ + u32 cur_postorder, i, top, stack_sz, s; + int *stack = NULL, *postorder = NULL, *state = NULL; + struct bpf_iarray *succ; + + postorder = kvcalloc(env->prog->len, sizeof(int), GFP_KERNEL_ACCOUNT); + state = kvcalloc(env->prog->len, sizeof(int), GFP_KERNEL_ACCOUNT); + stack = kvcalloc(env->prog->len, sizeof(int), GFP_KERNEL_ACCOUNT); + if (!postorder || !state || !stack) { + kvfree(postorder); + kvfree(state); + kvfree(stack); + return -ENOMEM; + } + cur_postorder = 0; + for (i = 0; i < env->subprog_cnt; i++) { + env->subprog_info[i].postorder_start = cur_postorder; + stack[0] = env->subprog_info[i].start; + stack_sz = 1; + do { + top = stack[stack_sz - 1]; + state[top] |= DISCOVERED; + if (state[top] & EXPLORED) { + postorder[cur_postorder++] = top; + stack_sz--; + continue; + } + succ = bpf_insn_successors(env, top); + for (s = 0; s < succ->cnt; ++s) { + if (!state[succ->items[s]]) { + stack[stack_sz++] = succ->items[s]; + state[succ->items[s]] |= DISCOVERED; + } + } + state[top] |= EXPLORED; + } while (stack_sz); + } + env->subprog_info[i].postorder_start = cur_postorder; + env->cfg.insn_postorder = postorder; + env->cfg.cur_postorder = cur_postorder; + kvfree(stack); + kvfree(state); + return 0; +} + static int check_abnormal_return(struct bpf_verifier_env *env) { int i; @@ -12550,20 +18462,18 @@ static int check_abnormal_return(struct bpf_verifier_env *env) #define MIN_BPF_FUNCINFO_SIZE 8 #define MAX_FUNCINFO_REC_SIZE 252 -static int check_btf_func(struct bpf_verifier_env *env, - const union bpf_attr *attr, - bpfptr_t uattr) +static int check_btf_func_early(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) { - const struct btf_type *type, *func_proto, *ret_type; - u32 i, nfuncs, urec_size, min_size; u32 krec_size = sizeof(struct bpf_func_info); + const struct btf_type *type, *func_proto; + u32 i, nfuncs, urec_size, min_size; struct bpf_func_info *krecord; - struct bpf_func_info_aux *info_aux = NULL; struct bpf_prog *prog; const struct btf *btf; - bpfptr_t urecord; u32 prev_offset = 0; - bool scalar_return; + bpfptr_t urecord; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; @@ -12573,11 +18483,6 @@ static int check_btf_func(struct bpf_verifier_env *env, return 0; } - if (nfuncs != env->subprog_cnt) { - verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); - return -EINVAL; - } - urec_size = attr->func_info_rec_size; if (urec_size < MIN_BPF_FUNCINFO_SIZE || urec_size > MAX_FUNCINFO_REC_SIZE || @@ -12592,12 +18497,9 @@ static int check_btf_func(struct bpf_verifier_env *env, urecord = make_bpfptr(attr->func_info, uattr.is_kernel); min_size = min_t(u32, krec_size, urec_size); - krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); + krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!krecord) return -ENOMEM; - info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); - if (!info_aux) - goto err_free; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); @@ -12636,11 +18538,6 @@ static int check_btf_func(struct bpf_verifier_env *env, goto err_free; } - if (env->subprog_info[i].start != krecord[i].insn_off) { - verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); - goto err_free; - } - /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); if (!type || !btf_type_is_func(type)) { @@ -12648,12 +18545,77 @@ static int check_btf_func(struct bpf_verifier_env *env, krecord[i].type_id); goto err_free; } - info_aux[i].linkage = BTF_INFO_VLEN(type->info); func_proto = btf_type_by_id(btf, type->type); if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto))) /* btf_func_check() already verified it during BTF load */ goto err_free; + + prev_offset = krecord[i].insn_off; + bpfptr_add(&urecord, urec_size); + } + + prog->aux->func_info = krecord; + prog->aux->func_info_cnt = nfuncs; + return 0; + +err_free: + kvfree(krecord); + return ret; +} + +static int check_btf_func(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + const struct btf_type *type, *func_proto, *ret_type; + u32 i, nfuncs, urec_size; + struct bpf_func_info *krecord; + struct bpf_func_info_aux *info_aux = NULL; + struct bpf_prog *prog; + const struct btf *btf; + bpfptr_t urecord; + bool scalar_return; + int ret = -ENOMEM; + + nfuncs = attr->func_info_cnt; + if (!nfuncs) { + if (check_abnormal_return(env)) + return -EINVAL; + return 0; + } + if (nfuncs != env->subprog_cnt) { + verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); + return -EINVAL; + } + + urec_size = attr->func_info_rec_size; + + prog = env->prog; + btf = prog->aux->btf; + + urecord = make_bpfptr(attr->func_info, uattr.is_kernel); + + krecord = prog->aux->func_info; + info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + if (!info_aux) + return -ENOMEM; + + for (i = 0; i < nfuncs; i++) { + /* check insn_off */ + ret = -EINVAL; + + if (env->subprog_info[i].start != krecord[i].insn_off) { + verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); + goto err_free; + } + + /* Already checked type_id */ + type = btf_type_by_id(btf, krecord[i].type_id); + info_aux[i].linkage = BTF_INFO_VLEN(type->info); + /* Already checked func_proto */ + func_proto = btf_type_by_id(btf, type->type); + ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL); scalar_return = btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type); @@ -12666,17 +18628,13 @@ static int check_btf_func(struct bpf_verifier_env *env, goto err_free; } - prev_offset = krecord[i].insn_off; bpfptr_add(&urecord, urec_size); } - prog->aux->func_info = krecord; - prog->aux->func_info_cnt = nfuncs; prog->aux->func_info_aux = info_aux; return 0; err_free: - kvfree(krecord); kfree(info_aux); return ret; } @@ -12689,7 +18647,8 @@ static void adjust_btf_func(struct bpf_verifier_env *env) if (!aux->func_info) return; - for (i = 0; i < env->subprog_cnt; i++) + /* func_info is not available for hidden subprogs */ + for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++) aux->func_info[i].insn_off = env->subprog_info[i].start; } @@ -12724,7 +18683,7 @@ static int check_btf_line(struct bpf_verifier_env *env, * pass in a smaller bpf_line_info object. */ linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info), - GFP_KERNEL | __GFP_NOWARN); + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!linfo) return -ENOMEM; @@ -12893,9 +18852,9 @@ static int check_core_relo(struct bpf_verifier_env *env, return err; } -static int check_btf_info(struct bpf_verifier_env *env, - const union bpf_attr *attr, - bpfptr_t uattr) +static int check_btf_info_early(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) { struct btf *btf; int err; @@ -12915,6 +18874,24 @@ static int check_btf_info(struct bpf_verifier_env *env, } env->prog->aux->btf = btf; + err = check_btf_func_early(env, attr, uattr); + if (err) + return err; + return 0; +} + +static int check_btf_info(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + int err; + + if (!attr->func_info_cnt && !attr->line_info_cnt) { + if (check_abnormal_return(env)) + return -EINVAL; + return 0; + } + err = check_btf_func(env, attr, uattr); if (err) return err; @@ -12931,8 +18908,8 @@ static int check_btf_info(struct bpf_verifier_env *env, } /* check %cur's range satisfies %old's */ -static bool range_within(struct bpf_reg_state *old, - struct bpf_reg_state *cur) +static bool range_within(const struct bpf_reg_state *old, + const struct bpf_reg_state *cur) { return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && @@ -12954,36 +18931,57 @@ static bool range_within(struct bpf_reg_state *old, * So we look through our idmap to see if this old id has been seen before. If * so, we require the new id to match; otherwise, we add the id pair to the map. */ -static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap) +static bool check_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) { + struct bpf_id_pair *map = idmap->map; unsigned int i; + /* either both IDs should be set or both should be zero */ + if (!!old_id != !!cur_id) + return false; + + if (old_id == 0) /* cur_id == 0 as well */ + return true; + for (i = 0; i < BPF_ID_MAP_SIZE; i++) { - if (!idmap[i].old) { + if (!map[i].old) { /* Reached an empty slot; haven't seen this id before */ - idmap[i].old = old_id; - idmap[i].cur = cur_id; + map[i].old = old_id; + map[i].cur = cur_id; return true; } - if (idmap[i].old == old_id) - return idmap[i].cur == cur_id; + if (map[i].old == old_id) + return map[i].cur == cur_id; + if (map[i].cur == cur_id) + return false; } /* We ran out of idmap slots, which should be impossible */ WARN_ON_ONCE(1); return false; } +/* Similar to check_ids(), but allocate a unique temporary ID + * for 'old_id' or 'cur_id' of zero. + * This makes pairs like '0 vs unique ID', 'unique ID vs 0' valid. + */ +static bool check_scalar_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) +{ + old_id = old_id ? old_id : ++idmap->tmp_id_gen; + cur_id = cur_id ? cur_id : ++idmap->tmp_id_gen; + + return check_ids(old_id, cur_id, idmap); +} + static void clean_func_state(struct bpf_verifier_env *env, - struct bpf_func_state *st) + struct bpf_func_state *st, + u32 ip) { - enum bpf_reg_liveness live; + u16 live_regs = env->insn_aux_data[ip].live_regs_before; int i, j; for (i = 0; i < BPF_REG_FP; i++) { - live = st->regs[i].live; /* liveness must not touch this register anymore */ - st->regs[i].live |= REG_LIVE_DONE; - if (!(live & REG_LIVE_READ)) + if (!(live_regs & BIT(i))) /* since the register is unused, clear its state * to make further comparison simpler */ @@ -12991,10 +18989,7 @@ static void clean_func_state(struct bpf_verifier_env *env, } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { - live = st->stack[i].spilled_ptr.live; - /* liveness must not touch this stack slot anymore */ - st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; - if (!(live & REG_LIVE_READ)) { + if (!bpf_stack_slot_alive(env, st->frameno, i)) { __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; @@ -13005,43 +19000,41 @@ static void clean_func_state(struct bpf_verifier_env *env, static void clean_verifier_state(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { - int i; - - if (st->frame[0]->regs[0].live & REG_LIVE_DONE) - /* all regs in this state in all frames were already marked */ - return; + int i, ip; - for (i = 0; i <= st->curframe; i++) - clean_func_state(env, st->frame[i]); + bpf_live_stack_query_init(env, st); + st->cleaned = true; + for (i = 0; i <= st->curframe; i++) { + ip = frame_insn_idx(st, i); + clean_func_state(env, st->frame[i], ip); + } } /* the parentage chains form a tree. * the verifier states are added to state lists at given insn and * pushed into state stack for future exploration. - * when the verifier reaches bpf_exit insn some of the verifer states + * when the verifier reaches bpf_exit insn some of the verifier states * stored in the state lists have their final liveness state already, * but a lot of states will get revised from liveness point of view when * the verifier explores other branches. * Example: - * 1: r0 = 1 + * 1: *(u64)(r10 - 8) = 1 * 2: if r1 == 100 goto pc+1 - * 3: r0 = 2 - * 4: exit - * when the verifier reaches exit insn the register r0 in the state list of - * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch - * of insn 2 and goes exploring further. At the insn 4 it will walk the - * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ. + * 3: *(u64)(r10 - 8) = 2 + * 4: r0 = *(u64)(r10 - 8) + * 5: exit + * when the verifier reaches exit insn the stack slot -8 in the state list of + * insn 2 is not yet marked alive. Then the verifier pops the other_branch + * of insn 2 and goes exploring further. After the insn 4 read, liveness + * analysis would propagate read mark for -8 at insn 2. * * Since the verifier pushes the branch states as it sees them while exploring * the program the condition of walking the branch instruction for the second * time means that all states below this branch were already explored and * their final liveness marks are already propagated. * Hence when the verifier completes the search of state list in is_state_visited() - * we can call this clean_live_states() function to mark all liveness states - * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' - * will not be used. - * This function also clears the registers and stack for states that !READ - * to simplify state merging. + * we can call this clean_live_states() function to clear dead the registers and stack + * slots to simplify state merging. * * Important note here that walking the same branch instruction in the callee * doesn't meant that the states are DONE. The verifier has to compare @@ -13051,97 +19044,135 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state *cur) { struct bpf_verifier_state_list *sl; - int i; + struct list_head *pos, *head; - sl = *explored_state(env, insn); - while (sl) { + head = explored_state(env, insn); + list_for_each(pos, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); if (sl->state.branches) - goto next; + continue; if (sl->state.insn_idx != insn || - sl->state.curframe != cur->curframe) - goto next; - for (i = 0; i <= cur->curframe; i++) - if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) - goto next; + !same_callsites(&sl->state, cur)) + continue; + if (sl->state.cleaned) + /* all regs in this state in all frames were already marked */ + continue; + if (incomplete_read_marks(env, &sl->state)) + continue; clean_verifier_state(env, &sl->state); -next: - sl = sl->next; } } +static bool regs_exact(const struct bpf_reg_state *rold, + const struct bpf_reg_state *rcur, + struct bpf_idmap *idmap) +{ + return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && + check_ids(rold->id, rcur->id, idmap) && + check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); +} + +enum exact_level { + NOT_EXACT, + EXACT, + RANGE_WITHIN +}; + /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, - struct bpf_reg_state *rcur, struct bpf_id_pair *idmap) + struct bpf_reg_state *rcur, struct bpf_idmap *idmap, + enum exact_level exact) { - bool equal; - - if (!(rold->live & REG_LIVE_READ)) - /* explored state didn't use this */ - return true; + if (exact == EXACT) + return regs_exact(rold, rcur, idmap); - equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; + if (rold->type == NOT_INIT) { + if (exact == NOT_EXACT || rcur->type == NOT_INIT) + /* explored state can't have used this */ + return true; + } - if (rold->type == NOT_INIT) - /* explored state can't have used this */ - return true; - if (rcur->type == NOT_INIT) + /* Enforce that register types have to match exactly, including their + * modifiers (like PTR_MAYBE_NULL, MEM_RDONLY, etc), as a general + * rule. + * + * One can make a point that using a pointer register as unbounded + * SCALAR would be technically acceptable, but this could lead to + * pointer leaks because scalars are allowed to leak while pointers + * are not. We could make this safe in special cases if root is + * calling us, but it's probably not worth the hassle. + * + * Also, register types that are *not* MAYBE_NULL could technically be + * safe to use as their MAYBE_NULL variants (e.g., PTR_TO_MAP_VALUE + * is safe to be used as PTR_TO_MAP_VALUE_OR_NULL, provided both point + * to the same map). + * However, if the old MAYBE_NULL register then got NULL checked, + * doing so could have affected others with the same id, and we can't + * check for that because we lost the id when we converted to + * a non-MAYBE_NULL variant. + * So, as a general rule we don't allow mixing MAYBE_NULL and + * non-MAYBE_NULL registers as well. + */ + if (rold->type != rcur->type) return false; + switch (base_type(rold->type)) { case SCALAR_VALUE: - if (equal) + if (env->explore_alu_limits) { + /* explore_alu_limits disables tnum_in() and range_within() + * logic and requires everything to be strict + */ + return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && + check_scalar_ids(rold->id, rcur->id, idmap); + } + if (!rold->precise && exact == NOT_EXACT) return true; - if (env->explore_alu_limits) + if ((rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST)) return false; - if (rcur->type == SCALAR_VALUE) { - if (!rold->precise) - return true; - /* new val must satisfy old val knowledge */ - return range_within(rold, rcur) && - tnum_in(rold->var_off, rcur->var_off); - } else { - /* We're trying to use a pointer in place of a scalar. - * Even if the scalar was unbounded, this could lead to - * pointer leaks because scalars are allowed to leak - * while pointers are not. We could make this safe in - * special cases if root is calling us, but it's - * probably not worth the hassle. - */ + if ((rold->id & BPF_ADD_CONST) && (rold->off != rcur->off)) return false; - } + /* Why check_ids() for scalar registers? + * + * Consider the following BPF code: + * 1: r6 = ... unbound scalar, ID=a ... + * 2: r7 = ... unbound scalar, ID=b ... + * 3: if (r6 > r7) goto +1 + * 4: r6 = r7 + * 5: if (r6 > X) goto ... + * 6: ... memory operation using r7 ... + * + * First verification path is [1-6]: + * - at (4) same bpf_reg_state::id (b) would be assigned to r6 and r7; + * - at (5) r6 would be marked <= X, sync_linked_regs() would also mark + * r7 <= X, because r6 and r7 share same id. + * Next verification path is [1-4, 6]. + * + * Instruction (6) would be reached in two states: + * I. r6{.id=b}, r7{.id=b} via path 1-6; + * II. r6{.id=a}, r7{.id=b} via path 1-4, 6. + * + * Use check_ids() to distinguish these states. + * --- + * Also verify that new value satisfies old value range knowledge. + */ + return range_within(rold, rcur) && + tnum_in(rold->var_off, rcur->var_off) && + check_scalar_ids(rold->id, rcur->id, idmap); case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: - /* a PTR_TO_MAP_VALUE could be safe to use as a - * PTR_TO_MAP_VALUE_OR_NULL into the same map. - * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- - * checked, doing so could have affected others with the same - * id, and we can't check for that because we lost the id when - * we converted to a PTR_TO_MAP_VALUE. - */ - if (type_may_be_null(rold->type)) { - if (!type_may_be_null(rcur->type)) - return false; - if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) - return false; - /* Check our ids match any regs they're supposed to */ - return check_ids(rold->id, rcur->id, idmap); - } - + case PTR_TO_MEM: + case PTR_TO_BUF: + case PTR_TO_TP_BUFFER: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. - * 'id' is not compared, since it's only used for maps with - * bpf_spin_lock inside map element and in such cases if - * the rest of the prog is valid for one map element then - * it's valid for all map elements regardless of the key - * used in bpf_map_lookup() */ - return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && + return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off) && - check_ids(rold->id, rcur->id, idmap); + check_ids(rold->id, rcur->id, idmap) && + check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != rold->type) - return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are * still safe. This is true even if old range < old off, @@ -13156,7 +19187,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, if (rold->off != rcur->off) return false; /* id relations must be preserved */ - if (rold->id && !check_ids(rold->id, rcur->id, idmap)) + if (!check_ids(rold->id, rcur->id, idmap)) return false; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && @@ -13165,19 +19196,57 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, /* two stack pointers are equal only if they're pointing to * the same stack frame, since fp-8 in foo != fp-8 in bar */ - return equal && rold->frameno == rcur->frameno; + return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; + case PTR_TO_ARENA: + return true; + case PTR_TO_INSN: + return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 && + rold->off == rcur->off && range_within(rold, rcur) && + tnum_in(rold->var_off, rcur->var_off); default: - /* Only valid matches are exact, which memcmp() */ - return equal; + return regs_exact(rold, rcur, idmap); } +} - /* Shouldn't get here; if we do, say it's not safe */ - WARN_ON_ONCE(1); - return false; +static struct bpf_reg_state unbound_reg; + +static __init int unbound_reg_init(void) +{ + __mark_reg_unknown_imprecise(&unbound_reg); + return 0; +} +late_initcall(unbound_reg_init); + +static bool is_stack_all_misc(struct bpf_verifier_env *env, + struct bpf_stack_state *stack) +{ + u32 i; + + for (i = 0; i < ARRAY_SIZE(stack->slot_type); ++i) { + if ((stack->slot_type[i] == STACK_MISC) || + (stack->slot_type[i] == STACK_INVALID && env->allow_uninit_stack)) + continue; + return false; + } + + return true; +} + +static struct bpf_reg_state *scalar_reg_for_stack(struct bpf_verifier_env *env, + struct bpf_stack_state *stack) +{ + if (is_spilled_scalar_reg64(stack)) + return &stack->spilled_ptr; + + if (is_stack_all_misc(env, stack)) + return &unbound_reg; + + return NULL; } static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, - struct bpf_func_state *cur, struct bpf_id_pair *idmap) + struct bpf_func_state *cur, struct bpf_idmap *idmap, + enum exact_level exact) { int i, spi; @@ -13186,23 +19255,43 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * didn't use them */ for (i = 0; i < old->allocated_stack; i++) { + struct bpf_reg_state *old_reg, *cur_reg; + spi = i / BPF_REG_SIZE; - if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) { - i += BPF_REG_SIZE - 1; - /* explored state didn't use this */ - continue; - } + if (exact != NOT_EXACT && + (i >= cur->allocated_stack || + old->stack[spi].slot_type[i % BPF_REG_SIZE] != + cur->stack[spi].slot_type[i % BPF_REG_SIZE])) + return false; if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) continue; + if (env->allow_uninit_stack && + old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC) + continue; + /* explored stack has more populated slots than current stack * and these slots were used */ if (i >= cur->allocated_stack) return false; + /* 64-bit scalar spill vs all slots MISC and vice versa. + * Load from all slots MISC produces unbound scalar. + * Construct a fake register for such stack and call + * regsafe() to ensure scalar ids are compared. + */ + old_reg = scalar_reg_for_stack(env, &old->stack[spi]); + cur_reg = scalar_reg_for_stack(env, &cur->stack[spi]); + if (old_reg && cur_reg) { + if (!regsafe(env, old_reg, cur_reg, idmap, exact)) + return false; + i += BPF_REG_SIZE - 1; + continue; + } + /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true @@ -13220,10 +19309,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, return false; if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; - if (!is_spilled_reg(&old->stack[spi])) - continue; - if (!regsafe(env, &old->stack[spi].spilled_ptr, - &cur->stack[spi].spilled_ptr, idmap)) + /* Both old and cur are having same slot_type */ + switch (old->stack[spi].slot_type[BPF_REG_SIZE - 1]) { + case STACK_SPILL: /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. @@ -13234,17 +19322,98 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * such verifier states are not equivalent. * return false to continue verification of this path */ + if (!regsafe(env, &old->stack[spi].spilled_ptr, + &cur->stack[spi].spilled_ptr, idmap, exact)) + return false; + break; + case STACK_DYNPTR: + old_reg = &old->stack[spi].spilled_ptr; + cur_reg = &cur->stack[spi].spilled_ptr; + if (old_reg->dynptr.type != cur_reg->dynptr.type || + old_reg->dynptr.first_slot != cur_reg->dynptr.first_slot || + !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) + return false; + break; + case STACK_ITER: + old_reg = &old->stack[spi].spilled_ptr; + cur_reg = &cur->stack[spi].spilled_ptr; + /* iter.depth is not compared between states as it + * doesn't matter for correctness and would otherwise + * prevent convergence; we maintain it only to prevent + * infinite loop check triggering, see + * iter_active_depths_differ() + */ + if (old_reg->iter.btf != cur_reg->iter.btf || + old_reg->iter.btf_id != cur_reg->iter.btf_id || + old_reg->iter.state != cur_reg->iter.state || + /* ignore {old_reg,cur_reg}->iter.depth, see above */ + !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) + return false; + break; + case STACK_IRQ_FLAG: + old_reg = &old->stack[spi].spilled_ptr; + cur_reg = &cur->stack[spi].spilled_ptr; + if (!check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap) || + old_reg->irq.kfunc_class != cur_reg->irq.kfunc_class) + return false; + break; + case STACK_MISC: + case STACK_ZERO: + case STACK_INVALID: + continue; + /* Ensure that new unhandled slot types return false by default */ + default: return false; + } } return true; } -static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) +static bool refsafe(struct bpf_verifier_state *old, struct bpf_verifier_state *cur, + struct bpf_idmap *idmap) { + int i; + if (old->acquired_refs != cur->acquired_refs) return false; - return !memcmp(old->refs, cur->refs, - sizeof(*old->refs) * old->acquired_refs); + + if (old->active_locks != cur->active_locks) + return false; + + if (old->active_preempt_locks != cur->active_preempt_locks) + return false; + + if (old->active_rcu_locks != cur->active_rcu_locks) + return false; + + if (!check_ids(old->active_irq_id, cur->active_irq_id, idmap)) + return false; + + if (!check_ids(old->active_lock_id, cur->active_lock_id, idmap) || + old->active_lock_ptr != cur->active_lock_ptr) + return false; + + for (i = 0; i < old->acquired_refs; i++) { + if (!check_ids(old->refs[i].id, cur->refs[i].id, idmap) || + old->refs[i].type != cur->refs[i].type) + return false; + switch (old->refs[i].type) { + case REF_TYPE_PTR: + case REF_TYPE_IRQ: + break; + case REF_TYPE_LOCK: + case REF_TYPE_RES_LOCK: + case REF_TYPE_RES_LOCK_IRQ: + if (old->refs[i].ptr != cur->refs[i].ptr) + return false; + break; + default: + WARN_ONCE(1, "Unhandled enum type for reference state: %d\n", old->refs[i].type); + return false; + } + } + + return true; } /* compare two verifier states @@ -13274,34 +19443,44 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, - struct bpf_func_state *cur) + struct bpf_func_state *cur, u32 insn_idx, enum exact_level exact) { - int i; + u16 live_regs = env->insn_aux_data[insn_idx].live_regs_before; + u16 i; + + if (old->callback_depth > cur->callback_depth) + return false; for (i = 0; i < MAX_BPF_REG; i++) - if (!regsafe(env, &old->regs[i], &cur->regs[i], - env->idmap_scratch)) + if (((1 << i) & live_regs) && + !regsafe(env, &old->regs[i], &cur->regs[i], + &env->idmap_scratch, exact)) return false; - if (!stacksafe(env, old, cur, env->idmap_scratch)) - return false; - - if (!refsafe(old, cur)) + if (!stacksafe(env, old, cur, &env->idmap_scratch, exact)) return false; return true; } +static void reset_idmap_scratch(struct bpf_verifier_env *env) +{ + env->idmap_scratch.tmp_id_gen = env->id_gen; + memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map)); +} + static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, - struct bpf_verifier_state *cur) + struct bpf_verifier_state *cur, + enum exact_level exact) { + u32 insn_idx; int i; if (old->curframe != cur->curframe) return false; - memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); + reset_idmap_scratch(env); /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. @@ -13309,136 +19488,54 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->speculative && !cur->speculative) return false; - if (old->active_lock.ptr != cur->active_lock.ptr) - return false; - - /* Old and cur active_lock's have to be either both present - * or both absent. - */ - if (!!old->active_lock.id != !!cur->active_lock.id) - return false; - - if (old->active_lock.id && - !check_ids(old->active_lock.id, cur->active_lock.id, env->idmap_scratch)) + if (old->in_sleepable != cur->in_sleepable) return false; - if (old->active_rcu_lock != cur->active_rcu_lock) + if (!refsafe(old, cur, &env->idmap_scratch)) return false; /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ for (i = 0; i <= old->curframe; i++) { + insn_idx = frame_insn_idx(old, i); if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; - if (!func_states_equal(env, old->frame[i], cur->frame[i])) + if (!func_states_equal(env, old->frame[i], cur->frame[i], insn_idx, exact)) return false; } return true; } -/* Return 0 if no propagation happened. Return negative error code if error - * happened. Otherwise, return the propagated bit. - */ -static int propagate_liveness_reg(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, - struct bpf_reg_state *parent_reg) -{ - u8 parent_flag = parent_reg->live & REG_LIVE_READ; - u8 flag = reg->live & REG_LIVE_READ; - int err; - - /* When comes here, read flags of PARENT_REG or REG could be any of - * REG_LIVE_READ64, REG_LIVE_READ32, REG_LIVE_NONE. There is no need - * of propagation if PARENT_REG has strongest REG_LIVE_READ64. - */ - if (parent_flag == REG_LIVE_READ64 || - /* Or if there is no read flag from REG. */ - !flag || - /* Or if the read flag from REG is the same as PARENT_REG. */ - parent_flag == flag) - return 0; - - err = mark_reg_read(env, reg, parent_reg, flag); - if (err) - return err; - - return flag; -} - -/* A write screens off any subsequent reads; but write marks come from the - * straight-line code between a state and its parent. When we arrive at an - * equivalent state (jump target or such) we didn't arrive by the straight-line - * code, so read marks in the state must propagate to the parent regardless - * of the state's write marks. That's what 'parent == state->parent' comparison - * in mark_reg_read() is for. - */ -static int propagate_liveness(struct bpf_verifier_env *env, - const struct bpf_verifier_state *vstate, - struct bpf_verifier_state *vparent) -{ - struct bpf_reg_state *state_reg, *parent_reg; - struct bpf_func_state *state, *parent; - int i, frame, err = 0; - - if (vparent->curframe != vstate->curframe) { - WARN(1, "propagate_live: parent frame %d current frame %d\n", - vparent->curframe, vstate->curframe); - return -EFAULT; - } - /* Propagate read liveness of registers... */ - BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); - for (frame = 0; frame <= vstate->curframe; frame++) { - parent = vparent->frame[frame]; - state = vstate->frame[frame]; - parent_reg = parent->regs; - state_reg = state->regs; - /* We don't need to worry about FP liveness, it's read-only */ - for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { - err = propagate_liveness_reg(env, &state_reg[i], - &parent_reg[i]); - if (err < 0) - return err; - if (err == REG_LIVE_READ64) - mark_insn_zext(env, &parent_reg[i]); - } - - /* Propagate stack slots. */ - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && - i < parent->allocated_stack / BPF_REG_SIZE; i++) { - parent_reg = &parent->stack[i].spilled_ptr; - state_reg = &state->stack[i].spilled_ptr; - err = propagate_liveness_reg(env, state_reg, - parent_reg); - if (err < 0) - return err; - } - } - return 0; -} - /* find precise scalars in the previous equivalent state and * propagate them into the current state */ static int propagate_precision(struct bpf_verifier_env *env, - const struct bpf_verifier_state *old) + const struct bpf_verifier_state *old, + struct bpf_verifier_state *cur, + bool *changed) { struct bpf_reg_state *state_reg; struct bpf_func_state *state; int i, err = 0, fr; + bool first; for (fr = old->curframe; fr >= 0; fr--) { state = old->frame[fr]; state_reg = state->regs; + first = true; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || !state_reg->precise) continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "frame %d: propagating r%d\n", i, fr); - err = mark_chain_precision_frame(env, fr, i); - if (err < 0) - return err; + if (env->log.level & BPF_LOG_LEVEL2) { + if (first) + verbose(env, "frame %d: propagating r%d", fr, i); + else + verbose(env, ",r%d", i); + } + bt_set_frame_reg(&env->bt, fr, i); + first = false; } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { @@ -13448,14 +19545,61 @@ static int propagate_precision(struct bpf_verifier_env *env, if (state_reg->type != SCALAR_VALUE || !state_reg->precise) continue; + if (env->log.level & BPF_LOG_LEVEL2) { + if (first) + verbose(env, "frame %d: propagating fp%d", + fr, (-i - 1) * BPF_REG_SIZE); + else + verbose(env, ",fp%d", (-i - 1) * BPF_REG_SIZE); + } + bt_set_frame_slot(&env->bt, fr, i); + first = false; + } + if (!first && (env->log.level & BPF_LOG_LEVEL2)) + verbose(env, "\n"); + } + + err = __mark_chain_precision(env, cur, -1, changed); + if (err < 0) + return err; + + return 0; +} + +#define MAX_BACKEDGE_ITERS 64 + +/* Propagate read and precision marks from visit->backedges[*].state->equal_state + * to corresponding parent states of visit->backedges[*].state until fixed point is reached, + * then free visit->backedges. + * After execution of this function incomplete_read_marks() will return false + * for all states corresponding to @visit->callchain. + */ +static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit) +{ + struct bpf_scc_backedge *backedge; + struct bpf_verifier_state *st; + bool changed; + int i, err; + + i = 0; + do { + if (i++ > MAX_BACKEDGE_ITERS) { if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "frame %d: propagating fp%d\n", - (-i - 1) * BPF_REG_SIZE, fr); - err = mark_chain_precision_stack_frame(env, fr, i); - if (err < 0) + verbose(env, "%s: too many iterations\n", __func__); + for (backedge = visit->backedges; backedge; backedge = backedge->next) + mark_all_scalars_precise(env, &backedge->state); + break; + } + changed = false; + for (backedge = visit->backedges; backedge; backedge = backedge->next) { + st = &backedge->state; + err = propagate_precision(env, st->equal_state, st, &changed); + if (err) return err; } - } + } while (changed); + + free_backedges(visit); return 0; } @@ -13472,19 +19616,110 @@ static bool states_maybe_looping(struct bpf_verifier_state *old, fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) if (memcmp(&fold->regs[i], &fcur->regs[i], - offsetof(struct bpf_reg_state, parent))) + offsetof(struct bpf_reg_state, frameno))) return false; return true; } +static bool is_iter_next_insn(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].is_iter_next; +} + +/* is_state_visited() handles iter_next() (see process_iter_next_call() for + * terminology) calls specially: as opposed to bounded BPF loops, it *expects* + * states to match, which otherwise would look like an infinite loop. So while + * iter_next() calls are taken care of, we still need to be careful and + * prevent erroneous and too eager declaration of "infinite loop", when + * iterators are involved. + * + * Here's a situation in pseudo-BPF assembly form: + * + * 0: again: ; set up iter_next() call args + * 1: r1 = &it ; <CHECKPOINT HERE> + * 2: call bpf_iter_num_next ; this is iter_next() call + * 3: if r0 == 0 goto done + * 4: ... something useful here ... + * 5: goto again ; another iteration + * 6: done: + * 7: r1 = &it + * 8: call bpf_iter_num_destroy ; clean up iter state + * 9: exit + * + * This is a typical loop. Let's assume that we have a prune point at 1:, + * before we get to `call bpf_iter_num_next` (e.g., because of that `goto + * again`, assuming other heuristics don't get in a way). + * + * When we first time come to 1:, let's say we have some state X. We proceed + * to 2:, fork states, enqueue ACTIVE, validate NULL case successfully, exit. + * Now we come back to validate that forked ACTIVE state. We proceed through + * 3-5, come to goto, jump to 1:. Let's assume our state didn't change, so we + * are converging. But the problem is that we don't know that yet, as this + * convergence has to happen at iter_next() call site only. So if nothing is + * done, at 1: verifier will use bounded loop logic and declare infinite + * looping (and would be *technically* correct, if not for iterator's + * "eventual sticky NULL" contract, see process_iter_next_call()). But we + * don't want that. So what we do in process_iter_next_call() when we go on + * another ACTIVE iteration, we bump slot->iter.depth, to mark that it's + * a different iteration. So when we suspect an infinite loop, we additionally + * check if any of the *ACTIVE* iterator states depths differ. If yes, we + * pretend we are not looping and wait for next iter_next() call. + * + * This only applies to ACTIVE state. In DRAINED state we don't expect to + * loop, because that would actually mean infinite loop, as DRAINED state is + * "sticky", and so we'll keep returning into the same instruction with the + * same state (at least in one of possible code paths). + * + * This approach allows to keep infinite loop heuristic even in the face of + * active iterator. E.g., C snippet below is and will be detected as + * infinitely looping: + * + * struct bpf_iter_num it; + * int *p, x; + * + * bpf_iter_num_new(&it, 0, 10); + * while ((p = bpf_iter_num_next(&t))) { + * x = p; + * while (x--) {} // <<-- infinite loop here + * } + * + */ +static bool iter_active_depths_differ(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) +{ + struct bpf_reg_state *slot, *cur_slot; + struct bpf_func_state *state; + int i, fr; + + for (fr = old->curframe; fr >= 0; fr--) { + state = old->frame[fr]; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_ITER) + continue; + + slot = &state->stack[i].spilled_ptr; + if (slot->iter.state != BPF_ITER_STATE_ACTIVE) + continue; + + cur_slot = &cur->frame[fr]->stack[i].spilled_ptr; + if (cur_slot->iter.depth != slot->iter.depth) + return true; + } + } + return false; +} static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; - struct bpf_verifier_state_list *sl, **pprev; + struct bpf_verifier_state_list *sl; struct bpf_verifier_state *cur = env->cur_state, *new; - int i, j, err, states_cnt = 0; - bool add_new_state = env->test_state_freq ? true : false; + bool force_new_state, add_new_state, loop; + int n, err, states_cnt = 0; + struct list_head *pos, *tmp, *head; + + force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) || + /* Avoid accumulating infinitely long jmp history */ + cur->jmp_history_cnt > 40; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -13494,19 +19729,20 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * In tests that amounts to up to 50% reduction into total verifier * memory consumption and 20% verifier time speedup. */ + add_new_state = force_new_state; if (env->jmps_processed - env->prev_jmps_processed >= 2 && env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; - pprev = explored_state(env, insn_idx); - sl = *pprev; - clean_live_states(env, insn_idx, cur); - while (sl) { + loop = false; + head = explored_state(env, insn_idx); + list_for_each_safe(pos, tmp, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); states_cnt++; if (sl->state.insn_idx != insn_idx) - goto next; + continue; if (sl->state.branches) { struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; @@ -13524,10 +19760,92 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * Since the verifier still needs to catch infinite loops * inside async callbacks. */ - } else if (states_maybe_looping(&sl->state, cur) && - states_equal(env, &sl->state, cur)) { + goto skip_inf_loop_check; + } + /* BPF open-coded iterators loop detection is special. + * states_maybe_looping() logic is too simplistic in detecting + * states that *might* be equivalent, because it doesn't know + * about ID remapping, so don't even perform it. + * See process_iter_next_call() and iter_active_depths_differ() + * for overview of the logic. When current and one of parent + * states are detected as equivalent, it's a good thing: we prove + * convergence and can stop simulating further iterations. + * It's safe to assume that iterator loop will finish, taking into + * account iter_next() contract of eventually returning + * sticky NULL result. + * + * Note, that states have to be compared exactly in this case because + * read and precision marks might not be finalized inside the loop. + * E.g. as in the program below: + * + * 1. r7 = -16 + * 2. r6 = bpf_get_prandom_u32() + * 3. while (bpf_iter_num_next(&fp[-8])) { + * 4. if (r6 != 42) { + * 5. r7 = -32 + * 6. r6 = bpf_get_prandom_u32() + * 7. continue + * 8. } + * 9. r0 = r10 + * 10. r0 += r7 + * 11. r8 = *(u64 *)(r0 + 0) + * 12. r6 = bpf_get_prandom_u32() + * 13. } + * + * Here verifier would first visit path 1-3, create a checkpoint at 3 + * with r7=-16, continue to 4-7,3. Existing checkpoint at 3 does + * not have read or precision mark for r7 yet, thus inexact states + * comparison would discard current state with r7=-32 + * => unsafe memory access at 11 would not be caught. + */ + if (is_iter_next_insn(env, insn_idx)) { + if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) { + struct bpf_func_state *cur_frame; + struct bpf_reg_state *iter_state, *iter_reg; + int spi; + + cur_frame = cur->frame[cur->curframe]; + /* btf_check_iter_kfuncs() enforces that + * iter state pointer is always the first arg + */ + iter_reg = &cur_frame->regs[BPF_REG_1]; + /* current state is valid due to states_equal(), + * so we can assume valid iter and reg state, + * no need for extra (re-)validations + */ + spi = __get_spi(iter_reg->off + iter_reg->var_off.value); + iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr; + if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) { + loop = true; + goto hit; + } + } + goto skip_inf_loop_check; + } + if (is_may_goto_insn_at(env, insn_idx)) { + if (sl->state.may_goto_depth != cur->may_goto_depth && + states_equal(env, &sl->state, cur, RANGE_WITHIN)) { + loop = true; + goto hit; + } + } + if (bpf_calls_callback(env, insn_idx)) { + if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) + goto hit; + goto skip_inf_loop_check; + } + /* attempt to detect infinite loop to avoid unnecessary doomed work */ + if (states_maybe_looping(&sl->state, cur) && + states_equal(env, &sl->state, cur, EXACT) && + !iter_active_depths_differ(&sl->state, cur) && + sl->state.may_goto_depth == cur->may_goto_depth && + sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); + verbose(env, "cur state:"); + print_verifier_state(env, cur, cur->curframe, true); + verbose(env, "old state:"); + print_verifier_state(env, &sl->state, cur->curframe, true); return -EINVAL; } /* if the verifier is processing a loop, avoid adding new state @@ -13542,34 +19860,118 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * This threshold shouldn't be too high either, since states * at the end of the loop are likely to be useful in pruning. */ - if (env->jmps_processed - env->prev_jmps_processed < 20 && +skip_inf_loop_check: + if (!force_new_state && + env->jmps_processed - env->prev_jmps_processed < 20 && env->insn_processed - env->prev_insn_processed < 100) add_new_state = false; goto miss; } - if (states_equal(env, &sl->state, cur)) { + /* See comments for mark_all_regs_read_and_precise() */ + loop = incomplete_read_marks(env, &sl->state); + if (states_equal(env, &sl->state, cur, loop ? RANGE_WITHIN : NOT_EXACT)) { +hit: sl->hit_cnt++; - /* reached equivalent register/stack state, - * prune the search. - * Registers read by the continuation are read by us. - * If we have any write marks in env->cur_state, they - * will prevent corresponding reads in the continuation - * from reaching our parent (an explored_state). Our - * own state will get the read marks recorded, but - * they'll be immediately forgotten as we're pruning - * this state and will pop a new one. - */ - 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. */ - err = err ? : push_jmp_history(env, cur); - err = err ? : propagate_precision(env, &sl->state); + err = 0; + if (is_jmp_point(env, env->insn_idx)) + err = push_jmp_history(env, cur, 0, 0); + err = err ? : propagate_precision(env, &sl->state, cur, NULL); if (err) return err; + /* When processing iterator based loops above propagate_liveness and + * propagate_precision calls are not sufficient to transfer all relevant + * read and precision marks. E.g. consider the following case: + * + * .-> A --. Assume the states are visited in the order A, B, C. + * | | | Assume that state B reaches a state equivalent to state A. + * | v v At this point, state C is not processed yet, so state A + * '-- B C has not received any read or precision marks from C. + * Thus, marks propagated from A to B are incomplete. + * + * The verifier mitigates this by performing the following steps: + * + * - Prior to the main verification pass, strongly connected components + * (SCCs) are computed over the program's control flow graph, + * intraprocedurally. + * + * - During the main verification pass, `maybe_enter_scc()` checks + * whether the current verifier state is entering an SCC. If so, an + * instance of a `bpf_scc_visit` object is created, and the state + * entering the SCC is recorded as the entry state. + * + * - This instance is associated not with the SCC itself, but with a + * `bpf_scc_callchain`: a tuple consisting of the call sites leading to + * the SCC and the SCC id. See `compute_scc_callchain()`. + * + * - When a verification path encounters a `states_equal(..., + * RANGE_WITHIN)` condition, there exists a call chain describing the + * current state and a corresponding `bpf_scc_visit` instance. A copy + * of the current state is created and added to + * `bpf_scc_visit->backedges`. + * + * - When a verification path terminates, `maybe_exit_scc()` is called + * from `update_branch_counts()`. For states with `branches == 0`, it + * checks whether the state is the entry state of any `bpf_scc_visit` + * instance. If it is, this indicates that all paths originating from + * this SCC visit have been explored. `propagate_backedges()` is then + * called, which propagates read and precision marks through the + * backedges until a fixed point is reached. + * (In the earlier example, this would propagate marks from A to B, + * from C to A, and then again from A to B.) + * + * A note on callchains + * -------------------- + * + * Consider the following example: + * + * void foo() { loop { ... SCC#1 ... } } + * void main() { + * A: foo(); + * B: ... + * C: foo(); + * } + * + * Here, there are two distinct callchains leading to SCC#1: + * - (A, SCC#1) + * - (C, SCC#1) + * + * Each callchain identifies a separate `bpf_scc_visit` instance that + * accumulates backedge states. The `propagate_{liveness,precision}()` + * functions traverse the parent state of each backedge state, which + * means these parent states must remain valid (i.e., not freed) while + * the corresponding `bpf_scc_visit` instance exists. + * + * Associating `bpf_scc_visit` instances directly with SCCs instead of + * callchains would break this invariant: + * - States explored during `C: foo()` would contribute backedges to + * SCC#1, but SCC#1 would only be exited once the exploration of + * `A: foo()` completes. + * - By that time, the states explored between `A: foo()` and `C: foo()` + * (i.e., `B: ...`) may have already been freed, causing the parent + * links for states from `C: foo()` to become invalid. + */ + if (loop) { + struct bpf_scc_backedge *backedge; + + backedge = kzalloc(sizeof(*backedge), GFP_KERNEL_ACCOUNT); + if (!backedge) + return -ENOMEM; + err = copy_verifier_state(&backedge->state, cur); + backedge->state.equal_state = &sl->state; + backedge->state.insn_idx = insn_idx; + err = err ?: add_scc_backedge(env, &sl->state, backedge); + if (err) { + free_verifier_state(&backedge->state, false); + kfree(backedge); + return err; + } + } return 1; } miss: @@ -13585,35 +19987,22 @@ miss: * to keep checking from state equivalence point of view. * Higher numbers increase max_states_per_insn and verification time, * but do not meaningfully decrease insn_processed. + * 'n' controls how many times state could miss before eviction. + * Use bigger 'n' for checkpoints because evicting checkpoint states + * too early would hinder iterator convergence. */ - if (sl->miss_cnt > sl->hit_cnt * 3 + 3) { + n = is_force_checkpoint(env, insn_idx) && sl->state.branches > 0 ? 64 : 3; + if (sl->miss_cnt > sl->hit_cnt * n + n) { /* the state is unlikely to be useful. Remove it to * speed up verification */ - *pprev = sl->next; - if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) { - u32 br = sl->state.branches; - - WARN_ONCE(br, - "BUG live_done but branches_to_explore %d\n", - br); - free_verifier_state(&sl->state, false); - kfree(sl); - env->peak_states--; - } else { - /* cannot free this state, since parentage chain may - * walk it later. Add it for free_list instead to - * be freed at the end of verification - */ - sl->next = env->free_list; - env->free_list = sl; - } - sl = *pprev; - continue; + sl->in_free_list = true; + list_del(&sl->node); + list_add(&sl->node, &env->free_list); + env->free_list_size++; + env->explored_states_size--; + maybe_free_verifier_state(env, sl); } -next: - pprev = &sl->next; - sl = *pprev; } if (env->max_states_per_insn < states_cnt) @@ -13634,11 +20023,12 @@ next: * When looping the sl->state.branches will be > 0 and this state * will not be considered for equivalence until branches == 0. */ - new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); + new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL_ACCOUNT); if (!new_sl) return -ENOMEM; env->total_states++; - env->peak_states++; + env->explored_states_size++; + update_peak_states(env); env->prev_jmps_processed = env->jmps_processed; env->prev_insn_processed = env->insn_processed; @@ -13655,45 +20045,21 @@ next: return err; } new->insn_idx = insn_idx; - WARN_ONCE(new->branches != 1, - "BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx); + verifier_bug_if(new->branches != 1, env, + "%s:branches_to_explore=%d insn %d", + __func__, new->branches, insn_idx); + err = maybe_enter_scc(env, new); + if (err) { + free_verifier_state(new, false); + kfree(new_sl); + return err; + } cur->parent = new; cur->first_insn_idx = insn_idx; + cur->dfs_depth = new->dfs_depth + 1; clear_jmp_history(cur); - new_sl->next = *explored_state(env, insn_idx); - *explored_state(env, insn_idx) = new_sl; - /* connect new state to parentage chain. Current frame needs all - * registers connected. Only r6 - r9 of the callers are alive (pushed - * to the stack implicitly by JITs) so in callers' frames connect just - * r6 - r9 as an optimization. Callers will have r1 - r5 connected to - * the state of the call instruction (with WRITTEN set), and r0 comes - * from callee with its full parentage chain, anyway. - */ - /* clear write marks in current state: the writes we did are not writes - * our child did, so they don't screen off its reads from us. - * (There are no read marks in current state, because reads always mark - * their parent and current state never has children yet. Only - * explored_states can get read marks.) - */ - for (j = 0; j <= cur->curframe; j++) { - for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) - cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; - for (i = 0; i < BPF_REG_FP; i++) - cur->frame[j]->regs[i].live = REG_LIVE_NONE; - } - - /* all stack frames are accessible from callee, clear them all */ - for (j = 0; j <= cur->curframe; j++) { - struct bpf_func_state *frame = cur->frame[j]; - struct bpf_func_state *newframe = new->frame[j]; - - for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { - frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; - frame->stack[i].spilled_ptr.parent = - &newframe->stack[i].spilled_ptr; - } - } + list_add(&new_sl->node, head); return 0; } @@ -13707,6 +20073,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: + case PTR_TO_ARENA: return false; default: return true; @@ -13731,20 +20098,394 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) !reg_type_mismatch_ok(prev)); } +static bool is_ptr_to_mem_or_btf_id(enum bpf_reg_type type) +{ + switch (base_type(type)) { + case PTR_TO_MEM: + case PTR_TO_BTF_ID: + return true; + default: + return false; + } +} + +static bool is_ptr_to_mem(enum bpf_reg_type type) +{ + return base_type(type) == PTR_TO_MEM; +} + +static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, + bool allow_trust_mismatch) +{ + enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type; + enum bpf_reg_type merged_type; + + if (*prev_type == NOT_INIT) { + /* Saw a valid insn + * dst_reg = *(u32 *)(src_reg + off) + * save type to validate intersecting paths + */ + *prev_type = type; + } else if (reg_type_mismatch(type, *prev_type)) { + /* Abuser program is trying to use the same insn + * dst_reg = *(u32*) (src_reg + off) + * with different pointer types: + * src_reg == ctx in one branch and + * src_reg == stack|map in some other branch. + * Reject it. + */ + if (allow_trust_mismatch && + is_ptr_to_mem_or_btf_id(type) && + is_ptr_to_mem_or_btf_id(*prev_type)) { + /* + * Have to support a use case when one path through + * the program yields TRUSTED pointer while another + * is UNTRUSTED. Fallback to UNTRUSTED to generate + * BPF_PROBE_MEM/BPF_PROBE_MEMSX. + * Same behavior of MEM_RDONLY flag. + */ + if (is_ptr_to_mem(type) || is_ptr_to_mem(*prev_type)) + merged_type = PTR_TO_MEM; + else + merged_type = PTR_TO_BTF_ID; + if ((type & PTR_UNTRUSTED) || (*prev_type & PTR_UNTRUSTED)) + merged_type |= PTR_UNTRUSTED; + if ((type & MEM_RDONLY) || (*prev_type & MEM_RDONLY)) + merged_type |= MEM_RDONLY; + *prev_type = merged_type; + } else { + verbose(env, "same insn cannot be used with different pointers\n"); + return -EINVAL; + } + } + + return 0; +} + +enum { + PROCESS_BPF_EXIT = 1 +}; + +static int process_bpf_exit_full(struct bpf_verifier_env *env, + bool *do_print_state, + bool exception_exit) +{ + /* We must do check_reference_leak here before + * prepare_func_exit to handle the case when + * state->curframe > 0, it may be a callback function, + * for which reference_state must match caller reference + * state when it exits. + */ + int err = check_resource_leak(env, exception_exit, + !env->cur_state->curframe, + "BPF_EXIT instruction in main prog"); + if (err) + return err; + + /* The side effect of the prepare_func_exit which is + * being skipped is that it frees bpf_func_state. + * Typically, process_bpf_exit will only be hit with + * outermost exit. copy_verifier_state in pop_stack will + * handle freeing of any extra bpf_func_state left over + * from not processing all nested function exits. We + * also skip return code checks as they are not needed + * for exceptional exits. + */ + if (exception_exit) + return PROCESS_BPF_EXIT; + + if (env->cur_state->curframe) { + /* exit from nested function */ + err = prepare_func_exit(env, &env->insn_idx); + if (err) + return err; + *do_print_state = true; + return 0; + } + + err = check_return_code(env, BPF_REG_0, "R0"); + if (err) + return err; + return PROCESS_BPF_EXIT; +} + +static int indirect_jump_min_max_index(struct bpf_verifier_env *env, + int regno, + struct bpf_map *map, + u32 *pmin_index, u32 *pmax_index) +{ + struct bpf_reg_state *reg = reg_state(env, regno); + u64 min_index, max_index; + const u32 size = 8; + + if (check_add_overflow(reg->umin_value, reg->off, &min_index) || + (min_index > (u64) U32_MAX * size)) { + verbose(env, "the sum of R%u umin_value %llu and off %u is too big\n", + regno, reg->umin_value, reg->off); + return -ERANGE; + } + if (check_add_overflow(reg->umax_value, reg->off, &max_index) || + (max_index > (u64) U32_MAX * size)) { + verbose(env, "the sum of R%u umax_value %llu and off %u is too big\n", + regno, reg->umax_value, reg->off); + return -ERANGE; + } + + min_index /= size; + max_index /= size; + + if (max_index >= map->max_entries) { + verbose(env, "R%u points to outside of jump table: [%llu,%llu] max_entries %u\n", + regno, min_index, max_index, map->max_entries); + return -EINVAL; + } + + *pmin_index = min_index; + *pmax_index = max_index; + return 0; +} + +/* gotox *dst_reg */ +static int check_indirect_jump(struct bpf_verifier_env *env, struct bpf_insn *insn) +{ + struct bpf_verifier_state *other_branch; + struct bpf_reg_state *dst_reg; + struct bpf_map *map; + u32 min_index, max_index; + int err = 0; + int n; + int i; + + dst_reg = reg_state(env, insn->dst_reg); + if (dst_reg->type != PTR_TO_INSN) { + verbose(env, "R%d has type %s, expected PTR_TO_INSN\n", + insn->dst_reg, reg_type_str(env, dst_reg->type)); + return -EINVAL; + } + + map = dst_reg->map_ptr; + if (verifier_bug_if(!map, env, "R%d has an empty map pointer", insn->dst_reg)) + return -EFAULT; + + if (verifier_bug_if(map->map_type != BPF_MAP_TYPE_INSN_ARRAY, env, + "R%d has incorrect map type %d", insn->dst_reg, map->map_type)) + return -EFAULT; + + err = indirect_jump_min_max_index(env, insn->dst_reg, map, &min_index, &max_index); + if (err) + return err; + + /* Ensure that the buffer is large enough */ + if (!env->gotox_tmp_buf || env->gotox_tmp_buf->cnt < max_index - min_index + 1) { + env->gotox_tmp_buf = iarray_realloc(env->gotox_tmp_buf, + max_index - min_index + 1); + if (!env->gotox_tmp_buf) + return -ENOMEM; + } + + n = copy_insn_array_uniq(map, min_index, max_index, env->gotox_tmp_buf->items); + if (n < 0) + return n; + if (n == 0) { + verbose(env, "register R%d doesn't point to any offset in map id=%d\n", + insn->dst_reg, map->id); + return -EINVAL; + } + + for (i = 0; i < n - 1; i++) { + other_branch = push_stack(env, env->gotox_tmp_buf->items[i], + env->insn_idx, env->cur_state->speculative); + if (IS_ERR(other_branch)) + return PTR_ERR(other_branch); + } + env->insn_idx = env->gotox_tmp_buf->items[n-1]; + return 0; +} + +static int do_check_insn(struct bpf_verifier_env *env, bool *do_print_state) +{ + int err; + struct bpf_insn *insn = &env->prog->insnsi[env->insn_idx]; + u8 class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + err = check_alu_op(env, insn); + if (err) + return err; + + } else if (class == BPF_LDX) { + bool is_ldsx = BPF_MODE(insn->code) == BPF_MEMSX; + + /* Check for reserved fields is already done in + * resolve_pseudo_ldimm64(). + */ + err = check_load_mem(env, insn, false, is_ldsx, true, "ldx"); + if (err) + return err; + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_ATOMIC) { + err = check_atomic(env, insn); + if (err) + return err; + env->insn_idx++; + return 0; + } + + if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) { + verbose(env, "BPF_STX uses reserved fields\n"); + return -EINVAL; + } + + err = check_store_reg(env, insn, false); + if (err) + return err; + } else if (class == BPF_ST) { + enum bpf_reg_type dst_reg_type; + + if (BPF_MODE(insn->code) != BPF_MEM || + insn->src_reg != BPF_REG_0) { + verbose(env, "BPF_ST uses reserved fields\n"); + return -EINVAL; + } + /* check src operand */ + err = check_reg_arg(env, insn->dst_reg, SRC_OP); + if (err) + return err; + + dst_reg_type = cur_regs(env)[insn->dst_reg].type; + + /* check that memory (dst_reg + off) is writeable */ + err = check_mem_access(env, env->insn_idx, insn->dst_reg, + insn->off, BPF_SIZE(insn->code), + BPF_WRITE, -1, false, false); + if (err) + return err; + + err = save_aux_ptr_type(env, dst_reg_type, false); + if (err) + return err; + } else if (class == BPF_JMP || class == BPF_JMP32) { + u8 opcode = BPF_OP(insn->code); + + env->jmps_processed++; + if (opcode == BPF_CALL) { + if (BPF_SRC(insn->code) != BPF_K || + (insn->src_reg != BPF_PSEUDO_KFUNC_CALL && + insn->off != 0) || + (insn->src_reg != BPF_REG_0 && + insn->src_reg != BPF_PSEUDO_CALL && + insn->src_reg != BPF_PSEUDO_KFUNC_CALL) || + insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { + verbose(env, "BPF_CALL uses reserved fields\n"); + return -EINVAL; + } + + if (env->cur_state->active_locks) { + if ((insn->src_reg == BPF_REG_0 && + insn->imm != BPF_FUNC_spin_unlock) || + (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && + (insn->off != 0 || !kfunc_spin_allowed(insn->imm)))) { + verbose(env, + "function calls are not allowed while holding a lock\n"); + return -EINVAL; + } + } + if (insn->src_reg == BPF_PSEUDO_CALL) { + err = check_func_call(env, insn, &env->insn_idx); + } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + err = check_kfunc_call(env, insn, &env->insn_idx); + if (!err && is_bpf_throw_kfunc(insn)) + return process_bpf_exit_full(env, do_print_state, true); + } else { + err = check_helper_call(env, insn, &env->insn_idx); + } + if (err) + return err; + + mark_reg_scratched(env, BPF_REG_0); + } else if (opcode == BPF_JA) { + if (BPF_SRC(insn->code) == BPF_X) { + if (insn->src_reg != BPF_REG_0 || + insn->imm != 0 || insn->off != 0) { + verbose(env, "BPF_JA|BPF_X uses reserved fields\n"); + return -EINVAL; + } + return check_indirect_jump(env, insn); + } + + if (BPF_SRC(insn->code) != BPF_K || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0 || + (class == BPF_JMP && insn->imm != 0) || + (class == BPF_JMP32 && insn->off != 0)) { + verbose(env, "BPF_JA uses reserved fields\n"); + return -EINVAL; + } + + if (class == BPF_JMP) + env->insn_idx += insn->off + 1; + else + env->insn_idx += insn->imm + 1; + return 0; + } else if (opcode == BPF_EXIT) { + if (BPF_SRC(insn->code) != BPF_K || + insn->imm != 0 || + insn->src_reg != BPF_REG_0 || + insn->dst_reg != BPF_REG_0 || + class == BPF_JMP32) { + verbose(env, "BPF_EXIT uses reserved fields\n"); + return -EINVAL; + } + return process_bpf_exit_full(env, do_print_state, false); + } else { + err = check_cond_jmp_op(env, insn, &env->insn_idx); + if (err) + return err; + } + } else if (class == BPF_LD) { + u8 mode = BPF_MODE(insn->code); + + if (mode == BPF_ABS || mode == BPF_IND) { + err = check_ld_abs(env, insn); + if (err) + return err; + + } else if (mode == BPF_IMM) { + err = check_ld_imm(env, insn); + if (err) + return err; + + env->insn_idx++; + sanitize_mark_insn_seen(env); + } else { + verbose(env, "invalid BPF_LD mode\n"); + return -EINVAL; + } + } else { + verbose(env, "unknown insn class %d\n", class); + return -EINVAL; + } + + env->insn_idx++; + return 0; +} + static int do_check(struct bpf_verifier_env *env) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; - struct bpf_reg_state *regs; int insn_cnt = env->prog->len; bool do_print_state = false; int prev_insn_idx = -1; for (;;) { struct bpf_insn *insn; - u8 class; - int err; + struct bpf_insn_aux_data *insn_aux; + int err, marks_err; + + /* reset current history entry on each new instruction */ + env->cur_hist_ent = NULL; env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { @@ -13754,7 +20495,7 @@ static int do_check(struct bpf_verifier_env *env) } insn = &insns[env->insn_idx]; - class = BPF_CLASS(insn->code); + insn_aux = &env->insn_aux_data[env->insn_idx]; if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, @@ -13764,6 +20505,7 @@ static int do_check(struct bpf_verifier_env *env) } state->last_insn_idx = env->prev_insn_idx; + state->insn_idx = env->insn_idx; if (is_prune_point(env, env->insn_idx)) { err = is_state_visited(env, env->insn_idx); @@ -13785,7 +20527,7 @@ static int do_check(struct bpf_verifier_env *env) } if (is_jmp_point(env, env->insn_idx)) { - err = push_jmp_history(env, state); + err = push_jmp_history(env, state, 0, 0); if (err) return err; } @@ -13801,290 +20543,101 @@ static int do_check(struct bpf_verifier_env *env) env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); - print_verifier_state(env, state->frame[state->curframe], true); + print_verifier_state(env, state, state->curframe, true); do_print_state = false; } if (env->log.level & BPF_LOG_LEVEL) { - const struct bpf_insn_cbs cbs = { - .cb_call = disasm_kfunc_name, - .cb_print = verbose, - .private_data = env, - }; - if (verifier_state_scratched(env)) - print_insn_state(env, state->frame[state->curframe]); + print_insn_state(env, state, state->curframe); verbose_linfo(env, env->insn_idx, "; "); - env->prev_log_len = env->log.len_used; + env->prev_log_pos = env->log.end_pos; verbose(env, "%d: ", env->insn_idx); - print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); - env->prev_insn_print_len = env->log.len_used - env->prev_log_len; - env->prev_log_len = env->log.len_used; + verbose_insn(env, insn); + env->prev_insn_print_pos = env->log.end_pos - env->prev_log_pos; + env->prev_log_pos = env->log.end_pos; } - if (bpf_prog_is_dev_bound(env->prog->aux)) { + if (bpf_prog_is_offloaded(env->prog->aux)) { err = bpf_prog_offload_verify_insn(env, env->insn_idx, env->prev_insn_idx); if (err) return err; } - regs = cur_regs(env); sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx; - if (class == BPF_ALU || class == BPF_ALU64) { - err = check_alu_op(env, insn); - if (err) - return err; - - } else if (class == BPF_LDX) { - enum bpf_reg_type *prev_src_type, src_reg_type; - - /* check for reserved fields is already done */ - - /* check src operand */ - err = check_reg_arg(env, insn->src_reg, SRC_OP); - if (err) - return err; - - err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); - if (err) - return err; - - src_reg_type = regs[insn->src_reg].type; + /* Reduce verification complexity by stopping speculative path + * verification when a nospec is encountered. + */ + if (state->speculative && insn_aux->nospec) + goto process_bpf_exit; - /* check that memory (src_reg + off) is readable, - * the state of dst_reg will be updated by this func + err = bpf_reset_stack_write_marks(env, env->insn_idx); + if (err) + return err; + err = do_check_insn(env, &do_print_state); + if (err >= 0 || error_recoverable_with_nospec(err)) { + marks_err = bpf_commit_stack_write_marks(env); + if (marks_err) + return marks_err; + } + if (error_recoverable_with_nospec(err) && state->speculative) { + /* Prevent this speculative path from ever reaching the + * insn that would have been unsafe to execute. */ - err = check_mem_access(env, env->insn_idx, insn->src_reg, - insn->off, BPF_SIZE(insn->code), - BPF_READ, insn->dst_reg, false); - if (err) - return err; - - prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type; - - if (*prev_src_type == NOT_INIT) { - /* saw a valid insn - * dst_reg = *(u32 *)(src_reg + off) - * save type to validate intersecting paths - */ - *prev_src_type = src_reg_type; - - } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { - /* ABuser program is trying to use the same insn - * dst_reg = *(u32*) (src_reg + off) - * with different pointer types: - * src_reg == ctx in one branch and - * src_reg == stack|map in some other branch. - * Reject it. - */ - verbose(env, "same insn cannot be used with different pointers\n"); - return -EINVAL; - } - - } else if (class == BPF_STX) { - enum bpf_reg_type *prev_dst_type, dst_reg_type; - - if (BPF_MODE(insn->code) == BPF_ATOMIC) { - err = check_atomic(env, env->insn_idx, insn); - if (err) - return err; - env->insn_idx++; - continue; - } - - if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) { - verbose(env, "BPF_STX uses reserved fields\n"); - return -EINVAL; - } - - /* check src1 operand */ - err = check_reg_arg(env, insn->src_reg, SRC_OP); - if (err) - return err; - /* check src2 operand */ - err = check_reg_arg(env, insn->dst_reg, SRC_OP); - if (err) - return err; - - dst_reg_type = regs[insn->dst_reg].type; - - /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, env->insn_idx, insn->dst_reg, - insn->off, BPF_SIZE(insn->code), - BPF_WRITE, insn->src_reg, false); + insn_aux->nospec = true; + /* If it was an ADD/SUB insn, potentially remove any + * markings for alu sanitization. + */ + insn_aux->alu_state = 0; + goto process_bpf_exit; + } else if (err < 0) { + return err; + } else if (err == PROCESS_BPF_EXIT) { + goto process_bpf_exit; + } + WARN_ON_ONCE(err); + + if (state->speculative && insn_aux->nospec_result) { + /* If we are on a path that performed a jump-op, this + * may skip a nospec patched-in after the jump. This can + * currently never happen because nospec_result is only + * used for the write-ops + * `*(size*)(dst_reg+off)=src_reg|imm32` which must + * never skip the following insn. Still, add a warning + * to document this in case nospec_result is used + * elsewhere in the future. + * + * All non-branch instructions have a single + * fall-through edge. For these, nospec_result should + * already work. + */ + if (verifier_bug_if(BPF_CLASS(insn->code) == BPF_JMP || + BPF_CLASS(insn->code) == BPF_JMP32, env, + "speculation barrier after jump instruction may not have the desired effect")) + return -EFAULT; +process_bpf_exit: + mark_verifier_state_scratched(env); + err = update_branch_counts(env, env->cur_state); if (err) return err; - - prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type; - - if (*prev_dst_type == NOT_INIT) { - *prev_dst_type = dst_reg_type; - } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { - verbose(env, "same insn cannot be used with different pointers\n"); - return -EINVAL; - } - - } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM || - insn->src_reg != BPF_REG_0) { - verbose(env, "BPF_ST uses reserved fields\n"); - return -EINVAL; - } - /* check src operand */ - err = check_reg_arg(env, insn->dst_reg, SRC_OP); + err = bpf_update_live_stack(env); if (err) return err; - - if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_ST stores into R%d %s is not allowed\n", - insn->dst_reg, - reg_type_str(env, reg_state(env, insn->dst_reg)->type)); - return -EACCES; - } - - /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, env->insn_idx, insn->dst_reg, - insn->off, BPF_SIZE(insn->code), - BPF_WRITE, -1, false); - if (err) - return err; - - } else if (class == BPF_JMP || class == BPF_JMP32) { - u8 opcode = BPF_OP(insn->code); - - env->jmps_processed++; - if (opcode == BPF_CALL) { - if (BPF_SRC(insn->code) != BPF_K || - (insn->src_reg != BPF_PSEUDO_KFUNC_CALL - && insn->off != 0) || - (insn->src_reg != BPF_REG_0 && - insn->src_reg != BPF_PSEUDO_CALL && - insn->src_reg != BPF_PSEUDO_KFUNC_CALL) || - insn->dst_reg != BPF_REG_0 || - class == BPF_JMP32) { - verbose(env, "BPF_CALL uses reserved fields\n"); - return -EINVAL; - } - - if (env->cur_state->active_lock.ptr) { - if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) || - (insn->src_reg == BPF_PSEUDO_CALL) || - (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && - (insn->off != 0 || !is_bpf_list_api_kfunc(insn->imm)))) { - verbose(env, "function calls are not allowed while holding a lock\n"); - return -EINVAL; - } - } - if (insn->src_reg == BPF_PSEUDO_CALL) - err = check_func_call(env, insn, &env->insn_idx); - else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) - err = check_kfunc_call(env, insn, &env->insn_idx); - else - err = check_helper_call(env, insn, &env->insn_idx); - if (err) + err = pop_stack(env, &prev_insn_idx, &env->insn_idx, + pop_log); + if (err < 0) { + if (err != -ENOENT) return err; - } else if (opcode == BPF_JA) { - if (BPF_SRC(insn->code) != BPF_K || - insn->imm != 0 || - insn->src_reg != BPF_REG_0 || - insn->dst_reg != BPF_REG_0 || - class == BPF_JMP32) { - verbose(env, "BPF_JA uses reserved fields\n"); - return -EINVAL; - } - - env->insn_idx += insn->off + 1; - continue; - - } else if (opcode == BPF_EXIT) { - if (BPF_SRC(insn->code) != BPF_K || - insn->imm != 0 || - insn->src_reg != BPF_REG_0 || - insn->dst_reg != BPF_REG_0 || - class == BPF_JMP32) { - verbose(env, "BPF_EXIT uses reserved fields\n"); - return -EINVAL; - } - - if (env->cur_state->active_lock.ptr) { - verbose(env, "bpf_spin_unlock is missing\n"); - return -EINVAL; - } - - if (env->cur_state->active_rcu_lock) { - verbose(env, "bpf_rcu_read_unlock is missing\n"); - 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 - * function, for which reference_state must - * match caller reference state when it exits. - */ - err = check_reference_leak(env); - if (err) - return err; - - if (state->curframe) { - /* exit from nested function */ - err = prepare_func_exit(env, &env->insn_idx); - if (err) - return err; - do_print_state = true; - continue; - } - - err = check_return_code(env); - if (err) - return err; -process_bpf_exit: - mark_verifier_state_scratched(env); - update_branch_counts(env, env->cur_state); - err = pop_stack(env, &prev_insn_idx, - &env->insn_idx, pop_log); - if (err < 0) { - if (err != -ENOENT) - return err; - break; - } else { - do_print_state = true; - continue; - } - } else { - err = check_cond_jmp_op(env, insn, &env->insn_idx); - if (err) - return err; - } - } else if (class == BPF_LD) { - u8 mode = BPF_MODE(insn->code); - - if (mode == BPF_ABS || mode == BPF_IND) { - err = check_ld_abs(env, insn); - if (err) - return err; - - } else if (mode == BPF_IMM) { - err = check_ld_imm(env, insn); - if (err) - return err; - - env->insn_idx++; - sanitize_mark_insn_seen(env); + break; } else { - verbose(env, "invalid BPF_LD mode\n"); - return -EINVAL; + do_print_state = true; + continue; } - } else { - verbose(env, "unknown insn class %d\n", class); - return -EINVAL; } - - env->insn_idx++; } return 0; @@ -14120,50 +20673,71 @@ static int find_btf_percpu_datasec(struct btf *btf) return -ENOENT; } +/* + * Add btf to the used_btfs array and return the index. (If the btf was + * already added, then just return the index.) Upon successful insertion + * increase btf refcnt, and, if present, also refcount the corresponding + * kernel module. + */ +static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf) +{ + struct btf_mod_pair *btf_mod; + int i; + + /* check whether we recorded this BTF (and maybe module) already */ + for (i = 0; i < env->used_btf_cnt; i++) + if (env->used_btfs[i].btf == btf) + return i; + + if (env->used_btf_cnt >= MAX_USED_BTFS) { + verbose(env, "The total number of btfs per program has reached the limit of %u\n", + MAX_USED_BTFS); + return -E2BIG; + } + + btf_get(btf); + + btf_mod = &env->used_btfs[env->used_btf_cnt]; + btf_mod->btf = btf; + btf_mod->module = NULL; + + /* if we reference variables from kernel module, bump its refcount */ + if (btf_is_module(btf)) { + btf_mod->module = btf_try_get_module(btf); + if (!btf_mod->module) { + btf_put(btf); + return -ENXIO; + } + } + + return env->used_btf_cnt++; +} + /* replace pseudo btf_id with kernel symbol address */ -static int check_pseudo_btf_id(struct bpf_verifier_env *env, - struct bpf_insn *insn, - struct bpf_insn_aux_data *aux) +static int __check_pseudo_btf_id(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_insn_aux_data *aux, + struct btf *btf) { const struct btf_var_secinfo *vsi; const struct btf_type *datasec; - struct btf_mod_pair *btf_mod; const struct btf_type *t; const char *sym_name; bool percpu = false; u32 type, id = insn->imm; - struct btf *btf; s32 datasec_id; u64 addr; - int i, btf_fd, err; - - btf_fd = insn[1].imm; - if (btf_fd) { - btf = btf_get_by_fd(btf_fd); - if (IS_ERR(btf)) { - verbose(env, "invalid module BTF object FD specified.\n"); - return -EINVAL; - } - } else { - if (!btf_vmlinux) { - verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); - return -EINVAL; - } - btf = btf_vmlinux; - btf_get(btf); - } + int i; t = btf_type_by_id(btf, id); if (!t) { verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id); - err = -ENOENT; - goto err_put; + return -ENOENT; } - if (!btf_type_is_var(t)) { - verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n", id); - err = -EINVAL; - goto err_put; + if (!btf_type_is_var(t) && !btf_type_is_func(t)) { + verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR or KIND_FUNC\n", id); + return -EINVAL; } sym_name = btf_name_by_offset(btf, t->name_off); @@ -14171,8 +20745,15 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, if (!addr) { verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n", sym_name); - err = -ENOENT; - goto err_put; + return -ENOENT; + } + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; + + if (btf_type_is_func(t)) { + aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; + aux->btf_var.mem_size = 0; + return 0; } datasec_id = find_btf_percpu_datasec(btf); @@ -14186,9 +20767,6 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, } } - insn[0].imm = (u32)addr; - insn[1].imm = addr >> 32; - type = t->type; t = btf_type_skip_modifiers(btf, type, NULL); if (percpu) { @@ -14206,8 +20784,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, tname = btf_name_by_offset(btf, t->name_off); verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); - err = -EINVAL; - goto err_put; + return -EINVAL; } aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = tsize; @@ -14217,38 +20794,42 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, aux->btf_var.btf_id = type; } - /* check whether we recorded this BTF (and maybe module) already */ - for (i = 0; i < env->used_btf_cnt; i++) { - if (env->used_btfs[i].btf == btf) { - btf_put(btf); - return 0; - } - } + return 0; +} - if (env->used_btf_cnt >= MAX_USED_BTFS) { - err = -E2BIG; - goto err_put; - } +static int check_pseudo_btf_id(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_insn_aux_data *aux) +{ + struct btf *btf; + int btf_fd; + int err; - btf_mod = &env->used_btfs[env->used_btf_cnt]; - btf_mod->btf = btf; - btf_mod->module = NULL; + btf_fd = insn[1].imm; + if (btf_fd) { + CLASS(fd, f)(btf_fd); - /* if we reference variables from kernel module, bump its refcount */ - if (btf_is_module(btf)) { - btf_mod->module = btf_try_get_module(btf); - if (!btf_mod->module) { - err = -ENXIO; - goto err_put; + btf = __btf_get_by_fd(f); + if (IS_ERR(btf)) { + verbose(env, "invalid module BTF object FD specified.\n"); + return -EINVAL; + } + } else { + if (!btf_vmlinux) { + verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); + return -EINVAL; } + btf = btf_vmlinux; } - env->used_btf_cnt++; + err = __check_pseudo_btf_id(env, insn, aux, btf); + if (err) + return err; + err = __add_used_btf(env, btf); + if (err < 0) + return err; return 0; -err_put: - btf_put(btf); - return err; } static bool is_tracing_prog_type(enum bpf_prog_type type) @@ -14265,6 +20846,12 @@ static bool is_tracing_prog_type(enum bpf_prog_type type) } } +static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +{ + return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); +} + static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) @@ -14272,14 +20859,21 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, { enum bpf_prog_type prog_type = resolve_prog_type(prog); - if (btf_record_has_field(map->record, BPF_LIST_HEAD)) { + if (map->excl_prog_sha && + memcmp(map->excl_prog_sha, prog->digest, SHA256_DIGEST_SIZE)) { + verbose(env, "program's hash doesn't match map's excl_prog_hash\n"); + return -EACCES; + } + + if (btf_record_has_field(map->record, BPF_LIST_HEAD) || + btf_record_has_field(map->record, BPF_RB_ROOT)) { if (is_tracing_prog_type(prog_type)) { - verbose(env, "tracing progs cannot use bpf_list_head yet\n"); + verbose(env, "tracing progs cannot use bpf_{list_head,rb_root} yet\n"); return -EINVAL; } } - if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) { + if (btf_record_has_field(map->record, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); return -EINVAL; @@ -14289,21 +20883,23 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } + } - if (prog->aux->sleepable) { - verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n"); + if (btf_record_has_field(map->record, BPF_TIMER)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_timer yet\n"); return -EINVAL; } } - if (btf_record_has_field(map->record, BPF_TIMER)) { + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) { if (is_tracing_prog_type(prog_type)) { - verbose(env, "tracing progs cannot use bpf_timer yet\n"); + verbose(env, "tracing progs cannot use bpf_wq yet\n"); return -EINVAL; } } - if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && + 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"); return -EINVAL; @@ -14314,7 +20910,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } - if (prog->aux->sleepable) + if (prog->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_LRU_HASH: @@ -14330,6 +20926,10 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_ARENA: + case BPF_MAP_TYPE_INSN_ARRAY: break; default: verbose(env, @@ -14337,13 +20937,98 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } + if (bpf_map_is_cgroup_storage(map) && + bpf_cgroup_storage_assign(env->prog->aux, map)) { + verbose(env, "only one cgroup storage of each type is allowed\n"); + return -EBUSY; + } + + if (map->map_type == BPF_MAP_TYPE_ARENA) { + if (env->prog->aux->arena) { + verbose(env, "Only one arena per program\n"); + return -EBUSY; + } + if (!env->allow_ptr_leaks || !env->bpf_capable) { + verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n"); + return -EPERM; + } + if (!env->prog->jit_requested) { + verbose(env, "JIT is required to use arena\n"); + return -EOPNOTSUPP; + } + if (!bpf_jit_supports_arena()) { + verbose(env, "JIT doesn't support arena\n"); + 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"); + return -EINVAL; + } + } + return 0; } -static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +static int __add_used_map(struct bpf_verifier_env *env, struct bpf_map *map) { - return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || - map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); + int i, err; + + /* check whether we recorded this map already */ + for (i = 0; i < env->used_map_cnt; i++) + if (env->used_maps[i] == map) + return i; + + 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); + return -E2BIG; + } + + err = check_map_prog_compatibility(env, map, env->prog); + if (err) + return err; + + if (env->prog->sleepable) + atomic64_inc(&map->sleepable_refcnt); + + /* hold the map. If the program is rejected by verifier, + * the map will be released by release_maps() or it + * will be used by the valid program until it's unloaded + * and all maps are released in bpf_free_used_maps() + */ + bpf_map_inc(map); + + env->used_maps[env->used_map_cnt++] = map; + + if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) { + err = bpf_insn_array_init(map, env->prog); + if (err) { + verbose(env, "Failed to properly initialize insn array\n"); + return err; + } + env->insn_array_maps[env->insn_array_map_cnt++] = map; + } + + return env->used_map_cnt - 1; +} + +/* Add map behind fd to used maps list, if it's not already there, and return + * its index. + * Returns <0 on error, or >= 0 index, on success. + */ +static int add_used_map(struct bpf_verifier_env *env, int fd) +{ + struct bpf_map *map; + CLASS(fd, f)(fd); + + map = __bpf_map_get(f); + if (IS_ERR(map)) { + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); + return PTR_ERR(map); + } + + return __add_used_map(env, map); } /* find and rewrite pseudo imm in ld_imm64 instructions: @@ -14357,7 +21042,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; - int i, j, err; + int i, err; err = bpf_prog_calc_tag(env->prog); if (err) @@ -14365,7 +21050,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && - (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { + ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) || + insn->imm != 0)) { verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } @@ -14373,7 +21059,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { struct bpf_insn_aux_data *aux; struct bpf_map *map; - struct fd f; + int map_idx; u64 addr; u32 fd; @@ -14436,21 +21122,14 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) break; } - 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); - return PTR_ERR(map); - } - - err = check_map_prog_compatibility(env, map, env->prog); - if (err) { - fdput(f); - return err; - } + map_idx = add_used_map(env, fd); + if (map_idx < 0) + return map_idx; + map = env->used_maps[map_idx]; aux = &env->insn_aux_data[i]; + aux->map_index = map_idx; + if (insn[0].src_reg == BPF_PSEUDO_MAP_FD || insn[0].src_reg == BPF_PSEUDO_MAP_IDX) { addr = (unsigned long)map; @@ -14459,13 +21138,11 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) if (off >= BPF_MAX_VAR_OFF) { verbose(env, "direct value offset of %u is not allowed\n", off); - fdput(f); return -EINVAL; } if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); - fdput(f); return -EINVAL; } @@ -14473,7 +21150,6 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) if (err) { verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", map->value_size, off); - fdput(f); return err; } @@ -14484,38 +21160,6 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; - /* check whether we recorded this map already */ - for (j = 0; j < env->used_map_cnt; j++) { - if (env->used_maps[j] == map) { - aux->map_index = j; - fdput(f); - goto next_insn; - } - } - - if (env->used_map_cnt >= MAX_USED_MAPS) { - fdput(f); - return -E2BIG; - } - - /* hold the map. If the program is rejected by verifier, - * the map will be released by release_maps() or it - * will be used by the valid program until it's unloaded - * and all maps are released in free_used_maps() - */ - bpf_map_inc(map); - - aux->map_index = env->used_map_cnt; - env->used_maps[env->used_map_cnt++] = map; - - if (bpf_map_is_cgroup_storage(map) && - bpf_cgroup_storage_assign(env->prog->aux, map)) { - verbose(env, "only one cgroup storage of each type is allowed\n"); - fdput(f); - return -EBUSY; - } - - fdput(f); next_insn: insn++; i++; @@ -14546,8 +21190,7 @@ static void release_maps(struct bpf_verifier_env *env) /* drop refcnt of maps used by the rejected program */ static void release_btfs(struct bpf_verifier_env *env) { - __bpf_free_used_btfs(env->prog->aux, env->used_btfs, - env->used_btf_cnt); + __bpf_free_used_btfs(env->used_btfs, env->used_btf_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ @@ -14571,12 +21214,11 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) * [0, off) and [off, end) to new locations, so the patched range stays zero */ static void adjust_insn_aux_data(struct bpf_verifier_env *env, - struct bpf_insn_aux_data *new_data, struct bpf_prog *new_prog, u32 off, u32 cnt) { - struct bpf_insn_aux_data *old_data = env->insn_aux_data; + struct bpf_insn_aux_data *data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; - u32 old_seen = old_data[off].seen; + u32 old_seen = data[off].seen; u32 prog_len; int i; @@ -14584,22 +21226,20 @@ static void adjust_insn_aux_data(struct bpf_verifier_env *env, * (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the * original insn at old prog. */ - old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1); + data[off].zext_dst = insn_has_def32(insn + off + cnt - 1); if (cnt == 1) return; prog_len = new_prog->len; - memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); - memcpy(new_data + off + cnt - 1, old_data + off, - sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); + memmove(data + off + cnt - 1, data + off, + sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); + memset(data + off, 0, sizeof(struct bpf_insn_aux_data) * (cnt - 1)); for (i = off; i < off + cnt - 1; i++) { /* Expand insni[off]'s seen count to the patched range. */ - new_data[i].seen = old_seen; - new_data[i].zext_dst = insn_has_def32(env, insn + i); + data[i].seen = old_seen; + data[i].zext_dst = insn_has_def32(insn + i); } - env->insn_aux_data = new_data; - vfree(old_data); } static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) @@ -14616,6 +21256,33 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len } } +static void release_insn_arrays(struct bpf_verifier_env *env) +{ + int i; + + for (i = 0; i < env->insn_array_map_cnt; i++) + bpf_insn_array_release(env->insn_array_maps[i]); +} + +static void adjust_insn_arrays(struct bpf_verifier_env *env, u32 off, u32 len) +{ + int i; + + if (len == 1) + return; + + for (i = 0; i < env->insn_array_map_cnt; i++) + bpf_insn_array_adjust(env->insn_array_maps[i], off, len); +} + +static void adjust_insn_arrays_after_remove(struct bpf_verifier_env *env, u32 off, u32 len) +{ + int i; + + for (i = 0; i < env->insn_array_map_cnt; i++) + bpf_insn_array_adjust_after_remove(env->insn_array_maps[i], off, len); +} + static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; @@ -14637,10 +21304,14 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of struct bpf_insn_aux_data *new_data = NULL; if (len > 1) { - new_data = vzalloc(array_size(env->prog->len + len - 1, - sizeof(struct bpf_insn_aux_data))); + new_data = vrealloc(env->insn_aux_data, + array_size(env->prog->len + len - 1, + sizeof(struct bpf_insn_aux_data)), + GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!new_data) return NULL; + + env->insn_aux_data = new_data; } new_prog = bpf_patch_insn_single(env->prog, off, patch, len); @@ -14649,15 +21320,53 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of verbose(env, "insn %d cannot be patched due to 16-bit range\n", env->insn_aux_data[off].orig_idx); - vfree(new_data); return NULL; } - adjust_insn_aux_data(env, new_data, new_prog, off, len); + adjust_insn_aux_data(env, new_prog, off, len); adjust_subprog_starts(env, off, len); + adjust_insn_arrays(env, off, len); adjust_poke_descs(new_prog, off, len); return new_prog; } +/* + * For all jmp insns in a given 'prog' that point to 'tgt_idx' insn adjust the + * jump offset by 'delta'. + */ +static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta) +{ + struct bpf_insn *insn = prog->insnsi; + u32 insn_cnt = prog->len, i; + s32 imm; + s16 off; + + for (i = 0; i < insn_cnt; i++, insn++) { + u8 code = insn->code; + + if (tgt_idx <= i && i < tgt_idx + delta) + continue; + + if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || + BPF_OP(code) == BPF_CALL || BPF_OP(code) == BPF_EXIT) + continue; + + if (insn->code == (BPF_JMP32 | BPF_JA)) { + if (i + 1 + insn->imm != tgt_idx) + continue; + if (check_add_overflow(insn->imm, delta, &imm)) + return -ERANGE; + insn->imm = imm; + } else { + if (i + 1 + insn->off != tgt_idx) + continue; + if (check_add_overflow(insn->off, delta, &off)) + return -ERANGE; + insn->off = off; + } + } + return 0; +} + static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { @@ -14778,15 +21487,39 @@ static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off, return 0; } +/* + * Clean up dynamically allocated fields of aux data for instructions [start, ...] + */ +static void clear_insn_aux_data(struct bpf_verifier_env *env, int start, int len) +{ + struct bpf_insn_aux_data *aux_data = env->insn_aux_data; + struct bpf_insn *insns = env->prog->insnsi; + int end = start + len; + int i; + + for (i = start; i < end; i++) { + if (aux_data[i].jt) { + kvfree(aux_data[i].jt); + aux_data[i].jt = NULL; + } + + if (bpf_is_ldimm64(&insns[i])) + i++; + } +} + static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; unsigned int orig_prog_len = env->prog->len; int err; - if (bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); + /* Should be called before bpf_remove_insns, as it uses prog->insnsi */ + clear_insn_aux_data(env, off, cnt); + err = bpf_remove_insns(env->prog, off, cnt); if (err) return err; @@ -14799,6 +21532,8 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) if (err) return err; + adjust_insn_arrays_after_remove(env, off, cnt); + memmove(aux_data + off, aux_data + off + cnt, sizeof(*aux_data) * (orig_prog_len - off - cnt)); @@ -14836,13 +21571,13 @@ static bool insn_is_cond_jump(u8 code) { u8 op; + op = BPF_OP(code); if (BPF_CLASS(code) == BPF_JMP32) - return true; + return op != BPF_JA; if (BPF_CLASS(code) != BPF_JMP) return false; - op = BPF_OP(code); return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; } @@ -14865,7 +21600,7 @@ static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) else continue; - if (bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_replace_insn(env, i, &ja); memcpy(insn, &ja, sizeof(ja)); @@ -14896,22 +21631,29 @@ static int opt_remove_dead_code(struct bpf_verifier_env *env) return 0; } +static const struct bpf_insn NOP = BPF_JMP_IMM(BPF_JA, 0, 0, 0); +static const struct bpf_insn MAY_GOTO_0 = BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0, 0); + static int opt_remove_nops(struct bpf_verifier_env *env) { - const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; + bool is_may_goto_0, is_ja; int i, err; for (i = 0; i < insn_cnt; i++) { - if (memcmp(&insn[i], &ja, sizeof(ja))) + is_may_goto_0 = !memcmp(&insn[i], &MAY_GOTO_0, sizeof(MAY_GOTO_0)); + is_ja = !memcmp(&insn[i], &NOP, sizeof(NOP)); + + if (!is_may_goto_0 && !is_ja) continue; err = verifier_remove_insns(env, i, 1); if (err) return err; insn_cnt--; - i--; + /* Go back one insn to catch may_goto +1; may_goto +0 sequence */ + i -= (is_may_goto_0 && i > 0) ? 2 : 1; } return 0; @@ -14920,7 +21662,10 @@ static int opt_remove_nops(struct bpf_verifier_env *env) static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, const union bpf_attr *attr) { - struct bpf_insn *patch, zext_patch[2], rnd_hi32_patch[4]; + struct bpf_insn *patch; + /* use env->insn_buf as two independent buffers */ + struct bpf_insn *zext_patch = env->insn_buf; + struct bpf_insn *rnd_hi32_patch = &env->insn_buf[2]; struct bpf_insn_aux_data *aux = env->insn_aux_data; int i, patch_len, delta = 0, len = env->prog->len; struct bpf_insn *insns = env->prog->insnsi; @@ -14955,7 +21700,7 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, * BPF_STX + SRC_OP, so it is safe to pass NULL * here. */ - if (is_reg64(env, &insn, load_reg, NULL, DST_OP)) { + if (is_reg64(&insn, load_reg, NULL, DST_OP)) { if (class == BPF_LD && BPF_MODE(code) == BPF_IMM) i++; @@ -14993,10 +21738,9 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, if (bpf_pseudo_kfunc_call(&insn)) continue; - if (WARN_ON(load_reg == -1)) { - verbose(env, "verifier bug. zext_dst is set, but no reg is defined\n"); + if (verifier_bug_if(load_reg == -1, env, + "zext_dst is set, but no reg is defined")) return -EFAULT; - } zext_patch[0] = insn; zext_patch[1].dst_reg = load_reg; @@ -15023,25 +21767,54 @@ apply_patch_buffer: */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { + struct bpf_subprog_info *subprogs = env->subprog_info; const struct bpf_verifier_ops *ops = env->ops; - int i, cnt, size, ctx_field_size, delta = 0; + int i, cnt, size, ctx_field_size, ret, delta = 0, epilogue_cnt = 0; const int insn_cnt = env->prog->len; - struct bpf_insn insn_buf[16], *insn; + struct bpf_insn *epilogue_buf = env->epilogue_buf; + struct bpf_insn *insn_buf = env->insn_buf; + struct bpf_insn *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; + int epilogue_idx = 0; + + if (ops->gen_epilogue) { + epilogue_cnt = ops->gen_epilogue(epilogue_buf, env->prog, + -(subprogs[0].stack_depth + 8)); + if (epilogue_cnt >= INSN_BUF_SIZE) { + verifier_bug(env, "epilogue is too long"); + return -EFAULT; + } else if (epilogue_cnt) { + /* Save the ARG_PTR_TO_CTX for the epilogue to use */ + cnt = 0; + subprogs[0].stack_depth += 8; + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_1, + -subprogs[0].stack_depth); + insn_buf[cnt++] = env->prog->insnsi[0]; + new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + env->prog = new_prog; + delta += cnt - 1; + + ret = add_kfunc_in_insns(env, epilogue_buf, epilogue_cnt - 1); + if (ret < 0) + return ret; + } + } if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + verifier_bug(env, "gen_prologue is null"); + return -EFAULT; } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); - if (cnt >= ARRAY_SIZE(insn_buf)) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + if (cnt >= INSN_BUF_SIZE) { + verifier_bug(env, "prologue is too long"); + return -EFAULT; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) @@ -15049,24 +21822,55 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) env->prog = new_prog; delta += cnt - 1; + + ret = add_kfunc_in_insns(env, insn_buf, cnt - 1); + if (ret < 0) + return ret; } } - if (bpf_prog_is_dev_bound(env->prog->aux)) + if (delta) + WARN_ON(adjust_jmp_off(env->prog, 0, delta)); + + if (bpf_prog_is_offloaded(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; - bool ctx_access; + u8 mode; + + if (env->insn_aux_data[i + delta].nospec) { + WARN_ON_ONCE(env->insn_aux_data[i + delta].alu_state); + struct bpf_insn *patch = insn_buf; + + *patch++ = BPF_ST_NOSPEC(); + *patch++ = *insn; + 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 = new_prog; + insn = new_prog->insnsi + i + delta; + /* This can not be easily merged with the + * nospec_result-case, because an insn may require a + * nospec before and after itself. Therefore also do not + * 'continue' here but potentially apply further + * patching to insn. *insn should equal patch[1] now. + */ + } if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || - insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) { + insn->code == (BPF_LDX | BPF_MEM | BPF_DW) || + insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) || + insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) || + insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) { type = BPF_READ; - ctx_access = true; } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || insn->code == (BPF_STX | BPF_MEM | BPF_H) || insn->code == (BPF_STX | BPF_MEM | BPF_W) || @@ -15076,20 +21880,48 @@ 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; - ctx_access = BPF_CLASS(insn->code) == BPF_STX; + } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_B) || + insn->code == (BPF_STX | BPF_ATOMIC | BPF_H) || + 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 if (insn->code == (BPF_JMP | BPF_EXIT) && + epilogue_cnt && + i + delta < subprogs[1].start) { + /* Generate epilogue for the main prog */ + if (epilogue_idx) { + /* jump back to the earlier generated epilogue */ + insn_buf[0] = BPF_JMP32_A(epilogue_idx - i - delta - 1); + cnt = 1; + } else { + memcpy(insn_buf, epilogue_buf, + epilogue_cnt * sizeof(*epilogue_buf)); + cnt = epilogue_cnt; + /* epilogue_idx cannot be 0. It must have at + * least one ctx ptr saving insn before the + * epilogue. + */ + epilogue_idx = i + delta; + } + goto patch_insn_buf; } else { continue; } if (type == BPF_WRITE && - env->insn_aux_data[i + delta].sanitize_stack_spill) { - struct bpf_insn patch[] = { - *insn, - BPF_ST_NOSPEC(), - }; + env->insn_aux_data[i + delta].nospec_result) { + /* nospec_result is only used to mitigate Spectre v4 and + * to limit verification-time for Spectre v1. + */ + struct bpf_insn *patch = insn_buf; - cnt = ARRAY_SIZE(patch); - new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt); + *patch++ = *insn; + *patch++ = BPF_ST_NOSPEC(); + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; @@ -15099,9 +21931,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } - if (!ctx_access) - continue; - switch ((int)env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) @@ -15127,18 +21956,36 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: + case PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED: if (type == BPF_READ) { - insn->code = BPF_LDX | BPF_PROBE_MEM | - BPF_SIZE((insn)->code); + if (BPF_MODE(insn->code) == BPF_MEM) + insn->code = BPF_LDX | BPF_PROBE_MEM | + BPF_SIZE((insn)->code); + else + insn->code = BPF_LDX | BPF_PROBE_MEMSX | + BPF_SIZE((insn)->code); env->prog->aux->num_exentries++; } continue; + case PTR_TO_ARENA: + if (BPF_MODE(insn->code) == BPF_MEMSX) { + if (!bpf_jit_supports_insn(insn, true)) { + verbose(env, "sign extending loads from arena are not supported yet\n"); + return -EOPNOTSUPP; + } + insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32SX | BPF_SIZE(insn->code); + } else { + insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32 | BPF_SIZE(insn->code); + } + env->prog->aux->num_exentries++; + continue; default: continue; } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); + mode = BPF_MODE(insn->code); /* If the read access is a narrower load of the field, * convert to a 4/8-byte load, to minimum program type specific @@ -15152,8 +21999,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) u8 size_code; if (type == BPF_WRITE) { - verbose(env, "bpf verifier narrow ctx access misconfigured\n"); - return -EINVAL; + verifier_bug(env, "narrow ctx access misconfigured"); + return -EFAULT; } size_code = BPF_H; @@ -15169,18 +22016,18 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) target_size = 0; cnt = convert_ctx_access(type, insn, insn_buf, env->prog, &target_size); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || + if (cnt == 0 || cnt >= INSN_BUF_SIZE || (ctx_field_size && !target_size)) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + verifier_bug(env, "error during ctx access conversion (%d)", cnt); + return -EFAULT; } if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; - if (shift && cnt + 1 >= ARRAY_SIZE(insn_buf)) { - verbose(env, "bpf verifier narrow ctx load misconfigured\n"); - return -EINVAL; + if (shift && cnt + 1 >= INSN_BUF_SIZE) { + verifier_bug(env, "narrow ctx load misconfigured"); + return -EFAULT; } if (ctx_field_size <= 4) { if (shift) @@ -15194,11 +22041,16 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); - insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } + if (mode == BPF_MEMSX) + insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X, + insn->dst_reg, insn->dst_reg, + size * 8, 0); +patch_insn_buf: new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; @@ -15221,6 +22073,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) struct bpf_insn *insn; void *old_bpf_func; int err, num_exentries; + int old_len, subprog_start_adjustment = 0; if (env->subprog_cnt <= 1) return 0; @@ -15234,11 +22087,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) * propagated in any case. */ subprog = find_subprog(env, i + insn->imm + 1); - if (subprog < 0) { - WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", - i + insn->imm + 1); + if (verifier_bug_if(subprog < 0, env, "No program to jit at insn %d", + i + insn->imm + 1)) return -EFAULT; - } /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ @@ -15249,12 +22100,19 @@ 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); @@ -15286,13 +22144,16 @@ 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; + func[i]->aux->subprog_start = subprog_start + subprog_start_adjustment; func[i]->aux->func_info = prog->aux->func_info; func[i]->aux->func_info_cnt = prog->aux->func_info_cnt; func[i]->aux->poke_tab = prog->aux->poke_tab; func[i]->aux->size_poke_tab = prog->aux->size_poke_tab; + func[i]->aux->main_prog_aux = prog->aux; for (j = 0; j < prog->aux->size_poke_tab; j++) { struct bpf_jit_poke_descriptor *poke; @@ -15305,6 +22166,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; + if (env->subprog_info[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) + func[i]->aux->jits_use_priv_stack = true; + func[i]->jit_requested = 1; func[i]->blinding_requested = prog->blinding_requested; func[i]->aux->kfunc_tab = prog->aux->kfunc_tab; @@ -15313,16 +22177,42 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; + func[i]->aux->arena = prog->aux->arena; + func[i]->aux->used_maps = env->used_maps; + func[i]->aux->used_map_cnt = env->used_map_cnt; num_exentries = 0; insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && - BPF_MODE(insn->code) == BPF_PROBE_MEM) + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEM32 || + BPF_MODE(insn->code) == BPF_PROBE_MEM32SX || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) + num_exentries++; + if ((BPF_CLASS(insn->code) == BPF_STX || + 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; + func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb; + func[i]->aux->changes_pkt_data = env->subprog_info[i].changes_pkt_data; + func[i]->aux->might_sleep = env->subprog_info[i].might_sleep; + if (!i) + func[i]->aux->exception_boundary = env->seen_exception; + + /* + * To properly pass the absolute subprog start to jit + * all instruction adjustments should be accumulated + */ + old_len = func[i]->len; func[i] = bpf_int_jit_compile(func[i]); + subprog_start_adjustment += func[i]->len - old_len; + if (!func[i]->jited) { err = -ENOTSUPP; goto out_free; @@ -15361,7 +22251,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) * the call instruction, as an index for this list */ func[i]->aux->func = func; - func[i]->aux->func_cnt = env->subprog_cnt; + func[i]->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; + func[i]->aux->real_func_cnt = env->subprog_cnt; } for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; @@ -15374,14 +22265,28 @@ static int jit_subprogs(struct bpf_verifier_env *env) cond_resched(); } - /* finally lock prog and jit images for all functions and - * populate kallsysm + /* + * Cleanup func[i]->aux fields which aren't required + * or can become invalid in future */ for (i = 0; i < env->subprog_cnt; i++) { - bpf_prog_lock_ro(func[i]); - bpf_prog_kallsyms_add(func[i]); + func[i]->aux->used_maps = NULL; + func[i]->aux->used_map_cnt = 0; } + /* finally lock prog and jit images for all functions and + * populate kallsysm. Begin at the first subprogram, since + * bpf_prog_load will add the kallsyms for the main program. + */ + for (i = 1; i < env->subprog_cnt; 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. @@ -15403,8 +22308,13 @@ static int jit_subprogs(struct bpf_verifier_env *env) prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->jited_len = func[0]->jited_len; + prog->aux->extable = func[0]->aux->extable; + prog->aux->num_exentries = func[0]->aux->num_exentries; prog->aux->func = func; - prog->aux->func_cnt = env->subprog_cnt; + prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; + prog->aux->real_func_cnt = env->subprog_cnt; + prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func; + prog->aux->exception_boundary = func[0]->aux->exception_boundary; bpf_prog_jit_attempt_done(prog); return 0; out_free: @@ -15452,7 +22362,7 @@ static int fixup_call_args(struct bpf_verifier_env *env) int err = 0; if (env->prog->jit_requested && - !bpf_prog_is_dev_bound(env->prog->aux)) { + !bpf_prog_is_offloaded(env->prog->aux)) { err = jit_subprogs(env); if (err == 0) return 0; @@ -15492,53 +22402,203 @@ static int fixup_call_args(struct bpf_verifier_env *env) return err; } +/* replace a generic kfunc with a specialized version if necessary */ +static int specialize_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_desc *desc, int insn_idx) +{ + struct bpf_prog *prog = env->prog; + bool seen_direct_write; + void *xdp_kfunc; + bool is_rdonly; + u32 func_id = desc->func_id; + u16 offset = desc->offset; + unsigned long addr = desc->addr; + + if (offset) /* return if module BTF is used */ + return 0; + + if (bpf_dev_bound_kfunc_id(func_id)) { + xdp_kfunc = bpf_dev_bound_resolve_kfunc(prog, func_id); + if (xdp_kfunc) + addr = (unsigned long)xdp_kfunc; + /* fallback to default kfunc when not supported by netdev */ + } else if (func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { + seen_direct_write = env->seen_direct_write; + is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE); + + if (is_rdonly) + addr = (unsigned long)bpf_dynptr_from_skb_rdonly; + + /* restore env->seen_direct_write to its original value, since + * may_access_direct_pkt_data mutates it + */ + env->seen_direct_write = seen_direct_write; + } else if (func_id == special_kfunc_list[KF_bpf_set_dentry_xattr]) { + if (bpf_lsm_has_d_inode_locked(prog)) + addr = (unsigned long)bpf_set_dentry_xattr_locked; + } else if (func_id == special_kfunc_list[KF_bpf_remove_dentry_xattr]) { + if (bpf_lsm_has_d_inode_locked(prog)) + addr = (unsigned long)bpf_remove_dentry_xattr_locked; + } else if (func_id == special_kfunc_list[KF_bpf_dynptr_from_file]) { + if (!env->insn_aux_data[insn_idx].non_sleepable) + addr = (unsigned long)bpf_dynptr_from_file_sleepable; + } + desc->addr = addr; + return 0; +} + +static void __fixup_collection_insert_kfunc(struct bpf_insn_aux_data *insn_aux, + u16 struct_meta_reg, + u16 node_offset_reg, + struct bpf_insn *insn, + struct bpf_insn *insn_buf, + int *cnt) +{ + struct btf_struct_meta *kptr_struct_meta = insn_aux->kptr_struct_meta; + struct bpf_insn addr[2] = { BPF_LD_IMM64(struct_meta_reg, (long)kptr_struct_meta) }; + + insn_buf[0] = addr[0]; + insn_buf[1] = addr[1]; + insn_buf[2] = BPF_MOV64_IMM(node_offset_reg, insn_aux->insert_off); + insn_buf[3] = *insn; + *cnt = 4; +} + static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn *insn_buf, int insn_idx, int *cnt) { - const struct bpf_kfunc_desc *desc; + struct bpf_kfunc_desc *desc; + int err; if (!insn->imm) { verbose(env, "invalid kernel function call not eliminated in verifier pass\n"); return -EINVAL; } - /* insn->imm has the btf func_id. Replace it with - * an address (relative to __bpf_call_base). + *cnt = 0; + + /* insn->imm has the btf func_id. Replace it with an offset relative to + * __bpf_call_base, unless the JIT needs to call functions that are + * further than 32 bits away (bpf_jit_supports_far_kfunc_call()). */ desc = find_kfunc_desc(env->prog, insn->imm, insn->off); if (!desc) { - verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n", - insn->imm); + verifier_bug(env, "kernel function descriptor not found for func_id %u", + insn->imm); return -EFAULT; } - *cnt = 0; - insn->imm = desc->imm; + err = specialize_kfunc(env, desc, insn_idx); + if (err) + return err; + + if (!bpf_jit_supports_far_kfunc_call()) + insn->imm = BPF_CALL_IMM(desc->addr); if (insn->off) return 0; - if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { + if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl] || + desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size; + if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && kptr_struct_meta) { + verifier_bug(env, "NULL kptr_struct_meta expected at insn_idx %d", + insn_idx); + return -EFAULT; + } + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size); insn_buf[1] = addr[0]; insn_buf[2] = addr[1]; insn_buf[3] = *insn; *cnt = 4; - } else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { + } else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl] || + desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] || + desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; + if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] && kptr_struct_meta) { + verifier_bug(env, "NULL kptr_struct_meta expected at insn_idx %d", + insn_idx); + return -EFAULT; + } + + if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] && + !kptr_struct_meta) { + verifier_bug(env, "kptr_struct_meta expected at insn_idx %d", + insn_idx); + return -EFAULT; + } + insn_buf[0] = addr[0]; insn_buf[1] = addr[1]; insn_buf[2] = *insn; *cnt = 3; + } else if (desc->func_id == special_kfunc_list[KF_bpf_list_push_back_impl] || + desc->func_id == special_kfunc_list[KF_bpf_list_push_front_impl] || + desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { + struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; + int struct_meta_reg = BPF_REG_3; + int node_offset_reg = BPF_REG_4; + + /* rbtree_add has extra 'less' arg, so args-to-fixup are in diff regs */ + if (desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { + struct_meta_reg = BPF_REG_4; + node_offset_reg = BPF_REG_5; + } + + if (!kptr_struct_meta) { + verifier_bug(env, "kptr_struct_meta expected at insn_idx %d", + insn_idx); + return -EFAULT; + } + + __fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg, + node_offset_reg, insn, insn_buf, cnt); } else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] || desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *cnt = 1; } + + if (env->insn_aux_data[insn_idx].arg_prog) { + u32 regno = env->insn_aux_data[insn_idx].arg_prog; + struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(regno, (long)env->prog->aux) }; + int idx = *cnt; + + insn_buf[idx++] = ld_addrs[0]; + insn_buf[idx++] = ld_addrs[1]; + insn_buf[idx++] = *insn; + *cnt = idx; + } + return 0; +} + +/* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */ +static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len) +{ + struct bpf_subprog_info *info = env->subprog_info; + int cnt = env->subprog_cnt; + struct bpf_prog *prog; + + /* We only reserve one slot for hidden subprogs in subprog_info. */ + if (env->hidden_subprog_cnt) { + verifier_bug(env, "only one hidden subprog supported"); + return -EFAULT; + } + /* We're not patching any existing instruction, just appending the new + * ones for the hidden subprog. Hence all of the adjustment operations + * in bpf_patch_insn_data are no-ops. + */ + prog = bpf_patch_insn_data(env, env->prog->len - 1, patch, len); + if (!prog) + return -ENOMEM; + env->prog = prog; + info[cnt + 1].start = info[cnt].start; + info[cnt].start = prog->len - len + 1; + env->subprog_cnt++; + env->hidden_subprog_cnt++; return 0; } @@ -15555,51 +22615,196 @@ static int do_misc_fixups(struct bpf_verifier_env *env) const int insn_cnt = prog->len; const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; - struct bpf_insn insn_buf[16]; + struct bpf_insn *insn_buf = env->insn_buf; struct bpf_prog *new_prog; struct bpf_map *map_ptr; - int i, ret, cnt, delta = 0; + int i, ret, cnt, delta = 0, cur_subprog = 0; + struct bpf_subprog_info *subprogs = env->subprog_info; + u16 stack_depth = subprogs[cur_subprog].stack_depth; + u16 stack_depth_extra = 0; - for (i = 0; i < insn_cnt; i++, insn++) { - /* Make divide-by-zero exceptions impossible. */ + if (env->seen_exception && !env->exception_callback_subprog) { + struct bpf_insn *patch = insn_buf; + + *patch++ = env->prog->insnsi[insn_cnt - 1]; + *patch++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); + *patch++ = BPF_EXIT_INSN(); + ret = add_hidden_subprog(env, insn_buf, patch - insn_buf); + if (ret < 0) + return ret; + prog = env->prog; + insn = prog->insnsi; + + env->exception_callback_subprog = env->subprog_cnt - 1; + /* Don't update insn_cnt, as add_hidden_subprog always appends insns */ + mark_subprog_exc_cb(env, env->exception_callback_subprog); + } + + for (i = 0; i < insn_cnt;) { + if (insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->imm) { + if ((insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1) || + (((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 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; + } + + if (env->insn_aux_data[i + delta].needs_zext) + /* Convert BPF_CLASS(insn->code) == BPF_ALU64 to 32-bit ALU */ + insn->code = BPF_ALU | BPF_OP(insn->code) | BPF_SRC(insn->code); + + /* Make sdiv/smod divide-by-minus-one exceptions impossible. */ + if ((insn->code == (BPF_ALU64 | BPF_MOD | BPF_K) || + insn->code == (BPF_ALU64 | BPF_DIV | BPF_K) || + insn->code == (BPF_ALU | BPF_MOD | BPF_K) || + insn->code == (BPF_ALU | BPF_DIV | BPF_K)) && + insn->off == 1 && insn->imm == -1) { + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; + bool isdiv = BPF_OP(insn->code) == BPF_DIV; + struct bpf_insn *patch = insn_buf; + + if (isdiv) + *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_NEG | BPF_K, insn->dst_reg, + 0, 0, 0); + else + *patch++ = BPF_MOV32_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; + } + + /* Make divide-by-zero and divide-by-minus-one exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || insn->code == (BPF_ALU | BPF_MOD | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; bool isdiv = BPF_OP(insn->code) == BPF_DIV; - struct bpf_insn *patchlet; - struct bpf_insn chk_and_div[] = { + bool is_sdiv = isdiv && insn->off == 1; + bool is_smod = !isdiv && insn->off == 1; + struct bpf_insn *patch = insn_buf; + + if (is_sdiv) { + /* [R,W]x sdiv 0 -> 0 + * LLONG_MIN sdiv -1 -> LLONG_MIN + * INT_MIN sdiv -1 -> INT_MIN + */ + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_ADD | BPF_K, BPF_REG_AX, + 0, 0, 1); + *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JGT | BPF_K, BPF_REG_AX, + 0, 4, 1); + *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JEQ | BPF_K, BPF_REG_AX, + 0, 1, 0); + *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_MOV | BPF_K, insn->dst_reg, + 0, 0, 0); + /* BPF_NEG(LLONG_MIN) == -LLONG_MIN == LLONG_MIN */ + *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_NEG | BPF_K, insn->dst_reg, + 0, 0, 0); + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = *insn; + cnt = patch - insn_buf; + } else if (is_smod) { + /* [R,W]x mod 0 -> [R,W]x */ + /* [R,W]x mod -1 -> 0 */ + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_ADD | BPF_K, BPF_REG_AX, + 0, 0, 1); + *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JGT | BPF_K, BPF_REG_AX, + 0, 3, 1); + *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JEQ | BPF_K, BPF_REG_AX, + 0, 3 + (is64 ? 0 : 1), 1); + *patch++ = BPF_MOV32_IMM(insn->dst_reg, 0); + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = *insn; + + if (!is64) { + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV32_REG(insn->dst_reg, insn->dst_reg); + } + cnt = patch - insn_buf; + } else if (isdiv) { /* [R,W]x div 0 -> 0 */ - BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | - BPF_JNE | BPF_K, insn->src_reg, - 0, 2, 0), - BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg), - BPF_JMP_IMM(BPF_JA, 0, 0, 1), - *insn, - }; - struct bpf_insn chk_and_mod[] = { + *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JNE | BPF_K, insn->src_reg, + 0, 2, 0); + *patch++ = BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg); + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = *insn; + cnt = patch - insn_buf; + } else { /* [R,W]x mod 0 -> [R,W]x */ - BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | - BPF_JEQ | BPF_K, insn->src_reg, - 0, 1 + (is64 ? 0 : 1), 0), - *insn, - BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_MOV32_REG(insn->dst_reg, insn->dst_reg), - }; + *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JEQ | BPF_K, insn->src_reg, + 0, 1 + (is64 ? 0 : 1), 0); + *patch++ = *insn; + + if (!is64) { + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV32_REG(insn->dst_reg, insn->dst_reg); + } + cnt = patch - insn_buf; + } - patchlet = isdiv ? chk_and_div : chk_and_mod; - cnt = isdiv ? ARRAY_SIZE(chk_and_div) : - ARRAY_SIZE(chk_and_mod) - (is64 ? 2 : 0); + 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; + } + + /* 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; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + goto next_insn; - new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); + *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; - continue; + goto next_insn; } /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ @@ -15607,9 +22812,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env) (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { cnt = env->ops->gen_ld_abs(insn, insn_buf); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + if (cnt == 0 || cnt >= INSN_BUF_SIZE) { + verifier_bug(env, "%d insns generated for ld_abs", cnt); + return -EFAULT; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); @@ -15619,7 +22824,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Rewrite pointer arithmetic to mitigate speculation attacks. */ @@ -15627,14 +22832,14 @@ static int do_misc_fixups(struct bpf_verifier_env *env) insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) { const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X; const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; - struct bpf_insn *patch = &insn_buf[0]; + struct bpf_insn *patch = insn_buf; bool issrc, isneg, isimm; u32 off_reg; aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) - continue; + goto next_insn; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == @@ -15672,19 +22877,85 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; + } + + if (is_may_goto_insn(insn) && bpf_jit_supports_timed_may_goto()) { + int stack_off_cnt = -stack_depth - 16; + + /* + * Two 8 byte slots, depth-16 stores the count, and + * depth-8 stores the start timestamp of the loop. + * + * The starting value of count is BPF_MAX_TIMED_LOOPS + * (0xffff). Every iteration loads it and subs it by 1, + * until the value becomes 0 in AX (thus, 1 in stack), + * after which we call arch_bpf_timed_may_goto, which + * either sets AX to 0xffff to keep looping, or to 0 + * upon timeout. AX is then stored into the stack. In + * the next iteration, we either see 0 and break out, or + * continue iterating until the next time value is 0 + * after subtraction, rinse and repeat. + */ + stack_depth_extra = 16; + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off_cnt); + if (insn->off >= 0) + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 5); + else + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1); + insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); + insn_buf[3] = BPF_JMP_IMM(BPF_JNE, BPF_REG_AX, 0, 2); + /* + * AX is used as an argument to pass in stack_off_cnt + * (to add to r10/fp), and also as the return value of + * the call to arch_bpf_timed_may_goto. + */ + insn_buf[4] = BPF_MOV64_IMM(BPF_REG_AX, stack_off_cnt); + insn_buf[5] = BPF_EMIT_CALL(arch_bpf_timed_may_goto); + insn_buf[6] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off_cnt); + cnt = 7; + + 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; + } else if (is_may_goto_insn(insn)) { + int stack_off = -stack_depth - 8; + + stack_depth_extra = 8; + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off); + if (insn->off >= 0) + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); + else + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1); + insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); + insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off); + cnt = 4; + + 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; } if (insn->code != (BPF_JMP | BPF_CALL)) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_CALL) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; if (cnt == 0) - continue; + goto next_insn; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) @@ -15693,9 +22964,13 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + 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) @@ -15729,7 +23004,7 @@ 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, }; @@ -15741,11 +23016,11 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } insn->imm = ret + 1; - continue; + goto next_insn; } if (!bpf_map_ptr_unpriv(aux)) - continue; + goto next_insn; /* instead of changing every JIT dealing with tail_call * emit two extra insns: @@ -15758,7 +23033,7 @@ 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, @@ -15774,7 +23049,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } if (insn->imm == BPF_FUNC_timer_set_callback) { @@ -15811,8 +23086,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } if (is_storage_get_function(insn->imm)) { - if (!env->prog->aux->sleepable || - env->insn_aux_data[i + delta].storage_get_func_atomic) + if (env->insn_aux_data[i + delta].non_sleepable) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); else insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); @@ -15829,6 +23103,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto patch_call_imm; } + /* bpf_per_cpu_ptr() and bpf_this_cpu_ptr() */ + if (env->insn_aux_data[i + delta].call_with_percpu_alloc_ptr) { + /* patch with 'r1 = *(u64 *)(r1 + 0)' since for percpu data, + * bpf_mem_alloc() returns a ptr to the percpu data ptr. + */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0); + insn_buf[1] = *insn; + cnt = 2; + + 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 patch_call_imm; + } + /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * and other inlining handlers are currently limited to 64 bit * only. @@ -15847,16 +23140,16 @@ 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) { cnt = ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == -EOPNOTSUPP) goto patch_map_ops_generic; - if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + if (cnt <= 0 || cnt >= INSN_BUF_SIZE) { + verifier_bug(env, "%d insns generated for map lookup", cnt); + return -EFAULT; } new_prog = bpf_patch_insn_data(env, i + delta, @@ -15867,27 +23160,27 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_delete_elem, - (int (*)(struct bpf_map *map, void *key))NULL)); + (long (*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_update_elem, - (int (*)(struct bpf_map *map, void *key, void *value, + (long (*)(struct bpf_map *map, void *key, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_push_elem, - (int (*)(struct bpf_map *map, void *value, + (long (*)(struct bpf_map *map, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_pop_elem, - (int (*)(struct bpf_map *map, void *value))NULL)); + (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_peek_elem, - (int (*)(struct bpf_map *map, void *value))NULL)); + (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, - (int (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); + (long (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, - (int (*)(struct bpf_map *map, + (long (*)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags))NULL)); @@ -15898,31 +23191,31 @@ patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); - continue; + goto next_insn; case BPF_FUNC_map_update_elem: insn->imm = BPF_CALL_IMM(ops->map_update_elem); - continue; + goto next_insn; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CALL_IMM(ops->map_delete_elem); - continue; + goto next_insn; case BPF_FUNC_map_push_elem: insn->imm = BPF_CALL_IMM(ops->map_push_elem); - continue; + goto next_insn; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CALL_IMM(ops->map_pop_elem); - continue; + goto next_insn; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CALL_IMM(ops->map_peek_elem); - continue; + goto next_insn; case BPF_FUNC_redirect_map: insn->imm = BPF_CALL_IMM(ops->map_redirect); - continue; + goto next_insn; case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); - continue; + goto next_insn; case BPF_FUNC_map_lookup_percpu_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); - continue; + goto next_insn; } goto patch_call_imm; @@ -15950,9 +23243,37 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) + /* Implement bpf_get_smp_processor_id() inline. */ + if (insn->imm == BPF_FUNC_get_smp_processor_id && + verifier_inlines_helper_call(env, insn->imm)) { + /* BPF_FUNC_get_smp_processor_id inlining is an + * optimization, so if cpu_number is ever + * changed in some incompatible and hard to support + * way, it's fine to back out this inlining logic + */ +#ifdef CONFIG_SMP + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)&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; +#else + insn_buf[0] = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); + cnt = 1; +#endif + 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) { @@ -15975,7 +23296,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ret inline. */ @@ -16003,7 +23324,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement get_func_arg_cnt inline. */ @@ -16018,7 +23339,7 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ip inline. */ @@ -16033,21 +23354,152 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + 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; + goto next_insn; + } + + /* Implement bpf_kptr_xchg inline */ + if (prog->jit_requested && BITS_PER_LONG == 64 && + insn->imm == BPF_FUNC_kptr_xchg && + bpf_jit_supports_ptr_xchg()) { + insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2); + insn_buf[1] = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0); + cnt = 2; + + 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; + } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ if (!fn->func) { - verbose(env, - "kernel subsystem misconfigured func %s#%d\n", - func_id_name(insn->imm), insn->imm); + verifier_bug(env, + "not inlined functions %s#%d is missing func", + func_id_name(insn->imm), insn->imm); return -EFAULT; } insn->imm = fn->func - __bpf_call_base; +next_insn: + if (subprogs[cur_subprog + 1].start == i + delta + 1) { + subprogs[cur_subprog].stack_depth += stack_depth_extra; + subprogs[cur_subprog].stack_extra = stack_depth_extra; + + stack_depth = subprogs[cur_subprog].stack_depth; + if (stack_depth > MAX_BPF_STACK && !prog->jit_requested) { + verbose(env, "stack size %d(extra %d) is too large\n", + stack_depth, stack_depth_extra); + return -EINVAL; + } + cur_subprog++; + stack_depth = subprogs[cur_subprog].stack_depth; + stack_depth_extra = 0; + } + i++; + insn++; + } + + env->prog->aux->stack_depth = subprogs[0].stack_depth; + for (i = 0; i < env->subprog_cnt; i++) { + int delta = bpf_jit_supports_timed_may_goto() ? 2 : 1; + int subprog_start = subprogs[i].start; + int stack_slots = subprogs[i].stack_extra / 8; + int slots = delta, cnt = 0; + + if (!stack_slots) + continue; + /* We need two slots in case timed may_goto is supported. */ + if (stack_slots > slots) { + verifier_bug(env, "stack_slots supports may_goto only"); + return -EFAULT; + } + + stack_depth = subprogs[i].stack_depth; + if (bpf_jit_supports_timed_may_goto()) { + insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth, + BPF_MAX_TIMED_LOOPS); + insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth + 8, 0); + } else { + /* Add ST insn to subprog prologue to init extra stack */ + insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth, + BPF_MAX_LOOPS); + } + /* Copy first actual insn to preserve it */ + insn_buf[cnt++] = env->prog->insnsi[subprog_start]; + + new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + env->prog = prog = new_prog; + /* + * If may_goto is a first insn of a prog there could be a jmp + * insn that points to it, hence adjust all such jmps to point + * to insn after BPF_ST that inits may_goto count. + * Adjustment will succeed because bpf_patch_insn_data() didn't fail. + */ + WARN_ON(adjust_jmp_off(env->prog, subprog_start, delta)); } /* Since poke tab is now finalized, publish aux to tracker. */ @@ -16056,8 +23508,8 @@ patch_call_imm: if (!map_ptr->ops->map_poke_track || !map_ptr->ops->map_poke_untrack || !map_ptr->ops->map_poke_run) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; + verifier_bug(env, "poke tab is misconfigured"); + return -EFAULT; } ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux); @@ -16067,7 +23519,9 @@ patch_call_imm: } } - sort_kfunc_descs_by_imm(env->prog); + ret = sort_kfunc_descs_by_imm_off(env); + if (ret) + return ret; return 0; } @@ -16076,7 +23530,7 @@ static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, int position, s32 stack_base, u32 callback_subprogno, - u32 *cnt) + u32 *total_cnt) { s32 r6_offset = stack_base + 0 * BPF_REG_SIZE; s32 r7_offset = stack_base + 1 * BPF_REG_SIZE; @@ -16085,55 +23539,56 @@ static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, int reg_loop_cnt = BPF_REG_7; int reg_loop_ctx = BPF_REG_8; + struct bpf_insn *insn_buf = env->insn_buf; struct bpf_prog *new_prog; u32 callback_start; u32 call_insn_offset; s32 callback_offset; + u32 cnt = 0; /* This represents an inlined version of bpf_iter.c:bpf_loop, * be careful to modify this code in sync. */ - struct bpf_insn insn_buf[] = { - /* Return error and jump to the end of the patch if - * expected number of iterations is too big. - */ - BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2), - BPF_MOV32_IMM(BPF_REG_0, -E2BIG), - BPF_JMP_IMM(BPF_JA, 0, 0, 16), - /* spill R6, R7, R8 to use these as loop vars */ - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset), - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset), - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset), - /* initialize loop vars */ - BPF_MOV64_REG(reg_loop_max, BPF_REG_1), - BPF_MOV32_IMM(reg_loop_cnt, 0), - BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3), - /* loop header, - * if reg_loop_cnt >= reg_loop_max skip the loop body - */ - BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5), - /* callback call, - * correct callback offset would be set after patching - */ - BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt), - BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx), - BPF_CALL_REL(0), - /* increment loop counter */ - BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1), - /* jump to loop header if callback returned 0 */ - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6), - /* return value of bpf_loop, - * set R0 to the number of iterations - */ - BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt), - /* restore original values of R6, R7, R8 */ - BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset), - BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset), - BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset), - }; - *cnt = ARRAY_SIZE(insn_buf); - new_prog = bpf_patch_insn_data(env, position, insn_buf, *cnt); + /* Return error and jump to the end of the patch if + * expected number of iterations is too big. + */ + insn_buf[cnt++] = BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2); + insn_buf[cnt++] = BPF_MOV32_IMM(BPF_REG_0, -E2BIG); + insn_buf[cnt++] = BPF_JMP_IMM(BPF_JA, 0, 0, 16); + /* spill R6, R7, R8 to use these as loop vars */ + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset); + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset); + insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset); + /* initialize loop vars */ + insn_buf[cnt++] = BPF_MOV64_REG(reg_loop_max, BPF_REG_1); + insn_buf[cnt++] = BPF_MOV32_IMM(reg_loop_cnt, 0); + insn_buf[cnt++] = BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3); + /* loop header, + * if reg_loop_cnt >= reg_loop_max skip the loop body + */ + insn_buf[cnt++] = BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5); + /* callback call, + * correct callback offset would be set after patching + */ + insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt); + insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx); + insn_buf[cnt++] = BPF_CALL_REL(0); + /* increment loop counter */ + insn_buf[cnt++] = BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1); + /* jump to loop header if callback returned 0 */ + insn_buf[cnt++] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6); + /* return value of bpf_loop, + * set R0 to the number of iterations + */ + insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt); + /* restore original values of R6, R7, R8 */ + insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset); + insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset); + insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset); + + *total_cnt = cnt; + new_prog = bpf_patch_insn_data(env, position, insn_buf, cnt); if (!new_prog) return new_prog; @@ -16208,39 +23663,88 @@ static int optimize_bpf_loop(struct bpf_verifier_env *env) return 0; } +/* Remove unnecessary spill/fill pairs, members of fastcall pattern, + * adjust subprograms stack depth when possible. + */ +static int remove_fastcall_spills_fills(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *subprog = env->subprog_info; + struct bpf_insn_aux_data *aux = env->insn_aux_data; + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + u32 spills_num; + bool modified = false; + int i, j; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (aux[i].fastcall_spills_num > 0) { + spills_num = aux[i].fastcall_spills_num; + /* NOPs would be removed by opt_remove_nops() */ + for (j = 1; j <= spills_num; ++j) { + *(insn - j) = NOP; + *(insn + j) = NOP; + } + modified = true; + } + if ((subprog + 1)->start == i + 1) { + if (modified && !subprog->keep_fastcall_stack) + subprog->stack_depth = -subprog->fastcall_stack_off; + subprog++; + modified = false; + } + } + + return 0; +} + static void free_states(struct bpf_verifier_env *env) { - struct bpf_verifier_state_list *sl, *sln; - int i; + struct bpf_verifier_state_list *sl; + struct list_head *head, *pos, *tmp; + struct bpf_scc_info *info; + int i, j; - sl = env->free_list; - while (sl) { - sln = sl->next; + free_verifier_state(env->cur_state, true); + env->cur_state = NULL; + while (!pop_stack(env, NULL, NULL, false)); + + list_for_each_safe(pos, tmp, &env->free_list) { + sl = container_of(pos, struct bpf_verifier_state_list, node); free_verifier_state(&sl->state, false); kfree(sl); - sl = sln; } - env->free_list = NULL; + INIT_LIST_HEAD(&env->free_list); + + for (i = 0; i < env->scc_cnt; ++i) { + info = env->scc_info[i]; + if (!info) + continue; + for (j = 0; j < info->num_visits; j++) + free_backedges(&info->visits[j]); + kvfree(info); + env->scc_info[i] = NULL; + } if (!env->explored_states) return; for (i = 0; i < state_htab_size(env); i++) { - sl = env->explored_states[i]; + head = &env->explored_states[i]; - while (sl) { - sln = sl->next; + list_for_each_safe(pos, tmp, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); free_verifier_state(&sl->state, false); kfree(sl); - sl = sln; } - env->explored_states[i] = NULL; + INIT_LIST_HEAD(&env->explored_states[i]); } } static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); + struct bpf_subprog_info *sub = subprog_info(env, subprog); + struct bpf_prog_aux *aux = env->prog->aux; struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; @@ -16248,13 +23752,14 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) env->prev_linfo = NULL; env->pass_cnt++; - state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); + state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL_ACCOUNT); if (!state) return -ENOMEM; state->curframe = 0; state->speculative = false; state->branches = 1; - state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); + state->in_sleepable = env->prog->sleepable; + state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL_ACCOUNT); if (!state->frame[0]) { kfree(state); return -ENOMEM; @@ -16269,58 +23774,107 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { - ret = btf_prepare_func_args(env, subprog, regs); + const char *sub_name = subprog_name(env, subprog); + struct bpf_subprog_arg_info *arg; + struct bpf_reg_state *reg; + + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, "Validating %s() func#%d...\n", sub_name, subprog); + ret = btf_prepare_func_args(env, subprog); if (ret) goto out; - for (i = BPF_REG_1; i <= BPF_REG_5; i++) { - if (regs[i].type == PTR_TO_CTX) + + if (subprog_is_exc_cb(env, subprog)) { + state->frame[0]->in_exception_callback_fn = true; + /* We have already ensured that the callback returns an integer, just + * like all global subprogs. We need to determine it only has a single + * scalar argument. + */ + if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) { + verbose(env, "exception cb only supports single integer argument\n"); + ret = -EINVAL; + goto out; + } + } + for (i = BPF_REG_1; i <= sub->arg_cnt; i++) { + arg = &sub->args[i - BPF_REG_1]; + reg = ®s[i]; + + if (arg->arg_type == ARG_PTR_TO_CTX) { + reg->type = PTR_TO_CTX; mark_reg_known_zero(env, regs, i); - else if (regs[i].type == SCALAR_VALUE) + } else if (arg->arg_type == ARG_ANYTHING) { + reg->type = SCALAR_VALUE; mark_reg_unknown(env, regs, i); - else if (base_type(regs[i].type) == PTR_TO_MEM) { - const u32 mem_size = regs[i].mem_size; - + } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { + /* assume unspecial LOCAL dynptr type */ + __mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen); + } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { + reg->type = PTR_TO_MEM; + reg->type |= arg->arg_type & + (PTR_MAYBE_NULL | PTR_UNTRUSTED | MEM_RDONLY); mark_reg_known_zero(env, regs, i); - regs[i].mem_size = mem_size; - regs[i].id = ++env->id_gen; + reg->mem_size = arg->mem_size; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->id = ++env->id_gen; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + reg->type = PTR_TO_BTF_ID; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->type |= PTR_MAYBE_NULL; + if (arg->arg_type & PTR_UNTRUSTED) + reg->type |= PTR_UNTRUSTED; + if (arg->arg_type & PTR_TRUSTED) + reg->type |= PTR_TRUSTED; + mark_reg_known_zero(env, regs, i); + reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */ + reg->btf_id = arg->btf_id; + reg->id = ++env->id_gen; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { + /* caller can pass either PTR_TO_ARENA or SCALAR */ + mark_reg_unknown(env, regs, i); + } else { + verifier_bug(env, "unhandled arg#%d type %d", + i - BPF_REG_1, arg->arg_type); + ret = -EFAULT; + goto out; } } } else { + /* if main BPF program has associated BTF info, validate that + * it's matching expected signature, and otherwise mark BTF + * info for main program as unreliable + */ + if (env->prog->aux->func_info_aux) { + ret = btf_prepare_func_args(env, 0); + if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX) + env->prog->aux->func_info_aux[0].unreliable = true; + } + /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); - ret = btf_check_subprog_arg_match(env, subprog, regs); - if (ret == -EFAULT) - /* unlikely verifier bug. abort. - * ret == 0 and ret < 0 are sadly acceptable for - * main() function due to backward compatibility. - * Like socket filter program may be written as: - * int bpf_prog(struct pt_regs *ctx) - * and never dereference that ctx in the program. - * 'struct pt_regs' is a type mismatch for socket - * filter that should be using 'struct __sk_buff'. - */ - goto out; + } + + /* Acquire references for struct_ops program arguments tagged with "__ref" */ + if (!subprog && env->prog->type == BPF_PROG_TYPE_STRUCT_OPS) { + for (i = 0; i < aux->ctx_arg_info_size; i++) + aux->ctx_arg_info[i].ref_obj_id = aux->ctx_arg_info[i].refcounted ? + acquire_reference(env, 0) : 0; } ret = do_check(env); out: - /* check for NULL is necessary, since cur_state can be freed inside - * do_check() under memory pressure. - */ - if (env->cur_state) { - free_verifier_state(env->cur_state, true); - env->cur_state = NULL; - } - while (!pop_stack(env, NULL, NULL, false)); if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); return ret; } -/* Verify all global functions in a BPF program one by one based on their BTF. - * All global functions must pass verification. Otherwise the whole program is rejected. +/* Lazily verify all global functions based on their BTF, if they are called + * from main BPF program or any of subprograms transitively. + * BPF global subprogs called from dead code are not validated. + * All callable global functions must pass verification. + * Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) @@ -16339,25 +23893,50 @@ out: static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; - int i, ret; + struct bpf_func_info_aux *sub_aux; + int i, ret, new_cnt; if (!aux->func_info) return 0; + /* exception callback is presumed to be always called */ + if (env->exception_callback_subprog) + subprog_aux(env, env->exception_callback_subprog)->called = true; + +again: + new_cnt = 0; for (i = 1; i < env->subprog_cnt; i++) { - if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) + if (!subprog_is_global(env, i)) continue; + + sub_aux = subprog_aux(env, i); + if (!sub_aux->called || sub_aux->verified) + continue; + env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { - verbose(env, - "Func#%d is safe for any args that match its prototype\n", - i); + verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n", + i, subprog_name(env, i)); } + + /* We verified new global subprog, it might have called some + * more global subprogs that we haven't verified yet, so we + * need to do another pass over subprogs to verify those. + */ + sub_aux->verified = true; + new_cnt++; } + + /* We can't loop forever as we verify at least one global subprog on + * each pass. + */ + if (new_cnt) + goto again; + return 0; } @@ -16397,29 +23976,57 @@ static void print_verification_stats(struct bpf_verifier_env *env) env->peak_states, env->longest_mark_read_walk); } +int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, + const struct bpf_ctx_arg_aux *info, u32 cnt) +{ + prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL_ACCOUNT); + prog->aux->ctx_arg_info_size = cnt; + + return prog->aux->ctx_arg_info ? 0 : -ENOMEM; +} + static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; + const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; - u32 btf_id, member_idx; + bool has_refcounted_arg = false; + u32 btf_id, member_idx, member_off; + struct btf *btf; const char *mname; + int i, err; if (!prog->gpl_compatible) { verbose(env, "struct ops programs must have a GPL compatible license\n"); return -EINVAL; } + if (!prog->aux->attach_btf_id) + return -ENOTSUPP; + + btf = prog->aux->attach_btf; + if (btf_is_module(btf)) { + /* Make sure st_ops is valid through the lifetime of env */ + env->attach_btf_mod = btf_try_get_module(btf); + if (!env->attach_btf_mod) { + verbose(env, "struct_ops module %s is not found\n", + btf_get_name(btf)); + return -ENOTSUPP; + } + } + btf_id = prog->aux->attach_btf_id; - st_ops = bpf_struct_ops_find(btf_id); - if (!st_ops) { + st_ops_desc = bpf_struct_ops_find(btf, btf_id); + if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } + st_ops = st_ops_desc->st_ops; - t = st_ops->type; + t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", @@ -16428,8 +24035,8 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } member = &btf_type_member(t)[member_idx]; - mname = btf_name_by_offset(btf_vmlinux, member->name_off); - func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, + mname = btf_name_by_offset(btf, member->name_off); + func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", @@ -16437,8 +24044,16 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + member_off = __btf_member_bit_offset(t, member) / 8; + err = bpf_struct_ops_supported(st_ops, member_off); + if (err) { + verbose(env, "attach to unsupported member %s of struct %s\n", + mname, st_ops->name); + return err; + } + if (st_ops->check_member) { - int err = st_ops->check_member(t, member); + err = st_ops->check_member(t, member, prog); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", @@ -16447,11 +24062,37 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } } + if (prog->aux->priv_stack_requested && !bpf_jit_supports_private_stack()) { + verbose(env, "Private stack not supported by jit\n"); + return -EACCES; + } + + for (i = 0; i < st_ops_desc->arg_info[member_idx].cnt; i++) { + if (st_ops_desc->arg_info[member_idx].info->refcounted) { + has_refcounted_arg = true; + break; + } + } + + /* Tail call is not allowed for programs with refcounted arguments since we + * cannot guarantee that valid refcounted kptrs will be passed to the callee. + */ + for (i = 0; i < env->subprog_cnt; i++) { + if (has_refcounted_arg && env->subprog_info[i].has_tail_call) { + verbose(env, "program with __ref argument cannot tail call\n"); + return -EINVAL; + } + } + + prog->aux->st_ops = st_ops; + prog->aux->attach_st_ops_member_off = member_off; + prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; - return 0; + return bpf_prog_ctx_arg_info_init(prog, st_ops_desc->arg_info[member_idx].info, + st_ops_desc->arg_info[member_idx].cnt); } #define SECURITY_PREFIX "security_" @@ -16472,8 +24113,12 @@ BTF_SET_START(btf_non_sleepable_error_inject) * Assume non-sleepable from bpf safety point of view. */ BTF_ID(func, __filemap_add_folio) +#ifdef CONFIG_FAIL_PAGE_ALLOC BTF_ID(func, should_fail_alloc_page) +#endif +#ifdef CONFIG_FAILSLAB BTF_ID(func, should_failslab) +#endif BTF_SET_END(btf_non_sleepable_error_inject) static int check_non_sleepable_error_inject(u32 btf_id) @@ -16488,13 +24133,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, struct bpf_attach_target_info *tgt_info) { bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; + bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING; + char trace_symbol[KSYM_SYMBOL_LEN]; const char prefix[] = "btf_trace_"; + struct bpf_raw_event_map *btp; int ret = 0, subprog = -1, i; const struct btf_type *t; bool conservative = true; - const char *tname; + const char *tname, *fname; struct btf *btf; long addr = 0; + struct module *mod = NULL; if (!btf_id) { bpf_log(log, "Tracing programs must provide btf_id\n"); @@ -16518,6 +24167,14 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, } if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; + bool tgt_changes_pkt_data; + bool tgt_might_sleep; + + if (bpf_prog_is_dev_bound(prog->aux) && + !bpf_prog_dev_bound_match(prog, tgt_prog)) { + bpf_log(log, "Target program bound device mismatch"); + return -EINVAL; + } for (i = 0; i < aux->func_info_cnt; i++) if (aux->func_info[i].type_id == btf_id) { @@ -16528,6 +24185,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, bpf_log(log, "Subprog %s doesn't exist\n", tname); return -EINVAL; } + if (aux->func && aux->func[subprog]->aux->exception_cb) { + bpf_log(log, + "%s programs cannot attach to exception callback\n", + prog_extension ? "Extension" : "FENTRY/FEXIT"); + return -EINVAL; + } conservative = aux->func_info_aux[subprog].unreliable; if (prog_extension) { if (conservative) { @@ -16540,15 +24203,43 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, "Extension programs should be JITed\n"); return -EINVAL; } + tgt_changes_pkt_data = aux->func + ? aux->func[subprog]->aux->changes_pkt_data + : aux->changes_pkt_data; + if (prog->aux->changes_pkt_data && !tgt_changes_pkt_data) { + bpf_log(log, + "Extension program changes packet data, while original does not\n"); + return -EINVAL; + } + + tgt_might_sleep = aux->func + ? aux->func[subprog]->aux->might_sleep + : aux->might_sleep; + if (prog->aux->might_sleep && !tgt_might_sleep) { + bpf_log(log, + "Extension program may sleep, while original does not\n"); + return -EINVAL; + } } if (!tgt_prog->jited) { bpf_log(log, "Can attach to only JITed progs\n"); return -EINVAL; } - if (tgt_prog->type == prog->type) { - /* Cannot fentry/fexit another fentry/fexit program. - * Cannot attach program extension to another extension. - * It's ok to attach fentry/fexit to extension program. + if (prog_tracing) { + if (aux->attach_tracing_prog) { + /* + * Target program is an fentry/fexit which is already attached + * to another tracing program. More levels of nesting + * attachment are not allowed. + */ + bpf_log(log, "Cannot nest tracing program attach more than once\n"); + return -EINVAL; + } + } else if (tgt_prog->type == prog->type) { + /* + * To avoid potential call chain cycles, prevent attaching of a + * program extension to another extension. It's ok to attach + * fentry/fexit to extension program. */ bpf_log(log, "Cannot recursively attach\n"); return -EINVAL; @@ -16561,16 +24252,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, * except fentry/fexit. The reason is the following. * The fentry/fexit programs are used for performance * analysis, stats and can be attached to any program - * type except themselves. When extension program is - * replacing XDP function it is necessary to allow - * performance analysis of all functions. Both original - * XDP program and its program extension. Hence - * attaching fentry/fexit to BPF_PROG_TYPE_EXT is - * allowed. If extending of fentry/fexit was allowed it - * would be possible to create long call chain - * fentry->extension->fentry->extension beyond - * reasonable stack size. Hence extending fentry is not - * allowed. + * type. When extension program is replacing XDP function + * it is necessary to allow performance analysis of all + * functions. Both original XDP program and its program + * extension. Hence attaching fentry/fexit to + * BPF_PROG_TYPE_EXT is allowed. If extending of + * fentry/fexit was allowed it would be possible to create + * long call chain fentry->extension->fentry->extension + * beyond reasonable stack size. Hence extending fentry + * is not allowed. */ bpf_log(log, "Cannot extend fentry/fexit\n"); return -EINVAL; @@ -16600,10 +24290,34 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, return -EINVAL; } tname += sizeof(prefix) - 1; - t = btf_type_by_id(btf, t->type); - if (!btf_type_is_ptr(t)) - /* should never happen in valid vmlinux build */ + + /* The func_proto of "btf_trace_##tname" is generated from typedef without argument + * names. Thus using bpf_raw_event_map to get argument names. + */ + btp = bpf_get_raw_tracepoint(tname); + if (!btp) return -EINVAL; + fname = kallsyms_lookup((unsigned long)btp->bpf_func, NULL, NULL, NULL, + trace_symbol); + bpf_put_raw_tracepoint(btp); + + if (fname) + ret = btf_find_by_name_kind(btf, fname, BTF_KIND_FUNC); + + if (!fname || ret < 0) { + bpf_log(log, "Cannot find btf of tracepoint template, fall back to %s%s.\n", + prefix, tname); + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_ptr(t)) + /* should never happen in valid vmlinux build */ + return -EINVAL; + } else { + t = btf_type_by_id(btf, ret); + if (!btf_type_is_func(t)) + /* should never happen in valid vmlinux build */ + return -EINVAL; + } + t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) /* should never happen in valid vmlinux build */ @@ -16662,8 +24376,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, else addr = (long) tgt_prog->aux->func[subprog]->bpf_func; } else { - addr = kallsyms_lookup_name(tname); + if (btf_is_module(btf)) { + mod = btf_try_get_module(btf); + if (mod) + addr = find_kallsyms_symbol_value(mod, tname); + else + addr = 0; + } else { + addr = kallsyms_lookup_name(tname); + } if (!addr) { + module_put(mod); bpf_log(log, "The address of function %s cannot be found\n", tname); @@ -16671,7 +24394,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, } } - if (prog->aux->sleepable) { + if (prog->sleepable) { ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: @@ -16686,7 +24409,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, * in the fmodret id set with the KF_SLEEPABLE flag. */ else { - u32 *flags = btf_kfunc_is_modify_return(btf, btf_id); + u32 *flags = btf_kfunc_is_modify_return(btf, btf_id, + prog); if (flags && (*flags & KF_SLEEPABLE)) ret = 0; @@ -16703,19 +24427,22 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, break; } if (ret) { + module_put(mod); bpf_log(log, "%s is not sleepable\n", tname); return ret; } } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { if (tgt_prog) { + module_put(mod); bpf_log(log, "can't modify return codes of BPF programs\n"); return -EINVAL; } ret = -EINVAL; - if (btf_kfunc_is_modify_return(btf, btf_id) || + if (btf_kfunc_is_modify_return(btf, btf_id, prog) || !check_attach_modify_return(addr, tname)) ret = 0; if (ret) { + module_put(mod); bpf_log(log, "%s() is not modifiable\n", tname); return ret; } @@ -16726,20 +24453,75 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, tgt_info->tgt_addr = addr; tgt_info->tgt_name = tname; tgt_info->tgt_type = t; + tgt_info->tgt_mod = mod; return 0; } BTF_SET_START(btf_id_deny) BTF_ID_UNUSED #ifdef CONFIG_SMP +BTF_ID(func, ___migrate_enable) BTF_ID(func, migrate_disable) BTF_ID(func, migrate_enable) #endif #if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU BTF_ID(func, rcu_read_unlock_strict) #endif +#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) +BTF_ID(func, preempt_count_add) +BTF_ID(func, preempt_count_sub) +#endif +#ifdef CONFIG_PREEMPT_RCU +BTF_ID(func, __rcu_read_lock) +BTF_ID(func, __rcu_read_unlock) +#endif BTF_SET_END(btf_id_deny) +/* fexit and fmod_ret can't be used to attach to __noreturn functions. + * Currently, we must manually list all __noreturn functions here. Once a more + * robust solution is implemented, this workaround can be removed. + */ +BTF_SET_START(noreturn_deny) +#ifdef CONFIG_IA32_EMULATION +BTF_ID(func, __ia32_sys_exit) +BTF_ID(func, __ia32_sys_exit_group) +#endif +#ifdef CONFIG_KUNIT +BTF_ID(func, __kunit_abort) +BTF_ID(func, kunit_try_catch_throw) +#endif +#ifdef CONFIG_MODULES +BTF_ID(func, __module_put_and_kthread_exit) +#endif +#ifdef CONFIG_X86_64 +BTF_ID(func, __x64_sys_exit) +BTF_ID(func, __x64_sys_exit_group) +#endif +BTF_ID(func, do_exit) +BTF_ID(func, do_group_exit) +BTF_ID(func, kthread_complete_and_exit) +BTF_ID(func, kthread_exit) +BTF_ID(func, make_task_dead) +BTF_SET_END(noreturn_deny) + +static bool can_be_sleepable(struct bpf_prog *prog) +{ + if (prog->type == BPF_PROG_TYPE_TRACING) { + switch (prog->expected_attach_type) { + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + case BPF_TRACE_ITER: + return true; + default: + return false; + } + } + return prog->type == BPF_PROG_TYPE_LSM || + prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ || + prog->type == BPF_PROG_TYPE_STRUCT_OPS; +} + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; @@ -16751,16 +24533,15 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) u64 key; if (prog->type == BPF_PROG_TYPE_SYSCALL) { - if (prog->aux->sleepable) + if (prog->sleepable) /* attach_btf_id checked to be zero already */ return 0; verbose(env, "Syscall programs can only be sleepable\n"); return -EINVAL; } - if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING && - prog->type != BPF_PROG_TYPE_LSM && prog->type != BPF_PROG_TYPE_KPROBE) { - verbose(env, "Only fentry/fexit/fmod_ret, lsm, and kprobe/uprobe programs can be sleepable\n"); + if (prog->sleepable && !can_be_sleepable(prog)) { + verbose(env, "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n"); return -EINVAL; } @@ -16788,6 +24569,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) /* store info about the attachment target that will be used later */ prog->aux->attach_func_proto = tgt_info.tgt_type; prog->aux->attach_func_name = tgt_info.tgt_name; + prog->aux->mod = tgt_info.tgt_mod; if (tgt_prog) { prog->aux->saved_dst_prog_type = tgt_prog->type; @@ -16798,9 +24580,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) prog->aux->attach_btf_trace = true; return 0; } else if (prog->expected_attach_type == BPF_TRACE_ITER) { - if (!bpf_iter_prog_supported(prog)) - return -EINVAL; - return 0; + return bpf_iter_prog_supported(prog); } if (prog->type == BPF_PROG_TYPE_LSM) { @@ -16809,6 +24589,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return ret; } else if (prog->type == BPF_PROG_TYPE_TRACING && btf_id_set_contains(&btf_id_deny, btf_id)) { + verbose(env, "Attaching tracing programs to function '%s' is rejected.\n", + tgt_info.tgt_name); + return -EINVAL; + } else if ((prog->expected_attach_type == BPF_TRACE_FEXIT || + prog->expected_attach_type == BPF_MODIFY_RETURN) && + btf_id_set_contains(&noreturn_deny, btf_id)) { + verbose(env, "Attaching fexit/fmod_ret to __noreturn function '%s' is rejected.\n", + tgt_info.tgt_name); return -EINVAL; } @@ -16817,6 +24605,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (!tr) return -ENOMEM; + if (tgt_prog && tgt_prog->aux->tail_call_reachable) + tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX; + prog->aux->dst_trampoline = tr; return 0; } @@ -16832,14 +24623,499 @@ struct btf *bpf_get_btf_vmlinux(void) return btf_vmlinux; } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) +/* + * The add_fd_from_fd_array() is executed only if fd_array_cnt is non-zero. In + * this case expect that every file descriptor in the array is either a map or + * a BTF. Everything else is considered to be trash. + */ +static int add_fd_from_fd_array(struct bpf_verifier_env *env, int fd) +{ + struct bpf_map *map; + struct btf *btf; + CLASS(fd, f)(fd); + int err; + + map = __bpf_map_get(f); + if (!IS_ERR(map)) { + err = __add_used_map(env, map); + if (err < 0) + return err; + return 0; + } + + btf = __btf_get_by_fd(f); + if (!IS_ERR(btf)) { + err = __add_used_btf(env, btf); + if (err < 0) + return err; + return 0; + } + + verbose(env, "fd %d is not pointing to valid bpf_map or btf\n", fd); + return PTR_ERR(map); +} + +static int process_fd_array(struct bpf_verifier_env *env, union bpf_attr *attr, bpfptr_t uattr) +{ + size_t size = sizeof(int); + int ret; + int fd; + u32 i; + + env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); + + /* + * The only difference between old (no fd_array_cnt is given) and new + * APIs is that in the latter case the fd_array is expected to be + * continuous and is scanned for map fds right away + */ + if (!attr->fd_array_cnt) + return 0; + + /* Check for integer overflow */ + if (attr->fd_array_cnt >= (U32_MAX / size)) { + verbose(env, "fd_array_cnt is too big (%u)\n", attr->fd_array_cnt); + return -EINVAL; + } + + for (i = 0; i < attr->fd_array_cnt; i++) { + if (copy_from_bpfptr_offset(&fd, env->fd_array, i * size, size)) + return -EFAULT; + + ret = add_fd_from_fd_array(env, fd); + if (ret) + return ret; + } + + return 0; +} + +/* Each field is a register bitmask */ +struct insn_live_regs { + u16 use; /* registers read by instruction */ + u16 def; /* registers written by instruction */ + u16 in; /* registers that may be alive before instruction */ + u16 out; /* registers that may be alive after instruction */ +}; + +/* Bitmask with 1s for all caller saved registers */ +#define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) + +/* Compute info->{use,def} fields for the instruction */ +static void compute_insn_live_regs(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct insn_live_regs *info) +{ + struct call_summary cs; + u8 class = BPF_CLASS(insn->code); + u8 code = BPF_OP(insn->code); + u8 mode = BPF_MODE(insn->code); + u16 src = BIT(insn->src_reg); + u16 dst = BIT(insn->dst_reg); + u16 r0 = BIT(0); + u16 def = 0; + u16 use = 0xffff; + + switch (class) { + case BPF_LD: + switch (mode) { + case BPF_IMM: + if (BPF_SIZE(insn->code) == BPF_DW) { + def = dst; + use = 0; + } + break; + case BPF_LD | BPF_ABS: + case BPF_LD | BPF_IND: + /* stick with defaults */ + break; + } + break; + case BPF_LDX: + switch (mode) { + case BPF_MEM: + case BPF_MEMSX: + def = dst; + use = src; + break; + } + break; + case BPF_ST: + switch (mode) { + case BPF_MEM: + def = 0; + use = dst; + break; + } + break; + case BPF_STX: + switch (mode) { + case BPF_MEM: + def = 0; + use = dst | src; + break; + case BPF_ATOMIC: + switch (insn->imm) { + case BPF_CMPXCHG: + use = r0 | dst | src; + def = r0; + break; + case BPF_LOAD_ACQ: + def = dst; + use = src; + break; + case BPF_STORE_REL: + def = 0; + use = dst | src; + break; + default: + use = dst | src; + if (insn->imm & BPF_FETCH) + def = src; + else + def = 0; + } + break; + } + break; + case BPF_ALU: + case BPF_ALU64: + switch (code) { + case BPF_END: + use = dst; + def = dst; + break; + case BPF_MOV: + def = dst; + if (BPF_SRC(insn->code) == BPF_K) + use = 0; + else + use = src; + break; + default: + def = dst; + if (BPF_SRC(insn->code) == BPF_K) + use = dst; + else + use = dst | src; + } + break; + case BPF_JMP: + case BPF_JMP32: + switch (code) { + case BPF_JA: + case BPF_JCOND: + def = 0; + use = 0; + break; + case BPF_EXIT: + def = 0; + use = r0; + break; + case BPF_CALL: + def = ALL_CALLER_SAVED_REGS; + use = def & ~BIT(BPF_REG_0); + if (get_call_summary(env, insn, &cs)) + use = GENMASK(cs.num_params, 1); + break; + default: + def = 0; + if (BPF_SRC(insn->code) == BPF_K) + use = dst; + else + use = dst | src; + } + break; + } + + info->def = def; + info->use = use; +} + +/* Compute may-live registers after each instruction in the program. + * The register is live after the instruction I if it is read by some + * instruction S following I during program execution and is not + * overwritten between I and S. + * + * Store result in env->insn_aux_data[i].live_regs. + */ +static int compute_live_registers(struct bpf_verifier_env *env) +{ + struct bpf_insn_aux_data *insn_aux = env->insn_aux_data; + struct bpf_insn *insns = env->prog->insnsi; + struct insn_live_regs *state; + int insn_cnt = env->prog->len; + int err = 0, i, j; + bool changed; + + /* Use the following algorithm: + * - define the following: + * - I.use : a set of all registers read by instruction I; + * - I.def : a set of all registers written by instruction I; + * - I.in : a set of all registers that may be alive before I execution; + * - I.out : a set of all registers that may be alive after I execution; + * - insn_successors(I): a set of instructions S that might immediately + * follow I for some program execution; + * - associate separate empty sets 'I.in' and 'I.out' with each instruction; + * - visit each instruction in a postorder and update + * state[i].in, state[i].out as follows: + * + * state[i].out = U [state[s].in for S in insn_successors(i)] + * state[i].in = (state[i].out / state[i].def) U state[i].use + * + * (where U stands for set union, / stands for set difference) + * - repeat the computation while {in,out} fields changes for + * any instruction. + */ + state = kvcalloc(insn_cnt, sizeof(*state), GFP_KERNEL_ACCOUNT); + if (!state) { + err = -ENOMEM; + goto out; + } + + for (i = 0; i < insn_cnt; ++i) + compute_insn_live_regs(env, &insns[i], &state[i]); + + changed = true; + while (changed) { + changed = false; + for (i = 0; i < env->cfg.cur_postorder; ++i) { + int insn_idx = env->cfg.insn_postorder[i]; + struct insn_live_regs *live = &state[insn_idx]; + struct bpf_iarray *succ; + u16 new_out = 0; + u16 new_in = 0; + + succ = bpf_insn_successors(env, insn_idx); + for (int s = 0; s < succ->cnt; ++s) + new_out |= state[succ->items[s]].in; + new_in = (new_out & ~live->def) | live->use; + if (new_out != live->out || new_in != live->in) { + live->in = new_in; + live->out = new_out; + changed = true; + } + } + } + + for (i = 0; i < insn_cnt; ++i) + insn_aux[i].live_regs_before = state[i].in; + + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "Live regs before insn:\n"); + for (i = 0; i < insn_cnt; ++i) { + if (env->insn_aux_data[i].scc) + verbose(env, "%3d ", env->insn_aux_data[i].scc); + else + verbose(env, " "); + verbose(env, "%3d: ", i); + for (j = BPF_REG_0; j < BPF_REG_10; ++j) + if (insn_aux[i].live_regs_before & BIT(j)) + verbose(env, "%d", j); + else + verbose(env, "."); + verbose(env, " "); + verbose_insn(env, &insns[i]); + if (bpf_is_ldimm64(&insns[i])) + i++; + } + } + +out: + kvfree(state); + return err; +} + +/* + * Compute strongly connected components (SCCs) on the CFG. + * Assign an SCC number to each instruction, recorded in env->insn_aux[*].scc. + * If instruction is a sole member of its SCC and there are no self edges, + * assign it SCC number of zero. + * Uses a non-recursive adaptation of Tarjan's algorithm for SCC computation. + */ +static int compute_scc(struct bpf_verifier_env *env) +{ + const u32 NOT_ON_STACK = U32_MAX; + + struct bpf_insn_aux_data *aux = env->insn_aux_data; + const u32 insn_cnt = env->prog->len; + int stack_sz, dfs_sz, err = 0; + u32 *stack, *pre, *low, *dfs; + u32 i, j, t, w; + u32 next_preorder_num; + u32 next_scc_id; + bool assign_scc; + struct bpf_iarray *succ; + + next_preorder_num = 1; + next_scc_id = 1; + /* + * - 'stack' accumulates vertices in DFS order, see invariant comment below; + * - 'pre[t] == p' => preorder number of vertex 't' is 'p'; + * - 'low[t] == n' => smallest preorder number of the vertex reachable from 't' is 'n'; + * - 'dfs' DFS traversal stack, used to emulate explicit recursion. + */ + stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); + pre = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); + low = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); + dfs = kvcalloc(insn_cnt, sizeof(*dfs), GFP_KERNEL_ACCOUNT); + if (!stack || !pre || !low || !dfs) { + err = -ENOMEM; + goto exit; + } + /* + * References: + * [1] R. Tarjan "Depth-First Search and Linear Graph Algorithms" + * [2] D. J. Pearce "A Space-Efficient Algorithm for Finding Strongly Connected Components" + * + * The algorithm maintains the following invariant: + * - suppose there is a path 'u' ~> 'v', such that 'pre[v] < pre[u]'; + * - then, vertex 'u' remains on stack while vertex 'v' is on stack. + * + * Consequently: + * - If 'low[v] < pre[v]', there is a path from 'v' to some vertex 'u', + * such that 'pre[u] == low[v]'; vertex 'u' is currently on the stack, + * and thus there is an SCC (loop) containing both 'u' and 'v'. + * - If 'low[v] == pre[v]', loops containing 'v' have been explored, + * and 'v' can be considered the root of some SCC. + * + * Here is a pseudo-code for an explicitly recursive version of the algorithm: + * + * NOT_ON_STACK = insn_cnt + 1 + * pre = [0] * insn_cnt + * low = [0] * insn_cnt + * scc = [0] * insn_cnt + * stack = [] + * + * next_preorder_num = 1 + * next_scc_id = 1 + * + * def recur(w): + * nonlocal next_preorder_num + * nonlocal next_scc_id + * + * pre[w] = next_preorder_num + * low[w] = next_preorder_num + * next_preorder_num += 1 + * stack.append(w) + * for s in successors(w): + * # Note: for classic algorithm the block below should look as: + * # + * # if pre[s] == 0: + * # recur(s) + * # low[w] = min(low[w], low[s]) + * # elif low[s] != NOT_ON_STACK: + * # low[w] = min(low[w], pre[s]) + * # + * # But replacing both 'min' instructions with 'low[w] = min(low[w], low[s])' + * # does not break the invariant and makes itartive version of the algorithm + * # simpler. See 'Algorithm #3' from [2]. + * + * # 's' not yet visited + * if pre[s] == 0: + * recur(s) + * # if 's' is on stack, pick lowest reachable preorder number from it; + * # if 's' is not on stack 'low[s] == NOT_ON_STACK > low[w]', + * # so 'min' would be a noop. + * low[w] = min(low[w], low[s]) + * + * if low[w] == pre[w]: + * # 'w' is the root of an SCC, pop all vertices + * # below 'w' on stack and assign same SCC to them. + * while True: + * t = stack.pop() + * low[t] = NOT_ON_STACK + * scc[t] = next_scc_id + * if t == w: + * break + * next_scc_id += 1 + * + * for i in range(0, insn_cnt): + * if pre[i] == 0: + * recur(i) + * + * Below implementation replaces explicit recursion with array 'dfs'. + */ + for (i = 0; i < insn_cnt; i++) { + if (pre[i]) + continue; + stack_sz = 0; + dfs_sz = 1; + dfs[0] = i; +dfs_continue: + while (dfs_sz) { + w = dfs[dfs_sz - 1]; + if (pre[w] == 0) { + low[w] = next_preorder_num; + pre[w] = next_preorder_num; + next_preorder_num++; + stack[stack_sz++] = w; + } + /* Visit 'w' successors */ + succ = bpf_insn_successors(env, w); + for (j = 0; j < succ->cnt; ++j) { + if (pre[succ->items[j]]) { + low[w] = min(low[w], low[succ->items[j]]); + } else { + dfs[dfs_sz++] = succ->items[j]; + goto dfs_continue; + } + } + /* + * Preserve the invariant: if some vertex above in the stack + * is reachable from 'w', keep 'w' on the stack. + */ + if (low[w] < pre[w]) { + dfs_sz--; + goto dfs_continue; + } + /* + * Assign SCC number only if component has two or more elements, + * or if component has a self reference. + */ + assign_scc = stack[stack_sz - 1] != w; + for (j = 0; j < succ->cnt; ++j) { + if (succ->items[j] == w) { + assign_scc = true; + break; + } + } + /* Pop component elements from stack */ + do { + t = stack[--stack_sz]; + low[t] = NOT_ON_STACK; + if (assign_scc) + aux[t].scc = next_scc_id; + } while (t != w); + if (assign_scc) + next_scc_id++; + dfs_sz--; + } + } + env->scc_info = kvcalloc(next_scc_id, sizeof(*env->scc_info), GFP_KERNEL_ACCOUNT); + if (!env->scc_info) { + err = -ENOMEM; + goto exit; + } + env->scc_cnt = next_scc_id; +exit: + kvfree(stack); + kvfree(pre); + kvfree(low); + kvfree(dfs); + return err; +} + +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; - struct bpf_verifier_log *log; - int i, len, ret = -EINVAL; + int i, len, ret = -EINVAL, err; + u32 log_true_size; bool is_priv; + BTF_TYPE_EMIT(enum bpf_features); + /* no program is valid */ if (ARRAY_SIZE(bpf_verifier_ops) == 0) return -EINVAL; @@ -16847,10 +25123,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ - env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); + env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL_ACCOUNT); if (!env) return -ENOMEM; - log = &env->log; + + env->bt.env = env; len = (*prog)->len; env->insn_aux_data = @@ -16860,10 +25137,17 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) goto err_free_env; for (i = 0; i < len; i++) env->insn_aux_data[i].orig_idx = i; + env->succ = iarray_realloc(NULL, 2); + if (!env->succ) + goto err_free_env; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; - env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); - is_priv = bpf_capable(); + + env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); + env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); + env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); + env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); + env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); @@ -16871,20 +25155,18 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (!is_priv) mutex_lock(&bpf_verifier_lock); - if (attr->log_level || attr->log_buf || attr->log_size) { - /* user requested verbose verifier output - * and supplied buffer to store the verification trace - */ - log->level = attr->log_level; - log->ubuf = (char __user *) (unsigned long) attr->log_buf; - log->len_total = attr->log_size; + /* user could have requested verbose verifier output + * and supplied buffer to store the verification trace + */ + ret = bpf_vlog_init(&env->log, attr->log_level, + (char __user *) (unsigned long) attr->log_buf, + attr->log_size); + if (ret) + goto err_unlock; - /* log attributes have to be sane */ - if (!bpf_verifier_log_attr_valid(log)) { - ret = -EINVAL; - goto err_unlock; - } - } + ret = process_fd_array(env, attr, uattr); + if (ret) + goto skip_full_check; mark_verifier_state_clean(env); @@ -16901,24 +25183,25 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - env->allow_ptr_leaks = bpf_allow_ptr_leaks(); - env->allow_uninit_stack = bpf_allow_uninit_stack(); - env->bypass_spec_v1 = bpf_bypass_spec_v1(); - env->bypass_spec_v4 = bpf_bypass_spec_v4(); - env->bpf_capable = bpf_capable(); - env->rcu_tag_supported = btf_vmlinux && - btf_find_by_name_kind(btf_vmlinux, "rcu", BTF_KIND_TYPE_TAG) > 0; - if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; + env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; env->explored_states = kvcalloc(state_htab_size(env), - sizeof(struct bpf_verifier_state_list *), - GFP_USER); + sizeof(struct list_head), + GFP_KERNEL_ACCOUNT); ret = -ENOMEM; if (!env->explored_states) goto skip_full_check; + for (i = 0; i < state_htab_size(env); i++) + INIT_LIST_HEAD(&env->explored_states[i]); + INIT_LIST_HEAD(&env->free_list); + + ret = check_btf_info_early(env, attr, uattr); + if (ret < 0) + goto skip_full_check; + ret = add_subprog_and_kfunc(env); if (ret < 0) goto skip_full_check; @@ -16931,15 +25214,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (ret < 0) goto skip_full_check; - ret = check_attach_btf_id(env); - if (ret) - goto skip_full_check; - ret = resolve_pseudo_ldimm64(env); if (ret < 0) goto skip_full_check; - if (bpf_prog_is_dev_bound(env->prog->aux)) { + if (bpf_prog_is_offloaded(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; @@ -16949,15 +25228,45 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (ret < 0) goto skip_full_check; - ret = do_check_subprogs(env); - ret = ret ?: do_check_main(env); + ret = compute_postorder(env); + if (ret < 0) + goto skip_full_check; + + ret = bpf_stack_liveness_init(env); + if (ret) + goto skip_full_check; + + ret = check_attach_btf_id(env); + if (ret) + goto skip_full_check; + + ret = compute_scc(env); + if (ret < 0) + goto skip_full_check; + + ret = compute_live_registers(env); + if (ret < 0) + goto skip_full_check; - if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) + ret = mark_fastcall_patterns(env); + if (ret < 0) + goto skip_full_check; + + ret = do_check_main(env); + ret = ret ?: do_check_subprogs(env); + + if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux)) ret = bpf_prog_offload_finalize(env); skip_full_check: kvfree(env->explored_states); + /* might decrease stack depth, keep it before passes that + * allocate additional slots. + */ + if (ret == 0) + ret = remove_fastcall_spills_fills(env); + if (ret == 0) ret = check_max_stack_depth(env); @@ -16987,7 +25296,7 @@ skip_full_check: /* do 32-bit optimization after insn patching has done so those patched * insns could be handled correctly. */ - if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) { + if (ret == 0 && !bpf_prog_is_offloaded(env->prog->aux)) { ret = opt_subreg_zext_lo32_rnd_hi32(env, attr); env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret : false; @@ -17000,9 +25309,14 @@ skip_full_check: print_verification_stats(env); env->prog->aux->verified_insns = env->insn_processed; - if (log->level && bpf_verifier_log_full(log)) - ret = -ENOSPC; - if (log->level && !log->ubuf) { + /* preserve original error even if log finalization is successful */ + err = bpf_vlog_finalize(&env->log, &log_true_size); + if (err) + ret = err; + + if (uattr_size >= offsetofend(union bpf_attr, log_true_size) && + copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, log_true_size), + &log_true_size, sizeof(log_true_size))) { ret = -EFAULT; goto err_release_maps; } @@ -17014,7 +25328,7 @@ skip_full_check: /* if program passed verifier, update used_maps in bpf_prog_info */ env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt, sizeof(env->used_maps[0]), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!env->prog->aux->used_maps) { ret = -ENOMEM; @@ -17029,7 +25343,7 @@ skip_full_check: /* if program passed verifier, update used_btfs in bpf_prog_aux */ env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt, sizeof(env->used_btfs[0]), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!env->prog->aux->used_btfs) { ret = -ENOMEM; goto err_release_maps; @@ -17049,6 +25363,8 @@ skip_full_check: adjust_btf_func(env); err_release_maps: + if (ret) + release_insn_arrays(env); if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_used_maps() will release them. @@ -17064,11 +25380,19 @@ err_release_maps: env->prog->expected_attach_type = 0; *prog = env->prog; + + module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); + clear_insn_aux_data(env, 0, env->prog->len); vfree(env->insn_aux_data); err_free_env: - kfree(env); + bpf_stack_liveness_free(env); + kvfree(env->cfg.insn_postorder); + kvfree(env->scc_info); + kvfree(env->succ); + kvfree(env->gotox_tmp_buf); + kvfree(env); return ret; } |