Merge tag 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull second round of rdma updates from Doug Ledford:
 "This can be split out into just two categories:

   - fixes to the RDMA R/W API in regards to SG list length limits
     (about 5 patches)

   - fixes/features for the Intel hfi1 driver (everything else)

  The hfi1 driver is still being brought to full feature support by
  Intel, and they have a lot of people working on it, so that amounts to
  almost the entirety of this pull request"

* tag 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (84 commits)
  IB/hfi1: Add cache evict LRU list
  IB/hfi1: Fix memory leak during unexpected shutdown
  IB/hfi1: Remove unneeded mm argument in remove function
  IB/hfi1: Consistently call ops->remove outside spinlock
  IB/hfi1: Use evict mmu rb operation
  IB/hfi1: Add evict operation to the mmu rb handler
  IB/hfi1: Fix TID caching actions
  IB/hfi1: Make the cache handler own its rb tree root
  IB/hfi1: Make use of mm consistent
  IB/hfi1: Fix user SDMA racy user request claim
  IB/hfi1: Fix error condition that needs to clean up
  IB/hfi1: Release node on insert failure
  IB/hfi1: Validate SDMA user iovector count
  IB/hfi1: Validate SDMA user request index
  IB/hfi1: Use the same capability state for all shared contexts
  IB/hfi1: Prevent null pointer dereference
  IB/hfi1: Rename TID mmu_rb_* functions
  IB/hfi1: Remove unneeded empty check in hfi1_mmu_rb_unregister()
  IB/hfi1: Restructure hfi1_file_open
  IB/hfi1: Make iovec loop index easy to understand
  ...

1 files changed, 11 insertions, 13 deletions

diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index 1eb9b1294a63..dbfd854c32c9 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -58,19 +58,13 @@ static inline bool rdma_rw_io_needs_mr(struct ib_device *dev, u8 port_num,
 	return false;
 }
 
-static inline u32 rdma_rw_max_sge(struct ib_device *dev,
-		enum dma_data_direction dir)
-{
-	return dir == DMA_TO_DEVICE ?
-		dev->attrs.max_sge : dev->attrs.max_sge_rd;
-}
-
 static inline u32 rdma_rw_fr_page_list_len(struct ib_device *dev)
 {
 	/* arbitrary limit to avoid allocating gigantic resources */
 	return min_t(u32, dev->attrs.max_fast_reg_page_list_len, 256);
 }
 
+/* Caller must have zero-initialized *reg. */
 static int rdma_rw_init_one_mr(struct ib_qp *qp, u8 port_num,
 		struct rdma_rw_reg_ctx *reg, struct scatterlist *sg,
 		u32 sg_cnt, u32 offset)
@@ -114,6 +108,7 @@ static int rdma_rw_init_mr_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		u8 port_num, struct scatterlist *sg, u32 sg_cnt, u32 offset,
 		u64 remote_addr, u32 rkey, enum dma_data_direction dir)
 {
+	struct rdma_rw_reg_ctx *prev = NULL;
 	u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device);
 	int i, j, ret = 0, count = 0;
 
@@ -125,7 +120,6 @@ static int rdma_rw_init_mr_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 	}
 
 	for (i = 0; i < ctx->nr_ops; i++) {
-		struct rdma_rw_reg_ctx *prev = i ? &ctx->reg[i - 1] : NULL;
 		struct rdma_rw_reg_ctx *reg = &ctx->reg[i];
 		u32 nents = min(sg_cnt, pages_per_mr);
 
@@ -162,9 +156,13 @@ static int rdma_rw_init_mr_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		sg_cnt -= nents;
 		for (j = 0; j < nents; j++)
 			sg = sg_next(sg);
+		prev = reg;
 		offset = 0;
 	}
 
+	if (prev)
+		prev->wr.wr.next = NULL;
+
 	ctx->type = RDMA_RW_MR;
 	return count;
 
@@ -181,7 +179,8 @@ static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		u64 remote_addr, u32 rkey, enum dma_data_direction dir)
 {
 	struct ib_device *dev = qp->pd->device;
-	u32 max_sge = rdma_rw_max_sge(dev, dir);
+	u32 max_sge = dir == DMA_TO_DEVICE ? qp->max_write_sge :
+		      qp->max_read_sge;
 	struct ib_sge *sge;
 	u32 total_len = 0, i, j;
 
@@ -205,11 +204,10 @@ static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 			rdma_wr->wr.opcode = IB_WR_RDMA_READ;
 		rdma_wr->remote_addr = remote_addr + total_len;
 		rdma_wr->rkey = rkey;
+		rdma_wr->wr.num_sge = nr_sge;
 		rdma_wr->wr.sg_list = sge;
 
 		for (j = 0; j < nr_sge; j++, sg = sg_next(sg)) {
-			rdma_wr->wr.num_sge++;
-
 			sge->addr = ib_sg_dma_address(dev, sg) + offset;
 			sge->length = ib_sg_dma_len(dev, sg) - offset;
 			sge->lkey = qp->pd->local_dma_lkey;
@@ -220,8 +218,8 @@ static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 			offset = 0;
 		}
 
-		if (i + 1 < ctx->nr_ops)
-			rdma_wr->wr.next = &ctx->map.wrs[i + 1].wr;
+		rdma_wr->wr.next = i + 1 < ctx->nr_ops ?
+			&ctx->map.wrs[i + 1].wr : NULL;
 	}
 
 	ctx->type = RDMA_RW_MULTI_WR;