From 92de36080c93296ef9005690705cba260b9bd68a Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jul 2024 08:34:39 -0700 Subject: bpf: Fail verification for sign-extension of packet data/data_end/data_meta syzbot reported a kernel crash due to commit 1f1e864b6555 ("bpf: Handle sign-extenstin ctx member accesses"). The reason is due to sign-extension of 32-bit load for packet data/data_end/data_meta uapi field. The original code looks like: r2 = *(s32 *)(r1 + 76) /* load __sk_buff->data */ r3 = *(u32 *)(r1 + 80) /* load __sk_buff->data_end */ r0 = r2 r0 += 8 if r3 > r0 goto +1 ... Note that __sk_buff->data load has 32-bit sign extension. After verification and convert_ctx_accesses(), the final asm code looks like: r2 = *(u64 *)(r1 +208) r2 = (s32)r2 r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 ... Note that 'r2 = (s32)r2' may make the kernel __sk_buff->data address invalid which may cause runtime failure. Currently, in C code, typically we have void *data = (void *)(long)skb->data; void *data_end = (void *)(long)skb->data_end; ... and it will generate r2 = *(u64 *)(r1 +208) r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 If we allow sign-extension, void *data = (void *)(long)(int)skb->data; void *data_end = (void *)(long)skb->data_end; ... the generated code looks like r2 = *(u64 *)(r1 +208) r2 <<= 32 r2 s>>= 32 r3 = *(u64 *)(r1 +80) r0 = r2 r0 += 8 if r3 > r0 goto pc+1 and this will cause verification failure since "r2 <<= 32" is not allowed as "r2" is a packet pointer. To fix this issue for case r2 = *(s32 *)(r1 + 76) /* load __sk_buff->data */ this patch added additional checking in is_valid_access() callback function for packet data/data_end/data_meta access. If those accesses are with sign-extenstion, the verification will fail. [1] https://lore.kernel.org/bpf/000000000000c90eee061d236d37@google.com/ Reported-by: syzbot+ad9ec60c8eaf69e6f99c@syzkaller.appspotmail.com Fixes: 1f1e864b6555 ("bpf: Handle sign-extenstin ctx member accesses") Acked-by: Eduard Zingerman Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20240723153439.2429035-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko --- net/core/filter.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index f3c72cf86099..78a6f746ea0b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8579,13 +8579,16 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; + case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range(struct __sk_buff, data_end): + if (info->is_ldsx || size != size_default) + return false; + break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): - case bpf_ctx_range(struct __sk_buff, data): - case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; break; @@ -9029,6 +9032,14 @@ static bool xdp_is_valid_access(int off, int size, } } return false; + } else { + switch (off) { + case offsetof(struct xdp_md, data_meta): + case offsetof(struct xdp_md, data): + case offsetof(struct xdp_md, data_end): + if (info->is_ldsx) + return false; + } } switch (off) { @@ -9354,12 +9365,12 @@ static bool flow_dissector_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, data): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; -- cgit v1.2.3-73-gaa49b From b6ab50902724a27f1fc7136927c27d29f9ba01c6 Mon Sep 17 00:00:00 2001 From: Yu Jiaoliang Date: Wed, 21 Aug 2024 15:37:08 +0800 Subject: bpf: Use kmemdup_array instead of kmemdup for multiple allocation Let the kmemdup_array() take care about multiplication and possible overflows. Signed-off-by: Yu Jiaoliang Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240821073709.4067177-1-yujiaoliang@vivo.com --- net/core/filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index 78a6f746ea0b..ecf2ddf633bf 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1265,8 +1265,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. */ - old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter), - GFP_KERNEL | __GFP_NOWARN); + old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter), + GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; -- cgit v1.2.3-73-gaa49b From 32556ce93bc45c730829083cb60f95a2728ea48b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 13 Sep 2024 21:17:48 +0200 Subject: bpf: Fix helper writes to read-only maps Lonial found an issue that despite user- and BPF-side frozen BPF map (like in case of .rodata), it was still possible to write into it from a BPF program side through specific helpers having ARG_PTR_TO_{LONG,INT} as arguments. In check_func_arg() when the argument is as mentioned, the meta->raw_mode is never set. Later, check_helper_mem_access(), under the case of PTR_TO_MAP_VALUE as register base type, it assumes BPF_READ for the subsequent call to check_map_access_type() and given the BPF map is read-only it succeeds. The helpers really need to be annotated as ARG_PTR_TO_{LONG,INT} | MEM_UNINIT when results are written into them as opposed to read out of them. The latter indicates that it's okay to pass a pointer to uninitialized memory as the memory is written to anyway. However, ARG_PTR_TO_{LONG,INT} is a special case of ARG_PTR_TO_FIXED_SIZE_MEM just with additional alignment requirement. So it is better to just get rid of the ARG_PTR_TO_{LONG,INT} special cases altogether and reuse the fixed size memory types. For this, add MEM_ALIGNED to additionally ensure alignment given these helpers write directly into the args via * = val. The .arg*_size has been initialized reflecting the actual sizeof(*). MEM_ALIGNED can only be used in combination with MEM_FIXED_SIZE annotated argument types, since in !MEM_FIXED_SIZE cases the verifier does not know the buffer size a priori and therefore cannot blindly write * = val. Fixes: 57c3bb725a3d ("bpf: Introduce ARG_PTR_TO_{INT,LONG} arg types") Reported-by: Lonial Con Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Shung-Hsi Yu Link: https://lore.kernel.org/r/20240913191754.13290-3-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 +++++-- kernel/bpf/helpers.c | 6 ++++-- kernel/bpf/syscall.c | 3 ++- kernel/bpf/verifier.c | 41 +++++------------------------------------ kernel/trace/bpf_trace.c | 6 ++++-- net/core/filter.c | 6 ++++-- 6 files changed, 24 insertions(+), 45 deletions(-) (limited to 'net/core') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7f3e8477d5e7..0c3893c47171 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -695,6 +695,11 @@ enum bpf_type_flag { /* DYNPTR points to xdp_buff */ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), + /* Memory must be aligned on some architectures, used in combination with + * MEM_FIXED_SIZE. + */ + MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -732,8 +737,6 @@ enum bpf_arg_type { ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ - ARG_PTR_TO_INT, /* pointer to int */ - ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5404bb964d83..5e97fdc6b20f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -537,7 +537,8 @@ const struct bpf_func_proto bpf_strtol_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_size = sizeof(s64), }; BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags, @@ -563,7 +564,8 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_size = sizeof(u64), }; BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6988e432fc3d..a7cd3719e26a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5954,7 +5954,8 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_LONG, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_size = sizeof(u64), }; static const struct bpf_func_proto * diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 068f763dcefb..7d62fd576089 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8301,16 +8301,6 @@ static bool arg_type_is_dynptr(enum bpf_arg_type type) return base_type(type) == ARG_PTR_TO_DYNPTR; } -static int int_ptr_type_to_size(enum bpf_arg_type type) -{ - if (type == ARG_PTR_TO_INT) - return sizeof(u32); - else if (type == ARG_PTR_TO_LONG) - return sizeof(u64); - - return -EINVAL; -} - static int resolve_map_arg_type(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_arg_type *arg_type) @@ -8383,16 +8373,6 @@ static const struct bpf_reg_types mem_types = { }, }; -static const struct bpf_reg_types int_ptr_types = { - .types = { - PTR_TO_STACK, - PTR_TO_PACKET, - PTR_TO_PACKET_META, - PTR_TO_MAP_KEY, - PTR_TO_MAP_VALUE, - }, -}; - static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE, @@ -8453,8 +8433,6 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, [ARG_PTR_TO_RINGBUF_MEM] = &ringbuf_mem_types, - [ARG_PTR_TO_INT] = &int_ptr_types, - [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK] = &stack_ptr_types, @@ -9017,9 +8995,11 @@ 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], false, meta); + if (err) + return err; + if (arg_type & MEM_ALIGNED) + err = check_ptr_alignment(env, reg, 0, fn->arg_size[arg], true); } break; case ARG_CONST_SIZE: @@ -9044,17 +9024,6 @@ skip_type_check: if (err) return err; break; - case ARG_PTR_TO_INT: - case ARG_PTR_TO_LONG: - { - int size = int_ptr_type_to_size(arg_type); - - err = check_helper_mem_access(env, regno, size, false, meta); - if (err) - return err; - err = check_ptr_alignment(env, reg, 0, size, true); - break; - } case ARG_PTR_TO_CONST_STR: { err = check_reg_const_str(env, reg, regno); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 68b5905c6eb5..b3283c250e27 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1202,7 +1202,8 @@ 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_LONG, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u64), }; BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) @@ -1218,7 +1219,8 @@ 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_LONG, + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg2_size = sizeof(u64), }; BPF_CALL_1(get_func_arg_cnt, void *, ctx) diff --git a/net/core/filter.c b/net/core/filter.c index ecf2ddf633bf..d0550c87e520 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6346,7 +6346,8 @@ 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_INT, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6357,7 +6358,8 @@ 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_INT, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; -- cgit v1.2.3-73-gaa49b From 4b3786a6c5397dc220b1483d8e2f4867743e966f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 13 Sep 2024 21:17:50 +0200 Subject: bpf: Zero former ARG_PTR_TO_{LONG,INT} args in case of error For all non-tracing helpers which formerly had ARG_PTR_TO_{LONG,INT} as input arguments, zero the value for the case of an error as otherwise it could leak memory. For tracing, it is not needed given CAP_PERFMON can already read all kernel memory anyway hence bpf_get_func_arg() and bpf_get_func_ret() is skipped in here. Also, the MTU helpers mtu_len pointer value is being written but also read. Technically, the MEM_UNINIT should not be there in order to always force init. Removing MEM_UNINIT needs more verifier rework though: MEM_UNINIT right now implies two things actually: i) write into memory, ii) memory does not have to be initialized. If we lift MEM_UNINIT, it then becomes: i) read into memory, ii) memory must be initialized. This means that for bpf_*_check_mtu() we're readding the issue we're trying to fix, that is, it would then be able to write back into things like .rodata BPF maps. Follow-up work will rework the MEM_UNINIT semantics such that the intent can be better expressed. For now just clear the *mtu_len on error path which can be lifted later again. Fixes: 8a67f2de9b1d ("bpf: expose bpf_strtol and bpf_strtoul to all program types") Fixes: d7a4cb9b6705 ("bpf: Introduce bpf_strtol and bpf_strtoul helpers") Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/e5edd241-59e7-5e39-0ee5-a51e31b6840a@iogearbox.net Link: https://lore.kernel.org/r/20240913191754.13290-5-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- kernel/bpf/helpers.c | 2 ++ kernel/bpf/syscall.c | 1 + net/core/filter.c | 44 +++++++++++++++++++++++--------------------- 3 files changed, 26 insertions(+), 21 deletions(-) (limited to 'net/core') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5e97fdc6b20f..1a43d06eab28 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -523,6 +523,7 @@ BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags, long long _res; int err; + *res = 0; err = __bpf_strtoll(buf, buf_len, flags, &_res); if (err < 0) return err; @@ -548,6 +549,7 @@ BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags, bool is_negative; int err; + *res = 0; err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); if (err < 0) return err; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a7cd3719e26a..593822d3d393 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5934,6 +5934,7 @@ static const struct bpf_func_proto bpf_sys_close_proto = { BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) { + *res = 0; if (flags) return -EINVAL; diff --git a/net/core/filter.c b/net/core/filter.c index d0550c87e520..e4a4454df5f9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6262,20 +6262,25 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; int skb_len, dev_len; - int mtu; + int mtu = 0; - if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) - return -EINVAL; + if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) { + ret = -EINVAL; + goto out; + } - if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) - return -EINVAL; + if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) { + ret = -EINVAL; + goto out; + } dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) - return -ENODEV; + if (unlikely(!dev)) { + ret = -ENODEV; + goto out; + } mtu = READ_ONCE(dev->mtu); - dev_len = mtu + dev->hard_header_len; /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ @@ -6293,15 +6298,12 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; - if (flags & BPF_MTU_CHK_SEGS && !skb_gso_validate_network_len(skb, mtu)) ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; } out: - /* BPF verifier guarantees valid pointer */ *mtu_len = mtu; - return ret; } @@ -6311,19 +6313,21 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; - int mtu, dev_len; + int mtu = 0, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ - if (unlikely(flags)) - return -EINVAL; + if (unlikely(flags)) { + ret = -EINVAL; + goto out; + } dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) - return -ENODEV; + if (unlikely(!dev)) { + ret = -ENODEV; + goto out; + } mtu = READ_ONCE(dev->mtu); - - /* Add L2-header as dev MTU is L3 size */ dev_len = mtu + dev->hard_header_len; /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ @@ -6333,10 +6337,8 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; - - /* BPF verifier guarantees valid pointer */ +out: *mtu_len = mtu; - return ret; } -- cgit v1.2.3-73-gaa49b