IB/mlx5: Add UARs write-combining and non-cached mapping

By this patch, the user space library will be able to improve
performance using appropriate ringing DoorBell method according to the
memory type it asked for.

Currently only one mapping command is allowed for UARs:
MLX5_IB_MMAP_REGULAR_PAGE. Using this mapping, the kernel maps the
UARs to write-combining (WC) if the system supports it.
If the system is not supporting WC the UARs are mapped to
non-cached(NC). In this case the user space library can't tell which
mapping is applied.
This patch adds 2 new mapping commands: MLX5_IB_MMAP_WC_PAGE and
MLX5_IB_MMAP_NC_PAGE. For these commands the kernel maps exactly as
requested and fails if it can't.

Since there is no generic way to check if the requested memory region
can be mapped as WC, driver enables conclusive WC mapping only for
x86, PowerPC and ARM which support WC for the device's memory region.

Signed-off-by: Guy Levy <guyle@mellanox.com>
Signed-off-by: Moshe Lazer <moshel@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

2 files changed, 77 insertions, 21 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index f2a1ad9..7456e44 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -38,6 +38,9 @@
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/io-mapping.h>
+#if defined(CONFIG_X86)
+#include <asm/pat.h>
+#endif
 #include <linux/sched.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_addr.h>
@@ -1068,38 +1071,89 @@ static int get_index(unsigned long offset)
 	return get_arg(offset);
 }
 
+static inline char *mmap_cmd2str(enum mlx5_ib_mmap_cmd cmd)
+{
+	switch (cmd) {
+	case MLX5_IB_MMAP_WC_PAGE:
+		return "WC";
+	case MLX5_IB_MMAP_REGULAR_PAGE:
+		return "best effort WC";
+	case MLX5_IB_MMAP_NC_PAGE:
+		return "NC";
+	default:
+		return NULL;
+	}
+}
+
+static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
+		    struct vm_area_struct *vma, struct mlx5_uuar_info *uuari)
+{
+	int err;
+	unsigned long idx;
+	phys_addr_t pfn, pa;
+	pgprot_t prot;
+
+	switch (cmd) {
+	case MLX5_IB_MMAP_WC_PAGE:
+/* Some architectures don't support WC memory */
+#if defined(CONFIG_X86)
+		if (!pat_enabled())
+			return -EPERM;
+#elif !(defined(CONFIG_PPC) || (defined(CONFIG_ARM) && defined(CONFIG_MMU)))
+			return -EPERM;
+#endif
+	/* fall through */
+	case MLX5_IB_MMAP_REGULAR_PAGE:
+		/* For MLX5_IB_MMAP_REGULAR_PAGE do the best effort to get WC */
+		prot = pgprot_writecombine(vma->vm_page_prot);
+		break;
+	case MLX5_IB_MMAP_NC_PAGE:
+		prot = pgprot_noncached(vma->vm_page_prot);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+		return -EINVAL;
+
+	idx = get_index(vma->vm_pgoff);
+	if (idx >= uuari->num_uars)
+		return -EINVAL;
+
+	pfn = uar_index2pfn(dev, uuari->uars[idx].index);
+	mlx5_ib_dbg(dev, "uar idx 0x%lx, pfn %pa\n", idx, &pfn);
+
+	vma->vm_page_prot = prot;
+	err = io_remap_pfn_range(vma, vma->vm_start, pfn,
+				 PAGE_SIZE, vma->vm_page_prot);
+	if (err) {
+		mlx5_ib_err(dev, "io_remap_pfn_range failed with error=%d, vm_start=0x%lx, pfn=%pa, mmap_cmd=%s\n",
+			    err, vma->vm_start, &pfn, mmap_cmd2str(cmd));
+		return -EAGAIN;
+	}
+
+	pa = pfn << PAGE_SHIFT;
+	mlx5_ib_dbg(dev, "mapped %s at 0x%lx, PA %pa\n", mmap_cmd2str(cmd),
+		    vma->vm_start, &pa);
+
+	return 0;
+}
+
 static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma)
 {
 	struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
 	struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);
 	struct mlx5_uuar_info *uuari = &context->uuari;
 	unsigned long command;
-	unsigned long idx;
 	phys_addr_t pfn;
 
 	command = get_command(vma->vm_pgoff);
 	switch (command) {
+	case MLX5_IB_MMAP_WC_PAGE:
+	case MLX5_IB_MMAP_NC_PAGE:
 	case MLX5_IB_MMAP_REGULAR_PAGE:
-		if (vma->vm_end - vma->vm_start != PAGE_SIZE)
-			return -EINVAL;
-
-		idx = get_index(vma->vm_pgoff);
-		if (idx >= uuari->num_uars)
-			return -EINVAL;
-
-		pfn = uar_index2pfn(dev, uuari->uars[idx].index);
-		mlx5_ib_dbg(dev, "uar idx 0x%lx, pfn 0x%llx\n", idx,
-			    (unsigned long long)pfn);
-
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-		if (io_remap_pfn_range(vma, vma->vm_start, pfn,
-				       PAGE_SIZE, vma->vm_page_prot))
-			return -EAGAIN;
-
-		mlx5_ib_dbg(dev, "mapped WC at 0x%lx, PA 0x%llx\n",
-			    vma->vm_start,
-			    (unsigned long long)pfn << PAGE_SHIFT);
-		break;
+		return uar_mmap(dev, command, vma, uuari);
 
 	case MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES:
 		return -ENOSYS;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index b46c255..6e81217 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -70,6 +70,8 @@ enum {
 enum mlx5_ib_mmap_cmd {
 	MLX5_IB_MMAP_REGULAR_PAGE		= 0,
 	MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES	= 1,
+	MLX5_IB_MMAP_WC_PAGE			= 2,
+	MLX5_IB_MMAP_NC_PAGE			= 3,
 	/* 5 is chosen in order to be compatible with old versions of libmlx5 */
 	MLX5_IB_MMAP_CORE_CLOCK			= 5,
 };