Merge branch 'for-next' of...

Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband into for-next

drivers/infiniband/core/umem.c

@@ -42,29 +42,29 @@
 
 #include "uverbs.h"
 
-#define IB_UMEM_MAX_PAGE_CHUNK						\
-	((PAGE_SIZE - offsetof(struct ib_umem_chunk, page_list)) /	\
-	 ((void *) &((struct ib_umem_chunk *) 0)->page_list[1] -	\
-	  (void *) &((struct ib_umem_chunk *) 0)->page_list[0]))
 
 static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)
 {
-	struct ib_umem_chunk *chunk, *tmp;
+	struct scatterlist *sg;
+	struct page *page;
 	int i;
 
-	list_for_each_entry_safe(chunk, tmp, &umem->chunk_list, list) {
-		ib_dma_unmap_sg(dev, chunk->page_list,
-				chunk->nents, DMA_BIDIRECTIONAL);
-		for (i = 0; i < chunk->nents; ++i) {
-			struct page *page = sg_page(&chunk->page_list[i]);
+	if (umem->nmap > 0)
+		ib_dma_unmap_sg(dev, umem->sg_head.sgl,
+				umem->nmap,
+				DMA_BIDIRECTIONAL);
 
+	for_each_sg(umem->sg_head.sgl, sg, umem->npages, i) {
+
+		page = sg_page(sg);
 		if (umem->writable && dirty)
 			set_page_dirty_lock(page);
 		put_page(page);
 	}
 
-		kfree(chunk);
-	}
+	sg_free_table(&umem->sg_head);
+	return;
+
 }
 
 /**
@@ -81,15 +81,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	struct ib_umem *umem;
 	struct page **page_list;
 	struct vm_area_struct **vma_list;
-	struct ib_umem_chunk *chunk;
 	unsigned long locked;
 	unsigned long lock_limit;
 	unsigned long cur_base;
 	unsigned long npages;
 	int ret;
-	int off;
 	int i;
 	DEFINE_DMA_ATTRS(attrs);
+	struct scatterlist *sg, *sg_list_start;
+	int need_release = 0;
 
 	if (dmasync)
 		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
@@ -97,7 +97,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (!can_do_mlock())
 		return ERR_PTR(-EPERM);
 
-	umem = kmalloc(sizeof *umem, GFP_KERNEL);
+	umem = kzalloc(sizeof *umem, GFP_KERNEL);
 	if (!umem)
 		return ERR_PTR(-ENOMEM);
 
@@ -117,8 +117,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	/* We assume the memory is from hugetlb until proved otherwise */
 	umem->hugetlb   = 1;
 
-	INIT_LIST_HEAD(&umem->chunk_list);
-
 	page_list = (struct page **) __get_free_page(GFP_KERNEL);
 	if (!page_list) {
 		kfree(umem);
@@ -147,7 +145,18 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	cur_base = addr & PAGE_MASK;
 
-	ret = 0;
+	if (npages == 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = sg_alloc_table(&umem->sg_head, npages, GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	need_release = 1;
+	sg_list_start = umem->sg_head.sgl;
+
 	while (npages) {
 		ret = get_user_pages(current, current->mm, cur_base,
 				     min_t(unsigned long, npages,
@@ -157,53 +166,37 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 		if (ret < 0)
 			goto out;
 
+		umem->npages += ret;
 		cur_base += ret * PAGE_SIZE;
 		npages   -= ret;
 
-		off = 0;
+		for_each_sg(sg_list_start, sg, ret, i) {
+			if (vma_list && !is_vm_hugetlb_page(vma_list[i]))
+				umem->hugetlb = 0;
 
-		while (ret) {
-			chunk = kmalloc(sizeof *chunk + sizeof (struct scatterlist) *
-					min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK),
-					GFP_KERNEL);
-			if (!chunk) {
-				ret = -ENOMEM;
-				goto out;
+			sg_set_page(sg, page_list[i], PAGE_SIZE, 0);
 		}
 
-			chunk->nents = min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK);
-			sg_init_table(chunk->page_list, chunk->nents);
-			for (i = 0; i < chunk->nents; ++i) {
-				if (vma_list &&
-				    !is_vm_hugetlb_page(vma_list[i + off]))
-					umem->hugetlb = 0;
-				sg_set_page(&chunk->page_list[i], page_list[i + off], PAGE_SIZE, 0);
+		/* preparing for next loop */
+		sg_list_start = sg;
 	}
 
-			chunk->nmap = ib_dma_map_sg_attrs(context->device,
-							  &chunk->page_list[0],
-							  chunk->nents,
+	umem->nmap = ib_dma_map_sg_attrs(context->device,
+				  umem->sg_head.sgl,
+				  umem->npages,
 				  DMA_BIDIRECTIONAL,
 				  &attrs);
-			if (chunk->nmap <= 0) {
-				for (i = 0; i < chunk->nents; ++i)
-					put_page(sg_page(&chunk->page_list[i]));
-				kfree(chunk);
 
+	if (umem->nmap <= 0) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-			ret -= chunk->nents;
-			off += chunk->nents;
-			list_add_tail(&chunk->list, &umem->chunk_list);
-		}
-
 	ret = 0;
-	}
 
 out:
 	if (ret < 0) {
+		if (need_release)
 			__ib_umem_release(context->device, umem, 0);
 		kfree(umem);
 	} else
@@ -278,17 +271,16 @@ EXPORT_SYMBOL(ib_umem_release);
 
 int ib_umem_page_count(struct ib_umem *umem)
 {
-	struct ib_umem_chunk *chunk;
 	int shift;
 	int i;
 	int n;
+	struct scatterlist *sg;
 
 	shift = ilog2(umem->page_size);
 
 	n = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		for (i = 0; i < chunk->nmap; ++i)
-			n += sg_dma_len(&chunk->page_list[i]) >> shift;
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i)
+		n += sg_dma_len(sg) >> shift;
 
 	return n;
 }

drivers/infiniband/core/verbs.c

@@ -1169,6 +1169,45 @@ int ib_dereg_mr(struct ib_mr *mr)
 }
 EXPORT_SYMBOL(ib_dereg_mr);
 
+struct ib_mr *ib_create_mr(struct ib_pd *pd,
+			   struct ib_mr_init_attr *mr_init_attr)
+{
+	struct ib_mr *mr;
+
+	if (!pd->device->create_mr)
+		return ERR_PTR(-ENOSYS);
+
+	mr = pd->device->create_mr(pd, mr_init_attr);
+
+	if (!IS_ERR(mr)) {
+		mr->device  = pd->device;
+		mr->pd      = pd;
+		mr->uobject = NULL;
+		atomic_inc(&pd->usecnt);
+		atomic_set(&mr->usecnt, 0);
+	}
+
+	return mr;
+}
+EXPORT_SYMBOL(ib_create_mr);
+
+int ib_destroy_mr(struct ib_mr *mr)
+{
+	struct ib_pd *pd;
+	int ret;
+
+	if (atomic_read(&mr->usecnt))
+		return -EBUSY;
+
+	pd = mr->pd;
+	ret = mr->device->destroy_mr(mr);
+	if (!ret)
+		atomic_dec(&pd->usecnt);
+
+	return ret;
+}
+EXPORT_SYMBOL(ib_destroy_mr);
+
 struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len)
 {
 	struct ib_mr *mr;
@@ -1398,3 +1437,11 @@ int ib_destroy_flow(struct ib_flow *flow_id)
 	return err;
 }
 EXPORT_SYMBOL(ib_destroy_flow);
+
+int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
+		       struct ib_mr_status *mr_status)
+{
+	return mr->device->check_mr_status ?
+		mr->device->check_mr_status(mr, check_mask, mr_status) : -ENOSYS;
+}
+EXPORT_SYMBOL(ib_check_mr_status);

drivers/infiniband/hw/amso1100/c2_provider.c

@@ -431,9 +431,9 @@ static struct ib_mr *c2_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	u64 *pages;
 	u64 kva = 0;
 	int shift, n, len;
-	int i, j, k;
+	int i, k, entry;
 	int err = 0;
-	struct ib_umem_chunk *chunk;
+	struct scatterlist *sg;
 	struct c2_pd *c2pd = to_c2pd(pd);
 	struct c2_mr *c2mr;
 
@@ -452,10 +452,7 @@ static struct ib_mr *c2_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	}
 
 	shift = ffs(c2mr->umem->page_size) - 1;
-
-	n = 0;
-	list_for_each_entry(chunk, &c2mr->umem->chunk_list, list)
-		n += chunk->nents;
+	n = c2mr->umem->nmap;
 
 	pages = kmalloc(n * sizeof(u64), GFP_KERNEL);
 	if (!pages) {
@@ -464,16 +461,14 @@ static struct ib_mr *c2_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	}
 
 	i = 0;
-	list_for_each_entry(chunk, &c2mr->umem->chunk_list, list) {
-		for (j = 0; j < chunk->nmap; ++j) {
-			len = sg_dma_len(&chunk->page_list[j]) >> shift;
+	for_each_sg(c2mr->umem->sg_head.sgl, sg, c2mr->umem->nmap, entry) {
+		len = sg_dma_len(sg) >> shift;
 		for (k = 0; k < len; ++k) {
 			pages[i++] =
-					sg_dma_address(&chunk->page_list[j]) +
+				sg_dma_address(sg) +
 				(c2mr->umem->page_size * k);
 		}
 	}
-	}
 
 	kva = virt;
   	err = c2_nsmr_register_phys_kern(to_c2dev(pd->device),

drivers/infiniband/hw/cxgb3/iwch_provider.c

@@ -618,14 +618,13 @@ static struct ib_mr *iwch_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 {
 	__be64 *pages;
 	int shift, n, len;
-	int i, j, k;
+	int i, k, entry;
 	int err = 0;
-	struct ib_umem_chunk *chunk;
 	struct iwch_dev *rhp;
 	struct iwch_pd *php;
 	struct iwch_mr *mhp;
 	struct iwch_reg_user_mr_resp uresp;
-
+	struct scatterlist *sg;
 	PDBG("%s ib_pd %p\n", __func__, pd);
 
 	php = to_iwch_pd(pd);
@@ -645,9 +644,7 @@ static struct ib_mr *iwch_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	shift = ffs(mhp->umem->page_size) - 1;
 
-	n = 0;
-	list_for_each_entry(chunk, &mhp->umem->chunk_list, list)
-		n += chunk->nents;
+	n = mhp->umem->nmap;
 
 	err = iwch_alloc_pbl(mhp, n);
 	if (err)
@@ -661,12 +658,10 @@ static struct ib_mr *iwch_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	i = n = 0;
 
-	list_for_each_entry(chunk, &mhp->umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; ++j) {
-			len = sg_dma_len(&chunk->page_list[j]) >> shift;
+	for_each_sg(mhp->umem->sg_head.sgl, sg, mhp->umem->nmap, entry) {
+			len = sg_dma_len(sg) >> shift;
 			for (k = 0; k < len; ++k) {
-				pages[i++] = cpu_to_be64(sg_dma_address(
-					&chunk->page_list[j]) +
+				pages[i++] = cpu_to_be64(sg_dma_address(sg) +
 					mhp->umem->page_size * k);
 				if (i == PAGE_SIZE / sizeof *pages) {
 					err = iwch_write_pbl(mhp, pages, i, n);

drivers/infiniband/hw/cxgb4/mem.c

@@ -678,9 +678,9 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 {
 	__be64 *pages;
 	int shift, n, len;
-	int i, j, k;
+	int i, k, entry;
 	int err = 0;
-	struct ib_umem_chunk *chunk;
+	struct scatterlist *sg;
 	struct c4iw_dev *rhp;
 	struct c4iw_pd *php;
 	struct c4iw_mr *mhp;
@@ -710,10 +710,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	shift = ffs(mhp->umem->page_size) - 1;
 
-	n = 0;
-	list_for_each_entry(chunk, &mhp->umem->chunk_list, list)
-		n += chunk->nents;
-
+	n = mhp->umem->nmap;
 	err = alloc_pbl(mhp, n);
 	if (err)
 		goto err;
@@ -726,12 +723,10 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	i = n = 0;
 
-	list_for_each_entry(chunk, &mhp->umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; ++j) {
-			len = sg_dma_len(&chunk->page_list[j]) >> shift;
+	for_each_sg(mhp->umem->sg_head.sgl, sg, mhp->umem->nmap, entry) {
+		len = sg_dma_len(sg) >> shift;
 		for (k = 0; k < len; ++k) {
-				pages[i++] = cpu_to_be64(sg_dma_address(
-					&chunk->page_list[j]) +
+			pages[i++] = cpu_to_be64(sg_dma_address(sg) +
 				mhp->umem->page_size * k);
 			if (i == PAGE_SIZE / sizeof *pages) {
 				err = write_pbl(&mhp->rhp->rdev,

drivers/infiniband/hw/ehca/ehca_classes.h

@@ -322,7 +322,7 @@ struct ehca_mr_pginfo {
 		} phy;
 		struct { /* type EHCA_MR_PGI_USER section */
 			struct ib_umem *region;
-			struct ib_umem_chunk *next_chunk;
+			struct scatterlist *next_sg;
 			u64 next_nmap;
 		} usr;
 		struct { /* type EHCA_MR_PGI_FMR section */

drivers/infiniband/hw/ehca/ehca_mrmw.c

@@ -400,10 +400,7 @@ struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	pginfo.num_hwpages = num_hwpages;
 	pginfo.u.usr.region = e_mr->umem;
 	pginfo.next_hwpage = e_mr->umem->offset / hwpage_size;
-	pginfo.u.usr.next_chunk = list_prepare_entry(pginfo.u.usr.next_chunk,
-						     (&e_mr->umem->chunk_list),
-						     list);
-
+	pginfo.u.usr.next_sg = pginfo.u.usr.region->sg_head.sgl;
 	ret = ehca_reg_mr(shca, e_mr, (u64 *)virt, length, mr_access_flags,
 			  e_pd, &pginfo, &e_mr->ib.ib_mr.lkey,
 			  &e_mr->ib.ib_mr.rkey, EHCA_REG_MR);
@@ -1858,30 +1855,23 @@ static int ehca_set_pagebuf_user1(struct ehca_mr_pginfo *pginfo,
 				  u64 *kpage)
 {
 	int ret = 0;
-	struct ib_umem_chunk *prev_chunk;
-	struct ib_umem_chunk *chunk;
 	u64 pgaddr;
-	u32 i = 0;
 	u32 j = 0;
 	int hwpages_per_kpage = PAGE_SIZE / pginfo->hwpage_size;
+	struct scatterlist **sg = &pginfo->u.usr.next_sg;
 
-	/* loop over desired chunk entries */
-	chunk      = pginfo->u.usr.next_chunk;
-	prev_chunk = pginfo->u.usr.next_chunk;
-	list_for_each_entry_continue(
-		chunk, (&(pginfo->u.usr.region->chunk_list)), list) {
-		for (i = pginfo->u.usr.next_nmap; i < chunk->nmap; ) {
-			pgaddr = page_to_pfn(sg_page(&chunk->page_list[i]))
-				<< PAGE_SHIFT ;
+	while (*sg != NULL) {
+		pgaddr = page_to_pfn(sg_page(*sg))
+			<< PAGE_SHIFT;
 		*kpage = pgaddr + (pginfo->next_hwpage *
 				   pginfo->hwpage_size);
-			if ( !(*kpage) ) {
+		if (!(*kpage)) {
 			ehca_gen_err("pgaddr=%llx "
-					     "chunk->page_list[i]=%llx "
-					     "i=%x next_hwpage=%llx",
-					     pgaddr, (u64)sg_dma_address(
-						     &chunk->page_list[i]),
-					     i, pginfo->next_hwpage);
+				     "sg_dma_address=%llx "
+				     "entry=%llx next_hwpage=%llx",
+				     pgaddr, (u64)sg_dma_address(*sg),
+				     pginfo->u.usr.next_nmap,
+				     pginfo->next_hwpage);
 			return -EFAULT;
 		}
 		(pginfo->hwpage_cnt)++;
@@ -1891,28 +1881,13 @@ static int ehca_set_pagebuf_user1(struct ehca_mr_pginfo *pginfo,
 			(pginfo->kpage_cnt)++;
 			(pginfo->u.usr.next_nmap)++;
 			pginfo->next_hwpage = 0;
-				i++;
+			*sg = sg_next(*sg);
 		}
 		j++;
-			if (j >= number) break;
-		}
-		if ((pginfo->u.usr.next_nmap >= chunk->nmap) &&
-		    (j >= number)) {
-			pginfo->u.usr.next_nmap = 0;
-			prev_chunk = chunk;
+		if (j >= number)
 			break;
-		} else if (pginfo->u.usr.next_nmap >= chunk->nmap) {
-			pginfo->u.usr.next_nmap = 0;
-			prev_chunk = chunk;
-		} else if (j >= number)
-			break;
-		else
-			prev_chunk = chunk;
 	}
-	pginfo->u.usr.next_chunk =
-		list_prepare_entry(prev_chunk,
-				   (&(pginfo->u.usr.region->chunk_list)),
-				   list);
+
 	return ret;
 }
 
@@ -1920,20 +1895,19 @@ static int ehca_set_pagebuf_user1(struct ehca_mr_pginfo *pginfo,
  * check given pages for contiguous layout
  * last page addr is returned in prev_pgaddr for further check
  */
-static int ehca_check_kpages_per_ate(struct scatterlist *page_list,
-				     int start_idx, int end_idx,
+static int ehca_check_kpages_per_ate(struct scatterlist **sg,
+				     int num_pages,
 				     u64 *prev_pgaddr)
 {
-	int t;
-	for (t = start_idx; t <= end_idx; t++) {
-		u64 pgaddr = page_to_pfn(sg_page(&page_list[t])) << PAGE_SHIFT;
+	for (; *sg && num_pages > 0; *sg = sg_next(*sg), num_pages--) {
+		u64 pgaddr = page_to_pfn(sg_page(*sg)) << PAGE_SHIFT;
 		if (ehca_debug_level >= 3)
 			ehca_gen_dbg("chunk_page=%llx value=%016llx", pgaddr,
 				     *(u64 *)__va(pgaddr));
 		if (pgaddr - PAGE_SIZE != *prev_pgaddr) {
 			ehca_gen_err("uncontiguous page found pgaddr=%llx "
-				     "prev_pgaddr=%llx page_list_i=%x",
-				     pgaddr, *prev_pgaddr, t);
+				     "prev_pgaddr=%llx entries_left_in_hwpage=%x",
+				     pgaddr, *prev_pgaddr, num_pages);
 			return -EINVAL;
 		}
 		*prev_pgaddr = pgaddr;
@@ -1947,27 +1921,21 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
 				  u64 *kpage)
 {
 	int ret = 0;
-	struct ib_umem_chunk *prev_chunk;
-	struct ib_umem_chunk *chunk;
 	u64 pgaddr, prev_pgaddr;
-	u32 i = 0;
 	u32 j = 0;
 	int kpages_per_hwpage = pginfo->hwpage_size / PAGE_SIZE;
 	int nr_kpages = kpages_per_hwpage;
+	struct scatterlist **sg = &pginfo->u.usr.next_sg;
+
+	while (*sg != NULL) {
 
-	/* loop over desired chunk entries */
-	chunk      = pginfo->u.usr.next_chunk;
-	prev_chunk = pginfo->u.usr.next_chunk;
-	list_for_each_entry_continue(
-		chunk, (&(pginfo->u.usr.region->chunk_list)), list) {
-		for (i = pginfo->u.usr.next_nmap; i < chunk->nmap; ) {
 		if (nr_kpages == kpages_per_hwpage) {
-				pgaddr = ( page_to_pfn(sg_page(&chunk->page_list[i]))
-					   << PAGE_SHIFT );
+			pgaddr = (page_to_pfn(sg_page(*sg))
+				   << PAGE_SHIFT);
 			*kpage = pgaddr;
-				if ( !(*kpage) ) {
-					ehca_gen_err("pgaddr=%llx i=%x",
-						     pgaddr, i);
+			if (!(*kpage)) {
+				ehca_gen_err("pgaddr=%llx entry=%llx",
+					     pgaddr, pginfo->u.usr.next_nmap);
 				ret = -EFAULT;
 				return ret;
 			}
@@ -1979,9 +1947,9 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
 				if (pginfo->hwpage_cnt) {
 					ehca_gen_err(
 						"invalid alignment "
-							"pgaddr=%llx i=%x "
+						"pgaddr=%llx entry=%llx "
 						"mr_pgsize=%llx",
-							pgaddr, i,
+						pgaddr, pginfo->u.usr.next_nmap,
 						pginfo->hwpage_size);
 					ret = -EFAULT;
 					return ret;
@@ -1997,12 +1965,12 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
 			}
 			if (ehca_debug_level >= 3) {
 				u64 val = *(u64 *)__va(pgaddr);
-					ehca_gen_dbg("kpage=%llx chunk_page=%llx "
+				ehca_gen_dbg("kpage=%llx page=%llx "
 					     "value=%016llx",
 					     *kpage, pgaddr, val);
 			}
 			prev_pgaddr = pgaddr;
-				i++;
+			*sg = sg_next(*sg);
 			pginfo->kpage_cnt++;
 			pginfo->u.usr.next_nmap++;
 			nr_kpages--;
@@ -2010,48 +1978,23 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
 				goto next_kpage;
 			continue;
 		}
-			if (i + nr_kpages > chunk->nmap) {
-				ret = ehca_check_kpages_per_ate(
-					chunk->page_list, i,
-					chunk->nmap - 1, &prev_pgaddr);
-				if (ret) return ret;
-				pginfo->kpage_cnt += chunk->nmap - i;
-				pginfo->u.usr.next_nmap += chunk->nmap - i;
-				nr_kpages -= chunk->nmap - i;
-				break;
-			}
 
-			ret = ehca_check_kpages_per_ate(chunk->page_list, i,
-							i + nr_kpages - 1,
+		ret = ehca_check_kpages_per_ate(sg, nr_kpages,
 						&prev_pgaddr);
-			if (ret) return ret;
-			i += nr_kpages;
+		if (ret)
+			return ret;
 		pginfo->kpage_cnt += nr_kpages;
 		pginfo->u.usr.next_nmap += nr_kpages;
+
 next_kpage:
 		nr_kpages = kpages_per_hwpage;
 		(pginfo->hwpage_cnt)++;
 		kpage++;
 		j++;
-			if (j >= number) break;
-		}
-		if ((pginfo->u.usr.next_nmap >= chunk->nmap) &&
-		    (j >= number)) {
-			pginfo->u.usr.next_nmap = 0;
-			prev_chunk = chunk;
-			break;
-		} else if (pginfo->u.usr.next_nmap >= chunk->nmap) {
-			pginfo->u.usr.next_nmap = 0;
-			prev_chunk = chunk;
-		} else if (j >= number)
+		if (j >= number)
 			break;
-		else
-			prev_chunk = chunk;
 	}
-	pginfo->u.usr.next_chunk =
-		list_prepare_entry(prev_chunk,
-				   (&(pginfo->u.usr.region->chunk_list)),
-				   list);
+
 	return ret;
 }
 

drivers/infiniband/hw/ipath/ipath_mr.c

@@ -188,8 +188,8 @@ struct ib_mr *ipath_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 {
 	struct ipath_mr *mr;
 	struct ib_umem *umem;
-	struct ib_umem_chunk *chunk;
-	int n, m, i;
+	int n, m, entry;
+	struct scatterlist *sg;
 	struct ib_mr *ret;
 
 	if (length == 0) {
@@ -202,10 +202,7 @@ struct ib_mr *ipath_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	if (IS_ERR(umem))
 		return (void *) umem;
 
-	n = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		n += chunk->nents;
-
+	n = umem->nmap;
 	mr = alloc_mr(n, &to_idev(pd->device)->lk_table);
 	if (!mr) {
 		ret = ERR_PTR(-ENOMEM);
@@ -224,11 +221,10 @@ struct ib_mr *ipath_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	m = 0;
 	n = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list) {
-		for (i = 0; i < chunk->nents; i++) {
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
 		void *vaddr;
 
-			vaddr = page_address(sg_page(&chunk->page_list[i]));
+		vaddr = page_address(sg_page(sg));
 		if (!vaddr) {
 			ret = ERR_PTR(-EINVAL);
 			goto bail;
@@ -241,7 +237,6 @@ struct ib_mr *ipath_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			n = 0;
 		}
 	}
-	}
 	ret = &mr->ibmr;
 
 bail:

drivers/infiniband/hw/mlx4/doorbell.c

@@ -45,7 +45,6 @@ int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
 			struct mlx4_db *db)
 {
 	struct mlx4_ib_user_db_page *page;
-	struct ib_umem_chunk *chunk;
 	int err = 0;
 
 	mutex_lock(&context->db_page_mutex);
@@ -73,8 +72,7 @@ int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
 	list_add(&page->list, &context->db_page_list);
 
 found:
-	chunk = list_entry(page->umem->chunk_list.next, struct ib_umem_chunk, list);
-	db->dma		= sg_dma_address(chunk->page_list) + (virt & ~PAGE_MASK);
+	db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK);
 	db->u.user_page = page;
 	++page->refcnt;
 

drivers/infiniband/hw/mlx4/mr.c

@@ -90,11 +90,11 @@ int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
 			   struct ib_umem *umem)
 {
 	u64 *pages;
-	struct ib_umem_chunk *chunk;
-	int i, j, k;
+	int i, k, entry;
 	int n;
 	int len;
 	int err = 0;
+	struct scatterlist *sg;
 
 	pages = (u64 *) __get_free_page(GFP_KERNEL);
 	if (!pages)
@@ -102,11 +102,10 @@ int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
 
 	i = n = 0;
 
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; ++j) {
-			len = sg_dma_len(&chunk->page_list[j]) >> mtt->page_shift;
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+		len = sg_dma_len(sg) >> mtt->page_shift;
 		for (k = 0; k < len; ++k) {
-				pages[i++] = sg_dma_address(&chunk->page_list[j]) +
+			pages[i++] = sg_dma_address(sg) +
 				umem->page_size * k;
 			/*
 			 * Be friendly to mlx4_write_mtt() and

drivers/infiniband/hw/mlx5/cq.c

@@ -366,6 +366,38 @@ static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
 	mlx5_buf_free(&dev->mdev, &buf->buf);
 }
 
+static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe,
+			     struct ib_sig_err *item)
+{
+	u16 syndrome = be16_to_cpu(cqe->syndrome);
+
+#define GUARD_ERR   (1 << 13)
+#define APPTAG_ERR  (1 << 12)
+#define REFTAG_ERR  (1 << 11)
+
+	if (syndrome & GUARD_ERR) {
+		item->err_type = IB_SIG_BAD_GUARD;
+		item->expected = be32_to_cpu(cqe->expected_trans_sig) >> 16;
+		item->actual = be32_to_cpu(cqe->actual_trans_sig) >> 16;
+	} else
+	if (syndrome & REFTAG_ERR) {
+		item->err_type = IB_SIG_BAD_REFTAG;
+		item->expected = be32_to_cpu(cqe->expected_reftag);
+		item->actual = be32_to_cpu(cqe->actual_reftag);
+	} else
+	if (syndrome & APPTAG_ERR) {
+		item->err_type = IB_SIG_BAD_APPTAG;
+		item->expected = be32_to_cpu(cqe->expected_trans_sig) & 0xffff;
+		item->actual = be32_to_cpu(cqe->actual_trans_sig) & 0xffff;
+	} else {
+		pr_err("Got signature completion error with bad syndrome %04x\n",
+		       syndrome);
+	}
+
+	item->sig_err_offset = be64_to_cpu(cqe->err_offset);
+	item->key = be32_to_cpu(cqe->mkey);
+}
+
 static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 			 struct mlx5_ib_qp **cur_qp,
 			 struct ib_wc *wc)
@@ -375,6 +407,9 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	struct mlx5_cqe64 *cqe64;
 	struct mlx5_core_qp *mqp;
 	struct mlx5_ib_wq *wq;
+	struct mlx5_sig_err_cqe *sig_err_cqe;
+	struct mlx5_core_mr *mmr;
+	struct mlx5_ib_mr *mr;
 	uint8_t opcode;
 	uint32_t qpn;
 	u16 wqe_ctr;
@@ -475,6 +510,33 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 			}
 		}
 		break;
+	case MLX5_CQE_SIG_ERR:
+		sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64;
+
+		read_lock(&dev->mdev.priv.mr_table.lock);
+		mmr = __mlx5_mr_lookup(&dev->mdev,
+				       mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
+		if (unlikely(!mmr)) {
+			read_unlock(&dev->mdev.priv.mr_table.lock);
+			mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n",
+				     cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey));
+			return -EINVAL;
+		}
+
+		mr = to_mibmr(mmr);
+		get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
+		mr->sig->sig_err_exists = true;
+		mr->sig->sigerr_count++;
+
+		mlx5_ib_warn(dev, "CQN: 0x%x Got SIGERR on key: 0x%x err_type %x err_offset %llx expected %x actual %x\n",
+			     cq->mcq.cqn, mr->sig->err_item.key,
+			     mr->sig->err_item.err_type,
+			     mr->sig->err_item.sig_err_offset,
+			     mr->sig->err_item.expected,
+			     mr->sig->err_item.actual);
+
+		read_unlock(&dev->mdev.priv.mr_table.lock);
+		goto repoll;
 	}
 
 	return 0;

drivers/infiniband/hw/mlx5/doorbell.c

@@ -47,7 +47,6 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
 			struct mlx5_db *db)
 {
 	struct mlx5_ib_user_db_page *page;
-	struct ib_umem_chunk *chunk;
 	int err = 0;
 
 	mutex_lock(&context->db_page_mutex);
@@ -75,8 +74,7 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
 	list_add(&page->list, &context->db_page_list);
 
 found:
-	chunk = list_entry(page->umem->chunk_list.next, struct ib_umem_chunk, list);
-	db->dma		= sg_dma_address(chunk->page_list) + (virt & ~PAGE_MASK);
+	db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK);
 	db->u.user_page = page;
 	++page->refcnt;
 

drivers/infiniband/hw/mlx5/main.c

@@ -273,6 +273,15 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	if (flags & MLX5_DEV_CAP_FLAG_XRC)
 		props->device_cap_flags |= IB_DEVICE_XRC;
 	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
+	if (flags & MLX5_DEV_CAP_FLAG_SIG_HAND_OVER) {
+		props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER;
+		/* At this stage no support for signature handover */
+		props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 |
+				      IB_PROT_T10DIF_TYPE_2 |
+				      IB_PROT_T10DIF_TYPE_3;
+		props->sig_guard_cap = IB_GUARD_T10DIF_CRC |
+				       IB_GUARD_T10DIF_CSUM;
+	}
 
 	props->vendor_id	   = be32_to_cpup((__be32 *)(out_mad->data + 36)) &
 		0xffffff;
@@ -1423,12 +1432,15 @@ static int init_one(struct pci_dev *pdev,
 	dev->ib_dev.get_dma_mr		= mlx5_ib_get_dma_mr;
 	dev->ib_dev.reg_user_mr		= mlx5_ib_reg_user_mr;
 	dev->ib_dev.dereg_mr		= mlx5_ib_dereg_mr;
+	dev->ib_dev.destroy_mr		= mlx5_ib_destroy_mr;
 	dev->ib_dev.attach_mcast	= mlx5_ib_mcg_attach;
 	dev->ib_dev.detach_mcast	= mlx5_ib_mcg_detach;
 	dev->ib_dev.process_mad		= mlx5_ib_process_mad;
+	dev->ib_dev.create_mr		= mlx5_ib_create_mr;
 	dev->ib_dev.alloc_fast_reg_mr	= mlx5_ib_alloc_fast_reg_mr;
 	dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list;
 	dev->ib_dev.free_fast_reg_page_list  = mlx5_ib_free_fast_reg_page_list;
+	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
 
 	if (mdev->caps.flags & MLX5_DEV_CAP_FLAG_XRC) {
 		dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd;

drivers/infiniband/hw/mlx5/mem.c

@@ -44,16 +44,17 @@
 void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 			int *ncont, int *order)
 {
-	struct ib_umem_chunk *chunk;
 	unsigned long tmp;
 	unsigned long m;
-	int i, j, k;
+	int i, k;
 	u64 base = 0;
 	int p = 0;
 	int skip;
 	int mask;
 	u64 len;
 	u64 pfn;
+	struct scatterlist *sg;
+	int entry;
 
 	addr = addr >> PAGE_SHIFT;
 	tmp = (unsigned long)addr;
@@ -61,10 +62,9 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	skip = 1 << m;
 	mask = skip - 1;
 	i = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; j++) {
-			len = sg_dma_len(&chunk->page_list[j]) >> PAGE_SHIFT;
-			pfn = sg_dma_address(&chunk->page_list[j]) >> PAGE_SHIFT;
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		pfn = sg_dma_address(sg) >> PAGE_SHIFT;
 		for (k = 0; k < len; k++) {
 			if (!(i & mask)) {
 				tmp = (unsigned long)pfn;
@@ -112,17 +112,17 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 {
 	int shift = page_shift - PAGE_SHIFT;
 	int mask = (1 << shift) - 1;
-	struct ib_umem_chunk *chunk;
-	int i, j, k;
+	int i, k;
 	u64 cur = 0;
 	u64 base;
 	int len;
+	struct scatterlist *sg;
+	int entry;
 
 	i = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; j++) {
-			len = sg_dma_len(&chunk->page_list[j]) >> PAGE_SHIFT;
-			base = sg_dma_address(&chunk->page_list[j]);
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		base = sg_dma_address(sg);
 		for (k = 0; k < len; k++) {
 			if (!(i & mask)) {
 				cur = base + (k << PAGE_SHIFT);

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -189,6 +189,9 @@ struct mlx5_ib_qp {
 
 	int			create_type;
 	u32			pa_lkey;
+
+	/* Store signature errors */
+	bool			signature_en;
 };
 
 struct mlx5_ib_cq_buf {
@@ -265,6 +268,7 @@ struct mlx5_ib_mr {
 	enum ib_wc_status	status;
 	struct mlx5_ib_dev     *dev;
 	struct mlx5_create_mkey_mbox_out out;
+	struct mlx5_core_sig_ctx    *sig;
 };
 
 struct mlx5_ib_fast_reg_page_list {
@@ -396,6 +400,11 @@ static inline struct mlx5_ib_qp *to_mibqp(struct mlx5_core_qp *mqp)
 	return container_of(mqp, struct mlx5_ib_qp, mqp);
 }
 
+static inline struct mlx5_ib_mr *to_mibmr(struct mlx5_core_mr *mmr)
+{
+	return container_of(mmr, struct mlx5_ib_mr, mmr);
+}
+
 static inline struct mlx5_ib_pd *to_mpd(struct ib_pd *ibpd)
 {
 	return container_of(ibpd, struct mlx5_ib_pd, ibpd);
@@ -495,6 +504,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
 				  struct ib_udata *udata);
 int mlx5_ib_dereg_mr(struct ib_mr *ibmr);
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr);
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+				struct ib_mr_init_attr *mr_init_attr);
 struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 					int max_page_list_len);
 struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
@@ -530,6 +542,8 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev);
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev);
 int mlx5_mr_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift);
 void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context);
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+			    struct ib_mr_status *mr_status);
 
 static inline void init_query_mad(struct ib_smp *mad)
 {

drivers/infiniband/hw/mlx5/mr.c

@@ -992,6 +992,122 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	return 0;
 }
 
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+				struct ib_mr_init_attr *mr_init_attr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct mlx5_create_mkey_mbox_in *in;
+	struct mlx5_ib_mr *mr;
+	int access_mode, err;
+	int ndescs = roundup(mr_init_attr->max_reg_descriptors, 4);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	in = kzalloc(sizeof(*in), GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	in->seg.status = 1 << 6; /* free */
+	in->seg.xlt_oct_size = cpu_to_be32(ndescs);
+	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+	in->seg.flags_pd = cpu_to_be32(to_mpd(pd)->pdn);
+	access_mode = MLX5_ACCESS_MODE_MTT;
+
+	if (mr_init_attr->flags & IB_MR_SIGNATURE_EN) {
+		u32 psv_index[2];
+
+		in->seg.flags_pd = cpu_to_be32(be32_to_cpu(in->seg.flags_pd) |
+							   MLX5_MKEY_BSF_EN);
+		in->seg.bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+		mr->sig = kzalloc(sizeof(*mr->sig), GFP_KERNEL);
+		if (!mr->sig) {
+			err = -ENOMEM;
+			goto err_free_in;
+		}
+
+		/* create mem & wire PSVs */
+		err = mlx5_core_create_psv(&dev->mdev, to_mpd(pd)->pdn,
+					   2, psv_index);
+		if (err)
+			goto err_free_sig;
+
+		access_mode = MLX5_ACCESS_MODE_KLM;
+		mr->sig->psv_memory.psv_idx = psv_index[0];
+		mr->sig->psv_wire.psv_idx = psv_index[1];
+
+		mr->sig->sig_status_checked = true;
+		mr->sig->sig_err_exists = false;
+		/* Next UMR, Arm SIGERR */
+		++mr->sig->sigerr_count;
+	}
+
+	in->seg.flags = MLX5_PERM_UMR_EN | access_mode;
+	err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in),
+				    NULL, NULL, NULL);
+	if (err)
+		goto err_destroy_psv;
+
+	mr->ibmr.lkey = mr->mmr.key;
+	mr->ibmr.rkey = mr->mmr.key;
+	mr->umem = NULL;
+	kfree(in);
+
+	return &mr->ibmr;
+
+err_destroy_psv:
+	if (mr->sig) {
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_memory.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+				     mr->sig->psv_memory.psv_idx);
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_wire.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+				     mr->sig->psv_wire.psv_idx);
+	}
+err_free_sig:
+	kfree(mr->sig);
+err_free_in:
+	kfree(in);
+err_free:
+	kfree(mr);
+	return ERR_PTR(err);
+}
+
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+	int err;
+
+	if (mr->sig) {
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_memory.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+				     mr->sig->psv_memory.psv_idx);
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_wire.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+				     mr->sig->psv_wire.psv_idx);
+		kfree(mr->sig);
+	}
+
+	err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
+	if (err) {
+		mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n",
+			     mr->mmr.key, err);
+		return err;
+	}
+
+	kfree(mr);
+
+	return err;
+}
+
 struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 					int max_page_list_len)
 {
@@ -1077,3 +1193,44 @@ void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
 	kfree(mfrpl->ibfrpl.page_list);
 	kfree(mfrpl);
 }
+
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+			    struct ib_mr_status *mr_status)
+{
+	struct mlx5_ib_mr *mmr = to_mmr(ibmr);
+	int ret = 0;
+
+	if (check_mask & ~IB_MR_CHECK_SIG_STATUS) {
+		pr_err("Invalid status check mask\n");
+		ret = -EINVAL;
+		goto done;
+	}
+
+	mr_status->fail_status = 0;
+	if (check_mask & IB_MR_CHECK_SIG_STATUS) {
+		if (!mmr->sig) {
+			ret = -EINVAL;
+			pr_err("signature status check requested on a non-signature enabled MR\n");
+			goto done;
+		}
+
+		mmr->sig->sig_status_checked = true;
+		if (!mmr->sig->sig_err_exists)
+			goto done;
+
+		if (ibmr->lkey == mmr->sig->err_item.key)
+			memcpy(&mr_status->sig_err, &mmr->sig->err_item,
+			       sizeof(mr_status->sig_err));
+		else {
+			mr_status->sig_err.err_type = IB_SIG_BAD_GUARD;
+			mr_status->sig_err.sig_err_offset = 0;
+			mr_status->sig_err.key = mmr->sig->err_item.key;
+		}
+
+		mmr->sig->sig_err_exists = false;
+		mr_status->fail_status |= IB_MR_CHECK_SIG_STATUS;
+	}
+
+done:
+	return ret;
+}

drivers/infiniband/hw/mlx5/qp.c

@@ -256,7 +256,10 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
 	}
 
 	size += attr->cap.max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-
+	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN &&
+	    ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB) < MLX5_SIG_WQE_SIZE)
+			return MLX5_SIG_WQE_SIZE;
+	else
 		return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
 }
 
@@ -284,6 +287,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 		sizeof(struct mlx5_wqe_inline_seg);
 	attr->cap.max_inline_data = qp->max_inline_data;
 
+	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN)
+		qp->signature_en = true;
+
 	wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size);
 	qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB;
 	if (qp->sq.wqe_cnt > dev->mdev.caps.max_wqes) {
@@ -665,7 +671,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	int err;
 
 	uuari = &dev->mdev.priv.uuari;
-	if (init_attr->create_flags)
+	if (init_attr->create_flags & ~IB_QP_CREATE_SIGNATURE_EN)
 		return -EINVAL;
 
 	if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
@@ -1771,6 +1777,27 @@ static __be64 frwr_mkey_mask(void)
 	return cpu_to_be64(result);
 }
 
+static __be64 sig_mkey_mask(void)
+{
+	u64 result;
+
+	result = MLX5_MKEY_MASK_LEN		|
+		MLX5_MKEY_MASK_PAGE_SIZE	|
+		MLX5_MKEY_MASK_START_ADDR	|
+		MLX5_MKEY_MASK_EN_SIGERR	|
+		MLX5_MKEY_MASK_EN_RINVAL	|
+		MLX5_MKEY_MASK_KEY		|
+		MLX5_MKEY_MASK_LR		|
+		MLX5_MKEY_MASK_LW		|
+		MLX5_MKEY_MASK_RR		|
+		MLX5_MKEY_MASK_RW		|
+		MLX5_MKEY_MASK_SMALL_FENCE	|
+		MLX5_MKEY_MASK_FREE		|
+		MLX5_MKEY_MASK_BSF_EN;
+
+	return cpu_to_be64(result);
+}
+
 static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 				 struct ib_send_wr *wr, int li)
 {
@@ -1826,7 +1853,7 @@ static u8 get_umr_flags(int acc)
 	       (acc & IB_ACCESS_REMOTE_WRITE  ? MLX5_PERM_REMOTE_WRITE : 0) |
 	       (acc & IB_ACCESS_REMOTE_READ   ? MLX5_PERM_REMOTE_READ  : 0) |
 	       (acc & IB_ACCESS_LOCAL_WRITE   ? MLX5_PERM_LOCAL_WRITE  : 0) |
-		MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN | MLX5_ACCESS_MODE_MTT;
+		MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN;
 }
 
 static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
@@ -1838,7 +1865,8 @@ static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
 		return;
 	}
 
-	seg->flags = get_umr_flags(wr->wr.fast_reg.access_flags);
+	seg->flags = get_umr_flags(wr->wr.fast_reg.access_flags) |
+		     MLX5_ACCESS_MODE_MTT;
 	*writ = seg->flags & (MLX5_PERM_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE);
 	seg->qpn_mkey7_0 = cpu_to_be32((wr->wr.fast_reg.rkey & 0xff) | 0xffffff00);
 	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL);
@@ -1954,6 +1982,342 @@ static int set_data_inl_seg(struct mlx5_ib_qp *qp, struct ib_send_wr *wr,
 	return 0;
 }
 
+static u16 prot_field_size(enum ib_signature_type type)
+{
+	switch (type) {
+	case IB_SIG_TYPE_T10_DIF:
+		return MLX5_DIF_SIZE;
+	default:
+		return 0;
+	}
+}
+
+static u8 bs_selector(int block_size)
+{
+	switch (block_size) {
+	case 512:	    return 0x1;
+	case 520:	    return 0x2;
+	case 4096:	    return 0x3;
+	case 4160:	    return 0x4;
+	case 1073741824:    return 0x5;
+	default:	    return 0;
+	}
+}
+
+static int format_selector(struct ib_sig_attrs *attr,
+			   struct ib_sig_domain *domain,
+			   int *selector)
+{
+
+#define FORMAT_DIF_NONE		0
+#define FORMAT_DIF_CRC_INC	8
+#define FORMAT_DIF_CRC_NO_INC	12
+#define FORMAT_DIF_CSUM_INC	13
+#define FORMAT_DIF_CSUM_NO_INC	14
+
+	switch (domain->sig.dif.type) {
+	case IB_T10DIF_NONE:
+		/* No DIF */
+		*selector = FORMAT_DIF_NONE;
+		break;
+	case IB_T10DIF_TYPE1: /* Fall through */
+	case IB_T10DIF_TYPE2:
+		switch (domain->sig.dif.bg_type) {
+		case IB_T10DIF_CRC:
+			*selector = FORMAT_DIF_CRC_INC;
+			break;
+		case IB_T10DIF_CSUM:
+			*selector = FORMAT_DIF_CSUM_INC;
+			break;
+		default:
+			return 1;
+		}
+		break;
+	case IB_T10DIF_TYPE3:
+		switch (domain->sig.dif.bg_type) {
+		case IB_T10DIF_CRC:
+			*selector = domain->sig.dif.type3_inc_reftag ?
+					   FORMAT_DIF_CRC_INC :
+					   FORMAT_DIF_CRC_NO_INC;
+			break;
+		case IB_T10DIF_CSUM:
+			*selector = domain->sig.dif.type3_inc_reftag ?
+					   FORMAT_DIF_CSUM_INC :
+					   FORMAT_DIF_CSUM_NO_INC;
+			break;
+		default:
+			return 1;
+		}
+		break;
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+static int mlx5_set_bsf(struct ib_mr *sig_mr,
+			struct ib_sig_attrs *sig_attrs,
+			struct mlx5_bsf *bsf, u32 data_size)
+{
+	struct mlx5_core_sig_ctx *msig = to_mmr(sig_mr)->sig;
+	struct mlx5_bsf_basic *basic = &bsf->basic;
+	struct ib_sig_domain *mem = &sig_attrs->mem;
+	struct ib_sig_domain *wire = &sig_attrs->wire;
+	int ret, selector;
+
+	switch (sig_attrs->mem.sig_type) {
+	case IB_SIG_TYPE_T10_DIF:
+		if (sig_attrs->wire.sig_type != IB_SIG_TYPE_T10_DIF)
+			return -EINVAL;
+
+		/* Input domain check byte mask */
+		basic->check_byte_mask = sig_attrs->check_mask;
+		if (mem->sig.dif.pi_interval == wire->sig.dif.pi_interval &&
+		    mem->sig.dif.type == wire->sig.dif.type) {
+			/* Same block structure */
+			basic->bsf_size_sbs = 1 << 4;
+			if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
+				basic->wire.copy_byte_mask = 0xff;
+			else
+				basic->wire.copy_byte_mask = 0x3f;
+		} else
+			basic->wire.bs_selector = bs_selector(wire->sig.dif.pi_interval);
+
+		basic->mem.bs_selector = bs_selector(mem->sig.dif.pi_interval);
+		basic->raw_data_size = cpu_to_be32(data_size);
+
+		ret = format_selector(sig_attrs, mem, &selector);
+		if (ret)
+			return -EINVAL;
+		basic->m_bfs_psv = cpu_to_be32(selector << 24 |
+					       msig->psv_memory.psv_idx);
+
+		ret = format_selector(sig_attrs, wire, &selector);
+		if (ret)
+			return -EINVAL;
+		basic->w_bfs_psv = cpu_to_be32(selector << 24 |
+					       msig->psv_wire.psv_idx);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int set_sig_data_segment(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+				void **seg, int *size)
+{
+	struct ib_sig_attrs *sig_attrs = wr->wr.sig_handover.sig_attrs;
+	struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+	struct mlx5_bsf *bsf;
+	u32 data_len = wr->sg_list->length;
+	u32 data_key = wr->sg_list->lkey;
+	u64 data_va = wr->sg_list->addr;
+	int ret;
+	int wqe_size;
+
+	if (!wr->wr.sig_handover.prot) {
+		/**
+		 * Source domain doesn't contain signature information
+		 * So need construct:
+		 *                  ------------------
+		 *                 |     data_klm     |
+		 *                  ------------------
+		 *                 |       BSF        |
+		 *                  ------------------
+		 **/
+		struct mlx5_klm *data_klm = *seg;
+
+		data_klm->bcount = cpu_to_be32(data_len);
+		data_klm->key = cpu_to_be32(data_key);
+		data_klm->va = cpu_to_be64(data_va);
+		wqe_size = ALIGN(sizeof(*data_klm), 64);
+	} else {
+		/**
+		 * Source domain contains signature information
+		 * So need construct a strided block format:
+		 *               ---------------------------
+		 *              |     stride_block_ctrl     |
+		 *               ---------------------------
+		 *              |          data_klm         |
+		 *               ---------------------------
+		 *              |          prot_klm         |
+		 *               ---------------------------
+		 *              |             BSF           |
+		 *               ---------------------------
+		 **/
+		struct mlx5_stride_block_ctrl_seg *sblock_ctrl;
+		struct mlx5_stride_block_entry *data_sentry;
+		struct mlx5_stride_block_entry *prot_sentry;
+		u32 prot_key = wr->wr.sig_handover.prot->lkey;
+		u64 prot_va = wr->wr.sig_handover.prot->addr;
+		u16 block_size = sig_attrs->mem.sig.dif.pi_interval;
+		int prot_size;
+
+		sblock_ctrl = *seg;
+		data_sentry = (void *)sblock_ctrl + sizeof(*sblock_ctrl);
+		prot_sentry = (void *)data_sentry + sizeof(*data_sentry);
+
+		prot_size = prot_field_size(sig_attrs->mem.sig_type);
+		if (!prot_size) {
+			pr_err("Bad block size given: %u\n", block_size);
+			return -EINVAL;
+		}
+		sblock_ctrl->bcount_per_cycle = cpu_to_be32(block_size +
+							    prot_size);
+		sblock_ctrl->op = cpu_to_be32(MLX5_STRIDE_BLOCK_OP);
+		sblock_ctrl->repeat_count = cpu_to_be32(data_len / block_size);
+		sblock_ctrl->num_entries = cpu_to_be16(2);
+
+		data_sentry->bcount = cpu_to_be16(block_size);
+		data_sentry->key = cpu_to_be32(data_key);
+		data_sentry->va = cpu_to_be64(data_va);
+		prot_sentry->bcount = cpu_to_be16(prot_size);
+		prot_sentry->key = cpu_to_be32(prot_key);
+
+		if (prot_key == data_key && prot_va == data_va) {
+			/**
+			 * The data and protection are interleaved
+			 * in a single memory region
+			 **/
+			prot_sentry->va = cpu_to_be64(data_va + block_size);
+			prot_sentry->stride = cpu_to_be16(block_size + prot_size);
+			data_sentry->stride = prot_sentry->stride;
+		} else {
+			/* The data and protection are two different buffers */
+			prot_sentry->va = cpu_to_be64(prot_va);
+			data_sentry->stride = cpu_to_be16(block_size);
+			prot_sentry->stride = cpu_to_be16(prot_size);
+		}
+		wqe_size = ALIGN(sizeof(*sblock_ctrl) + sizeof(*data_sentry) +
+				 sizeof(*prot_sentry), 64);
+	}
+
+	*seg += wqe_size;
+	*size += wqe_size / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	bsf = *seg;
+	ret = mlx5_set_bsf(sig_mr, sig_attrs, bsf, data_len);
+	if (ret)
+		return -EINVAL;
+
+	*seg += sizeof(*bsf);
+	*size += sizeof(*bsf) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	return 0;
+}
+
+static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
+				 struct ib_send_wr *wr, u32 nelements,
+				 u32 length, u32 pdn)
+{
+	struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+	u32 sig_key = sig_mr->rkey;
+	u8 sigerr = to_mmr(sig_mr)->sig->sigerr_count & 1;
+
+	memset(seg, 0, sizeof(*seg));
+
+	seg->flags = get_umr_flags(wr->wr.sig_handover.access_flags) |
+				   MLX5_ACCESS_MODE_KLM;
+	seg->qpn_mkey7_0 = cpu_to_be32((sig_key & 0xff) | 0xffffff00);
+	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL | sigerr << 26 |
+				    MLX5_MKEY_BSF_EN | pdn);
+	seg->len = cpu_to_be64(length);
+	seg->xlt_oct_size = cpu_to_be32(be16_to_cpu(get_klm_octo(nelements)));
+	seg->bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+}
+
+static void set_sig_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
+				struct ib_send_wr *wr, u32 nelements)
+{
+	memset(umr, 0, sizeof(*umr));
+
+	umr->flags = MLX5_FLAGS_INLINE | MLX5_FLAGS_CHECK_FREE;
+	umr->klm_octowords = get_klm_octo(nelements);
+	umr->bsf_octowords = cpu_to_be16(MLX5_MKEY_BSF_OCTO_SIZE);
+	umr->mkey_mask = sig_mkey_mask();
+}
+
+
+static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+			  void **seg, int *size)
+{
+	struct mlx5_ib_mr *sig_mr = to_mmr(wr->wr.sig_handover.sig_mr);
+	u32 pdn = get_pd(qp)->pdn;
+	u32 klm_oct_size;
+	int region_len, ret;
+
+	if (unlikely(wr->num_sge != 1) ||
+	    unlikely(wr->wr.sig_handover.access_flags &
+		     IB_ACCESS_REMOTE_ATOMIC) ||
+	    unlikely(!sig_mr->sig) || unlikely(!qp->signature_en) ||
+	    unlikely(!sig_mr->sig->sig_status_checked))
+		return -EINVAL;
+
+	/* length of the protected region, data + protection */
+	region_len = wr->sg_list->length;
+	if (wr->wr.sig_handover.prot)
+		region_len += wr->wr.sig_handover.prot->length;
+
+	/**
+	 * KLM octoword size - if protection was provided
+	 * then we use strided block format (3 octowords),
+	 * else we use single KLM (1 octoword)
+	 **/
+	klm_oct_size = wr->wr.sig_handover.prot ? 3 : 1;
+
+	set_sig_umr_segment(*seg, wr, klm_oct_size);
+	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
+	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	set_sig_mkey_segment(*seg, wr, klm_oct_size, region_len, pdn);
+	*seg += sizeof(struct mlx5_mkey_seg);
+	*size += sizeof(struct mlx5_mkey_seg) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	ret = set_sig_data_segment(wr, qp, seg, size);
+	if (ret)
+		return ret;
+
+	sig_mr->sig->sig_status_checked = false;
+	return 0;
+}
+
+static int set_psv_wr(struct ib_sig_domain *domain,
+		      u32 psv_idx, void **seg, int *size)
+{
+	struct mlx5_seg_set_psv *psv_seg = *seg;
+
+	memset(psv_seg, 0, sizeof(*psv_seg));
+	psv_seg->psv_num = cpu_to_be32(psv_idx);
+	switch (domain->sig_type) {
+	case IB_SIG_TYPE_T10_DIF:
+		psv_seg->transient_sig = cpu_to_be32(domain->sig.dif.bg << 16 |
+						     domain->sig.dif.app_tag);
+		psv_seg->ref_tag = cpu_to_be32(domain->sig.dif.ref_tag);
+
+		*seg += sizeof(*psv_seg);
+		*size += sizeof(*psv_seg) / 16;
+		break;
+
+	default:
+		pr_err("Bad signature type given.\n");
+		return 1;
+	}
+
+	return 0;
+}
+
 static int set_frwr_li_wr(void **seg, struct ib_send_wr *wr, int *size,
 			  struct mlx5_core_dev *mdev, struct mlx5_ib_pd *pd, struct mlx5_ib_qp *qp)
 {
@@ -2041,6 +2405,59 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr)
 	}
 }
 
+static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
+		     struct mlx5_wqe_ctrl_seg **ctrl,
+		     struct ib_send_wr *wr, int *idx,
+		     int *size, int nreq)
+{
+	int err = 0;
+
+	if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
+		err = -ENOMEM;
+		return err;
+	}
+
+	*idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
+	*seg = mlx5_get_send_wqe(qp, *idx);
+	*ctrl = *seg;
+	*(uint32_t *)(*seg + 8) = 0;
+	(*ctrl)->imm = send_ieth(wr);
+	(*ctrl)->fm_ce_se = qp->sq_signal_bits |
+		(wr->send_flags & IB_SEND_SIGNALED ?
+		 MLX5_WQE_CTRL_CQ_UPDATE : 0) |
+		(wr->send_flags & IB_SEND_SOLICITED ?
+		 MLX5_WQE_CTRL_SOLICITED : 0);
+
+	*seg += sizeof(**ctrl);
+	*size = sizeof(**ctrl) / 16;
+
+	return err;
+}
+
+static void finish_wqe(struct mlx5_ib_qp *qp,
+		       struct mlx5_wqe_ctrl_seg *ctrl,
+		       u8 size, unsigned idx, u64 wr_id,
+		       int nreq, u8 fence, u8 next_fence,
+		       u32 mlx5_opcode)
+{
+	u8 opmod = 0;
+
+	ctrl->opmod_idx_opcode = cpu_to_be32(((u32)(qp->sq.cur_post) << 8) |
+					     mlx5_opcode | ((u32)opmod << 24));
+	ctrl->qpn_ds = cpu_to_be32(size | (qp->mqp.qpn << 8));
+	ctrl->fm_ce_se |= fence;
+	qp->fm_cache = next_fence;
+	if (unlikely(qp->wq_sig))
+		ctrl->signature = wq_sig(ctrl);
+
+	qp->sq.wrid[idx] = wr_id;
+	qp->sq.w_list[idx].opcode = mlx5_opcode;
+	qp->sq.wqe_head[idx] = qp->sq.head + nreq;
+	qp->sq.cur_post += DIV_ROUND_UP(size * 16, MLX5_SEND_WQE_BB);
+	qp->sq.w_list[idx].next = qp->sq.cur_post;
+}
+
+
 int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		      struct ib_send_wr **bad_wr)
 {
@@ -2048,13 +2465,13 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx5_core_dev *mdev = &dev->mdev;
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
+	struct mlx5_ib_mr *mr;
 	struct mlx5_wqe_data_seg *dpseg;
 	struct mlx5_wqe_xrc_seg *xrc;
 	struct mlx5_bf *bf = qp->bf;
 	int uninitialized_var(size);
 	void *qend = qp->sq.qend;
 	unsigned long flags;
-	u32 mlx5_opcode;
 	unsigned idx;
 	int err = 0;
 	int inl = 0;
@@ -2063,7 +2480,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	int nreq;
 	int i;
 	u8 next_fence = 0;
-	u8 opmod = 0;
 	u8 fence;
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
@@ -2076,36 +2492,23 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			goto out;
 		}
 
-		if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
+		fence = qp->fm_cache;
+		num_sge = wr->num_sge;
+		if (unlikely(num_sge > qp->sq.max_gs)) {
 			mlx5_ib_warn(dev, "\n");
 			err = -ENOMEM;
 			*bad_wr = wr;
 			goto out;
 		}
 
-		fence = qp->fm_cache;
-		num_sge = wr->num_sge;
-		if (unlikely(num_sge > qp->sq.max_gs)) {
+		err = begin_wqe(qp, &seg, &ctrl, wr, &idx, &size, nreq);
+		if (err) {
 			mlx5_ib_warn(dev, "\n");
 			err = -ENOMEM;
 			*bad_wr = wr;
 			goto out;
 		}
 
-		idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
-		seg = mlx5_get_send_wqe(qp, idx);
-		ctrl = seg;
-		*(uint32_t *)(seg + 8) = 0;
-		ctrl->imm = send_ieth(wr);
-		ctrl->fm_ce_se = qp->sq_signal_bits |
-			(wr->send_flags & IB_SEND_SIGNALED ?
-			 MLX5_WQE_CTRL_CQ_UPDATE : 0) |
-			(wr->send_flags & IB_SEND_SOLICITED ?
-			 MLX5_WQE_CTRL_SOLICITED : 0);
-
-		seg += sizeof(*ctrl);
-		size = sizeof(*ctrl) / 16;
-
 		switch (ibqp->qp_type) {
 		case IB_QPT_XRC_INI:
 			xrc = seg;
@@ -2158,6 +2561,73 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				num_sge = 0;
 				break;
 
+			case IB_WR_REG_SIG_MR:
+				qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR;
+				mr = to_mmr(wr->wr.sig_handover.sig_mr);
+
+				ctrl->imm = cpu_to_be32(mr->ibmr.rkey);
+				err = set_sig_umr_wr(wr, qp, &seg, &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_UMR);
+				/*
+				 * SET_PSV WQEs are not signaled and solicited
+				 * on error
+				 */
+				wr->send_flags &= ~IB_SEND_SIGNALED;
+				wr->send_flags |= IB_SEND_SOLICITED;
+				err = begin_wqe(qp, &seg, &ctrl, wr,
+						&idx, &size, nreq);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					err = -ENOMEM;
+					*bad_wr = wr;
+					goto out;
+				}
+
+				err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->mem,
+						 mr->sig->psv_memory.psv_idx, &seg,
+						 &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_SET_PSV);
+				err = begin_wqe(qp, &seg, &ctrl, wr,
+						&idx, &size, nreq);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					err = -ENOMEM;
+					*bad_wr = wr;
+					goto out;
+				}
+
+				next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+				err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->wire,
+						 mr->sig->psv_wire.psv_idx, &seg,
+						 &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_SET_PSV);
+				num_sge = 0;
+				goto skip_psv;
+
 			default:
 				break;
 			}
@@ -2238,22 +2708,10 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			}
 		}
 
-		mlx5_opcode = mlx5_ib_opcode[wr->opcode];
-		ctrl->opmod_idx_opcode = cpu_to_be32(((u32)(qp->sq.cur_post) << 8)	|
-						     mlx5_opcode			|
-						     ((u32)opmod << 24));
-		ctrl->qpn_ds = cpu_to_be32(size | (qp->mqp.qpn << 8));
-		ctrl->fm_ce_se |= get_fence(fence, wr);
-		qp->fm_cache = next_fence;
-		if (unlikely(qp->wq_sig))
-			ctrl->signature = wq_sig(ctrl);
-
-		qp->sq.wrid[idx] = wr->wr_id;
-		qp->sq.w_list[idx].opcode = mlx5_opcode;
-		qp->sq.wqe_head[idx] = qp->sq.head + nreq;
-		qp->sq.cur_post += DIV_ROUND_UP(size * 16, MLX5_SEND_WQE_BB);
-		qp->sq.w_list[idx].next = qp->sq.cur_post;
-
+		finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
+			   get_fence(fence, wr), next_fence,
+			   mlx5_ib_opcode[wr->opcode]);
+skip_psv:
 		if (0)
 			dump_wqe(qp, idx, size);
 	}

drivers/infiniband/hw/mthca/mthca_provider.c

@@ -976,12 +976,12 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				       u64 virt, int acc, struct ib_udata *udata)
 {
 	struct mthca_dev *dev = to_mdev(pd->device);
-	struct ib_umem_chunk *chunk;
+	struct scatterlist *sg;
 	struct mthca_mr *mr;
 	struct mthca_reg_mr ucmd;
 	u64 *pages;
 	int shift, n, len;
-	int i, j, k;
+	int i, k, entry;
 	int err = 0;
 	int write_mtt_size;
 
@@ -1009,10 +1009,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	}
 
 	shift = ffs(mr->umem->page_size) - 1;
-
-	n = 0;
-	list_for_each_entry(chunk, &mr->umem->chunk_list, list)
-		n += chunk->nents;
+	n = mr->umem->nmap;
 
 	mr->mtt = mthca_alloc_mtt(dev, n);
 	if (IS_ERR(mr->mtt)) {
@@ -1030,11 +1027,10 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	write_mtt_size = min(mthca_write_mtt_size(dev), (int) (PAGE_SIZE / sizeof *pages));
 
-	list_for_each_entry(chunk, &mr->umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; ++j) {
-			len = sg_dma_len(&chunk->page_list[j]) >> shift;
+	for_each_sg(mr->umem->sg_head.sgl, sg, mr->umem->nmap, entry) {
+		len = sg_dma_len(sg) >> shift;
 		for (k = 0; k < len; ++k) {
-				pages[i++] = sg_dma_address(&chunk->page_list[j]) +
+			pages[i++] = sg_dma_address(sg) +
 				mr->umem->page_size * k;
 			/*
 			 * Be friendly to write_mtt and pass it chunks

drivers/infiniband/hw/nes/nes_verbs.c

@@ -2307,7 +2307,7 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	struct nes_device *nesdev = nesvnic->nesdev;
 	struct nes_adapter *nesadapter = nesdev->nesadapter;
 	struct ib_mr *ibmr = ERR_PTR(-EINVAL);
-	struct ib_umem_chunk *chunk;
+	struct scatterlist *sg;
 	struct nes_ucontext *nes_ucontext;
 	struct nes_pbl *nespbl;
 	struct nes_mr *nesmr;
@@ -2315,7 +2315,7 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	struct nes_mem_reg_req req;
 	struct nes_vpbl vpbl;
 	struct nes_root_vpbl root_vpbl;
-	int nmap_index, page_index;
+	int entry, page_index;
 	int page_count = 0;
 	int err, pbl_depth = 0;
 	int chunk_pages;
@@ -2330,6 +2330,7 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	u16 pbl_count;
 	u8 single_page = 1;
 	u8 stag_key;
+	int first_page = 1;
 
 	region = ib_umem_get(pd->uobject->context, start, length, acc, 0);
 	if (IS_ERR(region)) {
@@ -2380,21 +2381,18 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			}
 			nesmr->region = region;
 
-			list_for_each_entry(chunk, &region->chunk_list, list) {
-				nes_debug(NES_DBG_MR, "Chunk: nents = %u, nmap = %u .\n",
-						chunk->nents, chunk->nmap);
-				for (nmap_index = 0; nmap_index < chunk->nmap; ++nmap_index) {
-					if (sg_dma_address(&chunk->page_list[nmap_index]) & ~PAGE_MASK) {
+			for_each_sg(region->sg_head.sgl, sg, region->nmap, entry) {
+				if (sg_dma_address(sg) & ~PAGE_MASK) {
 					ib_umem_release(region);
 					nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
 					nes_debug(NES_DBG_MR, "Unaligned Memory Buffer: 0x%x\n",
-								(unsigned int) sg_dma_address(&chunk->page_list[nmap_index]));
+						  (unsigned int) sg_dma_address(sg));
 					ibmr = ERR_PTR(-EINVAL);
 					kfree(nesmr);
 					goto reg_user_mr_err;
 				}
 
-					if (!sg_dma_len(&chunk->page_list[nmap_index])) {
+				if (!sg_dma_len(sg)) {
 					ib_umem_release(region);
 					nes_free_resource(nesadapter, nesadapter->allocated_mrs,
 							  stag_index);
@@ -2404,12 +2402,12 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 					goto reg_user_mr_err;
 				}
 
-					region_length += sg_dma_len(&chunk->page_list[nmap_index]);
-					chunk_pages = sg_dma_len(&chunk->page_list[nmap_index]) >> 12;
+				region_length += sg_dma_len(sg);
+				chunk_pages = sg_dma_len(sg) >> 12;
 				region_length -= skip_pages << 12;
-					for (page_index=skip_pages; page_index < chunk_pages; page_index++) {
+				for (page_index = skip_pages; page_index < chunk_pages; page_index++) {
 					skip_pages = 0;
-						if ((page_count!=0)&&(page_count<<12)-(region->offset&(4096-1))>=region->length)
+					if ((page_count != 0) && (page_count<<12)-(region->offset&(4096-1)) >= region->length)
 						goto enough_pages;
 					if ((page_count&0x01FF) == 0) {
 						if (page_count >= 1024 * 512) {
@@ -2479,29 +2477,29 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 					if (single_page) {
 						if (page_count != 0) {
 							if ((last_dma_addr+4096) !=
-										(sg_dma_address(&chunk->page_list[nmap_index])+
+									(sg_dma_address(sg)+
 									(page_index*4096)))
 								single_page = 0;
-								last_dma_addr = sg_dma_address(&chunk->page_list[nmap_index])+
+							last_dma_addr = sg_dma_address(sg)+
 									(page_index*4096);
 						} else {
-								first_dma_addr = sg_dma_address(&chunk->page_list[nmap_index])+
+							first_dma_addr = sg_dma_address(sg)+
 									(page_index*4096);
 							last_dma_addr = first_dma_addr;
 						}
 					}
 
 					vpbl.pbl_vbase[cur_pbl_index].pa_low =
-								cpu_to_le32((u32)(sg_dma_address(&chunk->page_list[nmap_index])+
+							cpu_to_le32((u32)(sg_dma_address(sg)+
 							(page_index*4096)));
 					vpbl.pbl_vbase[cur_pbl_index].pa_high =
-								cpu_to_le32((u32)((((u64)(sg_dma_address(&chunk->page_list[nmap_index])+
+							cpu_to_le32((u32)((((u64)(sg_dma_address(sg)+
 							(page_index*4096))) >> 32)));
 					cur_pbl_index++;
 					page_count++;
 				}
 			}
-			}
+
 			enough_pages:
 			nes_debug(NES_DBG_MR, "calculating stag, stag_index=0x%08x, driver_key=0x%08x,"
 					" stag_key=0x%08x\n",
@@ -2613,17 +2611,20 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  nespbl->pbl_size, (unsigned long) nespbl->pbl_pbase,
 				  (void *) nespbl->pbl_vbase, nespbl->user_base);
 
-			list_for_each_entry(chunk, &region->chunk_list, list) {
-				for (nmap_index = 0; nmap_index < chunk->nmap; ++nmap_index) {
-					chunk_pages = sg_dma_len(&chunk->page_list[nmap_index]) >> 12;
-					chunk_pages += (sg_dma_len(&chunk->page_list[nmap_index]) & (4096-1)) ? 1 : 0;
-					nespbl->page = sg_page(&chunk->page_list[0]);
-					for (page_index=0; page_index<chunk_pages; page_index++) {
+			for_each_sg(region->sg_head.sgl, sg, region->nmap, entry) {
+				chunk_pages = sg_dma_len(sg) >> 12;
+				chunk_pages += (sg_dma_len(sg) & (4096-1)) ? 1 : 0;
+				if (first_page) {
+					nespbl->page = sg_page(sg);
+					first_page = 0;
+				}
+
+				for (page_index = 0; page_index < chunk_pages; page_index++) {
 					((__le32 *)pbl)[0] = cpu_to_le32((u32)
-								(sg_dma_address(&chunk->page_list[nmap_index])+
+							(sg_dma_address(sg)+
 							(page_index*4096)));
 					((__le32 *)pbl)[1] = cpu_to_le32(((u64)
-								(sg_dma_address(&chunk->page_list[nmap_index])+
+							(sg_dma_address(sg)+
 							(page_index*4096)))>>32);
 					nes_debug(NES_DBG_MR, "pbl=%p, *pbl=0x%016llx, 0x%08x%08x\n", pbl,
 						  (unsigned long long)*pbl,
@@ -2631,7 +2632,7 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 					pbl++;
 				}
 			}
-			}
+
 			if (req.reg_type == IWNES_MEMREG_TYPE_QP) {
 				list_add_tail(&nespbl->list, &nes_ucontext->qp_reg_mem_list);
 			} else {

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c

@@ -726,10 +726,10 @@ static void build_user_pbes(struct ocrdma_dev *dev, struct ocrdma_mr *mr,
 			    u32 num_pbes)
 {
 	struct ocrdma_pbe *pbe;
-	struct ib_umem_chunk *chunk;
+	struct scatterlist *sg;
 	struct ocrdma_pbl *pbl_tbl = mr->hwmr.pbl_table;
 	struct ib_umem *umem = mr->umem;
-	int i, shift, pg_cnt, pages, pbe_cnt, total_num_pbes = 0;
+	int shift, pg_cnt, pages, pbe_cnt, entry, total_num_pbes = 0;
 
 	if (!mr->hwmr.num_pbes)
 		return;
@@ -739,20 +739,18 @@ static void build_user_pbes(struct ocrdma_dev *dev, struct ocrdma_mr *mr,
 
 	shift = ilog2(umem->page_size);
 
-	list_for_each_entry(chunk, &umem->chunk_list, list) {
-		/* get all the dma regions from the chunk. */
-		for (i = 0; i < chunk->nmap; i++) {
-			pages = sg_dma_len(&chunk->page_list[i]) >> shift;
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+		pages = sg_dma_len(sg) >> shift;
 		for (pg_cnt = 0; pg_cnt < pages; pg_cnt++) {
 			/* store the page address in pbe */
 			pbe->pa_lo =
 			    cpu_to_le32(sg_dma_address
-						(&chunk->page_list[i]) +
+					(sg) +
 					(umem->page_size * pg_cnt));
 			pbe->pa_hi =
 			    cpu_to_le32(upper_32_bits
 					((sg_dma_address
-						  (&chunk->page_list[i]) +
+					  (sg) +
 					  umem->page_size * pg_cnt)));
 			pbe_cnt += 1;
 			total_num_pbes += 1;
@@ -771,7 +769,7 @@ static void build_user_pbes(struct ocrdma_dev *dev, struct ocrdma_mr *mr,
 				pbe = (struct ocrdma_pbe *)pbl_tbl->va;
 				pbe_cnt = 0;
 			}
-			}
+
 		}
 	}
 }

drivers/infiniband/hw/qib/qib_mr.c

@@ -232,8 +232,8 @@ struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 {
 	struct qib_mr *mr;
 	struct ib_umem *umem;
-	struct ib_umem_chunk *chunk;
-	int n, m, i;
+	struct scatterlist *sg;
+	int n, m, entry;
 	struct ib_mr *ret;
 
 	if (length == 0) {
@@ -246,9 +246,7 @@ struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	if (IS_ERR(umem))
 		return (void *) umem;
 
-	n = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		n += chunk->nents;
+	n = umem->nmap;
 
 	mr = alloc_mr(n, pd);
 	if (IS_ERR(mr)) {
@@ -268,11 +266,10 @@ struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		mr->mr.page_shift = ilog2(umem->page_size);
 	m = 0;
 	n = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list) {
-		for (i = 0; i < chunk->nents; i++) {
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
 			void *vaddr;
 
-			vaddr = page_address(sg_page(&chunk->page_list[i]));
+			vaddr = page_address(sg_page(sg));
 			if (!vaddr) {
 				ret = ERR_PTR(-EINVAL);
 				goto bail;
@@ -285,7 +282,6 @@ struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				n = 0;
 			}
 	}
-	}
 	ret = &mr->ibmr;
 
 bail:

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -446,6 +446,7 @@ int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 	mlx5_init_cq_table(dev);
 	mlx5_init_qp_table(dev);
 	mlx5_init_srq_table(dev);
+	mlx5_init_mr_table(dev);
 
 	return 0;
 

drivers/net/ethernet/mellanox/mlx5/core/mr.c

@@ -36,11 +36,24 @@
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
+void mlx5_init_mr_table(struct mlx5_core_dev *dev)
+{
+	struct mlx5_mr_table *table = &dev->priv.mr_table;
+
+	rwlock_init(&table->lock);
+	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+}
+
+void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev)
+{
+}
+
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 			  struct mlx5_create_mkey_mbox_in *in, int inlen,
 			  mlx5_cmd_cbk_t callback, void *context,
 			  struct mlx5_create_mkey_mbox_out *out)
 {
+	struct mlx5_mr_table *table = &dev->priv.mr_table;
 	struct mlx5_create_mkey_mbox_out lout;
 	int err;
 	u8 key;
@@ -73,14 +86,21 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n",
 		      be32_to_cpu(lout.mkey), key, mr->key);
 
+	/* connect to MR tree */
+	write_lock_irq(&table->lock);
+	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->key), mr);
+	write_unlock_irq(&table->lock);
+
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_create_mkey);
 
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 {
+	struct mlx5_mr_table *table = &dev->priv.mr_table;
 	struct mlx5_destroy_mkey_mbox_in in;
 	struct mlx5_destroy_mkey_mbox_out out;
+	unsigned long flags;
 	int err;
 
 	memset(&in, 0, sizeof(in));
@@ -95,6 +115,10 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 	if (out.hdr.status)
 		return mlx5_cmd_status_to_err(&out.hdr);
 
+	write_lock_irqsave(&table->lock, flags);
+	radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key));
+	write_unlock_irqrestore(&table->lock, flags);
+
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_destroy_mkey);
@@ -144,3 +168,64 @@ int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_dump_fill_mkey);
+
+int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
+			 int npsvs, u32 *sig_index)
+{
+	struct mlx5_allocate_psv_in in;
+	struct mlx5_allocate_psv_out out;
+	int i, err;
+
+	if (npsvs > MLX5_MAX_PSVS)
+		return -EINVAL;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_PSV);
+	in.npsv_pd = cpu_to_be32((npsvs << 28) | pdn);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err) {
+		mlx5_core_err(dev, "cmd exec failed %d\n", err);
+		return err;
+	}
+
+	if (out.hdr.status) {
+		mlx5_core_err(dev, "create_psv bad status %d\n", out.hdr.status);
+		return mlx5_cmd_status_to_err(&out.hdr);
+	}
+
+	for (i = 0; i < npsvs; i++)
+		sig_index[i] = be32_to_cpu(out.psv_idx[i]) & 0xffffff;
+
+	return err;
+}
+EXPORT_SYMBOL(mlx5_core_create_psv);
+
+int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num)
+{
+	struct mlx5_destroy_psv_in in;
+	struct mlx5_destroy_psv_out out;
+	int err;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+
+	in.psv_number = cpu_to_be32(psv_num);
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_PSV);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err) {
+		mlx5_core_err(dev, "destroy_psv cmd exec failed %d\n", err);
+		goto out;
+	}
+
+	if (out.hdr.status) {
+		mlx5_core_err(dev, "destroy_psv bad status %d\n", out.hdr.status);
+		err = mlx5_cmd_status_to_err(&out.hdr);
+		goto out;
+	}
+
+out:
+	return err;
+}
+EXPORT_SYMBOL(mlx5_core_destroy_psv);

include/linux/mlx5/cq.h

@@ -80,6 +80,7 @@ enum {
 	MLX5_CQE_RESP_SEND_IMM	= 3,
 	MLX5_CQE_RESP_SEND_INV	= 4,
 	MLX5_CQE_RESIZE_CQ	= 5,
+	MLX5_CQE_SIG_ERR	= 12,
 	MLX5_CQE_REQ_ERR	= 13,
 	MLX5_CQE_RESP_ERR	= 14,
 	MLX5_CQE_INVALID	= 15,

include/linux/mlx5/device.h

@@ -48,6 +48,8 @@ enum {
 	MLX5_MAX_COMMANDS		= 32,
 	MLX5_CMD_DATA_BLOCK_SIZE	= 512,
 	MLX5_PCI_CMD_XPORT		= 7,
+	MLX5_MKEY_BSF_OCTO_SIZE		= 4,
+	MLX5_MAX_PSVS			= 4,
 };
 
 enum {
@@ -116,6 +118,7 @@ enum {
 	MLX5_MKEY_MASK_START_ADDR	= 1ull << 6,
 	MLX5_MKEY_MASK_PD		= 1ull << 7,
 	MLX5_MKEY_MASK_EN_RINVAL	= 1ull << 8,
+	MLX5_MKEY_MASK_EN_SIGERR	= 1ull << 9,
 	MLX5_MKEY_MASK_BSF_EN		= 1ull << 12,
 	MLX5_MKEY_MASK_KEY		= 1ull << 13,
 	MLX5_MKEY_MASK_QPN		= 1ull << 14,
@@ -555,6 +558,23 @@ struct mlx5_cqe64 {
 	u8		op_own;
 };
 
+struct mlx5_sig_err_cqe {
+	u8		rsvd0[16];
+	__be32		expected_trans_sig;
+	__be32		actual_trans_sig;
+	__be32		expected_reftag;
+	__be32		actual_reftag;
+	__be16		syndrome;
+	u8		rsvd22[2];
+	__be32		mkey;
+	__be64		err_offset;
+	u8		rsvd30[8];
+	__be32		qpn;
+	u8		rsvd38[2];
+	u8		signature;
+	u8		op_own;
+};
+
 struct mlx5_wqe_srq_next_seg {
 	u8			rsvd0[2];
 	__be16			next_wqe_index;
@@ -936,4 +956,27 @@ enum {
 	MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO	= 1 <<  0
 };
 
+struct mlx5_allocate_psv_in {
+	struct mlx5_inbox_hdr   hdr;
+	__be32			npsv_pd;
+	__be32			rsvd_psv0;
+};
+
+struct mlx5_allocate_psv_out {
+	struct mlx5_outbox_hdr  hdr;
+	u8			rsvd[8];
+	__be32			psv_idx[4];
+};
+
+struct mlx5_destroy_psv_in {
+	struct mlx5_inbox_hdr	hdr;
+	__be32                  psv_number;
+	u8                      rsvd[4];
+};
+
+struct mlx5_destroy_psv_out {
+	struct mlx5_outbox_hdr  hdr;
+	u8                      rsvd[8];
+};
+
 #endif /* MLX5_DEVICE_H */

include/linux/mlx5/driver.h

@@ -401,6 +401,26 @@ struct mlx5_eq {
 	struct mlx5_rsc_debug	*dbg;
 };
 
+struct mlx5_core_psv {
+	u32	psv_idx;
+	struct psv_layout {
+		u32	pd;
+		u16	syndrome;
+		u16	reserved;
+		u16	bg;
+		u16	app_tag;
+		u32	ref_tag;
+	} psv;
+};
+
+struct mlx5_core_sig_ctx {
+	struct mlx5_core_psv	psv_memory;
+	struct mlx5_core_psv	psv_wire;
+	struct ib_sig_err       err_item;
+	bool			sig_status_checked;
+	bool			sig_err_exists;
+	u32			sigerr_count;
+};
 
 struct mlx5_core_mr {
 	u64			iova;
@@ -475,6 +495,13 @@ struct mlx5_srq_table {
 	struct radix_tree_root	tree;
 };
 
+struct mlx5_mr_table {
+	/* protect radix tree
+	 */
+	rwlock_t		lock;
+	struct radix_tree_root	tree;
+};
+
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
@@ -504,6 +531,10 @@ struct mlx5_priv {
 	struct mlx5_cq_table	cq_table;
 	/* end: cq staff */
 
+	/* start: mr staff */
+	struct mlx5_mr_table	mr_table;
+	/* end: mr staff */
+
 	/* start: alloc staff */
 	struct mutex            pgdir_mutex;
 	struct list_head        pgdir_list;
@@ -651,6 +682,11 @@ static inline void mlx5_vfree(const void *addr)
 		kfree(addr);
 }
 
+static inline u32 mlx5_base_mkey(const u32 key)
+{
+	return key & 0xffffff00u;
+}
+
 int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev);
 void mlx5_dev_cleanup(struct mlx5_core_dev *dev);
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
@@ -685,6 +721,8 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 			struct mlx5_query_srq_mbox_out *out);
 int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 		      u16 lwm, int is_srq);
+void mlx5_init_mr_table(struct mlx5_core_dev *dev);
+void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev);
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 			  struct mlx5_create_mkey_mbox_in *in, int inlen,
 			  mlx5_cmd_cbk_t callback, void *context,
@@ -746,6 +784,9 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db);
 const char *mlx5_command_str(int command);
 int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev);
+int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
+			 int npsvs, u32 *sig_index);
+int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num);
 
 static inline u32 mlx5_mkey_to_idx(u32 mkey)
 {

include/linux/mlx5/qp.h

@@ -37,6 +37,9 @@
 #include <linux/mlx5/driver.h>
 
 #define MLX5_INVALID_LKEY	0x100
+#define MLX5_SIG_WQE_SIZE	(MLX5_SEND_WQE_BB * 5)
+#define MLX5_DIF_SIZE		8
+#define MLX5_STRIDE_BLOCK_OP	0x400
 
 enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_ALT_ADDR_PATH		= 1 << 0,
@@ -151,6 +154,11 @@ enum {
 	MLX5_SND_DBR	= 1,
 };
 
+enum {
+	MLX5_FLAGS_INLINE	= 1<<7,
+	MLX5_FLAGS_CHECK_FREE   = 1<<5,
+};
+
 struct mlx5_wqe_fmr_seg {
 	__be32			flags;
 	__be32			mem_key;
@@ -278,6 +286,60 @@ struct mlx5_wqe_inline_seg {
 	__be32	byte_count;
 };
 
+struct mlx5_bsf {
+	struct mlx5_bsf_basic {
+		u8		bsf_size_sbs;
+		u8		check_byte_mask;
+		union {
+			u8	copy_byte_mask;
+			u8	bs_selector;
+			u8	rsvd_wflags;
+		} wire;
+		union {
+			u8	bs_selector;
+			u8	rsvd_mflags;
+		} mem;
+		__be32		raw_data_size;
+		__be32		w_bfs_psv;
+		__be32		m_bfs_psv;
+	} basic;
+	struct mlx5_bsf_ext {
+		__be32		t_init_gen_pro_size;
+		__be32		rsvd_epi_size;
+		__be32		w_tfs_psv;
+		__be32		m_tfs_psv;
+	} ext;
+	struct mlx5_bsf_inl {
+		__be32		w_inl_vld;
+		__be32		w_rsvd;
+		__be64		w_block_format;
+		__be32		m_inl_vld;
+		__be32		m_rsvd;
+		__be64		m_block_format;
+	} inl;
+};
+
+struct mlx5_klm {
+	__be32		bcount;
+	__be32		key;
+	__be64		va;
+};
+
+struct mlx5_stride_block_entry {
+	__be16		stride;
+	__be16		bcount;
+	__be32		key;
+	__be64		va;
+};
+
+struct mlx5_stride_block_ctrl_seg {
+	__be32		bcount_per_cycle;
+	__be32		op;
+	__be32		repeat_count;
+	u16		rsvd;
+	__be16		num_entries;
+};
+
 struct mlx5_core_qp {
 	void (*event)		(struct mlx5_core_qp *, int);
 	int			qpn;
@@ -444,6 +506,11 @@ static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u
 	return radix_tree_lookup(&dev->priv.qp_table.tree, qpn);
 }
 
+static inline struct mlx5_core_mr *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key)
+{
+	return radix_tree_lookup(&dev->priv.mr_table.tree, key);
+}
+
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 			struct mlx5_core_qp *qp,
 			struct mlx5_create_qp_mbox_in *in,

include/rdma/ib_umem.h

@@ -46,17 +46,12 @@ struct ib_umem {
 	int			page_size;
 	int                     writable;
 	int                     hugetlb;
-	struct list_head	chunk_list;
 	struct work_struct	work;
 	struct mm_struct       *mm;
 	unsigned long		diff;
-};
-
-struct ib_umem_chunk {
-	struct list_head	list;
-	int                     nents;
+	struct sg_table sg_head;
 	int             nmap;
-	struct scatterlist      page_list[0];
+	int             npages;
 };
 
 #ifdef CONFIG_INFINIBAND_USER_MEM

include/rdma/ib_verbs.h

@@ -122,7 +122,19 @@ enum ib_device_cap_flags {
 	IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1<<22),
 	IB_DEVICE_MEM_WINDOW_TYPE_2A	= (1<<23),
 	IB_DEVICE_MEM_WINDOW_TYPE_2B	= (1<<24),
-	IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29)
+	IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29),
+	IB_DEVICE_SIGNATURE_HANDOVER	= (1<<30)
+};
+
+enum ib_signature_prot_cap {
+	IB_PROT_T10DIF_TYPE_1 = 1,
+	IB_PROT_T10DIF_TYPE_2 = 1 << 1,
+	IB_PROT_T10DIF_TYPE_3 = 1 << 2,
+};
+
+enum ib_signature_guard_cap {
+	IB_GUARD_T10DIF_CRC	= 1,
+	IB_GUARD_T10DIF_CSUM	= 1 << 1,
 };
 
 enum ib_atomic_cap {
@@ -172,6 +184,8 @@ struct ib_device_attr {
 	unsigned int		max_fast_reg_page_list_len;
 	u16			max_pkeys;
 	u8			local_ca_ack_delay;
+	int			sig_prot_cap;
+	int			sig_guard_cap;
 };
 
 enum ib_mtu {
@@ -461,6 +475,130 @@ int ib_rate_to_mult(enum ib_rate rate) __attribute_const__;
  */
 int ib_rate_to_mbps(enum ib_rate rate) __attribute_const__;
 
+enum ib_mr_create_flags {
+	IB_MR_SIGNATURE_EN = 1,
+};
+
+/**
+ * ib_mr_init_attr - Memory region init attributes passed to routine
+ *     ib_create_mr.
+ * @max_reg_descriptors: max number of registration descriptors that
+ *     may be used with registration work requests.
+ * @flags: MR creation flags bit mask.
+ */
+struct ib_mr_init_attr {
+	int	    max_reg_descriptors;
+	u32	    flags;
+};
+
+enum ib_signature_type {
+	IB_SIG_TYPE_T10_DIF,
+};
+
+/**
+ * T10-DIF Signature types
+ * T10-DIF types are defined by SCSI
+ * specifications.
+ */
+enum ib_t10_dif_type {
+	IB_T10DIF_NONE,
+	IB_T10DIF_TYPE1,
+	IB_T10DIF_TYPE2,
+	IB_T10DIF_TYPE3
+};
+
+/**
+ * Signature T10-DIF block-guard types
+ * IB_T10DIF_CRC: Corresponds to T10-PI mandated CRC checksum rules.
+ * IB_T10DIF_CSUM: Corresponds to IP checksum rules.
+ */
+enum ib_t10_dif_bg_type {
+	IB_T10DIF_CRC,
+	IB_T10DIF_CSUM
+};
+
+/**
+ * struct ib_t10_dif_domain - Parameters specific for T10-DIF
+ *     domain.
+ * @type: T10-DIF type (0|1|2|3)
+ * @bg_type: T10-DIF block guard type (CRC|CSUM)
+ * @pi_interval: protection information interval.
+ * @bg: seed of guard computation.
+ * @app_tag: application tag of guard block
+ * @ref_tag: initial guard block reference tag.
+ * @type3_inc_reftag: T10-DIF type 3 does not state
+ *     about the reference tag, it is the user
+ *     choice to increment it or not.
+ */
+struct ib_t10_dif_domain {
+	enum ib_t10_dif_type	type;
+	enum ib_t10_dif_bg_type bg_type;
+	u16			pi_interval;
+	u16			bg;
+	u16			app_tag;
+	u32			ref_tag;
+	bool			type3_inc_reftag;
+};
+
+/**
+ * struct ib_sig_domain - Parameters for signature domain
+ * @sig_type: specific signauture type
+ * @sig: union of all signature domain attributes that may
+ *     be used to set domain layout.
+ */
+struct ib_sig_domain {
+	enum ib_signature_type sig_type;
+	union {
+		struct ib_t10_dif_domain dif;
+	} sig;
+};
+
+/**
+ * struct ib_sig_attrs - Parameters for signature handover operation
+ * @check_mask: bitmask for signature byte check (8 bytes)
+ * @mem: memory domain layout desciptor.
+ * @wire: wire domain layout desciptor.
+ */
+struct ib_sig_attrs {
+	u8			check_mask;
+	struct ib_sig_domain	mem;
+	struct ib_sig_domain	wire;
+};
+
+enum ib_sig_err_type {
+	IB_SIG_BAD_GUARD,
+	IB_SIG_BAD_REFTAG,
+	IB_SIG_BAD_APPTAG,
+};
+
+/**
+ * struct ib_sig_err - signature error descriptor
+ */
+struct ib_sig_err {
+	enum ib_sig_err_type	err_type;
+	u32			expected;
+	u32			actual;
+	u64			sig_err_offset;
+	u32			key;
+};
+
+enum ib_mr_status_check {
+	IB_MR_CHECK_SIG_STATUS = 1,
+};
+
+/**
+ * struct ib_mr_status - Memory region status container
+ *
+ * @fail_status: Bitmask of MR checks status. For each
+ *     failed check a corresponding status bit is set.
+ * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS
+ *     failure.
+ */
+struct ib_mr_status {
+	u32		    fail_status;
+	struct ib_sig_err   sig_err;
+};
+
 /**
  * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate
  * enum.
@@ -644,6 +782,7 @@ enum ib_qp_create_flags {
 	IB_QP_CREATE_IPOIB_UD_LSO		= 1 << 0,
 	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	= 1 << 1,
 	IB_QP_CREATE_NETIF_QP			= 1 << 5,
+	IB_QP_CREATE_SIGNATURE_EN		= 1 << 6,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -808,6 +947,7 @@ enum ib_wr_opcode {
 	IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
 	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
 	IB_WR_BIND_MW,
+	IB_WR_REG_SIG_MR,
 	/* reserve values for low level drivers' internal use.
 	 * These values will not be used at all in the ib core layer.
 	 */
@@ -913,6 +1053,12 @@ struct ib_send_wr {
 			u32                      rkey;
 			struct ib_mw_bind_info   bind_info;
 		} bind_mw;
+		struct {
+			struct ib_sig_attrs    *sig_attrs;
+			struct ib_mr	       *sig_mr;
+			int			access_flags;
+			struct ib_sge	       *prot;
+		} sig_handover;
 	} wr;
 	u32			xrc_remote_srq_num;	/* XRC TGT QPs only */
 };
@@ -1407,6 +1553,9 @@ struct ib_device {
 	int                        (*query_mr)(struct ib_mr *mr,
 					       struct ib_mr_attr *mr_attr);
 	int                        (*dereg_mr)(struct ib_mr *mr);
+	int                        (*destroy_mr)(struct ib_mr *mr);
+	struct ib_mr *		   (*create_mr)(struct ib_pd *pd,
+						struct ib_mr_init_attr *mr_init_attr);
 	struct ib_mr *		   (*alloc_fast_reg_mr)(struct ib_pd *pd,
 					       int max_page_list_len);
 	struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device,
@@ -1455,6 +1604,8 @@ struct ib_device {
 						  *flow_attr,
 						  int domain);
 	int			   (*destroy_flow)(struct ib_flow *flow_id);
+	int			   (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
+						      struct ib_mr_status *mr_status);
 
 	struct ib_dma_mapping_ops   *dma_ops;
 
@@ -2250,6 +2401,25 @@ int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
  */
 int ib_dereg_mr(struct ib_mr *mr);
 
+
+/**
+ * ib_create_mr - Allocates a memory region that may be used for
+ *     signature handover operations.
+ * @pd: The protection domain associated with the region.
+ * @mr_init_attr: memory region init attributes.
+ */
+struct ib_mr *ib_create_mr(struct ib_pd *pd,
+			   struct ib_mr_init_attr *mr_init_attr);
+
+/**
+ * ib_destroy_mr - Destroys a memory region that was created using
+ *     ib_create_mr and removes it from HW translation tables.
+ * @mr: The memory region to destroy.
+ *
+ * This function can fail, if the memory region has memory windows bound to it.
+ */
+int ib_destroy_mr(struct ib_mr *mr);
+
 /**
  * ib_alloc_fast_reg_mr - Allocates memory region usable with the
  *   IB_WR_FAST_REG_MR send work request.
@@ -2435,4 +2605,19 @@ static inline int ib_check_mr_access(int flags)
 	return 0;
 }
 
+/**
+ * ib_check_mr_status: lightweight check of MR status.
+ *     This routine may provide status checks on a selected
+ *     ib_mr. first use is for signature status check.
+ *
+ * @mr: A memory region.
+ * @check_mask: Bitmask of which checks to perform from
+ *     ib_mr_status_check enumeration.
+ * @mr_status: The container of relevant status checks.
+ *     failed checks will be indicated in the status bitmask
+ *     and the relevant info shall be in the error item.
+ */
+int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
+		       struct ib_mr_status *mr_status);
+
 #endif /* IB_VERBS_H */