diff options
Diffstat (limited to 'kernel/bpf')
73 files changed, 45766 insertions, 7998 deletions
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig new file mode 100644 index 000000000000..17067dcb4386 --- /dev/null +++ b/kernel/bpf/Kconfig @@ -0,0 +1,104 @@ +# SPDX-License-Identifier: GPL-2.0-only + +# BPF interpreter that, for example, classic socket filters depend on. +config BPF + bool + select CRYPTO_LIB_SHA1 + +# 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 +# eBPF JIT supersedes the cBPF JIT. + +# Classic BPF JIT (cBPF) +config HAVE_CBPF_JIT + bool + +# Extended BPF JIT (eBPF) +config HAVE_EBPF_JIT + bool + +# Used by archs to tell that they want the BPF JIT compiler enabled by +# default for kernels that were compiled with BPF JIT support. +config ARCH_WANT_DEFAULT_BPF_JIT + bool + +menu "BPF subsystem" + +config BPF_SYSCALL + bool "Enable bpf() system call" + select BPF + select IRQ_WORK + 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 + Enable the bpf() system call that allows to manipulate BPF programs + and maps via file descriptors. + +config BPF_JIT + bool "Enable BPF Just In Time compiler" + depends on BPF + depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT + 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 + into the kernel. This will significantly speed-up processing of BPF + programs. + + Note, an admin should enable this feature changing: + /proc/sys/net/core/bpf_jit_enable + /proc/sys/net/core/bpf_jit_harden (optional) + /proc/sys/net/core/bpf_jit_kallsyms (optional) + +config BPF_JIT_ALWAYS_ON + bool "Permanently enable BPF JIT and remove BPF interpreter" + depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT + help + Enables BPF JIT and removes BPF interpreter to avoid speculative + execution of BPF instructions by the interpreter. + + When CONFIG_BPF_JIT_ALWAYS_ON is enabled, /proc/sys/net/core/bpf_jit_enable + is permanently set to 1 and setting any other value than that will + return failure. + +config BPF_JIT_DEFAULT_ON + def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON + depends on HAVE_EBPF_JIT && BPF_JIT + +config BPF_UNPRIV_DEFAULT_OFF + bool "Disable unprivileged BPF by default" + default y + depends on BPF_SYSCALL + help + Disables unprivileged BPF by default by setting the corresponding + /proc/sys/kernel/unprivileged_bpf_disabled knob to 2. An admin can + still reenable it by setting it to 0 later on, or permanently + disable it by setting it to 1 (from which no other transition to + 0 is possible anymore). + + Unprivileged BPF could be used to exploit certain potential + speculative execution side-channel vulnerabilities on unmitigated + affected hardware. + + If you are unsure how to answer this question, answer Y. + +source "kernel/bpf/preload/Kconfig" + +config BPF_LSM + bool "Enable BPF LSM Instrumentation" + depends on BPF_EVENTS + depends on BPF_SYSCALL + depends on SECURITY + depends on BPF_JIT + help + Enables instrumentation of the security hooks with BPF programs for + implementing dynamic MAC and Audit Policies. + + If you are unsure how to answer this question, answer N. + +endmenu # "BPF subsystem" diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 1131a921e1a6..410028633621 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,23 +1,37 @@ # SPDX-License-Identifier: GPL-2.0 obj-y := core.o -CFLAGS_core.o += $(call cc-disable-warning, override-init) +ifneq ($(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 += -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 -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o +obj-$(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) += disasm.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o +obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o +obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o obj-$(CONFIG_BPF_JIT) += trampoline.o -obj-$(CONFIG_BPF_SYSCALL) += btf.o +obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.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 endif +ifeq ($(CONFIG_CGROUPS),y) +obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o bpf_cgrp_storage.o +endif obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o @@ -27,5 +41,21 @@ obj-$(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-$(CONFIG_BPF_SYSCALL) += btf_iter.o +obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o +obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o + +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) diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c new file mode 100644 index 000000000000..095a9554e1de --- /dev/null +++ b/kernel/bpf/arena.c @@ -0,0 +1,593 @@ +// 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, GFP_KERNEL | __GFP_ZERO, 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(current->mm, 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, GFP_KERNEL | __GFP_ZERO, + 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); + } +} + +__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_end_defs(); + +BTF_KFUNCS_START(arena_kfuncs) +BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +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); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 11584618e861..eb28c0f219ee 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -10,11 +10,14 @@ #include <linux/filter.h> #include <linux/perf_event.h> #include <uapi/linux/btf.h> +#include <linux/rcupdate_trace.h> +#include <linux/btf_ids.h> #include "map_in_map.h" #define ARRAY_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK) + (BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \ + BPF_F_PRESERVE_ELEMS | BPF_F_INNER_MAP) static void bpf_array_free_percpu(struct bpf_array *array) { @@ -32,8 +35,8 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) int i; for (i = 0; i < array->map.max_entries; i++) { - ptr = __alloc_percpu_gfp(array->elem_size, 8, - GFP_USER | __GFP_NOWARN); + ptr = bpf_map_alloc_percpu(&array->map, array->elem_size, 8, + GFP_USER | __GFP_NOWARN); if (!ptr) { bpf_array_free_percpu(array); return -ENOMEM; @@ -60,13 +63,18 @@ int array_map_alloc_check(union bpf_attr *attr) return -EINVAL; if (attr->map_type != BPF_MAP_TYPE_ARRAY && - attr->map_flags & BPF_F_MMAPABLE) + attr->map_flags & (BPF_F_MMAPABLE | BPF_F_INNER_MAP)) return -EINVAL; - if (attr->value_size > KMALLOC_MAX_SIZE) - /* if value_size is bigger, the user space won't be able to - * access the elements. - */ + if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY && + attr->map_flags & BPF_F_PRESERVE_ELEMS) + return -EINVAL; + + /* 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; @@ -75,11 +83,10 @@ int array_map_alloc_check(union bpf_attr *attr) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; - int ret, numa_node = bpf_map_attr_numa_node(attr); + int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(); - u64 cost, array_size, mask64; - struct bpf_map_memory mem; + bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); + u64 array_size, mask64; struct bpf_array *array; elem_size = round_up(attr->value_size, 8); @@ -120,44 +127,29 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) } } - /* make sure there is no u32 overflow later in round_up() */ - cost = array_size; - if (percpu) - cost += (u64)attr->max_entries * elem_size * num_possible_cpus(); - - ret = bpf_map_charge_init(&mem, cost); - if (ret < 0) - return ERR_PTR(ret); - /* allocate all map elements and zero-initialize them */ if (attr->map_flags & BPF_F_MMAPABLE) { void *data; /* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */ data = bpf_map_area_mmapable_alloc(array_size, numa_node); - if (!data) { - bpf_map_charge_finish(&mem); + if (!data) return ERR_PTR(-ENOMEM); - } array = data + PAGE_ALIGN(sizeof(struct bpf_array)) - offsetof(struct bpf_array, value); } else { array = bpf_map_area_alloc(array_size, numa_node); } - if (!array) { - bpf_map_charge_finish(&mem); + if (!array) return ERR_PTR(-ENOMEM); - } array->index_mask = index_mask; array->map.bypass_spec_v1 = bypass_spec_v1; /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - bpf_map_charge_move(&array->map.memory, &mem); array->elem_size = elem_size; if (percpu && bpf_array_alloc_percpu(array)) { - bpf_map_charge_finish(&array->map.memory); bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } @@ -165,6 +157,11 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) return &array->map; } +static void *array_map_elem_ptr(struct bpf_array* array, u32 index) +{ + return array->value + (u64)array->elem_size * index; +} + /* Called from syscall or from eBPF program */ static void *array_map_lookup_elem(struct bpf_map *map, void *key) { @@ -174,7 +171,7 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) if (unlikely(index >= array->map.max_entries)) return NULL; - return array->value + array->elem_size * (index & array->index_mask); + return array->value + (u64)array->elem_size * (index & array->index_mask); } static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, @@ -208,15 +205,18 @@ static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm, } /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ -static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +static int 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; - u32 elem_size = round_up(map->value_size, 8); + u32 elem_size = array->elem_size; const int ret = BPF_REG_0; const int map_ptr = BPF_REG_1; const int index = BPF_REG_2; + if (map->map_flags & BPF_F_INNER_MAP) + return -EOPNOTSUPP; + *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); if (!map->bypass_spec_v1) { @@ -249,6 +249,52 @@ 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); + u32 index = *(u32 *)key; + + if (cpu >= nr_cpu_ids) + return NULL; + + if (unlikely(index >= array->map.max_entries)) + return NULL; + + return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu); +} + int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) { struct bpf_array *array = container_of(map, struct bpf_array, map); @@ -264,11 +310,12 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) * access 'value_size' of them, so copying rounded areas * will not leak any kernel data */ - size = round_up(map->value_size, 8); + size = array->elem_size; rcu_read_lock(); pptr = array->pptrs[index & array->index_mask]; 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; } rcu_read_unlock(); @@ -295,8 +342,8 @@ 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; @@ -315,19 +362,21 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return -EEXIST; if (unlikely((map_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map))) + !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { - memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]), - value, map->value_size); + val = this_cpu_ptr(array->pptrs[index & array->index_mask]); + copy_map_value(map, val, value); + bpf_obj_free_fields(array->map.record, val); } else { val = array->value + - array->elem_size * (index & array->index_mask); + (u64)array->elem_size * (index & array->index_mask); if (map_flags & BPF_F_LOCK) copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); + bpf_obj_free_fields(array->map.record, val); } return 0; } @@ -359,11 +408,12 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, * returned or zeros which were zero-filled by percpu_alloc, * so no kernel data leaks possible */ - size = round_up(map->value_size, 8); + size = array->elem_size; rcu_read_lock(); pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { - bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size); + copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off); + bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu)); off += size; } rcu_read_unlock(); @@ -371,7 +421,7 @@ 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; } @@ -381,17 +431,46 @@ 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_wq(struct bpf_map *map) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + int i; + + /* We don't reset or free fields other than timer and workqueue + * on uref dropping to zero. + */ + if (btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE)) { + for (i = 0; i < array->map.max_entries; i++) { + if (btf_record_has_field(map->record, BPF_TIMER)) + bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i)); + } + } +} + /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void array_map_free(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); + int 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 - * disconnected from events. Wait for outstanding programs to complete - * and free the array - */ - synchronize_rcu(); + if (!IS_ERR_OR_NULL(map->record)) { + if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + for (i = 0; i < array->map.max_entries; i++) { + void __percpu *pptr = array->pptrs[i & array->index_mask]; + int cpu; + + for_each_possible_cpu(cpu) { + bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu)); + cond_resched(); + } + } + } else { + for (i = 0; i < array->map.max_entries; i++) + bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); + } + } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); @@ -418,7 +497,7 @@ 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(); } @@ -439,7 +518,7 @@ 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"); @@ -494,11 +573,222 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) vma->vm_pgoff + pgoff); } +static bool array_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1) +{ + if (!bpf_map_meta_equal(meta0, meta1)) + return false; + return meta0->map_flags & BPF_F_INNER_MAP ? true : + meta0->max_entries == meta1->max_entries; +} + +struct bpf_iter_seq_array_map_info { + struct bpf_map *map; + void *percpu_value_buf; + u32 index; +}; + +static void *bpf_array_map_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_array_map_info *info = seq->private; + struct bpf_map *map = info->map; + struct bpf_array *array; + u32 index; + + if (info->index >= map->max_entries) + return NULL; + + if (*pos == 0) + ++*pos; + array = container_of(map, struct bpf_array, map); + index = info->index & array->index_mask; + if (info->percpu_value_buf) + return (void *)(uintptr_t)array->pptrs[index]; + return array_map_elem_ptr(array, index); +} + +static void *bpf_array_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_array_map_info *info = seq->private; + struct bpf_map *map = info->map; + struct bpf_array *array; + u32 index; + + ++*pos; + ++info->index; + if (info->index >= map->max_entries) + return NULL; + + array = container_of(map, struct bpf_array, map); + index = info->index & array->index_mask; + if (info->percpu_value_buf) + return (void *)(uintptr_t)array->pptrs[index]; + return array_map_elem_ptr(array, index); +} + +static int __bpf_array_map_seq_show(struct seq_file *seq, void *v) +{ + struct bpf_iter_seq_array_map_info *info = seq->private; + struct bpf_iter__bpf_map_elem ctx = {}; + struct bpf_map *map = info->map; + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int off = 0, cpu = 0; + void __percpu *pptr; + u32 size; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, v == NULL); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.map = info->map; + if (v) { + ctx.key = &info->index; + + if (!info->percpu_value_buf) { + ctx.value = v; + } else { + 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, + per_cpu_ptr(pptr, cpu)); + check_and_init_map_value(map, info->percpu_value_buf + off); + off += size; + } + ctx.value = info->percpu_value_buf; + } + } + + return bpf_iter_run_prog(prog, &ctx); +} + +static int bpf_array_map_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_array_map_seq_show(seq, v); +} + +static void bpf_array_map_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__bpf_array_map_seq_show(seq, NULL); +} + +static int bpf_iter_init_array_map(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct bpf_iter_seq_array_map_info *seq_info = priv_data; + struct bpf_map *map = aux->map; + struct bpf_array *array = container_of(map, struct bpf_array, map); + void *value_buf; + u32 buf_size; + + if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + buf_size = array->elem_size * num_possible_cpus(); + value_buf = kmalloc(buf_size, GFP_USER | __GFP_NOWARN); + if (!value_buf) + return -ENOMEM; + + seq_info->percpu_value_buf = value_buf; + } + + /* bpf_iter_attach_map() acquires a map uref, and the uref may be + * released before or in the middle of iterating map elements, so + * acquire an extra map uref for iterator. + */ + bpf_map_inc_with_uref(map); + seq_info->map = map; + return 0; +} + +static void bpf_iter_fini_array_map(void *priv_data) +{ + struct bpf_iter_seq_array_map_info *seq_info = priv_data; + + bpf_map_put_with_uref(seq_info->map); + kfree(seq_info->percpu_value_buf); +} + +static const struct seq_operations bpf_array_map_seq_ops = { + .start = bpf_array_map_seq_start, + .next = bpf_array_map_seq_next, + .stop = bpf_array_map_seq_stop, + .show = bpf_array_map_seq_show, +}; + +static const struct bpf_iter_seq_info iter_seq_info = { + .seq_ops = &bpf_array_map_seq_ops, + .init_seq_private = bpf_iter_init_array_map, + .fini_seq_private = bpf_iter_fini_array_map, + .seq_priv_size = sizeof(struct bpf_iter_seq_array_map_info), +}; + +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; + bool is_percpu; + 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); + for (i = 0; i < map->max_entries; i++) { + if (is_percpu) + val = this_cpu_ptr(array->pptrs[i]); + else + val = array_map_elem_ptr(array, i); + num_elems++; + key = i; + ret = callback_fn((u64)(long)map, (u64)(long)&key, + (u64)(long)val, (u64)(long)callback_ctx, 0); + /* return value: 0 - continue, 1 - stop and return */ + if (ret) + break; + } + + 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_wq, .map_lookup_elem = array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, @@ -510,18 +800,33 @@ const struct bpf_map_ops array_map_ops = { .map_check_btf = array_map_check_btf, .map_lookup_batch = generic_map_lookup_batch, .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, }; const struct bpf_map_ops percpu_array_map_ops = { + .map_meta_equal = bpf_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_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, .map_seq_show_elem = percpu_array_map_seq_show_elem, .map_check_btf = array_map_check_btf, + .map_lookup_batch = generic_map_lookup_batch, + .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, }; static int fd_array_map_alloc_check(union bpf_attr *attr) @@ -540,8 +845,6 @@ static void fd_array_map_free(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - synchronize_rcu(); - /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) BUG_ON(array->ptrs[i] != NULL); @@ -603,11 +906,11 @@ 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; @@ -626,33 +929,60 @@ 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_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog = bpf_prog_get(fd); + bool is_extended; if (IS_ERR(prog)) return prog; - if (!bpf_prog_array_compatible(array, 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) @@ -661,13 +991,13 @@ 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, @@ -686,7 +1016,7 @@ 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'); } } @@ -749,6 +1079,12 @@ 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) @@ -761,7 +1097,7 @@ 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]; @@ -773,29 +1109,19 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, * there could be danger of use after free otherwise. * 2) Initially when we start tracking aux, the program * is not JITed yet and also does not have a kallsyms - * entry. We skip these as poke->ip_stable is not - * active yet. The JIT will do the final fixup before - * setting it stable. The various poke->ip_stable are - * successively 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 + * entry. We skip these as poke->tailcall_target_stable + * is not active yet. The JIT will do the final fixup + * before setting it stable. The various + * poke->tailcall_target_stable are successively + * activated, so tail call updates can arrive from here + * while JIT is still finishing its final fixup for + * non-activated poke entries. + * 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->ip_stable)) + if (!READ_ONCE(poke->tailcall_target_stable)) continue; if (poke->reason != BPF_POKE_REASON_TAIL_CALL) continue; @@ -803,12 +1129,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, poke->tail_call.key != key) continue; - ret = bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, - old ? (u8 *)old->bpf_func + - poke->adj_off : NULL, - new ? (u8 *)new->bpf_func + - poke->adj_off : NULL); - BUG_ON(ret < 0 && ret != -EINVAL); + bpf_arch_poke_desc_update(poke, new, old); } } } @@ -817,7 +1138,7 @@ 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); } @@ -834,7 +1155,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) struct bpf_array_aux *aux; struct bpf_map *map; - aux = kzalloc(sizeof(*aux), GFP_KERNEL); + aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT); if (!aux) return ERR_PTR(-ENOMEM); @@ -868,6 +1189,11 @@ static void prog_array_map_free(struct bpf_map *map) fd_array_map_free(map); } +/* prog_array->aux->{type,jited} is a runtime binding. + * Doing static check alone in the verifier is not enough. + * Thus, prog_array_map cannot be used as an inner_map + * and map_meta_equal is not implemented. + */ const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = prog_array_map_alloc, @@ -883,6 +1209,8 @@ 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], }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, @@ -890,7 +1218,7 @@ 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; @@ -940,8 +1268,9 @@ 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); } @@ -952,19 +1281,30 @@ static void perf_event_fd_array_release(struct bpf_map *map, struct bpf_event_entry *ee; int i; + if (map->map_flags & BPF_F_PRESERVE_ELEMS) + return; + rcu_read_lock(); 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(); } +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, false); + fd_array_map_free(map); +} + const struct bpf_map_ops perf_event_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, - .map_free = fd_array_map_free, + .map_free = perf_event_fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, @@ -972,6 +1312,8 @@ const struct bpf_map_ops perf_event_array_map_ops = { .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], }; #ifdef CONFIG_CGROUPS @@ -982,7 +1324,7 @@ 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); @@ -990,11 +1332,12 @@ 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); } const struct bpf_map_ops cgroup_array_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = cgroup_fd_array_free, @@ -1004,6 +1347,8 @@ const struct bpf_map_ops cgroup_array_map_ops = { .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 @@ -1032,7 +1377,7 @@ 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); } @@ -1046,11 +1391,11 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } -static u32 array_of_map_gen_lookup(struct bpf_map *map, +static int array_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_array *array = container_of(map, struct bpf_array, map); - u32 elem_size = round_up(map->value_size, 8); + u32 elem_size = array->elem_size; struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; const int map_ptr = BPF_REG_1; @@ -1088,5 +1433,9 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = array_of_map_gen_lookup, + .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 new file mode 100644 index 000000000000..35e1ddca74d2 --- /dev/null +++ b/kernel/bpf/bloom_filter.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bitmap.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <linux/jhash.h> +#include <linux/random.h> +#include <linux/btf_ids.h> + +#define BLOOM_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) + +struct bpf_bloom_filter { + struct bpf_map map; + u32 bitset_mask; + u32 hash_seed; + u32 nr_hash_funcs; + unsigned long bitset[]; +}; + +static u32 hash(struct bpf_bloom_filter *bloom, void *value, + u32 value_size, u32 index) +{ + u32 h; + + 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 long bloom_map_peek_elem(struct bpf_map *map, void *value) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + if (!test_bit(h, bloom->bitset)) + return -ENOENT; + } + + return 0; +} + +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); + u32 i, h; + + if (flags != BPF_ANY) + return -EINVAL; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + set_bit(h, bloom->bitset); + } + + return 0; +} + +static long bloom_map_pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long bloom_map_delete_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +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 (attr->key_size != 0 || attr->value_size == 0 || + attr->max_entries == 0 || + attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || + /* The lower 4 bits of map_extra (0xF) specify the number + * of hash functions + */ + (attr->map_extra & ~0xF)) + return ERR_PTR(-EINVAL); + + nr_hash_funcs = attr->map_extra; + if (nr_hash_funcs == 0) + /* Default to using 5 hash functions if unspecified */ + nr_hash_funcs = 5; + + /* For the bloom filter, the optimal bit array size that minimizes the + * false positive probability is n * k / ln(2) where n is the number of + * expected entries in the bloom filter and k is the number of hash + * functions. We use 7 / 5 to approximate 1 / ln(2). + * + * We round this up to the nearest power of two to enable more efficient + * hashing using bitmasks. The bitmask will be the bit array size - 1. + * + * If this overflows a u32, the bit array size will have 2^32 (4 + * GB) bits. + */ + if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || + check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || + nr_bits > (1UL << 31)) { + /* The bit array size is 2^32 bits but to avoid overflowing the + * u32, we use U32_MAX, which will round up to the equivalent + * number of bytes + */ + bitset_bytes = BITS_TO_BYTES(U32_MAX); + bitset_mask = U32_MAX; + } else { + if (nr_bits <= BITS_PER_LONG) + nr_bits = BITS_PER_LONG; + else + nr_bits = roundup_pow_of_two(nr_bits); + bitset_bytes = BITS_TO_BYTES(nr_bits); + bitset_mask = nr_bits - 1; + } + + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); + + if (!bloom) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&bloom->map, attr); + + bloom->nr_hash_funcs = nr_hash_funcs; + bloom->bitset_mask = bitset_mask; + + if (!(attr->map_flags & BPF_F_ZERO_SEED)) + bloom->hash_seed = get_random_u32(); + + return &bloom->map; +} + +static void bloom_map_free(struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + + bpf_map_area_free(bloom); +} + +static void *bloom_map_lookup_elem(struct bpf_map *map, void *key) +{ + /* The eBPF program should use map_peek_elem instead */ + return ERR_PTR(-EINVAL); +} + +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; +} + +static int bloom_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Bloom filter maps are keyless */ + 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, + .map_push_elem = bloom_map_push_elem, + .map_peek_elem = bloom_map_peek_elem, + .map_pop_elem = bloom_map_pop_elem, + .map_lookup_elem = bloom_map_lookup_elem, + .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 new file mode 100644 index 000000000000..54ff2a85d4c0 --- /dev/null +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + */ + +#include <linux/types.h> +#include <linux/bpf.h> +#include <linux/bpf_local_storage.h> +#include <uapi/linux/btf.h> +#include <linux/btf_ids.h> + +DEFINE_BPF_STORAGE_CACHE(cgroup_cache); + +static DEFINE_PER_CPU(int, bpf_cgrp_storage_busy); + +static void bpf_cgrp_storage_lock(void) +{ + cant_migrate(); + this_cpu_inc(bpf_cgrp_storage_busy); +} + +static void bpf_cgrp_storage_unlock(void) +{ + this_cpu_dec(bpf_cgrp_storage_busy); +} + +static bool bpf_cgrp_storage_trylock(void) +{ + cant_migrate(); + if (unlikely(this_cpu_inc_return(bpf_cgrp_storage_busy) != 1)) { + this_cpu_dec(bpf_cgrp_storage_busy); + return false; + } + return true; +} + +static struct bpf_local_storage __rcu **cgroup_storage_ptr(void *owner) +{ + struct cgroup *cg = owner; + + return &cg->bpf_cgrp_storage; +} + +void bpf_cgrp_storage_free(struct cgroup *cgroup) +{ + struct bpf_local_storage *local_storage; + + migrate_disable(); + rcu_read_lock(); + local_storage = rcu_dereference(cgroup->bpf_cgrp_storage); + if (!local_storage) + goto out; + + bpf_cgrp_storage_lock(); + bpf_local_storage_destroy(local_storage); + bpf_cgrp_storage_unlock(); +out: + rcu_read_unlock(); + migrate_enable(); +} + +static struct bpf_local_storage_data * +cgroup_storage_lookup(struct cgroup *cgroup, struct bpf_map *map, bool cacheit_lockit) +{ + struct bpf_local_storage *cgroup_storage; + struct bpf_local_storage_map *smap; + + cgroup_storage = rcu_dereference_check(cgroup->bpf_cgrp_storage, + bpf_rcu_lock_held()); + if (!cgroup_storage) + return NULL; + + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(cgroup_storage, smap, cacheit_lockit); +} + +static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_local_storage_data *sdata; + struct cgroup *cgroup; + int fd; + + fd = *(int *)key; + cgroup = cgroup_v1v2_get_from_fd(fd); + if (IS_ERR(cgroup)) + return ERR_CAST(cgroup); + + bpf_cgrp_storage_lock(); + sdata = cgroup_storage_lookup(cgroup, map, true); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return sdata ? sdata->data : NULL; +} + +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_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, false, GFP_ATOMIC); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return PTR_ERR_OR_ZERO(sdata); +} + +static int cgroup_storage_delete(struct cgroup *cgroup, struct bpf_map *map) +{ + struct bpf_local_storage_data *sdata; + + sdata = cgroup_storage_lookup(cgroup, map, false); + if (!sdata) + return -ENOENT; + + bpf_selem_unlink(SELEM(sdata), false); + return 0; +} + +static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct cgroup *cgroup; + int err, fd; + + fd = *(int *)key; + cgroup = cgroup_v1v2_get_from_fd(fd); + if (IS_ERR(cgroup)) + return PTR_ERR(cgroup); + + bpf_cgrp_storage_lock(); + err = cgroup_storage_delete(cgroup, map); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return err; +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -ENOTSUPP; +} + +static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) +{ + 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, &bpf_cgrp_storage_busy); +} + +/* *gfp_flags* is a hidden argument provided by the verifier */ +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; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) + return (unsigned long)NULL; + + if (!cgroup) + return (unsigned long)NULL; + + if (!bpf_cgrp_storage_trylock()) + return (unsigned long)NULL; + + sdata = cgroup_storage_lookup(cgroup, map, true); + 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)) + sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, + value, BPF_NOEXIST, false, gfp_flags); + +unlock: + bpf_cgrp_storage_unlock(); + return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; +} + +BPF_CALL_2(bpf_cgrp_storage_delete, struct bpf_map *, map, struct cgroup *, cgroup) +{ + int ret; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (!cgroup) + return -EINVAL; + + if (!bpf_cgrp_storage_trylock()) + return -EBUSY; + + ret = cgroup_storage_delete(cgroup, map); + bpf_cgrp_storage_unlock(); + return ret; +} + +const struct bpf_map_ops cgrp_storage_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = cgroup_storage_map_alloc, + .map_free = cgroup_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_cgrp_storage_lookup_elem, + .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, +}; + +const struct bpf_func_proto bpf_cgrp_storage_get_proto = { + .func = bpf_cgrp_storage_get, + .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_OR_NULL, + .arg2_btf_id = &bpf_cgroup_btf_id[0], + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_cgrp_storage_delete_proto = { + .func = bpf_cgrp_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .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 new file mode 100644 index 000000000000..15a3eb9b02d9 --- /dev/null +++ b/kernel/bpf/bpf_inode_storage.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Facebook + * Copyright 2020 Google LLC. + */ + +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <linux/bpf_local_storage.h> +#include <net/sock.h> +#include <uapi/linux/sock_diag.h> +#include <uapi/linux/btf.h> +#include <linux/bpf_lsm.h> +#include <linux/btf_ids.h> +#include <linux/rcupdate_trace.h> + +DEFINE_BPF_STORAGE_CACHE(inode_cache); + +static struct bpf_local_storage __rcu ** +inode_storage_ptr(void *owner) +{ + struct inode *inode = owner; + struct bpf_storage_blob *bsb; + + bsb = bpf_inode(inode); + if (!bsb) + return NULL; + return &bsb->storage; +} + +static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, + struct bpf_map *map, + bool cacheit_lockit) +{ + struct bpf_local_storage *inode_storage; + struct bpf_local_storage_map *smap; + struct bpf_storage_blob *bsb; + + bsb = bpf_inode(inode); + if (!bsb) + return NULL; + + inode_storage = + rcu_dereference_check(bsb->storage, bpf_rcu_lock_held()); + if (!inode_storage) + return NULL; + + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit); +} + +void bpf_inode_storage_free(struct inode *inode) +{ + struct bpf_local_storage *local_storage; + struct bpf_storage_blob *bsb; + + bsb = bpf_inode(inode); + if (!bsb) + return; + + migrate_disable(); + rcu_read_lock(); + + local_storage = rcu_dereference(bsb->storage); + if (!local_storage) + goto out; + + bpf_local_storage_destroy(local_storage); +out: + rcu_read_unlock(); + migrate_enable(); +} + +static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_local_storage_data *sdata; + CLASS(fd_raw, f)(*(int *)key); + + if (fd_empty(f)) + return ERR_PTR(-EBADF); + + sdata = inode_storage_lookup(file_inode(fd_file(f)), map, true); + return sdata ? sdata->data : NULL; +} + +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; + CLASS(fd_raw, f)(*(int *)key); + + if (fd_empty(f)) + return -EBADF; + if (!inode_storage_ptr(file_inode(fd_file(f)))) + return -EBADF; + + sdata = bpf_local_storage_update(file_inode(fd_file(f)), + (struct bpf_local_storage_map *)map, + value, map_flags, false, GFP_ATOMIC); + return PTR_ERR_OR_ZERO(sdata); +} + +static int inode_storage_delete(struct inode *inode, struct bpf_map *map) +{ + struct bpf_local_storage_data *sdata; + + sdata = inode_storage_lookup(inode, map, false); + if (!sdata) + return -ENOENT; + + bpf_selem_unlink(SELEM(sdata), false); + + return 0; +} + +static long bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) +{ + CLASS(fd_raw, f)(*(int *)key); + + if (fd_empty(f)) + return -EBADF; + return inode_storage_delete(file_inode(fd_file(f)), map); +} + +/* *gfp_flags* is a hidden argument provided by the verifier */ +BPF_CALL_5(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, + void *, value, u64, flags, gfp_t, gfp_flags) +{ + struct bpf_local_storage_data *sdata; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) + return (unsigned long)NULL; + + /* explicitly check that the inode_storage_ptr is not + * NULL as inode_storage_lookup returns NULL in this case and + * bpf_local_storage_update expects the owner to have a + * valid storage pointer. + */ + if (!inode || !inode_storage_ptr(inode)) + return (unsigned long)NULL; + + sdata = inode_storage_lookup(inode, map, true); + if (sdata) + return (unsigned long)sdata->data; + + /* This helper must only called from where the inode is guaranteed + * to have a refcount and cannot be freed. + */ + if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { + sdata = bpf_local_storage_update( + inode, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST, false, gfp_flags); + return IS_ERR(sdata) ? (unsigned long)NULL : + (unsigned long)sdata->data; + } + + return (unsigned long)NULL; +} + +BPF_CALL_2(bpf_inode_storage_delete, + struct bpf_map *, map, struct inode *, inode) +{ + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (!inode) + return -EINVAL; + + /* This helper must only called from where the inode is guaranteed + * to have a refcount and cannot be freed. + */ + return inode_storage_delete(inode, map); +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -ENOTSUPP; +} + +static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) +{ + return bpf_local_storage_map_alloc(attr, &inode_cache, false); +} + +static void inode_storage_map_free(struct bpf_map *map) +{ + bpf_local_storage_map_free(map, &inode_cache, NULL); +} + +const struct bpf_map_ops inode_storage_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = inode_storage_map_alloc, + .map_free = inode_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_fd_inode_storage_lookup_elem, + .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, +}; + +BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode) + +const struct bpf_func_proto bpf_inode_storage_get_proto = { + .func = bpf_inode_storage_get, + .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_OR_NULL, + .arg2_btf_id = &bpf_inode_storage_btf_ids[0], + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_inode_storage_delete_proto = { + .func = bpf_inode_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, + .arg2_btf_id = &bpf_inode_storage_btf_ids[0], +}; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index dd612b80b9fe..106735145948 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -5,6 +5,7 @@ #include <linux/anon_inodes.h> #include <linux/filter.h> #include <linux/bpf.h> +#include <linux/rcupdate_trace.h> struct bpf_iter_target_info { struct list_head list; @@ -14,11 +15,13 @@ struct bpf_iter_target_info { struct bpf_iter_link { struct bpf_link link; + struct bpf_iter_aux_info aux; struct bpf_iter_target_info *tinfo; }; struct bpf_iter_priv_data { struct bpf_iter_target_info *tinfo; + const struct bpf_iter_seq_info *seq_info; struct bpf_prog *prog; u64 session_id; u64 seq_num; @@ -35,7 +38,8 @@ 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); +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, + const struct bpf_iter_seq_info *seq_info); static void bpf_iter_inc_seq_num(struct seq_file *seq) { @@ -64,11 +68,27 @@ static void bpf_iter_done_stop(struct seq_file *seq) iter_priv->done_stop = true; } +static inline bool bpf_iter_target_support_resched(const struct bpf_iter_target_info *tinfo) +{ + return tinfo->reg_info->feature & BPF_ITER_RESCHED; +} + +static bool bpf_iter_support_resched(struct seq_file *seq) +{ + struct bpf_iter_priv_data *iter_priv; + + iter_priv = container_of(seq->private, struct bpf_iter_priv_data, + target_private); + return bpf_iter_target_support_resched(iter_priv->tinfo); +} + +/* maximum visited objects before bailing out */ +#define MAX_ITER_OBJECTS 1000000 + /* bpf_seq_read, a customized and simpler version for bpf iterator. - * no_llseek is assumed for this file. * The following are differences from seq_read(): * . fixed buffer size (PAGE_SIZE) - * . assuming no_llseek + * . assuming NULL ->llseek() * . stop() may call bpf program, handling potential overflow there */ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, @@ -76,14 +96,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, { struct seq_file *seq = file->private_data; size_t n, offs, copied = 0; - int err = 0; + int err = 0, num_objs = 0; + bool can_resched; void *p; mutex_lock(&seq->lock); if (!seq->buf) { - seq->size = PAGE_SIZE; - seq->buf = kmalloc(seq->size, GFP_KERNEL); + seq->size = PAGE_SIZE << 3; + seq->buf = kvmalloc(seq->size, GFP_KERNEL); if (!seq->buf) { err = -ENOMEM; goto done; @@ -129,9 +150,11 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, goto done; } + can_resched = bpf_iter_support_resched(seq); while (1) { loff_t pos = seq->index; + num_objs++; offs = seq->count; p = seq->op->next(seq, p, &seq->index); if (pos == seq->index) { @@ -150,6 +173,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, if (seq->count >= size) break; + if (num_objs >= MAX_ITER_OBJECTS) { + if (offs == 0) { + err = -EAGAIN; + seq->op->stop(seq, p); + goto done; + } + break; + } + err = seq->op->show(seq, p); if (err > 0) { bpf_iter_dec_seq_num(seq); @@ -164,9 +196,17 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, } break; } + + if (can_resched) + cond_resched(); } stop: offs = seq->count; + if (IS_ERR(p)) { + seq->op->stop(seq, NULL); + err = PTR_ERR(p); + goto done; + } /* bpf program called if !p */ seq->op->stop(seq, p); if (!p) { @@ -199,11 +239,25 @@ done: return copied; } +static const struct bpf_iter_seq_info * +__get_seq_info(struct bpf_iter_link *link) +{ + const struct bpf_iter_seq_info *seq_info; + + if (link->aux.map) { + seq_info = link->aux.map->ops->iter_seq_info; + if (seq_info) + return seq_info; + } + + return link->tinfo->reg_info->seq_info; +} + static int iter_open(struct inode *inode, struct file *file) { struct bpf_iter_link *link = inode->i_private; - return prepare_seq_file(file, link); + return prepare_seq_file(file, link, __get_seq_info(link)); } static int iter_release(struct inode *inode, struct file *file) @@ -218,8 +272,8 @@ static int iter_release(struct inode *inode, struct file *file) iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); - if (iter_priv->tinfo->reg_info->fini_seq_private) - iter_priv->tinfo->reg_info->fini_seq_private(seq->private); + if (iter_priv->seq_info->fini_seq_private) + iter_priv->seq_info->fini_seq_private(seq->private); bpf_prog_put(iter_priv->prog); seq->private = iter_priv; @@ -229,7 +283,6 @@ 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, }; @@ -243,7 +296,7 @@ int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info) { struct bpf_iter_target_info *tinfo; - tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); + tinfo = kzalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) return -ENOMEM; @@ -285,39 +338,65 @@ static void cache_btf_id(struct bpf_iter_target_info *tinfo, bool 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; u32 prog_btf_id = prog->aux->attach_btf_id; const char *prefix = BPF_ITER_FUNC_PREFIX; - struct bpf_iter_target_info *tinfo; int prefix_len = strlen(prefix); - bool supported = false; if (strncmp(attach_fname, prefix, prefix_len)) return false; mutex_lock(&targets_mutex); - list_for_each_entry(tinfo, &targets, list) { - if (tinfo->btf_id && tinfo->btf_id == prog_btf_id) { - supported = true; + list_for_each_entry(iter, &targets, list) { + if (iter->btf_id && iter->btf_id == prog_btf_id) { + tinfo = iter; break; } - if (!strcmp(attach_fname + prefix_len, tinfo->reg_info->target)) { - cache_btf_id(tinfo, prog); - supported = true; + if (!strcmp(attach_fname + prefix_len, iter->reg_info->target)) { + cache_btf_id(iter, prog); + tinfo = iter; break; } } mutex_unlock(&targets_mutex); - if (supported) { + 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; } - return supported; + return tinfo != NULL; +} + +const struct bpf_func_proto * +bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + const struct bpf_iter_target_info *tinfo; + const struct bpf_func_proto *fn = NULL; + + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (tinfo->btf_id == prog->aux->attach_btf_id) { + const struct bpf_iter_reg *reg_info; + + reg_info = tinfo->reg_info; + if (reg_info->get_func_proto) + fn = reg_info->get_func_proto(func_id, prog); + break; + } + } + mutex_unlock(&targets_mutex); + + return fn; } static void bpf_iter_link_release(struct bpf_link *link) { + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + + if (iter_link->tinfo->reg_info->detach_target) + iter_link->tinfo->reg_info->detach_target(&iter_link->aux); } static void bpf_iter_link_dealloc(struct bpf_link *link) @@ -355,10 +434,68 @@ out_unlock: return ret; } +static void bpf_iter_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + bpf_iter_show_fdinfo_t show_fdinfo; + + seq_printf(seq, + "target_name:\t%s\n", + iter_link->tinfo->reg_info->target); + + show_fdinfo = iter_link->tinfo->reg_info->show_fdinfo; + if (show_fdinfo) + show_fdinfo(&iter_link->aux, seq); +} + +static int bpf_iter_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + char __user *ubuf = u64_to_user_ptr(info->iter.target_name); + bpf_iter_fill_link_info_t fill_link_info; + u32 ulen = info->iter.target_name_len; + const char *target_name; + u32 target_len; + + if (!ulen ^ !ubuf) + return -EINVAL; + + target_name = iter_link->tinfo->reg_info->target; + target_len = strlen(target_name); + info->iter.target_name_len = target_len + 1; + + if (ubuf) { + if (ulen >= target_len + 1) { + if (copy_to_user(ubuf, target_name, target_len + 1)) + return -EFAULT; + } else { + char zero = '\0'; + + if (copy_to_user(ubuf, target_name, ulen - 1)) + return -EFAULT; + if (put_user(zero, ubuf + ulen - 1)) + return -EFAULT; + return -ENOSPC; + } + } + + fill_link_info = iter_link->tinfo->reg_info->fill_link_info; + if (fill_link_info) + return fill_link_info(&iter_link->aux, info); + + return 0; +} + static const struct bpf_link_ops bpf_iter_link_lops = { .release = bpf_iter_link_release, .dealloc = bpf_iter_link_dealloc, .update_prog = bpf_iter_link_replace, + .show_fdinfo = bpf_iter_link_show_fdinfo, + .fill_link_info = bpf_iter_link_fill_link_info, }; bool bpf_link_is_iter(struct bpf_link *link) @@ -366,30 +503,53 @@ bool bpf_link_is_iter(struct bpf_link *link) return link->ops == &bpf_iter_link_lops; } -int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, + struct bpf_prog *prog) { + struct bpf_iter_target_info *tinfo = NULL, *iter; struct bpf_link_primer link_primer; - struct bpf_iter_target_info *tinfo; + union bpf_iter_link_info linfo; struct bpf_iter_link *link; - bool existed = false; - u32 prog_btf_id; + u32 prog_btf_id, linfo_len; + bpfptr_t ulinfo; int err; if (attr->link_create.target_fd || attr->link_create.flags) return -EINVAL; + memset(&linfo, 0, sizeof(union bpf_iter_link_info)); + + ulinfo = make_bpfptr(attr->link_create.iter_info, uattr.is_kernel); + linfo_len = attr->link_create.iter_info_len; + if (bpfptr_is_null(ulinfo) ^ !linfo_len) + return -EINVAL; + + if (!bpfptr_is_null(ulinfo)) { + err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo), + linfo_len); + if (err) + return err; + linfo_len = min_t(u32, linfo_len, sizeof(linfo)); + if (copy_from_bpfptr(&linfo, ulinfo, linfo_len)) + return -EFAULT; + } + prog_btf_id = prog->aux->attach_btf_id; mutex_lock(&targets_mutex); - list_for_each_entry(tinfo, &targets, list) { - if (tinfo->btf_id == prog_btf_id) { - existed = true; + list_for_each_entry(iter, &targets, list) { + if (iter->btf_id == prog_btf_id) { + tinfo = iter; break; } } mutex_unlock(&targets_mutex); - if (!existed) + if (!tinfo) return -ENOENT; + /* Only allow sleepable program for resched-able iterator */ + if (prog->sleepable && !bpf_iter_target_support_resched(tinfo)) + return -EINVAL; + link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); if (!link) return -ENOMEM; @@ -397,27 +557,38 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); link->tinfo = tinfo; - err = bpf_link_prime(&link->link, &link_primer); + err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); return err; } + if (tinfo->reg_info->attach_target) { + err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux); + if (err) { + bpf_link_cleanup(&link_primer); + return err; + } + } + return bpf_link_settle(&link_primer); } static void init_seq_meta(struct bpf_iter_priv_data *priv_data, struct bpf_iter_target_info *tinfo, + const struct bpf_iter_seq_info *seq_info, struct bpf_prog *prog) { priv_data->tinfo = tinfo; + priv_data->seq_info = seq_info; priv_data->prog = prog; priv_data->session_id = atomic64_inc_return(&session_id); priv_data->seq_num = 0; priv_data->done_stop = false; } -static int prepare_seq_file(struct file *file, struct bpf_iter_link *link) +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, + const struct bpf_iter_seq_info *seq_info) { struct bpf_iter_priv_data *priv_data; struct bpf_iter_target_info *tinfo; @@ -433,21 +604,21 @@ static int prepare_seq_file(struct file *file, struct bpf_iter_link *link) tinfo = link->tinfo; total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) + - tinfo->reg_info->seq_priv_size; - priv_data = __seq_open_private(file, tinfo->reg_info->seq_ops, + seq_info->seq_priv_size; + priv_data = __seq_open_private(file, seq_info->seq_ops, total_priv_dsize); if (!priv_data) { err = -ENOMEM; goto release_prog; } - if (tinfo->reg_info->init_seq_private) { - err = tinfo->reg_info->init_seq_private(priv_data->target_private); + if (seq_info->init_seq_private) { + err = seq_info->init_seq_private(priv_data->target_private, &link->aux); if (err) goto release_seq_file; } - init_seq_meta(priv_data, tinfo, prog); + init_seq_meta(priv_data, tinfo, seq_info, prog); seq = file->private_data; seq->private = priv_data->target_private; @@ -463,6 +634,7 @@ 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; @@ -481,8 +653,8 @@ int bpf_iter_new_fd(struct bpf_link *link) goto free_fd; } - err = prepare_seq_file(file, - container_of(link, struct bpf_iter_link, link)); + iter_link = container_of(link, struct bpf_iter_link, link); + err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link)); if (err) goto free_file; @@ -521,13 +693,27 @@ struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop) int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) { + struct bpf_run_ctx run_ctx, *old_run_ctx; int ret; - rcu_read_lock(); - migrate_disable(); - ret = BPF_PROG_RUN(prog, ctx); - migrate_enable(); - rcu_read_unlock(); + if (prog->sleepable) { + rcu_read_lock_trace(); + migrate_disable(); + might_fault(); + 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_trace(); + } else { + rcu_read_lock(); + migrate_disable(); + 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(); + } /* bpf program can only return 0 or 1: * 0 : okay @@ -537,3 +723,121 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) */ return ret == 0 ? 0 : -EAGAIN; } + +BPF_CALL_4(bpf_for_each_map_elem, struct bpf_map *, map, void *, callback_fn, + void *, callback_ctx, u64, flags) +{ + return map->ops->map_for_each_callback(map, callback_fn, callback_ctx, flags); +} + +const struct bpf_func_proto bpf_for_each_map_elem_proto = { + .func = bpf_for_each_map_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_FUNC, + .arg3_type = ARG_PTR_TO_STACK_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx, + u64, flags) +{ + bpf_callback_t callback = (bpf_callback_t)callback_fn; + u64 ret; + u32 i; + + /* Note: these safety checks are also verified when bpf_loop + * is inlined, be careful to modify this code in sync. See + * function verifier.c:inline_bpf_loop. + */ + if (flags) + return -EINVAL; + if (nr_loops > BPF_MAX_LOOPS) + return -E2BIG; + + for (i = 0; i < nr_loops; i++) { + ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0); + /* return value: 0 - continue, 1 - stop and return */ + if (ret) + return i + 1; + } + + return i; +} + +const struct bpf_func_proto bpf_loop_proto = { + .func = bpf_loop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_FUNC, + .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 new file mode 100644 index 000000000000..fa56c30833ff --- /dev/null +++ b/kernel/bpf/bpf_local_storage.c @@ -0,0 +1,930 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <linux/btf_ids.h> +#include <linux/bpf_local_storage.h> +#include <net/sock.h> +#include <uapi/linux/sock_diag.h> +#include <uapi/linux/btf.h> +#include <linux/rcupdate.h> +#include <linux/rcupdate_trace.h> +#include <linux/rcupdate_wait.h> + +#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) + +static struct bpf_local_storage_map_bucket * +select_bucket(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) +{ + return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; +} + +static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) +{ + struct bpf_map *map = &smap->map; + + if (!map->ops->map_local_storage_charge) + return 0; + + return map->ops->map_local_storage_charge(smap, owner, size); +} + +static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, + u32 size) +{ + struct bpf_map *map = &smap->map; + + if (map->ops->map_local_storage_uncharge) + map->ops->map_local_storage_uncharge(smap, owner, size); +} + +static struct bpf_local_storage __rcu ** +owner_storage(struct bpf_local_storage_map *smap, void *owner) +{ + struct bpf_map *map = &smap->map; + + 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); +} + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, + void *value, bool charge_mem, bool swap_uptrs, gfp_t gfp_flags) +{ + struct bpf_local_storage_elem *selem; + + if (charge_mem && mem_charge(smap, owner, smap->elem_size)) + return NULL; + + if (smap->bpf_ma) { + selem = bpf_mem_cache_alloc_flags(&smap->selem_ma, gfp_flags); + if (selem) + /* Keep the original bpf_map_kzalloc behavior + * before started using the bpf_mem_cache_alloc. + * + * No need to use zero_map_value. The bpf_selem_free() + * only does bpf_mem_cache_free when there is + * no other bpf prog is using the selem. + */ + memset(SDATA(selem)->data, 0, smap->map.value_size); + } else { + selem = bpf_map_kzalloc(&smap->map, smap->elem_size, + gfp_flags | __GFP_NOWARN); + } + + if (selem) { + 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); + + return NULL; +} + +/* rcu tasks trace callback for bpf_ma == false */ +static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage *local_storage; + + /* If RCU Tasks Trace grace period implies RCU grace period, do + * kfree(), else do kfree_rcu(). + */ + local_storage = container_of(rcu, struct bpf_local_storage, rcu); + if (rcu_trace_implies_rcu_gp()) + kfree(local_storage); + else + kfree_rcu(local_storage, 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); + bpf_mem_cache_raw_free(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); +} + +/* Handle bpf_ma == 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(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool bpf_ma, bool reuse_now) +{ + if (!local_storage) + return; + + if (!bpf_ma) { + __bpf_local_storage_free(local_storage, reuse_now); + return; + } + + if (!reuse_now) { + call_rcu_tasks_trace(&local_storage->rcu, + bpf_local_storage_free_trace_rcu); + return; + } + + if (smap) + bpf_mem_cache_free(&smap->storage_ma, local_storage); + else + /* smap could be NULL if the selem that triggered + * this 'local_storage' creation had been long gone. + * In this case, directly do call_rcu(). + */ + call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu); +} + +/* rcu tasks trace callback for bpf_ma == false */ +static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage_elem *selem; + + selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + if (rcu_trace_implies_rcu_gp()) + kfree(selem); + else + kfree_rcu(selem, rcu); +} + +/* Handle bpf_ma == 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(); + bpf_mem_cache_raw_free(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, + struct bpf_local_storage_map *smap, + bool reuse_now) +{ + if (!smap->bpf_ma) { + /* Only task storage has uptrs and task storage + * has moved to bpf_mem_alloc. Meaning smap->bpf_ma == true + * for task storage, so this bpf_obj_free_fields() won't unpin + * any uptr. + */ + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + __bpf_selem_free(selem, reuse_now); + return; + } + + if (reuse_now) { + /* reuse_now == true only happens when the storage owner + * (e.g. task_struct) is being destructed or the map itself + * is being destructed (ie map_free). In both cases, + * no bpf prog can have a hold on the selem. It is + * safe to unpin the uptrs and free the selem now. + */ + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + /* Instead of using the vanilla call_rcu(), + * bpf_mem_cache_free will be able to reuse selem + * immediately. + */ + bpf_mem_cache_free(&smap->selem_ma, selem); + 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 bpf_local_storage_map *smap; + 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) { + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); + bpf_selem_free(selem, smap, 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, struct hlist_head *free_selem_list) +{ + struct bpf_local_storage_map *smap; + bool free_local_storage; + void *owner; + + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); + owner = local_storage->owner; + + /* All uncharging on the owner must be done first. + * The owner may be freed once the last selem is unlinked + * from local_storage. + */ + if (uncharge_mem) + mem_uncharge(smap, owner, smap->elem_size); + + free_local_storage = hlist_is_singular_node(&selem->snode, + &local_storage->list); + if (free_local_storage) { + mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); + local_storage->owner = NULL; + + /* After this RCU_INIT, owner may be freed and cannot be used */ + RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); + + /* local_storage is not freed now. local_storage->lock is + * still held and raw_spin_unlock_bh(&local_storage->lock) + * will be done by the caller. + * + * Although the unlock will be done under + * rcu_read_lock(), it is more intuitive to + * read if the freeing of the storage is done + * after the raw_spin_unlock_bh(&local_storage->lock). + * + * Hence, a "bool free_local_storage" is returned + * to the caller which then calls then frees the storage after + * all the RCU grace periods have expired. + */ + } + hlist_del_init_rcu(&selem->snode); + if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == + SDATA(selem)) + RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); + + 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 bool check_storage_bpf_ma(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *storage_smap, + struct bpf_local_storage_elem *selem) +{ + + struct bpf_local_storage_map *selem_smap; + + /* local_storage->smap may be NULL. If it is, get the bpf_ma + * from any selem in the local_storage->list. The bpf_ma of all + * local_storage and selem should have the same value + * for the same map type. + * + * If the local_storage->list is already empty, the caller will not + * care about the bpf_ma value also because the caller is not + * responsible to free the local_storage. + */ + + if (storage_smap) + return storage_smap->bpf_ma; + + if (!selem) { + struct hlist_node *n; + + n = rcu_dereference_check(hlist_first_rcu(&local_storage->list), + bpf_rcu_lock_held()); + if (!n) + return false; + + selem = hlist_entry(n, struct bpf_local_storage_elem, snode); + } + selem_smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); + + return selem_smap->bpf_ma; +} + +static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, + bool reuse_now) +{ + struct bpf_local_storage_map *storage_smap; + struct bpf_local_storage *local_storage; + bool bpf_ma, free_local_storage = false; + HLIST_HEAD(selem_free_list); + unsigned long flags; + + 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()); + storage_smap = rcu_dereference_check(local_storage->smap, + bpf_rcu_lock_held()); + bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, selem); + + 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, &selem_free_list); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); + + bpf_selem_free_list(&selem_free_list, reuse_now); + + if (free_local_storage) + bpf_local_storage_free(local_storage, storage_smap, bpf_ma, reuse_now); +} + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem) +{ + RCU_INIT_POINTER(selem->local_storage, local_storage); + hlist_add_head_rcu(&selem->snode, &local_storage->list); +} + +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_lockless(selem))) + /* selem has already be unlinked from smap */ + return; + + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); + b = select_bucket(smap, selem); + raw_spin_lock_irqsave(&b->lock, flags); + if (likely(selem_linked_to_map(selem))) + hlist_del_init_rcu(&selem->map_node); + raw_spin_unlock_irqrestore(&b->lock, flags); +} + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) +{ + struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); + 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 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, reuse_now); +} + +void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) +{ + 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(selem)); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); +} + +static int check_flags(const struct bpf_local_storage_data *old_sdata, + u64 map_flags) +{ + if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) + /* elem already exists */ + return -EEXIST; + + if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) + /* elem doesn't exist, cannot update it */ + return -ENOENT; + + return 0; +} + +int bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem, + gfp_t gfp_flags) +{ + struct bpf_local_storage *prev_storage, *storage; + struct bpf_local_storage **owner_storage_ptr; + int err; + + err = mem_charge(smap, owner, sizeof(*storage)); + if (err) + return err; + + if (smap->bpf_ma) + storage = bpf_mem_cache_alloc_flags(&smap->storage_ma, gfp_flags); + 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; + + bpf_selem_link_storage_nolock(storage, first_selem); + bpf_selem_link_map(smap, first_selem); + + owner_storage_ptr = + (struct bpf_local_storage **)owner_storage(smap, owner); + /* Publish storage to the owner. + * Instead of using any lock of the kernel object (i.e. owner), + * cmpxchg will work with any kernel object regardless what + * the running context is, bh, irq...etc. + * + * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) + * is protected by the storage->lock. Hence, when freeing + * the owner->storage, the storage->lock must be held before + * setting owner->storage ptr to NULL. + */ + prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); + if (unlikely(prev_storage)) { + 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: + bpf_local_storage_free(storage, smap, smap->bpf_ma, true); + mem_uncharge(smap, owner, sizeof(*storage)); + return err; +} + +/* sk cannot be going away because it is linking new elem + * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). + * Otherwise, it will become a leak (and other memory issues + * during map destruction). + */ +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + 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 *alloc_selem, *selem = NULL; + struct bpf_local_storage *local_storage; + HLIST_HEAD(old_selem_free_list); + unsigned long flags; + int err; + + /* BPF_EXIST and BPF_NOEXIST cannot be both set */ + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || + /* BPF_F_LOCK can only be used in a value with spin_lock */ + unlikely((map_flags & BPF_F_LOCK) && + !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) + return ERR_PTR(-EINVAL); + + if (gfp_flags == GFP_KERNEL && (map_flags & ~BPF_F_LOCK) != BPF_NOEXIST) + return ERR_PTR(-EINVAL); + + local_storage = rcu_dereference_check(*owner_storage(smap, owner), + bpf_rcu_lock_held()); + if (!local_storage || hlist_empty(&local_storage->list)) { + /* Very first elem for the owner */ + err = check_flags(NULL, map_flags); + if (err) + return ERR_PTR(err); + + selem = bpf_selem_alloc(smap, owner, value, true, swap_uptrs, gfp_flags); + if (!selem) + return ERR_PTR(-ENOMEM); + + err = bpf_local_storage_alloc(owner, smap, selem, gfp_flags); + if (err) { + bpf_selem_free(selem, smap, true); + mem_uncharge(smap, owner, smap->elem_size); + return ERR_PTR(err); + } + + return SDATA(selem); + } + + if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { + /* Hoping to find an old_sdata to do inline update + * such that it can avoid taking the local_storage->lock + * and changing the lists. + */ + old_sdata = + bpf_local_storage_lookup(local_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + return ERR_PTR(err); + 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; + } + } + + /* 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, true, swap_uptrs, gfp_flags); + if (!alloc_selem) + return ERR_PTR(-ENOMEM); + + raw_spin_lock_irqsave(&local_storage->lock, flags); + + /* Recheck local_storage->list under local_storage->lock */ + if (unlikely(hlist_empty(&local_storage->list))) { + /* A parallel del is happening and local_storage is going + * away. It has just been checked before, so very + * unlikely. Return instead of retry to keep things + * simple. + */ + err = -EAGAIN; + goto unlock; + } + + old_sdata = bpf_local_storage_lookup(local_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + goto unlock; + + if (old_sdata && (map_flags & BPF_F_LOCK)) { + copy_map_value_locked(&smap->map, old_sdata->data, value, + false); + selem = SELEM(old_sdata); + goto unlock; + } + + alloc_selem = NULL; + /* First, link the new selem to the map */ + bpf_selem_link_map(smap, selem); + + /* Second, link (and publish) the new selem to local_storage */ + bpf_selem_link_storage_nolock(local_storage, selem); + + /* Third, remove old selem, SELEM(old_sdata) */ + if (old_sdata) { + bpf_selem_unlink_map(SELEM(old_sdata)); + bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), + true, &old_selem_free_list); + } + +unlock: + raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_selem_free_list(&old_selem_free_list, false); + if (alloc_selem) { + mem_uncharge(smap, owner, smap->elem_size); + bpf_selem_free(alloc_selem, smap, true); + } + return err ? ERR_PTR(err) : SDATA(selem); +} + +static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) +{ + u64 min_usage = U64_MAX; + u16 i, res = 0; + + spin_lock(&cache->idx_lock); + + for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { + if (cache->idx_usage_counts[i] < min_usage) { + min_usage = cache->idx_usage_counts[i]; + res = i; + + /* Found a free cache_idx */ + if (!min_usage) + break; + } + } + cache->idx_usage_counts[res]++; + + spin_unlock(&cache->idx_lock); + + return res; +} + +static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx) +{ + spin_lock(&cache->idx_lock); + cache->idx_usage_counts[idx]--; + spin_unlock(&cache->idx_lock); +} + +int bpf_local_storage_map_alloc_check(union bpf_attr *attr) +{ + if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || + !(attr->map_flags & BPF_F_NO_PREALLOC) || + attr->max_entries || + attr->key_size != sizeof(int) || !attr->value_size || + /* Enforce BTF for userspace sk dumping */ + !attr->btf_key_type_id || !attr->btf_value_type_id) + return -EINVAL; + + if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) + return -E2BIG; + + return 0; +} + +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)) + return -EINVAL; + + return 0; +} + +void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) +{ + struct bpf_local_storage_map *storage_smap; + struct bpf_local_storage_elem *selem; + bool bpf_ma, free_storage = false; + HLIST_HEAD(free_selem_list); + struct hlist_node *n; + unsigned long flags; + + storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); + bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, NULL); + + /* Neither the bpf_prog nor the bpf_map's syscall + * could be modifying the local_storage->list now. + * Thus, no elem can be added to or deleted from the + * local_storage->list by the bpf_prog or by the bpf_map's syscall. + * + * It is racing with bpf_local_storage_map_free() alone + * 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. + */ + bpf_selem_unlink_map(selem); + /* If local_storage list has only one element, the + * bpf_selem_unlink_storage_nolock() will return true. + * Otherwise, it will return false. The current loop iteration + * intends to remove all local storage. So the last iteration + * of the loop will set the free_cgroup_storage to true. + */ + free_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, true, &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, storage_smap, bpf_ma, 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); + + /* The dynamically callocated selems are not counted currently. */ + usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); + return usage; +} + +/* When bpf_ma == true, the bpf_mem_alloc is used to allocate and free memory. + * A deadlock free allocator is useful for storage that the bpf prog can easily + * get a hold of the owner PTR_TO_BTF_ID in any context. eg. bpf_get_current_task_btf. + * The task and cgroup storage fall into this case. The bpf_mem_alloc reuses + * memory immediately. To be reuse-immediate safe, the owner destruction + * code path needs to go through a rcu grace period before calling + * bpf_local_storage_destroy(). + * + * When bpf_ma == false, the kmalloc and kfree are used. + */ +struct bpf_map * +bpf_local_storage_map_alloc(union bpf_attr *attr, + struct bpf_local_storage_cache *cache, + bool bpf_ma) +{ + struct bpf_local_storage_map *smap; + unsigned int i; + u32 nbuckets; + int err; + + 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 + * bpf_mem_alloc when CONFIG_PREEMPT_RT is enabled. + */ + smap->bpf_ma = IS_ENABLED(CONFIG_PREEMPT_RT) ? true : bpf_ma; + if (smap->bpf_ma) { + err = bpf_mem_alloc_init(&smap->selem_ma, smap->elem_size, false); + if (err) + goto free_smap; + + err = bpf_mem_alloc_init(&smap->storage_ma, sizeof(struct bpf_local_storage), false); + if (err) { + bpf_mem_alloc_destroy(&smap->selem_ma); + goto free_smap; + } + } + + 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, + struct bpf_local_storage_cache *cache, + int __percpu *busy_counter) +{ + struct bpf_local_storage_map_bucket *b; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; + unsigned int i; + + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(cache, smap->cache_idx); + + /* Note that this map might be concurrently cloned from + * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone + * RCU read section to finish before proceeding. New RCU + * read sections should be prevented via bpf_map_inc_not_zero. + */ + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the owner->storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or when the storage is freed e.g. + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_local_storage_elem, map_node))) { + if (busy_counter) + this_cpu_inc(*busy_counter); + bpf_selem_unlink(selem, true); + if (busy_counter) + this_cpu_dec(*busy_counter); + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* While freeing the storage we may still need to access the map. + * + * e.g. when bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exit immediately. + * + * However, while freeing the storage one still needs to access the + * smap->elem_size to do the uncharging in + * bpf_selem_unlink_storage_nolock(). + * + * Hence, wait another rcu grace period for the storage to be freed. + */ + synchronize_rcu(); + + if (smap->bpf_ma) { + rcu_barrier_tasks_trace(); + if (!rcu_trace_implies_rcu_gp()) + rcu_barrier(); + bpf_mem_alloc_destroy(&smap->selem_ma); + bpf_mem_alloc_destroy(&smap->storage_ma); + } + 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 1b6b9349cb85..3dabdd137d10 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -41,7 +41,12 @@ 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 +94,7 @@ 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 +115,7 @@ 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. @@ -353,7 +358,7 @@ 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 +424,7 @@ 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); } @@ -502,13 +507,14 @@ struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash) static void bpf_common_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { + u8 node_type = READ_ONCE(node->type); unsigned long flags; - if (WARN_ON_ONCE(node->type == BPF_LRU_LIST_T_FREE) || - WARN_ON_ONCE(node->type == BPF_LRU_LOCAL_LIST_T_FREE)) + if (WARN_ON_ONCE(node_type == BPF_LRU_LIST_T_FREE) || + WARN_ON_ONCE(node_type == BPF_LRU_LOCAL_LIST_T_FREE)) return; - if (node->type == BPF_LRU_LOCAL_LIST_T_PENDING) { + if (node_type == BPF_LRU_LOCAL_LIST_T_PENDING) { struct bpf_lru_locallist *loc_l; loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu); @@ -521,7 +527,7 @@ 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); @@ -567,7 +573,7 @@ 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; } @@ -593,7 +599,7 @@ 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 6b12f06ee18c..cbd8d3720c2b 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -4,6 +4,7 @@ #ifndef __BPF_LRU_LIST_H_ #define __BPF_LRU_LIST_H_ +#include <linux/cache.h> #include <linux/list.h> #include <linux/spinlock_types.h> @@ -63,11 +64,8 @@ struct bpf_lru { 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, @@ -77,6 +75,5 @@ 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 fb278144e9fd..967492b65185 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -7,10 +7,15 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/btf.h> +#include <linux/binfmts.h> #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> +#include <linux/ima.h> +#include <linux/bpf-cgroup.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -24,31 +29,417 @@ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ #include <linux/lsm_hook_defs.h> #undef LSM_HOOK -#define BPF_LSM_SYM_PREFX "bpf_lsm_" +#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) +BTF_SET_START(bpf_lsm_hooks) +#include <linux/lsm_hook_defs.h> +#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_SET_END(bpf_lsm_disabled_hooks) + +/* List of LSM hooks that should operate on 'current' cgroup regardless + * of function signature. + */ +BTF_SET_START(bpf_lsm_current_hooks) +/* operate on freshly allocated sk without any cgroup association */ +#ifdef CONFIG_SECURITY_NETWORK +BTF_ID(func, bpf_lsm_sk_alloc_security) +BTF_ID(func, bpf_lsm_sk_free_security) +#endif +BTF_SET_END(bpf_lsm_current_hooks) + +/* List of LSM hooks that trigger while the socket is properly locked. + */ +BTF_SET_START(bpf_lsm_locked_sockopt_hooks) +#ifdef CONFIG_SECURITY_NETWORK +BTF_ID(func, bpf_lsm_sock_graft) +BTF_ID(func, bpf_lsm_inet_csk_clone) +BTF_ID(func, bpf_lsm_inet_conn_established) +#endif +BTF_SET_END(bpf_lsm_locked_sockopt_hooks) + +/* List of LSM hooks that trigger while the socket is _not_ locked, + * but it's ok to call bpf_{g,s}etsockopt because the socket is still + * in the early init phase. + */ +BTF_SET_START(bpf_lsm_unlocked_sockopt_hooks) +#ifdef CONFIG_SECURITY_NETWORK +BTF_ID(func, bpf_lsm_socket_post_create) +BTF_ID(func, bpf_lsm_socket_socketpair) +#endif +BTF_SET_END(bpf_lsm_unlocked_sockopt_hooks) + +#ifdef CONFIG_CGROUP_BPF +void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, + bpf_func_t *bpf_func) +{ + const struct btf_param *args __maybe_unused; + + if (btf_type_vlen(prog->aux->attach_func_proto) < 1 || + btf_id_set_contains(&bpf_lsm_current_hooks, + prog->aux->attach_btf_id)) { + *bpf_func = __cgroup_bpf_run_lsm_current; + return; + } + +#ifdef CONFIG_NET + args = btf_params(prog->aux->attach_func_proto); + + if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCKET]) + *bpf_func = __cgroup_bpf_run_lsm_socket; + else if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCK]) + *bpf_func = __cgroup_bpf_run_lsm_sock; + else +#endif + *bpf_func = __cgroup_bpf_run_lsm_current; +} +#endif 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 (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name, - sizeof(BPF_LSM_SYM_PREFX) - 1)) { + 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; } return 0; } +/* Mask for all the currently supported BPRM option flags */ +#define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC + +BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) +{ + if (flags & ~BPF_F_BRPM_OPTS_MASK) + return -EINVAL; + + bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) + +static const struct bpf_func_proto bpf_bprm_opts_set_proto = { + .func = bpf_bprm_opts_set, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) +{ + return ima_inode_hash(inode, dst, size); +} + +static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) +{ + return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); +} + +BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) + +static const struct bpf_func_proto bpf_ima_inode_hash_proto = { + .func = bpf_ima_inode_hash, + .gpl_only = false, + .might_sleep = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, + .allowed = bpf_ima_inode_hash_allowed, +}; + +BPF_CALL_3(bpf_ima_file_hash, struct file *, file, void *, dst, u32, size) +{ + return ima_file_hash(file, dst, size); +} + +BTF_ID_LIST_SINGLE(bpf_ima_file_hash_btf_ids, struct, file) + +static const struct bpf_func_proto bpf_ima_file_hash_proto = { + .func = bpf_ima_file_hash, + .gpl_only = false, + .might_sleep = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_ima_file_hash_btf_ids[0], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, + .allowed = bpf_ima_inode_hash_allowed, +}; + +BPF_CALL_1(bpf_get_attach_cookie, void *, ctx) +{ + struct bpf_trace_run_ctx *run_ctx; + + run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); + return run_ctx->bpf_cookie; +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto = { + .func = bpf_get_attach_cookie, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +static const struct bpf_func_proto * +bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + const struct bpf_func_proto *func_proto; + + if (prog->expected_attach_type == BPF_LSM_CGROUP) { + func_proto = cgroup_common_func_proto(func_id, prog); + if (func_proto) + return func_proto; + } + + switch (func_id) { + case BPF_FUNC_inode_storage_get: + return &bpf_inode_storage_get_proto; + case BPF_FUNC_inode_storage_delete: + return &bpf_inode_storage_delete_proto; +#ifdef CONFIG_NET + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; +#endif /* CONFIG_NET */ + case BPF_FUNC_spin_lock: + return &bpf_spin_lock_proto; + case BPF_FUNC_spin_unlock: + return &bpf_spin_unlock_proto; + case BPF_FUNC_bprm_opts_set: + return &bpf_bprm_opts_set_proto; + case BPF_FUNC_ima_inode_hash: + return &bpf_ima_inode_hash_proto; + case BPF_FUNC_ima_file_hash: + return &bpf_ima_file_hash_proto; + case BPF_FUNC_get_attach_cookie: + return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL; +#ifdef CONFIG_NET + case BPF_FUNC_setsockopt: + if (prog->expected_attach_type != BPF_LSM_CGROUP) + return NULL; + if (btf_id_set_contains(&bpf_lsm_locked_sockopt_hooks, + prog->aux->attach_btf_id)) + return &bpf_sk_setsockopt_proto; + if (btf_id_set_contains(&bpf_lsm_unlocked_sockopt_hooks, + prog->aux->attach_btf_id)) + return &bpf_unlocked_sk_setsockopt_proto; + return NULL; + case BPF_FUNC_getsockopt: + if (prog->expected_attach_type != BPF_LSM_CGROUP) + return NULL; + if (btf_id_set_contains(&bpf_lsm_locked_sockopt_hooks, + prog->aux->attach_btf_id)) + return &bpf_sk_getsockopt_proto; + if (btf_id_set_contains(&bpf_lsm_unlocked_sockopt_hooks, + prog->aux->attach_btf_id)) + return &bpf_unlocked_sk_getsockopt_proto; + return NULL; +#endif + default: + return tracing_prog_func_proto(func_id, prog); + } +} + +/* The set of hooks which are called without pagefaults disabled and are allowed + * to "sleep" and thus can be used for sleepable BPF programs. + */ +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_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) +BTF_ID(func, bpf_lsm_bprm_creds_for_exec) +BTF_ID(func, bpf_lsm_bprm_creds_from_file) +BTF_ID(func, bpf_lsm_capget) +BTF_ID(func, bpf_lsm_capset) +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) + +BTF_ID(func, bpf_lsm_inode_create) +BTF_ID(func, bpf_lsm_inode_free_security) +BTF_ID(func, bpf_lsm_inode_getattr) +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_readlink) +BTF_ID(func, bpf_lsm_inode_rename) +BTF_ID(func, bpf_lsm_inode_rmdir) +BTF_ID(func, bpf_lsm_inode_setattr) +BTF_ID(func, bpf_lsm_inode_setxattr) +BTF_ID(func, bpf_lsm_inode_symlink) +BTF_ID(func, bpf_lsm_inode_unlink) +BTF_ID(func, bpf_lsm_kernel_module_request) +BTF_ID(func, bpf_lsm_kernel_read_file) +BTF_ID(func, bpf_lsm_kernfs_init_security) + +#ifdef CONFIG_SECURITY_PATH +BTF_ID(func, bpf_lsm_path_unlink) +BTF_ID(func, bpf_lsm_path_mkdir) +BTF_ID(func, bpf_lsm_path_rmdir) +BTF_ID(func, bpf_lsm_path_truncate) +BTF_ID(func, bpf_lsm_path_symlink) +BTF_ID(func, bpf_lsm_path_link) +BTF_ID(func, bpf_lsm_path_rename) +BTF_ID(func, bpf_lsm_path_chmod) +BTF_ID(func, bpf_lsm_path_chown) +#endif /* CONFIG_SECURITY_PATH */ + +BTF_ID(func, bpf_lsm_mmap_file) +BTF_ID(func, bpf_lsm_netlink_send) +BTF_ID(func, bpf_lsm_path_notify) +BTF_ID(func, bpf_lsm_release_secctx) +BTF_ID(func, bpf_lsm_sb_alloc_security) +BTF_ID(func, bpf_lsm_sb_eat_lsm_opts) +BTF_ID(func, bpf_lsm_sb_kern_mount) +BTF_ID(func, bpf_lsm_sb_mount) +BTF_ID(func, bpf_lsm_sb_remount) +BTF_ID(func, bpf_lsm_sb_set_mnt_opts) +BTF_ID(func, bpf_lsm_sb_show_options) +BTF_ID(func, bpf_lsm_sb_statfs) +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) +BTF_ID(func, bpf_lsm_socket_create) +BTF_ID(func, bpf_lsm_socket_getpeername) +BTF_ID(func, bpf_lsm_socket_getpeersec_dgram) +BTF_ID(func, bpf_lsm_socket_getsockname) +BTF_ID(func, bpf_lsm_socket_getsockopt) +BTF_ID(func, bpf_lsm_socket_listen) +BTF_ID(func, bpf_lsm_socket_post_create) +BTF_ID(func, bpf_lsm_socket_recvmsg) +BTF_ID(func, bpf_lsm_socket_sendmsg) +BTF_ID(func, bpf_lsm_socket_shutdown) +BTF_ID(func, bpf_lsm_socket_socketpair) +#endif /* CONFIG_SECURITY_NETWORK */ + +BTF_ID(func, bpf_lsm_syslog) +BTF_ID(func, bpf_lsm_task_alloc) +BTF_ID(func, bpf_lsm_task_prctl) +BTF_ID(func, bpf_lsm_task_setscheduler) +BTF_ID(func, bpf_lsm_task_to_inode) +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) +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 +BTF_ID(func, bpf_lsm_sk_alloc_security) +BTF_ID(func, bpf_lsm_sk_free_security) +#endif /* CONFIG_SECURITY_NETWORK */ +BTF_ID(func, bpf_lsm_task_free) +BTF_SET_END(untrusted_lsm_hooks) + +bool bpf_lsm_is_sleepable_hook(u32 btf_id) +{ + return btf_id_set_contains(&sleepable_lsm_hooks, btf_id); +} + +bool bpf_lsm_is_trusted(const struct bpf_prog *prog) +{ + return !btf_id_set_contains(&untrusted_lsm_hooks, prog->aux->attach_btf_id); +} + const struct bpf_prog_ops lsm_prog_ops = { }; const struct bpf_verifier_ops lsm_verifier_ops = { - .get_func_proto = tracing_prog_func_proto, + .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 c6b0decaa46a..040fb1cd840b 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -10,38 +10,37 @@ #include <linux/seq_file.h> #include <linux/refcount.h> #include <linux/mutex.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/btf_ids.h> +#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; - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; /* protect map_update */ struct mutex lock; - /* progs has all the bpf_prog that is populated + /* link has all the bpf_links that is populated * to the func ptr of the kernel's struct * (in kvalue.data). */ - struct bpf_prog **progs; - /* image is a page that has all the trampolines + struct bpf_link **links; + /* 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 - * "progs[]". */ - 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, @@ -56,176 +55,396 @@ 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 = { }; const struct bpf_prog_ops bpf_struct_ops_prog_ops = { +#ifdef CONFIG_NET + .test_run = bpf_struct_ops_test_run, +#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); - continue; - } - sprintf(value_name, "%s%s", VALUE_PREFIX, 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); + } +} - 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); +#define MAYBE_NULL_SUFFIX "__nullable" +#define MAX_STUB_NAME 128 + +/* Return the type info of a stub function, if it exists. + * + * The name of a stub function is made up of the name of the struct_ops and + * the name of the function pointer member, separated by "__". For example, + * if the struct_ops type is named "foo_ops" and the function pointer + * member is named "bar", the stub function name would be "foo_ops__bar". + */ +static const struct btf_type * +find_stub_func_proto(const struct btf *btf, const char *st_op_name, + const char *member_name) +{ + char stub_func_name[MAX_STUB_NAME]; + const struct btf_type *func_type; + s32 btf_id; + int cp; + + cp = snprintf(stub_func_name, MAX_STUB_NAME, "%s__%s", + st_op_name, member_name); + if (cp >= MAX_STUB_NAME) { + pr_warn("Stub function name too long\n"); + return NULL; + } + btf_id = btf_find_by_name_kind(btf, stub_func_name, BTF_KIND_FUNC); + if (btf_id < 0) + return NULL; + func_type = btf_type_by_id(btf, btf_id); + if (!func_type) + return NULL; + + return btf_type_by_id(btf, func_type->type); /* FUNC_PROTO */ +} + +/* 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, + struct bpf_struct_ops_arg_info *arg_info) +{ + const struct btf_type *stub_func_proto, *pointed_type; + const struct btf_param *stub_args, *args; + struct bpf_ctx_arg_aux *info, *info_buf; + u32 nargs, arg_no, info_cnt = 0; + u32 arg_btf_id; + int offset; + + stub_func_proto = find_stub_func_proto(btf, st_ops_name, member_name); + if (!stub_func_proto) + return 0; + + /* 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__%s does not match the number of arguments of the member %s of struct %s\n", + st_ops_name, member_name, 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". + */ + if (!btf_param_match_suffix(btf, &stub_args[arg_no], + MAYBE_NULL_SUFFIX)) 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__%s has %s tagging to an unsupported type\n", + st_ops_name, member_name, MAYBE_NULL_SUFFIX); + 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; + offset = btf_ctx_arg_offset(btf, func_proto, arg_no); + if (offset < 0) { + pr_warn("stub function %s__%s has an invalid trampoline ctx offset for arg#%u\n", + st_ops_name, member_name, arg_no); + 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; + + if (args[arg_no].type != stub_args[arg_no].type) { + pr_warn("arg#%u type in stub function %s__%s does not match with its original func_proto\n", + arg_no, st_ops_name, member_name); + goto err_out; } - for_each_member(j, t, member) { - const struct btf_type *func_proto; + /* Fill the information of the new argument */ + info->reg_type = + PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; + info->btf_id = arg_btf_id; + info->btf = btf; + info->offset = offset; - 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; - } + info++; + info_cnt++; + } - 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; - } + if (info_cnt) { + arg_info->info = info_buf; + arg_info->cnt = info_cnt; + } else { + kfree(info_buf); + } - 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; - } - } + return 0; - 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); - } - } - } +err_out: + kfree(info_buf); + + 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; + + arg_info = st_ops_desc->arg_info; + for (i = 0; i < btf_type_vlen(st_ops_desc->type); i++) + kfree(arg_info[i].info); -static const struct bpf_struct_ops * -bpf_struct_ops_find_value(u32 value_id) + 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_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { - unsigned int i; + 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); + + if (!st_ops->cfi_stubs) { + pr_warn("struct_ops for %s has no cfi_stubs\n", st_ops->name); + return -EINVAL; + } + + 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; + + 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); + if (!func_proto) + continue; + + 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; + } + + err = prepare_arg_info(btf, st_ops->name, mname, + func_proto, + arg_info + i); + if (err) + goto errout; + } - 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->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + err = -EINVAL; + goto errout; } - return NULL; + 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, @@ -244,13 +463,14 @@ 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; @@ -259,10 +479,17 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, /* No lock is needed. state and refcnt do not need * to be updated together under atomic context. */ - uvalue = (struct bpf_struct_ops_value *)value; + 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; } @@ -274,32 +501,39 @@ 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->progs[i]) { - bpf_prog_put(st_map->progs[i]); - st_map->progs[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; const struct btf_type *mtype; for_each_member(i, t, member) { - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (moff > prev_mend && 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, - NULL, NULL); + 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; @@ -312,19 +546,129 @@ static int check_zero_holes(const struct btf_type *t, void *data) return 0; } -static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static void bpf_struct_ops_link_release(struct bpf_link *link) +{ +} + +static void bpf_struct_ops_link_dealloc(struct bpf_link *link) +{ + struct bpf_tramp_link *tlink = container_of(link, struct bpf_tramp_link, link); + + kfree(tlink); +} + +const struct bpf_link_ops bpf_struct_ops_link_lops = { + .release = bpf_struct_ops_link_release, + .dealloc = bpf_struct_ops_link_dealloc, +}; + +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, + struct bpf_tramp_link *link, + const struct btf_func_model *model, + void *stub_func, + void **_image, u32 *_image_off, + bool allow_alloc) +{ + 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; + + if (model->ret_size > 0) + flags |= BPF_TRAMP_F_RET_FENTRY_RET; + + size = arch_bpf_trampoline_size(model, flags, tlinks, NULL); + if (size <= 0) + return size ? : -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 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_progs *tprogs = 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; - 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; @@ -332,20 +676,20 @@ 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 = (struct bpf_struct_ops_value *)value; - err = check_zero_holes(t, uvalue->data); + uvalue = value; + 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; - tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); - if (!tprogs) + tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); + if (!tlinks) return -ENOMEM; uvalue = (struct bpf_struct_ops_value *)st_map->uvalue; @@ -353,7 +697,7 @@ 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; } @@ -362,15 +706,21 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; - image = st_map->image; + 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); + moff = __btf_member_bit_offset(t, member) / 8; + 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; @@ -395,9 +745,8 @@ 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, - NULL, NULL); + 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; @@ -421,80 +770,134 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, err = PTR_ERR(prog); goto reset_unlock; } - st_map->progs[i] = prog; 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; goto reset_unlock; } - tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; - tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; - err = arch_prepare_bpf_trampoline(image, - st_map->image + PAGE_SIZE, - &st_ops->func_models[i], 0, - tprogs, NULL); - if (err < 0) + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + bpf_prog_put(prog); + err = -ENOMEM; goto reset_unlock; + } + bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, + &bpf_struct_ops_link_lops, prog); + *plink++ = &link->link; - *(void **)(kdata + moff) = image; - image += err; + 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], + *(void **)(st_ops->cfi_stubs + moff), + &image, &image_off, + st_map->image_pages_cnt < MAX_TRAMP_IMAGE_PAGES); + if (err) + goto reset_unlock; + + 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_ro((long)st_map->image, 1); - set_memory_x((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; } - /* Error during st_ops->reg(). It is very unlikely since - * the above init_member() should have caught it earlier - * before reg(). The only possibility is if there was a race - * in registering the struct_ops (under the same name) to + /* Error during st_ops->reg(). Can happen if this struct_ops needs to be + * verified as a whole, after all init_member() calls. Can also happen if + * 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(tprogs); + 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; @@ -510,6 +913,7 @@ 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; @@ -519,98 +923,195 @@ 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->progs) + if (st_map->links) bpf_struct_ops_map_put_progs(st_map); - bpf_map_area_free(st_map->progs); - bpf_jit_free_exec(st_map->image); + if (st_map->ksyms) + bpf_struct_ops_map_free_ksyms(st_map); + bpf_map_area_free(st_map->links); + 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; - size_t map_total_size, st_map_size; + 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 bpf_map_memory mem; + struct module *mod = NULL; struct bpf_map *map; - int err; + 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 * struct bpf_struct_ops_tcp_congestions_ops */ (vt->size - sizeof(struct bpf_struct_ops_value)); - map_total_size = st_map_size + - /* uvalue */ - sizeof(vt->size) + - /* struct bpf_progs **progs */ - btf_type_vlen(t) * sizeof(struct bpf_prog *); - err = bpf_map_charge_init(&mem, map_total_size); - if (err < 0) - return ERR_PTR(err); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); if (!st_map) { - bpf_map_charge_finish(&mem); - return ERR_PTR(-ENOMEM); + 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->progs = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *), + st_map->funcs_cnt = count_func_ptrs(btf, t); + st_map->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->progs || !st_map->image) { - bpf_struct_ops_map_free(map); - bpf_map_charge_finish(&mem); - 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); - bpf_map_charge_move(&map->memory, &mem); 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) const struct bpf_map_ops bpf_struct_ops_map_ops = { .map_alloc_check = bpf_struct_ops_map_alloc_check, .map_alloc = bpf_struct_ops_map_alloc, @@ -620,6 +1121,8 @@ 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], }; /* "const void *" because some subsystem is @@ -628,22 +1131,244 @@ 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); } void bpf_struct_ops_put(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); + + bpf_map_put(&st_map->map); +} + +int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) +{ + void *func_ptr = *(void **)(st_ops->cfi_stubs + moff); + + return func_ptr ? 0 : -ENOTSUPP; +} + +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_map = container_of(kvalue, struct bpf_struct_ops_map, - kvalue); + 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); + + 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 066d83ea1c99..000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#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 new file mode 100644 index 000000000000..1109475953c0 --- /dev/null +++ b/kernel/bpf/bpf_task_storage.c @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Facebook + * Copyright 2020 Google LLC. + */ + +#include <linux/pid.h> +#include <linux/sched.h> +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <linux/bpf_local_storage.h> +#include <linux/filter.h> +#include <uapi/linux/btf.h> +#include <linux/btf_ids.h> +#include <linux/rcupdate_trace.h> + +DEFINE_BPF_STORAGE_CACHE(task_cache); + +static DEFINE_PER_CPU(int, bpf_task_storage_busy); + +static void bpf_task_storage_lock(void) +{ + cant_migrate(); + this_cpu_inc(bpf_task_storage_busy); +} + +static void bpf_task_storage_unlock(void) +{ + this_cpu_dec(bpf_task_storage_busy); +} + +static bool bpf_task_storage_trylock(void) +{ + cant_migrate(); + if (unlikely(this_cpu_inc_return(bpf_task_storage_busy) != 1)) { + this_cpu_dec(bpf_task_storage_busy); + return false; + } + return true; +} + +static struct bpf_local_storage __rcu **task_storage_ptr(void *owner) +{ + struct task_struct *task = owner; + + return &task->bpf_storage; +} + +static struct bpf_local_storage_data * +task_storage_lookup(struct task_struct *task, struct bpf_map *map, + bool cacheit_lockit) +{ + struct bpf_local_storage *task_storage; + struct bpf_local_storage_map *smap; + + task_storage = + rcu_dereference_check(task->bpf_storage, bpf_rcu_lock_held()); + if (!task_storage) + return NULL; + + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(task_storage, smap, cacheit_lockit); +} + +void bpf_task_storage_free(struct task_struct *task) +{ + struct bpf_local_storage *local_storage; + + migrate_disable(); + rcu_read_lock(); + + local_storage = rcu_dereference(task->bpf_storage); + if (!local_storage) + goto out; + + bpf_task_storage_lock(); + bpf_local_storage_destroy(local_storage); + bpf_task_storage_unlock(); +out: + rcu_read_unlock(); + migrate_enable(); +} + +static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_local_storage_data *sdata; + struct task_struct *task; + unsigned int f_flags; + struct pid *pid; + int fd, err; + + fd = *(int *)key; + pid = pidfd_get_pid(fd, &f_flags); + if (IS_ERR(pid)) + return ERR_CAST(pid); + + /* We should be in an RCU read side critical section, it should be safe + * to call pid_task. + */ + WARN_ON_ONCE(!rcu_read_lock_held()); + task = pid_task(pid, PIDTYPE_PID); + if (!task) { + err = -ENOENT; + goto out; + } + + bpf_task_storage_lock(); + sdata = task_storage_lookup(task, map, true); + bpf_task_storage_unlock(); + put_pid(pid); + return sdata ? sdata->data : NULL; +out: + put_pid(pid); + return ERR_PTR(err); +} + +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; + unsigned int f_flags; + 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)) + return PTR_ERR(pid); + + /* We should be in an RCU read side critical section, it should be safe + * to call pid_task. + */ + WARN_ON_ONCE(!rcu_read_lock_held()); + task = pid_task(pid, PIDTYPE_PID); + if (!task) { + err = -ENOENT; + goto out; + } + + bpf_task_storage_lock(); + sdata = bpf_local_storage_update( + task, (struct bpf_local_storage_map *)map, value, map_flags, + true, GFP_ATOMIC); + bpf_task_storage_unlock(); + + err = PTR_ERR_OR_ZERO(sdata); +out: + put_pid(pid); + return err; +} + +static int task_storage_delete(struct task_struct *task, struct bpf_map *map, + bool nobusy) +{ + struct bpf_local_storage_data *sdata; + + sdata = task_storage_lookup(task, map, false); + if (!sdata) + return -ENOENT; + + if (!nobusy) + return -EBUSY; + + bpf_selem_unlink(SELEM(sdata), false); + + return 0; +} + +static long bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct task_struct *task; + unsigned int f_flags; + struct pid *pid; + int fd, err; + + fd = *(int *)key; + pid = pidfd_get_pid(fd, &f_flags); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + /* We should be in an RCU read side critical section, it should be safe + * to call pid_task. + */ + WARN_ON_ONCE(!rcu_read_lock_held()); + task = pid_task(pid, PIDTYPE_PID); + if (!task) { + err = -ENOENT; + goto out; + } + + bpf_task_storage_lock(); + err = task_storage_delete(task, map, true); + bpf_task_storage_unlock(); +out: + put_pid(pid); + return err; +} + +/* Called by bpf_task_storage_get*() helpers */ +static void *__bpf_task_storage_get(struct bpf_map *map, + struct task_struct *task, void *value, + u64 flags, gfp_t gfp_flags, bool nobusy) +{ + struct bpf_local_storage_data *sdata; + + sdata = task_storage_lookup(task, map, nobusy); + if (sdata) + return sdata->data; + + /* only allocate new storage, when the task is refcounted */ + if (refcount_read(&task->usage) && + (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy) { + sdata = bpf_local_storage_update( + task, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST, false, gfp_flags); + return IS_ERR(sdata) ? NULL : sdata->data; + } + + return NULL; +} + +/* *gfp_flags* is a hidden argument provided by the verifier */ +BPF_CALL_5(bpf_task_storage_get_recur, struct bpf_map *, map, struct task_struct *, + task, void *, value, u64, flags, gfp_t, gfp_flags) +{ + bool nobusy; + void *data; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (flags & ~BPF_LOCAL_STORAGE_GET_F_CREATE || !task) + return (unsigned long)NULL; + + nobusy = bpf_task_storage_trylock(); + data = __bpf_task_storage_get(map, task, value, flags, + gfp_flags, nobusy); + if (nobusy) + bpf_task_storage_unlock(); + return (unsigned long)data; +} + +/* *gfp_flags* is a hidden argument provided by the verifier */ +BPF_CALL_5(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, + task, void *, value, u64, flags, gfp_t, gfp_flags) +{ + void *data; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (flags & ~BPF_LOCAL_STORAGE_GET_F_CREATE || !task) + return (unsigned long)NULL; + + bpf_task_storage_lock(); + data = __bpf_task_storage_get(map, task, value, flags, + gfp_flags, true); + bpf_task_storage_unlock(); + return (unsigned long)data; +} + +BPF_CALL_2(bpf_task_storage_delete_recur, struct bpf_map *, map, struct task_struct *, + task) +{ + bool nobusy; + int ret; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (!task) + return -EINVAL; + + nobusy = bpf_task_storage_trylock(); + /* This helper must only be called from places where the lifetime of the task + * is guaranteed. Either by being refcounted or by being protected + * by an RCU read-side critical section. + */ + ret = task_storage_delete(task, map, nobusy); + if (nobusy) + bpf_task_storage_unlock(); + return ret; +} + +BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, + task) +{ + int ret; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (!task) + return -EINVAL; + + bpf_task_storage_lock(); + /* This helper must only be called from places where the lifetime of the task + * is guaranteed. Either by being refcounted or by being protected + * by an RCU read-side critical section. + */ + ret = task_storage_delete(task, map, true); + bpf_task_storage_unlock(); + return ret; +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -ENOTSUPP; +} + +static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) +{ + return bpf_local_storage_map_alloc(attr, &task_cache, true); +} + +static void task_storage_map_free(struct bpf_map *map) +{ + bpf_local_storage_map_free(map, &task_cache, &bpf_task_storage_busy); +} + +BTF_ID_LIST_GLOBAL_SINGLE(bpf_local_storage_map_btf_id, struct, bpf_local_storage_map) +const struct bpf_map_ops task_storage_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = task_storage_map_alloc, + .map_free = task_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_pid_task_storage_lookup_elem, + .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, +}; + +const struct bpf_func_proto bpf_task_storage_get_recur_proto = { + .func = bpf_task_storage_get_recur, + .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_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, +}; + +const struct bpf_func_proto bpf_task_storage_get_proto = { + .func = bpf_task_storage_get, + .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_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, +}; + +const struct bpf_func_proto bpf_task_storage_delete_recur_proto = { + .func = bpf_task_storage_delete_recur, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, + .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], +}; + +const struct bpf_func_proto bpf_task_storage_delete_proto = { + .func = bpf_task_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .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 0443600146dc..c3223e0db2f5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Facebook */ #include <uapi/linux/btf.h> @@ -18,9 +18,20 @@ #include <linux/sort.h> #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 <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 * the data types of BPF program/map. Hence, it basically focus @@ -47,7 +58,7 @@ * The BTF type section contains a list of 'struct btf_type' objects. * Each one describes a C type. Recall from the above section * that a 'struct btf_type' object could be immediately followed by extra - * data in order to desribe some particular C types. + * data in order to describe some particular C types. * * type_id: * ~~~~~~~ @@ -169,7 +180,7 @@ #define BITS_ROUNDUP_BYTES(bits) \ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) -#define BTF_INFO_MASK 0x8f00ffff +#define BTF_INFO_MASK 0x9f00ffff #define BTF_INT_MASK 0x0fffffff #define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) #define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) @@ -185,11 +196,6 @@ i < btf_type_vlen(struct_type); \ i++, member++) -#define for_each_vsi(i, struct_type, member) \ - for (i = 0, member = btf_type_var_secinfo(struct_type); \ - i < btf_type_vlen(struct_type); \ - i++, member++) - #define for_each_vsi_from(i, from, struct_type, member) \ for (i = from, member = btf_type_var_secinfo(struct_type) + from; \ i < btf_type_vlen(struct_type); \ @@ -198,6 +204,51 @@ DEFINE_IDR(btf_idr); DEFINE_SPINLOCK(btf_idr_lock); +enum btf_kfunc_hook { + BTF_KFUNC_HOOK_COMMON, + BTF_KFUNC_HOOK_XDP, + BTF_KFUNC_HOOK_TC, + BTF_KFUNC_HOOK_STRUCT_OPS, + 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 { + u32 cnt; + 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; @@ -206,12 +257,24 @@ struct btf { const char *strings; void *nohdr_data; struct btf_header hdr; - u32 nr_types; + u32 nr_types; /* includes VOID for base BTF */ u32 types_size; u32 data_size; refcount_t refcnt; u32 id; struct rcu_head rcu; + 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; + u32 start_id; /* first type ID in this BTF (0 for base 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 { @@ -274,13 +337,108 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", + [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", + [BTF_KIND_ENUM64] = "ENUM64", }; -static const char *btf_type_str(const struct btf_type *t) +const char *btf_type_str(const struct btf_type *t) { return btf_kind_str[BTF_INFO_KIND(t->info)]; } +/* Chunk size we use in safe copy of data to be shown. */ +#define BTF_SHOW_OBJ_SAFE_SIZE 32 + +/* + * This is the maximum size of a base type value (equivalent to a + * 128-bit int); if we are at the end of our safe buffer and have + * less than 16 bytes space we can't be assured of being able + * to copy the next type safely, so in such cases we will initiate + * a new copy. + */ +#define BTF_SHOW_OBJ_BASE_TYPE_SIZE 16 + +/* Type name size */ +#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. + * + * One challenge with showing nested data is we want to skip 0-valued + * data, but in order to figure out whether a nested object is all zeros + * we need to walk through it. As a result, we need to make two passes + * when handling structs, unions and arrays; the first path simply looks + * for nonzero data, while the second actually does the display. The first + * pass is signalled by show->state.depth_check being set, and if we + * encounter a non-zero value we set show->state.depth_to_show to + * the depth at which we encountered it. When we have completed the + * first pass, we will know if anything needs to be displayed if + * depth_to_show > depth. See btf_[struct,array]_show() for the + * implementation of this. + * + * Another problem is we want to ensure the data for display is safe to + * access. To support this, the anonymous "struct {} obj" tracks the data + * object and our safe copy of it. We copy portions of the data needed + * to the object "copy" buffer, but because its size is limited to + * BTF_SHOW_OBJ_COPY_LEN bytes, multiple copies may be required as we + * traverse larger objects for display. + * + * The various data type show functions all start with a call to + * btf_show_start_type() which returns a pointer to the safe copy + * of the data needed (or if BTF_SHOW_UNSAFE is specified, to the + * raw data itself). btf_show_obj_safe() is responsible for + * using copy_from_kernel_nofault() to update the safe data if necessary + * as we traverse the object's data. skbuff-like semantics are + * used: + * + * - obj.head points to the start of the toplevel object for display + * - obj.size is the size of the toplevel object + * - obj.data points to the current point in the original data at + * which our safe data starts. obj.data will advance as we copy + * portions of the data. + * + * In most cases a single copy will suffice, but larger data structures + * such as "struct task_struct" will require many copies. The logic in + * btf_show_obj_safe() handles the logic that determines if a new + * copy_from_kernel_nofault() is needed. + */ +struct btf_show { + u64 flags; + void *target; /* target of show operation (seq file, buffer) */ + __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 { + u8 depth; + u8 depth_to_show; + u8 depth_check; + u8 array_member:1, + array_terminated:1; + u16 array_encoding; + u32 type_id; + int status; /* non-zero for error */ + const struct btf_type *type; + const struct btf_member *member; + char name[BTF_SHOW_NAME_SIZE]; /* space for member name/type */ + } state; + struct { + u32 size; + void *head; + void *data; + u8 safe[BTF_SHOW_OBJ_SAFE_SIZE]; + } obj; +}; + struct btf_kind_operations { s32 (*check_meta)(struct btf_verifier_env *env, const struct btf_type *t, @@ -297,9 +455,9 @@ struct btf_kind_operations { const struct btf_type *member_type); void (*log_details)(struct btf_verifier_env *env, const struct btf_type *t); - void (*seq_show)(const struct btf *btf, const struct btf_type *t, + void (*show)(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offsets, - struct seq_file *m); + struct btf_show *show); }; static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; @@ -308,6 +466,9 @@ static struct btf_type btf_void; static int btf_resolve(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id); +static int btf_func_check(struct btf_verifier_env *env, + const struct btf_type *t); + static bool btf_type_is_modifier(const struct btf_type *t) { /* Some of them is not strictly a C modifier @@ -325,6 +486,7 @@ static bool btf_type_is_modifier(const struct btf_type *t) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: return true; } @@ -336,15 +498,21 @@ 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_FWD; + 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_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) @@ -352,44 +520,38 @@ static bool btf_type_nosize_or_null(const struct btf_type *t) return !t || btf_type_nosize(t); } -/* union is only a special case of struct: - * all its offsetof(member) == 0 - */ -static bool btf_type_is_struct(const struct btf_type *t) +static bool btf_type_is_decl_tag_target(const struct btf_type *t) { - u8 kind = BTF_INFO_KIND(t->info); - - return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; + return btf_type_is_func(t) || btf_type_is_struct(t) || + btf_type_is_var(t) || btf_type_is_typedef(t); } -static bool __btf_type_is_struct(const struct btf_type *t) +bool btf_is_vmlinux(const struct btf *btf) { - return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; + return btf->kernel_btf && !btf->base_btf; } -static bool btf_type_is_array(const struct btf_type *t) +u32 btf_nr_types(const struct btf *btf) { - return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; -} + u32 total = 0; -static bool btf_type_is_var(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; -} + while (btf) { + total += btf->nr_types; + btf = btf->base_btf; + } -static bool btf_type_is_datasec(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; + return total; } s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind) { const struct btf_type *t; const char *tname; - u32 i; + u32 i, total; - for (i = 1; i <= btf->nr_types; i++) { - t = btf->types[i]; + total = btf_nr_types(btf); + for (i = 1; i < total; i++) { + t = btf_type_by_id(btf, i); if (BTF_INFO_KIND(t->info) != kind) continue; @@ -401,6 +563,50 @@ s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind) return -ENOENT; } +s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p) +{ + struct btf *btf; + s32 ret; + int id; + + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return PTR_ERR(btf); + if (!btf) + return -EINVAL; + + ret = btf_find_by_name_kind(btf, name, kind); + /* ret is never zero, since btf_find_by_name_kind returns + * positive btf_id or negative error. + */ + if (ret > 0) { + btf_get(btf); + *btf_p = btf; + return ret; + } + + /* If name is not found in vmlinux's BTF then search in module's BTFs */ + spin_lock_bh(&btf_idr_lock); + idr_for_each_entry(&btf_idr, btf, id) { + if (!btf_is_module(btf)) + continue; + /* linear search could be slow hence unlock/lock + * the IDR to avoiding holding it for too long + */ + btf_get(btf); + spin_unlock_bh(&btf_idr_lock); + ret = btf_find_by_name_kind(btf, name, kind); + if (ret > 0) { + *btf_p = btf; + return ret; + } + btf_put(btf); + spin_lock_bh(&btf_idr_lock); + } + spin_unlock_bh(&btf_idr_lock); + return ret; +} + const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, u32 id, u32 *res_id) { @@ -447,6 +653,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -473,6 +680,8 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || + btf_type_is_func(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -485,6 +694,8 @@ static bool btf_type_has_size(const struct btf_type *t) case BTF_KIND_UNION: case BTF_KIND_ENUM: case BTF_KIND_DATASEC: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM64: return true; } @@ -525,9 +736,14 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } -static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t) +static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) { - return (const struct btf_var_secinfo *)(t + 1); + return (const struct btf_decl_tag *)(t + 1); +} + +static const struct btf_enum64 *btf_type_enum64(const struct btf_type *t) +{ + return (const struct btf_enum64 *)(t + 1); } static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) @@ -537,35 +753,52 @@ static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) static bool btf_name_offset_valid(const struct btf *btf, u32 offset) { - return BTF_STR_OFFSET_VALID(offset) && - offset < btf->hdr.str_len; + if (!BTF_STR_OFFSET_VALID(offset)) + return false; + + while (offset < btf->start_str_off) + btf = btf->base_btf; + + offset -= btf->start_str_off; + 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 bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) +const char *btf_str_by_offset(const struct btf *btf, u32 offset) +{ + while (offset < btf->start_str_off) + btf = btf->base_btf; + + offset -= btf->start_str_off; + if (offset < btf->hdr.str_len) + return &btf->strings[offset]; + + return NULL; +} + +static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) { /* offset must be valid */ - const char *src = &btf->strings[offset]; + 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++; } @@ -573,44 +806,54 @@ 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) { + const char *name; + if (!offset) return "(anon)"; - else if (offset < btf->hdr.str_len) - return &btf->strings[offset]; - else - return "(invalid-name-offset)"; + + name = btf_str_by_offset(btf, offset); + return name ?: "(invalid-name-offset)"; } const char *btf_name_by_offset(const struct btf *btf, u32 offset) { - if (offset < btf->hdr.str_len) - return &btf->strings[offset]; - - return NULL; + return btf_str_by_offset(btf, offset); } const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { - if (type_id > btf->nr_types) - return NULL; + while (type_id < btf->start_id) + btf = btf->base_btf; + type_id -= btf->start_id; + if (type_id >= btf->nr_types) + return NULL; return btf->types[type_id]; } +EXPORT_SYMBOL_GPL(btf_type_by_id); /* * Regular int is not a bit field and it must be either @@ -676,6 +919,489 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, return true; } +/* Similar to btf_type_skip_modifiers() but does not skip typedefs. */ +static const struct btf_type *btf_type_skip_qualifiers(const struct btf *btf, + u32 id) +{ + const struct btf_type *t = btf_type_by_id(btf, id); + + while (btf_type_is_modifier(t) && + BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) { + t = btf_type_by_id(btf, t->type); + } + + return t; +} + +#define BTF_SHOW_MAX_ITER 10 + +#define BTF_KIND_BIT(kind) (1ULL << kind) + +/* + * Populate show->state.name with type name information. + * Format of type name is + * + * [.member_name = ] (type_name) + */ +static const char *btf_show_name(struct btf_show *show) +{ + /* BTF_MAX_ITER array suffixes "[]" */ + const char *array_suffixes = "[][][][][][][][][][]"; + const char *array_suffix = &array_suffixes[strlen(array_suffixes)]; + /* BTF_MAX_ITER pointer suffixes "*" */ + const char *ptr_suffixes = "**********"; + const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)]; + const char *name = NULL, *prefix = "", *parens = ""; + const struct btf_member *m = show->state.member; + const struct btf_type *t; + const struct btf_array *array; + u32 id = show->state.type_id; + const char *member = NULL; + bool show_member = false; + u64 kinds = 0; + int i; + + show->state.name[0] = '\0'; + + /* + * Don't show type name if we're showing an array member; + * in that case we show the array type so don't need to repeat + * ourselves for each member. + */ + if (show->state.array_member) + return ""; + + /* Retrieve member name, if any. */ + if (m) { + member = btf_name_by_offset(show->btf, m->name_off); + show_member = strlen(member) > 0; + id = m->type; + } + + /* + * Start with type_id, as we have resolved the struct btf_type * + * via btf_modifier_show() past the parent typedef to the child + * struct, int etc it is defined as. In such cases, the type_id + * still represents the starting type while the struct btf_type * + * in our show->state points at the resolved type of the typedef. + */ + t = btf_type_by_id(show->btf, id); + if (!t) + return ""; + + /* + * The goal here is to build up the right number of pointer and + * array suffixes while ensuring the type name for a typedef + * is represented. Along the way we accumulate a list of + * BTF kinds we have encountered, since these will inform later + * display; for example, pointer types will not require an + * opening "{" for struct, we will just display the pointer value. + * + * We also want to accumulate the right number of pointer or array + * indices in the format string while iterating until we get to + * the typedef/pointee/array member target type. + * + * We start by pointing at the end of pointer and array suffix + * strings; as we accumulate pointers and arrays we move the pointer + * or array string backwards so it will show the expected number of + * '*' or '[]' for the type. BTF_SHOW_MAX_ITER of nesting of pointers + * and/or arrays and typedefs are supported as a precaution. + * + * We also want to get typedef name while proceeding to resolve + * type it points to so that we can add parentheses if it is a + * "typedef struct" etc. + */ + for (i = 0; i < BTF_SHOW_MAX_ITER; i++) { + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + if (!name) + name = btf_name_by_offset(show->btf, + t->name_off); + kinds |= BTF_KIND_BIT(BTF_KIND_TYPEDEF); + id = t->type; + break; + case BTF_KIND_ARRAY: + kinds |= BTF_KIND_BIT(BTF_KIND_ARRAY); + parens = "["; + if (!t) + return ""; + array = btf_type_array(t); + if (array_suffix > array_suffixes) + array_suffix -= 2; + id = array->type; + break; + case BTF_KIND_PTR: + kinds |= BTF_KIND_BIT(BTF_KIND_PTR); + if (ptr_suffix > ptr_suffixes) + ptr_suffix -= 1; + id = t->type; + break; + default: + id = 0; + break; + } + if (!id) + break; + t = btf_type_skip_qualifiers(show->btf, id); + } + /* We may not be able to represent this type; bail to be safe */ + if (i == BTF_SHOW_MAX_ITER) + return ""; + + if (!name) + name = btf_name_by_offset(show->btf, t->name_off); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + prefix = BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT ? + "struct" : "union"; + /* if it's an array of struct/union, parens is already set */ + if (!(kinds & (BTF_KIND_BIT(BTF_KIND_ARRAY)))) + parens = "{"; + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + prefix = "enum"; + break; + default: + break; + } + + /* pointer does not require parens */ + if (kinds & BTF_KIND_BIT(BTF_KIND_PTR)) + parens = ""; + /* typedef does not require struct/union/enum prefix */ + if (kinds & BTF_KIND_BIT(BTF_KIND_TYPEDEF)) + prefix = ""; + + if (!name) + name = ""; + + /* Even if we don't want type name info, we want parentheses etc */ + if (show->flags & BTF_SHOW_NONAME) + snprintf(show->state.name, sizeof(show->state.name), "%s", + parens); + else + snprintf(show->state.name, sizeof(show->state.name), + "%s%s%s(%s%s%s%s%s%s)%s", + /* first 3 strings comprise ".member = " */ + show_member ? "." : "", + show_member ? member : "", + show_member ? " = " : "", + /* ...next is our prefix (struct, enum, etc) */ + prefix, + strlen(prefix) > 0 && strlen(name) > 0 ? " " : "", + /* ...this is the type name itself */ + name, + /* ...suffixed by the appropriate '*', '[]' suffixes */ + strlen(ptr_suffix) > 0 ? " " : "", ptr_suffix, + array_suffix, parens); + + return show->state.name; +} + +static const char *__btf_show_indent(struct btf_show *show) +{ + const char *indents = " "; + const char *indent = &indents[strlen(indents)]; + + if ((indent - show->state.depth) >= indents) + return indent - show->state.depth; + return indents; +} + +static const char *btf_show_indent(struct btf_show *show) +{ + return show->flags & BTF_SHOW_COMPACT ? "" : __btf_show_indent(show); +} + +static const char *btf_show_newline(struct btf_show *show) +{ + return show->flags & BTF_SHOW_COMPACT ? "" : "\n"; +} + +static const char *btf_show_delim(struct btf_show *show) +{ + if (show->state.depth == 0) + return ""; + + if ((show->flags & BTF_SHOW_COMPACT) && show->state.type && + BTF_INFO_KIND(show->state.type->info) == BTF_KIND_UNION) + return "|"; + + return ","; +} + +__printf(2, 3) static void btf_show(struct btf_show *show, const char *fmt, ...) +{ + va_list args; + + if (!show->state.depth_check) { + va_start(args, fmt); + show->showfn(show, fmt, args); + va_end(args); + } +} + +/* Macros are used here as btf_show_type_value[s]() prepends and appends + * format specifiers to the format specifier passed in; these do the work of + * adding indentation, delimiters etc while the caller simply has to specify + * the type value(s) in the format specifier + value(s). + */ +#define btf_show_type_value(show, fmt, value) \ + do { \ + if ((value) != (__typeof__(value))0 || \ + (show->flags & BTF_SHOW_ZERO) || \ + show->state.depth == 0) { \ + btf_show(show, "%s%s" fmt "%s%s", \ + btf_show_indent(show), \ + btf_show_name(show), \ + value, btf_show_delim(show), \ + btf_show_newline(show)); \ + if (show->state.depth > show->state.depth_to_show) \ + show->state.depth_to_show = show->state.depth; \ + } \ + } while (0) + +#define btf_show_type_values(show, fmt, ...) \ + do { \ + btf_show(show, "%s%s" fmt "%s%s", btf_show_indent(show), \ + btf_show_name(show), \ + __VA_ARGS__, btf_show_delim(show), \ + btf_show_newline(show)); \ + if (show->state.depth > show->state.depth_to_show) \ + show->state.depth_to_show = show->state.depth; \ + } while (0) + +/* How much is left to copy to safe buffer after @data? */ +static int btf_show_obj_size_left(struct btf_show *show, void *data) +{ + return show->obj.head + show->obj.size - data; +} + +/* Is object pointed to by @data of @size already copied to our safe buffer? */ +static bool btf_show_obj_is_safe(struct btf_show *show, void *data, int size) +{ + return data >= show->obj.data && + (data + size) < (show->obj.data + BTF_SHOW_OBJ_SAFE_SIZE); +} + +/* + * If object pointed to by @data of @size falls within our safe buffer, return + * the equivalent pointer to the same safe data. Assumes + * copy_from_kernel_nofault() has already happened and our safe buffer is + * populated. + */ +static void *__btf_show_obj_safe(struct btf_show *show, void *data, int size) +{ + if (btf_show_obj_is_safe(show, data, size)) + return show->obj.safe + (data - show->obj.data); + return NULL; +} + +/* + * Return a safe-to-access version of data pointed to by @data. + * We do this by copying the relevant amount of information + * to the struct btf_show obj.safe buffer using copy_from_kernel_nofault(). + * + * If BTF_SHOW_UNSAFE is specified, just return data as-is; no + * safe copy is needed. + * + * Otherwise we need to determine if we have the required amount + * of data (determined by the @data pointer and the size of the + * largest base type we can encounter (represented by + * BTF_SHOW_OBJ_BASE_TYPE_SIZE). Having that much data ensures + * that we will be able to print some of the current object, + * and if more is needed a copy will be triggered. + * Some objects such as structs will not fit into the buffer; + * in such cases additional copies when we iterate over their + * members may be needed. + * + * btf_show_obj_safe() is used to return a safe buffer for + * btf_show_start_type(); this ensures that as we recurse into + * nested types we always have safe data for the given type. + * This approach is somewhat wasteful; it's possible for example + * that when iterating over a large union we'll end up copying the + * same data repeatedly, but the goal is safety not performance. + * We use stack data as opposed to per-CPU buffers because the + * iteration over a type can take some time, and preemption handling + * would greatly complicate use of the safe buffer. + */ +static void *btf_show_obj_safe(struct btf_show *show, + const struct btf_type *t, + void *data) +{ + const struct btf_type *rt; + int size_left, size; + void *safe = NULL; + + if (show->flags & BTF_SHOW_UNSAFE) + return data; + + rt = btf_resolve_size(show->btf, t, &size); + if (IS_ERR(rt)) { + show->state.status = PTR_ERR(rt); + return NULL; + } + + /* + * Is this toplevel object? If so, set total object size and + * initialize pointers. Otherwise check if we still fall within + * our safe object data. + */ + if (show->state.depth == 0) { + show->obj.size = size; + show->obj.head = data; + } else { + /* + * If the size of the current object is > our remaining + * safe buffer we _may_ need to do a new copy. However + * consider the case of a nested struct; it's size pushes + * us over the safe buffer limit, but showing any individual + * struct members does not. In such cases, we don't need + * to initiate a fresh copy yet; however we definitely need + * at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes left + * in our buffer, regardless of the current object size. + * The logic here is that as we resolve types we will + * hit a base type at some point, and we need to be sure + * the next chunk of data is safely available to display + * that type info safely. We cannot rely on the size of + * the current object here because it may be much larger + * than our current buffer (e.g. task_struct is 8k). + * All we want to do here is ensure that we can print the + * next basic type, which we can if either + * - the current type size is within the safe buffer; or + * - at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes are left in + * the safe buffer. + */ + safe = __btf_show_obj_safe(show, data, + min(size, + BTF_SHOW_OBJ_BASE_TYPE_SIZE)); + } + + /* + * We need a new copy to our safe object, either because we haven't + * yet copied and are initializing safe data, or because the data + * we want falls outside the boundaries of the safe object. + */ + if (!safe) { + size_left = btf_show_obj_size_left(show, data); + if (size_left > BTF_SHOW_OBJ_SAFE_SIZE) + size_left = BTF_SHOW_OBJ_SAFE_SIZE; + show->state.status = copy_from_kernel_nofault(show->obj.safe, + data, size_left); + if (!show->state.status) { + show->obj.data = data; + safe = show->obj.safe; + } + } + + return safe; +} + +/* + * Set the type we are starting to show and return a safe data pointer + * to be used for showing the associated data. + */ +static void *btf_show_start_type(struct btf_show *show, + const struct btf_type *t, + u32 type_id, void *data) +{ + show->state.type = t; + show->state.type_id = type_id; + show->state.name[0] = '\0'; + + return btf_show_obj_safe(show, t, data); +} + +static void btf_show_end_type(struct btf_show *show) +{ + show->state.type = NULL; + show->state.type_id = 0; + show->state.name[0] = '\0'; +} + +static void *btf_show_start_aggr_type(struct btf_show *show, + const struct btf_type *t, + u32 type_id, void *data) +{ + void *safe_data = btf_show_start_type(show, t, type_id, data); + + if (!safe_data) + return safe_data; + + btf_show(show, "%s%s%s", btf_show_indent(show), + btf_show_name(show), + btf_show_newline(show)); + show->state.depth++; + return safe_data; +} + +static void btf_show_end_aggr_type(struct btf_show *show, + const char *suffix) +{ + show->state.depth--; + btf_show(show, "%s%s%s%s", btf_show_indent(show), suffix, + btf_show_delim(show), btf_show_newline(show)); + btf_show_end_type(show); +} + +static void btf_show_start_member(struct btf_show *show, + const struct btf_member *m) +{ + show->state.member = m; +} + +static void btf_show_start_array_member(struct btf_show *show) +{ + show->state.array_member = 1; + btf_show_start_member(show, NULL); +} + +static void btf_show_end_member(struct btf_show *show) +{ + show->state.member = NULL; +} + +static void btf_show_end_array_member(struct btf_show *show) +{ + show->state.array_member = 0; + btf_show_end_member(show); +} + +static void *btf_show_start_array_type(struct btf_show *show, + const struct btf_type *t, + u32 type_id, + u16 array_encoding, + void *data) +{ + show->state.array_encoding = array_encoding; + show->state.array_terminated = 0; + return btf_show_start_aggr_type(show, t, type_id, data); +} + +static void btf_show_end_array_type(struct btf_show *show) +{ + show->state.array_encoding = 0; + show->state.array_terminated = 0; + btf_show_end_aggr_type(show, "]"); +} + +static void *btf_show_start_struct_type(struct btf_show *show, + const struct btf_type *t, + u32 type_id, + void *data) +{ + return btf_show_start_aggr_type(show, t, type_id, data); +} + +static void btf_show_end_struct_type(struct btf_show *show) +{ + btf_show_end_aggr_type(show, "}"); +} + __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, const char *fmt, ...) { @@ -706,23 +1432,28 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; - u8 kind = BTF_INFO_KIND(t->info); struct btf *btf = env->btf; va_list args; 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, - btf_kind_str[kind], + btf_type_str(t), __btf_name_by_offset(btf, t->name_off), log_details ? " " : ""); @@ -757,8 +1488,15 @@ 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 @@ -846,17 +1584,13 @@ static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) { struct btf *btf = env->btf; - /* < 2 because +1 for btf_void which is always in btf->types[0]. - * btf_void is not accounted in btf->nr_types because btf_void - * does not come from the BTF file. - */ - if (btf->types_size - btf->nr_types < 2) { + if (btf->types_size == btf->nr_types) { /* Expand 'types' array */ struct btf_type **new_types; u32 expand_by, new_size; - if (btf->types_size == BTF_MAX_TYPE) { + if (btf->start_id + btf->types_size == BTF_MAX_TYPE) { btf_verifier_log(env, "Exceeded max num of types"); return -E2BIG; } @@ -870,18 +1604,23 @@ static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) if (!new_types) return -ENOMEM; - if (btf->nr_types == 0) - new_types[0] = &btf_void; - else + if (btf->nr_types == 0) { + if (!btf->base_btf) { + /* lazily init VOID type */ + new_types[0] = &btf_void; + btf->nr_types++; + } + } else { memcpy(new_types, btf->types, - sizeof(*btf->types) * (btf->nr_types + 1)); + sizeof(*btf->types) * btf->nr_types); + } kvfree(btf->types); btf->types = new_types; btf->types_size = new_size; } - btf->types[++(btf->nr_types)] = t; + btf->types[btf->nr_types++] = t; return 0; } @@ -922,12 +1661,78 @@ static void btf_free_id(struct btf *btf) spin_unlock_irqrestore(&btf_idr_lock, flags); } +static void btf_free_kfunc_set_tab(struct btf *btf) +{ + struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab; + int hook; + + if (!tab) + return; + for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) + kfree(tab->sets[hook]); + kfree(tab); + btf->kfunc_set_tab = NULL; +} + +static void btf_free_dtor_kfunc_tab(struct btf *btf) +{ + struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; + + if (!tab) + return; + kfree(tab); + btf->dtor_kfunc_tab = NULL; +} + +static void btf_struct_metas_free(struct btf_struct_metas *tab) +{ + int i; + + if (!tab) + return; + for (i = 0; i < tab->cnt; i++) + btf_record_free(tab->types[i].record); + kfree(tab); +} + +static void btf_free_struct_meta_tab(struct btf *btf) +{ + struct btf_struct_metas *tab = btf->struct_meta_tab; + + btf_struct_metas_free(tab); + 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); } @@ -938,6 +1743,16 @@ 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); +} + void btf_put(struct btf *btf) { if (btf && refcount_dec_and_test(&btf->refcnt)) { @@ -946,6 +1761,23 @@ 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; @@ -954,18 +1786,17 @@ static int env_resolve_init(struct btf_verifier_env *env) u32 *resolved_ids = NULL; u8 *visit_states = NULL; - /* +1 for btf_void */ - resolved_sizes = kvcalloc(nr_types + 1, sizeof(*resolved_sizes), + resolved_sizes = kvcalloc(nr_types, sizeof(*resolved_sizes), GFP_KERNEL | __GFP_NOWARN); if (!resolved_sizes) goto nomem; - resolved_ids = kvcalloc(nr_types + 1, sizeof(*resolved_ids), + resolved_ids = kvcalloc(nr_types, sizeof(*resolved_ids), GFP_KERNEL | __GFP_NOWARN); if (!resolved_ids) goto nomem; - visit_states = kvcalloc(nr_types + 1, sizeof(*visit_states), + visit_states = kvcalloc(nr_types, sizeof(*visit_states), GFP_KERNEL | __GFP_NOWARN); if (!visit_states) goto nomem; @@ -1017,21 +1848,27 @@ static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, static bool env_type_is_resolved(const struct btf_verifier_env *env, u32 type_id) { - return env->visit_states[type_id] == RESOLVED; + /* base BTF types should be resolved by now */ + if (type_id < env->btf->start_id) + return true; + + return env->visit_states[type_id - env->btf->start_id] == RESOLVED; } static int env_stack_push(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) { + const struct btf *btf = env->btf; struct resolve_vertex *v; if (env->top_stack == MAX_RESOLVE_DEPTH) return -E2BIG; - if (env->visit_states[type_id] != NOT_VISITED) + if (type_id < btf->start_id + || env->visit_states[type_id - btf->start_id] != NOT_VISITED) return -EEXIST; - env->visit_states[type_id] = VISITED; + env->visit_states[type_id - btf->start_id] = VISITED; v = &env->stack[env->top_stack++]; v->t = t; @@ -1061,6 +1898,7 @@ static void env_stack_pop_resolved(struct btf_verifier_env *env, u32 type_id = env->stack[--(env->top_stack)].type_id; struct btf *btf = env->btf; + type_id -= btf->start_id; /* adjust to local type id */ btf->resolved_sizes[type_id] = resolved_size; btf->resolved_ids[type_id] = resolved_type_id; env->visit_states[type_id] = RESOLVED; @@ -1078,23 +1916,27 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) * *type_size: (x * y * sizeof(u32)). Hence, *type_size always * corresponds to the return type. * *elem_type: u32 + * *elem_id: id of u32 * *total_nelems: (x * y). Hence, individual elem size is * (*type_size / *total_nelems) + * *type_id: id of type if it's changed within the function, 0 if not * * type: is not an array (e.g. const struct X) * return type: type "struct X" * *type_size: sizeof(struct X) * *elem_type: same as return type ("struct X") + * *elem_id: 0 * *total_nelems: 1 + * *type_id: id of type if it's changed within the function, 0 if not */ -const struct btf_type * -btf_resolve_size(const struct btf *btf, const struct btf_type *type, - u32 *type_size, const struct btf_type **elem_type, - u32 *total_nelems) +static const struct btf_type * +__btf_resolve_size(const struct btf *btf, const struct btf_type *type, + u32 *type_size, const struct btf_type **elem_type, + u32 *elem_id, u32 *total_nelems, u32 *type_id) { const struct btf_type *array_type = NULL; - const struct btf_array *array; - u32 i, size, nelems = 1; + const struct btf_array *array = NULL; + u32 i, size, nelems = 1, id = 0; for (i = 0; i < MAX_RESOLVE_DEPTH; i++) { switch (BTF_INFO_KIND(type->info)) { @@ -1103,6 +1945,8 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type, case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM64: size = type->size; goto resolved; @@ -1115,6 +1959,8 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type, case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: + id = type->type; type = btf_type_by_id(btf, type->type); break; @@ -1145,18 +1991,45 @@ resolved: *total_nelems = nelems; if (elem_type) *elem_type = type; + if (elem_id) + *elem_id = array ? array->type : 0; + if (type_id && id) + *type_id = id; return array_type ? : type; } +const struct btf_type * +btf_resolve_size(const struct btf *btf, const struct btf_type *type, + u32 *type_size) +{ + return __btf_resolve_size(btf, type, type_size, NULL, NULL, NULL, NULL); +} + +static u32 btf_resolved_type_id(const struct btf *btf, u32 type_id) +{ + while (type_id < btf->start_id) + btf = btf->base_btf; + + return btf->resolved_ids[type_id - btf->start_id]; +} + /* The input param "type_id" must point to a needs_resolve type */ static const struct btf_type *btf_type_id_resolve(const struct btf *btf, u32 *type_id) { - *type_id = btf->resolved_ids[*type_id]; + *type_id = btf_resolved_type_id(btf, *type_id); return btf_type_by_id(btf, *type_id); } +static u32 btf_resolved_type_size(const struct btf *btf, u32 type_id) +{ + while (type_id < btf->start_id) + btf = btf->base_btf; + + return btf->resolved_sizes[type_id - btf->start_id]; +} + const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *type_id, u32 *ret_size) { @@ -1171,7 +2044,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, if (btf_type_has_size(size_type)) { size = size_type->size; } else if (btf_type_is_array(size_type)) { - size = btf->resolved_sizes[size_type_id]; + size = btf_resolved_type_size(btf, size_type_id); } else if (btf_type_is_ptr(size_type)) { size = sizeof(void *); } else { @@ -1179,14 +2052,14 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, !btf_type_is_var(size_type))) return NULL; - size_type_id = btf->resolved_ids[size_type_id]; + size_type_id = btf_resolved_type_id(btf, size_type_id); size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; else if (btf_type_has_size(size_type)) size = size_type->size; else if (btf_type_is_array(size_type)) - size = btf->resolved_sizes[size_type_id]; + size = btf_resolved_type_size(btf, size_type_id); else if (btf_type_is_ptr(size_type)) size = sizeof(void *); else @@ -1220,7 +2093,7 @@ static int btf_df_check_kflag_member(struct btf_verifier_env *env, return -EINVAL; } -/* Used for ptr, array and struct/union type members. +/* Used for ptr, array struct/union and float type members. * int, enum and modifier types have their specific callback functions. */ static int btf_generic_check_kflag_member(struct btf_verifier_env *env, @@ -1249,11 +2122,11 @@ static int btf_df_resolve(struct btf_verifier_env *env, return -EINVAL; } -static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t, - u32 type_id, void *data, u8 bits_offsets, - struct seq_file *m) +static void btf_df_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offsets, + struct btf_show *show) { - seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info)); + btf_show(show, "<unsupported kind:%u>", BTF_INFO_KIND(t->info)); } static int btf_int_check_member(struct btf_verifier_env *env, @@ -1426,7 +2299,7 @@ static void btf_int_log(struct btf_verifier_env *env, btf_int_encoding_str(BTF_INT_ENCODING(int_data))); } -static void btf_int128_print(struct seq_file *m, void *data) +static void btf_int128_print(struct btf_show *show, void *data) { /* data points to a __int128 number. * Suppose @@ -1445,9 +2318,10 @@ static void btf_int128_print(struct seq_file *m, void *data) lower_num = *(u64 *)data; #endif if (upper_num == 0) - seq_printf(m, "0x%llx", lower_num); + btf_show_type_value(show, "0x%llx", lower_num); else - seq_printf(m, "0x%llx%016llx", upper_num, lower_num); + btf_show_type_values(show, "0x%llx%016llx", upper_num, + lower_num); } static void btf_int128_shift(u64 *print_num, u16 left_shift_bits, @@ -1491,8 +2365,8 @@ static void btf_int128_shift(u64 *print_num, u16 left_shift_bits, #endif } -static void btf_bitfield_seq_show(void *data, u8 bits_offset, - u8 nr_bits, struct seq_file *m) +static void btf_bitfield_show(void *data, u8 bits_offset, + u8 nr_bits, struct btf_show *show) { u16 left_shift_bits, right_shift_bits; u8 nr_copy_bytes; @@ -1512,14 +2386,14 @@ static void btf_bitfield_seq_show(void *data, u8 bits_offset, right_shift_bits = BITS_PER_U128 - nr_bits; btf_int128_shift(print_num, left_shift_bits, right_shift_bits); - btf_int128_print(m, print_num); + btf_int128_print(show, print_num); } -static void btf_int_bits_seq_show(const struct btf *btf, - const struct btf_type *t, - void *data, u8 bits_offset, - struct seq_file *m) +static void btf_int_bits_show(const struct btf *btf, + const struct btf_type *t, + void *data, u8 bits_offset, + struct btf_show *show) { u32 int_data = btf_type_int(t); u8 nr_bits = BTF_INT_BITS(int_data); @@ -1532,55 +2406,77 @@ static void btf_int_bits_seq_show(const struct btf *btf, total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); - btf_bitfield_seq_show(data, bits_offset, nr_bits, m); + btf_bitfield_show(data, bits_offset, nr_bits, show); } -static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, - u32 type_id, void *data, u8 bits_offset, - struct seq_file *m) +static void btf_int_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) { u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; u8 nr_bits = BTF_INT_BITS(int_data); + void *safe_data; + + safe_data = btf_show_start_type(show, t, type_id, data); + if (!safe_data) + return; if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { - btf_int_bits_seq_show(btf, t, data, bits_offset, m); - return; + btf_int_bits_show(btf, t, safe_data, bits_offset, show); + goto out; } switch (nr_bits) { case 128: - btf_int128_print(m, data); + btf_int128_print(show, safe_data); break; case 64: if (sign) - seq_printf(m, "%lld", *(s64 *)data); + btf_show_type_value(show, "%lld", *(s64 *)safe_data); else - seq_printf(m, "%llu", *(u64 *)data); + btf_show_type_value(show, "%llu", *(u64 *)safe_data); break; case 32: if (sign) - seq_printf(m, "%d", *(s32 *)data); + btf_show_type_value(show, "%d", *(s32 *)safe_data); else - seq_printf(m, "%u", *(u32 *)data); + btf_show_type_value(show, "%u", *(u32 *)safe_data); break; case 16: if (sign) - seq_printf(m, "%d", *(s16 *)data); + btf_show_type_value(show, "%d", *(s16 *)safe_data); else - seq_printf(m, "%u", *(u16 *)data); + btf_show_type_value(show, "%u", *(u16 *)safe_data); break; case 8: + if (show->state.array_encoding == BTF_INT_CHAR) { + /* check for null terminator */ + if (show->state.array_terminated) + break; + if (*(char *)data == '\0') { + show->state.array_terminated = 1; + break; + } + if (isprint(*(char *)data)) { + btf_show_type_value(show, "'%c'", + *(char *)safe_data); + break; + } + } if (sign) - seq_printf(m, "%d", *(s8 *)data); + btf_show_type_value(show, "%d", *(s8 *)safe_data); else - seq_printf(m, "%u", *(u8 *)data); + btf_show_type_value(show, "%u", *(u8 *)safe_data); break; default: - btf_int_bits_seq_show(btf, t, data, bits_offset, m); + btf_int_bits_show(btf, t, safe_data, bits_offset, show); + break; } +out: + btf_show_end_type(show); } static const struct btf_kind_operations int_ops = { @@ -1589,7 +2485,7 @@ static const struct btf_kind_operations int_ops = { .check_member = btf_int_check_member, .check_kflag_member = btf_int_check_kflag_member, .log_details = btf_int_log, - .seq_show = btf_int_seq_show, + .show = btf_int_show, }; static int btf_modifier_check_member(struct btf_verifier_env *env, @@ -1672,6 +2568,8 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { + const char *value; + if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; @@ -1687,7 +2585,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } - /* typedef type must have a valid name, and other ref types, + /* typedef/type_tag type must have a valid name, and other ref types, * volatile, const, restrict, should have a null name. */ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) { @@ -1696,6 +2594,12 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } + } else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) { + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } } else { if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); @@ -1820,7 +2724,7 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, * * We now need to continue from the last-resolved-ptr to * ensure the last-resolved-ptr will not referring back to - * the currenct ptr (t). + * the current ptr (t). */ if (btf_type_is_modifier(next_type)) { const struct btf_type *resolved_type; @@ -1853,34 +2757,44 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, return 0; } -static void btf_modifier_seq_show(const struct btf *btf, - const struct btf_type *t, - u32 type_id, void *data, - u8 bits_offset, struct seq_file *m) +static void btf_modifier_show(const struct btf *btf, + const struct btf_type *t, + u32 type_id, void *data, + u8 bits_offset, struct btf_show *show) { if (btf->resolved_ids) t = btf_type_id_resolve(btf, &type_id); else t = btf_type_skip_modifiers(btf, type_id, NULL); - btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); + btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } -static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t, - u32 type_id, void *data, u8 bits_offset, - struct seq_file *m) +static void btf_var_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) { t = btf_type_id_resolve(btf, &type_id); - btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); + btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } -static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t, - u32 type_id, void *data, u8 bits_offset, - struct seq_file *m) +static void btf_ptr_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) { - /* It is a hashed value */ - seq_printf(m, "%p", *(void **)data); + void *safe_data; + + safe_data = btf_show_start_type(show, t, type_id, data); + if (!safe_data) + return; + + /* It is a hashed value unless BTF_SHOW_PTR_RAW is specified */ + if (show->flags & BTF_SHOW_PTR_RAW) + btf_show_type_value(show, "0x%px", *(void **)safe_data); + else + btf_show_type_value(show, "0x%p", *(void **)safe_data); + btf_show_end_type(show); } static void btf_ref_type_log(struct btf_verifier_env *env, @@ -1889,22 +2803,22 @@ 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, .check_kflag_member = btf_modifier_check_kflag_member, .log_details = btf_ref_type_log, - .seq_show = btf_modifier_seq_show, + .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, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_ref_type_log, - .seq_show = btf_ptr_seq_show, + .show = btf_ptr_show, }; static s32 btf_fwd_check_meta(struct btf_verifier_env *env, @@ -1939,13 +2853,13 @@ 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, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_fwd_type_log, - .seq_show = btf_df_seq_show, + .show = btf_df_show, }; static int btf_array_check_member(struct btf_verifier_env *env, @@ -2104,37 +3018,99 @@ static void btf_array_log(struct btf_verifier_env *env, array->type, array->index_type, array->nelems); } -static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t, - u32 type_id, void *data, u8 bits_offset, - struct seq_file *m) +static void __btf_array_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) { const struct btf_array *array = btf_type_array(t); const struct btf_kind_operations *elem_ops; const struct btf_type *elem_type; - u32 i, elem_size, elem_type_id; + u32 i, elem_size = 0, elem_type_id; + u16 encoding = 0; elem_type_id = array->type; - elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + elem_type = btf_type_skip_modifiers(btf, elem_type_id, NULL); + if (elem_type && btf_type_has_size(elem_type)) + elem_size = elem_type->size; + + if (elem_type && btf_type_is_int(elem_type)) { + u32 int_type = btf_type_int(elem_type); + + encoding = BTF_INT_ENCODING(int_type); + + /* + * BTF_INT_CHAR encoding never seems to be set for + * char arrays, so if size is 1 and element is + * printable as a char, we'll do that. + */ + if (elem_size == 1) + encoding = BTF_INT_CHAR; + } + + if (!btf_show_start_array_type(show, t, type_id, encoding, data)) + return; + + if (!elem_type) + goto out; elem_ops = btf_type_ops(elem_type); - seq_puts(m, "["); + for (i = 0; i < array->nelems; i++) { - if (i) - seq_puts(m, ","); - elem_ops->seq_show(btf, elem_type, elem_type_id, data, - bits_offset, m); + btf_show_start_array_member(show); + + elem_ops->show(btf, elem_type, elem_type_id, data, + bits_offset, show); data += elem_size; + + btf_show_end_array_member(show); + + if (show->state.array_terminated) + break; } - seq_puts(m, "]"); +out: + btf_show_end_array_type(show); } -static struct btf_kind_operations array_ops = { +static void btf_array_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) +{ + const struct btf_member *m = show->state.member; + + /* + * First check if any members would be shown (are non-zero). + * See comments above "struct btf_show" definition for more + * details on how this works at a high-level. + */ + if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) { + if (!show->state.depth_check) { + show->state.depth_check = show->state.depth + 1; + show->state.depth_to_show = 0; + } + __btf_array_show(btf, t, type_id, data, bits_offset, show); + show->state.member = m; + + if (show->state.depth_check != show->state.depth + 1) + return; + show->state.depth_check = 0; + + if (show->state.depth_to_show <= show->state.depth) + return; + /* + * Reaching here indicates we have recursed and found + * non-zero array member(s). + */ + } + __btf_array_show(btf, t, type_id, data, bits_offset, show); +} + +static const struct btf_kind_operations array_ops = { .check_meta = btf_array_check_meta, .resolve = btf_array_resolve, .check_member = btf_array_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_array_log, - .seq_show = btf_array_seq_show, + .show = btf_array_show, }; static int btf_struct_check_member(struct btf_verifier_env *env, @@ -2213,7 +3189,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } - offset = btf_member_bit_offset(t, member); + offset = __btf_member_bit_offset(t, member); if (is_union && offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); @@ -2257,7 +3233,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env, if (v->next_member) { const struct btf_type *last_member_type; const struct btf_member *last_member; - u16 last_member_type_id; + u32 last_member_type_id; last_member = btf_type_member(v->t) + v->next_member - 1; last_member_type_id = last_member->type; @@ -2320,52 +3296,851 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -/* find 'struct bpf_spin_lock' in map value. - * return >= 0 offset if found - * and < 0 in case of error - */ -int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) +enum { + BTF_FIELD_IGNORE = 0, + BTF_FIELD_FOUND = 1, +}; + +struct btf_field_info { + enum btf_field_type type; + u32 off; + union { + struct { + u32 type_id; + } kptr; + struct { + const char *node_name; + u32 value_btf_id; + } graph_root; + }; +}; + +static int btf_find_struct(const struct btf *btf, const struct btf_type *t, + u32 off, int sz, enum btf_field_type field_type, + struct btf_field_info *info) { - const struct btf_member *member; - u32 i, off = -ENOENT; + if (!__btf_type_is_struct(t)) + return BTF_FIELD_IGNORE; + if (t->size != sz) + return BTF_FIELD_IGNORE; + info->type = field_type; + info->off = off; + return BTF_FIELD_FOUND; +} + +static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, + u32 off, int sz, struct btf_field_info *info, u32 field_mask) +{ + enum btf_field_type type; + u32 res_id; + + /* Permit modifiers on the pointer itself */ + if (btf_type_is_volatile(t)) + t = btf_type_by_id(btf, t->type); + /* For PTR, sz is always == 8 */ + 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)) + 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_untrusted", __btf_name_by_offset(btf, t->name_off))) + type = BPF_KPTR_UNREF; + else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) + type = BPF_KPTR_REF; + else if (!strcmp("percpu_kptr", __btf_name_by_offset(btf, t->name_off))) + type = BPF_KPTR_PERCPU; + else if (!strcmp("uptr", __btf_name_by_offset(btf, t->name_off))) + 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 */ if (!__btf_type_is_struct(t)) return -EINVAL; - for_each_member(i, t, member) { - const struct btf_type *member_type = btf_type_by_id(btf, - member->type); - if (!__btf_type_is_struct(member_type)) + info->type = type; + info->off = off; + info->kptr.type_id = res_id; + return BTF_FIELD_FOUND; +} + +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 len = strlen(tag_key); + int i, n; + + for (i = last_id + 1, n = btf_nr_types(btf); i < n; i++) { + const struct btf_type *t = btf_type_by_id(btf, i); + + if (!btf_type_is_decl_tag(t)) continue; - if (member_type->size != sizeof(struct bpf_spin_lock)) + if (pt != btf_type_by_id(btf, t->type)) continue; - if (strcmp(__btf_name_by_offset(btf, member_type->name_off), - "bpf_spin_lock")) + if (btf_type_decl_tag(t)->component_idx != comp_idx) continue; - if (off != -ENOENT) - /* only one 'struct bpf_spin_lock' is allowed */ - return -E2BIG; - off = btf_member_bit_offset(t, member); + if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) + continue; + return i; + } + return -ENOENT; +} + +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; + s32 id; + + if (!__btf_type_is_struct(t)) + return BTF_FIELD_IGNORE; + if (t->size != sz) + return BTF_FIELD_IGNORE; + value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); + if (IS_ERR(value_type)) + return -EINVAL; + node_field_name = strstr(value_type, ":"); + if (!node_field_name) + return -EINVAL; + value_type = kstrndup(value_type, node_field_name - value_type, GFP_KERNEL | __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; + node_field_name++; + if (str_is_empty(node_field_name)) + return -EINVAL; + info->type = head_type; + info->off = off; + info->graph_root.value_btf_id = id; + info->graph_root.node_name = node_field_name; + return BTF_FIELD_FOUND; +} + +#define field_mask_test_name(field_type, field_type_str) \ + if (field_mask & field_type && !strcmp(name, field_type_str)) { \ + type = field_type; \ + goto end; \ + } + +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) +{ + int type = 0; + const char *name = __btf_name_by_offset(btf, var_type->name_off); + + 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) + return -E2BIG; + *seen_mask |= BPF_TIMER; + type = BPF_TIMER; + goto end; + } + } + if (field_mask & BPF_WORKQUEUE) { + if (!strcmp(name, "bpf_wq")) { + if (*seen_mask & BPF_WORKQUEUE) + return -E2BIG; + *seen_mask |= BPF_WORKQUEUE; + type = BPF_WORKQUEUE; + goto end; + } + } + field_mask_test_name(BPF_LIST_HEAD, "bpf_list_head"); + field_mask_test_name(BPF_LIST_NODE, "bpf_list_node"); + field_mask_test_name(BPF_RB_ROOT, "bpf_rb_root"); + field_mask_test_name(BPF_RB_NODE, "bpf_rb_node"); + field_mask_test_name(BPF_REFCOUNT, "bpf_refcount"); + + /* Only return BPF_KPTR when all other types with matchable names fail */ + if (field_mask & (BPF_KPTR | BPF_UPTR) && !__btf_type_is_struct(var_type)) { + type = BPF_KPTR_REF; + goto end; + } + return 0; +end: + *sz = btf_field_type_size(type); + *align = btf_field_type_align(type); + return type; +} + +#undef field_mask_test_name + +/* 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, + 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, 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_TIMER: + case BPF_WORKQUEUE: + case BPF_LIST_NODE: + case BPF_RB_NODE: + case BPF_REFCOUNT: + 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); + + off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; off /= 8; - if (off % __alignof__(struct bpf_spin_lock)) - /* valid struct bpf_spin_lock will be 4 byte aligned */ + + 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, u32 level) +{ + int ret, idx = 0; + const struct btf_var_secinfo *vsi; + 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); + + off = vsi->offset; + 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; +} + +static int btf_find_field(const struct btf *btf, const struct btf_type *t, + u32 field_mask, struct btf_field_info *info, + int info_cnt) +{ + if (__btf_type_is_struct(t)) + 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, 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; + /* 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; + + /* Find type in map BTF, and use it to look up the matching type + * in vmlinux or module BTFs, by name and kind. + */ + 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), + &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; + + /* Find and stash the function pointer for the destruction function that + * needs to be eventually invoked from the map free path. + */ + if (info->type == BPF_KPTR_REF) { + const struct btf_type *dtor_func; + const char *dtor_func_name; + unsigned long addr; + s32 dtor_btf_id; + + /* This call also serves as a whitelist of allowed objects that + * can be used as a referenced pointer and be stored in a map at + * the same time. + */ + 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(kptr_btf, dtor_btf_id); + if (!dtor_func) { + ret = -ENOENT; + goto end_btf; + } + + if (btf_is_module(kptr_btf)) { + mod = btf_try_get_module(kptr_btf); + if (!mod) { + ret = -ENXIO; + goto end_btf; + } + } + + /* We already verified dtor_func to be btf_type_is_func + * in register_btf_id_dtor_kfuncs. + */ + dtor_func_name = __btf_name_by_offset(kptr_btf, dtor_func->name_off); + addr = kallsyms_lookup_name(dtor_func_name); + if (!addr) { + ret = -EINVAL; + goto end_mod; + } + field->kptr.dtor = (void *)addr; + } + +found_dtor: + field->kptr.btf_id = id; + field->kptr.btf = kptr_btf; + field->kptr.module = mod; + return 0; +end_mod: + module_put(mod); +end_btf: + btf_put(kptr_btf); + return ret; +} + +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->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->graph_root.node_name, + __btf_name_by_offset(btf, member->name_off))) + continue; + /* Invalid BTF, two members with same name */ + if (n) return -EINVAL; + n = btf_type_by_id(btf, member->type); + if (!__btf_type_is_struct(n)) + return -EINVAL; + 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 % node_type_align) + return -EINVAL; + + 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; } - return off; + 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; + int ret, i, cnt; + + ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr)); + if (ret < 0) + return ERR_PTR(ret); + if (!ret) + return NULL; + + cnt = ret; + /* 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); + if (!rec) + return ERR_PTR(-ENOMEM); + + rec->spin_lock_off = -EINVAL; + rec->timer_off = -EINVAL; + rec->wq_off = -EINVAL; + rec->refcount_off = -EINVAL; + for (i = 0; i < cnt; i++) { + field_type_size = btf_field_type_size(info_arr[i].type); + 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; + } + if (info_arr[i].off < next_off) { + ret = -EEXIST; + goto end; + } + 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: + WARN_ON_ONCE(rec->spin_lock_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->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_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; + break; + case BPF_LIST_HEAD: + ret = btf_parse_list_head(btf, &rec->fields[i], &info_arr[i]); + 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; + goto end; + } + rec->cnt++; + } + + /* 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) { + 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); + return ERR_PTR(ret); +} + +int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) +{ + int i; + + /* There are three types that signify ownership of some other type: + * kptr_ref, bpf_list_head, bpf_rb_root. + * kptr_ref only supports storing kernel types, which can't store + * references to program allocated local types. + * + * Hence we only need to ensure that bpf_{list_head,rb_root} ownership + * does not form cycles. + */ + 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_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].graph_root.value_btf_id; + meta = btf_find_struct_meta(btf, btf_id); + if (!meta) + return -EFAULT; + rec->fields[i].graph_root.value_rec = meta->record; + + /* 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,rb_node} in a type. Instead, we use the + * following resaoning: + * + * - A type can only be owned by another type in user BTF if it + * has a bpf_{list,rb}_node. Let's call these node types. + * - A type can only _own_ another type in user BTF if it has a + * bpf_{list_head,rb_root}. Let's call these root types. + * + * We ensure that if a type is both a root and node, its + * element types cannot be root types. + * + * To ensure acyclicity: + * + * When A is an root type but not a node, its ownership + * chain can be: + * A -> B -> C + * Where: + * - A is an root, e.g. has bpf_rb_root. + * - B is both a root and node, e.g. has bpf_rb_node and + * bpf_list_head. + * - C is only an root, e.g. has bpf_list_node + * + * When A is both a root and node, some other type already + * owns it in the BTF domain, hence it can not own + * another root type through any of the ownership edges. + * A -> B + * Where: + * - A is both an root and node. + * - B is only an node. + */ + if (meta->record->field_mask & BPF_GRAPH_ROOT) + return -ELOOP; + } + return 0; } -static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, - u32 type_id, void *data, u8 bits_offset, - struct seq_file *m) +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) { - const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ","; const struct btf_member *member; + void *safe_data; u32 i; - seq_puts(m, "{"); + safe_data = btf_show_start_struct_type(show, t, type_id, data); + if (!safe_data) + return; + for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); @@ -2374,32 +4149,74 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, u32 bytes_offset; u8 bits8_offset; - if (i) - seq_puts(m, seq); + btf_show_start_member(show, member); - member_offset = btf_member_bit_offset(t, member); - bitfield_size = btf_member_bitfield_size(t, member); + member_offset = __btf_member_bit_offset(t, member); + bitfield_size = __btf_member_bitfield_size(t, member); bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); bits8_offset = BITS_PER_BYTE_MASKED(member_offset); if (bitfield_size) { - btf_bitfield_seq_show(data + bytes_offset, bits8_offset, - bitfield_size, m); + safe_data = btf_show_start_type(show, member_type, + member->type, + data + bytes_offset); + if (safe_data) + btf_bitfield_show(safe_data, + bits8_offset, + bitfield_size, show); + btf_show_end_type(show); } else { ops = btf_type_ops(member_type); - ops->seq_show(btf, member_type, member->type, - data + bytes_offset, bits8_offset, m); + ops->show(btf, member_type, member->type, + data + bytes_offset, bits8_offset, show); + } + + btf_show_end_member(show); + } + + btf_show_end_struct_type(show); +} + +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) +{ + const struct btf_member *m = show->state.member; + + /* + * First check if any members would be shown (are non-zero). + * See comments above "struct btf_show" definition for more + * details on how this works at a high-level. + */ + if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) { + if (!show->state.depth_check) { + show->state.depth_check = show->state.depth + 1; + show->state.depth_to_show = 0; } + __btf_struct_show(btf, t, type_id, data, bits_offset, show); + /* Restore saved member data here */ + show->state.member = m; + if (show->state.depth_check != show->state.depth + 1) + return; + show->state.depth_check = 0; + + if (show->state.depth_to_show <= show->state.depth) + return; + /* + * Reaching here indicates we have recursed and found + * non-zero child values. + */ } - seq_puts(m, "}"); + + __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, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_struct_log, - .seq_show = btf_struct_seq_show, + .show = btf_struct_show, }; static int btf_enum_check_member(struct btf_verifier_env *env, @@ -2468,6 +4285,7 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, { const struct btf_enum *enums = btf_type_enum(t); struct btf *btf = env->btf; + const char *fmt_str; u16 i, nr_enums; u32 meta_needed; @@ -2481,11 +4299,6 @@ static s32 btf_enum_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; - } - if (t->size > 8 || !is_power_of_2(t->size)) { btf_verifier_log_type(env, t, "Unexpected size"); return -EINVAL; @@ -2516,7 +4329,8 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, if (env->log.level == BPF_LOG_KERNEL) continue; - btf_verifier_log(env, "\t%s val=%d\n", + fmt_str = btf_type_kflag(t) ? "\t%s val=%d\n" : "\t%s val=%u\n"; + btf_verifier_log(env, fmt_str, __btf_name_by_offset(btf, enums[i].name_off), enums[i].val); } @@ -2530,33 +4344,150 @@ static void btf_enum_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t, - u32 type_id, void *data, u8 bits_offset, - struct seq_file *m) +static void btf_enum_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) { const struct btf_enum *enums = btf_type_enum(t); u32 i, nr_enums = btf_type_vlen(t); - int v = *(int *)data; + void *safe_data; + int v; + + safe_data = btf_show_start_type(show, t, type_id, data); + if (!safe_data) + return; + + v = *(int *)safe_data; for (i = 0; i < nr_enums; i++) { - if (v == enums[i].val) { - seq_printf(m, "%s", - __btf_name_by_offset(btf, - enums[i].name_off)); - return; - } + if (v != enums[i].val) + continue; + + btf_show_type_value(show, "%s", + __btf_name_by_offset(btf, + enums[i].name_off)); + + btf_show_end_type(show); + return; } - seq_printf(m, "%d", v); + if (btf_type_kflag(t)) + btf_show_type_value(show, "%d", v); + else + btf_show_type_value(show, "%u", v); + 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, .check_kflag_member = btf_enum_check_kflag_member, .log_details = btf_enum_log, - .seq_show = btf_enum_seq_show, + .show = btf_enum_show, +}; + +static s32 btf_enum64_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_enum64 *enums = btf_type_enum64(t); + struct btf *btf = env->btf; + const char *fmt_str; + u16 i, nr_enums; + u32 meta_needed; + + nr_enums = btf_type_vlen(t); + meta_needed = nr_enums * sizeof(*enums); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (t->size > 8 || !is_power_of_2(t->size)) { + btf_verifier_log_type(env, t, "Unexpected size"); + return -EINVAL; + } + + /* enum type either no name or a valid one */ + if (t->name_off && + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for (i = 0; i < nr_enums; i++) { + if (!btf_name_offset_valid(btf, enums[i].name_off)) { + btf_verifier_log(env, "\tInvalid name_offset:%u", + enums[i].name_off); + return -EINVAL; + } + + /* enum member must have a valid name */ + if (!enums[i].name_off || + !btf_name_valid_identifier(btf, enums[i].name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + if (env->log.level == BPF_LOG_KERNEL) + continue; + + fmt_str = btf_type_kflag(t) ? "\t%s val=%lld\n" : "\t%s val=%llu\n"; + btf_verifier_log(env, fmt_str, + __btf_name_by_offset(btf, enums[i].name_off), + btf_enum64_value(enums + i)); + } + + return meta_needed; +} + +static void btf_enum64_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) +{ + const struct btf_enum64 *enums = btf_type_enum64(t); + u32 i, nr_enums = btf_type_vlen(t); + void *safe_data; + s64 v; + + safe_data = btf_show_start_type(show, t, type_id, data); + if (!safe_data) + return; + + v = *(u64 *)safe_data; + + for (i = 0; i < nr_enums; i++) { + if (v != btf_enum64_value(enums + i)) + continue; + + btf_show_type_value(show, "%s", + __btf_name_by_offset(btf, + enums[i].name_off)); + + btf_show_end_type(show); + return; + } + + if (btf_type_kflag(t)) + btf_show_type_value(show, "%lld", v); + else + btf_show_type_value(show, "%llu", v); + btf_show_end_type(show); +} + +static const struct btf_kind_operations enum64_ops = { + .check_meta = btf_enum64_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_enum_check_member, + .check_kflag_member = btf_enum_check_kflag_member, + .log_details = btf_enum_log, + .show = btf_enum64_show, }; static s32 btf_func_proto_check_meta(struct btf_verifier_env *env, @@ -2628,14 +4559,14 @@ 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, /* * BTF_KIND_FUNC_PROTO cannot be directly referred by * a struct's member. * - * It should be a funciton pointer instead. + * It should be a function pointer instead. * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO) * * Hence, there is no btf_func_check_member(). @@ -2643,7 +4574,7 @@ static struct btf_kind_operations func_proto_ops = { .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_func_proto_log, - .seq_show = btf_df_seq_show, + .show = btf_df_show, }; static s32 btf_func_check_meta(struct btf_verifier_env *env, @@ -2671,13 +4602,28 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env, return 0; } -static struct btf_kind_operations func_ops = { +static int btf_func_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + int err; + + err = btf_func_check(env, t); + if (err) + return err; + + env_stack_pop_resolved(env, next_type_id, 0); + return 0; +} + +static const struct btf_kind_operations func_ops = { .check_meta = btf_func_check_meta, - .resolve = btf_df_resolve, + .resolve = btf_func_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_ref_type_log, - .seq_show = btf_df_seq_show, + .show = btf_df_show, }; static s32 btf_var_check_meta(struct btf_verifier_env *env, @@ -2705,7 +4651,7 @@ 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; } @@ -2741,7 +4687,7 @@ static const struct btf_kind_operations var_ops = { .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_var_log, - .seq_show = btf_var_seq_show, + .show = btf_var_show, }; static s32 btf_datasec_check_meta(struct btf_verifier_env *env, @@ -2760,11 +4706,6 @@ static s32 btf_datasec_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (!btf_type_vlen(t)) { - btf_verifier_log_type(env, t, "vlen == 0"); - return -EINVAL; - } - if (!t->size) { btf_verifier_log_type(env, t, "size == 0"); return -EINVAL; @@ -2829,6 +4770,7 @@ 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, @@ -2867,24 +4809,28 @@ static void btf_datasec_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -static void btf_datasec_seq_show(const struct btf *btf, - const struct btf_type *t, u32 type_id, - void *data, u8 bits_offset, - struct seq_file *m) +static void btf_datasec_show(const struct btf *btf, + const struct btf_type *t, u32 type_id, + void *data, u8 bits_offset, + struct btf_show *show) { const struct btf_var_secinfo *vsi; const struct btf_type *var; u32 i; - seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off)); + if (!btf_show_start_type(show, t, type_id, data)) + return; + + btf_show_type_value(show, "section (\"%s\") = {", + __btf_name_by_offset(btf, t->name_off)); for_each_vsi(i, t, vsi) { var = btf_type_by_id(btf, vsi->type); if (i) - seq_puts(m, ","); - btf_type_ops(var)->seq_show(btf, var, vsi->type, - data + vsi->offset, bits_offset, m); + btf_show(show, ","); + btf_type_ops(var)->show(btf, var, vsi->type, + data + vsi->offset, bits_offset, show); } - seq_puts(m, "}"); + btf_show_end_type(show); } static const struct btf_kind_operations datasec_ops = { @@ -2893,7 +4839,186 @@ static const struct btf_kind_operations datasec_ops = { .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_datasec_log, - .seq_show = btf_datasec_seq_show, + .show = btf_datasec_show, +}; + +static s32 btf_float_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + if (t->size != 2 && t->size != 4 && t->size != 8 && t->size != 12 && + t->size != 16) { + btf_verifier_log_type(env, t, "Invalid type_size"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static int btf_float_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u64 start_offset_bytes; + u64 end_offset_bytes; + u64 misalign_bits; + u64 align_bytes; + u64 align_bits; + + /* Different architectures have different alignment requirements, so + * here we check only for the reasonable minimum. This way we ensure + * that types after CO-RE can pass the kernel BTF verifier. + */ + align_bytes = min_t(u64, sizeof(void *), member_type->size); + align_bits = align_bytes * BITS_PER_BYTE; + div64_u64_rem(member->offset, align_bits, &misalign_bits); + if (misalign_bits) { + btf_verifier_log_member(env, struct_type, member, + "Member is not properly aligned"); + return -EINVAL; + } + + start_offset_bytes = member->offset / BITS_PER_BYTE; + end_offset_bytes = start_offset_bytes + member_type->size; + if (end_offset_bytes > struct_type->size) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static void btf_float_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u", t->size); +} + +static const struct btf_kind_operations float_ops = { + .check_meta = btf_float_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_float_check_member, + .check_kflag_member = btf_generic_check_kflag_member, + .log_details = btf_float_log, + .show = btf_df_show, +}; + +static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_decl_tag *tag; + u32 meta_needed = sizeof(*tag); + s32 component_idx; + const char *value; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid value"); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + 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"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_decl_tag_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + s32 component_idx; + u32 vlen; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type || !btf_type_is_decl_tag_target(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + component_idx = btf_type_decl_tag(t)->component_idx; + if (component_idx != -1) { + if (btf_type_is_var(next_type) || btf_type_is_typedef(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + + if (btf_type_is_struct(next_type)) { + vlen = btf_type_vlen(next_type); + } else { + /* next_type should be a function */ + next_type = btf_type_by_id(btf, next_type->type); + vlen = btf_type_vlen(next_type); + } + + if ((u32)component_idx >= vlen) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + } + + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +{ + btf_verifier_log(env, "type=%u component_idx=%d", t->type, + btf_type_decl_tag(t)->component_idx); +} + +static const struct btf_kind_operations decl_tag_ops = { + .check_meta = btf_decl_tag_check_meta, + .resolve = btf_decl_tag_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_decl_tag_log, + .show = btf_df_show, }; static int btf_func_proto_check(struct btf_verifier_env *env, @@ -2919,6 +5044,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env, return -EINVAL; } + if (btf_type_is_resolve_source_only(ret_type)) { + btf_verifier_log_type(env, t, "Invalid return type"); + return -EINVAL; + } + if (btf_type_needs_resolve(ret_type) && !env_type_is_resolved(env, ret_type_id)) { err = btf_resolve(env, ret_type, ret_type_id); @@ -2946,7 +5076,6 @@ static int btf_func_proto_check(struct btf_verifier_env *env, nr_args--; } - err = 0; for (i = 0; i < nr_args; i++) { const struct btf_type *arg_type; u32 arg_type_id; @@ -2955,8 +5084,12 @@ static int btf_func_proto_check(struct btf_verifier_env *env, arg_type = btf_type_by_id(btf, arg_type_id); if (!arg_type) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); - err = -EINVAL; - break; + return -EINVAL; + } + + if (btf_type_is_resolve_source_only(arg_type)) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + return -EINVAL; } if (args[i].name_off && @@ -2964,25 +5097,23 @@ static int btf_func_proto_check(struct btf_verifier_env *env, !btf_name_valid_identifier(btf, args[i].name_off))) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); - err = -EINVAL; - break; + return -EINVAL; } if (btf_type_needs_resolve(arg_type) && !env_type_is_resolved(env, arg_type_id)) { err = btf_resolve(env, arg_type, arg_type_id); if (err) - break; + return err; } if (!btf_type_id_size(btf, &arg_type_id, NULL)) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); - err = -EINVAL; - break; + return -EINVAL; } } - return err; + return 0; } static int btf_func_check(struct btf_verifier_env *env, @@ -3029,6 +5160,10 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_FUNC_PROTO] = &func_proto_ops, [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, + [BTF_KIND_FLOAT] = &float_ops, + [BTF_KIND_DECL_TAG] = &decl_tag_ops, + [BTF_KIND_TYPE_TAG] = &modifier_ops, + [BTF_KIND_ENUM64] = &enum64_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -3083,7 +5218,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env) cur = btf->nohdr_data + hdr->type_off; end = cur + hdr->type_len; - env->log_type_id = 1; + env->log_type_id = btf->base_btf ? btf->start_id : 1; while (cur < end) { struct btf_type *t = cur; s32 meta_size; @@ -3110,8 +5245,12 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return false; if (btf_type_is_struct(t) || btf_type_is_datasec(t)) - return !btf->resolved_ids[type_id] && - !btf->resolved_sizes[type_id]; + return !btf_resolved_type_id(btf, type_id) && + !btf_resolved_type_size(btf, type_id); + + if (btf_type_is_decl_tag(t) || btf_type_is_func(t)) + return btf_resolved_type_id(btf, type_id) && + !btf_resolved_type_size(btf, type_id); if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_var(t)) { @@ -3131,7 +5270,7 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); return elem_type && !btf_type_is_modifier(elem_type) && (array->nelems * elem_size == - btf->resolved_sizes[type_id]); + btf_resolved_type_size(btf, type_id)); } return false; @@ -3173,7 +5312,8 @@ static int btf_resolve(struct btf_verifier_env *env, static int btf_check_all_types(struct btf_verifier_env *env) { struct btf *btf = env->btf; - u32 type_id; + const struct btf_type *t; + u32 type_id, i; int err; err = env_resolve_init(env); @@ -3181,8 +5321,9 @@ static int btf_check_all_types(struct btf_verifier_env *env) return err; env->phase++; - for (type_id = 1; type_id <= btf->nr_types; type_id++) { - const struct btf_type *t = btf_type_by_id(btf, type_id); + for (i = btf->base_btf ? 0 : 1; i < btf->nr_types; i++) { + type_id = btf->start_id + i; + t = btf_type_by_id(btf, type_id); env->log_type_id = type_id; if (btf_type_needs_resolve(t) && @@ -3197,12 +5338,6 @@ static int btf_check_all_types(struct btf_verifier_env *env) if (err) return err; } - - if (btf_type_is_func(t)) { - err = btf_func_check(env, t); - if (err) - return err; - } } return 0; @@ -3219,7 +5354,7 @@ static int btf_parse_type_sec(struct btf_verifier_env *env) return -EINVAL; } - if (!hdr->type_len) { + if (!env->btf->base_btf && !hdr->type_len) { btf_verifier_log(env, "No type found"); return -EINVAL; } @@ -3246,13 +5381,18 @@ static int btf_parse_str_sec(struct btf_verifier_env *env) return -EINVAL; } - if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || - start[0] || end[-1]) { + btf->strings = start; + + if (btf->base_btf && !hdr->str_len) + return 0; + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || end[-1]) { + btf_verifier_log(env, "Invalid string section"); + return -EINVAL; + } + if (!btf->base_btf && start[0]) { btf_verifier_log(env, "Invalid string section"); return -EINVAL; } - - btf->strings = start; return 0; } @@ -3328,13 +5468,11 @@ static int btf_parse_hdr(struct btf_verifier_env *env) u32 hdr_len, hdr_copy, btf_data_size; const struct btf_header *hdr; struct btf *btf; - int err; btf = env->btf; btf_data_size = btf->data_size; - if (btf_data_size < - offsetof(struct btf_header, hdr_len) + sizeof(hdr->hdr_len)) { + if (btf_data_size < offsetofend(struct btf_header, hdr_len)) { btf_verifier_log(env, "hdr_len not found"); return -EINVAL; } @@ -3381,50 +5519,242 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return -ENOTSUPP; } - if (btf_data_size == hdr->hdr_len) { + if (!btf->base_btf && btf_data_size == hdr->hdr_len) { btf_verifier_log(env, "No data"); return -EINVAL; } - err = btf_check_sec_info(env, btf_data_size); - if (err) - return err; + return btf_check_sec_info(env, btf_data_size); +} + +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) +{ + 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)); + + 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; + + new_aof = krealloc(aof, offsetof(struct btf_id_set, 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, offsetof(struct btf_id_set, 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->cnt) { + kfree(aof); + return NULL; + } + sort(&aof->ids, aof->cnt, sizeof(aof->ids[0]), btf_id_cmp_func, NULL); + + for (i = 1; i < n; i++) { + struct btf_struct_metas *new_tab; + const struct btf_member *member; + 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 (!__btf_type_is_struct(t)) + continue; + + cond_resched(); + + for_each_member(j, t, member) { + 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]), + GFP_KERNEL | __GFP_NOWARN); + if (!new_tab) { + ret = -ENOMEM; + goto free; + } + if (!tab) + new_tab->cnt = 0; + tab = new_tab; + + type = &tab->types[tab->cnt]; + type->btf_id = i; + record = btf_parse_fields(btf, t, BPF_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; + } + type->record = record; + tab->cnt++; + } + kfree(aof); + return tab; +free: + btf_struct_metas_free(tab); +free_aof: + kfree(aof); + return ERR_PTR(ret); +} + +struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) +{ + struct btf_struct_metas *tab; + + BUILD_BUG_ON(offsetof(struct btf_struct_meta, btf_id) != 0); + tab = btf->struct_meta_tab; + if (!tab) + return NULL; + return bsearch(&btf_id, tab->types, tab->cnt, sizeof(tab->types[0]), btf_id_cmp_func); +} + +static int btf_check_type_tags(struct btf_verifier_env *env, + struct btf *btf, int start_id) +{ + int i, n, good_id = start_id - 1; + bool in_tags; + + n = btf_nr_types(btf); + for (i = start_id; i < n; i++) { + const struct btf_type *t; + int chain_limit = 32; + u32 cur_id = i; + + t = btf_type_by_id(btf, i); + if (!t) + return -EINVAL; + if (!btf_type_is_modifier(t)) + continue; + + cond_resched(); + + in_tags = btf_type_is_type_tag(t); + while (btf_type_is_modifier(t)) { + if (!chain_limit--) { + btf_verifier_log(env, "Max chain length or cycle detected"); + return -ELOOP; + } + if (btf_type_is_type_tag(t)) { + if (!in_tags) { + btf_verifier_log(env, "Type tags don't precede modifiers"); + return -EINVAL; + } + } else if (in_tags) { + in_tags = false; + } + if (cur_id <= good_id) + break; + /* Move to next type */ + cur_id = t->type; + t = btf_type_by_id(btf, cur_id); + if (!t) + return -EINVAL; + } + good_id = i; + } return 0; } -static struct btf *btf_parse(void __user *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 (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || - !log->level || !log->ubuf) { - 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) { @@ -3433,16 +5763,16 @@ static struct btf *btf_parse(void __user *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_user(data, btf_data, btf_data_size)) { + if (copy_from_bpfptr(data, btf_data, attr->btf_size)) { err = -EFAULT; goto errout; } @@ -3461,24 +5791,51 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, if (err) goto errout; - if (log->level && bpf_verifier_log_full(log)) { - err = -ENOSPC; + err = btf_check_type_tags(env, btf, 1); + if (err) + goto errout; + + struct_meta_tab = btf_parse_struct_metas(&env->log, btf); + if (IS_ERR(struct_meta_tab)) { + err = PTR_ERR(struct_meta_tab); goto errout; } + btf->struct_meta_tab = struct_meta_tab; + + if (struct_meta_tab) { + int i; + + for (i = 0; i < struct_meta_tab->cnt; i++) { + err = btf_check_and_fixup_fields(btf, struct_meta_tab->types[i].record); + if (err < 0) + 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); return btf; +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) @@ -3511,22 +5868,70 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -static const struct btf_member * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, 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)) { @@ -3535,30 +5940,30 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ - if (log->level & BPF_LOG_LEVEL) - bpf_log(log, "arg#%d type is not a struct\n", arg); - 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: @@ -3566,9 +5971,162 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, 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, @@ -3577,21 +6135,141 @@ 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) +{ + const struct btf_member *kctx_member; + const struct btf_type *conv_struct; + const struct btf_type *kctx_type; + u32 kctx_type_id; + + conv_struct = bpf_ctx_convert.t; + /* get member for kernel ctx type */ + kctx_member = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; + kctx_type_id = kctx_member->type; + kctx_type = btf_type_by_id(btf_vmlinux, kctx_type_id); + if (!btf_type_is_struct(kctx_type)) { + bpf_log(log, "kern ctx type id %u is not a struct\n", kctx_type_id); + return -EINVAL; + } + + return kctx_type_id; +} + +BTF_ID_LIST(bpf_ctx_convert_btf_id) +BTF_ID(struct, bpf_ctx_convert) + +static struct btf *btf_parse_base(struct btf_verifier_env *env, const char *name, + void *data, unsigned int data_size) +{ + struct btf *btf = NULL; + int err; + + if (!IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) + return ERR_PTR(-ENOENT); + + btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); + if (!btf) { + err = -ENOMEM; + goto errout; + } + env->btf = btf; + + btf->data = data; + btf->data_size = data_size; + btf->kernel_btf = true; + snprintf(btf->name, sizeof(btf->name), "%s", name); + + err = btf_parse_hdr(env); + if (err) + goto errout; + + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + + err = btf_parse_str_sec(env); + if (err) + goto errout; + + err = btf_check_all_metas(env); + if (err) + goto errout; + + err = btf_check_type_tags(env, btf, 1); + if (err) + goto errout; + + refcount_set(&btf->refcnt, 1); + + return btf; + +errout: + if (btf) { + kvfree(btf->types); + kfree(btf); + } + return ERR_PTR(err); } struct btf *btf_parse_vmlinux(void) { struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; - struct btf *btf = NULL; - int err, i; + 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, 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; + int err = 0; + + 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); if (!env) @@ -3600,6 +6278,16 @@ struct btf *btf_parse_vmlinux(void) 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; @@ -3607,8 +6295,18 @@ struct btf *btf_parse_vmlinux(void) } env->btf = btf; - btf->data = __start_BTF; - btf->data_size = __stop_BTF - __start_BTF; + btf->base_btf = base_btf; + btf->start_id = base_btf->nr_types; + btf->start_str_off = base_btf->hdr.str_len; + btf->kernel_btf = true; + snprintf(btf->name, sizeof(btf->name), "%s", module_name); + + btf->data = kvmemdup(data, data_size, GFP_KERNEL | __GFP_NOWARN); + if (!btf->data) { + err = -ENOMEM; + goto errout; + } + btf->data_size = data_size; err = btf_parse_hdr(env); if (err) @@ -3624,27 +6322,17 @@ struct btf *btf_parse_vmlinux(void) if (err) goto errout; - /* find struct bpf_ctx_convert for type checking later */ - for (i = 1; i <= btf->nr_types; i++) { - const struct btf_type *t; - const char *tname; - - t = btf_type_by_id(btf, i); - if (!__btf_type_is_struct(t)) - continue; - tname = __btf_name_by_offset(btf, t->name_off); - if (!strcmp(tname, "bpf_ctx_convert")) { - /* btf_parse_vmlinux() runs under bpf_verifier_lock */ - bpf_ctx_convert.t = t; - break; - } - } - if (i > btf->nr_types) { - err = -ENOENT; + err = btf_check_type_tags(env, btf, btf_nr_types(base_btf)); + if (err) goto errout; - } - bpf_struct_ops_init(btf, log); + 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); @@ -3652,47 +6340,209 @@ struct btf *btf_parse_vmlinux(void) 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); kfree(btf); } return ERR_PTR(err); } +#endif /* CONFIG_DEBUG_INFO_BTF_MODULES */ + struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) { - struct bpf_prog *tgt_prog = prog->aux->linked_prog; + struct bpf_prog *tgt_prog = prog->aux->dst_prog; - if (tgt_prog) { + if (tgt_prog) return tgt_prog->aux->btf; - } else { - return btf_vmlinux; + else + return prog->aux->attach_btf; +} + +static bool is_int_ptr(struct btf *btf, const struct btf_type *t) +{ + /* skip modifiers */ + t = btf_type_skip_modifiers(btf, t->type, NULL); + + return btf_type_is_int(t); +} + +static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, + int off) +{ + const struct btf_param *args; + const struct btf_type *t; + u32 offset = 0, nr_args; + int i; + + if (!func_proto) + return off / 8; + + nr_args = btf_type_vlen(func_proto); + args = (const struct btf_param *)(func_proto + 1); + for (i = 0; i < nr_args; i++) { + t = btf_type_skip_modifiers(btf, args[i].type, NULL); + offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8); + if (off < offset) + return i; } + + t = btf_type_skip_modifiers(btf, func_proto->type, NULL); + offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8); + if (off < offset) + return nr_args; + + return nr_args + 1; } -static bool is_string_ptr(struct btf *btf, const struct btf_type *t) +static bool prog_args_trusted(const struct bpf_prog *prog) { - /* t comes in already as a pointer */ - t = btf_type_by_id(btf, t->type); + enum bpf_attach_type atype = prog->expected_attach_type; - /* allow const */ - if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST) - t = btf_type_by_id(btf, t->type); + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + return atype == BPF_TRACE_RAW_TP || atype == BPF_TRACE_ITER; + case BPF_PROG_TYPE_LSM: + return bpf_lsm_is_trusted(prog); + case BPF_PROG_TYPE_STRUCT_OPS: + return true; + default: + return false; + } +} - /* char, signed char, unsigned char */ - return btf_type_is_int(t) && t->size == 1; +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 }, + /* 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 }, + /* 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 }, +}; + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const struct btf_type *t = prog->aux->attach_func_proto; - struct bpf_prog *tgt_prog = prog->aux->linked_prog; + struct bpf_prog *tgt_prog = prog->aux->dst_prog; struct btf *btf = bpf_prog_get_target_btf(prog); 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; @@ -3701,10 +6551,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, tname, off); return false; } - arg = off / 8; + arg = get_ctx_arg_idx(btf, t, off); args = (const struct btf_param *)(t + 1); - /* if (t == NULL) Fall back to default BPF prog with 5 u64 arguments */ - nr_args = t ? btf_type_vlen(t) : 5; + /* if (t == NULL) Fall back to default BPF prog with + * MAX_BPF_FUNC_REG_ARGS u64 arguments. + */ + nr_args = t ? btf_type_vlen(t) : MAX_BPF_FUNC_REG_ARGS; if (prog->aux->attach_btf_trace) { /* skip first 'void *__data' argument in btf_trace_##name typedef */ args++; @@ -3720,6 +6572,10 @@ 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_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 @@ -3749,7 +6605,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (!btf_type_is_small_int(t)) { bpf_log(log, "ret type %s not allowed for fmod_ret\n", - btf_kind_str[BTF_INFO_KIND(t->info)]); + btf_type_str(t)); return false; } break; @@ -3760,7 +6616,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } } else { if (!t) - /* Default prog with 5 args */ + /* Default prog with MAX_BPF_FUNC_REG_ARGS args */ return true; t = btf_type_by_id(btf, args[arg].type); } @@ -3768,7 +6624,7 @@ 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_type_is_enum(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)) { @@ -3776,9 +6632,30 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, "func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", tname, arg, __btf_name_by_offset(btf, t->name_off), - btf_kind_str[BTF_INFO_KIND(t->info)]); + btf_type_str(t)); 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]; + u32 type, flag; + + type = base_type(ctx_arg_info->reg_type); + flag = type_flag(ctx_arg_info->reg_type); + if (ctx_arg_info->offset == off && type == PTR_TO_BUF && + (flag & PTR_MAYBE_NULL)) { + info->reg_type = ctx_arg_info->reg_type; + return true; + } + } + if (t->type == 0) /* This is a pointer to void. * It is the same as scalar from the verifier safety pov. @@ -3786,23 +6663,77 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, */ return true; - if (is_string_ptr(btf, t)) + if (is_int_ptr(btf, t)) return true; /* this is a pointer to another type */ - info->reg_type = PTR_TO_BTF_ID; 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]; if (ctx_arg_info->offset == off) { + if (!ctx_arg_info->btf_id) { + bpf_log(log,"invalid btf_id for context argument offset %u\n", off); + return false; + } + info->reg_type = ctx_arg_info->reg_type; + info->btf = ctx_arg_info->btf ? : btf_vmlinux; + info->btf_id = ctx_arg_info->btf_id; + return true; + } + } + + info->reg_type = PTR_TO_BTF_ID; + 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 & (0x1 << (arg * 4))) + info->reg_type |= PTR_MAYBE_NULL; + /* Is the current arg IS_ERR? */ + if (raw_tp_null_args[i].mask & (0x2 << (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) { - ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg); + enum bpf_prog_type tgt_type; + + if (tgt_prog->type == BPF_PROG_TYPE_EXT) + tgt_type = tgt_prog->aux->saved_dst_prog_type; + else + tgt_type = tgt_prog->type; + + ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg); if (ret > 0) { + info->btf = btf_vmlinux; info->btf_id = ret; return true; } else { @@ -3810,8 +6741,18 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } } + info->btf = btf; info->btf_id = t->type; t = btf_type_by_id(btf, t->type); + + if (btf_type_is_type_tag(t)) { + tag_value = __btf_name_by_offset(btf, t->name_off); + if (strcmp(tag_value, "user") == 0) + info->reg_type |= MEM_USER; + if (strcmp(tag_value, "percpu") == 0) + info->reg_type |= MEM_PERCPU; + } + /* skip modifiers */ while (btf_type_is_modifier(t)) { info->btf_id = t->type; @@ -3820,34 +6761,61 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (!btf_type_is_struct(t)) { bpf_log(log, "func '%s' arg%d type %s is not a struct\n", - tname, arg, btf_kind_str[BTF_INFO_KIND(t->info)]); + tname, arg, btf_type_str(t)); return false; } bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", - tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)], + 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); -int btf_struct_access(struct bpf_verifier_log *log, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, - u32 *next_btf_id) +enum bpf_struct_walk_result { + /* < 0 error */ + WALK_SCALAR = 0, + WALK_PTR, + 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, + const char **field_name) { u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; const struct btf_type *mtype, *elem_type = NULL; const struct btf_member *member; - const char *tname, *mname; - u32 vlen; + const char *tname, *mname, *tag_value; + u32 vlen, elem_id, mid; again: - tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + 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); return -EINVAL; } 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. @@ -3858,7 +6826,7 @@ again: goto error; member = btf_type_member(t) + vlen - 1; - mtype = btf_type_skip_modifiers(btf_vmlinux, member->type, + mtype = btf_type_skip_modifiers(btf, member->type, NULL); if (!btf_type_is_array(mtype)) goto error; @@ -3867,21 +6835,22 @@ again: if (array_elem->nelems != 0) goto error; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off < moff) goto error; - /* Only allow structure for now, can be relaxed for - * other types later. - */ - elem_type = btf_type_skip_modifiers(btf_vmlinux, - array_elem->type, NULL); - if (!btf_type_is_struct(elem_type)) + /* 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; - off = (off - moff) % elem_type->size; - return btf_struct_access(log, elem_type, off, size, atype, - next_btf_id); + off = (off - moff) % t->size; + goto again; error: bpf_log(log, "access beyond struct %s at off %u size %u\n", @@ -3891,14 +6860,14 @@ error: for_each_member(i, t, member) { /* offset of the field in bytes */ - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off + size <= moff) /* won't find anything, field is already too far */ break; - if (btf_member_bitfield_size(t, member)) { - u32 end_bit = btf_member_bit_offset(t, member) + - btf_member_bitfield_size(t, member); + if (__btf_member_bitfield_size(t, member)) { + u32 end_bit = __btf_member_bit_offset(t, member) + + __btf_member_bitfield_size(t, member); /* off <= moff instead of off == moff because clang * does not generate a BTF member for anonymous @@ -3910,7 +6879,7 @@ error: */ if (off <= moff && BITS_ROUNDUP_BYTES(end_bit) <= off + size) - return SCALAR_VALUE; + return WALK_SCALAR; /* off may be accessing a following member * @@ -3932,11 +6901,13 @@ error: break; /* type of the field */ - mtype = btf_type_by_id(btf_vmlinux, member->type); - mname = __btf_name_by_offset(btf_vmlinux, member->name_off); + mid = member->type; + mtype = btf_type_by_id(btf, member->type); + mname = __btf_name_by_offset(btf, member->name_off); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, - &elem_type, &total_nelems); + mtype = __btf_resolve_size(btf, mtype, &msize, + &elem_type, &elem_id, &total_nelems, + &mid); if (IS_ERR(mtype)) { bpf_log(log, "field %s doesn't have size\n", mname); return -EFAULT; @@ -3950,7 +6921,7 @@ error: if (btf_type_is_array(mtype)) { u32 elem_idx; - /* btf_resolve_size() above helps to + /* __btf_resolve_size() above helps to * linearize a multi-dimensional array. * * The logic here is treating an array @@ -3998,6 +6969,7 @@ error: elem_idx = (off - moff) / msize; moff += elem_idx * msize; mtype = elem_type; + mid = elem_id; } /* the 'off' we're looking for is either equal to start @@ -4007,13 +6979,20 @@ error: /* our field must be inside that union or struct */ t = mtype; + /* return if the offset matches the member offset */ + if (off == moff) { + *next_btf_id = mid; + return WALK_STRUCT; + } + /* adjust offset we're looking for */ off -= moff; goto again; } if (btf_type_is_ptr(mtype)) { - const struct btf_type *stype; + const struct btf_type *stype, *t; + enum bpf_type_flag tmp_flag = 0; u32 id; if (msize != size || off != moff) { @@ -4023,10 +7002,28 @@ error: return -EACCES; } - stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); + /* check type tag */ + t = btf_type_by_id(btf, mtype->type); + if (btf_type_is_type_tag(t)) { + tag_value = __btf_name_by_offset(btf, t->name_off); + /* check __user tag */ + if (strcmp(tag_value, "user") == 0) + tmp_flag = MEM_USER; + /* check __percpu tag */ + if (strcmp(tag_value, "percpu") == 0) + tmp_flag = MEM_PERCPU; + /* check __rcu tag */ + if (strcmp(tag_value, "rcu") == 0) + tmp_flag = MEM_RCU; + } + + stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; - return PTR_TO_BTF_ID; + *flag |= tmp_flag; + if (field_name) + *field_name = mname; + return WALK_PTR; } } @@ -4036,140 +7033,182 @@ 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); return -EACCES; } - return SCALAR_VALUE; + return WALK_SCALAR; } bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off); return -EINVAL; } -static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, - int arg) +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, + const char **field_name) { - char fnname[KSYM_SYMBOL_LEN + 4] = "btf_"; - const struct btf_param *args; + const struct btf *btf = reg->btf; + enum bpf_type_flag tmp_flag = 0; const struct btf_type *t; - const char *tname, *sym; - u32 btf_id, i; + u32 id = reg->btf_id; + int err; - if (!btf_vmlinux) { - bpf_log(log, "btf_vmlinux doesn't exist\n"); - return -EINVAL; - } + while (type_is_alloc(reg->type)) { + struct btf_struct_meta *meta; + struct btf_record *rec; + int i; - if (IS_ERR(btf_vmlinux)) { - bpf_log(log, "btf_vmlinux is malformed\n"); - return -EINVAL; + meta = btf_find_struct_meta(btf, id); + if (!meta) + break; + rec = meta->record; + for (i = 0; i < rec->cnt; i++) { + struct btf_field *field = &rec->fields[i]; + u32 offset = field->offset; + if (off < offset + field->size && offset < off + size) { + bpf_log(log, + "direct access to %s is disallowed\n", + btf_field_type_name(field->type)); + return -EACCES; + } + } + break; } - sym = kallsyms_lookup((long)fn, NULL, NULL, NULL, fnname + 4); - if (!sym) { - bpf_log(log, "kernel doesn't have kallsyms\n"); - return -EFAULT; - } + t = btf_type_by_id(btf, id); + do { + err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag, field_name); - for (i = 1; i <= btf_vmlinux->nr_types; i++) { - t = btf_type_by_id(btf_vmlinux, i); - if (BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) - continue; - tname = __btf_name_by_offset(btf_vmlinux, t->name_off); - if (!strcmp(tname, fnname)) + switch (err) { + case WALK_PTR: + /* For local types, the destination register cannot + * become a pointer again. + */ + if (type_is_alloc(reg->type)) + return SCALAR_VALUE; + /* If we found the pointer or scalar on t+off, + * we're done. + */ + *next_btf_id = id; + *flag = tmp_flag; + return PTR_TO_BTF_ID; + case WALK_SCALAR: + return SCALAR_VALUE; + case WALK_STRUCT: + /* We found nested struct, so continue the search + * by diving in it. At this point the offset is + * aligned with the new type, so set it to 0. + */ + t = btf_type_by_id(btf, id); + off = 0; break; - } - if (i > btf_vmlinux->nr_types) { - bpf_log(log, "helper %s type is not found\n", fnname); - return -ENOENT; - } - - t = btf_type_by_id(btf_vmlinux, t->type); - if (!btf_type_is_ptr(t)) - return -EFAULT; - t = btf_type_by_id(btf_vmlinux, t->type); - if (!btf_type_is_func_proto(t)) - return -EFAULT; + default: + /* It's either error or unknown return value.. + * scream and leave. + */ + if (WARN_ONCE(err > 0, "unknown btf_struct_walk return value")) + return -EINVAL; + return err; + } + } while (t); - args = (const struct btf_param *)(t + 1); - if (arg >= btf_type_vlen(t)) { - bpf_log(log, "bpf helper %s doesn't have %d-th argument\n", - fnname, arg); - return -EINVAL; - } + return -EINVAL; +} - t = btf_type_by_id(btf_vmlinux, args[arg].type); - if (!btf_type_is_ptr(t) || !t->type) { - /* anything but the pointer to struct is a helper config bug */ - bpf_log(log, "ARG_PTR_TO_BTF is misconfigured\n"); - return -EFAULT; - } - btf_id = t->type; - t = btf_type_by_id(btf_vmlinux, t->type); - /* skip modifiers */ - while (btf_type_is_modifier(t)) { - btf_id = t->type; - t = btf_type_by_id(btf_vmlinux, t->type); - } - if (!btf_type_is_struct(t)) { - bpf_log(log, "ARG_PTR_TO_BTF is not a struct\n"); - return -EFAULT; - } - bpf_log(log, "helper %s arg%d has btf_id %d struct %s\n", fnname + 4, - arg, btf_id, __btf_name_by_offset(btf_vmlinux, t->name_off)); - return btf_id; +/* Check that two BTF types, each specified as an BTF object + id, are exactly + * the same. Trivial ID check is not enough due to module BTFs, because we can + * end up with two different module BTFs, but IDs point to the common type in + * vmlinux BTF. + */ +bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) +{ + if (id1 != id2) + return false; + if (btf1 == btf2) + return true; + return btf_type_by_id(btf1, id1) == btf_type_by_id(btf2, id2); } -int btf_resolve_helper_id(struct bpf_verifier_log *log, - const struct bpf_func_proto *fn, int arg) +bool btf_struct_ids_match(struct bpf_verifier_log *log, + const struct btf *btf, u32 id, int off, + const struct btf *need_btf, u32 need_type_id, + bool strict) { - int *btf_id = &fn->btf_id[arg]; - int ret; + const struct btf_type *type; + enum bpf_type_flag flag = 0; + int err; - if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID) - return -EINVAL; + /* Are we already done? */ + if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id)) + return true; + /* In case of strict type match, we do not walk struct, the top level + * type match must succeed. When strict is true, off should have already + * been 0. + */ + if (strict) + return false; +again: + type = btf_type_by_id(btf, id); + if (!type) + return false; + err = btf_struct_walk(log, btf, type, off, 1, &id, &flag, NULL); + if (err != WALK_STRUCT) + return false; - ret = READ_ONCE(*btf_id); - if (ret) - return ret; - /* ok to race the search. The result is the same */ - ret = __btf_resolve_helper_id(log, fn->func, arg); - if (!ret) { - /* Function argument cannot be type 'void' */ - bpf_log(log, "BTF resolution bug\n"); - return -EFAULT; + /* We found nested struct object. If it matches + * the requested ID, we're done. Otherwise let's + * continue the search with offset 0 in the new + * type. + */ + if (!btf_types_are_same(btf, id, need_btf, need_type_id)) { + off = 0; + goto again; } - WRITE_ONCE(*btf_id, ret); - return ret; + + return true; } static int __get_type_size(struct btf *btf, u32 btf_id, - const struct btf_type **bad_type) + const struct btf_type **ret_type) { const struct btf_type *t; + *ret_type = btf_type_by_id(btf, 0); if (!btf_id) /* void */ return 0; t = btf_type_by_id(btf, btf_id); while (t && btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (!t) { - *bad_type = btf->types[0]; + if (!t) return -EINVAL; - } + *ret_type = t; 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_type_is_enum(t)) + if (btf_type_is_int(t) || btf_is_any_enum(t) || __btf_type_is_struct(t)) return t->size; - *bad_type = t; 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, @@ -4183,40 +7222,59 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, if (!func) { /* BTF function prototype doesn't match the verifier types. - * Fall back to 5 u64 args. + * Fall back to MAX_BPF_FUNC_REG_ARGS u64 args. */ - for (i = 0; i < 5; i++) + for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { m->arg_size[i] = 8; + m->arg_flags[i] = 0; + } m->ret_size = 8; - m->nr_args = 5; + m->ret_flags = 0; + m->nr_args = MAX_BPF_FUNC_REG_ARGS; return 0; } args = (const struct btf_param *)(func + 1); nargs = btf_type_vlen(func); - if (nargs >= MAX_BPF_FUNC_ARGS) { + if (nargs > MAX_BPF_FUNC_ARGS) { bpf_log(log, "The function %s has %d arguments. Too many.\n", tname, nargs); return -EINVAL; } ret = __get_type_size(btf, func->type, &t); - if (ret < 0) { + if (ret < 0 || __btf_type_is_struct(t)) { bpf_log(log, "The function %s return type %s is unsupported.\n", - tname, btf_kind_str[BTF_INFO_KIND(t->info)]); + 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) { + bpf_log(log, + "The function %s with variable args is unsupported.\n", + tname); + return -EINVAL; + } ret = __get_type_size(btf, args[i].type, &t); - if (ret < 0) { + + /* No support of struct argument size greater than 16 bytes */ + if (ret < 0 || ret > 16) { bpf_log(log, "The function %s arg%d type %s is unsupported.\n", - tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]); + tname, i, btf_type_str(t)); + return -EINVAL; + } + if (ret == 0) { + bpf_log(log, + "The function %s has malformed void argument.\n", + tname); return -EINVAL; } m->arg_size[i] = ret; + m->arg_flags[i] = __get_type_fmodel_flags(t); } m->nr_args = nargs; return 0; @@ -4300,7 +7358,7 @@ static int btf_check_func_type_match(struct bpf_verifier_log *log, * to context only. And only global functions can be replaced. * Hence type check only those types. */ - if (btf_type_is_int(t1) || btf_type_is_enum(t1)) + if (btf_type_is_int(t1) || btf_is_any_enum(t1)) continue; if (!btf_type_is_ptr(t1)) { bpf_log(log, @@ -4341,7 +7399,7 @@ static int btf_check_func_type_match(struct bpf_verifier_log *log, } /* Compare BTFs of given program with BTF of target program */ -int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, +int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf2, const struct btf_type *t2) { struct btf *btf1 = prog->aux->btf; @@ -4349,7 +7407,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, u32 btf_id = 0; if (!prog->aux->func_info) { - bpf_log(&env->log, "Program extension requires BTF\n"); + bpf_log(log, "Program extension requires BTF\n"); return -EINVAL; } @@ -4361,139 +7419,142 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, if (!t1 || !btf_type_is_func(t1)) return -EFAULT; - return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2); + return btf_check_func_type_match(log, btf1, t1, btf2, t2); } -/* Compare BTF of a function 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_func_arg_match(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg) +static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) { - struct bpf_verifier_log *log = &env->log; - struct bpf_prog *prog = env->prog; - struct btf *btf = prog->aux->btf; - const struct btf_param *args; - const struct btf_type *t; - u32 i, nargs, btf_id; - const char *tname; + const char *name; - if (!prog->aux->func_info) - return -EINVAL; + t = btf_type_by_id(btf, t->type); /* skip PTR */ - btf_id = prog->aux->func_info[subprog].type_id; - if (!btf_id) - return -EFAULT; - - if (prog->aux->func_info_aux[subprog].unreliable) - return -EINVAL; + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); - t = btf_type_by_id(btf, btf_id); - if (!t || !btf_type_is_func(t)) { - /* These checks were already done by the verifier while loading - * struct bpf_func_info - */ - bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n", - subprog); - return -EFAULT; + /* 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; } - tname = btf_name_by_offset(btf, t->name_off); + return false; +} + +struct bpf_cand_cache { + const char *name; + u32 name_len; + u16 kind; + u16 cnt; + struct { + const struct btf *btf; + u32 id; + } cands[]; +}; + +static DEFINE_MUTEX(cand_cache_mutex); + +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id); + +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_cand_cache *cc; + struct bpf_core_ctx ctx = { + .btf = btf, + .log = log, + }; + u32 kern_type_id, type_id; + int err = 0; + + /* skip PTR and modifiers */ + type_id = t->type; 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", tname); - return -EFAULT; - } - args = (const struct btf_param *)(t + 1); - nargs = btf_type_vlen(t); - if (nargs > 5) { - bpf_log(log, "Function %s has %d > 5 args\n", tname, nargs); - goto out; - } - /* check that BTF function arguments match actual types that the - * verifier sees. - */ - for (i = 0; i < nargs; i++) { - 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_type_is_enum(t)) { - if (reg[i + 1].type == SCALAR_VALUE) - continue; - bpf_log(log, "R%d is not a scalar\n", i + 1); - goto out; - } - if (btf_type_is_ptr(t)) { - if (reg[i + 1].type == SCALAR_VALUE) { - bpf_log(log, "R%d is not a pointer\n", i + 1); - goto out; - } - /* If function expects ctx type in BTF check that caller - * is passing PTR_TO_CTX. - */ - if (btf_get_prog_ctx_type(log, btf, t, prog->type, i)) { - if (reg[i + 1].type != PTR_TO_CTX) { - bpf_log(log, - "arg#%d expected pointer to ctx, but got %s\n", - i, btf_kind_str[BTF_INFO_KIND(t->info)]); - goto out; - } - if (check_ctx_reg(env, ®[i + 1], i + 1)) - goto out; - continue; - } - } - bpf_log(log, "Unrecognized arg#%d type %s\n", - i, btf_kind_str[BTF_INFO_KIND(t->info)]); - goto out; + while (btf_type_is_modifier(t)) { + type_id = t->type; + t = btf_type_by_id(btf, t->type); } - return 0; -out: - /* 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. - */ - prog->aux->func_info_aux[subprog].unreliable = true; - return -EINVAL; + + 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) + 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_NULLABLE = BIT_ULL(3), + ARG_TAG_ARENA = BIT_ULL(4), +}; + +/* 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 *reg) +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; + const struct btf_type *t, *ref_t, *fn_t; u32 i, nargs, btf_id; const char *tname; - if (!prog->aux->func_info || - prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) { + if (sub->args_cached) + return 0; + + if (!prog->aux->func_info) { bpf_log(log, "Verifier bug\n"); return -EFAULT; } btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) { + if (!is_global) /* not fatal for static funcs */ + return -EINVAL; bpf_log(log, "Global functions need valid BTF\n"); return -EFAULT; } - t = btf_type_by_id(btf, btf_id); - if (!t || !btf_type_is_func(t)) { + fn_t = btf_type_by_id(btf, btf_id); + if (!fn_t || !btf_type_is_func(fn_t)) { /* These checks were already done by the verifier while loading * struct bpf_func_info */ @@ -4501,36 +7562,36 @@ 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); return -EFAULT; } if (prog_type == BPF_PROG_TYPE_EXT) - prog_type = prog->aux->linked_prog->type; + 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; } args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); - if (nargs > 5) { - bpf_log(log, "Global function %s() with %d > 5 args. Buggy compiler.\n", - tname, nargs); + 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_type_is_enum(t)) { + 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); @@ -4540,31 +7601,227 @@ 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++) { + 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, "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_type_is_enum(t)) { - reg[i + 1].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_type_is_ptr(t) && - btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { - reg[i + 1].type = PTR_TO_CTX; + 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 (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; + + 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), + PTR_ERR(ref_t)); + return -EINVAL; + } + + 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_kind_str[BTF_INFO_KIND(t->info)], tname); + i, btf_type_str(t), tname); return -EINVAL; } + + sub->arg_cnt = nargs; + sub->args_cached = true; + return 0; } +static void btf_type_show(const struct btf *btf, u32 type_id, void *obj, + struct btf_show *show) +{ + const struct btf_type *t = btf_type_by_id(btf, type_id); + + show->btf = btf; + memset(&show->state, 0, sizeof(show->state)); + memset(&show->obj, 0, sizeof(show->obj)); + + btf_type_ops(t)->show(btf, t, type_id, obj, 0, show); +} + +__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); +} + +int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, + void *obj, struct seq_file *m, u64 flags) +{ + struct btf_show sseq; + + sseq.target = m; + sseq.showfn = btf_seq_show; + sseq.flags = flags; + + btf_type_show(btf, type_id, obj, &sseq); + + return sseq.state.status; +} + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { - const struct btf_type *t = btf_type_by_id(btf, type_id); + (void) btf_type_seq_show_flags(btf, type_id, obj, m, + BTF_SHOW_NONAME | BTF_SHOW_COMPACT | + BTF_SHOW_ZERO | BTF_SHOW_UNSAFE); +} + +struct btf_show_snprintf { + struct btf_show show; + int len_left; /* space left in string */ + int len; /* length we would have written */ +}; + +__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; + + len = vsnprintf(show->target, ssnprintf->len_left, fmt, args); - btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m); + if (len < 0) { + ssnprintf->len_left = 0; + ssnprintf->len = len; + } else if (len >= ssnprintf->len_left) { + /* no space, drive on to get length we would have written */ + ssnprintf->len_left = 0; + ssnprintf->len += len; + } else { + ssnprintf->len_left -= len; + ssnprintf->len += len; + show->target += len; + } +} + +int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, + char *buf, int len, u64 flags) +{ + struct btf_show_snprintf ssnprintf; + + ssnprintf.show.target = buf; + ssnprintf.show.flags = flags; + ssnprintf.show.showfn = btf_snprintf_show; + ssnprintf.len_left = len; + ssnprintf.len = 0; + + btf_type_show(btf, type_id, obj, (struct btf_show *)&ssnprintf); + + /* If we encountered an error, return it. */ + if (ssnprintf.show.state.status) + return ssnprintf.show.state.status; + + /* Otherwise return length we would have written */ + return ssnprintf.len; } #ifdef CONFIG_PROC_FS @@ -4594,15 +7851,12 @@ 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) +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { struct btf *btf; int ret; - btf = btf_parse(u64_to_user_ptr(attr->btf), - 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); @@ -4628,21 +7882,11 @@ int btf_new_fd(const union bpf_attr *attr) struct btf *btf_get_by_fd(int fd) { struct btf *btf; - struct fd f; + CLASS(fd, f)(fd); - f = fdget(fd); - - if (!f.file) - return ERR_PTR(-EBADF); - - if (f.file->f_op != &btf_fops) { - fdput(f); - return ERR_PTR(-EINVAL); - } - - 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; } @@ -4655,7 +7899,9 @@ int btf_get_info_by_fd(const struct btf *btf, struct bpf_btf_info info; u32 info_copy, btf_copy; void __user *ubtf; - u32 uinfo_len; + char __user *uname; + u32 uinfo_len, uname_len, name_len; + int ret = 0; uinfo = u64_to_user_ptr(attr->info.info); uinfo_len = attr->info.info_len; @@ -4672,11 +7918,37 @@ int btf_get_info_by_fd(const struct btf *btf, return -EFAULT; info.btf_size = btf->data_size; + info.kernel_btf = btf->kernel_btf; + + uname = u64_to_user_ptr(info.name); + uname_len = info.name_len; + if (!uname ^ !uname_len) + return -EINVAL; + + name_len = strlen(btf->name); + info.name_len = name_len; + + if (uname) { + if (uname_len >= name_len + 1) { + if (copy_to_user(uname, btf->name, name_len + 1)) + return -EFAULT; + } else { + char zero = '\0'; + + if (copy_to_user(uname, btf->name, uname_len - 1)) + return -EFAULT; + if (put_user(zero, uname + uname_len - 1)) + return -EFAULT; + /* let user-space know about too short buffer */ + ret = -ENOSPC; + } + } + if (copy_to_user(uinfo, &info, info_copy) || put_user(info_copy, &uattr->info.info_len)) return -EFAULT; - return 0; + return ret; } int btf_get_fd_by_id(u32 id) @@ -4700,7 +7972,1443 @@ int btf_get_fd_by_id(u32 id) return fd; } -u32 btf_id(const struct btf *btf) +u32 btf_obj_id(const struct btf *btf) { return btf->id; } + +bool btf_is_kernel(const struct btf *btf) +{ + return btf->kernel_btf; +} + +bool btf_is_module(const struct btf *btf) +{ + return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0; +} + +enum { + BTF_MODULE_F_LIVE = (1 << 0), +}; + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +struct btf_module { + struct list_head list; + struct module *module; + struct btf *btf; + struct bin_attribute *sysfs_attr; + int flags; +}; + +static LIST_HEAD(btf_modules); +static DEFINE_MUTEX(btf_module_mutex); + +static void purge_cand_cache(struct btf *btf); + +static int btf_module_notify(struct notifier_block *nb, unsigned long op, + void *module) +{ + struct btf_module *btf_mod, *tmp; + struct module *mod = module; + struct btf *btf; + int err = 0; + + if (mod->btf_data_size == 0 || + (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE && + op != MODULE_STATE_GOING)) + goto out; + + switch (op) { + case MODULE_STATE_COMING: + btf_mod = kzalloc(sizeof(*btf_mod), GFP_KERNEL); + if (!btf_mod) { + err = -ENOMEM; + goto out; + } + 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)) { + kfree(btf_mod); + 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); + if (err) { + btf_free(btf); + kfree(btf_mod); + goto out; + } + + purge_cand_cache(NULL); + mutex_lock(&btf_module_mutex); + btf_mod->module = module; + btf_mod->btf = btf; + list_add(&btf_mod->list, &btf_modules); + mutex_unlock(&btf_module_mutex); + + if (IS_ENABLED(CONFIG_SYSFS)) { + struct bin_attribute *attr; + + attr = kzalloc(sizeof(*attr), GFP_KERNEL); + if (!attr) + goto out; + + sysfs_bin_attr_init(attr); + attr->attr.name = btf->name; + attr->attr.mode = 0444; + attr->size = btf->data_size; + attr->private = btf->data; + attr->read_new = sysfs_bin_attr_simple_read; + + err = sysfs_create_bin_file(btf_kobj, attr); + if (err) { + pr_warn("failed to register module [%s] BTF in sysfs: %d\n", + mod->name, err); + kfree(attr); + err = 0; + goto out; + } + + btf_mod->sysfs_attr = attr; + } + + break; + case MODULE_STATE_LIVE: + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + btf_mod->flags |= BTF_MODULE_F_LIVE; + break; + } + mutex_unlock(&btf_module_mutex); + break; + case MODULE_STATE_GOING: + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + list_del(&btf_mod->list); + if (btf_mod->sysfs_attr) + sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr); + purge_cand_cache(btf_mod->btf); + btf_put(btf_mod->btf); + kfree(btf_mod->sysfs_attr); + kfree(btf_mod); + break; + } + mutex_unlock(&btf_module_mutex); + break; + } +out: + return notifier_from_errno(err); +} + +static struct notifier_block btf_module_nb = { + .notifier_call = btf_module_notify, +}; + +static int __init btf_module_init(void) +{ + register_module_notifier(&btf_module_nb); + return 0; +} + +fs_initcall(btf_module_init); +#endif /* CONFIG_DEBUG_INFO_BTF_MODULES */ + +struct module *btf_try_get_module(const struct btf *btf) +{ + struct module *res = NULL; +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + struct btf_module *btf_mod, *tmp; + + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->btf != btf) + continue; + + /* We must only consider module whose __init routine has + * finished, hence we must check for BTF_MODULE_F_LIVE flag, + * which is set from the notifier callback for + * MODULE_STATE_LIVE. + */ + if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module)) + res = btf_mod->module; + + break; + } + mutex_unlock(&btf_module_mutex); +#endif + + return res; +} + +/* Returns struct btf corresponding to the struct module. + * This function can return NULL or ERR_PTR. + */ +static struct btf *btf_get_module_btf(const struct module *module) +{ +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + struct btf_module *btf_mod, *tmp; +#endif + struct btf *btf = NULL; + + if (!module) { + btf = bpf_get_btf_vmlinux(); + if (!IS_ERR_OR_NULL(btf)) + btf_get(btf); + return btf; + } + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + btf_get(btf_mod->btf); + btf = btf_mod->btf; + break; + } + mutex_unlock(&btf_module_mutex); +#endif + + 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; + int btf_obj_fd = 0; + long ret; + + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + ret = bpf_find_btf_id(name, kind, &btf); + if (ret > 0 && btf_is_module(btf)) { + btf_obj_fd = __btf_new_fd(btf); + if (btf_obj_fd < 0) { + btf_put(btf); + return btf_obj_fd; + } + return ret | (((u64)btf_obj_fd) << 32); + } + if (ret > 0) + btf_put(btf); + return ret; +} + +const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { + .func = bpf_btf_find_by_name_kind, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + +BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) +#define BTF_TRACING_TYPE(name, type) BTF_ID(struct, 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, + 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, i; + int ret; + + if (hook >= BTF_KFUNC_HOOK_MAX) { + ret = -EINVAL; + goto end; + } + + if (!add_set->cnt) + 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) + return -ENOMEM; + btf->kfunc_set_tab = tab; + } + + set = tab->sets[hook]; + /* Warn when register_btf_kfunc_id_set is called twice for the same hook + * for module sets. + */ + if (WARN_ON_ONCE(set && !vmlinux_set)) { + ret = -EINVAL; + goto end; + } + + /* 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; + + if (set_cnt > U32_MAX - add_set->cnt) { + ret = -EOVERFLOW; + goto end; + } + + if (set_cnt + add_set->cnt > BTF_KFUNC_SET_MAX_CNT) { + ret = -E2BIG; + goto end; + } + + /* Grow set */ + set = krealloc(tab->sets[hook], + offsetof(struct btf_id_set8, pairs[set_cnt + add_set->cnt]), + GFP_KERNEL | __GFP_NOWARN); + if (!set) { + ret = -ENOMEM; + goto end; + } + + /* For newly allocated set, initialize set->cnt to 0 */ + if (!tab->sets[hook]) + set->cnt = 0; + tab->sets[hook] = set; + + /* 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); + return ret; +} + +static u32 *__btf_kfunc_id_set_contains(const struct btf *btf, + enum btf_kfunc_hook hook, + u32 kfunc_btf_id, + const struct bpf_prog *prog) +{ + struct btf_kfunc_hook_filter *hook_filter; + struct btf_id_set8 *set; + 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; + id = btf_id_set8_contains(set, kfunc_btf_id); + if (!id) + return NULL; + /* The flags for BTF ID are located next to it */ + return id + 1; +} + +static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) +{ + switch (prog_type) { + case BPF_PROG_TYPE_UNSPEC: + return BTF_KFUNC_HOOK_COMMON; + case BPF_PROG_TYPE_XDP: + return BTF_KFUNC_HOOK_XDP; + case BPF_PROG_TYPE_SCHED_CLS: + return BTF_KFUNC_HOOK_TC; + 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: + 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; + } +} + +/* Caution: + * Reference to the module (obtained using btf_try_get_module) corresponding to + * the struct btf *MUST* be held when calling this function from verifier + * context. This is usually true as we stash references in prog's kfunc_btf_tab; + * keeping the reference for the duration of the call provides the necessary + * protection for looking up a well-formed btf->kfunc_set_tab. + */ +u32 *btf_kfunc_id_set_contains(const struct btf *btf, + 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, 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, prog); +} + +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, 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, i; + + btf = btf_get_module_btf(kset->owner); + if (!btf) + return check_btf_kconfigs(kset->owner, "kfunc"); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + 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; +} + +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *kset) +{ + 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); +} +EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); + +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset) +{ + return __register_btf_kfunc_id_set(BTF_KFUNC_HOOK_FMODRET, kset); +} +EXPORT_SYMBOL_GPL(register_btf_fmodret_id_set); + +s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) +{ + struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; + struct btf_id_dtor_kfunc *dtor; + + if (!tab) + return -ENOENT; + /* Even though the size of tab->dtors[0] is > sizeof(u32), we only need + * to compare the first u32 with btf_id, so we can reuse btf_id_cmp_func. + */ + BUILD_BUG_ON(offsetof(struct btf_id_dtor_kfunc, btf_id) != 0); + dtor = bsearch(&btf_id, tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func); + if (!dtor) + return -ENOENT; + return dtor->kfunc_btf_id; +} + +static int btf_check_dtor_kfuncs(struct btf *btf, const struct btf_id_dtor_kfunc *dtors, u32 cnt) +{ + const struct btf_type *dtor_func, *dtor_func_proto, *t; + const struct btf_param *args; + s32 dtor_btf_id; + u32 nr_args, i; + + for (i = 0; i < cnt; i++) { + 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)) + return -EINVAL; + + dtor_func_proto = btf_type_by_id(btf, dtor_func->type); + if (!dtor_func_proto || !btf_type_is_func_proto(dtor_func_proto)) + return -EINVAL; + + /* Make sure the prototype of the destructor kfunc is 'void func(type *)' */ + t = btf_type_by_id(btf, dtor_func_proto->type); + if (!t || !btf_type_is_void(t)) + return -EINVAL; + + nr_args = btf_type_vlen(dtor_func_proto); + if (nr_args != 1) + return -EINVAL; + args = btf_params(dtor_func_proto); + t = btf_type_by_id(btf, args[0].type); + /* Allow any pointer type, as width on targets Linux supports + * will be same for all pointer types (i.e. sizeof(void *)) + */ + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + } + return 0; +} + +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, + struct module *owner) +{ + struct btf_id_dtor_kfunc_tab *tab; + struct btf *btf; + u32 tab_cnt, i; + int ret; + + btf = btf_get_module_btf(owner); + if (!btf) + return check_btf_kconfigs(owner, "dtor kfuncs"); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + if (add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { + pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); + ret = -E2BIG; + goto end; + } + + /* Ensure that the prototype of dtor kfuncs being registered is sane */ + ret = btf_check_dtor_kfuncs(btf, dtors, add_cnt); + if (ret < 0) + goto end; + + tab = btf->dtor_kfunc_tab; + /* Only one call allowed for modules */ + if (WARN_ON_ONCE(tab && btf_is_module(btf))) { + ret = -EINVAL; + goto end; + } + + tab_cnt = tab ? tab->cnt : 0; + if (tab_cnt > U32_MAX - add_cnt) { + ret = -EOVERFLOW; + goto end; + } + if (tab_cnt + add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { + pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); + ret = -E2BIG; + goto end; + } + + tab = krealloc(btf->dtor_kfunc_tab, + offsetof(struct btf_id_dtor_kfunc_tab, dtors[tab_cnt + add_cnt]), + GFP_KERNEL | __GFP_NOWARN); + if (!tab) { + ret = -ENOMEM; + goto end; + } + + if (!btf->dtor_kfunc_tab) + tab->cnt = 0; + 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); + +end: + if (ret) + btf_free_dtor_kfunc_tab(btf); + btf_put(btf); + return ret; +} +EXPORT_SYMBOL_GPL(register_btf_id_dtor_kfuncs); + +#define MAX_TYPES_ARE_COMPAT_DEPTH 2 + +/* Check local and target types for compatibility. This check is used for + * type-based CO-RE relocations and follow slightly different rules than + * field-based relocations. This function assumes that root types were already + * checked for name match. Beyond that initial root-level name check, names + * are completely ignored. Compatibility rules are as follows: + * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs/ENUM64s are considered compatible, but + * kind should match for local and target types (i.e., STRUCT is not + * compatible with UNION); + * - for ENUMs/ENUM64s, the size is ignored; + * - for INT, size and signedness are ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - CONST/VOLATILE/RESTRICT modifiers are ignored; + * - TYPEDEFs/PTRs are compatible if types they pointing to are compatible; + * - FUNC_PROTOs are compatible if they have compatible signature: same + * number of input args and compatible return and argument types. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + return __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id, + MAX_TYPES_ARE_COMPAT_DEPTH); +} + +#define MAX_TYPES_MATCH_DEPTH 2 + +int bpf_core_types_match(const struct btf *local_btf, u32 local_id, + const struct btf *targ_btf, u32 targ_id) +{ + return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, + MAX_TYPES_MATCH_DEPTH); +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +static void bpf_free_cands(struct bpf_cand_cache *cands) +{ + if (!cands->cnt) + /* empty candidate array was allocated on stack */ + return; + kfree(cands); +} + +static void bpf_free_cands_from_cache(struct bpf_cand_cache *cands) +{ + kfree(cands->name); + kfree(cands); +} + +#define VMLINUX_CAND_CACHE_SIZE 31 +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 void __print_cand_cache(struct bpf_verifier_log *log, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc; + int i, j; + + for (i = 0; i < cache_size; i++) { + cc = cache[i]; + if (!cc) + continue; + bpf_log(log, "[%d]%s(", i, cc->name); + for (j = 0; j < cc->cnt; j++) { + bpf_log(log, "%d", cc->cands[j].id); + if (j < cc->cnt - 1) + bpf_log(log, " "); + } + bpf_log(log, "), "); + } +} + +static void print_cand_cache(struct bpf_verifier_log *log) +{ + mutex_lock(&cand_cache_mutex); + bpf_log(log, "vmlinux_cand_cache:"); + __print_cand_cache(log, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + bpf_log(log, "\nmodule_cand_cache:"); + __print_cand_cache(log, module_cand_cache, MODULE_CAND_CACHE_SIZE); + bpf_log(log, "\n"); + mutex_unlock(&cand_cache_mutex); +} + +static u32 hash_cands(struct bpf_cand_cache *cands) +{ + return jhash(cands->name, cands->name_len, 0); +} + +static struct bpf_cand_cache *check_cand_cache(struct bpf_cand_cache *cands, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc = cache[hash_cands(cands) % cache_size]; + + if (cc && cc->name_len == cands->name_len && + !strncmp(cc->name, cands->name, cands->name_len)) + return cc; + return NULL; +} + +static size_t sizeof_cands(int cnt) +{ + return offsetof(struct bpf_cand_cache, cands[cnt]); +} + +static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache **cc = &cache[hash_cands(cands) % cache_size], *new_cands; + + if (*cc) { + bpf_free_cands_from_cache(*cc); + *cc = NULL; + } + new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL); + if (!new_cands) { + bpf_free_cands(cands); + return ERR_PTR(-ENOMEM); + } + /* 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); + bpf_free_cands(cands); + if (!new_cands->name) { + kfree(new_cands); + return ERR_PTR(-ENOMEM); + } + *cc = new_cands; + return new_cands; +} + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +static void __purge_cand_cache(struct btf *btf, struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc; + int i, j; + + for (i = 0; i < cache_size; i++) { + cc = cache[i]; + if (!cc) + continue; + if (!btf) { + /* when new module is loaded purge all of module_cand_cache, + * since new module might have candidates with the name + * that matches cached cands. + */ + bpf_free_cands_from_cache(cc); + cache[i] = NULL; + continue; + } + /* when module is unloaded purge cache entries + * that match module's btf + */ + for (j = 0; j < cc->cnt; j++) + if (cc->cands[j].btf == btf) { + bpf_free_cands_from_cache(cc); + cache[i] = NULL; + break; + } + } + +} + +static void purge_cand_cache(struct btf *btf) +{ + mutex_lock(&cand_cache_mutex); + __purge_cand_cache(btf, module_cand_cache, MODULE_CAND_CACHE_SIZE); + mutex_unlock(&cand_cache_mutex); +} +#endif + +static struct bpf_cand_cache * +bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf, + int targ_start_id) +{ + struct bpf_cand_cache *new_cands; + const struct btf_type *t; + const char *targ_name; + size_t targ_essent_len; + int n, i; + + n = btf_nr_types(targ_btf); + for (i = targ_start_id; i < n; i++) { + t = btf_type_by_id(targ_btf, i); + if (btf_kind(t) != cands->kind) + continue; + + targ_name = btf_name_by_offset(targ_btf, t->name_off); + if (!targ_name) + continue; + + /* the resched point is before strncmp to make sure that search + * for non-existing name will have a chance to schedule(). + */ + cond_resched(); + + if (strncmp(cands->name, targ_name, cands->name_len) != 0) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != cands->name_len) + 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); + if (!new_cands) { + bpf_free_cands(cands); + return ERR_PTR(-ENOMEM); + } + + memcpy(new_cands, cands, sizeof_cands(cands->cnt)); + bpf_free_cands(cands); + cands = new_cands; + cands->cands[cands->cnt].btf = targ_btf; + cands->cands[cands->cnt].id = i; + cands->cnt++; + } + return cands; +} + +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id) +{ + struct bpf_cand_cache *cands, *cc, local_cand = {}; + const struct btf *local_btf = ctx->btf; + const struct btf_type *local_type; + const struct btf *main_btf; + size_t local_essent_len; + struct btf *mod_btf; + const char *name; + int id; + + main_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(main_btf)) + return ERR_CAST(main_btf); + if (!main_btf) + return ERR_PTR(-EINVAL); + + local_type = btf_type_by_id(local_btf, local_type_id); + if (!local_type) + return ERR_PTR(-EINVAL); + + name = btf_name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(name); + + cands = &local_cand; + cands->name = name; + cands->kind = btf_kind(local_type); + cands->name_len = local_essent_len; + + cc = check_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + /* cands is a pointer to stack here */ + if (cc) { + if (cc->cnt) + return cc; + goto check_modules; + } + + /* Attempt to find target candidates in vmlinux BTF first */ + cands = bpf_core_add_cands(cands, main_btf, 1); + if (IS_ERR(cands)) + return ERR_CAST(cands); + + /* cands is a pointer to kmalloced memory here if cands->cnt > 0 */ + + /* populate cache even when cands->cnt == 0 */ + cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + if (IS_ERR(cc)) + return ERR_CAST(cc); + + /* if vmlinux BTF has any candidate, don't go for module BTFs */ + if (cc->cnt) + return cc; + +check_modules: + /* cands is a pointer to stack here and cands->cnt == 0 */ + cc = check_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); + if (cc) + /* if cache has it return it even if cc->cnt == 0 */ + return cc; + + /* If candidate is not found in vmlinux's BTF then search in module's BTFs */ + spin_lock_bh(&btf_idr_lock); + idr_for_each_entry(&btf_idr, mod_btf, id) { + if (!btf_is_module(mod_btf)) + continue; + /* linear search could be slow hence unlock/lock + * the IDR to avoiding holding it for too long + */ + btf_get(mod_btf); + spin_unlock_bh(&btf_idr_lock); + cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf)); + btf_put(mod_btf); + if (IS_ERR(cands)) + return ERR_CAST(cands); + spin_lock_bh(&btf_idr_lock); + } + spin_unlock_bh(&btf_idr_lock); + /* cands is a pointer to kmalloced memory here if cands->cnt > 0 + * or pointer to stack if cands->cnd == 0. + * Copy it into the cache even when cands->cnt == 0 and + * return the result. + */ + return populate_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); +} + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn) +{ + bool need_cands = relo->kind != BPF_CORE_TYPE_ID_LOCAL; + 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); + 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; + + mutex_lock(&cand_cache_mutex); + cc = bpf_core_find_cands(ctx, relo->type_id); + if (IS_ERR(cc)) { + bpf_log(ctx->log, "target candidate search failed for %d\n", + relo->type_id); + err = PTR_ERR(cc); + goto out; + } + if (cc->cnt) { + cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL); + if (!cands.cands) { + err = -ENOMEM; + goto out; + } + } + for (i = 0; i < cc->cnt; i++) { + bpf_log(ctx->log, + "CO-RE relocating %s %s: found target candidate [%d]\n", + btf_kind_str[cc->kind], cc->name, cc->cands[i].id); + cands.cands[i].btf = cc->cands[i].btf; + cands.cands[i].id = cc->cands[i].id; + } + cands.len = cc->cnt; + /* cand_cache_mutex needs to span the cache lookup and + * copy of btf pointer into bpf_core_cand_list, + * since module can be unloaded while bpf_core_calc_relo_insn + * is working with module's btf. + */ + } + + err = bpf_core_calc_relo_insn((void *)ctx->log, relo, relo_idx, ctx->btf, &cands, specs, + &targ_res); + if (err) + goto out; + + err = bpf_core_patch_insn((void *)ctx->log, insn, relo->insn_off / 8, relo, relo_idx, + &targ_res); + +out: + kfree(specs); + if (need_cands) { + kfree(cands.cands); + mutex_unlock(&cand_cache_mutex); + if (ctx->log->level & BPF_LOG_LEVEL2) + print_cand_cache(ctx->log); + } + 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(offsetof(struct btf_struct_ops_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, + offsetof(struct btf_struct_ops_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 ac53102e244a..46e5db65dbc8 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -14,14 +14,198 @@ #include <linux/string.h> #include <linux/bpf.h> #include <linux/bpf-cgroup.h> +#include <linux/bpf_lsm.h> +#include <linux/bpf_verifier.h> #include <net/sock.h> #include <net/bpf_sk_storage.h> #include "../cgroup/cgroup-internal.h" -DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key); +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_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", 0, 1); + if (!cgroup_bpf_destroy_wq) + panic("Failed to alloc workqueue for cgroup bpf destroy.\n"); + return 0; +} +core_initcall(cgroup_bpf_wq_init); + +/* __always_inline is necessary to prevent indirect call through run_prog + * function pointer. + */ +static __always_inline int +bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, + enum cgroup_bpf_attach_type atype, + const void *ctx, bpf_prog_run_fn run_prog, + int retval, u32 *ret_flags) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_cg_run_ctx run_ctx; + u32 func_ret; + + run_ctx.retval = retval; + migrate_disable(); + rcu_read_lock(); + array = rcu_dereference(cgrp->effective[atype]); + item = &array->items[0]; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + while ((prog = READ_ONCE(item->prog))) { + run_ctx.prog_item = item; + func_ret = run_prog(prog, ctx); + if (ret_flags) { + *(ret_flags) |= (func_ret >> 1); + func_ret &= 1; + } + if (!func_ret && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; + item++; + } + bpf_reset_run_ctx(old_run_ctx); + rcu_read_unlock(); + migrate_enable(); + return run_ctx.retval; +} + +unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, + const struct bpf_insn *insn) +{ + const struct bpf_prog *shim_prog; + struct sock *sk; + struct cgroup *cgrp; + int ret = 0; + u64 *args; + + args = (u64 *)ctx; + sk = (void *)(unsigned long)args[0]; + /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ + shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); + + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + if (likely(cgrp)) + ret = bpf_prog_run_array_cg(&cgrp->bpf, + shim_prog->aux->cgroup_atype, + ctx, bpf_prog_run, 0, NULL); + return ret; +} + +unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, + const struct bpf_insn *insn) +{ + const struct bpf_prog *shim_prog; + struct socket *sock; + struct cgroup *cgrp; + int ret = 0; + u64 *args; + + args = (u64 *)ctx; + sock = (void *)(unsigned long)args[0]; + /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ + shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); + + cgrp = sock_cgroup_ptr(&sock->sk->sk_cgrp_data); + if (likely(cgrp)) + ret = bpf_prog_run_array_cg(&cgrp->bpf, + shim_prog->aux->cgroup_atype, + ctx, bpf_prog_run, 0, NULL); + return ret; +} + +unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, + const struct bpf_insn *insn) +{ + const struct bpf_prog *shim_prog; + struct cgroup *cgrp; + int ret = 0; + + /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ + shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); + + /* We rely on trampoline's __bpf_prog_enter_lsm_cgroup to grab RCU read lock. */ + cgrp = task_dfl_cgroup(current); + if (likely(cgrp)) + ret = bpf_prog_run_array_cg(&cgrp->bpf, + shim_prog->aux->cgroup_atype, + ctx, bpf_prog_run, 0, NULL); + return ret; +} + +#ifdef CONFIG_BPF_LSM +struct cgroup_lsm_atype { + u32 attach_btf_id; + int refcnt; +}; + +static struct cgroup_lsm_atype cgroup_lsm_atype[CGROUP_LSM_NUM]; + +static enum cgroup_bpf_attach_type +bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) +{ + int i; + + lockdep_assert_held(&cgroup_mutex); + + if (attach_type != BPF_LSM_CGROUP) + return to_cgroup_bpf_attach_type(attach_type); + + for (i = 0; i < ARRAY_SIZE(cgroup_lsm_atype); i++) + if (cgroup_lsm_atype[i].attach_btf_id == attach_btf_id) + return CGROUP_LSM_START + i; + + for (i = 0; i < ARRAY_SIZE(cgroup_lsm_atype); i++) + if (cgroup_lsm_atype[i].attach_btf_id == 0) + return CGROUP_LSM_START + i; + + return -E2BIG; + +} + +void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) +{ + int i = cgroup_atype - CGROUP_LSM_START; + + lockdep_assert_held(&cgroup_mutex); + + WARN_ON_ONCE(cgroup_lsm_atype[i].attach_btf_id && + cgroup_lsm_atype[i].attach_btf_id != attach_btf_id); + + cgroup_lsm_atype[i].attach_btf_id = attach_btf_id; + cgroup_lsm_atype[i].refcnt++; +} + +void bpf_cgroup_atype_put(int cgroup_atype) +{ + int i = cgroup_atype - CGROUP_LSM_START; + + 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); + cgroup_unlock(); +} +#else +static enum cgroup_bpf_attach_type +bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) +{ + if (attach_type != BPF_LSM_CGROUP) + return to_cgroup_bpf_attach_type(attach_type); + return -EOPNOTSUPP; +} +#endif /* CONFIG_BPF_LSM */ + void cgroup_bpf_offline(struct cgroup *cgrp) { cgroup_get(cgrp); @@ -37,17 +221,34 @@ static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[]) } static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[], - struct bpf_prog *prog) + struct bpf_cgroup_storage *new_storages[], + enum bpf_attach_type type, + struct bpf_prog *prog, + struct cgroup *cgrp) { enum bpf_cgroup_storage_type stype; + struct bpf_cgroup_storage_key key; + struct bpf_map *map; + + key.cgroup_inode_id = cgroup_id(cgrp); + key.attach_type = type; for_each_cgroup_storage_type(stype) { + map = prog->aux->cgroup_storage[stype]; + if (!map) + continue; + + storages[stype] = cgroup_storage_lookup((void *)map, &key, false); + if (storages[stype]) + continue; + storages[stype] = bpf_cgroup_storage_alloc(prog, stype); if (IS_ERR(storages[stype])) { - storages[stype] = NULL; - bpf_cgroup_storages_free(storages); + bpf_cgroup_storages_free(new_storages); return -ENOMEM; } + + new_storages[stype] = storages[stype]; } return 0; @@ -63,7 +264,7 @@ static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[], } static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[], - struct cgroup* cgrp, + struct cgroup *cgrp, enum bpf_attach_type attach_type) { enum bpf_cgroup_storage_type stype; @@ -72,14 +273,6 @@ static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[], bpf_cgroup_storage_link(storages[stype], cgrp, attach_type); } -static void bpf_cgroup_storages_unlink(struct bpf_cgroup_storage *storages[]) -{ - enum bpf_cgroup_storage_type stype; - - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_unlink(storages[stype]); -} - /* Called when bpf_cgroup_link is auto-detached from dying cgroup. * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It * doesn't free link memory, which will eventually be done by bpf_link's @@ -101,32 +294,45 @@ static void cgroup_bpf_release(struct work_struct *work) struct cgroup *p, *cgrp = container_of(work, struct cgroup, bpf.release_work); struct bpf_prog_array *old_array; - unsigned int type; + struct list_head *storages = &cgrp->bpf.storages; + struct bpf_cgroup_storage *storage, *stmp; + + unsigned int atype; - mutex_lock(&cgroup_mutex); + cgroup_lock(); - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { - struct list_head *progs = &cgrp->bpf.progs[type]; - struct bpf_prog_list *pl, *tmp; + for (atype = 0; atype < ARRAY_SIZE(cgrp->bpf.progs); atype++) { + struct hlist_head *progs = &cgrp->bpf.progs[atype]; + struct bpf_prog_list *pl; + struct hlist_node *pltmp; - list_for_each_entry_safe(pl, tmp, progs, node) { - list_del(&pl->node); - if (pl->prog) + hlist_for_each_entry_safe(pl, pltmp, progs, node) { + hlist_del(&pl->node); + if (pl->prog) { + if (pl->prog->expected_attach_type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(pl->prog); bpf_prog_put(pl->prog); - if (pl->link) + } + if (pl->link) { + if (pl->link->link.prog->expected_attach_type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(pl->link->link.prog); bpf_cgroup_link_auto_detach(pl->link); - bpf_cgroup_storages_unlink(pl->storage); - bpf_cgroup_storages_free(pl->storage); + } kfree(pl); - static_branch_dec(&cgroup_bpf_enabled_key); + static_branch_dec(&cgroup_bpf_enabled_key[atype]); } old_array = rcu_dereference_protected( - cgrp->bpf.effective[type], + cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); bpf_prog_array_free(old_array); } - mutex_unlock(&cgroup_mutex); + list_for_each_entry_safe(storage, stmp, storages, list_cg) { + bpf_cgroup_storage_unlink(storage); + bpf_cgroup_storage_free(storage); + } + + cgroup_unlock(); for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_put(p); @@ -145,7 +351,7 @@ 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 @@ -163,12 +369,12 @@ 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 list_head *head) +static u32 prog_list_length(struct hlist_head *head) { struct bpf_prog_list *pl; u32 cnt = 0; - list_for_each_entry(pl, head, node) { + hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; cnt++; @@ -181,7 +387,7 @@ static u32 prog_list_length(struct list_head *head) * if parent has overridable or multi-prog, allow attaching */ static bool hierarchy_allows_attach(struct cgroup *cgrp, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup *p; @@ -189,12 +395,12 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, if (!p) return true; do { - u32 flags = p->bpf.flags[type]; + u32 flags = p->bpf.flags[atype]; u32 cnt; if (flags & BPF_F_ALLOW_MULTI) return true; - cnt = prog_list_length(&p->bpf.progs[type]); + cnt = prog_list_length(&p->bpf.progs[atype]); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); @@ -210,7 +416,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, * to programs in this cgroup */ static int compute_effective_progs(struct cgroup *cgrp, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, struct bpf_prog_array **array) { struct bpf_prog_array_item *item; @@ -221,8 +427,8 @@ static int compute_effective_progs(struct cgroup *cgrp, /* count number of effective programs by walking parents */ do { - if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) - cnt += prog_list_length(&p->bpf.progs[type]); + if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) + cnt += prog_list_length(&p->bpf.progs[atype]); p = cgroup_parent(p); } while (p); @@ -234,10 +440,10 @@ static int compute_effective_progs(struct cgroup *cgrp, cnt = 0; p = cgrp; do { - if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; - list_for_each_entry(pl, &p->bpf.progs[type], node) { + hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; @@ -254,10 +460,10 @@ static int compute_effective_progs(struct cgroup *cgrp, } static void activate_effective_progs(struct cgroup *cgrp, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, struct bpf_prog_array *old_array) { - old_array = rcu_replace_pointer(cgrp->bpf.effective[type], old_array, + old_array = rcu_replace_pointer(cgrp->bpf.effective[atype], old_array, lockdep_is_held(&cgroup_mutex)); /* free prog array after grace period, since __cgroup_bpf_run_*() * might be still walking the array @@ -288,7 +494,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) cgroup_bpf_get(p); for (i = 0; i < NR; i++) - INIT_LIST_HEAD(&cgrp->bpf.progs[i]); + INIT_HLIST_HEAD(&cgrp->bpf.progs[i]); + + INIT_LIST_HEAD(&cgrp->bpf.storages); for (i = 0; i < NR; i++) if (compute_effective_progs(cgrp, i, &arrays[i])) @@ -311,7 +519,7 @@ cleanup: } static int update_effective_progs(struct cgroup *cgrp, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup_subsys_state *css; int err; @@ -323,7 +531,7 @@ static int update_effective_progs(struct cgroup *cgrp, if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; - err = compute_effective_progs(desc, type, &desc->bpf.inactive); + err = compute_effective_progs(desc, atype, &desc->bpf.inactive); if (err) goto cleanup; } @@ -340,7 +548,7 @@ static int update_effective_progs(struct cgroup *cgrp, continue; } - activate_effective_progs(desc, type, desc->bpf.inactive); + activate_effective_progs(desc, atype, desc->bpf.inactive); desc->bpf.inactive = NULL; } @@ -362,7 +570,7 @@ cleanup: #define BPF_CGROUP_MAX_PROGS 64 -static struct bpf_prog_list *find_attach_entry(struct list_head *progs, +static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs, struct bpf_prog *prog, struct bpf_cgroup_link *link, struct bpf_prog *replace_prog, @@ -372,12 +580,12 @@ static struct bpf_prog_list *find_attach_entry(struct list_head *progs, /* single-attach case */ if (!allow_multi) { - if (list_empty(progs)) + if (hlist_empty(progs)) return NULL; - return list_first_entry(progs, typeof(*pl), node); + return hlist_entry(progs->first, typeof(*pl), node); } - list_for_each_entry(pl, progs, node) { + hlist_for_each_entry(pl, progs, node) { if (prog && pl->prog == prog && prog != replace_prog) /* disallow attaching the same prog twice */ return ERR_PTR(-EINVAL); @@ -388,7 +596,7 @@ static struct bpf_prog_list *find_attach_entry(struct list_head *progs, /* direct prog multi-attach w/ replacement case */ if (replace_prog) { - list_for_each_entry(pl, progs, node) { + hlist_for_each_entry(pl, progs, node) { if (pl->prog == replace_prog) /* a match found */ return pl; @@ -413,17 +621,19 @@ static struct bpf_prog_list *find_attach_entry(struct list_head *progs, * Exactly one of @prog or @link can be non-null. * Must be called with cgroup_mutex held. */ -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) +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 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); - struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; - struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; + struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; + struct bpf_prog *new_prog = prog ? : link->link.prog; + enum cgroup_bpf_attach_type atype; struct bpf_prog_list *pl; + struct hlist_head *progs; int err; if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || @@ -437,10 +647,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, /* replace_prog implies BPF_F_REPLACE, and vice versa */ return -EINVAL; - if (!hierarchy_allows_attach(cgrp, type)) + atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id); + if (atype < 0) + return -EINVAL; + + progs = &cgrp->bpf.progs[atype]; + + if (!hierarchy_allows_attach(cgrp, atype)) return -EPERM; - if (!list_empty(progs) && cgrp->bpf.flags[type] != saved_flags) + if (!hlist_empty(progs) && cgrp->bpf.flags[atype] != saved_flags) /* Disallow attaching non-overridable on top * of existing overridable in this cgroup. * Disallow attaching multi-prog if overridable or none @@ -455,66 +671,99 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, if (IS_ERR(pl)) return PTR_ERR(pl); - if (bpf_cgroup_storages_alloc(storage, prog ? : link->link.prog)) + if (bpf_cgroup_storages_alloc(storage, new_storage, type, + prog ? : link->link.prog, cgrp)) return -ENOMEM; if (pl) { old_prog = pl->prog; - bpf_cgroup_storages_unlink(pl->storage); - bpf_cgroup_storages_assign(old_storage, pl->storage); } else { + struct hlist_node *last = NULL; + pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - bpf_cgroup_storages_free(storage); + bpf_cgroup_storages_free(new_storage); return -ENOMEM; } - list_add_tail(&pl->node, progs); + 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; + } } pl->prog = prog; pl->link = link; bpf_cgroup_storages_assign(pl->storage, storage); - cgrp->bpf.flags[type] = saved_flags; + cgrp->bpf.flags[atype] = saved_flags; - err = update_effective_progs(cgrp, type); + if (type == BPF_LSM_CGROUP) { + err = bpf_trampoline_link_cgroup_shim(new_prog, atype); + if (err) + goto cleanup; + } + + err = update_effective_progs(cgrp, atype); if (err) - goto cleanup; + goto cleanup_trampoline; - bpf_cgroup_storages_free(old_storage); - if (old_prog) + if (old_prog) { + if (type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); - else - static_branch_inc(&cgroup_bpf_enabled_key); - bpf_cgroup_storages_link(pl->storage, cgrp, type); + } else { + static_branch_inc(&cgroup_bpf_enabled_key[atype]); + } + bpf_cgroup_storages_link(new_storage, cgrp, type); return 0; +cleanup_trampoline: + if (type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(new_prog); + cleanup: if (old_prog) { pl->prog = old_prog; pl->link = NULL; } - bpf_cgroup_storages_free(pl->storage); - bpf_cgroup_storages_assign(pl->storage, old_storage); - bpf_cgroup_storages_link(pl->storage, cgrp, type); + bpf_cgroup_storages_free(new_storage); if (!old_prog) { - list_del(&pl->node); + hlist_del(&pl->node); kfree(pl); } return err; } +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) +{ + int ret; + + cgroup_lock(); + ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); + cgroup_unlock(); + return ret; +} + /* Swap updated BPF program for given link in effective program arrays across * all descendant cgroups. This function is guaranteed to succeed. */ static void replace_effective_prog(struct cgroup *cgrp, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, struct bpf_cgroup_link *link) { struct bpf_prog_array_item *item; struct cgroup_subsys_state *css; struct bpf_prog_array *progs; struct bpf_prog_list *pl; - struct list_head *head; + struct hlist_head *head; struct cgroup *cg; int pos; @@ -526,11 +775,11 @@ static void replace_effective_prog(struct cgroup *cgrp, /* find position of link in effective progs array */ for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { - if (pos && !(cg->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; - head = &cg->bpf.progs[type]; - list_for_each_entry(pl, head, node) { + head = &cg->bpf.progs[atype]; + hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; if (pl->link == link) @@ -541,7 +790,7 @@ static void replace_effective_prog(struct cgroup *cgrp, found: BUG_ON(!cg); progs = rcu_dereference_protected( - desc->bpf.effective[type], + desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); item = &progs->items[pos]; WRITE_ONCE(item->prog, link->link.prog); @@ -553,7 +802,8 @@ 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. */ @@ -561,15 +811,22 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, struct bpf_prog *new_prog) { - struct list_head *progs = &cgrp->bpf.progs[link->type]; + enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; struct bpf_prog_list *pl; + struct hlist_head *progs; bool found = false; + atype = bpf_cgroup_atype_find(link->type, new_prog->aux->attach_btf_id); + if (atype < 0) + return -EINVAL; + + progs = &cgrp->bpf.progs[atype]; + if (link->link.prog->type != new_prog->type) return -EINVAL; - list_for_each_entry(pl, progs, node) { + hlist_for_each_entry(pl, progs, node) { if (pl->link == link) { found = true; break; @@ -579,7 +836,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, return -ENOENT; old_prog = xchg(&link->link.prog, new_prog); - replace_effective_prog(cgrp, link->type, link); + replace_effective_prog(cgrp, atype, link); bpf_prog_put(old_prog); return 0; } @@ -592,7 +849,7 @@ 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; @@ -604,11 +861,11 @@ 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; } -static struct bpf_prog_list *find_detach_entry(struct list_head *progs, +static struct bpf_prog_list *find_detach_entry(struct hlist_head *progs, struct bpf_prog *prog, struct bpf_cgroup_link *link, bool allow_multi) @@ -616,14 +873,14 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs, struct bpf_prog_list *pl; if (!allow_multi) { - if (list_empty(progs)) + if (hlist_empty(progs)) /* report error when trying to detach and nothing is attached */ return ERR_PTR(-ENOENT); /* to maintain backward compatibility NONE and OVERRIDE cgroups * allow detaching with invalid FD (prog==NULL) in legacy mode */ - return list_first_entry(progs, typeof(*pl), node); + return hlist_entry(progs->first, typeof(*pl), node); } if (!prog && !link) @@ -633,7 +890,7 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs, return ERR_PTR(-EINVAL); /* find the prog or link and detach it */ - list_for_each_entry(pl, progs, node) { + hlist_for_each_entry(pl, progs, node) { if (pl->prog == prog && pl->link == link) return pl; } @@ -641,24 +898,93 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs, } /** + * purge_effective_progs() - After compute_effective_progs fails to alloc new + * cgrp->bpf.inactive table we can recover by + * recomputing the array in place. + * + * @cgrp: The cgroup which descendants to travers + * @prog: A program to detach or NULL + * @link: A link to detach or NULL + * @atype: Type of detach operation + */ +static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog, + struct bpf_cgroup_link *link, + enum cgroup_bpf_attach_type atype) +{ + struct cgroup_subsys_state *css; + struct bpf_prog_array *progs; + struct bpf_prog_list *pl; + struct hlist_head *head; + struct cgroup *cg; + int pos; + + /* recompute effective prog array in place */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + if (percpu_ref_is_zero(&desc->bpf.refcnt)) + continue; + + /* find position of link or prog in effective progs array */ + for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { + if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) + continue; + + head = &cg->bpf.progs[atype]; + hlist_for_each_entry(pl, head, node) { + if (!prog_list_prog(pl)) + continue; + if (pl->prog == prog && pl->link == link) + goto found; + pos++; + } + } + + /* no link or prog match, skip the cgroup of this layer */ + continue; +found: + progs = rcu_dereference_protected( + desc->bpf.effective[atype], + lockdep_is_held(&cgroup_mutex)); + + /* Remove the program from the array */ + WARN_ONCE(bpf_prog_array_delete_safe_at(progs, pos), + "Failed to purge a prog from array at index %d", pos); + } +} + +/** * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to detach or NULL - * @prog: A link to detach or NULL + * @link: A link to detach or NULL * @type: Type of detach operation * * At most one of @prog or @link can be non-NULL. * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_cgroup_link *link, enum bpf_attach_type type) +static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + struct bpf_cgroup_link *link, enum bpf_attach_type type) { - struct list_head *progs = &cgrp->bpf.progs[type]; - u32 flags = cgrp->bpf.flags[type]; - struct bpf_prog_list *pl; + enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; - int err; + struct bpf_prog_list *pl; + struct hlist_head *progs; + u32 attach_btf_id = 0; + u32 flags; + + if (prog) + attach_btf_id = prog->aux->attach_btf_id; + if (link) + attach_btf_id = link->link.prog->aux->attach_btf_id; + + atype = bpf_cgroup_atype_find(type, attach_btf_id); + if (atype < 0) + return -EINVAL; + + progs = &cgrp->bpf.progs[atype]; + flags = cgrp->bpf.flags[atype]; if (prog && link) /* only one of prog or link can be specified */ @@ -673,81 +999,151 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, pl->prog = NULL; pl->link = NULL; - err = update_effective_progs(cgrp, type); - if (err) - goto cleanup; + if (update_effective_progs(cgrp, atype)) { + /* if update effective array failed replace the prog with a dummy prog*/ + pl->prog = old_prog; + pl->link = link; + purge_effective_progs(cgrp, old_prog, link, atype); + } /* now can actually delete it from this cgroup list */ - list_del(&pl->node); - bpf_cgroup_storages_unlink(pl->storage); - bpf_cgroup_storages_free(pl->storage); + hlist_del(&pl->node); + kfree(pl); - if (list_empty(progs)) + if (hlist_empty(progs)) /* last program was detached, reset flags to zero */ - cgrp->bpf.flags[type] = 0; - if (old_prog) + cgrp->bpf.flags[atype] = 0; + if (old_prog) { + if (type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); - static_branch_dec(&cgroup_bpf_enabled_key); + } + static_branch_dec(&cgroup_bpf_enabled_key[atype]); return 0; +} -cleanup: - /* restore back prog or link */ - pl->prog = old_prog; - pl->link = link; - return err; +static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type) +{ + int ret; + + cgroup_lock(); + ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); + cgroup_unlock(); + return ret; } /* Must be called with cgroup_mutex held to avoid races. */ -int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr) +static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) { + __u32 __user *prog_attach_flags = u64_to_user_ptr(attr->query.prog_attach_flags); + bool effective_query = attr->query.query_flags & BPF_F_QUERY_EFFECTIVE; __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); enum bpf_attach_type type = attr->query.attach_type; - struct list_head *progs = &cgrp->bpf.progs[type]; - u32 flags = cgrp->bpf.flags[type]; + enum cgroup_bpf_attach_type from_atype, to_atype; + enum cgroup_bpf_attach_type atype; struct bpf_prog_array *effective; - struct bpf_prog *prog; int cnt, ret = 0, i; + int total_cnt = 0; + u32 flags; - effective = rcu_dereference_protected(cgrp->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); + if (effective_query && prog_attach_flags) + return -EINVAL; - if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) - cnt = bpf_prog_array_length(effective); - else - cnt = prog_list_length(progs); + if (type == BPF_LSM_CGROUP) { + if (!effective_query && attr->query.prog_cnt && + prog_ids && !prog_attach_flags) + return -EINVAL; + + from_atype = CGROUP_LSM_START; + to_atype = CGROUP_LSM_END; + flags = 0; + } else { + from_atype = to_cgroup_bpf_attach_type(type); + if (from_atype < 0) + return -EINVAL; + to_atype = from_atype; + flags = cgrp->bpf.flags[from_atype]; + } + + for (atype = from_atype; atype <= to_atype; atype++) { + if (effective_query) { + effective = rcu_dereference_protected(cgrp->bpf.effective[atype], + lockdep_is_held(&cgroup_mutex)); + total_cnt += bpf_prog_array_length(effective); + } else { + total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); + } + } + /* always output uattr->query.attach_flags as 0 during effective query */ + flags = effective_query ? 0 : flags; if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; - if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) + if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt))) return -EFAULT; - if (attr->query.prog_cnt == 0 || !prog_ids || !cnt) + if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt) /* return early if user requested only program count + flags */ return 0; - if (attr->query.prog_cnt < cnt) { - cnt = attr->query.prog_cnt; + + if (attr->query.prog_cnt < total_cnt) { + total_cnt = attr->query.prog_cnt; ret = -ENOSPC; } - if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { - return bpf_prog_array_copy_to_user(effective, prog_ids, cnt); - } else { - struct bpf_prog_list *pl; - u32 id; - - i = 0; - list_for_each_entry(pl, progs, node) { - prog = prog_list_prog(pl); - id = prog->aux->id; - if (copy_to_user(prog_ids + i, &id, sizeof(id))) - return -EFAULT; - if (++i == cnt) - break; + for (atype = from_atype; atype <= to_atype && total_cnt; atype++) { + if (effective_query) { + effective = rcu_dereference_protected(cgrp->bpf.effective[atype], + lockdep_is_held(&cgroup_mutex)); + cnt = min_t(int, bpf_prog_array_length(effective), total_cnt); + ret = bpf_prog_array_copy_to_user(effective, prog_ids, cnt); + } else { + struct hlist_head *progs; + struct bpf_prog_list *pl; + struct bpf_prog *prog; + u32 id; + + progs = &cgrp->bpf.progs[atype]; + cnt = min_t(int, prog_list_length(progs), total_cnt); + i = 0; + hlist_for_each_entry(pl, progs, node) { + prog = prog_list_prog(pl); + id = prog->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) + return -EFAULT; + if (++i == cnt) + break; + } + + if (prog_attach_flags) { + flags = cgrp->bpf.flags[atype]; + + for (i = 0; i < cnt; i++) + if (copy_to_user(prog_attach_flags + i, + &flags, sizeof(flags))) + return -EFAULT; + prog_attach_flags += cnt; + } } + + prog_ids += cnt; + total_cnt -= cnt; } return ret; } +static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ret; + + cgroup_lock(); + ret = __cgroup_bpf_query(cgrp, attr, uattr); + cgroup_unlock(); + return ret; +} + int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { @@ -803,6 +1199,7 @@ static void bpf_cgroup_link_release(struct bpf_link *link) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); + struct cgroup *cg; /* link might have been auto-detached by dying cgroup already, * in that case our work is done here @@ -810,19 +1207,25 @@ 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) + bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog); + + cg = cg_link->cgroup; + cg_link->cgroup = NULL; - mutex_unlock(&cgroup_mutex); - cgroup_put(cg_link->cgroup); + cgroup_unlock(); + + cgroup_put(cg); } static void bpf_cgroup_link_dealloc(struct bpf_link *link) @@ -833,6 +1236,13 @@ static void bpf_cgroup_link_dealloc(struct bpf_link *link) kfree(cg_link); } +static int bpf_cgroup_link_detach(struct bpf_link *link) +{ + bpf_cgroup_link_release(link); + + return 0; +} + static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { @@ -840,10 +1250,10 @@ 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" @@ -859,10 +1269,10 @@ 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; @@ -872,6 +1282,7 @@ static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_cgroup_link_lops = { .release = bpf_cgroup_link_release, .dealloc = bpf_cgroup_link_dealloc, + .detach = bpf_cgroup_link_detach, .update_prog = cgroup_bpf_replace, .show_fdinfo = bpf_cgroup_link_show_fdinfo, .fill_link_info = bpf_cgroup_link_fill_link_info, @@ -901,14 +1312,14 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) link->cgroup = cgrp; link->type = attr->link_create.attach_type; - err = bpf_link_prime(&link->link, &link_primer); + err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_cgroup; } - err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, - BPF_F_ALLOW_MULTI); + err = cgroup_bpf_attach(cgrp, NULL, NULL, link, + link->type, BPF_F_ALLOW_MULTI); if (err) { bpf_link_cleanup(&link_primer); goto out_put_cgroup; @@ -941,7 +1352,7 @@ 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 exectuted + * @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. @@ -954,7 +1365,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, * NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr * NET_XMIT_CN (2) - continue with packet output and notify TCP * to call cwr - * -EPERM - drop packet + * -err - drop packet * * For ingress packets, this function will return -EPERM if any * attached program was found and if it returned != 1 during execution. @@ -962,17 +1373,14 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, */ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, - enum bpf_attach_type type) + 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; @@ -984,13 +1392,41 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, /* compute pointers for the bpf prog */ bpf_compute_and_save_data_end(skb, &saved_data_end); - if (type == BPF_CGROUP_INET_EGRESS) { - ret = BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY( - cgrp->bpf.effective[type], skb, __bpf_prog_run_save_cb); + if (atype == CGROUP_INET_EGRESS) { + u32 flags = 0; + bool cn; + + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb, + __bpf_prog_run_save_cb, 0, &flags); + + /* Return values of CGROUP EGRESS BPF programs are: + * 0: drop packet + * 1: keep packet + * 2: drop packet and cn + * 3: keep packet and cn + * + * The returned value is then converted to one of the NET_XMIT + * or an error code that is then interpreted as drop packet + * (and no cn): + * 0: NET_XMIT_SUCCESS skb should be transmitted + * 1: NET_XMIT_DROP skb should be dropped and cn + * 2: NET_XMIT_CN skb should be transmitted and cn + * 3: -err skb should be dropped + */ + + cn = flags & BPF_RET_SET_CN; + if (ret && !IS_ERR_VALUE((long)ret)) + ret = -EFAULT; + if (!ret) + ret = (cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); + else + ret = (cn ? NET_XMIT_DROP : ret); } else { - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - __bpf_prog_run_save_cb); - ret = (ret == 1 ? 0 : -EPERM); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, + skb, __bpf_prog_run_save_cb, 0, + NULL); + if (ret && !IS_ERR_VALUE((long)ret)) + ret = -EFAULT; } bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); @@ -1003,7 +1439,7 @@ 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 exectuted + * @atype: The type of program to be executed * * socket is passed is expected to be of type INET or INET6. * @@ -1014,13 +1450,12 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); * and if it returned != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sk(struct sock *sk, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - int ret; - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN); - return ret == 1 ? 0 : -EPERM; + return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0, + NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -1029,18 +1464,25 @@ 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 exectuted + * @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, - enum bpf_attach_type type, - void *t_ctx) + int *uaddrlen, + enum cgroup_bpf_attach_type atype, + void *t_ctx, + u32 *flags) { struct bpf_sock_addr_kern ctx = { .sk = sk, @@ -1054,18 +1496,26 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, /* 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; + ctx.uaddrlen = 0; + } else { + ctx.uaddrlen = *uaddrlen; } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, + 0, flags); + + if (!ret && uaddr) + *uaddrlen = ctx.uaddrlen; - return ret == 1 ? 0 : -EPERM; + return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); @@ -1075,7 +1525,7 @@ 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 exectuted + * @atype: The type of program to be executed * * socket passed is expected to be of type INET or INET6. * @@ -1087,19 +1537,17 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); */ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - int ret; - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops, - BPF_PROG_RUN); - return ret == 1 ? 0 : -EPERM; + return bpf_prog_run_array_cg(&cgrp->bpf, atype, sock_ops, bpf_prog_run, + 0, NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, - short access, enum bpf_attach_type type) + short access, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp; struct bpf_cgroup_dev_ctx ctx = { @@ -1107,40 +1555,99 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, .major = major, .minor = minor, }; - int allow = 1; + int ret; rcu_read_lock(); cgrp = task_dfl_cgroup(current); - allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, - BPF_PROG_RUN); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, + NULL); rcu_read_unlock(); - return !allow; + return ret; +} + +BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) +{ + /* flags argument is not used now, + * but provides an ability to extend the API. + * verifier checks that its value is correct. + */ + enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + struct bpf_cgroup_storage *storage; + struct bpf_cg_run_ctx *ctx; + void *ptr; + + /* get current cgroup storage from BPF run context */ + ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + storage = ctx->prog_item->cgroup_storage[stype]; + + if (stype == BPF_CGROUP_STORAGE_SHARED) + ptr = &READ_ONCE(storage->buf)->data[0]; + else + ptr = this_cpu_ptr(storage->percpu_buf); + + return (unsigned long)ptr; +} + +const struct bpf_func_proto bpf_get_local_storage_proto = { + .func = bpf_get_local_storage, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_0(bpf_get_retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + return ctx->retval; +} + +const struct bpf_func_proto bpf_get_retval_proto = { + .func = bpf_get_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +BPF_CALL_1(bpf_set_retval, int, retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + ctx->retval = retval; + return 0; } +const struct bpf_func_proto bpf_set_retval_proto = { + .func = bpf_set_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * -cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + + func_proto = cgroup_common_func_proto(func_id, 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_get_current_uid_gid: - return &bpf_get_current_uid_gid_proto; - case BPF_FUNC_get_local_storage: - return &bpf_get_local_storage_proto; - case BPF_FUNC_get_current_cgroup_id: - return &bpf_get_current_cgroup_id_proto; 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); } } -static const struct bpf_func_proto * -cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) -{ - return cgroup_base_func_proto(func_id, prog); -} - static bool cgroup_dev_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -1192,7 +1699,7 @@ 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. @@ -1201,9 +1708,9 @@ 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, - void **buf, size_t *pcount, loff_t *ppos, - enum bpf_attach_type type) + const struct ctl_table *table, int write, + char **buf, size_t *pcount, loff_t *ppos, + enum cgroup_bpf_attach_type atype) { struct bpf_sysctl_kern ctx = { .head = head, @@ -1243,7 +1750,8 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, + NULL); rcu_read_unlock(); kfree(ctx.cur_val); @@ -1256,25 +1764,12 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, kfree(ctx.new_val); } - return ret == 1 ? 0 : -EPERM; + return ret; } #ifdef CONFIG_NET -static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, - enum bpf_attach_type attach_type) -{ - struct bpf_prog_array *prog_array; - bool empty; - - rcu_read_lock(); - prog_array = rcu_dereference(cgrp->bpf.effective[attach_type]); - empty = bpf_prog_array_is_empty(prog_array); - rcu_read_unlock(); - - return empty; -} - -static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) +static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen, + struct bpf_sockopt_buf *buf) { if (unlikely(max_optlen < 0)) return -EINVAL; @@ -1286,6 +1781,15 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) max_optlen = PAGE_SIZE; } + if (max_optlen <= sizeof(buf->data)) { + /* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE + * bytes avoid the cost of kzalloc. + */ + ctx->optval = buf->data; + ctx->optval_end = ctx->optval + max_optlen; + return max_optlen; + } + ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM; @@ -1295,16 +1799,26 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) return max_optlen; } -static void sockopt_free_buf(struct bpf_sockopt_kern *ctx) +static void sockopt_free_buf(struct bpf_sockopt_kern *ctx, + struct bpf_sockopt_buf *buf) { + if (ctx->optval == buf->data) + return; kfree(ctx->optval); } +static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx, + struct bpf_sockopt_buf *buf) +{ + return ctx->optval != buf->data; +} + 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); + struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = *level, @@ -1312,46 +1826,42 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, }; int ret, max_optlen; - /* Opportunistic check to see whether we have any BPF program - * attached to the hook so we don't waste time allocating - * memory and locking the socket. - */ - if (!cgroup_bpf_enabled || - __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) - return 0; - /* Allocate a bit more than the initial user buffer for * BPF program. The canonical use case is overriding * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic). */ max_optlen = max_t(int, 16, *optlen); - - max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; 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; } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT], - &ctx, BPF_PROG_RUN); + ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_SETSOCKOPT, + &ctx, bpf_prog_run, 0, NULL); release_sock(sk); - if (!ret) { - ret = -EPERM; + if (ret) goto out; - } if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ 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 */ @@ -1366,41 +1876,53 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, */ if (ctx.optlen != 0) { *optlen = ctx.optlen; - *kernel_optval = ctx.optval; + /* We've used bpf_sockopt_kern->buf as an intermediary + * storage, but the BPF program indicates that we need + * to pass this data to the kernel setsockopt handler. + * No way to export on-stack buf, have to allocate a + * new buffer. + */ + if (!sockopt_buf_allocated(&ctx, &buf)) { + void *p = kmalloc(ctx.optlen, GFP_USER); + + if (!p) { + ret = -ENOMEM; + goto out; + } + memcpy(p, ctx.optval, ctx.optlen); + *kernel_optval = p; + } else { + *kernel_optval = ctx.optval; + } + /* export and don't free sockopt buf */ + return 0; } } out: - if (ret) - sockopt_free_buf(&ctx); + sockopt_free_buf(&ctx, &buf); return ret; } 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); + struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = level, .optname = optname, - .retval = retval, + .current_task = current, }; + int orig_optlen; int ret; - /* Opportunistic check to see whether we have any BPF program - * attached to the hook so we don't waste time allocating - * memory and locking the socket. - */ - if (!cgroup_bpf_enabled || - __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) - return retval; - + orig_optlen = max_optlen; ctx.optlen = max_optlen; - - max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; @@ -1411,54 +1933,99 @@ 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 (copy_from_sockptr(&ctx.optlen, optlen, + sizeof(ctx.optlen))) { + ret = -EFAULT; + goto out; + } - if (get_user(ctx.optlen, optlen)) { + if (ctx.optlen < 0) { 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; } } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], - &ctx, BPF_PROG_RUN); + ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, + &ctx, bpf_prog_run, retval, NULL); release_sock(sk); - if (!ret) { - ret = -EPERM; - goto out; - } - - if (ctx.optlen > max_optlen) { - ret = -EFAULT; + if (ret < 0) goto out; - } - /* BPF programs only allowed to set retval to 0, not some - * arbitrary value. - */ - if (ctx.retval != 0 && ctx.retval != retval) { + 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; } } - ret = ctx.retval; - out: - sockopt_free_buf(&ctx); + sockopt_free_buf(&ctx, &buf); + return ret; +} + +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_kern ctx = { + .sk = sk, + .level = level, + .optname = optname, + .optlen = *optlen, + .optval = optval, + .optval_end = optval + *optlen, + .current_task = current, + }; + int ret; + + /* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy + * user data back into BPF buffer when reval != 0. This is + * done as an optimization to avoid extra copy, assuming + * kernel won't populate the data in case of an error. + * Here we always pass the data and memset() should + * be called if that data shouldn't be "exported". + */ + + ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, + &ctx, bpf_prog_run, retval, NULL); + if (ret < 0) + return ret; + + if (ctx.optlen > *optlen) + return -EFAULT; + + /* BPF programs can shrink the buffer, export the modifications. + */ + if (ctx.optlen != 0) + *optlen = ctx.optlen; + return ret; } #endif @@ -1607,18 +2174,24 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_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_RDONLY, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + + func_proto = cgroup_common_func_proto(func_id, 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_strtol: - return &bpf_strtol_proto; - case BPF_FUNC_strtoul: - return &bpf_strtoul_proto; case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; case BPF_FUNC_sysctl_get_current_value: @@ -1627,8 +2200,12 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; + case BPF_FUNC_perf_event_output: + return &bpf_event_output_data_proto; default: - return cgroup_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id, prog); } } @@ -1696,10 +2273,12 @@ 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)); @@ -1730,22 +2309,60 @@ const struct bpf_verifier_ops cg_sysctl_verifier_ops = { const struct bpf_prog_ops cg_sysctl_prog_ops = { }; +#ifdef CONFIG_NET +BPF_CALL_1(bpf_get_netns_cookie_sockopt, struct bpf_sockopt_kern *, ctx) +{ + const struct net *net = ctx ? sock_net(ctx->sk) : &init_net; + + return net->net_cookie; +} + +static const struct bpf_func_proto bpf_get_netns_cookie_sockopt_proto = { + .func = bpf_get_netns_cookie_sockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX_OR_NULL, +}; +#endif + static const struct bpf_func_proto * cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + + func_proto = cgroup_common_func_proto(func_id, 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: + return &bpf_get_netns_cookie_sockopt_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + case BPF_FUNC_setsockopt: + if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT) + return &bpf_sk_setsockopt_proto; + return NULL; + case BPF_FUNC_getsockopt: + if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT) + return &bpf_sk_getsockopt_proto; + return NULL; #endif #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif + case BPF_FUNC_perf_event_output: + return &bpf_event_output_data_proto; default: - return cgroup_base_func_proto(func_id, prog); + return bpf_base_func_proto(func_id, prog); } } @@ -1770,7 +2387,7 @@ static bool cg_sockopt_is_valid_access(int off, int size, return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; case offsetof(struct bpf_sockopt, optname): - /* fallthrough */ + fallthrough; case offsetof(struct bpf_sockopt, level): if (size != size_default) return false; @@ -1811,10 +2428,17 @@ 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, @@ -1826,37 +2450,68 @@ 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): - if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval); - else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval); + BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0); + + if (type == BPF_WRITE) { + int treg = BPF_REG_9; + + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg, + offsetof(struct bpf_sockopt_kern, tmp_reg)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), + treg, si->dst_reg, + offsetof(struct bpf_sockopt_kern, current_task)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), + treg, treg, + offsetof(struct task_struct, bpf_ctx)); + *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 { + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sockopt_kern, current_task)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), + si->dst_reg, si->dst_reg, + offsetof(struct task_struct, bpf_ctx)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), + si->dst_reg, si->dst_reg, + offsetof(struct bpf_cg_run_ctx, retval)); + } 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; } @@ -1881,3 +2536,71 @@ const struct bpf_verifier_ops cg_sockopt_verifier_ops = { const struct bpf_prog_ops cg_sockopt_prog_ops = { }; + +/* Common helpers for cgroup hooks. */ +const struct bpf_func_proto * +cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; + case BPF_FUNC_get_retval: + switch (prog->expected_attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + 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; + } + case BPF_FUNC_set_retval: + switch (prog->expected_attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + 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; + } + default: + 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_comm: + return &bpf_get_current_comm_proto; +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_curr_proto; +#endif + case BPF_FUNC_current_task_under_cgroup: + return &bpf_current_task_under_cgroup_proto; + default: + return NULL; + } +} diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c new file mode 100644 index 000000000000..f04a468cf6a7 --- /dev/null +++ b/kernel/bpf/cgroup_iter.c @@ -0,0 +1,359 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2022 Google */ +#include <linux/bpf.h> +#include <linux/btf_ids.h> +#include <linux/cgroup.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> + +#include "../cgroup/cgroup-internal.h" /* cgroup_mutex and cgroup_is_dead */ + +/* cgroup_iter provides four modes of traversal to the cgroup hierarchy. + * + * 1. Walk the descendants of a cgroup in pre-order. + * 2. Walk the descendants of a cgroup in post-order. + * 3. Walk the ancestors of a cgroup. + * 4. Show the given cgroup only. + * + * For walking descendants, cgroup_iter can walk in either pre-order or + * post-order. For walking ancestors, the iter walks up from a cgroup to + * the root. + * + * The iter program can terminate the walk early by returning 1. Walk + * continues if prog returns 0. + * + * The prog can check (seq->num == 0) to determine whether this is + * the first element. The prog may also be passed a NULL cgroup, + * which means the walk has completed and the prog has a chance to + * do post-processing, such as outputting an epilogue. + * + * Note: the iter_prog is called with cgroup_mutex held. + * + * Currently only one session is supported, which means, depending on the + * volume of data bpf program intends to send to user space, the number + * of cgroups that can be walked is limited. For example, given the current + * buffer size is 8 * PAGE_SIZE, if the program sends 64B data for each + * cgroup, assuming PAGE_SIZE is 4kb, the total number of cgroups that can + * be walked is 512. This is a limitation of cgroup_iter. If the output data + * is larger than the kernel buffer size, after all data in the kernel buffer + * is consumed by user space, the subsequent read() syscall will signal + * EOPNOTSUPP. In order to work around, the user may have to update their + * program to reduce the volume of data sent to output. For example, skip + * some uninteresting cgroups. + */ + +struct bpf_iter__cgroup { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct cgroup *, cgroup); +}; + +struct cgroup_iter_priv { + struct cgroup_subsys_state *start_css; + bool visited_all; + bool terminate; + int order; +}; + +static void *cgroup_iter_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct cgroup_iter_priv *p = seq->private; + + cgroup_lock(); + + /* cgroup_iter doesn't support read across multiple sessions. */ + if (*pos > 0) { + if (p->visited_all) + return NULL; + + /* Haven't visited all, but because cgroup_mutex has dropped, + * return -EOPNOTSUPP to indicate incomplete iteration. + */ + return ERR_PTR(-EOPNOTSUPP); + } + + ++*pos; + p->terminate = false; + p->visited_all = false; + if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE) + return css_next_descendant_pre(NULL, p->start_css); + else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST) + return css_next_descendant_post(NULL, p->start_css); + else /* BPF_CGROUP_ITER_SELF_ONLY and BPF_CGROUP_ITER_ANCESTORS_UP */ + return p->start_css; +} + +static int __cgroup_iter_seq_show(struct seq_file *seq, + struct cgroup_subsys_state *css, int in_stop); + +static void cgroup_iter_seq_stop(struct seq_file *seq, void *v) +{ + struct cgroup_iter_priv *p = seq->private; + + cgroup_unlock(); + + /* pass NULL to the prog for post-processing */ + if (!v) { + __cgroup_iter_seq_show(seq, NULL, true); + p->visited_all = true; + } +} + +static void *cgroup_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct cgroup_subsys_state *curr = (struct cgroup_subsys_state *)v; + struct cgroup_iter_priv *p = seq->private; + + ++*pos; + if (p->terminate) + return NULL; + + if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE) + return css_next_descendant_pre(curr, p->start_css); + else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST) + return css_next_descendant_post(curr, p->start_css); + else if (p->order == BPF_CGROUP_ITER_ANCESTORS_UP) + return curr->parent; + else /* BPF_CGROUP_ITER_SELF_ONLY */ + return NULL; +} + +static int __cgroup_iter_seq_show(struct seq_file *seq, + struct cgroup_subsys_state *css, int in_stop) +{ + struct cgroup_iter_priv *p = seq->private; + struct bpf_iter__cgroup ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int ret = 0; + + /* cgroup is dead, skip this element */ + if (css && cgroup_is_dead(css->cgroup)) + return 0; + + ctx.meta = &meta; + ctx.cgroup = css ? css->cgroup : NULL; + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (prog) + ret = bpf_iter_run_prog(prog, &ctx); + + /* if prog returns > 0, terminate after this element. */ + if (ret != 0) + p->terminate = true; + + return 0; +} + +static int cgroup_iter_seq_show(struct seq_file *seq, void *v) +{ + return __cgroup_iter_seq_show(seq, (struct cgroup_subsys_state *)v, + false); +} + +static const struct seq_operations cgroup_iter_seq_ops = { + .start = cgroup_iter_seq_start, + .next = cgroup_iter_seq_next, + .stop = cgroup_iter_seq_stop, + .show = cgroup_iter_seq_show, +}; + +BTF_ID_LIST_GLOBAL_SINGLE(bpf_cgroup_btf_id, struct, cgroup) + +static int cgroup_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux) +{ + struct cgroup_iter_priv *p = (struct cgroup_iter_priv *)priv; + struct cgroup *cgrp = aux->cgroup.start; + + /* bpf_iter_attach_cgroup() has already acquired an extra reference + * for the start cgroup, but the reference may be released after + * cgroup_iter_seq_init(), so acquire another reference for the + * start cgroup. + */ + p->start_css = &cgrp->self; + css_get(p->start_css); + p->terminate = false; + p->visited_all = false; + p->order = aux->cgroup.order; + return 0; +} + +static void cgroup_iter_seq_fini(void *priv) +{ + struct cgroup_iter_priv *p = (struct cgroup_iter_priv *)priv; + + css_put(p->start_css); +} + +static const struct bpf_iter_seq_info cgroup_iter_seq_info = { + .seq_ops = &cgroup_iter_seq_ops, + .init_seq_private = cgroup_iter_seq_init, + .fini_seq_private = cgroup_iter_seq_fini, + .seq_priv_size = sizeof(struct cgroup_iter_priv), +}; + +static int bpf_iter_attach_cgroup(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) +{ + int fd = linfo->cgroup.cgroup_fd; + u64 id = linfo->cgroup.cgroup_id; + int order = linfo->cgroup.order; + struct cgroup *cgrp; + + if (order != BPF_CGROUP_ITER_DESCENDANTS_PRE && + order != BPF_CGROUP_ITER_DESCENDANTS_POST && + order != BPF_CGROUP_ITER_ANCESTORS_UP && + order != BPF_CGROUP_ITER_SELF_ONLY) + return -EINVAL; + + if (fd && id) + return -EINVAL; + + if (fd) + cgrp = cgroup_v1v2_get_from_fd(fd); + else if (id) + cgrp = cgroup_get_from_id(id); + else /* walk the entire hierarchy by default. */ + cgrp = cgroup_get_from_path("/"); + + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + aux->cgroup.start = cgrp; + aux->cgroup.order = order; + return 0; +} + +static void bpf_iter_detach_cgroup(struct bpf_iter_aux_info *aux) +{ + cgroup_put(aux->cgroup.start); +} + +static void bpf_iter_cgroup_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq) +{ + char *buf; + + buf = kzalloc(PATH_MAX, GFP_KERNEL); + if (!buf) { + seq_puts(seq, "cgroup_path:\t<unknown>\n"); + goto show_order; + } + + /* If cgroup_path_ns() fails, buf will be an empty string, cgroup_path + * will print nothing. + * + * Path is in the calling process's cgroup namespace. + */ + cgroup_path_ns(aux->cgroup.start, buf, PATH_MAX, + current->nsproxy->cgroup_ns); + seq_printf(seq, "cgroup_path:\t%s\n", buf); + kfree(buf); + +show_order: + if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_PRE) + seq_puts(seq, "order: descendants_pre\n"); + else if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_POST) + seq_puts(seq, "order: descendants_post\n"); + else if (aux->cgroup.order == BPF_CGROUP_ITER_ANCESTORS_UP) + seq_puts(seq, "order: ancestors_up\n"); + else /* BPF_CGROUP_ITER_SELF_ONLY */ + seq_puts(seq, "order: self_only\n"); +} + +static int bpf_iter_cgroup_fill_link_info(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info) +{ + info->iter.cgroup.order = aux->cgroup.order; + info->iter.cgroup.cgroup_id = cgroup_id(aux->cgroup.start); + return 0; +} + +DEFINE_BPF_ITER_FUNC(cgroup, struct bpf_iter_meta *meta, + struct cgroup *cgroup) + +static struct bpf_iter_reg bpf_cgroup_reg_info = { + .target = "cgroup", + .feature = BPF_ITER_RESCHED, + .attach_target = bpf_iter_attach_cgroup, + .detach_target = bpf_iter_detach_cgroup, + .show_fdinfo = bpf_iter_cgroup_show_fdinfo, + .fill_link_info = bpf_iter_cgroup_fill_link_info, + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__cgroup, cgroup), + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, + }, + .seq_info = &cgroup_iter_seq_info, +}; + +static int __init bpf_cgroup_iter_init(void) +{ + bpf_cgroup_reg_info.ctx_arg_info[0].btf_id = bpf_cgroup_btf_id[0]; + return bpf_iter_reg_target(&bpf_cgroup_reg_info); +} + +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 9df4cc9a2907..da729cbbaeb9 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -21,18 +21,26 @@ #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/frame.h> +#include <linux/objtool.h> +#include <linux/overflow.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> -#include <asm/unaligned.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 <asm/barrier.h> +#include <linux/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] @@ -54,8 +62,12 @@ #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; +bool bpf_global_ma_set; + /* No hurry in this branch * * Exported for the bpf jit load helper. @@ -64,47 +76,70 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns { u8 *ptr = NULL; - if (k >= SKF_NET_OFF) + if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) + } else if (k >= SKF_LL_OFF) { + if (unlikely(!skb_mac_header_was_set(skb))) + return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - + } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; 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 | __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 | 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, bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); + if (!fp->active) { + vfree(fp); + kfree(aux); + return NULL; + } fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); + fp->blinding_requested = bpf_jit_blinding_enabled(fp); +#ifdef CONFIG_CGROUP_BPF + aux->cgroup_atype = CGROUP_BPF_ATTACH_TYPE_INVALID; +#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); return fp; } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __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; @@ -112,8 +147,9 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) if (!prog) return NULL; - prog->aux->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags); - if (!prog->aux->stats) { + prog->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags); + if (!prog->stats) { + free_percpu(prog->active); kfree(prog->aux); vfree(prog); return NULL; @@ -122,7 +158,7 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) for_each_possible_cpu(cpu) { struct bpf_prog_stats *pstats; - pstats = per_cpu_ptr(prog->aux->stats, cpu); + pstats = per_cpu_ptr(prog->stats, cpu); u64_stats_init(&pstats->syncp); } return prog; @@ -134,25 +170,25 @@ int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) if (!prog->aux->nr_linfo || !prog->jit_requested) return 0; - prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo, - sizeof(*prog->aux->jited_linfo), - GFP_KERNEL | __GFP_NOWARN); + prog->aux->jited_linfo = kvcalloc(prog->aux->nr_linfo, + sizeof(*prog->aux->jited_linfo), + bpf_memcg_flags(GFP_KERNEL | __GFP_NOWARN)); if (!prog->aux->jited_linfo) return -ENOMEM; return 0; } -void bpf_prog_free_jited_linfo(struct bpf_prog *prog) +void bpf_prog_jit_attempt_done(struct bpf_prog *prog) { - kfree(prog->aux->jited_linfo); - prog->aux->jited_linfo = NULL; -} + if (prog->aux->jited_linfo && + (!prog->jited || !prog->aux->jited_linfo[0])) { + kvfree(prog->aux->jited_linfo); + prog->aux->jited_linfo = NULL; + } -void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog) -{ - if (prog->aux->jited_linfo && !prog->aux->jited_linfo[0]) - bpf_prog_free_jited_linfo(prog); + kfree(prog->aux->kfunc_tab); + prog->aux->kfunc_tab = NULL; } /* The jit engine is responsible to provide an array @@ -162,7 +198,7 @@ void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog) * here is relative to the prog itself instead of the main prog. * This array has one entry for each xlated bpf insn. * - * jited_off is the byte off to the last byte of the jited insn. + * jited_off is the byte off to the end of the jited insn. * * Hence, with * insn_start: @@ -186,7 +222,7 @@ 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; @@ -208,34 +244,20 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, insn_to_jit_off[linfo[i].insn_off - insn_start - 1]; } -void bpf_prog_free_linfo(struct bpf_prog *prog) -{ - bpf_prog_free_jited_linfo(prog); - kvfree(prog->aux->linfo); -} - 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 | __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, delta; - int ret; + u32 pages; size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) return fp_old; - delta = pages - fp_old->pages; - ret = __bpf_prog_charge(fp_old->aux->user, delta); - if (ret) - return NULL; - fp = __vmalloc(size, gfp_flags); - if (fp == NULL) { - __bpf_prog_uncharge(fp_old->aux->user, delta); - } else { + if (fp) { memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = pages; fp->aux->prog = fp; @@ -244,6 +266,8 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, * reallocated structure. */ fp_old->aux = NULL; + fp_old->stats = NULL; + fp_old->active = NULL; __bpf_prog_free(fp_old); } @@ -253,10 +277,13 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { - free_percpu(fp->aux->stats); + mutex_destroy(&fp->aux->used_maps_mutex); + mutex_destroy(&fp->aux->dst_mutex); kfree(fp->aux->poke_tab); kfree(fp->aux); } + free_percpu(fp->stats); + free_percpu(fp->active); vfree(fp); } @@ -354,9 +381,18 @@ 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; @@ -364,8 +400,12 @@ 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; } @@ -387,6 +427,13 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, i = end_new; insn = prog->insnsi + end_old; } + if (bpf_pseudo_func(insn)) { + ret = bpf_adj_delta_to_imm(insn, pos, end_old, + end_new, i, probe_pass); + if (ret) + return ret; + continue; + } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || @@ -492,6 +539,8 @@ 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 */ @@ -499,14 +548,16 @@ 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]); } @@ -522,17 +573,15 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; +long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) { - const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog); - unsigned long addr = (unsigned long)hdr; - WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); prog->aux->ksym.start = (unsigned long) prog->bpf_func; - prog->aux->ksym.end = addr + hdr->pages * PAGE_SIZE; + prog->aux->ksym.end = prog->aux->ksym.start + prog->jited_len; } static void @@ -558,7 +607,7 @@ 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); @@ -592,7 +641,11 @@ 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; @@ -637,16 +690,10 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) return fp->jited && !bpf_prog_was_classic(fp); } -static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) -{ - return list_empty(&fp->aux->ksym.lnode) || - fp->aux->ksym.lnode.prev == LIST_POISON2; -} - 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); @@ -654,6 +701,23 @@ 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) @@ -662,6 +726,11 @@ 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) @@ -672,11 +741,11 @@ 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); @@ -684,9 +753,8 @@ 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) @@ -708,7 +776,7 @@ 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); @@ -750,7 +818,7 @@ 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; @@ -773,7 +841,8 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, if (size > poke_tab_max) return -ENOSPC; - if (poke->ip || poke->ip_stable || poke->adj_off) + if (poke->tailcall_target || poke->tailcall_target_stable || + poke->tailcall_bypass || poke->adj_off || poke->bypass_addr) return -EINVAL; switch (poke->reason) { @@ -785,7 +854,7 @@ 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; @@ -796,6 +865,166 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, return slot; } +/* + * BPF program pack allocator. + * + * Most BPF programs are pretty small. Allocating a hole page for each + * program is sometime a waste. Many small bpf program also adds pressure + * to instruction TLB. To solve this issue, we introduce a BPF program pack + * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86) + * to host BPF programs. + */ +#define BPF_PROG_CHUNK_SHIFT 6 +#define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT) +#define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1)) + +struct bpf_prog_pack { + struct list_head list; + void *ptr; + unsigned long bitmap[]; +}; + +void bpf_jit_fill_hole_with_zero(void *area, unsigned int size) +{ + memset(area, 0, size); +} + +#define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE) + +static DEFINE_MUTEX(pack_mutex); +static LIST_HEAD(pack_list); + +/* PMD_SIZE is not available in some special config, e.g. ARCH=arm with + * CONFIG_MMU=n. Use PAGE_SIZE in these cases. + */ +#ifdef PMD_SIZE +/* 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 + +#define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE) + +static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) +{ + struct bpf_prog_pack *pack; + int err; + + pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)), + GFP_KERNEL); + if (!pack) + return NULL; + pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE); + if (!pack->ptr) + goto out; + bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE); + bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); + + set_vm_flush_reset_perms(pack->ptr); + 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) +{ + unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); + struct bpf_prog_pack *pack; + unsigned long pos; + void *ptr = NULL; + + mutex_lock(&pack_mutex); + if (size > BPF_PROG_PACK_SIZE) { + size = round_up(size, PAGE_SIZE); + ptr = bpf_jit_alloc_exec(size); + if (ptr) { + int err; + + bpf_fill_ill_insns(ptr, size); + set_vm_flush_reset_perms(ptr); + err = set_memory_rox((unsigned long)ptr, + size / PAGE_SIZE); + if (err) { + bpf_jit_free_exec(ptr); + ptr = NULL; + } + } + goto out; + } + list_for_each_entry(pack, &pack_list, list) { + pos = bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, + nbits, 0); + if (pos < BPF_PROG_CHUNK_COUNT) + goto found_free_area; + } + + pack = alloc_new_pack(bpf_fill_ill_insns); + if (!pack) + goto out; + + pos = 0; + +found_free_area: + bitmap_set(pack->bitmap, pos, nbits); + ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT); + +out: + mutex_unlock(&pack_mutex); + return ptr; +} + +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 (size > BPF_PROG_PACK_SIZE) { + bpf_jit_free_exec(ptr); + goto out; + } + + list_for_each_entry(tmp, &pack_list, list) { + if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) { + pack = tmp; + break; + } + } + + if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) + goto out; + + 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(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); + bpf_jit_free_exec(pack->ptr); + kfree(pack); + } +out: + mutex_unlock(&pack_mutex); +} + static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, @@ -814,18 +1043,18 @@ u64 __weak bpf_jit_alloc_exec_limit(void) static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ - bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2, + bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); + bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } pure_initcall(bpf_jit_charge_init); -static int bpf_jit_charge_modmem(u32 pages) +int bpf_jit_charge_modmem(u32 size) { - if (atomic_long_add_return(pages, &bpf_jit_current) > - (bpf_jit_limit >> PAGE_SHIFT)) { - if (!capable(CAP_SYS_ADMIN)) { - atomic_long_sub(pages, &bpf_jit_current); + if (atomic_long_add_return(size, &bpf_jit_current) > READ_ONCE(bpf_jit_limit)) { + if (!bpf_capable()) { + atomic_long_sub(size, &bpf_jit_current); return -EPERM; } } @@ -833,19 +1062,19 @@ static int bpf_jit_charge_modmem(u32 pages) return 0; } -static void bpf_jit_uncharge_modmem(u32 pages) +void bpf_jit_uncharge_modmem(u32 size) { - atomic_long_sub(pages, &bpf_jit_current); + atomic_long_sub(size, &bpf_jit_current); } 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 * @@ -854,7 +1083,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; - u32 size, hole, start, pages; + u32 size, hole, start; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); @@ -864,23 +1093,22 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); - pages = size / PAGE_SIZE; - if (bpf_jit_charge_modmem(pages)) + if (bpf_jit_charge_modmem(size)) return NULL; hdr = bpf_jit_alloc_exec(size); if (!hdr) { - bpf_jit_uncharge_modmem(pages); + bpf_jit_uncharge_modmem(size); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); - hdr->pages = pages; + hdr->size = size; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); - start = (get_random_int() % hole) & ~(alignment - 1); + start = get_random_u32_below(hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; @@ -890,10 +1118,120 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr) { - u32 pages = hdr->pages; + u32 size = hdr->size; bpf_jit_free_exec(hdr); - bpf_jit_uncharge_modmem(pages); + bpf_jit_uncharge_modmem(size); +} + +/* Allocate jit binary from bpf_prog_pack allocator. + * Since the allocated memory is RO+X, the JIT engine cannot write directly + * to the memory. To solve this problem, a RW buffer is also allocated at + * as the same time. The JIT engine should calculate offsets based on the + * RO memory address, but write JITed program to the RW buffer. Once the + * JIT engine finishes, it calls bpf_jit_binary_pack_finalize, which copies + * the JITed program to the RO memory. + */ +struct bpf_binary_header * +bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, + unsigned int alignment, + struct bpf_binary_header **rw_header, + u8 **rw_image, + bpf_jit_fill_hole_t bpf_fill_ill_insns) +{ + struct bpf_binary_header *ro_header; + u32 size, hole, start; + + WARN_ON_ONCE(!is_power_of_2(alignment) || + alignment > BPF_IMAGE_ALIGNMENT); + + /* add 16 bytes for a random section of illegal instructions */ + size = round_up(proglen + sizeof(*ro_header) + 16, BPF_PROG_CHUNK_SIZE); + + if (bpf_jit_charge_modmem(size)) + return NULL; + ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns); + if (!ro_header) { + bpf_jit_uncharge_modmem(size); + return NULL; + } + + *rw_header = kvmalloc(size, GFP_KERNEL); + if (!*rw_header) { + bpf_prog_pack_free(ro_header, size); + bpf_jit_uncharge_modmem(size); + return NULL; + } + + /* Fill space with illegal/arch-dep instructions. */ + bpf_fill_ill_insns(*rw_header, size); + (*rw_header)->size = size; + + hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)), + BPF_PROG_CHUNK_SIZE - sizeof(*ro_header)); + start = get_random_u32_below(hole) & ~(alignment - 1); + + *image_ptr = &ro_header->image[start]; + *rw_image = &(*rw_header)->image[start]; + + return ro_header; +} + +/* Copy JITed text from rw_header to its final location, the ro_header. */ +int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header) +{ + void *ptr; + + ptr = bpf_arch_text_copy(ro_header, rw_header, rw_header->size); + + kvfree(rw_header); + + if (IS_ERR(ptr)) { + bpf_prog_pack_free(ro_header, ro_header->size); + return PTR_ERR(ptr); + } + return 0; +} + +/* bpf_jit_binary_pack_free is called in two different scenarios: + * 1) when the program is freed after; + * 2) when the JIT engine fails (before bpf_jit_binary_pack_finalize). + * For case 2), we need to free both the RO memory and the RW buffer. + * + * bpf_jit_binary_pack_free requires proper ro_header->size. However, + * bpf_jit_binary_pack_alloc does not set it. Therefore, ro_header->size + * must be set with either bpf_jit_binary_pack_finalize (normal path) or + * bpf_arch_text_copy (when jit fails). + */ +void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header) +{ + u32 size = ro_header->size; + + bpf_prog_pack_free(ro_header, size); + kvfree(rw_header); + bpf_jit_uncharge_modmem(size); +} + +struct bpf_binary_header * +bpf_jit_binary_pack_hdr(const struct bpf_prog *fp) +{ + unsigned long real_start = (unsigned long)fp->bpf_func; + unsigned long addr; + + addr = real_start & BPF_PROG_CHUNK_MASK; + return (void *)addr; +} + +static inline struct bpf_binary_header * +bpf_jit_binary_hdr(const struct bpf_prog *fp) +{ + unsigned long real_start = (unsigned long)fp->bpf_func; + unsigned long addr; + + addr = real_start & PAGE_MASK; + return (void *)addr; } /* This symbol is only overridden by archs that have different @@ -906,7 +1244,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp) struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); bpf_jit_binary_free(hdr); - WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); } @@ -920,6 +1257,7 @@ 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) { @@ -930,10 +1268,15 @@ 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 @@ -953,7 +1296,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, bool emit_zext) { struct bpf_insn *to = to_buff; - u32 imm_rnd = get_random_int(); + u32 imm_rnd = get_random_u32(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); @@ -998,7 +1341,7 @@ 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: @@ -1012,7 +1355,7 @@ 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: @@ -1111,6 +1454,8 @@ static void bpf_prog_clone_free(struct bpf_prog *fp) * clone is guaranteed to not be locked. */ fp->aux = NULL; + fp->stats = NULL; + fp->active = NULL; __bpf_prog_free(fp); } @@ -1131,7 +1476,7 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) struct bpf_insn *insn; int i, rewritten; - if (!bpf_jit_blinding_enabled(prog) || prog->blinded) + if (!prog->blinding_requested || prog->blinded) return prog; clone = bpf_prog_clone_create(prog, GFP_USER); @@ -1142,6 +1487,16 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { + if (bpf_pseudo_func(insn)) { + /* ld_imm64 with an address of bpf subprog is not + * a user controlled constant. Don't randomize it, + * since it will conflict with jit_subprogs() logic. + */ + insn++; + i++; + continue; + } + /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. @@ -1238,6 +1593,7 @@ 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), \ @@ -1306,14 +1662,15 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ + INSN_2(JMP32, JA), \ /* 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, XADD, W), \ - INSN_3(STX, XADD, DW), \ + INSN_3(STX, ATOMIC, W), \ + INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ @@ -1325,6 +1682,9 @@ 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) @@ -1343,6 +1703,7 @@ 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_JCOND] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL @@ -1350,21 +1711,16 @@ 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 + * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions - * @stack: is the eBPF storage stack * * Decode and execute eBPF instructions. + * + * Return: whatever value is in %BPF_R0 at program exit */ -static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) +static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z @@ -1375,10 +1731,14 @@ static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u6 /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, + [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [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 @@ -1390,29 +1750,54 @@ static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u6 select_insn: goto *jumptable[insn->code]; - /* ALU */ -#define ALU(OPCODE, OP) \ - ALU64_##OPCODE##_X: \ - DST = DST OP SRC; \ - CONT; \ - ALU_##OPCODE##_X: \ - DST = (u32) DST OP (u32) SRC; \ - CONT; \ - ALU64_##OPCODE##_K: \ - DST = DST OP IMM; \ - CONT; \ - ALU_##OPCODE##_K: \ - DST = (u32) DST OP (u32) IMM; \ + /* Explicitly mask the register-based shift amounts with 63 or 31 + * to avoid undefined behavior. Normally this won't affect the + * generated code, for example, in case of native 64 bit archs such + * as x86-64 or arm64, the compiler is optimizing the AND away for + * the interpreter. In case of JITs, each of the JIT backends compiles + * the BPF shift operations to machine instructions which produce + * implementation-defined results in such a case; the resulting + * contents of the register may be arbitrary, but program behaviour + * as a whole remains defined. In other words, in case of JIT backends, + * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation. + */ + /* ALU (shifts) */ +#define SHT(OPCODE, OP) \ + ALU64_##OPCODE##_X: \ + DST = DST OP (SRC & 63); \ + CONT; \ + ALU_##OPCODE##_X: \ + DST = (u32) DST OP ((u32) SRC & 31); \ + CONT; \ + ALU64_##OPCODE##_K: \ + DST = DST OP IMM; \ + CONT; \ + ALU_##OPCODE##_K: \ + DST = (u32) DST OP (u32) IMM; \ + CONT; + /* ALU (rest) */ +#define ALU(OPCODE, OP) \ + ALU64_##OPCODE##_X: \ + DST = DST OP SRC; \ + CONT; \ + ALU_##OPCODE##_X: \ + DST = (u32) DST OP (u32) SRC; \ + CONT; \ + ALU64_##OPCODE##_K: \ + DST = DST OP IMM; \ + CONT; \ + ALU_##OPCODE##_K: \ + DST = (u32) DST OP (u32) IMM; \ CONT; - ALU(ADD, +) ALU(SUB, -) ALU(AND, &) ALU(OR, |) - ALU(LSH, <<) - ALU(RSH, >>) ALU(XOR, ^) ALU(MUL, *) + SHT(LSH, <<) + SHT(RSH, >>) +#undef SHT #undef ALU ALU_NEG: DST = (u32) -DST; @@ -1421,13 +1806,36 @@ 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; @@ -1437,48 +1845,126 @@ select_insn: insn++; CONT; ALU_ARSH_X: - DST = (u64) (u32) (((s32) DST) >> SRC); + DST = (u64) (u32) (((s32) DST) >> (SRC & 31)); CONT; ALU_ARSH_K: DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: - (*(s64 *) &DST) >>= SRC; + (*(s64 *) &DST) >>= (SRC & 63); CONT; ALU64_ARSH_K: (*(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) { @@ -1506,6 +1992,19 @@ 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: @@ -1532,7 +2031,8 @@ select_insn: if (unlikely(index >= array->map.max_entries)) goto out; - if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) + + if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; @@ -1554,6 +2054,9 @@ out: JMP_JA: insn += insn->off; CONT; + JMP32_JA: + insn += insn->imm; + CONT; JMP_EXIT: return BPF_R0; /* JMP */ @@ -1594,7 +2097,19 @@ out: COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP - /* STX and ST and LDX*/ + /* 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. + */ + barrier_nospec(); + CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ @@ -1604,6 +2119,11 @@ out: CONT; \ LDX_MEM_##SIZEOP: \ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ + CONT; \ + LDX_PROBE_MEM_##SIZEOP: \ + bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ + (const void *)(long) (SRC + insn->off)); \ + DST = *((SIZE *)&DST); \ CONT; LDST(B, u8) @@ -1611,23 +2131,75 @@ out: LDST(W, u32) LDST(DW, u64) #undef LDST -#define LDX_PROBE(SIZEOP, SIZE) \ - LDX_PROBE_MEM_##SIZEOP: \ - bpf_probe_read_kernel(&DST, SIZE, (const void *)(long) (SRC + insn->off)); \ - CONT; - LDX_PROBE(B, 1) - LDX_PROBE(H, 2) - LDX_PROBE(W, 4) - LDX_PROBE(DW, 8) -#undef LDX_PROBE - - STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ - atomic_add((u32) SRC, (atomic_t *)(unsigned long) - (DST + insn->off)); + +#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; - STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ - atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) - (DST + insn->off)); + + 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 \ + atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ + (DST + insn->off)); \ + 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 \ + SRC = (u64) atomic64_fetch_##KOP( \ + (u64) SRC, \ + (atomic64_t *)(unsigned long) (DST + insn->off)); \ + break; + + STX_ATOMIC_DW: + STX_ATOMIC_W: + switch (IMM) { + ATOMIC_ALU_OP(BPF_ADD, add) + ATOMIC_ALU_OP(BPF_AND, and) + ATOMIC_ALU_OP(BPF_OR, or) + ATOMIC_ALU_OP(BPF_XOR, xor) +#undef ATOMIC_ALU_OP + + case BPF_XCHG: + if (BPF_SIZE(insn->code) == BPF_W) + SRC = (u32) atomic_xchg( + (atomic_t *)(unsigned long) (DST + insn->off), + (u32) SRC); + else + SRC = (u64) atomic64_xchg( + (atomic64_t *)(unsigned long) (DST + insn->off), + (u64) SRC); + 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 + BPF_R0 = (u64) atomic64_cmpxchg( + (atomic64_t *)(unsigned long) (DST + insn->off), + (u64) BPF_R0, (u64) SRC); + break; + + default: + goto default_label; + } CONT; default_label: @@ -1637,7 +2209,8 @@ out: * * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable(). */ - pr_warn("BPF interpreter: unknown opcode %02x\n", insn->code); + pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n", + insn->code, insn->imm); BUG_ON(1); return 0; } @@ -1647,11 +2220,12 @@ out: static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ - u64 regs[MAX_BPF_EXT_REG]; \ + 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, stack); \ + return ___bpf_prog_run(regs, insn); \ } #define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size @@ -1662,13 +2236,14 @@ 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; \ BPF_R3 = r3; \ BPF_R4 = r4; \ BPF_R5 = r5; \ - return ___bpf_prog_run(regs, insn, stack); \ + return ___bpf_prog_run(regs, insn); \ } #define EVAL1(FN, X) FN(X) @@ -1696,14 +2271,16 @@ 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); @@ -1712,7 +2289,7 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } - +#endif #else static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) @@ -1725,43 +2302,78 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, } #endif -bool bpf_prog_array_compatible(struct bpf_array *array, - const struct bpf_prog *fp) +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; + if (fp->kprobe_override) return false; - if (!array->aux->type) { + /* 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(aux)) + return false; + + spin_lock(&map->owner.lock); + if (!map->owner.type) { /* There's no owner yet where we could check for * compatibility. */ - array->aux->type = fp->type; - array->aux->jited = fp->jited; - return true; + map->owner.type = prog_type; + map->owner.jited = fp->jited; + map->owner.xdp_has_frags = aux->xdp_has_frags; + map->owner.attach_func_proto = aux->attach_func_proto; + ret = true; + } else { + ret = map->owner.type == prog_type && + map->owner.jited == fp->jited && + map->owner.xdp_has_frags == aux->xdp_has_frags; + 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); - return array->aux->type == fp->type && - array->aux->jited == fp->jited; + return ret; } static int bpf_check_tail_call(const struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; - int i; + int i, ret = 0; + mutex_lock(&aux->used_maps_mutex); for (i = 0; i < aux->used_map_cnt; i++) { struct bpf_map *map = aux->used_maps[i]; - struct bpf_array *array; - if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) + if (!map_type_contains_progs(map)) continue; - array = container_of(map, struct bpf_array, map); - if (!bpf_prog_array_compatible(array, fp)) - return -EINVAL; + if (!bpf_prog_map_compatible(map, fp)) { + ret = -EINVAL; + goto out; + } } - return 0; +out: + mutex_unlock(&aux->used_maps_mutex); + return ret; } static void bpf_prog_select_func(struct bpf_prog *fp) @@ -1777,20 +2389,29 @@ static void bpf_prog_select_func(struct bpf_prog *fp) /** * bpf_prog_select_runtime - select exec runtime for BPF program - * @fp: bpf_prog populated with internal BPF program + * @fp: bpf_prog populated with BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. - * The BPF program will be executed via BPF_PROG_RUN() macro. + * The BPF program will be executed via bpf_prog_run() function. + * + * Return: the &fp argument along with &err set to 0 for success or + * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ + bool jit_needed = false; + if (fp->bpf_func) goto finalize; + if (IS_ENABLED(CONFIG_BPF_JIT_ALWAYS_ON) || + bpf_prog_has_kfunc_call(fp)) + jit_needed = true; + bpf_prog_select_func(fp); /* eBPF JITs can rewrite the program in case constant @@ -1799,20 +2420,16 @@ 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; fp = bpf_int_jit_compile(fp); - if (!fp->jited) { - bpf_prog_free_jited_linfo(fp); -#ifdef CONFIG_BPF_JIT_ALWAYS_ON + bpf_prog_jit_attempt_done(fp); + if (!fp->jited && jit_needed) { *err = -ENOTSUPP; return fp; -#endif - } else { - bpf_prog_free_unused_jited_linfo(fp); } } else { *err = bpf_prog_offload_compile(fp); @@ -1821,7 +2438,9 @@ 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 @@ -1848,37 +2467,51 @@ static struct bpf_prog_dummy { }, }; -/* to avoid allocating empty bpf_prog_array for cgroups that - * don't have bpf program attached use one global 'empty_prog_array' - * It will not be modified the caller of bpf_prog_array_alloc() - * (since caller requested prog_cnt == 0) - * that pointer should be 'freed' by bpf_prog_array_free() - */ -static struct { - struct bpf_prog_array hdr; - struct bpf_prog *null_prog; -} empty_prog_array = { +struct bpf_empty_prog_array bpf_empty_prog_array = { .null_prog = NULL, }; +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 &empty_prog_array.hdr; + return p; } void bpf_prog_array_free(struct bpf_prog_array *progs) { - if (!progs || progs == &empty_prog_array.hdr) + if (!progs || progs == &bpf_empty_prog_array.hdr) return; kfree_rcu(progs, rcu); } +static void __bpf_prog_array_free_sleepable_cb(struct rcu_head *rcu) +{ + struct bpf_prog_array *progs; + + /* If RCU Tasks Trace grace period implies RCU grace period, there is + * no need to call kfree_rcu(), just call kfree() directly. + */ + progs = container_of(rcu, struct bpf_prog_array, rcu); + if (rcu_trace_implies_rcu_gp()) + kfree(progs); + else + kfree_rcu(progs, rcu); +} + +void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs) +{ + if (!progs || progs == &bpf_empty_prog_array.hdr) + return; + call_rcu_tasks_trace(&progs->rcu, __bpf_prog_array_free_sleepable_cb); +} + int bpf_prog_array_length(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; @@ -1958,16 +2591,71 @@ void bpf_prog_array_delete_safe(struct bpf_prog_array *array, } } +/** + * bpf_prog_array_delete_safe_at() - Replaces the program at the given + * index into the program array with + * a dummy no-op program. + * @array: a bpf_prog_array + * @index: the index of the program to replace + * + * Skips over dummy programs, by not counting them, when calculating + * the position of the program to replace. + * + * Return: + * * 0 - Success + * * -EINVAL - Invalid index value. Must be a non-negative integer. + * * -ENOENT - Index out of range + */ +int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index) +{ + return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog); +} + +/** + * bpf_prog_array_update_at() - Updates the program at the given index + * into the program array. + * @array: a bpf_prog_array + * @index: the index of the program to update + * @prog: the program to insert into the array + * + * Skips over dummy programs, by not counting them, when calculating + * the position of the program to update. + * + * Return: + * * 0 - Success + * * -EINVAL - Invalid index value. Must be a non-negative integer. + * * -ENOENT - Index out of range + */ +int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, + struct bpf_prog *prog) +{ + struct bpf_prog_array_item *item; + + if (unlikely(index < 0)) + return -EINVAL; + + for (item = array->items; item->prog; item++) { + if (item->prog == &dummy_bpf_prog.prog) + continue; + if (!index) { + WRITE_ONCE(item->prog, prog); + return 0; + } + index--; + } + return -ENOENT; +} + int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, + u64 bpf_cookie, struct bpf_prog_array **new_array) { int new_prog_cnt, carry_prog_cnt = 0; - struct bpf_prog_array_item *existing; + struct bpf_prog_array_item *existing, *new; struct bpf_prog_array *array; bool found_exclude = false; - int new_prog_idx = 0; /* Figure out how many existing progs we need to carry over to * the new array. @@ -2004,20 +2692,27 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL); if (!array) return -ENOMEM; + new = array->items; /* Fill in the new prog array */ if (carry_prog_cnt) { existing = old_array->items; - for (; existing->prog; existing++) - if (existing->prog != exclude_prog && - existing->prog != &dummy_bpf_prog.prog) { - array->items[new_prog_idx++].prog = - existing->prog; - } + for (; existing->prog; existing++) { + if (existing->prog == exclude_prog || + existing->prog == &dummy_bpf_prog.prog) + continue; + + new->prog = existing->prog; + new->bpf_cookie = existing->bpf_cookie; + new++; + } } - if (include_prog) - array->items[new_prog_idx++].prog = include_prog; - array->items[new_prog_idx].prog = NULL; + if (include_prog) { + new->prog = include_prog; + new->bpf_cookie = bpf_cookie; + new++; + } + new->prog = NULL; *new_array = array; return 0; } @@ -2042,28 +2737,20 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array, : 0; } -static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) -{ - enum bpf_cgroup_storage_type stype; - - for_each_cgroup_storage_type(stype) { - if (!aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]); - } -} - 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; - bpf_free_cgroup_storage(aux); + 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); } } @@ -2074,23 +2761,59 @@ static void bpf_free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } +void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len) +{ +#ifdef CONFIG_BPF_SYSCALL + struct btf_mod_pair *btf_mod; + u32 i; + + for (i = 0; i < len; i++) { + btf_mod = &used_btfs[i]; + if (btf_mod->module) + module_put(btf_mod->module); + btf_put(btf_mod->btf); + } +#endif +} + +static void bpf_free_used_btfs(struct bpf_prog_aux *aux) +{ + __bpf_free_used_btfs(aux->used_btfs, aux->used_btf_cnt); + kfree(aux->used_btfs); +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; int i; aux = container_of(work, struct bpf_prog_aux, work); +#ifdef CONFIG_BPF_SYSCALL + bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab); +#endif +#ifdef CONFIG_CGROUP_BPF + if (aux->cgroup_atype != CGROUP_BPF_ATTACH_TYPE_INVALID) + bpf_cgroup_atype_put(aux->cgroup_atype); +#endif 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 - bpf_trampoline_put(aux->trampoline); - for (i = 0; i < aux->func_cnt; i++) + if (aux->dst_trampoline) + bpf_trampoline_put(aux->dst_trampoline); + 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. + */ + 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 { @@ -2098,19 +2821,19 @@ static void bpf_prog_free_deferred(struct work_struct *work) } } -/* Free internal BPF program */ void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; - if (aux->linked_prog) - bpf_prog_put(aux->linked_prog); + 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) @@ -2148,6 +2871,7 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; +const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; @@ -2157,6 +2881,8 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_tai_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; @@ -2165,12 +2891,21 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; +const struct bpf_func_proto bpf_snprintf_btf_proto __weak; +const struct bpf_func_proto bpf_seq_printf_btf_proto __weak; +const struct bpf_func_proto bpf_set_retval_proto __weak; +const struct bpf_func_proto bpf_get_retval_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { return NULL; } +const struct bpf_func_proto * __weak bpf_get_trace_vprintk_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) @@ -2205,7 +2940,7 @@ 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; } @@ -2213,12 +2948,77 @@ bool __weak bpf_helper_changes_pkt_data(void *func) /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. + * + * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if + * you don't override this. JITs that don't want these extra insns can detect + * them using insn_is_zext. */ bool __weak bpf_jit_needs_zext(void) { return false; } +/* Return true if the JIT inlines the call to the helper corresponding to + * the imm. + * + * The verifier will not patch the insn->imm for the call to the helper if + * this returns true. + */ +bool __weak bpf_jit_inlines_helper_call(s32 imm) +{ + return false; +} + +/* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */ +bool __weak bpf_jit_supports_subprog_tailcalls(void) +{ + return false; +} + +bool __weak bpf_jit_supports_percpu_insn(void) +{ + return false; +} + +bool __weak bpf_jit_supports_kfunc_call(void) +{ + return false; +} + +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. */ @@ -2234,6 +3034,53 @@ int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, return -ENOTSUPP; } +void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + return ERR_PTR(-ENOTSUPP); +} + +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) +{ +} + +/* 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) +{ + int ret; + + ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false); + bpf_global_ma_set = !ret; + return ret; +} +late_initcall(bpf_global_ma_init); +#endif + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 27595fc6da56..774accbd4a22 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -4,30 +4,36 @@ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ -/* The 'cpumap' is primarily used as a backend map for XDP BPF helper +/** + * DOC: cpu map + * The 'cpumap' is primarily used as a backend map for XDP BPF helper * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. * - * Unlike devmap which redirects XDP frames out another NIC device, + * Unlike devmap which redirects XDP frames out to another NIC device, * this map type redirects raw XDP frames to another CPU. The remote * CPU will do SKB-allocation and call the normal network stack. - * + */ +/* * This is a scalability and isolation mechanism, that allow * separating the early driver network XDP layer, from the rest of the * netstack, and assigning dedicated CPUs for this stage. This * basically allows for 10G wirespeed pre-filtering via bpf. */ +#include <linux/bitops.h> #include <linux/bpf.h> #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_core */ +#include <linux/netdevice.h> /* netif_receive_skb_list */ #include <linux/etherdevice.h> /* eth_type_trans */ /* General idea: XDP packets getting XDP redirected to another CPU, @@ -52,180 +58,215 @@ struct xdp_bulk_queue { struct bpf_cpu_map_entry { u32 cpu; /* kthread CPU and map index */ int map_id; /* Back reference to map */ - u32 qsize; /* Queue size placeholder for map lookup */ /* 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 work_struct kthread_stop_wq; - atomic_t refcnt; /* Control when this struct can be free'ed */ - struct rcu_head rcu; + struct bpf_cpumap_val value; + struct bpf_prog *prog; + + struct completion kthread_running; + struct rcu_work free_work; }; struct bpf_cpu_map { struct bpf_map map; /* Below members specific for map type */ - struct bpf_cpu_map_entry **cpu_map; + struct bpf_cpu_map_entry __rcu **cpu_map; }; -static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); - -static int bq_flush_to_queue(struct xdp_bulk_queue *bq); - static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { + u32 value_size = attr->value_size; struct bpf_cpu_map *cmap; - int err = -ENOMEM; - u64 cost; - int ret; - - if (!bpf_capable()) - return ERR_PTR(-EPERM); /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + (value_size != offsetofend(struct bpf_cpumap_val, qsize) && + value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd)) || + attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); - cmap = kzalloc(sizeof(*cmap), GFP_USER); + /* Pre-limit array size based on NR_CPUS, not final CPU check */ + if (attr->max_entries > NR_CPUS) + return ERR_PTR(-E2BIG); + + cmap = bpf_map_area_alloc(sizeof(*cmap), NUMA_NO_NODE); if (!cmap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&cmap->map, attr); - /* Pre-limit array size based on NR_CPUS, not final CPU check */ - if (cmap->map.max_entries > NR_CPUS) { - err = -E2BIG; - goto free_cmap; - } - - /* make sure page count doesn't overflow */ - cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); - - /* Notice returns -EPERM on if map size is larger than memlock limit */ - ret = bpf_map_charge_init(&cmap->map.memory, cost); - if (ret) { - err = ret; - goto free_cmap; - } - /* Alloc array for possible remote "destination" CPUs */ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *), cmap->map.numa_node); - if (!cmap->cpu_map) - goto free_charge; + if (!cmap->cpu_map) { + bpf_map_area_free(cmap); + return ERR_PTR(-ENOMEM); + } return &cmap->map; -free_charge: - bpf_map_charge_finish(&cmap->map.memory); -free_cmap: - kfree(cmap); - return ERR_PTR(err); } -static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +static void __cpu_map_ring_cleanup(struct ptr_ring *ring) { - atomic_inc(&rcpu->refcnt); + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + void *ptr; + + 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); + } } -/* called from workqueue, to workaround syscall using preempt_disable */ -static void cpu_map_kthread_stop(struct work_struct *work) +static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, + struct list_head *listp, + struct xdp_cpumap_stats *stats) { - struct bpf_cpu_map_entry *rcpu; + struct sk_buff *skb, *tmp; + struct xdp_buff xdp; + u32 act; + int err; + + list_for_each_entry_safe(skb, tmp, listp, list) { + act = bpf_prog_run_generic_xdp(skb, &xdp, rcpu->prog); + switch (act) { + case XDP_PASS: + break; + case XDP_REDIRECT: + skb_list_del_init(skb); + err = xdp_do_generic_redirect(skb->dev, skb, &xdp, + rcpu->prog); + if (unlikely(err)) { + kfree_skb(skb); + stats->drop++; + } else { + stats->redirect++; + } + return; + default: + bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(skb->dev, rcpu->prog, act); + fallthrough; + case XDP_DROP: + skb_list_del_init(skb); + kfree_skb(skb); + stats->drop++; + return; + } + } +} - rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); +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_buff xdp; + int i, nframes = 0; - /* 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(); + xdp_set_return_frame_no_direct(); + xdp.rxq = &rxq; - /* kthread_stop will wake_up_process and wait for it to complete */ - kthread_stop(rcpu->kthread); -} + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + u32 act; + int err; -static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, - struct xdp_frame *xdpf, - struct sk_buff *skb) -{ - unsigned int hard_start_headroom; - unsigned int frame_size; - void *pkt_data_start; + rxq.dev = xdpf->dev_rx; + rxq.mem.type = xdpf->mem_type; + /* TODO: report queue_index to xdp_rxq_info */ - /* Part of headroom was reserved to xdpf */ - hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom; + xdp_convert_frame_to_buff(xdpf, &xdp); - /* Memory size backing xdp_frame data already have reserved - * room for build_skb to place skb_shared_info in tailroom. - */ - frame_size = xdpf->frame_sz; + act = bpf_prog_run_xdp(rcpu->prog, &xdp); + switch (act) { + case XDP_PASS: + err = xdp_update_frame_from_buff(&xdp, xdpf); + if (err < 0) { + xdp_return_frame(xdpf); + stats->drop++; + } else { + frames[nframes++] = xdpf; + stats->pass++; + } + break; + case XDP_REDIRECT: + err = xdp_do_redirect(xdpf->dev_rx, &xdp, + rcpu->prog); + if (unlikely(err)) { + xdp_return_frame(xdpf); + stats->drop++; + } else { + stats->redirect++; + } + break; + default: + bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act); + fallthrough; + case XDP_DROP: + xdp_return_frame(xdpf); + stats->drop++; + break; + } + } - pkt_data_start = xdpf->data - hard_start_headroom; - skb = build_skb_around(skb, pkt_data_start, frame_size); - if (unlikely(!skb)) - return NULL; + xdp_clear_return_frame_no_direct(); - skb_reserve(skb, hard_start_headroom); - __skb_put(skb, xdpf->len); - if (xdpf->metasize) - skb_metadata_set(skb, xdpf->metasize); + return nframes; +} - /* Essential SKB info: protocol and skb->dev */ - skb->protocol = eth_type_trans(skb, xdpf->dev_rx); +#define CPUMAP_BATCH 8 - /* Optional SKB info, currently missing: - * - HW checksum info (skb->ip_summed) - * - HW RX hash (skb_set_hash) - * - RX ring dev queue index (skb_record_rx_queue) - */ +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 bpf_net_context __bpf_net_ctx, *bpf_net_ctx; + int nframes; - /* Until page_pool get SKB return path, release DMA here */ - xdp_release_frame(xdpf); + if (!rcpu->prog) + return xdp_n; - /* Allow SKB to reuse area used by xdp_frame */ - xdp_scrub_frame(xdpf); + rcu_read_lock_bh(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); - return skb; -} + nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats); -static void __cpu_map_ring_cleanup(struct ptr_ring *ring) -{ - /* The tear-down procedure should have made sure that queue is - * empty. See __cpu_map_entry_replace() and work-queue - * invoked cpu_map_kthread_stop(). Catch any broken behaviour - * gracefully and warn once. - */ - struct xdp_frame *xdpf; + if (stats->redirect) + xdp_do_flush(); - while ((xdpf = ptr_ring_consume(ring))) - if (WARN_ON_ONCE(xdpf)) - xdp_return_frame(xdpf); -} + if (unlikely(!list_empty(list))) + cpu_map_bpf_prog_run_skb(rcpu, list, stats); -static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - if (atomic_dec_and_test(&rcpu->refcnt)) { - /* 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); - } -} + bpf_net_ctx_clear(bpf_net_ctx); + rcu_read_unlock_bh(); /* resched point, may call do_softirq() */ -#define CPUMAP_BATCH 8 + return nframes; +} static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + unsigned long last_qs = jiffies; + complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); /* When kthread gives stop order, then rcpu have been disconnected @@ -234,11 +275,13 @@ static int cpu_map_kthread_run(void *data) * kthread_stop signal until queue is empty. */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { - unsigned int drops = 0, sched = 0; + 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; void *frames[CPUMAP_BATCH]; void *skbs[CPUMAP_BATCH]; - gfp_t gfp = __GFP_ZERO | GFP_ATOMIC; - int i, n, m; + LIST_HEAD(list); /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { @@ -247,10 +290,12 @@ 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(); } @@ -259,11 +304,22 @@ static int cpu_map_kthread_run(void *data) * kthread CPU pinned. Lockless access to ptr_ring * consume side valid as no-resize allowed of queue. */ - n = ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH); - - for (i = 0; i < n; i++) { + n = __ptr_ring_consume_batched(rcpu->queue, frames, + CPUMAP_BATCH); + for (i = 0, xdp_n = 0; i < n; i++) { void *f = frames[i]; - struct page *page = virt_to_page(f); + struct page *page; + + if (unlikely(__ptr_test_bit(0, &f))) { + struct sk_buff *skb = f; + + __ptr_clear_bit(0, &skb); + list_add_tail(&skb->list, &list); + continue; + } + + frames[xdp_n++] = f; + page = virt_to_page(f); /* Bring struct page memory area to curr CPU. Read by * build_skb_around via page_is_pfmemalloc(), and when @@ -272,59 +328,87 @@ static int cpu_map_kthread_run(void *data) prefetchw(page); } - m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs); - if (unlikely(m == 0)) { - for (i = 0; i < n; i++) - skbs[i] = NULL; /* effect: xdp_return_frame */ - drops = n; + /* 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(net_hotdata.skbuff_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; + } } local_bh_disable(); - for (i = 0; i < n; i++) { + for (i = 0; i < nframes; i++) { struct xdp_frame *xdpf = frames[i]; struct sk_buff *skb = skbs[i]; - int ret; - skb = cpu_map_build_skb(rcpu, xdpf, skb); + skb = __xdp_build_skb_from_frame(xdpf, skb, + xdpf->dev_rx); if (!skb) { xdp_return_frame(xdpf); continue; } - /* Inject into network stack */ - ret = netif_receive_skb_core(skb); - if (ret == NET_RX_DROP) - drops++; + list_add_tail(&skb->list, &list); } - /* Feedback loop via tracepoint */ - trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched); + /* 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); + + netif_receive_skb_list(&list); local_bh_enable(); /* resched point, may call do_softirq() */ } __set_current_state(TASK_RUNNING); - put_cpu_map_entry(rcpu); return 0; } -static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, - int map_id) +static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, + struct bpf_map *map, int fd) { + struct bpf_prog *prog; + + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (prog->expected_attach_type != BPF_XDP_CPUMAP || + !bpf_prog_map_compatible(map, prog)) { + bpf_prog_put(prog); + return -EINVAL; + } + + rcpu->value.bpf_prog.id = prog->aux->id; + rcpu->prog = prog; + + return 0; +} + +static struct bpf_cpu_map_entry * +__cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, + u32 cpu) +{ + int numa, err, i, fd = value->bpf_prog.fd; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct bpf_cpu_map_entry *rcpu; struct xdp_bulk_queue *bq; - int numa, err, i; /* Have map->numa_node, but choose node of redirect target CPU */ numa = cpu_to_node(cpu); - rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + rcpu = bpf_map_kmalloc_node(map, sizeof(*rcpu), gfp | __GFP_ZERO, numa); if (!rcpu) return NULL; /* Alloc percpu bulkq */ - rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), - sizeof(void *), gfp); + rcpu->bulkq = bpf_map_alloc_percpu(map, sizeof(*rcpu->bulkq), + sizeof(void *), gfp); if (!rcpu->bulkq) goto free_rcu; @@ -334,33 +418,45 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, } /* Alloc queue */ - rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + rcpu->queue = bpf_map_kmalloc_node(map, sizeof(*rcpu->queue), gfp, + numa); if (!rcpu->queue) goto free_bulkq; - err = ptr_ring_init(rcpu->queue, qsize, gfp); + err = ptr_ring_init(rcpu->queue, value->qsize, gfp); if (err) goto free_queue; rcpu->cpu = cpu; - rcpu->map_id = map_id; - rcpu->qsize = qsize; + rcpu->map_id = map->id; + rcpu->value.qsize = value->qsize; + + 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); + "cpumap/%d/map:%d", cpu, + map->id); if (IS_ERR(rcpu->kthread)) - goto free_ptr_ring; - - get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ - get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ + goto free_prog; /* 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: ptr_ring_cleanup(rcpu->queue, NULL); free_queue: @@ -372,55 +468,54 @@ 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); + /* 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) { struct bpf_cpu_map_entry *old_rcpu; - old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + 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_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; @@ -428,21 +523,21 @@ 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 = {}; struct bpf_cpu_map_entry *rcpu; - /* Array index key correspond to CPU number */ u32 key_cpu = *(u32 *)key; - /* Value is the queue size */ - u32 qsize = *(u32 *)value; + + memcpy(&cpumap_value, value, map->value_size); if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -450,21 +545,20 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; - if (unlikely(qsize > 16384)) /* sanity limit on qsize */ + if (unlikely(cpumap_value.qsize > 16384)) /* sanity limit on qsize */ return -EOVERFLOW; /* Make sure CPU is a valid possible cpu */ if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu)) return -ENODEV; - if (qsize == 0) { + if (cpumap_value.qsize == 0) { rcpu = NULL; /* Same as deleting */ } else { /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ - rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); + 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); @@ -480,33 +574,35 @@ 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. */ - - bpf_clear_redirect_map(map); 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; - rcpu = READ_ONCE(cmap->cpu_map[i]); + rcpu = rcu_dereference_raw(cmap->cpu_map[i]); 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); - kfree(cmap); + bpf_map_area_free(cmap); } -struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ +static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); struct bpf_cpu_map_entry *rcpu; @@ -514,7 +610,8 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - rcpu = READ_ONCE(cmap->cpu_map[key]); + rcpu = rcu_dereference_check(cmap->cpu_map[key], + rcu_read_lock_bh_held()); return rcpu; } @@ -523,7 +620,7 @@ static void *cpu_map_lookup_elem(struct bpf_map *map, void *key) struct bpf_cpu_map_entry *rcpu = __cpu_map_lookup_elem(map, *(u32 *)key); - return rcpu ? &rcpu->qsize : NULL; + return rcpu ? &rcpu->value : NULL; } static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -543,7 +640,24 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +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, .map_alloc = cpu_map_alloc, .map_free = cpu_map_free, .map_delete_elem = cpu_map_delete_elem, @@ -551,9 +665,12 @@ 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, }; -static int bq_flush_to_queue(struct xdp_bulk_queue *bq) +static void bq_flush_to_queue(struct xdp_bulk_queue *bq) { struct bpf_cpu_map_entry *rcpu = bq->obj; unsigned int processed = 0, drops = 0; @@ -562,7 +679,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq) int i; if (unlikely(!bq->count)) - return 0; + return; q = rcpu->queue; spin_lock(&q->producer_lock); @@ -585,15 +702,13 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq) /* Feedback loop via tracepoints */ trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu); - return 0; } /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) +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)) @@ -610,21 +725,16 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) */ bq->q[bq->count++] = xdpf; - if (!bq->flush_node.prev) - list_add(&bq->flush_node, flush_list); + if (!bq->flush_node.prev) { + struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list(); - return 0; + list_add(&bq->flush_node, flush_list); + } } -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { - struct xdp_frame *xdpf; - - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - /* Info needed when constructing SKB on remote CPU */ xdpf->dev_rx = dev_rx; @@ -632,9 +742,27 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, return 0; } -void __cpu_map_flush(void) +int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb) +{ + int ret; + + __skb_pull(skb, skb->mac_len); + skb_set_redirected(skb, false); + __ptr_set_bit(0, &skb); + + ret = ptr_ring_produce(rcpu->queue, skb); + if (ret < 0) + goto trace; + + wake_up_process(rcpu->kthread); +trace: + trace_xdp_cpumap_enqueue(rcpu->map_id, !ret, !!ret, rcpu->cpu); + return ret; +} + +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) { @@ -644,14 +772,3 @@ 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..cfa1c18e3a48 --- /dev/null +++ b/kernel/bpf/cpumask.c @@ -0,0 +1,481 @@ +// 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. + */ +__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(). + */ +__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. + */ +__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. + */ +__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. + */ +__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. + */ +__bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask) +{ + return cpumask_weight(cpumask); +} + +__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_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..94854cd9c4cc --- /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) + 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 5fdbc776a760..482d284a1553 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -48,6 +48,7 @@ #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> +#include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) @@ -57,13 +58,13 @@ struct xdp_dev_bulk_queue { struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; + struct bpf_prog *xdp_prog; unsigned int count; }; 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; @@ -72,7 +73,7 @@ struct bpf_dtab_netdev { struct bpf_dtab { struct bpf_map map; - struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */ + struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ @@ -82,7 +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); @@ -92,7 +92,7 @@ static struct hlist_head *dev_map_create_hash(unsigned int entries, int i; struct hlist_head *hash; - hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node); + hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); @@ -106,11 +106,9 @@ 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; - u64 cost = 0; - int err; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex @@ -122,49 +120,43 @@ 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; - cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets; - } else { - cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); - } - - /* if map size is larger than memlock limit, reject it */ - err = bpf_map_charge_init(&dtab->map.memory, cost); - if (err) - 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) - goto free_charge; + return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { - dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * + dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) - goto free_charge; + return -ENOMEM; } return 0; - -free_charge: - bpf_map_charge_finish(&dtab->map.memory); - return -ENOMEM; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) @@ -172,16 +164,13 @@ 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 = kzalloc(sizeof(*dtab), GFP_USER); + dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { - kfree(dtab); + bpf_map_area_free(dtab); return ERR_PTR(err); } @@ -195,7 +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 @@ -211,7 +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. */ @@ -239,7 +235,7 @@ static void dev_map_free(struct bpf_map *map) for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; - dev = dtab->netdev_map[i]; + dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; @@ -252,7 +248,7 @@ static void dev_map_free(struct bpf_map *map) bpf_map_area_free(dtab->netdev_map); } - kfree(dtab); + bpf_map_area_free(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -272,7 +268,11 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ +static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); @@ -331,82 +331,112 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, return -ENOENT; } -bool dev_map_can_have_prog(struct bpf_map *map) +static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, + struct xdp_frame **frames, int n, + struct net_device *tx_dev, + struct net_device *rx_dev) { - if ((map->map_type == BPF_MAP_TYPE_DEVMAP || - map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) && - map->value_size != offsetofend(struct bpf_devmap_val, ifindex)) - return true; - - return false; + struct xdp_txq_info txq = { .dev = tx_dev }; + struct xdp_rxq_info rxq = { .dev = rx_dev }; + struct xdp_buff xdp; + int i, nframes = 0; + + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + u32 act; + int err; + + xdp_convert_frame_to_buff(xdpf, &xdp); + xdp.txq = &txq; + xdp.rxq = &rxq; + + act = bpf_prog_run_xdp(xdp_prog, &xdp); + switch (act) { + case XDP_PASS: + err = xdp_update_frame_from_buff(&xdp, xdpf); + if (unlikely(err < 0)) + xdp_return_frame_rx_napi(xdpf); + else + frames[nframes++] = xdpf; + break; + default: + bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(tx_dev, xdp_prog, act); + fallthrough; + case XDP_DROP: + xdp_return_frame_rx_napi(xdpf); + break; + } + } + return nframes; /* sent frames count */ } -static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) +static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; - int sent = 0, drops = 0, err = 0; + unsigned int cnt = bq->count; + int sent = 0, err = 0; + int to_send = cnt; int i; - if (unlikely(!bq->count)) - return 0; + if (unlikely(!cnt)) + return; - for (i = 0; i < bq->count; i++) { + for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } - sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags); + if (bq->xdp_prog) { + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); + if (!to_send) + goto out; + } + + sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { + /* If ndo_xdp_xmit fails with an errno, no frames have + * been xmit'ed. + */ err = sent; sent = 0; - goto error; } - drops = bq->count - sent; -out: - bq->count = 0; - trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err); - bq->dev_rx = NULL; - __list_del_clearprev(&bq->flush_node); - return 0; -error: - /* If ndo_xdp_xmit fails with an errno, no frames have been - * xmit'ed and it's our responsibility to them free all. + /* If not all frames have been transmitted, it is our + * responsibility to free them */ - for (i = 0; i < bq->count; i++) { - struct xdp_frame *xdpf = bq->q[i]; + for (i = sent; unlikely(i < to_send); i++) + xdp_return_frame_rx_napi(bq->q[i]); - xdp_return_frame_rx_napi(xdpf); - drops++; - } - goto out; -} - -/* __dev_flush is called from xdp_do_flush() which _must_ be signaled - * from the driver before returning from its napi->poll() routine. The poll() - * routine is called either from busy_poll context or net_rx_action signaled - * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the - * net device can be torn down. On devmap tear down we ensure the flush list - * is empty before completing to ensure all flush operations have completed. - * When drivers update the bpf program they may need to ensure any flush ops - * are also complete. Using synchronize_rcu or call_rcu will suffice for this - * because both wait for napi context to exit. +out: + bq->count = 0; + trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); +} + +/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the + * 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) + list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); + bq->dev_rx = NULL; + bq->xdp_prog = NULL; + __list_del_clearprev(&bq->flush_node); + } } -/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or - * update happens in parallel here a dev_put wont happen until after reading the - * ifindex. +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. */ -struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; @@ -414,17 +444,18 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - obj = READ_ONCE(dtab->netdev_map[key]); + obj = rcu_dereference_check(dtab->netdev_map[key], + rcu_read_lock_bh_held()); return obj; } -/* Runs under RCU-read-side, plus in softirq under NAPI protection. - * Thus, safe percpu variable access. +/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu + * variable access, and map elements stick around. See comment above + * xdp_do_flush() in filter.c. */ -static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, - struct net_device *dev_rx) +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)) @@ -433,99 +464,334 @@ static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. + * + * Do the same with xdp_prog and flush_list since these fields + * are only ever modified together. */ - if (!bq->dev_rx) - bq->dev_rx = dev_rx; - - bq->q[bq->count++] = xdpf; + if (!bq->dev_rx) { + struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); - if (!bq->flush_node.prev) + bq->dev_rx = dev_rx; + bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); + } - return 0; + bq->q[bq->count++] = xdpf; } -static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, - struct net_device *dev_rx) +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, + struct net_device *dev_rx, + struct bpf_prog *xdp_prog) { - 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->data_end - xdp->data); + err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); if (unlikely(err)) return err; - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - - return bq_enqueue(dev, xdpf, dev_rx); + bq_enqueue(dev, xdpf, dev_rx, xdp_prog); + return 0; } -static struct xdp_buff *dev_map_run_prog(struct net_device *dev, - struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { - struct xdp_txq_info txq = { .dev = dev }; + struct xdp_txq_info txq = { .dev = dst->dev }; + struct xdp_buff xdp; u32 act; - xdp_set_data_meta_invalid(xdp); - xdp->txq = &txq; + if (!dst->xdp_prog) + return XDP_PASS; + + __skb_pull(skb, skb->mac_len); + xdp.txq = &txq; - act = bpf_prog_run_xdp(xdp_prog, xdp); + act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: - return xdp; - case XDP_DROP: + __skb_push(skb, skb->mac_len); break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(dev, xdp_prog, act); + trace_xdp_exception(dst->dev, dst->xdp_prog, act); + fallthrough; + case XDP_DROP: + kfree_skb(skb); break; } - xdp_return_buff(xdp); - return NULL; + return act; } -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { - return __xdp_enqueue(dev, xdp, dev_rx); + return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; - if (dst->xdp_prog) { - xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog); - if (!xdp) - return 0; + return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); +} + +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) +{ + 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))) + return false; + + return true; +} + +static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, + struct net_device *dev_rx, + struct xdp_frame *xdpf) +{ + struct xdp_frame *nxdpf; + + nxdpf = xdpf_clone(xdpf); + if (!nxdpf) + return -ENOMEM; + + bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); + + return 0; +} + +static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) +{ + while (num_excluded--) { + if (ifindex == excluded[num_excluded]) + return true; } - return __xdp_enqueue(dev, xdp, dev_rx); + return false; +} + +/* Get ifindex of each upper device. 'indexes' must be able to hold at + * least MAX_NEST_DEV elements. + * Returns the number of ifindexes added. + */ +static int get_upper_ifindexes(struct net_device *dev, int *indexes) +{ + struct net_device *upper; + struct list_head *iter; + int n = 0; + + netdev_for_each_upper_dev_rcu(dev, upper, iter) { + indexes[n++] = upper->ifindex; + } + return n; +} + +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, + 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; + int excluded_devices[1+MAX_NEST_DEV]; + struct hlist_head *head; + int num_excluded = 0; + unsigned int i; + int err; + + if (exclude_ingress) { + num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); + excluded_devices[num_excluded++] = dev_rx->ifindex; + } + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); + if (!is_valid_dst(dst, xdpf)) + continue; + + if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + for (i = 0; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + hlist_for_each_entry_rcu(dst, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) { + if (!is_valid_dst(dst, xdpf)) + continue; + + if (is_ifindex_excluded(excluded_devices, num_excluded, + dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } + } + + /* consume the last copy of the frame */ + if (last_dst) + bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); + else + xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ + + return 0; } 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; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; + + /* Redirect has already succeeded semantically at this point, so we just + * return 0 even if packet is dropped. Helper below takes care of + * freeing skb. + */ + if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) + return 0; + skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } +static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, + struct sk_buff *skb, + const struct bpf_prog *xdp_prog) +{ + struct sk_buff *nskb; + int err; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + + err = dev_map_generic_redirect(dst, nskb, xdp_prog); + if (unlikely(err)) { + consume_skb(nskb); + return err; + } + + return 0; +} + +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + 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; + int excluded_devices[1+MAX_NEST_DEV]; + struct hlist_head *head; + struct hlist_node *next; + int num_excluded = 0; + unsigned int i; + int err; + + if (exclude_ingress) { + num_excluded = get_upper_ifindexes(dev, excluded_devices); + excluded_devices[num_excluded++] = dev->ifindex; + } + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); + if (!dst) + continue; + + if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; + + last_dst = dst; + + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + 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 (is_ifindex_excluded(excluded_devices, num_excluded, + dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; + + last_dst = dst; + } + } + } + + /* consume the first skb and return */ + if (last_dst) + return dev_map_generic_redirect(last_dst, skb, xdp_prog); + + /* dtab is empty */ + consume_skb(skb); + return 0; +} + static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); @@ -551,33 +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; - /* Use call_rcu() here to ensure any rcu critical sections have - * completed as well as any flush operations because call_rcu - * will wait for preempt-disable region to complete, NAPI in this - * context. And additionally, the driver tear down ensures all - * soft irqs are complete before removing the net device in the - * case of dev_put equals zero. - */ - old_dev = xchg(&dtab->netdev_map[k], NULL); - if (old_dev) + old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); + 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; @@ -603,8 +864,9 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; - dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, - dtab->map.numa_node); + dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), + GFP_NOWAIT | __GFP_NOWARN, + dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); @@ -617,12 +879,12 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; - if (prog->expected_attach_type != BPF_XDP_DEVMAP) + if (prog->expected_attach_type != BPF_XDP_DEVMAP || + !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } dev->idx = idx; - dev->dtab = dtab; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; @@ -642,8 +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; @@ -675,22 +937,24 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, * Remembering the driver side flush operation will happen before the * net device is removed. */ - old_dev = xchg(&dtab->netdev_map[i], dev); + 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; @@ -742,14 +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 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 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, @@ -757,9 +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, @@ -767,6 +1067,9 @@ 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, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, @@ -808,9 +1111,7 @@ static int dev_map_notification(struct notifier_block *notifier, break; /* will be freed in free_netdev() */ - netdev->xdp_bulkq = - __alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue), - sizeof(void *), GFP_ATOMIC); + netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; @@ -833,13 +1134,15 @@ static int dev_map_notification(struct notifier_block *notifier, for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; - dev = READ_ONCE(dtab->netdev_map[i]); + dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; - odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); - if (dev == odev) + odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); + if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); + atomic_dec((atomic_t *)&dtab->items); + } } } rcu_read_unlock(); @@ -856,15 +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 b44d8c447afd..309c4aa1b026 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ @@ -19,16 +19,23 @@ static const char *__func_get_name(const struct bpf_insn_cbs *cbs, { BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); - if (insn->src_reg != BPF_PSEUDO_CALL && + if (!insn->src_reg && insn->imm >= 0 && insn->imm < __BPF_FUNC_MAX_ID && func_id_str[insn->imm]) return func_id_str[insn->imm]; - if (cbs && cbs->cb_call) - return cbs->cb_call(cbs->private_data, insn); + if (cbs && cbs->cb_call) { + const char *res; + + res = cbs->cb_call(cbs->private_data, insn); + if (res) + return res; + } if (insn->src_reg == BPF_PSEUDO_CALL) snprintf(buff, len, "%+d", insn->imm); + else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) + snprintf(buff, len, "kernel-function"); return buff; } @@ -80,6 +87,24 @@ 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", + [BPF_OR >> 4] = "or", + [BPF_XOR >> 4] = "xor", +}; + static const char *const bpf_ldst_string[] = { [BPF_W >> 3] = "u32", [BPF_H >> 3] = "u16", @@ -87,6 +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] = "==", @@ -114,6 +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) @@ -124,7 +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) { @@ -132,18 +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, %d, %d)\n", + insn->code, insn->dst_reg, + insn->src_reg, ((u32)insn->imm) >> 16, (u16)insn->imm); + } else if (is_mov_percpu_addr(insn)) { + verbose(cbs->private_data, "(%02x) r%d = &(void __percpu *)(r%d)\n", + insn->code, insn->dst_reg, insn->src_reg); } else if (BPF_SRC(insn->code) == BPF_X) { - verbose(cbs->private_data, "(%02x) %c%d %s %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) { @@ -153,32 +232,66 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); - else if (BPF_MODE(insn->code) == BPF_XADD) - verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", + else if (BPF_MODE(insn->code) == BPF_ATOMIC && + (insn->imm == BPF_ADD || insn->imm == BPF_AND || + insn->imm == BPF_OR || insn->imm == BPF_XOR)) { + verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) %s r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, + bpf_alu_string[BPF_OP(insn->imm) >> 4], insn->src_reg); - else + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + (insn->imm == (BPF_ADD | BPF_FETCH) || + insn->imm == (BPF_AND | BPF_FETCH) || + insn->imm == (BPF_OR | BPF_FETCH) || + insn->imm == (BPF_XOR | BPF_FETCH))) { + verbose(cbs->private_data, "(%02x) r%d = atomic%s_fetch_%s((%s *)(r%d %+d), r%d)\n", + insn->code, insn->src_reg, + BPF_SIZE(insn->code) == BPF_DW ? "64" : "", + bpf_atomic_alu_string[BPF_OP(insn->imm) >> 4], + 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_CMPXCHG) { + verbose(cbs->private_data, "(%02x) r0 = atomic%s_cmpxchg((%s *)(r%d %+d), r0, r%d)\n", + insn->code, + 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_XCHG) { + verbose(cbs->private_data, "(%02x) r%d = atomic%s_xchg((%s *)(r%d %+d), r%d)\n", + insn->code, insn->src_reg, + BPF_SIZE(insn->code) == BPF_DW ? "64" : "", + 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); + } } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) == BPF_MEM) { + verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) { + verbose(cbs->private_data, "(%02x) nospec\n", insn->code); + } else { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); - return; } - verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); } 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) { @@ -233,6 +346,13 @@ 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_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) { diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h index e546b18d27da..a4b040793f44 100644 --- a/kernel/bpf/disasm.h +++ b/kernel/bpf/disasm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index 2444bd15cc2d..b77db7413f8c 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -4,6 +4,7 @@ #include <linux/hash.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/static_call.h> /* The BPF dispatcher is a multiway branch code generator. The * dispatcher is a mechanism to avoid the performance penalty of an @@ -85,12 +86,12 @@ static bool bpf_dispatcher_remove_prog(struct bpf_dispatcher *d, return false; } -int __weak arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs) +int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs) { return -ENOTSUPP; } -static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image) +static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf) { s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0]; int i; @@ -99,34 +100,38 @@ static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image) if (d->progs[i].prog) *ipsp++ = (s64)(uintptr_t)d->progs[i].prog->bpf_func; } - return arch_prepare_bpf_dispatcher(image, &ips[0], d->num_progs); + return arch_prepare_bpf_dispatcher(image, buf, &ips[0], d->num_progs); } static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) { - void *old, *new; - u32 noff; - int err; - - if (!prev_num_progs) { - old = NULL; - noff = 0; - } else { - old = d->image + d->image_off; + void *new, *tmp; + u32 noff = 0; + + if (prev_num_progs) noff = d->image_off ^ (PAGE_SIZE / 2); - } new = d->num_progs ? d->image + noff : NULL; + tmp = d->num_progs ? d->rw_image + noff : NULL; if (new) { - if (bpf_dispatcher_prepare(d, new)) + /* Prepare the dispatcher in d->rw_image. Then use + * bpf_arch_text_copy to update d->image, which is RO+X. + */ + if (bpf_dispatcher_prepare(d, new, tmp)) + return; + if (IS_ERR(bpf_arch_text_copy(new, tmp, PAGE_SIZE / 2))) return; } - err = bpf_arch_text_poke(d->func, BPF_MOD_JUMP, old, new); - if (err || !new) - return; + __BPF_DISPATCHER_UPDATE(d, new ?: (void *)&bpf_dispatcher_nop_func); + + /* Make sure all the callers executing the previous/old half of the + * image leave it, so following update call can modify it safely. + */ + synchronize_rcu(); - d->image_off = noff; + if (new) + d->image_off = noff; } void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, @@ -140,10 +145,17 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, mutex_lock(&d->mutex); if (!d->image) { - d->image = bpf_jit_alloc_exec_page(); + d->image = bpf_prog_pack_alloc(PAGE_SIZE, bpf_jit_fill_hole_with_zero); if (!d->image) goto out; - bpf_image_ksym_add(d->image, &d->ksym); + d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!d->rw_image) { + bpf_prog_pack_free(d->image, PAGE_SIZE); + d->image = NULL; + goto out; + } + 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/hashtab.c b/kernel/bpf/hashtab.c index b32cc8ce8ff6..4a9eeb7aef85 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -7,11 +7,15 @@ #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> +#include <linux/btf_ids.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" #include "map_in_map.h" +#include <linux/bpf_mem_alloc.h> #define HTAB_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ @@ -30,7 +34,7 @@ /* * The bucket lock has two protection scopes: * - * 1) Serializing concurrent operations from BPF programs on differrent + * 1) Serializing concurrent operations from BPF programs on different * CPUs * * 2) Serializing concurrent operations from BPF programs and sys_bpf() @@ -45,12 +49,12 @@ * events, kprobes and tracing to be invoked before the prior invocation * from one of these contexts completed. sys_bpf() uses the same mechanism * by pinning the task to the current CPU and incrementing the recursion - * protection accross the map operation. + * protection across the map operation. * * This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain * operations like memory allocations (even with GFP_ATOMIC) from atomic * contexts. This is required because even with GFP_ATOMIC the memory - * allocator calls into code pathes which acquire locks with long held lock + * allocator calls into code paths which acquire locks with long held lock * sections. To ensure the deterministic behaviour these locks are regular * spinlocks, which are converted to 'sleepable' spinlocks on RT. The only * true atomic contexts on an RT kernel are the low level hardware @@ -59,34 +63,31 @@ * * As regular device interrupt handlers and soft interrupts are forced into * thread context, the existing code which does - * spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*(); + * spin_lock*(); alloc(GFP_ATOMIC); spin_unlock*(); * just works. * * In theory the BPF locks could be converted to regular spinlocks as well, * but the bucket locks and percpu_freelist locks can be taken from * arbitrary contexts (perf, kprobes, tracepoints) which are required to be - * atomic contexts even on RT. These mechanisms require preallocated maps, - * so there is no need to invoke memory allocations within the lock held - * sections. - * - * BPF maps which need dynamic allocation are only used from (forced) - * thread context on RT and can therefore use regular spinlocks which in - * turn allows to invoke memory allocations from the lock held section. - * - * On a non RT kernel this distinction is neither possible nor required. - * spinlock maps to raw_spinlock and the extra code is optimized out by the - * compiler. + * atomic contexts even on RT. Before the introduction of bpf_mem_alloc, + * it is only safe to use raw spinlock for preallocated hash map on a RT kernel, + * because there is no memory allocation within the lock held sections. However + * after hash map was fully converted to use bpf_mem_alloc, there will be + * non-synchronous memory allocation for non-preallocated hash map, so it is + * safe to always use raw spinlock for bucket lock. */ struct bucket { struct hlist_nulls_head head; - union { - raw_spinlock_t raw_lock; - spinlock_t lock; - }; + raw_spinlock_t raw_lock; }; +#define HASHTAB_MAP_LOCK_COUNT 8 +#define HASHTAB_MAP_LOCK_MASK (HASHTAB_MAP_LOCK_COUNT - 1) + struct bpf_htab { struct bpf_map map; + struct bpf_mem_alloc ma; + struct bpf_mem_alloc pcpu_ma; struct bucket *buckets; void *elems; union { @@ -94,10 +95,17 @@ struct bpf_htab { struct bpf_lru lru; }; struct htab_elem *__percpu *extra_elems; - atomic_t count; /* number of elements in this hashtable */ + /* number of elements in non-preallocated hashtable are kept + * in either pcount or count + */ + struct percpu_counter pcount; + atomic_t count; + bool use_percpu_counter; 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 */ @@ -107,14 +115,14 @@ struct htab_elem { struct { void *padding; union { - struct bpf_htab *htab; struct pcpu_freelist_node fnode; struct htab_elem *batch_flink; }; }; }; union { - struct rcu_head rcu; + /* pointer to per-cpu pointer */ + void *ptr_to_pptr; struct bpf_lru_node lru_node; }; u32 hash; @@ -126,44 +134,51 @@ static inline bool htab_is_prealloc(const struct bpf_htab *htab) return !(htab->map.map_flags & BPF_F_NO_PREALLOC); } -static inline bool htab_use_raw_lock(const struct bpf_htab *htab) -{ - return (!IS_ENABLED(CONFIG_PREEMPT_RT) || htab_is_prealloc(htab)); -} - static void htab_init_buckets(struct bpf_htab *htab) { - unsigned i; + unsigned int i; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); - if (htab_use_raw_lock(htab)) - raw_spin_lock_init(&htab->buckets[i].raw_lock); - else - spin_lock_init(&htab->buckets[i].lock); + raw_spin_lock_init(&htab->buckets[i].raw_lock); + lockdep_set_class(&htab->buckets[i].raw_lock, + &htab->lockdep_key); + cond_resched(); } } -static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab, - struct bucket *b) +static inline int htab_lock_bucket(const struct bpf_htab *htab, + struct bucket *b, u32 hash, + unsigned long *pflags) { unsigned long flags; - if (htab_use_raw_lock(htab)) - raw_spin_lock_irqsave(&b->raw_lock, flags); - else - spin_lock_irqsave(&b->lock, flags); - return flags; + hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); + + preempt_disable(); + local_irq_save(flags); + if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) { + __this_cpu_dec(*(htab->map_locked[hash])); + local_irq_restore(flags); + preempt_enable(); + return -EBUSY; + } + + raw_spin_lock(&b->raw_lock); + *pflags = flags; + + return 0; } static inline void htab_unlock_bucket(const struct bpf_htab *htab, - struct bucket *b, + struct bucket *b, u32 hash, unsigned long flags) { - if (htab_use_raw_lock(htab)) - raw_spin_unlock_irqrestore(&b->raw_lock, flags); - else - spin_unlock_irqrestore(&b->lock, flags); + hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); + raw_spin_unlock(&b->raw_lock); + __this_cpu_dec(*(htab->map_locked[hash])); + local_irq_restore(flags); + preempt_enable(); } static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); @@ -198,7 +213,63 @@ static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l) static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) { - return (struct htab_elem *) (htab->elems + i * htab->elem_size); + return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size); +} + +static bool htab_has_extra_elems(struct bpf_htab *htab) +{ + return !htab_is_percpu(htab) && !htab_is_lru(htab); +} + +static void htab_free_prealloced_timers_and_wq(struct bpf_htab *htab) +{ + u32 num_entries = htab->map.max_entries; + int i; + + if (htab_has_extra_elems(htab)) + num_entries += num_possible_cpus(); + + for (i = 0; i < num_entries; i++) { + struct htab_elem *elem; + + elem = get_htab_elem(htab, i); + if (btf_record_has_field(htab->map.record, BPF_TIMER)) + bpf_obj_free_timer(htab->map.record, + elem->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(htab->map.record, + elem->key + round_up(htab->map.key_size, 8)); + cond_resched(); + } +} + +static void htab_free_prealloced_fields(struct bpf_htab *htab) +{ + u32 num_entries = htab->map.max_entries; + int i; + + if (IS_ERR_OR_NULL(htab->map.record)) + return; + if (htab_has_extra_elems(htab)) + num_entries += num_possible_cpus(); + for (i = 0; i < num_entries; i++) { + struct htab_elem *elem; + + elem = get_htab_elem(htab, i); + 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, elem->key + round_up(htab->map.key_size, 8)); + cond_resched(); + } + cond_resched(); + } } static void htab_free_elems(struct bpf_htab *htab) @@ -238,6 +309,7 @@ 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; @@ -251,10 +323,10 @@ static int prealloc_init(struct bpf_htab *htab) u32 num_entries = htab->map.max_entries; int err = -ENOMEM, i; - if (!htab_is_percpu(htab) && !htab_is_lru(htab)) + if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); - htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries, + htab->elems = bpf_map_area_alloc((u64)htab->elem_size * num_entries, htab->map.numa_node); if (!htab->elems) return -ENOMEM; @@ -266,7 +338,8 @@ static int prealloc_init(struct bpf_htab *htab) u32 size = round_up(htab->map.value_size, 8); void __percpu *pptr; - pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, size, 8, + GFP_USER | __GFP_NOWARN); if (!pptr) goto free_elems; htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, @@ -320,8 +393,8 @@ static int alloc_extra_elems(struct bpf_htab *htab) struct pcpu_freelist_node *l; int cpu; - pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8, - GFP_USER | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, sizeof(struct htab_elem *), 8, + GFP_USER | __GFP_NOWARN); if (!pptr) return -ENOMEM; @@ -354,17 +427,9 @@ static int htab_map_alloc_check(union bpf_attr *attr) bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED); int numa_node = bpf_map_attr_numa_node(attr); - BUILD_BUG_ON(offsetof(struct htab_elem, htab) != - offsetof(struct htab_elem, hash_node.pprev)); 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; @@ -389,20 +454,17 @@ static int htab_map_alloc_check(union bpf_attr *attr) attr->value_size == 0) return -EINVAL; - if (attr->key_size > MAX_BPF_STACK) - /* eBPF programs initialize keys on stack, so they cannot be - * larger than max stack size - */ - return -E2BIG; - - if (attr->value_size >= KMALLOC_MAX_SIZE - - MAX_BPF_STACK - sizeof(struct htab_elem)) - /* if value_size is bigger, the user space won't be able to - * access the elements via bpf syscall. This check also makes - * sure that the elem_size doesn't overflow and it's + if ((u64)attr->key_size + attr->value_size >= KMALLOC_MAX_SIZE - + sizeof(struct htab_elem)) + /* if key_size + value_size is bigger, the user space won't be + * able to access the elements via bpf syscall. This check + * also makes sure that the elem_size doesn't overflow and it's * 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; } @@ -421,13 +483,14 @@ 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; - u64 cost; - int err; + int err, i; - htab = kzalloc(sizeof(*htab), GFP_USER); + 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) { @@ -442,7 +505,13 @@ 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) + @@ -452,23 +521,11 @@ 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; - cost = (u64) htab->n_buckets * sizeof(struct bucket) + - (u64) htab->elem_size * htab->map.max_entries; - - if (percpu) - cost += (u64) round_up(htab->map.value_size, 8) * - num_possible_cpus() * htab->map.max_entries; - else - cost += (u64) htab->elem_size * num_possible_cpus(); - - /* if map size is larger than memlock limit, reject it */ - err = bpf_map_charge_init(&htab->map.memory, cost); + err = bpf_map_init_elem_count(&htab->map); if (err) goto free_htab; @@ -477,19 +534,51 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) sizeof(struct bucket), htab->map.numa_node); if (!htab->buckets) - goto free_charge; + goto free_elem_count; + + 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; + } if (htab->map.map_flags & BPF_F_ZERO_SEED) htab->hashrnd = 0; else - htab->hashrnd = get_random_int(); + htab->hashrnd = get_random_u32(); htab_init_buckets(htab); +/* compute_batch_value() computes batch value as num_online_cpus() * 2 + * and __percpu_counter_compare() needs + * htab->max_entries - cur_number_of_elems to be more than batch * num_online_cpus() + * for percpu_counter to be faster than atomic_t. In practice the average bpf + * hash map size is 10k, which means that a system with 64 cpus will fill + * hashmap to 20% of 10k before percpu_counter becomes ineffective. Therefore + * define our own batch count as 32 then 10k hash map can be filled up to 80%: + * 10k - 8k > 32 _batch_ * 64 _cpus_ + * and __percpu_counter_compare() will still be fast. At that point hash map + * collisions will dominate its performance anyway. Assume that hash map filled + * to 50+% isn't going to be O(1) and use the following formula to choose + * between percpu_counter and atomic_t. + */ +#define PERCPU_COUNTER_BATCH 32 + if (attr->max_entries / 2 > num_online_cpus() * PERCPU_COUNTER_BATCH) + htab->use_percpu_counter = true; + + if (htab->use_percpu_counter) { + err = percpu_counter_init(&htab->pcount, 0, GFP_KERNEL); + if (err) + goto free_map_locked; + } + if (prealloc) { err = prealloc_init(htab); if (err) - goto free_buckets; + goto free_map_locked; if (!percpu && !lru) { /* lru itself can remove the least used element, so @@ -499,23 +588,42 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (err) goto free_prealloc; } + } else { + err = bpf_mem_alloc_init(&htab->ma, htab->elem_size, false); + if (err) + goto free_map_locked; + if (percpu) { + err = bpf_mem_alloc_init(&htab->pcpu_ma, + round_up(htab->map.value_size, 8), true); + if (err) + goto free_map_locked; + } } return &htab->map; free_prealloc: prealloc_destroy(htab); -free_buckets: +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); -free_charge: - bpf_map_charge_finish(&htab->map.memory); + 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: - kfree(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); } @@ -577,8 +685,8 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) struct htab_elem *l; u32 hash, key_size; - /* Must be called with rcu_read_lock. */ - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -612,14 +720,14 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key) * bpf_prog * __htab_map_lookup_elem */ -static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -651,7 +759,7 @@ static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key) return __htab_lru_map_lookup_elem(map, key, false); } -static u32 htab_lru_map_gen_lookup(struct bpf_map *map, +static int htab_lru_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; @@ -660,7 +768,7 @@ static u32 htab_lru_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + @@ -676,32 +784,54 @@ static u32 htab_lru_map_gen_lookup(struct bpf_map *map, return insn - insn_buf; } +static void check_and_free_fields(struct bpf_htab *htab, + struct htab_elem *elem) +{ + 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 = elem->key + round_up(htab->map.key_size, 8); + + bpf_obj_free_fields(htab->map.record, map_value); + } +} + /* It is called from the bpf_lru_list when the LRU needs to delete * older elements from the htab. */ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) { - struct bpf_htab *htab = (struct bpf_htab *)arg; + struct bpf_htab *htab = arg; struct htab_elem *l = NULL, *tgt_l; struct hlist_nulls_head *head; struct hlist_nulls_node *n; unsigned long flags; struct bucket *b; + int ret; tgt_l = container_of(node, struct htab_elem, lru_node); b = __select_bucket(htab, tgt_l->hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, tgt_l->hash, &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); + bpf_map_dec_elem_count(&htab->map); break; } - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, tgt_l->hash, flags); + if (l == tgt_l) + check_and_free_fields(htab, l); return l == tgt_l; } @@ -766,17 +896,11 @@ find_first_elem: static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { - if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) - free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); - kfree(l); -} - -static void htab_elem_free_rcu(struct rcu_head *head) -{ - struct htab_elem *l = container_of(head, struct htab_elem, rcu); - struct bpf_htab *htab = l->htab; + check_and_free_fields(htab, l); - htab_elem_free(htab, l); + if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) + bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr); + bpf_mem_cache_free(&htab->ma, l); } static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) @@ -786,20 +910,50 @@ 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); } } +static bool is_map_full(struct bpf_htab *htab) +{ + if (htab->use_percpu_counter) + return __percpu_counter_compare(&htab->pcount, htab->map.max_entries, + PERCPU_COUNTER_BATCH) >= 0; + return atomic_read(&htab->count) >= htab->map.max_entries; +} + +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 + atomic_inc(&htab->count); +} + +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 + atomic_dec(&htab->count); +} + + static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { - __pcpu_freelist_push(&htab->freelist, &l->fnode); + bpf_map_dec_elem_count(&htab->map); + check_and_free_fields(htab, l); + pcpu_freelist_push(&htab->freelist, &l->fnode); } else { - atomic_dec(&htab->count); - l->htab = htab; - call_rcu(&l->rcu, htab_elem_free_rcu); + dec_elem_count(htab); + htab_elem_free(htab, l); } } @@ -808,19 +962,41 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, { if (!onallcpus) { /* copy true value_size bytes */ - memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + copy_map_value(&htab->map, this_cpu_ptr(pptr), value); } 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); + copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value + off); off += size; } } } +static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, + void *value, bool onallcpus) +{ + /* When not setting the initial value on all cpus, zero-fill element + * values for other cpus. Otherwise, bpf program has no way to ensure + * known initial values for cpus other than current one + * (onallcpus=false always when coming from bpf prog). + */ + if (!onallcpus) { + int current_cpu = raw_smp_processor_id(); + int cpu; + + for_each_possible_cpu(cpu) { + if (cpu == current_cpu) + 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); + } +} + static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && @@ -844,7 +1020,6 @@ 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; @@ -853,45 +1028,43 @@ 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 (atomic_inc_return(&htab->count) > htab->map.max_entries) - if (!old_elem) { + if (is_map_full(htab)) + if (!old_elem) /* when map is full and update() is replacing * old element, it's ok to allocate, since * old element will be freed immediately. * Otherwise return an error */ - l_new = ERR_PTR(-E2BIG); - goto dec_count; - } - l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, - htab->map.numa_node); + return ERR_PTR(-E2BIG); + inc_elem_count(htab); + l_new = bpf_mem_cache_alloc(&htab->ma); if (!l_new) { l_new = ERR_PTR(-ENOMEM); goto dec_count; } - check_and_init_map_lock(&htab->map, - l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); if (percpu) { - size = round_up(size, 8); if (prealloc) { pptr = htab_elem_get_ptr(l_new, key_size); } else { /* alloc_percpu zero-fills */ - pptr = __alloc_percpu_gfp(size, 8, - GFP_ATOMIC | __GFP_NOWARN); - if (!pptr) { - kfree(l_new); + 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 = ptr; + pptr = *(void __percpu **)ptr; } - pcpu_copy_value(htab, pptr, value, onallcpus); + pcpu_init_value(htab, pptr, value, onallcpus); if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); @@ -907,7 +1080,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new->hash = hash; return l_new; dec_count: - atomic_dec(&htab->count); + dec_elem_count(htab); return l_new; } @@ -926,13 +1099,14 @@ 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 hlist_nulls_head *head; unsigned long flags; + void *old_map_ptr; struct bucket *b; u32 key_size, hash; int ret; @@ -941,7 +1115,8 @@ 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()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -951,7 +1126,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, head = &b->head; if (unlikely(map_flags & BPF_F_LOCK)) { - if (unlikely(!map_value_has_spin_lock(map))) + if (unlikely(!btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; /* find an element without taking the bucket lock */ l_old = lookup_nulls_elem_raw(head, hash, key, key_size, @@ -972,7 +1147,9 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, */ } - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1008,17 +1185,41 @@ 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); + + /* l_old has already been stashed in htab->extra_elems, free + * its special fields before it is available for reuse. Also + * save the old map pointer in htab of maps before unlock + * and release it after unlock. + */ + old_map_ptr = NULL; + if (htab_is_prealloc(htab)) { + if (map->ops->map_fd_put_ptr) + old_map_ptr = fd_htab_map_get_ptr(map, l_old); + check_and_free_fields(htab, l_old); + } + } + htab_unlock_bucket(htab, b, hash, flags); + if (l_old) { + if (old_map_ptr) + map->ops->map_fd_put_ptr(map, old_map_ptr, true); if (!htab_is_prealloc(htab)) free_htab_elem(htab, l_old); } - ret = 0; + return 0; err: - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); return ret; } -static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +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 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; @@ -1032,7 +1233,8 @@ 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()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1049,9 +1251,12 @@ 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; - memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); + copy_map_value(&htab->map, + l_new->key + round_up(map->key_size, 8), value); - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1070,19 +1275,20 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, ret = 0; err: - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); +err_lock_bucket: if (ret) - bpf_lru_push_free(&htab->lru, &l_new->lru_node); + htab_lru_push_free(htab, l_new); else if (l_old) - bpf_lru_push_free(&htab->lru, &l_old->lru_node); + htab_lru_push_free(htab, l_old); 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_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; @@ -1096,7 +1302,8 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1105,7 +1312,9 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, b = __select_bucket(htab, hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1128,13 +1337,13 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); 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; @@ -1148,7 +1357,8 @@ 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()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1168,7 +1378,9 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, return -ENOMEM; } - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1183,34 +1395,37 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), value, onallcpus); } else { - pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), + pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; } ret = 0; err: - htab_unlock_bucket(htab, b, flags); - if (l_new) + htab_unlock_bucket(htab, b, hash, 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); } -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; @@ -1218,9 +1433,10 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) struct htab_elem *l; unsigned long flags; u32 hash, key_size; - int ret = -ENOENT; + int ret; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1228,21 +1444,24 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &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); - ret = 0; - } + else + ret = -ENOENT; + + htab_unlock_bucket(htab, b, hash, flags); - htab_unlock_bucket(htab, 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; @@ -1250,9 +1469,10 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) struct htab_elem *l; unsigned long flags; u32 hash, key_size; - int ret = -ENOENT; + int ret; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1260,18 +1480,20 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &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); - ret = 0; - } + else + ret = -ENOENT; - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); if (l) - bpf_lru_push_free(&htab->lru, &l->lru_node); + htab_lru_push_free(htab, l); return ret; } @@ -1279,6 +1501,9 @@ static void delete_all_elements(struct bpf_htab *htab) { int i; + /* It's called from a worker thread and migration has been disabled, + * therefore, it is OK to invoke bpf_mem_cache_free() directly. + */ for (i = 0; i < htab->n_buckets; i++) { struct hlist_nulls_head *head = select_bucket(htab, i); struct hlist_nulls_node *n; @@ -1288,6 +1513,44 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_nulls_del_rcu(&l->hash_node); htab_elem_free(htab, l); } + cond_resched(); + } +} + +static void htab_free_malloced_timers_and_wq(struct bpf_htab *htab) +{ + int i; + + rcu_read_lock(); + for (i = 0; i < htab->n_buckets; i++) { + struct hlist_nulls_head *head = select_bucket(htab, i); + struct hlist_nulls_node *n; + struct htab_elem *l; + + hlist_nulls_for_each_entry(l, n, head, hash_node) { + /* We only free timer on uref dropping to zero */ + if (btf_record_has_field(htab->map.record, BPF_TIMER)) + bpf_obj_free_timer(htab->map.record, + l->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(htab->map.record, + l->key + round_up(htab->map.key_size, 8)); + } + cond_resched_rcu(); + } + rcu_read_unlock(); +} + +static void htab_map_free_timers_and_wq(struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + /* We only free timer and workqueue on uref dropping to zero */ + if (btf_record_has_field(htab->map.record, BPF_TIMER | BPF_WORKQUEUE)) { + if (!htab_is_prealloc(htab)) + htab_free_malloced_timers_and_wq(htab); + else + htab_free_prealloced_timers_and_wq(htab); } } @@ -1295,26 +1558,35 @@ static void delete_all_elements(struct bpf_htab *htab) static void htab_map_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + int 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 - * disconnected from events. Wait for outstanding critical sections in - * these programs to complete + /* 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. + * There is no need to synchronize_rcu() here to protect map elements. */ - synchronize_rcu(); - /* some of free_htab_elem() callbacks for elements of this map may - * not have executed. Wait for them. + /* htab no longer uses call_rcu() directly. bpf_mem_alloc does it + * underneath and is responsible for waiting for callbacks to finish + * during bpf_mem_alloc_destroy(). */ - rcu_barrier(); - if (!htab_is_prealloc(htab)) + if (!htab_is_prealloc(htab)) { delete_all_elements(htab); - else + } else { + htab_free_prealloced_fields(htab); prealloc_destroy(htab); + } + bpf_map_free_elem_count(map); free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); - kfree(htab); + 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); } static void htab_map_seq_show_elem(struct bpf_map *map, void *key, @@ -1333,11 +1605,108 @@ 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(); } +static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, bool is_lru_map, + bool is_percpu, u64 flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_nulls_head *head; + unsigned long bflags; + struct htab_elem *l; + u32 hash, key_size; + struct bucket *b; + int ret; + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size, htab->hashrnd); + b = __select_bucket(htab, hash); + head = &b->head; + + ret = htab_lock_bucket(htab, b, hash, &bflags); + if (ret) + return ret; + + l = lookup_elem_raw(head, hash, key, key_size); + if (!l) { + ret = -ENOENT; + goto out_unlock; + } + + if (is_percpu) { + u32 roundup_value_size = round_up(map->value_size, 8); + void __percpu *pptr; + int off = 0, cpu; + + 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 { + u32 roundup_key_size = round_up(map->key_size, 8); + + 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); + /* Zeroing special fields in the temp buffer */ + check_and_init_map_value(map, value); + } + hlist_nulls_del_rcu(&l->hash_node); + +out_unlock: + htab_unlock_bucket(htab, b, hash, bflags); + + if (l) { + if (is_lru_map) + htab_lru_push_free(htab, l); + else + free_htab_elem(htab, l); + } + + return ret; +} + +static int htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, false, false, + flags); +} + +static int htab_percpu_map_lookup_and_delete_elem(struct bpf_map *map, + void *key, void *value, + u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, false, true, + flags); +} + +static int htab_lru_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, true, false, + flags); +} + +static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map, + void *key, void *value, + u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, true, true, + flags); +} + static int __htab_map_lookup_and_delete_batch(struct bpf_map *map, const union bpf_attr *attr, @@ -1350,8 +1719,8 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, 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 *ubatch = u64_to_user_ptr(attr->batch.in_batch); - u32 batch, max_count, size, bucket_size; + void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); + u32 batch, max_count, size, bucket_size, map_id; struct htab_elem *node_to_free = NULL; u64 elem_map_flags, map_flags; struct hlist_nulls_head *head; @@ -1364,7 +1733,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, elem_map_flags = attr->batch.elem_flags; if ((elem_map_flags & ~BPF_F_LOCK) || - ((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + ((elem_map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; map_flags = attr->batch.flags; @@ -1393,7 +1762,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, value_size = size * num_possible_cpus(); total = 0; /* while experimenting with hash tables with sizes ranging from 10 to - * 1000, it was observed that a bucket can have upto 5 entries. + * 1000, it was observed that a bucket can have up to 5 entries. */ bucket_size = 5; @@ -1401,8 +1770,8 @@ alloc: /* We cannot do copy_from_user or copy_to_user inside * the rcu_read_lock. Allocate enough space here. */ - keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN); - values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN); + keys = kvmalloc_array(key_size, bucket_size, GFP_USER | __GFP_NOWARN); + values = kvmalloc_array(value_size, bucket_size, GFP_USER | __GFP_NOWARN); if (!keys || !values) { ret = -ENOMEM; goto after_loop; @@ -1417,8 +1786,14 @@ again_nocopy: b = &htab->buckets[batch]; head = &b->head; /* do not grab the lock unless need it (bucket_cnt > 0). */ - if (locked) - flags = htab_lock_bucket(htab, b); + if (locked) { + ret = htab_lock_bucket(htab, b, batch, &flags); + if (ret) { + rcu_read_unlock(); + bpf_enable_instrumentation(); + goto after_loop; + } + } bucket_cnt = 0; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) @@ -1435,7 +1810,7 @@ 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, flags); + htab_unlock_bucket(htab, b, batch, flags); rcu_read_unlock(); bpf_enable_instrumentation(); goto after_loop; @@ -1446,7 +1821,7 @@ 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, flags); + htab_unlock_bucket(htab, b, batch, flags); rcu_read_unlock(); bpf_enable_instrumentation(); kvfree(keys); @@ -1467,18 +1842,27 @@ 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) { + struct bpf_map **inner_map = value; + + /* Actual value is the id of the inner map */ + map_id = map->ops->map_fd_sys_lookup_elem(*inner_map); + value = &map_id; + } + if (elem_map_flags & BPF_F_LOCK) copy_map_value_locked(map, dst_val, value, true); else copy_map_value(map, dst_val, value); - check_and_init_map_lock(map, dst_val); + /* Zeroing special fields in the temp buffer */ + check_and_init_map_value(map, dst_val); } if (do_delete) { hlist_nulls_del_rcu(&l->hash_node); @@ -1487,25 +1871,29 @@ 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, flags); + htab_unlock_bucket(htab, b, batch, flags); locked = false; while (node_to_free) { l = node_to_free; node_to_free = node_to_free->batch_flink; - bpf_lru_push_free(&htab->lru, &l->lru_node); + if (is_lru_map) + htab_lru_push_free(htab, l); + else + free_htab_elem(htab, l); } next_batch: @@ -1620,31 +2008,326 @@ htab_lru_map_lookup_and_delete_batch(struct bpf_map *map, true, false); } +struct bpf_iter_seq_hash_map_info { + struct bpf_map *map; + struct bpf_htab *htab; + void *percpu_value_buf; // non-zero means percpu hash + u32 bucket_id; + u32 skip_elems; +}; + +static struct htab_elem * +bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, + struct htab_elem *prev_elem) +{ + const struct bpf_htab *htab = info->htab; + u32 skip_elems = info->skip_elems; + u32 bucket_id = info->bucket_id; + struct hlist_nulls_head *head; + struct hlist_nulls_node *n; + struct htab_elem *elem; + struct bucket *b; + u32 i, count; + + if (bucket_id >= htab->n_buckets) + return NULL; + + /* try to find next elem in the same bucket */ + if (prev_elem) { + /* no update/deletion on this bucket, prev_elem should be still valid + * and we won't skip elements. + */ + n = rcu_dereference_raw(hlist_nulls_next_rcu(&prev_elem->hash_node)); + elem = hlist_nulls_entry_safe(n, struct htab_elem, hash_node); + if (elem) + return elem; + + /* not found, unlock and go to the next bucket */ + b = &htab->buckets[bucket_id++]; + rcu_read_unlock(); + skip_elems = 0; + } + + for (i = bucket_id; i < htab->n_buckets; i++) { + b = &htab->buckets[i]; + rcu_read_lock(); + + count = 0; + head = &b->head; + hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) { + if (count >= skip_elems) { + info->bucket_id = i; + info->skip_elems = count; + return elem; + } + count++; + } + + rcu_read_unlock(); + skip_elems = 0; + } + + info->bucket_id = i; + info->skip_elems = 0; + return NULL; +} + +static void *bpf_hash_map_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_hash_map_info *info = seq->private; + struct htab_elem *elem; + + elem = bpf_hash_map_seq_find_next(info, NULL); + if (!elem) + return NULL; + + if (*pos == 0) + ++*pos; + return elem; +} + +static void *bpf_hash_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_hash_map_info *info = seq->private; + + ++*pos; + ++info->skip_elems; + return bpf_hash_map_seq_find_next(info, v); +} + +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; + struct bpf_prog *prog; + void __percpu *pptr; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, elem == NULL); + if (prog) { + 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; + } else { + roundup_value_size = round_up(map->value_size, 8); + pptr = htab_elem_get_ptr(elem, map->key_size); + for_each_possible_cpu(cpu) { + 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; + } + } + ret = bpf_iter_run_prog(prog, &ctx); + } + + return ret; +} + +static int bpf_hash_map_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_hash_map_seq_show(seq, v); +} + +static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__bpf_hash_map_seq_show(seq, NULL); + else + rcu_read_unlock(); +} + +static int bpf_iter_init_hash_map(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct bpf_iter_seq_hash_map_info *seq_info = priv_data; + struct bpf_map *map = aux->map; + void *value_buf; + u32 buf_size; + + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + buf_size = round_up(map->value_size, 8) * num_possible_cpus(); + value_buf = kmalloc(buf_size, GFP_USER | __GFP_NOWARN); + if (!value_buf) + return -ENOMEM; + + seq_info->percpu_value_buf = value_buf; + } + + bpf_map_inc_with_uref(map); + seq_info->map = map; + seq_info->htab = container_of(map, struct bpf_htab, map); + return 0; +} + +static void bpf_iter_fini_hash_map(void *priv_data) +{ + struct bpf_iter_seq_hash_map_info *seq_info = priv_data; + + bpf_map_put_with_uref(seq_info->map); + kfree(seq_info->percpu_value_buf); +} + +static const struct seq_operations bpf_hash_map_seq_ops = { + .start = bpf_hash_map_seq_start, + .next = bpf_hash_map_seq_next, + .stop = bpf_hash_map_seq_stop, + .show = bpf_hash_map_seq_show, +}; + +static const struct bpf_iter_seq_info iter_seq_info = { + .seq_ops = &bpf_hash_map_seq_ops, + .init_seq_private = bpf_iter_init_hash_map, + .fini_seq_private = bpf_iter_fini_hash_map, + .seq_priv_size = sizeof(struct bpf_iter_seq_hash_map_info), +}; + +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; + void *key, *val; + 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); + /* 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(). + */ + 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) { + 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; + } + num_elems++; + ret = callback_fn((u64)(long)map, (u64)(long)key, + (u64)(long)val, (u64)(long)callback_ctx, 0); + /* return value: 0 - continue, 1 - stop and return */ + if (ret) { + rcu_read_unlock(); + goto out; + } + } + rcu_read_unlock(); + } +out: + 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, .map_alloc_check = htab_map_alloc_check, .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_and_wq, .map_lookup_elem = htab_map_lookup_elem, + .map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem, .map_update_elem = htab_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, .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, }; const struct bpf_map_ops htab_lru_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, .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_and_wq, .map_lookup_elem = htab_lru_map_lookup_elem, + .map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem, .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, .map_update_elem = htab_lru_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_gen_lookup = htab_lru_map_gen_lookup, .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, }; /* Called from eBPF program */ @@ -1658,6 +2341,40 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +/* inline bpf_map_lookup_elem() call for per-CPU hashmap */ +static int htab_percpu_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + + if (!bpf_jit_supports_percpu_insn()) + return -EOPNOTSUPP; + + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, + offsetof(struct htab_elem, key) + map->key_size); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); + *insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); + + return insn - insn_buf; +} + +static void *htab_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct htab_elem *l; + + if (cpu >= nr_cpu_ids) + return NULL; + + l = __htab_map_lookup_elem(map, key); + if (l) + return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu); + else + return NULL; +} + static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); @@ -1670,6 +2387,22 @@ static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static void *htab_lru_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct htab_elem *l; + + if (cpu >= nr_cpu_ids) + return NULL; + + l = __htab_map_lookup_elem(map, key); + if (l) { + bpf_lru_node_set_ref(&l->lru_node); + return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu); + } + + return NULL; +} + int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) { struct htab_elem *l; @@ -1692,8 +2425,8 @@ 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; @@ -1742,7 +2475,7 @@ 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"); @@ -1750,27 +2483,44 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, } const struct bpf_map_ops htab_percpu_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .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, + .map_lookup_percpu_elem = htab_percpu_map_lookup_percpu_elem, .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, }; const struct bpf_map_ops htab_lru_percpu_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_percpu_map_lookup_elem, + .map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_lookup_percpu_elem = htab_lru_percpu_map_lookup_percpu_elem, .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, }; static int fd_htab_map_alloc_check(union bpf_attr *attr) @@ -1794,7 +2544,7 @@ 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); } } @@ -1833,9 +2583,15 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, if (IS_ERR(ptr)) return PTR_ERR(ptr); + /* The htab bucket lock is always held during update operations in fd + * htab map, and the following rcu_read_lock() is only used to avoid + * the WARN_ON_ONCE in htab_map_update_elem(). + */ + rcu_read_lock(); ret = htab_map_update_elem(map, key, &ptr, map_flags); + rcu_read_unlock(); if (ret) - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); return ret; } @@ -1869,7 +2625,7 @@ static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } -static u32 htab_of_map_gen_lookup(struct bpf_map *map, +static int htab_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; @@ -1877,7 +2633,7 @@ static u32 htab_of_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -1905,4 +2661,7 @@ 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 be43ab3e619f..f27ce162427a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2,6 +2,9 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/bpf-cgroup.h> +#include <linux/cgroup.h> #include <linux/rcupdate.h> #include <linux/random.h> #include <linux/smp.h> @@ -13,7 +16,13 @@ #include <linux/ctype.h> #include <linux/jiffies.h> #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 "../../lib/kstrtox.h" @@ -23,12 +32,13 @@ * * 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()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return (unsigned long) map->ops->map_lookup_elem(map, key); } @@ -44,7 +54,8 @@ 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()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return map->ops->map_update_elem(map, key, value, flags); } @@ -61,7 +72,8 @@ 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()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return map->ops->map_delete_elem(map, key); } @@ -99,7 +111,7 @@ 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_UNINIT_MAP_VALUE, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) @@ -108,11 +120,27 @@ BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) } const struct bpf_func_proto bpf_map_peek_elem_proto = { - .func = bpf_map_pop_elem, + .func = bpf_map_peek_elem, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, + .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()); + return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu); +} + +const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto = { + .func = bpf_map_lookup_percpu_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, + .arg3_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_get_prandom_u32_proto = { @@ -130,6 +158,7 @@ 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) @@ -167,6 +196,29 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_ktime_get_coarse_ns) +{ + return ktime_get_coarse_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = { + .func = bpf_ktime_get_coarse_ns, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +BPF_CALL_0(bpf_ktime_get_tai_ns) +{ + /* NMI safe access to clock tai */ + return ktime_get_tai_fast_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_tai_ns_proto = { + .func = bpf_ktime_get_tai_ns, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; @@ -210,13 +262,8 @@ BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size) if (unlikely(!task)) goto err_clear; - strncpy(buf, task->comm, size); - - /* Verifier guarantees that size > 0. For task->comm exceeding - * size, guarantee that buf is %NUL-terminated. Unconditionally - * done here to save the size test. - */ - buf[size - 1] = 0; + /* Verifier guarantees that size > 0 */ + strscpy_pad(buf, task->comm, size); return 0; err_clear: memset(buf, 0, size); @@ -244,6 +291,7 @@ 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); } @@ -252,6 +300,7 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) arch_spinlock_t *l = (void *)lock; arch_spin_unlock(l); + preempt_enable(); } #else @@ -277,13 +326,18 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) static DEFINE_PER_CPU(unsigned long, irqsave_flags); -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) { unsigned long flags; local_irq_save(flags); __bpf_spin_lock(lock); __this_cpu_write(irqsave_flags, flags); +} + +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +{ + __bpf_spin_lock_irqsave(lock); return 0; } @@ -292,15 +346,21 @@ const struct bpf_func_proto bpf_spin_lock_proto = { .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_SPIN_LOCK, + .arg1_btf_id = BPF_PTR_POISON, }; -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) { unsigned long flags; flags = __this_cpu_read(irqsave_flags); __bpf_spin_unlock(lock); local_irq_restore(flags); +} + +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +{ + __bpf_spin_unlock_irqrestore(lock); return 0; } @@ -309,6 +369,7 @@ const struct bpf_func_proto bpf_spin_unlock_proto = { .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_SPIN_LOCK, + .arg1_btf_id = BPF_PTR_POISON, }; void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, @@ -317,13 +378,13 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, struct bpf_spin_lock *lock; if (lock_src) - lock = src + map->spin_lock_off; + lock = src + map->record->spin_lock_off; else - lock = dst + map->spin_lock_off; + lock = dst + map->record->spin_lock_off; preempt_disable(); - ____bpf_spin_lock(lock); + __bpf_spin_lock_irqsave(lock); copy_map_value(map, dst, src); - ____bpf_spin_unlock(lock); + __bpf_spin_unlock_irqrestore(lock); preempt_enable(); } @@ -341,9 +402,15 @@ const struct bpf_func_proto bpf_jiffies64_proto = { #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { - struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *cgrp; + u64 cgrp_id; + + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + cgrp_id = cgroup_id(cgrp); + rcu_read_unlock(); - return cgroup_id(cgrp); + return cgrp_id; } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { @@ -354,13 +421,17 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level) { - struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *cgrp; struct cgroup *ancestor; + u64 cgrp_id; + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); ancestor = cgroup_ancestor(cgrp, ancestor_level); - if (!ancestor) - return 0; - return cgroup_id(ancestor); + cgrp_id = ancestor ? cgroup_id(ancestor) : 0; + rcu_read_unlock(); + + return cgrp_id; } const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { @@ -369,39 +440,7 @@ const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; - -#ifdef CONFIG_CGROUP_BPF -DECLARE_PER_CPU(struct bpf_cgroup_storage*, - bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); - -BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) -{ - /* flags argument is not used now, - * but provides an ability to extend the API. - * verifier checks that its value is correct. - */ - enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); - struct bpf_cgroup_storage *storage; - void *ptr; - - storage = this_cpu_read(bpf_cgroup_storage[stype]); - - if (stype == BPF_CGROUP_STORAGE_SHARED) - ptr = &READ_ONCE(storage->buf)->data[0]; - else - ptr = this_cpu_ptr(storage->percpu_buf); - - return (unsigned long)ptr; -} - -const struct bpf_func_proto bpf_get_local_storage_proto = { - .func = bpf_get_local_storage, - .gpl_only = false, - .ret_type = RET_PTR_TO_MAP_VALUE, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_ANYTHING, -}; -#endif +#endif /* CONFIG_CGROUPS */ #define BPF_STRTOX_BASE_MASK 0x1F @@ -479,16 +518,15 @@ 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; } @@ -497,26 +535,26 @@ const struct bpf_func_proto bpf_strtol_proto = { .func = bpf_strtol, .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_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; } @@ -525,12 +563,26 @@ const struct bpf_func_proto bpf_strtoul_proto = { .func = bpf_strtoul, .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_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) +{ + return strncmp(s1, s2, s1_sz); +} + +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 | MEM_RDONLY, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_CONST_STR, }; -#endif BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino, struct bpf_pidns_info *, nsdata, u32, size) @@ -597,18 +649,1261 @@ const struct bpf_func_proto bpf_event_output_data_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size, + const void __user *, user_ptr) +{ + int ret = copy_from_user(dst, user_ptr, size); + + if (unlikely(ret)) { + memset(dst, 0, size); + ret = -EFAULT; + } + + return ret; +} + +const struct bpf_func_proto bpf_copy_from_user_proto = { + .func = bpf_copy_from_user, + .gpl_only = false, + .might_sleep = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size, + const void __user *, user_ptr, struct task_struct *, tsk, u64, flags) +{ + int ret; + + /* flags is not used yet */ + if (unlikely(flags)) + return -EINVAL; + + if (unlikely(!size)) + return 0; + + ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0); + if (ret == size) + return 0; + + memset(dst, 0, size); + /* Return -EFAULT for partial read */ + return ret < 0 ? ret : -EFAULT; +} + +const struct bpf_func_proto bpf_copy_from_user_task_proto = { + .func = bpf_copy_from_user_task, + .gpl_only = true, + .might_sleep = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_BTF_ID, + .arg4_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg5_type = ARG_ANYTHING +}; + +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 *)(const uintptr_t)ptr, cpu); +} + +const struct bpf_func_proto bpf_per_cpu_ptr_proto = { + .func = bpf_per_cpu_ptr, + .gpl_only = false, + .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY, + .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_1(bpf_this_cpu_ptr, const void *, 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 = { + .func = bpf_this_cpu_ptr, + .gpl_only = false, + .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY, + .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, +}; + +static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, + size_t bufsz) +{ + void __user *user_ptr = (__force void __user *)unsafe_ptr; + + buf[0] = 0; + + switch (fmt_ptype) { + case 's': +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + if ((unsigned long)unsafe_ptr < TASK_SIZE) + return strncpy_from_user_nofault(buf, user_ptr, bufsz); + fallthrough; +#endif + case 'k': + return strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz); + case 'u': + return strncpy_from_user_nofault(buf, user_ptr, bufsz); + } + + return -EINVAL; +} + +/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary + * arguments representation. + */ +#define MAX_BPRINTF_BIN_ARGS 512 + +/* Support executing three nested bprintf helper calls on a given CPU */ +#define MAX_BPRINTF_NEST_LEVEL 3 +struct bpf_bprintf_buffers { + char bin_args[MAX_BPRINTF_BIN_ARGS]; + char buf[MAX_BPRINTF_BUF]; +}; + +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_buffers(struct bpf_bprintf_buffers **bufs) +{ + int nest_level; + + preempt_disable(); + nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); + if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { + this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); + return -EBUSY; + } + *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]); + + return 0; +} + +void bpf_bprintf_cleanup(struct bpf_bprintf_data *data) +{ + if (!data->bin_args && !data->buf) + return; + if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0)) + return; + this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); +} + +/* + * bpf_bprintf_prepare - Generic pass on format strings for bprintf-like helpers + * + * 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 data->get_bin_args is false + * - Arguments preparation: in addition to the above verification, it writes in + * 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 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; + char fmt_ptype, cur_ip[16], ip_spec[] = "%pXX"; + + fmt_end = strnchr(fmt, fmt_size, 0); + if (!fmt_end) + return -EINVAL; + fmt_size = fmt_end - fmt; + + if (get_buffers && try_get_buffers(&buffers)) + return -EBUSY; + + 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; + goto out; + } + + if (fmt[i] != '%') + continue; + + if (fmt[i + 1] == '%') { + i++; + continue; + } + + if (num_spec >= num_args) { + err = -EINVAL; + goto out; + } + + /* The string is zero-terminated so if fmt[i] != 0, we can + * always access fmt[i + 1], in the worst case it will be a 0 + */ + i++; + + /* skip optional "[0 +-][num]" width formatting field */ + while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' || + fmt[i] == ' ') + i++; + if (fmt[i] >= '1' && fmt[i] <= '9') { + i++; + while (fmt[i] >= '0' && fmt[i] <= '9') + i++; + } + + if (fmt[i] == 'p') { + sizeof_cur_arg = sizeof(long); + + if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') && + fmt[i + 2] == 's') { + fmt_ptype = fmt[i + 1]; + i += 2; + goto fmt_str; + } + + if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || + ispunct(fmt[i + 1]) || 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++; + goto nocopy_fmt; + } + + if (fmt[i + 1] == 'B') { + if (tmp_buf) { + err = snprintf(tmp_buf, + (tmp_buf_end - tmp_buf), + "%pB", + (void *)(long)raw_args[num_spec]); + tmp_buf += (err + 1); + } + + i++; + num_spec++; + continue; + } + + /* only support "%pI4", "%pi4", "%pI6" and "%pi6". */ + if ((fmt[i + 1] != 'i' && fmt[i + 1] != 'I') || + (fmt[i + 2] != '4' && fmt[i + 2] != '6')) { + err = -EINVAL; + goto out; + } + + i += 2; + if (!tmp_buf) + goto nocopy_fmt; + + sizeof_cur_ip = (fmt[i] == '4') ? 4 : 16; + if (tmp_buf_end - tmp_buf < sizeof_cur_ip) { + err = -ENOSPC; + goto out; + } + + unsafe_ptr = (char *)(long)raw_args[num_spec]; + err = copy_from_kernel_nofault(cur_ip, unsafe_ptr, + sizeof_cur_ip); + if (err < 0) + memset(cur_ip, 0, sizeof_cur_ip); + + /* hack: bstr_printf expects IP addresses to be + * pre-formatted as strings, ironically, the easiest way + * to do that is to call snprintf. + */ + ip_spec[2] = fmt[i - 1]; + ip_spec[3] = fmt[i]; + err = snprintf(tmp_buf, tmp_buf_end - tmp_buf, + ip_spec, &cur_ip); + + tmp_buf += err + 1; + num_spec++; + + continue; + } else if (fmt[i] == 's') { + fmt_ptype = fmt[i]; +fmt_str: + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) { + err = -EINVAL; + goto out; + } + + if (!tmp_buf) + goto nocopy_fmt; + + if (tmp_buf_end == tmp_buf) { + err = -ENOSPC; + goto out; + } + + unsafe_ptr = (char *)(long)raw_args[num_spec]; + err = bpf_trace_copy_string(tmp_buf, unsafe_ptr, + fmt_ptype, + tmp_buf_end - tmp_buf); + if (err < 0) { + tmp_buf[0] = '\0'; + err = 1; + } + + tmp_buf += err; + num_spec++; + + continue; + } else if (fmt[i] == 'c') { + if (!tmp_buf) + goto nocopy_fmt; + + if (tmp_buf_end == tmp_buf) { + err = -ENOSPC; + goto out; + } + + *tmp_buf = raw_args[num_spec]; + tmp_buf++; + num_spec++; + + continue; + } + + sizeof_cur_arg = sizeof(int); + + if (fmt[i] == 'l') { + sizeof_cur_arg = sizeof(long); + i++; + } + if (fmt[i] == 'l') { + sizeof_cur_arg = sizeof(long long); + i++; + } + + if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' && + fmt[i] != 'x' && fmt[i] != 'X') { + err = -EINVAL; + goto out; + } + + if (tmp_buf) + cur_arg = raw_args[num_spec]; +nocopy_fmt: + if (tmp_buf) { + tmp_buf = PTR_ALIGN(tmp_buf, sizeof(u32)); + if (tmp_buf_end - tmp_buf < sizeof_cur_arg) { + err = -ENOSPC; + goto out; + } + + if (sizeof_cur_arg == 8) { + *(u32 *)tmp_buf = *(u32 *)&cur_arg; + *(u32 *)(tmp_buf + 4) = *((u32 *)&cur_arg + 1); + } else { + *(u32 *)tmp_buf = (u32)(long)cur_arg; + } + tmp_buf += sizeof_cur_arg; + } + num_spec++; + } + + err = 0; +out: + if (err) + bpf_bprintf_cleanup(data); + return err; +} + +BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, + const void *, args, u32, data_len) +{ + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; + int err, num_args; + + if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || + (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, args, num_args, &data); + if (err < 0) + return err; + + err = bstr_printf(str, str_size, fmt, data.bin_args); + + bpf_bprintf_cleanup(&data); + + return err + 1; +} + +const struct bpf_func_proto bpf_snprintf_proto = { + .func = bpf_snprintf, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM_OR_NULL, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_PTR_TO_CONST_STR, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, +}; + +struct bpf_async_cb { + struct bpf_map *map; + struct bpf_prog *prog; + void __rcu *callback_fn; + void *value; + 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_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. + * bpf_timer_start() arms the timer. + * If user space reference to a map goes to zero at this point + * ops->map_release_uref callback is responsible for cancelling the timers, + * freeing their memory, and decrementing prog's refcnts. + * bpf_timer_cancel() cancels the timer and decrements prog's refcnt. + * Inner maps can contain bpf timers as well. ops->map_release_uref is + * freeing the timers when inner map is replaced or deleted by user space. + */ +struct bpf_hrtimer { + struct bpf_async_cb cb; + struct hrtimer timer; + 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 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. + */ + 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->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->cb.callback_fn, rcu_read_lock_bh_held()); + if (!callback_fn) + goto out; + + /* bpf_timer_cb() runs in hrtimer_run_softirq. It doesn't migrate and + * cannot be preempted by another bpf_timer_cb() on the same cpu. + * Remember the timer this callback is servicing to prevent + * deadlock if callback_fn() calls bpf_timer_cancel() or + * 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); + } + + callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); + /* The verifier checked that return value is zero. */ + + this_cpu_write(hrtimer_running, NULL); +out: + return HRTIMER_NORESTART; +} + +static void bpf_wq_work(struct work_struct *work) +{ + struct bpf_work *w = container_of(work, struct bpf_work, work); + struct bpf_async_cb *cb = &w->cb; + struct bpf_map *map = cb->map; + bpf_callback_t callback_fn; + void *value = cb->value; + void *key; + u32 idx; + + BTF_TYPE_EMIT(struct bpf_wq); + + callback_fn = READ_ONCE(cb->callback_fn); + if (!callback_fn) + return; + + if (map->map_type == BPF_MAP_TYPE_ARRAY) { + struct bpf_array *array = container_of(map, struct bpf_array, map); + + /* compute the key */ + idx = ((char *)value - array->value) / array->elem_size; + key = &idx; + } else { /* hash or lru */ + key = value - round_up(map->key_size, 8); + } + + rcu_read_lock_trace(); + migrate_disable(); + + callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); + + migrate_enable(); + rcu_read_unlock_trace(); +} + +static void bpf_wq_delete_work(struct work_struct *work) +{ + struct bpf_work *w = container_of(work, struct bpf_work, delete_work); + + cancel_work_sync(&w->work); + + kfree_rcu(w, cb.rcu); +} + +static 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 + * kfree_rcu(t) 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); + kfree_rcu(t, cb.rcu); +} + +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; + + if (in_nmi()) + return -EOPNOTSUPP; + + 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(&async->lock); + t = async->timer; + if (t) { + ret = -EBUSY; + goto out; + } + + /* allocate hrtimer via map_kmalloc to use memcg accounting */ + cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, 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_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT); + t->timer.function = bpf_timer_cb; + cb->value = (void *)async - map->record->timer_off; + break; + case BPF_ASYNC_TYPE_WQ: + w = (struct bpf_work *)cb; + + INIT_WORK(&w->work, bpf_wq_work); + INIT_WORK(&w->delete_work, bpf_wq_delete_work); + cb->value = (void *)async - map->record->wq_off; + break; + } + cb->map = map; + cb->prog = NULL; + cb->flags = flags; + rcu_assign_pointer(cb->callback_fn, NULL); + + WRITE_ONCE(async->cb, cb); + /* Guarantee the order between async->cb and map->usercnt. So + * when there are concurrent uref release and bpf timer init, either + * bpf_timer_cancel_and_free() called by uref release reads a no-NULL + * timer or atomic64_read() below returns a zero usercnt. + */ + 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(cb); + ret = -EPERM; + } +out: + __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, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +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_async_cb *cb; + int ret = 0; + + if (in_nmi()) + return -EOPNOTSUPP; + __bpf_spin_lock_irqsave(&async->lock); + cb = async->cb; + if (!cb) { + ret = -EINVAL; + goto out; + } + 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 + * is gone, since map_release_uref won't ever be called. + */ + ret = -EPERM; + goto out; + } + 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. + */ + prog = bpf_prog_inc_not_zero(prog); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto out; + } + if (prev) + /* Drop prev prog refcnt when swapping with new prog */ + bpf_prog_put(prev); + cb->prog = prog; + } + rcu_assign_pointer(cb->callback_fn, callback_fn); +out: + __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, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_PTR_TO_FUNC, +}; + +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 & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN)) + return -EINVAL; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (!t || !t->cb.prog) { + ret = -EINVAL; + goto out; + } + + 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; +} + +static const struct bpf_func_proto bpf_timer_start_proto = { + .func = bpf_timer_start, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static void drop_prog_refcnt(struct bpf_async_cb *async) +{ + struct bpf_prog *prog = async->prog; + + if (prog) { + bpf_prog_put(prog); + async->prog = NULL; + rcu_assign_pointer(async->callback_fn, NULL); + } +} + +BPF_CALL_1(bpf_timer_cancel, struct bpf_async_kern *, timer) +{ + 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; + } + + 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. + */ + ret = -EDEADLK; + goto out; + } + + /* 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; +} + +static const struct bpf_func_proto bpf_timer_cancel_proto = { + .func = bpf_timer_cancel, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, +}; + +static struct bpf_async_cb *__bpf_async_cancel_and_free(struct bpf_async_kern *async) +{ + struct bpf_async_cb *cb; + + /* Performance optimization: read async->cb without lock first. */ + if (!READ_ONCE(async->cb)) + return NULL; + + __bpf_spin_lock_irqsave(&async->lock); + /* re-read it under lock */ + cb = async->cb; + if (!cb) + goto out; + drop_prog_refcnt(cb); + /* The subsequent bpf_timer_start/cancel() helpers won't be able to use + * this timer, since it won't be initialized. + */ + WRITE_ONCE(async->cb, NULL); +out: + __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; + /* 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 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 + * kfree_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_unbound_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) + kfree_rcu(t, cb.rcu); + else + queue_work(system_unbound_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. + */ + schedule_work(&work->delete_work); +} + +BPF_CALL_2(bpf_kptr_xchg, void *, dst, void *, ptr) +{ + unsigned long *kptr = dst; + + /* This helper may be inlined by verifier. */ + return xchg(kptr, (unsigned long)ptr); +} + +/* Unlike other PTR_TO_BTF_ID helpers the btf_id in bpf_kptr_xchg() + * helper is determined dynamically by the verifier. Use BPF_PTR_POISON to + * denote type that verifier will determine. + */ +static const struct bpf_func_proto bpf_kptr_xchg_proto = { + .func = bpf_kptr_xchg, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .ret_btf_id = BPF_PTR_POISON, + .arg1_type = ARG_KPTR_XCHG_DEST, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL | OBJ_RELEASE, + .arg2_btf_id = BPF_PTR_POISON, +}; + +/* Since the upper 8 bits of dynptr->size is reserved, the + * maximum supported size is 2^24 - 1. + */ +#define DYNPTR_MAX_SIZE ((1UL << 24) - 1) +#define DYNPTR_TYPE_SHIFT 28 +#define DYNPTR_SIZE_MASK 0xFFFFFF +#define DYNPTR_RDONLY_BIT BIT(31) + +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; +} + +static enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *ptr) +{ + return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT; +} + +u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr) +{ + return ptr->size & DYNPTR_SIZE_MASK; +} + +static void bpf_dynptr_set_size(struct bpf_dynptr_kern *ptr, u32 new_size) +{ + u32 metadata = ptr->size & ~DYNPTR_SIZE_MASK; + + ptr->size = new_size | metadata; +} + +int bpf_dynptr_check_size(u32 size) +{ + return size > DYNPTR_MAX_SIZE ? -E2BIG : 0; +} + +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size) +{ + ptr->data = data; + ptr->offset = offset; + ptr->size = size; + bpf_dynptr_set_type(ptr, type); +} + +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_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) +{ + int err; + + BTF_TYPE_EMIT(struct bpf_dynptr); + + err = bpf_dynptr_check_size(size); + if (err) + goto error; + + /* flags is currently unsupported */ + if (flags) { + err = -EINVAL; + goto error; + } + + bpf_dynptr_init(ptr, data, BPF_DYNPTR_TYPE_LOCAL, 0, size); + + return 0; + +error: + bpf_dynptr_set_null(ptr); + return err; +} + +static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { + .func = bpf_dynptr_from_mem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .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 | MEM_WRITE, +}; + +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, + u32, offset, u64, flags) +{ + enum bpf_dynptr_type type; + int err; + + if (!src->data || flags) + return -EINVAL; + + err = bpf_dynptr_check_off_len(src, offset, len); + if (err) + return err; + + type = bpf_dynptr_get_type(src); + + 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); + default: + WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type); + return -EFAULT; + } +} + +static const struct bpf_func_proto bpf_dynptr_read_proto = { + .func = bpf_dynptr_read, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src, + u32, len, u64, flags) +{ + enum bpf_dynptr_type type; + int err; + + if (!dst->data || __bpf_dynptr_is_rdonly(dst)) + return -EINVAL; + + err = bpf_dynptr_check_off_len(dst, offset, len); + if (err) + return err; + + type = bpf_dynptr_get_type(dst); + + 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); + default: + WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type); + return -EFAULT; + } +} + +static const struct bpf_func_proto bpf_dynptr_write_proto = { + .func = bpf_dynptr_write, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) +{ + enum bpf_dynptr_type type; + int err; + + if (!ptr->data) + return 0; + + err = bpf_dynptr_check_off_len(ptr, offset, len); + if (err) + return 0; + + if (__bpf_dynptr_is_rdonly(ptr)) + return 0; + + 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: + /* 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 = { + .func = bpf_dynptr_data, + .gpl_only = false, + .ret_type = RET_PTR_TO_DYNPTR_MEM_OR_NULL, + .arg1_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, +}; + const struct bpf_func_proto bpf_get_current_task_proto __weak; +const struct bpf_func_proto bpf_get_current_task_btf_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; 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_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: @@ -623,6 +1918,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; + case BPF_FUNC_map_lookup_percpu_elem: + return &bpf_map_lookup_percpu_elem_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: @@ -635,6 +1932,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_tai_ns: + return &bpf_ktime_get_tai_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: @@ -645,11 +1944,21 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ringbuf_discard_proto; case BPF_FUNC_ringbuf_query: return &bpf_ringbuf_query_proto; + case BPF_FUNC_strncmp: + return &bpf_strncmp_proto; + case BPF_FUNC_strtol: + return &bpf_strtol_proto; + case BPF_FUNC_strtoul: + return &bpf_strtoul_proto; + case BPF_FUNC_get_current_pid_tgid: + return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_get_ns_current_pid_tgid: + return &bpf_get_ns_current_pid_tgid_proto; default: break; } - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return NULL; switch (func_id) { @@ -657,31 +1966,1274 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: return &bpf_spin_unlock_proto; - case BPF_FUNC_trace_printk: - if (!perfmon_capable()) - return NULL; - return bpf_get_trace_printk_proto(); case BPF_FUNC_jiffies64: return &bpf_jiffies64_proto; + case BPF_FUNC_per_cpu_ptr: + return &bpf_per_cpu_ptr_proto; + case BPF_FUNC_this_cpu_ptr: + return &bpf_this_cpu_ptr_proto; + case BPF_FUNC_timer_init: + return &bpf_timer_init_proto; + case BPF_FUNC_timer_set_callback: + return &bpf_timer_set_callback_proto; + case BPF_FUNC_timer_start: + return &bpf_timer_start_proto; + case BPF_FUNC_timer_cancel: + return &bpf_timer_cancel_proto; + case BPF_FUNC_kptr_xchg: + return &bpf_kptr_xchg_proto; + case BPF_FUNC_for_each_map_elem: + return &bpf_for_each_map_elem_proto; + case BPF_FUNC_loop: + return &bpf_loop_proto; + case BPF_FUNC_user_ringbuf_drain: + return &bpf_user_ringbuf_drain_proto; + case BPF_FUNC_ringbuf_reserve_dynptr: + return &bpf_ringbuf_reserve_dynptr_proto; + case BPF_FUNC_ringbuf_submit_dynptr: + return &bpf_ringbuf_submit_dynptr_proto; + case BPF_FUNC_ringbuf_discard_dynptr: + return &bpf_ringbuf_discard_dynptr_proto; + case BPF_FUNC_dynptr_from_mem: + return &bpf_dynptr_from_mem_proto; + case BPF_FUNC_dynptr_read: + return &bpf_dynptr_read_proto; + case BPF_FUNC_dynptr_write: + return &bpf_dynptr_write_proto; + case BPF_FUNC_dynptr_data: + return &bpf_dynptr_data_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_cgrp_storage_get: + 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; +#endif default: break; } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; switch (func_id) { + case BPF_FUNC_trace_printk: + return bpf_get_trace_printk_proto(); case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; + case BPF_FUNC_get_current_task_btf: + return &bpf_get_current_task_btf_proto; case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return &bpf_probe_read_kernel_proto; + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? + NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return &bpf_probe_read_kernel_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? + NULL : &bpf_probe_read_kernel_str_proto; + case BPF_FUNC_snprintf_btf: + return &bpf_snprintf_btf_proto; + case BPF_FUNC_snprintf: + return &bpf_snprintf_proto; + case BPF_FUNC_task_pt_regs: + return &bpf_task_pt_regs_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_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) +{ + struct list_head *head = list_head, *orig_head = list_head; + + BUILD_BUG_ON(sizeof(struct list_head) > sizeof(struct bpf_list_head)); + BUILD_BUG_ON(__alignof__(struct list_head) > __alignof__(struct bpf_list_head)); + + /* Do the actual list draining outside the lock to not hold the lock for + * too long, and also prevent deadlocks if tracing programs end up + * executing on entry/exit of functions called inside the critical + * section, and end up doing map ops that call bpf_list_head_free for + * the same map value again. + */ + __bpf_spin_lock_irqsave(spin_lock); + if (!head->next || list_empty(head)) + goto unlock; + head = head->next; +unlock: + INIT_LIST_HEAD(orig_head); + __bpf_spin_unlock_irqrestore(spin_lock); + + while (head != orig_head) { + void *obj = head; + + 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_drop_impl(obj, field->graph_root.value_rec, false); + } +} + +/* 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_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; + void *p; + + p = bpf_mem_alloc(&bpf_global_ma, size); + if (!p) + return NULL; + if (meta) + bpf_obj_init(meta->record, p); + return p; +} + +__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; + + __bpf_obj_drop_impl(p, meta ? meta->record : NULL, false); +} + +__bpf_kfunc void bpf_percpu_obj_drop_impl(void *p__alloc, void *meta__ign) +{ + /* 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); + + /* 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; +} + +__bpf_kfunc int bpf_list_push_front_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta__ign, u64 off) +{ + 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); +} + +__bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta__ign, u64 off) +{ + 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; +} + +__bpf_kfunc struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) +{ + return __bpf_list_del(head, false); +} + +__bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) +{ + return __bpf_list_del(head, true); +} + +__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 + */ +static int __bpf_rbtree_add(struct bpf_rb_root *root, + struct bpf_rb_node_kern *node, + void *less, struct btf_record *rec, u64 off) +{ + 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 + */ + 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_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. + */ +__bpf_kfunc struct task_struct *bpf_task_acquire(struct task_struct *p) +{ + if (refcount_inc_not_zero(&p->rcu_users)) + return p; + return NULL; +} + +/** + * bpf_task_release - Release the reference acquired on a task. + * @p: The task on which a reference is being released. + */ +__bpf_kfunc void bpf_task_release(struct task_struct *p) +{ + put_task_struct_rcu_user(p); +} + +__bpf_kfunc void bpf_task_release_dtor(void *p) +{ + put_task_struct_rcu_user(p); +} +CFI_NOSEAL(bpf_task_release_dtor); + +#ifdef CONFIG_CGROUPS +/** + * bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by + * this kfunc which is not stored in a map as a kptr, must be released by + * calling bpf_cgroup_release(). + * @cgrp: The cgroup on which a reference is being acquired. + */ +__bpf_kfunc struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) +{ + return cgroup_tryget(cgrp) ? cgrp : NULL; +} + +/** + * bpf_cgroup_release - Release the reference acquired on a cgroup. + * If this kfunc is invoked in an RCU read region, the cgroup is guaranteed to + * not be freed until the current grace period has ended, even if its refcount + * drops to 0. + * @cgrp: The cgroup on which a reference is being released. + */ +__bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp) +{ + cgroup_put(cgrp); +} + +__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp) +{ + cgroup_put(cgrp); +} +CFI_NOSEAL(bpf_cgroup_release_dtor); + +/** + * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor + * array. A cgroup returned by this kfunc which is not subsequently stored in a + * map, must be released by calling bpf_cgroup_release(). + * @cgrp: The cgroup for which we're performing a lookup. + * @level: The level of ancestor to look up. + */ +__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]; + 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 */ + +/** + * bpf_task_from_pid - Find a struct task_struct from its pid by looking it up + * in the root pid namespace idr. If a task is returned, it must either be + * stored in a map, or released with bpf_task_release(). + * @pid: The pid of the task being looked up. + */ +__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) + 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; +} + +/** + * 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, u32 offset, + void *buffer__opt, u32 buffer__szk) +{ + const struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + enum bpf_dynptr_type type; + u32 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; + } 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, u32 offset, + void *buffer__opt, u32 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, u32 start, u32 end) +{ + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p; + u32 size; + + if (!ptr->data || start > end) + return -EINVAL; + + size = __bpf_dynptr_size(ptr); + + if (start > size || end > size) + return -ERANGE; + + ptr->offset += 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 __u32 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_kfunc void *bpf_cast_to_kern_ctx(void *obj) +{ + return obj; +} + +__bpf_kfunc void *bpf_rdonly_cast(const void *obj__ign, u32 btf_id__k) +{ + return (void *)obj__ign; +} + +__bpf_kfunc void bpf_rcu_read_lock(void) +{ + rcu_read_lock(); +} + +__bpf_kfunc void bpf_rcu_read_unlock(void) +{ + rcu_read_unlock(); +} + +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; + + if (!is_bpf_text_address(ip)) + return !ctx->cnt; + prog = bpf_prog_ksym_find(ip); + 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__ign) +{ + struct bpf_prog_aux *aux = (struct bpf_prog_aux *)aux__ign; + struct bpf_async_kern *async = (struct bpf_async_kern *)wq; + + if (flags) + return -EINVAL; + + return __bpf_async_set_callback(async, callback_fn, aux, flags, BPF_ASYNC_TYPE_WQ); +} + +__bpf_kfunc void bpf_preempt_disable(void) +{ + preempt_disable(); +} + +__bpf_kfunc void bpf_preempt_enable(void) +{ + preempt_enable(); +} + +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; +} + +/* 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_end_defs(); + +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_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_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) + +#ifdef CONFIG_CGROUPS +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_RCU | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU) +BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL) +#endif +BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_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 +BTF_KFUNCS_END(generic_btf_ids) + +static const struct btf_kfunc_id_set generic_kfunc_set = { + .owner = THIS_MODULE, + .set = &generic_btf_ids, +}; + + +BTF_ID_LIST(generic_dtor_ids) +BTF_ID(struct, task_struct) +BTF_ID(func, bpf_task_release_dtor) +#ifdef CONFIG_CGROUPS +BTF_ID(struct, cgroup) +BTF_ID(func, bpf_cgroup_release_dtor) +#endif + +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_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) +#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_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) +BTF_KFUNCS_END(common_btf_ids) + +static const struct btf_kfunc_id_set common_kfunc_set = { + .owner = THIS_MODULE, + .set = &common_btf_ids, +}; + +static int __init kfunc_init(void) +{ + int ret; + const struct btf_id_dtor_kfunc generic_dtors[] = { + { + .btf_id = generic_dtor_ids[0], + .kfunc_btf_id = generic_dtor_ids[1] + }, +#ifdef CONFIG_CGROUPS + { + .btf_id = generic_dtor_ids[2], + .kfunc_btf_id = generic_dtor_ids[3] + }, +#endif + }; + + 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); + return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); +} + +late_initcall(kfunc_init); + +/* Get a pointer to dynptr data up to len bytes for read only access. If + * the dynptr doesn't have continuous data up to len bytes, return NULL. + */ +const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len) +{ + 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, u32 len) +{ + if (__bpf_dynptr_is_rdonly(ptr)) + return NULL; + return (void *)__bpf_dynptr_data(ptr, len); } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index fb878ba3f22f..9aaf5124648b 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,8 @@ #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 { BPF_TYPE_UNSPEC = 0, @@ -97,9 +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; @@ -117,11 +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(inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); return inode; } @@ -147,11 +147,11 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, d_instantiate(dentry, inode); dget(dentry); - 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 inode *dir, struct dentry *dentry, umode_t mode) +static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -226,10 +226,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) else prev_key = key; + rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; - return NULL; + key = NULL; } + rcu_read_unlock(); return key; } @@ -369,16 +371,17 @@ static struct dentry * bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) { /* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future - * extensions. + * extensions. That allows popoulate_bpffs() create special files. */ - if (strchr(dentry->d_name.name, '.')) + if ((dir->i_mode & S_IALLUGO) && + strchr(dentry->d_name.name, '.')) return ERR_PTR(-EPERM); return simple_lookup(dir, dentry, flags); } -static int bpf_symlink(struct inode *dir, struct dentry *dentry, - const char *target) +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); struct inode *inode; @@ -409,7 +412,28 @@ static const struct inode_operations bpf_dir_iops = { .unlink = simple_unlink, }; -static int bpf_obj_do_pin(const char __user *pathname, void *raw, +/* pin iterator link into bpffs */ +static int bpf_iter_link_pin_kernel(struct dentry *parent, + const char *name, struct bpf_link *link) +{ + umode_t mode = S_IFREG | S_IRUSR; + 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); + return PTR_ERR(dentry); + } + ret = bpf_mkobj_ops(dentry, mode, link, &bpf_link_iops, + &bpf_iter_fops); + dput(dentry); + inode_unlock(parent->d_inode); + return ret; +} + +static int bpf_obj_do_pin(int path_fd, const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; @@ -418,22 +442,21 @@ 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 = user_path_create(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); @@ -452,7 +475,7 @@ out: 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; @@ -462,14 +485,14 @@ 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; @@ -477,12 +500,12 @@ 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); inode = d_backing_inode(path.dentry); - ret = inode_permission(inode, ACC_MODE(flags)); + ret = path_permission(&path, ACC_MODE(flags)); if (ret) goto out; @@ -501,7 +524,7 @@ 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; @@ -512,7 +535,7 @@ 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); @@ -521,7 +544,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); else if (type == BPF_TYPE_LINK) - ret = bpf_link_new_fd(raw); + ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw); else return -ENOENT; @@ -533,7 +556,7 @@ 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(inode, MAY_READ); + int ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ); if (ret) return ERR_PTR(ret); @@ -572,15 +595,183 @@ 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; } @@ -595,7 +786,7 @@ 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, .show_options = bpf_show_options, @@ -603,48 +794,230 @@ static const struct super_operations bpf_super_ops = { }; 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) + if (opt < 0) { /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd * better continue to ignore non-existing options for bpf. */ - return opt == -ENOPARAM ? 0 : opt; + if (opt == -ENOPARAM) { + opt = vfs_parse_fs_param_source(fc, param); + if (opt != -ENOPARAM) + return opt; + + return 0; + } + + if (opt < 0) + return opt; + } 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; +EXPORT_SYMBOL_GPL(bpf_preload_ops); + +static bool bpf_preload_mod_get(void) +{ + /* If bpf_preload.ko wasn't loaded earlier then load it now. + * When bpf_preload is built into vmlinux the module's __init + * function will populate it. + */ + if (!bpf_preload_ops) { + request_module("bpf_preload"); + if (!bpf_preload_ops) + return false; + } + /* And grab the reference, so the module doesn't disappear while the + * kernel is interacting with the kernel module and its UMD. + */ + if (!try_module_get(bpf_preload_ops->owner)) { + pr_err("bpf_preload module get failed.\n"); + return false; + } + return true; +} + +static void bpf_preload_mod_put(void) +{ + if (bpf_preload_ops) + /* now user can "rmmod bpf_preload" if necessary */ + module_put(bpf_preload_ops->owner); +} + +static DEFINE_MUTEX(bpf_preload_lock); + +static int populate_bpffs(struct dentry *parent) +{ + struct bpf_preload_info objs[BPF_PRELOAD_LINKS] = {}; + int err = 0, i; + + /* grab the mutex to make sure the kernel interactions with bpf_preload + * are serialized + */ + mutex_lock(&bpf_preload_lock); + + /* if bpf_preload.ko wasn't built into vmlinux then load it */ + if (!bpf_preload_mod_get()) + goto out; + + err = bpf_preload_ops->preload(objs); + if (err) + goto out_put; + for (i = 0; i < BPF_PRELOAD_LINKS; i++) { + bpf_link_inc(objs[i].link); + err = bpf_iter_link_pin_kernel(parent, + objs[i].link_name, objs[i].link); + if (err) { + bpf_link_put(objs[i].link); + goto out_put; + } + } +out_put: + bpf_preload_mod_put(); +out: + mutex_unlock(&bpf_preload_lock); + return err; } 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; @@ -652,10 +1025,12 @@ 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); inode->i_mode |= S_ISVTX | opts->mode; - return 0; } @@ -666,7 +1041,7 @@ 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 = { @@ -687,18 +1062,35 @@ static int bpf_init_fs_context(struct fs_context *fc) return -ENOMEM; opts->mode = S_IRWXUGO; + opts->uid = current_fsuid(); + opts->gid = current_fsgid(); + + /* 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->fs_private = opts; + 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_litter_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 new file mode 100644 index 000000000000..fec8005a121c --- /dev/null +++ b/kernel/bpf/link_iter.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2022 Red Hat, Inc. */ +#include <linux/bpf.h> +#include <linux/fs.h> +#include <linux/filter.h> +#include <linux/kernel.h> +#include <linux/btf_ids.h> + +struct bpf_iter_seq_link_info { + u32 link_id; +}; + +static void *bpf_link_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_link_info *info = seq->private; + struct bpf_link *link; + + link = bpf_link_get_curr_or_next(&info->link_id); + if (!link) + return NULL; + + if (*pos == 0) + ++*pos; + return link; +} + +static void *bpf_link_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_link_info *info = seq->private; + + ++*pos; + ++info->link_id; + bpf_link_put((struct bpf_link *)v); + return bpf_link_get_curr_or_next(&info->link_id); +} + +struct bpf_iter__bpf_link { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_link *, link); +}; + +DEFINE_BPF_ITER_FUNC(bpf_link, struct bpf_iter_meta *meta, struct bpf_link *link) + +static int __bpf_link_seq_show(struct seq_file *seq, void *v, bool in_stop) +{ + struct bpf_iter__bpf_link ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int ret = 0; + + ctx.meta = &meta; + ctx.link = v; + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (prog) + ret = bpf_iter_run_prog(prog, &ctx); + + return ret; +} + +static int bpf_link_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_link_seq_show(seq, v, false); +} + +static void bpf_link_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__bpf_link_seq_show(seq, v, true); + else + bpf_link_put((struct bpf_link *)v); +} + +static const struct seq_operations bpf_link_seq_ops = { + .start = bpf_link_seq_start, + .next = bpf_link_seq_next, + .stop = bpf_link_seq_stop, + .show = bpf_link_seq_show, +}; + +BTF_ID_LIST(btf_bpf_link_id) +BTF_ID(struct, bpf_link) + +static const struct bpf_iter_seq_info bpf_link_seq_info = { + .seq_ops = &bpf_link_seq_ops, + .init_seq_private = NULL, + .fini_seq_private = NULL, + .seq_priv_size = sizeof(struct bpf_iter_seq_link_info), +}; + +static struct bpf_iter_reg bpf_link_reg_info = { + .target = "bpf_link", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__bpf_link, link), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &bpf_link_seq_info, +}; + +static int __init bpf_link_iter_init(void) +{ + bpf_link_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_link_id; + return bpf_iter_reg_target(&bpf_link_reg_info); +} + +late_initcall(bpf_link_iter_init); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 33d01866bcc2..3969eb0382af 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -1,6 +1,7 @@ -//SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0 #include <linux/bpf-cgroup.h> #include <linux/bpf.h> +#include <linux/bpf_local_storage.h> #include <linux/btf.h> #include <linux/bug.h> #include <linux/filter.h> @@ -8,11 +9,12 @@ #include <linux/rbtree.h> #include <linux/slab.h> #include <uapi/linux/btf.h> - -DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +#include <linux/btf_ids.h> #ifdef CONFIG_CGROUP_BPF +#include "../cgroup/cgroup-internal.h" + #define LOCAL_STORAGE_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) @@ -20,7 +22,6 @@ struct bpf_cgroup_storage_map { struct bpf_map map; spinlock_t lock; - struct bpf_prog_aux *aux; struct rb_root root; struct list_head list; }; @@ -30,24 +31,41 @@ static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map) return container_of(map, struct bpf_cgroup_storage_map, map); } -static int bpf_cgroup_storage_key_cmp( - const struct bpf_cgroup_storage_key *key1, - const struct bpf_cgroup_storage_key *key2) +static bool attach_type_isolated(const struct bpf_map *map) { - if (key1->cgroup_inode_id < key2->cgroup_inode_id) - return -1; - else if (key1->cgroup_inode_id > key2->cgroup_inode_id) - return 1; - else if (key1->attach_type < key2->attach_type) - return -1; - else if (key1->attach_type > key2->attach_type) - return 1; + return map->key_size == sizeof(struct bpf_cgroup_storage_key); +} + +static int bpf_cgroup_storage_key_cmp(const struct bpf_cgroup_storage_map *map, + const void *_key1, const void *_key2) +{ + if (attach_type_isolated(&map->map)) { + const struct bpf_cgroup_storage_key *key1 = _key1; + const struct bpf_cgroup_storage_key *key2 = _key2; + + if (key1->cgroup_inode_id < key2->cgroup_inode_id) + return -1; + else if (key1->cgroup_inode_id > key2->cgroup_inode_id) + return 1; + else if (key1->attach_type < key2->attach_type) + return -1; + else if (key1->attach_type > key2->attach_type) + return 1; + } else { + const __u64 *cgroup_inode_id1 = _key1; + const __u64 *cgroup_inode_id2 = _key2; + + if (*cgroup_inode_id1 < *cgroup_inode_id2) + return -1; + else if (*cgroup_inode_id1 > *cgroup_inode_id2) + return 1; + } return 0; } -static struct bpf_cgroup_storage *cgroup_storage_lookup( - struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key, - bool locked) +struct bpf_cgroup_storage * +cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, + void *key, bool locked) { struct rb_root *root = &map->root; struct rb_node *node; @@ -61,7 +79,7 @@ static struct bpf_cgroup_storage *cgroup_storage_lookup( storage = container_of(node, struct bpf_cgroup_storage, node); - switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) { + switch (bpf_cgroup_storage_key_cmp(map, key, &storage->key)) { case -1: node = node->rb_left; break; @@ -93,7 +111,7 @@ static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map, this = container_of(*new, struct bpf_cgroup_storage, node); parent = *new; - switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) { + switch (bpf_cgroup_storage_key_cmp(map, &storage->key, &this->key)) { case -1: new = &((*new)->rb_left); break; @@ -111,10 +129,9 @@ static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map, return 0; } -static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key) +static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *key) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); - struct bpf_cgroup_storage_key *key = _key; struct bpf_cgroup_storage *storage; storage = cgroup_storage_lookup(map, key, false); @@ -124,21 +141,17 @@ 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_key *key = _key; struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; - if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST | BPF_NOEXIST))) - return -EINVAL; - - if (unlikely(flags & BPF_NOEXIST)) + if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST))) return -EINVAL; if (unlikely((flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map))) + !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, @@ -151,15 +164,14 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return 0; } - new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, - __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, - map->numa_node); + new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size), + __GFP_ZERO | GFP_NOWAIT | __GFP_NOWARN, + map->numa_node); if (!new) return -ENOMEM; memcpy(&new->data[0], value, map->value_size); - check_and_init_map_lock(map, new->data); + check_and_init_map_value(map, new->data); new = xchg(&storage->buf, new); kfree_rcu(new, rcu); @@ -167,11 +179,10 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return 0; } -int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key, +int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key, void *value) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); - struct bpf_cgroup_storage_key *key = _key; struct bpf_cgroup_storage *storage; int cpu, off = 0; u32 size; @@ -197,11 +208,10 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key, return 0; } -int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key, +int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key, void *value, u64 map_flags) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); - struct bpf_cgroup_storage_key *key = _key; struct bpf_cgroup_storage *storage; int cpu, off = 0; u32 size; @@ -232,12 +242,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key, return 0; } -static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key, +static int cgroup_storage_get_next_key(struct bpf_map *_map, void *key, void *_next_key) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); - struct bpf_cgroup_storage_key *key = _key; - struct bpf_cgroup_storage_key *next = _next_key; struct bpf_cgroup_storage *storage; spin_lock_bh(&map->lock); @@ -250,17 +258,23 @@ static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key, if (!storage) goto enoent; - storage = list_next_entry(storage, list); + storage = list_next_entry(storage, list_map); if (!storage) goto enoent; } else { storage = list_first_entry(&map->list, - struct bpf_cgroup_storage, list); + struct bpf_cgroup_storage, list_map); } spin_unlock_bh(&map->lock); - next->attach_type = storage->key.attach_type; - next->cgroup_inode_id = storage->key.cgroup_inode_id; + + if (attach_type_isolated(&map->map)) { + struct bpf_cgroup_storage_key *next = _next_key; + *next = storage->key; + } else { + __u64 *next = _next_key; + *next = storage->key.cgroup_inode_id; + } return 0; enoent: @@ -270,18 +284,25 @@ enoent: static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { + __u32 max_value_size = BPF_LOCAL_STORAGE_MAX_VALUE_SIZE; int numa_node = bpf_map_attr_numa_node(attr); struct bpf_cgroup_storage_map *map; - struct bpf_map_memory mem; - int ret; - if (attr->key_size != sizeof(struct bpf_cgroup_storage_key)) + /* percpu is bound by PCPU_MIN_UNIT_SIZE, non-percu + * is the same as other local storages. + */ + if (attr->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) + max_value_size = min_t(__u32, max_value_size, + PCPU_MIN_UNIT_SIZE); + + if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) && + attr->key_size != sizeof(__u64)) return ERR_PTR(-EINVAL); if (attr->value_size == 0) return ERR_PTR(-EINVAL); - if (attr->value_size > PAGE_SIZE) + if (attr->value_size > max_value_size) return ERR_PTR(-E2BIG); if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK || @@ -292,18 +313,9 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) /* max_entries is not used and enforced to be 0 */ return ERR_PTR(-EINVAL); - ret = bpf_map_charge_init(&mem, sizeof(struct bpf_cgroup_storage_map)); - if (ret < 0) - return ERR_PTR(ret); - - map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map), - __GFP_ZERO | GFP_USER, numa_node); - if (!map) { - bpf_map_charge_finish(&mem); + map = bpf_map_area_alloc(sizeof(struct bpf_cgroup_storage_map), numa_node); + if (!map) return ERR_PTR(-ENOMEM); - } - - bpf_map_charge_move(&map->map.memory, &mem); /* copy mandatory map attributes */ bpf_map_init_from_attr(&map->map, attr); @@ -318,14 +330,25 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) static void cgroup_storage_map_free(struct bpf_map *_map) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct list_head *storages = &map->list; + struct bpf_cgroup_storage *storage, *stmp; + + cgroup_lock(); + + list_for_each_entry_safe(storage, stmp, storages, list_map) { + bpf_cgroup_storage_unlink(storage); + bpf_cgroup_storage_free(storage); + } + + cgroup_unlock(); WARN_ON(!RB_EMPTY_ROOT(&map->root)); WARN_ON(!list_empty(&map->list)); - kfree(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; } @@ -335,49 +358,63 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) { - struct btf_member *m; - u32 offset, size; - - /* Key is expected to be of struct bpf_cgroup_storage_key type, - * which is: - * struct bpf_cgroup_storage_key { - * __u64 cgroup_inode_id; - * __u32 attach_type; - * }; - */ + if (attach_type_isolated(map)) { + struct btf_member *m; + u32 offset, size; + + /* Key is expected to be of struct bpf_cgroup_storage_key type, + * which is: + * struct bpf_cgroup_storage_key { + * __u64 cgroup_inode_id; + * __u32 attach_type; + * }; + */ + + /* + * Key_type must be a structure with two fields. + */ + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT || + BTF_INFO_VLEN(key_type->info) != 2) + return -EINVAL; + + /* + * The first field must be a 64 bit integer at 0 offset. + */ + m = (struct btf_member *)(key_type + 1); + size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id); + if (!btf_member_is_reg_int(btf, key_type, m, 0, size)) + return -EINVAL; + + /* + * The second field must be a 32 bit integer at 64 bit offset. + */ + m++; + offset = offsetof(struct bpf_cgroup_storage_key, attach_type); + size = sizeof_field(struct bpf_cgroup_storage_key, attach_type); + if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) + return -EINVAL; + } else { + u32 int_data; - /* - * Key_type must be a structure with two fields. - */ - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT || - BTF_INFO_VLEN(key_type->info) != 2) - return -EINVAL; + /* + * Key is expected to be u64, which stores the cgroup_inode_id + */ - /* - * The first field must be a 64 bit integer at 0 offset. - */ - m = (struct btf_member *)(key_type + 1); - size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id); - if (!btf_member_is_reg_int(btf, key_type, m, 0, size)) - return -EINVAL; + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; - /* - * The second field must be a 32 bit integer at 64 bit offset. - */ - m++; - offset = offsetof(struct bpf_cgroup_storage_key, attach_type); - size = sizeof_field(struct bpf_cgroup_storage_key, attach_type); - if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) - return -EINVAL; + int_data = *(u32 *)(key_type + 1); + if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data)) + return -EINVAL; + } return 0; } -static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key, +static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { - enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); - struct bpf_cgroup_storage_key *key = _key; + enum bpf_cgroup_storage_type stype; struct bpf_cgroup_storage *storage; int cpu; @@ -394,7 +431,7 @@ 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) { @@ -402,13 +439,21 @@ 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 = { .map_alloc = cgroup_storage_map_alloc, .map_free = cgroup_storage_map_free, @@ -418,43 +463,20 @@ 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], }; int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); - struct bpf_cgroup_storage_map *map = map_to_storage(_map); - int ret = -EBUSY; - - spin_lock_bh(&map->lock); - if (map->aux && map->aux != aux) - goto unlock; if (aux->cgroup_storage[stype] && aux->cgroup_storage[stype] != _map) - goto unlock; + return -EBUSY; - map->aux = aux; aux->cgroup_storage[stype] = _map; - ret = 0; -unlock: - spin_unlock_bh(&map->lock); - - return ret; -} - -void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map) -{ - enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); - struct bpf_cgroup_storage_map *map = map_to_storage(_map); - - spin_lock_bh(&map->lock); - if (map->aux == aux) { - WARN_ON(aux->cgroup_storage[stype] != _map); - map->aux = NULL; - aux->cgroup_storage[stype] = NULL; - } - spin_unlock_bh(&map->lock); + return 0; } static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) @@ -477,9 +499,9 @@ static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { + const gfp_t gfp = __GFP_ZERO | GFP_USER; struct bpf_cgroup_storage *storage; struct bpf_map *map; - gfp_t flags; size_t size; u32 pages; @@ -489,23 +511,19 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, size = bpf_cgroup_storage_calculate_size(map, &pages); - if (bpf_map_charge_memlock(map, pages)) - return ERR_PTR(-EPERM); - - storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), - __GFP_ZERO | GFP_USER, map->numa_node); + storage = bpf_map_kmalloc_node(map, sizeof(struct bpf_cgroup_storage), + gfp, map->numa_node); if (!storage) goto enomem; - flags = __GFP_ZERO | GFP_USER; - if (stype == BPF_CGROUP_STORAGE_SHARED) { - storage->buf = kmalloc_node(size, flags, map->numa_node); + storage->buf = bpf_map_kmalloc_node(map, size, gfp, + map->numa_node); if (!storage->buf) goto enomem; - check_and_init_map_lock(map, storage->buf->data); + check_and_init_map_value(map, storage->buf->data); } else { - storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); + storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp); if (!storage->percpu_buf) goto enomem; } @@ -515,7 +533,6 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, return storage; enomem: - bpf_map_uncharge_memlock(map, pages); kfree(storage); return ERR_PTR(-ENOMEM); } @@ -542,16 +559,11 @@ void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { enum bpf_cgroup_storage_type stype; struct bpf_map *map; - u32 pages; if (!storage) return; map = &storage->map->map; - - bpf_cgroup_storage_calculate_size(map, &pages); - bpf_map_uncharge_memlock(map, pages); - stype = cgroup_storage_type(map); if (stype == BPF_CGROUP_STORAGE_SHARED) call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); @@ -575,7 +587,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, spin_lock_bh(&map->lock); WARN_ON(cgroup_storage_insert(map, storage)); - list_add(&storage->list, &map->list); + list_add(&storage->list_map, &map->list); + list_add(&storage->list_cg, &cgroup->bpf.storages); spin_unlock_bh(&map->lock); } @@ -593,7 +606,8 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage) root = &map->root; rb_erase(&storage->node, root); - list_del(&storage->list); + list_del(&storage->list_map); + list_del(&storage->list_cg); spin_unlock_bh(&map->lock); } diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c new file mode 100644 index 000000000000..38050f4ee400 --- /dev/null +++ b/kernel/bpf/log.c @@ -0,0 +1,880 @@ +// 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_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_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' +}; + +static void print_liveness(struct bpf_verifier_env *env, + enum bpf_reg_liveness live) +{ + if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) + verbose(env, "_"); + if (live & REG_LIVE_READ) + verbose(env, "r"); + if (live & REG_LIVE_WRITTEN) + verbose(env, "w"); + if (live & REG_LIVE_DONE) + verbose(env, "D"); +} + +#define UNUM_MAX_DECIMAL U16_MAX +#define SNUM_MAX_DECIMAL S16_MAX +#define SNUM_MIN_DECIMAL S16_MIN + +static bool is_unum_decimal(u64 num) +{ + return num <= UNUM_MAX_DECIMAL; +} + +static bool is_snum_decimal(s64 num) +{ + return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL; +} + +static void verbose_unum(struct bpf_verifier_env *env, u64 num) +{ + if (is_unum_decimal(num)) + verbose(env, "%llu", num); + else + verbose(env, "%#llx", num); +} + +static void verbose_snum(struct bpf_verifier_env *env, s64 num) +{ + if (is_snum_decimal(num)) + verbose(env, "%lld", num); + else + verbose(env, "%#llx", num); +} + +int tnum_strn(char *str, size_t size, struct tnum a) +{ + /* print as a constant, if tnum is fully known */ + if (a.mask == 0) { + if (is_unum_decimal(a.value)) + return snprintf(str, size, "%llu", a.value); + else + return snprintf(str, size, "%#llx", a.value); + } + return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); +} +EXPORT_SYMBOL_GPL(tnum_strn); + +static void print_scalar_ranges(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + const char **sep) +{ + /* For signed ranges, we want to unify 64-bit and 32-bit values in the + * output as much as possible, but there is a bit of a complication. + * If we choose to print values as decimals, this is natural to do, + * because negative 64-bit and 32-bit values >= -S32_MIN have the same + * representation due to sign extension. But if we choose to print + * them in hex format (see is_snum_decimal()), then sign extension is + * misleading. + * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in + * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two + * very different numbers. + * So we avoid sign extension if we choose to print values in hex. + */ + struct { + const char *name; + u64 val; + bool omit; + } minmaxs[] = { + {"smin", reg->smin_value, reg->smin_value == S64_MIN}, + {"smax", reg->smax_value, reg->smax_value == S64_MAX}, + {"umin", reg->umin_value, reg->umin_value == 0}, + {"umax", reg->umax_value, reg->umax_value == U64_MAX}, + {"smin32", + is_snum_decimal((s64)reg->s32_min_value) + ? (s64)reg->s32_min_value + : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN}, + {"smax32", + is_snum_decimal((s64)reg->s32_max_value) + ? (s64)reg->s32_max_value + : (u32)reg->s32_max_value, reg->s32_max_value == S32_MAX}, + {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, + {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, + }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; + bool neg1, neg2; + + for (m1 = &minmaxs[0]; m1 < mend; m1++) { + if (m1->omit) + continue; + + neg1 = m1->name[0] == 's' && (s64)m1->val < 0; + + verbose(env, "%s%s=", *sep, m1->name); + *sep = ","; + + for (m2 = m1 + 2; m2 < mend; m2 += 2) { + if (m2->omit || m2->val != m1->val) + continue; + /* don't mix negatives with positives */ + neg2 = m2->name[0] == 's' && (s64)m2->val < 0; + if (neg2 != neg1) + continue; + m2->omit = true; + verbose(env, "%s=", m2->name); + } + + if (m1->name[0] == 's') + verbose_snum(env, m1->val); + else + verbose_unum(env, m1->val); + } +} + +static bool type_is_map_ptr(enum bpf_reg_type t) { + switch (base_type(t)) { + case CONST_PTR_TO_MAP: + case PTR_TO_MAP_KEY: + case PTR_TO_MAP_VALUE: + return true; + default: + return false; + } +} + +/* + * _a stands for append, was shortened to avoid multiline statements below. + * This macro is used to output a comma separated list of attributes. + */ +#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) + +static void print_reg_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state, + const struct bpf_reg_state *reg) +{ + enum bpf_reg_type t; + const char *sep = ""; + + t = reg->type; + if (t == SCALAR_VALUE && reg->precise) + verbose(env, "P"); + if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) { + 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); + print_liveness(env, reg->live); + verbose(env, "="); + print_reg_state(env, state, reg); + } + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + char types_buf[BPF_REG_SIZE + 1]; + const char *sep = ""; + bool valid = false; + u8 slot_type; + int j; + + if (!print_all && !stack_slot_scratched(env, i)) + continue; + + for (j = 0; j < BPF_REG_SIZE; j++) { + slot_type = state->stack[i].slot_type[j]; + if (slot_type != STACK_INVALID) + valid = true; + types_buf[j] = slot_type_char[slot_type]; + } + types_buf[BPF_REG_SIZE] = 0; + if (!valid) + continue; + + reg = &state->stack[i].spilled_ptr; + switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { + case STACK_SPILL: + /* print MISC/ZERO/INVALID slots above subreg spill */ + for (j = 0; j < BPF_REG_SIZE; j++) + if (state->stack[i].slot_type[j] == STACK_SPILL) + break; + types_buf[j] = '\0'; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=%s", types_buf); + print_reg_state(env, state, reg); + break; + case STACK_DYNPTR: + /* skip to main dynptr slot */ + i += BPF_DYNPTR_NR_SLOTS - 1; + reg = &state->stack[i].spilled_ptr; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type)); + if (reg->id) + verbose_a("id=%d", reg->id); + if (reg->ref_obj_id) + verbose_a("ref_id=%d", reg->ref_obj_id); + if (reg->dynptr_id) + verbose_a("dynptr_id=%d", reg->dynptr_id); + verbose(env, ")"); + break; + case STACK_ITER: + /* only main slot has ref_obj_id set; skip others */ + if (!reg->ref_obj_id) + continue; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)", + iter_type_str(reg->iter.btf, reg->iter.btf_id), + reg->ref_obj_id, iter_state_str(reg->iter.state), + reg->iter.depth); + break; + case STACK_MISC: + case STACK_ZERO: + default: + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=%s", types_buf); + break; + } + } + if (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 c8cc4e4cf98d..e8a772e64324 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -14,6 +14,8 @@ #include <linux/vmalloc.h> #include <net/ipv6.h> #include <uapi/linux/btf.h> +#include <linux/btf_ids.h> +#include <linux/bpf_mem_alloc.h> /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) @@ -21,7 +23,6 @@ struct lpm_trie_node; struct lpm_trie_node { - struct rcu_head rcu; struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; @@ -31,10 +32,11 @@ 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; + raw_spinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to @@ -154,22 +156,23 @@ 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) @@ -223,16 +226,27 @@ 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 ... */ - for (node = rcu_dereference(trie->root); node;) { + for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held()); + node;) { unsigned int next_bit; size_t matchlen; @@ -240,7 +254,7 @@ 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; @@ -264,7 +278,8 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) * traverse down. */ next_bit = extract_bit(key->data, node->prefixlen); - node = rcu_dereference(node->child[next_bit]); + node = rcu_dereference_check(node->child[next_bit], + rcu_read_lock_bh_held()); } if (!found) @@ -273,17 +288,13 @@ 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 = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, - trie->map.numa_node); if (!node) return NULL; @@ -296,14 +307,25 @@ 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; @@ -315,22 +337,12 @@ 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++; + raw_spin_lock_irqsave(&trie->lock, irq_flags); new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); @@ -349,8 +361,7 @@ static int trie_update_elem(struct bpf_map *map, 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); @@ -361,6 +372,10 @@ 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; } @@ -369,18 +384,30 @@ 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. */ @@ -393,6 +420,7 @@ 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; } @@ -410,28 +438,25 @@ static int trie_update_elem(struct bpf_map *map, rcu_assign_pointer(im_node->child[1], node); } - /* Finally, assign the intermediate node to the determined spot */ + /* Finally, assign the intermediate node to the determined slot */ rcu_assign_pointer(*slot, im_node); out: - if (ret) { - if (new_node) - trie->n_entries--; + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); - kfree(new_node); - kfree(im_node); - } - - spin_unlock_irqrestore(&trie->lock, irq_flags); + 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; @@ -442,7 +467,7 @@ 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); + raw_spin_lock_irqsave(&trie->lock, irq_flags); /* 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 @@ -500,8 +525,8 @@ 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; } @@ -515,10 +540,13 @@ 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_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; } @@ -530,7 +558,7 @@ 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) @@ -540,11 +568,8 @@ out: static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; - u64 cost = sizeof(*trie), cost_per_node; - int ret; - - if (!bpf_capable()) - return ERR_PTR(-EPERM); + size_t leaf_size; + int err; /* check sanity of attributes */ if (attr->max_entries == 0 || @@ -557,30 +582,29 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) attr->value_size > LPM_VAL_SIZE_MAX) return ERR_PTR(-EINVAL); - trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN); + trie = bpf_map_area_alloc(sizeof(*trie), NUMA_NO_NODE); if (!trie) return ERR_PTR(-ENOMEM); /* 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; - cost_per_node = sizeof(struct lpm_trie_node) + - attr->value_size + trie->data_size; - cost += (u64) attr->max_entries * cost_per_node; - - ret = bpf_map_charge_init(&trie->map.memory, cost); - if (ret) - goto out_err; - - spin_lock_init(&trie->lock); + raw_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; -out_err: - kfree(trie); - return ERR_PTR(ret); + +free_out: + bpf_map_area_free(trie); + return ERR_PTR(err); } static void trie_free(struct bpf_map *map) @@ -589,11 +613,6 @@ static void trie_free(struct bpf_map *map) struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; - /* Wait for outstanding programs to complete - * update/lookup/delete/get_next_key and free the trie. - */ - synchronize_rcu(); - /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent * and start over. @@ -617,25 +636,29 @@ 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: - kfree(trie); + bpf_mem_alloc_destroy(&trie->ma); + bpf_map_area_free(trie); } 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 @@ -657,7 +680,7 @@ 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) @@ -674,7 +697,7 @@ 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; @@ -718,7 +741,7 @@ 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); @@ -730,17 +753,34 @@ 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, .map_alloc = trie_alloc, .map_free = trie_free, .map_get_next_key = trie_get_next_key, .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, + .map_lookup_batch = generic_map_lookup_batch, + .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 17738c93bec8..645bd30bc9a9 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -3,6 +3,7 @@ */ #include <linux/slab.h> #include <linux/bpf.h> +#include <linux/btf.h> #include "map_in_map.h" @@ -10,67 +11,72 @@ 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; + 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; - /* prog_array->aux->{type,jited} is a runtime binding. - * Doing static check alone in the verifier is not enough. - */ - if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY || - inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || - inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE || - inner_map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { - fdput(f); - return ERR_PTR(-ENOTSUPP); - } - /* Does not support >1 level map-in-map */ - if (inner_map->inner_map_meta) { - fdput(f); + if (inner_map->inner_map_meta) return ERR_PTR(-EINVAL); - } - if (map_value_has_spin_lock(inner_map)) { - fdput(f); + 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) { - fdput(f); + 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; inner_map_meta->value_size = inner_map->value_size; inner_map_meta->map_flags = inner_map->map_flags; inner_map_meta->max_entries = inner_map->max_entries; - inner_map_meta->spin_lock_off = inner_map->spin_lock_off; + + inner_map_meta->record = btf_record_dup(inner_map->record); + if (IS_ERR(inner_map_meta->record)) { + /* btf_record_dup returns NULL or valid pointer in case of + * invalid/empty/valid, but ERR_PTR in case of errors. During + * equality NULL or IS_ERR is equivalent. + */ + 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 + * record->fields.list_head have pointers like value_rec pointing into + * inner_map->btf. + */ + if (inner_map->btf) { + btf_get(inner_map->btf); + inner_map_meta->btf = inner_map->btf; + } /* 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; } void bpf_map_meta_free(struct bpf_map *map_meta) { + bpf_map_free_record(map_meta); + btf_put(map_meta->btf); kfree(map_meta); } @@ -82,36 +88,44 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, meta0->key_size == meta1->key_size && meta0->value_size == meta1->value_size && meta0->map_flags == meta1->map_flags && - meta0->max_entries == meta1->max_entries; + btf_record_equal(meta0->record, meta1->record); } void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file /* not used */, int ufd) { - struct bpf_map *inner_map; - struct fd f; + struct bpf_map *inner_map, *inner_map_meta; + CLASS(fd, f)(ufd); - f = fdget(ufd); inner_map = __bpf_map_get(f); if (IS_ERR(inner_map)) return inner_map; - if (bpf_map_meta_equal(map->inner_map_meta, inner_map)) + inner_map_meta = map->inner_map_meta; + if (inner_map_meta->ops->map_meta_equal(inner_map_meta, inner_map)) bpf_map_inc(inner_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 a507bf6ef8b9..7d61602354de 100644 --- a/kernel/bpf/map_in_map.h +++ b/kernel/bpf/map_in_map.h @@ -11,11 +11,9 @@ struct bpf_map; struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd); void bpf_map_meta_free(struct bpf_map *map_meta); -bool bpf_map_meta_equal(const struct bpf_map *meta0, - const struct bpf_map *meta1); 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 c69071e334bf..9575314f40a6 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -4,9 +4,10 @@ #include <linux/fs.h> #include <linux/filter.h> #include <linux/kernel.h> +#include <linux/btf_ids.h> struct bpf_iter_seq_map_info { - u32 mid; + u32 map_id; }; static void *bpf_map_seq_start(struct seq_file *seq, loff_t *pos) @@ -14,27 +15,23 @@ static void *bpf_map_seq_start(struct seq_file *seq, loff_t *pos) struct bpf_iter_seq_map_info *info = seq->private; struct bpf_map *map; - map = bpf_map_get_curr_or_next(&info->mid); + map = bpf_map_get_curr_or_next(&info->map_id); if (!map) return NULL; - ++*pos; + if (*pos == 0) + ++*pos; return map; } static void *bpf_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_map_info *info = seq->private; - struct bpf_map *map; ++*pos; - ++info->mid; + ++info->map_id; bpf_map_put((struct bpf_map *)v); - map = bpf_map_get_curr_or_next(&info->mid); - if (!map) - return NULL; - - return map; + return bpf_map_get_curr_or_next(&info->map_id); } struct bpf_iter__bpf_map { @@ -81,22 +78,152 @@ static const struct seq_operations bpf_map_seq_ops = { .show = bpf_map_seq_show, }; -static const struct bpf_iter_reg bpf_map_reg_info = { - .target = "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, .init_seq_private = NULL, .fini_seq_private = NULL, .seq_priv_size = sizeof(struct bpf_iter_seq_map_info), +}; + +static struct bpf_iter_reg bpf_map_reg_info = { + .target = "bpf_map", .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, +}; + +static int bpf_iter_attach_map(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) +{ + u32 key_acc_size, value_acc_size, key_size, value_size; + struct bpf_map *map; + bool is_percpu = false; + int err = -EINVAL; + + if (!linfo->map.map_fd) + return -EBADF; + + map = bpf_map_get_with_uref(linfo->map.map_fd); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + is_percpu = true; + else if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) + goto put_map; + + key_acc_size = prog->aux->max_rdonly_access; + value_acc_size = prog->aux->max_rdwr_access; + key_size = map->key_size; + if (!is_percpu) + value_size = map->value_size; + else + value_size = round_up(map->value_size, 8) * num_possible_cpus(); + + if (key_acc_size > key_size || value_acc_size > value_size) { + err = -EACCES; + goto put_map; + } + + aux->map = map; + return 0; + +put_map: + bpf_map_put_with_uref(map); + return err; +} + +static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) +{ + bpf_map_put_with_uref(aux->map); +} + +void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq) +{ + seq_printf(seq, "map_id:\t%u\n", aux->map->id); +} + +int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info) +{ + info->iter.map.map_id = aux->map->id; + return 0; +} + +DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta, + struct bpf_map *map, void *key, void *value) + +static const struct bpf_iter_reg bpf_map_elem_reg_info = { + .target = "bpf_map_elem", + .attach_target = bpf_iter_attach_map, + .detach_target = bpf_iter_detach_map, + .show_fdinfo = bpf_iter_map_show_fdinfo, + .fill_link_info = bpf_iter_map_fill_link_info, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__bpf_map_elem, key), + PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY }, + { offsetof(struct bpf_iter__bpf_map_elem, value), + PTR_TO_BUF | PTR_MAYBE_NULL }, }, }; static int __init bpf_map_iter_init(void) { - return bpf_iter_reg_target(&bpf_map_reg_info); + int ret; + + bpf_map_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_map_id; + ret = bpf_iter_reg_target(&bpf_map_reg_info); + if (ret) + return ret; + + return bpf_iter_reg_target(&bpf_map_elem_reg_info); } 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 new file mode 100644 index 000000000000..889374722d0a --- /dev/null +++ b/kernel/bpf/memalloc.c @@ -0,0 +1,1016 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include <linux/mm.h> +#include <linux/llist.h> +#include <linux/bpf.h> +#include <linux/irq_work.h> +#include <linux/bpf_mem_alloc.h> +#include <linux/memcontrol.h> +#include <asm/local.h> + +/* Any context (including NMI) BPF specific memory allocator. + * + * Tracing BPF programs can attach to kprobe and fentry. Hence they + * run in unknown context where calling plain kmalloc() might not be safe. + * + * Front-end kmalloc() with per-cpu per-bucket cache of free elements. + * Refill this cache asynchronously from irq_work. + * + * CPU_0 buckets + * 16 32 64 96 128 196 256 512 1024 2048 4096 + * ... + * CPU_N buckets + * 16 32 64 96 128 196 256 512 1024 2048 4096 + * + * The buckets are prefilled at the start. + * BPF programs always run with migration disabled. + * It's safe to allocate from cache of the current cpu with irqs disabled. + * Free-ing is always done into bucket of the current cpu as well. + * irq_work trims extra free elements from buckets with kfree + * and refills them with kmalloc, so global kmalloc logic takes care + * of freeing objects allocated by one cpu and freed on another. + * + * Every allocated objected is padded with extra 8 bytes that contains + * struct llist_node. + */ +#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 */ + 3, /* 16 */ + 4, /* 24 */ + 4, /* 32 */ + 5, /* 40 */ + 5, /* 48 */ + 5, /* 56 */ + 5, /* 64 */ + 1, /* 72 */ + 1, /* 80 */ + 1, /* 88 */ + 1, /* 96 */ + 6, /* 104 */ + 6, /* 112 */ + 6, /* 120 */ + 6, /* 128 */ + 2, /* 136 */ + 2, /* 144 */ + 2, /* 152 */ + 2, /* 160 */ + 2, /* 168 */ + 2, /* 176 */ + 2, /* 184 */ + 2 /* 192 */ +}; + +static int bpf_mem_cache_idx(size_t size) +{ + if (!size || size > BPF_MEM_ALLOC_SIZE_MAX) + return -1; + + if (size <= 192) + return size_index[(size - 1) / 8] - 1; + + return fls(size - 1) - 2; +} + +#define NUM_CACHES 11 + +struct bpf_mem_cache { + /* per-cpu list of free objects of size 'unit_size'. + * All accesses are done with interrupts disabled and 'active' counter + * protection with __llist_add() and __llist_del_first(). + */ + struct llist_head free_llist; + local_t active; + + /* Operations on the free_list from unit_alloc/unit_free/bpf_mem_refill + * are sequenced by per-cpu 'active' counter. But unit_free() cannot + * fail. When 'active' is busy the unit_free() will add an object to + * free_llist_extra. + */ + struct llist_head free_llist_extra; + + struct irq_work refill_work; + struct obj_cgroup *objcg; + int unit_size; + /* count of objects in free_llist */ + int free_cnt; + int low_watermark, high_watermark, batch; + int percpu_size; + bool draining; + struct bpf_mem_cache *tgt; + + /* 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; + + entry = head->first; + if (!entry) + return NULL; + next = entry->next; + head->first = next; + return entry; +} + +static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags) +{ + if (c->percpu_size) { + 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); + kfree(obj); + return NULL; + } + obj[1] = pptr; + return obj; + } + + 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 + if (c->objcg) + return get_mem_cgroup_from_objcg(c->objcg); + 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, bool atomic) +{ + struct mem_cgroup *memcg = NULL, *old_memcg; + gfp_t gfp; + void *obj; + int i; + + gfp = __GFP_NOWARN | __GFP_ACCOUNT; + gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL; + + for (i = 0; i < cnt; i++) { + /* + * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is + * done only by one CPU == current CPU. Other CPUs might + * llist_add() and llist_del_all() in parallel. + */ + obj = llist_del_first(&c->free_by_rcu_ttrace); + if (!obj) + break; + add_obj_to_free_list(c, obj); + } + if (i >= cnt) + return; + + 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. + */ + 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(void *obj, bool percpu) +{ + if (percpu) + free_percpu(((void __percpu **)obj)[1]); + + kfree(obj); +} + +static int free_all(struct llist_node *llnode, bool percpu) +{ + struct llist_node *pos, *t; + int cnt = 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) +{ + /* If RCU Tasks Trace grace period implies RCU grace period, + * there is no need to invoke call_rcu(). + */ + if (rcu_trace_implies_rcu_gp()) + __free_rcu(head); + else + call_rcu(head, __free_rcu); +} + +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_ttrace list. + */ + llist_add(llnode, &c->free_by_rcu_ttrace); +} + +static void do_call_rcu_ttrace(struct bpf_mem_cache *c) +{ + struct llist_node *llnode, *t; + + if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { + if (unlikely(READ_ONCE(c->draining))) { + llnode = llist_del_all(&c->free_by_rcu_ttrace); + free_all(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; + } + + /* 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_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 { + inc_active(c, &flags); + llnode = __llist_del_first(&c->free_llist); + if (llnode) + cnt = --c->free_cnt; + else + cnt = 0; + dec_active(c, &flags); + if (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(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) +{ + struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work); + int cnt; + + /* Racy access to free_cnt. It doesn't need to be 100% accurate */ + cnt = c->free_cnt; + if (cnt < c->low_watermark) + /* 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, 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) +{ + irq_work_queue(&c->refill_work); +} + +/* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket + * the freelist cache will be elem_size * 64 (or less) on each cpu. + * + * For bpf programs that don't have statically known allocation sizes and + * assuming (low_mark + high_mark) / 2 as an average number of elements per + * bucket and all buckets are used the total amount of memory in freelists + * on each cpu will be: + * 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096 + * == ~ 116 Kbyte using below heuristic. + * Initialized, but unused bpf allocator (not bpf map specific one) will + * consume ~ 11 Kbyte per cpu. + * Typical case will be between 11K and 116K closer to 11K. + * bpf progs can and should share bpf_mem_cache when possible. + * + * Percpu allocation is typically rare. To avoid potential unnecessary large + * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1. + */ +static void init_refill_work(struct bpf_mem_cache *c) +{ + init_irq_work(&c->refill_work, bpf_mem_refill); + if (c->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 { + /* When page_size == 4k, order-0 cache will have low_mark == 2 + * and high_mark == 6 with batch alloc of 3 individual pages at + * a time. + * 8k allocs and above low == 1, high == 3, batch == 1. + */ + c->low_watermark = max(32 * 256 / c->unit_size, 1); + c->high_watermark = max(96 * 256 / c->unit_size, 3); + } + c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1); +} + +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. + */ + 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. + * This is typical bpf hash map use case when all elements have equal size. + * + * When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on + * kmalloc/kfree. Max allocation size is 4096 in this case. + * This is bpf_dynptr and bpf_kptr use case. + */ +int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) +{ + 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) + size += LLIST_NODE_SZ; /* room for llist_node */ + unit_size = size; + +#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; + } + + pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); + if (!pcc) + return -ENOMEM; +#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) +{ + 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_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now. + * + * Except for waiting_for_gp_ttrace list, there are no concurrent operations + * on these lists, so it is safe to use __llist_del_all(). + */ + 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; + ma->caches = NULL; +} + +static void free_mem_alloc(struct bpf_mem_alloc *ma) +{ + /* 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 + * to wait for the pending __free_rcu_tasks_trace() and __free_rcu(), + * so if call_rcu(head, __free_rcu) is skipped due to + * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by + * using rcu_trace_implies_rcu_gp() as well. + */ + 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); +} + +static void free_mem_alloc_deferred(struct work_struct *work) +{ + struct bpf_mem_alloc *ma = container_of(work, struct bpf_mem_alloc, work); + + free_mem_alloc(ma); + kfree(ma); +} + +static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress) +{ + struct bpf_mem_alloc *copy; + + if (!rcu_in_progress) { + /* Fast path. No callbacks are pending, hence no need to do + * rcu_barrier-s. + */ + free_mem_alloc_no_barrier(ma); + return; + } + + copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL); + if (!copy) { + /* Slow path with inline barrier-s */ + free_mem_alloc(ma); + return; + } + + /* Defer barriers into worker to let the rest of map memory to be freed */ + memset(ma, 0, sizeof(*ma)); + INIT_WORK(©->work, free_mem_alloc_deferred); + queue_work(system_unbound_wq, ©->work); +} + +void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) +{ + struct bpf_mem_caches *cc; + struct bpf_mem_cache *c; + int cpu, i, rcu_in_progress; + + if (ma->cache) { + rcu_in_progress = 0; + for_each_possible_cpu(cpu) { + c = per_cpu_ptr(ma->cache, cpu); + 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); + } + obj_cgroup_put(ma->objcg); + destroy_mem_alloc(ma, rcu_in_progress); + } + if (ma->caches) { + rcu_in_progress = 0; + for_each_possible_cpu(cpu) { + 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); + } + } + obj_cgroup_put(ma->objcg); + destroy_mem_alloc(ma, rcu_in_progress); + } +} + +/* notrace is necessary here and in other functions to make sure + * bpf programs cannot attach to them and cause llist corruptions. + */ +static void notrace *unit_alloc(struct bpf_mem_cache *c) +{ + struct llist_node *llnode = NULL; + unsigned long flags; + int cnt = 0; + + /* Disable irqs to prevent the following race for majority of prog types: + * prog_A + * bpf_mem_alloc + * preemption or irq -> prog_B + * bpf_mem_alloc + * + * but prog_B could be a perf_event NMI prog. + * Use per-cpu 'active' counter to order free_list access between + * unit_alloc/unit_free/bpf_mem_refill. + */ + local_irq_save(flags); + if (local_inc_return(&c->active) == 1) { + llnode = __llist_del_first(&c->free_llist); + if (llnode) { + cnt = --c->free_cnt; + *(struct bpf_mem_cache **)llnode = c; + } + } + local_dec(&c->active); + + 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; +} + +/* Though 'ptr' object could have been allocated on a different cpu + * add it to the free_llist of the current cpu. + * Let kfree() logic deal with it when it's later called from irq_work. + */ +static void notrace unit_free(struct bpf_mem_cache *c, void *ptr) +{ + struct llist_node *llnode = ptr - LLIST_NODE_SZ; + unsigned long flags; + int cnt = 0; + + 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); + cnt = ++c->free_cnt; + } else { + /* unit_free() cannot fail. Therefore add an object to atomic + * llist. free_bulk() will drain it. Though free_llist_extra is + * a per-cpu list we have to use atomic llist_add here, since + * it also can be interrupted by bpf nmi prog that does another + * unit_free() into the same free_llist_extra. + */ + llist_add(llnode, &c->free_llist_extra); + } + local_dec(&c->active); + + 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. + * In both cases migration is disabled. + */ +void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) +{ + int idx; + void *ret; + + if (!size) + return NULL; + + if (!ma->percpu) + size += LLIST_NODE_SZ; + idx = bpf_mem_cache_idx(size); + if (idx < 0) + return NULL; + + ret = unit_alloc(this_cpu_ptr(ma->caches)->cache + idx); + return !ret ? NULL : ret + LLIST_NODE_SZ; +} + +void notrace bpf_mem_free(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(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; + + ret = unit_alloc(this_cpu_ptr(ma->cache)); + return !ret ? NULL : ret + LLIST_NODE_SZ; +} + +void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr) +{ + if (!ptr) + return; + + 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/mmap_unlock_work.h b/kernel/bpf/mmap_unlock_work.h new file mode 100644 index 000000000000..5d18d7d85bef --- /dev/null +++ b/kernel/bpf/mmap_unlock_work.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021 Facebook + */ + +#ifndef __MMAP_UNLOCK_WORK_H__ +#define __MMAP_UNLOCK_WORK_H__ +#include <linux/irq_work.h> + +/* irq_work to run mmap_read_unlock() in irq_work */ +struct mmap_unlock_irq_work { + struct irq_work irq_work; + struct mm_struct *mm; +}; + +DECLARE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +/* + * We cannot do mmap_read_unlock() when the irq is disabled, because of + * risk to deadlock with rq_lock. To look up vma when the irqs are + * disabled, we need to run mmap_read_unlock() in irq_work. We use a + * percpu variable to do the irq_work. If the irq_work is already used + * by another lookup, we fall over. + */ +static inline bool bpf_mmap_unlock_get_irq_work(struct mmap_unlock_irq_work **work_ptr) +{ + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = false; + + if (irqs_disabled()) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + work = this_cpu_ptr(&mmap_unlock_work); + if (irq_work_is_busy(&work->irq_work)) { + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } + } else { + /* + * PREEMPT_RT does not allow to trylock mmap sem in + * interrupt disabled context. Force the fallback code. + */ + irq_work_busy = true; + } + } + + *work_ptr = work; + return irq_work_busy; +} + +static inline void bpf_mmap_unlock_mm(struct mmap_unlock_irq_work *work, struct mm_struct *mm) +{ + if (!work) { + mmap_read_unlock(mm); + } else { + work->mm = mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); + irq_work_queue(&work->irq_work); + } +} + +#endif /* __MMAP_UNLOCK_WORK_H__ */ 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 310241ca7991..868cc2c43899 100644 --- a/kernel/bpf/net_namespace.c +++ b/kernel/bpf/net_namespace.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> +#include <linux/bpf-netns.h> #include <linux/filter.h> #include <net/net_namespace.h> @@ -25,6 +26,32 @@ struct bpf_netns_link { /* Protects updates to netns_bpf */ DEFINE_MUTEX(netns_bpf_mutex); +static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type) +{ + switch (type) { +#ifdef CONFIG_INET + case NETNS_BPF_SK_LOOKUP: + static_branch_dec(&bpf_sk_lookup_enabled); + break; +#endif + default: + break; + } +} + +static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type) +{ + switch (type) { +#ifdef CONFIG_INET + case NETNS_BPF_SK_LOOKUP: + static_branch_inc(&bpf_sk_lookup_enabled); + break; +#endif + default: + break; + } +} + /* Must be called with netns_bpf_mutex held. */ static void netns_bpf_run_array_detach(struct net *net, enum netns_bpf_attach_type type) @@ -36,12 +63,50 @@ static void netns_bpf_run_array_detach(struct net *net, bpf_prog_array_free(run_array); } +static int link_index(struct net *net, enum netns_bpf_attach_type type, + struct bpf_netns_link *link) +{ + struct bpf_netns_link *pos; + int i = 0; + + list_for_each_entry(pos, &net->bpf.links[type], node) { + if (pos == link) + return i; + i++; + } + return -ENOENT; +} + +static int link_count(struct net *net, enum netns_bpf_attach_type type) +{ + struct list_head *pos; + int i = 0; + + list_for_each(pos, &net->bpf.links[type]) + i++; + return i; +} + +static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type, + struct bpf_prog_array *prog_array) +{ + struct bpf_netns_link *pos; + unsigned int i = 0; + + list_for_each_entry(pos, &net->bpf.links[type], node) { + prog_array->items[i].prog = pos->link.prog; + i++; + } +} + static void bpf_netns_link_release(struct bpf_link *link) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; + struct bpf_prog_array *old_array, *new_array; struct net *net; + int cnt, idx; mutex_lock(&netns_bpf_mutex); @@ -53,13 +118,41 @@ static void bpf_netns_link_release(struct bpf_link *link) if (!net) goto out_unlock; - netns_bpf_run_array_detach(net, type); + /* Mark attach point as unused */ + netns_bpf_attach_type_unneed(type); + + /* Remember link position in case of safe delete */ + idx = link_index(net, type, net_link); list_del(&net_link->node); + cnt = link_count(net, type); + if (!cnt) { + netns_bpf_run_array_detach(net, type); + goto out_unlock; + } + + old_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL); + if (!new_array) { + WARN_ON(bpf_prog_array_delete_safe_at(old_array, idx)); + goto out_unlock; + } + fill_prog_array(net, type, new_array); + rcu_assign_pointer(net->bpf.run_array[type], new_array); + bpf_prog_array_free(old_array); + out_unlock: + net_link->net = NULL; mutex_unlock(&netns_bpf_mutex); } +static int bpf_netns_link_detach(struct bpf_link *link) +{ + bpf_netns_link_release(link); + return 0; +} + static void bpf_netns_link_dealloc(struct bpf_link *link) { struct bpf_netns_link *net_link = @@ -77,7 +170,7 @@ static int bpf_netns_link_update_prog(struct bpf_link *link, enum netns_bpf_attach_type type = net_link->netns_type; struct bpf_prog_array *run_array; struct net *net; - int ret = 0; + int idx, ret; if (old_prog && old_prog != link->prog) return -EPERM; @@ -95,7 +188,10 @@ static int bpf_netns_link_update_prog(struct bpf_link *link, run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); - WRITE_ONCE(run_array->items[0].prog, new_prog); + idx = link_index(net, type, net_link); + ret = bpf_prog_array_update_at(run_array, idx, new_prog); + if (ret) + goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); @@ -140,6 +236,7 @@ static void bpf_netns_link_show_fdinfo(const struct bpf_link *link, static const struct bpf_link_ops bpf_netns_link_ops = { .release = bpf_netns_link_release, .dealloc = bpf_netns_link_dealloc, + .detach = bpf_netns_link_detach, .update_prog = bpf_netns_link_update_prog, .fill_link_info = bpf_netns_link_fill_info, .show_fdinfo = bpf_netns_link_show_fdinfo, @@ -309,18 +406,30 @@ int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) return ret; } +static int netns_bpf_max_progs(enum netns_bpf_attach_type type) +{ + switch (type) { + case NETNS_BPF_FLOW_DISSECTOR: + return 1; + case NETNS_BPF_SK_LOOKUP: + return 64; + default: + return 0; + } +} + static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, enum netns_bpf_attach_type type) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); struct bpf_prog_array *run_array; - int err; + int cnt, err; mutex_lock(&netns_bpf_mutex); - /* Allow attaching only one prog or link for now */ - if (!list_empty(&net->bpf.links[type])) { + cnt = link_count(net, type); + if (cnt >= netns_bpf_max_progs(type)) { err = -E2BIG; goto out_unlock; } @@ -334,6 +443,9 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, case NETNS_BPF_FLOW_DISSECTOR: err = flow_dissector_bpf_prog_attach_check(net, link->prog); break; + case NETNS_BPF_SK_LOOKUP: + err = 0; /* nothing to check */ + break; default: err = -EINVAL; break; @@ -341,16 +453,22 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, if (err) goto out_unlock; - run_array = bpf_prog_array_alloc(1, GFP_KERNEL); + run_array = bpf_prog_array_alloc(cnt + 1, GFP_KERNEL); if (!run_array) { err = -ENOMEM; goto out_unlock; } - run_array->items[0].prog = link->prog; - rcu_assign_pointer(net->bpf.run_array[type], run_array); list_add_tail(&net_link->node, &net->bpf.links[type]); + fill_prog_array(net, type, run_array); + run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array, + lockdep_is_held(&netns_bpf_mutex)); + bpf_prog_array_free(run_array); + + /* Mark attach point as used */ + netns_bpf_attach_type_need(type); + out_unlock: mutex_unlock(&netns_bpf_mutex); return err; @@ -426,8 +544,10 @@ static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) mutex_lock(&netns_bpf_mutex); for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { netns_bpf_run_array_detach(net, type); - list_for_each_entry(net_link, &net->bpf.links[type], node) + list_for_each_entry(net_link, &net->bpf.links[type], node) { net_link->net = NULL; /* auto-detach link */ + netns_bpf_attach_type_unneed(type); + } if (net->bpf.progs[type]) bpf_prog_put(net->bpf.progs[type]); } diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index bd09290e3648..1a4fec330eaa 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -25,6 +25,7 @@ #include <linux/rhashtable.h> #include <linux/rtnetlink.h> #include <linux/rwsem.h> +#include <net/xdp.h> /* Protects offdevs, members of bpf_offload_netdev and offload members * of all progs. @@ -41,7 +42,7 @@ 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 +57,6 @@ 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 +72,227 @@ 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; @@ -209,27 +378,25 @@ 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); - - /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */ - bpf_prog_free_id(prog, true); - - 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) @@ -343,22 +510,6 @@ 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; @@ -372,7 +523,7 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) attr->map_type != BPF_MAP_TYPE_HASH) return ERR_PTR(-EINVAL); - offmap = kzalloc(sizeof(*offmap), GFP_USER); + offmap = bpf_map_area_alloc(sizeof(*offmap), NUMA_NO_NODE); if (!offmap) return ERR_PTR(-ENOMEM); @@ -404,19 +555,10 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) err_unlock: up_write(&bpf_devs_lock); rtnl_unlock(); - kfree(offmap); + 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); @@ -428,7 +570,13 @@ void bpf_map_offload_map_free(struct bpf_map *map) up_write(&bpf_devs_lock); rtnl_unlock(); - kfree(offmap); + 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) @@ -576,12 +724,28 @@ 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); @@ -595,32 +759,11 @@ 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); + err = __bpf_offload_dev_netdev_register(offdev, netdev); up_write(&bpf_devs_lock); - return 0; - -err_unlock_free: - up_write(&bpf_devs_lock); - kfree(ondev); return err; } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); @@ -628,43 +771,8 @@ 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); @@ -673,18 +781,6 @@ 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) @@ -710,3 +806,68 @@ 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 b367430e611c..034cf87b54e9 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -17,6 +17,8 @@ int pcpu_freelist_init(struct pcpu_freelist *s) raw_spin_lock_init(&head->lock); head->first = NULL; } + raw_spin_lock_init(&s->extralist.lock); + s->extralist.first = NULL; return 0; } @@ -29,7 +31,7 @@ static inline void pcpu_freelist_push_node(struct pcpu_freelist_head *head, struct pcpu_freelist_node *node) { node->next = head->first; - head->first = node; + WRITE_ONCE(head->first, node); } static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, @@ -40,12 +42,48 @@ static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, 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)) + return false; + + pcpu_freelist_push_node(&s->extralist, node); + raw_spin_unlock(&s->extralist.lock); + return true; +} + +static inline void ___pcpu_freelist_push_nmi(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + int cpu, orig_cpu; + + orig_cpu = raw_smp_processor_id(); + while (1) { + for_each_cpu_wrap(cpu, cpu_possible_mask, orig_cpu) { + struct pcpu_freelist_head *head; + + 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)) + return; + } +} + void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { - struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - - ___pcpu_freelist_push(head, 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, @@ -62,48 +100,92 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems) { struct pcpu_freelist_head *head; - int i, cpu, pcpu_entries; + unsigned int cpu, cpu_idx, i, j, n, m; - pcpu_entries = nr_elems / num_possible_cpus() + 1; - i = 0; + n = nr_elems / num_possible_cpus(); + m = nr_elems % num_possible_cpus(); + cpu_idx = 0; for_each_possible_cpu(cpu) { -again: head = per_cpu_ptr(s->freelist, cpu); - /* No locking required as this is not visible yet. */ - pcpu_freelist_push_node(head, buf); - i++; - buf += elem_size; - if (i == nr_elems) - break; - if (i % pcpu_entries) - goto again; + j = n + (cpu_idx < m ? 1 : 0); + for (i = 0; i < j; i++) { + /* No locking required as this is not visible yet. */ + pcpu_freelist_push_node(head, buf); + buf += elem_size; + } + cpu_idx++; } } -struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) +static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; - int orig_cpu, cpu; + int cpu; - orig_cpu = cpu = raw_smp_processor_id(); - while (1) { + 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); node = head->first; if (node) { - head->first = node->next; + WRITE_ONCE(head->first, node->next); raw_spin_unlock(&head->lock); return node; } raw_spin_unlock(&head->lock); - cpu = cpumask_next(cpu, cpu_possible_mask); - if (cpu >= nr_cpu_ids) - cpu = 0; - if (cpu == orig_cpu) - return NULL; } + + /* 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); } struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index fbf8a8a28979..3c76553cfe57 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -13,6 +13,7 @@ struct pcpu_freelist_head { struct pcpu_freelist { struct pcpu_freelist_head __percpu *freelist; + struct pcpu_freelist_head extralist; }; struct pcpu_freelist_node { diff --git a/kernel/bpf/preload/.gitignore b/kernel/bpf/preload/.gitignore new file mode 100644 index 000000000000..9452322902a5 --- /dev/null +++ b/kernel/bpf/preload/.gitignore @@ -0,0 +1,2 @@ +/libbpf +/bpf_preload_umd diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig new file mode 100644 index 000000000000..c9d45c9d6918 --- /dev/null +++ b/kernel/bpf/preload/Kconfig @@ -0,0 +1,26 @@ +# 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 + depends on BPF_SYSCALL + # 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 + useful in debugging and introspection of BPF programs and maps. + +if BPF_PRELOAD +config BPF_PRELOAD_UMD + tristate "bpf_preload kernel module" + default m + help + This builds bpf_preload kernel module with embedded BPF programs for + introspection in bpffs. +endif diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile new file mode 100644 index 000000000000..20f89cc0a0a6 --- /dev/null +++ b/kernel/bpf/preload/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +LIBBPF_INCLUDE = $(srctree)/tools/lib + +obj-$(CONFIG_BPF_PRELOAD_UMD) += bpf_preload.o +CFLAGS_bpf_preload_kern.o += -I$(LIBBPF_INCLUDE) +bpf_preload-objs += bpf_preload_kern.o diff --git a/kernel/bpf/preload/bpf_preload.h b/kernel/bpf/preload/bpf_preload.h new file mode 100644 index 000000000000..f065c91213a0 --- /dev/null +++ b/kernel/bpf/preload/bpf_preload.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_PRELOAD_H +#define _BPF_PRELOAD_H + +struct bpf_preload_info { + char link_name[16]; + struct bpf_link *link; +}; + +struct bpf_preload_ops { + int (*preload)(struct bpf_preload_info *); + struct module *owner; +}; +extern struct bpf_preload_ops *bpf_preload_ops; +#define BPF_PRELOAD_LINKS 2 +#endif diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c new file mode 100644 index 000000000000..0c63bc2cd895 --- /dev/null +++ b/kernel/bpf/preload/bpf_preload_kern.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/init.h> +#include <linux/module.h> +#include "bpf_preload.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; + +static void free_links_and_skel(void) +{ + if (!IS_ERR_OR_NULL(maps_link)) + bpf_link_put(maps_link); + if (!IS_ERR_OR_NULL(progs_link)) + bpf_link_put(progs_link); + iterators_bpf__destroy(skel); +} + +static int preload(struct bpf_preload_info *obj) +{ + strscpy(obj[0].link_name, "maps.debug", sizeof(obj[0].link_name)); + obj[0].link = maps_link; + strscpy(obj[1].link_name, "progs.debug", sizeof(obj[1].link_name)); + obj[1].link = progs_link; + return 0; +} + +static struct bpf_preload_ops ops = { + .preload = preload, + .owner = THIS_MODULE, +}; + +static int load_skel(void) +{ + int err; + + skel = iterators_bpf__open(); + if (!skel) + return -ENOMEM; + err = iterators_bpf__load(skel); + if (err) + goto out; + err = iterators_bpf__attach(skel); + if (err) + goto out; + maps_link = bpf_link_get_from_fd(skel->links.dump_bpf_map_fd); + if (IS_ERR(maps_link)) { + err = PTR_ERR(maps_link); + goto out; + } + progs_link = bpf_link_get_from_fd(skel->links.dump_bpf_prog_fd); + if (IS_ERR(progs_link)) { + err = PTR_ERR(progs_link); + goto out; + } + /* Avoid taking over stdin/stdout/stderr of init process. Zeroing out + * makes skel_closenz() a no-op later in iterators_bpf__destroy(). + */ + close_fd(skel->links.dump_bpf_map_fd); + skel->links.dump_bpf_map_fd = 0; + close_fd(skel->links.dump_bpf_prog_fd); + skel->links.dump_bpf_prog_fd = 0; + return 0; +out: + free_links_and_skel(); + return err; +} + +static int __init load(void) +{ + int err; + + err = load_skel(); + if (err) + return err; + bpf_preload_ops = &ops; + return err; +} + +static void __exit fini(void) +{ + bpf_preload_ops = NULL; + free_links_and_skel(); +} +late_initcall(load); +module_exit(fini); +MODULE_LICENSE("GPL"); diff --git a/kernel/bpf/preload/iterators/.gitignore b/kernel/bpf/preload/iterators/.gitignore new file mode 100644 index 000000000000..ffdb70230c8b --- /dev/null +++ b/kernel/bpf/preload/iterators/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +/.output diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile new file mode 100644 index 000000000000..b83c2f5e9be1 --- /dev/null +++ b/kernel/bpf/preload/iterators/Makefile @@ -0,0 +1,67 @@ +# SPDX-License-Identifier: GPL-2.0 +OUTPUT := .output +abs_out := $(abspath $(OUTPUT)) + +CLANG ?= clang +LLC ?= llc +LLVM_STRIP ?= llvm-strip + +TOOLS_PATH := $(abspath ../../../../tools) +BPFTOOL_SRC := $(TOOLS_PATH)/bpf/bpftool +BPFTOOL_OUTPUT := $(abs_out)/bpftool +DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)/bootstrap/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) + +LIBBPF_SRC := $(TOOLS_PATH)/lib/bpf +LIBBPF_OUTPUT := $(abs_out)/libbpf +LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include +BPFOBJ := $(LIBBPF_OUTPUT)/libbpf.a + +INCLUDES := -I$(OUTPUT) -I$(LIBBPF_INCLUDE) -I$(TOOLS_PATH)/include/uapi +CFLAGS := -g -Wall + +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +.DELETE_ON_ERROR: + +.PHONY: all clean + +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) + $(call msg,GEN-SKEL,$@) + $(Q)$(BPFTOOL) gen skeleton -L $< > $@ + +$(OUTPUT)/%/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) + $(call msg,BPF,$@) + $(Q)mkdir -p $(@D) + $(Q)$(CLANG) -g -O2 --target=bpf -m$* $(INCLUDES) \ + -c $(filter %.c,$^) -o $@ && \ + $(LLVM_STRIP) -g $@ + +$(OUTPUT) $(LIBBPF_OUTPUT) $(BPFTOOL_OUTPUT): + $(call msg,MKDIR,$@) + $(Q)mkdir -p $@ + +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ + OUTPUT=$(abspath $(dir $@))/ prefix= \ + DESTDIR=$(LIBBPF_DESTDIR) $(abspath $@) install_headers + +$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOL_SRC) OUTPUT=$(BPFTOOL_OUTPUT)/ bootstrap diff --git a/kernel/bpf/preload/iterators/README b/kernel/bpf/preload/iterators/README new file mode 100644 index 000000000000..98e7c90ea012 --- /dev/null +++ b/kernel/bpf/preload/iterators/README @@ -0,0 +1,7 @@ +WARNING: +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 new file mode 100644 index 000000000000..b78968b63fab --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.bpf.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record) +struct seq_file; +struct bpf_iter_meta { + struct seq_file *seq; + __u64 session_id; + __u64 seq_num; +}; + +struct bpf_map { + __u32 id; + char name[16]; + __u32 max_entries; +}; + +struct bpf_iter__bpf_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; +}; + +struct btf_type { + __u32 name_off; +}; + +struct btf_header { + __u32 str_len; +}; + +struct btf { + const char *strings; + struct btf_type **types; + struct btf_header hdr; +}; + +struct bpf_prog_aux { + __u32 id; + char name[16]; + const char *attach_func_name; + struct bpf_prog *dst_prog; + struct bpf_func_info *func_info; + struct btf *btf; +}; + +struct bpf_prog { + struct bpf_prog_aux *aux; +}; + +struct bpf_iter__bpf_prog { + struct bpf_iter_meta *meta; + struct bpf_prog *prog; +}; +#pragma clang attribute pop + +static const char *get_name(struct btf *btf, long btf_id, const char *fallback) +{ + struct btf_type **types, *t; + unsigned int name_off; + const char *str; + + if (!btf) + return fallback; + str = btf->strings; + types = btf->types; + bpf_probe_read_kernel(&t, sizeof(t), types + btf_id); + name_off = BPF_CORE_READ(t, name_off); + if (name_off >= btf->hdr.str_len) + return 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) +{ + struct seq_file *seq = ctx->meta->seq; + __u64 seq_num = ctx->meta->seq_num; + struct bpf_map *map = ctx->map; + + if (!map) + return 0; + + if (seq_num == 0) + 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)); + + return 0; +} + +SEC("iter/bpf_prog") +int dump_bpf_prog(struct bpf_iter__bpf_prog *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u64 seq_num = ctx->meta->seq_num; + struct bpf_prog *prog = ctx->prog; + struct bpf_prog_aux *aux; + + if (!prog) + return 0; + + aux = prog->aux; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " id name attached\n"); + + BPF_SEQ_PRINTF(seq, "%4u %-16s %s %s\n", aux->id, + get_name(aux->btf, aux->func_info[0].type_id, aux->name), + aux->attach_func_name, aux->dst_prog->aux->name); + return 0; +} +char LICENSE[] SEC("license") = "GPL"; 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..ebdc6c0cdb70 --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h @@ -0,0 +1,419 @@ +/* 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 = 6008; + 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\xeb\x9f\x01\0\ +\0\0\0\x18\0\0\0\0\0\0\x04\x1c\0\0\x04\x1c\0\0\x05\x18\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\xc2\x04\0\0\x03\0\0\0\x18\0\0\0\ +\xd0\0\0\0\x09\0\0\0\0\0\0\0\xd4\0\0\0\x0b\0\0\0\x40\0\0\0\xdf\0\0\0\x0b\0\0\0\ +\x80\0\0\0\0\x02\0\0\0\0\0\0\x0a\0\0\0\xe7\x07\0\0\0\0\0\0\0\0\0\0\xf0\x08\0\0\ +\0\0\0\0\x0c\0\0\0\xf6\x01\0\0\0\0\0\0\x08\0\0\0\x40\0\0\x01\xb3\x04\0\0\x03\0\ +\0\0\x18\0\0\x01\xbb\0\0\0\x0e\0\0\0\0\0\0\x01\xbe\0\0\0\x11\0\0\0\x20\0\0\x01\ +\xc3\0\0\0\x0e\0\0\0\xa0\0\0\x01\xcf\x08\0\0\0\0\0\0\x0f\0\0\x01\xd5\x01\0\0\0\ +\0\0\0\x04\0\0\0\x20\0\0\x01\xe2\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\xe7\x01\0\0\0\0\0\0\x04\0\0\ +\0\x20\0\0\0\0\x02\0\0\0\0\0\0\x14\0\0\x02\x4b\x04\0\0\x02\0\0\0\x10\0\0\0\x13\ +\0\0\0\x03\0\0\0\0\0\0\x02\x5e\0\0\0\x15\0\0\0\x40\0\0\0\0\x02\0\0\0\0\0\0\x18\ +\0\0\0\0\x0d\0\0\x01\0\0\0\x06\0\0\0\x1c\0\0\0\x13\0\0\x02\x63\x0c\0\0\x01\0\0\ +\0\x16\0\0\x02\xaf\x04\0\0\x01\0\0\0\x08\0\0\x02\xb8\0\0\0\x19\0\0\0\0\0\0\0\0\ +\x02\0\0\0\0\0\0\x1a\0\0\x03\x09\x04\0\0\x06\0\0\0\x38\0\0\x01\xbb\0\0\0\x0e\0\ +\0\0\0\0\0\x01\xbe\0\0\0\x11\0\0\0\x20\0\0\x03\x16\0\0\0\x1b\0\0\0\xc0\0\0\x03\ +\x27\0\0\0\x15\0\0\x01\0\0\0\x03\x30\0\0\0\x1d\0\0\x01\x40\0\0\x03\x3a\0\0\0\ +\x1e\0\0\x01\x80\0\0\0\0\x02\0\0\0\0\0\0\x1c\0\0\0\0\x0a\0\0\0\0\0\0\x10\0\0\0\ +\0\x02\0\0\0\0\0\0\x1f\0\0\0\0\x02\0\0\0\0\0\0\x20\0\0\x03\x84\x04\0\0\x02\0\0\ +\0\x08\0\0\x03\x92\0\0\0\x0e\0\0\0\0\0\0\x03\x9b\0\0\0\x0e\0\0\0\x20\0\0\x03\ +\x3a\x04\0\0\x03\0\0\0\x18\0\0\x03\xa5\0\0\0\x1b\0\0\0\0\0\0\x03\xad\0\0\0\x21\ +\0\0\0\x40\0\0\x03\xb3\0\0\0\x23\0\0\0\x80\0\0\0\0\x02\0\0\0\0\0\0\x22\0\0\0\0\ +\x02\0\0\0\0\0\0\x24\0\0\x03\xb7\x04\0\0\x01\0\0\0\x04\0\0\x03\xc2\0\0\0\x0e\0\ +\0\0\0\0\0\x04\x2b\x04\0\0\x01\0\0\0\x04\0\0\x04\x34\0\0\0\x0e\0\0\0\0\0\0\0\0\ +\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\x04\xaa\x0e\0\0\0\0\0\0\ +\x25\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\x04\ +\xbe\x0e\0\0\0\0\0\0\x27\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\ +\0\0\0\x20\0\0\x04\xd4\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\x1c\0\0\0\x12\0\0\0\x11\0\0\x04\xe9\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\x10\0\0\0\x12\0\0\0\x04\0\0\x05\0\x0e\0\0\0\0\0\0\x2d\ +\0\0\0\x01\0\0\x05\x08\x0f\0\0\x04\0\0\0\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\x05\x10\x0f\0\0\x01\0\0\0\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\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\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\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\0\0\0\x09\x4c\0\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\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\x2f\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\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\x1a\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\xe8\xbf\x16\0\0\ +\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb7\x30\0\0\0\0\0\x23\xb7\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\xe8\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\xf0\0\0\ +\0\0\x61\x17\0\x14\0\0\0\0\x7b\xa1\xff\xf8\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\ +\0\0\xff\xff\xff\xe8\xbf\x16\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\x23\ +\xb7\x30\0\0\0\0\0\x0e\xb7\x50\0\0\0\0\0\x18\x85\0\0\0\0\0\0\x7e\xb7\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\x9a\0\x01\x3c\ +\x1e\0\0\0\x01\0\0\0\x42\0\0\0\x9a\0\x01\x3c\x24\0\0\0\x02\0\0\0\x42\0\0\x01\ +\x0d\0\x01\x44\x1d\0\0\0\x03\0\0\0\x42\0\0\x01\x2e\0\x01\x4c\x06\0\0\0\x04\0\0\ +\0\x42\0\0\x01\x3d\0\x01\x40\x1d\0\0\0\x05\0\0\0\x42\0\0\x01\x62\0\x01\x58\x06\ +\0\0\0\x07\0\0\0\x42\0\0\x01\x75\0\x01\x5c\x03\0\0\0\x0e\0\0\0\x42\0\0\x01\xfb\ +\0\x01\x64\x02\0\0\0\x1e\0\0\0\x42\0\0\x02\x49\0\x01\x6c\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\x09\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\x01\x39\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\x09\0\0\0\0\0\0\0\xa0\0\0\0\x0d\ +\0\0\x01\x39\0\0\0\0\0\0\0\x1a\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\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\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\x31\xb7\x30\0\0\0\0\0\x20\xb7\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\ +\xb7\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\ +\xb7\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\x3d\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\x51\xb7\x30\0\0\0\0\0\x11\ +\xb7\x50\0\0\0\0\0\x20\x85\0\0\0\0\0\0\x7e\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x9a\0\x01\x80\x1e\0\0\0\x01\0\0\0\ +\x42\0\0\0\x9a\0\x01\x80\x24\0\0\0\x02\0\0\0\x42\0\0\x02\x7f\0\x01\x88\x1f\0\0\ +\0\x03\0\0\0\x42\0\0\x02\xa3\0\x01\x94\x06\0\0\0\x04\0\0\0\x42\0\0\x02\xbc\0\ +\x01\xa0\x0e\0\0\0\x05\0\0\0\x42\0\0\x01\x3d\0\x01\x84\x1d\0\0\0\x06\0\0\0\x42\ +\0\0\x01\x62\0\x01\xa4\x06\0\0\0\x08\0\0\0\x42\0\0\x02\xce\0\x01\xa8\x03\0\0\0\ +\x10\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x17\0\0\0\x42\0\0\x03\x79\0\x01\ +\x04\x06\0\0\0\x1a\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x1b\0\0\0\x42\0\0\ +\x03\xca\0\x01\x10\x0f\0\0\0\x1c\0\0\0\x42\0\0\x03\xdf\0\x01\x14\x2d\0\0\0\x1e\ +\0\0\0\x42\0\0\x04\x16\0\x01\x0c\x0d\0\0\0\x20\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\ +\x02\0\0\0\x21\0\0\0\x42\0\0\x03\xdf\0\x01\x14\x02\0\0\0\x24\0\0\0\x42\0\0\x04\ +\x3d\0\x01\x18\x0d\0\0\0\x27\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x28\0\0\ +\0\x42\0\0\x04\x3d\0\x01\x18\x0d\0\0\0\x2b\0\0\0\x42\0\0\x04\x3d\0\x01\x18\x0d\ +\0\0\0\x2c\0\0\0\x42\0\0\x04\x6b\0\x01\x1c\x1b\0\0\0\x2d\0\0\0\x42\0\0\x04\x6b\ +\0\x01\x1c\x06\0\0\0\x2e\0\0\0\x42\0\0\x04\x8e\0\x01\x24\x0d\0\0\0\x30\0\0\0\ +\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x3f\0\0\0\x42\0\0\x02\x49\0\x01\xc0\x01\0\ +\0\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\x01\x09\0\0\0\0\0\0\0\x20\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\ +\x28\0\0\0\x08\0\0\x01\x39\0\0\0\0\0\0\0\x80\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\ +\x90\0\0\0\x1a\0\0\x01\x09\0\0\0\0\0\0\0\xa8\0\0\0\x1a\0\0\x03\x71\0\0\0\0\0\0\ +\0\xb0\0\0\0\x1a\0\0\x03\x75\0\0\0\0\0\0\0\xc0\0\0\0\x1f\0\0\x03\xa3\0\0\0\0\0\ +\0\0\xd8\0\0\0\x20\0\0\x01\x09\0\0\0\0\0\0\0\xf0\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\ +\0\x01\x18\0\0\0\x24\0\0\0\x3e\0\0\0\0\0\0\x01\x50\0\0\0\x1a\0\0\x01\x09\0\0\0\ +\0\0\0\x01\x60\0\0\0\x20\0\0\x04\x65\0\0\0\0\0\0\x01\x88\0\0\0\x1a\0\0\x01\x39\ +\0\0\0\0\0\0\x01\x98\0\0\0\x1a\0\0\x04\xa6\0\0\0\0\0\0\x01\xa0\0\0\0\x18\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\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\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\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\x68\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\x64\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\x58\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\x50\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\x50\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\x0e\xa0\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\x0e\x7c\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\x0e\x70\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\ +\x0e\xb8\xb7\x20\0\0\0\0\0\x62\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\x28\x63\ +\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x20\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x0f\x30\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0e\xb8\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x38\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\x28\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\x48\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\x48\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\x50\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\ +\x11\x70\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x58\x18\x16\0\ +\0\0\0\0\0\0\0\0\0\0\0\x11\x68\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\ +\0\0\x10\x58\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xb0\x7b\x10\0\0\0\0\0\0\x18\ +\x06\0\0\0\0\0\0\0\0\0\0\0\0\x10\x60\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xc0\ +\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x10\xf0\x18\x16\0\0\0\0\0\ +\0\0\0\0\0\0\0\x11\xe0\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\x11\xd8\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\x11\x78\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\x11\x7c\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\x11\x80\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\x11\xa8\x63\x10\0\0\0\0\0\ +\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xf0\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\x11\x60\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\x11\x60\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\x11\xd0\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\x4a\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\x08\x18\x16\0\ +\0\0\0\0\0\0\0\0\0\0\0\x16\xe0\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\ +\0\0\x12\x10\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd8\x7b\x10\0\0\0\0\0\0\x18\ +\x06\0\0\0\0\0\0\0\0\0\0\0\0\x14\x18\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x20\ +\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x14\x20\x18\x16\0\0\0\0\0\ +\0\0\0\0\0\0\0\x17\x30\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x15\ +\xb0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x50\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\x48\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\x16\xe8\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\x16\xec\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\x16\xf0\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\ +\x18\x63\x10\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x60\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\xff\x13\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd0\ +\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\x16\xd0\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\x40\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\x01\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"; + 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/prog_iter.c b/kernel/bpf/prog_iter.c new file mode 100644 index 000000000000..53a73c841c13 --- /dev/null +++ b/kernel/bpf/prog_iter.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <linux/fs.h> +#include <linux/filter.h> +#include <linux/kernel.h> +#include <linux/btf_ids.h> + +struct bpf_iter_seq_prog_info { + u32 prog_id; +}; + +static void *bpf_prog_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_prog_info *info = seq->private; + struct bpf_prog *prog; + + prog = bpf_prog_get_curr_or_next(&info->prog_id); + if (!prog) + return NULL; + + if (*pos == 0) + ++*pos; + return prog; +} + +static void *bpf_prog_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_prog_info *info = seq->private; + + ++*pos; + ++info->prog_id; + bpf_prog_put((struct bpf_prog *)v); + return bpf_prog_get_curr_or_next(&info->prog_id); +} + +struct bpf_iter__bpf_prog { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_prog *, prog); +}; + +DEFINE_BPF_ITER_FUNC(bpf_prog, struct bpf_iter_meta *meta, struct bpf_prog *prog) + +static int __bpf_prog_seq_show(struct seq_file *seq, void *v, bool in_stop) +{ + struct bpf_iter__bpf_prog ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int ret = 0; + + ctx.meta = &meta; + ctx.prog = v; + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (prog) + ret = bpf_iter_run_prog(prog, &ctx); + + return ret; +} + +static int bpf_prog_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_prog_seq_show(seq, v, false); +} + +static void bpf_prog_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__bpf_prog_seq_show(seq, v, true); + else + bpf_prog_put((struct bpf_prog *)v); +} + +static const struct seq_operations bpf_prog_seq_ops = { + .start = bpf_prog_seq_start, + .next = bpf_prog_seq_next, + .stop = bpf_prog_seq_stop, + .show = bpf_prog_seq_show, +}; + +BTF_ID_LIST(btf_bpf_prog_id) +BTF_ID(struct, bpf_prog) + +static const struct bpf_iter_seq_info bpf_prog_seq_info = { + .seq_ops = &bpf_prog_seq_ops, + .init_seq_private = NULL, + .fini_seq_private = NULL, + .seq_priv_size = sizeof(struct bpf_iter_seq_prog_info), +}; + +static struct bpf_iter_reg bpf_prog_reg_info = { + .target = "bpf_prog", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__bpf_prog, prog), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &bpf_prog_seq_info, +}; + +static int __init bpf_prog_iter_init(void) +{ + bpf_prog_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_prog_id; + return bpf_iter_reg_target(&bpf_prog_reg_info); +} + +late_initcall(bpf_prog_iter_init); diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 05c8e043b9d2..d869f51ea93a 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -7,7 +7,7 @@ #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" #define QUEUE_STACK_CREATE_FLAG_MASK \ @@ -45,9 +45,6 @@ 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 || @@ -66,29 +63,19 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr) static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { - int ret, numa_node = bpf_map_attr_numa_node(attr); - struct bpf_map_memory mem = {0}; + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; - u64 size, queue_size, cost; + u64 size, queue_size; size = (u64) attr->max_entries + 1; - cost = queue_size = sizeof(*qs) + size * attr->value_size; - - ret = bpf_map_charge_init(&mem, cost); - if (ret < 0) - return ERR_PTR(ret); + queue_size = sizeof(*qs) + size * attr->value_size; qs = bpf_map_area_alloc(queue_size, numa_node); - if (!qs) { - bpf_map_charge_finish(&mem); + if (!qs) return ERR_PTR(-ENOMEM); - } - - memset(qs, 0, sizeof(*qs)); bpf_map_init_from_attr(&qs->map, attr); - bpf_map_charge_move(&qs->map.memory, &mem); qs->size = size; raw_spin_lock_init(&qs->lock); @@ -101,24 +88,22 @@ static void queue_stack_map_free(struct bpf_map *map) { struct bpf_queue_stack *qs = bpf_queue_stack(map); - /* 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 - * disconnected from events. Wait for outstanding critical sections in - * these programs to complete - */ - synchronize_rcu(); - 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 (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, flags); + } if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -140,7 +125,7 @@ out: } -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; @@ -148,7 +133,12 @@ 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 (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, flags); + } if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -172,32 +162,32 @@ out: } /* 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; @@ -213,7 +203,12 @@ 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 (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, irq_flags); + } if (queue_stack_map_is_full(qs)) { if (!replace) { @@ -243,14 +238,14 @@ 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; } @@ -262,7 +257,17 @@ 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, .map_alloc_check = queue_stack_map_alloc_check, .map_alloc = queue_stack_map_alloc, .map_free = queue_stack_map_free, @@ -273,9 +278,12 @@ 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], }; const struct bpf_map_ops stack_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = queue_stack_map_alloc_check, .map_alloc = queue_stack_map_alloc, .map_free = queue_stack_map_free, @@ -286,4 +294,6 @@ 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..37b80a23ae1a --- /dev/null +++ b/kernel/bpf/range_tree.c @@ -0,0 +1,270 @@ +// 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_mem_alloc.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 bpf_mem_alloc. + * + * 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 */ + migrate_disable(); + new_rn = bpf_mem_alloc(&bpf_global_ma, sizeof(struct range_node)); + migrate_enable(); + 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); + migrate_disable(); + bpf_mem_free(&bpf_global_ma, rn); + migrate_enable(); + } + } + 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); + migrate_disable(); + bpf_mem_free(&bpf_global_ma, right); + migrate_enable(); + } 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 { + migrate_disable(); + left = bpf_mem_alloc(&bpf_global_ma, sizeof(struct range_node)); + migrate_enable(); + 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); + bpf_mem_free(&bpf_global_ma, 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 cae9d505e04a..49b8e5a0c6b4 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -6,6 +6,7 @@ #include <linux/err.h> #include <linux/sock_diag.h> #include <net/sock_reuseport.h> +#include <linux/btf_ids.h> struct reuseport_array { struct bpf_map map; @@ -20,14 +21,11 @@ static struct reuseport_array *reuseport_array(struct bpf_map *map) /* The caller must hold the reuseport_lock */ void bpf_sk_reuseport_detach(struct sock *sk) { - uintptr_t sk_user_data; + struct sock __rcu **socks; write_lock_bh(&sk->sk_callback_lock); - sk_user_data = (uintptr_t)sk->sk_user_data; - if (sk_user_data & SK_USER_DATA_BPF) { - struct sock __rcu **socks; - - socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK); + socks = __locked_read_sk_user_data_with_flags(sk, SK_USER_DATA_BPF); + if (socks) { WRITE_ONCE(sk->sk_user_data, NULL); /* * Do not move this NULL assignment outside of @@ -61,7 +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; @@ -99,12 +97,10 @@ static void reuseport_array_free(struct bpf_map *map) struct sock *sk; u32 i; - synchronize_rcu(); - /* * ops->map_*_elem() will not be able to access this * array now. Hence, this function only races with - * bpf_sk_reuseport_detach() which was triggerred by + * bpf_sk_reuseport_detach() which was triggered by * close() or disconnect(). * * This function and bpf_sk_reuseport_detach() are @@ -145,38 +141,23 @@ static void reuseport_array_free(struct bpf_map *map) /* * Once reaching here, all sk->sk_user_data is not - * referenceing this "array". "array" can be freed now. + * referencing this "array". "array" can be freed now. */ bpf_map_area_free(array); } static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) { - int err, numa_node = bpf_map_attr_numa_node(attr); + int numa_node = bpf_map_attr_numa_node(attr); struct reuseport_array *array; - struct bpf_map_memory mem; - u64 array_size; - - if (!bpf_capable()) - return ERR_PTR(-EPERM); - - array_size = sizeof(*array); - array_size += (u64)attr->max_entries * sizeof(struct sock *); - - err = bpf_map_charge_init(&mem, array_size); - if (err) - return ERR_PTR(err); /* allocate all map elements and zero-initialize them */ - array = bpf_map_area_alloc(array_size, numa_node); - if (!array) { - bpf_map_charge_finish(&mem); + array = bpf_map_area_alloc(struct_size(array, ptrs, attr->max_entries), numa_node); + if (!array) return ERR_PTR(-ENOMEM); - } /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - bpf_map_charge_move(&array->map.memory, &mem); return &array->map; } @@ -193,7 +174,7 @@ int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, rcu_read_lock(); sk = reuseport_array_lookup_elem(map, key); if (sk) { - *(u64 *)value = sock_gen_cookie(sk); + *(u64 *)value = __sock_gen_cookie(sk); err = 0; } else { err = -ENOENT; @@ -327,7 +308,7 @@ put_file_unlock: spin_unlock_bh(&reuseport_lock); put_file: - fput(socket->file); + sockfd_put(socket); return err; } @@ -351,11 +332,22 @@ 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, .map_alloc_check = reuseport_array_alloc_check, .map_alloc = reuseport_array_alloc, .map_free = reuseport_array_free, .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 0af88bbc1c15..1499d8caa9a3 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -8,7 +8,9 @@ #include <linux/vmalloc.h> #include <linux/wait.h> #include <linux/poll.h> +#include <linux/kmemleak.h> #include <uapi/linux/btf.h> +#include <linux/btf_ids.h> #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) @@ -17,38 +19,64 @@ (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; - /* Consumer and producer counters are put into separate pages to allow - * mapping consumer page as r/w, but restrict producer page to r/o. - * This protects producer position from being modified by user-space - * application and ruining in-kernel position tracking. + raw_spinlock_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 + * done because the ring buffer must hold a lock across a BPF program's + * callback: + * + * __bpf_user_ringbuf_peek() // lock acquired + * -> program callback_fn() + * -> __bpf_user_ringbuf_sample_release() // lock released + * + * It is unsafe and incorrect to hold an IRQ spinlock across what could + * be a long execution window, so we instead simply disallow concurrent + * access to the ring buffer by kernel consumers, and return -EBUSY from + * __bpf_user_ringbuf_peek() if the busy bit is held by another task. + */ + atomic_t busy ____cacheline_aligned_in_smp; + /* Consumer and producer counters are put into separate pages to + * allow each position to be mapped with different permissions. + * 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. Note that the pending counter is placed in the same + * page as the producer, so that it shares the same cache line. + * + * Kernel-producer + * --------------- + * The producer position and data pages are mapped as r/o in + * userspace. For this approach, bits in the header of samples are + * used to signal to user-space, and to other producers, whether a + * sample is currently being written. + * + * User-space producer + * ------------------- + * Only the page containing the consumer position is mapped r/o in + * user-space. User-space producers also use bits of the header to + * communicate to the kernel, but the kernel must carefully check and + * validate each sample to ensure that they're correctly formatted, and + * fully contained within the ring buffer. */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); + unsigned long pending_pos; char data[] __aligned(PAGE_SIZE); }; struct bpf_ringbuf_map { struct bpf_map map; - struct bpf_map_memory memory; struct bpf_ringbuf *rb; }; @@ -60,9 +88,9 @@ struct bpf_ringbuf_hdr { static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { - const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | - __GFP_ZERO; - int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; + const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | + __GFP_NOWARN | __GFP_ZERO; + 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; @@ -88,10 +116,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) * user-space implementations significantly. */ array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); - if (array_size > PAGE_SIZE) - pages = vmalloc_node(array_size, numa_node); - else - pages = kmalloc_node(array_size, flags, numa_node); + pages = bpf_map_area_alloc(array_size, numa_node); if (!pages) return NULL; @@ -107,8 +132,9 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) } rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, - VM_ALLOC | VM_USERMAP, PAGE_KERNEL); + VM_MAP | VM_USERMAP, PAGE_KERNEL); if (rb) { + kmemleak_not_leak(pages); rb->pages = pages; rb->nr_pages = nr_pages; return rb; @@ -117,7 +143,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) err_free_pages: for (i = 0; i < nr_pages; i++) __free_page(pages[i]); - kvfree(pages); + bpf_map_area_free(pages); return NULL; } @@ -128,21 +154,34 @@ static void bpf_ringbuf_notify(struct irq_work *work) wake_up_all(&rb->waitq); } +/* 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) { struct bpf_ringbuf *rb; rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) - return ERR_PTR(-ENOMEM); + return NULL; - spin_lock_init(&rb->spinlock); + raw_spin_lock_init(&rb->spinlock); + atomic_set(&rb->busy, 0); init_waitqueue_head(&rb->waitq); init_irq_work(&rb->work, bpf_ringbuf_notify); rb->mask = data_sz - 1; rb->consumer_pos = 0; rb->producer_pos = 0; + rb->pending_pos = 0; return rb; } @@ -150,8 +189,6 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { struct bpf_ringbuf_map *rb_map; - u64 cost; - int err; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); @@ -161,38 +198,19 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) !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 = kzalloc(sizeof(*rb_map), GFP_USER); + 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); - cost = sizeof(struct bpf_ringbuf_map) + - sizeof(struct bpf_ringbuf) + - attr->max_entries; - err = bpf_map_charge_init(&rb_map->map.memory, cost); - if (err) - goto err_free_map; - rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); - if (IS_ERR(rb_map->rb)) { - err = PTR_ERR(rb_map->rb); - goto err_uncharge; + if (!rb_map->rb) { + bpf_map_area_free(rb_map); + return ERR_PTR(-ENOMEM); } return &rb_map->map; - -err_uncharge: - bpf_map_charge_finish(&rb_map->map.memory); -err_free_map: - kfree(rb_map); - return ERR_PTR(err); } static void bpf_ringbuf_free(struct bpf_ringbuf *rb) @@ -206,23 +224,16 @@ static void bpf_ringbuf_free(struct bpf_ringbuf *rb) vunmap(rb); for (i = 0; i < nr_pages; i++) __free_page(pages[i]); - kvfree(pages); + bpf_map_area_free(pages); } static void ringbuf_map_free(struct bpf_map *map) { struct bpf_ringbuf_map *rb_map; - /* 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 - * disconnected from events. Wait for outstanding critical sections in - * these programs to complete - */ - synchronize_rcu(); - rb_map = container_of(map, struct bpf_ringbuf_map, map); bpf_ringbuf_free(rb_map->rb); - kfree(rb_map); + bpf_map_area_free(rb_map); } static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) @@ -230,13 +241,13 @@ 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; } @@ -247,27 +258,38 @@ static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static size_t bpf_ringbuf_mmap_page_cnt(const struct bpf_ringbuf *rb) +static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma) { - size_t data_pages = (rb->mask + 1) >> PAGE_SHIFT; + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); - /* consumer page + producer page + 2 x data pages */ - return RINGBUF_POS_PAGES + 2 * data_pages; + if (vma->vm_flags & VM_WRITE) { + /* allow writable mapping for the consumer_pos only */ + if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EPERM; + } + /* remap_vmalloc_range() checks size and offset constraints */ + return remap_vmalloc_range(vma, rb_map->rb, + vma->vm_pgoff + RINGBUF_PGOFF); } -static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; - size_t mmap_sz; rb_map = container_of(map, struct bpf_ringbuf_map, map); - mmap_sz = bpf_ringbuf_mmap_page_cnt(rb_map->rb) << PAGE_SHIFT; - - if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > mmap_sz) - return -EINVAL; - return remap_vmalloc_range(vma, rb_map->rb, - vma->vm_pgoff + RINGBUF_PGOFF); + if (vma->vm_flags & VM_WRITE) { + if (vma->vm_pgoff == 0) + /* Disallow writable mappings to the consumer pointer, + * and allow writable mappings to both the producer + * position, and the ring buffer data itself. + */ + return -EPERM; + } + /* remap_vmalloc_range() checks size and offset constraints */ + return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) @@ -279,8 +301,13 @@ static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) return prod_pos - cons_pos; } -static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp, - struct poll_table_struct *pts) +static u32 ringbuf_total_data_sz(const struct bpf_ringbuf *rb) +{ + return rb->mask + 1; +} + +static __poll_t ringbuf_map_poll_kern(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts) { struct bpf_ringbuf_map *rb_map; @@ -292,15 +319,62 @@ static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp, return 0; } +static __poll_t ringbuf_map_poll_user(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts) +{ + struct bpf_ringbuf_map *rb_map; + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + poll_wait(filp, &rb_map->rb->waitq, pts); + + if (ringbuf_avail_data_sz(rb_map->rb) < ringbuf_total_data_sz(rb_map->rb)) + return EPOLLOUT | EPOLLWRNORM; + 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, .map_alloc = ringbuf_map_alloc, .map_free = ringbuf_map_free, - .map_mmap = ringbuf_map_mmap, - .map_poll = ringbuf_map_poll, + .map_mmap = ringbuf_map_mmap_kern, + .map_poll = ringbuf_map_poll_kern, .map_lookup_elem = ringbuf_map_lookup_elem, .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], +}; + +BTF_ID_LIST_SINGLE(user_ringbuf_map_btf_ids, struct, bpf_ringbuf_map) +const struct bpf_map_ops user_ringbuf_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = ringbuf_map_alloc, + .map_free = ringbuf_map_free, + .map_mmap = ringbuf_map_mmap_user, + .map_poll = ringbuf_map_poll_user, + .map_lookup_elem = ringbuf_map_lookup_elem, + .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], }; /* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself, @@ -329,31 +403,50 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) 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, flags; struct bpf_ringbuf_hdr *hdr; + u32 len, pg_off, tmp_size, hdr_len; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + if (len > ringbuf_total_data_sz(rb)) + return NULL; + cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { - if (!spin_trylock_irqsave(&rb->spinlock, flags)) + if (!raw_spin_trylock_irqsave(&rb->spinlock, flags)) return NULL; } else { - spin_lock_irqsave(&rb->spinlock, flags); + raw_spin_lock_irqsave(&rb->spinlock, flags); } + 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 + 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; + tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT; + tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8); + pend_pos += tmp_size; + } + rb->pending_pos = pend_pos; + + /* check for out of ringbuf space: + * - by ensuring producer position doesn't advance more than + * (ringbuf_size - 1) ahead + * - by ensuring oldest not yet committed record until newest + * record does not span more than (ringbuf_size - 1) */ - if (new_prod_pos - cons_pos > rb->mask) { - spin_unlock_irqrestore(&rb->spinlock, flags); + if (new_prod_pos - cons_pos > rb->mask || + new_prod_pos - pend_pos > rb->mask) { + raw_spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } @@ -365,7 +458,7 @@ 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_spin_unlock_irqrestore(&rb->spinlock, flags); return (void *)hdr + BPF_RINGBUF_HDR_SZ; } @@ -383,7 +476,7 @@ BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags) const struct bpf_func_proto bpf_ringbuf_reserve_proto = { .func = bpf_ringbuf_reserve, - .ret_type = RET_PTR_TO_ALLOC_MEM_OR_NULL, + .ret_type = RET_PTR_TO_RINGBUF_MEM_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, @@ -426,7 +519,7 @@ BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) const struct bpf_func_proto bpf_ringbuf_submit_proto = { .func = bpf_ringbuf_submit, .ret_type = RET_VOID, - .arg1_type = ARG_PTR_TO_ALLOC_MEM, + .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; @@ -439,7 +532,7 @@ BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) const struct bpf_func_proto bpf_ringbuf_discard_proto = { .func = bpf_ringbuf_discard, .ret_type = RET_VOID, - .arg1_type = ARG_PTR_TO_ALLOC_MEM, + .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; @@ -466,7 +559,7 @@ const struct bpf_func_proto bpf_ringbuf_output_proto = { .func = bpf_ringbuf_output, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -481,7 +574,7 @@ BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) case BPF_RB_AVAIL_DATA: return ringbuf_avail_data_sz(rb); case BPF_RB_RING_SIZE: - return rb->mask + 1; + return ringbuf_total_data_sz(rb); case BPF_RB_CONS_POS: return smp_load_acquire(&rb->consumer_pos); case BPF_RB_PROD_POS: @@ -497,3 +590,215 @@ const struct bpf_func_proto bpf_ringbuf_query_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; + +BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags, + struct bpf_dynptr_kern *, ptr) +{ + struct bpf_ringbuf_map *rb_map; + void *sample; + int err; + + if (unlikely(flags)) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + err = bpf_dynptr_check_size(size); + if (err) { + bpf_dynptr_set_null(ptr); + return err; + } + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + + sample = __bpf_ringbuf_reserve(rb_map->rb, size); + if (!sample) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { + .func = bpf_ringbuf_reserve_dynptr, + .ret_type = RET_INTEGER, + .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 | MEM_WRITE, +}; + +BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, false /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = { + .func = bpf_ringbuf_submit_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, true /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = { + .func = bpf_ringbuf_discard_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +static int __bpf_user_ringbuf_peek(struct bpf_ringbuf *rb, void **sample, u32 *size) +{ + int err; + u32 hdr_len, sample_len, total_len, flags, *hdr; + u64 cons_pos, prod_pos; + + /* Synchronizes with smp_store_release() in user-space producer. */ + prod_pos = smp_load_acquire(&rb->producer_pos); + if (prod_pos % 8) + return -EINVAL; + + /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_sample_release() */ + cons_pos = smp_load_acquire(&rb->consumer_pos); + if (cons_pos >= prod_pos) + return -ENODATA; + + hdr = (u32 *)((uintptr_t)rb->data + (uintptr_t)(cons_pos & rb->mask)); + /* Synchronizes with smp_store_release() in user-space producer. */ + hdr_len = smp_load_acquire(hdr); + flags = hdr_len & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT); + sample_len = hdr_len & ~flags; + total_len = round_up(sample_len + BPF_RINGBUF_HDR_SZ, 8); + + /* The sample must fit within the region advertised by the producer position. */ + if (total_len > prod_pos - cons_pos) + return -EINVAL; + + /* The sample must fit within the data region of the ring buffer. */ + if (total_len > ringbuf_total_data_sz(rb)) + return -E2BIG; + + /* The sample must fit into a struct bpf_dynptr. */ + err = bpf_dynptr_check_size(sample_len); + if (err) + return -E2BIG; + + if (flags & BPF_RINGBUF_DISCARD_BIT) { + /* If the discard bit is set, the sample should be skipped. + * + * Update the consumer pos, and return -EAGAIN so the caller + * knows to skip this sample and try to read the next one. + */ + smp_store_release(&rb->consumer_pos, cons_pos + total_len); + return -EAGAIN; + } + + if (flags & BPF_RINGBUF_BUSY_BIT) + return -ENODATA; + + *sample = (void *)((uintptr_t)rb->data + + (uintptr_t)((cons_pos + BPF_RINGBUF_HDR_SZ) & rb->mask)); + *size = sample_len; + return 0; +} + +static void __bpf_user_ringbuf_sample_release(struct bpf_ringbuf *rb, size_t size, u64 flags) +{ + u64 consumer_pos; + u32 rounded_size = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + + /* Using smp_load_acquire() is unnecessary here, as the busy-bit + * prevents another task from writing to consumer_pos after it was read + * by this task with smp_load_acquire() in __bpf_user_ringbuf_peek(). + */ + consumer_pos = rb->consumer_pos; + /* Synchronizes with smp_load_acquire() in user-space producer. */ + smp_store_release(&rb->consumer_pos, consumer_pos + rounded_size); +} + +BPF_CALL_4(bpf_user_ringbuf_drain, struct bpf_map *, map, + void *, callback_fn, void *, callback_ctx, u64, flags) +{ + struct bpf_ringbuf *rb; + long samples, discarded_samples = 0, ret = 0; + bpf_callback_t callback = (bpf_callback_t)callback_fn; + u64 wakeup_flags = BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP; + int busy = 0; + + if (unlikely(flags & ~wakeup_flags)) + return -EINVAL; + + rb = container_of(map, struct bpf_ringbuf_map, map)->rb; + + /* If another consumer is already consuming a sample, wait for them to finish. */ + if (!atomic_try_cmpxchg(&rb->busy, &busy, 1)) + return -EBUSY; + + for (samples = 0; samples < BPF_MAX_USER_RINGBUF_SAMPLES && ret == 0; samples++) { + int err; + u32 size; + void *sample; + struct bpf_dynptr_kern dynptr; + + err = __bpf_user_ringbuf_peek(rb, &sample, &size); + if (err) { + if (err == -ENODATA) { + break; + } else if (err == -EAGAIN) { + discarded_samples++; + continue; + } else { + ret = err; + goto schedule_work_return; + } + } + + bpf_dynptr_init(&dynptr, sample, BPF_DYNPTR_TYPE_LOCAL, 0, size); + ret = callback((uintptr_t)&dynptr, (uintptr_t)callback_ctx, 0, 0, 0); + __bpf_user_ringbuf_sample_release(rb, size, flags); + } + ret = samples - discarded_samples; + +schedule_work_return: + /* Prevent the clearing of the busy-bit from being reordered before the + * storing of any rb consumer or producer positions. + */ + atomic_set_release(&rb->busy, 0); + + if (flags & BPF_RB_FORCE_WAKEUP) + irq_work_queue(&rb->work); + else if (!(flags & BPF_RB_NO_WAKEUP) && samples > 0) + irq_work_queue(&rb->work); + return ret; +} + +const struct bpf_func_proto bpf_user_ringbuf_drain_proto = { + .func = bpf_user_ringbuf_drain, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_FUNC, + .arg3_type = ARG_PTR_TO_STACK_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 599488f25e40..3615c06b7dfa 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -4,12 +4,13 @@ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> +#include <linux/kernel.h> #include <linux/stacktrace.h> #include <linux/perf_event.h> -#include <linux/elf.h> -#include <linux/pagemap.h> -#include <linux/irq_work.h> +#include <linux/btf_ids.h> +#include <linux/buildid.h> #include "percpu_freelist.h" +#include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \ @@ -27,28 +28,9 @@ 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); }; -/* irq_work to run up_read() for build_id lookup in nmi context */ -struct stack_map_irq_work { - struct irq_work irq_work; - struct mm_struct *mm; -}; - -static void do_up_read(struct irq_work *entry) -{ - struct stack_map_irq_work *work; - - if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) - return; - - work = container_of(entry, struct stack_map_irq_work, irq_work); - mmap_read_unlock_non_owner(work->mm); -} - -static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work); - static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -62,7 +44,8 @@ static inline int stack_map_data_size(struct bpf_map *map) static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { - u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + u64 elem_size = sizeof(struct stack_map_bucket) + + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, @@ -88,13 +71,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; struct bpf_stack_map *smap; - struct bpf_map_memory mem; 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); @@ -112,281 +91,157 @@ 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 */ + /* 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); - cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); - err = bpf_map_charge_init(&mem, cost); - if (err) - return ERR_PTR(err); - smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); - if (!smap) { - bpf_map_charge_finish(&mem); + if (!smap) return ERR_PTR(-ENOMEM); - } bpf_map_init_from_attr(&smap->map, attr); - smap->map.value_size = value_size; smap->n_buckets = n_buckets; err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) - goto free_charge; + goto free_smap; err = prealloc_elems_and_freelist(smap); if (err) goto put_buffers; - bpf_map_charge_move(&smap->map.memory, &mem); - return &smap->map; put_buffers: put_callchain_buffers(); -free_charge: - bpf_map_charge_finish(&mem); +free_smap: bpf_map_area_free(smap); return ERR_PTR(err); } -#define BPF_BUILD_ID 3 -/* - * Parse build id from the note segment. This logic can be shared between - * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are - * identical. - */ -static inline int stack_map_parse_build_id(void *page_addr, - unsigned char *build_id, - void *note_start, - Elf32_Word note_size) -{ - Elf32_Word note_offs = 0, new_offs; - - /* check for overflow */ - if (note_start < page_addr || note_start + note_size < note_start) - return -EINVAL; - - /* only supports note that fits in the first page */ - if (note_start + note_size > page_addr + PAGE_SIZE) - return -EINVAL; - - while (note_offs + sizeof(Elf32_Nhdr) < note_size) { - Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs); - - if (nhdr->n_type == BPF_BUILD_ID && - nhdr->n_namesz == sizeof("GNU") && - nhdr->n_descsz > 0 && - nhdr->n_descsz <= BPF_BUILD_ID_SIZE) { - memcpy(build_id, - note_start + note_offs + - ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr), - nhdr->n_descsz); - memset(build_id + nhdr->n_descsz, 0, - BPF_BUILD_ID_SIZE - nhdr->n_descsz); - return 0; - } - new_offs = note_offs + sizeof(Elf32_Nhdr) + - ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4); - if (new_offs <= note_offs) /* overflow */ - break; - note_offs = new_offs; - } - return -EINVAL; -} - -/* Parse build ID from 32-bit ELF */ -static int stack_map_get_build_id_32(void *page_addr, - unsigned char *build_id) -{ - Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr; - Elf32_Phdr *phdr; - int i; - - /* only supports phdr that fits in one page */ - if (ehdr->e_phnum > - (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr)) - return -EINVAL; - - phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr)); - - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); - return -EINVAL; -} - -/* Parse build ID from 64-bit ELF */ -static int stack_map_get_build_id_64(void *page_addr, - unsigned char *build_id) -{ - Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr; - Elf64_Phdr *phdr; - int i; - - /* only supports phdr that fits in one page */ - if (ehdr->e_phnum > - (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr)) - return -EINVAL; - - phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr)); - - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); - return -EINVAL; -} - -/* Parse build ID of ELF file mapped to vma */ -static int stack_map_get_build_id(struct vm_area_struct *vma, - unsigned char *build_id) +static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault) { - Elf32_Ehdr *ehdr; - struct page *page; - void *page_addr; - int ret; - - /* only works for page backed storage */ - if (!vma->vm_file) - return -EINVAL; - - page = find_get_page(vma->vm_file->f_mapping, 0); - if (!page) - return -EFAULT; /* page not mapped */ - - ret = -EINVAL; - page_addr = kmap_atomic(page); - ehdr = (Elf32_Ehdr *)page_addr; - - /* compare magic x7f "ELF" */ - if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0) - goto out; - - /* only support executable file and shared object file */ - if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) - goto out; - - if (ehdr->e_ident[EI_CLASS] == ELFCLASS32) - ret = stack_map_get_build_id_32(page_addr, build_id); - else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64) - ret = stack_map_get_build_id_64(page_addr, build_id); -out: - kunmap_atomic(page_addr); - put_page(page); - return ret; + 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 vm_area_struct *vma; - bool irq_work_busy = false; - struct stack_map_irq_work *work = NULL; - - if (irqs_disabled()) { - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { - work = this_cpu_ptr(&up_read_work); - if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) { - /* cannot queue more up_read, fallback */ - irq_work_busy = true; - } - } else { - /* - * PREEMPT_RT does not allow to trylock mmap sem in - * interrupt disabled context. Force the fallback code. - */ - irq_work_busy = true; - } - } - - /* - * We cannot do up_read() when the irq is disabled, because of - * risk to deadlock with rq_lock. To do build_id lookup when the - * irqs are disabled, we need to run up_read() in irq_work. We use - * a percpu variable to do the irq_work. If the irq_work is - * already used by another lookup, we fall back to report ips. - * - * Same fallback is used for kernel stack (!user) on a stackmap - * with build_id. + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); + struct vm_area_struct *vma, *prev_vma = NULL; + const char *prev_build_id; + + /* If the irq_work is in use, fall back to report ips. Same + * fallback is used for kernel stack (!user) on a stackmap with + * build_id. */ if (!user || !current || !current->mm || irq_work_busy || - !mmap_read_trylock_non_owner(current->mm)) { + !mmap_read_trylock(current->mm)) { /* 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, BPF_BUILD_ID_SIZE); + memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); } return; } for (i = 0; i < trace_nr; i++) { - vma = find_vma(current->mm, ips[i]); - if (!vma || stack_map_get_build_id(vma, id_offs[i].build_id)) { + 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); + goto build_id_valid; + } + 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, BPF_BUILD_ID_SIZE); + memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); continue; } - id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i] - - vma->vm_start; +build_id_valid: + 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; } + bpf_mmap_unlock_mm(work, current->mm); +} - if (!work) { - mmap_read_unlock_non_owner(current->mm); - } else { - work->mm = current->mm; - irq_work_queue(&work->irq_work); +static struct perf_callchain_entry * +get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) +{ +#ifdef CONFIG_STACKTRACE + struct perf_callchain_entry *entry; + int rctx; + + entry = get_callchain_entry(&rctx); + + if (!entry) + return NULL; + + entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip, + max_depth, 0); + + /* stack_trace_save_tsk() works on unsigned long array, while + * perf_callchain_entry uses u64 array. For 32-bit systems, it is + * necessary to fix this mismatch. + */ + if (__BITS_PER_LONG != 64) { + unsigned long *from = (unsigned long *) entry->ip; + u64 *to = entry->ip; + int i; + + /* copy data from the end to avoid using extra buffer */ + for (i = entry->nr - 1; i >= 0; i--) + to[i] = (u64)(from[i]); } + + put_callchain_entry(rctx); + + return entry; +#else /* CONFIG_STACKTRACE */ + return NULL; +#endif } -BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, - u64, flags) +static long __bpf_get_stackid(struct bpf_map *map, + struct perf_callchain_entry *trace, u64 flags) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - struct perf_callchain_entry *trace; struct stack_map_bucket *bucket, *new_bucket, *old_bucket; - u32 max_depth = map->value_size / stack_map_data_size(map); - /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */ - u32 init_nr = sysctl_perf_event_max_stack - max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; - u32 hash, id, trace_nr, trace_len; + u32 hash, id, trace_nr, trace_len, i; bool user = flags & BPF_F_USER_STACK; - bool kernel = !user; u64 *ips; bool hash_matches; - if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | - BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) - return -EINVAL; - - trace = get_perf_callchain(regs, init_nr, kernel, user, - sysctl_perf_event_max_stack, false, false); - - if (unlikely(!trace)) - /* couldn't fetch the stack trace */ - return -EFAULT; - - /* get_perf_callchain() guarantees that trace->nr >= init_nr - * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth - */ - trace_nr = trace->nr - init_nr; - - if (trace_nr <= skip) + if (trace->nr <= skip) /* skipping more than usable stack trace */ return -EFAULT; - trace_nr -= skip; + trace_nr = trace->nr - skip; trace_len = trace_nr * sizeof(u64); - ips = trace->ip + skip + init_nr; + ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); bucket = READ_ONCE(smap->buckets[id]); @@ -397,15 +252,18 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, 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) { @@ -439,6 +297,33 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, return id; } +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; + bool user = flags & BPF_F_USER_STACK; + struct perf_callchain_entry *trace; + bool kernel = !user; + + 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); + + if (unlikely(!trace)) + /* couldn't fetch the stack trace */ + return -EFAULT; + + return __bpf_get_stackid(map, trace, flags); +} + const struct bpf_func_proto bpf_get_stackid_proto = { .func = bpf_get_stackid, .gpl_only = true, @@ -448,11 +333,82 @@ const struct bpf_func_proto bpf_get_stackid_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, - u64, flags) +static __u64 count_kernel_ip(struct perf_callchain_entry *trace) +{ + __u64 nr_kernel = 0; + + while (nr_kernel < trace->nr) { + if (trace->ip[nr_kernel] == PERF_CONTEXT_USER) + break; + nr_kernel++; + } + return nr_kernel; +} + +BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, + struct bpf_map *, map, u64, flags) { - u32 init_nr, trace_nr, copy_len, elem_size, num_elem; + struct perf_event *event = ctx->event; + struct perf_callchain_entry *trace; + bool kernel, user; + __u64 nr_kernel; + int ret; + + /* perf_sample_data doesn't have callchain, use bpf_get_stackid */ + if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) + return bpf_get_stackid((unsigned long)(ctx->regs), + (unsigned long) map, flags, 0, 0); + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) + return -EINVAL; + + user = flags & BPF_F_USER_STACK; + kernel = !user; + + trace = ctx->data->callchain; + if (unlikely(!trace)) + return -EFAULT; + + nr_kernel = count_kernel_ip(trace); + + 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; + + skip += nr_kernel; + if (skip > BPF_F_SKIP_FIELD_MASK) + return -EFAULT; + + flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; + ret = __bpf_get_stackid(map, trace, flags); + } + return ret; +} + +const struct bpf_func_proto bpf_get_stackid_proto_pe = { + .func = bpf_get_stackid_pe, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +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, bool may_fault) +{ + u32 trace_nr, copy_len, elem_size, num_elem, 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; @@ -466,33 +422,65 @@ BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, 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; + /* cannot get valid user stack for task without user_mode regs */ + if (task && user && !user_mode(regs)) + goto err_fault; + + /* 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; + } + num_elem = size / elem_size; - if (sysctl_perf_event_max_stack < num_elem) - init_nr = 0; + max_depth = num_elem + skip; + if (sysctl_perf_event_max_stack < max_depth) + max_depth = sysctl_perf_event_max_stack; + + if (may_fault) + rcu_read_lock(); /* need RCU for perf's callchain below */ + + if (trace_in) + trace = trace_in; + else if (kernel && task) + trace = get_callchain_entry_for_task(task, max_depth); else - init_nr = sysctl_perf_event_max_stack - num_elem; - trace = get_perf_callchain(regs, init_nr, kernel, user, - sysctl_perf_event_max_stack, false, false); - if (unlikely(!trace)) - goto err_fault; + trace = get_perf_callchain(regs, 0, kernel, user, max_depth, + crosstask, false); - trace_nr = trace->nr - init_nr; - if (trace_nr < skip) + if (unlikely(!trace) || trace->nr < skip) { + if (may_fault) + rcu_read_unlock(); goto err_fault; + } - trace_nr -= skip; + 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 + init_nr; - if (user && user_build_id) - stack_map_get_build_id_offset(buf, ips, trace_nr, user); - else + + ips = trace->ip + skip; + 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); @@ -505,6 +493,12 @@ clear: return err; } +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, false /* !may_fault */); +} + const struct bpf_func_proto bpf_get_stack_proto = { .func = bpf_get_stack, .gpl_only = true, @@ -515,6 +509,136 @@ const struct bpf_func_proto bpf_get_stack_proto = { .arg4_type = ARG_ANYTHING, }; +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; + + if (!try_get_task_stack(task)) + return -EFAULT; + + regs = task_pt_regs(task); + if (regs) + 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, + .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_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) +{ + struct pt_regs *regs = (struct pt_regs *)(ctx->regs); + struct perf_event *event = ctx->event; + struct perf_callchain_entry *trace; + bool kernel, user; + int err = -EINVAL; + __u64 nr_kernel; + + if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) + 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))) + goto clear; + + user = flags & BPF_F_USER_STACK; + kernel = !user; + + err = -EFAULT; + trace = ctx->data->callchain; + if (unlikely(!trace)) + goto clear; + + nr_kernel = count_kernel_ip(trace); + + if (kernel) { + __u64 nr = trace->nr; + + trace->nr = nr_kernel; + err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */); + + /* restore nr */ + trace->nr = nr; + } else { /* user */ + u64 skip = flags & BPF_F_SKIP_FIELD_MASK; + + skip += nr_kernel; + if (skip > BPF_F_SKIP_FIELD_MASK) + goto clear; + + flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; + err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */); + } + return err; + +clear: + memset(buf, 0, size); + return err; + +} + +const struct bpf_func_proto bpf_get_stack_proto_pe = { + .func = bpf_get_stack_pe, + .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, +}; + /* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) { @@ -574,14 +698,14 @@ 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; @@ -604,16 +728,28 @@ static void stack_map_free(struct bpf_map *map) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - /* wait for bpf programs to complete before freeing stack map */ - synchronize_rcu(); - bpf_map_area_free(smap->elems); pcpu_freelist_destroy(&smap->freelist); bpf_map_area_free(smap); 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, .map_alloc = stack_map_alloc, .map_free = stack_map_free, .map_get_next_key = stack_map_get_next_key, @@ -621,17 +757,6 @@ const struct bpf_map_ops stack_trace_map_ops = { .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], }; - -static int __init stack_map_init(void) -{ - int cpu; - struct stack_map_irq_work *work; - - for_each_possible_cpu(cpu) { - work = per_cpu_ptr(&up_read_work, cpu); - init_irq_work(&work->irq_work, do_up_read); - } - return 0; -} -subsys_initcall(stack_map_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0fd80ac81f70..e1e42e918ba7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2,8 +2,11 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> +#include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> +#include <linux/bpf_verifier.h> +#include <linux/bsearch.h> #include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> @@ -16,7 +19,6 @@ #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> -#include <linux/version.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> @@ -28,7 +30,16 @@ #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> +#include <linux/sort.h> #include <linux/bpf-netns.h> +#include <linux/rcupdate_trace.h> +#include <linux/memcontrol.h> +#include <linux/trace_events.h> +#include <linux/tracepoint.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 || \ @@ -48,7 +59,8 @@ static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); -int sysctl_unprivileged_bpf_disabled __read_mostly; +int sysctl_unprivileged_bpf_disabled __read_mostly = + IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) @@ -70,11 +82,10 @@ static const struct bpf_map_ops * const bpf_map_types[] = { * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ -int bpf_check_uarg_tail_zero(void __user *uaddr, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { - unsigned char __user *addr = uaddr + expected_size; int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ @@ -83,48 +94,41 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, if (actual_size <= expected_size) return 0; - res = check_zeroed_user(addr, actual_size - expected_size); + if (uaddr.is_kernel) + res = memchr_inv(uaddr.kernel + expected_size, 0, + actual_size - expected_size) == NULL; + else + res = check_zeroed_user(uaddr.user + expected_size, + actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { + .map_meta_equal = bpf_map_meta_equal, .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) +static void bpf_map_write_active_inc(struct bpf_map *map) { - const struct bpf_map_ops *ops; - u32 type = attr->map_type; - struct bpf_map *map; - int err; + atomic64_inc(&map->writecnt); +} - 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); +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} - 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; +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; } -static u32 bpf_map_value_size(struct bpf_map *map) +static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || @@ -139,30 +143,119 @@ static u32 bpf_map_value_size(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(); } -static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, - void *value, __u64 flags) +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, + void *key, void *value, __u64 flags) { 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_SOCKHASH || - map->map_type == BPF_MAP_TYPE_SOCKMAP || + 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 || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { + return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { - return bpf_fd_array_map_update_elem(map, f.file, key, value, + return bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } @@ -176,29 +269,30 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, 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, f.file, key, value, + 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, f.file, key, value, + 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, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + 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; } @@ -209,7 +303,7 @@ 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(); @@ -229,7 +323,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -251,18 +346,21 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); - /* mask lock, since value wasn't zero inited */ - check_and_init_map_lock(map, value); + /* mask lock and timer, since value wasn't zero inited */ + check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); return err; } +/* Please, do not use this function outside from the map creation path + * (e.g. in map update path) without taking care of setting the active + * memory cgroup (see at bpf_map_kmalloc_node() for example). + */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer @@ -275,7 +373,7 @@ 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_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO); unsigned int flags = 0; unsigned long align = 1; void *area; @@ -335,134 +433,438 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); + map->map_extra = attr->map_extra; } -static int bpf_charge_memlock(struct user_struct *user, u32 pages) +static int bpf_map_alloc_id(struct bpf_map *map) { - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + int id; - if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - return 0; + idr_preload(GFP_KERNEL); + spin_lock_bh(&map_idr_lock); + id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); + if (id > 0) + map->id = id; + spin_unlock_bh(&map_idr_lock); + idr_preload_end(); + + if (WARN_ON_ONCE(!id)) + return -ENOSPC; + + return id > 0 ? 0 : id; } -static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) +void bpf_map_free_id(struct bpf_map *map) { - if (user) - atomic_long_sub(pages, &user->locked_vm); + unsigned long flags; + + /* Offloaded maps are removed from the IDR store when their device + * disappears - even if someone holds an fd to them they are unusable, + * the memory is gone, all ops will fail; they are simply waiting for + * refcnt to drop to be freed. + */ + if (!map->id) + return; + + spin_lock_irqsave(&map_idr_lock, flags); + + idr_remove(&map_idr, map->id); + map->id = 0; + + spin_unlock_irqrestore(&map_idr_lock, flags); } -int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) +#ifdef CONFIG_MEMCG +static void bpf_map_save_memcg(struct bpf_map *map) { - u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; - struct user_struct *user; - int ret; + /* Currently if a map is created by a process belonging to the root + * memory cgroup, get_obj_cgroup_from_current() will return NULL. + * So we have to check map->objcg for being NULL each time it's + * being used. + */ + if (memcg_bpf_enabled()) + map->objcg = get_obj_cgroup_from_current(); +} - if (size >= U32_MAX - PAGE_SIZE) - return -E2BIG; +static void bpf_map_release_memcg(struct bpf_map *map) +{ + if (map->objcg) + obj_cgroup_put(map->objcg); +} - user = get_current_user(); - ret = bpf_charge_memlock(user, pages); - if (ret) { - free_uid(user); - return ret; - } +static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) +{ + if (map->objcg) + return get_mem_cgroup_from_objcg(map->objcg); - mem->pages = pages; - mem->user = user; + return root_mem_cgroup; +} - return 0; +void *bpf_map_kmalloc_node(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_node(size, flags | __GFP_ACCOUNT, node); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; } -void bpf_map_charge_finish(struct bpf_map_memory *mem) +void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { - bpf_uncharge_memlock(mem->user, mem->pages); - free_uid(mem->user); + struct mem_cgroup *memcg, *old_memcg; + void *ptr; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = kzalloc(size, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; } -void bpf_map_charge_move(struct bpf_map_memory *dst, - struct bpf_map_memory *src) +void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, + gfp_t flags) { - *dst = *src; + 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); - /* Make sure src will not be used for the redundant uncharging. */ - memset(src, 0, sizeof(struct bpf_map_memory)); + return ptr; } -int bpf_map_charge_memlock(struct bpf_map *map, u32 pages) +void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, + size_t align, gfp_t flags) { - int ret; + struct mem_cgroup *memcg, *old_memcg; + void __percpu *ptr; - ret = bpf_charge_memlock(map->memory.user, pages); - if (ret) - return ret; - map->memory.pages += pages; + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; +} + +#else +static void bpf_map_save_memcg(struct bpf_map *map) +{ +} + +static void bpf_map_release_memcg(struct bpf_map *map) +{ +} +#endif + +int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, 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 = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); + + if (pg) { + pages[i] = pg; + continue; + } + for (j = 0; j < i; j++) + __free_page(pages[j]); + ret = -ENOMEM; + break; + } + +#ifdef CONFIG_MEMCG + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); +#endif return ret; } -void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages) + +static int btf_field_cmp(const void *a, const void *b) { - bpf_uncharge_memlock(map->memory.user, pages); - map->memory.pages -= pages; + const struct btf_field *f1 = a, *f2 = b; + + if (f1->offset < f2->offset) + return -1; + else if (f1->offset > f2->offset) + return 1; + return 0; } -static int bpf_map_alloc_id(struct bpf_map *map) +struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, + u32 field_mask) { - int id; + struct btf_field *field; - idr_preload(GFP_KERNEL); - spin_lock_bh(&map_idr_lock); - id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); - if (id > 0) - map->id = id; - spin_unlock_bh(&map_idr_lock); - idr_preload_end(); + 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 & field_mask)) + return NULL; + return field; +} - if (WARN_ON_ONCE(!id)) - return -ENOSPC; +void btf_record_free(struct btf_record *rec) +{ + int i; - return id > 0 ? 0 : id; + if (IS_ERR_OR_NULL(rec)) + return; + for (i = 0; i < rec->cnt; i++) { + switch (rec->fields[i].type) { + 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); + 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: + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_TIMER: + case BPF_REFCOUNT: + case BPF_WORKQUEUE: + /* Nothing to release */ + break; + default: + WARN_ON_ONCE(1); + continue; + } + } + kfree(rec); } -void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +void bpf_map_free_record(struct bpf_map *map) { - unsigned long flags; + btf_record_free(map->record); + map->record = NULL; +} - /* Offloaded maps are removed from the IDR store when their device - * disappears - even if someone holds an fd to them they are unusable, - * the memory is gone, all ops will fail; they are simply waiting for - * refcnt to drop to be freed. +struct btf_record *btf_record_dup(const struct btf_record *rec) +{ + const struct btf_field *fields; + struct btf_record *new_rec; + int ret, size, i; + + if (IS_ERR_OR_NULL(rec)) + return NULL; + size = offsetof(struct btf_record, fields[rec->cnt]); + new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); + if (!new_rec) + return ERR_PTR(-ENOMEM); + /* Do a deep copy of the btf_record */ + fields = rec->fields; + new_rec->cnt = 0; + for (i = 0; i < rec->cnt; i++) { + switch (fields[i].type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + 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; + } + break; + case BPF_LIST_HEAD: + case BPF_LIST_NODE: + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_TIMER: + case BPF_REFCOUNT: + case BPF_WORKQUEUE: + /* Nothing to acquire */ + break; + default: + ret = -EFAULT; + WARN_ON_ONCE(1); + goto free; + } + new_rec->cnt++; + } + return new_rec; +free: + btf_record_free(new_rec); + return ERR_PTR(ret); +} + +bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b) +{ + bool a_has_fields = !IS_ERR_OR_NULL(rec_a), b_has_fields = !IS_ERR_OR_NULL(rec_b); + int size; + + if (!a_has_fields && !b_has_fields) + return true; + if (a_has_fields != b_has_fields) + return false; + if (rec_a->cnt != rec_b->cnt) + return false; + size = offsetof(struct btf_record, 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. + * + * While spin_lock, timer, and kptr have no relation to map BTF, + * list_head metadata is specific to map BTF, the btf and value_rec + * members in particular. btf is the map BTF, while value_rec points to + * btf_record in that map BTF. + * + * So while by default, we don't rely on the map BTF (which the records + * were parsed from) matching for both records, which is not backwards + * compatible, in case list_head is part of it, we implicitly rely on + * that by way of depending on memcmp succeeding for it. */ - if (!map->id) + return !memcmp(rec_a, rec_b, size); +} + +void bpf_obj_free_timer(const struct btf_record *rec, void *obj) +{ + if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TIMER))) return; + bpf_timer_cancel_and_free(obj + rec->timer_off); +} - if (do_idr_lock) - spin_lock_irqsave(&map_idr_lock, flags); - else - __acquire(&map_idr_lock); +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); +} - idr_remove(&map_idr, map->id); - map->id = 0; +void bpf_obj_free_fields(const struct btf_record *rec, void *obj) +{ + const struct btf_field *fields; + int i; - if (do_idr_lock) - spin_unlock_irqrestore(&map_idr_lock, flags); - else - __release(&map_idr_lock); + if (IS_ERR_OR_NULL(rec)) + 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: + 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_KPTR_UNREF: + WRITE_ONCE(*(u64 *)field_ptr, 0); + break; + case BPF_KPTR_REF: + 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); + continue; + } + } +} + +static void bpf_map_free(struct bpf_map *map) +{ + struct btf_record *rec = map->record; + struct btf *btf = map->btf; + + /* implementation dependent freeing. Disabling migration to simplify + * the free of values or special fields allocated from bpf memory + * allocator. + */ + migrate_disable(); + map->ops->map_free(map); + 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. + * + * Note that the btf_record stashed in map->inner_map_meta->record was + * already freed using the map_free callback for map in map case which + * eventually calls bpf_map_free_meta, since inner_map_meta is only a + * template bpf_map struct used during verification. + */ + 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); - struct bpf_map_memory mem; - bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); - /* implementation dependent freeing */ - map->ops->map_free(map); - bpf_map_charge_finish(&mem); + bpf_map_release_memcg(map); + bpf_map_free(map); } static void bpf_map_put_uref(struct bpf_map *map) @@ -473,23 +875,45 @@ 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_unbound_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); - schedule_work(&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); @@ -512,7 +936,7 @@ 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. @@ -523,16 +947,22 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) } #ifdef CONFIG_PROC_FS +/* Show the memory usage of a bpf map */ +static u64 bpf_map_memory_usage(const struct bpf_map *map) +{ + return map->ops->map_mem_usage(map); +} + static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { - const struct bpf_map *map = filp->private_data; - const struct bpf_array *array; + struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; - if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { - array = container_of(map, struct bpf_array, map); - type = array->aux->type; - jited = array->aux->jited; + if (map_type_contains_progs(map)) { + spin_lock(&map->owner.lock); + type = map->owner.type; + jited = map->owner.jited; + spin_unlock(&map->owner.lock); } seq_printf(m, @@ -541,6 +971,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" + "map_extra:\t%#llx\n" "memlock:\t%llu\n" "map_id:\t%u\n" "frozen:\t%u\n", @@ -549,7 +980,8 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, - map->memory.pages * 1ULL << PAGE_SHIFT, + (unsigned long long)map->map_extra, + bpf_map_memory_usage(map), map->id, READ_ONCE(map->frozen)); if (type) { @@ -582,11 +1014,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -594,11 +1023,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -609,9 +1035,9 @@ 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 || map_value_has_spin_lock(map)) + if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -633,24 +1059,33 @@ 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) - map->writecnt++; -out: - mutex_unlock(&map->freeze_mutex); return err; } @@ -664,6 +1099,21 @@ 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(current->mm, 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, @@ -673,6 +1123,7 @@ 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) @@ -738,8 +1189,8 @@ 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; @@ -760,38 +1211,118 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!value_type || value_size != map->value_size) return -EINVAL; - map->spin_lock_off = btf_find_spin_lock(btf, value_type); - - if (map_value_has_spin_lock(map)) { - if (map->map_flags & BPF_F_RDONLY_PROG) - return -EACCES; - if (map->map_type != BPF_MAP_TYPE_HASH && - map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && - map->map_type != BPF_MAP_TYPE_SK_STORAGE) - return -ENOTSUPP; - if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > - map->value_size) { - WARN_ONCE(1, - "verifier bug spin_lock_off %d value_size %d\n", - map->spin_lock_off, map->value_size); - return -EFAULT; + map->record = btf_parse_fields(btf, value_type, + BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | + BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR, + map->value_size); + if (!IS_ERR_OR_NULL(map->record)) { + int i; + + if (!bpf_token_capable(token, CAP_BPF)) { + ret = -EPERM; + goto free_map_tab; + } + if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { + ret = -EACCES; + goto free_map_tab; + } + for (i = 0; i < sizeof(map->record->field_mask) * 8; i++) { + switch (map->record->field_mask & (1 << i)) { + case 0: + continue; + case BPF_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 && + 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_TIMER: + case BPF_WORKQUEUE: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + 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_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) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; + default: + /* Fail if map_type checks are missing for a field type */ + ret = -EOPNOTSUPP; + goto free_map_tab; + } } } - if (map->ops->map_check_btf) + ret = btf_check_and_fixup_fields(btf, map->record); + if (ret < 0) + goto free_map_tab; + + if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); + if (ret < 0) + goto free_map_tab; + } return ret; +free_map_tab: + bpf_map_free_record(map); + return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +static bool bpf_net_capable(void) +{ + return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); +} + +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { + const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); - struct bpf_map_memory mem; + u32 map_type = attr->map_type; struct bpf_map *map; + bool token_flag; int f_flags; int err; @@ -799,6 +1330,12 @@ 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) @@ -807,6 +1344,11 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_type != BPF_MAP_TYPE_ARENA && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -817,9 +1359,106 @@ 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: + 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)); @@ -829,8 +1468,8 @@ static int map_create(union bpf_attr *attr) atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); + spin_lock_init(&map->owner.lock); - map->spin_lock_off = -EINVAL; if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with @@ -846,10 +1485,15 @@ static int map_create(union bpf_attr *attr) err = PTR_ERR(btf); goto free_map; } + if (btf_is_kernel(btf)) { + btf_put(btf); + err = -EACCES; + goto free_map; + } 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; @@ -861,14 +1505,17 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = security_bpf_map_create(map, attr, token); if (err) - goto free_map; + 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) { /* failed to allocate fd. @@ -886,28 +1533,12 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); free_map: - btf_put(map->btf); - bpf_map_charge_move(&mem, &map->memory); - map->ops->map_free(map); - bpf_map_charge_finish(&mem); + 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); @@ -923,36 +1554,31 @@ 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; + CLASS(fd, f)(ufd); + struct bpf_map *map = __bpf_map_get(f); - map = __bpf_map_get(f); - if (IS_ERR(map)) - return map; - - bpf_map_inc(map); - fdput(f); + if (!IS_ERR(map)) + bpf_map_inc(map); return map; } +EXPORT_SYMBOL(bpf_map_get); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { - struct fd f = fdget(ufd); - struct bpf_map *map; + CLASS(fd, f)(ufd); + struct bpf_map *map = __bpf_map_get(f); - map = __bpf_map_get(f); - if (IS_ERR(map)) - return map; - - 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; @@ -983,7 +1609,7 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) - return memdup_user(ukey, key_size); + return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); @@ -991,6 +1617,17 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size) return NULL; } +static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) +{ + if (key_size) + return kvmemdup_bpfptr(ukey, key_size); + + if (!bpfptr_is_null(ukey)) + return ERR_PTR(-EINVAL); + + return NULL; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags @@ -998,11 +1635,9 @@ 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)) @@ -1011,34 +1646,36 @@ static int map_lookup_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); - 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) && - !map_value_has_spin_lock(map)) { - err = -EINVAL; - goto err_put; - } + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) + return -EINVAL; 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); err = -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -1050,110 +1687,97 @@ static int map_lookup_elem(union bpf_attr *attr) err = 0; free_value: - kfree(value); + kvfree(value); free_key: - kfree(key); -err_put: - fdput(f); + kvfree(key); return err; } #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags -static int map_update_elem(union bpf_attr *attr) +static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { - void __user *ukey = u64_to_user_ptr(attr->key); - void __user *uvalue = u64_to_user_ptr(attr->value); - int ufd = attr->map_fd; + bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); + bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); 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); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if ((attr->flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } - key = __bpf_copy_key(ukey, map->key_size); + key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || - map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) - value_size = round_up(map->value_size, 8) * num_possible_cpus(); - else - value_size = map->value_size; - - err = -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); - if (!value) + value_size = bpf_map_value_size(map); + value = kvmemdup_bpfptr(uvalue, value_size); + if (IS_ERR(value)) { + err = PTR_ERR(value); goto free_key; + } - err = -EFAULT; - if (copy_from_user(value, uvalue, value_size) != 0) - goto free_value; - - err = bpf_map_update_value(map, f, key, value, attr->flags); + err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags); + if (!err) + maybe_wait_bpf_programs(map); -free_value: - kfree(value); + kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: - fdput(f); + bpf_map_write_active_dec(map); return err; } #define BPF_MAP_DELETE_ELEM_LAST_FIELD key -static int map_delete_elem(union bpf_attr *attr) +static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { - void __user *ukey = u64_to_user_ptr(attr->key); - int ufd = attr->map_fd; + bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); 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); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } - key = __bpf_copy_key(ukey, map->key_size); + key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); 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) || @@ -1168,11 +1792,12 @@ static int map_delete_elem(union bpf_attr *attr) 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: - kfree(key); + kvfree(key); err_put: - fdput(f); + bpf_map_write_active_dec(map); return err; } @@ -1183,40 +1808,34 @@ 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; } err = -ENOMEM; - next_key = kmalloc(map->key_size, GFP_USER); + next_key = kvmalloc(map->key_size, GFP_USER); 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; } @@ -1235,11 +1854,9 @@ out: err = 0; free_next_key: - kfree(next_key); + kvfree(next_key); free_key: - kfree(key); -err_put: - fdput(f); + kvfree(key); return err; } @@ -1256,7 +1873,7 @@ int generic_map_delete_batch(struct bpf_map *map, return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } @@ -1264,7 +1881,10 @@ int generic_map_delete_batch(struct bpf_map *map, if (!max_count) return 0; - key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1274,7 +1894,7 @@ 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; } @@ -1284,35 +1904,33 @@ int generic_map_delete_batch(struct bpf_map *map, err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; - kfree(key); + kvfree(key); + return err; } -int generic_map_update_batch(struct bpf_map *map, +int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; - int ufd = attr->map_fd; void *key, *value; - struct fd f; int err = 0; - f = fdget(ufd); if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } @@ -1322,13 +1940,16 @@ int generic_map_update_batch(struct bpf_map *map, if (!max_count) return 0; - key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { - kfree(key); + kvfree(key); return -ENOMEM; } @@ -1339,23 +1960,23 @@ int generic_map_update_batch(struct bpf_map *map, copy_from_user(value, values + cp * value_size, value_size)) break; - err = bpf_map_update_value(map, f, key, value, + err = bpf_map_update_value(map, map_file, key, value, attr->batch.elem_flags); if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; - kfree(value); - kfree(key); + 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) @@ -1365,14 +1986,14 @@ 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) && - !map_value_has_spin_lock(map)) + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; value_size = bpf_map_value_size(map); @@ -1384,13 +2005,13 @@ int generic_map_lookup_batch(struct bpf_map *map, if (put_user(0, &uattr->batch.count)) return -EFAULT; - buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; - buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); + buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { - kfree(buf_prevkey); + kvfree(buf_prevkey); return -ENOMEM; } @@ -1412,14 +2033,8 @@ 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; @@ -1434,12 +2049,13 @@ 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(); } if (err == -EFAULT) @@ -1450,55 +2066,80 @@ int generic_map_lookup_batch(struct bpf_map *map, err = -EFAULT; free_buf: - kfree(buf_prevkey); - kfree(buf); + kvfree(buf_prevkey); + kvfree(buf); return err; } -#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags 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)) return -EINVAL; - f = fdget(ufd); + if (attr->flags & ~BPF_F_LOCK) + return -EINVAL; + + CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } + if (attr->flags && + (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK)) { + err = -EINVAL; + goto err_put; + } + + if ((attr->flags & BPF_F_LOCK) && + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } - value_size = map->value_size; + value_size = bpf_map_value_size(map); err = -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; + err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); - } else { - err = -ENOTSUPP; + } 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_offloaded(map)) { + bpf_disable_instrumentation(); + rcu_read_lock(); + err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); + rcu_read_unlock(); + bpf_enable_instrumentation(); + } } if (err) @@ -1512,11 +2153,11 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) err = 0; free_value: - kfree(value); + kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: - fdput(f); + bpf_map_write_active_dec(map); return err; } @@ -1524,26 +2165,25 @@ 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) { - fdput(f); + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; - } - mutex_lock(&map->freeze_mutex); + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) + return -EPERM; - if (map->writecnt) { + mutex_lock(&map->freeze_mutex); + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -1551,15 +2191,10 @@ 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; } @@ -1585,7 +2220,7 @@ 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; @@ -1613,7 +2248,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) return; if (audit_enabled == AUDIT_OFF) return; - if (op == BPF_AUDIT_LOAD) + if (!in_irq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) @@ -1623,51 +2258,6 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) audit_log_end(ab); } -int __bpf_prog_charge(struct user_struct *user, u32 pages) -{ - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - unsigned long user_bufs; - - if (user) { - user_bufs = atomic_long_add_return(pages, &user->locked_vm); - if (user_bufs > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - } - - return 0; -} - -void __bpf_prog_uncharge(struct user_struct *user, u32 pages) -{ - if (user) - atomic_long_sub(pages, &user->locked_vm); -} - -static int bpf_prog_charge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = get_current_user(); - int ret; - - ret = __bpf_prog_charge(user, prog->pages); - if (ret) { - free_uid(user); - return ret; - } - - prog->aux->user = user; - return 0; -} - -static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = prog->aux->user; - - __bpf_prog_uncharge(user, prog->pages); - free_uid(user); -} - static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; @@ -1687,8 +2277,10 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog) return id > 0 ? 0 : id; } -void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) +void bpf_prog_free_id(struct bpf_prog *prog) { + unsigned long flags; + /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, @@ -1697,18 +2289,10 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) if (!prog->aux->id) return; - if (do_idr_lock) - spin_lock_bh(&prog_idr_lock); - else - __acquire(&prog_idr_lock); - + spin_lock_irqsave(&prog_idr_lock, flags); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; - - if (do_idr_lock) - spin_unlock_bh(&prog_idr_lock); - else - __release(&prog_idr_lock); + spin_unlock_irqrestore(&prog_idr_lock, flags); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) @@ -1717,8 +2301,8 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); - bpf_prog_uncharge_memlock(aux->prog); - security_bpf_prog_free(aux); + free_uid(aux->user); + security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } @@ -1726,28 +2310,53 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); - bpf_prog_free_linfo(prog); - - if (deferred) - call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); - else + module_put(prog->aux->mod); + kvfree(prog->aux->jited_linfo); + kvfree(prog->aux->linfo); + kfree(prog->aux->kfunc_tab); + if (prog->aux->attach_btf) + btf_put(prog->aux->attach_btf); + + if (deferred) { + if (prog->sleepable) + call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); + else + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); + } else { __bpf_prog_put_rcu(&prog->aux->rcu); + } +} + +static void bpf_prog_put_deferred(struct work_struct *work) +{ + struct bpf_prog_aux *aux; + struct bpf_prog *prog; + + aux = container_of(work, struct bpf_prog_aux, work); + prog = aux->prog; + perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); + bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); + bpf_prog_free_id(prog); + __bpf_prog_put_noref(prog, true); } -static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) +static void __bpf_prog_put(struct bpf_prog *prog) { - if (atomic64_dec_and_test(&prog->aux->refcnt)) { - perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); - bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); - /* bpf_prog_free_id() must be called first */ - bpf_prog_free_id(prog, do_idr_lock); - __bpf_prog_put_noref(prog, true); + struct bpf_prog_aux *aux = prog->aux; + + if (atomic64_dec_and_test(&aux->refcnt)) { + if (in_irq() || irqs_disabled()) { + INIT_WORK(&aux->work, bpf_prog_put_deferred); + schedule_work(&aux->work); + } else { + bpf_prog_put_deferred(&aux->work); + } } } void bpf_prog_put(struct bpf_prog *prog) { - __bpf_prog_put(prog, true); + __bpf_prog_put(prog); } EXPORT_SYMBOL_GPL(bpf_prog_put); @@ -1759,28 +2368,48 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) return 0; } +struct bpf_prog_kstats { + u64 nsecs; + u64 cnt; + u64 misses; +}; + +void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) +{ + struct bpf_prog_stats *stats; + unsigned int flags; + + stats = this_cpu_ptr(prog->stats); + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->misses); + u64_stats_update_end_irqrestore(&stats->syncp, flags); +} + static void bpf_prog_get_stats(const struct bpf_prog *prog, - struct bpf_prog_stats *stats) + struct bpf_prog_kstats *stats) { - u64 nsecs = 0, cnt = 0; + u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; - u64 tnsecs, tcnt; + u64 tnsecs, tcnt, tmisses; - st = per_cpu_ptr(prog->aux->stats, cpu); + st = per_cpu_ptr(prog->stats, cpu); do { - start = u64_stats_fetch_begin_irq(&st->syncp); - tnsecs = st->nsecs; - tcnt = st->cnt; - } while (u64_stats_fetch_retry_irq(&st->syncp, start)); + start = u64_stats_fetch_begin(&st->syncp); + tnsecs = u64_stats_read(&st->nsecs); + tcnt = u64_stats_read(&st->cnt); + tmisses = u64_stats_read(&st->misses); + } while (u64_stats_fetch_retry(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; + misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; + stats->misses = misses; } #ifdef CONFIG_PROC_FS @@ -1788,7 +2417,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); @@ -1799,14 +2428,18 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" - "run_cnt:\t%llu\n", + "run_cnt:\t%llu\n" + "recursion_misses:\t%llu\n" + "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, - stats.cnt); + stats.cnt, + stats.misses, + prog->aux->verified_insns); } #endif @@ -1831,18 +2464,6 @@ 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); @@ -1889,7 +2510,7 @@ 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; @@ -1898,20 +2519,19 @@ 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; } @@ -1950,18 +2570,27 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; + case BPF_PROG_TYPE_SK_REUSEPORT: + if (!attr->expected_attach_type) + attr->expected_attach_type = + BPF_SK_REUSEPORT_SELECT; + break; } } static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, - u32 btf_id, u32 prog_fd) + struct btf *attach_btf, u32 btf_id, + struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; + if (!attach_btf && !dst_prog) + return -EINVAL; + switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: @@ -1973,7 +2602,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, } } - if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING && + if (attach_btf && (!btf_id || dst_prog)) + return -EINVAL; + + if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; @@ -1981,6 +2613,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return 0; @@ -1993,14 +2626,19 @@ 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; @@ -2021,10 +2659,27 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_SK_LOOKUP: + if (expected_attach_type == BPF_SK_LOOKUP) + return 0; + return -EINVAL; + case BPF_PROG_TYPE_SK_REUSEPORT: + switch (expected_attach_type) { + case BPF_SK_REUSEPORT_SELECT: + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: + return 0; + 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) return -EINVAL; - /* fallthrough */ + fallthrough; default: return 0; } @@ -2042,7 +2697,6 @@ 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: @@ -2051,6 +2705,7 @@ 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 */ @@ -2080,15 +2735,17 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd +#define BPF_PROG_LOAD_LAST_FIELD fd_array_cnt -static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *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; + 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; @@ -2096,89 +2753,186 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | - BPF_F_TEST_RND_HI32)) + BPF_F_SLEEPABLE | + BPF_F_TEST_RND_HI32 | + 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_user(license, u64_to_user_ptr(attr->license), - 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 + */ + if (attr->attach_prog_fd) { + dst_prog = bpf_prog_get(attr->attach_prog_fd); + if (IS_ERR(dst_prog)) { + dst_prog = NULL; + attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); + 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); + 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)) { + 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, - attr->attach_btf_id, - attr->attach_prog_fd)) - return -EINVAL; + attach_btf, attr->attach_btf_id, + dst_prog)) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); + err = -EINVAL; + goto put_token; + } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); - if (!prog) - return -ENOMEM; + if (!prog) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); + 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; - if (attr->attach_prog_fd) { - struct bpf_prog *tgt_prog; - - tgt_prog = bpf_prog_get(attr->attach_prog_fd); - if (IS_ERR(tgt_prog)) { - err = PTR_ERR(tgt_prog); - goto free_prog_nouncharge; - } - prog->aux->linked_prog = tgt_prog; - } - - prog->aux->offload_requested = !!attr->prog_ifindex; + prog->aux->dst_prog = dst_prog; + 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_nouncharge; - - err = bpf_prog_charge_memlock(prog); - if (err) - goto free_prog_sec; + /* 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; err = -EFAULT; - if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns), - bpf_prog_insn_size(prog)) != 0) + if (copy_from_bpfptr(prog->insns, + make_bpfptr(attr->insns, uattr.is_kernel), + bpf_prog_insn_size(prog)) != 0) + 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; 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; } + /* + * 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) @@ -2190,8 +2944,12 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (err < 0) goto free_prog; + err = security_bpf_prog_load(prog, attr, token); + 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; @@ -2231,47 +2989,83 @@ 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: - bpf_prog_uncharge_memlock(prog); + free_prog_sec: - security_bpf_prog_free(prog->aux); -free_prog_nouncharge: + 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, + 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; } +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(link, type, ops, prog, false); +} + static void bpf_link_free_id(int id) { if (!id) @@ -2284,10 +3078,12 @@ 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) { @@ -2302,17 +3098,59 @@ 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) @@ -2322,27 +3160,31 @@ 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; } @@ -2362,23 +3204,37 @@ 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]) { + 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, @@ -2388,6 +3244,16 @@ 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; @@ -2408,7 +3274,7 @@ static int bpf_link_alloc_id(struct bpf_link *link) * pre-allocated resources are to be freed with bpf_cleanup() call. All the * transient state is passed around in struct bpf_link_primer. * This is preferred way to create and initialize bpf_link, especially when - * there are complicated and expensive operations inbetween creating bpf_link + * there are complicated and expensive operations in between creating bpf_link * itself and attaching it to BPF hook. By using bpf_link_prime() and * bpf_link_settle() kernel code using bpf_link doesn't have to perform * expensive (and potentially failing) roll back operations in a rare case @@ -2430,7 +3296,9 @@ 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); @@ -2458,42 +3326,47 @@ 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; } - -struct bpf_tracing_link { - struct bpf_link link; - enum bpf_attach_type attach_type; -}; +EXPORT_SYMBOL(bpf_link_get_from_fd); static void bpf_tracing_link_release(struct bpf_link *link) { - WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog)); + struct bpf_tracing_link *tr_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->tgt_prog)); + + bpf_trampoline_put(tr_link->trampoline); + + /* tgt_prog is NULL if target is a kernel function */ + if (tr_link->tgt_prog) + bpf_prog_put(tr_link->tgt_prog); } static void bpf_tracing_link_dealloc(struct bpf_link *link) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, link); + container_of(link, struct bpf_tracing_link, link.link); kfree(tr_link); } @@ -2502,20 +3375,30 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, 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", + tr_link->attach_type, + target_obj_id, + target_btf_id); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, link); + container_of(link, struct bpf_tracing_link, link.link); info->tracing.attach_type = tr_link->attach_type; + bpf_trampoline_unpack_key(tr_link->trampoline->key, + &info->tracing.target_obj_id, + &info->tracing.target_btf_id); return 0; } @@ -2527,10 +3410,16 @@ static const struct bpf_link_ops bpf_tracing_link_lops = { .fill_link_info = bpf_tracing_link_fill_link_info, }; -static int bpf_tracing_prog_attach(struct bpf_prog *prog) +static int bpf_tracing_prog_attach(struct bpf_prog *prog, + int tgt_prog_fd, + u32 btf_id, + u64 bpf_cookie) { struct bpf_link_primer link_primer; + struct bpf_prog *tgt_prog = NULL; + struct bpf_trampoline *tr = NULL; struct bpf_tracing_link *link; + u64 key = 0; int err; switch (prog->type) { @@ -2559,44 +3448,171 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog) goto out_put_prog; } + if (!!tgt_prog_fd != !!btf_id) { + err = -EINVAL; + goto out_put_prog; + } + + if (tgt_prog_fd) { + /* + * 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; + } + + tgt_prog = bpf_prog_get(tgt_prog_fd); + if (IS_ERR(tgt_prog)) { + err = PTR_ERR(tgt_prog); + tgt_prog = NULL; + goto out_put_prog; + } + + key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); + } + link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_prog; } - bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING, + bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog); link->attach_type = prog->expected_attach_type; + link->link.cookie = bpf_cookie; - err = bpf_link_prime(&link->link, &link_primer); - if (err) { - kfree(link); - goto out_put_prog; + mutex_lock(&prog->aux->dst_mutex); + + /* There are a few possible cases here: + * + * - if prog->aux->dst_trampoline is set, the program was just loaded + * and not yet attached to anything, so we can use the values stored + * 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) + * + * - if tgt_prog != NULL, the caller specified tgt_prog_fd + + * target_btf_id using the link_create API. + * + * - if tgt_prog == NULL when this function was called using the old + * raw_tracepoint_open API, and we need a target from prog->aux + * + * - 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) { + /* + * Allow re-attach for TRACING and LSM programs. If it's + * currently linked, bpf_trampoline_link_prog will fail. + * EXT programs need to specify tgt_prog_fd, so they + * re-attach in separate code path. + */ + if (prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_LSM) { + 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); } - err = bpf_trampoline_link_prog(prog); + if (!prog->aux->dst_trampoline || + (key && key != prog->aux->dst_trampoline->key)) { + /* If there is no saved target, or the specified target is + * different from the destination specified at load time, we + * need a new trampoline and a check for compatibility + */ + struct bpf_attach_target_info tgt_info = {}; + + err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id, + &tgt_info); + 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; + goto out_unlock; + } + } else { + /* The caller didn't specify a target, or the target was the + * same as the destination supplied during program load. This + * means we can reuse the trampoline and reference from program + * load time, and there is no need to allocate a new one. This + * can only happen once for any program, as the saved values in + * prog->aux are cleared below. + */ + tr = prog->aux->dst_trampoline; + tgt_prog = prog->aux->dst_prog; + } + + err = bpf_link_prime(&link->link.link, &link_primer); + if (err) + goto out_unlock; + + err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog); if (err) { bpf_link_cleanup(&link_primer); - goto out_put_prog; + link = NULL; + goto out_unlock; } + link->tgt_prog = tgt_prog; + link->trampoline = tr; + + /* Always clear the trampoline and target prog from prog->aux to make + * sure the original attach destination is not kept alive after a + * program is (re-)attached to another target. + */ + if (prog->aux->dst_prog && + (tgt_prog_fd || tr != prog->aux->dst_trampoline)) + /* got extra prog ref from syscall, or attaching to different prog */ + bpf_prog_put(prog->aux->dst_prog); + if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline) + /* we allocated a new trampoline, so free the old one */ + bpf_trampoline_put(prog->aux->dst_trampoline); + + prog->aux->dst_prog = NULL; + prog->aux->dst_trampoline = NULL; + mutex_unlock(&prog->aux->dst_mutex); + return bpf_link_settle(&link_primer); +out_unlock: + if (tr && tr != prog->aux->dst_trampoline) + bpf_trampoline_put(tr); + mutex_unlock(&prog->aux->dst_mutex); + kfree(link); out_put_prog: - bpf_prog_put(prog); + if (tgt_prog_fd && tgt_prog) + bpf_prog_put(tgt_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); } @@ -2619,6 +3635,25 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, raw_tp_link->btp->tp->name); } +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, struct bpf_link_info *info) { @@ -2629,7 +3664,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); - if (ulen && !ubuf) + if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; @@ -2637,95 +3672,310 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, if (!ubuf) return 0; - if (ulen >= tp_len + 1) { - if (copy_to_user(ubuf, tp_name, tp_len + 1)) - return -EFAULT; + 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_deferred = bpf_raw_tp_link_dealloc, + .show_fdinfo = bpf_raw_tp_link_show_fdinfo, + .fill_link_info = bpf_raw_tp_link_fill_link_info, +}; + +#ifdef CONFIG_PERF_EVENTS +struct bpf_perf_link { + struct bpf_link link; + struct file *perf_file; +}; + +static void bpf_perf_link_release(struct bpf_link *link) +{ + struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); + struct perf_event *event = perf_link->perf_file->private_data; + + perf_event_free_bpf_prog(event); + fput(perf_link->perf_file); +} + +static void bpf_perf_link_dealloc(struct bpf_link *link) +{ + struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_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 (copy_to_user(ubuf, tp_name, ulen - 1)) - return -EFAULT; - if (put_user(zero, ubuf + ulen - 1)) + if (put_user(zero, uname)) return -EFAULT; - return -ENOSPC; } + 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; } +#endif -static const struct bpf_link_ops bpf_raw_tp_link_lops = { - .release = bpf_raw_tp_link_release, - .dealloc = bpf_raw_tp_link_dealloc, - .show_fdinfo = bpf_raw_tp_link_show_fdinfo, - .fill_link_info = bpf_raw_tp_link_fill_link_info, +#ifdef CONFIG_UPROBE_EVENTS +static int bpf_perf_link_fill_uprobe(const struct perf_event *event, + struct bpf_link_info *info) +{ + char __user *uname; + u64 addr, offset; + 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, &addr, + &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; + return 0; +} +#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 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, }; -#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd +static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct bpf_perf_link *link; + struct perf_event *event; + struct file *perf_file; + int err; -static int bpf_raw_tracepoint_open(const union bpf_attr *attr) + if (attr->link_create.flags) + return -EINVAL; + + perf_file = perf_event_get(attr->link_create.target_fd); + if (IS_ERR(perf_file)) + return PTR_ERR(perf_file); + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_file; + } + bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog); + link->perf_file = perf_file; + + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + goto out_put_file; + } + + event = perf_file->private_data; + err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); + if (err) { + bpf_link_cleanup(&link_primer); + goto out_put_file; + } + /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ + bpf_prog_inc(prog); + + return bpf_link_settle(&link_primer); + +out_put_file: + fput(perf_file); + return err; +} +#else +static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_PERF_EVENTS */ + +static int bpf_raw_tp_link_attach(struct bpf_prog *prog, + const char __user *user_tp_name, u64 cookie) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; - struct bpf_prog *prog; const char *tp_name; char buf[128]; int err; - if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) - return -EINVAL; - - prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); - if (IS_ERR(prog)) - return PTR_ERR(prog); - switch (prog->type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: - if (attr->raw_tracepoint.name) { + if (user_tp_name) /* The attach point for this category of programs * should be specified via btf_id during program load. */ - err = -EINVAL; - goto out_put_prog; - } + return -EINVAL; if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; break; } - return bpf_tracing_prog_attach(prog); + return bpf_tracing_prog_attach(prog, 0, 0, 0); case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: - if (strncpy_from_user(buf, - u64_to_user_ptr(attr->raw_tracepoint.name), - sizeof(buf) - 1) < 0) { - err = -EFAULT; - goto out_put_prog; - } + if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) + return -EFAULT; buf[sizeof(buf) - 1] = 0; tp_name = buf; break; default: - err = -EINVAL; - goto out_put_prog; + return -EINVAL; } btp = bpf_get_raw_tracepoint(tp_name); - if (!btp) { - err = -ENOENT; - goto out_put_prog; - } + if (!btp) + return -ENOENT; link = kzalloc(sizeof(*link), GFP_USER); if (!link) { 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, + tracepoint_is_faultable(btp->tp)); link->btp = btp; + link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -2733,7 +3983,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) 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; @@ -2743,31 +3993,31 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) out_put_btp: bpf_put_raw_tracepoint(btp); -out_put_prog: - bpf_prog_put(prog); return err; } -static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, - enum bpf_attach_type attach_type) +#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie + +static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { - switch (prog->type) { - case BPF_PROG_TYPE_CGROUP_SOCK: - case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: - 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; - } + struct bpf_prog *prog; + void __user *tp_name; + __u64 cookie; + int fd; + + if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) + return -EINVAL; + + prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); + cookie = attr->raw_tracepoint.cookie; + fd = bpf_raw_tp_link_attach(prog, tp_name, cookie); + if (fd < 0) + bpf_prog_put(prog); + return fd; } static enum bpf_prog_type @@ -2777,8 +4027,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return BPF_PROG_TYPE_CGROUP_SKB; - break; case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return BPF_PROG_TYPE_CGROUP_SOCK; @@ -2786,14 +4036,19 @@ 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; @@ -2803,6 +4058,7 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: + case BPF_SK_SKB_VERDICT: return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: return BPF_PROG_TYPE_LIRC_MODE2; @@ -2814,16 +4070,113 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; case BPF_TRACE_ITER: + case BPF_TRACE_RAW_TP: + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: return BPF_PROG_TYPE_TRACING; + case BPF_LSM_MAC: + return BPF_PROG_TYPE_LSM; + case BPF_SK_LOOKUP: + return BPF_PROG_TYPE_SK_LOOKUP; + case BPF_XDP: + 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; -#define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) + 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; + } +} + +#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) + +#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) { @@ -2834,12 +4187,19 @@ 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 (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)) @@ -2868,7 +4228,19 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: - ret = cgroup_bpf_prog_attach(attr, ptype, prog); + case BPF_PROG_TYPE_LSM: + if (ptype == BPF_PROG_TYPE_LSM && + prog->expected_attach_type != BPF_LSM_CGROUP) + ret = -EINVAL; + else + ret = cgroup_bpf_prog_attach(attr, ptype, prog); + break; + 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 = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; @@ -2879,25 +4251,45 @@ static int bpf_prog_attach(const union bpf_attr *attr) 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 (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: @@ -2905,18 +4297,31 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: - return cgroup_bpf_prog_detach(attr, ptype); + case BPF_PROG_TYPE_LSM: + 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_cnt +#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; @@ -2927,36 +4332,55 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_POST_BIND: 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: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: + case BPF_LSM_CGROUP: return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: + case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); + case BPF_SK_SKB_STREAM_PARSER: + case BPF_SK_SKB_STREAM_VERDICT: + 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; } } -#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out +#define BPF_PROG_TEST_RUN_LAST_FIELD test.batch_size static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -3033,6 +4457,25 @@ again: return map; } +struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id) +{ + struct bpf_prog *prog; + + spin_lock_bh(&prog_idr_lock); +again: + prog = idr_get_next(&prog_idr, id); + if (prog) { + prog = bpf_prog_inc_not_zero(prog); + if (IS_ERR(prog)) { + (*id)++; + goto again; + } + } + spin_unlock_bh(&prog_idr_lock); + + return prog; +} + #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id struct bpf_prog *bpf_prog_by_id(u32 id) @@ -3120,21 +4563,25 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, const struct bpf_map *map; int i; + mutex_lock(&prog->aux->used_maps_mutex); for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { map = prog->aux->used_maps[i]; if (map == (void *)addr) { *type = BPF_PSEUDO_MAP_FD; - return map; + goto out; } if (!map->ops->map_direct_value_meta) continue; if (!map->ops->map_direct_value_meta(map, addr, off)) { *type = BPF_PSEUDO_MAP_VALUE; - return map; + goto out; } } + map = NULL; - return NULL; +out: + mutex_unlock(&prog->aux->used_maps_mutex); + return map; } static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, @@ -3173,6 +4620,12 @@ 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; @@ -3226,14 +4679,15 @@ static int bpf_prog_get_info_by_fd(struct file *file, union bpf_attr __user *uattr) { struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct btf *attach_btf = bpf_prog_get_target_btf(prog); struct bpf_prog_info info; u32 info_len = attr->info.info_len; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3252,6 +4706,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); + mutex_lock(&prog->aux->used_maps_mutex); ulen = info.nr_map_ids; info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); @@ -3261,9 +4716,12 @@ static int bpf_prog_get_info_by_fd(struct file *file, for (i = 0; i < ulen; i++) if (put_user(prog->aux->used_maps[i]->id, - &user_map_ids[i])) + &user_map_ids[i])) { + mutex_unlock(&prog->aux->used_maps_mutex); return -EFAULT; + } } + mutex_unlock(&prog->aux->used_maps_mutex); err = set_info_rec_size(&info); if (err) @@ -3272,6 +4730,9 @@ static int bpf_prog_get_info_by_fd(struct file *file, bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; + info.recursion_misses = stats.misses; + + info.verified_insns = prog->aux->verified_insns; if (!bpf_capable()) { info.jited_prog_len = 0; @@ -3305,7 +4766,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, 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; @@ -3419,7 +4880,10 @@ static int bpf_prog_get_info_by_fd(struct file *file, } if (prog->aux->btf) - info.btf_id = btf_id(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); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; @@ -3452,14 +4916,15 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { + unsigned long line_addr; __u64 __user *user_linfo; u32 i; user_linfo = u64_to_user_ptr(info.jited_line_info); ulen = min_t(u32, info.nr_jited_line_info, ulen); for (i = 0; i < ulen; i++) { - if (put_user((__u64)(long)prog->aux->jited_linfo[i], - &user_linfo[i])) + line_addr = (unsigned long)prog->aux->jited_linfo[i]; + if (put_user((__u64)line_addr, &user_linfo[i])) return -EFAULT; } } else { @@ -3507,7 +4972,7 @@ static int bpf_map_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3519,16 +4984,19 @@ static int bpf_map_get_info_by_fd(struct file *file, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { - info.btf_id = btf_id(map->btf); + info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; 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; @@ -3550,7 +5018,7 @@ static int bpf_btf_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; @@ -3567,7 +5035,7 @@ static int bpf_link_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3578,7 +5046,8 @@ 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); @@ -3599,46 +5068,57 @@ static int bpf_link_get_info_by_fd(struct file *file, 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; + 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) +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; + } + + bpf_token_put(token); - return btf_new_fd(attr); + return btf_new_fd(attr, uattr, uattr_size); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id @@ -3709,7 +5189,6 @@ static int bpf_task_fd_query(const union bpf_attr *attr, pid_t pid = attr->task_fd_query.pid; u32 fd = attr->task_fd_query.fd; const struct perf_event *event; - struct files_struct *files; struct task_struct *task; struct file *file; int err; @@ -3723,29 +5202,19 @@ static int bpf_task_fd_query(const union bpf_attr *attr, if (attr->task_fd_query.flags != 0) return -EINVAL; + rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + rcu_read_unlock(); if (!task) return -ENOENT; - files = get_files_struct(task); - put_task_struct(task); - if (!files) - return -ENOENT; - err = 0; - spin_lock(&files->file_lock); - file = fcheck_files(files, fd); + file = fget_task(task, fd); + put_task_struct(task); if (!file) - err = -EBADF; - else - get_file(file); - spin_unlock(&files->file_lock); - put_files_struct(files); - - if (err) - goto out; + 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) { @@ -3770,7 +5239,7 @@ 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, @@ -3783,98 +5252,87 @@ out_not_supp: err = -ENOTSUPP; put_file: fput(file); -out: return err; } #define BPF_MAP_BATCH_LAST_FIELD batch.flags -#define BPF_DO_BATCH(fn) \ +#define BPF_DO_BATCH(fn, ...) \ do { \ if (!fn) { \ err = -ENOTSUPP; \ goto err_put; \ } \ - err = fn(map, attr, uattr); \ + err = fn(__VA_ARGS__); \ } while (0) static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + 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); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (cmd == BPF_MAP_LOOKUP_BATCH) - BPF_DO_BATCH(map->ops->map_lookup_batch); + BPF_DO_BATCH(map->ops->map_lookup_batch, map, attr, uattr); else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) - BPF_DO_BATCH(map->ops->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); + BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr); else - BPF_DO_BATCH(map->ops->map_delete_batch); - + BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: - fdput(f); + if (has_write) { + maybe_wait_bpf_programs(map); + bpf_map_write_active_dec(map); + } return err; } -static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid +static int link_create(union bpf_attr *attr, bpfptr_t uattr) { - if (attr->link_create.attach_type == BPF_TRACE_ITER && - prog->expected_attach_type == BPF_TRACE_ITER) - return bpf_iter_link_attach(attr, prog); - - return -EINVAL; -} - -#define BPF_LINK_CREATE_LAST_FIELD link_create.flags -static int link_create(union bpf_attr *attr) -{ - enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; - ptype = attach_type_to_prog_type(attr->link_create.attach_type); - if (ptype == BPF_PROG_TYPE_UNSPEC) - return -EINVAL; + if (attr->link_create.attach_type == BPF_STRUCT_OPS) + return bpf_struct_ops_link_create(attr); - prog = bpf_prog_get_type(attr->link_create.prog_fd, ptype); + prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_attach_check_attach_type(prog, attr->link_create.attach_type); if (ret) - goto err_out; + goto out; - switch (ptype) { + switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: @@ -3884,22 +5342,106 @@ static int link_create(union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; + case BPF_PROG_TYPE_EXT: + ret = bpf_tracing_prog_attach(prog, + attr->link_create.target_fd, + attr->link_create.target_btf_id, + attr->link_create.tracing.cookie); + break; + case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_TRACING: - ret = tracing_bpf_link_attach(attr, prog); + if (attr->link_create.attach_type != prog->expected_attach_type) { + ret = -EINVAL; + goto out; + } + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie); + else if (prog->expected_attach_type == BPF_TRACE_ITER) + ret = bpf_iter_link_attach(attr, uattr, prog); + else if (prog->expected_attach_type == BPF_LSM_CGROUP) + ret = cgroup_bpf_link_attach(attr, prog); + else + ret = bpf_tracing_prog_attach(prog, + attr->link_create.target_fd, + attr->link_create.target_btf_id, + attr->link_create.tracing.cookie); 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: + ret = bpf_perf_link_attach(attr, prog); + break; + case BPF_PROG_TYPE_KPROBE: + if (attr->link_create.attach_type == BPF_PERF_EVENT) + ret = bpf_perf_link_attach(attr, prog); + else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || + 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; } -err_out: +out: if (ret < 0) bpf_prog_put(prog); 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) @@ -3920,6 +5462,11 @@ 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); @@ -3949,48 +5496,101 @@ out_put_progs: if (ret) bpf_prog_put(new_prog); out_put_link: - bpf_link_put(link); + bpf_link_put_direct(link); return ret; } -static int bpf_link_inc_not_zero(struct bpf_link *link) +#define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd + +static int link_detach(union bpf_attr *attr) { - return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT; + struct bpf_link *link; + int ret; + + if (CHECK_ATTR(BPF_LINK_DETACH)) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->link_detach.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + if (link->ops->detach) + ret = link->ops->detach(link); + else + ret = -EOPNOTSUPP; + + bpf_link_put_direct(link); + return ret; } -#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id +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); -static int bpf_link_get_fd_by_id(const union bpf_attr *attr) +struct bpf_link *bpf_link_by_id(u32 id) { struct bpf_link *link; - u32 id = attr->link_id; - int fd, err; - if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + if (!id) + return ERR_PTR(-ENOENT); spin_lock_bh(&link_idr_lock); - link = idr_find(&link_idr, id); /* before link is "settled", ID is 0, pretend it doesn't exist yet */ + link = idr_find(&link_idr, id); if (link) { if (link->id) - err = bpf_link_inc_not_zero(link); + link = bpf_link_inc_not_zero(link); else - err = -EAGAIN; + link = ERR_PTR(-EAGAIN); } else { - err = -ENOENT; + link = ERR_PTR(-ENOENT); } spin_unlock_bh(&link_idr_lock); + return link; +} - if (err) - return err; +struct bpf_link *bpf_link_get_curr_or_next(u32 *id) +{ + struct bpf_link *link; + + spin_lock_bh(&link_idr_lock); +again: + link = idr_get_next(&link_idr, id); + if (link) { + link = bpf_link_inc_not_zero(link); + if (IS_ERR(link)) { + (*id)++; + goto again; + } + } + spin_unlock_bh(&link_idr_lock); + + return link; +} + +#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id + +static int bpf_link_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_link *link; + u32 id = attr->link_id; + int fd; + + if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + link = bpf_link_by_id(id); + if (IS_ERR(link)) + return PTR_ERR(link); fd = bpf_link_new_fd(link); if (fd < 0) - bpf_link_put(link); + bpf_link_put_direct(link); return fd; } @@ -4067,19 +5667,97 @@ 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; } -SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +#define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags + +static int bpf_prog_bind_map(union bpf_attr *attr) +{ + struct bpf_prog *prog; + struct bpf_map *map; + struct bpf_map **used_maps_old, **used_maps_new; + int i, ret = 0; + + if (CHECK_ATTR(BPF_PROG_BIND_MAP)) + return -EINVAL; + + if (attr->prog_bind_map.flags) + return -EINVAL; + + prog = bpf_prog_get(attr->prog_bind_map.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + map = bpf_map_get(attr->prog_bind_map.map_fd); + if (IS_ERR(map)) { + ret = PTR_ERR(map); + goto out_prog_put; + } + + mutex_lock(&prog->aux->used_maps_mutex); + + used_maps_old = prog->aux->used_maps; + + for (i = 0; i < prog->aux->used_map_cnt; i++) + if (used_maps_old[i] == map) { + bpf_map_put(map); + goto out_unlock; + } + + used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1, + sizeof(used_maps_new[0]), + GFP_KERNEL); + if (!used_maps_new) { + ret = -ENOMEM; + 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; + + prog->aux->used_map_cnt++; + prog->aux->used_maps = used_maps_new; + + kfree(used_maps_old); + +out_unlock: + mutex_unlock(&prog->aux->used_maps_mutex); + + if (ret) + bpf_map_put(map); +out_prog_put: + bpf_prog_put(prog); + return ret; +} + +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + +static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; - err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; @@ -4087,7 +5765,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); - if (copy_from_user(&attr, uattr, size) != 0) + if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size); @@ -4102,10 +5780,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: - err = map_update_elem(&attr); + err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: - err = map_delete_elem(&attr); + err = map_delete_elem(&attr, uattr); break; case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); @@ -4114,7 +5792,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz 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); @@ -4129,21 +5807,21 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: - err = bpf_prog_query(&attr, uattr); + err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: - err = bpf_prog_test_run(&attr, uattr); + err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: @@ -4153,38 +5831,38 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: - err = bpf_obj_get_info_by_fd(&attr, uattr); + err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: - err = bpf_btf_load(&attr); + err = bpf_btf_load(&attr, uattr, size); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: - err = bpf_task_fd_query(&attr, uattr); + err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: - err = link_create(&attr); + err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); @@ -4193,7 +5871,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: @@ -4202,6 +5880,15 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_ITER_CREATE: err = bpf_iter_create(&attr); break; + case BPF_LINK_DETACH: + err = link_detach(&attr); + break; + case BPF_PROG_BIND_MAP: + err = bpf_prog_bind_map(&attr); + break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; @@ -4209,3 +5896,261 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz return err; } + +SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +{ + return __sys_bpf(cmd, USER_BPFPTR(uattr), size); +} + +static bool syscall_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= U16_MAX) + return false; + if (off % size != 0) + return false; + return true; +} + +BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) +{ + switch (cmd) { + case BPF_MAP_CREATE: + case BPF_MAP_DELETE_ELEM: + case BPF_MAP_UPDATE_ELEM: + case BPF_MAP_FREEZE: + case BPF_MAP_GET_FD_BY_ID: + case BPF_PROG_LOAD: + case BPF_BTF_LOAD: + case BPF_LINK_CREATE: + case BPF_RAW_TRACEPOINT_OPEN: + break; + default: + return -EINVAL; + } + return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); +} + + +/* To shut up -Wmissing-prototypes. + * This function is used by the kernel light skeleton + * to load bpf programs when modules are loaded or during kernel boot. + * See tools/lib/bpf/skel_internal.h + */ +int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); + +int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) +{ + struct bpf_prog * __maybe_unused prog; + struct bpf_tramp_run_ctx __maybe_unused run_ctx; + + switch (cmd) { +#ifdef CONFIG_BPF_JIT /* __bpf_prog_enter_sleepable used by trampoline and JIT */ + case BPF_PROG_TEST_RUN: + if (attr->test.data_in || attr->test.data_out || + attr->test.ctx_out || attr->test.duration || + attr->test.repeat || attr->test.flags) + return -EINVAL; + + prog = bpf_prog_get_type(attr->test.prog_fd, BPF_PROG_TYPE_SYSCALL); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (attr->test.ctx_size_in < prog->aux->max_ctx_offset || + attr->test.ctx_size_in > U16_MAX) { + bpf_prog_put(prog); + return -EINVAL; + } + + run_ctx.bpf_cookie = 0; + 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; + } + attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); + __bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */, + &run_ctx); + bpf_prog_put(prog); + return 0; +#endif + default: + return ____bpf_sys_bpf(cmd, attr, size); + } +} +EXPORT_SYMBOL(kern_sys_bpf); + +static const struct bpf_func_proto bpf_sys_bpf_proto = { + .func = bpf_sys_bpf, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg3_type = ARG_CONST_SIZE, +}; + +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, prog); +} + +BPF_CALL_1(bpf_sys_close, u32, fd) +{ + /* When bpf program calls this helper there should not be + * an fdget() without matching completed fdput(). + * This helper is allowed in the following callchain only: + * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close + */ + return close_fd(fd); +} + +static const struct bpf_func_proto bpf_sys_close_proto = { + .func = bpf_sys_close, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) +{ + *res = 0; + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + if (!bpf_dump_raw_ok(current_cred())) + return -EPERM; + + *res = kallsyms_lookup_name(name); + return *res ? 0 : -ENOENT; +} + +static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { + .func = bpf_kallsyms_lookup_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, + .arg4_size = sizeof(u64), +}; + +static const struct bpf_func_proto * +syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_sys_bpf: + 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: + return &bpf_sys_close_proto; + case BPF_FUNC_kallsyms_lookup_name: + return &bpf_kallsyms_lookup_name_proto; + default: + return tracing_prog_func_proto(func_id, prog); + } +} + +const struct bpf_verifier_ops bpf_syscall_verifier_ops = { + .get_func_proto = syscall_prog_func_proto, + .is_valid_access = syscall_prog_is_valid_access, +}; + +const struct bpf_prog_ops bpf_syscall_prog_ops = { + .test_run = bpf_prog_test_run_syscall, +}; + +#ifdef CONFIG_SYSCTL +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; + static int saved_val; + int val, ret; + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(val), + .mode = table->mode, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&bpf_stats_enabled_mutex); + val = saved_val; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret && val != saved_val) { + if (val) + static_key_slow_inc(key); + else + static_key_slow_dec(key); + saved_val = val; + } + mutex_unlock(&bpf_stats_enabled_mutex); + return ret; +} + +void __weak unpriv_ebpf_notify(int new_state) +{ +} + +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; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + + if (write) + unpriv_ebpf_notify(unpriv_enable); + + return ret; +} + +static const struct ctl_table bpf_syscall_table[] = { + { + .procname = "unprivileged_bpf_disabled", + .data = &sysctl_unprivileged_bpf_disabled, + .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), + .mode = 0644, + .proc_handler = bpf_unpriv_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "bpf_stats_enabled", + .data = &bpf_stats_enabled_key.key, + .mode = 0644, + .proc_handler = bpf_stats_handler, + }, +}; + +static int __init bpf_syscall_sysctl_init(void) +{ + register_sysctl_init("kernel", bpf_syscall_table); + return 0; +} +late_initcall(bpf_syscall_sysctl_init); +#endif /* CONFIG_SYSCTL */ diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index 3b495773de5a..81d6cf90584a 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -9,36 +9,28 @@ #include <linux/sysfs.h> /* See scripts/link-vmlinux.sh, gen_btf() func for details */ -extern char __weak __start_BTF[]; -extern char __weak __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) -{ - memcpy(buf, __start_BTF + off, len); - return len; -} +extern char __start_BTF[]; +extern char __stop_BTF[]; static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = { .attr = { .name = "vmlinux", .mode = 0444, }, - .read = btf_vmlinux_read, + .read_new = sysfs_bin_attr_simple_read, }; -static struct kobject *btf_kobj; +struct kobject *btf_kobj; static int __init btf_vmlinux_init(void) { - if (!__start_BTF) + bin_attr_btf_vmlinux.private = __start_BTF; + bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; + + if (bin_attr_btf_vmlinux.size == 0) return 0; btf_kobj = kobject_create_and_add("btf", kernel_kobj); if (!btf_kobj) return -ENOMEM; - bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; - return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); } diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 4dbf2b6035f8..98d9b4c0daff 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -5,11 +5,23 @@ #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[] = { + "ALL", + "TID", + "PID", +}; struct bpf_iter_seq_task_common { struct pid_namespace *ns; + enum bpf_iter_task_type type; + u32 pid; + u32 pid_visiting; }; struct bpf_iter_seq_task_info { @@ -20,20 +32,103 @@ struct bpf_iter_seq_task_info { u32 tid; }; -static struct task_struct *task_seq_get_next(struct pid_namespace *ns, - u32 *tid) +static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_common *common, + u32 *tid, + bool skip_if_dup_files) +{ + struct task_struct *task; + struct pid *pid; + u32 next_tid; + + if (!*tid) { + /* The first time, the iterator calls this function. */ + pid = find_pid_ns(common->pid, common->ns); + task = get_pid_task(pid, PIDTYPE_TGID); + if (!task) + return NULL; + + *tid = common->pid; + common->pid_visiting = common->pid; + + return task; + } + + /* If the control returns to user space and comes back to the + * kernel again, *tid and common->pid_visiting should be the + * same for task_seq_start() to pick up the correct task. + */ + if (*tid == common->pid_visiting) { + pid = find_pid_ns(common->pid_visiting, common->ns); + task = get_pid_task(pid, PIDTYPE_PID); + + return task; + } + + task = find_task_by_pid_ns(common->pid_visiting, common->ns); + if (!task) + return NULL; + +retry: + task = __next_thread(task); + if (!task) + return NULL; + + 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) + goto retry; + + *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, + u32 *tid, + bool skip_if_dup_files) { struct task_struct *task = NULL; struct pid *pid; + if (common->type == BPF_TASK_ITER_TID) { + if (*tid && *tid != common->pid) + return NULL; + rcu_read_lock(); + pid = find_pid_ns(common->pid, common->ns); + if (pid) { + task = get_pid_task(pid, PIDTYPE_PID); + *tid = common->pid; + } + rcu_read_unlock(); + + return task; + } + + if (common->type == BPF_TASK_ITER_TGID) { + rcu_read_lock(); + task = task_group_seq_get_next(common, tid, skip_if_dup_files); + rcu_read_unlock(); + + return task; + } + rcu_read_lock(); retry: - pid = idr_get_next(&ns->idr, tid); + pid = find_ge_pid(*tid, common->ns); if (pid) { + *tid = pid_nr_ns(pid, common->ns); task = get_pid_task(pid, PIDTYPE_PID); if (!task) { ++*tid; goto retry; + } else if (skip_if_dup_files && !thread_group_leader(task) && + task->files == task->group_leader->files) { + put_task_struct(task); + task = NULL; + ++*tid; + goto retry; } } rcu_read_unlock(); @@ -46,11 +141,12 @@ static void *task_seq_start(struct seq_file *seq, loff_t *pos) struct bpf_iter_seq_task_info *info = seq->private; struct task_struct *task; - task = task_seq_get_next(info->common.ns, &info->tid); + task = task_seq_get_next(&info->common, &info->tid, false); if (!task) return NULL; - ++*pos; + if (*pos == 0) + ++*pos; return task; } @@ -62,7 +158,7 @@ static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; ++info->tid; put_task_struct((struct task_struct *)v); - task = task_seq_get_next(info->common.ns, &info->tid); + task = task_seq_get_next(&info->common, &info->tid, false); if (!task) return NULL; @@ -88,7 +184,6 @@ static int __task_seq_show(struct seq_file *seq, struct task_struct *task, if (!prog) return 0; - meta.seq = seq; ctx.meta = &meta; ctx.task = task; return bpf_iter_run_prog(prog, &ctx); @@ -107,6 +202,41 @@ static void task_seq_stop(struct seq_file *seq, void *v) put_task_struct((struct task_struct *)v); } +static int bpf_iter_attach_task(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) +{ + unsigned int flags; + struct pid *pid; + pid_t tgid; + + if ((!!linfo->task.tid + !!linfo->task.pid + !!linfo->task.pid_fd) > 1) + return -EINVAL; + + aux->task.type = BPF_TASK_ITER_ALL; + if (linfo->task.tid != 0) { + aux->task.type = BPF_TASK_ITER_TID; + aux->task.pid = linfo->task.tid; + } + if (linfo->task.pid != 0) { + aux->task.type = BPF_TASK_ITER_TGID; + aux->task.pid = linfo->task.pid; + } + if (linfo->task.pid_fd != 0) { + aux->task.type = BPF_TASK_ITER_TGID; + + pid = pidfd_get_pid(linfo->task.pid_fd, &flags); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + tgid = pid_nr_ns(pid, task_active_pid_ns(current)); + aux->task.pid = tgid; + put_pid(pid); + } + + return 0; +} + static const struct seq_operations task_seq_ops = { .start = task_seq_start, .next = task_seq_next, @@ -120,98 +250,71 @@ struct bpf_iter_seq_task_file_info { */ struct bpf_iter_seq_task_common common; struct task_struct *task; - struct files_struct *files; u32 tid; u32 fd; }; static struct file * -task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info, - struct task_struct **task, struct files_struct **fstruct) +task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info) { - struct pid_namespace *ns = info->common.ns; - u32 curr_tid = info->tid, max_fds; - struct files_struct *curr_files; + u32 saved_tid = info->tid; struct task_struct *curr_task; - int curr_fd = info->fd; + 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/files_struct/file. + * it held a reference to the task/file. * Otherwise, it does not hold any reference. */ again: - if (*task) { - curr_task = *task; - curr_files = *fstruct; + if (info->task) { + curr_task = info->task; curr_fd = info->fd; } else { - curr_task = task_seq_get_next(ns, &curr_tid); - if (!curr_task) - return NULL; + curr_task = task_seq_get_next(&info->common, &info->tid, true); + if (!curr_task) { + info->task = NULL; + return NULL; + } - curr_files = get_files_struct(curr_task); - if (!curr_files) { - put_task_struct(curr_task); - curr_tid = ++(info->tid); - info->fd = 0; - goto again; - } - - /* set *fstruct, *task and info->tid */ - *fstruct = curr_files; - *task = curr_task; - if (curr_tid == info->tid) { + /* set info->task */ + info->task = curr_task; + if (saved_tid == info->tid) curr_fd = info->fd; - } else { - info->tid = curr_tid; + else curr_fd = 0; - } } - rcu_read_lock(); - max_fds = files_fdtable(curr_files)->max_fds; - for (; curr_fd < max_fds; curr_fd++) { - struct file *f; - - f = fcheck_files(curr_files, curr_fd); - if (!f) - continue; - + f = fget_task_next(curr_task, &curr_fd); + if (f) { /* set info->fd */ info->fd = curr_fd; - get_file(f); - rcu_read_unlock(); return f; } /* the current task is done, go to the next task */ - rcu_read_unlock(); - put_files_struct(curr_files); put_task_struct(curr_task); - *task = NULL; - *fstruct = NULL; + + if (info->common.type == BPF_TASK_ITER_TID) { + info->task = NULL; + return NULL; + } + + info->task = NULL; info->fd = 0; - curr_tid = ++(info->tid); + saved_tid = ++(info->tid); goto again; } static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) { struct bpf_iter_seq_task_file_info *info = seq->private; - struct files_struct *files = NULL; - struct task_struct *task = NULL; struct file *file; - file = task_file_seq_get_next(info, &task, &files); - if (!file) { - info->files = NULL; - info->task = NULL; - return NULL; - } - - ++*pos; - info->task = task; - info->files = files; + info->task = NULL; + file = task_file_seq_get_next(info); + if (file && *pos == 0) + ++*pos; return file; } @@ -219,24 +322,11 @@ static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_task_file_info *info = seq->private; - struct files_struct *files = info->files; - struct task_struct *task = info->task; - struct file *file; ++*pos; ++info->fd; fput((struct file *)v); - file = task_file_seq_get_next(info, &task, &files); - if (!file) { - info->files = NULL; - info->task = NULL; - return NULL; - } - - info->task = task; - info->files = files; - - return file; + return task_file_seq_get_next(info); } struct bpf_iter__task_file { @@ -283,18 +373,19 @@ static void task_file_seq_stop(struct seq_file *seq, void *v) (void)__task_file_seq_show(seq, v, true); } else { fput((struct file *)v); - put_files_struct(info->files); put_task_struct(info->task); - info->files = NULL; info->task = NULL; } } -static int init_seq_pidns(void *priv_data) +static int init_seq_pidns(void *priv_data, struct bpf_iter_aux_info *aux) { struct bpf_iter_seq_task_common *common = priv_data; common->ns = get_pid_ns(task_active_pid_ns(current)); + common->type = aux->task.type; + common->pid = aux->task.pid; + return 0; } @@ -312,25 +403,316 @@ static const struct seq_operations task_file_seq_ops = { .show = task_file_seq_show, }; -static const struct bpf_iter_reg task_reg_info = { - .target = "task", +struct bpf_iter_seq_task_vma_info { + /* The first field must be struct bpf_iter_seq_task_common. + * this is assumed by {init, fini}_seq_pidns() callback functions. + */ + struct bpf_iter_seq_task_common common; + struct task_struct *task; + struct mm_struct *mm; + struct vm_area_struct *vma; + u32 tid; + unsigned long prev_vm_start; + unsigned long prev_vm_end; +}; + +enum bpf_task_vma_iter_find_op { + task_vma_iter_first_vma, /* use find_vma() with addr 0 */ + task_vma_iter_next_vma, /* use vma_next() with curr_vma */ + task_vma_iter_find_vma, /* use find_vma() to find next vma */ +}; + +static struct vm_area_struct * +task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info) +{ + enum bpf_task_vma_iter_find_op op; + struct vm_area_struct *curr_vma; + struct task_struct *curr_task; + struct mm_struct *curr_mm; + u32 saved_tid = info->tid; + + /* If this function returns a non-NULL vma, it holds a reference to + * the task_struct, holds a refcount on mm->mm_users, and holds + * read lock on vma->mm->mmap_lock. + * If this function returns NULL, it does not hold any reference or + * lock. + */ + if (info->task) { + curr_task = info->task; + curr_vma = info->vma; + curr_mm = info->mm; + /* In case of lock contention, drop mmap_lock to unblock + * the writer. + * + * After relock, call find(mm, prev_vm_end - 1) to find + * new vma to process. + * + * +------+------+-----------+ + * | VMA1 | VMA2 | VMA3 | + * +------+------+-----------+ + * | | | | + * 4k 8k 16k 400k + * + * For example, curr_vma == VMA2. Before unlock, we set + * + * prev_vm_start = 8k + * prev_vm_end = 16k + * + * There are a few cases: + * + * 1) VMA2 is freed, but VMA3 exists. + * + * find_vma() will return VMA3, just process VMA3. + * + * 2) VMA2 still exists. + * + * find_vma() will return VMA2, process VMA2->next. + * + * 3) no more vma in this mm. + * + * Process the next task. + * + * 4) find_vma() returns a different vma, VMA2'. + * + * 4.1) If VMA2 covers same range as VMA2', skip VMA2', + * because we already covered the range; + * 4.2) VMA2 and VMA2' covers different ranges, process + * VMA2'. + */ + if (mmap_lock_is_contended(curr_mm)) { + info->prev_vm_start = curr_vma->vm_start; + info->prev_vm_end = curr_vma->vm_end; + op = task_vma_iter_find_vma; + mmap_read_unlock(curr_mm); + if (mmap_read_lock_killable(curr_mm)) { + mmput(curr_mm); + goto finish; + } + } else { + op = task_vma_iter_next_vma; + } + } else { +again: + curr_task = task_seq_get_next(&info->common, &info->tid, true); + if (!curr_task) { + info->tid++; + goto finish; + } + + if (saved_tid != info->tid) { + /* new task, process the first vma */ + op = task_vma_iter_first_vma; + } else { + /* Found the same tid, which means the user space + * finished data in previous buffer and read more. + * We dropped mmap_lock before returning to user + * space, so it is necessary to use find_vma() to + * find the next vma to process. + */ + op = task_vma_iter_find_vma; + } + + curr_mm = get_task_mm(curr_task); + if (!curr_mm) + goto next_task; + + if (mmap_read_lock_killable(curr_mm)) { + mmput(curr_mm); + goto finish; + } + } + + switch (op) { + case task_vma_iter_first_vma: + curr_vma = find_vma(curr_mm, 0); + break; + case task_vma_iter_next_vma: + curr_vma = find_vma(curr_mm, curr_vma->vm_end); + break; + case task_vma_iter_find_vma: + /* We dropped mmap_lock so it is necessary to use find_vma + * to find the next vma. This is similar to the mechanism + * in show_smaps_rollup(). + */ + curr_vma = find_vma(curr_mm, info->prev_vm_end - 1); + /* case 1) and 4.2) above just use curr_vma */ + + /* check for case 2) or case 4.1) above */ + if (curr_vma && + curr_vma->vm_start == info->prev_vm_start && + curr_vma->vm_end == info->prev_vm_end) + curr_vma = find_vma(curr_mm, curr_vma->vm_end); + break; + } + if (!curr_vma) { + /* case 3) above, or case 2) 4.1) with vma->next == NULL */ + mmap_read_unlock(curr_mm); + mmput(curr_mm); + goto next_task; + } + info->task = curr_task; + info->vma = curr_vma; + info->mm = curr_mm; + return curr_vma; + +next_task: + if (info->common.type == BPF_TASK_ITER_TID) + goto finish; + + put_task_struct(curr_task); + info->task = NULL; + info->mm = NULL; + info->tid++; + goto again; + +finish: + if (curr_task) + put_task_struct(curr_task); + info->task = NULL; + info->vma = NULL; + info->mm = NULL; + return NULL; +} + +static void *task_vma_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + struct vm_area_struct *vma; + + vma = task_vma_seq_get_next(info); + if (vma && *pos == 0) + ++*pos; + + return vma; +} + +static void *task_vma_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + + ++*pos; + return task_vma_seq_get_next(info); +} + +struct bpf_iter__task_vma { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct task_struct *, task); + __bpf_md_ptr(struct vm_area_struct *, vma); +}; + +DEFINE_BPF_ITER_FUNC(task_vma, struct bpf_iter_meta *meta, + struct task_struct *task, struct vm_area_struct *vma) + +static int __task_vma_seq_show(struct seq_file *seq, bool in_stop) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + struct bpf_iter__task_vma ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.task = info->task; + ctx.vma = info->vma; + return bpf_iter_run_prog(prog, &ctx); +} + +static int task_vma_seq_show(struct seq_file *seq, void *v) +{ + return __task_vma_seq_show(seq, false); +} + +static void task_vma_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + + if (!v) { + (void)__task_vma_seq_show(seq, true); + } else { + /* info->vma has not been seen by the BPF program. If the + * user space reads more, task_vma_seq_get_next should + * return this vma again. Set prev_vm_start to ~0UL, + * so that we don't skip the vma returned by the next + * find_vma() (case task_vma_iter_find_vma in + * task_vma_seq_get_next()). + */ + info->prev_vm_start = ~0UL; + info->prev_vm_end = info->vma->vm_end; + mmap_read_unlock(info->mm); + mmput(info->mm); + info->mm = NULL; + put_task_struct(info->task); + info->task = NULL; + } +} + +static const struct seq_operations task_vma_seq_ops = { + .start = task_vma_seq_start, + .next = task_vma_seq_next, + .stop = task_vma_seq_stop, + .show = task_vma_seq_show, +}; + +static const struct bpf_iter_seq_info task_seq_info = { .seq_ops = &task_seq_ops, .init_seq_private = init_seq_pidns, .fini_seq_private = fini_seq_pidns, .seq_priv_size = sizeof(struct bpf_iter_seq_task_info), +}; + +static int bpf_iter_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info) +{ + switch (aux->task.type) { + case BPF_TASK_ITER_TID: + info->iter.task.tid = aux->task.pid; + break; + case BPF_TASK_ITER_TGID: + info->iter.task.pid = aux->task.pid; + break; + default: + break; + } + return 0; +} + +static void bpf_iter_task_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq) +{ + seq_printf(seq, "task_type:\t%s\n", iter_task_type_names[aux->task.type]); + if (aux->task.type == BPF_TASK_ITER_TID) + seq_printf(seq, "tid:\t%u\n", aux->task.pid); + else if (aux->task.type == BPF_TASK_ITER_TGID) + seq_printf(seq, "pid:\t%u\n", aux->task.pid); +} + +static struct bpf_iter_reg task_reg_info = { + .target = "task", + .attach_target = bpf_iter_attach_task, + .feature = BPF_ITER_RESCHED, .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, + .show_fdinfo = bpf_iter_task_show_fdinfo, }; -static const struct bpf_iter_reg task_file_reg_info = { - .target = "task_file", +static const struct bpf_iter_seq_info task_file_seq_info = { .seq_ops = &task_file_seq_ops, .init_seq_private = init_seq_pidns, .fini_seq_private = fini_seq_pidns, .seq_priv_size = sizeof(struct bpf_iter_seq_task_file_info), +}; + +static struct bpf_iter_reg task_file_reg_info = { + .target = "task_file", + .attach_target = bpf_iter_attach_task, + .feature = BPF_ITER_RESCHED, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__task_file, task), @@ -338,16 +720,351 @@ static const struct bpf_iter_reg task_file_reg_info = { { offsetof(struct bpf_iter__task_file, file), PTR_TO_BTF_ID_OR_NULL }, }, + .seq_info = &task_file_seq_info, + .fill_link_info = bpf_iter_fill_link_info, + .show_fdinfo = bpf_iter_task_show_fdinfo, +}; + +static const struct bpf_iter_seq_info task_vma_seq_info = { + .seq_ops = &task_vma_seq_ops, + .init_seq_private = init_seq_pidns, + .fini_seq_private = fini_seq_pidns, + .seq_priv_size = sizeof(struct bpf_iter_seq_task_vma_info), +}; + +static struct bpf_iter_reg task_vma_reg_info = { + .target = "task_vma", + .attach_target = bpf_iter_attach_task, + .feature = BPF_ITER_RESCHED, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__task_vma, task), + PTR_TO_BTF_ID_OR_NULL }, + { offsetof(struct bpf_iter__task_vma, vma), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &task_vma_seq_info, + .fill_link_info = bpf_iter_fill_link_info, + .show_fdinfo = bpf_iter_task_show_fdinfo, +}; + +BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start, + bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags) +{ + struct mmap_unlock_irq_work *work = NULL; + struct vm_area_struct *vma; + bool irq_work_busy = false; + struct mm_struct *mm; + int ret = -ENOENT; + + if (flags) + return -EINVAL; + + if (!task) + return -ENOENT; + + mm = task->mm; + if (!mm) + return -ENOENT; + + irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); + + if (irq_work_busy || !mmap_read_trylock(mm)) + return -EBUSY; + + vma = find_vma(mm, start); + + if (vma && vma->vm_start <= start && vma->vm_end > start) { + callback_fn((u64)(long)task, (u64)(long)vma, + (u64)(long)callback_ctx, 0, 0); + ret = 0; + } + bpf_mmap_unlock_mm(work, mm); + return ret; +} + +const struct bpf_func_proto bpf_find_vma_proto = { + .func = bpf_find_vma, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_FUNC, + .arg4_type = ARG_PTR_TO_STACK_OR_NULL, + .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) +{ + struct mmap_unlock_irq_work *work; + + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return; + + work = container_of(entry, struct mmap_unlock_irq_work, irq_work); + mmap_read_unlock_non_owner(work->mm); +} + static int __init task_iter_init(void) { - int ret; + struct mmap_unlock_irq_work *work; + int ret, cpu; + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&mmap_unlock_work, cpu); + init_irq_work(&work->irq_work, do_mmap_read_unlock); + } + + task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; ret = bpf_iter_reg_target(&task_reg_info); if (ret) return ret; - return bpf_iter_reg_target(&task_file_reg_info); + task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE]; + ret = bpf_iter_reg_target(&task_file_reg_info); + if (ret) + return ret; + + task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; + return bpf_iter_reg_target(&task_vma_reg_info); } late_initcall(task_iter_init); diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c new file mode 100644 index 000000000000..2e4885e7781f --- /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 = tcx->location == 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 = tcx->location == 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 = tcx->location == 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", + tcx->location, + tcx->location == 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 = tcx->location; + 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); + tcx->location = 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 ceac5281bd31..9dbc31b25e3d 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -111,28 +111,31 @@ struct tnum tnum_xor(struct tnum a, struct tnum b) return TNUM(v & ~mu, mu); } -/* half-multiply add: acc += (unknown * mask * value). - * An intermediate step in the multiply algorithm. +/* 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. */ -static struct tnum hma(struct tnum acc, u64 value, u64 mask) -{ - while (mask) { - if (mask & 1) - acc = tnum_add(acc, TNUM(0, value)); - mask >>= 1; - value <<= 1; - } - return acc; -} - struct tnum tnum_mul(struct tnum a, struct tnum b) { - struct tnum acc; - u64 pi; - - pi = a.value * b.value; - acc = hma(TNUM(pi, 0), a.mask, b.mask | b.value); - return hma(acc, b.mask, a.value); + u64 acc_v = a.value * b.value; + struct tnum acc_m = 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)); + /* LSB of tnum a is uncertain */ + else if (a.mask & 1) + acc_m = tnum_add(acc_m, TNUM(0, b.value | b.mask)); + /* 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); } /* Note that if a and b disagree - i.e. one has a 'known 1' where the other has @@ -169,12 +172,6 @@ bool tnum_in(struct tnum a, struct tnum b) return a.value == b.value; } -int tnum_strn(char *str, size_t size, struct tnum a) -{ - return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); -} -EXPORT_SYMBOL_GPL(tnum_strn); - int tnum_sbin(char *str, size_t size, struct tnum a) { size_t n; @@ -205,7 +202,12 @@ struct tnum tnum_clear_subreg(struct tnum a) return tnum_lshift(tnum_rshift(a, 32), 32); } +struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg) +{ + return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg)); +} + struct tnum tnum_const_subreg(struct tnum a, u32 value) { - return tnum_or(tnum_clear_subreg(a), tnum_const(value)); + return tnum_with_subreg(a, tnum_const(value)); } diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..26057aa13503 --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,255 @@ +#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 = { }; + +static 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_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + CLASS(fd, f)(attr->token_create.bpffs_fd); + struct path path; + struct super_block *sb; + umode_t mode; + int err, fd; + + 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 */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + return PTR_ERR(file); + } + + token = kzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(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) + goto out_token; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); + return err; +} + +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 9be85aa4ec5f..c4b1a98ff726 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -7,6 +7,12 @@ #include <linux/rbtree_latch.h> #include <linux/perf_event.h> #include <linux/btf.h> +#include <linux/rcupdate_trace.h> +#include <linux/rcupdate_wait.h> +#include <linux/static_call.h> +#include <linux/bpf_verifier.h> +#include <linux/bpf_lsm.h> +#include <linux/delay.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -23,26 +29,100 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; /* serializes access to trampoline_table */ static DEFINE_MUTEX(trampoline_mutex); -void *bpf_jit_alloc_exec_page(void) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex); + +static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, enum ftrace_ops_cmd cmd) { - void *image; + struct bpf_trampoline *tr = ops->private; + int ret = 0; - image = bpf_jit_alloc_exec(PAGE_SIZE); - if (!image) - return NULL; + if (cmd == FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF) { + /* This is called inside register_ftrace_direct_multi(), so + * tr->mutex is already locked. + */ + lockdep_assert_held_once(&tr->mutex); + + /* Instead of updating the trampoline here, we propagate + * -EAGAIN to register_ftrace_direct(). Then we can + * retry register_ftrace_direct() after updating the + * trampoline. + */ + if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) && + !(tr->flags & BPF_TRAMP_F_ORIG_STACK)) { + if (WARN_ON_ONCE(tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY)) + return -EBUSY; + + tr->flags |= BPF_TRAMP_F_SHARE_IPMODIFY; + return -EAGAIN; + } + + return 0; + } - set_vm_flush_reset_perms(image); - /* Keep image as writeable. The alternative is to keep flipping ro/rw - * everytime new program is attached or detached. + /* The normal locking order is + * tr->mutex => direct_mutex (ftrace.c) => ftrace_lock (ftrace.c) + * + * The following two commands are called from + * + * prepare_direct_functions_for_ipmodify + * cleanup_direct_functions_after_ipmodify + * + * In both cases, direct_mutex is already locked. Use + * mutex_trylock(&tr->mutex) to avoid deadlock in race condition + * (something else is making changes to this same trampoline). */ - set_memory_x((long)image, 1); - return image; + if (!mutex_trylock(&tr->mutex)) { + /* sleep 1 ms to make sure whatever holding tr->mutex makes + * some progress. + */ + msleep(1); + return -EAGAIN; + } + + switch (cmd) { + case FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER: + tr->flags |= BPF_TRAMP_F_SHARE_IPMODIFY; + + if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) && + !(tr->flags & BPF_TRAMP_F_ORIG_STACK)) + ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */); + break; + case FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER: + tr->flags &= ~BPF_TRAMP_F_SHARE_IPMODIFY; + + if (tr->flags & BPF_TRAMP_F_ORIG_STACK) + ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */); + break; + default: + ret = -EINVAL; + break; + } + + mutex_unlock(&tr->mutex); + return ret; } +#endif -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym) +bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + enum bpf_attach_type eatype = prog->expected_attach_type; + enum bpf_prog_type ptype = prog->type; + + return (ptype == BPF_PROG_TYPE_TRACING && + (eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN)) || + (ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC); +} + +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); @@ -55,19 +135,10 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym) PAGE_SIZE, true, ksym->name); } -static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr) -{ - struct bpf_ksym *ksym = &tr->ksym; - - snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key); - bpf_image_ksym_add(tr->image, ksym); -} - -struct bpf_trampoline *bpf_trampoline_lookup(u64 key) +static struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { struct bpf_trampoline *tr; struct hlist_head *head; - void *image; int i; mutex_lock(&trampoline_mutex); @@ -81,14 +152,16 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) tr = kzalloc(sizeof(*tr), GFP_KERNEL); if (!tr) goto out; - - /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ - image = bpf_jit_alloc_exec_page(); - if (!image) { +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + tr->fops = kzalloc(sizeof(struct ftrace_ops), GFP_KERNEL); + if (!tr->fops) { kfree(tr); tr = NULL; goto out; } + tr->fops->private = tr; + tr->fops->ops_func = bpf_tramp_ftrace_ops_func; +#endif tr->key = key; INIT_HLIST_NODE(&tr->hlist); @@ -97,47 +170,38 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) mutex_init(&tr->mutex); for (i = 0; i < BPF_TRAMP_MAX; i++) INIT_HLIST_HEAD(&tr->progs_hlist[i]); - tr->image = image; - INIT_LIST_HEAD_RCU(&tr->ksym.lnode); - bpf_trampoline_ksym_add(tr); out: mutex_unlock(&trampoline_mutex); return tr; } -static int is_ftrace_location(void *ip) -{ - long addr; - - addr = ftrace_location((long)ip); - if (!addr) - return 0; - if (WARN_ON_ONCE(addr != (long)ip)) - return -EFAULT; - return 1; -} - static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) { void *ip = tr->func.addr; int ret; if (tr->func.ftrace_managed) - ret = unregister_ftrace_direct((long)ip, (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); + return ret; } -static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr) +static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr, + bool lock_direct_mutex) { void *ip = tr->func.addr; int ret; - if (tr->func.ftrace_managed) - ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr); - else + if (tr->func.ftrace_managed) { + if (lock_direct_mutex) + ret = modify_ftrace_direct(tr->fops, (long)new_addr); + else + ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr); + } else { ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr); + } return ret; } @@ -145,93 +209,301 @@ static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_ad static int register_fentry(struct bpf_trampoline *tr, void *new_addr) { void *ip = tr->func.addr; + unsigned long faddr; int ret; - ret = is_ftrace_location(ip); - if (ret < 0) - return ret; - tr->func.ftrace_managed = ret; + faddr = ftrace_location((unsigned long)ip); + if (faddr) { + if (!tr->fops) + return -ENOTSUPP; + tr->func.ftrace_managed = true; + } - if (tr->func.ftrace_managed) - ret = register_ftrace_direct((long)ip, (long)new_addr); - else + if (tr->func.ftrace_managed) { + ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1); + ret = register_ftrace_direct(tr->fops, (long)new_addr); + } else { ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + } + return ret; } -static struct bpf_tramp_progs * -bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total) +static struct bpf_tramp_links * +bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg) { - const struct bpf_prog_aux *aux; - struct bpf_tramp_progs *tprogs; - struct bpf_prog **progs; + struct bpf_tramp_link *link; + struct bpf_tramp_links *tlinks; + struct bpf_tramp_link **links; int kind; *total = 0; - tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); - if (!tprogs) + tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); + if (!tlinks) return ERR_PTR(-ENOMEM); for (kind = 0; kind < BPF_TRAMP_MAX; kind++) { - tprogs[kind].nr_progs = tr->progs_cnt[kind]; + tlinks[kind].nr_links = tr->progs_cnt[kind]; *total += tr->progs_cnt[kind]; - progs = tprogs[kind].progs; + links = tlinks[kind].links; - hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) - *progs++ = aux->prog; + hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) { + *ip_arg |= link->link.prog->call_get_func_ip; + *links++ = link; + } } - return tprogs; + 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_tramp_image_free(im); } -static int bpf_trampoline_update(struct bpf_trampoline *tr) +/* callback, fexit step 3 or fentry step 2 */ +static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu) { - void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2; - void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2; - struct bpf_tramp_progs *tprogs; - u32 flags = BPF_TRAMP_F_RESTORE_REGS; - int err, total; + struct bpf_tramp_image *im; - tprogs = bpf_trampoline_get_progs(tr, &total); - if (IS_ERR(tprogs)) - return PTR_ERR(tprogs); + im = container_of(rcu, struct bpf_tramp_image, rcu); + INIT_WORK(&im->work, __bpf_tramp_image_put_deferred); + schedule_work(&im->work); +} + +/* callback, fexit step 2. Called after percpu_ref_kill confirms. */ +static void __bpf_tramp_image_release(struct percpu_ref *pcref) +{ + struct bpf_tramp_image *im; + + im = container_of(pcref, struct bpf_tramp_image, pcref); + call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu); +} + +/* callback, fexit or fentry step 1 */ +static void __bpf_tramp_image_put_rcu_tasks(struct rcu_head *rcu) +{ + struct bpf_tramp_image *im; + + im = container_of(rcu, struct bpf_tramp_image, rcu); + if (im->ip_after_call) + /* the case of fmod_ret/fexit trampoline and CONFIG_PREEMPTION=y */ + percpu_ref_kill(&im->pcref); + else + /* the case of fentry trampoline */ + call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu); +} + +static void bpf_tramp_image_put(struct bpf_tramp_image *im) +{ + /* The trampoline image that calls original function is using: + * rcu_read_lock_trace to protect sleepable bpf progs + * rcu_read_lock to protect normal bpf progs + * percpu_ref to protect trampoline itself + * rcu tasks to protect trampoline asm not covered by percpu_ref + * (which are few asm insns before __bpf_tramp_enter and + * after __bpf_tramp_exit) + * + * The trampoline is unreachable before bpf_tramp_image_put(). + * + * First, patch the trampoline to avoid calling into fexit progs. + * The progs will be freed even if the original function is still + * executing or sleeping. + * In case of CONFIG_PREEMPT=y use call_rcu_tasks() to wait on + * first few asm instructions to execute and call into + * __bpf_tramp_enter->percpu_ref_get. + * Then use percpu_ref_kill to wait for the trampoline and the original + * function to finish. + * Then use call_rcu_tasks() to make sure few asm insns in + * the trampoline epilogue are done as well. + * + * In !PREEMPT case the task that got interrupted in the first asm + * insns won't go through an RCU quiescent state which the + * percpu_ref_kill will be waiting for. Hence the first + * call_rcu_tasks() is not necessary. + */ + if (im->ip_after_call) { + int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP, + NULL, im->ip_epilogue); + WARN_ON(err); + if (IS_ENABLED(CONFIG_TASKS_RCU)) + call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks); + else + percpu_ref_kill(&im->pcref); + return; + } + + /* The trampoline without fexit and fmod_ret progs doesn't call original + * function and doesn't use percpu_ref. + * Use call_rcu_tasks_trace() to wait for sleepable progs to finish. + * Then use call_rcu_tasks() to wait for the rest of trampoline asm + * and normal progs. + */ + call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); +} + +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size) +{ + struct bpf_tramp_image *im; + struct bpf_ksym *ksym; + void *image; + int err = -ENOMEM; + + im = kzalloc(sizeof(*im), GFP_KERNEL); + if (!im) + goto out; + + err = bpf_jit_charge_modmem(size); + if (err) + goto out_free_im; + im->size = size; + + err = -ENOMEM; + im->image = image = arch_alloc_bpf_trampoline(size); + if (!image) + goto out_uncharge; + + err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL); + if (err) + goto out_free_image; + + ksym = &im->ksym; + INIT_LIST_HEAD_RCU(&ksym->lnode); + 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: + arch_free_bpf_trampoline(im->image, im->size); +out_uncharge: + bpf_jit_uncharge_modmem(size); +out_free_im: + kfree(im); +out: + return ERR_PTR(err); +} + +static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex) +{ + struct bpf_tramp_image *im; + struct bpf_tramp_links *tlinks; + u32 orig_flags = tr->flags; + bool ip_arg = false; + 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, old_image); - tr->selector = 0; + err = unregister_fentry(tr, tr->cur_image->image); + bpf_tramp_image_put(tr->cur_image); + tr->cur_image = NULL; goto out; } - if (tprogs[BPF_TRAMP_FEXIT].nr_progs || - tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs) - flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; + /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */ + tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX); - /* Though the second half of trampoline page is unused a task could be - * preempted in the middle of the first half of trampoline and two - * updates to trampoline would change the code from underneath the - * preempted task. Hence wait for tasks to voluntarily schedule or go - * to userspace. - */ + if (tlinks[BPF_TRAMP_FEXIT].nr_links || + tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) { + /* NOTE: BPF_TRAMP_F_RESTORE_REGS and BPF_TRAMP_F_SKIP_FRAME + * should not be set together. + */ + tr->flags |= BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; + } else { + tr->flags |= BPF_TRAMP_F_RESTORE_REGS; + } + + if (ip_arg) + tr->flags |= BPF_TRAMP_F_IP_ARG; + +#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; +#endif + + 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; + } - synchronize_rcu_tasks(); + im = bpf_tramp_image_alloc(tr->key, size); + if (IS_ERR(im)) { + err = PTR_ERR(im); + goto out; + } - err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2, - &tr->func.model, flags, tprogs, + 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; + + err = arch_protect_bpf_trampoline(im->image, im->size); + if (err) + goto out_free; - if (tr->selector) + WARN_ON(tr->cur_image && total == 0); + if (tr->cur_image) /* progs already running at this address */ - err = modify_fentry(tr, old_image, new_image); + err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex); else /* first time registering */ - err = register_fentry(tr, new_image); + err = register_fentry(tr, im->image); + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + if (err == -EAGAIN) { + /* -EAGAIN from bpf_tramp_ftrace_ops_func. Now + * 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; + + /* free im memory and reallocate later */ + bpf_tramp_image_free(im); + goto again; + } +#endif if (err) - goto out; - tr->selector++; + goto out_free; + + if (tr->cur_image) + bpf_tramp_image_put(tr->cur_image); + tr->cur_image = im; out: - kfree(tprogs); + /* If any error happens, restore previous flags */ + if (err) + tr->flags = orig_flags; + 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) @@ -256,149 +528,601 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) } } -int bpf_trampoline_link_prog(struct bpf_prog *prog) +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_trampoline *tr; + struct bpf_tramp_link *link_exiting; int err = 0; - int cnt; + int cnt = 0, i; - tr = prog->aux->trampoline; - kind = bpf_attach_type_to_tramp(prog); - mutex_lock(&tr->mutex); - if (tr->extension_prog) { + kind = bpf_attach_type_to_tramp(link->link.prog); + if (tr->extension_prog) /* cannot attach fentry/fexit if extension prog is attached. * cannot overwrite extension prog either. */ - err = -EBUSY; - goto out; - } - cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]; + return -EBUSY; + + for (i = 0; i < BPF_TRAMP_MAX; i++) + cnt += tr->progs_cnt[i]; + if (kind == BPF_TRAMP_REPLACE) { /* Cannot attach extension if fentry/fexit are in use. */ - if (cnt) { - err = -EBUSY; - goto out; - } - tr->extension_prog = prog; - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL, - prog->bpf_func); - goto out; - } - if (cnt >= BPF_MAX_TRAMP_PROGS) { - err = -E2BIG; - goto out; + 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, + link->link.prog->bpf_func); } - if (!hlist_unhashed(&prog->aux->tramp_hlist)) { + if (cnt >= BPF_MAX_TRAMP_LINKS) + return -E2BIG; + if (!hlist_unhashed(&link->tramp_hlist)) /* prog already linked */ - err = -EBUSY; - goto out; + return -EBUSY; + hlist_for_each_entry(link_exiting, &tr->progs_hlist[kind], tramp_hlist) { + if (link_exiting->link.prog != link->link.prog) + continue; + /* prog already linked */ + return -EBUSY; } - hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]); + + hlist_add_head(&link->tramp_hlist, &tr->progs_hlist[kind]); tr->progs_cnt[kind]++; - err = bpf_trampoline_update(prog->aux->trampoline); + err = bpf_trampoline_update(tr, true /* lock_direct_mutex */); if (err) { - hlist_del(&prog->aux->tramp_hlist); + hlist_del_init(&link->tramp_hlist); tr->progs_cnt[kind]--; } -out: + return err; +} + +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, tgt_prog); mutex_unlock(&tr->mutex); return err; } -/* bpf_trampoline_unlink_prog() should never fail. */ -int bpf_trampoline_unlink_prog(struct bpf_prog *prog) +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; - struct bpf_trampoline *tr; int err; - tr = prog->aux->trampoline; - kind = bpf_attach_type_to_tramp(prog); - mutex_lock(&tr->mutex); + kind = bpf_attach_type_to_tramp(link->link.prog); if (kind == BPF_TRAMP_REPLACE) { WARN_ON_ONCE(!tr->extension_prog); err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, tr->extension_prog->bpf_func, NULL); tr->extension_prog = NULL; - goto out; + guard(mutex)(&tgt_prog->aux->ext_mutex); + tgt_prog->aux->is_extended = false; + return err; } - hlist_del(&prog->aux->tramp_hlist); + hlist_del_init(&link->tramp_hlist); tr->progs_cnt[kind]--; - err = bpf_trampoline_update(prog->aux->trampoline); -out: + return bpf_trampoline_update(tr, true /* lock_direct_mutex */); +} + +/* bpf_trampoline_unlink_prog() should never fail. */ +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, tgt_prog); + mutex_unlock(&tr->mutex); + return err; +} + +#if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) +static void bpf_shim_tramp_link_release(struct bpf_link *link) +{ + struct bpf_shim_tramp_link *shim_link = + container_of(link, struct bpf_shim_tramp_link, link.link); + + /* paired with 'shim_link->trampoline = tr' in bpf_trampoline_link_cgroup_shim */ + if (!shim_link->trampoline) + return; + + WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); + bpf_trampoline_put(shim_link->trampoline); +} + +static void bpf_shim_tramp_link_dealloc(struct bpf_link *link) +{ + struct bpf_shim_tramp_link *shim_link = + container_of(link, struct bpf_shim_tramp_link, link.link); + + kfree(shim_link); +} + +static const struct bpf_link_ops bpf_shim_tramp_link_lops = { + .release = bpf_shim_tramp_link_release, + .dealloc = bpf_shim_tramp_link_dealloc, +}; + +static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog, + bpf_func_t bpf_func, + int cgroup_atype) +{ + struct bpf_shim_tramp_link *shim_link = NULL; + struct bpf_prog *p; + + shim_link = kzalloc(sizeof(*shim_link), GFP_USER); + if (!shim_link) + return NULL; + + p = bpf_prog_alloc(1, 0); + if (!p) { + kfree(shim_link); + return NULL; + } + + p->jited = false; + p->bpf_func = bpf_func; + + p->aux->cgroup_atype = cgroup_atype; + p->aux->attach_func_proto = prog->aux->attach_func_proto; + p->aux->attach_btf_id = prog->aux->attach_btf_id; + p->aux->attach_btf = prog->aux->attach_btf; + btf_get(p->aux->attach_btf); + p->type = BPF_PROG_TYPE_LSM; + 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_cgroup_atype_get(p->aux->attach_btf_id, cgroup_atype); + + return shim_link; +} + +static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr, + bpf_func_t bpf_func) +{ + struct bpf_tramp_link *link; + int kind; + + for (kind = 0; kind < BPF_TRAMP_MAX; kind++) { + hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) { + struct bpf_prog *p = link->link.prog; + + if (p->bpf_func == bpf_func) + return container_of(link, struct bpf_shim_tramp_link, link); + } + } + + return NULL; +} + +int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype) +{ + struct bpf_shim_tramp_link *shim_link = NULL; + struct bpf_attach_target_info tgt_info = {}; + struct bpf_trampoline *tr; + bpf_func_t bpf_func; + u64 key; + int err; + + err = bpf_check_attach_target(NULL, prog, NULL, + prog->aux->attach_btf_id, + &tgt_info); + if (err) + return err; + + key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, + prog->aux->attach_btf_id); + + bpf_lsm_find_cgroup_shim(prog, &bpf_func); + tr = bpf_trampoline_get(key, &tgt_info); + if (!tr) + return -ENOMEM; + + mutex_lock(&tr->mutex); + + shim_link = cgroup_shim_find(tr, bpf_func); + if (shim_link) { + /* Reusing existing shim attached by the other program. */ + bpf_link_inc(&shim_link->link.link); + + mutex_unlock(&tr->mutex); + bpf_trampoline_put(tr); /* bpf_trampoline_get above */ + return 0; + } + + /* Allocate and install new shim. */ + + shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype); + if (!shim_link) { + err = -ENOMEM; + goto err; + } + + err = __bpf_trampoline_link_prog(&shim_link->link, tr, NULL); + if (err) + goto err; + + shim_link->trampoline = tr; + /* note, we're still holding tr refcnt from above */ + + mutex_unlock(&tr->mutex); + + return 0; +err: mutex_unlock(&tr->mutex); + + if (shim_link) + bpf_link_put(&shim_link->link.link); + + /* have to release tr while _not_ holding its mutex */ + bpf_trampoline_put(tr); /* bpf_trampoline_get above */ + return err; } +void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) +{ + struct bpf_shim_tramp_link *shim_link = NULL; + struct bpf_trampoline *tr; + bpf_func_t bpf_func; + u64 key; + + key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, + prog->aux->attach_btf_id); + + bpf_lsm_find_cgroup_shim(prog, &bpf_func); + tr = bpf_trampoline_lookup(key); + if (WARN_ON_ONCE(!tr)) + return; + + mutex_lock(&tr->mutex); + shim_link = cgroup_shim_find(tr, bpf_func); + mutex_unlock(&tr->mutex); + + if (shim_link) + bpf_link_put(&shim_link->link.link); + + bpf_trampoline_put(tr); /* bpf_trampoline_lookup above */ +} +#endif + +struct bpf_trampoline *bpf_trampoline_get(u64 key, + struct bpf_attach_target_info *tgt_info) +{ + struct bpf_trampoline *tr; + + tr = bpf_trampoline_lookup(key); + if (!tr) + return NULL; + + mutex_lock(&tr->mutex); + if (tr->func.addr) + goto out; + + memcpy(&tr->func.model, &tgt_info->fmodel, sizeof(tgt_info->fmodel)); + tr->func.addr = (void *)tgt_info->tgt_addr; +out: + mutex_unlock(&tr->mutex); + return tr; +} + void bpf_trampoline_put(struct bpf_trampoline *tr) { + int i; + if (!tr) return; mutex_lock(&trampoline_mutex); if (!refcount_dec_and_test(&tr->refcnt)) goto out; WARN_ON_ONCE(mutex_is_locked(&tr->mutex)); - if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FENTRY]))) - goto out; - if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) - goto out; - bpf_image_ksym_del(&tr->ksym); - /* wait for tasks to get out of trampoline before freeing it */ - synchronize_rcu_tasks(); - bpf_jit_free_exec(tr->image); + + for (i = 0; i < BPF_TRAMP_MAX; i++) + if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[i]))) + goto out; + + /* This code will be executed even when the last bpf_tramp_image + * is alive. All progs are detached from the trampoline and the + * trampoline image is patched with jmp into epilogue to skip + * fexit progs. The fentry-only trampoline will be freed via + * multiple rcu callbacks. + */ hlist_del(&tr->hlist); + if (tr->fops) { + ftrace_free_filter(tr->fops); + kfree(tr->fops); + } kfree(tr); out: mutex_unlock(&trampoline_mutex); } -/* The logic is similar to BPF_PROG_RUN, but with an explicit +#define NO_START_TIME 1 +static __always_inline u64 notrace bpf_prog_start_time(void) +{ + u64 start = NO_START_TIME; + + if (static_branch_unlikely(&bpf_stats_enabled_key)) { + start = sched_clock(); + if (unlikely(!start)) + start = NO_START_TIME; + } + return start; +} + +/* The logic is similar to bpf_prog_run(), but with an explicit * rcu_read_lock() and migrate_disable() which are required * for the trampoline. The macro is split into - * call _bpf_prog_enter + * call __bpf_prog_enter * call prog->bpf_func * call __bpf_prog_exit + * + * __bpf_prog_enter returns: + * 0 - skip execution of the bpf prog + * 1 - execute bpf prog + * [2..MAX_U64] - execute bpf prog and record execution time. + * This is start time. */ -u64 notrace __bpf_prog_enter(void) +static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { - u64 start = 0; - rcu_read_lock(); migrate_disable(); - if (static_branch_unlikely(&bpf_stats_enabled_key)) - start = sched_clock(); - return start; + + 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(); } -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) - __releases(RCU) +static void notrace update_prog_stats(struct bpf_prog *prog, + u64 start) { struct bpf_prog_stats *stats; if (static_branch_unlikely(&bpf_stats_enabled_key) && - /* static_key could be enabled in __bpf_prog_enter - * and disabled in __bpf_prog_exit. + /* static_key could be enabled in __bpf_prog_enter* + * and disabled in __bpf_prog_exit*. * And vice versa. - * Hence check that 'start' is not zero. + * Hence check that 'start' is valid. */ - start) { - stats = this_cpu_ptr(prog->aux->stats); - u64_stats_update_begin(&stats->syncp); - stats->cnt++; - stats->nsecs += sched_clock() - start; - u64_stats_update_end(&stats->syncp); + start > NO_START_TIME) { + u64 duration = sched_clock() - start; + unsigned long flags; + + stats = this_cpu_ptr(prog->stats); + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, duration); + u64_stats_update_end_irqrestore(&stats->syncp, flags); } +} + +static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) + __releases(RCU) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + update_prog_stats(prog, start); + this_cpu_dec(*(prog->active)); + migrate_enable(); + rcu_read_unlock(); +} + +static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) + __acquires(RCU) +{ + /* Runtime stats are exported via actual BPF_LSM_CGROUP + * programs, not the shims. + */ + rcu_read_lock(); + migrate_disable(); + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + + return NO_START_TIME; +} + +static void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) + __releases(RCU) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + migrate_enable(); + rcu_read_unlock(); +} + +u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) +{ + rcu_read_lock_trace(); + 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; + } + return bpf_prog_start_time(); +} + +void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + update_prog_stats(prog, start); + this_cpu_dec(*(prog->active)); + migrate_enable(); + rcu_read_unlock_trace(); +} + +static u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) +{ + rcu_read_lock_trace(); + migrate_disable(); + might_fault(); + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + + return bpf_prog_start_time(); +} + +static void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + update_prog_stats(prog, start); + migrate_enable(); + rcu_read_unlock_trace(); +} + +static u64 notrace __bpf_prog_enter(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) + __acquires(RCU) +{ + rcu_read_lock(); + migrate_disable(); + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + + return bpf_prog_start_time(); +} + +static void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) + __releases(RCU) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + update_prog_stats(prog, start); migrate_enable(); rcu_read_unlock(); } +void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr) +{ + percpu_ref_get(&tr->pcref); +} + +void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) +{ + percpu_ref_put(&tr->pcref); +} + +bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) +{ + bool sleepable = prog->sleepable; + + if (bpf_prog_check_recur(prog)) + return sleepable ? __bpf_prog_enter_sleepable_recur : + __bpf_prog_enter_recur; + + if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_CGROUP) + return __bpf_prog_enter_lsm_cgroup; + + return sleepable ? __bpf_prog_enter_sleepable : __bpf_prog_enter; +} + +bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) +{ + bool sleepable = prog->sleepable; + + if (bpf_prog_check_recur(prog)) + return sleepable ? __bpf_prog_exit_sleepable_recur : + __bpf_prog_exit_recur; + + if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_CGROUP) + return __bpf_prog_exit_lsm_cgroup; + + return sleepable ? __bpf_prog_exit_sleepable : __bpf_prog_exit; +} + int __weak -arch_prepare_bpf_trampoline(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_progs *tprogs, - void *orig_call) + struct bpf_tramp_links *tlinks, + 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 94cead5a43e5..60611df77957 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4,6 +4,7 @@ * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> +#include <linux/bpf-cgroup.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> @@ -21,6 +22,14 @@ #include <linux/ctype.h> #include <linux/error-injection.h> #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" @@ -35,6 +44,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #undef BPF_LINK_TYPE }; +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. @@ -46,7 +58,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * - unreachable insns exist (shouldn't be a forest. program = one function) * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. - * Since it's analyzing all pathes through the program, the length of the + * Since it's analyzing all paths through the program, the length of the * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k @@ -131,7 +143,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * If it's ok, then verifier allows this BPF_CALL insn and looks at * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function - * returns ether pointer to map value or NULL. + * returns either pointer to map value or NULL. * * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' * insn, the register holding that pointer in the true branch changes state to @@ -162,7 +174,7 @@ 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' */ @@ -180,28 +192,39 @@ 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 + +#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 void specialize_kfunc(struct bpf_verifier_env *env, + u32 func_id, u16 offset, unsigned long *addr); +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) @@ -227,516 +250,1217 @@ 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) && + insn->src_reg == BPF_PSEUDO_CALL; +} + +static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_CALL) && + insn->src_reg == BPF_PSEUDO_KFUNC_CALL; +} + struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; bool pkt_access; + u8 release_regno; int regno; int access_size; int mem_size; u64 msize_max_value; int ref_obj_id; + int dynptr_id; + int map_uid; int func_id; + struct btf *btf; u32 btf_id; + struct btf *ret_btf; + u32 ret_btf_id; + u32 subprogno; + struct btf_field *kptr_field; + s64 const_map_key; +}; + +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; + + /* 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; + + 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; }; struct btf *btf_vmlinux; +static const char *btf_type_name(const struct btf *btf, u32 id) +{ + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); +} + static DEFINE_MUTEX(bpf_verifier_lock); +static DEFINE_MUTEX(bpf_percpu_ma_lock); -static const struct bpf_line_info * -find_linfo(const struct bpf_verifier_env *env, u32 insn_off) +__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { - const struct bpf_line_info *linfo; - const struct bpf_prog *prog; - u32 i, nr_linfo; + struct bpf_verifier_env *env = private_data; + va_list args; - prog = env->prog; - nr_linfo = prog->aux->nr_linfo; + if (!bpf_verifier_log_needed(&env->log)) + return; - if (!nr_linfo || insn_off >= prog->len) - return NULL; + va_start(args, fmt); + bpf_verifier_vlog(&env->log, fmt, args); + va_end(args); +} - linfo = prog->aux->linfo; - for (i = 1; i < nr_linfo; i++) - if (insn_off < linfo[i].insn_off) - break; +static void verbose_invalid_scalar(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + struct bpf_retval_range range, const char *ctx, + const char *reg_name) +{ + bool unknown = true; - return &linfo[i - 1]; + 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; + } + if (unknown) + verbose(env, " unknown scalar value"); + verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval); } -void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, - va_list args) +static bool reg_not_null(const struct bpf_reg_state *reg) { - unsigned int n; + enum bpf_reg_type type; - n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); + type = reg->type; + if (type_may_be_null(type)) + return false; - WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, - "verifier log line truncated - local buffer too short\n"); + 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 || + (type == PTR_TO_BTF_ID && is_trusted_reg(reg)) || + type == PTR_TO_MEM; +} - n = min(log->len_total - log->len_used - 1, n); - log->kbuf[n] = '\0'; +static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) +{ + struct btf_record *rec = NULL; + struct btf_struct_meta *meta; - if (log->level == BPF_LOG_KERNEL) { - pr_err("BPF:%s\n", log->kbuf); - return; + if (reg->type == PTR_TO_MAP_VALUE) { + rec = reg->map_ptr->record; + } else if (type_is_ptr_alloc_obj(reg->type)) { + meta = btf_find_struct_meta(reg->btf, reg->btf_id); + if (meta) + rec = meta->record; } - if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) - log->len_used += n; - else - log->ubuf = NULL; + return rec; } -static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos) +static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) { - char zero = 0; + struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; - if (!bpf_verifier_log_needed(log)) - return; + return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL; +} + +static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) +{ + struct bpf_func_info *info; + + if (!env->prog->aux->func_info) + return ""; - log->len_used = new_pos; - if (put_user(zero, log->ubuf + new_pos)) - log->ubuf = NULL; + info = &env->prog->aux->func_info[subprog]; + return btf_type_name(env->prog->aux->btf, info->type_id); } -/* 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, ...) +static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog) { - va_list args; + struct bpf_subprog_info *info = subprog_info(env, subprog); - if (!bpf_verifier_log_needed(&env->log)) - return; + info->is_cb = true; + info->is_async_cb = true; + info->is_exception_cb = true; +} - va_start(args, fmt); - bpf_verifier_vlog(&env->log, fmt, args); - va_end(args); +static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog) +{ + return subprog_info(env, subprog)->is_exception_cb; } -EXPORT_SYMBOL_GPL(bpf_verifier_log_write); -__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) +static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { - struct bpf_verifier_env *env = private_data; - va_list args; + return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); +} - if (!bpf_verifier_log_needed(&env->log)) - return; +static bool type_is_rdonly_mem(u32 type) +{ + return type & MEM_RDONLY; +} - va_start(args, fmt); - bpf_verifier_vlog(&env->log, fmt, args); - va_end(args); +static bool is_acquire_function(enum bpf_func_id func_id, + const struct bpf_map *map) +{ + enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC; + + if (func_id == BPF_FUNC_sk_lookup_tcp || + func_id == BPF_FUNC_sk_lookup_udp || + func_id == BPF_FUNC_skc_lookup_tcp || + func_id == BPF_FUNC_ringbuf_reserve || + func_id == BPF_FUNC_kptr_xchg) + return true; + + if (func_id == BPF_FUNC_map_lookup_elem && + (map_type == BPF_MAP_TYPE_SOCKMAP || + map_type == BPF_MAP_TYPE_SOCKHASH)) + return true; + + return false; } -__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, - const char *fmt, ...) +static bool is_ptr_cast_function(enum bpf_func_id func_id) { - va_list args; + return func_id == BPF_FUNC_tcp_sock || + func_id == BPF_FUNC_sk_fullsock || + func_id == BPF_FUNC_skc_to_tcp_sock || + func_id == BPF_FUNC_skc_to_tcp6_sock || + func_id == BPF_FUNC_skc_to_udp6_sock || + func_id == BPF_FUNC_skc_to_mptcp_sock || + func_id == BPF_FUNC_skc_to_tcp_timewait_sock || + func_id == BPF_FUNC_skc_to_tcp_request_sock; +} - if (!bpf_verifier_log_needed(log)) - return; +static bool is_dynptr_ref_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_dynptr_data; +} - va_start(args, fmt); - bpf_verifier_vlog(log, fmt, args); - va_end(args); +static bool is_sync_callback_calling_kfunc(u32 btf_id); +static bool is_async_callback_calling_kfunc(u32 btf_id); +static bool is_callback_calling_kfunc(u32 btf_id); +static bool is_bpf_throw_kfunc(struct bpf_insn *insn); + +static bool is_bpf_wq_set_callback_impl_kfunc(u32 btf_id); + +static bool is_sync_callback_calling_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_for_each_map_elem || + func_id == BPF_FUNC_find_vma || + func_id == BPF_FUNC_loop || + func_id == BPF_FUNC_user_ringbuf_drain; } -static const char *ltrim(const char *s) +static bool is_async_callback_calling_function(enum bpf_func_id func_id) { - while (isspace(*s)) - s++; + return func_id == BPF_FUNC_timer_set_callback; +} - return s; +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); } -__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env, - u32 insn_off, - const char *prefix_fmt, ...) +static bool is_sync_callback_calling_insn(struct bpf_insn *insn) { - const struct bpf_line_info *linfo; + return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) || + (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); +} - if (!bpf_verifier_log_needed(&env->log)) - return; +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)); +} - linfo = find_linfo(env, insn_off); - if (!linfo || linfo == env->prev_linfo) - return; +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]); +} - if (prefix_fmt) { - va_list args; +static bool is_storage_get_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_sk_storage_get || + func_id == BPF_FUNC_inode_storage_get || + func_id == BPF_FUNC_task_storage_get || + func_id == BPF_FUNC_cgrp_storage_get; +} - va_start(args, prefix_fmt); - bpf_verifier_vlog(&env->log, prefix_fmt, args); - va_end(args); +static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id, + const struct bpf_map *map) +{ + int ref_obj_uses = 0; + + if (is_ptr_cast_function(func_id)) + ref_obj_uses++; + if (is_acquire_function(func_id, map)) + ref_obj_uses++; + if (is_dynptr_ref_function(func_id)) + ref_obj_uses++; + + return ref_obj_uses > 1; +} + +static bool is_cmpxchg_insn(const struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_STX && + BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_CMPXCHG; +} + +static int __get_spi(s32 off) +{ + return (-off - 1) / BPF_REG_SIZE; +} + +static struct bpf_func_state *func(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg) +{ + struct bpf_verifier_state *cur = env->cur_state; + + return cur->frame[reg->frameno]; +} + +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 int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + const char *obj_kind, int nr_slots) +{ + int off, spi; + + if (!tnum_is_const(reg->var_off)) { + verbose(env, "%s has to be at a constant offset\n", obj_kind); + return -EINVAL; + } + + 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; } - verbose(env, "%s\n", - ltrim(btf_name_by_offset(env->prog->aux->btf, - linfo->line_off))); + 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; + } - env->prev_linfo = linfo; + if (!is_spi_bounds_valid(func(env, reg), spi, nr_slots)) + return -ERANGE; + return spi; } -static bool type_is_pkt_pointer(enum bpf_reg_type type) +static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - return type == PTR_TO_PACKET || - type == PTR_TO_PACKET_META; + return stack_slot_obj_get_spi(env, reg, "dynptr", BPF_DYNPTR_NR_SLOTS); } -static bool type_is_sk_pointer(enum bpf_reg_type type) +static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { - return type == PTR_TO_SOCKET || - type == PTR_TO_SOCK_COMMON || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_XDP_SOCK; + return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); } -static bool reg_type_not_null(enum bpf_reg_type type) +static int irq_flag_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - return type == PTR_TO_SOCKET || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_MAP_VALUE || - type == PTR_TO_SOCK_COMMON; + return stack_slot_obj_get_spi(env, reg, "irq_flag", 1); } -static bool reg_type_may_be_null(enum bpf_reg_type type) +static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) { - return type == PTR_TO_MAP_VALUE_OR_NULL || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_SOCK_COMMON_OR_NULL || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_BTF_ID_OR_NULL || - type == PTR_TO_MEM_OR_NULL; + switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { + case DYNPTR_TYPE_LOCAL: + 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; + default: + return BPF_DYNPTR_TYPE_INVALID; + } } -static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) +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; + default: + return 0; + } +} + +static bool dynptr_type_refcounted(enum bpf_dynptr_type type) { - return reg->type == PTR_TO_MAP_VALUE && - map_value_has_spin_lock(reg->map_ptr); + return type == BPF_DYNPTR_TYPE_RINGBUF; } -static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) +static void __mark_dynptr_reg(struct bpf_reg_state *reg, + enum bpf_dynptr_type type, + 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_verifier_env *env, + struct bpf_reg_state *sreg1, + struct bpf_reg_state *sreg2, + enum bpf_dynptr_type type) { - return type == PTR_TO_SOCKET || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_MEM || - type == PTR_TO_MEM_OR_NULL; + int id = ++env->id_gen; + + __mark_dynptr_reg(sreg1, type, true, id); + __mark_dynptr_reg(sreg2, type, false, id); } -static bool arg_type_may_be_refcounted(enum bpf_arg_type type) +static void mark_dynptr_cb_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + enum bpf_dynptr_type type) { - return type == ARG_PTR_TO_SOCK_COMMON; + __mark_dynptr_reg(reg, type, true, ++env->id_gen); } -/* Determine whether the function releases some resources allocated by another - * function call. The first reference type argument will be assumed to be - * released by release_reference(). - */ -static bool is_release_function(enum bpf_func_id func_id) +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, int clone_ref_obj_id) { - return func_id == BPF_FUNC_sk_release || - func_id == BPF_FUNC_ringbuf_submit || - func_id == BPF_FUNC_ringbuf_discard; + struct bpf_func_state *state = func(env, reg); + enum bpf_dynptr_type type; + 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; + state->stack[spi - 1].slot_type[i] = STACK_DYNPTR; + } + + type = arg_to_dynptr_type(arg_type); + if (type == BPF_DYNPTR_TYPE_INVALID) + return -EINVAL; + + 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 */ + int id; + + if (clone_ref_obj_id) + id = clone_ref_obj_id; + else + id = acquire_reference(env, insn_idx); + + if (id < 0) + return id; + + state->stack[spi].spilled_ptr.ref_obj_id = id; + state->stack[spi - 1].spilled_ptr.ref_obj_id = id; + } + + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; + + return 0; } -static bool may_be_acquire_function(enum bpf_func_id func_id) +static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) { - return func_id == BPF_FUNC_sk_lookup_tcp || - func_id == BPF_FUNC_sk_lookup_udp || - func_id == BPF_FUNC_skc_lookup_tcp || - func_id == BPF_FUNC_map_lookup_elem || - func_id == BPF_FUNC_ringbuf_reserve; + 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); + + /* Why do we need to set REG_LIVE_WRITTEN for STACK_INVALID slot? + * + * While we don't allow reading STACK_INVALID, it is still possible to + * do <8 byte writes marking some but not all slots as STACK_MISC. Then, + * helpers or insns can do partial read of that part without failing, + * but check_stack_range_initialized, check_stack_read_var_off, and + * check_stack_read_fixed_off will do mark_reg_read for all 8-bytes of + * the slot conservatively. Hence we need to prevent those liveness + * marking walks. + * + * This was not a problem before because STACK_INVALID is only set by + * default (where the default reg state has its reg->parent as NULL), or + * in clean_live_states after REG_LIVE_DONE (at which point + * mark_reg_read won't walk reg->parent chain), but not randomly during + * verifier state exploration (like we did above). Hence, for our case + * parentage chain will still be live (i.e. reg->parent may be + * non-NULL), while earlier reg->parent was NULL, so we need + * REG_LIVE_WRITTEN to screen off read marker propagation when it is + * done later on reads or by mark_dynptr_read as well to unnecessary + * mark registers in verifier state. + */ + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; } -static bool is_acquire_function(enum bpf_func_id func_id, - const struct bpf_map *map) +static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC; + struct bpf_func_state *state = func(env, reg); + int spi, ref_obj_id, i; - if (func_id == BPF_FUNC_sk_lookup_tcp || - func_id == BPF_FUNC_sk_lookup_udp || - func_id == BPF_FUNC_skc_lookup_tcp || - func_id == BPF_FUNC_ringbuf_reserve) + 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) { + verbose(env, "verifier internal error: misconfigured ref_obj_id\n"); + 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); +} + +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; + + /* 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 */ + 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); + + /* Same reason as unmark_stack_slots_dynptr above */ + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; + + return 0; +} + +static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + int spi; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return false; + + spi = dynptr_get_spi(env, reg); + + /* -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 i, spi; + + /* 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; - if (func_id == BPF_FUNC_map_lookup_elem && - (map_type == BPF_MAP_TYPE_SOCKMAP || - map_type == BPF_MAP_TYPE_SOCKHASH)) + 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++) { + if (state->stack[spi].slot_type[i] != STACK_DYNPTR || + state->stack[spi - 1].slot_type[i] != STACK_DYNPTR) + return false; + } + + return true; +} + +static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + enum bpf_arg_type arg_type) +{ + struct bpf_func_state *state = func(env, reg); + enum bpf_dynptr_type dynptr_type; + int spi; + + /* ARG_PTR_TO_DYNPTR takes any type of dynptr */ + if (arg_type == ARG_PTR_TO_DYNPTR) return true; - return false; + dynptr_type = arg_to_dynptr_type(arg_type); + if (reg->type == CONST_PTR_TO_DYNPTR) { + return reg->dynptr.type == dynptr_type; + } else { + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return false; + return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; + } } -static bool is_ptr_cast_function(enum bpf_func_id func_id) +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 func_id == BPF_FUNC_tcp_sock || - func_id == BPF_FUNC_sk_fullsock; -} - -/* string representation of 'enum bpf_reg_type' */ -static const char * const reg_type_str[] = { - [NOT_INIT] = "?", - [SCALAR_VALUE] = "inv", - [PTR_TO_CTX] = "ctx", - [CONST_PTR_TO_MAP] = "map_ptr", - [PTR_TO_MAP_VALUE] = "map_value", - [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", - [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_SOCKET_OR_NULL] = "sock_or_null", - [PTR_TO_SOCK_COMMON] = "sock_common", - [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", - [PTR_TO_TCP_SOCK] = "tcp_sock", - [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", - [PTR_TO_TP_BUFFER] = "tp_buffer", - [PTR_TO_XDP_SOCK] = "xdp_sock", - [PTR_TO_BTF_ID] = "ptr_", - [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_", - [PTR_TO_MEM] = "mem", - [PTR_TO_MEM_OR_NULL] = "mem_or_null", -}; + struct bpf_func_state *state = func(env, reg); + int spi, i, j, id; -static char slot_type_char[] = { - [STACK_INVALID] = '?', - [STACK_SPILL] = 'r', - [STACK_MISC] = 'm', - [STACK_ZERO] = '0', -}; + 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->live |= REG_LIVE_WRITTEN; + 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; -static void print_liveness(struct bpf_verifier_env *env, - enum bpf_reg_liveness live) + for (j = 0; j < BPF_REG_SIZE; j++) + slot->slot_type[j] = STACK_ITER; + + mark_stack_slot_scratched(env, spi - i); + } + + return 0; +} + +static int unmark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int nr_slots) { - 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"); + 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); + + /* see unmark_stack_slots_dynptr() for why we need to set REG_LIVE_WRITTEN */ + st->live |= REG_LIVE_WRITTEN; + + for (j = 0; j < BPF_REG_SIZE; j++) + slot->slot_type[j] = STACK_INVALID; + + mark_stack_slot_scratched(env, spi - i); + } + + return 0; } -static struct bpf_func_state *func(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg) +static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int nr_slots) { - struct bpf_verifier_state *cur = env->cur_state; + struct bpf_func_state *state = func(env, reg); + int spi, i, j; - return cur->frame[reg->frameno]; + /* 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; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + + for (j = 0; j < BPF_REG_SIZE; j++) + if (slot->slot_type[j] == STACK_ITER) + return false; + } + + return true; } -const char *kernel_type_name(u32 id) +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) { - return btf_name_by_offset(btf_vmlinux, - btf_type_by_id(btf_vmlinux, id)->name_off); + 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 void print_verifier_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state) +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) { - const struct bpf_reg_state *reg; - enum bpf_reg_type t; - int i; + struct bpf_func_state *state = func(env, reg); + struct bpf_stack_state *slot; + struct bpf_reg_state *st; + int spi, i, id; - 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; - verbose(env, " R%d", i); - print_liveness(env, reg->live); - verbose(env, "=%s", reg_type_str[t]); - 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, "%lld", reg->var_off.value + reg->off); - } else { - if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL) - verbose(env, "%s", kernel_type_name(reg->btf_id)); - verbose(env, "(id=%d", reg->id); - if (reg_type_may_be_refcounted_or_null(t)) - verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); - if (t != SCALAR_VALUE) - verbose(env, ",off=%d", reg->off); - if (type_is_pkt_pointer(t)) - verbose(env, ",r=%d", reg->range); - else if (t == CONST_PTR_TO_MAP || - t == PTR_TO_MAP_VALUE || - t == PTR_TO_MAP_VALUE_OR_NULL) - verbose(env, ",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(env, ",imm=%llx", reg->var_off.value); - } else { - if (reg->smin_value != reg->umin_value && - reg->smin_value != S64_MIN) - verbose(env, ",smin_value=%lld", - (long long)reg->smin_value); - if (reg->smax_value != reg->umax_value && - reg->smax_value != S64_MAX) - verbose(env, ",smax_value=%lld", - (long long)reg->smax_value); - if (reg->umin_value != 0) - verbose(env, ",umin_value=%llu", - (unsigned long long)reg->umin_value); - if (reg->umax_value != U64_MAX) - verbose(env, ",umax_value=%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(env, ",var_off=%s", tn_buf); - } - if (reg->s32_min_value != reg->smin_value && - reg->s32_min_value != S32_MIN) - verbose(env, ",s32_min_value=%d", - (int)(reg->s32_min_value)); - if (reg->s32_max_value != reg->smax_value && - reg->s32_max_value != S32_MAX) - verbose(env, ",s32_max_value=%d", - (int)(reg->s32_max_value)); - if (reg->u32_min_value != reg->umin_value && - reg->u32_min_value != U32_MIN) - verbose(env, ",u32_min_value=%d", - (int)(reg->u32_min_value)); - if (reg->u32_max_value != reg->umax_value && - reg->u32_max_value != U32_MAX) - verbose(env, ",u32_max_value=%d", - (int)(reg->u32_max_value)); - } - verbose(env, ")"); - } - } - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - char types_buf[BPF_REG_SIZE + 1]; - bool valid = false; - int j; + 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; + + __mark_reg_known_zero(st); + st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + st->live |= REG_LIVE_WRITTEN; + st->ref_obj_id = id; + + 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) +{ + 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; - 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]]; + slot = &state->stack[spi]; + st = &slot->spilled_ptr; + + 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; + } } - types_buf[BPF_REG_SIZE] = 0; - if (!valid) - continue; - verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); - print_liveness(env, state->stack[i].spilled_ptr.live); - if (state->stack[i].slot_type[0] == STACK_SPILL) { - reg = &state->stack[i].spilled_ptr; - t = reg->type; - verbose(env, "=%s", reg_type_str[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); - } - } - 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); - } - verbose(env, "\n"); -} - -#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \ -static int copy_##NAME##_state(struct bpf_func_state *dst, \ - const struct bpf_func_state *src) \ -{ \ - if (!src->FIELD) \ - return 0; \ - if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \ - /* internal bug, make state invalid to reject the program */ \ - memset(dst, 0, sizeof(*dst)); \ - return -EFAULT; \ - } \ - memcpy(dst->FIELD, src->FIELD, \ - sizeof(*src->FIELD) * (src->COUNT / SIZE)); \ - return 0; \ -} -/* copy_reference_state() */ -COPY_STATE_FN(reference, acquired_refs, refs, 1) -/* copy_stack_state() */ -COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) -#undef COPY_STATE_FN - -#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \ -static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \ - bool copy_old) \ -{ \ - u32 old_size = state->COUNT; \ - struct bpf_##NAME##_state *new_##FIELD; \ - int slot = size / SIZE; \ - \ - if (size <= old_size || !size) { \ - if (copy_old) \ - return 0; \ - state->COUNT = slot * SIZE; \ - if (!size && old_size) { \ - kfree(state->FIELD); \ - state->FIELD = NULL; \ - } \ - return 0; \ - } \ - new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \ - GFP_KERNEL); \ - if (!new_##FIELD) \ - return -ENOMEM; \ - if (copy_old) { \ - if (state->FIELD) \ - memcpy(new_##FIELD, state->FIELD, \ - sizeof(*new_##FIELD) * (old_size / SIZE)); \ - memset(new_##FIELD + old_size / SIZE, 0, \ - sizeof(*new_##FIELD) * (size - old_size) / SIZE); \ - } \ - state->COUNT = slot * SIZE; \ - kfree(state->FIELD); \ - state->FIELD = new_##FIELD; \ - return 0; \ -} -/* realloc_reference_state() */ -REALLOC_STATE_FN(reference, acquired_refs, refs, 1) -/* realloc_stack_state() */ -REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) -#undef REALLOC_STATE_FN - -/* do_check() starts with zero-sized stack in struct bpf_verifier_state to - * make it consume minimal amount of memory. check_stack_write() access from - * the program calls into realloc_func_state() to grow the stack size. - * Note there is a non-zero 'parent' pointer inside bpf_verifier_state - * which realloc_stack_state() copies over. It points to previous - * bpf_verifier_state which is never reallocated. + + 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; + } + + __mark_reg_not_init(env, st); + + /* see unmark_stack_slots_dynptr() for why we need to set REG_LIVE_WRITTEN */ + st->live |= REG_LIVE_WRITTEN; + + for (i = 0; i < BPF_REG_SIZE; i++) + slot->slot_type[i] = STACK_INVALID; + + mark_stack_slot_scratched(env, spi); + return 0; +} + +static bool is_irq_flag_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + 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 int is_irq_flag_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + 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 int realloc_func_state(struct bpf_func_state *state, int stack_size, - int refs_size, bool copy_old) +static bool is_stack_slot_special(const struct bpf_stack_state *stack) { - int err = realloc_reference_state(state, refs_size, copy_old); - if (err) - return err; - return realloc_stack_state(state, stack_size, copy_old); + 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; + } +} + +/* 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 + * small to hold src. This is different from krealloc since we don't want to preserve + * the contents of dst. + * + * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could + * not be allocated. + */ +static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags) +{ + size_t alloc_bytes; + void *orig = dst; + size_t bytes; + + if (ZERO_OR_NULL_PTR(src)) + goto out; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + + alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes)); + dst = krealloc(orig, alloc_bytes, flags); + if (!dst) { + kfree(orig); + return NULL; + } + + memcpy(dst, src, bytes); +out: + return dst ? dst : ZERO_SIZE_PTR; +} + +/* resize an array from old_n items to new_n items. the array is reallocated if it's too + * small to hold new_n items. new items are zeroed out if the array grows. + * + * Contrary to krealloc_array, does not free arr if new_n is zero. + */ +static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) +{ + size_t alloc_size; + void *new_arr; + + if (!new_n || old_n == new_n) + goto out; + + alloc_size = kmalloc_size_roundup(size_mul(new_n, size)); + new_arr = krealloc(arr, alloc_size, GFP_KERNEL); + if (!new_arr) { + kfree(arr); + return NULL; + } + arr = new_arr; + + if (new_n > old_n) + memset(arr + old_n * size, 0, (new_n - old_n) * size); + +out: + return arr ? arr : ZERO_SIZE_PTR; +} + +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); + 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_lock = src->active_rcu_lock; + dst->active_irq_id = src->active_irq_id; + return 0; +} + +static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src) +{ + 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); + if (!dst->stack) + return -ENOMEM; + + dst->allocated_stack = src->allocated_stack; + return 0; +} + +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)); + if (!state->refs) + return -ENOMEM; + + state->acquired_refs = n; + return 0; +} + +/* 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; + + /* 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; + + state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state)); + if (!state->stack) + 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; } /* Acquire a pointer id from the env and update the state->refs to include @@ -744,69 +1468,146 @@ static int realloc_func_state(struct bpf_func_state *state, int stack_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 = realloc_reference_state(state, state->acquired_refs + 1, true); + 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; - 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++; + 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 int release_lock_state(struct bpf_verifier_state *state, int type, int id, void *ptr) +{ + int i; + for (i = 0; i < state->acquired_refs; i++) { - if (state->refs[i].id == ptr_id) { - 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) + continue; + if (state->refs[i].id == id && state->refs[i].ptr == ptr) { + release_reference_state(state, i); + state->active_locks--; return 0; } } return -EINVAL; } -static int transfer_reference_state(struct bpf_func_state *dst, - struct bpf_func_state *src) +static int release_irq_state(struct bpf_verifier_state *state, int id) { - int err = realloc_reference_state(dst, src->acquired_refs, false); - if (err) - return err; - err = copy_reference_state(dst, src); - if (err) - return err; - return 0; + 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 free_func_state(struct bpf_func_state *state) { if (!state) return; - kfree(state->refs); kfree(state->stack); kfree(state); } -static void clear_jmp_history(struct bpf_verifier_state *state) -{ - kfree(state->jmp_history); - state->jmp_history = NULL; - state->jmp_history_cnt = 0; -} - static void free_verifier_state(struct bpf_verifier_state *state, bool free_self) { @@ -816,7 +1617,7 @@ static void free_verifier_state(struct bpf_verifier_state *state, free_func_state(state->frame[i]); state->frame[i] = NULL; } - clear_jmp_history(state); + kfree(state->refs); if (free_self) kfree(state); } @@ -827,16 +1628,7 @@ static void free_verifier_state(struct bpf_verifier_state *state, static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { - int err; - - err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs, - false); - if (err) - return 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); } @@ -844,30 +1636,31 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src) { struct bpf_func_state *dst; - u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt; int i, err; - if (dst_state->jmp_history_cnt < src->jmp_history_cnt) { - kfree(dst_state->jmp_history); - dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER); - if (!dst_state->jmp_history) - return -ENOMEM; - } - memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz); - 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->in_sleepable = src->in_sleepable; dst_state->curframe = src->curframe; - dst_state->active_spin_lock = src->active_spin_lock; 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->insn_hist_start = src->insn_hist_start; + dst_state->insn_hist_end = src->insn_hist_end; + dst_state->dfs_depth = src->dfs_depth; + dst_state->callback_unroll_depth = src->callback_unroll_depth; + dst_state->used_as_loop_entry = src->used_as_loop_entry; + dst_state->may_goto_depth = src->may_goto_depth; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -883,11 +1676,203 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, return 0; } +static u32 state_htab_size(struct bpf_verifier_env *env) +{ + return env->prog->len; +} + +static struct bpf_verifier_state_list **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; +} + +/* Open coded iterators allow back-edges in the state graph in order to + * check unbounded loops that iterators. + * + * In is_state_visited() it is necessary to know if explored states are + * part of some loops in order to decide whether non-exact states + * comparison could be used: + * - non-exact states comparison establishes sub-state relation and uses + * read and precision marks to do so, these marks are propagated from + * children states and thus are not guaranteed to be final in a loop; + * - exact states comparison just checks if current and explored states + * are identical (and thus form a back-edge). + * + * Paper "A New Algorithm for Identifying Loops in Decompilation" + * by Tao Wei, Jian Mao, Wei Zou and Yu Chen [1] presents a convenient + * algorithm for loop structure detection and gives an overview of + * relevant terminology. It also has helpful illustrations. + * + * [1] https://api.semanticscholar.org/CorpusID:15784067 + * + * We use a similar algorithm but because loop nested structure is + * irrelevant for verifier ours is significantly simpler and resembles + * strongly connected components algorithm from Sedgewick's textbook. + * + * Define topmost loop entry as a first node of the loop traversed in a + * depth first search starting from initial state. The goal of the loop + * tracking algorithm is to associate topmost loop entries with states + * derived from these entries. + * + * For each step in the DFS states traversal algorithm needs to identify + * the following situations: + * + * initial initial initial + * | | | + * V V V + * ... ... .---------> hdr + * | | | | + * V V | V + * cur .-> succ | .------... + * | | | | | | + * V | V | V V + * succ '-- cur | ... ... + * | | | + * | V V + * | succ <- cur + * | | + * | V + * | ... + * | | + * '----' + * + * (A) successor state of cur (B) successor state of cur or it's entry + * not yet traversed are in current DFS path, thus cur and succ + * are members of the same outermost loop + * + * initial initial + * | | + * V V + * ... ... + * | | + * V V + * .------... .------... + * | | | | + * V V V V + * .-> hdr ... ... ... + * | | | | | + * | V V V V + * | succ <- cur succ <- cur + * | | | + * | V V + * | ... ... + * | | | + * '----' exit + * + * (C) successor state of cur is a part of some loop but this loop + * does not include cur or successor state is not in a loop at all. + * + * Algorithm could be described as the following python code: + * + * traversed = set() # Set of traversed nodes + * entries = {} # Mapping from node to loop entry + * depths = {} # Depth level assigned to graph node + * path = set() # Current DFS path + * + * # Find outermost loop entry known for n + * def get_loop_entry(n): + * h = entries.get(n, None) + * while h in entries and entries[h] != h: + * h = entries[h] + * return h + * + * # Update n's loop entry if h's outermost entry comes + * # before n's outermost entry in current DFS path. + * def update_loop_entry(n, h): + * n1 = get_loop_entry(n) or n + * h1 = get_loop_entry(h) or h + * if h1 in path and depths[h1] <= depths[n1]: + * entries[n] = h1 + * + * def dfs(n, depth): + * traversed.add(n) + * path.add(n) + * depths[n] = depth + * for succ in G.successors(n): + * if succ not in traversed: + * # Case A: explore succ and update cur's loop entry + * # only if succ's entry is in current DFS path. + * dfs(succ, depth + 1) + * h = get_loop_entry(succ) + * update_loop_entry(n, h) + * else: + * # Case B or C depending on `h1 in path` check in update_loop_entry(). + * update_loop_entry(n, succ) + * path.remove(n) + * + * To adapt this algorithm for use with verifier: + * - use st->branch == 0 as a signal that DFS of succ had been finished + * and cur's loop entry has to be updated (case A), handle this in + * update_branch_counts(); + * - use st->branch > 0 as a signal that st is in the current DFS path; + * - handle cases B and C in is_state_visited(); + * - update topmost loop entry for intermediate states in get_loop_entry(). + */ +static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_state *st) +{ + struct bpf_verifier_state *topmost = st->loop_entry, *old; + + while (topmost && topmost->loop_entry && topmost != topmost->loop_entry) + topmost = topmost->loop_entry; + /* Update loop entries for intermediate states to avoid this + * traversal in future get_loop_entry() calls. + */ + while (st && st->loop_entry != topmost) { + old = st->loop_entry; + st->loop_entry = topmost; + st = old; + } + return topmost; +} + +static void update_loop_entry(struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr) +{ + struct bpf_verifier_state *cur1, *hdr1; + + cur1 = get_loop_entry(cur) ?: cur; + hdr1 = get_loop_entry(hdr) ?: hdr; + /* The head1->branches check decides between cases B and C in + * comment for get_loop_entry(). If hdr1->branches == 0 then + * head's topmost loop entry is not in current DFS path, + * hence 'cur' and 'hdr' are not in the same loop and there is + * no need to update cur->loop_entry. + */ + if (hdr1->branches && hdr1->dfs_depth <= cur1->dfs_depth) { + cur->loop_entry = hdr; + hdr->used_as_loop_entry = true; + } +} + static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { while (st) { u32 br = --st->branches; + /* br == 0 signals that DFS exploration for 'st' is finished, + * thus it is necessary to update parent's loop entry if it + * turned out that st is a part of some loop. + * This is a part of 'case A' in get_loop_entry() comment. + */ + if (br == 0 && st->parent && st->loop_entry) + update_loop_entry(st->parent, st->loop_entry); + /* WARN_ON(br > 1) technically makes sense here, * but see comment in push_stack(), hence: */ @@ -944,7 +1929,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, 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); @@ -982,17 +1967,9 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(const struct bpf_verifier_env *env, - struct bpf_reg_state *reg); - -/* Mark the unknown part of a register (variable offset or scalar value) as - * known to have the value @imm. - */ -static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) +/* This helper doesn't clear reg->id */ +static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) { - /* Clear id, off, and union(map_ptr, range) */ - memset(((u8 *)reg) + sizeof(reg->type), 0, - offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); reg->var_off = tnum_const(imm); reg->smin_value = (s64)imm; reg->smax_value = (s64)imm; @@ -1005,6 +1982,19 @@ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) reg->u32_max_value = (u32)imm; } +/* Mark the unknown part of a register (variable offset or scalar value) as + * known to have the value @imm. + */ +static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) +{ + /* 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); +} + static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const_subreg(reg->var_off, imm); @@ -1022,10 +2012,14 @@ 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, @@ -1041,6 +2035,60 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, __mark_reg_known_zero(regs + regno); } +static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, + 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 + * set it unconditionally as it is ignored for STACK_DYNPTR anyway. + */ + __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; +} + +static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) +{ + if (base_type(reg->type) == PTR_TO_MAP_VALUE) { + const struct bpf_map *map = reg->map_ptr; + + if (map->inner_map_meta) { + reg->type = CONST_PTR_TO_MAP; + reg->map_ptr = map->inner_map_meta; + /* 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)) + reg->map_uid = reg->id; + if (btf_record_has_field(map->inner_map_meta->record, BPF_WORKQUEUE)) + reg->map_uid = reg->id; + } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { + reg->type = PTR_TO_XDP_SOCK; + } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH) { + reg->type = PTR_TO_SOCKET; + } else { + reg->type = PTR_TO_MAP_VALUE; + } + return; + } + + 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); @@ -1052,6 +2100,12 @@ 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 || reg->type & DYNPTR_TYPE_XDP); +} + /* 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) @@ -1133,69 +2187,252 @@ 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); + } } - /* Learn sign from unsigned bounds. Signed bounds cross the sign - * boundary, so we must be careful. + 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 ((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->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); + } + /* 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 ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { + reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); + reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); } } static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { - /* Learn sign from signed bounds. - * If we cannot cross the sign boundary, then signed and unsigned bounds + /* If u64 range forms a valid s64 range (due to matching sign bit), + * try to learn from that. Let's do a bit of ASCII art to see when + * this is happening. Let's take u64 range first: + * + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * + * Valid u64 range is formed when umin and umax are anywhere in the + * range [0, U64_MAX], and umin <= umax. u64 case is simple and + * straightforward. Let's see how s64 range maps onto the same range + * of values, annotated below the line for comparison: + * + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * 0 S64_MAX S64_MIN -1 + * + * So s64 values basically start in the middle and they are logically + * contiguous to the right of it, wrapping around from -1 to 0, and + * then finishing as S64_MAX (0x7fffffffffffffff) right before + * S64_MIN. We can try drawing the continuity of u64 vs s64 values + * more visually as mapped to sign-agnostic range of hex values. + * + * u64 start u64 end + * _______________________________________________________________ + * / \ + * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX + * |-------------------------------|--------------------------------| + * 0 S64_MAX S64_MIN -1 + * / \ + * >------------------------------ -------------------------------> + * s64 continues... s64 end s64 start s64 "midpoint" + * + * What this means is that, in general, we can't always derive + * something new about u64 from any random s64 range, and vice versa. + * + * But we can do that in two particular cases. One is when entire + * u64/s64 range is *entirely* contained within left half of the above + * diagram or when it is *entirely* contained in the right half. I.e.: + * + * |-------------------------------|--------------------------------| + * ^ ^ ^ ^ + * A B C D + * + * [A, B] and [C, D] are contained entirely in their respective halves + * and form valid contiguous ranges as both u64 and s64 values. [A, B] + * will be non-negative both as u64 and s64 (and in fact it will be + * identical ranges no matter the signedness). [C, D] treated as s64 + * will be a range of negative values, while in u64 it will be + * non-negative range of values larger than 0x8000000000000000. + * + * Now, any other range here can't be represented in both u64 and s64 + * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid + * contiguous u64 ranges, but they are discontinuous in s64. [B, C] + * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX], + * for example. Similarly, valid s64 range [D, A] (going from negative + * to positive values), would be two separate [D, U64_MAX] and [0, A] + * ranges as u64. Currently reg_state can't represent two segments per + * numeric domain, so in such situations we can only derive maximal + * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64). + * + * So we use these facts to derive umin/umax from smin/smax and vice + * versa only if they stay within the same "half". This is equivalent + * to checking sign bit: lower half will have sign bit as zero, upper + * half have sign bit 1. Below in code we simplify this by just + * casting umin/umax as smin/smax and checking if they form valid + * range, and vice versa. Those are equivalent checks. + */ + if ((s64)reg->umin_value <= (s64)reg->umax_value) { + reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value); + reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value); + } + /* If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ - if (reg->smin_value >= 0 || reg->smax_value < 0) { - reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, - reg->umin_value); - reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, - reg->umax_value); - return; + if ((u64)reg->smin_value <= (u64)reg->smax_value) { + reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); + reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); } - /* Learn sign from unsigned bounds. Signed bounds cross the sign - * boundary, so we must be careful. +} + +static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg) +{ + /* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit + * values on both sides of 64-bit range in hope to have 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); + + /* if s32 can be treated as valid u32 range, we can use it as well */ + if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { + /* s32 -> u64 tightening */ + new_umin = (reg->umin_value & ~0xffffffffULL) | (u32)reg->s32_min_value; + new_umax = (reg->umax_value & ~0xffffffffULL) | (u32)reg->s32_max_value; + reg->umin_value = max_t(u64, reg->umin_value, new_umin); + reg->umax_value = min_t(u64, reg->umax_value, new_umax); + /* s32 -> s64 tightening */ + new_smin = (reg->smin_value & ~0xffffffffULL) | (u32)reg->s32_min_value; + new_smax = (reg->smax_value & ~0xffffffffULL) | (u32)reg->s32_max_value; + reg->smin_value = max_t(s64, reg->smin_value, new_smin); + reg->smax_value = min_t(s64, reg->smax_value, new_smax); + } + + /* 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)); } } @@ -1203,6 +2440,7 @@ 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 */ @@ -1211,112 +2449,130 @@ 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); } -static void __reg_assign_32_into_64(struct bpf_reg_state *reg) +static void reg_bounds_sync(struct bpf_reg_state *reg) { - reg->umin_value = reg->u32_min_value; - reg->umax_value = reg->u32_max_value; - /* Attempt to pull 32-bit signed bounds into 64-bit bounds - * but must be positive otherwise set to worse case bounds - * and refine later from tnum. - */ - if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0) - reg->smax_value = reg->s32_max_value; - else - reg->smax_value = U32_MAX; - if (reg->s32_min_value >= 0) - reg->smin_value = reg->s32_min_value; - else - reg->smin_value = 0; -} - -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); - __update_reg_bounds(reg); - } - + /* We might have learned new bounds from the var_off. */ + __update_reg_bounds(reg); + /* We might have learned something about the sign bit. */ + __reg_deduce_bounds(reg); + __reg_deduce_bounds(reg); + /* We might have learned some bits from the bounds. */ + __reg_bound_offset(reg); /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * slightly, e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. */ - __reg_deduce_bounds(reg); - __reg_bound_offset(reg); __update_reg_bounds(reg); } -static bool __reg64_bound_s32(s64 a) +static int reg_bounds_sanity_check(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, const char *ctx) { - if (a > S32_MIN && a < S32_MAX) - return true; - return false; + const char *msg; + + if (reg->umin_value > reg->umax_value || + reg->smin_value > reg->smax_value || + reg->u32_min_value > reg->u32_max_value || + reg->s32_min_value > reg->s32_max_value) { + msg = "range bounds violation"; + goto out; + } + + if (tnum_is_const(reg->var_off)) { + u64 uval = reg->var_off.value; + s64 sval = (s64)uval; + + if (reg->umin_value != uval || reg->umax_value != uval || + reg->smin_value != sval || reg->smax_value != sval) { + msg = "const tnum out of sync with range bounds"; + goto out; + } + } + + if (tnum_subreg_is_const(reg->var_off)) { + u32 uval32 = tnum_subreg(reg->var_off).value; + s32 sval32 = (s32)uval32; + + if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 || + reg->s32_min_value != sval32 || reg->s32_max_value != sval32) { + msg = "const subreg tnum out of sync with range bounds"; + goto out; + } + } + + return 0; +out: + verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] " + "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n", + ctx, msg, reg->umin_value, reg->umax_value, + reg->smin_value, reg->smax_value, + reg->u32_min_value, reg->u32_max_value, + reg->s32_min_value, reg->s32_max_value, + reg->var_off.value, reg->var_off.mask); + if (env->test_reg_invariants) + return -EFAULT; + __mark_reg_unbounded(reg); + return 0; } -static bool __reg64_bound_u32(u64 a) +static bool __reg32_bound_s64(s32 a) { - if (a > U32_MIN && a < U32_MAX) - return true; - return false; + return a >= 0 && a <= S32_MAX; } -static void __reg_combine_64_into_32(struct bpf_reg_state *reg) +static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { - __mark_reg32_unbounded(reg); - - if (__reg64_bound_s32(reg->smin_value)) - reg->s32_min_value = (s32)reg->smin_value; - if (__reg64_bound_s32(reg->smax_value)) - reg->s32_max_value = (s32)reg->smax_value; - if (__reg64_bound_u32(reg->umin_value)) - reg->u32_min_value = (u32)reg->umin_value; - if (__reg64_bound_u32(reg->umax_value)) - reg->u32_max_value = (u32)reg->umax_value; + reg->umin_value = reg->u32_min_value; + reg->umax_value = reg->u32_max_value; - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. + /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must + * be positive otherwise set to worse case bounds and refine later + * from tnum. */ - __reg_deduce_bounds(reg); - __reg_bound_offset(reg); - __update_reg_bounds(reg); + if (__reg32_bound_s64(reg->s32_min_value) && + __reg32_bound_s64(reg->s32_max_value)) { + reg->smin_value = reg->s32_min_value; + reg->smax_value = reg->s32_max_value; + } else { + reg->smin_value = 0; + reg->smax_value = U32_MAX; + } } /* 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->subprog_cnt > 1 || !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) { @@ -1330,6 +2586,25 @@ 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) { @@ -1350,6 +2625,24 @@ 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) +{ + if (reg_type == SCALAR_VALUE) { + mark_reg_unknown(env, regs, regno); + return; + } + 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; +} + #define DEF_NOT_SUBREG (0) static void init_reg_state(struct bpf_verifier_env *env, struct bpf_func_state *state) @@ -1370,6 +2663,11 @@ 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, @@ -1378,9 +2676,65 @@ static void init_func_state(struct bpf_verifier_env *env, state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; + state->callback_ret_range = retval_range(0, 0); init_reg_state(env, state); + mark_verifier_state_scratched(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, bool is_sleepable) +{ + struct bpf_verifier_stack_elem *elem; + struct bpf_func_state *frame; + + elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); + if (!elem) + goto err; + + elem->insn_idx = insn_idx; + elem->prev_insn_idx = prev_insn_idx; + elem->next = env->head; + 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; + } + /* Unlike push_stack() do not copy_verifier_state(). + * The caller state doesn't matter. + * This is async callback. It starts in a fresh stack. + * Initialize it similar to do_check_common(). + * But we do need to make sure to not clobber insn_hist, so we keep + * chaining insn_hist_start/insn_hist_end indices as for a normal + * child state. + */ + elem->st.branches = 1; + elem->st.in_sleepable = is_sleepable; + elem->st.insn_hist_start = env->cur_state->insn_hist_end; + elem->st.insn_hist_end = elem->st.insn_hist_start; + frame = kzalloc(sizeof(*frame), GFP_KERNEL); + if (!frame) + goto err; + 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; +} + + enum reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ @@ -1393,16 +2747,36 @@ static int cmp_subprogs(const void *a, const void *b) ((struct bpf_subprog_info *)b)->start; } +/* Find subprogram that contains instruction at 'off' */ +static struct bpf_subprog_info *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 = 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) @@ -1416,45 +2790,473 @@ static int add_subprog(struct bpf_verifier_env *env, int off) } ret = find_subprog(env, off); if (ret >= 0) - return 0; + return ret; if (env->subprog_cnt >= BPF_MAX_SUBPROGS) { verbose(env, "too many subprograms\n"); return -E2BIG; } + /* determine subprog starts. The end is one before the next starts */ env->subprog_info[env->subprog_cnt++].start = off; sort(env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs, NULL); + 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 + +struct bpf_kfunc_desc { + struct btf_func_model func_model; + u32 func_id; + s32 imm; + u16 offset; + unsigned long addr; +}; + +struct bpf_kfunc_btf { + struct btf *btf; + struct module *module; + u16 offset; +}; + +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; +}; + +struct bpf_kfunc_btf_tab { + struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS]; + u32 nr_descs; +}; + +static int kfunc_desc_cmp_by_id_off(const void *a, const void *b) +{ + const struct bpf_kfunc_desc *d0 = a; + const struct bpf_kfunc_desc *d1 = b; + + /* func_id is not greater than BTF_MAX_TYPE */ + return d0->func_id - d1->func_id ?: d0->offset - d1->offset; +} + +static int kfunc_btf_cmp_by_off(const void *a, const void *b) +{ + const struct bpf_kfunc_btf *d0 = a; + const struct bpf_kfunc_btf *d1 = b; + + return d0->offset - d1->offset; +} + +static const struct bpf_kfunc_desc * +find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) +{ + struct bpf_kfunc_desc desc = { + .func_id = func_id, + .offset = offset, + }; + struct bpf_kfunc_desc_tab *tab; + + tab = prog->aux->kfunc_tab; + return bsearch(&desc, tab->descs, tab->nr_descs, + 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 int check_subprogs(struct bpf_verifier_env *env) +static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, + s16 offset) +{ + struct bpf_kfunc_btf kf_btf = { .offset = offset }; + struct bpf_kfunc_btf_tab *tab; + struct bpf_kfunc_btf *b; + struct module *mod; + struct btf *btf; + int btf_fd; + + tab = env->prog->aux->kfunc_btf_tab; + b = bsearch(&kf_btf, tab->descs, tab->nr_descs, + sizeof(tab->descs[0]), kfunc_btf_cmp_by_off); + if (!b) { + if (tab->nr_descs == MAX_KFUNC_BTFS) { + verbose(env, "too many different module BTFs\n"); + return ERR_PTR(-E2BIG); + } + + if (bpfptr_is_null(env->fd_array)) { + verbose(env, "kfunc offset > 0 without fd_array is invalid\n"); + return ERR_PTR(-EPROTO); + } + + if (copy_from_bpfptr_offset(&btf_fd, env->fd_array, + offset * sizeof(btf_fd), + sizeof(btf_fd))) + return ERR_PTR(-EFAULT); + + btf = btf_get_by_fd(btf_fd); + if (IS_ERR(btf)) { + verbose(env, "invalid module BTF fd specified\n"); + return btf; + } + + if (!btf_is_module(btf)) { + verbose(env, "BTF fd for kfunc is not a module BTF\n"); + btf_put(btf); + return ERR_PTR(-EINVAL); + } + + mod = btf_try_get_module(btf); + if (!mod) { + btf_put(btf); + return ERR_PTR(-ENXIO); + } + + b = &tab->descs[tab->nr_descs++]; + b->btf = btf; + 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 btf; +} + +void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) +{ + if (!tab) + return; + + while (tab->nr_descs--) { + module_put(tab->descs[tab->nr_descs].module); + btf_put(tab->descs[tab->nr_descs].btf); + } + kfree(tab); +} + +static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) +{ + if (offset) { + if (offset < 0) { + /* In the future, this can be allowed to increase limit + * of fd index into fd_array, interpreted as u16. + */ + verbose(env, "negative offset disallowed for kernel module function call\n"); + return ERR_PTR(-EINVAL); + } + + return __find_kfunc_desc_btf(env, offset); + } + return btf_vmlinux ?: ERR_PTR(-ENOENT); +} + +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 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; + + prog_aux = env->prog->aux; + tab = prog_aux->kfunc_tab; + btf_tab = prog_aux->kfunc_btf_tab; + if (!tab) { + if (!btf_vmlinux) { + verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n"); + return -ENOTSUPP; + } + + if (!env->prog->jit_requested) { + verbose(env, "JIT is required for calling kernel function\n"); + return -ENOTSUPP; + } + + if (!bpf_jit_supports_kfunc_call()) { + verbose(env, "JIT does not support calling kernel function\n"); + return -ENOTSUPP; + } + + if (!env->prog->gpl_compatible) { + verbose(env, "cannot call kernel function from non-GPL compatible program\n"); + return -EINVAL; + } + + tab = kzalloc(sizeof(*tab), GFP_KERNEL); + if (!tab) + return -ENOMEM; + prog_aux->kfunc_tab = tab; + } + + /* func_id == 0 is always invalid, but instead of returning an error, be + * conservative and wait until the code elimination pass before returning + * error, so that invalid calls that get pruned out can be in BPF programs + * loaded from userspace. It is also required that offset be untouched + * for such calls. + */ + if (!func_id && !offset) + return 0; + + if (!btf_tab && offset) { + btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL); + if (!btf_tab) + return -ENOMEM; + prog_aux->kfunc_btf_tab = btf_tab; + } + + desc_btf = find_kfunc_desc_btf(env, offset); + if (IS_ERR(desc_btf)) { + verbose(env, "failed to find BTF for kernel function\n"); + return PTR_ERR(desc_btf); + } + + if (find_kfunc_desc(env->prog, func_id, offset)) + return 0; + + if (tab->nr_descs == MAX_KFUNC_DESCS) { + verbose(env, "too many different kernel function calls\n"); + return -E2BIG; + } + + func = btf_type_by_id(desc_btf, func_id); + if (!func || !btf_type_is_func(func)) { + verbose(env, "kernel btf_id %u is not a function\n", + func_id); + return -EINVAL; + } + func_proto = btf_type_by_id(desc_btf, func->type); + if (!func_proto || !btf_type_is_func_proto(func_proto)) { + verbose(env, "kernel function btf_id %u does not have a valid func_proto\n", + func_id); + return -EINVAL; + } + + func_name = btf_name_by_offset(desc_btf, func->name_off); + addr = kallsyms_lookup_name(func_name); + if (!addr) { + verbose(env, "cannot find address for kernel function %s\n", + func_name); + return -EINVAL; + } + specialize_kfunc(env, func_id, offset, &addr); + + if (bpf_jit_supports_far_kfunc_call()) { + call_imm = func_id; + } else { + call_imm = BPF_CALL_IMM(addr); + /* Check whether 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; + } + + desc = &tab->descs[tab->nr_descs++]; + desc->func_id = func_id; + desc->imm = call_imm; + desc->offset = offset; + desc->addr = addr; + 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; +} + +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 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_off(struct bpf_prog *prog) +{ + struct bpf_kfunc_desc_tab *tab; + + tab = prog->aux->kfunc_tab; + if (!tab) + return; + + sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), + kfunc_desc_cmp_by_imm_off, NULL); +} + +bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) +{ + return !!prog->aux->kfunc_tab; +} + +const struct btf_func_model * +bpf_jit_find_kfunc_model(const struct bpf_prog *prog, + const struct bpf_insn *insn) +{ + 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_off); + + return res ? &res->func_model : NULL; +} + +static int add_subprog_and_kfunc(struct bpf_verifier_env *env) { - int i, ret, subprog_start, subprog_end, off, cur_subprog = 0; 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 insn_cnt = env->prog->len; /* Add entry function. */ ret = add_subprog(env, 0); - if (ret < 0) + if (ret) return ret; - /* determine subprog starts. The end is one before the next starts */ - for (i = 0; i < insn_cnt; i++) { - if (insn[i].code != (BPF_JMP | BPF_CALL)) - continue; - if (insn[i].src_reg != BPF_PSEUDO_CALL) + for (i = 0; i < insn_cnt; i++, insn++) { + if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn) && + !bpf_pseudo_kfunc_call(insn)) continue; + if (!env->bpf_capable) { - verbose(env, - "function calls to other bpf functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n"); + verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n"); return -EPERM; } - ret = add_subprog(env, i + insn[i].imm + 1); + + if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn)) + ret = add_subprog(env, i + insn->imm + 1); + else + ret = add_kfunc_call(env, insn->imm, insn->off); + if (ret < 0) 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. */ @@ -1464,17 +3266,39 @@ static int check_subprogs(struct bpf_verifier_env *env) for (i = 0; i < env->subprog_cnt; i++) verbose(env, "func#%d @%d\n", i, subprog[i].start); + return 0; +} + +static int check_subprogs(struct bpf_verifier_env *env) +{ + int i, subprog_start, subprog_end, off, cur_subprog = 0; + struct bpf_subprog_info *subprog = env->subprog_info; + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + /* now check that all jumps are within the same subprog */ subprog_start = subprog[cur_subprog].start; subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; + if (code == (BPF_JMP | BPF_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) goto next; - off = i + insn[i].off + 1; + if (code == (BPF_JMP32 | BPF_JA)) + off = i + insn[i].imm + 1; + else + off = i + insn[i].off + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; @@ -1483,9 +3307,10 @@ 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; @@ -1515,7 +3340,7 @@ static int mark_reg_read(struct bpf_verifier_env *env, break; if (parent->live & REG_LIVE_DONE) { verbose(env, "verifier BUG type %s var_off %lld off %d\n", - reg_type_str[parent->type], + reg_type_str(env, parent->type), parent->var_off.value, parent->off); return -EFAULT; } @@ -1550,6 +3375,60 @@ static int mark_reg_read(struct bpf_verifier_env *env, return 0; } +static int mark_stack_slot_obj_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int spi, int nr_slots) +{ + struct bpf_func_state *state = func(env, reg); + int err, i; + + for (i = 0; i < nr_slots; i++) { + struct bpf_reg_state *st = &state->stack[spi - i].spilled_ptr; + + err = mark_reg_read(env, st, st->parent, REG_LIVE_READ64); + 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. @@ -1586,8 +3465,10 @@ 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; @@ -1596,13 +3477,17 @@ 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) { - if (reg->type != SCALAR_VALUE) + /* BPF_STX (including atomic variants) has multiple source + * operands, one of which is a ptr. Check whether the caller is + * asking about it. + */ + if (t == SRC_OP && reg->type != SCALAR_VALUE) return true; return BPF_SIZE(code) == BPF_DW; } @@ -1634,22 +3519,39 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, return true; } -/* Return TRUE if INSN doesn't have explicit value define. */ -static bool insn_no_def(struct bpf_insn *insn) -{ - u8 class = BPF_CLASS(insn->code); - - return (class == BPF_JMP || class == BPF_JMP32 || - class == BPF_STX || class == BPF_ST); +/* Return the regno defined by the insn, or -1. */ +static int insn_def_regno(const struct bpf_insn *insn) +{ + switch (BPF_CLASS(insn->code)) { + case BPF_JMP: + case BPF_JMP32: + case BPF_ST: + return -1; + case BPF_STX: + if ((BPF_MODE(insn->code) == BPF_ATOMIC || + BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) && + (insn->imm & BPF_FETCH)) { + if (insn->imm == BPF_CMPXCHG) + return BPF_REG_0; + else + return insn->src_reg; + } else { + 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) { - if (insn_no_def(insn)) + int dst_reg = insn_def_regno(insn); + + if (dst_reg == -1) return false; - return !is_reg64(env, insn, insn->dst_reg, NULL, DST_OP); + return !is_reg64(env, insn, dst_reg, NULL, DST_OP); } static void mark_insn_zext(struct bpf_verifier_env *env, @@ -1665,13 +3567,11 @@ 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) { @@ -1679,6 +3579,8 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return -EINVAL; } + mark_reg_scratched(env, regno); + reg = ®s[regno]; rw64 = is_reg64(env, insn, regno, reg, t); if (t == SRC_OP) { @@ -1710,49 +3612,424 @@ 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; +} + +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_insn_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_insn_hist_entry *p; + size_t alloc_size; + + /* combine instruction flags if we already recorded this instruction */ + if (env->cur_hist_ent) { + /* atomic instructions push insn_flags twice, for READ and + * WRITE sides, but they should agree on stack slot + */ + WARN_ONCE((env->cur_hist_ent->flags & insn_flags) && + (env->cur_hist_ent->flags & insn_flags) != insn_flags, + "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n", + env->insn_idx, env->cur_hist_ent->flags, insn_flags); + env->cur_hist_ent->flags |= insn_flags; + WARN_ONCE(env->cur_hist_ent->linked_regs != 0, + "verifier insn history bug: insn_idx %d linked_regs != 0: %#llx\n", + env->insn_idx, env->cur_hist_ent->linked_regs); + env->cur_hist_ent->linked_regs = linked_regs; + return 0; + } + + if (cur->insn_hist_end + 1 > env->insn_hist_cap) { + alloc_size = size_mul(cur->insn_hist_end + 1, sizeof(*p)); + p = kvrealloc(env->insn_hist, alloc_size, GFP_USER); + if (!p) + return -ENOMEM; + env->insn_hist = p; + env->insn_hist_cap = alloc_size / sizeof(*p); + } + + p = &env->insn_hist[cur->insn_hist_end]; + p->idx = env->insn_idx; + p->prev_idx = env->prev_insn_idx; + p->flags = insn_flags; + p->linked_regs = linked_regs; + + cur->insn_hist_end++; + env->cur_hist_ent = p; - cnt++; - p = krealloc(cur->jmp_history, cnt * sizeof(*p), GFP_USER); - if (!p) - return -ENOMEM; - p[cnt - 1].idx = env->insn_idx; - p[cnt - 1].prev_idx = env->prev_insn_idx; - cur->jmp_history = p; - cur->jmp_history_cnt = cnt; return 0; } +static struct bpf_insn_hist_entry *get_insn_hist_entry(struct bpf_verifier_env *env, + u32 hist_start, u32 hist_end, int insn_idx) +{ + if (hist_end > hist_start && env->insn_hist[hist_end - 1].idx == insn_idx) + return &env->insn_hist[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) +static int get_prev_insn_idx(const struct bpf_verifier_env *env, + struct bpf_verifier_state *st, + int insn_idx, u32 hist_start, u32 *hist_endp) { - u32 cnt = *history; + u32 hist_end = *hist_endp; + u32 cnt = hist_end - hist_start; + + if (insn_idx == st->first_insn_idx) { + if (cnt == 0) + return -ENOENT; + if (cnt == 1 && env->insn_hist[hist_start].idx == insn_idx) + return -ENOENT; + } - if (cnt && st->jmp_history[cnt - 1].idx == i) { - i = st->jmp_history[cnt - 1].prev_idx; - (*history)--; + if (cnt && env->insn_hist[hist_end - 1].idx == insn_idx) { + (*hist_endp)--; + return env->insn_hist[hist_end - 1].prev_idx; } else { - i--; + return insn_idx - 1; } - return i; } +static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) +{ + const struct btf_type *func; + struct btf *desc_btf; + + if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) + return NULL; + + desc_btf = find_kfunc_desc_btf(data, insn->off); + if (IS_ERR(desc_btf)) + return "<error>"; + + func = btf_type_by_id(desc_btf, insn->imm); + return btf_name_by_offset(desc_btf, func->name_off); +} + +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) { + verbose(bt->env, "BUG subprog enter from frame %d\n", bt->frame); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + bt->frame++; + return 0; +} + +static inline int bt_subprog_exit(struct backtrack_state *bt) +{ + if (bt->frame == 0) { + verbose(bt->env, "BUG subprog exit from frame 0\n"); + WARN_ONCE(1, "verifier backtracking bug"); + 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 */ +static void 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_insn_hist_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); + } +} + +static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); + /* 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, - u32 *reg_mask, u64 *stack_mask) +static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, + struct bpf_insn_hist_entry *hist, struct backtrack_state *bt) { const struct bpf_insn_cbs cbs = { + .cb_call = disasm_kfunc_name, .cb_print = verbose, .private_data = env, }; @@ -1760,29 +4037,45 @@ static int backtrack_insn(struct bpf_verifier_env *env, int 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_LEVEL) { - verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); + if (env->log.level & BPF_LOG_LEVEL2) { + 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); + 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); } + /* 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. @@ -1790,7 +4083,7 @@ 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) { @@ -1798,15 +4091,16 @@ 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)) + 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. @@ -1814,66 +4108,197 @@ 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) - return 0; - if (BPF_SIZE(insn->code) != BPF_DW) + 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; - if (BPF_SIZE(insn->code) != BPF_DW) + 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; - 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))) - 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) + 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 + */ + WARN_ONCE(idx + 1 != subseq_idx, "verifier backtracking bug"); + /* 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) { + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + 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) { + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + /* we are now tracking register spills correctly, + * so any instance of leftover slots is a bug + */ + if (bt_stack_mask(bt) != 0) { + verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)"); + return -EFAULT; + } + /* propagate r1-r5 to the caller */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) { + if (bt_is_reg_set(bt, i)) { + 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 (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + if (bt_stack_mask(bt) != 0) { + verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)"); + return -EFAULT; + } + /* clear r1-r5 in callback subprog's mask */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + bt_clear_reg(bt, i); + 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. + */ + 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) { + bt_clear_reg(bt, BPF_REG_0); + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { /* if backtracing was looking for registers R1-R5 * they should have been found already. */ - verbose(env, "BUG regs %x\n", *reg_mask); + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); 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 && 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) { + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + 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. + */ + bt_set_reg(bt, dreg); + bt_set_reg(bt, sreg); + } 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 @@ -1882,6 +4307,10 @@ 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; } @@ -1944,110 +4373,256 @@ 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, + * because precision markings in current non-checkpointed state are + * not needed. See why in the comment in __mark_chain_precision below. */ - for (; st; st = st->parent) + for (st = st->parent; st; st = st->parent) { for (i = 0; i <= st->curframe; i++) { 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 (func->stack[j].slot_type[0] != STACK_SPILL) + 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); + } } } + } } -static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, - int spi) +static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { + struct bpf_func_state *func; + struct bpf_reg_state *reg; + int i, j; + + for (i = 0; i <= st->curframe; i++) { + func = st->frame[i]; + for (j = 0; j < BPF_REG_FP; j++) { + reg = &func->regs[j]; + if (reg->type != SCALAR_VALUE) + continue; + reg->precise = false; + } + 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) + continue; + reg->precise = false; + } + } +} + +/* + * __mark_chain_precision() backtracks BPF program instruction sequence and + * chain of verifier states making sure that register *regno* (if regno >= 0) + * and/or stack slot *spi* (if spi >= 0) are marked as precisely tracked + * SCALARS, as well as any other registers and slots that contribute to + * a tracked state of given registers/stack slots, depending on specific BPF + * assembly instructions (see backtrack_insns() for exact instruction handling + * logic). This backtracking relies on recorded insn_hist and is able to + * traverse entire chain of parent states. This process ends only when all the + * necessary registers/slots and their transitive dependencies are marked as + * precise. + * + * One important and subtle aspect is that precise marks *do not matter* in + * the currently verified state (current state). It is important to understand + * why this is the case. + * + * First, note that current state is the state that is not yet "checkpointed", + * i.e., it is not yet put into env->explored_states, and it has no children + * states as well. It's ephemeral, and can end up either a) being discarded if + * compatible explored state is found at some point or BPF_EXIT instruction is + * reached or b) checkpointed and put into env->explored_states, branching out + * into one or more children states. + * + * In the former case, precise markings in current state are completely + * ignored by state comparison code (see regsafe() for details). Only + * checkpointed ("old") state precise markings are important, and if old + * state's register/slot is precise, regsafe() assumes current state's + * register/slot as precise and checks value ranges exactly and precisely. If + * states turn out to be compatible, current state's necessary precise + * markings and any required parent states' precise markings are enforced + * after the fact with propagate_precision() logic, after the fact. But it's + * important to realize that in this case, even after marking current state + * registers/slots as precise, we immediately discard current state. So what + * actually matters is any of the precise markings propagated into current + * state's parent states, which are always checkpointed (due to b) case above). + * As such, for scenario a) it doesn't matter if current state has precise + * markings set or not. + * + * Now, for the scenario b), checkpointing and forking into child(ren) + * state(s). Note that before current state gets to checkpointing step, any + * processed instruction always assumes precise SCALAR register/slot + * knowledge: if precise value or range is useful to prune jump branch, BPF + * verifier takes this opportunity enthusiastically. Similarly, when + * register's value is used to calculate offset or memory address, exact + * knowledge of SCALAR range is assumed, checked, and enforced. So, similar to + * what we mentioned above about state comparison ignoring precise markings + * during state comparison, BPF verifier ignores and also assumes precise + * markings *at will* during instruction verification process. But as verifier + * assumes precision, it also propagates any precision dependencies across + * parent states, which are not yet finalized, so can be further restricted + * based on new knowledge gained from restrictions enforced by their children + * states. This is so that once those parent states are finalized, i.e., when + * they have no more active children state, state comparison logic in + * is_state_visited() would enforce strict and precise SCALAR ranges, if + * required for correctness. + * + * To build a bit more intuition, note also that once a state is checkpointed, + * the path we took to get to that state is not important. This is crucial + * property for state pruning. When state is checkpointed and finalized at + * some instruction index, it can be correctly and safely used to "short + * circuit" any *compatible* state that reaches exactly the same instruction + * index. I.e., if we jumped to that instruction from a completely different + * code path than original finalized state was derived from, it doesn't + * matter, current state can be discarded because from that instruction + * forward having a compatible state will ensure we will safely reach the + * exit. States describe preconditions for further exploration, but completely + * forget the history of how we got here. + * + * This also means that even if we needed precise SCALAR range to get to + * finalized state, but from that point forward *that same* SCALAR register is + * never used in a precise context (i.e., it's precise value is not needed for + * correctness), it's correct and safe to mark such register as "imprecise" + * (i.e., precise marking set to false). This is what we rely on when we do + * not set precise marking in current state. If no child state requires + * precision for any given SCALAR register, it's safe to dictate that it can + * be imprecise. If any child state does require this register to be precise, + * we'll mark it precise later retroactively during precise markings + * propagation from child state to parent states. + * + * Skipping precise marking setting in current state is a mild version of + * relying on the above observation. But we can utilize this property even + * more aggressively by proactively forgetting any precise marking in the + * current state (which we inherited from the parent state), right before we + * checkpoint it and branch off into new child state. This is done by + * 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 regno) +{ + struct backtrack_state *bt = &env->bt; struct bpf_verifier_state *st = env->cur_state; int first_idx = st->first_insn_idx; int last_idx = env->insn_idx; + int subseq_idx = -1; struct bpf_func_state *func; 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; - func = st->frame[st->curframe]; + /* set frame number from which we are starting to backtrack */ + bt_init(bt, env->cur_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[bt->frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { WARN_ONCE(1, "backtracing misuse"); return -EFAULT; } - if (!reg->precise) - new_marks = true; - else - reg_mask = 0; - reg->precise = true; + bt_set_reg(bt, regno); } - while (spi >= 0) { - if (func->stack[spi].slot_type[0] != STACK_SPILL) { - stack_mask = 0; - break; - } - reg = &func->stack[spi].spilled_ptr; - if (reg->type != SCALAR_VALUE) { - stack_mask = 0; - break; - } - if (!reg->precise) - new_marks = true; - else - stack_mask = 0; - reg->precise = true; - break; - } - - 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; + u32 hist_start = st->insn_hist_start; + u32 hist_end = st->insn_hist_end; + struct bpf_insn_hist_entry *hist; + + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", + bt->frame, last_idx, first_idx, subseq_idx); + } + + if (last_idx < 0) { + /* we are at the entry into subprog, which + * is expected for global funcs, but only if + * requested precise registers are R1-R5 + * (which are global func's input arguments) + */ + if (st->curframe == 0 && + st->frame[0]->subprogno > 0 && + st->frame[0]->callsite == BPF_MAIN_FUNC && + 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]; + bt_clear_reg(bt, i); + if (reg->type == SCALAR_VALUE) + reg->precise = true; + } + return 0; + } + + verbose(env, "BUG backtracking func entry subprog %d reg_mask %x stack_mask %llx\n", + st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } - if (env->log.level & BPF_LOG_LEVEL) - verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); for (i = last_idx;;) { if (skip_first) { err = 0; skip_first = false; } else { - err = backtrack_insn(env, i, ®_mask, &stack_mask); + hist = get_insn_hist_entry(env, hist_start, hist_end, i); + err = backtrack_insn(env, i, subseq_idx, hist, bt); } if (err == -ENOTSUPP) { - mark_all_scalars_precise(env, st); + mark_all_scalars_precise(env, env->cur_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) + subseq_idx = i; + i = get_prev_insn_idx(env, st, i, hist_start, &hist_end); + if (i == -ENOENT) break; - i = get_prev_insn_idx(st, i, &history); if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask @@ -2064,86 +4639,89 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, if (!st) break; - new_marks = false; - func = st->frame[st->curframe]; - 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; } - if (func->stack[i].slot_type[0] != STACK_SPILL) { - stack_mask &= ~(1ull << i); - continue; + bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); + for_each_set_bit(i, mask, 64) { + if (i >= func->allocated_stack / BPF_REG_SIZE) { + verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n", + i, func->allocated_stack / BPF_REG_SIZE); + WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)"); + return -EFAULT; + } + + if (!is_spilled_scalar_reg(&func->stack[i])) { + 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; } - 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); + 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_LEVEL) { - print_verifier_state(env, func); - verbose(env, "parent %s regs=%x stack=%llx marks\n", - new_marks ? "didn't have" : "already had", - reg_mask, stack_mask); } - 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, env->cur_state); + bt_reset(bt); + } + return 0; } -static int mark_chain_precision(struct bpf_verifier_env *env, int regno) +int mark_chain_precision(struct bpf_verifier_env *env, int regno) { - return __mark_chain_precision(env, regno, -1); + return __mark_chain_precision(env, regno); } -static int mark_chain_precision_stack(struct bpf_verifier_env *env, 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) { - return __mark_chain_precision(env, -1, spi); + return __mark_chain_precision(env, -1); } static bool is_spillable_regtype(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_MAP_VALUE: - case PTR_TO_MAP_VALUE_OR_NULL: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: @@ -2152,14 +4730,15 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: + case PTR_TO_BUF: + case PTR_TO_MEM: + case PTR_TO_FUNC: + case PTR_TO_MAP_KEY: + case PTR_TO_ARENA: return true; default: return false; @@ -2172,9 +4751,17 @@ 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); +} + +/* 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 subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value; } static bool __is_pointer_value(bool allow_ptr_leaks, @@ -2186,39 +4773,116 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } -static void save_register_state(struct bpf_func_state *state, - int spi, struct bpf_reg_state *reg) +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) +{ + struct bpf_reg_state *parent = dst->parent; + enum bpf_reg_liveness live = dst->live; + + *dst = *src; + dst->parent = parent; + dst->live = live; +} + +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; - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + copy_register_state(&state->stack[spi].spilled_ptr, reg); + if (size == BPF_REG_SIZE) + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; - for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_SPILL; + 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--) + 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 functions track spill/fill of registers, +/* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ -static int check_stack_write(struct bpf_verifier_env *env, - struct bpf_func_state *state, /* func where register points to */ - int off, int size, int value_regno, int insn_idx) +static int check_stack_write_fixed_off(struct bpf_verifier_env *env, + /* stack frame we're writing to */ + struct bpf_func_state *state, + int off, int size, int value_regno, + int insn_idx) { 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 = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), - state->acquired_refs, true); - 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; @@ -2227,21 +4891,47 @@ static int check_stack_write(struct bpf_verifier_env *env, cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; + if (!env->bypass_spec_v4) { + bool sanitize = reg && is_spillable_regtype(reg->type); - if (reg && size == BPF_REG_SIZE && register_is_const(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 conervative. - * 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; + for (i = 0; i < size; i++) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { + sanitize = true; + break; + } } - save_register_state(state, spi, reg); + + if (sanitize) + env->insn_aux_data[insn_idx].sanitize_stack_spill = true; + } + + err = destroy_if_dynptr_stack_slot(env, state, spi); + if (err) + return err; + + check_fastcall_stack_contract(env, state, insn_idx, off); + mark_stack_slot_scratched(env, spi); + 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) { @@ -2249,57 +4939,20 @@ static int check_stack_write(struct bpf_verifier_env *env, verbose(env, "invalid size of register spill\n"); return -EACCES; } - if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - - if (!env->bypass_spec_v4) { - bool sanitize = false; - - if (state->stack[spi].slot_type[0] == STACK_SPILL && - register_is_const(&state->stack[spi].spilled_ptr)) - sanitize = true; - for (i = 0; i < BPF_REG_SIZE; i++) - if (state->stack[spi].slot_type[i] == STACK_MISC) { - sanitize = true; - break; - } - if (sanitize) { - int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; - int soff = (-spi - 1) * BPF_REG_SIZE; - - /* detected reuse of integer stack slot with a pointer - * which means either llvm is reusing stack slot or - * an attacker is trying to exploit CVE-2018-3639 - * (speculative store bypass) - * Have to sanitize that slot with preemptive - * store of zero. - */ - if (*poff && *poff != soff) { - /* disallow programs where single insn stores - * into two different stack slots, since verifier - * cannot sanitize them - */ - verbose(env, - "insn %d cannot access two stack slots fp%d and fp%d", - insn_idx, *poff, soff); - return -EINVAL; - } - *poff = soff; - } - } - save_register_state(state, spi, reg); + 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 (state->stack[spi].slot_type[0] == STACK_SPILL) + /* 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++) - state->stack[spi].slot_type[i] = STACK_MISC; + 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 @@ -2313,8 +4966,14 @@ static int check_stack_write(struct bpf_verifier_env *env, 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; @@ -2323,61 +4982,289 @@ static int check_stack_write(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_insn_history(env, env->cur_state, insn_flags, 0); return 0; } -static int check_stack_read(struct bpf_verifier_env *env, - struct bpf_func_state *reg_state /* func where register points to */, - int off, int size, int value_regno) +/* Write the stack: 'stack[ptr_regno + off] = value_regno'. 'ptr_regno' is + * known to contain a variable offset. + * This function checks whether the write is permitted and conservatively + * tracks the effects of the write, considering that each stack slot in the + * dynamic range is potentially written to. + * + * 'off' includes 'regno->off'. + * 'value_regno' can be -1, meaning that an unknown value is being written to + * the stack. + * + * Spilled pointers in range are not marked as written because we don't know + * what's going to be actually written. This means that read propagation for + * future reads cannot be terminated by this write. + * + * For privileged programs, uninitialized stack slots are considered + * initialized by this write (even though we don't know exactly what offsets + * are going to be written to). The idea is that we don't want the verifier to + * reject future reads that access slots written to through variable offsets. + */ +static int check_stack_write_var_off(struct bpf_verifier_env *env, + /* func where register points to */ + struct bpf_func_state *state, + int ptr_regno, int off, int size, + int value_regno, int insn_idx) +{ + struct bpf_func_state *cur; /* state of the current function */ + 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 + */ + bool zero_used = false; + + cur = env->cur_state->frame[env->cur_state->curframe]; + ptr_reg = &cur->regs[ptr_regno]; + min_off = ptr_reg->smin_value + off; + 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)) || + (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0)) + writing_zero = true; + + 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; + int slot, spi; + + slot = -i - 1; + spi = slot / BPF_REG_SIZE; + stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; + mark_stack_slot_scratched(env, spi); + + if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) { + /* Reject the write if range we may write to has not + * been initialized beforehand. If we didn't reject + * here, the ptr status would be erased below (even + * though not all slots are actually overwritten), + * possibly opening the door to leaks. + * + * We do however catch STACK_INVALID case below, and + * only allow reading possibly uninitialized memory + * later for CAP_PERFMON, as the write may not happen to + * that slot. + */ + verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d", + insn_idx, i); + return -EINVAL; + } + + /* 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. */ + new_type = STACK_MISC; + if (writing_zero && *stype == STACK_ZERO) { + new_type = STACK_ZERO; + zero_used = true; + } + /* If the slot is STACK_INVALID, we check whether it's OK to + * pretend that it will be initialized by this write. The slot + * might not actually be written to, and so if we mark it as + * initialized future reads might leak uninitialized memory. + * For privileged programs, we will accept such reads to slots + * that may or may not be written because, if we're reject + * them, the error would be too confusing. + */ + if (*stype == STACK_INVALID && !env->allow_uninit_stack) { + verbose(env, "uninit stack in range of var-offset write prohibited for !root; insn %d, off: %d", + insn_idx, i); + return -EINVAL; + } + *stype = new_type; + } + if (zero_used) { + /* backtracking doesn't work for STACK_ZERO yet. */ + err = mark_chain_precision(env, value_regno); + if (err) + return err; + } + return 0; +} + +/* When register 'dst_regno' is assigned some values from stack[min_off, + * max_off), we set the register's type according to the types of the + * respective stack slots. If all the stack values are known to be zeros, then + * so is the destination reg. Otherwise, the register is considered to be + * SCALAR. This function does not deal with register filling; the caller must + * ensure that all spilled registers in the stack range have been marked as + * read. + */ +static void mark_reg_stack_read(struct bpf_verifier_env *env, + /* func where src register points to */ + struct bpf_func_state *ptr_state, + int min_off, int max_off, int dst_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; - int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; - struct bpf_reg_state *reg; + int i, slot, spi; u8 *stype; + int zeros = 0; - if (reg_state->allocated_stack <= slot) { - verbose(env, "invalid read from stack off %d+0 size %d\n", - off, size); - return -EACCES; + 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(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 + * 'dst_regno'. It handles reg filling if the addressed stack slot is a + * spilled reg. + * + * 'dst_regno' can be -1, meaning that the read value is not going to a + * register. + * + * The access is assumed to be within the current stack bounds. + */ +static int check_stack_read_fixed_off(struct bpf_verifier_env *env, + /* func where src register points to */ + struct bpf_func_state *reg_state, + int off, int size, int dst_regno) +{ + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; + struct bpf_reg_state *reg; + u8 *stype, type; + int insn_flags = insn_stack_access_flags(reg_state->frameno, spi); + stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; - if (stype[0] == STACK_SPILL) { - if (size != BPF_REG_SIZE) { + mark_stack_slot_scratched(env, spi); + check_fastcall_stack_contract(env, state, env->insn_idx, off); + + if (is_spilled_reg(®_state->stack[spi])) { + u8 spill_size = 1; + + for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) + spill_size++; + + if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } - if (value_regno >= 0) { - mark_reg_unknown(env, state->regs, value_regno); - state->regs[value_regno].live |= REG_LIVE_WRITTEN; - } + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); - return 0; - } - for (i = 1; i < BPF_REG_SIZE; i++) { - if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { - verbose(env, "corrupted spill memory\n"); - return -EACCES; - } - } + if (dst_regno < 0) + return 0; + + 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; + + copy_register_state(&state->regs[dst_regno], reg); + state->regs[dst_regno].subreg_def = subreg_def; - if (value_regno >= 0) { + /* 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) { + 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; + } + + if (spill_cnt == size && + tnum_is_const(reg->var_off) && reg->var_off.value == 0) { + __mark_reg_const_zero(env, &state->regs[dst_regno]); + /* this IS register fill, so keep insn_flags */ + } else if (zero_cnt == size) { + /* similarly to mark_reg_stack_read(), preserve zeroes */ + __mark_reg_const_zero(env, &state->regs[dst_regno]); + insn_flags = 0; /* not restoring original register state */ + } else { + mark_reg_unknown(env, state->regs, dst_regno); + insn_flags = 0; /* not restoring original register state */ + } + } + state->regs[dst_regno].live |= REG_LIVE_WRITTEN; + } else if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[value_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[value_regno].live |= REG_LIVE_WRITTEN; + state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) { - /* If value_regno==-1, the caller is asking us whether + /* If dst_regno==-1, the caller is asking us whether * it is acceptable to use this value as a SCALAR_VALUE * (e.g. for XADD). * We must not allow unprivileged callers to do that @@ -2389,70 +5276,167 @@ static int check_stack_read(struct bpf_verifier_env *env, } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { - int zeros = 0; - for (i = 0; i < size; i++) { - if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC) + type = stype[(slot - i) % BPF_REG_SIZE]; + if (type == STACK_MISC) continue; - if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) { - zeros++; + 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 (value_regno >= 0) { - if (zeros == size) { - /* any size read into register is zero extended, - * so the whole register == const_zero - */ - __mark_reg_const_zero(&state->regs[value_regno]); - /* backtracking doesn't support STACK_ZERO yet, - * so mark it precise here, so that later - * backtracking can stop here. - * Backtracking may not need this if this register - * doesn't participate in pointer adjustment. - * Forward propagation of precise flag is not - * necessary either. This mark is only to stop - * backtracking. Any register that contributed - * to const 0 was marked precise before spill. - */ - state->regs[value_regno].precise = true; - } else { - /* have read misc data from the stack */ - mark_reg_unknown(env, state->regs, value_regno); - } - state->regs[value_regno].live |= REG_LIVE_WRITTEN; - } + 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_insn_history(env, env->cur_state, insn_flags, 0); return 0; } -static int check_stack_access(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, - int off, int size) +enum bpf_access_src { + ACCESS_DIRECT = 1, /* the access is performed by an instruction */ + ACCESS_HELPER = 2, /* the access is performed by a helper */ +}; + +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_type type, + struct bpf_call_arg_meta *meta); + +static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) { - /* Stack accesses must be at a fixed offset, so that we - * can determine what type of data were returned. See - * check_stack_read(). + return cur_regs(env) + regno; +} + +/* Read the stack at 'ptr_regno + off' and put the result into the register + * 'dst_regno'. + * 'off' includes the pointer register's fixed offset(i.e. 'ptr_regno.off'), + * but not its variable offset. + * 'size' is assumed to be <= reg size and the access is assumed to be aligned. + * + * As opposed to check_stack_read_fixed_off, this function doesn't deal with + * filling registers (i.e. reads of spilled register cannot be detected when + * the offset is not fixed). We conservatively mark 'dst_regno' as containing + * SCALAR_VALUE. That's why we assert that the 'ptr_regno' has a variable + * offset; for a fixed offset check_stack_read_fixed_off should be used + * instead. + */ +static int check_stack_read_var_off(struct bpf_verifier_env *env, + int ptr_regno, int off, int size, int dst_regno) +{ + /* The state of the source register. */ + struct bpf_reg_state *reg = reg_state(env, ptr_regno); + struct bpf_func_state *ptr_state = func(env, reg); + int err; + int min_off, max_off; + + /* Note that we pass a NULL meta, so raw access will not be permitted. */ - if (!tnum_is_const(reg->var_off)) { + err = check_stack_range_initialized(env, ptr_regno, off, size, + 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; +} + +/* check_stack_read dispatches to check_stack_read_fixed_off or + * check_stack_read_var_off. + * + * The caller must ensure that the offset falls within the allocated stack + * bounds. + * + * 'dst_regno' is a register which will receive the value from the stack. It + * can be -1, meaning that the read value is not going to a register. + */ +static int check_stack_read(struct bpf_verifier_env *env, + int ptr_regno, int off, int size, + int dst_regno) +{ + struct bpf_reg_state *reg = reg_state(env, ptr_regno); + struct bpf_func_state *state = func(env, reg); + int err; + /* Some accesses are only permitted with a static offset. */ + bool var_off = !tnum_is_const(reg->var_off); + + /* The offset is required to be static when reads don't go to a + * register, in order to not leak pointers (see + * check_stack_read_fixed_off). + */ + if (dst_regno < 0 && var_off) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable stack access var_off=%s off=%d size=%d\n", + verbose(env, "variable offset stack pointer cannot be passed into helper function; var_off=%s off=%d size=%d\n", tn_buf, off, size); return -EACCES; } - - if (off >= 0 || off < -MAX_BPF_STACK) { - verbose(env, "invalid stack off=%d size=%d\n", off, size); - return -EACCES; + /* 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(). 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 (!var_off) { + off += reg->var_off.value; + err = check_stack_read_fixed_off(env, state, off, size, + dst_regno); + } else { + /* Variable offset stack reads need more conservative handling + * than fixed offset ones. Note that dst_regno >= 0 on this + * branch. + */ + err = check_stack_read_var_off(env, ptr_regno, off, size, + dst_regno); } + return err; +} - return 0; + +/* check_stack_write dispatches to check_stack_write_fixed_off or + * check_stack_write_var_off. + * + * 'ptr_regno' is the register used as a pointer into the stack. + * 'off' includes 'ptr_regno->off', but not its variable offset (if any). + * 'value_regno' is the register whose value we're writing to the stack. It can + * be -1, meaning that we're not writing from a register. + * + * The caller must ensure that the offset falls within the maximum stack size. + */ +static int check_stack_write(struct bpf_verifier_env *env, + int ptr_regno, int off, int size, + int value_regno, int insn_idx) +{ + struct bpf_reg_state *reg = reg_state(env, ptr_regno); + struct bpf_func_state *state = func(env, reg); + int err; + + if (tnum_is_const(reg->var_off)) { + off += reg->var_off.value; + err = check_stack_write_fixed_off(env, state, off, size, + value_regno, insn_idx); + } else { + /* Variable offset stack reads need more conservative handling + * than fixed offset ones. + */ + err = check_stack_write_var_off(env, state, + ptr_regno, off, size, + value_regno, insn_idx); + } + return err; } static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, @@ -2490,6 +5474,10 @@ static int __check_mem_access(struct bpf_verifier_env *env, int regno, reg = &cur_regs(env)[regno]; switch (reg->type) { + case PTR_TO_MAP_KEY: + verbose(env, "invalid access to map key, key_size=%d off=%d size=%d\n", + mem_size, off, size); + break; case PTR_TO_MAP_VALUE: verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", mem_size, off, size); @@ -2522,11 +5510,8 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. - */ - if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, state); - - /* The minimum value is only important with signed + * + * The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use @@ -2568,36 +5553,345 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, return 0; } +static int __check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + bool fixed_off_ok) +{ + /* Access to this pointer-typed register or passing it to a helper + * is only allowed in its original, unmodified form. + */ + + if (reg->off < 0) { + verbose(env, "negative offset %s ptr R%d off=%d disallowed\n", + reg_type_str(env, reg->type), regno, reg->off); + return -EACCES; + } + + if (!fixed_off_ok && reg->off) { + verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", + reg_type_str(env, reg->type), regno, reg->off); + return -EACCES; + } + + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "variable %s access var_off=%s disallowed\n", + reg_type_str(env, reg->type), tn_buf); + return -EACCES; + } + + return 0; +} + +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); +} + +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 = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); + int perm_flags; + const char *reg_name = ""; + + 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; + + /* We need to verify reg->type and reg->btf, before accessing reg->btf */ + 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 + * normal store of unreferenced kptr, we must ensure var_off is zero. + * Since ref_ptr cannot be accessed directly by BPF insns, checks for + * reg->off and reg->ref_obj_id are not needed here. + */ + if (__check_ptr_off_reg(env, reg, regno, true)) + return -EACCES; + + /* 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: + * + * struct foo { + * struct bar br; + * struct baz bz; + * }; + * + * struct foo *v; + * v = func(); // PTR_TO_BTF_ID + * val->foo = v; // reg->off is zero, btf and btf_id match type + * val->bar = &v->br; // reg->off is still zero, but we need to retry with + * // first member type of struct after comparison fails + * val->baz = &v->bz; // reg->off is non-zero, so struct needs to be walked + * // to match type + * + * In the kptr_ref case, check_func_arg_reg_off already ensures reg->off + * is zero. We must also ensure that btf_struct_ids_match does not walk + * the struct to match type against first member of struct, i.e. reject + * second case from above. Hence, when type is BPF_KPTR_REF, we set + * strict mode to true for type match. + */ + 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_UNREF)) + goto bad_type; + return 0; +bad_type: + verbose(env, "invalid kptr access, R%d type=%s%s ", regno, + reg_type_str(env, reg->type), reg_name); + verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name); + if (kptr_field->type == BPF_KPTR_UNREF) + verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED), + targ_name); + else + verbose(env, "\n"); + return -EINVAL; +} + +static bool in_sleepable(struct bpf_verifier_env *env) +{ + return env->prog->sleepable || + (env->cur_state && env->cur_state->in_sleepable); +} + +/* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() + * 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_lock || + 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) +{ + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; + int class = BPF_CLASS(insn->code); + struct bpf_reg_state *val_reg; + + /* Things we already checked for in check_map_access and caller: + * - Reject cases where variable offset may touch kptr + * - size of access (must be BPF_DW) + * - tnum_is_const(reg->var_off) + * - kptr_field->offset == off + reg->var_off.value + */ + /* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */ + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n"); + return -EACCES; + } + + /* 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 || 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) { + 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, btf_ld_kptr_type(env, kptr_field)); + } else if (class == BPF_STX) { + val_reg = reg_state(env, value_regno); + if (!register_is_null(val_reg) && + map_kptr_match_type(env, kptr_field, val_reg, value_regno)) + return -EACCES; + } else if (class == BPF_ST) { + if (insn->imm) { + verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n", + kptr_field->offset); + return -EACCES; + } + } else { + verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n"); + return -EACCES; + } + return 0; +} + /* 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) + int off, int size, bool zero_size_allowed, + enum bpf_access_src src) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; - int err; + struct btf_record *rec; + int err, i; err = check_mem_region_access(env, regno, off, size, map->value_size, zero_size_allowed); if (err) return err; - if (map_value_has_spin_lock(map)) { - u32 lock = map->spin_lock_off; + if (IS_ERR_OR_NULL(map->record)) + return 0; + rec = map->record; + for (i = 0; i < rec->cnt; i++) { + struct btf_field *field = &rec->fields[i]; + u32 p = field->offset; - /* if any part of struct bpf_spin_lock can be touched by - * load/store reject this program. - * To check that [x1, x2) overlaps with [y1, y2) + /* If any part of a field can be touched by load/store, reject + * 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 < lock + sizeof(struct bpf_spin_lock) && - lock < reg->umax_value + off + size) { - verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); - return -EACCES; + 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, "%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, "%s access cannot have variable offset\n", + btf_field_type_name(field->type)); + return -EACCES; + } + if (p != off + reg->var_off.value) { + 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, "%s access size must be BPF_DW\n", + btf_field_type_name(field->type)); + return -EACCES; + } + break; + default: + verbose(env, "%s cannot be accessed directly by load/store\n", + btf_field_type_name(field->type)); + return -EACCES; + } } } - return err; + return 0; } #define MAX_PACKET_OFF 0xffff @@ -2606,7 +5900,9 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) { - switch (env->prog->type) { + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); + + switch (prog_type) { /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: @@ -2616,7 +5912,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; - /* fallthrough */ + fallthrough; /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: @@ -2662,7 +5958,9 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, regno); return -EACCES; } - err = __check_mem_access(env, regno, off, size, reg->range, + + err = reg->range < 0 ? -EINVAL : + __check_mem_access(env, regno, off, size, reg->range, zero_size_allowed); if (err) { verbose(env, "R%d offset is outside of the packet\n", regno); @@ -2685,11 +5983,13 @@ 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, - u32 *btf_id) + struct btf **btf, u32 *btf_id, bool *is_retval, bool is_ldsx) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, .log = &env->log, + .is_retval = false, + .is_ldsx = is_ldsx, }; if (env->ops->is_valid_access && @@ -2702,11 +6002,14 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, * type of narrower access. */ *reg_type = info.reg_type; + *is_retval = info.is_retval; - if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) + if (base_type(*reg_type) == PTR_TO_BTF_ID) { + *btf = info.btf; *btf_id = info.btf_id; - else + } else { 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) env->prog->aux->max_ctx_offset = off + size; @@ -2769,16 +6072,11 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, } verbose(env, "R%d invalid %s access off=%d size=%d\n", - regno, reg_type_str[reg->type], off, size); + regno, reg_type_str(env, reg->type), off, size); return -EACCES; } -static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) -{ - return cur_regs(env) + regno; -} - static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno)); @@ -2813,6 +6111,56 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_FLOW_KEYS; } +static bool is_arena_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = reg_state(env, regno); + + return reg->type == PTR_TO_ARENA; +} + +static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { +#ifdef CONFIG_NET + [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], + [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 + * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are + * not. + * + * Eventually, we should make PTR_TRUSTED the single source of truth + * for whether a register is trusted. + */ + return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS && + !bpf_type_has_unsafe_modifiers(reg->type); +} + +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) @@ -2889,6 +6237,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_FLOW_KEYS: pointer_desc = "flow keys "; break; + case PTR_TO_MAP_KEY: + pointer_desc = "key "; + break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; @@ -2897,8 +6248,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, break; case PTR_TO_STACK: pointer_desc = "stack "; - /* The stack spill tracking logic in check_stack_write() - * and check_stack_read() relies on stack accesses being + /* The stack spill tracking logic in check_stack_write_fixed_off() + * and check_stack_read_fixed_off() relies on stack accesses being * aligned. */ strict = true; @@ -2915,6 +6266,8 @@ 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; } @@ -2922,18 +6275,43 @@ 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 @@ -2942,43 +6320,133 @@ 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: - /* round up to 32-bytes, since this is granularity - * of interpreter stack size + /* protect against potential stack overflow that might happen when + * bpf2bpf calls get combined with tailcalls. Limit the caller's stack + * depth for such case down to 256 so that the worst case scenario + * would result in 8k stack size (32 which is tailcall limit * 256 = + * 8k). + * + * To get the idea what might happen, see an example: + * func1 -> sub rsp, 128 + * subfunc1 -> sub rsp, 256 + * tailcall1 -> add rsp, 256 + * func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320) + * subfunc2 -> sub rsp, 64 + * subfunc22 -> sub rsp, 128 + * tailcall2 -> add rsp, 128 + * func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416) + * + * tailcall will unwind the current stack frame but it will not get rid + * of caller's stack as shown on the example above. */ - 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); + if (idx && subprog[idx].has_tail_call && depth >= 256) { + verbose(env, + "tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n", + 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++) { - if (insn[i].code != (BPF_JMP | BPF_CALL)) - continue; - if (insn[i].src_reg != BPF_PSEUDO_CALL) + 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; /* remember insn and function to return to */ ret_insn[frame] = i + 1; ret_prog[frame] = idx; /* find the callee */ - i = i + insn[i].imm + 1; - idx = find_subprog(env, i); - if (idx < 0) { + next_insn = i + insn[i].imm + 1; + sidx = find_subprog(env, next_insn); + if (sidx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", - i); + next_insn); return -EFAULT; } + if (subprog[sidx].is_async_cb) { + if (subprog[sidx].has_tail_call) { + verbose(env, "verifier bug. subprog has tail_call and async cb\n"); + return -EFAULT; + } + /* 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\n", 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; + frame++; if (frame >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep !\n", @@ -2987,18 +6455,79 @@ continue_func: } goto process_func; } + /* if tail call got detected across bpf2bpf calls then mark each of the + * currently present subprog frames as tail call reachable subprogs; + * this info will be utilized by JIT so that we will be preserving the + * tail call counter throughout bpf2bpf calls combined with tailcalls + */ + if (tail_call_reachable) + 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; + /* end of for() loop means the last insn of the 'subprog' * was reached. Doesn't matter whether it was JA or EXIT */ 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) @@ -3015,24 +6544,24 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, } #endif -int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +static int __check_buffer_access(struct bpf_verifier_env *env, + const char *buf_info, + const struct bpf_reg_state *reg, + int regno, int off, int size) { - /* Access to ctx or passing it to a helper is only allowed in - * its original, unmodified form. - */ - - if (reg->off) { - verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n", - regno, reg->off); + if (off < 0) { + verbose(env, + "R%d invalid %s buffer access: off=%d, size=%d\n", + regno, buf_info, off, size); return -EACCES; } - if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf); + verbose(env, + "R%d invalid variable buffer offset: off=%d, var_off=%s\n", + regno, off, tn_buf); return -EACCES; } @@ -3043,27 +6572,37 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size) { - if (off < 0) { - verbose(env, - "R%d invalid tracepoint buffer access: off=%d, size=%d", - regno, off, size); - return -EACCES; - } - if (!tnum_is_const(reg->var_off) || reg->var_off.value) { - char tn_buf[48]; + int err; + + err = __check_buffer_access(env, "tracepoint", reg, regno, off, size); + if (err) + return err; - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, - "R%d invalid variable buffer offset: off=%d, var_off=%s", - regno, off, tn_buf); - return -EACCES; - } if (off + size > env->prog->aux->max_tp_access) env->prog->aux->max_tp_access = off + size; return 0; } +static int check_buffer_access(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + int regno, int off, int size, + bool zero_size_allowed, + u32 *max_access) +{ + const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr"; + int err; + + err = __check_buffer_access(env, buf_info, reg, regno, off, size); + if (err) + return err; + + if (off + size > *max_access) + *max_access = off + size; + + return 0; +} + /* BPF architecture zero extends alu32 ops into 64-bit registesr */ static void zext_32_to_64(struct bpf_reg_state *reg) { @@ -3097,17 +6636,177 @@ 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; + } + +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; - __reg_combine_64_into_32(reg); + } + + 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) { - return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; + /* A map is considered read-only if the following condition are true: + * + * 1) BPF program side cannot change any of the map content. The + * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map + * and was set at map creation time. + * 2) The map value(s) have been initialized from user space by a + * loader and then "frozen", such that no new map update/delete + * operations from syscall side are possible for the rest of + * the map's lifetime from that point onwards. + * 3) Any parallel/pending map update/delete operations from syscall + * side have been completed. Only after that point, it's safe to + * assume that map value(s) are immutable. + */ + return (map->map_flags & BPF_F_RDONLY_PROG) && + READ_ONCE(map->frozen) && + !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; @@ -3120,13 +6819,13 @@ 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; @@ -3137,6 +6836,122 @@ 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; +}; + +/* 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; +}; + +/* 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(struct dentry) { + /* no negative dentry-s in places where bpf can see it */ + struct inode *d_inode; +}; + +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) { + struct sock *sk; +}; + +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)); + + 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)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); +} + +static bool type_is_trusted_or_null(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const char *field_name, u32 btf_id) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, + "__safe_trusted_or_null"); +} + static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, @@ -3144,11 +6959,25 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, int value_regno) { struct bpf_reg_state *reg = regs + regno; - const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id); - const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off); - u32 btf_id; + 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 = 0; int ret; + if (!env->allow_ptr_leaks) { + verbose(env, + "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", + tname); + return -EPERM; + } + if (!env->prog->gpl_compatible && btf_is_kernel(reg->btf)) { + verbose(env, + "Cannot access kernel 'struct %s' from non-GPL compatible program\n", + tname); + return -EINVAL; + } if (off < 0) { verbose(env, "R%d is ptr_%s invalid negative access: off=%d\n", @@ -3165,35 +6994,273 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - if (env->ops->btf_struct_access) { - ret = env->ops->btf_struct_access(&env->log, t, off, size, - atype, &btf_id); + if (reg->type & MEM_USER) { + verbose(env, + "R%d is ptr_%s access user memory: off=%d\n", + regno, tname, off); + return -EACCES; + } + + if (reg->type & MEM_PERCPU) { + verbose(env, + "R%d is ptr_%s access percpu memory: off=%d\n", + regno, tname, off); + return -EACCES; + } + + 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"); + return -EFAULT; + } + ret = env->ops->btf_struct_access(&env->log, reg, off, size); } else { - if (atype != BPF_READ) { + /* 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 && !type_is_ptr_alloc_obj(reg->type)) { verbose(env, "only read is supported\n"); return -EACCES; } - ret = btf_struct_access(&env->log, t, off, size, atype, - &btf_id); + if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) && + !(reg->type & MEM_RCU) && !reg->ref_obj_id) { + verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n"); + return -EFAULT; + } + + ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag, &field_name); } if (ret < 0) return ret; - if (atype == BPF_READ && value_regno >= 0) { - if (ret == SCALAR_VALUE) { - mark_reg_unknown(env, regs, value_regno); - return 0; + if (ret != PTR_TO_BTF_ID) { + /* just mark; */ + + } 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. + */ + 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. + */ + 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; } - mark_reg_known_zero(env, regs, value_regno); - regs[value_regno].type = PTR_TO_BTF_ID; - regs[value_regno].btf_id = btf_id; + } 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); + + return 0; +} + +static int check_ptr_to_map_access(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, + int regno, int off, int size, + enum bpf_access_type atype, + int value_regno) +{ + struct bpf_reg_state *reg = regs + regno; + struct bpf_map *map = reg->map_ptr; + struct bpf_reg_state map_reg; + enum bpf_type_flag flag = 0; + const struct btf_type *t; + const char *tname; + u32 btf_id; + int ret; + + if (!btf_vmlinux) { + verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n"); + return -ENOTSUPP; + } + + if (!map->ops->map_btf_id || !*map->ops->map_btf_id) { + verbose(env, "map_ptr access not supported for map type %d\n", + map->map_type); + return -ENOTSUPP; + } + + t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id); + tname = btf_name_by_offset(btf_vmlinux, t->name_off); + + if (!env->allow_ptr_leaks) { + verbose(env, + "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", + tname); + return -EPERM; + } + + if (off < 0) { + verbose(env, "R%d is %s invalid negative access: off=%d\n", + regno, tname, off); + return -EACCES; + } + + if (atype != BPF_READ) { + verbose(env, "only read from %s is supported\n", tname); + return -EACCES; + } + + /* 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, NULL); + if (ret < 0) + return ret; + + if (value_regno >= 0) + mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag); + + return 0; +} + +/* Check that the stack access at the given offset is within bounds. The + * maximum valid offset is -1. + * + * The minimum valid offset is -MAX_BPF_STACK for writes, and + * -state->allocated_stack for reads. + */ +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 || env->allow_uninit_stack) + min_valid_off = -MAX_BPF_STACK; + else + min_valid_off = -state->allocated_stack; + + if (off < min_valid_off || off > -1) + return -EACCES; return 0; } +/* Check that the stack access at 'regno + off' falls within the maximum stack + * bounds. + * + * 'off' includes `regno->offset`, but not its dynamic part (if any). + */ +static int check_stack_access_within_bounds( + struct bpf_verifier_env *env, + int regno, int off, int access_size, + 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); + s64 min_off, max_off; + int err; + char *err_extra; + + if (type == BPF_READ) + err_extra = " read from"; + else + err_extra = " write to"; + + if (tnum_is_const(reg->var_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) { + verbose(env, "invalid unbounded variable-offset%s stack R%d\n", + err_extra, regno); + return -EACCES; + } + min_off = reg->smin_value + off; + max_off = reg->smax_value + off + access_size; + } + + 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)) { + verbose(env, "invalid%s stack R%d off=%d size=%d\n", + err_extra, regno, off, access_size); + } else { + 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 off=%d size=%d\n", + err_extra, regno, tn_buf, off, access_size); + } + 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) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -3202,11 +7269,10 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, */ 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); @@ -3221,7 +7287,21 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn /* for access checks, reg->off is just part of off */ off += reg->off; - if (reg->type == PTR_TO_MAP_VALUE) { + if (reg->type == PTR_TO_MAP_KEY) { + if (t == BPF_WRITE) { + verbose(env, "write to change key R%d not allowed\n", regno); + return -EACCES; + } + + err = check_mem_region_access(env, regno, off, size, + reg->map_ptr->key_size, false); + if (err) + return err; + if (value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_MAP_VALUE) { + struct btf_field *kptr_field = NULL; + if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into map\n", value_regno); @@ -3230,8 +7310,15 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_map_access_type(env, regno, off, size, t); if (err) return err; - err = check_map_access(env, regno, off, size, false); - if (!err && t == BPF_READ && value_regno >= 0) { + err = check_map_access(env, regno, off, size, false, ACCESS_DIRECT); + if (err) + 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 | 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 */ @@ -3242,7 +7329,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn u64 val = 0; err = bpf_map_direct_read(map, map_off, size, - &val); + &val, is_ldsx); if (err) return err; @@ -3252,18 +7339,36 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn mark_reg_unknown(env, regs, value_regno); } } - } else if (reg->type == PTR_TO_MEM) { + } else if (base_type(reg->type) == PTR_TO_MEM) { + bool rdonly_mem = type_is_rdonly_mem(reg->type); + + if (type_may_be_null(reg->type)) { + verbose(env, "R%d invalid mem access '%s'\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } + + if (t == BPF_WRITE && rdonly_mem) { + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str(env, reg->type)); + return -EACCES; + } + if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into mem\n", value_regno); return -EACCES; } + err = check_mem_region_access(env, regno, off, size, reg->mem_size, false); - if (!err && t == BPF_READ && value_regno >= 0) + if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { + bool is_retval = false; + struct bpf_retval_range range; enum bpf_reg_type reg_type = SCALAR_VALUE; + struct btf *btf = NULL; u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && @@ -3272,11 +7377,12 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return -EACCES; } - err = check_ctx_reg(env, reg, regno); + err = check_ptr_off_reg(env, reg, regno); if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf_id); + err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, + &btf_id, &is_retval, is_ldsx); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { @@ -3285,11 +7391,18 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) { - mark_reg_unknown(env, regs, value_regno); + if (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 (reg_type_may_be_null(reg_type)) + if (type_may_be_null(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 @@ -3297,30 +7410,26 @@ 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 (reg_type == PTR_TO_BTF_ID || - reg_type == PTR_TO_BTF_ID_OR_NULL) + if (base_type(reg_type) == PTR_TO_BTF_ID) { + regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; + } } regs[value_regno].type = reg_type; } } else if (reg->type == PTR_TO_STACK) { - off += reg->var_off.value; - err = check_stack_access(env, reg, off, size); - if (err) - return err; - - state = func(env, reg); - err = update_stack_depth(env, state, off); + /* Basic bounds checks. */ + err = check_stack_access_within_bounds(env, regno, off, size, t); if (err) return err; - if (t == BPF_WRITE) - err = check_stack_write(env, state, off, size, - value_regno, insn_idx); - else - err = check_stack_read(env, state, off, size, + if (t == BPF_READ) + err = check_stack_read(env, regno, off, size, value_regno); + else + err = check_stack_write(env, regno, off, size, + value_regno, insn_idx); } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose(env, "cannot write into packet\n"); @@ -3349,7 +7458,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str[reg->type]); + regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); @@ -3359,30 +7468,80 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); - } else if (reg->type == PTR_TO_BTF_ID) { + } else if (base_type(reg->type) == PTR_TO_BTF_ID && + !type_may_be_null(reg->type)) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); + } else if (reg->type == CONST_PTR_TO_MAP) { + err = check_ptr_to_map_access(env, regs, regno, off, size, t, + value_regno); + } else if (base_type(reg->type) == PTR_TO_BUF) { + bool rdonly_mem = type_is_rdonly_mem(reg->type); + u32 *max_access; + + if (rdonly_mem) { + if (t == BPF_WRITE) { + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str(env, reg->type)); + return -EACCES; + } + max_access = &env->prog->aux->max_rdonly_access; + } else { + max_access = &env->prog->aux->max_rdwr_access; + } + + err = check_buffer_access(env, reg, regno, off, size, false, + max_access); + + 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[reg->type]); + reg_type_str(env, reg->type)); return -EACCES; } 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_xadd(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_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { + int load_reg; int err; - if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || - insn->imm != 0) { - verbose(env, "BPF_XADD uses reserved fields\n"); + 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; + } + + if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) { + verbose(env, "invalid atomic operand size\n"); return -EINVAL; } @@ -3396,6 +7555,20 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if (err) return err; + if (insn->imm == BPF_CMPXCHG) { + /* Check comparison of R0 with memory location */ + const u32 aux_reg = BPF_REG_0; + + err = check_reg_arg(env, aux_reg, SRC_OP); + if (err) + return err; + + if (is_pointer_value(env, aux_reg)) { + verbose(env, "R%d leaks addr into mem\n", aux_reg); + return -EACCES; + } + } + if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; @@ -3404,79 +7577,94 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins 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)) { - verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", + is_sk_reg(env, insn->dst_reg) || + (is_arena_reg(env, insn->dst_reg) && !bpf_jit_supports_insn(insn, true))) { + verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, - reg_type_str[reg_state(env, insn->dst_reg)->type]); + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } - /* check whether atomic_add can read the memory */ + if (insn->imm & BPF_FETCH) { + if (insn->imm == BPF_CMPXCHG) + load_reg = BPF_REG_0; + else + load_reg = insn->src_reg; + + /* check and record load of old value */ + err = check_reg_arg(env, load_reg, DST_OP); + if (err) + return err; + } else { + /* This instruction accesses a memory location but doesn't + * actually load it into a register. + */ + load_reg = -1; + } + + /* 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); + 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, false); if (err) return err; - /* check whether atomic_add can write into the same memory */ - return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, -1, true); -} - -static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno, - int off, int access_size, - bool zero_size_allowed) -{ - struct bpf_reg_state *reg = reg_state(env, regno); - - if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || - access_size < 0 || (access_size == 0 && !zero_size_allowed)) { - if (tnum_is_const(reg->var_off)) { - verbose(env, "invalid stack type R%d off=%d access_size=%d\n", - regno, off, access_size); - } else { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n", - regno, tn_buf, access_size); - } - return -EACCES; + if (is_arena_reg(env, insn->dst_reg)) { + err = save_aux_ptr_type(env, PTR_TO_ARENA, false); + if (err) + return err; } + /* Check whether we can write into the same memory. */ + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); + if (err) + return err; return 0; } -/* when register 'regno' is passed into function that will read 'access_size' - * bytes from that pointer, make sure that it's within stack boundary - * and all elements of stack are initialized. - * Unlike most pointer bounds-checking functions, this one doesn't take an - * 'off' argument, so it has to add in reg->off itself. +/* 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 and privileges, that all elements of the stack are + * initialized. + * + * 'off' includes 'regno->off', but not its dynamic part (if any). + * + * All registers that have been spilled on the stack in the slots within the + * read offsets are marked as read. */ -static int check_stack_boundary(struct bpf_verifier_env *env, int regno, - int access_size, bool zero_size_allowed, - struct bpf_call_arg_meta *meta) +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_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; + /* Some accesses can write anything into the stack, others are + * read-only. + */ + bool clobber = false; - if (reg->type != PTR_TO_STACK) { - /* Allow zero-byte read from NULL, regardless of pointer type */ - if (zero_size_allowed && access_size == 0 && - register_is_null(reg)) - return 0; - - verbose(env, "R%d type=%s expected=%s\n", regno, - reg_type_str[reg->type], - reg_type_str[PTR_TO_STACK]); + if (access_size == 0 && !zero_size_allowed) { + verbose(env, "invalid zero-sized read\n"); return -EACCES; } + if (type == BPF_WRITE) + clobber = true; + + err = check_stack_access_within_bounds(env, regno, off, access_size, type); + if (err) + return err; + + if (tnum_is_const(reg->var_off)) { - min_off = max_off = reg->var_off.value + reg->off; - err = __check_stack_boundary(env, regno, min_off, access_size, - zero_size_allowed); - if (err) - return err; + min_off = max_off = reg->var_off.value + off; } else { /* Variable offset is prohibited for unprivileged mode for * simplicity since it requires corresponding support in @@ -3487,7 +7675,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n", + verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n", regno, tn_buf); return -EACCES; } @@ -3500,31 +7688,36 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, if (meta && meta->raw_mode) meta = NULL; - if (reg->smax_value >= BPF_MAX_VAR_OFF || - reg->smax_value <= -BPF_MAX_VAR_OFF) { - verbose(env, "R%d unbounded indirect variable offset stack access\n", - regno); - return -EACCES; - } - min_off = reg->smin_value + reg->off; - max_off = reg->smax_value + reg->off; - err = __check_stack_boundary(env, regno, min_off, access_size, - zero_size_allowed); - if (err) { - verbose(env, "R%d min value is outside of stack bound\n", - regno); - return err; - } - err = __check_stack_boundary(env, regno, max_off, access_size, - zero_size_allowed); - if (err) { - verbose(env, "R%d max value is outside of stack bound\n", - regno); - return err; - } + min_off = reg->smin_value + off; + max_off = reg->smax_value + off; } 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; @@ -3535,39 +7728,43 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, slot = -i - 1; spi = slot / BPF_REG_SIZE; - if (state->allocated_stack <= slot) - goto err; + if (state->allocated_stack <= slot) { + verbose(env, "verifier bug: 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) { - /* helper can write anything into the stack */ - *stype = STACK_MISC; + if ((*stype == STACK_ZERO) || + (*stype == STACK_INVALID && env->allow_uninit_stack)) { + if (clobber) { + /* helper can write anything into the stack */ + *stype = STACK_MISC; + } goto mark; } - if (state->stack[spi].slot_type[0] == STACK_SPILL && - state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID) - goto mark; - - if (state->stack[spi].slot_type[0] == STACK_SPILL && - state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { - __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); - for (j = 0; j < BPF_REG_SIZE; j++) - state->stack[spi].slot_type[j] = STACK_MISC; + if (is_spilled_reg(&state->stack[spi]) && + (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || + env->allow_ptr_leaks)) { + if (clobber) { + __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); + for (j = 0; j < BPF_REG_SIZE; j++) + scrub_spilled_slot(&state->stack[spi].slot_type[j]); + } goto mark; } -err: if (tnum_is_const(reg->var_off)) { - verbose(env, "invalid indirect read from stack off %d+%d size %d\n", - 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 indirect read from stack var_off %s+%d size %d\n", - 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: @@ -3577,56 +7774,238 @@ mark: 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 + * 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]; + u32 *max_access; - switch (reg->type) { + switch (base_type(reg->type)) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); + case PTR_TO_MAP_KEY: + if (access_type == BPF_WRITE) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } + 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); + zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: + if (type_is_rdonly_mem(reg->type)) { + if (access_type == BPF_WRITE) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } + } return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); - default: /* scalar_value|ptr_to_stack or invalid ptr */ - return check_stack_boundary(env, regno, access_size, - zero_size_allowed, meta); + case PTR_TO_BUF: + if (type_is_rdonly_mem(reg->type)) { + if (access_type == BPF_WRITE) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } + + max_access = &env->prog->aux->max_rdonly_access; + } else { + max_access = &env->prog->aux->max_rdwr_access; + } + return check_buffer_access(env, reg, regno, reg->off, + access_size, zero_size_allowed, + max_access); + case PTR_TO_STACK: + return check_stack_range_initialized( + env, + regno, reg->off, access_size, + 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 + * can not statically check its size. + * Dynamically check it now. + */ + if (!env->ops->convert_ctx_access) { + int offset = access_size - 1; + + /* Allow zero-byte read from PTR_TO_CTX */ + if (access_size == 0) + return zero_size_allowed ? 0 : -EACCES; + + return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, + access_type, -1, false, false); + } + + fallthrough; + default: /* scalar_value or invalid ptr */ + /* Allow zero-byte read from NULL, regardless of pointer type */ + if (zero_size_allowed && access_size == 0 && + register_is_null(reg)) + return 0; + + verbose(env, "R%d type=%s ", regno, + reg_type_str(env, reg->type)); + verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK)); + return -EACCES; } } +/* 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) +{ + int err; + + /* This is used to refine r0 return value bounds for helpers + * that enforce this value as an upper bound on return values. + * See do_refine_retval_range() for helpers that can refine + * the return value. C type of helper is u32 so we pull register + * bound from umax_value however, if negative verifier errors + * out. Only upper bounds can be learned because retval is an + * int type and negative retvals are allowed. + */ + meta->msize_max_value = reg->umax_value; + + /* 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)) + meta = NULL; + + if (reg->smin_value < 0) { + verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", + regno); + return -EACCES; + } + + 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) { + verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", + regno); + return -EACCES; + } + 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; +} + +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; + int err; + + if (register_is_null(reg)) + return 0; + + /* 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. + */ + if (may_be_null) { + saved_reg = *reg; + mark_ptr_not_null_reg(reg); + } + + 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; + + return err; +} + +static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno) +{ + struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; + bool may_be_null = type_may_be_null(mem_reg->type); + struct bpf_reg_state saved_reg; + struct bpf_call_arg_meta meta; + int err; + + WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); + + memset(&meta, 0, sizeof(meta)); + + if (may_be_null) { + saved_reg = *mem_reg; + mark_ptr_not_null_reg(mem_reg); + } + + 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; +} + /* Implementation details: - * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL + * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL. + * bpf_obj_new returns PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL. * Two bpf_map_lookups (even with the same key) will have different reg->id. - * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after - * value_or_null->value transition, since the verifier only cares about - * the range of access to valid map value pointer and doesn't care about actual - * address of the map element. + * Two separate bpf_obj_new will also have different reg->id. + * For traditional PTR_TO_MAP_VALUE or PTR_TO_BTF_ID | MEM_ALLOC, the verifier + * clears reg->id after value_or_null->value transition, since the verifier only + * cares about the range of access to valid map value pointer and doesn't care + * about actual address of the map element. * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps * reg->id > 0 after value_or_null->value transition. By doing so * two bpf_map_lookups will be considered two different pointers that - * point to different bpf_spin_locks. + * point to different bpf_spin_locks. Likewise for pointers to allocated objects + * returned from bpf_obj_new. * The verifier allows taking only one bpf_spin_lock at a time to avoid * dead-locks. * 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_spin_lock remembers which map value element got locked - * and clears it after bpf_spin_unlock. + * 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) @@ -3634,71 +8013,630 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, 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); - struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; + struct bpf_map *map = NULL; + struct btf *btf = NULL; + struct btf_record *rec; + int err; - if (reg->type != PTR_TO_MAP_VALUE) { - verbose(env, "R%d is not a pointer to map_value\n", regno); - return -EINVAL; - } if (!is_const) { verbose(env, "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", regno); return -EINVAL; } - if (!map->btf) { - verbose(env, - "map '%s' has to have BTF in order to use bpf_spin_lock\n", - map->name); - return -EINVAL; - } - if (!map_value_has_spin_lock(map)) { - if (map->spin_lock_off == -E2BIG) - verbose(env, - "map '%s' has more than one 'struct bpf_spin_lock'\n", - map->name); - else if (map->spin_lock_off == -ENOENT) - verbose(env, - "map '%s' doesn't have 'struct bpf_spin_lock'\n", - map->name); - else + if (reg->type == PTR_TO_MAP_VALUE) { + map = reg->map_ptr; + if (!map->btf) { verbose(env, - "map '%s' is not a struct type or bpf_spin_lock is mangled\n", + "map '%s' has to have BTF in order to use bpf_spin_lock\n", map->name); + return -EINVAL; + } + } else { + btf = reg->btf; + } + + 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"); return -EINVAL; } - if (map->spin_lock_off != val + reg->off) { - verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", - val + reg->off); + 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); return -EINVAL; } if (is_lock) { - if (cur->active_spin_lock) { + void *ptr; + + if (map) + ptr = map; + else + ptr = btf; + + if (cur->active_locks) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } - cur->active_spin_lock = reg->id; + err = acquire_lock_state(env, env->insn_idx, REF_TYPE_LOCK, reg->id, ptr); + if (err < 0) { + verbose(env, "Failed to acquire lock state\n"); + return err; + } } else { - if (!cur->active_spin_lock) { + void *ptr; + + if (map) + ptr = map; + else + ptr = btf; + + if (!cur->active_locks) { verbose(env, "bpf_spin_unlock without taking a lock\n"); return -EINVAL; } - if (cur->active_spin_lock != reg->id) { + + if (release_lock_state(env->cur_state, REF_TYPE_LOCK, reg->id, ptr)) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } - cur->active_spin_lock = 0; + + 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) +{ + 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; + + if (!is_const) { + verbose(env, + "R%d doesn't have constant offset. bpf_timer has to be at the constant offset\n", + regno); + return -EINVAL; + } + if (!map->btf) { + verbose(env, "map '%s' has to have BTF in order to use bpf_timer\n", + map->name); + return -EINVAL; + } + if (!btf_record_has_field(map->record, BPF_TIMER)) { + verbose(env, "map '%s' has no valid bpf_timer\n", map->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); + return -EINVAL; + } + if (meta->map_ptr) { + verbose(env, "verifier bug. Two map pointers in a timer helper\n"); + return -EFAULT; + } + 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; + u64 val = reg->var_off.value; + + if (map->record->wq_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct bpf_wq' that is at %d\n", + val + reg->off, map->record->wq_off); + return -EINVAL; + } + meta->map.uid = reg->map_uid; + meta->map.ptr = map; + return 0; +} + +static int process_kptr_func(struct bpf_verifier_env *env, int regno, + struct bpf_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + 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 (!btf_record_has_field(rec, BPF_KPTR)) { + verbose(env, "R%d has no valid kptr\n", regno); + return -EINVAL; + } + + kptr_off = reg->off + reg->var_off.value; + 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 && kptr_field->type != BPF_KPTR_PERCPU) { + verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); + return -EACCES; + } + meta->kptr_field = kptr_field; + return 0; +} + +/* There are two register types representing a bpf_dynptr, one is PTR_TO_STACK + * which points to a stack slot, and the other is CONST_PTR_TO_DYNPTR. + * + * In both cases we deal with the first 8 bytes, but need to mark the next 8 + * bytes as STACK_DYNPTR in case of PTR_TO_STACK. In case of + * CONST_PTR_TO_DYNPTR, we are guaranteed to get the beginning of the object. + * + * Mutability of bpf_dynptr is at two levels, one is at the level of struct + * bpf_dynptr itself, i.e. whether the helper is receiving a pointer to struct + * bpf_dynptr or pointer to const struct bpf_dynptr. In the former case, it can + * mutate the view of the dynptr and also possibly destroy it. In the latter + * case, it cannot mutate the bpf_dynptr itself but it can still mutate the + * memory that dynptr points to. + * + * The verifier will keep track both levels of mutation (bpf_dynptr's in + * reg->type and the memory's in reg->dynptr.type), but there is no support for + * readonly dynptr view yet, hence only the first case is tracked and checked. + * + * This is consistent with how C applies the const modifier to a struct object, + * where the pointer itself inside bpf_dynptr becomes const but not what it + * points to. + * + * 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. + */ +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"); + return -EFAULT; + } + + /* MEM_UNINIT - Points to memory that is an appropriate candidate for + * constructing a mutable bpf_dynptr object. + * + * Currently, this is only possible with PTR_TO_STACK + * pointing to a region of at least 16 bytes which doesn't + * contain an existing bpf_dynptr. + * + * MEM_RDONLY - Points to a initialized bpf_dynptr that will not be + * mutated or destroyed. However, the memory it points to + * may be mutated. + * + * None - Points to a initialized dynptr that can be mutated and + * destroyed, including mutation of the memory it points + * 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 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; + } + + 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)) { + verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n"); + return -EINVAL; + } + + if (!is_dynptr_reg_valid_init(env, reg)) { + verbose(env, + "Expected an initialized dynptr as arg #%d\n", + 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)) { + verbose(env, + "Expected a dynptr of type %s as arg #%d\n", + 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; } -static bool arg_type_is_mem_ptr(enum bpf_arg_type type) +/* 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; + + /* Explored states are pushed in stack order, most recent states come first */ + sl = *explored_state(env, insn_idx); + for (; sl; sl = sl->next) { + /* 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) { - return type == ARG_PTR_TO_MEM || - type == ARG_PTR_TO_MEM_OR_NULL || - type == ARG_PTR_TO_UNINIT_MEM; + 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; + + 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); + + for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; 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) { + verbose(env, "verifier internal error: unexpected iterator state %d (%s)\n", + 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)) { + verbose(env, "bug: 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 (!queued_st) + return -ENOMEM; + + 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; } static bool arg_type_is_mem_size(enum bpf_arg_type type) @@ -3707,39 +8645,586 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type) type == ARG_CONST_SIZE_OR_ZERO; } -static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type) +static bool arg_type_is_raw_mem(enum bpf_arg_type type) { - return type == ARG_PTR_TO_ALLOC_MEM || - type == ARG_PTR_TO_ALLOC_MEM_OR_NULL; + return base_type(type) == ARG_PTR_TO_MEM && + type & MEM_UNINIT; } -static bool arg_type_is_alloc_size(enum bpf_arg_type type) +static bool arg_type_is_release(enum bpf_arg_type type) { - return type == ARG_CONST_ALLOC_SIZE_OR_ZERO; + return type & OBJ_RELEASE; } -static bool arg_type_is_int_ptr(enum bpf_arg_type type) +static bool arg_type_is_dynptr(enum bpf_arg_type type) { - return type == ARG_PTR_TO_INT || - type == ARG_PTR_TO_LONG; + return base_type(type) == ARG_PTR_TO_DYNPTR; } -static int int_ptr_type_to_size(enum bpf_arg_type type) +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 (type == ARG_PTR_TO_INT) - return sizeof(u32); - else if (type == ARG_PTR_TO_LONG) - return sizeof(u64); + if (!meta->map_ptr) { + /* kernel subsystem misconfigured verifier */ + verbose(env, "invalid map_ptr to access map->type\n"); + return -EACCES; + } - return -EINVAL; + switch (meta->map_ptr->map_type) { + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + if (*arg_type == ARG_PTR_TO_MAP_VALUE) { + *arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON; + } else { + verbose(env, "invalid arg_type for sockmap/sockhash\n"); + return -EINVAL; + } + break; + case BPF_MAP_TYPE_BLOOM_FILTER: + if (meta->func_id == BPF_FUNC_map_peek_elem) + *arg_type = ARG_PTR_TO_MAP_VALUE; + break; + default: + break; + } + return 0; } -static int check_func_arg(struct bpf_verifier_env *env, u32 regno, +struct bpf_reg_types { + const enum bpf_reg_type types[10]; + u32 *btf_id; +}; + +static const struct bpf_reg_types sock_types = { + .types = { + PTR_TO_SOCK_COMMON, + PTR_TO_SOCKET, + PTR_TO_TCP_SOCK, + PTR_TO_XDP_SOCK, + }, +}; + +#ifdef CONFIG_NET +static const struct bpf_reg_types btf_id_sock_common_types = { + .types = { + PTR_TO_SOCK_COMMON, + PTR_TO_SOCKET, + PTR_TO_TCP_SOCK, + PTR_TO_XDP_SOCK, + PTR_TO_BTF_ID, + PTR_TO_BTF_ID | PTR_TRUSTED, + }, + .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], +}; +#endif + +static const struct bpf_reg_types mem_types = { + .types = { + PTR_TO_STACK, + PTR_TO_PACKET, + PTR_TO_PACKET_META, + PTR_TO_MAP_KEY, + PTR_TO_MAP_VALUE, + PTR_TO_MEM, + PTR_TO_MEM | MEM_RINGBUF, + PTR_TO_BUF, + PTR_TO_BTF_ID | PTR_TRUSTED, + }, +}; + +static const struct bpf_reg_types spin_lock_types = { + .types = { + PTR_TO_MAP_VALUE, + PTR_TO_BTF_ID | MEM_ALLOC, + } +}; + +static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; +static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; +static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; +static const struct bpf_reg_types ringbuf_mem_types = { .types = { PTR_TO_MEM | MEM_RINGBUF } }; +static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; +static const struct bpf_reg_types btf_ptr_types = { + .types = { + PTR_TO_BTF_ID, + PTR_TO_BTF_ID | PTR_TRUSTED, + PTR_TO_BTF_ID | MEM_RCU, + }, +}; +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, + } +}; +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_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, + CONST_PTR_TO_DYNPTR, + } +}; + +static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { + [ARG_PTR_TO_MAP_KEY] = &mem_types, + [ARG_PTR_TO_MAP_VALUE] = &mem_types, + [ARG_CONST_SIZE] = &scalar_types, + [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, + [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, + [ARG_CONST_MAP_PTR] = &const_map_ptr_types, + [ARG_PTR_TO_CTX] = &context_types, + [ARG_PTR_TO_SOCK_COMMON] = &sock_types, +#ifdef CONFIG_NET + [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, +#endif + [ARG_PTR_TO_SOCKET] = &fullsock_types, + [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, + [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_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_KPTR_XCHG_DEST] = &kptr_xchg_dest_types, + [ARG_PTR_TO_DYNPTR] = &dynptr_types, +}; + +static int check_reg_type(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, + const u32 *arg_btf_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; - enum bpf_reg_type expected_type, type = reg->type; + enum bpf_reg_type expected, type = reg->type; + const struct bpf_reg_types *compatible; + int i, j; + + compatible = compatible_reg_types[base_type(arg_type)]; + if (!compatible) { + verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type); + return -EFAULT; + } + + /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY, + * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY + * + * Same for MAYBE_NULL: + * + * 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]; + if (expected == NOT_INIT) + break; + + if (type == expected) + goto found; + } + + verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type)); + for (j = 0; j + 1 < i; j++) + verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); + verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); + return -EACCES; + +found: + 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. + */ + 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"); + return -EFAULT; + } + arg_btf_id = compatible->btf_id; + } + + if (meta->func_id == BPF_FUNC_kptr_xchg) { + if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) + return -EACCES; + } else { + if (arg_btf_id == BPF_PTR_POISON) { + verbose(env, "verifier internal error:"); + verbose(env, "R%d has non-overwritten BPF_PTR_POISON type\n", + regno); + return -EACCES; + } + + if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, + btf_vmlinux, *arg_btf_id, + strict_type_match)) { + verbose(env, "R%d is of type %s but %s is expected\n", + regno, btf_type_name(reg->btf, reg->btf_id), + btf_type_name(btf_vmlinux, *arg_btf_id)); + return -EACCES; + } + } + 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) { + verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n"); + 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: + verbose(env, "verifier internal error: invalid PTR_TO_BTF_ID register for type match\n"); + return -EFAULT; + } + return 0; +} + +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; + + /* When referenced register is passed to release function, its fixed + * offset must be 0. + * + * We will check arg_type_is_release reg has ref_obj_id when storing + * meta->release_regno. + */ + if (arg_type_is_release(arg_type)) { + /* ARG_PTR_TO_DYNPTR with OBJ_RELEASE is a bit special, as it + * may not directly point to the object being released, but to + * dynptr pointing to such object, which might be at some offset + * on the stack. In that case, we simply to fallback to the + * default handling. + */ + 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. + */ + if (reg->off) { + verbose(env, "R%d must have zero offset when passed to release func or trusted arg to kfunc\n", + regno); + return -EINVAL; + } + return __check_ptr_off_reg(env, reg, regno, false); + } + + switch (type) { + /* Pointer types where both fixed and variable offset is explicitly allowed: */ + case PTR_TO_STACK: + case PTR_TO_PACKET: + case PTR_TO_PACKET_META: + case PTR_TO_MAP_KEY: + case PTR_TO_MAP_VALUE: + case PTR_TO_MEM: + case PTR_TO_MEM | MEM_RDONLY: + 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 + * fixed offset. + */ + case PTR_TO_BTF_ID: + 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 | 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 + * fixed_off_ok as true to allow fixed offset for all other + * cases. var_off always must be 0 for PTR_TO_BTF_ID, hence we + * still need to do checks instead of returning. + */ + return __check_ptr_off_reg(env, reg, regno, true); + default: + return __check_ptr_off_reg(env, reg, regno, false); + } +} + +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->id; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + return state->stack[spi].spilled_ptr.id; +} + +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); + 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, + 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) @@ -3764,107 +9249,65 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EACCES; } - if (arg_type == ARG_PTR_TO_MAP_KEY || - arg_type == ARG_PTR_TO_MAP_VALUE || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || - arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { - expected_type = PTR_TO_STACK; - if (register_is_null(reg) && - arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) - /* final test in check_stack_boundary() */; - else if (!type_is_pkt_pointer(type) && - type != PTR_TO_MAP_VALUE && - type != expected_type) - goto err_type; - } else if (arg_type == ARG_CONST_SIZE || - arg_type == ARG_CONST_SIZE_OR_ZERO || - arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) { - expected_type = SCALAR_VALUE; - if (type != expected_type) - goto err_type; - } else if (arg_type == ARG_CONST_MAP_PTR) { - expected_type = CONST_PTR_TO_MAP; - if (type != expected_type) - goto err_type; - } else if (arg_type == ARG_PTR_TO_CTX || - arg_type == ARG_PTR_TO_CTX_OR_NULL) { - expected_type = PTR_TO_CTX; - if (!(register_is_null(reg) && - arg_type == ARG_PTR_TO_CTX_OR_NULL)) { - if (type != expected_type) - goto err_type; - err = check_ctx_reg(env, reg, regno); - if (err < 0) - return err; - } - } else if (arg_type == ARG_PTR_TO_SOCK_COMMON) { - expected_type = PTR_TO_SOCK_COMMON; - /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ - if (!type_is_sk_pointer(type)) - goto err_type; - if (reg->ref_obj_id) { - if (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); - return -EFAULT; - } - meta->ref_obj_id = reg->ref_obj_id; - } - } else if (arg_type == ARG_PTR_TO_SOCKET) { - expected_type = PTR_TO_SOCKET; - if (type != expected_type) - goto err_type; - } else if (arg_type == ARG_PTR_TO_BTF_ID) { - expected_type = PTR_TO_BTF_ID; - if (type != expected_type) - goto err_type; - if (reg->btf_id != meta->btf_id) { - verbose(env, "Helper has type %s got %s in R%d\n", - kernel_type_name(meta->btf_id), - kernel_type_name(reg->btf_id), regno); + if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) { + err = resolve_map_arg_type(env, meta, &arg_type); + if (err) + return err; + } - return -EACCES; - } - if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) { - verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n", + if (register_is_null(reg) && type_may_be_null(arg_type)) + /* A NULL register has a SCALAR_VALUE type, so skip + * type checking. + */ + goto skip_type_check; + + /* arg_btf_id and arg_size are in a union. */ + if (base_type(arg_type) == ARG_PTR_TO_BTF_ID || + base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK) + arg_btf_id = fn->arg_btf_id[arg]; + + err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); + if (err) + return err; + + err = check_func_arg_reg_off(env, reg, regno, arg_type); + if (err) + return err; + +skip_type_check: + if (arg_type_is_release(arg_type)) { + if (arg_type_is_dynptr(arg_type)) { + struct bpf_func_state *state = func(env, reg); + int spi; + + /* Only dynptr created on stack can be released, thus + * the get_spi and stack state checks for spilled_ptr + * should only be done before process_dynptr_func for + * PTR_TO_STACK. + */ + if (reg->type == PTR_TO_STACK) { + 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; + } + } else { + verbose(env, "cannot release unowned const bpf_dynptr\n"); + return -EINVAL; + } + } else if (!reg->ref_obj_id && !register_is_null(reg)) { + verbose(env, "R%d must be referenced when passed to release function\n", regno); - return -EACCES; + return -EINVAL; } - } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { - if (meta->func_id == BPF_FUNC_spin_lock) { - if (process_spin_lock(env, regno, true)) - return -EACCES; - } else if (meta->func_id == BPF_FUNC_spin_unlock) { - if (process_spin_lock(env, regno, false)) - return -EACCES; - } else { - verbose(env, "verifier internal error\n"); + if (meta->release_regno) { + verbose(env, "verifier internal error: more than one release argument\n"); return -EFAULT; } - } else if (arg_type_is_mem_ptr(arg_type)) { - expected_type = PTR_TO_STACK; - /* One exception here. In case function allows for NULL to be - * passed in as argument, it's a SCALAR_VALUE type. Final test - * happens during stack boundary checking. - */ - if (register_is_null(reg) && - (arg_type == ARG_PTR_TO_MEM_OR_NULL || - arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL)) - /* final test in check_stack_boundary() */; - else if (!type_is_pkt_pointer(type) && - type != PTR_TO_MAP_VALUE && - type != PTR_TO_MEM && - type != expected_type) - goto err_type; - meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; - } else if (arg_type_is_alloc_mem_ptr(arg_type)) { - expected_type = PTR_TO_MEM; - if (register_is_null(reg) && - arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL) - /* final test in check_stack_boundary() */; - else if (type != expected_type) - goto err_type; + meta->release_regno = regno; + } + + 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", regno, reg->ref_obj_id, @@ -3872,21 +9315,36 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; - } else if (arg_type_is_int_ptr(arg_type)) { - expected_type = PTR_TO_STACK; - if (!type_is_pkt_pointer(type) && - type != PTR_TO_MAP_VALUE && - type != expected_type) - goto err_type; - } else { - verbose(env, "unsupported arg_type %d\n", arg_type); - return -EFAULT; } - if (arg_type == ARG_CONST_MAP_PTR) { + switch (base_type(arg_type)) { + case ARG_CONST_MAP_PTR: /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ + if (meta->map_ptr) { + /* 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) { + * timer = bpf_map_lookup_elem(inner_map1); + * if (timer) + * // mismatch would have been allowed + * bpf_timer_init(timer, inner_map2); + * } + * + * Comparing map_ptr is enough to distinguish normal and outer maps. + */ + if (meta->map_ptr != reg->map_ptr || + meta->map_uid != reg->map_uid) { + verbose(env, + "timer 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; - } else if (arg_type == ARG_PTR_TO_MAP_KEY) { + meta->map_uid = reg->map_uid; + break; + case ARG_PTR_TO_MAP_KEY: /* bpf_map_xxx(..., map_ptr, ..., key) call: * check that [key, key + map->key_size) are within * stack limits and initialized @@ -3900,13 +9358,25 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } - err = check_helper_mem_access(env, regno, - meta->map_ptr->key_size, false, - NULL); - } else if (arg_type == ARG_PTR_TO_MAP_VALUE || - (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && - !register_is_null(reg)) || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { + 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; + } + } + break; + case ARG_PTR_TO_MAP_VALUE: + if (type_may_be_null(arg_type) && register_is_null(reg)) + return 0; + /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ @@ -3915,79 +9385,147 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } - meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE); - err = check_helper_mem_access(env, regno, - meta->map_ptr->value_size, false, - meta); - } else if (arg_type_is_mem_size(arg_type)) { - bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); - - /* This is used to refine r0 return value bounds for helpers - * that enforce this value as an upper bound on return values. - * See do_refine_retval_range() for helpers that can refine - * the return value. C type of helper is u32 so we pull register - * bound from umax_value however, if negative verifier errors - * out. Only upper bounds can be learned because retval is an - * int type and negative retvals are allowed. - */ - meta->msize_max_value = reg->umax_value; - - /* The register is SCALAR_VALUE; the access check - * happens using its boundaries. - */ - 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) { - verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", - regno); + meta->raw_mode = arg_type & MEM_UNINIT; + 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) { + verbose(env, "Helper has invalid btf_id in R%d\n", regno); return -EACCES; } - - if (reg->umin_value == 0) { - err = check_helper_mem_access(env, regno - 1, 0, - zero_size_allowed, - meta); + meta->ret_btf = reg->btf; + 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); + if (err) + return err; + } else if (meta->func_id == BPF_FUNC_spin_unlock) { + err = process_spin_lock(env, regno, false); if (err) return err; + } else { + verbose(env, "verifier internal error\n"); + return -EFAULT; } - - if (reg->umax_value >= BPF_MAX_VAR_SIZ) { - verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", - regno); - return -EACCES; + break; + case ARG_PTR_TO_TIMER: + err = process_timer_func(env, regno, meta); + if (err) + return err; + break; + case ARG_PTR_TO_FUNC: + meta->subprogno = reg->subprogno; + break; + case ARG_PTR_TO_MEM: + /* The access to this pointer is only checked when we hit the + * next is_mem_size argument below. + */ + meta->raw_mode = arg_type & MEM_UNINIT; + if (arg_type & MEM_FIXED_SIZE) { + 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); } - err = check_helper_mem_access(env, regno - 1, - reg->umax_value, - zero_size_allowed, meta); - if (!err) - err = mark_chain_precision(env, regno); - } else if (arg_type_is_alloc_size(arg_type)) { + break; + case ARG_CONST_SIZE: + 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, + 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, insn_idx, arg_type, 0); + if (err) + return err; + break; + case ARG_CONST_ALLOC_SIZE_OR_ZERO: if (!tnum_is_const(reg->var_off)) { - verbose(env, "R%d unbounded size, use 'var &= const' or 'if (var < const)'\n", + verbose(env, "R%d is not a known constant'\n", regno); return -EACCES; } meta->mem_size = reg->var_off.value; - } else if (arg_type_is_int_ptr(arg_type)) { - int size = int_ptr_type_to_size(arg_type); - - err = check_helper_mem_access(env, regno, size, false, meta); + err = mark_chain_precision(env, regno); if (err) return err; - err = check_ptr_alignment(env, reg, 0, size, true); + break; + case ARG_PTR_TO_CONST_STR: + { + err = check_reg_const_str(env, reg, regno); + if (err) + return err; + break; + } + case ARG_KPTR_XCHG_DEST: + err = process_kptr_func(env, regno, meta); + if (err) + return err; + break; } return err; -err_type: - verbose(env, "R%d type=%s expected=%s\n", regno, - reg_type_str[type], reg_type_str[expected_type]); - return -EACCES; +} + +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 && + func_id != BPF_FUNC_map_delete_elem) + return false; + + /* It's not possible to get access to a locked struct sock in these + * contexts, so updating is safe. + */ + switch (type) { + case BPF_PROG_TYPE_TRACING: + 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: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_SK_REUSEPORT: + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_SK_LOOKUP: + return true; + default: + break; + } + + verbose(env, "cannot update sockmap in this context\n"); + return false; +} + +static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env) +{ + return env->prog->jit_requested && + bpf_jit_supports_subprog_tailcalls(); } static int check_map_func_compatibility(struct bpf_verifier_env *env, @@ -4013,9 +9551,14 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && - func_id != BPF_FUNC_ringbuf_submit && - func_id != BPF_FUNC_ringbuf_discard && - func_id != BPF_FUNC_ringbuf_query) + func_id != BPF_FUNC_ringbuf_query && + func_id != BPF_FUNC_ringbuf_reserve_dynptr && + func_id != BPF_FUNC_ringbuf_submit_dynptr && + func_id != BPF_FUNC_ringbuf_discard_dynptr) + goto error; + break; + case BPF_MAP_TYPE_USER_RINGBUF: + if (func_id != BPF_FUNC_user_ringbuf_drain) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -4058,19 +9601,19 @@ 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) + func_id != BPF_FUNC_map_lookup_elem && + !may_update_sockmap(env, func_id)) goto error; break; 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) + func_id != BPF_FUNC_map_lookup_elem && + !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: @@ -4086,7 +9629,31 @@ 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_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_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_kptr_xchg) + goto error; + break; + case BPF_MAP_TYPE_BLOOM_FILTER: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_push_elem) goto error; break; default: @@ -4098,8 +9665,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; - if (env->subprog_cnt > 1) { - verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n"); + 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"); return -EINVAL; } break; @@ -4111,6 +9678,19 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; + case BPF_FUNC_ringbuf_output: + case BPF_FUNC_ringbuf_reserve: + case BPF_FUNC_ringbuf_query: + case BPF_FUNC_ringbuf_reserve_dynptr: + case BPF_FUNC_ringbuf_submit_dynptr: + case BPF_FUNC_ringbuf_discard_dynptr: + if (map->map_type != BPF_MAP_TYPE_RINGBUF) + goto error; + break; + case BPF_FUNC_user_ringbuf_drain: + if (map->map_type != BPF_MAP_TYPE_USER_RINGBUF) + goto error; + break; case BPF_FUNC_get_stackid: if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; @@ -4150,18 +9730,44 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; - case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_pop_elem: - case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK && + map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) + goto error; + break; + case BPF_FUNC_map_lookup_percpu_elem: + if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && + map->map_type != BPF_MAP_TYPE_PERCPU_HASH && + map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto error; break; + case BPF_FUNC_inode_storage_get: + case BPF_FUNC_inode_storage_delete: + if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE) + goto error; + break; + case BPF_FUNC_task_storage_get: + case BPF_FUNC_task_storage_delete: + if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) + goto error; + break; + case BPF_FUNC_cgrp_storage_get: + case BPF_FUNC_cgrp_storage_delete: + if (map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) + goto error; + break; default: break; } @@ -4177,15 +9783,15 @@ 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, @@ -4195,13 +9801,19 @@ static bool check_raw_mode_ok(const struct bpf_func_proto *fn) return count <= 1; } -static bool check_args_pair_invalid(enum bpf_arg_type arg_curr, - enum bpf_arg_type arg_next) +static bool check_args_pair_invalid(const struct bpf_func_proto *fn, int arg) { - return (arg_type_is_mem_ptr(arg_curr) && - !arg_type_is_mem_size(arg_next)) || - (!arg_type_is_mem_ptr(arg_curr) && - arg_type_is_mem_size(arg_next)); + bool is_fixed = fn->arg_type[arg] & MEM_FIXED_SIZE; + bool has_size = fn->arg_size[arg] != 0; + bool is_next_size = false; + + if (arg + 1 < ARRAY_SIZE(fn->arg_type)) + is_next_size = arg_type_is_mem_size(fn->arg_type[arg + 1]); + + if (base_type(fn->arg_type[arg]) != ARG_PTR_TO_MEM) + return is_next_size; + + return has_size == is_next_size || is_next_size == is_fixed; } static bool check_arg_pair_ok(const struct bpf_func_proto *fn) @@ -4212,119 +9824,135 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) * helper function specification. */ if (arg_type_is_mem_size(fn->arg1_type) || - arg_type_is_mem_ptr(fn->arg5_type) || - check_args_pair_invalid(fn->arg1_type, fn->arg2_type) || - check_args_pair_invalid(fn->arg2_type, fn->arg3_type) || - check_args_pair_invalid(fn->arg3_type, fn->arg4_type) || - check_args_pair_invalid(fn->arg4_type, fn->arg5_type)) + check_args_pair_invalid(fn, 0) || + check_args_pair_invalid(fn, 1) || + check_args_pair_invalid(fn, 2) || + check_args_pair_invalid(fn, 3) || + check_args_pair_invalid(fn, 4)) return false; return true; } -static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id) +static bool check_btf_id_ok(const struct bpf_func_proto *fn) { - int count = 0; - - if (arg_type_may_be_refcounted(fn->arg1_type)) - count++; - if (arg_type_may_be_refcounted(fn->arg2_type)) - count++; - if (arg_type_may_be_refcounted(fn->arg3_type)) - count++; - if (arg_type_may_be_refcounted(fn->arg4_type)) - count++; - if (arg_type_may_be_refcounted(fn->arg5_type)) - count++; + int i; - /* A reference acquiring function cannot acquire - * another refcounted ptr. - */ - if (may_be_acquire_function(func_id) && count) - return false; + for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) { + if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID) + return !!fn->arg_btf_id[i]; + if (base_type(fn->arg_type[i]) == ARG_PTR_TO_SPIN_LOCK) + return fn->arg_btf_id[i] == BPF_PTR_POISON; + if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i] && + /* arg_btf_id and arg_size are in a union. */ + (base_type(fn->arg_type[i]) != ARG_PTR_TO_MEM || + !(fn->arg_type[i] & MEM_FIXED_SIZE))) + return false; + } - /* We only support one arg being unreferenced at the moment, - * which is sufficient for the helper functions we have right now. - */ - return count <= 1; + return true; } static int check_func_proto(const struct bpf_func_proto *fn, int func_id) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && - check_refcount_ok(fn, func_id) ? 0 : -EINVAL; + check_btf_id_ok(fn) ? 0 : -EINVAL; } /* 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, - struct bpf_func_state *state) +static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { - struct bpf_reg_state *regs = state->regs, *reg; - int i; - - for (i = 0; i < MAX_BPF_REG; i++) - if (reg_is_pkt_pointer_any(®s[i])) - mark_reg_unknown(env, regs, i); + struct bpf_func_state *state; + struct bpf_reg_state *reg; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(env, reg); - } + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) + mark_reg_invalid(env, reg); + })); } -static void clear_all_pkt_pointers(struct bpf_verifier_env *env) +enum { + AT_PKT_END = -1, + BEYOND_PKT_END = -2, +}; + +static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open) { - struct bpf_verifier_state *vstate = env->cur_state; - int i; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + struct bpf_reg_state *reg = &state->regs[regn]; - for (i = 0; i <= vstate->curframe; i++) - __clear_all_pkt_pointers(env, vstate->frame[i]); + if (reg->type != PTR_TO_PACKET) + /* PTR_TO_PACKET_META is not supported yet */ + return; + + /* The 'reg' is pkt > pkt_end or pkt >= pkt_end. + * How far beyond pkt_end it goes is unknown. + * if (!range_open) it's the case of pkt >= pkt_end + * if (range_open) it's the case of pkt > pkt_end + * hence this pointer is at least 1 byte bigger than pkt_end + */ + if (range_open) + reg->range = BEYOND_PKT_END; + else + reg->range = AT_PKT_END; } -static void release_reg_references(struct bpf_verifier_env *env, - struct bpf_func_state *state, - int ref_obj_id) +static int release_reference_nomark(struct bpf_verifier_state *state, int ref_obj_id) { - struct bpf_reg_state *regs = state->regs, *reg; int i; - for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].ref_obj_id == ref_obj_id) - mark_reg_unknown(env, regs, i); - - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].type != REF_TYPE_PTR) continue; - if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(env, reg); + 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; - int i; - err = release_reference_state(cur_func(env), ref_obj_id); + err = release_reference_nomark(vstate, ref_obj_id); if (err) return err; - for (i = 0; i <= vstate->curframe; i++) - release_reg_references(env, vstate->frame[i], ref_obj_id); + 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) { @@ -4333,18 +9961,25 @@ 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); } } -static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx) +typedef int (*set_callee_state_fn)(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx); + +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 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 i, err, subprog, target_insn; - bool is_global = false; + int err; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -4352,47 +9987,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -E2BIG; } - target_insn = *insn_idx + insn->imm; - subprog = find_subprog(env, target_insn + 1); - if (subprog < 0) { - verbose(env, "verifier bug. No program starts at insn %d\n", - target_insn + 1); - return -EFAULT; - } - - caller = state->frame[state->curframe]; if (state->frame[state->curframe + 1]) { verbose(env, "verifier bug. Frame %d already allocated\n", 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_func_arg_match(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); - - /* All global functions return SCALAR_VALUE */ - mark_reg_unknown(env, caller->regs, BPF_REG_0); - - /* continue with next insn after call */ - return 0; - } - } - + caller = state->frame[state->curframe]; callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; @@ -4404,43 +10005,544 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, */ init_func_state(env, callee, /* remember the callsite, it will be used by bpf_exit */ - *insn_idx /* callsite */, + 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; - /* Transfer references to the callee */ - err = transfer_reference_state(callee, caller); + /* 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 == 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 { + bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n", + i, arg->arg_type); + return -EFAULT; + } + } + + return 0; +} + +/* Compare BTF of a function call with given bpf_reg_state. + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - there is a type mismatch or BTF is not available. + * 0 - BTF matches with what bpf_reg_state expects. + * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. + */ +static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *regs) +{ + struct bpf_prog *prog = env->prog; + struct btf *btf = prog->aux->btf; + u32 btf_id; + int err; + + if (!prog->aux->func_info) + return -EINVAL; + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) + return -EFAULT; + + if (prog->aux->func_info_aux[subprog].unreliable) + return -EINVAL; + + err = btf_check_func_arg_match(env, subprog, btf, regs); + /* Compiler optimizations can remove arguments from static functions + * or mismatched type can be passed into a global function. + * In such cases mark the function as unreliable from BTF point of view. + */ if (err) + prog->aux->func_info_aux[subprog].unreliable = true; + return err; +} + +static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int insn_idx, int subprog, + set_callee_state_fn set_callee_state_cb) +{ + 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; - /* copy r1 - r5 args that callee can access. The copy includes parent - * pointers, which connects us up to the liveness chain + /* set_callee_state is used for direct subprog calls, but we are + * interested in validating only BPF helpers that can call subprogs as + * callbacks */ - for (i = BPF_REG_1; i <= BPF_REG_5; i++) - callee->regs[i] = caller->regs[i]; + env->subprog_info[subprog].is_cb = true; + if (bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_kfunc(insn->imm)) { + verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } else if (!bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_function(insn->imm)) { /* helper */ + verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } - clear_caller_saved_regs(env, caller->regs); + if (is_async_callback_calling_insn(insn)) { + struct bpf_verifier_state *async_cb; - /* only increment it after check_reg_arg() finished */ - state->curframe++; + /* 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, + is_bpf_wq_set_callback_impl_kfunc(insn->imm)); + if (!async_cb) + return -EFAULT; + 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); + 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 (!callback_state) + return -ENOMEM; + + 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 (subprog < 0) { + verbose(env, "verifier bug. No program starts at insn %d\n", 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); + + /* Only global subprogs cannot be called with a lock held. */ + 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; + } + + /* Only global subprogs cannot be called with preemption disabled. */ + if (env->cur_state->active_preempt_locks) { + verbose(env, "global function calls are not allowed with preemption disabled,\n" + "use static function instead\n"); + return -EINVAL; + } + + if (env->cur_state->active_irq_id) { + verbose(env, "global function calls are not allowed with IRQs disabled,\n" + "use static function instead\n"); + return -EINVAL; + } + + if (err) { + verbose(env, "Caller passes invalid args into func#%d ('%s')\n", + subprog, sub_name); + return err; + } + + 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; + } + + /* for regular function entry setup new frame and continue + * from that frame. + */ + err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state); + if (err) + return err; + + clear_caller_saved_regs(env, caller->regs); /* and go analyze first insn of the callee */ - *insn_idx = target_insn; + *insn_idx = env->subprog_info[subprog].start - 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); - print_verifier_state(env, caller); + print_verifier_state(env, state, caller->frameno, true); verbose(env, "callee:\n"); - print_verifier_state(env, callee); + print_verifier_state(env, state, state->curframe, true); } + return 0; } -static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) +int map_set_for_each_callback_args(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee) +{ + /* bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, + * void *callback_ctx, u64 flags); + * callback_fn(struct bpf_map *map, void *key, void *value, + * void *callback_ctx); + */ + callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; + + 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 = caller->regs[BPF_REG_1].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 = caller->regs[BPF_REG_1].map_ptr; + + /* pointer to stack or null */ + callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + return 0; +} + +static int set_callee_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, int insn_idx) +{ + int i; + + /* copy r1 - r5 args that callee can access. The copy includes parent + * pointers, which connects us up to the liveness chain + */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + callee->regs[i] = caller->regs[i]; + return 0; +} + +static int set_map_elem_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + struct bpf_insn_aux_data *insn_aux = &env->insn_aux_data[insn_idx]; + struct bpf_map *map; + int err; + + /* 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"); + return -ENOTSUPP; + } + + err = map->ops->map_set_for_each_callback_args(env, caller, callee); + if (err) + return err; + + callee->in_callback_fn = true; + callee->callback_ret_range = retval_range(0, 1); + return 0; +} + +static int set_loop_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, + * u64 flags); + * 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]; + + /* unused */ + __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_timer_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_1].map_ptr; + + /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); + * 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(0, 1); + return 0; +} + +static int set_find_vma_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_find_vma(struct task_struct *task, u64 addr, + * void *callback_fn, void *callback_ctx, u64 flags) + * (callback_fn)(struct task_struct *task, + * struct vm_area_struct *vma, void *callback_ctx); + */ + callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; + + 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]; + + /* pointer to stack or null */ + callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; + + /* unused */ + __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_user_ringbuf_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void + * callback_ctx, u64 flags); + * 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(env, &callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); + callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; + + /* unused */ + __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_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 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; callee = state->frame[state->curframe]; @@ -4456,47 +10558,112 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return -EINVAL; } - state->curframe--; - caller = state->frame[state->curframe]; - /* return to the caller whatever r0 had in the callee */ - caller->regs[BPF_REG_0] = *r0; + caller = state->frame[state->curframe - 1]; + if (callee->in_callback_fn) { + if (r0->type != SCALAR_VALUE) { + verbose(env, "R0 not a scalar value\n"); + return -EACCES; + } - /* Transfer references to the caller */ - err = transfer_reference_state(caller, callee); - if (err) - return err; + /* we are going to rely on register's precise value */ + err = mark_reg_read(env, r0, r0->parent, REG_LIVE_READ64); + err = 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 (!calls_callback(env, callee->callsite)) { + verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n", + *insn_idx, callee->callsite); + return -EFAULT; + } + } else { + /* return to the caller whatever r0 had in the callee */ + caller->regs[BPF_REG_0] = *r0; + } + + /* 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. + */ + 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); + print_verifier_state(env, state, callee->frameno, true); verbose(env, "to caller at %d:\n", *insn_idx); - print_verifier_state(env, caller); + 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 + 1] = NULL; + 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_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; - ret_reg->smax_value = meta->msize_max_value; - ret_reg->s32_max_value = meta->msize_max_value; - __reg_deduce_bounds(ret_reg); - __reg_bound_offset(ret_reg); - __update_reg_bounds(ret_reg); + 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; + } + + return reg_bounds_sanity_check(env, ret_reg, "retval"); } static int @@ -4512,7 +10679,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_map_push_elem && func_id != BPF_FUNC_map_pop_elem && - func_id != BPF_FUNC_map_peek_elem) + func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_for_each_map_elem && + func_id != BPF_FUNC_redirect_map && + func_id != BPF_FUNC_map_lookup_percpu_elem) return 0; if (map == NULL) { @@ -4533,12 +10703,12 @@ 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; } @@ -4549,8 +10719,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_reg_state *regs = cur_regs(env), *reg; struct bpf_map *map = meta->map_ptr; - struct tnum range; - u64 val; + u64 val, max; int err; if (func_id != BPF_FUNC_tail_call) @@ -4560,10 +10729,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return -EINVAL; } - range = tnum_range(0, map->max_entries - 1); reg = ®s[BPF_REG_3]; + val = reg->var_off.value; + max = map->max_entries; - if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) { + if (!(is_reg_const(reg, false) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } @@ -4571,8 +10741,6 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, err = mark_chain_precision(env, BPF_REG_3); if (err) return err; - - val = reg->var_off.value; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); else if (!bpf_map_key_poisoned(aux) && @@ -4581,39 +10749,206 @@ 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; + bool refs_lingering = false; int i; + if (!exception_exit && cur_func(env)->frameno) + return 0; + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].type != REF_TYPE_PTR) + continue; verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); + refs_lingering = true; + } + 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_lock) { + 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; + + /* data must be an array of u64 */ + if (data_len_reg->var_off.value % 8) + return -EINVAL; + num_args = data_len_reg->var_off.value / 8; + + /* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const + * and map_direct_value_addr is set. + */ + fmt_map_off = fmt_reg->off + fmt_reg->var_off.value; + err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr, + fmt_map_off); + if (err) { + verbose(env, "verifier bug\n"); + return -EFAULT; } - return state->acquired_refs ? -EINVAL : 0; + fmt = (char *)(long)fmt_addr + fmt_map_off; + + /* 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, num_args, &data); + if (err < 0) + verbose(env, "Invalid format string\n"); + + return err; } -static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) +static int check_get_func_ip(struct bpf_verifier_env *env) { + enum bpf_prog_type type = resolve_prog_type(env->prog); + int func_id = BPF_FUNC_get_func_ip; + + if (type == BPF_PROG_TYPE_TRACING) { + if (!bpf_prog_has_trampoline(env->prog)) { + verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n", + func_id_name(func_id), func_id); + return -ENOTSUPP; + } + return 0; + } else if (type == BPF_PROG_TYPE_KPROBE) { + return 0; + } + + verbose(env, "func %s#%d not supported for program type %d\n", + func_id_name(func_id), func_id, type); + return -ENOTSUPP; +} + +static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) +{ + return &env->insn_aux_data[env->insn_idx]; +} + +static bool loop_flag_is_zero(struct bpf_verifier_env *env) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[BPF_REG_4]; + bool reg_is_null = register_is_null(reg); + + if (reg_is_null) + mark_chain_precision(env, BPF_REG_4); + + return reg_is_null; +} + +static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) +{ + struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state; + + if (!state->initialized) { + state->initialized = 1; + state->fit_for_inline = loop_flag_is_zero(env); + state->callback_subprogno = subprogno; + return; + } + + if (!state->fit_for_inline) + return; + + state->fit_for_inline = (loop_flag_is_zero(env) && + 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 ? 0 : -EINVAL; +} + +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; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; + int insn_idx = *insn_idx_p; bool changes_data; - int i, err; + int i, err, func_id; /* find function prototype */ - if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { - verbose(env, "invalid func %s#%d\n", func_id_name(func_id), - func_id); + func_id = insn->imm; + 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 */ @@ -4622,8 +10957,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + if (fn->allowed && !fn->allowed(env->prog)) { + verbose(env, "helper call is not allowed in probe\n"); + return -EINVAL; + } + + 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); @@ -4640,13 +10985,43 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + if (env->cur_state->active_rcu_lock) { + 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 (in_sleepable(env) && is_storage_get_function(func_id)) + env->insn_aux_data[insn_idx].storage_get_func_atomic = true; + } + + 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 (in_sleepable(env) && 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; + } + + if (in_sleepable(env) && is_storage_get_function(func_id)) + env->insn_aux_data[insn_idx].storage_get_func_atomic = true; + } + meta.func_id = func_id; /* check args */ - for (i = 0; i < 5; i++) { - err = btf_resolve_helper_id(&env->log, fn, i); - if (err > 0) - meta.btf_id = err; - err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta); + for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { + err = check_func_arg(env, i, &meta, fn, insn_idx); if (err) return err; } @@ -4664,19 +11039,53 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int 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; } - if (func_id == BPF_FUNC_tail_call) { - err = check_reference_leak(env); - if (err) { - verbose(env, "tail_call would lead to reference leak\n"); - return err; + regs = cur_regs(env); + + 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])) { + /* meta.ref_obj_id can only be 0 if register that is meant to be + * released is NULL, which must be > R0. + */ + err = 0; } - } else if (is_release_function(func_id)) { - err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); @@ -4684,16 +11093,155 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } } - regs = cur_regs(env); + switch (func_id) { + case BPF_FUNC_tail_call: + 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, + * this is required because get_local_storage() can't return an error. + */ + if (!register_is_null(®s[BPF_REG_2])) { + verbose(env, "get_local_storage() doesn't support non-zero flags\n"); + return -EINVAL; + } + break; + case BPF_FUNC_for_each_map_elem: + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_map_elem_callback_state); + break; + case BPF_FUNC_timer_set_callback: + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_timer_callback_state); + break; + case BPF_FUNC_find_vma: + 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); + /* 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) { + verbose(env, "Unsupported reg type %s for bpf_dynptr_from_mem data\n", + reg_type_str(env, regs[BPF_REG_1].type)); + return -EACCES; + } + break; + case BPF_FUNC_set_retval: + if (prog_type == BPF_PROG_TYPE_LSM && + env->prog->expected_attach_type == BPF_LSM_CGROUP) { + if (!env->prog->aux->attach_func_proto->type) { + /* Make sure programs that attach to void + * hooks don't try to modify return value. + */ + verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); + return -EINVAL; + } + } + break; + case BPF_FUNC_dynptr_data: + { + struct bpf_reg_state *reg; + int id, ref_obj_id; - /* check that flags argument in get_local_storage(map, flags) is 0, - * this is required because get_local_storage() can't return an error. - */ - if (func_id == BPF_FUNC_get_local_storage && - !register_is_null(®s[BPF_REG_2])) { - verbose(env, "get_local_storage() doesn't support non-zero flags\n"); - return -EINVAL; + reg = get_dynptr_arg_reg(env, fn, regs); + if (!reg) + return -EFAULT; + + + if (meta.dynptr_id) { + verbose(env, "verifier internal error: meta.dynptr_id already set\n"); + return -EFAULT; + } + if (meta.ref_obj_id) { + verbose(env, "verifier internal error: meta.ref_obj_id already set\n"); + return -EFAULT; + } + + id = dynptr_id(env, reg); + if (id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr id\n"); + return id; + } + + ref_obj_id = dynptr_ref_obj_id(env, reg); + if (ref_obj_id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr ref_obj_id\n"); + 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) + /* 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 = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_user_ringbuf_callback_state); + break; + } + + if (err) + return err; /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { @@ -4705,13 +11253,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* update return register (already marked as written above) */ - if (fn->ret_type == RET_INTEGER) { + ret_type = fn->ret_type; + ret_flag = type_flag(ret_type); + + switch (base_type(ret_type)) { + case RET_INTEGER: /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); - } else if (fn->ret_type == RET_VOID) { + break; + case RET_VOID: regs[BPF_REG_0].type = NOT_INIT; - } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || - fn->ret_type == RET_PTR_TO_MAP_VALUE) { + break; + case RET_PTR_TO_MAP_VALUE: /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() @@ -4723,43 +11276,135 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn "kernel subsystem misconfigured verifier\n"); return -EINVAL; } + + 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; - if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; - if (map_value_has_spin_lock(meta.map_ptr)) - regs[BPF_REG_0].id = ++env->id_gen; - } else { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + 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_flag) && + btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK)) { regs[BPF_REG_0].id = ++env->id_gen; } - } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + break; + case RET_PTR_TO_SOCKET: mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; - regs[BPF_REG_0].id = ++env->id_gen; - } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) { + regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag; + break; + case RET_PTR_TO_SOCK_COMMON: mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; - regs[BPF_REG_0].id = ++env->id_gen; - } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { + regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag; + break; + case RET_PTR_TO_TCP_SOCK: mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; - regs[BPF_REG_0].id = ++env->id_gen; - } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) { + regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; + break; + case RET_PTR_TO_MEM: mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL; - regs[BPF_REG_0].id = ++env->id_gen; + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; - } else { - verbose(env, "unknown return type %d of func %s#%d\n", - fn->ret_type, func_id_name(func_id), func_id); + break; + case RET_PTR_TO_MEM_OR_BTF_ID: + { + const struct btf_type *t; + + mark_reg_known_zero(env, regs, BPF_REG_0); + t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL); + if (!btf_type_is_struct(t)) { + u32 tsize; + const struct btf_type *ret; + const char *tname; + + /* resolve the type size of ksym. */ + ret = btf_resolve_size(meta.ret_btf, t, &tsize); + if (IS_ERR(ret)) { + tname = btf_name_by_offset(meta.ret_btf, t->name_off); + verbose(env, "unable to resolve the size of type '%s': %ld\n", + tname, PTR_ERR(ret)); + return -EINVAL; + } + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; + regs[BPF_REG_0].mem_size = tsize; + } else { + 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].btf = meta.ret_btf; + regs[BPF_REG_0].btf_id = meta.ret_btf_id; + } + break; + } + case RET_PTR_TO_BTF_ID: + { + struct btf *ret_btf; + int ret_btf_id; + + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; + 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; + } + ret_btf = btf_vmlinux; + ret_btf_id = *fn->ret_btf_id; + } + if (ret_btf_id == 0) { + verbose(env, "invalid return type %u of func %s#%d\n", + base_type(ret_type), func_id_name(func_id), + func_id); + return -EINVAL; + } + regs[BPF_REG_0].btf = ret_btf; + regs[BPF_REG_0].btf_id = ret_btf_id; + break; + } + default: + verbose(env, "unknown return type %u of func %s#%d\n", + base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } - if (is_ptr_cast_function(func_id)) { + if (type_may_be_null(regs[BPF_REG_0].type)) + 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); + 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; @@ -4769,13 +11414,17 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int 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) return err; - if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) { + if ((func_id == BPF_FUNC_get_stack || + func_id == BPF_FUNC_get_task_stack) && + !env->prog->has_callchain_buf) { const char *err_str; #ifdef CONFIG_PERF_EVENTS @@ -4793,49 +11442,2076 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn env->prog->has_callchain_buf = true; } + if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack) + env->prog->call_get_stack = true; + + if (func_id == BPF_FUNC_get_func_ip) { + if (check_get_func_ip(env)) + return -ENOTSUPP; + env->prog->call_get_func_ip = true; + } + if (changes_data) clear_all_pkt_pointers(env); return 0; } -static bool signed_add_overflows(s64 a, s64 b) +/* 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) +{ + struct bpf_reg_state *reg = &cur_regs(env)[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 { + /* 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); + } + } +} + +static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ACQUIRE; +} + +static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RELEASE; +} + +static bool is_kfunc_trusted_args(struct bpf_kfunc_call_arg_meta *meta) +{ + return (meta->kfunc_flags & KF_TRUSTED_ARGS) || is_kfunc_release(meta); +} + +static bool is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_SLEEPABLE; +} + +static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_DESTRUCTIVE; +} + +static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RCU; +} + +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RCU_PROTECTED; +} + +static bool is_kfunc_arg_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) +{ + const struct btf_type *t; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + return btf_param_match_suffix(btf, arg, "__sz"); +} + +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; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + 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 btf_param_match_suffix(btf, arg, "__k"); +} + +static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) +{ + 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 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) { - /* Do the add in u64, where overflow is well-defined */ - s64 res = (s64)((u64)a + (u64)b); + return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); +} - if (b < 0) - return res > a; - return res < a; +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 signed_add32_overflows(s64 a, s64 b) +static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) { - /* Do the add in u32, where overflow is well-defined */ - s32 res = (s32)((u32)a + (u32)b); + return btf_param_match_suffix(btf, arg, "__str"); +} - if (b < 0) - return res > a; - return res < a; +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 signed_sub_overflows(s32 a, s32 b) +static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, + const struct btf_param *arg, + const char *name) { - /* Do the sub in u64, where overflow is well-defined */ - s64 res = (s64)((u64)a - (u64)b); + int len, target_len = strlen(name); + const char *param_name; + + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len != target_len) + return false; + if (strcmp(param_name, name)) + return false; - if (b < 0) - return res < a; - return res > a; + return true; } -static bool signed_sub32_overflows(s32 a, s32 b) +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, +}; + +BTF_ID_LIST(kf_arg_btf_ids) +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) + +static bool __is_kfunc_ptr_arg_type(const struct btf *btf, + const struct btf_param *arg, int type) { - /* Do the sub in u64, where overflow is well-defined */ - s32 res = (s32)((u32)a - (u32)b); + const struct btf_type *t; + u32 res_id; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t) + return false; + if (!btf_type_is_ptr(t)) + return false; + t = btf_type_skip_modifiers(btf, t->type, &res_id); + if (!t) + return false; + return btf_types_are_same(btf, res_id, btf_vmlinux, kf_arg_btf_ids[type]); +} + +static bool is_kfunc_arg_dynptr(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_DYNPTR_ID); +} + +static bool is_kfunc_arg_list_head(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_HEAD_ID); +} + +static bool is_kfunc_arg_list_node(const struct btf *btf, const struct btf_param *arg) +{ + 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_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, + const struct btf_type *t, int rec) +{ + const struct btf_type *member_type; + const struct btf_member *member; + u32 i; + + if (!btf_type_is_struct(t)) + return false; + + for_each_member(i, t, member) { + const struct btf_array *array; + + member_type = btf_type_skip_modifiers(btf, member->type, NULL); + if (btf_type_is_struct(member_type)) { + if (rec >= 3) { + verbose(env, "max struct nesting depth exceeded\n"); + return false; + } + if (!__btf_type_is_scalar_struct(env, btf, member_type, rec + 1)) + return false; + continue; + } + if (btf_type_is_array(member_type)) { + array = btf_array(member_type); + if (!array->nelems) + return false; + member_type = btf_type_skip_modifiers(btf, array->type, NULL); + if (!btf_type_is_scalar(member_type)) + return false; + continue; + } + if (!btf_type_is_scalar(member_type)) + return false; + } + return true; +} + +enum kfunc_ptr_arg_type { + KF_ARG_PTR_TO_CTX, + 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_MEM, + 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, +}; + +enum special_kfunc_type { + KF_bpf_obj_new_impl, + KF_bpf_obj_drop_impl, + 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_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_dynptr_from_skb, + KF_bpf_dynptr_from_xdp, + 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, +}; + +BTF_SET_START(special_kfunc_set) +BTF_ID(func, bpf_obj_new_impl) +BTF_ID(func, bpf_obj_drop_impl) +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_cast_to_kern_ctx) +BTF_ID(func, bpf_rdonly_cast) +BTF_ID(func, bpf_rbtree_remove) +BTF_ID(func, bpf_rbtree_add_impl) +BTF_ID(func, bpf_rbtree_first) +#ifdef CONFIG_NET +BTF_ID(func, bpf_dynptr_from_skb) +BTF_ID(func, bpf_dynptr_from_xdp) +#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) +#ifdef CONFIG_CGROUPS +BTF_ID(func, bpf_iter_css_task_new) +#endif +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_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_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) +#ifdef CONFIG_NET +BTF_ID(func, bpf_dynptr_from_skb) +BTF_ID(func, bpf_dynptr_from_xdp) +#else +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) - if (b < 0) - return res < a; - return res > a; +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) +{ + return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_lock]; +} + +static bool is_kfunc_bpf_rcu_read_unlock(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_unlock]; +} + +static bool is_kfunc_bpf_preempt_disable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_preempt_disable]; +} + +static bool is_kfunc_bpf_preempt_enable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_preempt_enable]; +} + +static enum kfunc_ptr_arg_type +get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, + const struct btf_type *t, const struct btf_type *ref_t, + const char *ref_tname, const struct btf_param *args, + int argno, int nargs) +{ + u32 regno = argno + 1; + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + bool arg_mem_size = false; + + if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) + return KF_ARG_PTR_TO_CTX; + + /* In this function, we verify the kfunc's BTF as per the argument type, + * leaving the rest of the verification with respect to the register + * 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_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_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_irq_flag(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_IRQ_FLAG; + + 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", + meta->func_name, argno, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return KF_ARG_PTR_TO_BTF_ID; + } + + 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 + * check_helper_mem_access. However, we only allow when argument type is + * pointer to scalar, or struct composed (recursively) of scalars. When + * arg_mem_size is true, the pointer can be void *. + */ + if (!btf_type_is_scalar(ref_t) && !__btf_type_is_scalar_struct(env, meta->btf, ref_t, 0) && + (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { + verbose(env, "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", + argno, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); + return -EINVAL; + } + return arg_mem_size ? KF_ARG_PTR_TO_MEM_SIZE : KF_ARG_PTR_TO_MEM; +} + +static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const struct btf_type *ref_t, + const char *ref_tname, u32 ref_id, + struct bpf_kfunc_call_arg_meta *meta, + int argno) +{ + const struct btf_type *reg_ref_t; + 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) { + reg_btf = reg->btf; + reg_ref_id = reg->btf_id; + } else { + reg_btf = btf_vmlinux; + reg_ref_id = *reg2btf_ids[base_type(reg->type)]; + } + + /* 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); + 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); + return -EINVAL; + } + return 0; +} + +static int process_irq_flag(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]; + bool irq_save; + int err; + + if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_save]) { + irq_save = true; + } else if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_restore]) { + irq_save = false; + } else { + verbose(env, "verifier internal error: unknown irq flags kfunc\n"); + return -EFAULT; + } + + 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); + 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); + if (err) + return err; + } + return 0; +} + + +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) { + verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n"); + return -EFAULT; + } + + if (type_flag(reg->type) & NON_OWN_REF) { + verbose(env, "verifier internal error: NON_OWN_REF already set\n"); + return -EFAULT; + } + + reg->type |= NON_OWN_REF; + if (rec->refcount_off >= 0) + reg->type |= MEM_RCU; + + return 0; +} + +static int ref_convert_owning_non_owning(struct bpf_verifier_env *env, u32 ref_obj_id) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *unused; + struct bpf_reg_state *reg; + int i; + + if (!ref_obj_id) { + verbose(env, "verifier internal error: ref_obj_id is zero for " + "owning -> non-owning conversion\n"); + return -EFAULT; + } + + for (i = 0; i < state->acquired_refs; i++) { + 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); + } + })); + return 0; + } + + verbose(env, "verifier internal error: ref state missing for ref_obj_id\n"); + return -EFAULT; +} + +/* Implementation details: + * + * Each register points to some region of memory, which we define as an + * allocation. Each allocation may embed a bpf_spin_lock which protects any + * special BPF objects (bpf_list_head, bpf_rb_root, etc.) part of the same + * allocation. The lock and the data it protects are colocated in the same + * memory region. + * + * Hence, everytime a register holds a pointer value pointing to such + * allocation, the verifier preserves a unique reg->id for it. + * + * The verifier remembers the lock 'ptr' and the lock 'id' whenever + * bpf_spin_lock is called. + * + * To enable this, lock state in the verifier captures two values: + * active_lock.ptr = Register's type specific pointer + * active_lock.id = A unique ID for each register pointer value + * + * Currently, PTR_TO_MAP_VALUE and PTR_TO_BTF_ID | MEM_ALLOC are the two + * supported register types. + * + * The active_lock.ptr in case of map values is the reg->map_ptr, and in case of + * allocated objects is the reg->btf pointer. + * + * The active_lock.id is non-unique for maps supporting direct_value_addr, as we + * can establish the provenance of the map value statically for each distinct + * lookup into such maps. They always contain a single map value hence unique + * IDs for each pseudo load pessimizes the algorithm and rejects valid programs. + * + * So, in case of global variables, they use array maps with max_entries = 1, + * hence their active_lock.ptr becomes map_ptr and id = 0 (since they all point + * into the same map value as max_entries is 1, as described above). + * + * In case of inner map lookups, the inner map pointer has same map_ptr as the + * outer map pointer (in verifier context), but each lookup into an inner map + * assigns a fresh reg->id to the lookup, so while lookups into distinct inner + * maps from the same outer map share the same map_ptr as active_lock.ptr, they + * will get different reg->id assigned to each lookup, hence different + * active_lock.id. + * + * In case of allocated objects, active_lock.ptr is the reg->btf, and the + * reg->id is a unique ID preserved after the NULL pointer check on the pointer + * returned from bpf_obj_new. Each allocation receives a new reg->id. + */ +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; + + switch ((int)reg->type) { + case PTR_TO_MAP_VALUE: + ptr = reg->map_ptr; + break; + case PTR_TO_BTF_ID | MEM_ALLOC: + ptr = reg->btf; + break; + default: + verbose(env, "verifier internal error: unknown reg type for lock check\n"); + return -EFAULT; + } + id = reg->id; + + if (!env->cur_state->active_locks) + return -EINVAL; + s = find_lock_state(env->cur_state, REF_TYPE_LOCK, id, ptr); + if (!s) { + verbose(env, "held lock and object are not in the same allocation\n"); + return -EINVAL; + } + return 0; +} + +static bool is_bpf_list_api_kfunc(u32 btf_id) +{ + 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]; +} + +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]; +} + +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 kfunc_spin_allowed(u32 btf_id) +{ + return is_bpf_graph_api_kfunc(btf_id) || is_bpf_iter_num_api_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]; +} + +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]); + 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 head_off; + + if (meta->btf != btf_vmlinux) { + verbose(env, "verifier internal error: unexpected btf mismatch in kfunc call\n"); + 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. %s has to be at the constant offset\n", + regno, head_type_name); + return -EINVAL; + } + + rec = reg_btf_record(reg); + head_off = reg->off + reg->var_off.value; + field = btf_record_find(rec, head_off, head_field_type); + if (!field) { + 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 %s\n", + rec->spin_lock_off, head_type_name); + return -EINVAL; + } + + if (*head_field) { + verbose(env, "verifier internal error: repeating %s arg\n", head_type_name); + return -EFAULT; + } + *head_field = field; + return 0; +} + +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; + u32 node_off; + + if (meta->btf != btf_vmlinux) { + verbose(env, "verifier internal error: unexpected btf mismatch in kfunc call\n"); + 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. %s has to be at the constant offset\n", + regno, node_type_name); + return -EINVAL; + } + + 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 = *node_field; + + 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->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", + 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 (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; + } + + 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); +} + +/* + * 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; + + args = (const struct btf_param *)(meta->func_proto + 1); + nargs = btf_type_vlen(meta->func_proto); + if (nargs > MAX_BPF_FUNC_REG_ARGS) { + verbose(env, "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++) { + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[i + 1]; + const struct btf_type *t, *ref_t, *resolve_ret; + enum bpf_arg_type arg_type = ARG_DONTCARE; + u32 regno = i + 1, ref_id, type_size; + bool is_ret_buf_sz = false; + int kf_arg_type; + + t = btf_type_skip_modifiers(btf, args[i].type, NULL); + + if (is_kfunc_arg_ignore(btf, &args[i])) + continue; + + if (btf_type_is_scalar(t)) { + if (reg->type != SCALAR_VALUE) { + verbose(env, "R%d is not a scalar\n", regno); + return -EINVAL; + } + + 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"); + return -EFAULT; + } + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d must be a known constant\n", regno); + return -EINVAL; + } + ret = mark_chain_precision(env, regno); + if (ret < 0) + return ret; + meta->arg_constant.found = true; + meta->arg_constant.value = reg->var_off.value; + } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdonly_buf_size")) { + meta->r0_rdonly = true; + is_ret_buf_sz = true; + } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdwr_buf_size")) { + is_ret_buf_sz = true; + } + + if (is_ret_buf_sz) { + if (meta->r0_size) { + verbose(env, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); + return -EINVAL; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d is not a const\n", regno); + return -EINVAL; + } + + meta->r0_size = reg->var_off.value; + ret = mark_chain_precision(env, regno); + if (ret) + return ret; + } + continue; + } + + if (!btf_type_is_ptr(t)) { + verbose(env, "Unrecognized arg#%d type %s\n", i, btf_type_str(t)); + 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); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; + if (is_kfunc_release(meta)) + meta->release_regno = regno; + } + + ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); + ref_tname = btf_name_by_offset(btf, ref_t->name_off); + + kf_arg_type = get_kfunc_ptr_arg_type(env, meta, t, ref_t, ref_tname, args, i, nargs); + if (kf_arg_type < 0) + 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) { + /* Use map_uid (which is unique id of inner map) to reject: + * inner_map1 = bpf_map_lookup_elem(outer_map, key1) + * inner_map2 = bpf_map_lookup_elem(outer_map, key2) + * if (inner_map1 && inner_map2) { + * wq = bpf_map_lookup_elem(inner_map1); + * if (wq) + * // mismatch would have been allowed + * bpf_wq_init(wq, inner_map2); + * } + * + * Comparing map_ptr is enough to distinguish normal and outer maps. + */ + if (meta->map.ptr != reg->map_ptr || + meta->map.uid != reg->map_uid) { + verbose(env, + "workqueue pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", + meta->map.uid, reg->map_uid); + return -EINVAL; + } + } + meta->map.ptr = reg->map_ptr; + meta->map.uid = reg->map_uid; + fallthrough; + case KF_ARG_PTR_TO_ALLOC_BTF_ID: + case KF_ARG_PTR_TO_BTF_ID: + if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) + break; + + if (!is_trusted_reg(reg)) { + if (!is_kfunc_rcu(meta)) { + verbose(env, "R%d must be referenced or trusted\n", regno); + return -EINVAL; + } + if (!is_rcu_reg(reg)) { + verbose(env, "R%d must be a rcu pointer\n", regno); + return -EINVAL; + } + } + fallthrough; + case KF_ARG_PTR_TO_CTX: + 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: + 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_IRQ_FLAG: + break; + default: + WARN_ON_ONCE(1); + return -EFAULT; + } + + if (is_kfunc_release(meta) && reg->ref_obj_id) + arg_type |= OBJ_RELEASE; + ret = check_func_arg_reg_off(env, reg, regno, arg_type); + if (ret < 0) + return ret; + + 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, reg_type_str(env, reg->type)); + return -EINVAL; + } + + if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + ret = get_kern_ctx_btf_id(&env->log, resolve_prog_type(env->prog)); + if (ret < 0) + return -EINVAL; + meta->ret_btf_id = ret; + } + break; + case KF_ARG_PTR_TO_ALLOC_BTF_ID: + 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; + } + if (!reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + if (meta->btf == btf_vmlinux) { + meta->arg_btf = reg->btf; + meta->arg_btf_id = reg->btf_id; + } + break; + 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_clone] && + (dynptr_arg_type & MEM_UNINIT)) { + enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type; + + if (parent_type == BPF_DYNPTR_TYPE_INVALID) { + verbose(env, "verifier internal error: no dynptr type for parent of clone\n"); + 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) { + verbose(env, "verifier internal error: missing ref obj id for parent of clone\n"); + return -EFAULT; + } + } + + ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type, clone_ref_obj_id); + if (ret < 0) + return ret; + + if (!(dynptr_arg_type & MEM_UNINIT)) { + int id = dynptr_id(env, reg); + + if (id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr id\n"); + 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); + } + + 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; + case KF_ARG_PTR_TO_LIST_HEAD: + 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_list_head(env, reg, regno, meta); + 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); + return -EINVAL; + } + if (!reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_list_node(env, reg, regno, meta); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_RB_NODE: + if (meta->func_id == special_kfunc_list[KF_bpf_rbtree_remove]) { + if (!type_is_non_owning_ref(reg->type) || reg->ref_obj_id) { + verbose(env, "rbtree_remove node input must be non-owning ref\n"); + return -EINVAL; + } + if (in_rbtree_lock_required_cb(env)) { + verbose(env, "rbtree_remove not allowed in rbtree cb\n"); + return -EINVAL; + } + } else { + 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; + } + } + + 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 || + (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && + !reg2btf_ids[base_type(reg->type)]) { + verbose(env, "arg#%d is %s ", i, reg_type_str(env, reg->type)); + verbose(env, "expected %s or socket\n", + reg_type_str(env, base_type(reg->type) | + (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM: + resolve_ret = btf_resolve_size(btf, ref_t, &type_size); + if (IS_ERR(resolve_ret)) { + verbose(env, "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; + } + ret = check_mem_reg(env, reg, regno, type_size); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM_SIZE: + { + 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) { + verbose(env, "verifier internal error: only one constant argument permitted\n"); + 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' 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) { + verbose(env, "verifier internal error: Couldn't find btf_record\n"); + 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_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; + } + } + + if (is_kfunc_release(meta) && !meta->release_regno) { + verbose(env, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", + func_name); + return -EINVAL; + } + + return 0; +} + +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 *func, *func_proto; + u32 func_id, *kfunc_flags; + const char *func_name; + struct btf *desc_btf; + + if (kfunc_name) + *kfunc_name = NULL; + + if (!insn->imm) + return -EINVAL; + + desc_btf = find_kfunc_desc_btf(env, insn->off); + if (IS_ERR(desc_btf)) + return PTR_ERR(desc_btf); + + 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, func_id, env->prog); + if (!kfunc_flags) { + return -EACCES; + } + + 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; +} + +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; + const struct btf_type *ret_t; + 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 (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { + verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); + return -EACCES; + } + + sleepable = is_kfunc_sleepable(&meta); + if (sleepable && !in_sleepable(env)) { + verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); + return -EACCES; + } + + /* 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; + } + } + + rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); + rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); + + preempt_disable = is_kfunc_bpf_preempt_disable(&meta); + preempt_enable = is_kfunc_bpf_preempt_enable(&meta); + + if (env->cur_state->active_rcu_lock) { + struct bpf_func_state *state; + struct bpf_reg_state *reg; + u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER); + + 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 (rcu_lock) { + verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); + return -EINVAL; + } else if (rcu_unlock) { + 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) { + verbose(env, "kernel func %s is sleepable within rcu_read_lock 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); + return -EINVAL; + } + + 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 non-preemptible region\n", func_name); + return -EACCES; + } + } 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; + } + + if (env->cur_state->active_irq_id && sleepable) { + verbose(env, "kernel func %s is sleepable within IRQ-disabled region\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); + if (err) { + verbose(env, "kfunc %s#%d reference has not been acquired before\n", + func_name, meta.func_id); + 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, 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, 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] && + 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; + } + } + + if (btf_type_is_scalar(t)) { + mark_reg_unknown(env, regs, 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); + + 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] || + 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 (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_graph_node(regs, BPF_REG_0, &field->graph_root); + } else if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_remove] || + meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) { + 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 || !btf_type_is_struct(ret_t)) { + verbose(env, + "kfunc bpf_rdonly_cast 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 | PTR_UNTRUSTED; + regs[BPF_REG_0].btf = desc_btf; + regs[BPF_REG_0].btf_id = meta.arg_constant.value; + } 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) { + verbose(env, "verifier internal error: bpf_dynptr_slice(_rdwr) no constant size\n"); + 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) { + verbose(env, "verifier internal error: no dynptr id\n"); + 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 { + verbose(env, "kernel function %s unhandled dynamic return type\n", + meta.func_name); + return -EFAULT; + } + } 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 (!IS_ERR(btf_resolve_size(desc_btf, ptr_type, &sz))) { + meta.r0_size = sz; + meta.r0_rdonly = true; + } + } + if (!meta.r0_size) { + ptr_type_name = btf_name_by_offset(desc_btf, + ptr_type->name_off); + verbose(env, + "kernel function %s returns pointer type %s %s is not supported\n", + func_name, + btf_type_str(ptr_type), + ptr_type_name); + return -EINVAL; + } + + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_MEM; + regs[BPF_REG_0].mem_size = meta.r0_size; + + if (meta.r0_rdonly) + regs[BPF_REG_0].type |= MEM_RDONLY; + + /* 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; + } 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; + + 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)) { + regs[BPF_REG_0].type |= PTR_MAYBE_NULL; + /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ + regs[BPF_REG_0].id = ++env->id_gen; + } + mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); + if (is_kfunc_acquire(&meta)) { + 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 (meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) { + 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 if (btf_type_is_void(t)) { + 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_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(meta.func_proto); + args = (const struct btf_param *)(meta.func_proto + 1); + for (i = 0; i < nargs; i++) { + u32 regno = i + 1; + + t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL); + if (btf_type_is_ptr(t)) + mark_btf_func_reg_size(env, regno, sizeof(void *)); + else + /* scalar. ensured by btf_check_kfunc_arg_match() */ + mark_btf_func_reg_size(env, regno, t->size); + } + + if (is_iter_next_kfunc(&meta)) { + err = process_iter_next_call(env, insn_idx, &meta); + if (err) + return err; + } + + return 0; } static bool check_reg_sane_offset(struct bpf_verifier_env *env, @@ -4848,65 +13524,68 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env, if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", - reg_type_str[type], val); + reg_type_str(env, type), val); return false; } if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %d is not allowed\n", - reg_type_str[type], reg->off); + reg_type_str(env, type), reg->off); return false; } if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", - reg_type_str[type]); + reg_type_str(env, type)); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", - smin, reg_type_str[type]); + smin, reg_type_str(env, type)); return false; } return true; } -static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) -{ - return &env->insn_aux_data[env->insn_idx]; -} +enum { + REASON_BOUNDS = -1, + REASON_TYPE = -2, + REASON_PATHS = -3, + REASON_LIMIT = -4, + REASON_STACK = -5, +}; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, - u32 *ptr_limit, u8 opcode, bool off_is_neg) + u32 *alu_limit, bool mask_to_left) { - bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || - (opcode == BPF_SUB && !off_is_neg); - u32 off; + u32 max = 0, ptr_limit = 0; switch (ptr_reg->type) { case PTR_TO_STACK: - /* Indirect variable offset stack access is prohibited in - * unprivileged mode so it's not handled here. + /* Offset 0 is out-of-bounds, but acceptable start for the + * left direction, see BPF_REG_FP. Also, unknown scalar + * offset where we would need to deal with min/max bounds is + * currently prohibited for unprivileged. */ - off = ptr_reg->off + ptr_reg->var_off.value; - if (mask_to_left) - *ptr_limit = MAX_BPF_STACK + off; - else - *ptr_limit = -off; - return 0; + max = MAX_BPF_STACK + mask_to_left; + ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off); + break; case PTR_TO_MAP_VALUE: - if (mask_to_left) { - *ptr_limit = ptr_reg->umax_value + ptr_reg->off; - } else { - off = ptr_reg->smin_value + ptr_reg->off; - *ptr_limit = ptr_reg->map_ptr->value_size - off; - } - return 0; + max = ptr_reg->map_ptr->value_size; + ptr_limit = (mask_to_left ? + ptr_reg->smin_value : + ptr_reg->umax_value) + ptr_reg->off; + break; default: - return -EINVAL; + return REASON_TYPE; } + + if (ptr_limit >= max) + return REASON_LIMIT; + *alu_limit = ptr_limit; + return 0; } static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, @@ -4924,9 +13603,9 @@ static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, if (aux->alu_state && (aux->alu_state != alu_state || aux->alu_limit != alu_limit)) - return -EACCES; + return REASON_PATHS; - /* Corresponding fixup done in fixup_bpf_calls(). */ + /* Corresponding fixup done in do_misc_fixups(). */ aux->alu_state = alu_state; aux->alu_limit = alu_limit; return 0; @@ -4943,19 +13622,55 @@ static int sanitize_val_alu(struct bpf_verifier_env *env, return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); } +static bool sanitize_needed(u8 opcode) +{ + return opcode == BPF_ADD || opcode == BPF_SUB; +} + +struct bpf_sanitize_info { + struct bpf_insn_aux_data aux; + 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) +{ + struct bpf_verifier_state *branch; + struct bpf_reg_state *regs; + + branch = push_stack(env, next_idx, curr_idx, true); + if (branch && insn) { + regs = branch->frame[branch->curframe]->regs; + if (BPF_SRC(insn->code) == BPF_K) { + mark_reg_unknown(env, regs, insn->dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X) { + mark_reg_unknown(env, regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->src_reg); + } + } + return branch; +} + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, + const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, - bool off_is_neg) + struct bpf_sanitize_info *info, + const bool commit_window) { + struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; - struct bpf_insn_aux_data *aux = cur_aux(env); + bool off_is_imm = tnum_is_const(off_reg->var_off); + bool off_is_neg = off_reg->smin_value < 0; bool ptr_is_dst_reg = ptr_reg == dst_reg; 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)) return 0; @@ -4967,15 +13682,53 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (vstate->speculative) goto do_sim; - alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; - alu_state |= ptr_is_dst_reg ? - BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + if (!commit_window) { + if (!tnum_is_const(off_reg->var_off) && + (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) + return REASON_BOUNDS; - if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg)) - return 0; - if (update_alu_sanitation_state(aux, alu_state, alu_limit)) - return -EACCES; + info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + } + + err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); + if (err < 0) + return err; + + if (commit_window) { + /* In commit phase we narrow the masking window based on + * the observed pointer move after the simulated operation. + */ + alu_state = info->aux.alu_state; + alu_limit = abs(info->aux.alu_limit - alu_limit); + } else { + alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; + alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; + alu_state |= ptr_is_dst_reg ? + BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + + /* Limit pruning on unknown scalars to enable deep search for + * potential masking differences from other program paths. + */ + if (!off_is_imm) + env->explore_alu_limits = true; + } + + err = update_alu_sanitation_state(aux, alu_state, alu_limit); + if (err < 0) + return err; do_sim: + /* If we're in commit phase, we're done here given we already + * pushed the truncated dst_reg into the speculative verification + * stack. + * + * Also, when register is a known constant, we rewrite register-based + * operation to immediate-based, and thus do not need masking (and as + * a consequence, do not need to simulate the zero-truncation either). + */ + if (commit_window || off_is_imm) + return 0; + /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of * masking when off was not within expected range. If off @@ -4987,12 +13740,131 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } - ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); + ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, + env->insn_idx); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; - return !ret ? -EFAULT : 0; + return !ret ? REASON_STACK : 0; +} + +static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) +{ + struct bpf_verifier_state *vstate = env->cur_state; + + /* If we simulate paths under speculation, we don't update the + * insn as 'seen' such that when we verify unreachable paths in + * the non-speculative domain, sanitize_dead_code() can still + * rewrite/sanitize them. + */ + if (!vstate->speculative) + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; +} + +static int sanitize_err(struct bpf_verifier_env *env, + const struct bpf_insn *insn, int reason, + const struct bpf_reg_state *off_reg, + const struct bpf_reg_state *dst_reg) +{ + static const char *err = "pointer arithmetic with it prohibited for !root"; + const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub"; + u32 dst = insn->dst_reg, src = insn->src_reg; + + switch (reason) { + case REASON_BOUNDS: + verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n", + off_reg == dst_reg ? dst : src, err); + break; + case REASON_TYPE: + verbose(env, "R%d has pointer with unsupported alu operation, %s\n", + off_reg == dst_reg ? src : dst, err); + break; + case REASON_PATHS: + verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n", + dst, op, err); + break; + case REASON_LIMIT: + verbose(env, "R%d tried to %s beyond pointer bounds, %s\n", + dst, op, err); + break; + case REASON_STACK: + verbose(env, "R%d could not be pushed for speculative verification, %s\n", + dst, err); + break; + default: + verbose(env, "verifier internal error: unknown reason (%d)\n", + reason); + break; + } + + return -EACCES; +} + +/* check that stack access falls within stack limits and that 'reg' doesn't + * have a variable offset. + * + * 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(). + * + * + * 'off' includes 'reg->off'. + */ +static int check_stack_access_for_ptr_arithmetic( + struct bpf_verifier_env *env, + int regno, + const struct bpf_reg_state *reg, + int off) +{ + if (!tnum_is_const(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "R%d variable stack access prohibited for !root, var_off=%s off=%d\n", + regno, tn_buf, off); + return -EACCES; + } + + if (off >= 0 || off < -MAX_BPF_STACK) { + verbose(env, "R%d stack pointer arithmetic goes out of range, " + "prohibited for !root; off=%d\n", regno, off); + return -EACCES; + } + + return 0; +} + +static int sanitize_check_bounds(struct bpf_verifier_env *env, + const struct bpf_insn *insn, + const struct bpf_reg_state *dst_reg) +{ + u32 dst = insn->dst_reg; + + /* For unprivileged we require that resulting offset must be in bounds + * in order to be able to sanitize access later on. + */ + if (env->bypass_spec_v1) + return 0; + + switch (dst_reg->type) { + case PTR_TO_STACK: + if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg, + dst_reg->off + dst_reg->var_off.value)) + return -EACCES; + break; + case PTR_TO_MAP_VALUE: + if (check_map_access(env, dst, dst_reg->off, 1, false, ACCESS_HELPER)) { + verbose(env, "R%d pointer arithmetic of map value goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } + break; + default: + break; + } + + return 0; } /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. @@ -5013,8 +13885,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; - u32 dst = insn->dst_reg, src = insn->src_reg; + struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); + u32 dst = insn->dst_reg; int ret; dst_reg = ®s[dst]; @@ -5030,38 +13903,50 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ + if (opcode == BPF_SUB && env->allow_ptr_leaks) { + __mark_reg_unknown(env, dst_reg); + return 0; + } + verbose(env, "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } - switch (ptr_reg->type) { - case PTR_TO_MAP_VALUE_OR_NULL: + if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; + } + + 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: - case PTR_TO_PACKET_END: - case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: - case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: - case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: - case PTR_TO_XDP_SOCK: + /* smin_val represents the known value */ + if (known && smin_val == 0 && opcode == BPF_ADD) + break; + fallthrough; + default: verbose(env, "R%d pointer arithmetic on %s prohibited\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; - case PTR_TO_MAP_VALUE: - if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) { - verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n", - off_reg == dst_reg ? dst : src); - return -EACCES; - } - /* fall-through */ - default: - break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. @@ -5077,13 +13962,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* pointer types do not carry 32-bit bounds at the moment. */ __mark_reg32_unbounded(dst_reg); + if (sanitize_needed(opcode)) { + ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, + &info, false); + if (ret < 0) + return sanitize_err(env, insn, ret, off_reg, dst_reg); + } + switch (opcode) { case BPF_ADD: - ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); - if (ret < 0) { - verbose(env, "R%d tried to add from different maps or paths\n", dst); - return ret; - } /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ @@ -5108,21 +13995,15 @@ 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; @@ -5130,15 +14011,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ - dst_reg->raw = 0; + memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_SUB: - ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); - if (ret < 0) { - verbose(env, "R%d tried to sub from different maps or paths\n", dst); - return ret; - } if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", @@ -5170,14 +14046,11 @@ 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 */ @@ -5195,7 +14068,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) - dst_reg->raw = 0; + memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_AND: @@ -5214,27 +14087,14 @@ 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; - - __update_reg_bounds(dst_reg); - __reg_deduce_bounds(dst_reg); - __reg_bound_offset(dst_reg); - - /* For unprivileged we require that resulting offset must be in bounds - * in order to be able to sanitize access later on. - */ - if (!env->bypass_spec_v1) { - if (dst_reg->type == PTR_TO_MAP_VALUE && - check_map_access(env, dst, dst_reg->off, 1, false)) { - verbose(env, "R%d pointer arithmetic of map value goes out of range, " - "prohibited for !root\n", dst); - return -EACCES; - } else if (dst_reg->type == PTR_TO_STACK && - check_stack_access(env, dst_reg, dst_reg->off + - dst_reg->var_off.value, 1)) { - verbose(env, "R%d stack pointer arithmetic goes out of range, " - "prohibited for !root\n", dst); - return -EACCES; - } + reg_bounds_sync(dst_reg); + if (sanitize_check_bounds(env, insn, dst_reg) < 0) + return -EACCES; + if (sanitize_needed(opcode)) { + ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, + &info, true); + if (ret < 0) + return sanitize_err(env, insn, ret, off_reg, dst_reg); } return 0; @@ -5243,71 +14103,56 @@ 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; - 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; - 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 (check_add_overflow(*dst_umin, src_reg->u32_min_value, dst_umin) || + check_add_overflow(*dst_umax, src_reg->u32_max_value, dst_umax)) { + *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; - 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; - 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 (check_add_overflow(*dst_umin, src_reg->umin_value, dst_umin) || + check_add_overflow(*dst_umax, src_reg->umax_value, dst_umax)) { + *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 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; - 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 */ @@ -5323,19 +14168,16 @@ static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, 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 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; - 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 */ @@ -5351,64 +14193,56 @@ static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, 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); } } @@ -5418,34 +14252,29 @@ 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; - /* Assuming scalar64_min_max_and will be called so its safe - * to skip updating register for known 32-bit case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ 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; } - } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, @@ -5453,12 +14282,10 @@ 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) { - __mark_reg_known(dst_reg, dst_reg->var_off.value & - src_reg->var_off.value); + __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } @@ -5467,18 +14294,16 @@ 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); @@ -5490,32 +14315,28 @@ 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->smin_value; - u32 umin_val = src_reg->umin_value; + u32 umin_val = src_reg->u32_min_value; - /* Assuming scalar64_min_max_or will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ 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. - */ + + /* 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; - } else { - /* ORing two positives gives a positive, so safe to - * cast result into s64. - */ - dst_reg->s32_min_value = dst_reg->umin_value; - dst_reg->s32_max_value = dst_reg->umax_value; } } @@ -5524,12 +14345,10 @@ 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) { - __mark_reg_known(dst_reg, dst_reg->var_off.value | - src_reg->var_off.value); + __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } @@ -5538,20 +14357,76 @@ 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. - */ + + /* 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); +} + +static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_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); + + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); + return; + } + + /* We get both minimum and maximum from the var32_off. */ + dst_reg->u32_min_value = var32_off.value; + dst_reg->u32_max_value = var32_off.value | var32_off.mask; + + /* 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 { - /* ORing two positives gives a positive, so safe to - * cast result into s64. - */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } +} + +static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_is_const(src_reg->var_off); + bool dst_known = tnum_is_const(dst_reg->var_off); + + if (src_known && dst_known) { + /* dst_reg->var_off.value has been updated earlier */ + __mark_reg_known(dst_reg, dst_reg->var_off.value); + return; + } + + /* We get both minimum and maximum from the var_off. */ + dst_reg->umin_value = dst_reg->var_off.value; + dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; + + /* 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); } @@ -5652,7 +14527,7 @@ static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg, * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the - * unsigned bounts capture the signed bounds. + * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. @@ -5683,7 +14558,7 @@ static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg, * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the - * unsigned bounts capture the signed bounds. + * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. @@ -5752,6 +14627,46 @@ static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, __update_reg_bounds(dst_reg); } +static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn, + const struct bpf_reg_state *src_reg) +{ + bool src_is_const = false; + u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; + + if (insn_bitness == 32) { + if (tnum_subreg_is_const(src_reg->var_off) + && src_reg->s32_min_value == src_reg->s32_max_value + && src_reg->u32_min_value == src_reg->u32_max_value) + src_is_const = true; + } else { + if (tnum_is_const(src_reg->var_off) + && src_reg->smin_value == src_reg->smax_value + && src_reg->umin_value == src_reg->umax_value) + src_is_const = true; + } + + switch (BPF_OP(insn->code)) { + case BPF_ADD: + case BPF_SUB: + case BPF_AND: + case BPF_XOR: + case BPF_OR: + case BPF_MUL: + return true; + + /* Shift operators range is only computable if shift dimension operand + * is a constant. Shifts greater than 31 or 63 are undefined. This + * includes shifts by a negative number. + */ + case BPF_LSH: + case BPF_RSH: + case BPF_ARSH: + return (src_is_const && src_reg->umax_value < insn_bitness); + default: + return false; + } +} + /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. @@ -5761,58 +14676,21 @@ 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; - u32 dst = insn->dst_reg; - int ret; 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; } + if (sanitize_needed(opcode)) { + ret = sanitize_val_alu(env, insn); + if (ret < 0) + return sanitize_err(env, insn, ret, NULL, NULL); + } + /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. * There are two classes of instructions: The first class we track both * alu32 and alu64 sign/unsigned bounds independently this provides the @@ -5829,21 +14707,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, */ switch (opcode) { case BPF_ADD: - ret = sanitize_val_alu(env, insn); - if (ret < 0) { - verbose(env, "R%d tried to add from different pointers or scalars\n", dst); - return ret; - } scalar32_min_max_add(dst_reg, &src_reg); scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: - ret = sanitize_val_alu(env, insn); - if (ret < 0) { - verbose(env, "R%d tried to sub from different pointers or scalars\n", dst); - return ret; - } scalar32_min_max_sub(dst_reg, &src_reg); scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); @@ -5863,57 +14731,37 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, scalar32_min_max_or(dst_reg, &src_reg); scalar_min_max_or(dst_reg, &src_reg); break; + case BPF_XOR: + dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off); + scalar32_min_max_xor(dst_reg, &src_reg); + 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; } /* ALU32 ops are zero extended into 64bit register */ if (alu32) zext_32_to_64(dst_reg); - - __update_reg_bounds(dst_reg); - __reg_deduce_bounds(dst_reg); - __reg_bound_offset(dst_reg); + reg_bounds_sync(dst_reg); return 0; } @@ -5927,13 +14775,30 @@ 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; + if (BPF_SRC(insn->code) == BPF_X) { src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { @@ -5968,6 +14833,11 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); + } else if (dst_reg->precise) { + /* if dst_reg is precise, src_reg should be precise as well */ + err = mark_chain_precision(env, insn->src_reg); + if (err) + return err; } } else { /* Pretend the src is a reg with a known value, since we only @@ -5983,16 +14853,53 @@ 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); + print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(env, state); + print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } - 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 */ @@ -6004,7 +14911,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (opcode == BPF_END || opcode == BPF_NEG) { if (opcode == BPF_NEG) { - if (BPF_SRC(insn->code) != 0 || + if (BPF_SRC(insn->code) != BPF_K || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { verbose(env, "BPF_NEG uses reserved fields\n"); @@ -6013,7 +14920,8 @@ 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; } @@ -6038,9 +14946,27 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } 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 */ @@ -6064,12 +14990,45 @@ 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 - */ - *dst_reg = *src_reg; - dst_reg->live |= REG_LIVE_WRITTEN; - dst_reg->subreg_def = DEF_NOT_SUBREG; + 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 + */ + assign_scalar_id_before_mov(env, src_reg); + copy_register_state(dst_reg, src_reg); + dst_reg->live |= REG_LIVE_WRITTEN; + 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->live |= REG_LIVE_WRITTEN; + 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)) { @@ -6078,14 +15037,39 @@ 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; - 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->live |= REG_LIVE_WRITTEN; + 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->live |= REG_LIVE_WRITTEN; + 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); } zext_32_to_64(dst_reg); + reg_bounds_sync(dst_reg); } } else { /* case: R = imm @@ -6110,7 +15094,8 @@ 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 > 1 || + (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } @@ -6119,7 +15104,8 @@ 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 > 1 || + (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } @@ -6148,35 +15134,12 @@ 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; -} - -static void __find_good_pkt_pointers(struct bpf_func_state *state, - struct bpf_reg_state *dst_reg, - enum bpf_reg_type type, u16 new_range) -{ - struct bpf_reg_state *reg; - int i; - - for (i = 0; i < MAX_BPF_REG; i++) { - reg = &state->regs[i]; - if (reg->type == type && reg->id == dst_reg->id) - /* keep the maximum range already checked */ - reg->range = max(reg->range, new_range); - } - - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - if (reg->type == type && reg->id == dst_reg->id) - reg->range = max(reg->range, new_range); - } + return reg_bounds_sanity_check(env, ®s[insn->dst_reg], "alu"); } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, @@ -6184,8 +15147,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, enum bpf_reg_type type, bool range_right_open) { - u16 new_range; - int i; + struct bpf_func_state *state; + struct bpf_reg_state *reg; + int new_range; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) @@ -6201,7 +15165,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, new_range = dst_reg->off; if (range_right_open) - new_range--; + new_range++; /* Examples for register markings: * @@ -6250,77 +15214,137 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ - for (i = 0; i <= vstate->curframe; i++) - __find_good_pkt_pointers(vstate->frame[i], dst_reg, type, - new_range); + bpf_for_each_reg_in_vstate(vstate, state, reg, ({ + if (reg->type == type && reg->id == dst_reg->id) + /* keep the maximum range already checked */ + reg->range = max(reg->range, new_range); + })); } -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; switch (opcode) { case BPF_JEQ: - if (tnum_is_const(subreg)) - return !!tnum_equals_const(subreg, 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; + /* non-overlapping ranges */ + if (umin1 > umax2 || umax1 < umin2) + return 0; + if (smin1 > smax2 || smax1 < smin2) + return 0; + if (!is_jmp32) { + /* if 64-bit ranges are inconclusive, see if we can + * utilize 32-bit subrange knowledge to eliminate + * branches that can't be taken a priori + */ + if (reg1->u32_min_value > reg2->u32_max_value || + reg1->u32_max_value < reg2->u32_min_value) + return 0; + if (reg1->s32_min_value > reg2->s32_max_value || + reg1->s32_max_value < reg2->s32_min_value) + return 0; + } break; case BPF_JNE: - if (tnum_is_const(subreg)) - return !tnum_equals_const(subreg, 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; + /* non-overlapping ranges */ + if (umin1 > umax2 || umax1 < umin2) + return 1; + if (smin1 > smax2 || smax1 < smin2) + return 1; + if (!is_jmp32) { + /* if 64-bit ranges are inconclusive, see if we can + * utilize 32-bit subrange knowledge to eliminate + * branches that can't be taken a priori + */ + if (reg1->u32_min_value > reg2->u32_max_value || + reg1->u32_max_value < reg2->u32_min_value) + return 1; + if (reg1->s32_min_value > reg2->s32_max_value || + reg1->s32_max_value < reg2->s32_min_value) + return 1; + } break; case BPF_JSET: - if ((~subreg.mask & subreg.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 (!((subreg.mask | subreg.value) & val)) + if (!((t1.mask | t1.value) & t2.value)) return 0; break; case BPF_JGT: - if (reg->u32_min_value > val) + if (umin1 > umax2) return 1; - else if (reg->u32_max_value <= val) + else if (umax1 <= umin2) return 0; break; case BPF_JSGT: - if (reg->s32_min_value > sval) + if (smin1 > smax2) return 1; - else if (reg->s32_max_value < sval) + else if (smax1 <= smin2) return 0; break; case BPF_JLT: - if (reg->u32_max_value < val) + if (umax1 < umin2) return 1; - else if (reg->u32_min_value >= val) + else if (umin1 >= umax2) return 0; break; case BPF_JSLT: - if (reg->s32_max_value < sval) + if (smax1 < smin2) return 1; - else if (reg->s32_min_value >= sval) + else if (smin1 >= smax2) return 0; break; case BPF_JGE: - if (reg->u32_min_value >= val) + if (umin1 >= umax2) return 1; - else if (reg->u32_max_value < val) + else if (umax1 < umin2) return 0; break; case BPF_JSGE: - if (reg->s32_min_value >= sval) + if (smin1 >= smax2) return 1; - else if (reg->s32_max_value < sval) + else if (smax1 < smin2) return 0; break; case BPF_JLE: - if (reg->u32_max_value <= val) + if (umax1 <= umin2) return 1; - else if (reg->u32_min_value > val) + else if (umin1 > umax2) return 0; break; case BPF_JSLE: - if (reg->s32_max_value <= sval) + if (smax1 <= smin2) return 1; - else if (reg->s32_min_value > sval) + else if (smin1 > smax2) return 0; break; } @@ -6328,96 +15352,99 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) return -1; } +static int flip_opcode(u32 opcode) +{ + /* How can we transform "a <op> b" into "b <op> a"? */ + static const u8 opcode_flip[16] = { + /* these stay the same */ + [BPF_JEQ >> 4] = BPF_JEQ, + [BPF_JNE >> 4] = BPF_JNE, + [BPF_JSET >> 4] = BPF_JSET, + /* these swap "lesser" and "greater" (L and G in the opcodes) */ + [BPF_JGE >> 4] = BPF_JLE, + [BPF_JGT >> 4] = BPF_JLT, + [BPF_JLE >> 4] = BPF_JGE, + [BPF_JLT >> 4] = BPF_JGT, + [BPF_JSGE >> 4] = BPF_JSLE, + [BPF_JSGT >> 4] = BPF_JSLT, + [BPF_JSLE >> 4] = BPF_JSGE, + [BPF_JSLT >> 4] = BPF_JSGT + }; + return opcode_flip[opcode >> 4]; +} -static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) +static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg, + u8 opcode) { - s64 sval = (s64)val; + struct bpf_reg_state *pkt; + + if (src_reg->type == PTR_TO_PACKET_END) { + pkt = dst_reg; + } else if (dst_reg->type == PTR_TO_PACKET_END) { + pkt = src_reg; + opcode = flip_opcode(opcode); + } else { + return -1; + } + + if (pkt->range >= 0) + return -1; 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); - break; - case BPF_JSET: - if ((~reg->var_off.mask & reg->var_off.value) & val) - return 1; - if (!((reg->var_off.mask | reg->var_off.value) & val)) - return 0; - break; + case BPF_JLE: + /* pkt <= pkt_end */ + fallthrough; case BPF_JGT: - if (reg->umin_value > val) - return 1; - else if (reg->umax_value <= val) - return 0; - break; - case BPF_JSGT: - if (reg->smin_value > sval) - return 1; - else if (reg->smax_value < sval) - return 0; + /* pkt > pkt_end */ + if (pkt->range == BEYOND_PKT_END) + /* pkt has at last one extra byte beyond pkt_end */ + return opcode == BPF_JGT; break; case BPF_JLT: - if (reg->umax_value < val) - return 1; - else if (reg->umin_value >= val) - return 0; - break; - case BPF_JSLT: - if (reg->smax_value < sval) - return 1; - else if (reg->smin_value >= sval) - return 0; - break; + /* pkt < pkt_end */ + fallthrough; case BPF_JGE: - if (reg->umin_value >= val) - return 1; - else if (reg->umax_value < val) - return 0; - break; - case BPF_JSGE: - if (reg->smin_value >= sval) - return 1; - else if (reg->smax_value < sval) - return 0; - break; - case BPF_JLE: - if (reg->umax_value <= val) - return 1; - else if (reg->umin_value > val) - return 0; - break; - case BPF_JSLE: - if (reg->smax_value <= sval) - return 1; - else if (reg->smin_value > sval) - return 0; + /* pkt >= pkt_end */ + if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END) + return opcode == BPF_JGE; break; } - return -1; } -/* compute branch direction of the expression "if (reg opcode val) goto target;" +/* 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 (reg < 5)" is unknown when register value + * -1 - unknown. Example: "if (reg1 < 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) +static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, + u8 opcode, bool is_jmp32) { - if (__is_pointer_value(false, reg)) { - if (!reg_type_not_null(reg->type)) + 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; @@ -6431,293 +15458,279 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, } } - if (is_jmp32) - return is_branch32_taken(reg, val, opcode); - return is_branch64_taken(reg, val, opcode); + /* now deal with two scalars, but not necessarily constants */ + return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32); } -/* 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. +/* Opcode that corresponds to a *false* branch condition. + * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2 */ -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 u8 rev_opcode(u8 opcode) +{ + switch (opcode) { + 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) { + 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 { + 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: - { - struct bpf_reg_state *reg = - opcode == BPF_JEQ ? true_reg : false_reg; + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; - /* For BPF_JEQ, if this is false we know nothing Jon Snow, but - * if it is true we know the value for sure. Likewise for - * BPF_JNE. + /* try to recompute the bound of reg1 if reg2 is a const and + * is exactly the edge of reg1. */ - if (is_jmp32) - __mark_reg32_known(reg, val32); - else - __mark_reg_known(reg, val); + val = reg_const_value(reg2, is_jmp32); + if (is_jmp32) { + /* 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 { + if (reg1->umin_value == (u64)val) + reg1->umin_value++; + if (reg1->umax_value == (u64)val) + reg1->umax_value--; + if (reg1->smin_value == (s64)val) + reg1->smin_value++; + if (reg1->smax_value == (s64)val) + reg1->smax_value--; + } break; - } case BPF_JSET: + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + val = reg_const_value(reg2, is_jmp32); + /* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X) + * requires single bit to learn something useful. E.g., if we + * know that `r1 & 0x3` is true, then which bits (0, 1, or both) + * are actually set? We can learn something definite only if + * it's a single-bit value to begin with. + * + * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have + * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor + * bit 1 is set, which we can readily use in adjustments. + */ + if (!is_power_of_2(val)) + break; if (is_jmp32) { - false_32off = tnum_and(false_32off, tnum_const(~val32)); - if (is_power_of_2(val32)) - true_32off = tnum_or(true_32off, - tnum_const(val32)); + t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { - false_64off = tnum_and(false_64off, tnum_const(~val)); - if (is_power_of_2(val)) - true_64off = tnum_or(true_64off, - tnum_const(val)); + reg1->var_off = tnum_or(reg1->var_off, tnum_const(val)); } break; - case BPF_JGE: - case BPF_JGT: - { + case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */ + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + val = reg_const_value(reg2, is_jmp32); if (is_jmp32) { - u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1; - u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32; - - false_reg->u32_max_value = min(false_reg->u32_max_value, - false_umax); - true_reg->u32_min_value = max(true_reg->u32_min_value, - true_umin); + t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val)); + reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { - u64 false_umax = opcode == BPF_JGT ? val : val - 1; - u64 true_umin = opcode == BPF_JGT ? val + 1 : val; - - false_reg->umax_value = min(false_reg->umax_value, false_umax); - true_reg->umin_value = max(true_reg->umin_value, true_umin); + reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val)); } break; - } - case BPF_JSGE: - case BPF_JSGT: - { + case BPF_JLE: if (is_jmp32) { - s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1; - s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32; - - false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax); - true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); + reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); } else { - s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; - s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; - - false_reg->smax_value = min(false_reg->smax_value, false_smax); - true_reg->smin_value = max(true_reg->smin_value, true_smin); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value); + reg2->umin_value = max(reg1->umin_value, reg2->umin_value); } break; - } - case BPF_JLE: case BPF_JLT: - { if (is_jmp32) { - u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1; - u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32; - - false_reg->u32_min_value = max(false_reg->u32_min_value, - false_umin); - true_reg->u32_max_value = min(true_reg->u32_max_value, - true_umax); + reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1); + reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value); } else { - u64 false_umin = opcode == BPF_JLT ? val : val + 1; - u64 true_umax = opcode == BPF_JLT ? val - 1 : val; - - false_reg->umin_value = max(false_reg->umin_value, false_umin); - true_reg->umax_value = min(true_reg->umax_value, true_umax); + reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1); + reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value); } break; - } case BPF_JSLE: + if (is_jmp32) { + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); + reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); + } else { + reg1->smax_value = min(reg1->smax_value, reg2->smax_value); + reg2->smin_value = max(reg1->smin_value, reg2->smin_value); + } + break; case BPF_JSLT: - { if (is_jmp32) { - s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1; - s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32; - - false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin); - true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax); + reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1); + reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value); } else { - s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; - s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; - - false_reg->smin_value = max(false_reg->smin_value, false_smin); - true_reg->smax_value = min(true_reg->smax_value, true_smax); + reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1); + reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value); } break; - } 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) { - /* How can we transform "a <op> b" into "b <op> a"? */ - static const u8 opcode_flip[16] = { - /* these stay the same */ - [BPF_JEQ >> 4] = BPF_JEQ, - [BPF_JNE >> 4] = BPF_JNE, - [BPF_JSET >> 4] = BPF_JSET, - /* these swap "lesser" and "greater" (L and G in the opcodes) */ - [BPF_JGE >> 4] = BPF_JLE, - [BPF_JGT >> 4] = BPF_JLT, - [BPF_JLE >> 4] = BPF_JGE, - [BPF_JLT >> 4] = BPF_JGT, - [BPF_JSGE >> 4] = BPF_JSLE, - [BPF_JSGT >> 4] = BPF_JSLT, - [BPF_JSLE >> 4] = BPF_JSGE, - [BPF_JSLT >> 4] = BPF_JSGT - }; - opcode = opcode_flip[opcode >> 4]; - /* This uses zero as "not present in table"; luckily the zero opcode, - * BPF_JA, can't get here. - */ - 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); - /* We might have learned new bounds from the var_off. */ - __update_reg_bounds(src_reg); - __update_reg_bounds(dst_reg); - /* We might have learned something about the sign bit. */ - __reg_deduce_bounds(src_reg); - __reg_deduce_bounds(dst_reg); - /* We might have learned some bits from the bounds. */ - __reg_bound_offset(src_reg); - __reg_bound_offset(dst_reg); - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. + 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). */ - __update_reg_bounds(src_reg); - __update_reg_bounds(dst_reg); -} + if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE) + return 0; -static void reg_combine_min_max(struct bpf_reg_state *true_src, - struct bpf_reg_state *true_dst, - struct bpf_reg_state *false_src, - struct bpf_reg_state *false_dst, - u8 opcode) -{ - switch (opcode) { - case BPF_JEQ: - __reg_combine_min_max(true_src, true_dst); - break; - case BPF_JNE: - __reg_combine_min_max(false_src, false_dst); - break; - } + /* fallthrough (FALSE) branch */ + regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32); + reg_bounds_sync(false_reg1); + reg_bounds_sync(false_reg2); + + /* jump (TRUE) branch */ + regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32); + reg_bounds_sync(true_reg1); + reg_bounds_sync(true_reg2); + + err = reg_bounds_sanity_check(env, true_reg1, "true_reg1"); + err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2"); + err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1"); + err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2"); + return err; } static void mark_ptr_or_null_reg(struct bpf_func_state *state, struct bpf_reg_state *reg, u32 id, bool is_null) { - if (reg_type_may_be_null(reg->type) && reg->id == id) { - /* Old offset (both fixed and variable parts) should - * have been known-zero, because we don't allow pointer - * arithmetic on pointers that might be NULL. + if (type_may_be_null(reg->type) && reg->id == id && + (is_rcu_reg(reg) || !WARN_ON_ONCE(!reg->id))) { + /* Old offset (both fixed and variable parts) should have been + * known-zero, because we don't allow pointer arithmetic on + * pointers that might be NULL. If we see this happening, don't + * convert the register. + * + * But in some cases, some helpers that return local kptrs + * advance offset for the returned pointer. In those cases, it + * is fine to expect to see reg->off. */ - if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || - !tnum_equals_const(reg->var_off, 0) || - reg->off)) { - __mark_reg_known_zero(reg); - reg->off = 0; - } + if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0))) + return; + 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; - } else if (reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - const struct bpf_map *map = reg->map_ptr; - - if (map->inner_map_meta) { - reg->type = CONST_PTR_TO_MAP; - reg->map_ptr = map->inner_map_meta; - } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { - reg->type = PTR_TO_XDP_SOCK; - } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || - map->map_type == BPF_MAP_TYPE_SOCKHASH) { - reg->type = PTR_TO_SOCKET; - } else { - reg->type = PTR_TO_MAP_VALUE; - } - } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { - reg->type = PTR_TO_SOCKET; - } else if (reg->type == PTR_TO_SOCK_COMMON_OR_NULL) { - reg->type = PTR_TO_SOCK_COMMON; - } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { - reg->type = PTR_TO_TCP_SOCK; - } else if (reg->type == PTR_TO_BTF_ID_OR_NULL) { - reg->type = PTR_TO_BTF_ID; - } else if (reg->type == PTR_TO_MEM_OR_NULL) { - reg->type = PTR_TO_MEM; - } - if (is_null) { /* We don't need id and ref_obj_id from this point * onwards anymore, thus we should better reset it, * so that state pruning has chances to take effect. */ reg->id = 0; reg->ref_obj_id = 0; - } else if (!reg_may_point_to_spin_lock(reg)) { + + return; + } + + mark_ptr_not_null_reg(reg); + + if (!reg_may_point_to_spin_lock(reg)) { /* For not-NULL ptr, reg->ref_obj_id will be reset - * in release_reg_references(). + * in release_reference(). * * reg->id is still used by spin_lock ptr. Other * than spin_lock ptr type, reg->id can be reset. @@ -6727,22 +15740,6 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } } -static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id, - bool is_null) -{ - struct bpf_reg_state *reg; - int i; - - for (i = 0; i < MAX_BPF_REG; i++) - mark_ptr_or_null_reg(state, &state->regs[i], id, is_null); - - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - mark_ptr_or_null_reg(state, reg, id, is_null); - } -} - /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ @@ -6750,20 +15747,20 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *regs = state->regs, *reg; u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; - int i; if (ref_obj_id && ref_obj_id == id && is_null) /* regs[regno] is in the " == NULL" branch. * 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)); - for (i = 0; i <= vstate->curframe; i++) - __mark_ptr_or_null_regs(vstate->frame[i], id, is_null); + bpf_for_each_reg_in_vstate(vstate, state, reg, ({ + mark_ptr_or_null_reg(state, reg, id, is_null); + })); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, @@ -6788,6 +15785,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' > pkt_end, pkt_meta' > pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, false); + mark_pkt_end(other_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -6795,6 +15793,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end > pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, true); + mark_pkt_end(this_branch, insn->src_reg, false); } else { return false; } @@ -6807,6 +15806,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' < pkt_end, pkt_meta' < pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, true); + mark_pkt_end(this_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -6814,6 +15814,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end < pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, false); + mark_pkt_end(other_branch, insn->src_reg, true); } else { return false; } @@ -6826,6 +15827,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, true); + mark_pkt_end(other_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -6833,6 +15835,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, false); + mark_pkt_end(this_branch, insn->src_reg, true); } else { return false; } @@ -6845,6 +15848,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, false); + mark_pkt_end(this_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && @@ -6852,6 +15856,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, true); + mark_pkt_end(other_branch, insn->src_reg, false); } else { return false; } @@ -6863,6 +15868,99 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, return true; } +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 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; + + 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, struct bpf_insn *insn, int *insn_idx) { @@ -6870,17 +15968,49 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_verifier_state *other_branch; 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); 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 (!queued_st) + return -ENOMEM; + + 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"); @@ -6892,110 +16022,156 @@ 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]; } 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 (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); - } - + 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. */ if (!__is_pointer_value(false, dst_reg)) err = mark_chain_precision(env, insn->dst_reg); - if (BPF_SRC(insn->code) == BPF_X && !err) + if (BPF_SRC(insn->code) == BPF_X && !err && + !__is_pointer_value(false, src_reg)) err = mark_chain_precision(env, insn->src_reg); if (err) return err; } + if (pred == 1) { - /* only follow the goto, ignore fall-through */ + /* Only follow the goto, ignore fall-through. If needed, push + * 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->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch, this_branch->curframe); *insn_idx += insn->off; return 0; } else if (pred == 0) { - /* only follow fall-through branch, since - * that's where the program will go + /* Only follow the fall-through branch, since that's where the + * 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->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch, this_branch->curframe); return 0; } + /* 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_insn_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 (!other_branch) return -EFAULT; other_branch_regs = other_branch->frame[other_branch->curframe]->regs; - /* detect if we are comparing against a constant value so we can adjust - * our min/max values for our dst register. - * this is only legit if both are scalars (or pointers to the same - * object, I suppose, but we don't support that right now), 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); - } - } 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)) { + 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 + * register check if PTR_MAYBE_NULL could be lifted. + * E.g. register A - maybe null + * register B - not null + * for JNE A, B, ... - A is not null in the false branch; + * for JEQ A, B, ... - A is not null in the true branch. + * + * Since PTR_TO_BTF_ID points to a kernel struct that does + * not need to be null checked by the BPF program, i.e., + * could be null even without PTR_MAYBE_NULL marking, so + * only propagate nullness when neither reg is that type. + */ + if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X && + __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) && + type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) && + base_type(src_reg->type) != PTR_TO_BTF_ID && + base_type(dst_reg->type) != PTR_TO_BTF_ID) { + eq_branch_regs = NULL; + switch (opcode) { + case BPF_JEQ: + eq_branch_regs = other_branch_regs; + break; + case BPF_JNE: + eq_branch_regs = regs; + break; + default: + /* do nothing */ + break; + } + if (eq_branch_regs) { + if (type_may_be_null(src_reg->type)) + mark_ptr_not_null_reg(&eq_branch_regs[insn->src_reg]); + else + mark_ptr_not_null_reg(&eq_branch_regs[insn->dst_reg]); + } } /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). @@ -7004,7 +16180,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && - reg_type_may_be_null(dst_reg->type)) { + type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ @@ -7020,7 +16196,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, this_branch->frame[this_branch->curframe]); + print_insn_state(env, this_branch, this_branch->curframe); return 0; } @@ -7029,6 +16205,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *dst_reg; struct bpf_map *map; int err; @@ -7045,25 +16222,73 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + dst_reg = ®s[insn->dst_reg]; if (insn->src_reg == 0) { u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - regs[insn->dst_reg].type = SCALAR_VALUE; + dst_reg->type = SCALAR_VALUE; __mark_reg_known(®s[insn->dst_reg], imm); return 0; } - map = env->used_maps[aux->map_index]; + /* All special src_reg cases are listed below. From this point onwards + * we either succeed and assign a corresponding dst_reg->type after + * zeroing the offset, or fail and reject the program. + */ mark_reg_known_zero(env, regs, insn->dst_reg); - regs[insn->dst_reg].map_ptr = map; - - if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) { - regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; - regs[insn->dst_reg].off = aux->map_off; - if (map_value_has_spin_lock(map)) - regs[insn->dst_reg].id = ++env->id_gen; - } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { - regs[insn->dst_reg].type = CONST_PTR_TO_MAP; + + if (insn->src_reg == BPF_PSEUDO_BTF_ID) { + dst_reg->type = aux->btf_var.reg_type; + switch (base_type(dst_reg->type)) { + case PTR_TO_MEM: + dst_reg->mem_size = aux->btf_var.mem_size; + break; + case PTR_TO_BTF_ID: + dst_reg->btf = aux->btf_var.btf; + dst_reg->btf_id = aux->btf_var.btf_id; + break; + default: + verbose(env, "bpf verifier is misconfigured\n"); + return -EFAULT; + } + return 0; + } + + if (insn->src_reg == BPF_PSEUDO_FUNC) { + struct bpf_prog_aux *aux = env->prog->aux; + u32 subprogno = find_subprog(env, + env->insn_idx + insn->imm + 1); + + if (!aux->func_info) { + verbose(env, "missing btf func_info\n"); + return -EINVAL; + } + if (aux->func_info_aux[subprogno].linkage != BTF_FUNC_STATIC) { + verbose(env, "callback function not static\n"); + return -EINVAL; + } + + dst_reg->type = PTR_TO_FUNC; + dst_reg->subprogno = subprogno; + return 0; + } + + map = env->used_maps[aux->map_index]; + dst_reg->map_ptr = map; + + 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); + /* 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; @@ -7106,7 +16331,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) u8 mode = BPF_MODE(insn->code); int i, err; - if (!may_access_skb(env->prog->type)) { + if (!may_access_skb(resolve_prog_type(env->prog))) { verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } @@ -7116,18 +16341,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (env->subprog_cnt > 1) { - /* when program has LD_ABS insn JITs and interpreter assume - * that r1 == ctx == skb which is not the case for callees - * that can have arbitrary arguments. It's problematic - * for main prog as well since JITs would need to analyze - * all functions in order to make proper register save/restore - * decisions in the main prog. Hence disallow LD_ABS with calls - */ - verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n"); - return -EINVAL; - } - if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { @@ -7144,16 +16357,9 @@ 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_spin_lock) { - verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); - return -EINVAL; - } if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, @@ -7168,7 +16374,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } - err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; @@ -7188,48 +16394,88 @@ 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_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; /* LSM and struct_ops func-ptr's return type could be "void" */ - if ((env->prog->type == BPF_PROG_TYPE_STRUCT_OPS || - env->prog->type == BPF_PROG_TYPE_LSM) && - !prog->aux->attach_func_proto->type) - return 0; + 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; + case BPF_PROG_TYPE_STRUCT_OPS: + if (!prog->aux->attach_func_proto->type) + return 0; + break; + default: + break; + } + } - /* eBPF calling convetion is such that R0 is used + /* eBPF calling convention is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time * 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; } - switch (env->prog->type) { + reg = cur_regs(env) + regno; + + if (frame->in_async_callback_fn) { + /* enforce return zero from async callbacks like timer */ + exit_ctx = "At async callback return"; + range = retval_range(0, 0); + goto enforce_retval; + } + + if (is_subprog && !frame->in_exception_callback_fn) { + if (reg->type != SCALAR_VALUE) { + 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; + } + + switch (prog_type) { 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 = 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; @@ -7242,13 +16488,13 @@ 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: @@ -7259,6 +16505,40 @@ 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 = retval_range(SK_DROP, SK_PASS); + break; + + case BPF_PROG_TYPE_LSM: + if (env->prog->expected_attach_type != BPF_LSM_CGROUP) { + /* 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 = retval_range(1, 1); + } + break; + + case BPF_PROG_TYPE_NETFILTER: + range = retval_range(NF_DROP, NF_ACCEPT); + 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. @@ -7267,25 +16547,24 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; } - reg = cur_regs(env) + BPF_REG_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[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)) { - char tn_buf[48]; + err = mark_chain_precision(env, regno); + if (err) + return err; - verbose(env, "At program exit the register R0 "); - 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"); - } - tnum_strn(tn_buf, sizeof(tn_buf), range); - verbose(env, " should have been in %s\n", tn_buf); + 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"); return -EINVAL; } @@ -7295,13 +16574,36 @@ 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 = find_containing_subprog(env, off); + subprog->changes_pkt_data = 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 = find_containing_subprog(env, t); + callee = find_containing_subprog(env, w); + caller->changes_pkt_data |= callee->changes_pkt_data; +} + /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered * 3 let S be a stack * 4 S.push(v) * 5 while S is not empty - * 6 t <- S.pop() + * 6 t <- S.peek() * 7 if t is what we're looking for: * 8 return t * 9 for all edges e in G.adjacentEdges(t) do @@ -7335,42 +16637,56 @@ 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 init_explored_state(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 void mark_calls_callback(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].calls_callback = true; +} + +static bool calls_callback(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].calls_callback; +} + +enum { + DONE_EXPLORING = 0, + KEEP_EXPLORING = 1, +}; + /* t, w, e - match pseudo-code above: * t - index of current instruction * 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; if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) - return 0; + return DONE_EXPLORING; if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) - return 0; + return DONE_EXPLORING; if (w < 0 || w >= env->prog->len) { verbose_linfo(env, t, "%d: ", t); @@ -7378,9 +16694,11 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, return -EINVAL; } - if (e == BRANCH) + if (e == BRANCH) { /* mark branch target for state pruning */ - init_explored_state(env, w); + mark_prune_point(env, w); + mark_jmp_point(env, w); + } if (insn_state[w] == 0) { /* tree-edge */ @@ -7389,10 +16707,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; - return 1; + return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { - if (loop_ok && env->bpf_capable) - return 0; + if (env->bpf_capable) + return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); @@ -7404,19 +16722,412 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, verbose(env, "insn state internal bug\n"); return -EFAULT; } + return DONE_EXPLORING; +} + +static int visit_func_call_insn(int t, struct bpf_insn *insns, + struct bpf_verifier_env *env, + bool visit_callee) +{ + int ret, insn_sz; + int w; + + 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 + insn_sz); + /* when we exit from subprog, we need to record non-linear history */ + mark_jmp_point(env, t + insn_sz); + + if (visit_callee) { + w = t + insns[t].imm + 1; + mark_prune_point(env, 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) + +/* Return a bitmask specifying which caller saved registers are + * clobbered by a call to a helper *as if* this helper follows + * bpf_fastcall contract: + * - includes R0 if function is non-void; + * - includes R1-R5 if corresponding parameter has is described + * in the function prototype. + */ +static u32 helper_fastcall_clobber_mask(const struct bpf_func_proto *fn) +{ + u32 mask; + int i; + + mask = 0; + if (fn->ret_type != RET_VOID) + mask |= BIT(BPF_REG_0); + for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i) + if (fn->arg_type[i] != ARG_DONTCARE) + mask |= BIT(BPF_REG_1 + i); + return mask; +} + +/* 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; + } +} + +/* Same as helper_fastcall_clobber_mask() but for kfuncs, see comment above */ +static u32 kfunc_fastcall_clobber_mask(struct bpf_kfunc_call_arg_meta *meta) +{ + u32 vlen, i, mask; + + vlen = btf_type_vlen(meta->func_proto); + mask = 0; + if (!btf_type_is_void(btf_type_by_id(meta->btf, meta->func_proto->type))) + mask |= BIT(BPF_REG_0); + for (i = 0; i < vlen; ++i) + mask |= BIT(BPF_REG_1 + i); + return mask; +} + +/* Same as verifier_inlines_helper_call() but for kfuncs, see comment above */ +static bool is_fastcall_kfunc_call(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_FASTCALL; +} + +/* 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]; + const struct bpf_func_proto *fn; + u32 clobbered_regs_mask = ALL_CALLER_SAVED_REGS; + u32 expected_regs_mask; + bool can_be_inlined = false; + s16 off; + int i; + + if (bpf_helper_call(call)) { + if (get_helper_proto(env, call->imm, &fn) < 0) + /* error would be reported later */ + return; + clobbered_regs_mask = helper_fastcall_clobber_mask(fn); + can_be_inlined = fn->allow_fastcall && + (verifier_inlines_helper_call(env, call->imm) || + bpf_jit_inlines_helper_call(call->imm)); + } + + if (bpf_pseudo_kfunc_call(call)) { + struct bpf_kfunc_call_arg_meta meta; + int err; + + err = fetch_kfunc_meta(env, call, &meta, NULL); + if (err < 0) + /* error would be reported later */ + return; + + clobbered_regs_mask = kfunc_fastcall_clobber_mask(&meta); + can_be_inlined = is_fastcall_kfunc_call(&meta); + } + + if (clobbered_regs_mask == ALL_CALLER_SAVED_REGS) + return; + + /* 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 (can_be_inlined) + 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; } +/* Visits the instruction at index t and returns one of the following: + * < 0 - an error occurred + * DONE_EXPLORING - the instruction was fully explored + * KEEP_EXPLORING - there is still work to be done before it is fully explored + */ +static int visit_insn(int t, struct bpf_verifier_env *env) +{ + struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; + int ret, off, insn_sz; + + 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(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(insn->code)) { + case BPF_EXIT: + return DONE_EXPLORING; + + case BPF_CALL: + 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); + /* 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) && bpf_helper_changes_pkt_data(insn->imm)) + mark_subprog_changes_pkt_data(env, t); + 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); + } + } + return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); + + case BPF_JA: + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + + if (BPF_CLASS(insn->code) == BPF_JMP) + off = insn->off; + else + off = insn->imm; + + /* unconditional jump with single edge */ + ret = push_insn(t, t + off + 1, FALLTHROUGH, env); + if (ret) + return ret; + + 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); + if (ret) + return ret; + + return push_insn(t, t + insn->off + 1, BRANCH, env); + } +} + /* non-recursive depth-first-search to detect loops in BPF program * loop == back-edge in directed graph */ static int check_cfg(struct bpf_verifier_env *env) { - struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; int *insn_stack, *insn_state; - int ret = 0; - int i, t; + int ex_insn_beg, i, ret = 0; + bool ex_done = false; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) @@ -7432,100 +17143,62 @@ static int check_cfg(struct bpf_verifier_env *env) insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; -peek_stack: - if (env->cfg.cur_stack == 0) - goto check_state; - t = insn_stack[env->cfg.cur_stack - 1]; +walk_cfg: + while (env->cfg.cur_stack > 0) { + int t = insn_stack[env->cfg.cur_stack - 1]; - if (BPF_CLASS(insns[t].code) == BPF_JMP || - BPF_CLASS(insns[t].code) == BPF_JMP32) { - u8 opcode = BPF_OP(insns[t].code); - - if (opcode == BPF_EXIT) { - goto mark_explored; - } else if (opcode == BPF_CALL) { - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); - if (insns[t].src_reg == BPF_PSEUDO_CALL) { - init_explored_state(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, - env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - } - } else if (opcode == BPF_JA) { - if (BPF_SRC(insns[t].code) != BPF_K) { - ret = -EINVAL; - goto err_free; + ret = visit_insn(t, env); + switch (ret) { + case DONE_EXPLORING: + insn_state[t] = EXPLORED; + env->cfg.cur_stack--; + break; + case KEEP_EXPLORING: + break; + default: + if (ret > 0) { + verbose(env, "visit_insn internal bug\n"); + ret = -EFAULT; } - /* unconditional jump with single edge */ - ret = push_insn(t, t + insns[t].off + 1, - FALLTHROUGH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - /* unconditional jmp is not a good pruning point, - * but it's marked, since backtracking needs - * to record jmp history in is_state_visited(). - */ - init_explored_state(env, t + insns[t].off + 1); - /* tell verifier to check for equivalent states - * after every call and jump - */ - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); - } else { - /* conditional jump with two edges */ - init_explored_state(env, t); - ret = push_insn(t, t + 1, FALLTHROUGH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - - ret = push_insn(t, t + insns[t].off + 1, BRANCH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - } - } else { - /* all other non-branch instructions with single - * fall-through edge - */ - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) goto err_free; + } } -mark_explored: - insn_state[t] = EXPLORED; - if (env->cfg.cur_stack-- <= 0) { + if (env->cfg.cur_stack < 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } - goto peek_stack; -check_state: + if (env->exception_callback_subprog && !ex_done) { + ex_insn_beg = env->subprog_info[env->exception_callback_subprog].start; + + insn_state[ex_insn_beg] = DISCOVERED; + insn_stack[0] = ex_insn_beg; + env->cfg.cur_stack = 1; + ex_done = true; + 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; err_free: kvfree(insn_state); @@ -7534,32 +17207,46 @@ err_free: return ret; } +static int check_abnormal_return(struct bpf_verifier_env *env) +{ + int i; + + for (i = 1; i < env->subprog_cnt; i++) { + if (env->subprog_info[i].has_ld_abs) { + verbose(env, "LD_ABS is not allowed in subprogs without BTF\n"); + return -EINVAL; + } + if (env->subprog_info[i].has_tail_call) { + verbose(env, "tail_call is not allowed in subprogs without BTF\n"); + return -EINVAL; + } + } + return 0; +} + /* The minimum supported BTF func info size */ #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, - union bpf_attr __user *uattr) +static int check_btf_func_early(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) { - 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; - const struct btf_type *type; struct bpf_prog *prog; const struct btf *btf; - void __user *urecord; u32 prev_offset = 0; + bpfptr_t urecord; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; - if (!nfuncs) + 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; @@ -7573,15 +17260,12 @@ static int check_btf_func(struct bpf_verifier_env *env, prog = env->prog; btf = prog->aux->btf; - urecord = u64_to_user_ptr(attr->func_info); + 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); 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); @@ -7591,37 +17275,32 @@ static int check_btf_func(struct bpf_verifier_env *env, /* set the size kernel expects so loader can zero * out the rest of the record. */ - if (put_user(min_size, &uattr->func_info_rec_size)) + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, func_info_rec_size), + &min_size, sizeof(min_size))) ret = -EFAULT; } goto err_free; } - if (copy_from_user(&krecord[i], urecord, min_size)) { + if (copy_from_bpfptr(&krecord[i], urecord, min_size)) { ret = -EFAULT; goto err_free; } /* check insn_off */ + ret = -EINVAL; if (i == 0) { if (krecord[i].insn_off) { verbose(env, "nonzero insn_off %u for the first func info record", krecord[i].insn_off); - ret = -EINVAL; goto err_free; } } else if (krecord[i].insn_off <= prev_offset) { verbose(env, "same or smaller insn offset (%u) than previous func info record (%u)", krecord[i].insn_off, prev_offset); - ret = -EINVAL; - 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"); - ret = -EINVAL; goto err_free; } @@ -7630,21 +17309,98 @@ static int check_btf_func(struct bpf_verifier_env *env, if (!type || !btf_type_is_func(type)) { verbose(env, "invalid type id %d in func info", krecord[i].type_id); - ret = -EINVAL; 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; - urecord += urec_size; + 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); + 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 | __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); + if (i && !scalar_return && env->subprog_info[i].has_ld_abs) { + verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n"); + goto err_free; + } + if (i && !scalar_return && env->subprog_info[i].has_tail_call) { + verbose(env, "tail_call is only allowed in functions that return 'int'.\n"); + goto err_free; + } + + bpfptr_add(&urecord, urec_size); + } + + prog->aux->func_info_aux = info_aux; + return 0; + +err_free: kfree(info_aux); return ret; } @@ -7657,29 +17413,31 @@ 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; } -#define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \ - sizeof(((struct bpf_line_info *)(0))->line_col)) +#define MIN_BPF_LINEINFO_SIZE offsetofend(struct bpf_line_info, line_col) #define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE static int check_btf_line(struct bpf_verifier_env *env, const union bpf_attr *attr, - union bpf_attr __user *uattr) + bpfptr_t uattr) { u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; struct bpf_subprog_info *sub; struct bpf_line_info *linfo; struct bpf_prog *prog; const struct btf *btf; - void __user *ulinfo; + bpfptr_t ulinfo; int err; nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; + if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info)) + return -EINVAL; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || @@ -7700,7 +17458,7 @@ static int check_btf_line(struct bpf_verifier_env *env, s = 0; sub = env->subprog_info; - ulinfo = u64_to_user_ptr(attr->line_info); + ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel); expected_size = sizeof(struct bpf_line_info); ncopy = min_t(u32, expected_size, rec_size); for (i = 0; i < nr_linfo; i++) { @@ -7708,14 +17466,15 @@ static int check_btf_line(struct bpf_verifier_env *env, if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in line_info"); - if (put_user(expected_size, - &uattr->line_info_rec_size)) + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, line_info_rec_size), + &expected_size, sizeof(expected_size))) err = -EFAULT; } goto err_free; } - if (copy_from_user(&linfo[i], ulinfo, ncopy)) { + if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) { err = -EFAULT; goto err_free; } @@ -7767,7 +17526,7 @@ static int check_btf_line(struct bpf_verifier_env *env, } prev_offset = linfo[i].insn_off; - ulinfo += rec_size; + bpfptr_add(&ulinfo, rec_size); } if (s != env->subprog_cnt) { @@ -7787,21 +17546,118 @@ err_free: return err; } -static int check_btf_info(struct bpf_verifier_env *env, - const union bpf_attr *attr, - union bpf_attr __user *uattr) +#define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) +#define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE + +static int check_core_relo(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + u32 i, nr_core_relo, ncopy, expected_size, rec_size; + struct bpf_core_relo core_relo = {}; + struct bpf_prog *prog = env->prog; + const struct btf *btf = prog->aux->btf; + struct bpf_core_ctx ctx = { + .log = &env->log, + .btf = btf, + }; + bpfptr_t u_core_relo; + int err; + + nr_core_relo = attr->core_relo_cnt; + if (!nr_core_relo) + return 0; + if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) + return -EINVAL; + + rec_size = attr->core_relo_rec_size; + if (rec_size < MIN_CORE_RELO_SIZE || + rec_size > MAX_CORE_RELO_SIZE || + rec_size % sizeof(u32)) + return -EINVAL; + + u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); + expected_size = sizeof(struct bpf_core_relo); + ncopy = min_t(u32, expected_size, rec_size); + + /* Unlike func_info and line_info, copy and apply each CO-RE + * relocation record one at a time. + */ + for (i = 0; i < nr_core_relo; i++) { + /* future proofing when sizeof(bpf_core_relo) changes */ + err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); + if (err) { + if (err == -E2BIG) { + verbose(env, "nonzero tailing record in core_relo"); + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, core_relo_rec_size), + &expected_size, sizeof(expected_size))) + err = -EFAULT; + } + break; + } + + if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { + err = -EFAULT; + break; + } + + if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { + verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", + i, core_relo.insn_off, prog->len); + err = -EINVAL; + break; + } + + err = bpf_core_apply(&ctx, &core_relo, i, + &prog->insnsi[core_relo.insn_off / 8]); + if (err) + break; + bpfptr_add(&u_core_relo, rec_size); + } + return err; +} + +static int check_btf_info_early(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) { struct btf *btf; int err; - if (!attr->func_info_cnt && !attr->line_info_cnt) + if (!attr->func_info_cnt && !attr->line_info_cnt) { + if (check_abnormal_return(env)) + return -EINVAL; return 0; + } btf = btf_get_by_fd(attr->prog_btf_fd); if (IS_ERR(btf)) return PTR_ERR(btf); + if (btf_is_kernel(btf)) { + btf_put(btf); + return -EACCES; + } 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; @@ -7810,26 +17666,27 @@ static int check_btf_info(struct bpf_verifier_env *env, if (err) return err; + err = check_core_relo(env, attr, uattr); + if (err) + return err; + return 0; } /* 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 && old->smin_value <= cur->smin_value && - old->smax_value >= cur->smax_value; + old->smax_value >= cur->smax_value && + old->u32_min_value <= cur->u32_min_value && + old->u32_max_value >= cur->u32_max_value && + old->s32_min_value <= cur->s32_min_value && + old->s32_max_value >= cur->s32_max_value; } -/* Maximum number of register states that can exist at once */ -#define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) -struct idpair { - u32 old; - u32 cur; -}; - /* If in the old state two registers had the same id, then they need to have * the same id in the new state as well. But that id could be different from * the old state, so we need to track the mapping from old to new ids. @@ -7840,25 +17697,47 @@ struct idpair { * 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 idpair *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; - for (i = 0; i < ID_MAP_SIZE; i++) { - if (!idmap[i].old) { + /* 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 (!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) { @@ -7921,7 +17800,7 @@ static void clean_verifier_state(struct bpf_verifier_env *env, * 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 markes are already propagated. + * 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' @@ -7937,98 +17816,133 @@ 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; sl = *explored_state(env, insn); while (sl) { if (sl->state.branches) goto next; if (sl->state.insn_idx != insn || - sl->state.curframe != cur->curframe) + !same_callsites(&sl->state, cur)) goto next; - for (i = 0; i <= cur->curframe; i++) - if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) - goto next; clean_verifier_state(env, &sl->state); next: sl = sl->next; } } -/* Returns true if (rold safe implies rcur safe) */ -static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, - struct idpair *idmap) +static bool regs_exact(const struct bpf_reg_state *rold, + const struct bpf_reg_state *rcur, + struct bpf_idmap *idmap) { - bool equal; - - if (!(rold->live & REG_LIVE_READ)) - /* explored state didn't use this */ - return true; + 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); +} - equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; +enum exact_level { + NOT_EXACT, + EXACT, + RANGE_WITHIN +}; - if (rold->type == PTR_TO_STACK) - /* two stack pointers are equal only if they're pointing to - * the same stack frame, since fp-8 in foo != fp-8 in bar - */ - return equal && rold->frameno == rcur->frameno; +/* 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_idmap *idmap, + enum exact_level exact) +{ + if (exact == EXACT) + return regs_exact(rold, rcur, idmap); - if (equal) + if (!(rold->live & REG_LIVE_READ) && exact == NOT_EXACT) + /* explored state didn't use this */ return true; + 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 (rold->type) { + + switch (base_type(rold->type)) { case SCALAR_VALUE: - if (rcur->type == SCALAR_VALUE) { - if (!rold->precise && !rcur->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 (env->explore_alu_limits) { + /* explore_alu_limits disables tnum_in() and range_within() + * logic and requires everything to be strict */ - return false; + 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 ((rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST)) + return false; + 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: + 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); - case PTR_TO_MAP_VALUE_OR_NULL: - /* 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 (rcur->type != PTR_TO_MAP_VALUE_OR_NULL) - 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); + tnum_in(rold->var_off, rcur->var_off) && + 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, @@ -8043,38 +17957,63 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, 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) && tnum_in(rold->var_off, rcur->var_off); - case PTR_TO_CTX: - case CONST_PTR_TO_MAP: - case PTR_TO_PACKET_END: - case PTR_TO_FLOW_KEYS: - case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: - case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: - case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: - case PTR_TO_XDP_SOCK: - /* Only valid matches are exact, which memcmp() above - * would have accepted + case PTR_TO_STACK: + /* two stack pointers are equal only if they're pointing to + * the same stack frame, since fp-8 in foo != fp-8 in bar */ + return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; + case PTR_TO_ARENA: + return true; default: - /* Don't know what's going on, just say it's not safe */ + return regs_exact(rold, rcur, idmap); + } +} + +static struct bpf_reg_state unbound_reg; + +static __init int unbound_reg_init(void) +{ + __mark_reg_unknown_imprecise(&unbound_reg); + unbound_reg.live |= REG_LIVE_READ; + 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; } - /* Shouldn't get here; if we do, say it's not safe */ - WARN_ON_ONCE(1); - return false; + return true; } -static bool stacksafe(struct bpf_func_state *old, - struct bpf_func_state *cur, - struct idpair *idmap) +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_idmap *idmap, + enum exact_level exact) { int i, spi; @@ -8083,9 +18022,18 @@ static bool stacksafe(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)) { + 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].spilled_ptr.live & REG_LIVE_READ) + && exact == NOT_EXACT) { i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; @@ -8094,12 +18042,30 @@ static bool stacksafe(struct bpf_func_state *old, 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 @@ -8110,18 +18076,16 @@ static bool stacksafe(struct bpf_func_state *old, if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) /* Ex: old explored (safe) state has STACK_SPILL in - * this stack slot, but current has has STACK_MISC -> + * this stack slot, but current has STACK_MISC -> * this verifier states are not equivalent, * return false to continue verification of this path */ return false; - if (i % BPF_REG_SIZE) + if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; - if (old->stack[spi].slot_type[0] != STACK_SPILL) - continue; - if (!regsafe(&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. @@ -8132,17 +18096,91 @@ static bool stacksafe(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)) + 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_lock != cur->active_rcu_lock) + return false; + + if (!check_ids(old->active_irq_id, cur->active_irq_id, idmap)) + 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: + 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 @@ -8171,50 +18209,53 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ -static bool func_states_equal(struct bpf_func_state *old, - struct bpf_func_state *cur) +static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, + struct bpf_func_state *cur, enum exact_level exact) { - struct idpair *idmap; - bool ret = false; int i; - idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL); - /* If we failed to allocate the idmap, just say it's not safe */ - if (!idmap) + if (old->callback_depth > cur->callback_depth) return false; - for (i = 0; i < MAX_BPF_REG; i++) { - if (!regsafe(&old->regs[i], &cur->regs[i], idmap)) - goto out_free; - } + for (i = 0; i < MAX_BPF_REG; i++) + if (!regsafe(env, &old->regs[i], &cur->regs[i], + &env->idmap_scratch, exact)) + return false; - if (!stacksafe(old, cur, idmap)) - goto out_free; + if (!stacksafe(env, old, cur, &env->idmap_scratch, exact)) + return false; - if (!refsafe(old, cur)) - goto out_free; - ret = true; -out_free: - kfree(idmap); - return ret; + 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) { int i; if (old->curframe != cur->curframe) return false; + reset_idmap_scratch(env); + /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. */ if (old->speculative && !cur->speculative) return false; - if (old->active_spin_lock != cur->active_spin_lock) + if (old->in_sleepable != cur->in_sleepable) + return false; + + if (!refsafe(old, cur, &env->idmap_scratch)) return false; /* for states to be equal callsites have to be the same @@ -8223,7 +18264,7 @@ static bool states_equal(struct bpf_verifier_env *env, for (i = 0; i <= old->curframe; i++) { if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; - if (!func_states_equal(old->frame[i], cur->frame[i])) + if (!func_states_equal(env, old->frame[i], cur->frame[i], exact)) return false; } return true; @@ -8317,35 +18358,54 @@ static int propagate_precision(struct bpf_verifier_env *env, { struct bpf_reg_state *state_reg; struct bpf_func_state *state; - int i, err = 0; + int i, err = 0, fr; + bool first; - state = old->frame[old->curframe]; - state_reg = state->regs; - 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, "propagating r%d\n", i); - err = mark_chain_precision(env, i); - if (err < 0) - return err; - } + 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 || + !(state_reg->live & REG_LIVE_READ)) + continue; + 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++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) - continue; - state_reg = &state->stack[i].spilled_ptr; - if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) - continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "propagating fp%d\n", - (-i - 1) * BPF_REG_SIZE); - err = mark_chain_precision_stack(env, i); - if (err < 0) - return err; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (!is_spilled_reg(&state->stack[i])) + continue; + state_reg = &state->stack[i].spilled_ptr; + if (state_reg->type != SCALAR_VALUE || + !state_reg->precise || + !(state_reg->live & REG_LIVE_READ)) + 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) + verbose(env, "\n"); } + + err = mark_chain_precision_batch(env); + if (err < 0) + return err; + return 0; } @@ -8367,21 +18427,104 @@ static bool states_maybe_looping(struct bpf_verifier_state *old, 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 "ininite 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 + * inifintely 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 *cur = env->cur_state, *new; - int i, j, err, states_cnt = 0; - bool add_new_state = env->test_state_freq ? true : false; - - cur->last_insn_idx = env->prev_insn_idx; - if (!env->insn_aux_data[insn_idx].prune_point) - /* this 'insn_idx' instruction wasn't marked, so we will not - * be doing state search here - */ - return 0; + struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry; + int i, j, n, err, states_cnt = 0; + bool force_new_state, add_new_state, force_exact; + + force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) || + /* Avoid accumulating infinitely long jmp history */ + cur->insn_hist_end - cur->insn_hist_start > 40; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -8391,6 +18534,7 @@ 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; @@ -8404,11 +18548,109 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) states_cnt++; if (sl->state.insn_idx != insn_idx) goto next; + if (sl->state.branches) { + struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; + + if (frame->in_async_callback_fn && + frame->async_entry_cnt != cur->frame[cur->curframe]->async_entry_cnt) { + /* Different async_entry_cnt means that the verifier is + * processing another entry into async callback. + * Seeing the same state is not an indication of infinite + * loop or infinite recursion. + * But finding the same state doesn't mean that it's safe + * to stop processing the current state. The previous state + * hasn't yet reached bpf_exit, since state.branches > 0. + * Checking in_async_callback_fn alone is not enough either. + * Since the verifier still needs to catch infinite loops + * inside async callbacks. + */ + 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) { + update_loop_entry(cur, &sl->state); + 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)) { + update_loop_entry(cur, &sl->state); + goto hit; + } + } + if (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)) { + 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 @@ -8423,12 +18665,44 @@ 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)) { + /* If sl->state is a part of a loop and this loop's entry is a part of + * current verification path then states have to be compared exactly. + * 'force_exact' is needed to catch the following case: + * + * initial Here state 'succ' was processed first, + * | it was eventually tracked to produce a + * V state identical to 'hdr'. + * .---------> hdr All branches from 'succ' had been explored + * | | and thus 'succ' has its .branches == 0. + * | V + * | .------... Suppose states 'cur' and 'succ' correspond + * | | | to the same instruction + callsites. + * | V V In such case it is necessary to check + * | ... ... if 'succ' and 'cur' are states_equal(). + * | | | If 'succ' and 'cur' are a part of the + * | V V same loop exact flag has to be set. + * | succ <- cur To check if that is the case, verify + * | | if loop entry of 'succ' is in current + * | V DFS path. + * | ... + * | | + * '----' + * + * Additional details are in the comment before get_loop_entry(). + */ + loop_entry = get_loop_entry(&sl->state); + force_exact = loop_entry && loop_entry->branches > 0; + if (states_equal(env, &sl->state, cur, force_exact ? RANGE_WITHIN : NOT_EXACT)) { + if (force_exact) + update_loop_entry(cur, loop_entry); +hit: sl->hit_cnt++; /* reached equivalent register/stack state, * prune the search. @@ -8443,11 +18717,12 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) 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); + if (is_jmp_point(env, env->insn_idx)) + err = err ? : push_insn_history(env, cur, 0, 0); err = err ? : propagate_precision(env, &sl->state); if (err) return err; @@ -8466,13 +18741,18 @@ 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) { + if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE && + !sl->state.used_as_loop_entry) { u32 br = sl->state.branches; WARN_ONCE(br, @@ -8501,10 +18781,10 @@ next: env->max_states_per_insn = states_cnt; if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) - return push_jmp_history(env, cur); + return 0; if (!add_new_state) - return push_jmp_history(env, cur); + return 0; /* There were no equivalent states, remember the current one. * Technically the current state is not proven to be safe yet, @@ -8523,6 +18803,10 @@ next: env->prev_jmps_processed = env->jmps_processed; env->prev_insn_processed = env->insn_processed; + /* forget precise markings we inherited, see __mark_chain_precision */ + if (env->bpf_capable) + mark_all_scalars_imprecise(env, cur); + /* add new state to the head of linked list */ new = &new_sl->state; err = copy_verifier_state(new, cur); @@ -8537,7 +18821,8 @@ next: cur->parent = new; cur->first_insn_idx = insn_idx; - clear_jmp_history(cur); + cur->insn_hist_start = cur->insn_hist_end; + cur->dfs_depth = new->dfs_depth + 1; 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 @@ -8577,17 +18862,14 @@ next: /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_CTX: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: + case PTR_TO_ARENA: return false; default: return true; @@ -8612,6 +18894,44 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) !reg_type_mismatch_ok(prev)); } +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; + + 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 && + base_type(type) == PTR_TO_BTF_ID && + base_type(*prev_type) == PTR_TO_BTF_ID) { + /* + * 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. + */ + *prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED; + } else { + verbose(env, "same insn cannot be used with different pointers\n"); + return -EINVAL; + } + } + + return 0; +} + static int do_check(struct bpf_verifier_env *env) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); @@ -8623,10 +18943,14 @@ static int do_check(struct bpf_verifier_env *env) int prev_insn_idx = -1; for (;;) { + bool exception_exit = false; struct bpf_insn *insn; u8 class; int err; + /* reset current history entry on each new instruction */ + env->cur_hist_ent = NULL; + env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", @@ -8644,21 +18968,31 @@ static int do_check(struct bpf_verifier_env *env) return -E2BIG; } - err = is_state_visited(env, env->insn_idx); - if (err < 0) - return err; - if (err == 1) { - /* found equivalent state, can prune the search */ - if (env->log.level & BPF_LOG_LEVEL) { - if (do_print_state) - verbose(env, "\nfrom %d to %d%s: safe\n", - env->prev_insn_idx, env->insn_idx, - env->cur_state->speculative ? - " (speculative execution)" : ""); - else - verbose(env, "%d: safe\n", env->insn_idx); + state->last_insn_idx = env->prev_insn_idx; + + if (is_prune_point(env, env->insn_idx)) { + err = is_state_visited(env, env->insn_idx); + if (err < 0) + return err; + if (err == 1) { + /* found equivalent state, can prune the search */ + if (env->log.level & BPF_LOG_LEVEL) { + if (do_print_state) + verbose(env, "\nfrom %d to %d%s: safe\n", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); + else + verbose(env, "%d: safe\n", env->insn_idx); + } + goto process_bpf_exit; } - goto process_bpf_exit; + } + + if (is_jmp_point(env, env->insn_idx)) { + err = push_insn_history(env, state, 0, 0); + if (err) + return err; } if (signal_pending(current)) @@ -8667,31 +19001,34 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (env->log.level & BPF_LOG_LEVEL2 || - (env->log.level & BPF_LOG_LEVEL && do_print_state)) { - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "%d:", env->insn_idx); - else - verbose(env, "\nfrom %d to %d%s:", - env->prev_insn_idx, env->insn_idx, - env->cur_state->speculative ? - " (speculative execution)" : ""); - print_verifier_state(env, state->frame[state->curframe]); + if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) { + verbose(env, "\nfrom %d to %d%s:", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); + 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, state->curframe); + verbose_linfo(env, env->insn_idx, "; "); + 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_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) @@ -8699,7 +19036,7 @@ static int do_check(struct bpf_verifier_env *env) } regs = cur_regs(env); - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { @@ -8708,7 +19045,7 @@ static int do_check(struct bpf_verifier_env *env) return err; } else if (class == BPF_LDX) { - enum bpf_reg_type *prev_src_type, src_reg_type; + enum bpf_reg_type src_reg_type; /* check for reserved fields is already done */ @@ -8728,42 +19065,28 @@ static int do_check(struct bpf_verifier_env *env) */ err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), - BPF_READ, insn->dst_reg, false); + BPF_READ, insn->dst_reg, false, + BPF_MODE(insn->code) == BPF_MEMSX); + err = err ?: save_aux_ptr_type(env, src_reg_type, true); + err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], "ldx"); if (err) return err; - - 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; + enum bpf_reg_type dst_reg_type; - if (BPF_MODE(insn->code) == BPF_XADD) { - err = check_xadd(env, env->insn_idx, insn); + 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) @@ -8778,20 +19101,16 @@ static int do_check(struct bpf_verifier_env *env) /* 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); + BPF_WRITE, insn->src_reg, false, false); 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; - } - + err = save_aux_ptr_type(env, dst_reg_type, 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"); @@ -8802,59 +19121,72 @@ static int do_check(struct bpf_verifier_env *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[reg_state(env, insn->dst_reg)->type]); - return -EACCES; - } + 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, -1, false); + 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->off != 0 || + (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_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_spin_lock && - (insn->src_reg == BPF_PSEUDO_CALL || - insn->imm != BPF_FUNC_spin_unlock)) { - verbose(env, "function calls are not allowed while holding a lock\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) + if (insn->src_reg == BPF_PSEUDO_CALL) { err = check_func_call(env, insn, &env->insn_idx); - else - err = check_helper_call(env, insn->imm, 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)) { + exception_exit = true; + goto process_bpf_exit_full; + } + } 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_K || - insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || - class == BPF_JMP32) { + (class == BPF_JMP && insn->imm != 0) || + (class == BPF_JMP32 && insn->off != 0)) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } - env->insn_idx += insn->off + 1; + if (class == BPF_JMP) + env->insn_idx += insn->off + 1; + else + env->insn_idx += insn->imm + 1; continue; } else if (opcode == BPF_EXIT) { @@ -8866,11 +19198,30 @@ static int do_check(struct bpf_verifier_env *env) verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } +process_bpf_exit_full: + /* 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_resource_leak(env, exception_exit, !env->cur_state->curframe, + "BPF_EXIT instruction in main prog"); + if (err) + return err; - if (env->cur_state->active_spin_lock) { - verbose(env, "bpf_spin_unlock is missing\n"); - return -EINVAL; - } + /* 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) + goto process_bpf_exit; if (state->curframe) { /* exit from nested function */ @@ -8881,14 +19232,11 @@ static int do_check(struct bpf_verifier_env *env) continue; } - err = check_reference_leak(env); - if (err) - return err; - - err = check_return_code(env); + err = check_return_code(env, BPF_REG_0, "R0"); 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); @@ -8919,7 +19267,7 @@ process_bpf_exit: return err; env->insn_idx++; - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -8935,12 +19283,190 @@ process_bpf_exit: return 0; } -static int check_map_prealloc(struct bpf_map *map) +static int find_btf_percpu_datasec(struct btf *btf) +{ + const struct btf_type *t; + const char *tname; + int i, n; + + /* + * Both vmlinux and module each have their own ".data..percpu" + * DATASECs in BTF. So for module's case, we need to skip vmlinux BTF + * types to look at only module's own BTF types. + */ + n = btf_nr_types(btf); + if (btf_is_module(btf)) + i = btf_nr_types(btf_vmlinux); + else + i = 1; + + for(; i < n; i++) { + t = btf_type_by_id(btf, i); + if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) + continue; + + tname = btf_name_by_offset(btf, t->name_off); + if (!strcmp(tname, ".data..percpu")) + return i; + } + + 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) + 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, + struct btf *btf) +{ + const struct btf_var_secinfo *vsi; + const struct btf_type *datasec; + const struct btf_type *t; + const char *sym_name; + bool percpu = false; + u32 type, id = insn->imm; + s32 datasec_id; + u64 addr; + int i; + + t = btf_type_by_id(btf, id); + if (!t) { + verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id); + return -ENOENT; + } + + 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); + addr = kallsyms_lookup_name(sym_name); + if (!addr) { + verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n", + sym_name); + 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); + if (datasec_id > 0) { + datasec = btf_type_by_id(btf, datasec_id); + for_each_vsi(i, datasec, vsi) { + if (vsi->type == id) { + percpu = true; + break; + } + } + } + + type = t->type; + t = btf_type_skip_modifiers(btf, type, NULL); + if (percpu) { + aux->btf_var.reg_type = PTR_TO_BTF_ID | MEM_PERCPU; + aux->btf_var.btf = btf; + aux->btf_var.btf_id = type; + } else if (!btf_type_is_struct(t)) { + const struct btf_type *ret; + const char *tname; + u32 tsize; + + /* resolve the type size of ksym. */ + ret = btf_resolve_size(btf, t, &tsize); + if (IS_ERR(ret)) { + 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)); + return -EINVAL; + } + aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; + aux->btf_var.mem_size = tsize; + } else { + aux->btf_var.reg_type = PTR_TO_BTF_ID; + aux->btf_var.btf = btf; + aux->btf_var.btf_id = type; + } + + return 0; +} + +static int check_pseudo_btf_id(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_insn_aux_data *aux) { - return (map->map_type != BPF_MAP_TYPE_HASH && - map->map_type != BPF_MAP_TYPE_PERCPU_HASH && - map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) || - !(map->map_flags & BPF_F_NO_PREALLOC); + struct btf *btf; + int btf_fd; + int err; + + btf_fd = insn[1].imm; + if (btf_fd) { + CLASS(fd, f)(btf_fd); + + 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; + } + + 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; } static bool is_tracing_prog_type(enum bpf_prog_type type) @@ -8950,19 +19476,17 @@ static bool is_tracing_prog_type(enum bpf_prog_type type) case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: return true; default: return false; } } -static bool is_preallocated_map(struct bpf_map *map) +static bool bpf_map_is_cgroup_storage(struct bpf_map *map) { - if (!check_map_prealloc(map)) - return false; - if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta)) - return false; - return true; + 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, @@ -8970,44 +19494,43 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_prog *prog) { - /* - * Validate that trace type programs use preallocated hash maps. - * - * For programs attached to PERF events this is mandatory as the - * perf NMI can hit any arbitrary code sequence. - * - * All other trace types using preallocated hash maps are unsafe as - * well because tracepoint or kprobes can be inside locked regions - * of the memory allocator or at a place where a recursion into the - * memory allocator would see inconsistent state. - * - * On RT enabled kernels run-time allocation of all trace type - * programs is strictly prohibited due to lock type constraints. On - * !RT kernels it is allowed for backwards compatibility reasons for - * now, but warnings are emitted so developers are made aware of - * the unsafety and can fix their programs before this is enforced. - */ - if (is_tracing_prog_type(prog->type) && !is_preallocated_map(map)) { - if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { - verbose(env, "perf_event programs can only use preallocated hash map\n"); + enum bpf_prog_type prog_type = resolve_prog_type(prog); + + 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,rb_root} yet\n"); return -EINVAL; } - if (IS_ENABLED(CONFIG_PREEMPT_RT)) { - verbose(env, "trace type programs can only use preallocated hash map\n"); + } + + if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) { + if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { + verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); + return -EINVAL; + } + + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } - WARN_ONCE(1, "trace type BPF program uses run-time allocation\n"); - verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n"); } - if ((is_tracing_prog_type(prog->type) || - prog->type == BPF_PROG_TYPE_SOCKET_FILTER) && - map_value_has_spin_lock(map)) { - verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); - return -EINVAL; + 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 ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_wq yet\n"); + return -EINVAL; + } + } + + if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; @@ -9018,23 +19541,129 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } + if (prog->sleepable) + switch (map->map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_LRU_HASH: + case BPF_MAP_TYPE_ARRAY: + case BPF_MAP_TYPE_PERCPU_HASH: + case BPF_MAP_TYPE_PERCPU_ARRAY: + case BPF_MAP_TYPE_LRU_PERCPU_HASH: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_RINGBUF: + case BPF_MAP_TYPE_USER_RINGBUF: + case BPF_MAP_TYPE_INODE_STORAGE: + 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: + break; + default: + verbose(env, + "Sleepable programs can only use array, hash, ringbuf and local storage maps\n"); + 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; + + return env->used_map_cnt - 1; } -/* look for pseudo eBPF instructions that access map FDs and - * replace them with actual map pointers +/* 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 replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) +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: + * + * 1. if it accesses map FD, replace it with actual map pointer. + * 2. if it accesses btf_id of a VAR, replace it with pointer to the var. + * + * NOTE: btf_vmlinux is required for converting pseudo btf_id. + */ +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) @@ -9042,23 +19671,18 @@ static int replace_map_fd_with_map_ptr(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; } - if (BPF_CLASS(insn->code) == BPF_STX && - ((BPF_MODE(insn->code) != BPF_MEM && - BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) { - verbose(env, "BPF_STX uses reserved fields\n"); - return -EINVAL; - } - 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; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || @@ -9071,47 +19695,75 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) /* valid generic load 64-bit imm */ goto next_insn; + if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) { + aux = &env->insn_aux_data[i]; + err = check_pseudo_btf_id(env, insn, aux); + if (err) + return err; + goto next_insn; + } + + if (insn[0].src_reg == BPF_PSEUDO_FUNC) { + aux = &env->insn_aux_data[i]; + aux->ptr_type = PTR_TO_FUNC; + goto next_insn; + } + /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ - if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD && - insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) || - (insn[0].src_reg == BPF_PSEUDO_MAP_FD && - insn[1].imm != 0)) { - verbose(env, - "unrecognized bpf_ld_imm64 insn\n"); + switch (insn[0].src_reg) { + case BPF_PSEUDO_MAP_VALUE: + case BPF_PSEUDO_MAP_IDX_VALUE: + break; + case BPF_PSEUDO_MAP_FD: + case BPF_PSEUDO_MAP_IDX: + if (insn[1].imm == 0) + break; + fallthrough; + default: + verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } - f = fdget(insn[0].imm); - 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); + switch (insn[0].src_reg) { + case BPF_PSEUDO_MAP_IDX_VALUE: + case BPF_PSEUDO_MAP_IDX: + if (bpfptr_is_null(env->fd_array)) { + verbose(env, "fd_idx without fd_array is invalid\n"); + return -EPROTO; + } + if (copy_from_bpfptr_offset(&fd, env->fd_array, + insn[0].imm * sizeof(fd), + sizeof(fd))) + return -EFAULT; + break; + default: + fd = insn[0].imm; + break; } - 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]; - if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + 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; } else { u32 off = insn[1].imm; 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; } @@ -9119,7 +19771,6 @@ static int replace_map_fd_with_map_ptr(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; } @@ -9130,38 +19781,6 @@ static int replace_map_fd_with_map_ptr(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++; @@ -9189,6 +19808,12 @@ static void release_maps(struct bpf_verifier_env *env) env->used_map_cnt); } +/* drop refcnt of maps used by the rejected program */ +static void release_btfs(struct bpf_verifier_env *env) +{ + __bpf_free_used_btfs(env->used_btfs, env->used_btf_cnt); +} + /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) { @@ -9196,20 +19821,26 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) int insn_cnt = env->prog->len; int i; - for (i = 0; i < insn_cnt; i++, insn++) - if (insn->code == (BPF_LD | BPF_IMM | BPF_DW)) - insn->src_reg = 0; + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) + continue; + if (insn->src_reg == BPF_PSEUDO_FUNC) + continue; + insn->src_reg = 0; + } } /* single env->prog->insni[off] instruction was replaced with the range * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying * [0, off) and [off, end) to new locations, so the patched range stays zero */ -static int adjust_insn_aux_data(struct bpf_verifier_env *env, - struct bpf_prog *new_prog, u32 off, u32 cnt) +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 *new_data, *old_data = env->insn_aux_data; + struct bpf_insn_aux_data *old_data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; + u32 old_seen = old_data[off].seen; u32 prog_len; int i; @@ -9220,22 +19851,19 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1); if (cnt == 1) - return 0; + return; prog_len = new_prog->len; - new_data = vzalloc(array_size(prog_len, - sizeof(struct bpf_insn_aux_data))); - if (!new_data) - return -ENOMEM; + 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)); for (i = off; i < off + cnt - 1; i++) { - new_data[i].seen = env->pass_cnt; + /* 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); } env->insn_aux_data = new_data; vfree(old_data); - return 0; } static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) @@ -9252,10 +19880,32 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len } } +static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len) +{ + struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; + int i, sz = prog->aux->size_poke_tab; + struct bpf_jit_poke_descriptor *desc; + + for (i = 0; i < sz; i++) { + desc = &tab[i]; + if (desc->insn_idx <= off) + continue; + desc->insn_idx += len - 1; + } +} + static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { struct bpf_prog *new_prog; + struct bpf_insn_aux_data *new_data = NULL; + + if (len > 1) { + new_data = vzalloc(array_size(env->prog->len + len - 1, + sizeof(struct bpf_insn_aux_data))); + if (!new_data) + return NULL; + } new_prog = bpf_patch_insn_single(env->prog, off, patch, len); if (IS_ERR(new_prog)) { @@ -9263,14 +19913,53 @@ 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; } - if (adjust_insn_aux_data(env, new_prog, off, len)) - return NULL; + adjust_insn_aux_data(env, new_data, new_prog, off, len); adjust_subprog_starts(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) { @@ -9397,7 +20086,7 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) unsigned int orig_prog_len = env->prog->len; int err; - if (bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); err = bpf_remove_insns(env->prog, off, cnt); @@ -9441,6 +20130,7 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) if (aux_data[i].seen) continue; memcpy(insn + i, &trap, sizeof(trap)); + aux_data[i].zext_dst = false; } } @@ -9448,13 +20138,13 @@ 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; } @@ -9477,7 +20167,7 @@ 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)); @@ -9508,22 +20198,29 @@ 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; @@ -9547,8 +20244,10 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, for (i = 0; i < len; i++) { int adj_idx = i + delta; struct bpf_insn insn; + int load_reg; insn = insns[adj_idx]; + load_reg = insn_def_regno(&insn); if (!aux[adj_idx].zext_dst) { u8 code, class; u32 imm_rnd; @@ -9558,14 +20257,14 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, code = insn.code; class = BPF_CLASS(code); - if (insn_no_def(&insn)) + if (load_reg == -1) continue; /* NOTE: arg "reg" (the fourth one) is only used for - * BPF_STX which has been ruled out in above - * check, it is safe to pass NULL here. + * BPF_STX + SRC_OP, so it is safe to pass NULL + * here. */ - if (is_reg64(env, &insn, insn.dst_reg, NULL, DST_OP)) { + if (is_reg64(env, &insn, load_reg, NULL, DST_OP)) { if (class == BPF_LD && BPF_MODE(code) == BPF_IMM) i++; @@ -9577,21 +20276,40 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, aux[adj_idx].ptr_type == PTR_TO_CTX) continue; - imm_rnd = get_random_int(); + imm_rnd = get_random_u32(); rnd_hi32_patch[0] = insn; rnd_hi32_patch[1].imm = imm_rnd; - rnd_hi32_patch[3].dst_reg = insn.dst_reg; + rnd_hi32_patch[3].dst_reg = load_reg; patch = rnd_hi32_patch; patch_len = 4; goto apply_patch_buffer; } - if (!bpf_jit_needs_zext()) + /* Add in an zero-extend instruction if a) the JIT has requested + * it or b) it's a CMPXCHG. + * + * The latter is because: BPF_CMPXCHG always loads a value into + * R0, therefore always zero-extends. However some archs' + * equivalent instruction only does this load when the + * comparison is successful. This detail of CMPXCHG is + * orthogonal to the general zero-extension behaviour of the + * CPU, so it's treated independently of bpf_jit_needs_zext. + */ + if (!bpf_jit_needs_zext() && !is_cmpxchg_insn(&insn)) continue; + /* Zero-extension is done by the caller. */ + 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"); + return -EFAULT; + } + zext_patch[0] = insn; - zext_patch[1].dst_reg = insn.dst_reg; - zext_patch[1].src_reg = insn.dst_reg; + zext_patch[1].dst_reg = load_reg; + zext_patch[1].src_reg = load_reg; patch = zext_patch; patch_len = 2; apply_patch_buffer: @@ -9614,14 +20332,39 @@ 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, 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) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } 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; + } + } if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { @@ -9630,7 +20373,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); - if (cnt >= ARRAY_SIZE(insn_buf)) { + if (cnt >= INSN_BUF_SIZE) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { @@ -9643,42 +20386,69 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - 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; + u8 mode; 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; - 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) || - insn->code == (BPF_STX | BPF_MEM | BPF_DW)) + } 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) || + insn->code == (BPF_STX | BPF_MEM | BPF_DW) || + insn->code == (BPF_ST | BPF_MEM | BPF_B) || + insn->code == (BPF_ST | BPF_MEM | BPF_H) || + insn->code == (BPF_ST | BPF_MEM | BPF_W) || + insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - else + } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || + insn->code == (BPF_STX | BPF_ATOMIC | BPF_DW)) && + env->insn_aux_data[i + delta].ptr_type == PTR_TO_ARENA) { + insn->code = BPF_STX | BPF_PROBE_ATOMIC | BPF_SIZE(insn->code); + env->prog->aux->num_exentries++; continue; + } else 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_off) { + env->insn_aux_data[i + delta].sanitize_stack_spill) { struct bpf_insn patch[] = { - /* Sanitize suspicious stack slot with zero. - * There are no memory dependencies for this store, - * since it's only using frame pointer and immediate - * constant of zero - */ - BPF_ST_MEM(BPF_DW, BPF_REG_FP, - env->insn_aux_data[i + delta].sanitize_stack_off, - 0), - /* the original STX instruction will immediately - * overwrite the same stack slot with appropriate value - */ *insn, + BPF_ST_NOSPEC(), }; cnt = ARRAY_SIZE(patch); @@ -9692,7 +20462,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } - switch (env->insn_aux_data[i + delta].ptr_type) { + switch ((int)env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) continue; @@ -9709,21 +20479,39 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; case PTR_TO_BTF_ID: + case PTR_TO_BTF_ID | PTR_UNTRUSTED: + /* PTR_TO_BTF_ID | MEM_ALLOC always has a valid lifetime, unlike + * PTR_TO_BTF_ID, and an active ref_obj_id, but the same cannot + * be said once it is marked PTR_UNTRUSTED, hence we must handle + * any faults for loads into such types. BPF_WRITE is disallowed + * for this case. + */ + case PTR_TO_BTF_ID | MEM_ALLOC | 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++; - } else if (env->prog->type != BPF_PROG_TYPE_STRUCT_OPS) { - verbose(env, "Writes through BTF pointers are not allowed\n"); - return -EINVAL; } continue; + case PTR_TO_ARENA: + if (BPF_MODE(insn->code) == BPF_MEMSX) { + verbose(env, "sign extending loads from arena are not supported yet\n"); + return -EOPNOTSUPP; + } + 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 @@ -9754,7 +20542,7 @@ 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; @@ -9763,6 +20551,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; + if (shift && cnt + 1 >= INSN_BUF_SIZE) { + verbose(env, "bpf verifier narrow ctx load misconfigured\n"); + return -EINVAL; + } if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, @@ -9775,11 +20567,16 @@ 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; @@ -9798,6 +20595,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog, **func, *tmp; int i, j, subprog_start, subprog_end = 0, len, subprog; + struct bpf_map *map_ptr; struct bpf_insn *insn; void *old_bpf_func; int err, num_exentries; @@ -9806,9 +20604,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - if (insn->code != (BPF_JMP | BPF_CALL) || - insn->src_reg != BPF_PSEUDO_CALL) + if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn)) continue; + /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. @@ -9829,6 +20627,19 @@ 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 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. + * Set close enough to possible prog address. + */ + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; + } } err = bpf_prog_alloc_jited_linfo(prog); @@ -9845,10 +20656,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; - /* BPF_PROG_RUN doesn't call subprogs directly, + /* bpf_prog_run() doesn't call subprogs directly, * hence main prog stats include the runtime of subprogs. * subprogs don't have IDs and not reachable via prog_get_next_id - * func[i]->aux->stats will never be accessed and stays NULL + * func[i]->stats will never be accessed and stays NULL */ func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER); if (!func[i]) @@ -9860,29 +20671,60 @@ 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; - /* the btf and func_info will be freed only at prog->aux */ + /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; 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; + + for (j = 0; j < prog->aux->size_poke_tab; j++) { + struct bpf_jit_poke_descriptor *poke; + + poke = &prog->aux->poke_tab[j]; + if (poke->insn_idx < subprog_end && + poke->insn_idx >= subprog_start) + poke->aux = func[i]->aux; + } - /* Use bpf_prog_F_tag to indicate functions in stack traces. - * Long term would need debug info to populate names - */ 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; + func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab; func[i]->aux->linfo = prog->aux->linfo; 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; 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_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; + if (!i) + func[i]->aux->exception_boundary = env->seen_exception; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; @@ -9890,6 +20732,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) } cond_resched(); } + /* at this point all bpf functions were successfully JITed * now populate all bpf_calls with correct addresses and * run last pass of JIT @@ -9897,12 +20740,16 @@ static int jit_subprogs(struct bpf_verifier_env *env) for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { - if (insn->code != (BPF_JMP | BPF_CALL) || - insn->src_reg != BPF_PSEUDO_CALL) + if (bpf_pseudo_func(insn)) { + subprog = insn->off; + insn[0].imm = (u32)(long)func[subprog]->bpf_func; + insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32; + continue; + } + if (!bpf_pseudo_call(insn)) continue; subprog = insn->off; - insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func); } /* we use the aux data to keep a list of the start addresses @@ -9917,7 +20764,8 @@ 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; @@ -9931,20 +20779,30 @@ static int jit_subprogs(struct bpf_verifier_env *env) } /* finally lock prog and jit images for all functions and - * populate kallsysm + * populate kallsysm. Begin at the first subprogram, since + * bpf_prog_load will add the kallsyms for the main program. */ - for (i = 0; i < env->subprog_cnt; i++) { - bpf_prog_lock_ro(func[i]); - bpf_prog_kallsyms_add(func[i]); + 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. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - if (insn->code != (BPF_JMP | BPF_CALL) || - insn->src_reg != BPF_PSEUDO_CALL) + if (bpf_pseudo_func(insn)) { + insn[0].imm = env->insn_aux_data[i].call_imm; + insn[1].imm = insn->off; + insn->off = 0; + continue; + } + if (!bpf_pseudo_call(insn)) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); @@ -9953,26 +20811,47 @@ 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; - bpf_prog_free_unused_jited_linfo(prog); + 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: - for (i = 0; i < env->subprog_cnt; i++) - if (func[i]) - bpf_jit_free(func[i]); + /* We failed JIT'ing, so at this point we need to unregister poke + * descriptors from subprogs, so that kernel is not attempting to + * patch it anymore as we're freeing the subprog JIT memory. + */ + for (i = 0; i < prog->aux->size_poke_tab; i++) { + map_ptr = prog->aux->poke_tab[i].tail_call.map; + map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); + } + /* At this point we're guaranteed that poke descriptors are not + * live anymore. We can just unlink its descriptor table as it's + * released with the main prog. + */ + for (i = 0; i < env->subprog_cnt; i++) { + if (!func[i]) + continue; + func[i]->aux->poke_tab = NULL; + bpf_jit_free(func[i]); + } kfree(func); out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; + prog->blinding_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - if (insn->code != (BPF_JMP | BPF_CALL) || - insn->src_reg != BPF_PSEUDO_CALL) + if (!bpf_pseudo_call(insn)) continue; insn->off = 0; insn->imm = env->insn_aux_data[i].call_imm; } - bpf_prog_free_jited_linfo(prog); + bpf_prog_jit_attempt_done(prog); return err; } @@ -9981,12 +20860,13 @@ static int fixup_call_args(struct bpf_verifier_env *env) #ifndef CONFIG_BPF_JIT_ALWAYS_ON struct bpf_prog *prog = env->prog; struct bpf_insn *insn = prog->insnsi; + bool has_kfunc_call = bpf_prog_has_kfunc_call(prog); int i, depth; #endif 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; @@ -9994,9 +20874,27 @@ static int fixup_call_args(struct bpf_verifier_env *env) return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON + if (has_kfunc_call) { + verbose(env, "calling kernel functions are not allowed in non-JITed programs\n"); + return -EINVAL; + } + if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) { + /* When JIT fails the progs with bpf2bpf calls and tail_calls + * have to be rejected, since interpreter doesn't support them yet. + */ + verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); + return -EINVAL; + } for (i = 0; i < prog->len; i++, insn++) { - if (insn->code != (BPF_JMP | BPF_CALL) || - insn->src_reg != BPF_PSEUDO_CALL) + if (bpf_pseudo_func(insn)) { + /* When JIT fails the progs with callback calls + * have to be rejected, since interpreter doesn't support them yet. + */ + verbose(env, "callbacks are not allowed in non-JITed programs\n"); + return -EINVAL; + } + + if (!bpf_pseudo_call(insn)) continue; depth = get_callee_stack_depth(env, insn, i); if (depth < 0) @@ -10008,54 +20906,358 @@ static int fixup_call_args(struct bpf_verifier_env *env) return err; } -/* fixup insn->imm field of bpf_call instructions - * and inline eligible helpers as explicit sequence of BPF instructions - * - * this function is called after eBPF program passed verification +/* replace a generic kfunc with a specialized version if necessary */ +static void specialize_kfunc(struct bpf_verifier_env *env, + u32 func_id, u16 offset, unsigned long *addr) +{ + struct bpf_prog *prog = env->prog; + bool seen_direct_write; + void *xdp_kfunc; + bool is_rdonly; + + 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; + return; + } + /* fallback to default kfunc when not supported by netdev */ + } + + if (offset) + return; + + 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; + } +} + +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; + + if (!insn->imm) { + verbose(env, "invalid kernel function call not eliminated in verifier pass\n"); + return -EINVAL; + } + + *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); + return -EFAULT; + } + + 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] || + 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) { + verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n", + 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] || + 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) { + verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n", + insn_idx); + return -EFAULT; + } + + if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] && + !kptr_struct_meta) { + verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n", + 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) { + verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n", + 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; + } else if (is_bpf_wq_set_callback_impl_kfunc(desc->func_id)) { + struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(BPF_REG_4, (long)env->prog->aux) }; + + insn_buf[0] = ld_addrs[0]; + insn_buf[1] = ld_addrs[1]; + insn_buf[2] = *insn; + *cnt = 3; + } + return 0; +} + +/* 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) { + verbose(env, "verifier internal error: only one hidden subprog supported\n"); + 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; +} + +/* Do various post-verification rewrites in a single program pass. + * These rewrites simplify JIT and interpreter implementations. */ -static int fixup_bpf_calls(struct bpf_verifier_env *env) +static int do_misc_fixups(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; - bool expect_blinding = bpf_jit_blinding_enabled(prog); + enum bpf_attach_type eatype = prog->expected_attach_type; + enum bpf_prog_type prog_type = resolve_prog_type(prog); struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; 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; + + if (env->seen_exception && !env->exception_callback_subprog) { + struct bpf_insn patch[] = { + env->prog->insnsi[insn_cnt - 1], + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }; + + ret = add_hidden_subprog(env, patch, ARRAY_SIZE(patch)); + 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; + } - for (i = 0; i < insn_cnt; i++, 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 *patchlet; + struct bpf_insn chk_and_sdiv[] = { + BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_NEG | BPF_K, insn->dst_reg, + 0, 0, 0), + }; + struct bpf_insn chk_and_smod[] = { + BPF_MOV32_IMM(insn->dst_reg, 0), + }; + + patchlet = isdiv ? chk_and_sdiv : chk_and_smod; + cnt = isdiv ? ARRAY_SIZE(chk_and_sdiv) : ARRAY_SIZE(chk_and_smod); + + new_prog = bpf_patch_insn_data(env, i + delta, patchlet, 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; - struct bpf_insn mask_and_div[] = { - BPF_MOV32_REG(insn->src_reg, insn->src_reg), - /* Rx div 0 -> 0 */ - BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2), + bool isdiv = BPF_OP(insn->code) == BPF_DIV; + bool is_sdiv = isdiv && insn->off == 1; + bool is_smod = !isdiv && insn->off == 1; + struct bpf_insn *patchlet; + struct bpf_insn chk_and_div[] = { + /* [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 mask_and_mod[] = { - BPF_MOV32_REG(insn->src_reg, insn->src_reg), - /* Rx mod 0 -> Rx */ - BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1), + struct bpf_insn chk_and_mod[] = { + /* [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), + }; + struct bpf_insn chk_and_sdiv[] = { + /* [R,W]x sdiv 0 -> 0 + * LLONG_MIN sdiv -1 -> LLONG_MIN + * INT_MIN sdiv -1 -> INT_MIN + */ + BPF_MOV64_REG(BPF_REG_AX, insn->src_reg), + BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_ADD | BPF_K, BPF_REG_AX, + 0, 0, 1), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JGT | BPF_K, BPF_REG_AX, + 0, 4, 1), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JEQ | BPF_K, BPF_REG_AX, + 0, 1, 0), + 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 */ + BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_NEG | BPF_K, insn->dst_reg, + 0, 0, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + *insn, + }; + struct bpf_insn chk_and_smod[] = { + /* [R,W]x mod 0 -> [R,W]x */ + /* [R,W]x mod -1 -> 0 */ + BPF_MOV64_REG(BPF_REG_AX, insn->src_reg), + BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | + BPF_ADD | BPF_K, BPF_REG_AX, + 0, 0, 1), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JGT | BPF_K, BPF_REG_AX, + 0, 3, 1), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JEQ | BPF_K, BPF_REG_AX, + 0, 3 + (is64 ? 0 : 1), 1), + BPF_MOV32_IMM(insn->dst_reg, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + *insn, + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV32_REG(insn->dst_reg, insn->dst_reg), }; - struct bpf_insn *patchlet; - if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || - insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { - patchlet = mask_and_div + (is64 ? 1 : 0); - cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0); + if (is_sdiv) { + patchlet = chk_and_sdiv; + cnt = ARRAY_SIZE(chk_and_sdiv); + } else if (is_smod) { + patchlet = chk_and_smod; + cnt = ARRAY_SIZE(chk_and_smod) - (is64 ? 2 : 0); } else { - patchlet = mask_and_mod + (is64 ? 1 : 0); - cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0); + 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, patchlet, cnt); @@ -10065,14 +21267,45 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; + } + + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + goto next_insn; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; } + /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { cnt = env->ops->gen_ld_abs(insn, insn_buf); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + if (cnt == 0 || cnt >= INSN_BUF_SIZE) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -10084,48 +21317,49 @@ static int fixup_bpf_calls(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. */ if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) || 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 insn_buf[16]; struct bpf_insn *patch = &insn_buf[0]; - bool issrc, isneg; + 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) == BPF_ALU_SANITIZE_SRC; + isimm = aux->alu_state & BPF_ALU_IMMEDIATE; off_reg = issrc ? insn->src_reg : insn->dst_reg; - if (isneg) - *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); - *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1); - *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); - *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); - *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); - *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); - if (issrc) { - *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, - off_reg); - insn->src_reg = BPF_REG_AX; + if (isimm) { + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); } else { - *patch++ = BPF_ALU64_REG(BPF_AND, off_reg, - BPF_REG_AX); + if (isneg) + *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); + *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); + *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); + *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg); } + if (!issrc) + *patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg); + insn->src_reg = BPF_REG_AX; if (isneg) insn->code = insn->code == code_add ? code_sub : code_add; *patch++ = *insn; - if (issrc && isneg) + if (issrc && isneg && !isimm) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); cnt = patch - insn_buf; @@ -10136,13 +21370,56 @@ static int fixup_bpf_calls(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)) { + 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) + goto next_insn; + + 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; + } + + /* 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; @@ -10157,11 +21434,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) * the program array. */ prog->cb_access = 1; - env->prog->aux->stack_depth = MAX_BPF_STACK; - env->prog->aux->max_pkt_offset = MAX_PACKET_OFF; + if (!allow_tail_call_in_subprogs(env)) + prog->aux->stack_depth = MAX_BPF_STACK; + prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid - * conditional branch in the interpeter for every normal + * conditional branch in the interpreter for every normal * call and to prevent accidental JITing by JIT compiler * that doesn't support bpf_tail_call yet */ @@ -10169,15 +21447,16 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; - if (env->bpf_capable && !expect_blinding && + if (env->bpf_capable && !prog->blinding_requested && prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !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, }; ret = bpf_jit_add_poke_descriptor(prog, &desc); @@ -10187,11 +21466,11 @@ static int fixup_bpf_calls(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: @@ -10204,7 +21483,7 @@ static int fixup_bpf_calls(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, @@ -10220,7 +21499,78 @@ static int fixup_bpf_calls(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) { + /* The verifier will process callback_fn as many times as necessary + * with different maps and the register states prepared by + * set_timer_callback_state will be accurate. + * + * The following use case is valid: + * map1 is shared by prog1, prog2, prog3. + * prog1 calls bpf_timer_init for some map1 elements + * prog2 calls bpf_timer_set_callback for some map1 elements. + * Those that were not bpf_timer_init-ed will return -EINVAL. + * prog3 calls bpf_timer_start for some map1 elements. + * Those that were not both bpf_timer_init-ed and + * bpf_timer_set_callback-ed will return -EINVAL. + */ + struct bpf_insn ld_addrs[2] = { + BPF_LD_IMM64(BPF_REG_3, (long)prog->aux), + }; + + insn_buf[0] = ld_addrs[0]; + insn_buf[1] = ld_addrs[1]; + insn_buf[2] = *insn; + cnt = 3; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto patch_call_imm; + } + + if (is_storage_get_function(insn->imm)) { + if (!in_sleepable(env) || + env->insn_aux_data[i + delta].storage_get_func_atomic) + 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); + 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_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 @@ -10233,17 +21583,22 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->imm == BPF_FUNC_map_delete_elem || insn->imm == BPF_FUNC_map_push_elem || insn->imm == BPF_FUNC_map_pop_elem || - insn->imm == BPF_FUNC_map_peek_elem)) { + insn->imm == BPF_FUNC_map_peek_elem || + insn->imm == BPF_FUNC_redirect_map || + insn->imm == BPF_FUNC_for_each_map_elem || + insn->imm == BPF_FUNC_map_lookup_percpu_elem)) { aux = &env->insn_aux_data[i + delta]; 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 == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + if (cnt == -EOPNOTSUPP) + goto patch_map_ops_generic; + if (cnt <= 0 || cnt >= INSN_BUF_SIZE) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -10256,54 +21611,68 @@ static int fixup_bpf_calls(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, + (long (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, + (long (*)(struct bpf_map *map, + bpf_callback_t callback_fn, + void *callback_ctx, + u64 flags))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_lookup_percpu_elem, + (void *(*)(struct bpf_map *map, void *key, u32 cpu))NULL)); +patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: - insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - - __bpf_call_base; - continue; + insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); + goto next_insn; case BPF_FUNC_map_update_elem: - insn->imm = BPF_CAST_CALL(ops->map_update_elem) - - __bpf_call_base; - continue; + insn->imm = BPF_CALL_IMM(ops->map_update_elem); + goto next_insn; case BPF_FUNC_map_delete_elem: - insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - - __bpf_call_base; - continue; + insn->imm = BPF_CALL_IMM(ops->map_delete_elem); + goto next_insn; case BPF_FUNC_map_push_elem: - insn->imm = BPF_CAST_CALL(ops->map_push_elem) - - __bpf_call_base; - continue; + insn->imm = BPF_CALL_IMM(ops->map_push_elem); + goto next_insn; case BPF_FUNC_map_pop_elem: - insn->imm = BPF_CAST_CALL(ops->map_pop_elem) - - __bpf_call_base; - continue; + insn->imm = BPF_CALL_IMM(ops->map_pop_elem); + goto next_insn; case BPF_FUNC_map_peek_elem: - insn->imm = BPF_CAST_CALL(ops->map_peek_elem) - - __bpf_call_base; - continue; + insn->imm = BPF_CALL_IMM(ops->map_peek_elem); + goto next_insn; + case BPF_FUNC_redirect_map: + insn->imm = BPF_CALL_IMM(ops->map_redirect); + goto next_insn; + case BPF_FUNC_for_each_map_elem: + insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); + goto next_insn; + case BPF_FUNC_map_lookup_percpu_elem: + insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); + goto next_insn; } goto patch_call_imm; } + /* Implement bpf_jiffies64 inline. */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_jiffies64) { struct bpf_insn ld_jiffies_addr[2] = { @@ -10325,9 +21694,193 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) 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 pcpu_hot.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_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number); + insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); + insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0); + cnt = 3; +#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) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6); + insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3); + insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1); + insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0); + insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0); + insn_buf[7] = BPF_JMP_A(1); + insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); + cnt = 9; + + 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_get_func_ret inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_ret) { + if (eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); + insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); + insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0); + insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0); + cnt = 6; + } else { + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP); + cnt = 1; + } + + 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 get_func_arg_cnt inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_arg_cnt) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); + if (!new_prog) + return -ENOMEM; + + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } + + /* Implement bpf_get_func_ip inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_ip) { + /* Load IP address from ctx - 16 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16); + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); + if (!new_prog) + return -ENOMEM; + + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + 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 @@ -10340,6 +21893,47 @@ patch_call_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; + 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 subprog_start = subprogs[i].start; + int stack_slots = subprogs[i].stack_extra / 8; + + if (!stack_slots) + continue; + if (stack_slots > 1) { + verbose(env, "verifier bug: stack_slots supports may_goto only\n"); + return -EFAULT; + } + + /* Add ST insn to subprog prologue to init extra stack */ + insn_buf[0] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, + -subprogs[i].stack_depth, BPF_MAX_LOOPS); + /* Copy first actual insn to preserve it */ + insn_buf[1] = env->prog->insnsi[subprog_start]; + + new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, 2); + 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, 1)); } /* Since poke tab is now finalized, publish aux to tracker. */ @@ -10359,6 +21953,179 @@ patch_call_imm: } } + sort_kfunc_descs_by_imm_off(env->prog); + + return 0; +} + +static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, + int position, + s32 stack_base, + u32 callback_subprogno, + u32 *total_cnt) +{ + s32 r6_offset = stack_base + 0 * BPF_REG_SIZE; + s32 r7_offset = stack_base + 1 * BPF_REG_SIZE; + s32 r8_offset = stack_base + 2 * BPF_REG_SIZE; + int reg_loop_max = BPF_REG_6; + 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. + */ + + /* 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; + + /* callback start is known only after patching */ + callback_start = env->subprog_info[callback_subprogno].start; + /* Note: insn_buf[12] is an offset of BPF_CALL_REL instruction */ + call_insn_offset = position + 12; + callback_offset = callback_start - call_insn_offset - 1; + new_prog->insnsi[call_insn_offset].imm = callback_offset; + + return new_prog; +} + +static bool is_bpf_loop_call(struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_CALL) && + insn->src_reg == 0 && + insn->imm == BPF_FUNC_loop; +} + +/* For all sub-programs in the program (including main) check + * insn_aux_data to see if there are bpf_loop calls that require + * inlining. If such calls are found the calls are replaced with a + * sequence of instructions produced by `inline_bpf_loop` function and + * subprog stack_depth is increased by the size of 3 registers. + * This stack space is used to spill values of the R6, R7, R8. These + * registers are used to store the loop bound, counter and context + * variables. + */ +static int optimize_bpf_loop(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *subprogs = env->subprog_info; + int i, cur_subprog = 0, cnt, delta = 0; + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + u16 stack_depth = subprogs[cur_subprog].stack_depth; + u16 stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; + u16 stack_depth_extra = 0; + + for (i = 0; i < insn_cnt; i++, insn++) { + struct bpf_loop_inline_state *inline_state = + &env->insn_aux_data[i + delta].loop_inline_state; + + if (is_bpf_loop_call(insn) && inline_state->fit_for_inline) { + struct bpf_prog *new_prog; + + stack_depth_extra = BPF_REG_SIZE * 3 + stack_depth_roundup; + new_prog = inline_bpf_loop(env, + i + delta, + -(stack_depth + stack_depth_extra), + inline_state->callback_subprogno, + &cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = new_prog; + insn = new_prog->insnsi + i + delta; + } + + if (subprogs[cur_subprog + 1].start == i + delta + 1) { + subprogs[cur_subprog].stack_depth += stack_depth_extra; + cur_subprog++; + stack_depth = subprogs[cur_subprog].stack_depth; + stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; + stack_depth_extra = 0; + } + } + + env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; + + 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; } @@ -10392,37 +22159,10 @@ static void free_states(struct bpf_verifier_env *env) } } -/* The verifier is using insn_aux_data[] to store temporary data during - * verification and to store information for passes that run after the - * verification like dead code sanitization. do_check_common() for subprogram N - * may analyze many other subprograms. sanitize_insn_aux_data() clears all - * temporary data after do_check_common() finds that subprogram N cannot be - * verified independently. pass_cnt counts the number of times - * do_check_common() was run and insn->aux->seen tells the pass number - * insn_aux_data was touched. These variables are compared to clear temporary - * data from failed pass. For testing and experiments do_check_common() can be - * run multiple times even when prior attempt to verify is unsuccessful. - */ -static void sanitize_insn_aux_data(struct bpf_verifier_env *env) -{ - struct bpf_insn *insn = env->prog->insnsi; - struct bpf_insn_aux_data *aux; - int i, class; - - for (i = 0; i < env->prog->len; i++) { - class = BPF_CLASS(insn[i].code); - if (class != BPF_LDX && class != BPF_STX) - continue; - aux = &env->insn_aux_data[i]; - if (aux->seen != env->pass_cnt) - continue; - memset(aux, 0, offsetof(typeof(*aux), orig_idx)); - } -} - static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); + struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; @@ -10446,34 +22186,88 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) BPF_MAIN_FUNC /* callsite */, 0 /* frameno */, subprog); + state->first_insn_idx = env->subprog_info[subprog].start; + state->last_insn_idx = -1; regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { - ret = btf_prepare_func_args(env, subprog, regs); + const char *sub_name = subprog_name(env, subprog); + struct bpf_subprog_arg_info *arg; + struct bpf_reg_state *reg; + + verbose(env, "Validating %s() func#%d...\n", sub_name, subprog); + ret = btf_prepare_func_args(env, subprog); if (ret) goto out; - for (i = BPF_REG_1; i <= BPF_REG_5; i++) { - if (regs[i].type == PTR_TO_CTX) + + if (subprog_is_exc_cb(env, subprog)) { + state->frame[0]->in_exception_callback_fn = true; + /* We have already ensured that the callback returns an integer, just + * like all global subprogs. We need to determine it only has a single + * scalar argument. + */ + if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) { + verbose(env, "exception cb only supports single integer argument\n"); + ret = -EINVAL; + goto out; + } + } + for (i = BPF_REG_1; i <= sub->arg_cnt; i++) { + arg = &sub->args[i - BPF_REG_1]; + reg = ®s[i]; + + if (arg->arg_type == ARG_PTR_TO_CTX) { + reg->type = PTR_TO_CTX; mark_reg_known_zero(env, regs, i); - else if (regs[i].type == SCALAR_VALUE) + } else if (arg->arg_type == ARG_ANYTHING) { + reg->type = SCALAR_VALUE; mark_reg_unknown(env, regs, i); + } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { + /* assume unspecial LOCAL dynptr type */ + __mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen); + } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { + reg->type = PTR_TO_MEM; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->type |= PTR_MAYBE_NULL; + mark_reg_known_zero(env, regs, i); + reg->mem_size = arg->mem_size; + 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 { + WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", + 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_func_arg_match(env, subprog, regs); - if (ret == -EFAULT) - /* unlikely verifier bug. abort. - * ret == 0 and ret < 0 are sadly acceptable for - * main() function due to backward compatibility. - * Like socket filter program may be written as: - * int bpf_prog(struct pt_regs *ctx) - * and never dereference that ctx in the program. - * 'struct pt_regs' is a type mismatch for socket - * filter that should be using 'struct __sk_buff'. - */ - goto out; } ret = do_check(env); @@ -10489,14 +22283,14 @@ out: if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); - if (ret) - /* clean aux data in case subprog was rejected */ - sanitize_insn_aux_data(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) @@ -10515,25 +22309,50 @@ 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; } @@ -10576,21 +22395,44 @@ static void print_verification_stats(struct bpf_verifier_env *env) 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; + struct btf *btf; const char *mname; + int 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", @@ -10599,8 +22441,8 @@ 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", @@ -10608,8 +22450,15 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + err = bpf_struct_ops_supported(st_ops, __btf_member_bit_offset(t, member) / 8); + 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", @@ -10618,6 +22467,17 @@ 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; + } + + /* btf_ctx_access() used this to provide argument type info */ + prog->aux->ctx_arg_info = + st_ops_desc->arg_info[member_idx].info; + prog->aux->ctx_arg_info_size = + st_ops_desc->arg_info[member_idx].cnt; + prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; @@ -10626,63 +22486,84 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } #define SECURITY_PREFIX "security_" -static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr) +static int check_attach_modify_return(unsigned long addr, const char *func_name) { if (within_error_injection_list(addr) || - !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name, - sizeof(SECURITY_PREFIX) - 1)) + !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1)) return 0; return -EINVAL; } -static int check_attach_btf_id(struct bpf_verifier_env *env) +/* list of non-sleepable functions that are otherwise on + * ALLOW_ERROR_INJECTION list + */ +BTF_SET_START(btf_non_sleepable_error_inject) +/* Three functions below can be called from sleepable and non-sleepable context. + * 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) +{ + return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id); +} + +int bpf_check_attach_target(struct bpf_verifier_log *log, + const struct bpf_prog *prog, + const struct bpf_prog *tgt_prog, + u32 btf_id, + struct bpf_attach_target_info *tgt_info) { - struct bpf_prog *prog = env->prog; bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; - struct bpf_prog *tgt_prog = prog->aux->linked_prog; - u32 btf_id = prog->aux->attach_btf_id; + bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING; + char trace_symbol[KSYM_SYMBOL_LEN]; const char prefix[] = "btf_trace_"; - struct btf_func_model fmodel; + struct bpf_raw_event_map *btp; int ret = 0, subprog = -1, i; - struct bpf_trampoline *tr; const struct btf_type *t; bool conservative = true; - const char *tname; + const char *tname, *fname; struct btf *btf; - long addr; - u64 key; - - if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) - return check_struct_ops_btf_id(env); - - if (prog->type != BPF_PROG_TYPE_TRACING && - prog->type != BPF_PROG_TYPE_LSM && - !prog_extension) - return 0; + long addr = 0; + struct module *mod = NULL; if (!btf_id) { - verbose(env, "Tracing programs must provide btf_id\n"); + bpf_log(log, "Tracing programs must provide btf_id\n"); return -EINVAL; } - btf = bpf_prog_get_target_btf(prog); + btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf; if (!btf) { - verbose(env, + bpf_log(log, "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); return -EINVAL; } t = btf_type_by_id(btf, btf_id); if (!t) { - verbose(env, "attach_btf_id %u is invalid\n", btf_id); + bpf_log(log, "attach_btf_id %u is invalid\n", btf_id); return -EINVAL; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { - verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id); + bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id); return -EINVAL; } if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; + bool tgt_changes_pkt_data; + + 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) { @@ -10690,34 +22571,57 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) break; } if (subprog == -1) { - verbose(env, "Subprog %s doesn't exist\n", tname); + 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) { - verbose(env, + bpf_log(log, "Cannot replace static functions\n"); return -EINVAL; } if (!prog->jit_requested) { - verbose(env, + bpf_log(log, "Extension programs should be JITed\n"); return -EINVAL; } - env->ops = bpf_verifier_ops[tgt_prog->type]; - prog->expected_attach_type = tgt_prog->expected_attach_type; + 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; + } } if (!tgt_prog->jited) { - verbose(env, "Can attach to only JITed progs\n"); + 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. */ - verbose(env, "Cannot recursively attach\n"); + bpf_log(log, "Cannot recursively attach\n"); return -EINVAL; } if (tgt_prog->type == BPF_PROG_TYPE_TRACING && @@ -10728,165 +22632,416 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) * 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. */ - verbose(env, "Cannot extend fentry/fexit\n"); + bpf_log(log, "Cannot extend fentry/fexit\n"); return -EINVAL; } - key = ((u64)aux->id) << 32 | btf_id; } else { if (prog_extension) { - verbose(env, "Cannot replace kernel functions\n"); + bpf_log(log, "Cannot replace kernel functions\n"); return -EINVAL; } - key = btf_id; } switch (prog->expected_attach_type) { case BPF_TRACE_RAW_TP: if (tgt_prog) { - verbose(env, + bpf_log(log, "Only FENTRY/FEXIT progs are attachable to another BPF prog\n"); return -EINVAL; } if (!btf_type_is_typedef(t)) { - verbose(env, "attach_btf_id %u is not a typedef\n", + bpf_log(log, "attach_btf_id %u is not a typedef\n", btf_id); return -EINVAL; } if (strncmp(prefix, tname, sizeof(prefix) - 1)) { - verbose(env, "attach_btf_id %u points to wrong type name %s\n", + bpf_log(log, "attach_btf_id %u points to wrong type name %s\n", btf_id, tname); 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 */ return -EINVAL; - /* remember two read only pointers that are valid for - * the life time of the kernel - */ - prog->aux->attach_func_name = tname; - prog->aux->attach_func_proto = t; - prog->aux->attach_btf_trace = true; - return 0; + break; case BPF_TRACE_ITER: if (!btf_type_is_func(t)) { - verbose(env, "attach_btf_id %u is not a function\n", + bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; - prog->aux->attach_func_name = tname; - prog->aux->attach_func_proto = t; - if (!bpf_iter_prog_supported(prog)) - return -EINVAL; - ret = btf_distill_func_proto(&env->log, btf, t, - tname, &fmodel); - return ret; + ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); + if (ret) + return ret; + break; default: if (!prog_extension) return -EINVAL; - /* fallthrough */ + fallthrough; case BPF_MODIFY_RETURN: case BPF_LSM_MAC: + case BPF_LSM_CGROUP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: - prog->aux->attach_func_name = tname; - if (prog->type == BPF_PROG_TYPE_LSM) { - ret = bpf_lsm_verify_prog(&env->log, prog); - if (ret < 0) - return ret; - } - if (!btf_type_is_func(t)) { - verbose(env, "attach_btf_id %u is not a function\n", + bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } if (prog_extension && - btf_check_type_match(env, prog, btf, t)) + btf_check_type_match(log, prog, btf, t)) return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; - tr = bpf_trampoline_lookup(key); - if (!tr) - return -ENOMEM; - /* t is either vmlinux type or another program's type */ - prog->aux->attach_func_proto = t; - mutex_lock(&tr->mutex); - if (tr->func.addr) { - prog->aux->trampoline = tr; - goto out; - } - if (tgt_prog && conservative) { - prog->aux->attach_func_proto = NULL; + + if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) && + (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type || + prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type)) + return -EINVAL; + + if (tgt_prog && conservative) t = NULL; - } - ret = btf_distill_func_proto(&env->log, btf, t, - tname, &tr->func.model); + + ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); if (ret < 0) - goto out; + return ret; + if (tgt_prog) { if (subprog == 0) addr = (long) tgt_prog->bpf_func; 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) { - verbose(env, + module_put(mod); + bpf_log(log, "The address of function %s cannot be found\n", tname); - ret = -ENOENT; - goto out; + return -ENOENT; } } - if (prog->expected_attach_type == BPF_MODIFY_RETURN) { - ret = check_attach_modify_return(prog, addr); - if (ret) - verbose(env, "%s() is not modifiable\n", - prog->aux->attach_func_name); + if (prog->sleepable) { + ret = -EINVAL; + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + + /* fentry/fexit/fmod_ret progs can be sleepable if they are + * attached to ALLOW_ERROR_INJECTION and are not in denylist. + */ + if (!check_non_sleepable_error_inject(btf_id) && + within_error_injection_list(addr)) + ret = 0; + /* fentry/fexit/fmod_ret progs can also be sleepable if they are + * in the fmodret id set with the KF_SLEEPABLE flag. + */ + else { + u32 *flags = btf_kfunc_is_modify_return(btf, btf_id, + prog); + + if (flags && (*flags & KF_SLEEPABLE)) + ret = 0; + } + break; + case BPF_PROG_TYPE_LSM: + /* LSM progs check that they are attached to bpf_lsm_*() funcs. + * Only some of them are sleepable. + */ + if (bpf_lsm_is_sleepable_hook(btf_id)) + ret = 0; + break; + default: + 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, 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; + } } - if (ret) - goto out; - tr->func.addr = (void *)addr; - prog->aux->trampoline = tr; -out: - mutex_unlock(&tr->mutex); - if (ret) - bpf_trampoline_put(tr); + break; + } + 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_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) + +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; + struct bpf_prog *tgt_prog = prog->aux->dst_prog; + struct bpf_attach_target_info tgt_info = {}; + u32 btf_id = prog->aux->attach_btf_id; + struct bpf_trampoline *tr; + int ret; + u64 key; + + if (prog->type == BPF_PROG_TYPE_SYSCALL) { + 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->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; + } + + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) + return check_struct_ops_btf_id(env); + + if (prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_LSM && + prog->type != BPF_PROG_TYPE_EXT) + return 0; + + ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info); + if (ret) return ret; + + if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) { + /* to make freplace equivalent to their targets, they need to + * inherit env->ops and expected_attach_type for the rest of the + * verification + */ + env->ops = bpf_verifier_ops[tgt_prog->type]; + prog->expected_attach_type = tgt_prog->expected_attach_type; + } + + /* 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; + prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type; + } + + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { + 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; + } + + if (prog->type == BPF_PROG_TYPE_LSM) { + ret = bpf_lsm_verify_prog(&env->log, prog); + if (ret < 0) + return ret; + } else if (prog->type == BPF_PROG_TYPE_TRACING && + btf_id_set_contains(&btf_id_deny, btf_id)) { + return -EINVAL; + } + + key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); + tr = bpf_trampoline_get(key, &tgt_info); + 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; +} + +struct btf *bpf_get_btf_vmlinux(void) +{ + if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + mutex_lock(&bpf_verifier_lock); + if (!btf_vmlinux) + btf_vmlinux = btf_parse_vmlinux(); + mutex_unlock(&bpf_verifier_lock); } + return btf_vmlinux; } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, - union bpf_attr __user *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; +} + +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; /* no program is valid */ @@ -10896,10 +23051,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, /* '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); if (!env) return -ENOMEM; - log = &env->log; + + env->bt.env = env; len = (*prog)->len; env->insn_aux_data = @@ -10911,33 +23067,33 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; - is_priv = bpf_capable(); - if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { - mutex_lock(&bpf_verifier_lock); - if (!btf_vmlinux) - btf_vmlinux = btf_parse_vmlinux(); - mutex_unlock(&bpf_verifier_lock); - } + 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(); /* grab the mutex to protect few globals used by verifier */ 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; - ret = -EINVAL; - /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 || - !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK) - goto err_unlock; - } + ret = process_fd_array(env, attr, uattr); + if (ret) + goto skip_full_check; + + mark_verifier_state_clean(env); if (IS_ERR(btf_vmlinux)) { /* Either gcc or pahole or kernel are broken. */ @@ -10952,23 +23108,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - env->allow_ptr_leaks = bpf_allow_ptr_leaks(); - env->bypass_spec_v1 = bpf_bypass_spec_v1(); - env->bypass_spec_v4 = bpf_bypass_spec_v4(); - env->bpf_capable = bpf_capable(); - if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; - - ret = replace_map_fd_with_map_ptr(env); - if (ret < 0) - goto skip_full_check; - - if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env->prog); - if (ret) - goto skip_full_check; - } + 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 *), @@ -10977,6 +23119,14 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (!env->explored_states) goto skip_full_check; + 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; + ret = check_subprogs(env); if (ret < 0) goto skip_full_check; @@ -10985,27 +23135,50 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (ret < 0) goto skip_full_check; + ret = resolve_pseudo_ldimm64(env); + if (ret < 0) + goto skip_full_check; + + if (bpf_prog_is_offloaded(env->prog->aux)) { + ret = bpf_prog_offload_verifier_prep(env->prog); + if (ret) + goto skip_full_check; + } + + ret = check_cfg(env); + if (ret < 0) + goto skip_full_check; + ret = check_attach_btf_id(env); if (ret) goto skip_full_check; - ret = check_cfg(env); + ret = mark_fastcall_patterns(env); if (ret < 0) goto skip_full_check; - ret = do_check_subprogs(env); - ret = ret ?: do_check_main(env); + ret = do_check_main(env); + ret = ret ?: do_check_subprogs(env); - if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) + 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); /* instruction rewrites happen after this point */ + if (ret == 0) + ret = optimize_bpf_loop(env); + if (is_priv) { if (ret == 0) opt_hard_wire_dead_code_branches(env); @@ -11023,12 +23196,12 @@ skip_full_check: ret = convert_ctx_accesses(env); if (ret == 0) - ret = fixup_bpf_calls(env); + ret = do_misc_fixups(env); /* 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; @@ -11039,15 +23212,24 @@ skip_full_check: env->verification_time = ktime_get_ns() - start_time; 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; } - if (ret == 0 && env->used_map_cnt) { + if (ret) + goto err_release_maps; + + if (env->used_map_cnt) { /* 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]), @@ -11061,15 +23243,29 @@ skip_full_check: memcpy(env->prog->aux->used_maps, env->used_maps, sizeof(env->used_maps[0]) * env->used_map_cnt); env->prog->aux->used_map_cnt = env->used_map_cnt; + } + if (env->used_btf_cnt) { + /* 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); + if (!env->prog->aux->used_btfs) { + ret = -ENOMEM; + goto err_release_maps; + } + memcpy(env->prog->aux->used_btfs, env->used_btfs, + sizeof(env->used_btfs[0]) * env->used_btf_cnt); + env->prog->aux->used_btf_cnt = env->used_btf_cnt; + } + if (env->used_map_cnt || env->used_btf_cnt) { /* program is valid. Convert pseudo bpf_ld_imm64 into generic * bpf_ld_imm64 instructions */ convert_pseudo_ld_imm64(env); } - if (ret == 0) - adjust_btf_func(env); + adjust_btf_func(env); err_release_maps: if (!env->prog->aux->used_maps) @@ -11077,6 +23273,8 @@ err_release_maps: * them now. Otherwise free_used_maps() will release them. */ release_maps(env); + if (!env->prog->aux->used_btfs) + release_btfs(env); /* extension progs temporarily inherit the attach_type of their targets for verification purposes, so set it back to zero before returning @@ -11085,11 +23283,14 @@ 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); vfree(env->insn_aux_data); + kvfree(env->insn_hist); err_free_env: - kfree(env); + kvfree(env); return ret; } |