Commit 90384824 authored by Willem de Bruijn's avatar Willem de Bruijn Committed by Jakub Kicinski

selftests/net: toeplitz: fix race on tpacket_v3 block close

Avoid race between process wakeup and tpacket_v3 block timeout.

The test waits for cfg_timeout_msec for packets to arrive. Packets
arrive in tpacket_v3 rings, which pass packets ("frames") to the
process in batches ("blocks"). The sk waits for req3.tp_retire_blk_tov
msec to release a block.

Set the block timeout lower than the process waiting time, else
the process may find that no block has been released by the time it
scans the socket list. Convert to a ring of more than one, smaller,
blocks with shorter timeouts. Blocks must be page aligned, so >= 64KB.

Fixes: 5ebfb4cc ("selftests/net: toeplitz test")
Signed-off-by: default avatarWillem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230118151847.4124260-1-willemdebruijn.kernel@gmail.comSigned-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 8ccc9936
...@@ -215,7 +215,7 @@ static char *recv_frame(const struct ring_state *ring, char *frame) ...@@ -215,7 +215,7 @@ static char *recv_frame(const struct ring_state *ring, char *frame)
} }
/* A single TPACKET_V3 block can hold multiple frames */ /* A single TPACKET_V3 block can hold multiple frames */
static void recv_block(struct ring_state *ring) static bool recv_block(struct ring_state *ring)
{ {
struct tpacket_block_desc *block; struct tpacket_block_desc *block;
char *frame; char *frame;
...@@ -223,7 +223,7 @@ static void recv_block(struct ring_state *ring) ...@@ -223,7 +223,7 @@ static void recv_block(struct ring_state *ring)
block = (void *)(ring->mmap + ring->idx * ring_block_sz); block = (void *)(ring->mmap + ring->idx * ring_block_sz);
if (!(block->hdr.bh1.block_status & TP_STATUS_USER)) if (!(block->hdr.bh1.block_status & TP_STATUS_USER))
return; return false;
frame = (char *)block; frame = (char *)block;
frame += block->hdr.bh1.offset_to_first_pkt; frame += block->hdr.bh1.offset_to_first_pkt;
...@@ -235,6 +235,8 @@ static void recv_block(struct ring_state *ring) ...@@ -235,6 +235,8 @@ static void recv_block(struct ring_state *ring)
block->hdr.bh1.block_status = TP_STATUS_KERNEL; block->hdr.bh1.block_status = TP_STATUS_KERNEL;
ring->idx = (ring->idx + 1) % ring_block_nr; ring->idx = (ring->idx + 1) % ring_block_nr;
return true;
} }
/* simple test: sleep once unconditionally and then process all rings */ /* simple test: sleep once unconditionally and then process all rings */
...@@ -245,7 +247,7 @@ static void process_rings(void) ...@@ -245,7 +247,7 @@ static void process_rings(void)
usleep(1000 * cfg_timeout_msec); usleep(1000 * cfg_timeout_msec);
for (i = 0; i < num_cpus; i++) for (i = 0; i < num_cpus; i++)
recv_block(&rings[i]); do {} while (recv_block(&rings[i]));
fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n", fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n",
frames_received - frames_nohash - frames_error, frames_received - frames_nohash - frames_error,
...@@ -257,12 +259,12 @@ static char *setup_ring(int fd) ...@@ -257,12 +259,12 @@ static char *setup_ring(int fd)
struct tpacket_req3 req3 = {0}; struct tpacket_req3 req3 = {0};
void *ring; void *ring;
req3.tp_retire_blk_tov = cfg_timeout_msec; req3.tp_retire_blk_tov = cfg_timeout_msec / 8;
req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH; req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
req3.tp_frame_size = 2048; req3.tp_frame_size = 2048;
req3.tp_frame_nr = 1 << 10; req3.tp_frame_nr = 1 << 10;
req3.tp_block_nr = 2; req3.tp_block_nr = 16;
req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr; req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr;
req3.tp_block_size /= req3.tp_block_nr; req3.tp_block_size /= req3.tp_block_nr;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment