net/smc: optimize for smc_sndbuf_sync_sg_for_device and smc_rmb_sync_sg_for_cpu

Some CPU, such as Xeon, can guarantee DMA cache coherency.
So it is no need to use dma sync APIs to flush cache on such CPUs.
In order to avoid calling dma sync APIs on the IO path, use the
dma_need_sync to check whether smc_buf_desc needs dma sync when
creating smc_buf_desc.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/smc_core.c

@@ -2016,6 +2016,9 @@ static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb,
 		goto free_table;
 	}
 
+	buf_desc->is_dma_need_sync |=
+		smc_ib_is_sg_need_sync(lnk, buf_desc) << lnk->link_idx;
+
 	/* create a new memory region for the RMB */
 	if (is_rmb) {
 		rc = smc_ib_get_memory_region(lnk->roce_pd,
@@ -2234,6 +2237,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		/* check for reusable slot in the link group */
 		buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list);
 		if (buf_desc) {
+			buf_desc->is_dma_need_sync = 0;
 			SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
 			SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb);
 			break; /* found reusable slot */
@@ -2292,6 +2296,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 
 void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn)
 {
+	if (!conn->sndbuf_desc->is_dma_need_sync)
+		return;
 	if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd ||
 	    !smc_link_active(conn->lnk))
 		return;
@@ -2302,6 +2308,8 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
 {
 	int i;
 
+	if (!conn->rmb_desc->is_dma_need_sync)
+		return;
 	if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd)
 		return;
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {

net/smc/smc_core.h

@@ -180,6 +180,7 @@ struct smc_buf_desc {
 					/* mem region registered */
 			u8		is_map_ib[SMC_LINKS_PER_LGR_MAX];
 					/* mem region mapped to lnk */
+			u8		is_dma_need_sync;
 			u8		is_reg_err;
 					/* buffer registration err */
 		};

net/smc/smc_ib.c

@@ -729,6 +729,29 @@ int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 	return 0;
 }
 
+bool smc_ib_is_sg_need_sync(struct smc_link *lnk,
+			    struct smc_buf_desc *buf_slot)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+	bool ret = false;
+
+	/* for now there is just one DMA address */
+	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
+		    buf_slot->sgt[lnk->link_idx].nents, i) {
+		if (!sg_dma_len(sg))
+			break;
+		if (dma_need_sync(lnk->smcibdev->ibdev->dma_device,
+				  sg_dma_address(sg))) {
+			ret = true;
+			goto out;
+		}
+	}
+
+out:
+	return ret;
+}
+
 /* synchronize buffer usage for cpu access */
 void smc_ib_sync_sg_for_cpu(struct smc_link *lnk,
 			    struct smc_buf_desc *buf_slot,
@@ -737,6 +760,9 @@ void smc_ib_sync_sg_for_cpu(struct smc_link *lnk,
 	struct scatterlist *sg;
 	unsigned int i;
 
+	if (!(buf_slot->is_dma_need_sync & (1U << lnk->link_idx)))
+		return;
+
 	/* for now there is just one DMA address */
 	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
 		    buf_slot->sgt[lnk->link_idx].nents, i) {
@@ -757,6 +783,9 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
 	struct scatterlist *sg;
 	unsigned int i;
 
+	if (!(buf_slot->is_dma_need_sync & (1U << lnk->link_idx)))
+		return;
+
 	/* for now there is just one DMA address */
 	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
 		    buf_slot->sgt[lnk->link_idx].nents, i) {

net/smc/smc_ib.h

@@ -102,6 +102,8 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
 int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 			     struct smc_buf_desc *buf_slot, u8 link_idx);
 void smc_ib_put_memory_region(struct ib_mr *mr);
+bool smc_ib_is_sg_need_sync(struct smc_link *lnk,
+			    struct smc_buf_desc *buf_slot);
 void smc_ib_sync_sg_for_cpu(struct smc_link *lnk,
 			    struct smc_buf_desc *buf_slot,
 			    enum dma_data_direction data_direction);