From: Jakub Kicinski kuba@kernel.org
commit 74836ec828fe17b63f2006fdbf53311d691396bf upstream.
When receive buffer is small, or the TCP rx queue looks too complicated to bother using it directly - we allocate a new skb and copy data into it.
We already use sk->sk_allocation... but nothing actually sets it to GFP_ATOMIC on the ->sk_data_ready() path.
Users of HW offload are far more likely to experience problems due to scheduling while atomic. "Copy mode" is very rarely triggered with SW crypto.
Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram samiram@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tls/tls_sw.c | 4 ++++ 1 file changed, 4 insertions(+)
--- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2289,8 +2289,12 @@ static void tls_data_ready(struct sock * struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_psock *psock; + gfp_t alloc_save;
+ alloc_save = sk->sk_allocation; + sk->sk_allocation = GFP_ATOMIC; tls_strp_data_ready(&ctx->strp); + sk->sk_allocation = alloc_save;
psock = sk_psock_get(sk); if (psock) {