Commit 74836ec8 authored by Jakub Kicinski's avatar Jakub Kicinski Committed by David S. Miller
Browse files

tls: rx: strp: don't use GFP_KERNEL in softirq context 



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: 84c61fe1 ("tls: rx: do not use the standard strparser")
Tested-by: default avatarShai Amiram <samiram@nvidia.com>
Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
Reviewed-by: default avatarSimon Horman <simon.horman@corigine.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent eca9bfaf

net/tls/tls_sw.c

+4 −0
Original line number Diff line number Diff line
@@ -2304,10 +2304,14 @@ static void tls_data_ready(struct sock *sk) 
	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;



	trace_sk_data_ready(sk);



	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) {