Merge branch 'linus/master' into rdma.git for-next

rdma.git merge resolution for the 4.19 merge window

Conflicts:
 drivers/infiniband/core/rdma_core.c
   - Use the rdma code and revise with the new spelling for
     atomic_fetch_add_unless
 drivers/nvme/host/rdma.c
   - Replace max_sge with max_send_sge in new blk code
 drivers/nvme/target/rdma.c
   - Use the blk code and revise to use NULL for ib_post_recv when
     appropriate
   - Replace max_sge with max_recv_sge in new blk code
 net/rds/ib_send.c
   - Use the net code and revise to use NULL for ib_post_recv when
     appropriate

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 149 insertions, 71 deletions

diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index bd56653b9bbc..c866a62f766d 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -6,6 +6,7 @@
  *
  * Copyright (c) 2006-2007, D G Murray.
  *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -26,10 +27,6 @@
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/mmu_notifier.h>
-#include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
@@ -37,6 +34,9 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/refcount.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/of_device.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/grant_table.h>
@@ -47,6 +47,11 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#include "gntdev-common.h"
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+#include "gntdev-dmabuf.h"
+#endif
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
 	      "Gerd Hoffmann <kraxel@redhat.com>");
@@ -62,51 +67,23 @@ static atomic_t pages_mapped = ATOMIC_INIT(0);
 static int use_ptemod;
 #define populate_freeable_maps use_ptemod
 
-struct gntdev_priv {
-	/* maps with visible offsets in the file descriptor */
-	struct list_head maps;
-	/* maps that are not visible; will be freed on munmap.
-	 * Only populated if populate_freeable_maps == 1 */
-	struct list_head freeable_maps;
-	/* lock protects maps and freeable_maps */
-	struct mutex lock;
-	struct mm_struct *mm;
-	struct mmu_notifier mn;
-};
-
-struct unmap_notify {
-	int flags;
-	/* Address relative to the start of the grant_map */
-	int addr;
-	int event;
-};
-
-struct grant_map {
-	struct list_head next;
-	struct vm_area_struct *vma;
-	int index;
-	int count;
-	int flags;
-	refcount_t users;
-	struct unmap_notify notify;
-	struct ioctl_gntdev_grant_ref *grants;
-	struct gnttab_map_grant_ref   *map_ops;
-	struct gnttab_unmap_grant_ref *unmap_ops;
-	struct gnttab_map_grant_ref   *kmap_ops;
-	struct gnttab_unmap_grant_ref *kunmap_ops;
-	struct page **pages;
-	unsigned long pages_vm_start;
-};
+static int unmap_grant_pages(struct gntdev_grant_map *map,
+			     int offset, int pages);
 
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
+static struct miscdevice gntdev_miscdev;
 
 /* ------------------------------------------------------------------ */
 
+bool gntdev_account_mapped_pages(int count)
+{
+	return atomic_add_return(count, &pages_mapped) > limit;
+}
+
 static void gntdev_print_maps(struct gntdev_priv *priv,
 			      char *text, int text_index)
 {
 #ifdef DEBUG
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("%s: maps list (priv %p)\n", __func__, priv);
 	list_for_each_entry(map, &priv->maps, next)
@@ -116,13 +93,32 @@ static void gntdev_print_maps(struct gntdev_priv *priv,
 #endif
 }
 
-static void gntdev_free_map(struct grant_map *map)
+static void gntdev_free_map(struct gntdev_grant_map *map)
 {
 	if (map == NULL)
 		return;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	if (map->dma_vaddr) {
+		struct gnttab_dma_alloc_args args;
+
+		args.dev = map->dma_dev;
+		args.coherent = !!(map->dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = map->count;
+		args.pages = map->pages;
+		args.frames = map->frames;
+		args.vaddr = map->dma_vaddr;
+		args.dev_bus_addr = map->dma_bus_addr;
+
+		gnttab_dma_free_pages(&args);
+	} else
+#endif
 	if (map->pages)
 		gnttab_free_pages(map->count, map->pages);
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	kfree(map->frames);
+#endif
 	kfree(map->pages);
 	kfree(map->grants);
 	kfree(map->map_ops);
@@ -132,12 +128,13 @@ static void gntdev_free_map(struct grant_map *map)
 	kfree(map);
 }
 
-static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags)
 {
-	struct grant_map *add;
+	struct gntdev_grant_map *add;
 	int i;
 
-	add = kzalloc(sizeof(struct grant_map), GFP_KERNEL);
+	add = kzalloc(sizeof(*add), GFP_KERNEL);
 	if (NULL == add)
 		return NULL;
 
@@ -155,6 +152,37 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	    NULL == add->pages)
 		goto err;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	add->dma_flags = dma_flags;
+
+	/*
+	 * Check if this mapping is requested to be backed
+	 * by a DMA buffer.
+	 */
+	if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) {
+		struct gnttab_dma_alloc_args args;
+
+		add->frames = kcalloc(count, sizeof(add->frames[0]),
+				      GFP_KERNEL);
+		if (!add->frames)
+			goto err;
+
+		/* Remember the device, so we can free DMA memory. */
+		add->dma_dev = priv->dma_dev;
+
+		args.dev = priv->dma_dev;
+		args.coherent = !!(dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = count;
+		args.pages = add->pages;
+		args.frames = add->frames;
+
+		if (gnttab_dma_alloc_pages(&args))
+			goto err;
+
+		add->dma_vaddr = args.vaddr;
+		add->dma_bus_addr = args.dev_bus_addr;
+	} else
+#endif
 	if (gnttab_alloc_pages(count, add->pages))
 		goto err;
 
@@ -176,9 +204,9 @@ err:
 	return NULL;
 }
 
-static void gntdev_add_map(struct gntdev_priv *priv, struct grant_map *add)
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (add->index + add->count < map->index) {
@@ -193,10 +221,10 @@ done:
 	gntdev_print_maps(priv, "[new]", add->index);
 }
 
-static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
-		int index, int count)
+static struct gntdev_grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
+						      int index, int count)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (map->index != index)
@@ -208,7 +236,7 @@ static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
 	return NULL;
 }
 
-static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 {
 	if (!map)
 		return;
@@ -239,7 +267,7 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
 static int find_grant_ptes(pte_t *pte, pgtable_t token,
 		unsigned long addr, void *data)
 {
-	struct grant_map *map = data;
+	struct gntdev_grant_map *map = data;
 	unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
 	int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte;
 	u64 pte_maddr;
@@ -272,7 +300,7 @@ static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token,
 }
 #endif
 
-static int map_grant_pages(struct grant_map *map)
+int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 {
 	int i, err = 0;
 
@@ -325,11 +353,20 @@ static int map_grant_pages(struct grant_map *map)
 		map->unmap_ops[i].handle = map->map_ops[i].handle;
 		if (use_ptemod)
 			map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+		else if (map->dma_vaddr) {
+			unsigned long bfn;
+
+			bfn = pfn_to_bfn(page_to_pfn(map->pages[i]));
+			map->unmap_ops[i].dev_bus_addr = __pfn_to_phys(bfn);
+		}
+#endif
 	}
 	return err;
 }
 
-static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			       int pages)
 {
 	int i, err = 0;
 	struct gntab_unmap_queue_data unmap_data;
@@ -364,7 +401,8 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
 	return err;
 }
 
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			     int pages)
 {
 	int range, err = 0;
 
@@ -396,7 +434,7 @@ static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
 
 static void gntdev_vma_open(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	pr_debug("gntdev_vma_open %p\n", vma);
 	refcount_inc(&map->users);
@@ -404,7 +442,7 @@ static void gntdev_vma_open(struct vm_area_struct *vma)
 
 static void gntdev_vma_close(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 	struct file *file = vma->vm_file;
 	struct gntdev_priv *priv = file->private_data;
 
@@ -428,7 +466,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma,
 						 unsigned long addr)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	return map->pages[(addr - map->pages_vm_start) >> PAGE_SHIFT];
 }
@@ -441,7 +479,7 @@ static const struct vm_operations_struct gntdev_vmops = {
 
 /* ------------------------------------------------------------------ */
 
-static void unmap_if_in_range(struct grant_map *map,
+static void unmap_if_in_range(struct gntdev_grant_map *map,
 			      unsigned long start, unsigned long end)
 {
 	unsigned long mstart, mend;
@@ -470,7 +508,7 @@ static void mn_invl_range_start(struct mmu_notifier *mn,
 				unsigned long start, unsigned long end)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	mutex_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
@@ -486,7 +524,7 @@ static void mn_release(struct mmu_notifier *mn,
 		       struct mm_struct *mm)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	mutex_lock(&priv->lock);
@@ -531,6 +569,15 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	INIT_LIST_HEAD(&priv->freeable_maps);
 	mutex_init(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	priv->dmabuf_priv = gntdev_dmabuf_init();
+	if (IS_ERR(priv->dmabuf_priv)) {
+		ret = PTR_ERR(priv->dmabuf_priv);
+		kfree(priv);
+		return ret;
+	}
+#endif
+
 	if (use_ptemod) {
 		priv->mm = get_task_mm(current);
 		if (!priv->mm) {
@@ -548,6 +595,17 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	}
 
 	flip->private_data = priv;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	priv->dma_dev = gntdev_miscdev.this_device;
+
+	/*
+	 * The device is not spawn from a device tree, so arch_setup_dma_ops
+	 * is not called, thus leaving the device with dummy DMA ops.
+	 * Fix this by calling of_dma_configure() with a NULL node to set
+	 * default DMA ops.
+	 */
+	of_dma_configure(priv->dma_dev, NULL, true);
+#endif
 	pr_debug("priv %p\n", priv);
 
 	return 0;
@@ -556,21 +614,27 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 static int gntdev_release(struct inode *inode, struct file *flip)
 {
 	struct gntdev_priv *priv = flip->private_data;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("priv %p\n", priv);
 
 	mutex_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
-		map = list_entry(priv->maps.next, struct grant_map, next);
+		map = list_entry(priv->maps.next,
+				 struct gntdev_grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
 	WARN_ON(!list_empty(&priv->freeable_maps));
 	mutex_unlock(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	gntdev_dmabuf_fini(priv->dmabuf_priv);
+#endif
+
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
+
 	kfree(priv);
 	return 0;
 }
@@ -579,7 +643,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 				       struct ioctl_gntdev_map_grant_ref __user *u)
 {
 	struct ioctl_gntdev_map_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -589,11 +653,11 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 		return -EINVAL;
 
 	err = -ENOMEM;
-	map = gntdev_alloc_map(priv, op.count);
+	map = gntdev_alloc_map(priv, op.count, 0 /* This is not a dma-buf. */);
 	if (!map)
 		return err;
 
-	if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
+	if (unlikely(gntdev_account_mapped_pages(op.count))) {
 		pr_debug("can't map: over limit\n");
 		gntdev_put_map(NULL, map);
 		return err;
@@ -620,7 +684,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 					 struct ioctl_gntdev_unmap_grant_ref __user *u)
 {
 	struct ioctl_gntdev_unmap_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err = -ENOENT;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -646,7 +710,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 {
 	struct ioctl_gntdev_get_offset_for_vaddr op;
 	struct vm_area_struct *vma;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rv = -EINVAL;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -677,7 +741,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 {
 	struct ioctl_gntdev_unmap_notify op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rc;
 	int out_flags;
 	unsigned int out_event;
@@ -962,6 +1026,20 @@ static long gntdev_ioctl(struct file *flip,
 	case IOCTL_GNTDEV_GRANT_COPY:
 		return gntdev_ioctl_grant_copy(priv, ptr);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	case IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS:
+		return gntdev_ioctl_dmabuf_exp_from_refs(priv, use_ptemod, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED:
+		return gntdev_ioctl_dmabuf_exp_wait_released(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_TO_REFS:
+		return gntdev_ioctl_dmabuf_imp_to_refs(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_RELEASE:
+		return gntdev_ioctl_dmabuf_imp_release(priv, ptr);
+#endif
+
 	default:
 		pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
 		return -ENOIOCTLCMD;
@@ -975,7 +1053,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	struct gntdev_priv *priv = flip->private_data;
 	int index = vma->vm_pgoff;
 	int count = vma_pages(vma);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int i, err = -EINVAL;
 
 	if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
@@ -1032,7 +1110,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		}
 	}
 
-	err = map_grant_pages(map);
+	err = gntdev_map_grant_pages(map);
 	if (err)
 		goto out_put_map;