lkml.org 
[lkml]   [2019]   [Aug]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 07/19] virtio_fs, dax: Set up virtio_fs dax_device
Date
From: Stefan Hajnoczi <stefanha@redhat.com>

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>
---
fs/fuse/fuse_i.h | 1 +
fs/fuse/inode.c | 8 +++
fs/fuse/virtio_fs.c | 119 ++++++++++++++++++++++++++++++++-
include/uapi/linux/virtio_fs.h | 3 +
4 files changed, 129 insertions(+), 2 deletions(-)

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ecd9dbc3312e..7b365a29b156 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -72,6 +72,7 @@ struct fuse_mount_data {
unsigned group_id_present:1;
unsigned default_permissions:1;
unsigned allow_other:1;
+ unsigned dax:1;
unsigned destroy:1;
unsigned no_abort:1;
unsigned max_read;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 6d9258a4091a..0f58107a8269 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -436,6 +436,7 @@ enum {
OPT_ALLOW_OTHER,
OPT_MAX_READ,
OPT_BLKSIZE,
+ OPT_DAX,
OPT_ERR
};

@@ -448,6 +449,7 @@ static const match_table_t tokens = {
{OPT_ALLOW_OTHER, "allow_other"},
{OPT_MAX_READ, "max_read=%u"},
{OPT_BLKSIZE, "blksize=%u"},
+ {OPT_DAX, "dax"},
{OPT_ERR, NULL}
};

@@ -534,6 +536,10 @@ int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev,
d->blksize = value;
break;

+ case OPT_DAX:
+ d->dax = 1;
+ break;
+
default:
return 0;
}
@@ -562,6 +568,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
seq_printf(m, ",max_read=%u", fc->max_read);
if (sb->s_bdev && sb->s_blocksize != FUSE_DEFAULT_BLKSIZE)
seq_printf(m, ",blksize=%lu", sb->s_blocksize);
+ if (fc->dax_dev)
+ seq_printf(m, ",dax");
return 0;
}

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 706b27e0502a..32604722a7fb 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -5,6 +5,9 @@
*/

#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>
@@ -40,6 +43,12 @@ struct virtio_fs {
struct virtio_fs_vq *vqs;
unsigned nvqs; /* number of virtqueues */
unsigned num_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 {
@@ -433,6 +442,109 @@ 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 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,
+};
+
+static void virtio_fs_cleanup_dax(void *data)
+{
+ struct virtio_fs *fs = data;
+
+ kill_dax(fs->dax_dev);
+ put_dax(fs->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_DAX_DRIVER))
+ 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;
+ } else {
+ 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 (!fs->dax_dev)
+ return -ENOMEM;
+
+ return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax, fs);
+}
+
static int virtio_fs_probe(struct virtio_device *vdev)
{
struct virtio_fs *fs;
@@ -454,6 +566,10 @@ static int virtio_fs_probe(struct virtio_device *vdev)
/* TODO vq affinity */
/* TODO populate notifications vq */

+ 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.
*/
@@ -468,7 +584,6 @@ static int virtio_fs_probe(struct virtio_device *vdev)
out_vqs:
vdev->config->reset(vdev);
virtio_fs_cleanup_vqs(vdev, fs);
-
out:
vdev->priv = NULL;
return ret;
@@ -986,7 +1101,7 @@ static struct dentry *virtio_fs_mount(struct file_system_type *fs_type,
fc = kzalloc(sizeof(struct fuse_conn), GFP_KERNEL);
if (!fc)
return ERR_PTR(-ENOMEM);
- d.dax_dev = NULL;
+ d.dax_dev = d.dax ? fs->dax_dev : NULL;
fuse_conn_init(fc, get_user_ns(current_user_ns()), d.dax_dev,
&virtio_fs_fiq_ops, fs);
fc->release = fuse_free_conn;
diff --git a/include/uapi/linux/virtio_fs.h b/include/uapi/linux/virtio_fs.h
index 48f3590dcfbe..d4bb549568eb 100644
--- a/include/uapi/linux/virtio_fs.h
+++ b/include/uapi/linux/virtio_fs.h
@@ -38,4 +38,7 @@ struct virtio_fs_config {
__u32 num_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 */
--
2.20.1
\
 
 \ /
  Last update: 2019-08-21 20:01    [W:0.241 / U:4.964 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site