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

Pull infiniband updates from Roland Dreier:
 "Main batch of InfiniBand/RDMA changes for 3.19:

   - On-demand paging support in core midlayer and mlx5 driver.  This
     lets userspace create non-pinned memory regions and have the
     adapter HW trigger page faults.
   - iSER and IPoIB updates and fixes.
   - Low-level HW driver updates for cxgb4, mlx4 and ocrdma.
   - Other miscellaneous fixes"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (56 commits)
  IB/mlx5: Implement on demand paging by adding support for MMU notifiers
  IB/mlx5: Add support for RDMA read/write responder page faults
  IB/mlx5: Handle page faults
  IB/mlx5: Page faults handling infrastructure
  IB/mlx5: Add mlx5_ib_update_mtt to update page tables after creation
  IB/mlx5: Changes in memory region creation to support on-demand paging
  IB/mlx5: Implement the ODP capability query verb
  mlx5_core: Add support for page faults events and low level handling
  mlx5_core: Re-add MLX5_DEV_CAP_FLAG_ON_DMND_PG flag
  IB/srp: Allow newline separator for connection string
  IB/core: Implement support for MMU notifiers regarding on demand paging regions
  IB/core: Add support for on demand paging regions
  IB/core: Add flags for on demand paging support
  IB/core: Add support for extended query device caps
  IB/mlx5: Add function to read WQE from user-space
  IB/core: Add umem function to read data from user-space
  IB/core: Replace ib_umem's offset field with a full address
  IB/mlx5: Enhance UMR support to allow partial page table update
  IB/mlx5: Remove per-MR pas and dma pointers
  RDMA/ocrdma: Always resolve destination mac from GRH for UD QPs
  ...

1 files changed, 65 insertions, 4 deletions

diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index dae07eae9507..b56e4c5593ee 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -32,6 +32,7 @@
 
 #include <linux/module.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_umem_odp.h>
 #include "mlx5_ib.h"
 
 /* @umem: umem object to scan
@@ -57,6 +58,17 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	int entry;
 	unsigned long page_shift = ilog2(umem->page_size);
 
+	/* With ODP we must always match OS page size. */
+	if (umem->odp_data) {
+		*count = ib_umem_page_count(umem);
+		*shift = PAGE_SHIFT;
+		*ncont = *count;
+		if (order)
+			*order = ilog2(roundup_pow_of_two(*count));
+
+		return;
+	}
+
 	addr = addr >> page_shift;
 	tmp = (unsigned long)addr;
 	m = find_first_bit(&tmp, sizeof(tmp));
@@ -108,8 +120,36 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	*count = i;
 }
 
-void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
-			  int page_shift, __be64 *pas, int umr)
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
+{
+	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
+
+	if (umem_dma & ODP_READ_ALLOWED_BIT)
+		mtt_entry |= MLX5_IB_MTT_READ;
+	if (umem_dma & ODP_WRITE_ALLOWED_BIT)
+		mtt_entry |= MLX5_IB_MTT_WRITE;
+
+	return mtt_entry;
+}
+#endif
+
+/*
+ * Populate the given array with bus addresses from the umem.
+ *
+ * dev - mlx5_ib device
+ * umem - umem to use to fill the pages
+ * page_shift - determines the page size used in the resulting array
+ * offset - offset into the umem to start from,
+ *          only implemented for ODP umems
+ * num_pages - total number of pages to fill
+ * pas - bus addresses array to fill
+ * access_flags - access flags to set on all present pages.
+		  use enum mlx5_ib_mtt_access_flags for this.
+ */
+void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
+			    int page_shift, size_t offset, size_t num_pages,
+			    __be64 *pas, int access_flags)
 {
 	unsigned long umem_page_shift = ilog2(umem->page_size);
 	int shift = page_shift - umem_page_shift;
@@ -120,6 +160,21 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	int len;
 	struct scatterlist *sg;
 	int entry;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	const bool odp = umem->odp_data != NULL;
+
+	if (odp) {
+		WARN_ON(shift != 0);
+		WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE));
+
+		for (i = 0; i < num_pages; ++i) {
+			dma_addr_t pa = umem->odp_data->dma_list[offset + i];
+
+			pas[i] = cpu_to_be64(umem_dma_to_mtt(pa));
+		}
+		return;
+	}
+#endif
 
 	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
@@ -128,8 +183,7 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 		for (k = 0; k < len; k++) {
 			if (!(i & mask)) {
 				cur = base + (k << umem_page_shift);
-				if (umr)
-					cur |= 3;
+				cur |= access_flags;
 
 				pas[i >> shift] = cpu_to_be64(cur);
 				mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
@@ -142,6 +196,13 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	}
 }
 
+void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
+			  int page_shift, __be64 *pas, int access_flags)
+{
+	return __mlx5_ib_populate_pas(dev, umem, page_shift, 0,
+				      ib_umem_num_pages(umem), pas,
+				      access_flags);
+}
 int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset)
 {
 	u64 page_size;