kernel/linux.git/tools/testing/selftests/net/tls.c, branch linux-5.11.y

selftests/tls: fix selftest with CHACHA20-POLY1305

2021-02-04T02:47:36+00:00

TLS selftests were broken also because of use of structure that was not exported to UAPI. Fix by defining the union in tests. Fixes: 4f336e88a870 (selftests/tls: add CHACHA20-POLY1305 to tls selftests) Reported-by: Rong Chen Signed-off-by: Vadim Fedorenko Link: https://lore.kernel.org/r/1612384634-5377-1-git-send-email-vfedorenko@novek.ru Signed-off-by: Jakub Kicinski

selftests/tls: fix selftests after adding ChaCha20-Poly1305

2021-01-09T22:26:30+00:00

TLS selftests where broken because of wrong variable types used. Fix it by changing u16 -> uint16_t Fixes: 4f336e88a870 ("selftests/tls: add CHACHA20-POLY1305 to tls selftests") Reported-by: kernel test robot Signed-off-by: Vadim Fedorenko Link: https://lore.kernel.org/r/1610141865-7142-1-git-send-email-vfedorenko@novek.ru Signed-off-by: Jakub Kicinski

selftests/tls: add CHACHA20-POLY1305 to tls selftests

2020-11-27T22:32:37+00:00

Add new cipher as a variant of standard tls selftests Signed-off-by: Vadim Fedorenko Signed-off-by: Jakub Kicinski

net/tls(TLS_SW): Add selftest for 'chunked' sendfile test

2020-06-09T02:01:54+00:00

This selftest tests for cases where sendfile's 'count' parameter is provided with a size greater than the intended file size. Motivation: When sendfile is provided with 'count' parameter value that is greater than the size of the file, kTLS example fails to send the file correctly. Last chunk of the file is not sent, and the data integrity is compromised. The reason is that the last chunk has MSG_MORE flag set because of which it gets added to pending records, but is not pushed. Note that if user space were to send SSL_shutdown control message, pending records would get flushed and the issue would not happen. So a shutdown control message following sendfile can mask the issue. Signed-off-by: Pooja Trivedi Signed-off-by: Mallesham Jatharkonda Signed-off-by: Josh Tway Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller

selftests: tls: run all tests for TLS 1.2 and TLS 1.3

2020-04-28T20:30:44+00:00

TLS 1.2 and TLS 1.3 differ in the implementation. Use fixture parameters to run all tests for both versions, and remove the one-off TLS 1.2 test. Signed-off-by: Jakub Kicinski Reviewed-by: Kees Cook Signed-off-by: David S. Miller

selftests: net: tls: remove recv_rcvbuf test

2019-12-15T03:53:53+00:00

This test only works when [1] is applied, which was rejected. Basically, the errors are reported and cleared. In this particular case of tls sockets, following reads will block. The test case was originally submitted with the rejected patch, but, then, was included as part of a different patchset, possibly by mistake. [1] https://lore.kernel.org/netdev/20191007035323.4360-2-jakub.kicinski@netronome.com/#t Thanks Paolo Pisati for pointing out the original patchset where this appeared. Fixes: 65190f77424d (selftests/tls: add a test for fragmented messages) Reported-by: Paolo Pisati Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Jakub Kicinski

net/tls: Fix return values to avoid ENOTSUPP

2019-12-07T04:15:39+00:00

ENOTSUPP is not available in userspace, for example: setsockopt failed, 524, Unknown error 524 Signed-off-by: Valentin Vidic Acked-by: Jakub Kicinski Signed-off-by: David S. Miller

selftests/tls: add a test for fragmented messages

2019-11-29T06:40:29+00:00

Add a sendmsg test with very fragmented messages. This should fill up sk_msg and test the boundary conditions. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller

selftests/tls: add test for concurrent recv and send

2019-11-07T01:33:32+00:00

Add a test which spawns 16 threads and performs concurrent send and recv calls on the same socket. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller

selftests/tls: add a litmus test for the socket reuse through shutdown

2019-08-05T20:15:30+00:00

Make sure that shutdown never works, and at the same time document how I tested to came to the conclusion that currently reuse is not possible. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller