xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

IB/rxe: Offload CRC calculation when possible

Browse Source 
Use CPU ability to perform CRC calculations, by
replacing direct calls to crc32_le() with crypto_shash_updata().

The overall performance gain measured with ib_send_bw tool is 10% and it
was tested on "Intel CPU ES-2660 v2 @ 2.20Ghz" CPU.

ib_send_bw -d rxe0  -x 1 -n 9000 -e  -s $((1024 * 1024 )) -l 100

---------------------------------------------------------------------------------------------
|             | bytes   | iterations | BW peak[MB/sec] | BW average[MB/sec] | MsgRate[Mpps] |
---------------------------------------------------------------------------------------------
| crc32_le    | 1048576 | 9000       | inf             | 497.60             | 0.000498      |
| CRC offload | 1048576 | 9000       | inf             | 546.70             | 0.000547      |
---------------------------------------------------------------------------------------------

Fixes: 8700e3e7c4 ("Soft RoCE driver")
Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This commit is contained in:
yonatanc
2017-04-20 20:55:55 +03:00
committed by Doug Ledford
parent 0d38ac8a8b
commit cee2688e3c
9 changed files with 44 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
drivers/infiniband/sw/rxe/rxe.h
View File

@@ -50,6 +50,7 @@
#include <rdma/ib_umem.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_addr.h>
#include <crypto/hash.h>
#include "rxe_net.h"
#include "rxe_opcode.h"
@@ -64,6 +65,25 @@
#define RXE_ROCE_V2_SPORT (0xc000)
static inline u32 rxe_crc32(struct rxe_dev *rxe,
u32 crc, void *next, size_t len)
{
int err;
SHASH_DESC_ON_STACK(shash, rxe->tfm);
shash->tfm = rxe->tfm;
shash->flags = 0;
*(u32 *)shash_desc_ctx(shash) = crc;
err = crypto_shash_update(shash, next, len);
if (unlikely(err)) {
pr_warn_ratelimited("failed crc calculation, err: %d\n", err);
return crc32_le(crc, next, len);
}
return *(u32 *)shash_desc_ctx(shash);
}
int rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu);
int rxe_add(struct rxe_dev *rxe, unsigned int mtu);