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

Pull rdma updates from Jason Gunthorpe:
 "This has been a slightly more active cycle than normal with ongoing
  core changes and quite a lot of collected driver updates.

   - Various driver fixes for bnxt_re, cxgb4, hns, mlx5, pvrdma, rxe

   - A new data transfer mode for HFI1 giving higher performance

   - Significant functional and bug fix update to the mlx5
     On-Demand-Paging MR feature

   - A chip hang reset recovery system for hns

   - Change mm->pinned_vm to an atomic64

   - Update bnxt_re to support a new 57500 chip

   - A sane netlink 'rdma link add' method for creating rxe devices and
     fixing the various unregistration race conditions in rxe's
     unregister flow

   - Allow lookup up objects by an ID over netlink

   - Various reworking of the core to driver interface:
       - drivers should not assume umem SGLs are in PAGE_SIZE chunks
       - ucontext is accessed via udata not other means
       - start to make the core code responsible for object memory
         allocation
       - drivers should convert struct device to struct ib_device via a
         helper
       - drivers have more tools to avoid use after unregister problems"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (280 commits)
  net/mlx5: ODP support for XRC transport is not enabled by default in FW
  IB/hfi1: Close race condition on user context disable and close
  RDMA/umem: Revert broken 'off by one' fix
  RDMA/umem: minor bug fix in error handling path
  RDMA/hns: Use GFP_ATOMIC in hns_roce_v2_modify_qp
  cxgb4: kfree mhp after the debug print
  IB/rdmavt: Fix concurrency panics in QP post_send and modify to error
  IB/rdmavt: Fix loopback send with invalidate ordering
  IB/iser: Fix dma_nents type definition
  IB/mlx5: Set correct write permissions for implicit ODP MR
  bnxt_re: Clean cq for kernel consumers only
  RDMA/uverbs: Don't do double free of allocated PD
  RDMA: Handle ucontext allocations by IB/core
  RDMA/core: Fix a WARN() message
  bnxt_re: fix the regression due to changes in alloc_pbl
  IB/mlx4: Increase the timeout for CM cache
  IB/core: Abort page fault handler silently during owning process exit
  IB/mlx5: Validate correct PD before prefetch MR
  IB/mlx5: Protect against prefetch of invalid MR
  RDMA/uverbs: Store PR pointer before it is overwritten
  ...

1 files changed, 28 insertions, 47 deletions

diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 16543d5e80c3..123ca8f64f75 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -49,43 +49,6 @@ static void __qib_release_user_pages(struct page **p, size_t num_pages,
 	}
 }
 
-/*
- * Call with current->mm->mmap_sem held.
- */
-static int __qib_get_user_pages(unsigned long start_page, size_t num_pages,
-				struct page **p)
-{
-	unsigned long lock_limit;
-	size_t got;
-	int ret;
-
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
-	if (num_pages > lock_limit && !capable(CAP_IPC_LOCK)) {
-		ret = -ENOMEM;
-		goto bail;
-	}
-
-	for (got = 0; got < num_pages; got += ret) {
-		ret = get_user_pages(start_page + got * PAGE_SIZE,
-				     num_pages - got,
-				     FOLL_WRITE | FOLL_FORCE,
-				     p + got, NULL);
-		if (ret < 0)
-			goto bail_release;
-	}
-
-	current->mm->pinned_vm += num_pages;
-
-	ret = 0;
-	goto bail;
-
-bail_release:
-	__qib_release_user_pages(p, got, 0);
-bail:
-	return ret;
-}
-
 /**
  * qib_map_page - a safety wrapper around pci_map_page()
  *
@@ -137,26 +100,44 @@ int qib_map_page(struct pci_dev *hwdev, struct page *page, dma_addr_t *daddr)
 int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 		       struct page **p)
 {
+	unsigned long locked, lock_limit;
+	size_t got;
 	int ret;
 
-	down_write(&current->mm->mmap_sem);
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	locked = atomic64_add_return(num_pages, &current->mm->pinned_vm);
 
-	ret = __qib_get_user_pages(start_page, num_pages, p);
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+		ret = -ENOMEM;
+		goto bail;
+	}
 
-	up_write(&current->mm->mmap_sem);
+	down_read(&current->mm->mmap_sem);
+	for (got = 0; got < num_pages; got += ret) {
+		ret = get_user_pages_longterm(start_page + got * PAGE_SIZE,
+					      num_pages - got,
+					      FOLL_WRITE | FOLL_FORCE,
+					      p + got, NULL);
+		if (ret < 0) {
+			up_read(&current->mm->mmap_sem);
+			goto bail_release;
+		}
+	}
+	up_read(&current->mm->mmap_sem);
 
+	return 0;
+bail_release:
+	__qib_release_user_pages(p, got, 0);
+bail:
+	atomic64_sub(num_pages, &current->mm->pinned_vm);
 	return ret;
 }
 
 void qib_release_user_pages(struct page **p, size_t num_pages)
 {
-	if (current->mm) /* during close after signal, mm can be NULL */
-		down_write(&current->mm->mmap_sem);
-
 	__qib_release_user_pages(p, num_pages, 1);
 
-	if (current->mm) {
-		current->mm->pinned_vm -= num_pages;
-		up_write(&current->mm->mmap_sem);
-	}
+	/* during close after signal, mm can be NULL */
+	if (current->mm)
+		atomic64_sub(num_pages, &current->mm->pinned_vm);
 }