From 376040e47334c6dc6a939a32197acceb00fe4acf Mon Sep 17 00:00:00 2001 From: Kenny Yu Date: Mon, 24 Jan 2022 10:54:01 -0800 Subject: bpf: Add bpf_copy_from_user_task() helper This adds a helper for bpf programs to read the memory of other tasks. As an example use case at Meta, we are using a bpf task iterator program and this new helper to print C++ async stack traces for all threads of a given process. Signed-off-by: Kenny Yu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20220124185403.468466-3-kennyyu@fb.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 16a7574292a5..4a2f7041ebae 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5076,6 +5076,16 @@ union bpf_attr { * associated to *xdp_md*, at *offset*. * Return * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5269,6 +5279,7 @@ union bpf_attr { FN(xdp_get_buff_len), \ FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3-71-gd317 From 4421a582718ab81608d8486734c18083b822390d Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 30 Jan 2022 12:55:17 +0100 Subject: bpf: Make dst_port field in struct bpf_sock 16-bit wide Menglong Dong reports that the documentation for the dst_port field in struct bpf_sock is inaccurate and confusing. From the BPF program PoV, the field is a zero-padded 16-bit integer in network byte order. The value appears to the BPF user as if laid out in memory as so: offsetof(struct bpf_sock, dst_port) + 0 + 8 +16 0x00 +24 0x00 32-, 16-, and 8-bit wide loads from the field are all allowed, but only if the offset into the field is 0. 32-bit wide loads from dst_port are especially confusing. The loaded value, after converting to host byte order with bpf_ntohl(dst_port), contains the port number in the upper 16-bits. Remove the confusion by splitting the field into two 16-bit fields. For backward compatibility, allow 32-bit wide loads from offsetof(struct bpf_sock, dst_port). While at it, allow loads 8-bit loads at offset [0] and [1] from dst_port. Reported-by: Menglong Dong Signed-off-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220130115518.213259-2-jakub@cloudflare.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 3 ++- net/core/filter.c | 10 +++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4a2f7041ebae..a7f0ddedac1f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5574,7 +5574,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; diff --git a/net/core/filter.c b/net/core/filter.c index a06931c27eeb..99a05199a806 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8265,6 +8265,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); + int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; @@ -8276,7 +8277,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): - case offsetof(struct bpf_sock, dst_port): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): @@ -8285,6 +8285,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case bpf_ctx_range(struct bpf_sock, dst_port): + field_size = size == size_default ? + size_default : sizeof_field(struct bpf_sock, dst_port); + bpf_ctx_record_field_size(info, field_size); + return bpf_ctx_narrow_access_ok(off, size, field_size); + case offsetofend(struct bpf_sock, dst_port) ... + offsetof(struct bpf_sock, dst_ip4) - 1: + return false; } return size == size_default; -- cgit v1.2.3-71-gd317 From 9a69e2b385f443f244a7e8b8bcafe5ccfb0866b4 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Wed, 9 Feb 2022 19:43:32 +0100 Subject: bpf: Make remote_port field in struct bpf_sk_lookup 16-bit wide remote_port is another case of a BPF context field documented as a 32-bit value in network byte order for which the BPF context access converter generates a load of a zero-padded 16-bit integer in network byte order. First such case was dst_port in bpf_sock which got addressed in commit 4421a582718a ("bpf: Make dst_port field in struct bpf_sock 16-bit wide"). Loading 4-bytes from the remote_port offset and converting the value with bpf_ntohl() leads to surprising results, as the expected value is shifted by 16 bits. Reduce the confusion by splitting the field in two - a 16-bit field holding a big-endian integer, and a 16-bit zero-padding anonymous field that follows it. Suggested-by: Alexei Starovoitov Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220209184333.654927-2-jakub@cloudflare.com --- include/uapi/linux/bpf.h | 3 ++- net/bpf/test_run.c | 4 ++-- net/core/filter.c | 3 ++- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a7f0ddedac1f..afe3d0d7f5f2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6453,7 +6453,8 @@ struct bpf_sk_lookup { __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index cb150f756f3d..f08034500813 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1147,7 +1147,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx))) goto out; - if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) { + if (user_ctx->local_port > U16_MAX) { ret = -ERANGE; goto out; } @@ -1155,7 +1155,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat ctx.family = (u16)user_ctx->family; ctx.protocol = (u16)user_ctx->protocol; ctx.dport = (u16)user_ctx->local_port; - ctx.sport = (__force __be16)user_ctx->remote_port; + ctx.sport = user_ctx->remote_port; switch (ctx.family) { case AF_INET: diff --git a/net/core/filter.c b/net/core/filter.c index 99a05199a806..83f06d3b2c52 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10843,7 +10843,8 @@ static bool sk_lookup_is_valid_access(int off, int size, case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): - case bpf_ctx_range(struct bpf_sk_lookup, remote_port): + case offsetof(struct bpf_sk_lookup, remote_port) ... + offsetof(struct bpf_sk_lookup, local_ip4) - 1: case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); -- cgit v1.2.3-71-gd317