IB/rxe: Offload CRC calculation when possible

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>

drivers/infiniband/sw/rxe/Kconfig

@@ -2,6 +2,7 @@ config RDMA_RXE
 	tristate "Software RDMA over Ethernet (RoCE) driver"
 	depends on INET && PCI && INFINIBAND
 	depends on NET_UDP_TUNNEL
+	depends on CRYPTO_CRC32
 	select DMA_VIRT_OPS
 	---help---
 	This driver implements the InfiniBand RDMA transport over

drivers/infiniband/sw/rxe/rxe.c

@@ -64,6 +64,8 @@ static void rxe_cleanup(struct rxe_dev *rxe)
 	rxe_pool_cleanup(&rxe->mc_elem_pool);
 
 	rxe_cleanup_ports(rxe);
+
+	crypto_free_shash(rxe->tfm);
 }
 
 /* called when all references have been dropped */

drivers/infiniband/sw/rxe/rxe.h

@@ -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);

drivers/infiniband/sw/rxe/rxe_icrc.c

@@ -87,10 +87,10 @@ u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb)
 	bth->qpn |= cpu_to_be32(~BTH_QPN_MASK);
 
 	length = hdr_size + RXE_BTH_BYTES;
-	crc = crc32_le(crc, pshdr, length);
+	crc = rxe_crc32(pkt->rxe, crc, pshdr, length);
 
 	/* And finish to compute the CRC on the remainder of the headers. */
-	crc = crc32_le(crc, pkt->hdr + RXE_BTH_BYTES,
+	crc = rxe_crc32(pkt->rxe, crc, pkt->hdr + RXE_BTH_BYTES,
 			rxe_opcode[pkt->opcode].length - RXE_BTH_BYTES);
 	return crc;
 }

drivers/infiniband/sw/rxe/rxe_mr.c

@@ -370,7 +370,8 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
 			((void *)(uintptr_t)iova) : addr;
 
 		if (crcp)
-			*crcp = crc32_le(*crcp, src, length);
+			crc = rxe_crc32(to_rdev(mem->pd->ibpd.device),
+					*crcp, src, length);
 
 		memcpy(dest, src, length);
 
@@ -403,7 +404,8 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
 			bytes = length;
 
 		if (crcp)
-			crc = crc32_le(crc, src, bytes);
+			crc = rxe_crc32(to_rdev(mem->pd->ibpd.device),
+					crc, src, bytes);
 
 		memcpy(dest, src, bytes);
 

drivers/infiniband/sw/rxe/rxe_recv.c

@@ -387,7 +387,7 @@ int rxe_rcv(struct sk_buff *skb)
 	pack_icrc = be32_to_cpu(*icrcp);
 
 	calc_icrc = rxe_icrc_hdr(pkt, skb);
-	calc_icrc = crc32_le(calc_icrc, (u8 *)payload_addr(pkt),
+	calc_icrc = rxe_crc32(rxe, calc_icrc, (u8 *)payload_addr(pkt),
 			      payload_size(pkt));
 	calc_icrc = (__force u32)cpu_to_be32(~calc_icrc);
 	if (unlikely(calc_icrc != pack_icrc)) {

drivers/infiniband/sw/rxe/rxe_req.c

@@ -32,6 +32,7 @@
  */
 
 #include <linux/skbuff.h>
+#include <crypto/hash.h>
 
 #include "rxe.h"
 #include "rxe_loc.h"
@@ -483,8 +484,7 @@ static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 		if (wqe->wr.send_flags & IB_SEND_INLINE) {
 			u8 *tmp = &wqe->dma.inline_data[wqe->dma.sge_offset];
 
-			crc = crc32_le(crc, tmp, paylen);
+			crc = rxe_crc32(rxe, crc, tmp, paylen);
-
 			memcpy(payload_addr(pkt), tmp, paylen);
 
 			wqe->dma.resid -= paylen;

drivers/infiniband/sw/rxe/rxe_verbs.c

@@ -1322,6 +1322,13 @@ int rxe_register_device(struct rxe_dev *rxe)
 	dev->get_hw_stats = rxe_ib_get_hw_stats;
 	dev->alloc_hw_stats = rxe_ib_alloc_hw_stats;
 
+	rxe->tfm = crypto_alloc_shash("crc32", 0, 0);
+	if (IS_ERR(rxe->tfm)) {
+		pr_err("failed to allocate crc algorithmi err:%ld",
+		       PTR_ERR(rxe->tfm));
+		return PTR_ERR(rxe->tfm);
+	}
+
 	err = ib_register_device(dev, NULL);
 	if (err) {
 		pr_warn("rxe_register_device failed, err = %d\n", err);
@@ -1342,6 +1349,8 @@ int rxe_register_device(struct rxe_dev *rxe)
 err2:
 	ib_unregister_device(dev);
 err1:
+	crypto_free_shash(rxe->tfm);
+
 	return err;
 }
 

drivers/infiniband/sw/rxe/rxe_verbs.h

@@ -406,6 +406,7 @@ struct rxe_dev {
 
 	struct rxe_port		port;
 	struct list_head	list;
+	struct crypto_shash	*tfm;
 };
 
 static inline void rxe_counter_inc(struct rxe_dev *rxe, enum rxe_counters cnt)