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

Pull rdma updates from Jason Gunthorpe:
 "A usual cycle for RDMA with a typical mix of driver and core subsystem
  updates:

   - Driver minor changes and bug fixes for mlx5, efa, rxe, vmw_pvrdma,
     hns, usnic, qib, qedr, cxgb4, hns, bnxt_re

   - Various rtrs fixes and updates

   - Bug fix for mlx4 CM emulation for virtualization scenarios where
     MRA wasn't working right

   - Use tracepoints instead of pr_debug in the CM code

   - Scrub the locking in ucma and cma to close more syzkaller bugs

   - Use tasklet_setup in the subsystem

   - Revert the idea that 'destroy' operations are not allowed to fail
     at the driver level. This proved unworkable from a HW perspective.

   - Revise how the umem API works so drivers make fewer mistakes using
     it

   - XRC support for qedr

   - Convert uverbs objects RWQ and MW to new the allocation scheme

   - Large queue entry sizes for hns

   - Use hmm_range_fault() for mlx5 On Demand Paging

   - uverbs APIs to inspect the GID table instead of sysfs

   - Move some of the RDMA code for building large page SGLs into
     lib/scatterlist"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (191 commits)
  RDMA/ucma: Fix use after free in destroy id flow
  RDMA/rxe: Handle skb_clone() failure in rxe_recv.c
  RDMA/rxe: Move the definitions for rxe_av.network_type to uAPI
  RDMA: Explicitly pass in the dma_device to ib_register_device
  lib/scatterlist: Do not limit max_segment to PAGE_ALIGNED values
  IB/mlx4: Convert rej_tmout radix-tree to XArray
  RDMA/rxe: Fix bug rejecting all multicast packets
  RDMA/rxe: Fix skb lifetime in rxe_rcv_mcast_pkt()
  RDMA/rxe: Remove duplicate entries in struct rxe_mr
  IB/hfi,rdmavt,qib,opa_vnic: Update MAINTAINERS
  IB/rdmavt: Fix sizeof mismatch
  MAINTAINERS: CISCO VIC LOW LATENCY NIC DRIVER
  RDMA/bnxt_re: Fix sizeof mismatch for allocation of pbl_tbl.
  RDMA/bnxt_re: Use rdma_umem_for_each_dma_block()
  RDMA/umem: Move to allocate SG table from pages
  lib/scatterlist: Add support in dynamic allocation of SG table from pages
  tools/testing/scatterlist: Show errors in human readable form
  tools/testing/scatterlist: Rejuvenate bit-rotten test
  RDMA/ipoib: Set rtnl_link_ops for ipoib interfaces
  RDMA/uverbs: Expose the new GID query API to user space
  ...

1 files changed, 29 insertions, 52 deletions

diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index e5df3884b41d..7f81a695e9af 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -589,28 +589,22 @@ err_table:
 	return ret;
 }
 
-struct ib_mw *hns_roce_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
-				struct ib_udata *udata)
+int hns_roce_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(ib_pd->device);
-	struct hns_roce_mw *mw;
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibmw->device);
+	struct hns_roce_mw *mw = to_hr_mw(ibmw);
 	unsigned long index = 0;
 	int ret;
 
-	mw = kmalloc(sizeof(*mw), GFP_KERNEL);
-	if (!mw)
-		return ERR_PTR(-ENOMEM);
-
 	/* Allocate a key for mw from bitmap */
 	ret = hns_roce_bitmap_alloc(&hr_dev->mr_table.mtpt_bitmap, &index);
 	if (ret)
-		goto err_bitmap;
+		return ret;
 
 	mw->rkey = hw_index_to_key(index);
 
-	mw->ibmw.rkey = mw->rkey;
-	mw->ibmw.type = type;
-	mw->pdn = to_hr_pd(ib_pd)->pdn;
+	ibmw->rkey = mw->rkey;
+	mw->pdn = to_hr_pd(ibmw->pd)->pdn;
 	mw->pbl_hop_num = hr_dev->caps.pbl_hop_num;
 	mw->pbl_ba_pg_sz = hr_dev->caps.pbl_ba_pg_sz;
 	mw->pbl_buf_pg_sz = hr_dev->caps.pbl_buf_pg_sz;
@@ -619,15 +613,11 @@ struct ib_mw *hns_roce_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
 	if (ret)
 		goto err_mw;
 
-	return &mw->ibmw;
+	return 0;
 
 err_mw:
 	hns_roce_mw_free(hr_dev, mw);
-
-err_bitmap:
-	kfree(mw);
-
-	return ERR_PTR(ret);
+	return ret;
 }
 
 int hns_roce_dealloc_mw(struct ib_mw *ibmw)
@@ -636,8 +626,6 @@ int hns_roce_dealloc_mw(struct ib_mw *ibmw)
 	struct hns_roce_mw *mw = to_hr_mw(ibmw);
 
 	hns_roce_mw_free(hr_dev, mw);
-	kfree(mw);
-
 	return 0;
 }
 
@@ -707,19 +695,6 @@ static inline size_t mtr_bufs_size(struct hns_roce_buf_attr *attr)
 	return size;
 }
 
-static inline int mtr_umem_page_count(struct ib_umem *umem,
-				      unsigned int page_shift)
-{
-	int count = ib_umem_page_count(umem);
-
-	if (page_shift >= PAGE_SHIFT)
-		count >>= page_shift - PAGE_SHIFT;
-	else
-		count <<= PAGE_SHIFT - page_shift;
-
-	return count;
-}
-
 static inline size_t mtr_kmem_direct_size(bool is_direct, size_t alloc_size,
 					  unsigned int page_shift)
 {
@@ -767,13 +742,11 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 			  struct ib_udata *udata, unsigned long user_addr)
 {
 	struct ib_device *ibdev = &hr_dev->ib_dev;
-	unsigned int max_pg_shift = buf_attr->page_shift;
-	unsigned int best_pg_shift = 0;
+	unsigned int best_pg_shift;
 	int all_pg_count = 0;
 	size_t direct_size;
 	size_t total_size;
-	unsigned long tmp;
-	int ret = 0;
+	int ret;
 
 	total_size = mtr_bufs_size(buf_attr);
 	if (total_size < 1) {
@@ -782,6 +755,9 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 	}
 
 	if (udata) {
+		unsigned long pgsz_bitmap;
+		unsigned long page_size;
+
 		mtr->kmem = NULL;
 		mtr->umem = ib_umem_get(ibdev, user_addr, total_size,
 					buf_attr->user_access);
@@ -790,15 +766,17 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 				  PTR_ERR(mtr->umem));
 			return -ENOMEM;
 		}
-		if (buf_attr->fixed_page) {
-			best_pg_shift = max_pg_shift;
-		} else {
-			tmp = GENMASK(max_pg_shift, 0);
-			ret = ib_umem_find_best_pgsz(mtr->umem, tmp, user_addr);
-			best_pg_shift = (ret <= PAGE_SIZE) ?
-					PAGE_SHIFT : ilog2(ret);
-		}
-		all_pg_count = mtr_umem_page_count(mtr->umem, best_pg_shift);
+		if (buf_attr->fixed_page)
+			pgsz_bitmap = 1 << buf_attr->page_shift;
+		else
+			pgsz_bitmap = GENMASK(buf_attr->page_shift, PAGE_SHIFT);
+
+		page_size = ib_umem_find_best_pgsz(mtr->umem, pgsz_bitmap,
+						   user_addr);
+		if (!page_size)
+			return -EINVAL;
+		best_pg_shift = order_base_2(page_size);
+		all_pg_count = ib_umem_num_dma_blocks(mtr->umem, page_size);
 		ret = 0;
 	} else {
 		mtr->umem = NULL;
@@ -808,16 +786,15 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 			return -ENOMEM;
 		}
 		direct_size = mtr_kmem_direct_size(is_direct, total_size,
-						   max_pg_shift);
+						   buf_attr->page_shift);
 		ret = hns_roce_buf_alloc(hr_dev, total_size, direct_size,
-					 mtr->kmem, max_pg_shift);
+					 mtr->kmem, buf_attr->page_shift);
 		if (ret) {
 			ibdev_err(ibdev, "Failed to alloc kmem, ret %d\n", ret);
 			goto err_alloc_mem;
-		} else {
-			best_pg_shift = max_pg_shift;
-			all_pg_count = mtr->kmem->npages;
 		}
+		best_pg_shift = buf_attr->page_shift;
+		all_pg_count = mtr->kmem->npages;
 	}
 
 	/* must bigger than minimum hardware page shift */
@@ -967,7 +944,7 @@ static int mtr_init_buf_cfg(struct hns_roce_dev *hr_dev,
 			    unsigned int *buf_page_shift)
 {
 	struct hns_roce_buf_region *r;
-	unsigned int page_shift = 0;
+	unsigned int page_shift;
 	int page_cnt = 0;
 	size_t buf_size;
 	int region_cnt;