Merge branch 'sg_nents' into rdma.git for-next

From Maor Gottlieb
====================

Fix the use of nents and orig_nents in the sg table append helpers. The
nents should be used by the DMA layer to store the number of DMA mapped
sges, the orig_nents is the number of CPU sges.

Since the sg append logic doesn't always create a SGL with exactly
orig_nents entries store a total_nents as well to allow the table to be
properly free'd and reorganize the freeing logic to share across all the
use cases.

====================

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

* 'sg_nents':
  RDMA: Use the sg_table directly and remove the opencoded version from umem
  lib/scatterlist: Fix wrong update of orig_nents
  lib/scatterlist: Provide a dedicated function to support table append

3 files changed, 43 insertions, 35 deletions

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index c3f2facafd02..c40791baced5 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -926,12 +926,25 @@ static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp)
 	return ret;
 }
 
+static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp)
+{
+	struct ib_qp_attr qp_attr;
+	int qp_attr_mask, ret;
+
+	qp_attr.qp_state = IB_QPS_INIT;
+	ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
+	if (ret)
+		return ret;
+
+	return ib_modify_qp(qp, &qp_attr, qp_attr_mask);
+}
+
 int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
 		   struct ib_qp_init_attr *qp_init_attr)
 {
 	struct rdma_id_private *id_priv;
 	struct ib_qp *qp;
-	int ret = 0;
+	int ret;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
 	if (id->device != pd->device) {
@@ -948,6 +961,8 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
 
 	if (id->qp_type == IB_QPT_UD)
 		ret = cma_init_ud_qp(id_priv, qp);
+	else
+		ret = cma_init_conn_qp(id_priv, qp);
 	if (ret)
 		goto out_destroy;
 
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 0eb40025075f..86d479772fbc 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -51,15 +51,15 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 	struct scatterlist *sg;
 	unsigned int i;
 
-	if (umem->nmap > 0)
-		ib_dma_unmap_sg(dev, umem->sg_head.sgl, umem->sg_nents,
-				DMA_BIDIRECTIONAL);
+	if (dirty)
+		ib_dma_unmap_sgtable_attrs(dev, &umem->sgt_append.sgt,
+					   DMA_BIDIRECTIONAL, 0);
 
-	for_each_sg(umem->sg_head.sgl, sg, umem->sg_nents, i)
+	for_each_sgtable_sg(&umem->sgt_append.sgt, sg, i)
 		unpin_user_page_range_dirty_lock(sg_page(sg),
 			DIV_ROUND_UP(sg->length, PAGE_SIZE), make_dirty);
 
-	sg_free_table(&umem->sg_head);
+	sg_free_append_table(&umem->sgt_append);
 }
 
 /**
@@ -111,7 +111,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 	/* offset into first SGL */
 	pgoff = umem->address & ~PAGE_MASK;
 
-	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) {
+	for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) {
 		/* Walk SGL and reduce max page size if VA/PA bits differ
 		 * for any address.
 		 */
@@ -121,7 +121,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 		 * the maximum possible page size as the low bits of the iova
 		 * must be zero when starting the next chunk.
 		 */
-		if (i != (umem->nmap - 1))
+		if (i != (umem->sgt_append.sgt.nents - 1))
 			mask |= va;
 		pgoff = 0;
 	}
@@ -155,8 +155,7 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	unsigned long dma_attr = 0;
 	struct mm_struct *mm;
 	unsigned long npages;
-	int ret;
-	struct scatterlist *sg = NULL;
+	int pinned, ret;
 	unsigned int gup_flags = FOLL_WRITE;
 
 	/*
@@ -216,24 +215,24 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 
 	while (npages) {
 		cond_resched();
-		ret = pin_user_pages_fast(cur_base,
+		pinned = pin_user_pages_fast(cur_base,
 					  min_t(unsigned long, npages,
 						PAGE_SIZE /
 						sizeof(struct page *)),
 					  gup_flags | FOLL_LONGTERM, page_list);
-		if (ret < 0)
+		if (pinned < 0) {
+			ret = pinned;
 			goto umem_release;
+		}
 
-		cur_base += ret * PAGE_SIZE;
-		npages -= ret;
-		sg = __sg_alloc_table_from_pages(&umem->sg_head, page_list, ret,
-				0, ret << PAGE_SHIFT,
-				ib_dma_max_seg_size(device), sg, npages,
-				GFP_KERNEL);
-		umem->sg_nents = umem->sg_head.nents;
-		if (IS_ERR(sg)) {
-			unpin_user_pages_dirty_lock(page_list, ret, 0);
-			ret = PTR_ERR(sg);
+		cur_base += pinned * PAGE_SIZE;
+		npages -= pinned;
+		ret = sg_alloc_append_table_from_pages(
+			&umem->sgt_append, page_list, pinned, 0,
+			pinned << PAGE_SHIFT, ib_dma_max_seg_size(device),
+			npages, GFP_KERNEL);
+		if (ret) {
+			unpin_user_pages_dirty_lock(page_list, pinned, 0);
 			goto umem_release;
 		}
 	}
@@ -241,16 +240,10 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	if (access & IB_ACCESS_RELAXED_ORDERING)
 		dma_attr |= DMA_ATTR_WEAK_ORDERING;
 
-	umem->nmap =
-		ib_dma_map_sg_attrs(device, umem->sg_head.sgl, umem->sg_nents,
-				    DMA_BIDIRECTIONAL, dma_attr);
-
-	if (!umem->nmap) {
-		ret = -ENOMEM;
+	ret = ib_dma_map_sgtable_attrs(device, &umem->sgt_append.sgt,
+				       DMA_BIDIRECTIONAL, dma_attr);
+	if (ret)
 		goto umem_release;
-	}
-
-	ret = 0;
 	goto out;
 
 umem_release:
@@ -310,7 +303,8 @@ int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
 		return -EINVAL;
 	}
 
-	ret = sg_pcopy_to_buffer(umem->sg_head.sgl, umem->sg_nents, dst, length,
+	ret = sg_pcopy_to_buffer(umem->sgt_append.sgt.sgl,
+				 umem->sgt_append.sgt.orig_nents, dst, length,
 				 offset + ib_umem_offset(umem));
 
 	if (ret < 0)
diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c
index c6e875619fac..e824baf4640d 100644
--- a/drivers/infiniband/core/umem_dmabuf.c
+++ b/drivers/infiniband/core/umem_dmabuf.c
@@ -55,9 +55,8 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
 		cur += sg_dma_len(sg);
 	}
 
-	umem_dmabuf->umem.sg_head.sgl = umem_dmabuf->first_sg;
-	umem_dmabuf->umem.sg_head.nents = nmap;
-	umem_dmabuf->umem.nmap = nmap;
+	umem_dmabuf->umem.sgt_append.sgt.sgl = umem_dmabuf->first_sg;
+	umem_dmabuf->umem.sgt_append.sgt.nents = nmap;
 	umem_dmabuf->sgt = sgt;
 
 wait_fence: