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
  ...

4 files changed, 43 insertions, 15 deletions

diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h
index e94290b29e99..ef1bae2983f3 100644
--- a/include/linux/cgroup_rdma.h
+++ b/include/linux/cgroup_rdma.h
@@ -39,7 +39,7 @@ struct rdmacg_device {
  * APIs for RDMA/IB stack to publish when a device wants to
  * participate in resource accounting
  */
-int rdmacg_register_device(struct rdmacg_device *device);
+void rdmacg_register_device(struct rdmacg_device *device);
 void rdmacg_unregister_device(struct rdmacg_device *device);
 
 /* APIs for RDMA/IB stack to charge/uncharge pool specific resources */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5ffb5df1a2c2..022541dc5dbf 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -365,6 +365,7 @@ struct mlx5_core_sig_ctx {
 enum {
 	MLX5_MKEY_MR = 1,
 	MLX5_MKEY_MW,
+	MLX5_MKEY_INDIRECT_DEVX,
 };
 
 struct mlx5_core_mkey {
@@ -960,10 +961,6 @@ int mlx5_query_odp_caps(struct mlx5_core_dev *dev,
 			struct mlx5_odp_caps *odp_caps);
 int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev,
 			     u8 port_num, void *out, size_t sz);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
-				u32 wq_num, u8 type, int error);
-#endif
 
 int mlx5_init_rl_table(struct mlx5_core_dev *dev);
 void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 86e7a7a46353..7eade9132f02 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -411,7 +411,7 @@ struct mm_struct {
 
 		unsigned long total_vm;	   /* Total pages mapped */
 		unsigned long locked_vm;   /* Pages that have PG_mlocked set */
-		unsigned long pinned_vm;   /* Refcount permanently increased */
+		atomic64_t    pinned_vm;   /* Refcount permanently increased */
 		unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
 		unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
 		unsigned long stack_vm;	   /* VM_STACK */
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index b96f0d0b5b8f..b4be960c7e5d 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -339,12 +339,12 @@ int sg_alloc_table_chained(struct sg_table *table, int nents,
 /*
  * sg page iterator
  *
- * Iterates over sg entries page-by-page.  On each successful iteration,
- * you can call sg_page_iter_page(@piter) and sg_page_iter_dma_address(@piter)
- * to get the current page and its dma address. @piter->sg will point to the
- * sg holding this page and @piter->sg_pgoffset to the page's page offset
- * within the sg. The iteration will stop either when a maximum number of sg
- * entries was reached or a terminating sg (sg_last(sg) == true) was reached.
+ * Iterates over sg entries page-by-page.  On each successful iteration, you
+ * can call sg_page_iter_page(@piter) to get the current page and its dma
+ * address. @piter->sg will point to the sg holding this page and
+ * @piter->sg_pgoffset to the page's page offset within the sg. The iteration
+ * will stop either when a maximum number of sg entries was reached or a
+ * terminating sg (sg_last(sg) == true) was reached.
  */
 struct sg_page_iter {
 	struct scatterlist	*sg;		/* sg holding the page */
@@ -356,7 +356,19 @@ struct sg_page_iter {
 						 * next step */
 };
 
+/*
+ * sg page iterator for DMA addresses
+ *
+ * This is the same as sg_page_iter however you can call
+ * sg_page_iter_dma_address(@dma_iter) to get the page's DMA
+ * address. sg_page_iter_page() cannot be called on this iterator.
+ */
+struct sg_dma_page_iter {
+	struct sg_page_iter base;
+};
+
 bool __sg_page_iter_next(struct sg_page_iter *piter);
+bool __sg_page_iter_dma_next(struct sg_dma_page_iter *dma_iter);
 void __sg_page_iter_start(struct sg_page_iter *piter,
 			  struct scatterlist *sglist, unsigned int nents,
 			  unsigned long pgoffset);
@@ -372,11 +384,13 @@ static inline struct page *sg_page_iter_page(struct sg_page_iter *piter)
 /**
  * sg_page_iter_dma_address - get the dma address of the current page held by
  * the page iterator.
- * @piter:	page iterator holding the page
+ * @dma_iter:	page iterator holding the page
  */
-static inline dma_addr_t sg_page_iter_dma_address(struct sg_page_iter *piter)
+static inline dma_addr_t
+sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter)
 {
-	return sg_dma_address(piter->sg) + (piter->sg_pgoffset << PAGE_SHIFT);
+	return sg_dma_address(dma_iter->base.sg) +
+	       (dma_iter->base.sg_pgoffset << PAGE_SHIFT);
 }
 
 /**
@@ -385,11 +399,28 @@ static inline dma_addr_t sg_page_iter_dma_address(struct sg_page_iter *piter)
  * @piter:	page iterator to hold current page, sg, sg_pgoffset
  * @nents:	maximum number of sg entries to iterate over
  * @pgoffset:	starting page offset
+ *
+ * Callers may use sg_page_iter_page() to get each page pointer.
  */
 #define for_each_sg_page(sglist, piter, nents, pgoffset)		   \
 	for (__sg_page_iter_start((piter), (sglist), (nents), (pgoffset)); \
 	     __sg_page_iter_next(piter);)
 
+/**
+ * for_each_sg_dma_page - iterate over the pages of the given sg list
+ * @sglist:	sglist to iterate over
+ * @dma_iter:	page iterator to hold current page
+ * @dma_nents:	maximum number of sg entries to iterate over, this is the value
+ *              returned from dma_map_sg
+ * @pgoffset:	starting page offset
+ *
+ * Callers may use sg_page_iter_dma_address() to get each page's DMA address.
+ */
+#define for_each_sg_dma_page(sglist, dma_iter, dma_nents, pgoffset)            \
+	for (__sg_page_iter_start(&(dma_iter)->base, sglist, dma_nents,        \
+				  pgoffset);                                   \
+	     __sg_page_iter_dma_next(dma_iter);)
+
 /*
  * Mapping sg iterator
  *