From 1f97c03f43fadc407de5b5cb01c07755053e1c22 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 22 Oct 2024 21:01:33 +0800 Subject: bpf: Preserve param->string when parsing mount options In bpf_parse_param(), keep the value of param->string intact so it can be freed later. Otherwise, the kmalloc area pointed to by param->string will be leaked as shown below: unreferenced object 0xffff888118c46d20 (size 8): comm "new_name", pid 12109, jiffies 4295580214 hex dump (first 8 bytes): 61 6e 79 00 38 c9 5c 7e any.8.\~ backtrace (crc e1b7f876): [<00000000c6848ac7>] kmemleak_alloc+0x4b/0x80 [<00000000de9f7d00>] __kmalloc_node_track_caller_noprof+0x36e/0x4a0 [<000000003e29b886>] memdup_user+0x32/0xa0 [<0000000007248326>] strndup_user+0x46/0x60 [<0000000035b3dd29>] __x64_sys_fsconfig+0x368/0x3d0 [<0000000018657927>] x64_sys_call+0xff/0x9f0 [<00000000c0cabc95>] do_syscall_64+0x3b/0xc0 [<000000002f331597>] entry_SYSCALL_64_after_hwframe+0x4b/0x53 Fixes: 6c1752e0b6ca ("bpf: Support symbolic BPF FS delegation mount options") Signed-off-by: Hou Tao Signed-off-by: Andrii Nakryiko Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20241022130133.3798232-1-houtao@huaweicloud.com --- kernel/bpf/inode.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index d8fc5eba529d..9aaf5124648b 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -880,7 +880,7 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) const struct btf_type *enum_t; const char *enum_pfx; u64 *delegate_msk, msk = 0; - char *p; + char *p, *str; int val; /* ignore errors, fallback to hex */ @@ -911,7 +911,8 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) return -EINVAL; } - while ((p = strsep(¶m->string, ":"))) { + 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)) { -- cgit v1.2.3 From 6fad274f06f038c29660aa53fbad14241c9fd976 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 21 Oct 2024 17:28:05 +0200 Subject: bpf: Add MEM_WRITE attribute Add a MEM_WRITE attribute for BPF helper functions which can be used in bpf_func_proto to annotate an argument type in order to let the verifier know that the helper writes into the memory passed as an argument. In the past MEM_UNINIT has been (ab)used for this function, but the latter merely tells the verifier that the passed memory can be uninitialized. There have been bugs with overloading the latter but aside from that there are also cases where the passed memory is read + written which currently cannot be expressed, see also 4b3786a6c539 ("bpf: Zero former ARG_PTR_TO_{LONG,INT} args in case of error"). Signed-off-by: Daniel Borkmann Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241021152809.33343-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 14 +++++++++++--- kernel/bpf/helpers.c | 10 +++++----- kernel/bpf/ringbuf.c | 2 +- kernel/bpf/syscall.c | 2 +- kernel/trace/bpf_trace.c | 4 ++-- net/core/filter.c | 4 ++-- 6 files changed, 22 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 19d8ca8ac960..bdadb0bb6cec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -635,6 +635,7 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ @@ -700,6 +701,13 @@ enum bpf_type_flag { */ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + /* MEM is being written to, often combined with MEM_UNINIT. Non-presence + * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the + * MEM_UNINIT means that memory needs to be initialized since it is also + * read. + */ + MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -758,10 +766,10 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, - /* pointer to memory does not need to be initialized, helper function must fill - * all bytes or clear them in error case. + /* Pointer to memory does not need to be initialized, since helper function + * fills all bytes or clears them in error case. */ - ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1a43d06eab28..ca3f0a2e5ed5 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -111,7 +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_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) @@ -124,7 +124,7 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu) @@ -538,7 +538,7 @@ const struct bpf_func_proto bpf_strtol_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(s64), }; @@ -566,7 +566,7 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; @@ -1742,7 +1742,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index de3b681d1d13..e1cfe890e0be 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -632,7 +632,7 @@ const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8cfa7183d2ef..67179529080b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5892,7 +5892,7 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 3bd402fa62a4..95b6b3b16bac 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1202,7 +1202,7 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u64), }; @@ -1219,7 +1219,7 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = { .func = get_func_ret, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg2_size = sizeof(u64), }; diff --git a/net/core/filter.c b/net/core/filter.c index cb272b35d484..16b324d519da 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6368,7 +6368,7 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6380,7 +6380,7 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, -- cgit v1.2.3 From 8ea607330a39184f51737c6ae706db7fdca7628e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 21 Oct 2024 17:28:06 +0200 Subject: bpf: Fix overloading of MEM_UNINIT's meaning Lonial reported an issue in the BPF verifier where check_mem_size_reg() has the following code: 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; This means that writes are not checked when the register containing the size of the passed buffer has not a fixed size. Through this bug, a BPF program can write to a map which is marked as read-only, for example, .rodata global maps. The problem is that MEM_UNINIT's initial meaning that "the passed buffer to the BPF helper does not need to be initialized" which was added back in commit 435faee1aae9 ("bpf, verifier: add ARG_PTR_TO_RAW_STACK type") got overloaded over time with "the passed buffer is being written to". The problem however is that checks such as the above which were added later via 06c1c049721a ("bpf: allow helpers access to variable memory") set meta to NULL in order force the user to always initialize the passed buffer to the helper. Due to the current double meaning of MEM_UNINIT, this bypasses verifier write checks to the memory (not boundary checks though) and only assumes the latter memory is read instead. Fix this by reverting MEM_UNINIT back to its original meaning, and having MEM_WRITE as an annotation to BPF helpers in order to then trigger the BPF verifier checks for writing to memory. Some notes: check_arg_pair_ok() ensures that for ARG_CONST_SIZE{,_OR_ZERO} we can access fn->arg_type[arg - 1] since it must contain a preceding ARG_PTR_TO_MEM. For check_mem_reg() the meta argument can be removed altogether since we do check both BPF_READ and BPF_WRITE. Same for the equivalent check_kfunc_mem_size_reg(). Fixes: 7b3552d3f9f6 ("bpf: Reject writes for PTR_TO_MAP_KEY in check_helper_mem_access") Fixes: 97e6d7dab1ca ("bpf: Check PTR_TO_MEM | MEM_RDONLY in check_helper_mem_access") Fixes: 15baa55ff5b0 ("bpf/verifier: allow all functions to read user provided context") Reported-by: Lonial Con Signed-off-by: Daniel Borkmann Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241021152809.33343-2-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 73 ++++++++++++++++++++++++--------------------------- 1 file changed, 35 insertions(+), 38 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 411ab1b57af4..f9e2f1cd4975 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7438,7 +7438,8 @@ mark: } 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]; @@ -7450,7 +7451,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7458,15 +7459,13 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: - if (check_map_access_type(env, regno, reg->off, access_size, - meta && meta->raw_mode ? BPF_WRITE : - BPF_READ)) + if (check_map_access_type(env, regno, reg->off, access_size, access_type)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7477,7 +7476,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7505,7 +7504,6 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, * Dynamically check it now. */ if (!env->ops->convert_ctx_access) { - enum bpf_access_type atype = meta && meta->raw_mode ? BPF_WRITE : BPF_READ; int offset = access_size - 1; /* Allow zero-byte read from PTR_TO_CTX */ @@ -7513,7 +7511,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return zero_size_allowed ? 0 : -EACCES; return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, - atype, -1, false, false); + access_type, -1, false, false); } fallthrough; @@ -7538,6 +7536,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, */ 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) { @@ -7553,15 +7552,12 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, */ meta->msize_max_value = reg->umax_value; - /* The register is SCALAR_VALUE; the access check - * happens using its boundaries. + /* The register is SCALAR_VALUE; the access check happens using + * its boundaries. For unprivileged variable accesses, disable + * raw mode so that the program is required to initialize all + * the memory that the helper could just partially fill up. */ if (!tnum_is_const(reg->var_off)) - /* For unprivileged variable accesses, disable raw - * mode so that the program is required to - * initialize all the memory that the helper could - * just partially fill up. - */ meta = NULL; if (reg->smin_value < 0) { @@ -7581,9 +7577,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, regno); return -EACCES; } - err = check_helper_mem_access(env, regno - 1, - reg->umax_value, - zero_size_allowed, meta); + err = check_helper_mem_access(env, regno - 1, reg->umax_value, + access_type, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); return err; @@ -7594,13 +7589,11 @@ static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; - struct bpf_call_arg_meta meta; int err; if (register_is_null(reg)) return 0; - memset(&meta, 0, sizeof(meta)); /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. @@ -7610,10 +7603,8 @@ static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg mark_ptr_not_null_reg(reg); } - err = check_helper_mem_access(env, regno, mem_size, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); + err = check_helper_mem_access(env, regno, mem_size, BPF_READ, true, NULL); + err = err ?: check_helper_mem_access(env, regno, mem_size, BPF_WRITE, true, NULL); if (may_be_null) *reg = saved_reg; @@ -7639,13 +7630,12 @@ static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg mark_ptr_not_null_reg(mem_reg); } - err = check_mem_size_reg(env, reg, regno, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); + err = check_mem_size_reg(env, reg, regno, BPF_READ, true, &meta); + err = err ?: check_mem_size_reg(env, reg, regno, BPF_WRITE, true, &meta); if (may_be_null) *mem_reg = saved_reg; + return err; } @@ -8948,9 +8938,8 @@ skip_type_check: 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); + err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, + BPF_READ, false, NULL); break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) @@ -8965,9 +8954,9 @@ skip_type_check: return -EACCES; } meta->raw_mode = arg_type & MEM_UNINIT; - err = check_helper_mem_access(env, regno, - meta->map_ptr->value_size, false, - meta); + err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); break; case ARG_PTR_TO_PERCPU_BTF_ID: if (!reg->btf_id) { @@ -9009,7 +8998,9 @@ skip_type_check: */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { - err = check_helper_mem_access(env, regno, fn->arg_size[arg], false, meta); + err = check_helper_mem_access(env, regno, fn->arg_size[arg], + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); if (err) return err; if (arg_type & MEM_ALIGNED) @@ -9017,10 +9008,16 @@ skip_type_check: } break; case ARG_CONST_SIZE: - err = check_mem_size_reg(env, reg, regno, false, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + false, meta); break; case ARG_CONST_SIZE_OR_ZERO: - err = check_mem_size_reg(env, reg, regno, true, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + true, meta); break; case ARG_PTR_TO_DYNPTR: err = process_dynptr_func(env, regno, insn_idx, arg_type, 0); -- cgit v1.2.3 From 0ee288e69d033850bc87abe0f9cc3ada24763d7f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 Oct 2024 22:03:52 +0200 Subject: bpf,perf: Fix perf_event_detach_bpf_prog error handling Peter reported that perf_event_detach_bpf_prog might skip to release the bpf program for -ENOENT error from bpf_prog_array_copy. This can't happen because bpf program is stored in perf event and is detached and released only when perf event is freed. Let's drop the -ENOENT check and make sure the bpf program is released in any case. Fixes: 170a7e3ea070 ("bpf: bpf_prog_array_copy() should return -ENOENT if exclude_prog not found") Reported-by: Peter Zijlstra Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241023200352.3488610-1-jolsa@kernel.org Closes: https://lore.kernel.org/lkml/20241022111638.GC16066@noisy.programming.kicks-ass.net/ --- kernel/trace/bpf_trace.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 95b6b3b16bac..630b763e5240 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2216,8 +2216,6 @@ void perf_event_detach_bpf_prog(struct perf_event *event) old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); - if (ret == -ENOENT) - goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { -- cgit v1.2.3 From 9806f283140ef3e4d259b7646bd8c66026bbaac5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 23 Oct 2024 09:19:16 -0700 Subject: bpf: fix do_misc_fixups() for bpf_get_branch_snapshot() We need `goto next_insn;` at the end of patching instead of `continue;`. It currently works by accident by making verifier re-process patched instructions. Reported-by: Shung-Hsi Yu Fixes: 314a53623cd4 ("bpf: inline bpf_get_branch_snapshot() helper") Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Acked-by: Shung-Hsi Yu Link: https://lore.kernel.org/r/20241023161916.2896274-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f9e2f1cd4975..587a6c76e564 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21210,7 +21210,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_kptr_xchg inline */ -- cgit v1.2.3 From 8421d4c8762bd022cb491f2f0f7019ef51b4f0a7 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Thu, 24 Oct 2024 09:35:58 +0800 Subject: bpf: Check validity of link->type in bpf_link_show_fdinfo() If a newly-added link type doesn't invoke BPF_LINK_TYPE(), accessing bpf_link_type_strs[link->type] may result in an out-of-bounds access. To spot such missed invocations early in the future, checking the validity of link->type in bpf_link_show_fdinfo() and emitting a warning when such invocations are missed. Signed-off-by: Hou Tao Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241024013558.1135167-3-houtao@huaweicloud.com --- kernel/bpf/syscall.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 67179529080b..c5aa127ed4cc 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3069,13 +3069,17 @@ 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] = { }; - seq_printf(m, - "link_type:\t%s\n" - "link_id:\t%u\n", - bpf_link_type_strs[link->type], - link->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, -- cgit v1.2.3