Linux-NVDIMM Archive on lore.kernel.org
 help / color / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org
Cc: miklos@szeredi.hu, dgilbert@redhat.com, virtio-fs@redhat.com,
	Sebastien Boeuf <sebastien.boeuf@intel.com>,
	Liu Bo <bo.liu@linux.alibaba.com>,
	stefanha@redhat.com
Subject: [PATCH 07/19] virtio_fs, dax: Set up virtio_fs dax_device
Date: Wed, 21 Aug 2019 13:57:08 -0400
Message-ID: <20190821175720.25901-8-vgoyal@redhat.com> (raw)
In-Reply-To: <20190821175720.25901-1-vgoyal@redhat.com>

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

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

  parent reply index

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-21 17:57 [PATCH v3 00/19][RFC] virtio-fs: Enable DAX support Vivek Goyal
2019-08-21 17:57 ` [PATCH 01/19] dax: remove block device dependencies Vivek Goyal
2019-08-26 11:51   ` Christoph Hellwig
2019-08-27 16:38     ` Vivek Goyal
2019-08-28  6:58       ` Christoph Hellwig
2019-08-28 17:58         ` Vivek Goyal
2019-08-28 22:53           ` Dave Chinner
2019-08-29  0:04             ` Dan Williams
2019-08-29  9:32               ` Christoph Hellwig
2019-12-16 18:10               ` Vivek Goyal
2020-01-07 12:51                 ` Christoph Hellwig
2020-01-07 14:22                   ` Dan Williams
2020-01-07 17:07                     ` Darrick J. Wong
2020-01-07 17:29                       ` Dan Williams
2020-01-07 18:01                         ` Vivek Goyal
2020-01-07 18:07                           ` Dan Williams
2020-01-07 18:33                             ` Vivek Goyal
2020-01-07 18:49                               ` Dan Williams
2020-01-07 19:02                                 ` Darrick J. Wong
2020-01-07 19:46                                   ` Dan Williams
2020-01-07 23:38                                     ` Dan Williams
2020-01-09 11:24                                 ` Jan Kara
2020-01-09 20:03                                   ` Dan Williams
2020-01-10 12:36                                     ` Christoph Hellwig
2020-01-14 20:31                                     ` Vivek Goyal
2020-01-14 20:39                                       ` Dan Williams
2020-01-14 21:28                                         ` Vivek Goyal
2020-01-14 22:23                                           ` Dan Williams
2020-01-15 19:56                                             ` Vivek Goyal
2020-01-15 20:17                                               ` Dan Williams
2020-01-15 21:08                                                 ` Jeff Moyer
2020-01-16 18:09                                                   ` Dan Williams
2020-01-16 18:39                                                     ` Vivek Goyal
2020-01-16 19:09                                                       ` Dan Williams
2020-01-16 19:23                                                         ` Vivek Goyal
2020-02-11 17:33                                                     ` Vivek Goyal
2020-01-15  9:03                                           ` Jan Kara
2019-08-21 17:57 ` [PATCH 02/19] dax: Pass dax_dev to dax_writeback_mapping_range() Vivek Goyal
2019-08-26 11:53   ` Christoph Hellwig
2019-08-26 20:33     ` Vivek Goyal
2019-08-26 20:58       ` Vivek Goyal
2019-08-26 21:33         ` Dan Williams
2019-08-28  6:58         ` Christoph Hellwig
2020-01-03 14:12         ` Vivek Goyal
2020-01-03 18:12           ` Dan Williams
2020-01-03 18:18             ` Dan Williams
2020-01-03 18:33               ` Vivek Goyal
2020-01-03 19:30                 ` Dan Williams
2020-01-03 18:43               ` Vivek Goyal
2019-08-27 13:45       ` Jan Kara
2019-08-21 17:57 ` [PATCH 03/19] virtio: Add get_shm_region method Vivek Goyal
2019-08-21 17:57 ` [PATCH 04/19] virtio: Implement get_shm_region for PCI transport Vivek Goyal
2019-08-26  1:43   ` [Virtio-fs] " piaojun
2019-08-26 13:06     ` Vivek Goyal
2019-08-27  9:41       ` piaojun
2019-08-27  8:34   ` Cornelia Huck
2019-08-27  8:46     ` Cornelia Huck
2019-08-27 11:53     ` Vivek Goyal
2019-08-21 17:57 ` [PATCH 05/19] virtio: Implement get_shm_region for MMIO transport Vivek Goyal
2019-08-27  8:39   ` Cornelia Huck
2019-08-27 11:54     ` Vivek Goyal
2019-08-21 17:57 ` [PATCH 06/19] fuse, dax: add fuse_conn->dax_dev field Vivek Goyal
2019-08-21 17:57 ` Vivek Goyal [this message]
2019-08-21 17:57 ` [PATCH 08/19] fuse: Keep a list of free dax memory ranges Vivek Goyal
2019-08-21 17:57 ` [PATCH 09/19] fuse: implement FUSE_INIT map_alignment field Vivek Goyal
2019-08-21 17:57 ` [PATCH 10/19] fuse: Introduce setupmapping/removemapping commands Vivek Goyal
2019-08-21 17:57 ` [PATCH 11/19] fuse, dax: Implement dax read/write operations Vivek Goyal
2019-08-21 19:49   ` Liu Bo
2019-08-22 12:59     ` Vivek Goyal
2019-08-21 17:57 ` [PATCH 12/19] fuse, dax: add DAX mmap support Vivek Goyal
2019-08-21 17:57 ` [PATCH 13/19] fuse: Define dax address space operations Vivek Goyal
2019-08-21 17:57 ` [PATCH 14/19] fuse, dax: Take ->i_mmap_sem lock during dax page fault Vivek Goyal
2019-08-21 17:57 ` [PATCH 15/19] fuse: Maintain a list of busy elements Vivek Goyal
2019-08-21 17:57 ` [PATCH 16/19] dax: Create a range version of dax_layout_busy_page() Vivek Goyal
2019-08-21 17:57 ` [PATCH 17/19] fuse: Add logic to free up a memory range Vivek Goyal
2019-08-21 17:57 ` [PATCH 18/19] fuse: Release file in process context Vivek Goyal
2019-08-21 17:57 ` [PATCH 19/19] fuse: Take inode lock for dax inode truncation Vivek Goyal

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190821175720.25901-8-vgoyal@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=bo.liu@linux.alibaba.com \
    --cc=dgilbert@redhat.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=miklos@szeredi.hu \
    --cc=sebastien.boeuf@intel.com \
    --cc=stefanha@redhat.com \
    --cc=virtio-fs@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-NVDIMM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvdimm/0 linux-nvdimm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvdimm linux-nvdimm/ https://lore.kernel.org/linux-nvdimm \
		linux-nvdimm@lists.01.org
	public-inbox-index linux-nvdimm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.01.lists.linux-nvdimm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git