From: Jason Xing kerneljasonxing@gmail.com
[ Upstream commit fd93eaffb3f977b23bc0a48d4c8616e654fcf133 ]
The subsequent patch will implement BPF TX timestamping. It will call the sockops BPF program without holding the sock lock.
This breaks the current assumption that all sock ops programs will hold the sock lock. The sock's fields of the uapi's bpf_sock_ops requires this assumption.
To address this, a new "u8 is_locked_tcp_sock;" field is added. This patch sets it in the current sock_ops callbacks. The "is_fullsock" test is then replaced by the "is_locked_tcp_sock" test during sock_ops_convert_ctx_access().
The new TX timestamping callbacks added in the subsequent patch will not have this set. This will prevent unsafe access from the new timestamping callbacks.
Potentially, we could allow read-only access. However, this would require identifying which callback is read-safe-only and also requires additional BPF instruction rewrites in the covert_ctx. Since the BPF program can always read everything from a socket (e.g., by using bpf_core_cast), this patch keeps it simple and disables all read and write access to any socket fields through the bpf_sock_ops UAPI from the new TX timestamping callback.
Moreover, note that some of the fields in bpf_sock_ops are specific to tcp_sock, and sock_ops currently only supports tcp_sock. In the future, UDP timestamping will be added, which will also break this assumption. The same idea used in this patch will be reused. Considering that the current sock_ops only supports tcp_sock, the variable is named is_locked_"tcp"_sock.
Signed-off-by: Jason Xing kerneljasonxing@gmail.com Signed-off-by: Martin KaFai Lau martin.lau@kernel.org Link: https://patch.msgid.link/20250220072940.99994-4-kerneljasonxing@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/filter.h | 1 + include/net/tcp.h | 1 + net/core/filter.c | 8 ++++---- net/ipv4/tcp_input.c | 2 ++ net/ipv4/tcp_output.c | 2 ++ 5 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h index a3ea462815957..d36d5d5180b11 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1508,6 +1508,7 @@ struct bpf_sock_ops_kern { void *skb_data_end; u8 op; u8 is_fullsock; + u8 is_locked_tcp_sock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling diff --git a/include/net/tcp.h b/include/net/tcp.h index 2d08473a6dc00..33c50ea976c88 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2671,6 +2671,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_owned_by_me(sk); }
diff --git a/net/core/filter.c b/net/core/filter.c index b0df9b7d16d3f..5fc520c815aee 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10366,10 +10366,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ - is_fullsock), \ + is_locked_tcp_sock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ - is_fullsock)); \ + is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ @@ -10454,10 +10454,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ - is_fullsock), \ + is_locked_tcp_sock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ - is_fullsock)); \ + is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1b09b4d76c296..d1ed4ac74e1d0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -169,6 +169,7 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB; sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
@@ -185,6 +186,7 @@ static void bpf_skops_established(struct sock *sk, int bpf_op, memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = bpf_op; sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ if (skb) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6031d7f7f5198..2398b0fc62225 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -525,6 +525,7 @@ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, sock_owned_by_me(sk);
sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; }
@@ -570,6 +571,7 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, sock_owned_by_me(sk);
sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; }