1 files changed, 160 insertions, 86 deletions

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index f40f6ed0fbdb..ff49a11f57b8 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -347,6 +347,8 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type))
 		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_BUF_TYPE, lgr->buf_type))
+		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id))
 		goto errattr;
 	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_R_NET_COOKIE,
@@ -907,6 +909,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 		lgr->net = smc_ib_net(lnk->smcibdev);
 		lgr_list = &smc_lgr_list.list;
 		lgr_lock = &smc_lgr_list.lock;
+		lgr->buf_type = lgr->net->smc.sysctl_smcr_buf_type;
 		atomic_inc(&lgr_cnt);
 	}
 	smc->conn.lgr = lgr;
@@ -1086,34 +1089,37 @@ err_out:
 	return NULL;
 }
 
-static void smcr_buf_unuse(struct smc_buf_desc *rmb_desc,
+static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
 			   struct smc_link_group *lgr)
 {
+	struct mutex *lock;	/* lock buffer list */
 	int rc;
 
-	if (rmb_desc->is_conf_rkey && !list_empty(&lgr->list)) {
+	if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) {
 		/* unregister rmb with peer */
 		rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
 		if (!rc) {
 			/* protect against smc_llc_cli_rkey_exchange() */
 			mutex_lock(&lgr->llc_conf_mutex);
-			smc_llc_do_delete_rkey(lgr, rmb_desc);
-			rmb_desc->is_conf_rkey = false;
+			smc_llc_do_delete_rkey(lgr, buf_desc);
+			buf_desc->is_conf_rkey = false;
 			mutex_unlock(&lgr->llc_conf_mutex);
 			smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
 		}
 	}
 
-	if (rmb_desc->is_reg_err) {
+	if (buf_desc->is_reg_err) {
 		/* buf registration failed, reuse not possible */
-		mutex_lock(&lgr->rmbs_lock);
-		list_del(&rmb_desc->list);
-		mutex_unlock(&lgr->rmbs_lock);
+		lock = is_rmb ? &lgr->rmbs_lock :
+				&lgr->sndbufs_lock;
+		mutex_lock(lock);
+		list_del(&buf_desc->list);
+		mutex_unlock(lock);
 
-		smc_buf_free(lgr, true, rmb_desc);
+		smc_buf_free(lgr, is_rmb, buf_desc);
 	} else {
-		rmb_desc->used = 0;
-		memset(rmb_desc->cpu_addr, 0, rmb_desc->len);
+		buf_desc->used = 0;
+		memset(buf_desc->cpu_addr, 0, buf_desc->len);
 	}
 }
 
@@ -1121,15 +1127,23 @@ static void smc_buf_unuse(struct smc_connection *conn,
 			  struct smc_link_group *lgr)
 {
 	if (conn->sndbuf_desc) {
-		conn->sndbuf_desc->used = 0;
-		memset(conn->sndbuf_desc->cpu_addr, 0, conn->sndbuf_desc->len);
+		if (!lgr->is_smcd && conn->sndbuf_desc->is_vm) {
+			smcr_buf_unuse(conn->sndbuf_desc, false, lgr);
+		} else {
+			conn->sndbuf_desc->used = 0;
+			memset(conn->sndbuf_desc->cpu_addr, 0,
+			       conn->sndbuf_desc->len);
+		}
 	}
-	if (conn->rmb_desc && lgr->is_smcd) {
-		conn->rmb_desc->used = 0;
-		memset(conn->rmb_desc->cpu_addr, 0, conn->rmb_desc->len +
-		       sizeof(struct smcd_cdc_msg));
-	} else if (conn->rmb_desc) {
-		smcr_buf_unuse(conn->rmb_desc, lgr);
+	if (conn->rmb_desc) {
+		if (!lgr->is_smcd) {
+			smcr_buf_unuse(conn->rmb_desc, true, lgr);
+		} else {
+			conn->rmb_desc->used = 0;
+			memset(conn->rmb_desc->cpu_addr, 0,
+			       conn->rmb_desc->len +
+			       sizeof(struct smcd_cdc_msg));
+		}
 	}
 }
 
@@ -1177,20 +1191,21 @@ lgr_put:
 static void smcr_buf_unmap_link(struct smc_buf_desc *buf_desc, bool is_rmb,
 				struct smc_link *lnk)
 {
-	if (is_rmb)
+	if (is_rmb || buf_desc->is_vm)
 		buf_desc->is_reg_mr[lnk->link_idx] = false;
 	if (!buf_desc->is_map_ib[lnk->link_idx])
 		return;
-	if (is_rmb) {
-		if (buf_desc->mr_rx[lnk->link_idx]) {
-			smc_ib_put_memory_region(
-					buf_desc->mr_rx[lnk->link_idx]);
-			buf_desc->mr_rx[lnk->link_idx] = NULL;
-		}
+
+	if ((is_rmb || buf_desc->is_vm) &&
+	    buf_desc->mr[lnk->link_idx]) {
+		smc_ib_put_memory_region(buf_desc->mr[lnk->link_idx]);
+		buf_desc->mr[lnk->link_idx] = NULL;
+	}
+	if (is_rmb)
 		smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_FROM_DEVICE);
-	} else {
+	else
 		smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_TO_DEVICE);
-	}
+
 	sg_free_table(&buf_desc->sgt[lnk->link_idx]);
 	buf_desc->is_map_ib[lnk->link_idx] = false;
 }
@@ -1279,8 +1294,10 @@ static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb,
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++)
 		smcr_buf_unmap_link(buf_desc, is_rmb, &lgr->lnk[i]);
 
-	if (buf_desc->pages)
+	if (!buf_desc->is_vm && buf_desc->pages)
 		__free_pages(buf_desc->pages, buf_desc->order);
+	else if (buf_desc->is_vm && buf_desc->cpu_addr)
+		vfree(buf_desc->cpu_addr);
 	kfree(buf_desc);
 }
 
@@ -1992,39 +2009,69 @@ static inline int smc_rmb_wnd_update_limit(int rmbe_size)
 	return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
 }
 
-/* map an rmb buf to a link */
+/* map an buf to a link */
 static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb,
 			     struct smc_link *lnk)
 {
-	int rc;
+	int rc, i, nents, offset, buf_size, size, access_flags;
+	struct scatterlist *sg;
+	void *buf;
 
 	if (buf_desc->is_map_ib[lnk->link_idx])
 		return 0;
 
-	rc = sg_alloc_table(&buf_desc->sgt[lnk->link_idx], 1, GFP_KERNEL);
+	if (buf_desc->is_vm) {
+		buf = buf_desc->cpu_addr;
+		buf_size = buf_desc->len;
+		offset = offset_in_page(buf_desc->cpu_addr);
+		nents = PAGE_ALIGN(buf_size + offset) / PAGE_SIZE;
+	} else {
+		nents = 1;
+	}
+
+	rc = sg_alloc_table(&buf_desc->sgt[lnk->link_idx], nents, GFP_KERNEL);
 	if (rc)
 		return rc;
-	sg_set_buf(buf_desc->sgt[lnk->link_idx].sgl,
-		   buf_desc->cpu_addr, buf_desc->len);
+
+	if (buf_desc->is_vm) {
+		/* virtually contiguous buffer */
+		for_each_sg(buf_desc->sgt[lnk->link_idx].sgl, sg, nents, i) {
+			size = min_t(int, PAGE_SIZE - offset, buf_size);
+			sg_set_page(sg, vmalloc_to_page(buf), size, offset);
+			buf += size / sizeof(*buf);
+			buf_size -= size;
+			offset = 0;
+		}
+	} else {
+		/* physically contiguous buffer */
+		sg_set_buf(buf_desc->sgt[lnk->link_idx].sgl,
+			   buf_desc->cpu_addr, buf_desc->len);
+	}
 
 	/* map sg table to DMA address */
 	rc = smc_ib_buf_map_sg(lnk, buf_desc,
 			       is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
 	/* SMC protocol depends on mapping to one DMA address only */
-	if (rc != 1) {
+	if (rc != nents) {
 		rc = -EAGAIN;
 		goto free_table;
 	}
 
-	/* create a new memory region for the RMB */
-	if (is_rmb) {
-		rc = smc_ib_get_memory_region(lnk->roce_pd,
-					      IB_ACCESS_REMOTE_WRITE |
-					      IB_ACCESS_LOCAL_WRITE,
+	buf_desc->is_dma_need_sync |=
+		smc_ib_is_sg_need_sync(lnk, buf_desc) << lnk->link_idx;
+
+	if (is_rmb || buf_desc->is_vm) {
+		/* create a new memory region for the RMB or vzalloced sndbuf */
+		access_flags = is_rmb ?
+			       IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
+			       IB_ACCESS_LOCAL_WRITE;
+
+		rc = smc_ib_get_memory_region(lnk->roce_pd, access_flags,
 					      buf_desc, lnk->link_idx);
 		if (rc)
 			goto buf_unmap;
-		smc_ib_sync_sg_for_device(lnk, buf_desc, DMA_FROM_DEVICE);
+		smc_ib_sync_sg_for_device(lnk, buf_desc,
+					  is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
 	}
 	buf_desc->is_map_ib[lnk->link_idx] = true;
 	return 0;
@@ -2037,20 +2084,23 @@ free_table:
 	return rc;
 }
 
-/* register a new rmb on IB device,
+/* register a new buf on IB device, rmb or vzalloced sndbuf
  * must be called under lgr->llc_conf_mutex lock
  */
-int smcr_link_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc)
+int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc)
 {
 	if (list_empty(&link->lgr->list))
 		return -ENOLINK;
-	if (!rmb_desc->is_reg_mr[link->link_idx]) {
-		/* register memory region for new rmb */
-		if (smc_wr_reg_send(link, rmb_desc->mr_rx[link->link_idx])) {
-			rmb_desc->is_reg_err = true;
+	if (!buf_desc->is_reg_mr[link->link_idx]) {
+		/* register memory region for new buf */
+		if (buf_desc->is_vm)
+			buf_desc->mr[link->link_idx]->iova =
+				(uintptr_t)buf_desc->cpu_addr;
+		if (smc_wr_reg_send(link, buf_desc->mr[link->link_idx])) {
+			buf_desc->is_reg_err = true;
 			return -EFAULT;
 		}
-		rmb_desc->is_reg_mr[link->link_idx] = true;
+		buf_desc->is_reg_mr[link->link_idx] = true;
 	}
 	return 0;
 }
@@ -2102,18 +2152,38 @@ int smcr_buf_reg_lgr(struct smc_link *lnk)
 	struct smc_buf_desc *buf_desc, *bf;
 	int i, rc = 0;
 
+	/* reg all RMBs for a new link */
 	mutex_lock(&lgr->rmbs_lock);
 	for (i = 0; i < SMC_RMBE_SIZES; i++) {
 		list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) {
 			if (!buf_desc->used)
 				continue;
-			rc = smcr_link_reg_rmb(lnk, buf_desc);
-			if (rc)
-				goto out;
+			rc = smcr_link_reg_buf(lnk, buf_desc);
+			if (rc) {
+				mutex_unlock(&lgr->rmbs_lock);
+				return rc;
+			}
 		}
 	}
-out:
 	mutex_unlock(&lgr->rmbs_lock);
+
+	if (lgr->buf_type == SMCR_PHYS_CONT_BUFS)
+		return rc;
+
+	/* reg all vzalloced sndbufs for a new link */
+	mutex_lock(&lgr->sndbufs_lock);
+	for (i = 0; i < SMC_RMBE_SIZES; i++) {
+		list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) {
+			if (!buf_desc->used || !buf_desc->is_vm)
+				continue;
+			rc = smcr_link_reg_buf(lnk, buf_desc);
+			if (rc) {
+				mutex_unlock(&lgr->sndbufs_lock);
+				return rc;
+			}
+		}
+	}
+	mutex_unlock(&lgr->sndbufs_lock);
 	return rc;
 }
 
@@ -2127,18 +2197,39 @@ static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr,
 	if (!buf_desc)
 		return ERR_PTR(-ENOMEM);
 
-	buf_desc->order = get_order(bufsize);
-	buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN |
-				      __GFP_NOMEMALLOC | __GFP_COMP |
-				      __GFP_NORETRY | __GFP_ZERO,
-				      buf_desc->order);
-	if (!buf_desc->pages) {
-		kfree(buf_desc);
-		return ERR_PTR(-EAGAIN);
-	}
-	buf_desc->cpu_addr = (void *)page_address(buf_desc->pages);
-	buf_desc->len = bufsize;
+	switch (lgr->buf_type) {
+	case SMCR_PHYS_CONT_BUFS:
+	case SMCR_MIXED_BUFS:
+		buf_desc->order = get_order(bufsize);
+		buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN |
+					      __GFP_NOMEMALLOC | __GFP_COMP |
+					      __GFP_NORETRY | __GFP_ZERO,
+					      buf_desc->order);
+		if (buf_desc->pages) {
+			buf_desc->cpu_addr =
+				(void *)page_address(buf_desc->pages);
+			buf_desc->len = bufsize;
+			buf_desc->is_vm = false;
+			break;
+		}
+		if (lgr->buf_type == SMCR_PHYS_CONT_BUFS)
+			goto out;
+		fallthrough;	// try virtually continguous buf
+	case SMCR_VIRT_CONT_BUFS:
+		buf_desc->order = get_order(bufsize);
+		buf_desc->cpu_addr = vzalloc(PAGE_SIZE << buf_desc->order);
+		if (!buf_desc->cpu_addr)
+			goto out;
+		buf_desc->pages = NULL;
+		buf_desc->len = bufsize;
+		buf_desc->is_vm = true;
+		break;
+	}
 	return buf_desc;
+
+out:
+	kfree(buf_desc);
+	return ERR_PTR(-EAGAIN);
 }
 
 /* map buf_desc on all usable links,
@@ -2234,6 +2325,7 @@ 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 */
@@ -2268,7 +2360,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 
 	if (!is_smcd) {
 		if (smcr_buf_map_usable_links(lgr, buf_desc, is_rmb)) {
-			smcr_buf_unuse(buf_desc, lgr);
+			smcr_buf_unuse(buf_desc, is_rmb, lgr);
 			return -ENOMEM;
 		}
 	}
@@ -2290,16 +2382,10 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 	return 0;
 }
 
-void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn)
-{
-	if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd ||
-	    !smc_link_active(conn->lnk))
-		return;
-	smc_ib_sync_sg_for_cpu(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE);
-}
-
 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;
@@ -2310,6 +2396,8 @@ 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++) {
@@ -2320,20 +2408,6 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
 	}
 }
 
-void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
-{
-	int i;
-
-	if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd)
-		return;
-	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
-		if (!smc_link_active(&conn->lgr->lnk[i]))
-			continue;
-		smc_ib_sync_sg_for_device(&conn->lgr->lnk[i], conn->rmb_desc,
-					  DMA_FROM_DEVICE);
-	}
-}
-
 /* create the send and receive buffer for an SMC socket;
  * receive buffers are called RMBs;
  * (even though the SMC protocol allows more than one RMB-element per RMB,