virtiofs: set up virtio_fs dax_device

Setup a dax device.

Use the shm capability to find the cache entry and map it.

The DAX window is accessed by the fs/dax.c infrastructure and must have
struct pages (at least on x86).  Use devm_memremap_pages() to map the
DAX window PCI BAR and allocate struct page.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

fs/fuse/virtio_fs.c

@@ -5,12 +5,16 @@
  */
 
 #include <linux/fs.h>
+#include <linux/dax.h>
+#include <linux/pci.h>
+#include <linux/pfn_t.h>
 #include <linux/module.h>
 #include <linux/virtio.h>
 #include <linux/virtio_fs.h>
 #include <linux/delay.h>
 #include <linux/fs_context.h>
 #include <linux/highmem.h>
+#include <linux/uio.h>
 #include "fuse_i.h"
 
 /* List of virtio-fs device instances and a lock for the list. Also provides
@@ -49,6 +53,12 @@ struct virtio_fs {
 	struct virtio_fs_vq *vqs;
 	unsigned int nvqs;               /* number of virtqueues */
 	unsigned int num_request_queues; /* number of request queues */
+	struct dax_device *dax_dev;
+
+	/* DAX memory window where file contents are mapped */
+	void *window_kaddr;
+	phys_addr_t window_phys_addr;
+	size_t window_len;
 };
 
 struct virtio_fs_forget_req {
@@ -686,6 +696,130 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev,
 	vdev->config->del_vqs(vdev);
 }
 
+/* Map a window offset to a page frame number.  The window offset will have
+ * been produced by .iomap_begin(), which maps a file offset to a window
+ * offset.
+ */
+static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+				    long nr_pages, void **kaddr, pfn_t *pfn)
+{
+	struct virtio_fs *fs = dax_get_private(dax_dev);
+	phys_addr_t offset = PFN_PHYS(pgoff);
+	size_t max_nr_pages = fs->window_len/PAGE_SIZE - pgoff;
+
+	if (kaddr)
+		*kaddr = fs->window_kaddr + offset;
+	if (pfn)
+		*pfn = phys_to_pfn_t(fs->window_phys_addr + offset,
+					PFN_DEV | PFN_MAP);
+	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
+}
+
+static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev,
+				       pgoff_t pgoff, void *addr,
+				       size_t bytes, struct iov_iter *i)
+{
+	return copy_from_iter(addr, bytes, i);
+}
+
+static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev,
+				       pgoff_t pgoff, void *addr,
+				       size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
+static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
+				     pgoff_t pgoff, size_t nr_pages)
+{
+	long rc;
+	void *kaddr;
+
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	if (rc < 0)
+		return rc;
+	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
+	dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT);
+	return 0;
+}
+
+static const struct dax_operations virtio_fs_dax_ops = {
+	.direct_access = virtio_fs_direct_access,
+	.copy_from_iter = virtio_fs_copy_from_iter,
+	.copy_to_iter = virtio_fs_copy_to_iter,
+	.zero_page_range = virtio_fs_zero_page_range,
+};
+
+static void virtio_fs_cleanup_dax(void *data)
+{
+	struct dax_device *dax_dev = data;
+
+	kill_dax(dax_dev);
+	put_dax(dax_dev);
+}
+
+static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
+{
+	struct virtio_shm_region cache_reg;
+	struct dev_pagemap *pgmap;
+	bool have_cache;
+
+	if (!IS_ENABLED(CONFIG_FUSE_DAX))
+		return 0;
+
+	/* Get cache region */
+	have_cache = virtio_get_shm_region(vdev, &cache_reg,
+					   (u8)VIRTIO_FS_SHMCAP_ID_CACHE);
+	if (!have_cache) {
+		dev_notice(&vdev->dev, "%s: No cache capability\n", __func__);
+		return 0;
+	}
+
+	if (!devm_request_mem_region(&vdev->dev, cache_reg.addr, cache_reg.len,
+				     dev_name(&vdev->dev))) {
+		dev_warn(&vdev->dev, "could not reserve region addr=0x%llx len=0x%llx\n",
+			 cache_reg.addr, cache_reg.len);
+		return -EBUSY;
+	}
+
+	dev_notice(&vdev->dev, "Cache len: 0x%llx @ 0x%llx\n", cache_reg.len,
+		   cache_reg.addr);
+
+	pgmap = devm_kzalloc(&vdev->dev, sizeof(*pgmap), GFP_KERNEL);
+	if (!pgmap)
+		return -ENOMEM;
+
+	pgmap->type = MEMORY_DEVICE_FS_DAX;
+
+	/* Ideally we would directly use the PCI BAR resource but
+	 * devm_memremap_pages() wants its own copy in pgmap.  So
+	 * initialize a struct resource from scratch (only the start
+	 * and end fields will be used).
+	 */
+	pgmap->res = (struct resource){
+		.name = "virtio-fs dax window",
+		.start = (phys_addr_t) cache_reg.addr,
+		.end = (phys_addr_t) cache_reg.addr + cache_reg.len - 1,
+	};
+
+	fs->window_kaddr = devm_memremap_pages(&vdev->dev, pgmap);
+	if (IS_ERR(fs->window_kaddr))
+		return PTR_ERR(fs->window_kaddr);
+
+	fs->window_phys_addr = (phys_addr_t) cache_reg.addr;
+	fs->window_len = (phys_addr_t) cache_reg.len;
+
+	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n",
+		__func__, fs->window_kaddr, cache_reg.addr, cache_reg.len);
+
+	fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0);
+	if (IS_ERR(fs->dax_dev))
+		return PTR_ERR(fs->dax_dev);
+
+	return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax,
+					fs->dax_dev);
+}
+
 static int virtio_fs_probe(struct virtio_device *vdev)
 {
 	struct virtio_fs *fs;
@@ -707,6 +841,10 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 
 	/* TODO vq affinity */
 
+	ret = virtio_fs_setup_dax(vdev, fs);
+	if (ret < 0)
+		goto out_vqs;
+
 	/* Bring the device online in case the filesystem is mounted and
 	 * requests need to be sent before we return.
 	 */

include/uapi/linux/virtio_fs.h

@@ -16,4 +16,7 @@ struct virtio_fs_config {
 	__le32 num_request_queues;
 } __attribute__((packed));
 
+/* For the id field in virtio_pci_shm_cap */
+#define VIRTIO_FS_SHMCAP_ID_CACHE 0
+
 #endif /* _UAPI_LINUX_VIRTIO_FS_H */