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
  ...

drivers/misc/mic/scif/scif_rma.c

@@ -272,21 +272,12 @@ static inline void __scif_release_mm(struct mm_struct *mm)
 
 static inline int
 __scif_dec_pinned_vm_lock(struct mm_struct *mm,
-			  int nr_pages, bool try_lock)
+			  int nr_pages)
 {
 	if (!mm || !nr_pages || !scif_ulimit_check)
 		return 0;
-	if (try_lock) {
-		if (!down_write_trylock(&mm->mmap_sem)) {
-			dev_err(scif_info.mdev.this_device,
-				"%s %d err\n", __func__, __LINE__);
-			return -1;
-		}
-	} else {
-		down_write(&mm->mmap_sem);
-	}
-	mm->pinned_vm -= nr_pages;
-	up_write(&mm->mmap_sem);
+
+	atomic64_sub(nr_pages, &mm->pinned_vm);
 	return 0;
 }
 
@@ -298,16 +289,16 @@ static inline int __scif_check_inc_pinned_vm(struct mm_struct *mm,
 	if (!mm || !nr_pages || !scif_ulimit_check)
 		return 0;
 
-	locked = nr_pages;
-	locked += mm->pinned_vm;
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	locked = atomic64_add_return(nr_pages, &mm->pinned_vm);
+
 	if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
+		atomic64_sub(nr_pages, &mm->pinned_vm);
 		dev_err(scif_info.mdev.this_device,
 			"locked(%lu) > lock_limit(%lu)\n",
 			locked, lock_limit);
 		return -ENOMEM;
 	}
-	mm->pinned_vm = locked;
 	return 0;
 }
 
@@ -326,7 +317,7 @@ int scif_destroy_window(struct scif_endpt *ep, struct scif_window *window)
 
 	might_sleep();
 	if (!window->temp && window->mm) {
-		__scif_dec_pinned_vm_lock(window->mm, window->nr_pages, 0);
+		__scif_dec_pinned_vm_lock(window->mm, window->nr_pages);
 		__scif_release_mm(window->mm);
 		window->mm = NULL;
 	}
@@ -737,7 +728,7 @@ done:
 					    ep->rma_info.dma_chan);
 		} else {
 			if (!__scif_dec_pinned_vm_lock(window->mm,
-						       window->nr_pages, 1)) {
+						       window->nr_pages)) {
 				__scif_release_mm(window->mm);
 				window->mm = NULL;
 			}
@@ -1385,28 +1376,23 @@ int __scif_pin_pages(void *addr, size_t len, int *out_prot,
 		prot |= SCIF_PROT_WRITE;
 retry:
 		mm = current->mm;
-		down_write(&mm->mmap_sem);
 		if (ulimit) {
 			err = __scif_check_inc_pinned_vm(mm, nr_pages);
 			if (err) {
-				up_write(&mm->mmap_sem);
 				pinned_pages->nr_pages = 0;
 				goto error_unmap;
 			}
 		}
 
-		pinned_pages->nr_pages = get_user_pages(
+		pinned_pages->nr_pages = get_user_pages_fast(
 				(u64)addr,
 				nr_pages,
 				(prot & SCIF_PROT_WRITE) ? FOLL_WRITE : 0,
-				pinned_pages->pages,
-				NULL);
-		up_write(&mm->mmap_sem);
+				pinned_pages->pages);
 		if (nr_pages != pinned_pages->nr_pages) {
 			if (try_upgrade) {
 				if (ulimit)
-					__scif_dec_pinned_vm_lock(mm,
-								  nr_pages, 0);
+					__scif_dec_pinned_vm_lock(mm, nr_pages);
 				/* Roll back any pinned pages */
 				for (i = 0; i < pinned_pages->nr_pages; i++) {
 					if (pinned_pages->pages[i])
@@ -1433,7 +1419,7 @@ retry:
 	return err;
 dec_pinned:
 	if (ulimit)
-		__scif_dec_pinned_vm_lock(mm, nr_pages, 0);
+		__scif_dec_pinned_vm_lock(mm, nr_pages);
 	/* Something went wrong! Rollback */
 error_unmap:
 	pinned_pages->nr_pages = nr_pages;