Jakub Kicinski b026755cc9 tls: rx: strp: don't use GFP_KERNEL in softirq context ...

commit 74836ec828 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: 84c61fe1a7 ("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>

2023-06-09 10:34:29 +02:00

..

Kconfig

…

Makefile

tls: rx: async: hold onto the input skb

2022-07-18 11:24:11 +01:00

tls_device_fallback.c

net/tls: Fix memory leak in tls_enc_skb() and tls_sw_fallback_init()

2022-11-11 20:08:17 -08:00

tls_device.c

tls: rx: strp: preserve decryption status of skbs when needed

2023-06-05 09:26:18 +02:00

tls_main.c

net: deal with most data-races in sk_wait_event()

2023-05-24 17:32:32 +01:00

tls_proc.c

tls: rx: add counter for NoPad violations

2022-07-11 19:48:33 -07:00

tls_strp.c

tls: improve lockless access safety of tls_err_abort()

2023-06-09 10:34:01 +02:00

tls_sw.c

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

2023-06-09 10:34:29 +02:00

tls_toe.c

tls: create an internal header

2022-07-08 18:38:45 -07:00

tls.h

tls: rx: strp: preserve decryption status of skbs when needed

2023-06-05 09:26:18 +02:00

trace.c

…

trace.h

…