RDMA/siw: Switch to using the crc32c library

Now that the crc32c() library function directly takes advantage of
architecture-specific optimizations, it is unnecessary to go through the
crypto API.  Just use crc32c().  This is much simpler, and it improves
performance due to eliminating the crypto API overhead.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://patch.msgid.link/20250227051207.19470-1-ebiggers@kernel.org
Acked-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>

7 files changed, 74 insertions, 113 deletions

diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig
index 81b70a3eeb87..ae4a953e2a03 100644
--- a/drivers/infiniband/sw/siw/Kconfig
+++ b/drivers/infiniband/sw/siw/Kconfig
@@ -2,9 +2,7 @@ config RDMA_SIW
 	tristate "Software RDMA over TCP/IP (iWARP) driver"
 	depends on INET && INFINIBAND
 	depends on INFINIBAND_VIRT_DMA
-	select LIBCRC32C
-	select CRYPTO
-	select CRYPTO_CRC32C
+	select CRC32
 	help
 	This driver implements the iWARP RDMA transport over
 	the Linux TCP/IP network stack. It enables a system with a
diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h
index ea5eee50dc39..21238746716a 100644
--- a/drivers/infiniband/sw/siw/siw.h
+++ b/drivers/infiniband/sw/siw/siw.h
@@ -10,9 +10,9 @@
 #include <rdma/restrack.h>
 #include <linux/socket.h>
 #include <linux/skbuff.h>
-#include <crypto/hash.h>
 #include <linux/crc32.h>
 #include <linux/crc32c.h>
+#include <linux/unaligned.h>
 
 #include <rdma/siw-abi.h>
 #include "iwarp.h"
@@ -289,7 +289,8 @@ struct siw_rx_stream {
 
 	union iwarp_hdr hdr;
 	struct mpa_trailer trailer;
-	struct shash_desc *mpa_crc_hd;
+	u32 mpa_crc;
+	bool mpa_crc_enabled;
 
 	/*
 	 * For each FPDU, main RX loop runs through 3 stages:
@@ -390,7 +391,8 @@ struct siw_iwarp_tx {
 	int burst;
 	int bytes_unsent; /* ddp payload bytes */
 
-	struct shash_desc *mpa_crc_hd;
+	u32 mpa_crc;
+	bool mpa_crc_enabled;
 
 	u8 do_crc : 1; /* do crc for segment */
 	u8 use_sendpage : 1; /* send w/o copy */
@@ -496,7 +498,6 @@ extern u_char mpa_version;
 extern const bool peer_to_peer;
 extern struct task_struct *siw_tx_thread[];
 
-extern struct crypto_shash *siw_crypto_shash;
 extern struct iwarp_msg_info iwarp_pktinfo[RDMAP_TERMINATE + 1];
 
 /* QP general functions */
@@ -668,6 +669,30 @@ static inline struct siw_sqe *irq_alloc_free(struct siw_qp *qp)
 	return NULL;
 }
 
+static inline void siw_crc_init(u32 *crc)
+{
+	*crc = ~0;
+}
+
+static inline void siw_crc_update(u32 *crc, const void *data, size_t len)
+{
+	*crc = crc32c(*crc, data, len);
+}
+
+static inline void siw_crc_final(u32 *crc, u8 out[4])
+{
+	put_unaligned_le32(~*crc, out);
+}
+
+static inline void siw_crc_oneshot(const void *data, size_t len, u8 out[4])
+{
+	u32 crc;
+
+	siw_crc_init(&crc);
+	siw_crc_update(&crc, data, len);
+	return siw_crc_final(&crc, out);
+}
+
 static inline __wsum siw_csum_update(const void *buff, int len, __wsum sum)
 {
 	return (__force __wsum)crc32c((__force __u32)sum, buff, len);
@@ -686,11 +711,11 @@ static inline void siw_crc_skb(struct siw_rx_stream *srx, unsigned int len)
 		.update = siw_csum_update,
 		.combine = siw_csum_combine,
 	};
-	__wsum crc = *(u32 *)shash_desc_ctx(srx->mpa_crc_hd);
+	__wsum crc = (__force __wsum)srx->mpa_crc;
 
 	crc = __skb_checksum(srx->skb, srx->skb_offset, len, crc,
 			     &siw_cs_ops);
-	*(u32 *)shash_desc_ctx(srx->mpa_crc_hd) = crc;
+	srx->mpa_crc = (__force u32)crc;
 }
 
 #define siw_dbg(ibdev, fmt, ...)                                               \
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index b17752bd1ecc..5168307229a9 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -59,7 +59,6 @@ u_char mpa_version = MPA_REVISION_2;
 const bool peer_to_peer;
 
 struct task_struct *siw_tx_thread[NR_CPUS];
-struct crypto_shash *siw_crypto_shash;
 
 static int siw_device_register(struct siw_device *sdev, const char *name)
 {
@@ -467,20 +466,7 @@ static __init int siw_init_module(void)
 		rv = -ENOMEM;
 		goto out_error;
 	}
-	/*
-	 * Locate CRC32 algorithm. If unsuccessful, fail
-	 * loading siw only, if CRC is required.
-	 */
-	siw_crypto_shash = crypto_alloc_shash("crc32c", 0, 0);
-	if (IS_ERR(siw_crypto_shash)) {
-		pr_info("siw: Loading CRC32c failed: %ld\n",
-			PTR_ERR(siw_crypto_shash));
-		siw_crypto_shash = NULL;
-		if (mpa_crc_required) {
-			rv = -EOPNOTSUPP;
-			goto out_error;
-		}
-	}
+
 	rv = register_netdevice_notifier(&siw_netdev_nb);
 	if (rv)
 		goto out_error;
@@ -493,9 +479,6 @@ static __init int siw_init_module(void)
 out_error:
 	siw_stop_tx_threads();
 
-	if (siw_crypto_shash)
-		crypto_free_shash(siw_crypto_shash);
-
 	pr_info("SoftIWARP attach failed. Error: %d\n", rv);
 
 	siw_cm_exit();
@@ -516,9 +499,6 @@ static void __exit siw_exit_module(void)
 
 	siw_destroy_cpulist(siw_cpu_info.num_nodes);
 
-	if (siw_crypto_shash)
-		crypto_free_shash(siw_crypto_shash);
-
 	pr_info("SoftiWARP detached\n");
 }
 
diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c
index da92cfa2073d..c1e6e7d6e32f 100644
--- a/drivers/infiniband/sw/siw/siw_qp.c
+++ b/drivers/infiniband/sw/siw/siw_qp.c
@@ -226,33 +226,6 @@ static int siw_qp_readq_init(struct siw_qp *qp, int irq_size, int orq_size)
 	return 0;
 }
 
-static int siw_qp_enable_crc(struct siw_qp *qp)
-{
-	struct siw_rx_stream *c_rx = &qp->rx_stream;
-	struct siw_iwarp_tx *c_tx = &qp->tx_ctx;
-	int size;
-
-	if (siw_crypto_shash == NULL)
-		return -ENOENT;
-
-	size = crypto_shash_descsize(siw_crypto_shash) +
-		sizeof(struct shash_desc);
-
-	c_tx->mpa_crc_hd = kzalloc(size, GFP_KERNEL);
-	c_rx->mpa_crc_hd = kzalloc(size, GFP_KERNEL);
-	if (!c_tx->mpa_crc_hd || !c_rx->mpa_crc_hd) {
-		kfree(c_tx->mpa_crc_hd);
-		kfree(c_rx->mpa_crc_hd);
-		c_tx->mpa_crc_hd = NULL;
-		c_rx->mpa_crc_hd = NULL;
-		return -ENOMEM;
-	}
-	c_tx->mpa_crc_hd->tfm = siw_crypto_shash;
-	c_rx->mpa_crc_hd->tfm = siw_crypto_shash;
-
-	return 0;
-}
-
 /*
  * Send a non signalled READ or WRITE to peer side as negotiated
  * with MPAv2 P2P setup protocol. The work request is only created
@@ -583,20 +556,15 @@ void siw_send_terminate(struct siw_qp *qp)
 
 	term->ctrl.mpa_len =
 		cpu_to_be16(len_terminate - (MPA_HDR_SIZE + MPA_CRC_SIZE));
-	if (qp->tx_ctx.mpa_crc_hd) {
-		crypto_shash_init(qp->tx_ctx.mpa_crc_hd);
-		if (crypto_shash_update(qp->tx_ctx.mpa_crc_hd,
-					(u8 *)iov[0].iov_base,
-					iov[0].iov_len))
-			goto out;
-
+	if (qp->tx_ctx.mpa_crc_enabled) {
+		siw_crc_init(&qp->tx_ctx.mpa_crc);
+		siw_crc_update(&qp->tx_ctx.mpa_crc,
+			       iov[0].iov_base, iov[0].iov_len);
 		if (num_frags == 3) {
-			if (crypto_shash_update(qp->tx_ctx.mpa_crc_hd,
-						(u8 *)iov[1].iov_base,
-						iov[1].iov_len))
-				goto out;
+			siw_crc_update(&qp->tx_ctx.mpa_crc,
+				       iov[1].iov_base, iov[1].iov_len);
 		}
-		crypto_shash_final(qp->tx_ctx.mpa_crc_hd, (u8 *)&crc);
+		siw_crc_final(&qp->tx_ctx.mpa_crc, (u8 *)&crc);
 	}
 
 	rv = kernel_sendmsg(s, &msg, iov, num_frags, len_terminate);
@@ -604,7 +572,6 @@ void siw_send_terminate(struct siw_qp *qp)
 		   rv == len_terminate ? "success" : "failure",
 		   __rdmap_term_layer(term), __rdmap_term_etype(term),
 		   __rdmap_term_ecode(term), rv);
-out:
 	kfree(term);
 	kfree(err_hdr);
 }
@@ -643,9 +610,10 @@ static int siw_qp_nextstate_from_idle(struct siw_qp *qp,
 	switch (attrs->state) {
 	case SIW_QP_STATE_RTS:
 		if (attrs->flags & SIW_MPA_CRC) {
-			rv = siw_qp_enable_crc(qp);
-			if (rv)
-				break;
+			siw_crc_init(&qp->tx_ctx.mpa_crc);
+			qp->tx_ctx.mpa_crc_enabled = true;
+			siw_crc_init(&qp->rx_stream.mpa_crc);
+			qp->rx_stream.mpa_crc_enabled = true;
 		}
 		if (!(mask & SIW_QP_ATTR_LLP_HANDLE)) {
 			siw_dbg_qp(qp, "no socket\n");
diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c
index ed4fc39718b4..32554eba1eac 100644
--- a/drivers/infiniband/sw/siw/siw_qp_rx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_rx.c
@@ -67,10 +67,10 @@ static int siw_rx_umem(struct siw_rx_stream *srx, struct siw_umem *umem,
 
 			return -EFAULT;
 		}
-		if (srx->mpa_crc_hd) {
+		if (srx->mpa_crc_enabled) {
 			if (rdma_is_kernel_res(&rx_qp(srx)->base_qp.res)) {
-				crypto_shash_update(srx->mpa_crc_hd,
-					(u8 *)(dest + pg_off), bytes);
+				siw_crc_update(&srx->mpa_crc, dest + pg_off,
+					       bytes);
 				kunmap_atomic(dest);
 			} else {
 				kunmap_atomic(dest);
@@ -114,8 +114,8 @@ static int siw_rx_kva(struct siw_rx_stream *srx, void *kva, int len)
 
 		return rv;
 	}
-	if (srx->mpa_crc_hd)
-		crypto_shash_update(srx->mpa_crc_hd, (u8 *)kva, len);
+	if (srx->mpa_crc_enabled)
+		siw_crc_update(&srx->mpa_crc, kva, len);
 
 	srx->skb_offset += len;
 	srx->skb_copied += len;
@@ -966,16 +966,16 @@ static int siw_get_trailer(struct siw_qp *qp, struct siw_rx_stream *srx)
 	if (srx->fpdu_part_rem)
 		return -EAGAIN;
 
-	if (!srx->mpa_crc_hd)
+	if (!srx->mpa_crc_enabled)
 		return 0;
 
 	if (srx->pad)
-		crypto_shash_update(srx->mpa_crc_hd, tbuf, srx->pad);
+		siw_crc_update(&srx->mpa_crc, tbuf, srx->pad);
 	/*
 	 * CRC32 is computed, transmitted and received directly in NBO,
 	 * so there's never a reason to convert byte order.
 	 */
-	crypto_shash_final(srx->mpa_crc_hd, (u8 *)&crc_own);
+	siw_crc_final(&srx->mpa_crc, (u8 *)&crc_own);
 	crc_in = (__force __wsum)srx->trailer.crc;
 
 	if (unlikely(crc_in != crc_own)) {
@@ -1093,13 +1093,12 @@ static int siw_get_hdr(struct siw_rx_stream *srx)
 	 * (tagged/untagged). E.g., a WRITE can get intersected by a SEND,
 	 * but not by a READ RESPONSE etc.
 	 */
-	if (srx->mpa_crc_hd) {
+	if (srx->mpa_crc_enabled) {
 		/*
 		 * Restart CRC computation
 		 */
-		crypto_shash_init(srx->mpa_crc_hd);
-		crypto_shash_update(srx->mpa_crc_hd, (u8 *)c_hdr,
-				    srx->fpdu_part_rcvd);
+		siw_crc_init(&srx->mpa_crc);
+		siw_crc_update(&srx->mpa_crc, c_hdr, srx->fpdu_part_rcvd);
 	}
 	if (frx->more_ddp_segs) {
 		frx->first_ddp_seg = 0;
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index a034264c5669..6432bce7d083 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -248,10 +248,8 @@ static int siw_qp_prepare_tx(struct siw_iwarp_tx *c_tx)
 		/*
 		 * Do complete CRC if enabled and short packet
 		 */
-		if (c_tx->mpa_crc_hd &&
-		    crypto_shash_digest(c_tx->mpa_crc_hd, (u8 *)&c_tx->pkt,
-					c_tx->ctrl_len, (u8 *)crc) != 0)
-			return -EINVAL;
+		if (c_tx->mpa_crc_enabled)
+			siw_crc_oneshot(&c_tx->pkt, c_tx->ctrl_len, (u8 *)crc);
 		c_tx->ctrl_len += MPA_CRC_SIZE;
 
 		return PKT_COMPLETE;
@@ -482,9 +480,8 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 			iov[seg].iov_len = sge_len;
 
 			if (do_crc)
-				crypto_shash_update(c_tx->mpa_crc_hd,
-						    iov[seg].iov_base,
-						    sge_len);
+				siw_crc_update(&c_tx->mpa_crc,
+					       iov[seg].iov_base, sge_len);
 			sge_off += sge_len;
 			data_len -= sge_len;
 			seg++;
@@ -516,15 +513,14 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 					iov[seg].iov_len = plen;
 
 					if (do_crc)
-						crypto_shash_update(
-							c_tx->mpa_crc_hd,
+						siw_crc_update(
+							&c_tx->mpa_crc,
 							iov[seg].iov_base,
 							plen);
 				} else if (do_crc) {
 					kaddr = kmap_local_page(p);
-					crypto_shash_update(c_tx->mpa_crc_hd,
-							    kaddr + fp_off,
-							    plen);
+					siw_crc_update(&c_tx->mpa_crc,
+						       kaddr + fp_off, plen);
 					kunmap_local(kaddr);
 				}
 			} else {
@@ -536,10 +532,9 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 
 				page_array[seg] = ib_virt_dma_to_page(va);
 				if (do_crc)
-					crypto_shash_update(
-						c_tx->mpa_crc_hd,
-						ib_virt_dma_to_ptr(va),
-						plen);
+					siw_crc_update(&c_tx->mpa_crc,
+						       ib_virt_dma_to_ptr(va),
+						       plen);
 			}
 
 			sge_len -= plen;
@@ -576,14 +571,14 @@ sge_done:
 	if (c_tx->pad) {
 		*(u32 *)c_tx->trailer.pad = 0;
 		if (do_crc)
-			crypto_shash_update(c_tx->mpa_crc_hd,
-				(u8 *)&c_tx->trailer.crc - c_tx->pad,
-				c_tx->pad);
+			siw_crc_update(&c_tx->mpa_crc,
+				       (u8 *)&c_tx->trailer.crc - c_tx->pad,
+				       c_tx->pad);
 	}
-	if (!c_tx->mpa_crc_hd)
+	if (!c_tx->mpa_crc_enabled)
 		c_tx->trailer.crc = 0;
 	else if (do_crc)
-		crypto_shash_final(c_tx->mpa_crc_hd, (u8 *)&c_tx->trailer.crc);
+		siw_crc_final(&c_tx->mpa_crc, (u8 *)&c_tx->trailer.crc);
 
 	data_len = c_tx->bytes_unsent;
 
@@ -736,10 +731,9 @@ static void siw_prepare_fpdu(struct siw_qp *qp, struct siw_wqe *wqe)
 	/*
 	 * Init MPA CRC computation
 	 */
-	if (c_tx->mpa_crc_hd) {
-		crypto_shash_init(c_tx->mpa_crc_hd);
-		crypto_shash_update(c_tx->mpa_crc_hd, (u8 *)&c_tx->pkt,
-				    c_tx->ctrl_len);
+	if (c_tx->mpa_crc_enabled) {
+		siw_crc_init(&c_tx->mpa_crc);
+		siw_crc_update(&c_tx->mpa_crc, &c_tx->pkt, c_tx->ctrl_len);
 		c_tx->do_crc = 1;
 	}
 }
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 5ac8bd450d24..fd7b266a221b 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -631,9 +631,6 @@ int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata)
 	}
 	up_write(&qp->state_lock);
 
-	kfree(qp->tx_ctx.mpa_crc_hd);
-	kfree(qp->rx_stream.mpa_crc_hd);
-
 	qp->scq = qp->rcq = NULL;
 
 	siw_qp_put(qp);