Hello:
This series was applied to bpf/bpf-next.git (master) by Alexei Starovoitov ast@kernel.org:
On Mon, 7 Apr 2025 22:21:19 +0800 you wrote:
I was writing a benchmark based on sockmap + TCP and discovered several issues:
- When EAGAIN occurs, the direction of skb is incorrect, causing data loss when retry.
- When sending partial data, the offset is not recorded, leading to duplicate data being sent when retry.
- An unexpected BUG_ON() judgment in skb_linearize is triggered.
- The memory of psock->ingress_skb is not limited by the socket buffer and memcg.
[...]
Here is the summary with links: - [bpf-next,v1,1/4] bpf, sockmap: Fix data lost during EAGAIN retries https://git.kernel.org/bpf/bpf-next/c/7683167196bd - [bpf-next,v1,2/4] bpf, sockmap: fix duplicated data transmission https://git.kernel.org/bpf/bpf-next/c/3b4f14b79428 - [bpf-next,v1,3/4] bpf, sockmap: Fix panic when calling skb_linearize https://git.kernel.org/bpf/bpf-next/c/5ca2e29f6834 - [bpf-next,v1,4/4] selftest/bpf/benchs: Add benchmark for sockmap usage https://git.kernel.org/bpf/bpf-next/c/7b2fa44de5e7
You are awesome, thank you!