[PATCH v2 01/26] IB/core: Introduce new fast registration API

[PATCH v2 01/26] IB/core: Introduce new fast registration API

[Sagi Grimberg]

The new fast registration  verb ib_map_mr_sg receives a scatterlist
and converts it to a page list under the verbs API thus hiding
the specific HW mapping details away from the consumer.

The provider drivers are provided with a generic helper ib_sg_to_pages
that converts a scatterlist into a vector of page addresses. The
drivers can still perform any HW specific page address setting
by passing a set_page function pointer which will be invoked for
each page address. This allows drivers to avoid keeping a shadow
page vectors and convert them to HW specific translations by doing
extra copies.

This API will allow ULPs to remove the duplicated code of constructing
a page vector from a given sg list.

The send work request ib_reg_wr also shrinks as it will contain only
mr, key and access flags in addition.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Tested-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Tested-by: Signed-off-by: Santosh Shilimkar <santosh.shilimkar-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
---
 drivers/infiniband/core/verbs.c | 107 ++++++++++++++++++++++++++++++++++++++++
 include/rdma/ib_verbs.h         |  44 +++++++++++++++++
 2 files changed, 151 insertions(+)

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index e1f2c9887f3f..b84d168f6e21 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1469,3 +1469,110 @@ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
 		mr->device->check_mr_status(mr, check_mask, mr_status) : -ENOSYS;
 }
 EXPORT_SYMBOL(ib_check_mr_status);
+
+/**
+ * ib_map_mr_sg() - Map the largest prefix of a dma mapped SG list
+ *     and set it the memory region.
+ * @mr:            memory region
+ * @sg:            dma mapped scatterlist
+ * @sg_nents:      number of entries in sg
+ * @page_size:     page vector desired page size
+ *
+ * Constraints:
+ * - The first sg element is allowed to have an offset.
+ * - Each sg element must be aligned to page_size (or physically
+ *   contiguous to the previous element). In case an sg element has a
+ *   non contiguous offset, the mapping prefix will not include it.
+ * - The last sg element is allowed to have length less than page_size.
+ * - If sg_nents total byte length exceeds the mr max_num_sge * page_size
+ *   then only max_num_sg entries will be mapped.
+ *
+ * Returns the number of sg elements that were mapped to the memory region.
+ *
+ * After this completes successfully, the  memory region
+ * is ready for registration.
+ */
+int ib_map_mr_sg(struct ib_mr *mr,
+		 struct scatterlist *sg,
+		 unsigned int sg_nents,
+		 unsigned int page_size)
+{
+	if (unlikely(!mr->device->map_mr_sg))
+		return -ENOSYS;
+
+	mr->page_size = page_size;
+
+	return mr->device->map_mr_sg(mr, sg, sg_nents);
+}
+EXPORT_SYMBOL(ib_map_mr_sg);
+
+/**
+ * ib_sg_to_pages() - Convert the largest prefix of a sg list
+ *     to a page vector
+ * @mr:            memory region
+ * @sgl:           dma mapped scatterlist
+ * @sg_nents:      number of entries in sg
+ * @set_page:      driver page assignment function pointer
+ *
+ * Core service helper for drivers to covert the largest
+ * prefix of given sg list to a page vector. The sg list
+ * prefix converted is the prefix that meet the requirements
+ * of ib_map_mr_sg.
+ *
+ * Returns the number of sg elements that were assigned to
+ * a page vector.
+ */
+int ib_sg_to_pages(struct ib_mr *mr,
+		   struct scatterlist *sgl,
+		   unsigned int sg_nents,
+		   int (*set_page)(struct ib_mr *, u64))
+{
+	struct scatterlist *sg;
+	u64 last_end_dma_addr = 0, last_page_addr = 0;
+	unsigned int last_page_off = 0;
+	u64 page_mask = ~((u64)mr->page_size - 1);
+	int i;
+
+	mr->iova = sg_dma_address(&sgl[0]);
+	mr->length = 0;
+
+	for_each_sg(sgl, sg, sg_nents, i) {
+		u64 dma_addr = sg_dma_address(sg);
+		unsigned int dma_len = sg_dma_len(sg);
+		u64 end_dma_addr = dma_addr + dma_len;
+		u64 page_addr = dma_addr & page_mask;
+
+		if (i && page_addr != dma_addr) {
+			if (last_end_dma_addr != dma_addr) {
+				/* gap */
+				goto done;
+
+			} else if (last_page_off + dma_len < mr->page_size) {
+				/* chunk this fragment with the last */
+				mr->length += dma_len;
+				last_end_dma_addr += dma_len;
+				last_page_off += dma_len;
+				continue;
+			} else {
+				/* map starting from the next page */
+				page_addr = last_page_addr + mr->page_size;
+				dma_len -= mr->page_size - last_page_off;
+			}
+		}
+
+		do {
+			if (unlikely(set_page(mr, page_addr)))
+				goto done;
+			page_addr += mr->page_size;
+		} while (page_addr < end_dma_addr);
+
+		mr->length += dma_len;
+		last_end_dma_addr = end_dma_addr;
+		last_page_addr = end_dma_addr & page_mask;
+		last_page_off = end_dma_addr & ~page_mask;
+	}
+
+done:
+	return i;
+}
+EXPORT_SYMBOL(ib_sg_to_pages);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index edf02908a0fd..f9a3436702c8 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -737,6 +737,7 @@ enum ib_wc_opcode {
 	IB_WC_LSO,
 	IB_WC_LOCAL_INV,
 	IB_WC_FAST_REG_MR,
+	IB_WC_REG_MR,
 	IB_WC_MASKED_COMP_SWAP,
 	IB_WC_MASKED_FETCH_ADD,
 /*
@@ -1029,6 +1030,7 @@ enum ib_wr_opcode {
 	IB_WR_RDMA_READ_WITH_INV,
 	IB_WR_LOCAL_INV,
 	IB_WR_FAST_REG_MR,
+	IB_WR_REG_MR,
 	IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
 	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
 	IB_WR_BIND_MW,
@@ -1161,6 +1163,18 @@ static inline struct ib_fast_reg_wr *fast_reg_wr(struct ib_send_wr *wr)
 	return container_of(wr, struct ib_fast_reg_wr, wr);
 }
 
+struct ib_reg_wr {
+	struct ib_send_wr	wr;
+	struct ib_mr		*mr;
+	u32			key;
+	int			access;
+};
+
+static inline struct ib_reg_wr *reg_wr(struct ib_send_wr *wr)
+{
+	return container_of(wr, struct ib_reg_wr, wr);
+}
+
 struct ib_bind_mw_wr {
 	struct ib_send_wr	wr;
 	struct ib_mw		*mw;
@@ -1373,6 +1387,9 @@ struct ib_mr {
 	struct ib_uobject *uobject;
 	u32		   lkey;
 	u32		   rkey;
+	u64		   iova;
+	u32		   length;
+	unsigned int	   page_size;
 	atomic_t	   usecnt; /* count number of MWs */
 };
 
@@ -1757,6 +1774,9 @@ struct ib_device {
 	struct ib_mr *		   (*alloc_mr)(struct ib_pd *pd,
 					       enum ib_mr_type mr_type,
 					       u32 max_num_sg);
+	int                        (*map_mr_sg)(struct ib_mr *mr,
+						struct scatterlist *sg,
+						unsigned int sg_nents);
 	struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device,
 								   int page_list_len);
 	void			   (*free_fast_reg_page_list)(struct ib_fast_reg_page_list *page_list);
@@ -3062,4 +3082,28 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port,
 					    u16 pkey, const union ib_gid *gid,
 					    const struct sockaddr *addr);
 
+int ib_map_mr_sg(struct ib_mr *mr,
+		 struct scatterlist *sg,
+		 unsigned int sg_nents,
+		 unsigned int page_size);
+
+static inline int
+ib_map_mr_sg_zbva(struct ib_mr *mr,
+		  struct scatterlist *sg,
+		  unsigned int sg_nents,
+		  unsigned int page_size)
+{
+	int n;
+
+	n = ib_map_mr_sg(mr, sg, sg_nents, page_size);
+	mr->iova = 0;
+
+	return n;
+}
+
+int ib_sg_to_pages(struct ib_mr *mr,
+		   struct scatterlist *sgl,
+		   unsigned int sg_nents,
+		   int (*set_page)(struct ib_mr *, u64));
+
 #endif /* IB_VERBS_H */
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 02/26] IB/mlx5: Remove dead fmr code

[Sagi Grimberg]

Just function declarations - no need for those
laying arround. If for some reason someone will want
FMR support in mlx5, it should be easy enough to restore
a few structs.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Reviewed-by: Bart Van Assche <bart.vanassche-XdAiOPVOjttBDgjK7y7TUQ@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h | 25 -------------------------
 1 file changed, 25 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index ef4a47658f7a..210f99877b0b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -364,20 +364,6 @@ enum {
 	MLX5_FMR_BUSY,
 };
 
-struct mlx5_ib_fmr {
-	struct ib_fmr			ibfmr;
-	struct mlx5_core_mr		mr;
-	int				access_flags;
-	int				state;
-	/* protect fmr state
-	 */
-	spinlock_t			lock;
-	u64				wrid;
-	struct ib_send_wr		wr[2];
-	u8				page_shift;
-	struct ib_fast_reg_page_list	page_list;
-};
-
 struct mlx5_cache_ent {
 	struct list_head	head;
 	/* sync access to the cahce entry
@@ -462,11 +448,6 @@ static inline struct mlx5_ib_dev *to_mdev(struct ib_device *ibdev)
 	return container_of(ibdev, struct mlx5_ib_dev, ib_dev);
 }
 
-static inline struct mlx5_ib_fmr *to_mfmr(struct ib_fmr *ibfmr)
-{
-	return container_of(ibfmr, struct mlx5_ib_fmr, ibfmr);
-}
-
 static inline struct mlx5_ib_cq *to_mcq(struct ib_cq *ibcq)
 {
 	return container_of(ibcq, struct mlx5_ib_cq, ibcq);
@@ -582,12 +563,6 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
 							       int page_list_len);
 void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
-struct ib_fmr *mlx5_ib_fmr_alloc(struct ib_pd *pd, int acc,
-				 struct ib_fmr_attr *fmr_attr);
-int mlx5_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
-		      int npages, u64 iova);
-int mlx5_ib_unmap_fmr(struct list_head *fmr_list);
-int mlx5_ib_fmr_dealloc(struct ib_fmr *ibfmr);
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
 			const struct ib_mad_hdr *in, size_t in_mad_size,
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 03/26] IB/mlx5: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in mlx5_ib_mr and populate it when
mlx5_ib_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by setting the exact WQE as IB_WR_FAST_REG_MR, just take the
needed information from different places:
- page_size, iova, length, access flags (ib_mr)
- page array (mlx5_ib_mr)
- key (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/mlx5/cq.c      |  3 ++
 drivers/infiniband/hw/mlx5/main.c    |  1 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  8 ++++
 drivers/infiniband/hw/mlx5/mr.c      | 87 ++++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx5/qp.c      | 83 ++++++++++++++++++++++++++++++++++
 5 files changed, 182 insertions(+)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 5c9eeea62805..90daf791d51d 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -108,6 +108,9 @@ static enum ib_wc_opcode get_umr_comp(struct mlx5_ib_wq *wq, int idx)
 	case IB_WR_LOCAL_INV:
 		return IB_WC_LOCAL_INV;
 
+	case IB_WR_REG_MR:
+		return IB_WC_REG_MR;
+
 	case IB_WR_FAST_REG_MR:
 		return IB_WC_FAST_REG_MR;
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 276d7824be8a..7ebce545daf1 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1432,6 +1432,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.detach_mcast	= mlx5_ib_mcg_detach;
 	dev->ib_dev.process_mad		= mlx5_ib_process_mad;
 	dev->ib_dev.alloc_mr		= mlx5_ib_alloc_mr;
+	dev->ib_dev.map_mr_sg		= mlx5_ib_map_mr_sg;
 	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;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 210f99877b0b..bc1853f8e67d 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -319,6 +319,11 @@ enum mlx5_ib_mtt_access_flags {
 
 struct mlx5_ib_mr {
 	struct ib_mr		ibmr;
+	void			*descs;
+	dma_addr_t		desc_map;
+	int			ndescs;
+	int			max_descs;
+	int			desc_size;
 	struct mlx5_core_mr	mmr;
 	struct ib_umem	       *umem;
 	struct mlx5_shared_mr_info	*smr_info;
@@ -560,6 +565,9 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr);
 struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 			       enum ib_mr_type mr_type,
 			       u32 max_num_sg);
+int mlx5_ib_map_mr_sg(struct ib_mr *ibmr,
+		      struct scatterlist *sg,
+		      unsigned int sg_nents);
 struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
 							       int page_list_len);
 void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 6d8aac0c1748..e071685e192d 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1165,6 +1165,46 @@ error:
 	return err;
 }
 
+static int
+mlx5_alloc_priv_descs(struct ib_device *device,
+		      struct mlx5_ib_mr *mr,
+		      int ndescs,
+		      int desc_size)
+{
+	int size = ndescs * desc_size;
+	int ret;
+
+	mr->descs = kzalloc(size, GFP_KERNEL);
+	if (!mr->descs)
+		return -ENOMEM;
+
+	mr->desc_map = dma_map_single(device->dma_device, mr->descs,
+				      size, DMA_TO_DEVICE);
+	if (dma_mapping_error(device->dma_device, mr->desc_map)) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	return 0;
+err:
+	kfree(mr->descs);
+	return ret;
+}
+
+static void
+mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
+{
+	struct ib_device *device = mr->ibmr.device;
+	int size = mr->max_descs * mr->desc_size;
+
+	if (mr->descs) {
+		dma_unmap_single(device->dma_device, mr->desc_map,
+				 size, DMA_TO_DEVICE);
+		kfree(mr->descs);
+		mr->descs = NULL;
+	}
+}
+
 static int clean_mr(struct mlx5_ib_mr *mr)
 {
 	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
@@ -1184,6 +1224,8 @@ static int clean_mr(struct mlx5_ib_mr *mr)
 		mr->sig = NULL;
 	}
 
+	mlx5_free_priv_descs(mr);
+
 	if (!umred) {
 		err = destroy_mkey(dev, mr);
 		if (err) {
@@ -1273,6 +1315,14 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 	if (mr_type == IB_MR_TYPE_MEM_REG) {
 		access_mode = MLX5_ACCESS_MODE_MTT;
 		in->seg.log2_page_size = PAGE_SHIFT;
+
+		err = mlx5_alloc_priv_descs(pd->device, mr,
+					    ndescs, sizeof(u64));
+		if (err)
+			goto err_free_in;
+
+		mr->desc_size = sizeof(u64);
+		mr->max_descs = ndescs;
 	} else if (mr_type == IB_MR_TYPE_SIGNATURE) {
 		u32 psv_index[2];
 
@@ -1329,6 +1379,7 @@ err_destroy_psv:
 			mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
 				     mr->sig->psv_wire.psv_idx);
 	}
+	mlx5_free_priv_descs(mr);
 err_free_sig:
 	kfree(mr->sig);
 err_free_in:
@@ -1420,3 +1471,39 @@ int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 done:
 	return ret;
 }
+
+static int mlx5_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+	__be64 *descs;
+
+	if (unlikely(mr->ndescs == mr->max_descs))
+		return -ENOMEM;
+
+	descs = mr->descs;
+	descs[mr->ndescs++] = cpu_to_be64(addr | MLX5_EN_RD | MLX5_EN_WR);
+
+	return 0;
+}
+
+int mlx5_ib_map_mr_sg(struct ib_mr *ibmr,
+		      struct scatterlist *sg,
+		      unsigned int sg_nents)
+{
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+	int n;
+
+	mr->ndescs = 0;
+
+	ib_dma_sync_single_for_cpu(ibmr->device, mr->desc_map,
+				   mr->desc_size * mr->max_descs,
+				   DMA_TO_DEVICE);
+
+	n = ib_sg_to_pages(ibmr, sg, sg_nents, mlx5_set_page);
+
+	ib_dma_sync_single_for_device(ibmr->device, mr->desc_map,
+				      mr->desc_size * mr->max_descs,
+				      DMA_TO_DEVICE);
+
+	return n;
+}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index dcd8d58f95e1..61d3aa9a6ca9 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -65,6 +65,7 @@ static const u32 mlx5_ib_opcode[] = {
 	[IB_WR_SEND_WITH_INV]			= MLX5_OPCODE_SEND_INVAL,
 	[IB_WR_LOCAL_INV]			= MLX5_OPCODE_UMR,
 	[IB_WR_FAST_REG_MR]			= MLX5_OPCODE_UMR,
+	[IB_WR_REG_MR]				= MLX5_OPCODE_UMR,
 	[IB_WR_MASKED_ATOMIC_CMP_AND_SWP]	= MLX5_OPCODE_ATOMIC_MASKED_CS,
 	[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD]	= MLX5_OPCODE_ATOMIC_MASKED_FA,
 	[MLX5_IB_WR_UMR]			= MLX5_OPCODE_UMR,
@@ -1901,6 +1902,17 @@ static __be64 sig_mkey_mask(void)
 	return cpu_to_be64(result);
 }
 
+static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
+				struct mlx5_ib_mr *mr)
+{
+	int ndescs = mr->ndescs;
+
+	memset(umr, 0, sizeof(*umr));
+	umr->flags = MLX5_UMR_CHECK_NOT_FREE;
+	umr->klm_octowords = get_klm_octo(ndescs);
+	umr->mkey_mask = frwr_mkey_mask();
+}
+
 static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 				 struct ib_send_wr *wr, int li)
 {
@@ -1992,6 +2004,22 @@ static u8 get_umr_flags(int acc)
 		MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN;
 }
 
+static void set_reg_mkey_seg(struct mlx5_mkey_seg *seg,
+			     struct mlx5_ib_mr *mr,
+			     u32 key, int access)
+{
+	int ndescs = ALIGN(mr->ndescs, 8) >> 1;
+
+	memset(seg, 0, sizeof(*seg));
+	seg->flags = get_umr_flags(access) | MLX5_ACCESS_MODE_MTT;
+	seg->qpn_mkey7_0 = cpu_to_be32((key & 0xff) | 0xffffff00);
+	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL);
+	seg->start_addr = cpu_to_be64(mr->ibmr.iova);
+	seg->len = cpu_to_be64(mr->ibmr.length);
+	seg->xlt_oct_size = cpu_to_be32(ndescs);
+	seg->log2_page_size = ilog2(mr->ibmr.page_size);
+}
+
 static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
 			     int li, int *writ)
 {
@@ -2033,6 +2061,17 @@ static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *w
 				       mlx5_mkey_variant(umrwr->mkey));
 }
 
+static void set_reg_data_seg(struct mlx5_wqe_data_seg *dseg,
+			     struct mlx5_ib_mr *mr,
+			     struct mlx5_ib_pd *pd)
+{
+	int bcount = mr->desc_size * mr->ndescs;
+
+	dseg->addr = cpu_to_be64(mr->desc_map);
+	dseg->byte_count = cpu_to_be32(ALIGN(bcount, 64));
+	dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
+}
+
 static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
 			   struct ib_send_wr *wr,
 			   struct mlx5_core_dev *mdev,
@@ -2438,6 +2477,38 @@ static int set_psv_wr(struct ib_sig_domain *domain,
 	return 0;
 }
 
+static int set_reg_wr(struct mlx5_ib_qp *qp,
+		      struct ib_reg_wr *wr,
+		      void **seg, int *size)
+{
+	struct mlx5_ib_mr *mr = to_mmr(wr->mr);
+	struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd);
+
+	if (unlikely(wr->wr.send_flags & IB_SEND_INLINE)) {
+		mlx5_ib_warn(to_mdev(qp->ibqp.device),
+			     "Invalid IB_SEND_INLINE send flag\n");
+		return -EINVAL;
+	}
+
+	set_reg_umr_seg(*seg, mr);
+	*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_reg_mkey_seg(*seg, mr, wr->key, wr->access);
+	*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);
+
+	set_reg_data_seg(*seg, mr, pd);
+	*seg += sizeof(struct mlx5_wqe_data_seg);
+	*size += (sizeof(struct mlx5_wqe_data_seg) / 16);
+
+	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)
 {
@@ -2680,6 +2751,18 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				num_sge = 0;
 				break;
 
+			case IB_WR_REG_MR:
+				next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+				qp->sq.wr_data[idx] = IB_WR_REG_MR;
+				ctrl->imm = cpu_to_be32(reg_wr(wr)->key);
+				err = set_reg_wr(qp, reg_wr(wr), &seg, &size);
+				if (err) {
+					*bad_wr = wr;
+					goto out;
+				}
+				num_sge = 0;
+				break;
+
 			case IB_WR_REG_SIG_MR:
 				qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR;
 				mr = to_mmr(sig_handover_wr(wr)->sig_mr);
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 04/26] IB/mlx4: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in mlx4_ib_mr and populate it when
mlx4_ib_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by setting the exact WQE as IB_WR_FAST_REG_MR, just take the
needed information from different places:
- page_size, iova, length, access flags (ib_mr)
- page array (mlx4_ib_mr)
- key (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Tested-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Tested-by: Signed-off-by: Santosh Shilimkar <santosh.shilimkar-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
---
 drivers/infiniband/hw/mlx4/cq.c      |  1 +
 drivers/infiniband/hw/mlx4/main.c    |  1 +
 drivers/infiniband/hw/mlx4/mlx4_ib.h |  7 +++
 drivers/infiniband/hw/mlx4/mr.c      | 95 +++++++++++++++++++++++++++++++++---
 drivers/infiniband/hw/mlx4/qp.c      | 25 ++++++++++
 5 files changed, 123 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 2f4259525bb1..b62236e24708 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -819,6 +819,7 @@ repoll:
 			break;
 		case MLX4_OPCODE_FMR:
 			wc->opcode    = IB_WC_FAST_REG_MR;
+			/* TODO: wc->opcode    = IB_WC_REG_MR; */
 			break;
 		case MLX4_OPCODE_LOCAL_INVAL:
 			wc->opcode    = IB_WC_LOCAL_INV;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index efecdf0216d8..bb82f5fa1612 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2247,6 +2247,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.rereg_user_mr	= mlx4_ib_rereg_user_mr;
 	ibdev->ib_dev.dereg_mr		= mlx4_ib_dereg_mr;
 	ibdev->ib_dev.alloc_mr		= mlx4_ib_alloc_mr;
+	ibdev->ib_dev.map_mr_sg		= mlx4_ib_map_mr_sg;
 	ibdev->ib_dev.alloc_fast_reg_page_list = mlx4_ib_alloc_fast_reg_page_list;
 	ibdev->ib_dev.free_fast_reg_page_list  = mlx4_ib_free_fast_reg_page_list;
 	ibdev->ib_dev.attach_mcast	= mlx4_ib_mcg_attach;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 1e7b23bb2eb0..07fcf3a49256 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -131,6 +131,10 @@ struct mlx4_ib_cq {
 
 struct mlx4_ib_mr {
 	struct ib_mr		ibmr;
+	__be64			*pages;
+	dma_addr_t		page_map;
+	u32			npages;
+	u32			max_pages;
 	struct mlx4_mr		mmr;
 	struct ib_umem	       *umem;
 };
@@ -706,6 +710,9 @@ int mlx4_ib_dealloc_mw(struct ib_mw *mw);
 struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
 			       enum ib_mr_type mr_type,
 			       u32 max_num_sg);
+int mlx4_ib_map_mr_sg(struct ib_mr *ibmr,
+		      struct scatterlist *sg,
+		      unsigned int sg_nents);
 struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
 							       int page_list_len);
 void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 5bba176e9dfa..c361a0d52b1f 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -59,7 +59,7 @@ struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
 	struct mlx4_ib_mr *mr;
 	int err;
 
-	mr = kmalloc(sizeof *mr, GFP_KERNEL);
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
@@ -140,7 +140,7 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int err;
 	int n;
 
-	mr = kmalloc(sizeof *mr, GFP_KERNEL);
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
@@ -271,11 +271,53 @@ release_mpt_entry:
 	return err;
 }
 
+static int
+mlx4_alloc_priv_pages(struct ib_device *device,
+		      struct mlx4_ib_mr *mr,
+		      int max_pages)
+{
+	int size = max_pages * sizeof(u64);
+	int ret;
+
+	mr->pages = kzalloc(size, GFP_KERNEL);
+	if (!mr->pages)
+		return -ENOMEM;
+
+	mr->page_map = dma_map_single(device->dma_device, mr->pages,
+				      size, DMA_TO_DEVICE);
+
+	if (dma_mapping_error(device->dma_device, mr->page_map)) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	return 0;
+err:
+	kfree(mr->pages);
+	return ret;
+}
+
+static void
+mlx4_free_priv_pages(struct mlx4_ib_mr *mr)
+{
+	struct ib_device *device = mr->ibmr.device;
+	int size = mr->max_pages * sizeof(u64);
+
+	if (mr->pages) {
+		dma_unmap_single(device->dma_device, mr->page_map,
+				 size, DMA_TO_DEVICE);
+		kfree(mr->pages);
+		mr->pages = NULL;
+	}
+}
+
 int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
 {
 	struct mlx4_ib_mr *mr = to_mmr(ibmr);
 	int ret;
 
+	mlx4_free_priv_pages(mr);
+
 	ret = mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
 	if (ret)
 		return ret;
@@ -362,7 +404,7 @@ struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
 	    max_num_sg > MLX4_MAX_FAST_REG_PAGES)
 		return ERR_PTR(-EINVAL);
 
-	mr = kmalloc(sizeof *mr, GFP_KERNEL);
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
@@ -371,18 +413,25 @@ struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
 	if (err)
 		goto err_free;
 
+	err = mlx4_alloc_priv_pages(pd->device, mr, max_num_sg);
+	if (err)
+		goto err_free_mr;
+
+	mr->max_pages = max_num_sg;
+
 	err = mlx4_mr_enable(dev->dev, &mr->mmr);
 	if (err)
-		goto err_mr;
+		goto err_free_pl;
 
 	mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
 	mr->umem = NULL;
 
 	return &mr->ibmr;
 
-err_mr:
+err_free_pl:
+	mlx4_free_priv_pages(mr);
+err_free_mr:
 	(void) mlx4_mr_free(dev->dev, &mr->mmr);
-
 err_free:
 	kfree(mr);
 	return ERR_PTR(err);
@@ -528,3 +577,37 @@ int mlx4_ib_fmr_dealloc(struct ib_fmr *ibfmr)
 
 	return err;
 }
+
+static int mlx4_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct mlx4_ib_mr *mr = to_mmr(ibmr);
+
+	if (unlikely(mr->npages == mr->max_pages))
+		return -ENOMEM;
+
+	mr->pages[mr->npages++] = cpu_to_be64(addr | MLX4_MTT_FLAG_PRESENT);
+
+	return 0;
+}
+
+int mlx4_ib_map_mr_sg(struct ib_mr *ibmr,
+		      struct scatterlist *sg,
+		      unsigned int sg_nents)
+{
+	struct mlx4_ib_mr *mr = to_mmr(ibmr);
+	int rc;
+
+	mr->npages = 0;
+
+	ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
+				   sizeof(u64) * mr->max_pages,
+				   DMA_TO_DEVICE);
+
+	rc = ib_sg_to_pages(ibmr, sg, sg_nents, mlx4_set_page);
+
+	ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
+				      sizeof(u64) * mr->max_pages,
+				      DMA_TO_DEVICE);
+
+	return rc;
+}
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 3831cddb551f..850d4e9c13c5 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -112,6 +112,7 @@ static const __be32 mlx4_ib_opcode[] = {
 	[IB_WR_SEND_WITH_INV]			= cpu_to_be32(MLX4_OPCODE_SEND_INVAL),
 	[IB_WR_LOCAL_INV]			= cpu_to_be32(MLX4_OPCODE_LOCAL_INVAL),
 	[IB_WR_FAST_REG_MR]			= cpu_to_be32(MLX4_OPCODE_FMR),
+	[IB_WR_REG_MR]				= cpu_to_be32(MLX4_OPCODE_FMR),
 	[IB_WR_MASKED_ATOMIC_CMP_AND_SWP]	= cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_CS),
 	[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD]	= cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA),
 	[IB_WR_BIND_MW]				= cpu_to_be32(MLX4_OPCODE_BIND_MW),
@@ -2405,6 +2406,22 @@ static __be32 convert_access(int acc)
 		cpu_to_be32(MLX4_WQE_FMR_PERM_LOCAL_READ);
 }
 
+static void set_reg_seg(struct mlx4_wqe_fmr_seg *fseg,
+			struct ib_reg_wr *wr)
+{
+	struct mlx4_ib_mr *mr = to_mmr(wr->mr);
+
+	fseg->flags		= convert_access(wr->access);
+	fseg->mem_key		= cpu_to_be32(wr->key);
+	fseg->buf_list		= cpu_to_be64(mr->page_map);
+	fseg->start_addr	= cpu_to_be64(mr->ibmr.iova);
+	fseg->reg_len		= cpu_to_be64(mr->ibmr.length);
+	fseg->offset		= 0; /* XXX -- is this just for ZBVA? */
+	fseg->page_size		= cpu_to_be32(ilog2(mr->ibmr.page_size));
+	fseg->reserved[0]	= 0;
+	fseg->reserved[1]	= 0;
+}
+
 static void set_fmr_seg(struct mlx4_wqe_fmr_seg *fseg,
 		struct ib_fast_reg_wr *wr)
 {
@@ -2766,6 +2783,14 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				size += sizeof (struct mlx4_wqe_fmr_seg) / 16;
 				break;
 
+			case IB_WR_REG_MR:
+				ctrl->srcrb_flags |=
+					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
+				set_reg_seg(wqe, reg_wr(wr));
+				wqe  += sizeof(struct mlx4_wqe_fmr_seg);
+				size += sizeof(struct mlx4_wqe_fmr_seg) / 16;
+				break;
+
 			case IB_WR_BIND_MW:
 				ctrl->srcrb_flags |=
 					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 05/26] RDMA/ocrdma: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in ocrdma_mr and populate it when
ocrdma_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating IB_WR_FAST_REG_MR, but take the needed
information from different places:
- page_size, iova, length, access flags (ib_mr)
- page array (ocrdma_mr)
- key (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/ocrdma/ocrdma.h       |  2 +
 drivers/infiniband/hw/ocrdma/ocrdma_main.c  |  1 +
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 90 +++++++++++++++++++++++++++++
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.h |  3 +
 4 files changed, 96 insertions(+)

diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index b4091ab48db0..c2f3af5d5194 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -193,6 +193,8 @@ struct ocrdma_mr {
 	struct ib_mr ibmr;
 	struct ib_umem *umem;
 	struct ocrdma_hw_mr hwmr;
+	u64 *pages;
+	u32 npages;
 };
 
 struct ocrdma_stats {
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 87aa55df7c82..874beb4b07a1 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -182,6 +182,7 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
 	dev->ibdev.reg_user_mr = ocrdma_reg_user_mr;
 
 	dev->ibdev.alloc_mr = ocrdma_alloc_mr;
+	dev->ibdev.map_mr_sg = ocrdma_map_mr_sg;
 	dev->ibdev.alloc_fast_reg_page_list = ocrdma_alloc_frmr_page_list;
 	dev->ibdev.free_fast_reg_page_list = ocrdma_free_frmr_page_list;
 
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index eb09e224acb9..66cc15a78f63 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1013,6 +1013,7 @@ int ocrdma_dereg_mr(struct ib_mr *ib_mr)
 
 	(void) ocrdma_mbx_dealloc_lkey(dev, mr->hwmr.fr_mr, mr->hwmr.lkey);
 
+	kfree(mr->pages);
 	ocrdma_free_mr_pbl_tbl(dev, &mr->hwmr);
 
 	/* it could be user registered memory. */
@@ -2177,6 +2178,61 @@ static int get_encoded_page_size(int pg_sz)
 	return i;
 }
 
+static int ocrdma_build_reg(struct ocrdma_qp *qp,
+			    struct ocrdma_hdr_wqe *hdr,
+			    struct ib_reg_wr *wr)
+{
+	u64 fbo;
+	struct ocrdma_ewqe_fr *fast_reg = (struct ocrdma_ewqe_fr *)(hdr + 1);
+	struct ocrdma_mr *mr = get_ocrdma_mr(wr->mr);
+	struct ocrdma_pbl *pbl_tbl = mr->hwmr.pbl_table;
+	struct ocrdma_pbe *pbe;
+	u32 wqe_size = sizeof(*fast_reg) + sizeof(*hdr);
+	int num_pbes = 0, i;
+
+	wqe_size = roundup(wqe_size, OCRDMA_WQE_ALIGN_BYTES);
+
+	hdr->cw |= (OCRDMA_FR_MR << OCRDMA_WQE_OPCODE_SHIFT);
+	hdr->cw |= ((wqe_size / OCRDMA_WQE_STRIDE) << OCRDMA_WQE_SIZE_SHIFT);
+
+	if (wr->access & IB_ACCESS_LOCAL_WRITE)
+		hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_LOCAL_WR;
+	if (wr->access & IB_ACCESS_REMOTE_WRITE)
+		hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_WR;
+	if (wr->access & IB_ACCESS_REMOTE_READ)
+		hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_RD;
+	hdr->lkey = wr->key;
+	hdr->total_len = mr->ibmr.length;
+
+	fbo = mr->ibmr.iova - mr->pages[0];
+
+	fast_reg->va_hi = upper_32_bits(mr->ibmr.iova);
+	fast_reg->va_lo = (u32) (mr->ibmr.iova & 0xffffffff);
+	fast_reg->fbo_hi = upper_32_bits(fbo);
+	fast_reg->fbo_lo = (u32) fbo & 0xffffffff;
+	fast_reg->num_sges = mr->npages;
+	fast_reg->size_sge = get_encoded_page_size(mr->ibmr.page_size);
+
+	pbe = pbl_tbl->va;
+	for (i = 0; i < mr->npages; i++) {
+		u64 buf_addr = mr->pages[i];
+
+		pbe->pa_lo = cpu_to_le32((u32) (buf_addr & PAGE_MASK));
+		pbe->pa_hi = cpu_to_le32((u32) upper_32_bits(buf_addr));
+		num_pbes += 1;
+		pbe++;
+
+		/* if the pbl is full storing the pbes,
+		 * move to next pbl.
+		*/
+		if (num_pbes == (mr->hwmr.pbl_size/sizeof(u64))) {
+			pbl_tbl++;
+			pbe = (struct ocrdma_pbe *)pbl_tbl->va;
+		}
+	}
+
+	return 0;
+}
 
 static int ocrdma_build_fr(struct ocrdma_qp *qp, struct ocrdma_hdr_wqe *hdr,
 			   struct ib_send_wr *send_wr)
@@ -2304,6 +2360,9 @@ int ocrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		case IB_WR_FAST_REG_MR:
 			status = ocrdma_build_fr(qp, hdr, wr);
 			break;
+		case IB_WR_REG_MR:
+			status = ocrdma_build_reg(qp, hdr, reg_wr(wr));
+			break;
 		default:
 			status = -EINVAL;
 			break;
@@ -3059,6 +3118,12 @@ struct ib_mr *ocrdma_alloc_mr(struct ib_pd *ibpd,
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
+	mr->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL);
+	if (!mr->pages) {
+		status = -ENOMEM;
+		goto pl_err;
+	}
+
 	status = ocrdma_get_pbl_info(dev, mr, max_num_sg);
 	if (status)
 		goto pbl_err;
@@ -3082,6 +3147,8 @@ struct ib_mr *ocrdma_alloc_mr(struct ib_pd *ibpd,
 mbx_err:
 	ocrdma_free_mr_pbl_tbl(dev, &mr->hwmr);
 pbl_err:
+	kfree(mr->pages);
+pl_err:
 	kfree(mr);
 	return ERR_PTR(-ENOMEM);
 }
@@ -3268,3 +3335,26 @@ pbl_err:
 	kfree(mr);
 	return ERR_PTR(status);
 }
+
+static int ocrdma_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct ocrdma_mr *mr = get_ocrdma_mr(ibmr);
+
+	if (unlikely(mr->npages == mr->hwmr.num_pbes))
+		return -ENOMEM;
+
+	mr->pages[mr->npages++] = addr;
+
+	return 0;
+}
+
+int ocrdma_map_mr_sg(struct ib_mr *ibmr,
+		     struct scatterlist *sg,
+		     unsigned int sg_nents)
+{
+	struct ocrdma_mr *mr = get_ocrdma_mr(ibmr);
+
+	mr->npages = 0;
+
+	return ib_sg_to_pages(ibmr, sg, sg_nents, ocrdma_set_page);
+}
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index 308c16857a5d..4edf63f9c6c7 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -125,6 +125,9 @@ struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *, u64 start, u64 length,
 struct ib_mr *ocrdma_alloc_mr(struct ib_pd *pd,
 			      enum ib_mr_type mr_type,
 			      u32 max_num_sg);
+int ocrdma_map_mr_sg(struct ib_mr *ibmr,
+		     struct scatterlist *sg,
+		     unsigned int sg_nents);
 struct ib_fast_reg_page_list *ocrdma_alloc_frmr_page_list(struct ib_device
 							*ibdev,
 							int page_list_len);
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 06/26] RDMA/cxgb3: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in iwch_mr and populate it when
iwch_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating build_fastreg just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (iwch_mr)
- key, access flags (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/cxgb3/iwch_provider.c | 33 ++++++++++++++++++++
 drivers/infiniband/hw/cxgb3/iwch_provider.h |  2 ++
 drivers/infiniband/hw/cxgb3/iwch_qp.c       | 48 +++++++++++++++++++++++++++++
 3 files changed, 83 insertions(+)

diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 93308c45f298..ee3d5ca7de6c 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -463,6 +463,7 @@ static int iwch_dereg_mr(struct ib_mr *ib_mr)
 		return -EINVAL;
 
 	mhp = to_iwch_mr(ib_mr);
+	kfree(mhp->pages);
 	rhp = mhp->rhp;
 	mmid = mhp->attr.stag >> 8;
 	cxio_dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
@@ -821,6 +822,12 @@ static struct ib_mr *iwch_alloc_mr(struct ib_pd *pd,
 	if (!mhp)
 		goto err;
 
+	mhp->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL);
+	if (!mhp->pages) {
+		ret = -ENOMEM;
+		goto pl_err;
+	}
+
 	mhp->rhp = rhp;
 	ret = iwch_alloc_pbl(mhp, max_num_sg);
 	if (ret)
@@ -847,11 +854,36 @@ err3:
 err2:
 	iwch_free_pbl(mhp);
 err1:
+	kfree(mhp->pages);
+pl_err:
 	kfree(mhp);
 err:
 	return ERR_PTR(ret);
 }
 
+static int iwch_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct iwch_mr *mhp = to_iwch_mr(ibmr);
+
+	if (unlikely(mhp->npages == mhp->attr.pbl_size))
+		return -ENOMEM;
+
+	mhp->pages[mhp->npages++] = addr;
+
+	return 0;
+}
+
+static int iwch_map_mr_sg(struct ib_mr *ibmr,
+			  struct scatterlist *sg,
+			  unsigned int sg_nents)
+{
+	struct iwch_mr *mhp = to_iwch_mr(ibmr);
+
+	mhp->npages = 0;
+
+	return ib_sg_to_pages(ibmr, sg, sg_nents, iwch_set_page);
+}
+
 static struct ib_fast_reg_page_list *iwch_alloc_fastreg_pbl(
 					struct ib_device *device,
 					int page_list_len)
@@ -1450,6 +1482,7 @@ int iwch_register_device(struct iwch_dev *dev)
 	dev->ibdev.bind_mw = iwch_bind_mw;
 	dev->ibdev.dealloc_mw = iwch_dealloc_mw;
 	dev->ibdev.alloc_mr = iwch_alloc_mr;
+	dev->ibdev.map_mr_sg = iwch_map_mr_sg;
 	dev->ibdev.alloc_fast_reg_page_list = iwch_alloc_fastreg_pbl;
 	dev->ibdev.free_fast_reg_page_list = iwch_free_fastreg_pbl;
 	dev->ibdev.attach_mcast = iwch_multicast_attach;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.h b/drivers/infiniband/hw/cxgb3/iwch_provider.h
index 87c14b0c5ac0..2ac85b86a680 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.h
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.h
@@ -77,6 +77,8 @@ struct iwch_mr {
 	struct iwch_dev *rhp;
 	u64 kva;
 	struct tpt_attributes attr;
+	u64 *pages;
+	u32 npages;
 };
 
 typedef struct iwch_mw iwch_mw_handle;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c
index bac0508fedd9..a09ea538e990 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_qp.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c
@@ -146,6 +146,49 @@ static int build_rdma_read(union t3_wr *wqe, struct ib_send_wr *wr,
 	return 0;
 }
 
+static int build_memreg(union t3_wr *wqe, struct ib_reg_wr *wr,
+			  u8 *flit_cnt, int *wr_cnt, struct t3_wq *wq)
+{
+	struct iwch_mr *mhp = to_iwch_mr(wr->mr);
+	int i;
+	__be64 *p;
+
+	if (mhp->npages > T3_MAX_FASTREG_DEPTH)
+		return -EINVAL;
+	*wr_cnt = 1;
+	wqe->fastreg.stag = cpu_to_be32(wr->key);
+	wqe->fastreg.len = cpu_to_be32(mhp->ibmr.length);
+	wqe->fastreg.va_base_hi = cpu_to_be32(mhp->ibmr.iova >> 32);
+	wqe->fastreg.va_base_lo_fbo =
+				cpu_to_be32(mhp->ibmr.iova & 0xffffffff);
+	wqe->fastreg.page_type_perms = cpu_to_be32(
+		V_FR_PAGE_COUNT(mhp->npages) |
+		V_FR_PAGE_SIZE(ilog2(wr->mr->page_size) - 12) |
+		V_FR_TYPE(TPT_VATO) |
+		V_FR_PERMS(iwch_ib_to_tpt_access(wr->access)));
+	p = &wqe->fastreg.pbl_addrs[0];
+	for (i = 0; i < mhp->npages; i++, p++) {
+
+		/* If we need a 2nd WR, then set it up */
+		if (i == T3_MAX_FASTREG_FRAG) {
+			*wr_cnt = 2;
+			wqe = (union t3_wr *)(wq->queue +
+				Q_PTR2IDX((wq->wptr+1), wq->size_log2));
+			build_fw_riwrh((void *)wqe, T3_WR_FASTREG, 0,
+			       Q_GENBIT(wq->wptr + 1, wq->size_log2),
+			       0, 1 + mhp->npages - T3_MAX_FASTREG_FRAG,
+			       T3_EOP);
+
+			p = &wqe->pbl_frag.pbl_addrs[0];
+		}
+		*p = cpu_to_be64((u64)mhp->pages[i]);
+	}
+	*flit_cnt = 5 + mhp->npages;
+	if (*flit_cnt > 15)
+		*flit_cnt = 15;
+	return 0;
+}
+
 static int build_fastreg(union t3_wr *wqe, struct ib_send_wr *send_wr,
 				u8 *flit_cnt, int *wr_cnt, struct t3_wq *wq)
 {
@@ -419,6 +462,11 @@ int iwch_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			err = build_fastreg(wqe, wr, &t3_wr_flit_cnt,
 						 &wr_cnt, &qhp->wq);
 			break;
+		case IB_WR_REG_MR:
+			t3_wr_opcode = T3_WR_FASTREG;
+			err = build_memreg(wqe, reg_wr(wr), &t3_wr_flit_cnt,
+					   &wr_cnt, &qhp->wq);
+			break;
 		case IB_WR_LOCAL_INV:
 			if (wr->send_flags & IB_SEND_FENCE)
 				t3_wr_flags |= T3_LOCAL_FENCE_FLAG;
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 07/26] iw_cxgb4: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in c4iw_mr and populate it when
c4iw_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating build_fastreg just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (c4iw_mr)
- key, access flags (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h |  7 ++++
 drivers/infiniband/hw/cxgb4/mem.c      | 38 +++++++++++++++++
 drivers/infiniband/hw/cxgb4/provider.c |  1 +
 drivers/infiniband/hw/cxgb4/qp.c       | 74 ++++++++++++++++++++++++++++++++++
 4 files changed, 120 insertions(+)

diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index c7bb38c931a5..032f90aa8ac9 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -386,6 +386,10 @@ struct c4iw_mr {
 	struct c4iw_dev *rhp;
 	u64 kva;
 	struct tpt_attributes attr;
+	u64 *mpl;
+	dma_addr_t mpl_addr;
+	u32 max_mpl_len;
+	u32 mpl_len;
 };
 
 static inline struct c4iw_mr *to_c4iw_mr(struct ib_mr *ibmr)
@@ -973,6 +977,9 @@ struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(
 struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 			    enum ib_mr_type mr_type,
 			    u32 max_num_sg);
+int c4iw_map_mr_sg(struct ib_mr *ibmr,
+		   struct scatterlist *sg,
+		   unsigned int sg_nents);
 int c4iw_dealloc_mw(struct ib_mw *mw);
 struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
 struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 026b91ebd5e2..86ec65721797 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -863,6 +863,7 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 	u32 mmid;
 	u32 stag = 0;
 	int ret = 0;
+	int length = roundup(max_num_sg * sizeof(u64), 32);
 
 	if (mr_type != IB_MR_TYPE_MEM_REG ||
 	    max_num_sg > t4_max_fr_depth(use_dsgl))
@@ -876,6 +877,14 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 		goto err;
 	}
 
+	mhp->mpl = dma_alloc_coherent(&rhp->rdev.lldi.pdev->dev,
+				      length, &mhp->mpl_addr, GFP_KERNEL);
+	if (!mhp->mpl) {
+		ret = -ENOMEM;
+		goto err_mpl;
+	}
+	mhp->max_mpl_len = length;
+
 	mhp->rhp = rhp;
 	ret = alloc_pbl(mhp, max_num_sg);
 	if (ret)
@@ -905,11 +914,37 @@ err2:
 	c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
 			      mhp->attr.pbl_size << 3);
 err1:
+	dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev,
+			  mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr);
+err_mpl:
 	kfree(mhp);
 err:
 	return ERR_PTR(ret);
 }
 
+static int c4iw_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
+
+	if (unlikely(mhp->mpl_len == mhp->max_mpl_len))
+		return -ENOMEM;
+
+	mhp->mpl[mhp->mpl_len++] = addr;
+
+	return 0;
+}
+
+int c4iw_map_mr_sg(struct ib_mr *ibmr,
+		   struct scatterlist *sg,
+		   unsigned int sg_nents)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
+
+	mhp->mpl_len = 0;
+
+	return ib_sg_to_pages(ibmr, sg, sg_nents, c4iw_set_page);
+}
+
 struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(struct ib_device *device,
 						     int page_list_len)
 {
@@ -970,6 +1005,9 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr)
 	rhp = mhp->rhp;
 	mmid = mhp->attr.stag >> 8;
 	remove_handle(rhp, &rhp->mmidr, mmid);
+	if (mhp->mpl)
+		dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev,
+				  mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr);
 	dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
 		       mhp->attr.pbl_addr);
 	if (mhp->attr.pbl_size)
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 7746113552e7..55dedadcffaa 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -557,6 +557,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.bind_mw = c4iw_bind_mw;
 	dev->ibdev.dealloc_mw = c4iw_dealloc_mw;
 	dev->ibdev.alloc_mr = c4iw_alloc_mr;
+	dev->ibdev.map_mr_sg = c4iw_map_mr_sg;
 	dev->ibdev.alloc_fast_reg_page_list = c4iw_alloc_fastreg_pbl;
 	dev->ibdev.free_fast_reg_page_list = c4iw_free_fastreg_pbl;
 	dev->ibdev.attach_mcast = c4iw_multicast_attach;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index b60498fff99a..12a23bc935f3 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -605,10 +605,76 @@ static int build_rdma_recv(struct c4iw_qp *qhp, union t4_recv_wr *wqe,
 	return 0;
 }
 
+static int build_memreg(struct t4_sq *sq, union t4_wr *wqe,
+			struct ib_reg_wr *wr, u8 *len16, u8 t5dev)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(wr->mr);
+	struct fw_ri_immd *imdp;
+	__be64 *p;
+	int i;
+	int pbllen = roundup(mhp->mpl_len * sizeof(u64), 32);
+	int rem;
+
+	if (mhp->mpl_len > t4_max_fr_depth(use_dsgl))
+		return -EINVAL;
+
+	wqe->fr.qpbinde_to_dcacpu = 0;
+	wqe->fr.pgsz_shift = ilog2(wr->mr->page_size) - 12;
+	wqe->fr.addr_type = FW_RI_VA_BASED_TO;
+	wqe->fr.mem_perms = c4iw_ib_to_tpt_access(wr->access);
+	wqe->fr.len_hi = 0;
+	wqe->fr.len_lo = cpu_to_be32(mhp->ibmr.length);
+	wqe->fr.stag = cpu_to_be32(wr->key);
+	wqe->fr.va_hi = cpu_to_be32(mhp->ibmr.iova >> 32);
+	wqe->fr.va_lo_fbo = cpu_to_be32(mhp->ibmr.iova &
+					0xffffffff);
+
+	if (t5dev && use_dsgl && (pbllen > max_fr_immd)) {
+		struct fw_ri_dsgl *sglp;
+
+		for (i = 0; i < mhp->mpl_len; i++)
+			mhp->mpl[i] = (__force u64)cpu_to_be64((u64)mhp->mpl[i]);
+
+		sglp = (struct fw_ri_dsgl *)(&wqe->fr + 1);
+		sglp->op = FW_RI_DATA_DSGL;
+		sglp->r1 = 0;
+		sglp->nsge = cpu_to_be16(1);
+		sglp->addr0 = cpu_to_be64(mhp->mpl_addr);
+		sglp->len0 = cpu_to_be32(pbllen);
+
+		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*sglp), 16);
+	} else {
+		imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
+		imdp->op = FW_RI_DATA_IMMD;
+		imdp->r1 = 0;
+		imdp->r2 = 0;
+		imdp->immdlen = cpu_to_be32(pbllen);
+		p = (__be64 *)(imdp + 1);
+		rem = pbllen;
+		for (i = 0; i < mhp->mpl_len; i++) {
+			*p = cpu_to_be64((u64)mhp->mpl[i]);
+			rem -= sizeof(*p);
+			if (++p == (__be64 *)&sq->queue[sq->size])
+				p = (__be64 *)sq->queue;
+		}
+		BUG_ON(rem < 0);
+		while (rem) {
+			*p = 0;
+			rem -= sizeof(*p);
+			if (++p == (__be64 *)&sq->queue[sq->size])
+				p = (__be64 *)sq->queue;
+		}
+		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*imdp)
+				      + pbllen, 16);
+	}
+	return 0;
+}
+
 static int build_fastreg(struct t4_sq *sq, union t4_wr *wqe,
 			 struct ib_send_wr *send_wr, u8 *len16, u8 t5dev)
 {
 	struct ib_fast_reg_wr *wr = fast_reg_wr(send_wr);
+
 	struct fw_ri_immd *imdp;
 	__be64 *p;
 	int i;
@@ -817,6 +883,14 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 					    qhp->rhp->rdev.lldi.adapter_type) ?
 					    1 : 0);
 			break;
+		case IB_WR_REG_MR:
+			fw_opcode = FW_RI_FR_NSMR_WR;
+			swsqe->opcode = FW_RI_FAST_REGISTER;
+			err = build_memreg(&qhp->wq.sq, wqe, reg_wr(wr), &len16,
+					   is_t5(
+					   qhp->rhp->rdev.lldi.adapter_type) ?
+					   1 : 0);
+			break;
 		case IB_WR_LOCAL_INV:
 			if (wr->send_flags & IB_SEND_FENCE)
 				fw_flags |= FW_RI_LOCAL_FENCE_FLAG;
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 08/26] IB/qib: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in qib_mr and populate it when
qib_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating qib_fastreg_mr just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (qib_mr)
- key, access flags (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/qib/qib_keys.c  | 56 +++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/qib/qib_mr.c    | 32 ++++++++++++++++++++
 drivers/infiniband/hw/qib/qib_verbs.c |  9 +++++-
 drivers/infiniband/hw/qib/qib_verbs.h |  8 +++++
 4 files changed, 104 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/qib/qib_keys.c b/drivers/infiniband/hw/qib/qib_keys.c
index eaf139a33b2e..95b8b9110fc6 100644
--- a/drivers/infiniband/hw/qib/qib_keys.c
+++ b/drivers/infiniband/hw/qib/qib_keys.c
@@ -390,3 +390,59 @@ bail:
 	spin_unlock_irqrestore(&rkt->lock, flags);
 	return ret;
 }
+
+/*
+ * Initialize the memory region specified by the work request.
+ */
+int qib_reg_mr(struct qib_qp *qp, struct ib_reg_wr *wr)
+{
+	struct qib_lkey_table *rkt = &to_idev(qp->ibqp.device)->lk_table;
+	struct qib_pd *pd = to_ipd(qp->ibqp.pd);
+	struct qib_mr *mr = to_imr(wr->mr);
+	struct qib_mregion *mrg;
+	u32 key = wr->key;
+	unsigned i, n, m;
+	int ret = -EINVAL;
+	unsigned long flags;
+	u64 *page_list;
+	size_t ps;
+
+	spin_lock_irqsave(&rkt->lock, flags);
+	if (pd->user || key == 0)
+		goto bail;
+
+	mrg = rcu_dereference_protected(
+		rkt->table[(key >> (32 - ib_qib_lkey_table_size))],
+		lockdep_is_held(&rkt->lock));
+	if (unlikely(mrg == NULL || qp->ibqp.pd != mrg->pd))
+		goto bail;
+
+	if (mr->npages > mrg->max_segs)
+		goto bail;
+
+	ps = mr->ibmr.page_size;
+	if (mr->ibmr.length > ps * mr->npages)
+		goto bail;
+
+	mrg->user_base = mr->ibmr.iova;
+	mrg->iova = mr->ibmr.iova;
+	mrg->lkey = key;
+	mrg->length = mr->ibmr.length;
+	mrg->access_flags = wr->access;
+	page_list = mr->pages;
+	m = 0;
+	n = 0;
+	for (i = 0; i < mr->npages; i++) {
+		mrg->map[m]->segs[n].vaddr = (void *) page_list[i];
+		mrg->map[m]->segs[n].length = ps;
+		if (++n == QIB_SEGSZ) {
+			m++;
+			n = 0;
+		}
+	}
+
+	ret = 0;
+bail:
+	spin_unlock_irqrestore(&rkt->lock, flags);
+	return ret;
+}
diff --git a/drivers/infiniband/hw/qib/qib_mr.c b/drivers/infiniband/hw/qib/qib_mr.c
index 19220dcb9a3b..0fa4b0de8074 100644
--- a/drivers/infiniband/hw/qib/qib_mr.c
+++ b/drivers/infiniband/hw/qib/qib_mr.c
@@ -303,6 +303,7 @@ int qib_dereg_mr(struct ib_mr *ibmr)
 	int ret = 0;
 	unsigned long timeout;
 
+	kfree(mr->pages);
 	qib_free_lkey(&mr->mr);
 
 	qib_put_mr(&mr->mr); /* will set completion if last */
@@ -340,7 +341,38 @@ struct ib_mr *qib_alloc_mr(struct ib_pd *pd,
 	if (IS_ERR(mr))
 		return (struct ib_mr *)mr;
 
+	mr->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL);
+	if (!mr->pages)
+		goto err;
+
 	return &mr->ibmr;
+
+err:
+	qib_dereg_mr(&mr->ibmr);
+	return ERR_PTR(-ENOMEM);
+}
+
+static int qib_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct qib_mr *mr = to_imr(ibmr);
+
+	if (unlikely(mr->npages == mr->mr.max_segs))
+		return -ENOMEM;
+
+	mr->pages[mr->npages++] = addr;
+
+	return 0;
+}
+
+int qib_map_mr_sg(struct ib_mr *ibmr,
+		  struct scatterlist *sg,
+		  unsigned int sg_nents)
+{
+	struct qib_mr *mr = to_imr(ibmr);
+
+	mr->npages = 0;
+
+	return ib_sg_to_pages(ibmr, sg, sg_nents, qib_set_page);
 }
 
 struct ib_fast_reg_page_list *
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index a6b0b098ff30..a1e53d7b662b 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -362,7 +362,10 @@ static int qib_post_one_send(struct qib_qp *qp, struct ib_send_wr *wr,
 	 * undefined operations.
 	 * Make sure buffer is large enough to hold the result for atomics.
 	 */
-	if (wr->opcode == IB_WR_FAST_REG_MR) {
+	if (wr->opcode == IB_WR_REG_MR) {
+		if (qib_reg_mr(qp, reg_wr(wr)))
+			goto bail_inval;
+	} else if (wr->opcode == IB_WR_FAST_REG_MR) {
 		if (qib_fast_reg_mr(qp, wr))
 			goto bail_inval;
 	} else if (qp->ibqp.qp_type == IB_QPT_UC) {
@@ -401,6 +404,9 @@ static int qib_post_one_send(struct qib_qp *qp, struct ib_send_wr *wr,
 	if (qp->ibqp.qp_type != IB_QPT_UC &&
 	    qp->ibqp.qp_type != IB_QPT_RC)
 		memcpy(&wqe->ud_wr, ud_wr(wr), sizeof(wqe->ud_wr));
+	else if (wr->opcode == IB_WR_REG_MR)
+		memcpy(&wqe->reg_wr, reg_wr(wr),
+			sizeof(wqe->reg_wr));
 	else if (wr->opcode == IB_WR_FAST_REG_MR)
 		memcpy(&wqe->fast_reg_wr, fast_reg_wr(wr),
 			sizeof(wqe->fast_reg_wr));
@@ -2260,6 +2266,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	ibdev->reg_user_mr = qib_reg_user_mr;
 	ibdev->dereg_mr = qib_dereg_mr;
 	ibdev->alloc_mr = qib_alloc_mr;
+	ibdev->map_mr_sg = qib_map_mr_sg;
 	ibdev->alloc_fast_reg_page_list = qib_alloc_fast_reg_page_list;
 	ibdev->free_fast_reg_page_list = qib_free_fast_reg_page_list;
 	ibdev->alloc_fmr = qib_alloc_fmr;
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index 8aa16851a5e6..dbc81c5761e3 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -330,6 +330,8 @@ struct qib_mr {
 	struct ib_mr ibmr;
 	struct ib_umem *umem;
 	struct qib_mregion mr;  /* must be last */
+	u64 *pages;
+	u32 npages;
 };
 
 /*
@@ -341,6 +343,7 @@ struct qib_swqe {
 	union {
 		struct ib_send_wr wr;   /* don't use wr.sg_list */
 		struct ib_ud_wr ud_wr;
+		struct ib_reg_wr reg_wr;
 		struct ib_fast_reg_wr fast_reg_wr;
 		struct ib_rdma_wr rdma_wr;
 		struct ib_atomic_wr atomic_wr;
@@ -1044,12 +1047,17 @@ struct ib_mr *qib_alloc_mr(struct ib_pd *pd,
 			   enum ib_mr_type mr_type,
 			   u32 max_entries);
 
+int qib_map_mr_sg(struct ib_mr *ibmr,
+		  struct scatterlist *sg,
+		  unsigned int sg_nents);
+
 struct ib_fast_reg_page_list *qib_alloc_fast_reg_page_list(
 				struct ib_device *ibdev, int page_list_len);
 
 void qib_free_fast_reg_page_list(struct ib_fast_reg_page_list *pl);
 
 int qib_fast_reg_mr(struct qib_qp *qp, struct ib_send_wr *wr);
+int qib_reg_mr(struct qib_qp *qp, struct ib_reg_wr *wr);
 
 struct ib_fmr *qib_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
 			     struct ib_fmr_attr *fmr_attr);
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 09/26] RDMA/nes: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in nes_mr and populate it when
nes_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating IB_WR_FAST_REG_MR handling and take the
needed information from different places:
- page_size, iova, length (ib_mr)
- page array (nes_mr)
- key, access flags (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/nes/nes_verbs.c | 117 +++++++++++++++++++++++++++++++++-
 drivers/infiniband/hw/nes/nes_verbs.h |   4 ++
 2 files changed, 120 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index f71b37b75f82..f5b0cc972403 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -51,6 +51,7 @@ atomic_t qps_created;
 atomic_t sw_qps_destroyed;
 
 static void nes_unregister_ofa_device(struct nes_ib_device *nesibdev);
+static int nes_dereg_mr(struct ib_mr *ib_mr);
 
 /**
  * nes_alloc_mw
@@ -443,9 +444,46 @@ static struct ib_mr *nes_alloc_mr(struct ib_pd *ibpd,
 	} else {
 		kfree(nesmr);
 		nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
-		ibmr = ERR_PTR(-ENOMEM);
+		return ERR_PTR(-ENOMEM);
 	}
+
+	nesmr->pages = pci_alloc_consistent(nesdev->pcidev,
+					    max_num_sg * sizeof(u64),
+					    &nesmr->paddr);
+	if (!nesmr->paddr)
+		goto err;
+
+	nesmr->max_pages = max_num_sg;
+
 	return ibmr;
+
+err:
+	nes_dereg_mr(ibmr);
+
+	return ERR_PTR(-ENOMEM);
+}
+
+static int nes_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct nes_mr *nesmr = to_nesmr(ibmr);
+
+	if (unlikely(nesmr->npages == nesmr->max_pages))
+		return -ENOMEM;
+
+	nesmr->pages[nesmr->npages++] = cpu_to_le64(addr);
+
+	return 0;
+}
+
+static int nes_map_mr_sg(struct ib_mr *ibmr,
+			 struct scatterlist *sg,
+			 unsigned int sg_nents)
+{
+	struct nes_mr *nesmr = to_nesmr(ibmr);
+
+	nesmr->npages = 0;
+
+	return ib_sg_to_pages(ibmr, sg, sg_nents, nes_set_page);
 }
 
 /*
@@ -2683,6 +2721,13 @@ static int nes_dereg_mr(struct ib_mr *ib_mr)
 	u16 major_code;
 	u16 minor_code;
 
+
+	if (nesmr->pages)
+		pci_free_consistent(nesdev->pcidev,
+				    nesmr->max_pages * sizeof(u64),
+				    nesmr->pages,
+				    nesmr->paddr);
+
 	if (nesmr->region) {
 		ib_umem_release(nesmr->region);
 	}
@@ -3513,6 +3558,75 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr,
 				  wqe_misc);
 			break;
 		}
+		case IB_WR_REG_MR:
+		{
+			struct nes_mr *mr = to_nesmr(reg_wr(ib_wr)->mr);
+			int page_shift = ilog2(reg_wr(ib_wr)->mr->page_size);
+			int flags = reg_wr(ib_wr)->access;
+
+			if (mr->npages > (NES_4K_PBL_CHUNK_SIZE / sizeof(u64))) {
+				nes_debug(NES_DBG_IW_TX, "SQ_FMR: bad page_list_len\n");
+				err = -EINVAL;
+				break;
+			}
+			wqe_misc = NES_IWARP_SQ_OP_FAST_REG;
+			set_wqe_64bit_value(wqe->wqe_words,
+					    NES_IWARP_SQ_FMR_WQE_VA_FBO_LOW_IDX,
+					    mr->ibmr.iova);
+			set_wqe_32bit_value(wqe->wqe_words,
+					    NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX,
+					    mr->ibmr.length);
+			set_wqe_32bit_value(wqe->wqe_words,
+					    NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0);
+			set_wqe_32bit_value(wqe->wqe_words,
+					    NES_IWARP_SQ_FMR_WQE_MR_STAG_IDX,
+					    reg_wr(ib_wr)->key);
+
+			if (page_shift == 12) {
+				wqe_misc |= NES_IWARP_SQ_FMR_WQE_PAGE_SIZE_4K;
+			} else if (page_shift == 21) {
+				wqe_misc |= NES_IWARP_SQ_FMR_WQE_PAGE_SIZE_2M;
+			} else {
+				nes_debug(NES_DBG_IW_TX, "Invalid page shift,"
+					  " ib_wr=%u, max=1\n", ib_wr->num_sge);
+				err = -EINVAL;
+				break;
+			}
+
+			/* Set access_flags */
+			wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_LOCAL_READ;
+			if (flags & IB_ACCESS_LOCAL_WRITE)
+				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_LOCAL_WRITE;
+
+			if (flags & IB_ACCESS_REMOTE_WRITE)
+				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_REMOTE_WRITE;
+
+			if (flags & IB_ACCESS_REMOTE_READ)
+				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_REMOTE_READ;
+
+			if (flags & IB_ACCESS_MW_BIND)
+				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_WINDOW_BIND;
+
+			/* Fill in PBL info: */
+			set_wqe_64bit_value(wqe->wqe_words,
+					    NES_IWARP_SQ_FMR_WQE_PBL_ADDR_LOW_IDX,
+					    mr->paddr);
+
+			set_wqe_32bit_value(wqe->wqe_words,
+					    NES_IWARP_SQ_FMR_WQE_PBL_LENGTH_IDX,
+					    mr->npages * 8);
+
+			nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, "
+				  "length: %d, rkey: %0x, pgl_paddr: %llx, "
+				  "page_list_len: %u, wqe_misc: %x\n",
+				  (unsigned long long) mr->ibmr.iova,
+				  mr->ibmr.length,
+				  reg_wr(ib_wr)->key,
+				  (unsigned long long) mr->paddr,
+				  mr->npages,
+				  wqe_misc);
+			break;
+		}
 		default:
 			/* error */
 			err = -EINVAL;
@@ -3940,6 +4054,7 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev)
 	nesibdev->ibdev.bind_mw = nes_bind_mw;
 
 	nesibdev->ibdev.alloc_mr = nes_alloc_mr;
+	nesibdev->ibdev.map_mr_sg = nes_map_mr_sg;
 	nesibdev->ibdev.alloc_fast_reg_page_list = nes_alloc_fast_reg_page_list;
 	nesibdev->ibdev.free_fast_reg_page_list = nes_free_fast_reg_page_list;
 
diff --git a/drivers/infiniband/hw/nes/nes_verbs.h b/drivers/infiniband/hw/nes/nes_verbs.h
index 309b31c31ae1..a204b677af22 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.h
+++ b/drivers/infiniband/hw/nes/nes_verbs.h
@@ -79,6 +79,10 @@ struct nes_mr {
 	u16               pbls_used;
 	u8                mode;
 	u8                pbl_4k;
+	__le64            *pages;
+	dma_addr_t        paddr;
+	u32               max_pages;
+	u32		  npages;
 };
 
 struct nes_hw_pb {
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 10/26] IB/iser: Port to new fast registration API

[Sagi Grimberg]

Remove fastreg page list allocation as the page vector
is now private to the provider. Instead of constructing
the page list and fast_req work request, call ib_map_mr_sg
and construct ib_reg_wr.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/ulp/iser/iscsi_iser.h  |  8 ++---
 drivers/infiniband/ulp/iser/iser_memory.c | 54 ++++++++++++++-----------------
 drivers/infiniband/ulp/iser/iser_verbs.c  | 16 +--------
 3 files changed, 27 insertions(+), 51 deletions(-)

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 2484bee993ec..271aa71e827c 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -297,7 +297,7 @@ struct iser_tx_desc {
 	u8                           wr_idx;
 	union iser_wr {
 		struct ib_send_wr		send;
-		struct ib_fast_reg_wr		fast_reg;
+		struct ib_reg_wr		fast_reg;
 		struct ib_sig_handover_wr	sig;
 	} wrs[ISER_MAX_WRS];
 	struct iser_mem_reg          data_reg;
@@ -412,7 +412,6 @@ struct iser_device {
  *
  * @mr:         memory region
  * @fmr_pool:   pool of fmrs
- * @frpl:       fast reg page list used by frwrs
  * @page_vec:   fast reg page list used by fmr pool
  * @mr_valid:   is mr valid indicator
  */
@@ -421,10 +420,7 @@ struct iser_reg_resources {
 		struct ib_mr             *mr;
 		struct ib_fmr_pool       *fmr_pool;
 	};
-	union {
-		struct ib_fast_reg_page_list     *frpl;
-		struct iser_page_vec             *page_vec;
-	};
+	struct iser_page_vec             *page_vec;
 	u8				  mr_valid:1;
 };
 
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index b29fda3e8e74..ea765fb9664d 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -472,7 +472,7 @@ iser_reg_sig_mr(struct iscsi_iser_task *iser_task,
 	sig_reg->sge.addr = 0;
 	sig_reg->sge.length = scsi_transfer_length(iser_task->sc);
 
-	iser_dbg("sig reg: lkey: 0x%x, rkey: 0x%x, addr: 0x%llx, length: %u\n",
+	iser_dbg("lkey=0x%x rkey=0x%x addr=0x%llx length=%u\n",
 		 sig_reg->sge.lkey, sig_reg->rkey, sig_reg->sge.addr,
 		 sig_reg->sge.length);
 err:
@@ -484,47 +484,41 @@ static int iser_fast_reg_mr(struct iscsi_iser_task *iser_task,
 			    struct iser_reg_resources *rsc,
 			    struct iser_mem_reg *reg)
 {
-	struct ib_conn *ib_conn = &iser_task->iser_conn->ib_conn;
-	struct iser_device *device = ib_conn->device;
-	struct ib_mr *mr = rsc->mr;
-	struct ib_fast_reg_page_list *frpl = rsc->frpl;
 	struct iser_tx_desc *tx_desc = &iser_task->desc;
-	struct ib_fast_reg_wr *wr;
-	int offset, size, plen;
-
-	plen = iser_sg_to_page_vec(mem, device->ib_device, frpl->page_list,
-				   &offset, &size);
-	if (plen * SIZE_4K < size) {
-		iser_err("fast reg page_list too short to hold this SG\n");
-		return -EINVAL;
-	}
+	struct ib_mr *mr = rsc->mr;
+	struct ib_reg_wr *wr;
+	int n;
 
 	if (!rsc->mr_valid)
 		iser_inv_rkey(iser_tx_next_wr(tx_desc), mr);
 
-	wr = fast_reg_wr(iser_tx_next_wr(tx_desc));
-	wr->wr.opcode = IB_WR_FAST_REG_MR;
+	n = ib_map_mr_sg(mr, mem->sg, mem->size, SIZE_4K);
+	if (unlikely(n != mem->size)) {
+		iser_err("failed to map sg (%d/%d)\n",
+			 n, mem->size);
+		return n < 0 ? n : -EINVAL;
+	}
+
+	wr = reg_wr(iser_tx_next_wr(tx_desc));
+	wr->wr.opcode = IB_WR_REG_MR;
 	wr->wr.wr_id = ISER_FASTREG_LI_WRID;
 	wr->wr.send_flags = 0;
-	wr->iova_start = frpl->page_list[0] + offset;
-	wr->page_list = frpl;
-	wr->page_list_len = plen;
-	wr->page_shift = SHIFT_4K;
-	wr->length = size;
-	wr->rkey = mr->rkey;
-	wr->access_flags = (IB_ACCESS_LOCAL_WRITE  |
-			    IB_ACCESS_REMOTE_WRITE |
-			    IB_ACCESS_REMOTE_READ);
+	wr->wr.num_sge = 0;
+	wr->mr = mr;
+	wr->key = mr->rkey;
+	wr->access = IB_ACCESS_LOCAL_WRITE  |
+		     IB_ACCESS_REMOTE_WRITE |
+		     IB_ACCESS_REMOTE_READ;
+
 	rsc->mr_valid = 0;
 
 	reg->sge.lkey = mr->lkey;
 	reg->rkey = mr->rkey;
-	reg->sge.addr = frpl->page_list[0] + offset;
-	reg->sge.length = size;
+	reg->sge.addr = mr->iova;
+	reg->sge.length = mr->length;
 
-	iser_dbg("fast reg: lkey=0x%x, rkey=0x%x, addr=0x%llx,"
-		 " length=0x%x\n", reg->sge.lkey, reg->rkey,
-		 reg->sge.addr, reg->sge.length);
+	iser_dbg("lkey=0x%x rkey=0x%x addr=0x%llx length=0x%x\n",
+		 reg->sge.lkey, reg->rkey, reg->sge.addr, reg->sge.length);
 
 	return 0;
 }
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index b26022e30af1..a66b9dea96d8 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -293,35 +293,21 @@ iser_alloc_reg_res(struct ib_device *ib_device,
 {
 	int ret;
 
-	res->frpl = ib_alloc_fast_reg_page_list(ib_device, size);
-	if (IS_ERR(res->frpl)) {
-		ret = PTR_ERR(res->frpl);
-		iser_err("Failed to allocate ib_fast_reg_page_list err=%d\n",
-			 ret);
-		return PTR_ERR(res->frpl);
-	}
-
 	res->mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, size);
 	if (IS_ERR(res->mr)) {
 		ret = PTR_ERR(res->mr);
 		iser_err("Failed to allocate ib_fast_reg_mr err=%d\n", ret);
-		goto fast_reg_mr_failure;
+		return ret;
 	}
 	res->mr_valid = 1;
 
 	return 0;
-
-fast_reg_mr_failure:
-	ib_free_fast_reg_page_list(res->frpl);
-
-	return ret;
 }
 
 static void
 iser_free_reg_res(struct iser_reg_resources *rsc)
 {
 	ib_dereg_mr(rsc->mr);
-	ib_free_fast_reg_page_list(rsc->frpl);
 }
 
 static int
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 11/26] iser-target: Port to new memory registration API

[Sagi Grimberg]

Remove fastreg page list allocation as the page vector
is now private to the provider. Instead of constructing
the page list and fast_req work request, call ib_map_mr_sg
and construct ib_reg_wr.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/ulp/isert/ib_isert.c | 130 +++++++-------------------------
 drivers/infiniband/ulp/isert/ib_isert.h |   2 -
 2 files changed, 28 insertions(+), 104 deletions(-)

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index dcb29d166211..692875ba7a1f 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -475,10 +475,8 @@ isert_conn_free_fastreg_pool(struct isert_conn *isert_conn)
 	list_for_each_entry_safe(fr_desc, tmp,
 				 &isert_conn->fr_pool, list) {
 		list_del(&fr_desc->list);
-		ib_free_fast_reg_page_list(fr_desc->data_frpl);
 		ib_dereg_mr(fr_desc->data_mr);
 		if (fr_desc->pi_ctx) {
-			ib_free_fast_reg_page_list(fr_desc->pi_ctx->prot_frpl);
 			ib_dereg_mr(fr_desc->pi_ctx->prot_mr);
 			ib_dereg_mr(fr_desc->pi_ctx->sig_mr);
 			kfree(fr_desc->pi_ctx);
@@ -506,22 +504,13 @@ isert_create_pi_ctx(struct fast_reg_descriptor *desc,
 		return -ENOMEM;
 	}
 
-	pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(device,
-					    ISCSI_ISER_SG_TABLESIZE);
-	if (IS_ERR(pi_ctx->prot_frpl)) {
-		isert_err("Failed to allocate prot frpl err=%ld\n",
-			  PTR_ERR(pi_ctx->prot_frpl));
-		ret = PTR_ERR(pi_ctx->prot_frpl);
-		goto err_pi_ctx;
-	}
-
 	pi_ctx->prot_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG,
 				      ISCSI_ISER_SG_TABLESIZE);
 	if (IS_ERR(pi_ctx->prot_mr)) {
 		isert_err("Failed to allocate prot frmr err=%ld\n",
 			  PTR_ERR(pi_ctx->prot_mr));
 		ret = PTR_ERR(pi_ctx->prot_mr);
-		goto err_prot_frpl;
+		goto err_pi_ctx;
 	}
 	desc->ind |= ISERT_PROT_KEY_VALID;
 
@@ -541,8 +530,6 @@ isert_create_pi_ctx(struct fast_reg_descriptor *desc,
 
 err_prot_mr:
 	ib_dereg_mr(pi_ctx->prot_mr);
-err_prot_frpl:
-	ib_free_fast_reg_page_list(pi_ctx->prot_frpl);
 err_pi_ctx:
 	kfree(pi_ctx);
 
@@ -553,34 +540,18 @@ static int
 isert_create_fr_desc(struct ib_device *ib_device, struct ib_pd *pd,
 		     struct fast_reg_descriptor *fr_desc)
 {
-	int ret;
-
-	fr_desc->data_frpl = ib_alloc_fast_reg_page_list(ib_device,
-							 ISCSI_ISER_SG_TABLESIZE);
-	if (IS_ERR(fr_desc->data_frpl)) {
-		isert_err("Failed to allocate data frpl err=%ld\n",
-			  PTR_ERR(fr_desc->data_frpl));
-		return PTR_ERR(fr_desc->data_frpl);
-	}
-
 	fr_desc->data_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG,
 				       ISCSI_ISER_SG_TABLESIZE);
 	if (IS_ERR(fr_desc->data_mr)) {
 		isert_err("Failed to allocate data frmr err=%ld\n",
 			  PTR_ERR(fr_desc->data_mr));
-		ret = PTR_ERR(fr_desc->data_mr);
-		goto err_data_frpl;
+		return PTR_ERR(fr_desc->data_mr);
 	}
 	fr_desc->ind |= ISERT_DATA_KEY_VALID;
 
 	isert_dbg("Created fr_desc %p\n", fr_desc);
 
 	return 0;
-
-err_data_frpl:
-	ib_free_fast_reg_page_list(fr_desc->data_frpl);
-
-	return ret;
 }
 
 static int
@@ -2516,45 +2487,6 @@ unmap_cmd:
 	return ret;
 }
 
-static int
-isert_map_fr_pagelist(struct ib_device *ib_dev,
-		      struct scatterlist *sg_start, int sg_nents, u64 *fr_pl)
-{
-	u64 start_addr, end_addr, page, chunk_start = 0;
-	struct scatterlist *tmp_sg;
-	int i = 0, new_chunk, last_ent, n_pages;
-
-	n_pages = 0;
-	new_chunk = 1;
-	last_ent = sg_nents - 1;
-	for_each_sg(sg_start, tmp_sg, sg_nents, i) {
-		start_addr = ib_sg_dma_address(ib_dev, tmp_sg);
-		if (new_chunk)
-			chunk_start = start_addr;
-		end_addr = start_addr + ib_sg_dma_len(ib_dev, tmp_sg);
-
-		isert_dbg("SGL[%d] dma_addr: 0x%llx len: %u\n",
-			  i, (unsigned long long)tmp_sg->dma_address,
-			  tmp_sg->length);
-
-		if ((end_addr & ~PAGE_MASK) && i < last_ent) {
-			new_chunk = 0;
-			continue;
-		}
-		new_chunk = 1;
-
-		page = chunk_start & PAGE_MASK;
-		do {
-			fr_pl[n_pages++] = page;
-			isert_dbg("Mapped page_list[%d] page_addr: 0x%llx\n",
-				  n_pages - 1, page);
-			page += PAGE_SIZE;
-		} while (page < end_addr);
-	}
-
-	return n_pages;
-}
-
 static inline void
 isert_inv_rkey(struct ib_send_wr *inv_wr, struct ib_mr *mr)
 {
@@ -2580,11 +2512,9 @@ isert_fast_reg_mr(struct isert_conn *isert_conn,
 	struct isert_device *device = isert_conn->device;
 	struct ib_device *ib_dev = device->ib_device;
 	struct ib_mr *mr;
-	struct ib_fast_reg_page_list *frpl;
-	struct ib_fast_reg_wr fr_wr;
+	struct ib_reg_wr reg_wr;
 	struct ib_send_wr inv_wr, *bad_wr, *wr = NULL;
-	int ret, pagelist_len;
-	u32 page_off;
+	int ret, n;
 
 	if (mem->dma_nents == 1) {
 		sge->lkey = device->pd->local_dma_lkey;
@@ -2595,45 +2525,41 @@ isert_fast_reg_mr(struct isert_conn *isert_conn,
 		return 0;
 	}
 
-	if (ind == ISERT_DATA_KEY_VALID) {
+	if (ind == ISERT_DATA_KEY_VALID)
 		/* Registering data buffer */
 		mr = fr_desc->data_mr;
-		frpl = fr_desc->data_frpl;
-	} else {
+	else
 		/* Registering protection buffer */
 		mr = fr_desc->pi_ctx->prot_mr;
-		frpl = fr_desc->pi_ctx->prot_frpl;
-	}
-
-	page_off = mem->offset % PAGE_SIZE;
-
-	isert_dbg("Use fr_desc %p sg_nents %d offset %u\n",
-		  fr_desc, mem->nents, mem->offset);
-
-	pagelist_len = isert_map_fr_pagelist(ib_dev, mem->sg, mem->nents,
-					     &frpl->page_list[0]);
 
 	if (!(fr_desc->ind & ind)) {
 		isert_inv_rkey(&inv_wr, mr);
 		wr = &inv_wr;
 	}
 
-	/* Prepare FASTREG WR */
-	memset(&fr_wr, 0, sizeof(fr_wr));
-	fr_wr.wr.wr_id = ISER_FASTREG_LI_WRID;
-	fr_wr.wr.opcode = IB_WR_FAST_REG_MR;
-	fr_wr.iova_start = frpl->page_list[0] + page_off;
-	fr_wr.page_list = frpl;
-	fr_wr.page_list_len = pagelist_len;
-	fr_wr.page_shift = PAGE_SHIFT;
-	fr_wr.length = mem->len;
-	fr_wr.rkey = mr->rkey;
-	fr_wr.access_flags = IB_ACCESS_LOCAL_WRITE;
+	n = ib_map_mr_sg(mr, mem->sg, mem->nents, PAGE_SIZE);
+	if (unlikely(n != mem->nents)) {
+		isert_err("failed to map mr sg (%d/%d)\n",
+			 n, mem->nents);
+		return n < 0 ? n : -EINVAL;
+	}
+
+	isert_dbg("Use fr_desc %p sg_nents %d offset %u\n",
+		  fr_desc, mem->nents, mem->offset);
+
+	reg_wr.wr.next = NULL;
+	reg_wr.wr.opcode = IB_WR_REG_MR;
+	reg_wr.wr.wr_id = ISER_FASTREG_LI_WRID;
+	reg_wr.wr.send_flags = 0;
+	reg_wr.wr.num_sge = 0;
+	reg_wr.mr = mr;
+	reg_wr.key = mr->lkey;
+	reg_wr.access = IB_ACCESS_LOCAL_WRITE;
 
 	if (!wr)
-		wr = &fr_wr.wr;
+		wr = &reg_wr.wr;
 	else
-		wr->next = &fr_wr.wr;
+		wr->next = &reg_wr.wr;
 
 	ret = ib_post_send(isert_conn->qp, wr, &bad_wr);
 	if (ret) {
@@ -2643,8 +2569,8 @@ isert_fast_reg_mr(struct isert_conn *isert_conn,
 	fr_desc->ind &= ~ind;
 
 	sge->lkey = mr->lkey;
-	sge->addr = frpl->page_list[0] + page_off;
-	sge->length = mem->len;
+	sge->addr = mr->iova;
+	sge->length = mr->length;
 
 	isert_dbg("sge: addr: 0x%llx  length: %u lkey: %x\n",
 		  sge->addr, sge->length, sge->lkey);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 0a4a7861cce9..e87f9b096533 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -84,14 +84,12 @@ enum isert_indicator {
 
 struct pi_context {
 	struct ib_mr		       *prot_mr;
-	struct ib_fast_reg_page_list   *prot_frpl;
 	struct ib_mr		       *sig_mr;
 };
 
 struct fast_reg_descriptor {
 	struct list_head		list;
 	struct ib_mr		       *data_mr;
-	struct ib_fast_reg_page_list   *data_frpl;
 	u8				ind;
 	struct pi_context	       *pi_ctx;
 };
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 12/26] xprtrdma: Port to new memory registration API

[Sagi Grimberg]

Instead of maintaining a fastreg page list, keep an sg table
and convert an array of pages to a sg list. Then call ib_map_mr_sg
and construct ib_reg_wr.

Note that the next step would be to have NFS work with sg lists
as it maps well to sk_frags (see comment from hch
http://marc.info/?l=linux-rdma&m=143677002622296&w=2).

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 net/sunrpc/xprtrdma/frwr_ops.c  | 113 +++++++++++++++++++++++-----------------
 net/sunrpc/xprtrdma/xprt_rdma.h |   3 +-
 2 files changed, 68 insertions(+), 48 deletions(-)

diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 0d2f46f600b6..b80a82149977 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -151,9 +151,13 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
 	f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth);
 	if (IS_ERR(f->fr_mr))
 		goto out_mr_err;
-	f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth);
-	if (IS_ERR(f->fr_pgl))
+
+	f->sg = kcalloc(depth, sizeof(*f->sg), GFP_KERNEL);
+	if (!f->sg)
 		goto out_list_err;
+
+	sg_init_table(f->sg, depth);
+
 	return 0;
 
 out_mr_err:
@@ -163,7 +167,7 @@ out_mr_err:
 	return rc;
 
 out_list_err:
-	rc = PTR_ERR(f->fr_pgl);
+	rc = -ENOMEM;
 	dprintk("RPC:       %s: ib_alloc_fast_reg_page_list status %i\n",
 		__func__, rc);
 	ib_dereg_mr(f->fr_mr);
@@ -179,7 +183,7 @@ __frwr_release(struct rpcrdma_mw *r)
 	if (rc)
 		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
 			__func__, rc);
-	ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
+	kfree(r->r.frmr.sg);
 }
 
 static int
@@ -312,14 +316,11 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	struct rpcrdma_mw *mw;
 	struct rpcrdma_frmr *frmr;
 	struct ib_mr *mr;
-	struct ib_fast_reg_wr fastreg_wr;
+	struct ib_reg_wr reg_wr;
 	struct ib_send_wr *bad_wr;
+	unsigned int dma_nents;
 	u8 key;
-	int len, pageoff;
-	int i, rc;
-	int seg_len;
-	u64 pa;
-	int page_no;
+	int i, rc, len, n;
 
 	mw = seg1->rl_mw;
 	seg1->rl_mw = NULL;
@@ -332,64 +333,81 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	} while (mw->r.frmr.fr_state != FRMR_IS_INVALID);
 	frmr = &mw->r.frmr;
 	frmr->fr_state = FRMR_IS_VALID;
+	mr = frmr->fr_mr;
 
-	pageoff = offset_in_page(seg1->mr_offset);
-	seg1->mr_offset -= pageoff;	/* start of page */
-	seg1->mr_len += pageoff;
-	len = -pageoff;
 	if (nsegs > ia->ri_max_frmr_depth)
 		nsegs = ia->ri_max_frmr_depth;
 
-	for (page_no = i = 0; i < nsegs;) {
-		rpcrdma_map_one(device, seg, direction);
-		pa = seg->mr_dma;
-		for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) {
-			frmr->fr_pgl->page_list[page_no++] = pa;
-			pa += PAGE_SIZE;
-		}
+	for (len = 0, i = 0; i < nsegs;) {
+		if (seg->mr_page)
+			sg_set_page(&frmr->sg[i],
+				    seg->mr_page,
+				    seg->mr_len,
+				    offset_in_page(seg->mr_offset));
+		else
+			sg_set_buf(&frmr->sg[i], seg->mr_offset,
+				   seg->mr_len);
+
 		len += seg->mr_len;
 		++seg;
 		++i;
+
 		/* Check for holes */
 		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
 			break;
 	}
+	frmr->sg_nents = i;
+
+	dma_nents = ib_dma_map_sg(device, frmr->sg, frmr->sg_nents, direction);
+	if (!dma_nents) {
+		pr_err("RPC:       %s: failed to dma map sg %p sg_nents %d\n",
+		       __func__, frmr->sg, frmr->sg_nents);
+		return -ENOMEM;
+	}
+
+	n = ib_map_mr_sg(mr, frmr->sg, frmr->sg_nents, PAGE_SIZE);
+	if (unlikely(n != frmr->sg_nents)) {
+		pr_err("RPC:       %s: failed to map mr %p (%d/%d)\n",
+		       __func__, frmr->fr_mr, n, frmr->sg_nents);
+		rc = n < 0 ? n : -EINVAL;
+		goto out_senderr;
+	}
+
 	dprintk("RPC:       %s: Using frmr %p to map %d segments (%d bytes)\n",
-		__func__, mw, i, len);
-
-	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
-	fastreg_wr.wr.wr_id = (unsigned long)(void *)mw;
-	fastreg_wr.wr.opcode = IB_WR_FAST_REG_MR;
-	fastreg_wr.iova_start = seg1->mr_dma + pageoff;
-	fastreg_wr.page_list = frmr->fr_pgl;
-	fastreg_wr.page_shift = PAGE_SHIFT;
-	fastreg_wr.page_list_len = page_no;
-	fastreg_wr.length = len;
-	fastreg_wr.access_flags = writing ?
-				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
-				IB_ACCESS_REMOTE_READ;
-	mr = frmr->fr_mr;
+		__func__, mw, frmr->sg_nents, mr->length);
+
 	key = (u8)(mr->rkey & 0x000000FF);
 	ib_update_fast_reg_key(mr, ++key);
-	fastreg_wr.rkey = mr->rkey;
+
+	reg_wr.wr.next = NULL;
+	reg_wr.wr.opcode = IB_WR_REG_MR;
+	reg_wr.wr.wr_id = (uintptr_t)mw;
+	reg_wr.wr.num_sge = 0;
+	reg_wr.wr.send_flags = 0;
+	reg_wr.mr = mr;
+	reg_wr.key = mr->rkey;
+	reg_wr.access = writing ?
+			IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
+			IB_ACCESS_REMOTE_READ;
 
 	DECR_CQCOUNT(&r_xprt->rx_ep);
-	rc = ib_post_send(ia->ri_id->qp, &fastreg_wr.wr, &bad_wr);
+	rc = ib_post_send(ia->ri_id->qp, &reg_wr.wr, &bad_wr);
 	if (rc)
 		goto out_senderr;
 
+	seg1->mr_dir = direction;
 	seg1->rl_mw = mw;
 	seg1->mr_rkey = mr->rkey;
-	seg1->mr_base = seg1->mr_dma + pageoff;
-	seg1->mr_nsegs = i;
-	seg1->mr_len = len;
-	return i;
+	seg1->mr_base = mr->iova;
+	seg1->mr_nsegs = frmr->sg_nents;
+	seg1->mr_len = mr->length;
+
+	return frmr->sg_nents;
 
 out_senderr:
 	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
-	while (i--)
-		rpcrdma_unmap_one(device, --seg);
+	ib_dma_unmap_sg(device, frmr->sg, frmr->sg_nents, direction);
 	__frwr_queue_recovery(mw);
 	return rc;
 }
@@ -403,28 +421,29 @@ frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
 	struct rpcrdma_mr_seg *seg1 = seg;
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	struct rpcrdma_mw *mw = seg1->rl_mw;
+	struct rpcrdma_frmr *frmr = &mw->r.frmr;
 	struct ib_send_wr invalidate_wr, *bad_wr;
 	int rc, nsegs = seg->mr_nsegs;
 
 	dprintk("RPC:       %s: FRMR %p\n", __func__, mw);
 
 	seg1->rl_mw = NULL;
-	mw->r.frmr.fr_state = FRMR_IS_INVALID;
+	frmr->fr_state = FRMR_IS_INVALID;
 
 	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
 	invalidate_wr.wr_id = (unsigned long)(void *)mw;
 	invalidate_wr.opcode = IB_WR_LOCAL_INV;
-	invalidate_wr.ex.invalidate_rkey = mw->r.frmr.fr_mr->rkey;
+	invalidate_wr.ex.invalidate_rkey = frmr->fr_mr->rkey;
 	DECR_CQCOUNT(&r_xprt->rx_ep);
 
-	while (seg1->mr_nsegs--)
-		rpcrdma_unmap_one(ia->ri_device, seg++);
 	read_lock(&ia->ri_qplock);
 	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
 	read_unlock(&ia->ri_qplock);
 	if (rc)
 		goto out_err;
 
+	ib_dma_unmap_sg(ia->ri_device, frmr->sg, frmr->sg_nents, seg1->mr_dir);
+
 	rpcrdma_put_mw(r_xprt, mw);
 	return nsegs;
 
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index d252457ff21a..00773636d17e 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -195,7 +195,8 @@ enum rpcrdma_frmr_state {
 };
 
 struct rpcrdma_frmr {
-	struct ib_fast_reg_page_list	*fr_pgl;
+	struct scatterlist		*sg;
+	unsigned int			sg_nents;
 	struct ib_mr			*fr_mr;
 	enum rpcrdma_frmr_state		fr_state;
 	struct work_struct		fr_work;
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 13/26] svcrdma: Port to new memory registration API

[Sagi Grimberg]

Instead of maintaining a fastreg page list, keep an sg table
and convert an array of pages to a sg list. Then call ib_map_mr_sg
and construct ib_reg_wr.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 include/linux/sunrpc/svc_rdma.h          |  6 +--
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  | 76 ++++++++++++++++++--------------
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 34 +++++---------
 3 files changed, 55 insertions(+), 61 deletions(-)

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 83211bc9219e..e240d102a911 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -105,11 +105,9 @@ struct svc_rdma_chunk_sge {
 };
 struct svc_rdma_fastreg_mr {
 	struct ib_mr *mr;
-	void *kva;
-	struct ib_fast_reg_page_list *page_list;
-	int page_list_len;
+	struct scatterlist *sg;
+	unsigned int sg_nents;
 	unsigned long access_flags;
-	unsigned long map_len;
 	enum dma_data_direction direction;
 	struct list_head frmr_list;
 };
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 7be42d0da19e..303f194970f9 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -220,12 +220,12 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 {
 	struct ib_rdma_wr read_wr;
 	struct ib_send_wr inv_wr;
-	struct ib_fast_reg_wr fastreg_wr;
+	struct ib_reg_wr reg_wr;
 	u8 key;
-	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
+	unsigned int nents = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
 	struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
 	struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt);
-	int ret, read, pno;
+	int ret, read, pno, dma_nents, n;
 	u32 pg_off = *page_offset;
 	u32 pg_no = *page_no;
 
@@ -234,16 +234,14 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 
 	ctxt->direction = DMA_FROM_DEVICE;
 	ctxt->frmr = frmr;
-	pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len);
-	read = min_t(int, pages_needed << PAGE_SHIFT, rs_length);
+	nents = min_t(unsigned int, nents, xprt->sc_frmr_pg_list_len);
+	read = min_t(int, nents << PAGE_SHIFT, rs_length);
 
-	frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]);
 	frmr->direction = DMA_FROM_DEVICE;
 	frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE);
-	frmr->map_len = pages_needed << PAGE_SHIFT;
-	frmr->page_list_len = pages_needed;
+	frmr->sg_nents = nents;
 
-	for (pno = 0; pno < pages_needed; pno++) {
+	for (pno = 0; pno < nents; pno++) {
 		int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
 
 		head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no];
@@ -251,17 +249,12 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 		head->arg.len += len;
 		if (!pg_off)
 			head->count++;
+
+		sg_set_page(&frmr->sg[pno], rqstp->rq_arg.pages[pg_no],
+			    len, pg_off);
+
 		rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
 		rqstp->rq_next_page = rqstp->rq_respages + 1;
-		frmr->page_list->page_list[pno] =
-			ib_dma_map_page(xprt->sc_cm_id->device,
-					head->arg.pages[pg_no], 0,
-					PAGE_SIZE, DMA_FROM_DEVICE);
-		ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
-					   frmr->page_list->page_list[pno]);
-		if (ret)
-			goto err;
-		atomic_inc(&xprt->sc_dma_used);
 
 		/* adjust offset and wrap to next page if needed */
 		pg_off += len;
@@ -277,28 +270,42 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	else
 		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
 
+	dma_nents = ib_dma_map_sg(xprt->sc_cm_id->device,
+				  frmr->sg, frmr->sg_nents,
+				  frmr->direction);
+	if (!dma_nents) {
+		pr_err("svcrdma: failed to dma map sg %p\n",
+		       frmr->sg);
+		return -ENOMEM;
+	}
+	atomic_inc(&xprt->sc_dma_used);
+
+	n = ib_map_mr_sg(frmr->mr, frmr->sg, frmr->sg_nents, PAGE_SIZE);
+	if (unlikely(n != frmr->sg_nents)) {
+		pr_err("svcrdma: failed to map mr %p (%d/%d elements)\n",
+		       frmr->mr, n, frmr->sg_nents);
+		return n < 0 ? n : -EINVAL;
+	}
+
 	/* Bump the key */
 	key = (u8)(frmr->mr->lkey & 0x000000FF);
 	ib_update_fast_reg_key(frmr->mr, ++key);
 
-	ctxt->sge[0].addr = (unsigned long)frmr->kva + *page_offset;
+	ctxt->sge[0].addr = frmr->mr->iova;
 	ctxt->sge[0].lkey = frmr->mr->lkey;
-	ctxt->sge[0].length = read;
+	ctxt->sge[0].length = frmr->mr->length;
 	ctxt->count = 1;
 	ctxt->read_hdr = head;
 
-	/* Prepare FASTREG WR */
-	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
-	fastreg_wr.wr.opcode = IB_WR_FAST_REG_MR;
-	fastreg_wr.wr.send_flags = IB_SEND_SIGNALED;
-	fastreg_wr.iova_start = (unsigned long)frmr->kva;
-	fastreg_wr.page_list = frmr->page_list;
-	fastreg_wr.page_list_len = frmr->page_list_len;
-	fastreg_wr.page_shift = PAGE_SHIFT;
-	fastreg_wr.length = frmr->map_len;
-	fastreg_wr.access_flags = frmr->access_flags;
-	fastreg_wr.rkey = frmr->mr->lkey;
-	fastreg_wr.wr.next = &read_wr.wr;
+	/* Prepare REG WR */
+	reg_wr.wr.opcode = IB_WR_REG_MR;
+	reg_wr.wr.wr_id = 0;
+	reg_wr.wr.send_flags = IB_SEND_SIGNALED;
+	reg_wr.wr.num_sge = 0;
+	reg_wr.mr = frmr->mr;
+	reg_wr.key = frmr->mr->lkey;
+	reg_wr.access = frmr->access_flags;
+	reg_wr.wr.next = &read_wr.wr;
 
 	/* Prepare RDMA_READ */
 	memset(&read_wr, 0, sizeof(read_wr));
@@ -324,7 +331,7 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	ctxt->wr_op = read_wr.wr.opcode;
 
 	/* Post the chain */
-	ret = svc_rdma_send(xprt, &fastreg_wr.wr);
+	ret = svc_rdma_send(xprt, &reg_wr.wr);
 	if (ret) {
 		pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
 		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
@@ -338,7 +345,8 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	atomic_inc(&rdma_stat_read);
 	return ret;
  err:
-	svc_rdma_unmap_dma(ctxt);
+	ib_dma_unmap_sg(xprt->sc_cm_id->device,
+			frmr->sg, frmr->sg_nents, frmr->direction);
 	svc_rdma_put_context(ctxt, 0);
 	svc_rdma_put_frmr(xprt, frmr);
 	return ret;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index b9fe134bb416..27aeda42f444 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -731,7 +731,7 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt)
 {
 	struct ib_mr *mr;
-	struct ib_fast_reg_page_list *pl;
+	struct scatterlist *sg;
 	struct svc_rdma_fastreg_mr *frmr;
 	u32 num_sg;
 
@@ -744,13 +744,14 @@ static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt)
 	if (IS_ERR(mr))
 		goto err_free_frmr;
 
-	pl = ib_alloc_fast_reg_page_list(xprt->sc_cm_id->device,
-					 num_sg);
-	if (IS_ERR(pl))
+	sg = kcalloc(RPCSVC_MAXPAGES, sizeof(*sg), GFP_KERNEL);
+	if (!sg)
 		goto err_free_mr;
 
+	sg_init_table(sg, RPCSVC_MAXPAGES);
+
 	frmr->mr = mr;
-	frmr->page_list = pl;
+	frmr->sg = sg;
 	INIT_LIST_HEAD(&frmr->frmr_list);
 	return frmr;
 
@@ -770,8 +771,8 @@ static void rdma_dealloc_frmr_q(struct svcxprt_rdma *xprt)
 		frmr = list_entry(xprt->sc_frmr_q.next,
 				  struct svc_rdma_fastreg_mr, frmr_list);
 		list_del_init(&frmr->frmr_list);
+		kfree(frmr->sg);
 		ib_dereg_mr(frmr->mr);
-		ib_free_fast_reg_page_list(frmr->page_list);
 		kfree(frmr);
 	}
 }
@@ -785,8 +786,7 @@ struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *rdma)
 		frmr = list_entry(rdma->sc_frmr_q.next,
 				  struct svc_rdma_fastreg_mr, frmr_list);
 		list_del_init(&frmr->frmr_list);
-		frmr->map_len = 0;
-		frmr->page_list_len = 0;
+		frmr->sg_nents = 0;
 	}
 	spin_unlock_bh(&rdma->sc_frmr_q_lock);
 	if (frmr)
@@ -795,25 +795,13 @@ struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *rdma)
 	return rdma_alloc_frmr(rdma);
 }
 
-static void frmr_unmap_dma(struct svcxprt_rdma *xprt,
-			   struct svc_rdma_fastreg_mr *frmr)
-{
-	int page_no;
-	for (page_no = 0; page_no < frmr->page_list_len; page_no++) {
-		dma_addr_t addr = frmr->page_list->page_list[page_no];
-		if (ib_dma_mapping_error(frmr->mr->device, addr))
-			continue;
-		atomic_dec(&xprt->sc_dma_used);
-		ib_dma_unmap_page(frmr->mr->device, addr, PAGE_SIZE,
-				  frmr->direction);
-	}
-}
-
 void svc_rdma_put_frmr(struct svcxprt_rdma *rdma,
 		       struct svc_rdma_fastreg_mr *frmr)
 {
 	if (frmr) {
-		frmr_unmap_dma(rdma, frmr);
+		ib_dma_unmap_sg(rdma->sc_cm_id->device,
+				frmr->sg, frmr->sg_nents, frmr->direction);
+		atomic_dec(&rdma->sc_dma_used);
 		spin_lock_bh(&rdma->sc_frmr_q_lock);
 		WARN_ON_ONCE(!list_empty(&frmr->frmr_list));
 		list_add(&frmr->frmr_list, &rdma->sc_frmr_q);
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 14/26] RDS/IW: Convert to new memory registration API

[Sagi Grimberg]

Get rid of fast_reg page list and its construction.
Instead, just pass the RDS sg list to ib_map_mr_sg
and post the new ib_reg_wr.

This is done both for server IW RDMA_READ registration
and the client remote key registration.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 net/rds/iw.h      |   5 +--
 net/rds/iw_rdma.c | 128 +++++++++++++++++++-----------------------------------
 net/rds/iw_send.c |  57 ++++++++++++------------
 3 files changed, 75 insertions(+), 115 deletions(-)

diff --git a/net/rds/iw.h b/net/rds/iw.h
index fe858e5dd8d1..5af01d1758b3 100644
--- a/net/rds/iw.h
+++ b/net/rds/iw.h
@@ -74,13 +74,12 @@ struct rds_iw_send_work {
 	struct rm_rdma_op	*s_op;
 	struct rds_iw_mapping	*s_mapping;
 	struct ib_mr		*s_mr;
-	struct ib_fast_reg_page_list *s_page_list;
 	unsigned char		s_remap_count;
 
 	union {
 		struct ib_send_wr	s_send_wr;
 		struct ib_rdma_wr	s_rdma_wr;
-		struct ib_fast_reg_wr	s_fast_reg_wr;
+		struct ib_reg_wr	s_reg_wr;
 	};
 	struct ib_sge		s_sge[RDS_IW_MAX_SGE];
 	unsigned long		s_queued;
@@ -199,7 +198,7 @@ struct rds_iw_device {
 
 /* Magic WR_ID for ACKs */
 #define RDS_IW_ACK_WR_ID	((u64)0xffffffffffffffffULL)
-#define RDS_IW_FAST_REG_WR_ID	((u64)0xefefefefefefefefULL)
+#define RDS_IW_REG_WR_ID	((u64)0xefefefefefefefefULL)
 #define RDS_IW_LOCAL_INV_WR_ID	((u64)0xdfdfdfdfdfdfdfdfULL)
 
 struct rds_iw_statistics {
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index f8a612cc69e6..47bd68451ff7 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -47,7 +47,6 @@ struct rds_iw_mr {
 	struct rdma_cm_id	*cm_id;
 
 	struct ib_mr	*mr;
-	struct ib_fast_reg_page_list *page_list;
 
 	struct rds_iw_mapping	mapping;
 	unsigned char		remap_count;
@@ -77,8 +76,8 @@ struct rds_iw_mr_pool {
 
 static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all);
 static void rds_iw_mr_pool_flush_worker(struct work_struct *work);
-static int rds_iw_init_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
-static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool,
+static int rds_iw_init_reg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
+static int rds_iw_map_reg(struct rds_iw_mr_pool *pool,
 			  struct rds_iw_mr *ibmr,
 			  struct scatterlist *sg, unsigned int nents);
 static void rds_iw_free_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
@@ -258,19 +257,18 @@ static void rds_iw_set_scatterlist(struct rds_iw_scatterlist *sg,
 	sg->bytes = 0;
 }
 
-static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev,
-			struct rds_iw_scatterlist *sg)
+static int rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev,
+				  struct rds_iw_scatterlist *sg)
 {
 	struct ib_device *dev = rds_iwdev->dev;
-	u64 *dma_pages = NULL;
-	int i, j, ret;
+	int i, ret;
 
 	WARN_ON(sg->dma_len);
 
 	sg->dma_len = ib_dma_map_sg(dev, sg->list, sg->len, DMA_BIDIRECTIONAL);
 	if (unlikely(!sg->dma_len)) {
 		printk(KERN_WARNING "RDS/IW: dma_map_sg failed!\n");
-		return ERR_PTR(-EBUSY);
+		return -EBUSY;
 	}
 
 	sg->bytes = 0;
@@ -303,31 +301,14 @@ static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev,
 	if (sg->dma_npages > fastreg_message_size)
 		goto out_unmap;
 
-	dma_pages = kmalloc(sizeof(u64) * sg->dma_npages, GFP_ATOMIC);
-	if (!dma_pages) {
-		ret = -ENOMEM;
-		goto out_unmap;
-	}
 
-	for (i = j = 0; i < sg->dma_len; ++i) {
-		unsigned int dma_len = ib_sg_dma_len(dev, &sg->list[i]);
-		u64 dma_addr = ib_sg_dma_address(dev, &sg->list[i]);
-		u64 end_addr;
 
-		end_addr = dma_addr + dma_len;
-		dma_addr &= ~PAGE_MASK;
-		for (; dma_addr < end_addr; dma_addr += PAGE_SIZE)
-			dma_pages[j++] = dma_addr;
-		BUG_ON(j > sg->dma_npages);
-	}
-
-	return dma_pages;
+	return 0;
 
 out_unmap:
 	ib_dma_unmap_sg(rds_iwdev->dev, sg->list, sg->len, DMA_BIDIRECTIONAL);
 	sg->dma_len = 0;
-	kfree(dma_pages);
-	return ERR_PTR(ret);
+	return ret;
 }
 
 
@@ -440,7 +421,7 @@ static struct rds_iw_mr *rds_iw_alloc_mr(struct rds_iw_device *rds_iwdev)
 	INIT_LIST_HEAD(&ibmr->mapping.m_list);
 	ibmr->mapping.m_mr = ibmr;
 
-	err = rds_iw_init_fastreg(pool, ibmr);
+	err = rds_iw_init_reg(pool, ibmr);
 	if (err)
 		goto out_no_cigar;
 
@@ -622,7 +603,7 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents,
 	ibmr->cm_id = cm_id;
 	ibmr->device = rds_iwdev;
 
-	ret = rds_iw_map_fastreg(rds_iwdev->mr_pool, ibmr, sg, nents);
+	ret = rds_iw_map_reg(rds_iwdev->mr_pool, ibmr, sg, nents);
 	if (ret == 0)
 		*key_ret = ibmr->mr->rkey;
 	else
@@ -638,7 +619,7 @@ out:
 }
 
 /*
- * iWARP fastreg handling
+ * iWARP reg handling
  *
  * The life cycle of a fastreg registration is a bit different from
  * FMRs.
@@ -650,7 +631,7 @@ out:
  * This creates a bit of a problem for us, as we do not have the destination
  * IP in GET_MR, so the connection must be setup prior to the GET_MR call for
  * RDMA to be correctly setup.  If a fastreg request is present, rds_iw_xmit
- * will try to queue a LOCAL_INV (if needed) and a FAST_REG_MR work request
+ * will try to queue a LOCAL_INV (if needed) and a REG_MR work request
  * before queuing the SEND. When completions for these arrive, they are
  * dispatched to the MR has a bit set showing that RDMa can be performed.
  *
@@ -659,11 +640,10 @@ out:
  * The expectation there is that this invalidation step includes ALL
  * PREVIOUSLY FREED MRs.
  */
-static int rds_iw_init_fastreg(struct rds_iw_mr_pool *pool,
-				struct rds_iw_mr *ibmr)
+static int rds_iw_init_reg(struct rds_iw_mr_pool *pool,
+			   struct rds_iw_mr *ibmr)
 {
 	struct rds_iw_device *rds_iwdev = pool->device;
-	struct ib_fast_reg_page_list *page_list = NULL;
 	struct ib_mr *mr;
 	int err;
 
@@ -676,56 +656,44 @@ static int rds_iw_init_fastreg(struct rds_iw_mr_pool *pool,
 		return err;
 	}
 
-	/* FIXME - this is overkill, but mapping->m_sg.dma_len/mapping->m_sg.dma_npages
-	 * is not filled in.
-	 */
-	page_list = ib_alloc_fast_reg_page_list(rds_iwdev->dev, pool->max_message_size);
-	if (IS_ERR(page_list)) {
-		err = PTR_ERR(page_list);
-
-		printk(KERN_WARNING "RDS/IW: ib_alloc_fast_reg_page_list failed (err=%d)\n", err);
-		ib_dereg_mr(mr);
-		return err;
-	}
-
-	ibmr->page_list = page_list;
 	ibmr->mr = mr;
 	return 0;
 }
 
-static int rds_iw_rdma_build_fastreg(struct rds_iw_mapping *mapping)
+static int rds_iw_rdma_reg_mr(struct rds_iw_mapping *mapping)
 {
 	struct rds_iw_mr *ibmr = mapping->m_mr;
-	struct ib_fast_reg_wr f_wr;
+	struct rds_iw_scatterlist *m_sg = &mapping->m_sg;
+	struct ib_reg_wr reg_wr;
 	struct ib_send_wr *failed_wr;
-	int ret;
+	int ret, n;
+
+	n = ib_map_mr_sg_zbva(ibmr->mr, m_sg->list, m_sg->len, PAGE_SIZE);
+	if (unlikely(n != m_sg->len))
+		return n < 0 ? n : -EINVAL;
+
+	reg_wr.wr.next = NULL;
+	reg_wr.wr.opcode = IB_WR_REG_MR;
+	reg_wr.wr.wr_id = RDS_IW_REG_WR_ID;
+	reg_wr.wr.num_sge = 0;
+	reg_wr.mr = ibmr->mr;
+	reg_wr.key = mapping->m_rkey;
+	reg_wr.access = IB_ACCESS_LOCAL_WRITE |
+			IB_ACCESS_REMOTE_READ |
+			IB_ACCESS_REMOTE_WRITE;
 
 	/*
-	 * Perform a WR for the fast_reg_mr. Each individual page
+	 * Perform a WR for the reg_mr. Each individual page
 	 * in the sg list is added to the fast reg page list and placed
-	 * inside the fast_reg_mr WR.  The key used is a rolling 8bit
+	 * inside the reg_mr WR.  The key used is a rolling 8bit
 	 * counter, which should guarantee uniqueness.
 	 */
 	ib_update_fast_reg_key(ibmr->mr, ibmr->remap_count++);
 	mapping->m_rkey = ibmr->mr->rkey;
 
-	memset(&f_wr, 0, sizeof(f_wr));
-	f_wr.wr.wr_id = RDS_IW_FAST_REG_WR_ID;
-	f_wr.wr.opcode = IB_WR_FAST_REG_MR;
-	f_wr.length = mapping->m_sg.bytes;
-	f_wr.rkey = mapping->m_rkey;
-	f_wr.page_list = ibmr->page_list;
-	f_wr.page_list_len = mapping->m_sg.dma_len;
-	f_wr.page_shift = PAGE_SHIFT;
-	f_wr.access_flags = IB_ACCESS_LOCAL_WRITE |
-				IB_ACCESS_REMOTE_READ |
-				IB_ACCESS_REMOTE_WRITE;
-	f_wr.iova_start = 0;
-	f_wr.wr.send_flags = IB_SEND_SIGNALED;
-
-	failed_wr = &f_wr.wr;
-	ret = ib_post_send(ibmr->cm_id->qp, &f_wr.wr, &failed_wr);
-	BUG_ON(failed_wr != &f_wr.wr);
+	failed_wr = &reg_wr.wr;
+	ret = ib_post_send(ibmr->cm_id->qp, &reg_wr.wr, &failed_wr);
+	BUG_ON(failed_wr != &reg_wr.wr);
 	if (ret)
 		printk_ratelimited(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n",
 			__func__, __LINE__, ret);
@@ -757,21 +725,20 @@ out:
 	return ret;
 }
 
-static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool,
-			struct rds_iw_mr *ibmr,
-			struct scatterlist *sg,
-			unsigned int sg_len)
+static int rds_iw_map_reg(struct rds_iw_mr_pool *pool,
+			  struct rds_iw_mr *ibmr,
+			  struct scatterlist *sg,
+			  unsigned int sg_len)
 {
 	struct rds_iw_device *rds_iwdev = pool->device;
 	struct rds_iw_mapping *mapping = &ibmr->mapping;
 	u64 *dma_pages;
-	int i, ret = 0;
+	int ret = 0;
 
 	rds_iw_set_scatterlist(&mapping->m_sg, sg, sg_len);
 
-	dma_pages = rds_iw_map_scatterlist(rds_iwdev, &mapping->m_sg);
-	if (IS_ERR(dma_pages)) {
-		ret = PTR_ERR(dma_pages);
+	ret = rds_iw_map_scatterlist(rds_iwdev, &mapping->m_sg);
+	if (ret) {
 		dma_pages = NULL;
 		goto out;
 	}
@@ -781,10 +748,7 @@ static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool,
 		goto out;
 	}
 
-	for (i = 0; i < mapping->m_sg.dma_npages; ++i)
-		ibmr->page_list->page_list[i] = dma_pages[i];
-
-	ret = rds_iw_rdma_build_fastreg(mapping);
+	ret = rds_iw_rdma_reg_mr(mapping);
 	if (ret)
 		goto out;
 
@@ -870,8 +834,6 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool,
 		struct rds_iw_mr *ibmr)
 {
-	if (ibmr->page_list)
-		ib_free_fast_reg_page_list(ibmr->page_list);
 	if (ibmr->mr)
 		ib_dereg_mr(ibmr->mr);
 }
diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c
index f6e23c515b44..e20bd503f4bd 100644
--- a/net/rds/iw_send.c
+++ b/net/rds/iw_send.c
@@ -159,13 +159,6 @@ void rds_iw_send_init_ring(struct rds_iw_connection *ic)
 			printk(KERN_WARNING "RDS/IW: ib_alloc_mr failed\n");
 			break;
 		}
-
-		send->s_page_list = ib_alloc_fast_reg_page_list(
-			ic->i_cm_id->device, fastreg_message_size);
-		if (IS_ERR(send->s_page_list)) {
-			printk(KERN_WARNING "RDS/IW: ib_alloc_fast_reg_page_list failed\n");
-			break;
-		}
 	}
 }
 
@@ -177,8 +170,6 @@ void rds_iw_send_clear_ring(struct rds_iw_connection *ic)
 	for (i = 0, send = ic->i_sends; i < ic->i_send_ring.w_nr; i++, send++) {
 		BUG_ON(!send->s_mr);
 		ib_dereg_mr(send->s_mr);
-		BUG_ON(!send->s_page_list);
-		ib_free_fast_reg_page_list(send->s_page_list);
 		if (send->s_send_wr.opcode == 0xdead)
 			continue;
 		if (send->s_rm)
@@ -227,7 +218,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context)
 			continue;
 		}
 
-		if (wc.opcode == IB_WC_FAST_REG_MR && wc.wr_id == RDS_IW_FAST_REG_WR_ID) {
+		if (wc.opcode == IB_WC_REG_MR && wc.wr_id == RDS_IW_REG_WR_ID) {
 			ic->i_fastreg_posted = 1;
 			continue;
 		}
@@ -252,7 +243,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context)
 				if (send->s_rm)
 					rds_iw_send_unmap_rm(ic, send, wc.status);
 				break;
-			case IB_WR_FAST_REG_MR:
+			case IB_WR_REG_MR:
 			case IB_WR_RDMA_WRITE:
 			case IB_WR_RDMA_READ:
 			case IB_WR_RDMA_READ_WITH_INV:
@@ -770,24 +761,26 @@ out:
 	return ret;
 }
 
-static void rds_iw_build_send_fastreg(struct rds_iw_device *rds_iwdev, struct rds_iw_connection *ic, struct rds_iw_send_work *send, int nent, int len, u64 sg_addr)
+static int rds_iw_build_send_reg(struct rds_iw_send_work *send,
+				 struct scatterlist *sg,
+				 int sg_nents)
 {
-	BUG_ON(nent > send->s_page_list->max_page_list_len);
-	/*
-	 * Perform a WR for the fast_reg_mr. Each individual page
-	 * in the sg list is added to the fast reg page list and placed
-	 * inside the fast_reg_mr WR.
-	 */
-	send->s_fast_reg_wr.wr.opcode = IB_WR_FAST_REG_MR;
-	send->s_fast_reg_wr.length = len;
-	send->s_fast_reg_wr.rkey = send->s_mr->rkey;
-	send->s_fast_reg_wr.page_list = send->s_page_list;
-	send->s_fast_reg_wr.page_list_len = nent;
-	send->s_fast_reg_wr.page_shift = PAGE_SHIFT;
-	send->s_fast_reg_wr.access_flags = IB_ACCESS_REMOTE_WRITE;
-	send->s_fast_reg_wr.iova_start = sg_addr;
+	int n;
+
+	n = ib_map_mr_sg(send->s_mr, sg, sg_nents, PAGE_SIZE);
+	if (unlikely(n != sg_nents))
+		return n < 0 ? n : -EINVAL;
+
+	send->s_reg_wr.wr.opcode = IB_WR_REG_MR;
+	send->s_reg_wr.wr.wr_id = 0;
+	send->s_reg_wr.wr.num_sge = 0;
+	send->s_reg_wr.mr = send->s_mr;
+	send->s_reg_wr.key = send->s_mr->rkey;
+	send->s_reg_wr.access = IB_ACCESS_REMOTE_WRITE;
 
 	ib_update_fast_reg_key(send->s_mr, send->s_remap_count++);
+
+	return 0;
 }
 
 int rds_iw_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
@@ -808,6 +801,7 @@ int rds_iw_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 	int sent;
 	int ret;
 	int num_sge;
+	int sg_nents;
 
 	rds_iwdev = ib_get_client_data(ic->i_cm_id->device, &rds_iw_client);
 
@@ -861,6 +855,7 @@ int rds_iw_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 	scat = &op->op_sg[0];
 	sent = 0;
 	num_sge = op->op_count;
+	sg_nents = 0;
 
 	for (i = 0; i < work_alloc && scat != &op->op_sg[op->op_count]; i++) {
 		send->s_rdma_wr.wr.send_flags = 0;
@@ -904,7 +899,7 @@ int rds_iw_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 			len = ib_sg_dma_len(ic->i_cm_id->device, scat);
 
 			if (send->s_rdma_wr.wr.opcode == IB_WR_RDMA_READ_WITH_INV)
-				send->s_page_list->page_list[j] = ib_sg_dma_address(ic->i_cm_id->device, scat);
+				sg_nents++;
 			else {
 				send->s_sge[j].addr = ib_sg_dma_address(ic->i_cm_id->device, scat);
 				send->s_sge[j].length = len;
@@ -951,8 +946,12 @@ int rds_iw_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 	 * fastreg_mr (or possibly a dma_mr)
 	 */
 	if (!op->op_write) {
-		rds_iw_build_send_fastreg(rds_iwdev, ic, &ic->i_sends[fr_pos],
-			op->op_count, sent, conn->c_xmit_rm->m_rs->rs_user_addr);
+		ret = rds_iw_build_send_reg(&ic->i_sends[fr_pos],
+					    &op->op_sg[0], sg_nents);
+		if (ret) {
+			printk(KERN_WARNING "RDS/IW: failed to reg send mem\n");
+			goto out;
+		}
 		work_alloc++;
 	}
 
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 15/26] IB/srp: Split srp_map_sg

[Sagi Grimberg]

This is a perparation patch for the new registration API
conversion. It splits srp_map_sg per registration strategy
(srp_map_sg[fmr|fr|dma]. On its own it adds some code duplication,
but it makes the API switch easier to comprehend.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/ulp/srp/ib_srp.c | 156 ++++++++++++++++++++++++------------
 1 file changed, 105 insertions(+), 51 deletions(-)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index f8b9c18da03d..74748d1075fc 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1286,6 +1286,17 @@ static int srp_map_finish_fmr(struct srp_map_state *state,
 	if (WARN_ON_ONCE(state->fmr.next >= state->fmr.end))
 		return -ENOMEM;
 
+	WARN_ON_ONCE(!dev->use_fmr);
+
+	if (state->npages == 0)
+		return 0;
+
+	if (state->npages == 1 && target->global_mr) {
+		srp_map_desc(state, state->base_dma_addr, state->dma_len,
+			     target->global_mr->rkey);
+		return 0;
+	}
+
 	fmr = ib_fmr_pool_map_phys(ch->fmr_pool, state->pages,
 				   state->npages, io_addr);
 	if (IS_ERR(fmr))
@@ -1297,6 +1308,9 @@ static int srp_map_finish_fmr(struct srp_map_state *state,
 	srp_map_desc(state, state->base_dma_addr & ~dev->mr_page_mask,
 		     state->dma_len, fmr->fmr->rkey);
 
+	state->npages = 0;
+	state->dma_len = 0;
+
 	return 0;
 }
 
@@ -1309,10 +1323,23 @@ static int srp_map_finish_fr(struct srp_map_state *state,
 	struct ib_fast_reg_wr wr;
 	struct srp_fr_desc *desc;
 	u32 rkey;
+	int err;
+
 
 	if (WARN_ON_ONCE(state->fr.next >= state->fr.end))
 		return -ENOMEM;
 
+	WARN_ON_ONCE(!dev->use_fast_reg);
+
+	if (state->npages == 0)
+		return 0;
+
+	if (state->npages == 1 && target->global_mr) {
+		srp_map_desc(state, state->base_dma_addr, state->dma_len,
+			     target->global_mr->rkey);
+		return 0;
+	}
+
 	desc = srp_fr_pool_get(ch->fr_pool);
 	if (!desc)
 		return -ENOMEM;
@@ -1342,7 +1369,14 @@ static int srp_map_finish_fr(struct srp_map_state *state,
 	srp_map_desc(state, state->base_dma_addr, state->dma_len,
 		     desc->mr->rkey);
 
-	return ib_post_send(ch->qp, &wr.wr, &bad_wr);
+	err = ib_post_send(ch->qp, &wr.wr, &bad_wr);
+	if (err)
+		return err;
+
+	state->npages = 0;
+	state->dma_len = 0;
+
+	return 0;
 }
 
 static int srp_finish_mapping(struct srp_map_state *state,
@@ -1350,26 +1384,9 @@ static int srp_finish_mapping(struct srp_map_state *state,
 {
 	struct srp_target_port *target = ch->target;
 	struct srp_device *dev = target->srp_host->srp_dev;
-	int ret = 0;
-
-	WARN_ON_ONCE(!dev->use_fast_reg && !dev->use_fmr);
-
-	if (state->npages == 0)
-		return 0;
 
-	if (state->npages == 1 && target->global_mr)
-		srp_map_desc(state, state->base_dma_addr, state->dma_len,
-			     target->global_mr->rkey);
-	else
-		ret = dev->use_fast_reg ? srp_map_finish_fr(state, ch) :
-			srp_map_finish_fmr(state, ch);
-
-	if (ret == 0) {
-		state->npages = 0;
-		state->dma_len = 0;
-	}
-
-	return ret;
+	return dev->use_fast_reg ? srp_map_finish_fr(state, ch) :
+				   srp_map_finish_fmr(state, ch);
 }
 
 static int srp_map_sg_entry(struct srp_map_state *state,
@@ -1415,47 +1432,79 @@ static int srp_map_sg_entry(struct srp_map_state *state,
 	return ret;
 }
 
-static int srp_map_sg(struct srp_map_state *state, struct srp_rdma_ch *ch,
-		      struct srp_request *req, struct scatterlist *scat,
-		      int count)
+static int srp_map_sg_fmr(struct srp_map_state *state, struct srp_rdma_ch *ch,
+			  struct srp_request *req, struct scatterlist *scat,
+			  int count)
 {
-	struct srp_target_port *target = ch->target;
-	struct srp_device *dev = target->srp_host->srp_dev;
 	struct scatterlist *sg;
 	int i, ret;
 
-	state->desc	= req->indirect_desc;
-	state->pages	= req->map_page;
-	if (dev->use_fast_reg) {
-		state->fr.next = req->fr_list;
-		state->fr.end = req->fr_list + target->cmd_sg_cnt;
-	} else if (dev->use_fmr) {
-		state->fmr.next = req->fmr_list;
-		state->fmr.end = req->fmr_list + target->cmd_sg_cnt;
+	state->desc = req->indirect_desc;
+	state->pages = req->map_page;
+	state->fmr.next = req->fmr_list;
+	state->fmr.end = req->fmr_list + ch->target->cmd_sg_cnt;
+
+	for_each_sg(scat, sg, count, i) {
+		ret = srp_map_sg_entry(state, ch, sg, i);
+		if (ret)
+			return ret;
 	}
 
-	if (dev->use_fast_reg || dev->use_fmr) {
-		for_each_sg(scat, sg, count, i) {
-			ret = srp_map_sg_entry(state, ch, sg, i);
-			if (ret)
-				goto out;
-		}
-		ret = srp_finish_mapping(state, ch);
+	ret = srp_finish_mapping(state, ch);
+	if (ret)
+		return ret;
+
+	req->nmdesc = state->nmdesc;
+
+	return 0;
+}
+
+static int srp_map_sg_fr(struct srp_map_state *state, struct srp_rdma_ch *ch,
+			 struct srp_request *req, struct scatterlist *scat,
+			 int count)
+{
+	struct scatterlist *sg;
+	int i, ret;
+
+	state->desc = req->indirect_desc;
+	state->pages = req->map_page;
+	state->fmr.next = req->fmr_list;
+	state->fmr.end = req->fmr_list + ch->target->cmd_sg_cnt;
+
+	for_each_sg(scat, sg, count, i) {
+		ret = srp_map_sg_entry(state, ch, sg, i);
 		if (ret)
-			goto out;
-	} else {
-		for_each_sg(scat, sg, count, i) {
-			srp_map_desc(state, ib_sg_dma_address(dev->dev, sg),
-				     ib_sg_dma_len(dev->dev, sg),
-				     target->global_mr->rkey);
-		}
+			return ret;
+	}
+
+	ret = srp_finish_mapping(state, ch);
+	if (ret)
+		return ret;
+
+	req->nmdesc = state->nmdesc;
+
+	return 0;
+}
+
+static int srp_map_sg_dma(struct srp_map_state *state, struct srp_rdma_ch *ch,
+			  struct srp_request *req, struct scatterlist *scat,
+			  int count)
+{
+	struct srp_target_port *target = ch->target;
+	struct srp_device *dev = target->srp_host->srp_dev;
+	struct scatterlist *sg;
+	int i;
+
+	state->desc = req->indirect_desc;
+	for_each_sg(scat, sg, count, i) {
+		srp_map_desc(state, ib_sg_dma_address(dev->dev, sg),
+			     ib_sg_dma_len(dev->dev, sg),
+			     target->global_mr->rkey);
 	}
 
 	req->nmdesc = state->nmdesc;
-	ret = 0;
 
-out:
-	return ret;
+	return 0;
 }
 
 /*
@@ -1563,7 +1612,12 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
 				   target->indirect_size, DMA_TO_DEVICE);
 
 	memset(&state, 0, sizeof(state));
-	srp_map_sg(&state, ch, req, scat, count);
+	if (dev->use_fast_reg)
+		srp_map_sg_fr(&state, ch, req, scat, count);
+	else if (dev->use_fmr)
+		srp_map_sg_fmr(&state, ch, req, scat, count);
+	else
+		srp_map_sg_dma(&state, ch, req, scat, count);
 
 	/* We've mapped the request, now pull as much of the indirect
 	 * descriptor table as we can into the command buffer. If this
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 16/26] IB/srp: Convert to new registration API

[Sagi Grimberg]

Instead of constructing a page list, call ib_map_mr_sg
and post a new ib_reg_wr. srp_map_finish_fr now returns
the number of sg elements registered.

Remove srp_finish_mapping since no one is calling it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/ulp/srp/ib_srp.c | 135 +++++++++++++++++-------------------
 drivers/infiniband/ulp/srp/ib_srp.h |  11 ++-
 2 files changed, 71 insertions(+), 75 deletions(-)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 74748d1075fc..8b3cbf9b6f40 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -340,8 +340,6 @@ static void srp_destroy_fr_pool(struct srp_fr_pool *pool)
 		return;
 
 	for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) {
-		if (d->frpl)
-			ib_free_fast_reg_page_list(d->frpl);
 		if (d->mr)
 			ib_dereg_mr(d->mr);
 	}
@@ -362,7 +360,6 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device,
 	struct srp_fr_pool *pool;
 	struct srp_fr_desc *d;
 	struct ib_mr *mr;
-	struct ib_fast_reg_page_list *frpl;
 	int i, ret = -EINVAL;
 
 	if (pool_size <= 0)
@@ -385,12 +382,6 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device,
 			goto destroy_pool;
 		}
 		d->mr = mr;
-		frpl = ib_alloc_fast_reg_page_list(device, max_page_list_len);
-		if (IS_ERR(frpl)) {
-			ret = PTR_ERR(frpl);
-			goto destroy_pool;
-		}
-		d->frpl = frpl;
 		list_add_tail(&d->entry, &pool->free_list);
 	}
 
@@ -1320,24 +1311,24 @@ static int srp_map_finish_fr(struct srp_map_state *state,
 	struct srp_target_port *target = ch->target;
 	struct srp_device *dev = target->srp_host->srp_dev;
 	struct ib_send_wr *bad_wr;
-	struct ib_fast_reg_wr wr;
+	struct ib_reg_wr wr;
 	struct srp_fr_desc *desc;
 	u32 rkey;
-	int err;
-
+	int n, err;
 
 	if (WARN_ON_ONCE(state->fr.next >= state->fr.end))
 		return -ENOMEM;
 
 	WARN_ON_ONCE(!dev->use_fast_reg);
 
-	if (state->npages == 0)
+	if (state->sg_nents == 0)
 		return 0;
 
-	if (state->npages == 1 && target->global_mr) {
-		srp_map_desc(state, state->base_dma_addr, state->dma_len,
+	if (state->sg_nents == 1 && target->global_mr) {
+		srp_map_desc(state, sg_dma_address(state->sg),
+			     sg_dma_len(state->sg),
 			     target->global_mr->rkey);
-		return 0;
+		return 1;
 	}
 
 	desc = srp_fr_pool_get(ch->fr_pool);
@@ -1347,46 +1338,33 @@ static int srp_map_finish_fr(struct srp_map_state *state,
 	rkey = ib_inc_rkey(desc->mr->rkey);
 	ib_update_fast_reg_key(desc->mr, rkey);
 
-	memcpy(desc->frpl->page_list, state->pages,
-	       sizeof(state->pages[0]) * state->npages);
+	n = ib_map_mr_sg(desc->mr, state->sg, state->sg_nents,
+			 dev->mr_page_size);
+	if (unlikely(n < 0))
+		return n;
 
-	memset(&wr, 0, sizeof(wr));
-	wr.wr.opcode = IB_WR_FAST_REG_MR;
+	wr.wr.next = NULL;
+	wr.wr.opcode = IB_WR_REG_MR;
 	wr.wr.wr_id = FAST_REG_WR_ID_MASK;
-	wr.iova_start = state->base_dma_addr;
-	wr.page_list = desc->frpl;
-	wr.page_list_len = state->npages;
-	wr.page_shift = ilog2(dev->mr_page_size);
-	wr.length = state->dma_len;
-	wr.access_flags = (IB_ACCESS_LOCAL_WRITE |
-			   IB_ACCESS_REMOTE_READ |
-			   IB_ACCESS_REMOTE_WRITE);
-	wr.rkey = desc->mr->lkey;
+	wr.wr.num_sge = 0;
+	wr.wr.send_flags = 0;
+	wr.mr = desc->mr;
+	wr.key = desc->mr->rkey;
+	wr.access = (IB_ACCESS_LOCAL_WRITE |
+		     IB_ACCESS_REMOTE_READ |
+		     IB_ACCESS_REMOTE_WRITE);
 
 	*state->fr.next++ = desc;
 	state->nmdesc++;
 
-	srp_map_desc(state, state->base_dma_addr, state->dma_len,
-		     desc->mr->rkey);
+	srp_map_desc(state, desc->mr->iova,
+		     desc->mr->length, desc->mr->rkey);
 
 	err = ib_post_send(ch->qp, &wr.wr, &bad_wr);
-	if (err)
+	if (unlikely(err))
 		return err;
 
-	state->npages = 0;
-	state->dma_len = 0;
-
-	return 0;
-}
-
-static int srp_finish_mapping(struct srp_map_state *state,
-			      struct srp_rdma_ch *ch)
-{
-	struct srp_target_port *target = ch->target;
-	struct srp_device *dev = target->srp_host->srp_dev;
-
-	return dev->use_fast_reg ? srp_map_finish_fr(state, ch) :
-				   srp_map_finish_fmr(state, ch);
+	return n;
 }
 
 static int srp_map_sg_entry(struct srp_map_state *state,
@@ -1406,7 +1384,7 @@ static int srp_map_sg_entry(struct srp_map_state *state,
 	while (dma_len) {
 		unsigned offset = dma_addr & ~dev->mr_page_mask;
 		if (state->npages == dev->max_pages_per_mr || offset != 0) {
-			ret = srp_finish_mapping(state, ch);
+			ret = srp_map_finish_fmr(state, ch);
 			if (ret)
 				return ret;
 		}
@@ -1428,7 +1406,7 @@ static int srp_map_sg_entry(struct srp_map_state *state,
 	 */
 	ret = 0;
 	if (len != dev->mr_page_size)
-		ret = srp_finish_mapping(state, ch);
+		ret = srp_map_finish_fmr(state, ch);
 	return ret;
 }
 
@@ -1450,7 +1428,7 @@ static int srp_map_sg_fmr(struct srp_map_state *state, struct srp_rdma_ch *ch,
 			return ret;
 	}
 
-	ret = srp_finish_mapping(state, ch);
+	ret = srp_map_finish_fmr(state, ch);
 	if (ret)
 		return ret;
 
@@ -1463,23 +1441,23 @@ static int srp_map_sg_fr(struct srp_map_state *state, struct srp_rdma_ch *ch,
 			 struct srp_request *req, struct scatterlist *scat,
 			 int count)
 {
-	struct scatterlist *sg;
-	int i, ret;
-
 	state->desc = req->indirect_desc;
-	state->pages = req->map_page;
-	state->fmr.next = req->fmr_list;
-	state->fmr.end = req->fmr_list + ch->target->cmd_sg_cnt;
+	state->fr.next = req->fr_list;
+	state->fr.end = req->fr_list + ch->target->cmd_sg_cnt;
+	state->sg = scat;
+	state->sg_nents = scsi_sg_count(req->scmnd);
 
-	for_each_sg(scat, sg, count, i) {
-		ret = srp_map_sg_entry(state, ch, sg, i);
-		if (ret)
-			return ret;
-	}
+	while (state->sg_nents) {
+		int i, n;
 
-	ret = srp_finish_mapping(state, ch);
-	if (ret)
-		return ret;
+		n = srp_map_finish_fr(state, ch);
+		if (unlikely(n < 0))
+			return n;
+
+		state->sg_nents -= n;
+		for (i = 0; i < n; i++)
+			state->sg = sg_next(state->sg);
+	}
 
 	req->nmdesc = state->nmdesc;
 
@@ -1523,6 +1501,7 @@ static int srp_map_idb(struct srp_rdma_ch *ch, struct srp_request *req,
 	struct srp_map_state state;
 	struct srp_direct_buf idb_desc;
 	u64 idb_pages[1];
+	struct scatterlist idb_sg[1];
 	int ret;
 
 	memset(&state, 0, sizeof(state));
@@ -1530,20 +1509,32 @@ static int srp_map_idb(struct srp_rdma_ch *ch, struct srp_request *req,
 	state.gen.next = next_mr;
 	state.gen.end = end_mr;
 	state.desc = &idb_desc;
-	state.pages = idb_pages;
-	state.pages[0] = (req->indirect_dma_addr &
-			  dev->mr_page_mask);
-	state.npages = 1;
 	state.base_dma_addr = req->indirect_dma_addr;
 	state.dma_len = idb_len;
-	ret = srp_finish_mapping(&state, ch);
-	if (ret < 0)
-		goto out;
+
+	if (dev->use_fast_reg) {
+		state.sg = idb_sg;
+		state.sg_nents = 1;
+		sg_set_buf(idb_sg, req->indirect_desc, idb_len);
+		idb_sg->dma_address = req->indirect_dma_addr; /* hack! */
+		ret = srp_map_finish_fr(&state, ch);
+		if (ret < 0)
+			return ret;
+	} else if (dev->use_fmr) {
+		state.pages = idb_pages;
+		state.pages[0] = (req->indirect_dma_addr &
+				  dev->mr_page_mask);
+		state.npages = 1;
+		ret = srp_map_finish_fmr(&state, ch);
+		if (ret < 0)
+			return ret;
+	} else {
+		return -EINVAL;
+	}
 
 	*idb_rkey = idb_desc.key;
 
-out:
-	return ret;
+	return 0;
 }
 
 static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 3608f2e4819c..a31a93716f3f 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -242,7 +242,6 @@ struct srp_iu {
 struct srp_fr_desc {
 	struct list_head		entry;
 	struct ib_mr			*mr;
-	struct ib_fast_reg_page_list	*frpl;
 };
 
 /**
@@ -294,11 +293,17 @@ struct srp_map_state {
 		} gen;
 	};
 	struct srp_direct_buf  *desc;
-	u64		       *pages;
+	union {
+		u64			*pages;
+		struct scatterlist	*sg;
+	};
 	dma_addr_t		base_dma_addr;
 	u32			dma_len;
 	u32			total_len;
-	unsigned int		npages;
+	union {
+		unsigned int		npages;
+		unsigned int		sg_nents;
+	};
 	unsigned int		nmdesc;
 	unsigned int		ndesc;
 };
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 17/26] IB/srp: Dont allocate a page vector when using fast_reg

[Sagi Grimberg]

The new fast registration API does not reuqire a page vector
so we can't avoid allocating it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/ulp/srp/ib_srp.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 8b3cbf9b6f40..f5a365395c23 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -840,11 +840,12 @@ static void srp_free_req_data(struct srp_target_port *target,
 
 	for (i = 0; i < target->req_ring_size; ++i) {
 		req = &ch->req_ring[i];
-		if (dev->use_fast_reg)
+		if (dev->use_fast_reg) {
 			kfree(req->fr_list);
-		else
+		} else {
 			kfree(req->fmr_list);
-		kfree(req->map_page);
+			kfree(req->map_page);
+		}
 		if (req->indirect_dma_addr) {
 			ib_dma_unmap_single(ibdev, req->indirect_dma_addr,
 					    target->indirect_size,
@@ -878,14 +879,15 @@ static int srp_alloc_req_data(struct srp_rdma_ch *ch)
 				  GFP_KERNEL);
 		if (!mr_list)
 			goto out;
-		if (srp_dev->use_fast_reg)
+		if (srp_dev->use_fast_reg) {
 			req->fr_list = mr_list;
-		else
+		} else {
 			req->fmr_list = mr_list;
-		req->map_page = kmalloc(srp_dev->max_pages_per_mr *
-					sizeof(void *), GFP_KERNEL);
-		if (!req->map_page)
-			goto out;
+			req->map_page = kmalloc(srp_dev->max_pages_per_mr *
+						sizeof(void *), GFP_KERNEL);
+			if (!req->map_page)
+				goto out;
+		}
 		req->indirect_desc = kmalloc(target->indirect_size, GFP_KERNEL);
 		if (!req->indirect_desc)
 			goto out;
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 18/26] IB/mlx5: Remove old FRWR API support

[Sagi Grimberg]

No ULP uses it anymore, go ahead and remove it.
Keep only the local invalidate part of the handlers.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/mlx5/cq.c      |  3 --
 drivers/infiniband/hw/mlx5/main.c    |  2 -
 drivers/infiniband/hw/mlx5/mlx5_ib.h | 14 ------
 drivers/infiniband/hw/mlx5/mr.c      | 42 ----------------
 drivers/infiniband/hw/mlx5/qp.c      | 97 ++++--------------------------------
 5 files changed, 9 insertions(+), 149 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 90daf791d51d..640c54ef5eed 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -111,9 +111,6 @@ static enum ib_wc_opcode get_umr_comp(struct mlx5_ib_wq *wq, int idx)
 	case IB_WR_REG_MR:
 		return IB_WC_REG_MR;
 
-	case IB_WR_FAST_REG_MR:
-		return IB_WC_FAST_REG_MR;
-
 	default:
 		pr_warn("unknown completion status\n");
 		return 0;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 7ebce545daf1..32f20d0fd632 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1433,8 +1433,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.process_mad		= mlx5_ib_process_mad;
 	dev->ib_dev.alloc_mr		= mlx5_ib_alloc_mr;
 	dev->ib_dev.map_mr_sg		= mlx5_ib_map_mr_sg;
-	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;
 	dev->ib_dev.get_port_immutable  = mlx5_port_immutable;
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bc1853f8e67d..91062d648125 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -337,12 +337,6 @@ struct mlx5_ib_mr {
 	int			live;
 };
 
-struct mlx5_ib_fast_reg_page_list {
-	struct ib_fast_reg_page_list	ibfrpl;
-	__be64			       *mapped_page_list;
-	dma_addr_t			map;
-};
-
 struct mlx5_ib_umr_context {
 	enum ib_wc_status	status;
 	struct completion	done;
@@ -493,11 +487,6 @@ static inline struct mlx5_ib_mr *to_mmr(struct ib_mr *ibmr)
 	return container_of(ibmr, struct mlx5_ib_mr, ibmr);
 }
 
-static inline struct mlx5_ib_fast_reg_page_list *to_mfrpl(struct ib_fast_reg_page_list *ibfrpl)
-{
-	return container_of(ibfrpl, struct mlx5_ib_fast_reg_page_list, ibfrpl);
-}
-
 struct mlx5_ib_ah {
 	struct ib_ah		ibah;
 	struct mlx5_av		av;
@@ -568,9 +557,6 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 int mlx5_ib_map_mr_sg(struct ib_mr *ibmr,
 		      struct scatterlist *sg,
 		      unsigned int sg_nents);
-struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
-							       int page_list_len);
-void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
 			const struct ib_mad_hdr *in, size_t in_mad_size,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index e071685e192d..580c19b9fd66 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1389,48 +1389,6 @@ err_free:
 	return ERR_PTR(err);
 }
 
-struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
-							       int page_list_len)
-{
-	struct mlx5_ib_fast_reg_page_list *mfrpl;
-	int size = page_list_len * sizeof(u64);
-
-	mfrpl = kmalloc(sizeof(*mfrpl), GFP_KERNEL);
-	if (!mfrpl)
-		return ERR_PTR(-ENOMEM);
-
-	mfrpl->ibfrpl.page_list = kmalloc(size, GFP_KERNEL);
-	if (!mfrpl->ibfrpl.page_list)
-		goto err_free;
-
-	mfrpl->mapped_page_list = dma_alloc_coherent(ibdev->dma_device,
-						     size, &mfrpl->map,
-						     GFP_KERNEL);
-	if (!mfrpl->mapped_page_list)
-		goto err_free;
-
-	WARN_ON(mfrpl->map & 0x3f);
-
-	return &mfrpl->ibfrpl;
-
-err_free:
-	kfree(mfrpl->ibfrpl.page_list);
-	kfree(mfrpl);
-	return ERR_PTR(-ENOMEM);
-}
-
-void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
-{
-	struct mlx5_ib_fast_reg_page_list *mfrpl = to_mfrpl(page_list);
-	struct mlx5_ib_dev *dev = to_mdev(page_list->device);
-	int size = page_list->max_page_list_len * sizeof(u64);
-
-	dma_free_coherent(&dev->mdev->pdev->dev, size, mfrpl->mapped_page_list,
-			  mfrpl->map);
-	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)
 {
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 61d3aa9a6ca9..96adc6f13dcb 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -64,7 +64,6 @@ static const u32 mlx5_ib_opcode[] = {
 	[IB_WR_ATOMIC_FETCH_AND_ADD]		= MLX5_OPCODE_ATOMIC_FA,
 	[IB_WR_SEND_WITH_INV]			= MLX5_OPCODE_SEND_INVAL,
 	[IB_WR_LOCAL_INV]			= MLX5_OPCODE_UMR,
-	[IB_WR_FAST_REG_MR]			= MLX5_OPCODE_UMR,
 	[IB_WR_REG_MR]				= MLX5_OPCODE_UMR,
 	[IB_WR_MASKED_ATOMIC_CMP_AND_SWP]	= MLX5_OPCODE_ATOMIC_MASKED_CS,
 	[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD]	= MLX5_OPCODE_ATOMIC_MASKED_FA,
@@ -1913,20 +1912,11 @@ static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
 	umr->mkey_mask = frwr_mkey_mask();
 }
 
-static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
-				 struct ib_send_wr *wr, int li)
+static void set_linv_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr)
 {
 	memset(umr, 0, sizeof(*umr));
-
-	if (li) {
-		umr->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
-		umr->flags = 1 << 7;
-		return;
-	}
-
-	umr->flags = (1 << 5); /* fail if not free */
-	umr->klm_octowords = get_klm_octo(fast_reg_wr(wr)->page_list_len);
-	umr->mkey_mask = frwr_mkey_mask();
+	umr->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
+	umr->flags = 1 << 7;
 }
 
 static __be64 get_umr_reg_mr_mask(void)
@@ -2020,24 +2010,10 @@ static void set_reg_mkey_seg(struct mlx5_mkey_seg *seg,
 	seg->log2_page_size = ilog2(mr->ibmr.page_size);
 }
 
-static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
-			     int li, int *writ)
+static void set_linv_mkey_seg(struct mlx5_mkey_seg *seg)
 {
 	memset(seg, 0, sizeof(*seg));
-	if (li) {
-		seg->status = MLX5_MKEY_STATUS_FREE;
-		return;
-	}
-
-	seg->flags = get_umr_flags(fast_reg_wr(wr)->access_flags) |
-		     MLX5_ACCESS_MODE_MTT;
-	*writ = seg->flags & (MLX5_PERM_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE);
-	seg->qpn_mkey7_0 = cpu_to_be32((fast_reg_wr(wr)->rkey & 0xff) | 0xffffff00);
-	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL);
-	seg->start_addr = cpu_to_be64(fast_reg_wr(wr)->iova_start);
-	seg->len = cpu_to_be64(fast_reg_wr(wr)->length);
-	seg->xlt_oct_size = cpu_to_be32((fast_reg_wr(wr)->page_list_len + 1) / 2);
-	seg->log2_page_size = fast_reg_wr(wr)->page_shift;
+	seg->status = MLX5_MKEY_STATUS_FREE;
 }
 
 static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr)
@@ -2072,24 +2048,6 @@ static void set_reg_data_seg(struct mlx5_wqe_data_seg *dseg,
 	dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
 }
 
-static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
-			   struct ib_send_wr *wr,
-			   struct mlx5_core_dev *mdev,
-			   struct mlx5_ib_pd *pd,
-			   int writ)
-{
-	struct mlx5_ib_fast_reg_page_list *mfrpl = to_mfrpl(fast_reg_wr(wr)->page_list);
-	u64 *page_list = fast_reg_wr(wr)->page_list->page_list;
-	u64 perm = MLX5_EN_RD | (writ ? MLX5_EN_WR : 0);
-	int i;
-
-	for (i = 0; i < fast_reg_wr(wr)->page_list_len; i++)
-		mfrpl->mapped_page_list[i] = cpu_to_be64(page_list[i] | perm);
-	dseg->addr = cpu_to_be64(mfrpl->map);
-	dseg->byte_count = cpu_to_be32(ALIGN(sizeof(u64) * fast_reg_wr(wr)->page_list_len, 64));
-	dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
-}
-
 static __be32 send_ieth(struct ib_send_wr *wr)
 {
 	switch (wr->opcode) {
@@ -2509,36 +2467,18 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 	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)
+static void set_linv_wr(struct mlx5_ib_qp *qp, void **seg, int *size)
 {
-	int writ = 0;
-	int li;
-
-	li = wr->opcode == IB_WR_LOCAL_INV ? 1 : 0;
-	if (unlikely(wr->send_flags & IB_SEND_INLINE))
-		return -EINVAL;
-
-	set_frwr_umr_segment(*seg, wr, li);
+	set_linv_umr_seg(*seg);
 	*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_mkey_segment(*seg, wr, li, &writ);
+	set_linv_mkey_seg(*seg);
 	*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);
-	if (!li) {
-		if (unlikely(fast_reg_wr(wr)->page_list_len >
-			     fast_reg_wr(wr)->page_list->max_page_list_len))
-			return	-ENOMEM;
-
-		set_frwr_pages(*seg, wr, mdev, pd, writ);
-		*seg += sizeof(struct mlx5_wqe_data_seg);
-		*size += (sizeof(struct mlx5_wqe_data_seg) / 16);
-	}
-	return 0;
 }
 
 static void dump_wqe(struct mlx5_ib_qp *qp, int idx, int size_16)
@@ -2654,7 +2594,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 {
 	struct mlx5_wqe_ctrl_seg *ctrl = NULL;  /* compiler warning */
 	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;
@@ -2729,25 +2668,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
 				qp->sq.wr_data[idx] = IB_WR_LOCAL_INV;
 				ctrl->imm = cpu_to_be32(wr->ex.invalidate_rkey);
-				err = set_frwr_li_wr(&seg, wr, &size, mdev, to_mpd(ibqp->pd), qp);
-				if (err) {
-					mlx5_ib_warn(dev, "\n");
-					*bad_wr = wr;
-					goto out;
-				}
-				num_sge = 0;
-				break;
-
-			case IB_WR_FAST_REG_MR:
-				next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
-				qp->sq.wr_data[idx] = IB_WR_FAST_REG_MR;
-				ctrl->imm = cpu_to_be32(fast_reg_wr(wr)->rkey);
-				err = set_frwr_li_wr(&seg, wr, &size, mdev, to_mpd(ibqp->pd), qp);
-				if (err) {
-					mlx5_ib_warn(dev, "\n");
-					*bad_wr = wr;
-					goto out;
-				}
+				set_linv_wr(qp, &seg, &size);
 				num_sge = 0;
 				break;
 
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 19/26] IB/mlx4: Remove old FRWR API support

[Sagi Grimberg]

No ULP uses it anymore, go ahead and remove it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/mlx4/cq.c      |  3 +--
 drivers/infiniband/hw/mlx4/main.c    |  2 --
 drivers/infiniband/hw/mlx4/mlx4_ib.h | 15 -----------
 drivers/infiniband/hw/mlx4/mr.c      | 48 ------------------------------------
 drivers/infiniband/hw/mlx4/qp.c      | 31 -----------------------
 5 files changed, 1 insertion(+), 98 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index b62236e24708..84ff03618e31 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -818,8 +818,7 @@ repoll:
 			wc->opcode    = IB_WC_LSO;
 			break;
 		case MLX4_OPCODE_FMR:
-			wc->opcode    = IB_WC_FAST_REG_MR;
-			/* TODO: wc->opcode    = IB_WC_REG_MR; */
+			wc->opcode    = IB_WC_REG_MR;
 			break;
 		case MLX4_OPCODE_LOCAL_INVAL:
 			wc->opcode    = IB_WC_LOCAL_INV;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index bb82f5fa1612..a25048bf9913 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2248,8 +2248,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.dereg_mr		= mlx4_ib_dereg_mr;
 	ibdev->ib_dev.alloc_mr		= mlx4_ib_alloc_mr;
 	ibdev->ib_dev.map_mr_sg		= mlx4_ib_map_mr_sg;
-	ibdev->ib_dev.alloc_fast_reg_page_list = mlx4_ib_alloc_fast_reg_page_list;
-	ibdev->ib_dev.free_fast_reg_page_list  = mlx4_ib_free_fast_reg_page_list;
 	ibdev->ib_dev.attach_mcast	= mlx4_ib_mcg_attach;
 	ibdev->ib_dev.detach_mcast	= mlx4_ib_mcg_detach;
 	ibdev->ib_dev.process_mad	= mlx4_ib_process_mad;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 07fcf3a49256..de6eab38b024 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -144,12 +144,6 @@ struct mlx4_ib_mw {
 	struct mlx4_mw		mmw;
 };
 
-struct mlx4_ib_fast_reg_page_list {
-	struct ib_fast_reg_page_list	ibfrpl;
-	__be64			       *mapped_page_list;
-	dma_addr_t			map;
-};
-
 struct mlx4_ib_fmr {
 	struct ib_fmr           ibfmr;
 	struct mlx4_fmr         mfmr;
@@ -642,11 +636,6 @@ static inline struct mlx4_ib_mw *to_mmw(struct ib_mw *ibmw)
 	return container_of(ibmw, struct mlx4_ib_mw, ibmw);
 }
 
-static inline struct mlx4_ib_fast_reg_page_list *to_mfrpl(struct ib_fast_reg_page_list *ibfrpl)
-{
-	return container_of(ibfrpl, struct mlx4_ib_fast_reg_page_list, ibfrpl);
-}
-
 static inline struct mlx4_ib_fmr *to_mfmr(struct ib_fmr *ibfmr)
 {
 	return container_of(ibfmr, struct mlx4_ib_fmr, ibfmr);
@@ -713,10 +702,6 @@ struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
 int mlx4_ib_map_mr_sg(struct ib_mr *ibmr,
 		      struct scatterlist *sg,
 		      unsigned int sg_nents);
-struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
-							       int page_list_len);
-void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
-
 int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
 struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index c361a0d52b1f..fa01f7560e08 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -437,54 +437,6 @@ err_free:
 	return ERR_PTR(err);
 }
 
-struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
-							       int page_list_len)
-{
-	struct mlx4_ib_dev *dev = to_mdev(ibdev);
-	struct mlx4_ib_fast_reg_page_list *mfrpl;
-	int size = page_list_len * sizeof (u64);
-
-	if (page_list_len > MLX4_MAX_FAST_REG_PAGES)
-		return ERR_PTR(-EINVAL);
-
-	mfrpl = kmalloc(sizeof *mfrpl, GFP_KERNEL);
-	if (!mfrpl)
-		return ERR_PTR(-ENOMEM);
-
-	mfrpl->ibfrpl.page_list = kmalloc(size, GFP_KERNEL);
-	if (!mfrpl->ibfrpl.page_list)
-		goto err_free;
-
-	mfrpl->mapped_page_list = dma_alloc_coherent(&dev->dev->persist->
-						     pdev->dev,
-						     size, &mfrpl->map,
-						     GFP_KERNEL);
-	if (!mfrpl->mapped_page_list)
-		goto err_free;
-
-	WARN_ON(mfrpl->map & 0x3f);
-
-	return &mfrpl->ibfrpl;
-
-err_free:
-	kfree(mfrpl->ibfrpl.page_list);
-	kfree(mfrpl);
-	return ERR_PTR(-ENOMEM);
-}
-
-void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
-{
-	struct mlx4_ib_dev *dev = to_mdev(page_list->device);
-	struct mlx4_ib_fast_reg_page_list *mfrpl = to_mfrpl(page_list);
-	int size = page_list->max_page_list_len * sizeof (u64);
-
-	dma_free_coherent(&dev->dev->persist->pdev->dev, size,
-			  mfrpl->mapped_page_list,
-			  mfrpl->map);
-	kfree(mfrpl->ibfrpl.page_list);
-	kfree(mfrpl);
-}
-
 struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc,
 				 struct ib_fmr_attr *fmr_attr)
 {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 850d4e9c13c5..b88a2b78ee88 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -111,7 +111,6 @@ static const __be32 mlx4_ib_opcode[] = {
 	[IB_WR_ATOMIC_FETCH_AND_ADD]		= cpu_to_be32(MLX4_OPCODE_ATOMIC_FA),
 	[IB_WR_SEND_WITH_INV]			= cpu_to_be32(MLX4_OPCODE_SEND_INVAL),
 	[IB_WR_LOCAL_INV]			= cpu_to_be32(MLX4_OPCODE_LOCAL_INVAL),
-	[IB_WR_FAST_REG_MR]			= cpu_to_be32(MLX4_OPCODE_FMR),
 	[IB_WR_REG_MR]				= cpu_to_be32(MLX4_OPCODE_FMR),
 	[IB_WR_MASKED_ATOMIC_CMP_AND_SWP]	= cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_CS),
 	[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD]	= cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA),
@@ -2422,28 +2421,6 @@ static void set_reg_seg(struct mlx4_wqe_fmr_seg *fseg,
 	fseg->reserved[1]	= 0;
 }
 
-static void set_fmr_seg(struct mlx4_wqe_fmr_seg *fseg,
-		struct ib_fast_reg_wr *wr)
-{
-	struct mlx4_ib_fast_reg_page_list *mfrpl = to_mfrpl(wr->page_list);
-	int i;
-
-	for (i = 0; i < wr->page_list_len; ++i)
-		mfrpl->mapped_page_list[i] =
-			cpu_to_be64(wr->page_list->page_list[i] |
-				    MLX4_MTT_FLAG_PRESENT);
-
-	fseg->flags		= convert_access(wr->access_flags);
-	fseg->mem_key		= cpu_to_be32(wr->rkey);
-	fseg->buf_list		= cpu_to_be64(mfrpl->map);
-	fseg->start_addr	= cpu_to_be64(wr->iova_start);
-	fseg->reg_len		= cpu_to_be64(wr->length);
-	fseg->offset		= 0; /* XXX -- is this just for ZBVA? */
-	fseg->page_size		= cpu_to_be32(wr->page_shift);
-	fseg->reserved[0]	= 0;
-	fseg->reserved[1]	= 0;
-}
-
 static void set_bind_seg(struct mlx4_wqe_bind_seg *bseg,
 		struct ib_bind_mw_wr *wr)
 {
@@ -2775,14 +2752,6 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				size += sizeof (struct mlx4_wqe_local_inval_seg) / 16;
 				break;
 
-			case IB_WR_FAST_REG_MR:
-				ctrl->srcrb_flags |=
-					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
-				set_fmr_seg(wqe, fast_reg_wr(wr));
-				wqe  += sizeof (struct mlx4_wqe_fmr_seg);
-				size += sizeof (struct mlx4_wqe_fmr_seg) / 16;
-				break;
-
 			case IB_WR_REG_MR:
 				ctrl->srcrb_flags |=
 					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 20/26] RDMA/ocrdma: Remove old FRWR API

[Sagi Grimberg]

No ULP uses it anymore, go ahead and remove it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/ocrdma/ocrdma_main.c  |   2 -
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 104 +---------------------------
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.h |   4 --
 3 files changed, 1 insertion(+), 109 deletions(-)

diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 874beb4b07a1..9bf430ef8eb6 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -183,8 +183,6 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
 
 	dev->ibdev.alloc_mr = ocrdma_alloc_mr;
 	dev->ibdev.map_mr_sg = ocrdma_map_mr_sg;
-	dev->ibdev.alloc_fast_reg_page_list = ocrdma_alloc_frmr_page_list;
-	dev->ibdev.free_fast_reg_page_list = ocrdma_free_frmr_page_list;
 
 	/* mandatory to support user space verbs consumer. */
 	dev->ibdev.alloc_ucontext = ocrdma_alloc_ucontext;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 66cc15a78f63..0b8598c9d56b 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -2133,41 +2133,6 @@ static void ocrdma_build_read(struct ocrdma_qp *qp, struct ocrdma_hdr_wqe *hdr,
 	ext_rw->len = hdr->total_len;
 }
 
-static void build_frmr_pbes(struct ib_fast_reg_wr *wr,
-			    struct ocrdma_pbl *pbl_tbl,
-			    struct ocrdma_hw_mr *hwmr)
-{
-	int i;
-	u64 buf_addr = 0;
-	int num_pbes;
-	struct ocrdma_pbe *pbe;
-
-	pbe = (struct ocrdma_pbe *)pbl_tbl->va;
-	num_pbes = 0;
-
-	/* go through the OS phy regions & fill hw pbe entries into pbls. */
-	for (i = 0; i < wr->page_list_len; i++) {
-		/* number of pbes can be more for one OS buf, when
-		 * buffers are of different sizes.
-		 * split the ib_buf to one or more pbes.
-		 */
-		buf_addr = wr->page_list->page_list[i];
-		pbe->pa_lo = cpu_to_le32((u32) (buf_addr & PAGE_MASK));
-		pbe->pa_hi = cpu_to_le32((u32) upper_32_bits(buf_addr));
-		num_pbes += 1;
-		pbe++;
-
-		/* if the pbl is full storing the pbes,
-		 * move to next pbl.
-		*/
-		if (num_pbes == (hwmr->pbl_size/sizeof(u64))) {
-			pbl_tbl++;
-			pbe = (struct ocrdma_pbe *)pbl_tbl->va;
-		}
-	}
-	return;
-}
-
 static int get_encoded_page_size(int pg_sz)
 {
 	/* Max size is 256M 4096 << 16 */
@@ -2234,50 +2199,6 @@ static int ocrdma_build_reg(struct ocrdma_qp *qp,
 	return 0;
 }
 
-static int ocrdma_build_fr(struct ocrdma_qp *qp, struct ocrdma_hdr_wqe *hdr,
-			   struct ib_send_wr *send_wr)
-{
-	u64 fbo;
-	struct ib_fast_reg_wr *wr = fast_reg_wr(send_wr);
-	struct ocrdma_ewqe_fr *fast_reg = (struct ocrdma_ewqe_fr *)(hdr + 1);
-	struct ocrdma_mr *mr;
-	struct ocrdma_dev *dev = get_ocrdma_dev(qp->ibqp.device);
-	u32 wqe_size = sizeof(*fast_reg) + sizeof(*hdr);
-
-	wqe_size = roundup(wqe_size, OCRDMA_WQE_ALIGN_BYTES);
-
-	if (wr->page_list_len > dev->attr.max_pages_per_frmr)
-		return -EINVAL;
-
-	hdr->cw |= (OCRDMA_FR_MR << OCRDMA_WQE_OPCODE_SHIFT);
-	hdr->cw |= ((wqe_size / OCRDMA_WQE_STRIDE) << OCRDMA_WQE_SIZE_SHIFT);
-
-	if (wr->page_list_len == 0)
-		BUG();
-	if (wr->access_flags & IB_ACCESS_LOCAL_WRITE)
-		hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_LOCAL_WR;
-	if (wr->access_flags & IB_ACCESS_REMOTE_WRITE)
-		hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_WR;
-	if (wr->access_flags & IB_ACCESS_REMOTE_READ)
-		hdr->rsvd_lkey_flags |= OCRDMA_LKEY_FLAG_REMOTE_RD;
-	hdr->lkey = wr->rkey;
-	hdr->total_len = wr->length;
-
-	fbo = wr->iova_start - (wr->page_list->page_list[0] & PAGE_MASK);
-
-	fast_reg->va_hi = upper_32_bits(wr->iova_start);
-	fast_reg->va_lo = (u32) (wr->iova_start & 0xffffffff);
-	fast_reg->fbo_hi = upper_32_bits(fbo);
-	fast_reg->fbo_lo = (u32) fbo & 0xffffffff;
-	fast_reg->num_sges = wr->page_list_len;
-	fast_reg->size_sge =
-		get_encoded_page_size(1 << wr->page_shift);
-	mr = (struct ocrdma_mr *) (unsigned long)
-		dev->stag_arr[(hdr->lkey >> 8) & (OCRDMA_MAX_STAG - 1)];
-	build_frmr_pbes(wr, mr->hwmr.pbl_table, &mr->hwmr);
-	return 0;
-}
-
 static void ocrdma_ring_sq_db(struct ocrdma_qp *qp)
 {
 	u32 val = qp->sq.dbid | (1 << OCRDMA_DB_SQ_SHIFT);
@@ -2357,9 +2278,6 @@ int ocrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				OCRDMA_WQE_STRIDE) << OCRDMA_WQE_SIZE_SHIFT;
 			hdr->lkey = wr->ex.invalidate_rkey;
 			break;
-		case IB_WR_FAST_REG_MR:
-			status = ocrdma_build_fr(qp, hdr, wr);
-			break;
 		case IB_WR_REG_MR:
 			status = ocrdma_build_reg(qp, hdr, reg_wr(wr));
 			break;
@@ -2627,7 +2545,7 @@ static void ocrdma_update_wc(struct ocrdma_qp *qp, struct ib_wc *ibwc,
 		ibwc->opcode = IB_WC_SEND;
 		break;
 	case OCRDMA_FR_MR:
-		ibwc->opcode = IB_WC_FAST_REG_MR;
+		ibwc->opcode = IB_WC_REG_MR;
 		break;
 	case OCRDMA_LKEY_INV:
 		ibwc->opcode = IB_WC_LOCAL_INV;
@@ -3153,26 +3071,6 @@ pl_err:
 	return ERR_PTR(-ENOMEM);
 }
 
-struct ib_fast_reg_page_list *ocrdma_alloc_frmr_page_list(struct ib_device
-							  *ibdev,
-							  int page_list_len)
-{
-	struct ib_fast_reg_page_list *frmr_list;
-	int size;
-
-	size = sizeof(*frmr_list) + (page_list_len * sizeof(u64));
-	frmr_list = kzalloc(size, GFP_KERNEL);
-	if (!frmr_list)
-		return ERR_PTR(-ENOMEM);
-	frmr_list->page_list = (u64 *)(frmr_list + 1);
-	return frmr_list;
-}
-
-void ocrdma_free_frmr_page_list(struct ib_fast_reg_page_list *page_list)
-{
-	kfree(page_list);
-}
-
 #define MAX_KERNEL_PBE_SIZE 65536
 static inline int count_kernel_pbes(struct ib_phys_buf *buf_list,
 				    int buf_cnt, u32 *pbe_size)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index 4edf63f9c6c7..62d6608830cb 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -128,9 +128,5 @@ struct ib_mr *ocrdma_alloc_mr(struct ib_pd *pd,
 int ocrdma_map_mr_sg(struct ib_mr *ibmr,
 		     struct scatterlist *sg,
 		     unsigned int sg_nents);
-struct ib_fast_reg_page_list *ocrdma_alloc_frmr_page_list(struct ib_device
-							*ibdev,
-							int page_list_len);
-void ocrdma_free_frmr_page_list(struct ib_fast_reg_page_list *page_list);
 
 #endif				/* __OCRDMA_VERBS_H__ */
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 21/26] RDMA/cxgb3: Remove old FRWR API

[Sagi Grimberg]

No ULP uses it anymore, go ahead and remove it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/cxgb3/iwch_cq.c       |  2 +-
 drivers/infiniband/hw/cxgb3/iwch_provider.c | 24 ---------------
 drivers/infiniband/hw/cxgb3/iwch_qp.c       | 47 -----------------------------
 3 files changed, 1 insertion(+), 72 deletions(-)

diff --git a/drivers/infiniband/hw/cxgb3/iwch_cq.c b/drivers/infiniband/hw/cxgb3/iwch_cq.c
index cf5474ae68ff..cfe404925a39 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cq.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cq.c
@@ -123,7 +123,7 @@ static int iwch_poll_cq_one(struct iwch_dev *rhp, struct iwch_cq *chp,
 			wc->opcode = IB_WC_LOCAL_INV;
 			break;
 		case T3_FAST_REGISTER:
-			wc->opcode = IB_WC_FAST_REG_MR;
+			wc->opcode = IB_WC_REG_MR;
 			break;
 		default:
 			printk(KERN_ERR MOD "Unexpected opcode %d "
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index ee3d5ca7de6c..99ae2ab14b9e 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -884,28 +884,6 @@ static int iwch_map_mr_sg(struct ib_mr *ibmr,
 	return ib_sg_to_pages(ibmr, sg, sg_nents, iwch_set_page);
 }
 
-static struct ib_fast_reg_page_list *iwch_alloc_fastreg_pbl(
-					struct ib_device *device,
-					int page_list_len)
-{
-	struct ib_fast_reg_page_list *page_list;
-
-	page_list = kmalloc(sizeof *page_list + page_list_len * sizeof(u64),
-			    GFP_KERNEL);
-	if (!page_list)
-		return ERR_PTR(-ENOMEM);
-
-	page_list->page_list = (u64 *)(page_list + 1);
-	page_list->max_page_list_len = page_list_len;
-
-	return page_list;
-}
-
-static void iwch_free_fastreg_pbl(struct ib_fast_reg_page_list *page_list)
-{
-	kfree(page_list);
-}
-
 static int iwch_destroy_qp(struct ib_qp *ib_qp)
 {
 	struct iwch_dev *rhp;
@@ -1483,8 +1461,6 @@ int iwch_register_device(struct iwch_dev *dev)
 	dev->ibdev.dealloc_mw = iwch_dealloc_mw;
 	dev->ibdev.alloc_mr = iwch_alloc_mr;
 	dev->ibdev.map_mr_sg = iwch_map_mr_sg;
-	dev->ibdev.alloc_fast_reg_page_list = iwch_alloc_fastreg_pbl;
-	dev->ibdev.free_fast_reg_page_list = iwch_free_fastreg_pbl;
 	dev->ibdev.attach_mcast = iwch_multicast_attach;
 	dev->ibdev.detach_mcast = iwch_multicast_detach;
 	dev->ibdev.process_mad = iwch_process_mad;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c
index a09ea538e990..d0548fc6395e 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_qp.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c
@@ -189,48 +189,6 @@ static int build_memreg(union t3_wr *wqe, struct ib_reg_wr *wr,
 	return 0;
 }
 
-static int build_fastreg(union t3_wr *wqe, struct ib_send_wr *send_wr,
-				u8 *flit_cnt, int *wr_cnt, struct t3_wq *wq)
-{
-	struct ib_fast_reg_wr *wr = fast_reg_wr(send_wr);
-	int i;
-	__be64 *p;
-
-	if (wr->page_list_len > T3_MAX_FASTREG_DEPTH)
-		return -EINVAL;
-	*wr_cnt = 1;
-	wqe->fastreg.stag = cpu_to_be32(wr->rkey);
-	wqe->fastreg.len = cpu_to_be32(wr->length);
-	wqe->fastreg.va_base_hi = cpu_to_be32(wr->iova_start >> 32);
-	wqe->fastreg.va_base_lo_fbo = cpu_to_be32(wr->iova_start & 0xffffffff);
-	wqe->fastreg.page_type_perms = cpu_to_be32(
-		V_FR_PAGE_COUNT(wr->page_list_len) |
-		V_FR_PAGE_SIZE(wr->page_shift-12) |
-		V_FR_TYPE(TPT_VATO) |
-		V_FR_PERMS(iwch_ib_to_tpt_access(wr->access_flags)));
-	p = &wqe->fastreg.pbl_addrs[0];
-	for (i = 0; i < wr->page_list_len; i++, p++) {
-
-		/* If we need a 2nd WR, then set it up */
-		if (i == T3_MAX_FASTREG_FRAG) {
-			*wr_cnt = 2;
-			wqe = (union t3_wr *)(wq->queue +
-				Q_PTR2IDX((wq->wptr+1), wq->size_log2));
-			build_fw_riwrh((void *)wqe, T3_WR_FASTREG, 0,
-			       Q_GENBIT(wq->wptr + 1, wq->size_log2),
-			       0, 1 + wr->page_list_len - T3_MAX_FASTREG_FRAG,
-			       T3_EOP);
-
-			p = &wqe->pbl_frag.pbl_addrs[0];
-		}
-		*p = cpu_to_be64((u64)wr->page_list->page_list[i]);
-	}
-	*flit_cnt = 5 + wr->page_list_len;
-	if (*flit_cnt > 15)
-		*flit_cnt = 15;
-	return 0;
-}
-
 static int build_inv_stag(union t3_wr *wqe, struct ib_send_wr *wr,
 				u8 *flit_cnt)
 {
@@ -457,11 +415,6 @@ int iwch_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			if (!qhp->wq.oldest_read)
 				qhp->wq.oldest_read = sqp;
 			break;
-		case IB_WR_FAST_REG_MR:
-			t3_wr_opcode = T3_WR_FASTREG;
-			err = build_fastreg(wqe, wr, &t3_wr_flit_cnt,
-						 &wr_cnt, &qhp->wq);
-			break;
 		case IB_WR_REG_MR:
 			t3_wr_opcode = T3_WR_FASTREG;
 			err = build_memreg(wqe, reg_wr(wr), &t3_wr_flit_cnt,
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 22/26] iw_cxgb4: Remove old FRWR API

[Sagi Grimberg]

No ULP uses it anymore, go ahead and remove it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/cxgb4/cq.c       |  2 +-
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 18 --------
 drivers/infiniband/hw/cxgb4/mem.c      | 45 --------------------
 drivers/infiniband/hw/cxgb4/provider.c |  2 -
 drivers/infiniband/hw/cxgb4/qp.c       | 77 ----------------------------------
 5 files changed, 1 insertion(+), 143 deletions(-)

diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index c7aab48f07cd..4f8c3ff3da5e 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -752,7 +752,7 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 			wc->opcode = IB_WC_LOCAL_INV;
 			break;
 		case FW_RI_FAST_REGISTER:
-			wc->opcode = IB_WC_FAST_REG_MR;
+			wc->opcode = IB_WC_REG_MR;
 			break;
 		default:
 			printk(KERN_ERR MOD "Unexpected opcode %d "
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 032f90aa8ac9..699c52b875b1 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -409,20 +409,6 @@ static inline struct c4iw_mw *to_c4iw_mw(struct ib_mw *ibmw)
 	return container_of(ibmw, struct c4iw_mw, ibmw);
 }
 
-struct c4iw_fr_page_list {
-	struct ib_fast_reg_page_list ibpl;
-	DEFINE_DMA_UNMAP_ADDR(mapping);
-	dma_addr_t dma_addr;
-	struct c4iw_dev *dev;
-	int pll_len;
-};
-
-static inline struct c4iw_fr_page_list *to_c4iw_fr_page_list(
-					struct ib_fast_reg_page_list *ibpl)
-{
-	return container_of(ibpl, struct c4iw_fr_page_list, ibpl);
-}
-
 struct c4iw_cq {
 	struct ib_cq ibcq;
 	struct c4iw_dev *rhp;
@@ -970,10 +956,6 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param);
 int c4iw_reject_cr(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len);
 void c4iw_qp_add_ref(struct ib_qp *qp);
 void c4iw_qp_rem_ref(struct ib_qp *qp);
-void c4iw_free_fastreg_pbl(struct ib_fast_reg_page_list *page_list);
-struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(
-					struct ib_device *device,
-					int page_list_len);
 struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 			    enum ib_mr_type mr_type,
 			    u32 max_num_sg);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 86ec65721797..ada42ed425a0 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -945,51 +945,6 @@ int c4iw_map_mr_sg(struct ib_mr *ibmr,
 	return ib_sg_to_pages(ibmr, sg, sg_nents, c4iw_set_page);
 }
 
-struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(struct ib_device *device,
-						     int page_list_len)
-{
-	struct c4iw_fr_page_list *c4pl;
-	struct c4iw_dev *dev = to_c4iw_dev(device);
-	dma_addr_t dma_addr;
-	int pll_len = roundup(page_list_len * sizeof(u64), 32);
-
-	c4pl = kmalloc(sizeof(*c4pl), GFP_KERNEL);
-	if (!c4pl)
-		return ERR_PTR(-ENOMEM);
-
-	c4pl->ibpl.page_list = dma_alloc_coherent(&dev->rdev.lldi.pdev->dev,
-						  pll_len, &dma_addr,
-						  GFP_KERNEL);
-	if (!c4pl->ibpl.page_list) {
-		kfree(c4pl);
-		return ERR_PTR(-ENOMEM);
-	}
-	dma_unmap_addr_set(c4pl, mapping, dma_addr);
-	c4pl->dma_addr = dma_addr;
-	c4pl->dev = dev;
-	c4pl->pll_len = pll_len;
-
-	PDBG("%s c4pl %p pll_len %u page_list %p dma_addr %pad\n",
-	     __func__, c4pl, c4pl->pll_len, c4pl->ibpl.page_list,
-	     &c4pl->dma_addr);
-
-	return &c4pl->ibpl;
-}
-
-void c4iw_free_fastreg_pbl(struct ib_fast_reg_page_list *ibpl)
-{
-	struct c4iw_fr_page_list *c4pl = to_c4iw_fr_page_list(ibpl);
-
-	PDBG("%s c4pl %p pll_len %u page_list %p dma_addr %pad\n",
-	     __func__, c4pl, c4pl->pll_len, c4pl->ibpl.page_list,
-	     &c4pl->dma_addr);
-
-	dma_free_coherent(&c4pl->dev->rdev.lldi.pdev->dev,
-			  c4pl->pll_len,
-			  c4pl->ibpl.page_list, dma_unmap_addr(c4pl, mapping));
-	kfree(c4pl);
-}
-
 int c4iw_dereg_mr(struct ib_mr *ib_mr)
 {
 	struct c4iw_dev *rhp;
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 55dedadcffaa..8f115b405d76 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -558,8 +558,6 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.dealloc_mw = c4iw_dealloc_mw;
 	dev->ibdev.alloc_mr = c4iw_alloc_mr;
 	dev->ibdev.map_mr_sg = c4iw_map_mr_sg;
-	dev->ibdev.alloc_fast_reg_page_list = c4iw_alloc_fastreg_pbl;
-	dev->ibdev.free_fast_reg_page_list = c4iw_free_fastreg_pbl;
 	dev->ibdev.attach_mcast = c4iw_multicast_attach;
 	dev->ibdev.detach_mcast = c4iw_multicast_detach;
 	dev->ibdev.process_mad = c4iw_process_mad;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 12a23bc935f3..c7d05a933e2d 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -670,75 +670,6 @@ static int build_memreg(struct t4_sq *sq, union t4_wr *wqe,
 	return 0;
 }
 
-static int build_fastreg(struct t4_sq *sq, union t4_wr *wqe,
-			 struct ib_send_wr *send_wr, u8 *len16, u8 t5dev)
-{
-	struct ib_fast_reg_wr *wr = fast_reg_wr(send_wr);
-
-	struct fw_ri_immd *imdp;
-	__be64 *p;
-	int i;
-	int pbllen = roundup(wr->page_list_len * sizeof(u64), 32);
-	int rem;
-
-	if (wr->page_list_len > t4_max_fr_depth(use_dsgl))
-		return -EINVAL;
-
-	wqe->fr.qpbinde_to_dcacpu = 0;
-	wqe->fr.pgsz_shift = wr->page_shift - 12;
-	wqe->fr.addr_type = FW_RI_VA_BASED_TO;
-	wqe->fr.mem_perms = c4iw_ib_to_tpt_access(wr->access_flags);
-	wqe->fr.len_hi = 0;
-	wqe->fr.len_lo = cpu_to_be32(wr->length);
-	wqe->fr.stag = cpu_to_be32(wr->rkey);
-	wqe->fr.va_hi = cpu_to_be32(wr->iova_start >> 32);
-	wqe->fr.va_lo_fbo = cpu_to_be32(wr->iova_start & 0xffffffff);
-
-	if (t5dev && use_dsgl && (pbllen > max_fr_immd)) {
-		struct c4iw_fr_page_list *c4pl =
-			to_c4iw_fr_page_list(wr->page_list);
-		struct fw_ri_dsgl *sglp;
-
-		for (i = 0; i < wr->page_list_len; i++) {
-			wr->page_list->page_list[i] = (__force u64)
-				cpu_to_be64((u64)wr->page_list->page_list[i]);
-		}
-
-		sglp = (struct fw_ri_dsgl *)(&wqe->fr + 1);
-		sglp->op = FW_RI_DATA_DSGL;
-		sglp->r1 = 0;
-		sglp->nsge = cpu_to_be16(1);
-		sglp->addr0 = cpu_to_be64(c4pl->dma_addr);
-		sglp->len0 = cpu_to_be32(pbllen);
-
-		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*sglp), 16);
-	} else {
-		imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
-		imdp->op = FW_RI_DATA_IMMD;
-		imdp->r1 = 0;
-		imdp->r2 = 0;
-		imdp->immdlen = cpu_to_be32(pbllen);
-		p = (__be64 *)(imdp + 1);
-		rem = pbllen;
-		for (i = 0; i < wr->page_list_len; i++) {
-			*p = cpu_to_be64((u64)wr->page_list->page_list[i]);
-			rem -= sizeof(*p);
-			if (++p == (__be64 *)&sq->queue[sq->size])
-				p = (__be64 *)sq->queue;
-		}
-		BUG_ON(rem < 0);
-		while (rem) {
-			*p = 0;
-			rem -= sizeof(*p);
-			if (++p == (__be64 *)&sq->queue[sq->size])
-				p = (__be64 *)sq->queue;
-		}
-		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*imdp)
-				      + pbllen, 16);
-	}
-	return 0;
-}
-
 static int build_inv_stag(union t4_wr *wqe, struct ib_send_wr *wr,
 			  u8 *len16)
 {
@@ -875,14 +806,6 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			if (!qhp->wq.sq.oldest_read)
 				qhp->wq.sq.oldest_read = swsqe;
 			break;
-		case IB_WR_FAST_REG_MR:
-			fw_opcode = FW_RI_FR_NSMR_WR;
-			swsqe->opcode = FW_RI_FAST_REGISTER;
-			err = build_fastreg(&qhp->wq.sq, wqe, wr, &len16,
-					    is_t5(
-					    qhp->rhp->rdev.lldi.adapter_type) ?
-					    1 : 0);
-			break;
 		case IB_WR_REG_MR:
 			fw_opcode = FW_RI_FR_NSMR_WR;
 			swsqe->opcode = FW_RI_FAST_REGISTER;
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 23/26] IB/qib: Remove old FRWR API

[Sagi Grimberg]

No ULP uses it anymore, go ahead and remove it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/qib/qib_keys.c  | 56 -----------------------------------
 drivers/infiniband/hw/qib/qib_mr.c    | 32 +-------------------
 drivers/infiniband/hw/qib/qib_verbs.c |  8 -----
 drivers/infiniband/hw/qib/qib_verbs.h |  7 -----
 4 files changed, 1 insertion(+), 102 deletions(-)

diff --git a/drivers/infiniband/hw/qib/qib_keys.c b/drivers/infiniband/hw/qib/qib_keys.c
index 95b8b9110fc6..d725c565518d 100644
--- a/drivers/infiniband/hw/qib/qib_keys.c
+++ b/drivers/infiniband/hw/qib/qib_keys.c
@@ -336,62 +336,6 @@ bail:
 }
 
 /*
- * Initialize the memory region specified by the work reqeust.
- */
-int qib_fast_reg_mr(struct qib_qp *qp, struct ib_send_wr *send_wr)
-{
-	struct ib_fast_reg_wr *wr = fast_reg_wr(send_wr);
-	struct qib_lkey_table *rkt = &to_idev(qp->ibqp.device)->lk_table;
-	struct qib_pd *pd = to_ipd(qp->ibqp.pd);
-	struct qib_mregion *mr;
-	u32 rkey = wr->rkey;
-	unsigned i, n, m;
-	int ret = -EINVAL;
-	unsigned long flags;
-	u64 *page_list;
-	size_t ps;
-
-	spin_lock_irqsave(&rkt->lock, flags);
-	if (pd->user || rkey == 0)
-		goto bail;
-
-	mr = rcu_dereference_protected(
-		rkt->table[(rkey >> (32 - ib_qib_lkey_table_size))],
-		lockdep_is_held(&rkt->lock));
-	if (unlikely(mr == NULL || qp->ibqp.pd != mr->pd))
-		goto bail;
-
-	if (wr->page_list_len > mr->max_segs)
-		goto bail;
-
-	ps = 1UL << wr->page_shift;
-	if (wr->length > ps * wr->page_list_len)
-		goto bail;
-
-	mr->user_base = wr->iova_start;
-	mr->iova = wr->iova_start;
-	mr->lkey = rkey;
-	mr->length = wr->length;
-	mr->access_flags = wr->access_flags;
-	page_list = wr->page_list->page_list;
-	m = 0;
-	n = 0;
-	for (i = 0; i < wr->page_list_len; i++) {
-		mr->map[m]->segs[n].vaddr = (void *) page_list[i];
-		mr->map[m]->segs[n].length = ps;
-		if (++n == QIB_SEGSZ) {
-			m++;
-			n = 0;
-		}
-	}
-
-	ret = 0;
-bail:
-	spin_unlock_irqrestore(&rkt->lock, flags);
-	return ret;
-}
-
-/*
  * Initialize the memory region specified by the work request.
  */
 int qib_reg_mr(struct qib_qp *qp, struct ib_reg_wr *wr)
diff --git a/drivers/infiniband/hw/qib/qib_mr.c b/drivers/infiniband/hw/qib/qib_mr.c
index 0fa4b0de8074..73f78c0f9522 100644
--- a/drivers/infiniband/hw/qib/qib_mr.c
+++ b/drivers/infiniband/hw/qib/qib_mr.c
@@ -324,7 +324,7 @@ out:
 
 /*
  * Allocate a memory region usable with the
- * IB_WR_FAST_REG_MR send work request.
+ * IB_WR_REG_MR send work request.
  *
  * Return the memory region on success, otherwise return an errno.
  */
@@ -375,36 +375,6 @@ int qib_map_mr_sg(struct ib_mr *ibmr,
 	return ib_sg_to_pages(ibmr, sg, sg_nents, qib_set_page);
 }
 
-struct ib_fast_reg_page_list *
-qib_alloc_fast_reg_page_list(struct ib_device *ibdev, int page_list_len)
-{
-	unsigned size = page_list_len * sizeof(u64);
-	struct ib_fast_reg_page_list *pl;
-
-	if (size > PAGE_SIZE)
-		return ERR_PTR(-EINVAL);
-
-	pl = kzalloc(sizeof(*pl), GFP_KERNEL);
-	if (!pl)
-		return ERR_PTR(-ENOMEM);
-
-	pl->page_list = kzalloc(size, GFP_KERNEL);
-	if (!pl->page_list)
-		goto err_free;
-
-	return pl;
-
-err_free:
-	kfree(pl);
-	return ERR_PTR(-ENOMEM);
-}
-
-void qib_free_fast_reg_page_list(struct ib_fast_reg_page_list *pl)
-{
-	kfree(pl->page_list);
-	kfree(pl);
-}
-
 /**
  * qib_alloc_fmr - allocate a fast memory region
  * @pd: the protection domain for this memory region
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index a1e53d7b662b..de6cb6fcda8d 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -365,9 +365,6 @@ static int qib_post_one_send(struct qib_qp *qp, struct ib_send_wr *wr,
 	if (wr->opcode == IB_WR_REG_MR) {
 		if (qib_reg_mr(qp, reg_wr(wr)))
 			goto bail_inval;
-	} else if (wr->opcode == IB_WR_FAST_REG_MR) {
-		if (qib_fast_reg_mr(qp, wr))
-			goto bail_inval;
 	} else if (qp->ibqp.qp_type == IB_QPT_UC) {
 		if ((unsigned) wr->opcode >= IB_WR_RDMA_READ)
 			goto bail_inval;
@@ -407,9 +404,6 @@ static int qib_post_one_send(struct qib_qp *qp, struct ib_send_wr *wr,
 	else if (wr->opcode == IB_WR_REG_MR)
 		memcpy(&wqe->reg_wr, reg_wr(wr),
 			sizeof(wqe->reg_wr));
-	else if (wr->opcode == IB_WR_FAST_REG_MR)
-		memcpy(&wqe->fast_reg_wr, fast_reg_wr(wr),
-			sizeof(wqe->fast_reg_wr));
 	else if (wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM ||
 		 wr->opcode == IB_WR_RDMA_WRITE ||
 		 wr->opcode == IB_WR_RDMA_READ)
@@ -2267,8 +2261,6 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	ibdev->dereg_mr = qib_dereg_mr;
 	ibdev->alloc_mr = qib_alloc_mr;
 	ibdev->map_mr_sg = qib_map_mr_sg;
-	ibdev->alloc_fast_reg_page_list = qib_alloc_fast_reg_page_list;
-	ibdev->free_fast_reg_page_list = qib_free_fast_reg_page_list;
 	ibdev->alloc_fmr = qib_alloc_fmr;
 	ibdev->map_phys_fmr = qib_map_phys_fmr;
 	ibdev->unmap_fmr = qib_unmap_fmr;
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index dbc81c5761e3..bb11fe56ac6e 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -344,7 +344,6 @@ struct qib_swqe {
 		struct ib_send_wr wr;   /* don't use wr.sg_list */
 		struct ib_ud_wr ud_wr;
 		struct ib_reg_wr reg_wr;
-		struct ib_fast_reg_wr fast_reg_wr;
 		struct ib_rdma_wr rdma_wr;
 		struct ib_atomic_wr atomic_wr;
 	};
@@ -1051,12 +1050,6 @@ int qib_map_mr_sg(struct ib_mr *ibmr,
 		  struct scatterlist *sg,
 		  unsigned int sg_nents);
 
-struct ib_fast_reg_page_list *qib_alloc_fast_reg_page_list(
-				struct ib_device *ibdev, int page_list_len);
-
-void qib_free_fast_reg_page_list(struct ib_fast_reg_page_list *pl);
-
-int qib_fast_reg_mr(struct qib_qp *qp, struct ib_send_wr *wr);
 int qib_reg_mr(struct qib_qp *qp, struct ib_reg_wr *wr);
 
 struct ib_fmr *qib_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 24/26] RDMA/nes: Remove old FRWR API

[Sagi Grimberg]

No ULP uses it anymore, go ahead and remove it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/nes/nes_hw.h    |   6 --
 drivers/infiniband/hw/nes/nes_verbs.c | 162 +---------------------------------
 2 files changed, 1 insertion(+), 167 deletions(-)

diff --git a/drivers/infiniband/hw/nes/nes_hw.h b/drivers/infiniband/hw/nes/nes_hw.h
index d748e4b31b8d..c9080208aad2 100644
--- a/drivers/infiniband/hw/nes/nes_hw.h
+++ b/drivers/infiniband/hw/nes/nes_hw.h
@@ -1200,12 +1200,6 @@ struct nes_fast_mr_wqe_pbl {
 	dma_addr_t	paddr;
 };
 
-struct nes_ib_fast_reg_page_list {
-	struct ib_fast_reg_page_list	ibfrpl;
-	struct nes_fast_mr_wqe_pbl 	nes_wqe_pbl;
-	u64 				pbl;
-};
-
 struct nes_listener {
 	struct work_struct      work;
 	struct workqueue_struct *wq;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index f5b0cc972403..c58091a6635f 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -486,76 +486,6 @@ static int nes_map_mr_sg(struct ib_mr *ibmr,
 	return ib_sg_to_pages(ibmr, sg, sg_nents, nes_set_page);
 }
 
-/*
- * nes_alloc_fast_reg_page_list
- */
-static struct ib_fast_reg_page_list *nes_alloc_fast_reg_page_list(
-							struct ib_device *ibdev,
-							int page_list_len)
-{
-	struct nes_vnic *nesvnic = to_nesvnic(ibdev);
-	struct nes_device *nesdev = nesvnic->nesdev;
-	struct ib_fast_reg_page_list *pifrpl;
-	struct nes_ib_fast_reg_page_list *pnesfrpl;
-
-	if (page_list_len > (NES_4K_PBL_CHUNK_SIZE / sizeof(u64)))
-		return ERR_PTR(-E2BIG);
-	/*
-	 * Allocate the ib_fast_reg_page_list structure, the
-	 * nes_fast_bpl structure, and the PLB table.
-	 */
-	pnesfrpl = kmalloc(sizeof(struct nes_ib_fast_reg_page_list) +
-			   page_list_len * sizeof(u64), GFP_KERNEL);
-
-	if (!pnesfrpl)
-		return ERR_PTR(-ENOMEM);
-
-	pifrpl = &pnesfrpl->ibfrpl;
-	pifrpl->page_list = &pnesfrpl->pbl;
-	pifrpl->max_page_list_len = page_list_len;
-	/*
-	 * Allocate the WQE PBL
-	 */
-	pnesfrpl->nes_wqe_pbl.kva = pci_alloc_consistent(nesdev->pcidev,
-							 page_list_len * sizeof(u64),
-							 &pnesfrpl->nes_wqe_pbl.paddr);
-
-	if (!pnesfrpl->nes_wqe_pbl.kva) {
-		kfree(pnesfrpl);
-		return ERR_PTR(-ENOMEM);
-	}
-	nes_debug(NES_DBG_MR, "nes_alloc_fast_reg_pbl: nes_frpl = %p, "
-		  "ibfrpl = %p, ibfrpl.page_list = %p, pbl.kva = %p, "
-		  "pbl.paddr = %llx\n", pnesfrpl, &pnesfrpl->ibfrpl,
-		  pnesfrpl->ibfrpl.page_list, pnesfrpl->nes_wqe_pbl.kva,
-		  (unsigned long long) pnesfrpl->nes_wqe_pbl.paddr);
-
-	return pifrpl;
-}
-
-/*
- * nes_free_fast_reg_page_list
- */
-static void nes_free_fast_reg_page_list(struct ib_fast_reg_page_list *pifrpl)
-{
-	struct nes_vnic *nesvnic = to_nesvnic(pifrpl->device);
-	struct nes_device *nesdev = nesvnic->nesdev;
-	struct nes_ib_fast_reg_page_list *pnesfrpl;
-
-	pnesfrpl = container_of(pifrpl, struct nes_ib_fast_reg_page_list, ibfrpl);
-	/*
-	 * Free the WQE PBL.
-	 */
-	pci_free_consistent(nesdev->pcidev,
-			    pifrpl->max_page_list_len * sizeof(u64),
-			    pnesfrpl->nes_wqe_pbl.kva,
-			    pnesfrpl->nes_wqe_pbl.paddr);
-	/*
-	 * Free the PBL structure
-	 */
-	kfree(pnesfrpl);
-}
-
 /**
  * nes_query_device
  */
@@ -3470,94 +3400,6 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr,
 					    NES_IWARP_SQ_LOCINV_WQE_INV_STAG_IDX,
 					    ib_wr->ex.invalidate_rkey);
 			break;
-		case IB_WR_FAST_REG_MR:
-		{
-			int i;
-			struct ib_fast_reg_wr *fwr = fast_reg_wr(ib_wr);
-			int flags = fwr->access_flags;
-			struct nes_ib_fast_reg_page_list *pnesfrpl =
-				container_of(fwr->page_list,
-					     struct nes_ib_fast_reg_page_list,
-					     ibfrpl);
-			u64 *src_page_list = pnesfrpl->ibfrpl.page_list;
-			u64 *dst_page_list = pnesfrpl->nes_wqe_pbl.kva;
-
-			if (fwr->page_list_len >
-			    (NES_4K_PBL_CHUNK_SIZE / sizeof(u64))) {
-				nes_debug(NES_DBG_IW_TX, "SQ_FMR: bad page_list_len\n");
-				err = -EINVAL;
-				break;
-			}
-			wqe_misc = NES_IWARP_SQ_OP_FAST_REG;
-			set_wqe_64bit_value(wqe->wqe_words,
-					    NES_IWARP_SQ_FMR_WQE_VA_FBO_LOW_IDX,
-					    fwr->iova_start);
-			set_wqe_32bit_value(wqe->wqe_words,
-					    NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX,
-					    fwr->length);
-			set_wqe_32bit_value(wqe->wqe_words,
-					    NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0);
-			set_wqe_32bit_value(wqe->wqe_words,
-					    NES_IWARP_SQ_FMR_WQE_MR_STAG_IDX,
-					    fwr->rkey);
-			/* Set page size: */
-			if (fwr->page_shift == 12) {
-				wqe_misc |= NES_IWARP_SQ_FMR_WQE_PAGE_SIZE_4K;
-			} else if (fwr->page_shift == 21) {
-				wqe_misc |= NES_IWARP_SQ_FMR_WQE_PAGE_SIZE_2M;
-			} else {
-				nes_debug(NES_DBG_IW_TX, "Invalid page shift,"
-					  " ib_wr=%u, max=1\n", ib_wr->num_sge);
-				err = -EINVAL;
-				break;
-			}
-			/* Set access_flags */
-			wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_LOCAL_READ;
-			if (flags & IB_ACCESS_LOCAL_WRITE)
-				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_LOCAL_WRITE;
-
-			if (flags & IB_ACCESS_REMOTE_WRITE)
-				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_REMOTE_WRITE;
-
-			if (flags & IB_ACCESS_REMOTE_READ)
-				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_REMOTE_READ;
-
-			if (flags & IB_ACCESS_MW_BIND)
-				wqe_misc |= NES_IWARP_SQ_FMR_WQE_RIGHTS_ENABLE_WINDOW_BIND;
-
-			/* Fill in PBL info: */
-			if (fwr->page_list_len >
-			    pnesfrpl->ibfrpl.max_page_list_len) {
-				nes_debug(NES_DBG_IW_TX, "Invalid page list length,"
-					  " ib_wr=%p, value=%u, max=%u\n",
-					  ib_wr, fwr->page_list_len,
-					  pnesfrpl->ibfrpl.max_page_list_len);
-				err = -EINVAL;
-				break;
-			}
-
-			set_wqe_64bit_value(wqe->wqe_words,
-					    NES_IWARP_SQ_FMR_WQE_PBL_ADDR_LOW_IDX,
-					    pnesfrpl->nes_wqe_pbl.paddr);
-
-			set_wqe_32bit_value(wqe->wqe_words,
-					    NES_IWARP_SQ_FMR_WQE_PBL_LENGTH_IDX,
-					    fwr->page_list_len * 8);
-
-			for (i = 0; i < fwr->page_list_len; i++)
-				dst_page_list[i] = cpu_to_le64(src_page_list[i]);
-
-			nes_debug(NES_DBG_IW_TX, "SQ_FMR: iova_start: %llx, "
-				  "length: %d, rkey: %0x, pgl_paddr: %llx, "
-				  "page_list_len: %u, wqe_misc: %x\n",
-				  (unsigned long long) fwr->iova_start,
-				  fwr->length,
-				  fwr->rkey,
-				  (unsigned long long) pnesfrpl->nes_wqe_pbl.paddr,
-				  fwr->page_list_len,
-				  wqe_misc);
-			break;
-		}
 		case IB_WR_REG_MR:
 		{
 			struct nes_mr *mr = to_nesmr(reg_wr(ib_wr)->mr);
@@ -3866,7 +3708,7 @@ static int nes_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 						entry->opcode = IB_WC_LOCAL_INV;
 						break;
 					case NES_IWARP_SQ_OP_FAST_REG:
-						entry->opcode = IB_WC_FAST_REG_MR;
+						entry->opcode = IB_WC_REG_MR;
 						break;
 				}
 
@@ -4055,8 +3897,6 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev)
 
 	nesibdev->ibdev.alloc_mr = nes_alloc_mr;
 	nesibdev->ibdev.map_mr_sg = nes_map_mr_sg;
-	nesibdev->ibdev.alloc_fast_reg_page_list = nes_alloc_fast_reg_page_list;
-	nesibdev->ibdev.free_fast_reg_page_list = nes_free_fast_reg_page_list;
 
 	nesibdev->ibdev.attach_mcast = nes_multicast_attach;
 	nesibdev->ibdev.detach_mcast = nes_multicast_detach;
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 25/26] IB/hfi1: Remove Old fast registraion API support

[Sagi Grimberg]

It wasn't supported before as well (post_send
returned -EINVAL for IB_WR_FAST_REG_MR). Perhaps
the new API adoption will be joint for all IB SW
implementations.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/staging/hfi1/keys.c  | 55 --------------------------------------------
 drivers/staging/hfi1/mr.c    | 32 +-------------------------
 drivers/staging/hfi1/verbs.c |  9 +-------
 drivers/staging/hfi1/verbs.h |  8 -------
 4 files changed, 2 insertions(+), 102 deletions(-)

diff --git a/drivers/staging/hfi1/keys.c b/drivers/staging/hfi1/keys.c
index 82c21b1c0263..cb4e6087dfdb 100644
--- a/drivers/staging/hfi1/keys.c
+++ b/drivers/staging/hfi1/keys.c
@@ -354,58 +354,3 @@ bail:
 	rcu_read_unlock();
 	return 0;
 }
-
-/*
- * Initialize the memory region specified by the work request.
- */
-int hfi1_fast_reg_mr(struct hfi1_qp *qp, struct ib_fast_reg_wr *wr)
-{
-	struct hfi1_lkey_table *rkt = &to_idev(qp->ibqp.device)->lk_table;
-	struct hfi1_pd *pd = to_ipd(qp->ibqp.pd);
-	struct hfi1_mregion *mr;
-	u32 rkey = wr->rkey;
-	unsigned i, n, m;
-	int ret = -EINVAL;
-	unsigned long flags;
-	u64 *page_list;
-	size_t ps;
-
-	spin_lock_irqsave(&rkt->lock, flags);
-	if (pd->user || rkey == 0)
-		goto bail;
-
-	mr = rcu_dereference_protected(
-		rkt->table[(rkey >> (32 - hfi1_lkey_table_size))],
-		lockdep_is_held(&rkt->lock));
-	if (unlikely(mr == NULL || qp->ibqp.pd != mr->pd))
-		goto bail;
-
-	if (wr->page_list_len > mr->max_segs)
-		goto bail;
-
-	ps = 1UL << wr->page_shift;
-	if (wr->length > ps * wr->page_list_len)
-		goto bail;
-
-	mr->user_base = wr->iova_start;
-	mr->iova = wr->iova_start;
-	mr->lkey = rkey;
-	mr->length = wr->length;
-	mr->access_flags = wr->access_flags;
-	page_list = wr->page_list->page_list;
-	m = 0;
-	n = 0;
-	for (i = 0; i < wr->page_list_len; i++) {
-		mr->map[m]->segs[n].vaddr = (void *) page_list[i];
-		mr->map[m]->segs[n].length = ps;
-		if (++n == HFI1_SEGSZ) {
-			m++;
-			n = 0;
-		}
-	}
-
-	ret = 0;
-bail:
-	spin_unlock_irqrestore(&rkt->lock, flags);
-	return ret;
-}
diff --git a/drivers/staging/hfi1/mr.c b/drivers/staging/hfi1/mr.c
index bd64e4f986f9..3f5623add3df 100644
--- a/drivers/staging/hfi1/mr.c
+++ b/drivers/staging/hfi1/mr.c
@@ -344,7 +344,7 @@ out:
 
 /*
  * Allocate a memory region usable with the
- * IB_WR_FAST_REG_MR send work request.
+ * IB_WR_REG_MR send work request.
  *
  * Return the memory region on success, otherwise return an errno.
  */
@@ -364,36 +364,6 @@ struct ib_mr *hfi1_alloc_mr(struct ib_pd *pd,
 	return &mr->ibmr;
 }
 
-struct ib_fast_reg_page_list *
-hfi1_alloc_fast_reg_page_list(struct ib_device *ibdev, int page_list_len)
-{
-	unsigned size = page_list_len * sizeof(u64);
-	struct ib_fast_reg_page_list *pl;
-
-	if (size > PAGE_SIZE)
-		return ERR_PTR(-EINVAL);
-
-	pl = kzalloc(sizeof(*pl), GFP_KERNEL);
-	if (!pl)
-		return ERR_PTR(-ENOMEM);
-
-	pl->page_list = kzalloc(size, GFP_KERNEL);
-	if (!pl->page_list)
-		goto err_free;
-
-	return pl;
-
-err_free:
-	kfree(pl);
-	return ERR_PTR(-ENOMEM);
-}
-
-void hfi1_free_fast_reg_page_list(struct ib_fast_reg_page_list *pl)
-{
-	kfree(pl->page_list);
-	kfree(pl);
-}
-
 /**
  * hfi1_alloc_fmr - allocate a fast memory region
  * @pd: the protection domain for this memory region
diff --git a/drivers/staging/hfi1/verbs.c b/drivers/staging/hfi1/verbs.c
index 542ad803bfce..a6c9bf88a4c4 100644
--- a/drivers/staging/hfi1/verbs.c
+++ b/drivers/staging/hfi1/verbs.c
@@ -380,9 +380,7 @@ static int post_one_send(struct hfi1_qp *qp, struct ib_send_wr *wr)
 	 * undefined operations.
 	 * Make sure buffer is large enough to hold the result for atomics.
 	 */
-	if (wr->opcode == IB_WR_FAST_REG_MR) {
-		return -EINVAL;
-	} else if (qp->ibqp.qp_type == IB_QPT_UC) {
+	if (qp->ibqp.qp_type == IB_QPT_UC) {
 		if ((unsigned) wr->opcode >= IB_WR_RDMA_READ)
 			return -EINVAL;
 	} else if (qp->ibqp.qp_type != IB_QPT_RC) {
@@ -417,9 +415,6 @@ static int post_one_send(struct hfi1_qp *qp, struct ib_send_wr *wr)
 	if (qp->ibqp.qp_type != IB_QPT_UC &&
 	    qp->ibqp.qp_type != IB_QPT_RC)
 		memcpy(&wqe->ud_wr, ud_wr(wr), sizeof(wqe->ud_wr));
-	else if (wr->opcode == IB_WR_FAST_REG_MR)
-		memcpy(&wqe->fast_reg_wr, fast_reg_wr(wr),
-			sizeof(wqe->fast_reg_wr));
 	else if (wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM ||
 		 wr->opcode == IB_WR_RDMA_WRITE ||
 		 wr->opcode == IB_WR_RDMA_READ)
@@ -2063,8 +2058,6 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	ibdev->reg_user_mr = hfi1_reg_user_mr;
 	ibdev->dereg_mr = hfi1_dereg_mr;
 	ibdev->alloc_mr = hfi1_alloc_mr;
-	ibdev->alloc_fast_reg_page_list = hfi1_alloc_fast_reg_page_list;
-	ibdev->free_fast_reg_page_list = hfi1_free_fast_reg_page_list;
 	ibdev->alloc_fmr = hfi1_alloc_fmr;
 	ibdev->map_phys_fmr = hfi1_map_phys_fmr;
 	ibdev->unmap_fmr = hfi1_unmap_fmr;
diff --git a/drivers/staging/hfi1/verbs.h b/drivers/staging/hfi1/verbs.h
index cf5a3c956284..159ec08bfcd8 100644
--- a/drivers/staging/hfi1/verbs.h
+++ b/drivers/staging/hfi1/verbs.h
@@ -353,7 +353,6 @@ struct hfi1_swqe {
 		struct ib_rdma_wr rdma_wr;
 		struct ib_atomic_wr atomic_wr;
 		struct ib_ud_wr ud_wr;
-		struct ib_fast_reg_wr fast_reg_wr;
 	};
 	u32 psn;                /* first packet sequence number */
 	u32 lpsn;               /* last packet sequence number */
@@ -1026,13 +1025,6 @@ struct ib_mr *hfi1_alloc_mr(struct ib_pd *pd,
 			    enum ib_mr_type mr_type,
 			    u32 max_entries);
 
-struct ib_fast_reg_page_list *hfi1_alloc_fast_reg_page_list(
-				struct ib_device *ibdev, int page_list_len);
-
-void hfi1_free_fast_reg_page_list(struct ib_fast_reg_page_list *pl);
-
-int hfi1_fast_reg_mr(struct hfi1_qp *qp, struct ib_fast_reg_wr *wr);
-
 struct ib_fmr *hfi1_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
 			      struct ib_fmr_attr *fmr_attr);
 
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 26/26] IB/core: Remove old fast registration API

[Sagi Grimberg]

No callers and no providers left, go ahead and remove it.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/core/verbs.c | 25 -------------------
 include/rdma/ib_verbs.h         | 54 -----------------------------------------
 2 files changed, 79 deletions(-)

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index b84d168f6e21..e0368fcf5fdb 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1253,31 +1253,6 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
 }
 EXPORT_SYMBOL(ib_alloc_mr);
 
-struct ib_fast_reg_page_list *ib_alloc_fast_reg_page_list(struct ib_device *device,
-							  int max_page_list_len)
-{
-	struct ib_fast_reg_page_list *page_list;
-
-	if (!device->alloc_fast_reg_page_list)
-		return ERR_PTR(-ENOSYS);
-
-	page_list = device->alloc_fast_reg_page_list(device, max_page_list_len);
-
-	if (!IS_ERR(page_list)) {
-		page_list->device = device;
-		page_list->max_page_list_len = max_page_list_len;
-	}
-
-	return page_list;
-}
-EXPORT_SYMBOL(ib_alloc_fast_reg_page_list);
-
-void ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
-{
-	page_list->device->free_fast_reg_page_list(page_list);
-}
-EXPORT_SYMBOL(ib_free_fast_reg_page_list);
-
 /* Memory windows */
 
 struct ib_mw *ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index f9a3436702c8..c1b5bfa66b84 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -736,7 +736,6 @@ enum ib_wc_opcode {
 	IB_WC_BIND_MW,
 	IB_WC_LSO,
 	IB_WC_LOCAL_INV,
-	IB_WC_FAST_REG_MR,
 	IB_WC_REG_MR,
 	IB_WC_MASKED_COMP_SWAP,
 	IB_WC_MASKED_FETCH_ADD,
@@ -1029,7 +1028,6 @@ enum ib_wr_opcode {
 	IB_WR_SEND_WITH_INV,
 	IB_WR_RDMA_READ_WITH_INV,
 	IB_WR_LOCAL_INV,
-	IB_WR_FAST_REG_MR,
 	IB_WR_REG_MR,
 	IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
 	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
@@ -1068,12 +1066,6 @@ struct ib_sge {
 	u32	lkey;
 };
 
-struct ib_fast_reg_page_list {
-	struct ib_device       *device;
-	u64		       *page_list;
-	unsigned int		max_page_list_len;
-};
-
 /**
  * struct ib_mw_bind_info - Parameters for a memory window bind operation.
  * @mr: A memory region to bind the memory window to.
@@ -1147,22 +1139,6 @@ static inline struct ib_ud_wr *ud_wr(struct ib_send_wr *wr)
 	return container_of(wr, struct ib_ud_wr, wr);
 }
 
-struct ib_fast_reg_wr {
-	struct ib_send_wr	wr;
-	u64			iova_start;
-	struct ib_fast_reg_page_list *page_list;
-	unsigned int		page_shift;
-	unsigned int		page_list_len;
-	u32			length;
-	int			access_flags;
-	u32			rkey;
-};
-
-static inline struct ib_fast_reg_wr *fast_reg_wr(struct ib_send_wr *wr)
-{
-	return container_of(wr, struct ib_fast_reg_wr, wr);
-}
-
 struct ib_reg_wr {
 	struct ib_send_wr	wr;
 	struct ib_mr		*mr;
@@ -1777,9 +1753,6 @@ struct ib_device {
 	int                        (*map_mr_sg)(struct ib_mr *mr,
 						struct scatterlist *sg,
 						unsigned int sg_nents);
-	struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device,
-								   int page_list_len);
-	void			   (*free_fast_reg_page_list)(struct ib_fast_reg_page_list *page_list);
 	int                        (*rereg_phys_mr)(struct ib_mr *mr,
 						    int mr_rereg_mask,
 						    struct ib_pd *pd,
@@ -2888,33 +2861,6 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
 			  u32 max_num_sg);
 
 /**
- * ib_alloc_fast_reg_page_list - Allocates a page list array
- * @device - ib device pointer.
- * @page_list_len - size of the page list array to be allocated.
- *
- * This allocates and returns a struct ib_fast_reg_page_list * and a
- * page_list array that is at least page_list_len in size.  The actual
- * size is returned in max_page_list_len.  The caller is responsible
- * for initializing the contents of the page_list array before posting
- * a send work request with the IB_WC_FAST_REG_MR opcode.
- *
- * The page_list array entries must be translated using one of the
- * ib_dma_*() functions just like the addresses passed to
- * ib_map_phys_fmr().  Once the ib_post_send() is issued, the struct
- * ib_fast_reg_page_list must not be modified by the caller until the
- * IB_WC_FAST_REG_MR work request completes.
- */
-struct ib_fast_reg_page_list *ib_alloc_fast_reg_page_list(
-				struct ib_device *device, int page_list_len);
-
-/**
- * ib_free_fast_reg_page_list - Deallocates a previously allocated
- *   page list array.
- * @page_list - struct ib_fast_reg_page_list pointer to be deallocated.
- */
-void ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
-
-/**
  * ib_update_fast_reg_key - updates the key portion of the fast_reg MR
  *   R_Key and L_Key.
  * @mr - struct ib_mr pointer to be updated.
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2 01/26] IB/core: Introduce new fast registration API

[Sagi Grimberg]

Not sure how a second set glitched in, my mail server
flipped I guess....

Sorry for the double send.

Sagi.
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2 12/26] xprtrdma: Port to new memory registration API

[Chuck Lever]

> On Sep 24, 2015, at 10:34 AM, Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org> wrote:
> 
> Instead of maintaining a fastreg page list, keep an sg table
> and convert an array of pages to a sg list. Then call ib_map_mr_sg
> and construct ib_reg_wr.
> 
> Note that the next step would be to have NFS work with sg lists
> as it maps well to sk_frags (see comment from hch
> http://marc.info/?l=linux-rdma&m=143677002622296&w=2).

Fwiw, you would need to change tcp_sendpages() first.

One more comment below.


> Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
> ---
> net/sunrpc/xprtrdma/frwr_ops.c  | 113 +++++++++++++++++++++++-----------------
> net/sunrpc/xprtrdma/xprt_rdma.h |   3 +-
> 2 files changed, 68 insertions(+), 48 deletions(-)
> 
> diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
> index 0d2f46f600b6..b80a82149977 100644
> --- a/net/sunrpc/xprtrdma/frwr_ops.c
> +++ b/net/sunrpc/xprtrdma/frwr_ops.c
> @@ -151,9 +151,13 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
> 	f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth);
> 	if (IS_ERR(f->fr_mr))
> 		goto out_mr_err;
> -	f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth);
> -	if (IS_ERR(f->fr_pgl))
> +
> +	f->sg = kcalloc(depth, sizeof(*f->sg), GFP_KERNEL);
> +	if (!f->sg)
> 		goto out_list_err;
> +
> +	sg_init_table(f->sg, depth);
> +
> 	return 0;
> 
> out_mr_err:
> @@ -163,7 +167,7 @@ out_mr_err:
> 	return rc;
> 
> out_list_err:
> -	rc = PTR_ERR(f->fr_pgl);
> +	rc = -ENOMEM;
> 	dprintk("RPC:       %s: ib_alloc_fast_reg_page_list status %i\n",
> 		__func__, rc);
> 	ib_dereg_mr(f->fr_mr);
> @@ -179,7 +183,7 @@ __frwr_release(struct rpcrdma_mw *r)
> 	if (rc)
> 		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
> 			__func__, rc);
> -	ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
> +	kfree(r->r.frmr.sg);
> }
> 
> static int
> @@ -312,14 +316,11 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
> 	struct rpcrdma_mw *mw;
> 	struct rpcrdma_frmr *frmr;
> 	struct ib_mr *mr;
> -	struct ib_fast_reg_wr fastreg_wr;
> +	struct ib_reg_wr reg_wr;
> 	struct ib_send_wr *bad_wr;
> +	unsigned int dma_nents;
> 	u8 key;
> -	int len, pageoff;
> -	int i, rc;
> -	int seg_len;
> -	u64 pa;
> -	int page_no;
> +	int i, rc, len, n;
> 
> 	mw = seg1->rl_mw;
> 	seg1->rl_mw = NULL;
> @@ -332,64 +333,81 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
> 	} while (mw->r.frmr.fr_state != FRMR_IS_INVALID);
> 	frmr = &mw->r.frmr;
> 	frmr->fr_state = FRMR_IS_VALID;
> +	mr = frmr->fr_mr;
> 
> -	pageoff = offset_in_page(seg1->mr_offset);
> -	seg1->mr_offset -= pageoff;	/* start of page */
> -	seg1->mr_len += pageoff;
> -	len = -pageoff;
> 	if (nsegs > ia->ri_max_frmr_depth)
> 		nsegs = ia->ri_max_frmr_depth;
> 
> -	for (page_no = i = 0; i < nsegs;) {
> -		rpcrdma_map_one(device, seg, direction);
> -		pa = seg->mr_dma;
> -		for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) {
> -			frmr->fr_pgl->page_list[page_no++] = pa;
> -			pa += PAGE_SIZE;
> -		}
> +	for (len = 0, i = 0; i < nsegs;) {
> +		if (seg->mr_page)
> +			sg_set_page(&frmr->sg[i],
> +				    seg->mr_page,
> +				    seg->mr_len,
> +				    offset_in_page(seg->mr_offset));
> +		else
> +			sg_set_buf(&frmr->sg[i], seg->mr_offset,
> +				   seg->mr_len);
> +
> 		len += seg->mr_len;
> 		++seg;
> 		++i;
> +
> 		/* Check for holes */
> 		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
> 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
> 			break;
> 	}
> +	frmr->sg_nents = i;
> +
> +	dma_nents = ib_dma_map_sg(device, frmr->sg, frmr->sg_nents, direction);
> +	if (!dma_nents) {
> +		pr_err("RPC:       %s: failed to dma map sg %p sg_nents %d\n",
> +		       __func__, frmr->sg, frmr->sg_nents);
> +		return -ENOMEM;
> +	}
> +
> +	n = ib_map_mr_sg(mr, frmr->sg, frmr->sg_nents, PAGE_SIZE);
> +	if (unlikely(n != frmr->sg_nents)) {
> +		pr_err("RPC:       %s: failed to map mr %p (%d/%d)\n",
> +		       __func__, frmr->fr_mr, n, frmr->sg_nents);
> +		rc = n < 0 ? n : -EINVAL;
> +		goto out_senderr;
> +	}
> +
> 	dprintk("RPC:       %s: Using frmr %p to map %d segments (%d bytes)\n",
> -		__func__, mw, i, len);
> -
> -	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
> -	fastreg_wr.wr.wr_id = (unsigned long)(void *)mw;
> -	fastreg_wr.wr.opcode = IB_WR_FAST_REG_MR;
> -	fastreg_wr.iova_start = seg1->mr_dma + pageoff;
> -	fastreg_wr.page_list = frmr->fr_pgl;
> -	fastreg_wr.page_shift = PAGE_SHIFT;
> -	fastreg_wr.page_list_len = page_no;
> -	fastreg_wr.length = len;
> -	fastreg_wr.access_flags = writing ?
> -				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
> -				IB_ACCESS_REMOTE_READ;
> -	mr = frmr->fr_mr;
> +		__func__, mw, frmr->sg_nents, mr->length);
> +
> 	key = (u8)(mr->rkey & 0x000000FF);
> 	ib_update_fast_reg_key(mr, ++key);
> -	fastreg_wr.rkey = mr->rkey;
> +
> +	reg_wr.wr.next = NULL;
> +	reg_wr.wr.opcode = IB_WR_REG_MR;
> +	reg_wr.wr.wr_id = (uintptr_t)mw;
> +	reg_wr.wr.num_sge = 0;
> +	reg_wr.wr.send_flags = 0;
> +	reg_wr.mr = mr;
> +	reg_wr.key = mr->rkey;
> +	reg_wr.access = writing ?
> +			IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
> +			IB_ACCESS_REMOTE_READ;
> 
> 	DECR_CQCOUNT(&r_xprt->rx_ep);
> -	rc = ib_post_send(ia->ri_id->qp, &fastreg_wr.wr, &bad_wr);
> +	rc = ib_post_send(ia->ri_id->qp, &reg_wr.wr, &bad_wr);
> 	if (rc)
> 		goto out_senderr;
> 
> +	seg1->mr_dir = direction;
> 	seg1->rl_mw = mw;
> 	seg1->mr_rkey = mr->rkey;
> -	seg1->mr_base = seg1->mr_dma + pageoff;
> -	seg1->mr_nsegs = i;
> -	seg1->mr_len = len;
> -	return i;
> +	seg1->mr_base = mr->iova;
> +	seg1->mr_nsegs = frmr->sg_nents;
> +	seg1->mr_len = mr->length;
> +
> +	return frmr->sg_nents;
> 
> out_senderr:
> 	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
> -	while (i--)
> -		rpcrdma_unmap_one(device, --seg);
> +	ib_dma_unmap_sg(device, frmr->sg, frmr->sg_nents, direction);
> 	__frwr_queue_recovery(mw);
> 	return rc;
> }
> @@ -403,28 +421,29 @@ frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
> 	struct rpcrdma_mr_seg *seg1 = seg;
> 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
> 	struct rpcrdma_mw *mw = seg1->rl_mw;
> +	struct rpcrdma_frmr *frmr = &mw->r.frmr;
> 	struct ib_send_wr invalidate_wr, *bad_wr;
> 	int rc, nsegs = seg->mr_nsegs;
> 
> 	dprintk("RPC:       %s: FRMR %p\n", __func__, mw);
> 
> 	seg1->rl_mw = NULL;
> -	mw->r.frmr.fr_state = FRMR_IS_INVALID;
> +	frmr->fr_state = FRMR_IS_INVALID;
> 
> 	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
> 	invalidate_wr.wr_id = (unsigned long)(void *)mw;
> 	invalidate_wr.opcode = IB_WR_LOCAL_INV;
> -	invalidate_wr.ex.invalidate_rkey = mw->r.frmr.fr_mr->rkey;
> +	invalidate_wr.ex.invalidate_rkey = frmr->fr_mr->rkey;
> 	DECR_CQCOUNT(&r_xprt->rx_ep);
> 
> -	while (seg1->mr_nsegs--)
> -		rpcrdma_unmap_one(ia->ri_device, seg++);
> 	read_lock(&ia->ri_qplock);
> 	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
> 	read_unlock(&ia->ri_qplock);
> 	if (rc)
> 		goto out_err;
> 
> +	ib_dma_unmap_sg(ia->ri_device, frmr->sg, frmr->sg_nents, seg1->mr_dir);

What benefit does moving the DMA unmap after the post_send have?
Remember that the LOCAL_INV WRs may not have started yet, even after
the post_send.

I’m OK with you not moving the DMA unmap into the completion handler
yet, it’s a rather complex change to consider. I have a plan and
some patches cooking that will address this problem and the issue of
flow controlling invalidation WRs.


> +
> 	rpcrdma_put_mw(r_xprt, mw);
> 	return nsegs;
> 
> diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
> index d252457ff21a..00773636d17e 100644
> --- a/net/sunrpc/xprtrdma/xprt_rdma.h
> +++ b/net/sunrpc/xprtrdma/xprt_rdma.h
> @@ -195,7 +195,8 @@ enum rpcrdma_frmr_state {
> };
> 
> struct rpcrdma_frmr {
> -	struct ib_fast_reg_page_list	*fr_pgl;
> +	struct scatterlist		*sg;
> +	unsigned int			sg_nents;
> 	struct ib_mr			*fr_mr;
> 	enum rpcrdma_frmr_state		fr_state;
> 	struct work_struct		fr_work;
> -- 
> 1.8.4.3
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

—
Chuck Lever



--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2 12/26] xprtrdma: Port to new memory registration API

[Sagi Grimberg]

On 9/25/2015 7:51 PM, Chuck Lever wrote:
>
>> On Sep 24, 2015, at 10:34 AM, Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org> wrote:
>>
>> Instead of maintaining a fastreg page list, keep an sg table
>> and convert an array of pages to a sg list. Then call ib_map_mr_sg
>> and construct ib_reg_wr.
>>
>> Note that the next step would be to have NFS work with sg lists
>> as it maps well to sk_frags (see comment from hch
>> http://marc.info/?l=linux-rdma&m=143677002622296&w=2).
>
> Fwiw, you would need to change tcp_sendpages() first.
>
> One more comment below.
>
>
>> Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
>> Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
>> ---
>> net/sunrpc/xprtrdma/frwr_ops.c  | 113 +++++++++++++++++++++++-----------------
>> net/sunrpc/xprtrdma/xprt_rdma.h |   3 +-
>> 2 files changed, 68 insertions(+), 48 deletions(-)
>>
>> diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
>> index 0d2f46f600b6..b80a82149977 100644
>> --- a/net/sunrpc/xprtrdma/frwr_ops.c
>> +++ b/net/sunrpc/xprtrdma/frwr_ops.c
>> @@ -151,9 +151,13 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
>> 	f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth);
>> 	if (IS_ERR(f->fr_mr))
>> 		goto out_mr_err;
>> -	f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth);
>> -	if (IS_ERR(f->fr_pgl))
>> +
>> +	f->sg = kcalloc(depth, sizeof(*f->sg), GFP_KERNEL);
>> +	if (!f->sg)
>> 		goto out_list_err;
>> +
>> +	sg_init_table(f->sg, depth);
>> +
>> 	return 0;
>>
>> out_mr_err:
>> @@ -163,7 +167,7 @@ out_mr_err:
>> 	return rc;
>>
>> out_list_err:
>> -	rc = PTR_ERR(f->fr_pgl);
>> +	rc = -ENOMEM;
>> 	dprintk("RPC:       %s: ib_alloc_fast_reg_page_list status %i\n",
>> 		__func__, rc);
>> 	ib_dereg_mr(f->fr_mr);
>> @@ -179,7 +183,7 @@ __frwr_release(struct rpcrdma_mw *r)
>> 	if (rc)
>> 		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
>> 			__func__, rc);
>> -	ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
>> +	kfree(r->r.frmr.sg);
>> }
>>
>> static int
>> @@ -312,14 +316,11 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
>> 	struct rpcrdma_mw *mw;
>> 	struct rpcrdma_frmr *frmr;
>> 	struct ib_mr *mr;
>> -	struct ib_fast_reg_wr fastreg_wr;
>> +	struct ib_reg_wr reg_wr;
>> 	struct ib_send_wr *bad_wr;
>> +	unsigned int dma_nents;
>> 	u8 key;
>> -	int len, pageoff;
>> -	int i, rc;
>> -	int seg_len;
>> -	u64 pa;
>> -	int page_no;
>> +	int i, rc, len, n;
>>
>> 	mw = seg1->rl_mw;
>> 	seg1->rl_mw = NULL;
>> @@ -332,64 +333,81 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
>> 	} while (mw->r.frmr.fr_state != FRMR_IS_INVALID);
>> 	frmr = &mw->r.frmr;
>> 	frmr->fr_state = FRMR_IS_VALID;
>> +	mr = frmr->fr_mr;
>>
>> -	pageoff = offset_in_page(seg1->mr_offset);
>> -	seg1->mr_offset -= pageoff;	/* start of page */
>> -	seg1->mr_len += pageoff;
>> -	len = -pageoff;
>> 	if (nsegs > ia->ri_max_frmr_depth)
>> 		nsegs = ia->ri_max_frmr_depth;
>>
>> -	for (page_no = i = 0; i < nsegs;) {
>> -		rpcrdma_map_one(device, seg, direction);
>> -		pa = seg->mr_dma;
>> -		for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) {
>> -			frmr->fr_pgl->page_list[page_no++] = pa;
>> -			pa += PAGE_SIZE;
>> -		}
>> +	for (len = 0, i = 0; i < nsegs;) {
>> +		if (seg->mr_page)
>> +			sg_set_page(&frmr->sg[i],
>> +				    seg->mr_page,
>> +				    seg->mr_len,
>> +				    offset_in_page(seg->mr_offset));
>> +		else
>> +			sg_set_buf(&frmr->sg[i], seg->mr_offset,
>> +				   seg->mr_len);
>> +
>> 		len += seg->mr_len;
>> 		++seg;
>> 		++i;
>> +
>> 		/* Check for holes */
>> 		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
>> 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
>> 			break;
>> 	}
>> +	frmr->sg_nents = i;
>> +
>> +	dma_nents = ib_dma_map_sg(device, frmr->sg, frmr->sg_nents, direction);
>> +	if (!dma_nents) {
>> +		pr_err("RPC:       %s: failed to dma map sg %p sg_nents %d\n",
>> +		       __func__, frmr->sg, frmr->sg_nents);
>> +		return -ENOMEM;
>> +	}
>> +
>> +	n = ib_map_mr_sg(mr, frmr->sg, frmr->sg_nents, PAGE_SIZE);
>> +	if (unlikely(n != frmr->sg_nents)) {
>> +		pr_err("RPC:       %s: failed to map mr %p (%d/%d)\n",
>> +		       __func__, frmr->fr_mr, n, frmr->sg_nents);
>> +		rc = n < 0 ? n : -EINVAL;
>> +		goto out_senderr;
>> +	}
>> +
>> 	dprintk("RPC:       %s: Using frmr %p to map %d segments (%d bytes)\n",
>> -		__func__, mw, i, len);
>> -
>> -	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
>> -	fastreg_wr.wr.wr_id = (unsigned long)(void *)mw;
>> -	fastreg_wr.wr.opcode = IB_WR_FAST_REG_MR;
>> -	fastreg_wr.iova_start = seg1->mr_dma + pageoff;
>> -	fastreg_wr.page_list = frmr->fr_pgl;
>> -	fastreg_wr.page_shift = PAGE_SHIFT;
>> -	fastreg_wr.page_list_len = page_no;
>> -	fastreg_wr.length = len;
>> -	fastreg_wr.access_flags = writing ?
>> -				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
>> -				IB_ACCESS_REMOTE_READ;
>> -	mr = frmr->fr_mr;
>> +		__func__, mw, frmr->sg_nents, mr->length);
>> +
>> 	key = (u8)(mr->rkey & 0x000000FF);
>> 	ib_update_fast_reg_key(mr, ++key);
>> -	fastreg_wr.rkey = mr->rkey;
>> +
>> +	reg_wr.wr.next = NULL;
>> +	reg_wr.wr.opcode = IB_WR_REG_MR;
>> +	reg_wr.wr.wr_id = (uintptr_t)mw;
>> +	reg_wr.wr.num_sge = 0;
>> +	reg_wr.wr.send_flags = 0;
>> +	reg_wr.mr = mr;
>> +	reg_wr.key = mr->rkey;
>> +	reg_wr.access = writing ?
>> +			IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
>> +			IB_ACCESS_REMOTE_READ;
>>
>> 	DECR_CQCOUNT(&r_xprt->rx_ep);
>> -	rc = ib_post_send(ia->ri_id->qp, &fastreg_wr.wr, &bad_wr);
>> +	rc = ib_post_send(ia->ri_id->qp, &reg_wr.wr, &bad_wr);
>> 	if (rc)
>> 		goto out_senderr;
>>
>> +	seg1->mr_dir = direction;
>> 	seg1->rl_mw = mw;
>> 	seg1->mr_rkey = mr->rkey;
>> -	seg1->mr_base = seg1->mr_dma + pageoff;
>> -	seg1->mr_nsegs = i;
>> -	seg1->mr_len = len;
>> -	return i;
>> +	seg1->mr_base = mr->iova;
>> +	seg1->mr_nsegs = frmr->sg_nents;
>> +	seg1->mr_len = mr->length;
>> +
>> +	return frmr->sg_nents;
>>
>> out_senderr:
>> 	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
>> -	while (i--)
>> -		rpcrdma_unmap_one(device, --seg);
>> +	ib_dma_unmap_sg(device, frmr->sg, frmr->sg_nents, direction);
>> 	__frwr_queue_recovery(mw);
>> 	return rc;
>> }
>> @@ -403,28 +421,29 @@ frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
>> 	struct rpcrdma_mr_seg *seg1 = seg;
>> 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
>> 	struct rpcrdma_mw *mw = seg1->rl_mw;
>> +	struct rpcrdma_frmr *frmr = &mw->r.frmr;
>> 	struct ib_send_wr invalidate_wr, *bad_wr;
>> 	int rc, nsegs = seg->mr_nsegs;
>>
>> 	dprintk("RPC:       %s: FRMR %p\n", __func__, mw);
>>
>> 	seg1->rl_mw = NULL;
>> -	mw->r.frmr.fr_state = FRMR_IS_INVALID;
>> +	frmr->fr_state = FRMR_IS_INVALID;
>>
>> 	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
>> 	invalidate_wr.wr_id = (unsigned long)(void *)mw;
>> 	invalidate_wr.opcode = IB_WR_LOCAL_INV;
>> -	invalidate_wr.ex.invalidate_rkey = mw->r.frmr.fr_mr->rkey;
>> +	invalidate_wr.ex.invalidate_rkey = frmr->fr_mr->rkey;
>> 	DECR_CQCOUNT(&r_xprt->rx_ep);
>>
>> -	while (seg1->mr_nsegs--)
>> -		rpcrdma_unmap_one(ia->ri_device, seg++);
>> 	read_lock(&ia->ri_qplock);
>> 	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
>> 	read_unlock(&ia->ri_qplock);
>> 	if (rc)
>> 		goto out_err;
>>
>> +	ib_dma_unmap_sg(ia->ri_device, frmr->sg, frmr->sg_nents, seg1->mr_dir);
>
> What benefit does moving the DMA unmap after the post_send have?
> Remember that the LOCAL_INV WRs may not have started yet, even after
> the post_send.

It doesn't have a benefit. I can move it back...
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 07/26] iw_cxgb4: Support the new memory registration API

[Sagi Grimberg]

Support the new memory registration API by allocating a
private page list array in c4iw_mr and populate it when
c4iw_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating build_fastreg just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (c4iw_mr)
- key, access flags (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Acked-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h |  7 ++++
 drivers/infiniband/hw/cxgb4/mem.c      | 38 +++++++++++++++++
 drivers/infiniband/hw/cxgb4/provider.c |  1 +
 drivers/infiniband/hw/cxgb4/qp.c       | 74 ++++++++++++++++++++++++++++++++++
 4 files changed, 120 insertions(+)

diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index c7bb38c931a5..032f90aa8ac9 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -386,6 +386,10 @@ struct c4iw_mr {
 	struct c4iw_dev *rhp;
 	u64 kva;
 	struct tpt_attributes attr;
+	u64 *mpl;
+	dma_addr_t mpl_addr;
+	u32 max_mpl_len;
+	u32 mpl_len;
 };
 
 static inline struct c4iw_mr *to_c4iw_mr(struct ib_mr *ibmr)
@@ -973,6 +977,9 @@ struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(
 struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 			    enum ib_mr_type mr_type,
 			    u32 max_num_sg);
+int c4iw_map_mr_sg(struct ib_mr *ibmr,
+		   struct scatterlist *sg,
+		   unsigned int sg_nents);
 int c4iw_dealloc_mw(struct ib_mw *mw);
 struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
 struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 026b91ebd5e2..86ec65721797 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -863,6 +863,7 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 	u32 mmid;
 	u32 stag = 0;
 	int ret = 0;
+	int length = roundup(max_num_sg * sizeof(u64), 32);
 
 	if (mr_type != IB_MR_TYPE_MEM_REG ||
 	    max_num_sg > t4_max_fr_depth(use_dsgl))
@@ -876,6 +877,14 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 		goto err;
 	}
 
+	mhp->mpl = dma_alloc_coherent(&rhp->rdev.lldi.pdev->dev,
+				      length, &mhp->mpl_addr, GFP_KERNEL);
+	if (!mhp->mpl) {
+		ret = -ENOMEM;
+		goto err_mpl;
+	}
+	mhp->max_mpl_len = length;
+
 	mhp->rhp = rhp;
 	ret = alloc_pbl(mhp, max_num_sg);
 	if (ret)
@@ -905,11 +914,37 @@ err2:
 	c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
 			      mhp->attr.pbl_size << 3);
 err1:
+	dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev,
+			  mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr);
+err_mpl:
 	kfree(mhp);
 err:
 	return ERR_PTR(ret);
 }
 
+static int c4iw_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
+
+	if (unlikely(mhp->mpl_len == mhp->max_mpl_len))
+		return -ENOMEM;
+
+	mhp->mpl[mhp->mpl_len++] = addr;
+
+	return 0;
+}
+
+int c4iw_map_mr_sg(struct ib_mr *ibmr,
+		   struct scatterlist *sg,
+		   unsigned int sg_nents)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
+
+	mhp->mpl_len = 0;
+
+	return ib_sg_to_pages(ibmr, sg, sg_nents, c4iw_set_page);
+}
+
 struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(struct ib_device *device,
 						     int page_list_len)
 {
@@ -970,6 +1005,9 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr)
 	rhp = mhp->rhp;
 	mmid = mhp->attr.stag >> 8;
 	remove_handle(rhp, &rhp->mmidr, mmid);
+	if (mhp->mpl)
+		dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev,
+				  mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr);
 	dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
 		       mhp->attr.pbl_addr);
 	if (mhp->attr.pbl_size)
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 7746113552e7..55dedadcffaa 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -557,6 +557,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.bind_mw = c4iw_bind_mw;
 	dev->ibdev.dealloc_mw = c4iw_dealloc_mw;
 	dev->ibdev.alloc_mr = c4iw_alloc_mr;
+	dev->ibdev.map_mr_sg = c4iw_map_mr_sg;
 	dev->ibdev.alloc_fast_reg_page_list = c4iw_alloc_fastreg_pbl;
 	dev->ibdev.free_fast_reg_page_list = c4iw_free_fastreg_pbl;
 	dev->ibdev.attach_mcast = c4iw_multicast_attach;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index b60498fff99a..12a23bc935f3 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -605,10 +605,76 @@ static int build_rdma_recv(struct c4iw_qp *qhp, union t4_recv_wr *wqe,
 	return 0;
 }
 
+static int build_memreg(struct t4_sq *sq, union t4_wr *wqe,
+			struct ib_reg_wr *wr, u8 *len16, u8 t5dev)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(wr->mr);
+	struct fw_ri_immd *imdp;
+	__be64 *p;
+	int i;
+	int pbllen = roundup(mhp->mpl_len * sizeof(u64), 32);
+	int rem;
+
+	if (mhp->mpl_len > t4_max_fr_depth(use_dsgl))
+		return -EINVAL;
+
+	wqe->fr.qpbinde_to_dcacpu = 0;
+	wqe->fr.pgsz_shift = ilog2(wr->mr->page_size) - 12;
+	wqe->fr.addr_type = FW_RI_VA_BASED_TO;
+	wqe->fr.mem_perms = c4iw_ib_to_tpt_access(wr->access);
+	wqe->fr.len_hi = 0;
+	wqe->fr.len_lo = cpu_to_be32(mhp->ibmr.length);
+	wqe->fr.stag = cpu_to_be32(wr->key);
+	wqe->fr.va_hi = cpu_to_be32(mhp->ibmr.iova >> 32);
+	wqe->fr.va_lo_fbo = cpu_to_be32(mhp->ibmr.iova &
+					0xffffffff);
+
+	if (t5dev && use_dsgl && (pbllen > max_fr_immd)) {
+		struct fw_ri_dsgl *sglp;
+
+		for (i = 0; i < mhp->mpl_len; i++)
+			mhp->mpl[i] = (__force u64)cpu_to_be64((u64)mhp->mpl[i]);
+
+		sglp = (struct fw_ri_dsgl *)(&wqe->fr + 1);
+		sglp->op = FW_RI_DATA_DSGL;
+		sglp->r1 = 0;
+		sglp->nsge = cpu_to_be16(1);
+		sglp->addr0 = cpu_to_be64(mhp->mpl_addr);
+		sglp->len0 = cpu_to_be32(pbllen);
+
+		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*sglp), 16);
+	} else {
+		imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
+		imdp->op = FW_RI_DATA_IMMD;
+		imdp->r1 = 0;
+		imdp->r2 = 0;
+		imdp->immdlen = cpu_to_be32(pbllen);
+		p = (__be64 *)(imdp + 1);
+		rem = pbllen;
+		for (i = 0; i < mhp->mpl_len; i++) {
+			*p = cpu_to_be64((u64)mhp->mpl[i]);
+			rem -= sizeof(*p);
+			if (++p == (__be64 *)&sq->queue[sq->size])
+				p = (__be64 *)sq->queue;
+		}
+		BUG_ON(rem < 0);
+		while (rem) {
+			*p = 0;
+			rem -= sizeof(*p);
+			if (++p == (__be64 *)&sq->queue[sq->size])
+				p = (__be64 *)sq->queue;
+		}
+		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*imdp)
+				      + pbllen, 16);
+	}
+	return 0;
+}
+
 static int build_fastreg(struct t4_sq *sq, union t4_wr *wqe,
 			 struct ib_send_wr *send_wr, u8 *len16, u8 t5dev)
 {
 	struct ib_fast_reg_wr *wr = fast_reg_wr(send_wr);
+
 	struct fw_ri_immd *imdp;
 	__be64 *p;
 	int i;
@@ -817,6 +883,14 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 					    qhp->rhp->rdev.lldi.adapter_type) ?
 					    1 : 0);
 			break;
+		case IB_WR_REG_MR:
+			fw_opcode = FW_RI_FR_NSMR_WR;
+			swsqe->opcode = FW_RI_FAST_REGISTER;
+			err = build_memreg(&qhp->wq.sq, wqe, reg_wr(wr), &len16,
+					   is_t5(
+					   qhp->rhp->rdev.lldi.adapter_type) ?
+					   1 : 0);
+			break;
 		case IB_WR_LOCAL_INV:
 			if (wr->send_flags & IB_SEND_FENCE)
 				fw_flags |= FW_RI_LOCAL_FENCE_FLAG;
-- 
1.8.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html