linux-nvdimm.lists.01.org archive mirror
 help / color / mirror / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org, virtio-fs@redhat.com,
	miklos@szeredi.hu
Cc: stefanha@redhat.com, dgilbert@redhat.com, mst@redhat.com,
	Sebastien Boeuf <sebastien.boeuf@intel.com>,
	Liu Bo <bo.liu@linux.alibaba.com>
Subject: [PATCH 09/20] virtio_fs, dax: Set up virtio_fs dax_device
Date: Wed,  4 Mar 2020 11:58:34 -0500	[thread overview]
Message-ID: <20200304165845.3081-10-vgoyal@redhat.com> (raw)
In-Reply-To: <20200304165845.3081-1-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/virtio_fs.c            | 115 +++++++++++++++++++++++++++++++++
 include/uapi/linux/virtio_fs.h |   3 +
 2 files changed, 118 insertions(+)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 62cdd6817b5b..b0574b208cd5 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>
@@ -50,6 +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 {
@@ -690,6 +699,108 @@ 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;
@@ -711,6 +822,10 @@ 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.
 	 */
diff --git a/include/uapi/linux/virtio_fs.h b/include/uapi/linux/virtio_fs.h
index b02eb2ac3d99..2f64abce781f 100644
--- a/include/uapi/linux/virtio_fs.h
+++ b/include/uapi/linux/virtio_fs.h
@@ -16,4 +16,7 @@ struct virtio_fs_config {
 	__u32 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 */
-- 
2.20.1
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org

  parent reply	other threads:[~2020-03-04 16:59 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-04 16:58 [PATCH 00/20] virtiofs: Add DAX support Vivek Goyal
2020-03-04 16:58 ` [PATCH 01/20] dax: Modify bdev_dax_pgoff() to handle NULL bdev Vivek Goyal
2020-03-04 16:58 ` [PATCH 02/20] dax: Create a range version of dax_layout_busy_page() Vivek Goyal
2020-03-10 15:19   ` Ira Weiny
2020-03-10 20:29     ` Vivek Goyal
2020-03-04 16:58 ` [PATCH 03/20] virtio: Add get_shm_region method Vivek Goyal
2020-03-10 10:53   ` Stefan Hajnoczi
2020-03-04 16:58 ` [PATCH 04/20] virtio: Implement get_shm_region for PCI transport Vivek Goyal
2020-03-10 11:04   ` Stefan Hajnoczi
2020-03-10 18:19     ` Vivek Goyal
2020-03-11 17:34       ` Stefan Hajnoczi
2020-03-11 19:29         ` Vivek Goyal
2020-03-10 11:12   ` Michael S. Tsirkin
2020-03-10 18:47     ` Vivek Goyal
2020-03-10 21:27       ` Michael S. Tsirkin
2020-03-04 16:58 ` [PATCH 05/20] virtio: Implement get_shm_region for MMIO transport Vivek Goyal
2020-03-10 11:06   ` Stefan Hajnoczi
2020-03-04 16:58 ` [PATCH 06/20] virtiofs: Provide a helper function for virtqueue initialization Vivek Goyal
2020-03-10 14:10   ` Miklos Szeredi
2020-03-04 16:58 ` [PATCH 07/20] fuse: Get rid of no_mount_options Vivek Goyal
2020-03-10 14:12   ` Miklos Szeredi
2020-03-04 16:58 ` [PATCH 08/20] fuse,virtiofs: Add a mount option to enable dax Vivek Goyal
2020-03-10 14:16   ` Miklos Szeredi
2020-03-04 16:58 ` Vivek Goyal [this message]
2020-03-04 16:58 ` [PATCH 10/20] fuse,virtiofs: Keep a list of free dax memory ranges Vivek Goyal
2020-03-10 19:29   ` Miklos Szeredi
2020-03-04 16:58 ` [PATCH 11/20] fuse: implement FUSE_INIT map_alignment field Vivek Goyal
2020-03-10 19:31   ` Miklos Szeredi
2020-03-04 16:58 ` [PATCH 12/20] fuse: Introduce setupmapping/removemapping commands Vivek Goyal
2020-03-10 19:49   ` Miklos Szeredi
2020-03-10 20:33     ` Vivek Goyal
2020-03-11  7:03       ` Amir Goldstein
2020-03-11 14:19         ` Miklos Szeredi
2020-03-11 14:41           ` Vivek Goyal
2020-03-11 15:12             ` Miklos Szeredi
2020-03-04 16:58 ` [PATCH 13/20] fuse, dax: Implement dax read/write operations Vivek Goyal
2020-03-12  9:43   ` Miklos Szeredi
2020-03-12 16:02     ` Vivek Goyal
2020-03-13 10:18       ` Miklos Szeredi
2020-03-13 13:41         ` Vivek Goyal
2020-04-04  0:25   ` Liu Bo
2020-04-14 12:54     ` Vivek Goyal
2020-03-04 16:58 ` [PATCH 14/20] fuse,dax: add DAX mmap support Vivek Goyal
2020-03-04 16:58 ` [PATCH 15/20] fuse, dax: Take ->i_mmap_sem lock during dax page fault Vivek Goyal
2020-03-04 16:58 ` [PATCH 16/20] fuse,virtiofs: Define dax address space operations Vivek Goyal
2020-03-04 16:58 ` [PATCH 17/20] fuse,virtiofs: Maintain a list of busy elements Vivek Goyal
2020-03-04 16:58 ` [PATCH 18/20] fuse: Release file in process context Vivek Goyal
2020-03-04 16:58 ` [PATCH 19/20] fuse: Take inode lock for dax inode truncation Vivek Goyal
2020-03-04 16:58 ` [PATCH 20/20] fuse,virtiofs: Add logic to free up a memory range Vivek Goyal
2020-03-11  5:16   ` Liu Bo
2020-03-11 12:59     ` Vivek Goyal
2020-03-11 17:24       ` Liu Bo
2020-03-26  0:09   ` Liu Bo
2020-03-27 14:01     ` Vivek Goyal
2020-03-27 22:06       ` Liu Bo
2020-04-14 19:30         ` Vivek Goyal
2020-04-15 17:22           ` Liu Bo
2020-04-16 19:05             ` Vivek Goyal
2020-04-17 18:05               ` Liu Bo
2020-03-11  5:22 ` [PATCH 00/20] virtiofs: Add DAX support Amir Goldstein
2020-03-11 13:09   ` Vivek Goyal
2020-03-11 18:48   ` Vivek Goyal
2020-03-11 19:32     ` Amir Goldstein
2020-03-11 19:39       ` Vivek Goyal
2020-03-11 13:38 ` Patrick Ohly
2020-03-16 13:02   ` Vivek Goyal
2020-03-17  8:28     ` Patrick Ohly

Reply instructions:

You may reply publicly 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=20200304165845.3081-10-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=mst@redhat.com \
    --cc=sebastien.boeuf@intel.com \
    --cc=stefanha@redhat.com \
    --cc=virtio-fs@redhat.com \
    --subject='Re: [PATCH 09/20] virtio_fs, dax: Set up virtio_fs dax_device' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).