LKML 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,
	kvm@vger.kernel.org
Cc: vgoyal@redhat.com, miklos@szeredi.hu, stefanha@redhat.com,
	dgilbert@redhat.com, sweil@redhat.com, swhiteho@redhat.com
Subject: [PATCH 15/52] fuse: map virtio_fs DAX window BAR
Date: Mon, 10 Dec 2018 12:12:41 -0500
Message-ID: <20181210171318.16998-16-vgoyal@redhat.com> (raw)
In-Reply-To: <20181210171318.16998-1-vgoyal@redhat.com>

From: Stefan Hajnoczi <stefanha@redhat.com>

Experimental QEMU code introduces an MMIO BAR for mapping portions of
files in the virtio-fs device.  Map this BAR so that FUSE DAX can access
file contents from the host page cache.

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>
---
 fs/fuse/virtio_fs.c | 166 ++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 143 insertions(+), 23 deletions(-)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index ba615ec2603e..87b7e42a6763 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -6,12 +6,18 @@
 
 #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 "fuse_i.h"
 
+enum {
+	/* PCI BAR number of the virtio-fs DAX window */
+	VIRTIO_FS_WINDOW_BAR = 2,
+};
+
 /* List of virtio-fs device instances and a lock for the list */
 static DEFINE_MUTEX(virtio_fs_mutex);
 static LIST_HEAD(virtio_fs_instances);
@@ -24,6 +30,18 @@ struct virtio_fs_vq {
 	char name[24];
 } ____cacheline_aligned_in_smp;
 
+/* State needed for devm_memremap_pages().  This API is called on the
+ * underlying pci_dev instead of struct virtio_fs (layering violation).  Since
+ * the memremap release function only gets called when the pci_dev is released,
+ * keep the associated state separate from struct virtio_fs (it has a different
+ * lifecycle from pci_dev).
+ */
+struct virtio_fs_memremap_info {
+	struct dev_pagemap pgmap;
+	struct percpu_ref ref;
+	struct completion completion;
+};
+
 /* A virtio-fs device instance */
 struct virtio_fs {
 	struct list_head list;    /* on virtio_fs_instances */
@@ -36,6 +54,7 @@ struct virtio_fs {
 	/* DAX memory window where file contents are mapped */
 	void *window_kaddr;
 	phys_addr_t window_phys_addr;
+	size_t window_len;
 };
 
 static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
@@ -395,6 +414,127 @@ static const struct dax_operations virtio_fs_dax_ops = {
 	.copy_to_iter = virtio_fs_copy_to_iter,
 };
 
+static void virtio_fs_percpu_release(struct percpu_ref *ref)
+{
+	struct virtio_fs_memremap_info *mi =
+		container_of(ref, struct virtio_fs_memremap_info, ref);
+
+	complete(&mi->completion);
+}
+
+static void virtio_fs_percpu_exit(void *data)
+{
+	struct virtio_fs_memremap_info *mi = data;
+
+	wait_for_completion(&mi->completion);
+	percpu_ref_exit(&mi->ref);
+}
+
+static void virtio_fs_percpu_kill(void *data)
+{
+	percpu_ref_kill(data);
+}
+
+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_fs_memremap_info *mi;
+	struct dev_pagemap *pgmap;
+	struct pci_dev *pci_dev;
+	phys_addr_t phys_addr;
+	size_t len;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_DAX_DRIVER))
+		return 0;
+
+	/* HACK implement VIRTIO shared memory regions instead of
+	 * directly accessing the PCI BAR from a virtio device driver.
+	 */
+	pci_dev = container_of(vdev->dev.parent, struct pci_dev, dev);
+
+	/* TODO Is this safe - the virtio_pci_* driver doesn't use managed
+	 * device APIs? */
+	ret = pcim_enable_device(pci_dev);
+	if (ret < 0)
+		return ret;
+
+	/* TODO handle case where device doesn't expose BAR? */
+	ret = pci_request_region(pci_dev, VIRTIO_FS_WINDOW_BAR,
+				 "virtio-fs-window");
+	if (ret < 0) {
+		dev_err(&vdev->dev, "%s: failed to request window BAR\n",
+			__func__);
+		return ret;
+	}
+
+	phys_addr = pci_resource_start(pci_dev, VIRTIO_FS_WINDOW_BAR);
+	len = pci_resource_len(pci_dev, VIRTIO_FS_WINDOW_BAR);
+
+	mi = devm_kzalloc(&pci_dev->dev, sizeof(*mi), GFP_KERNEL);
+	if (!mi)
+		return -ENOMEM;
+
+	init_completion(&mi->completion);
+	ret = percpu_ref_init(&mi->ref, virtio_fs_percpu_release, 0,
+			      GFP_KERNEL);
+	if (ret < 0) {
+		dev_err(&vdev->dev, "%s: percpu_ref_init failed (%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	ret = devm_add_action(&pci_dev->dev, virtio_fs_percpu_exit, mi);
+	if (ret < 0) {
+		percpu_ref_exit(&mi->ref);
+		return ret;
+	}
+
+	pgmap = &mi->pgmap;
+	pgmap->altmap_valid = false;
+	pgmap->ref = &mi->ref;
+	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,
+		.end = phys_addr + len,
+	};
+
+	fs->window_kaddr = devm_memremap_pages(&pci_dev->dev, pgmap);
+	if (IS_ERR(fs->window_kaddr))
+		return PTR_ERR(fs->window_kaddr);
+
+	ret = devm_add_action_or_reset(&pci_dev->dev, virtio_fs_percpu_kill,
+				       &mi->ref);
+	if (ret < 0)
+		return ret;
+
+	fs->window_phys_addr = phys_addr;
+	fs->window_len = len;
+
+	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len %zu\n",
+		__func__, fs->window_kaddr, phys_addr, len);
+
+	fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops);
+	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;
@@ -416,16 +556,9 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 	/* TODO vq affinity */
 	/* TODO populate notifications vq */
 
-	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
-		/* TODO map window */
-		fs->window_kaddr = NULL;
-		fs->window_phys_addr = 0;
-
-		fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops);
-		if (!fs->dax_dev)
-			goto out_vqs; /* TODO handle case where device doesn't expose
-					 BAR */
-	}
+	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.
@@ -441,13 +574,6 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 out_vqs:
 	vdev->config->reset(vdev);
 	virtio_fs_cleanup_vqs(vdev, fs);
-
-	if (fs->dax_dev) {
-		kill_dax(fs->dax_dev);
-		put_dax(fs->dax_dev);
-		fs->dax_dev = NULL;
-	}
-
 out:
 	vdev->priv = NULL;
 	return ret;
@@ -466,12 +592,6 @@ static void virtio_fs_remove(struct virtio_device *vdev)
 	list_del(&fs->list);
 	mutex_unlock(&virtio_fs_mutex);
 
-	if (fs->dax_dev) {
-		kill_dax(fs->dax_dev);
-		put_dax(fs->dax_dev);
-		fs->dax_dev = NULL;
-	}
-
 	vdev->priv = NULL;
 }
 
-- 
2.13.6


  parent reply index

Thread overview: 98+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-12-10 17:12 [PATCH 00/52] [RFC] virtio-fs: shared file system for virtual machines Vivek Goyal
2018-12-10 17:12 ` [PATCH 01/52] fuse: add skeleton virtio_fs.ko module Vivek Goyal
2018-12-10 17:12 ` [PATCH 02/52] fuse: add probe/remove virtio driver Vivek Goyal
2018-12-10 17:12 ` [PATCH 03/52] fuse: rely on mutex_unlock() barrier instead of fput() Vivek Goyal
2018-12-10 17:12 ` [PATCH 04/52] fuse: extract fuse_fill_super_common() Vivek Goyal
2018-12-10 17:12 ` [PATCH 05/52] virtio_fs: get mount working Vivek Goyal
2018-12-10 17:12 ` [PATCH 06/52] fuse: export fuse_end_request() Vivek Goyal
2018-12-10 17:12 ` [PATCH 07/52] fuse: export fuse_len_args() Vivek Goyal
2018-12-10 17:12 ` [PATCH 08/52] fuse: add fuse_iqueue_ops callbacks Vivek Goyal
2018-12-10 17:12 ` [PATCH 09/52] fuse: process requests queues Vivek Goyal
2018-12-10 17:12 ` [PATCH 10/52] fuse: export fuse_get_unique() Vivek Goyal
2018-12-10 17:12 ` [PATCH 11/52] fuse: implement FUSE_FORGET for virtio-fs Vivek Goyal
2018-12-10 17:12 ` [PATCH 12/52] virtio_fs: Set up dax_device Vivek Goyal
2018-12-10 17:12 ` [PATCH 13/52] dax: remove block device dependencies Vivek Goyal
2018-12-10 17:12 ` [PATCH 14/52] fuse: add fuse_conn->dax_dev field Vivek Goyal
2018-12-10 17:12 ` Vivek Goyal [this message]
2018-12-12 16:37   ` [PATCH 15/52] fuse: map virtio_fs DAX window BAR Christian Borntraeger
2018-12-13 11:55     ` Stefan Hajnoczi
2018-12-13 16:06   ` kbuild test robot
2018-12-13 19:55   ` Dan Williams
2018-12-13 20:09     ` Dr. David Alan Gilbert
2018-12-13 20:15       ` Dan Williams
2018-12-13 20:40         ` Vivek Goyal
2018-12-13 21:18           ` Vivek Goyal
2018-12-14 10:09             ` Dr. David Alan Gilbert
2018-12-10 17:12 ` [PATCH 16/52] virtio-fs: Add VIRTIO_PCI_CAP_SHARED_MEMORY_CFG and utility to find them Vivek Goyal
2018-12-12 16:36   ` [PATCH] virtio-fs: fix semicolon.cocci warnings kbuild test robot
2018-12-12 16:36   ` [PATCH 16/52] virtio-fs: Add VIRTIO_PCI_CAP_SHARED_MEMORY_CFG and utility to find them kbuild test robot
2018-12-10 17:12 ` [PATCH 17/52] virtio-fs: Retrieve shm capabilities for cache Vivek Goyal
2018-12-10 17:12 ` [PATCH 18/52] virtio-fs: Map cache using the values from the capabilities Vivek Goyal
2018-12-13  9:10   ` David Hildenbrand
2018-12-13  9:13     ` Dr. David Alan Gilbert
2018-12-13  9:34       ` David Hildenbrand
2018-12-13 10:00         ` Dr. David Alan Gilbert
2018-12-13 11:26           ` David Hildenbrand
2018-12-13 12:15             ` Dr. David Alan Gilbert
2018-12-13 12:24               ` David Hildenbrand
2018-12-13 12:38                 ` Cornelia Huck
2018-12-14 13:44                   ` Stefan Hajnoczi
2018-12-14 13:50                     ` Cornelia Huck
2018-12-14 14:06                       ` Dr. David Alan Gilbert
2018-12-17 11:25                       ` Stefan Hajnoczi
2018-12-17 10:53                     ` David Hildenbrand
2018-12-17 14:56                       ` Stefan Hajnoczi
2018-12-18 17:13                         ` Cornelia Huck
2018-12-18 17:25                           ` David Hildenbrand
2019-01-02 10:24                             ` Stefan Hajnoczi
2019-03-17  0:33   ` Liu Bo
2019-03-20 10:42     ` Dr. David Alan Gilbert
2019-03-17  0:35   ` [PATCH] virtio-fs: fix multiple tag support Liu Bo
2019-03-19 20:26     ` Vivek Goyal
2019-03-20  2:04       ` Liu Bo
2018-12-10 17:12 ` [PATCH 19/52] virito-fs: Make dax optional Vivek Goyal
2018-12-10 17:12 ` [PATCH 20/52] Limit number of pages returned by direct_access() Vivek Goyal
2018-12-10 17:12 ` [PATCH 21/52] fuse: Introduce fuse_dax_mapping Vivek Goyal
2018-12-10 17:12 ` [PATCH 22/52] Create a list of free memory ranges Vivek Goyal
2018-12-11 17:44   ` kbuild test robot
2018-12-15 19:22   ` kbuild test robot
2018-12-10 17:12 ` [PATCH 23/52] fuse: simplify fuse_fill_super_common() calling Vivek Goyal
2018-12-10 17:12 ` [PATCH 24/52] fuse: Introduce setupmapping/removemapping commands Vivek Goyal
2018-12-10 17:12 ` [PATCH 25/52] Introduce interval tree basic data structures Vivek Goyal
2018-12-10 17:12 ` [PATCH 26/52] fuse: Implement basic DAX read/write support commands Vivek Goyal
2018-12-10 17:12 ` [PATCH 27/52] fuse: Maintain a list of busy elements Vivek Goyal
2018-12-10 17:12 ` [PATCH 28/52] Do fallocate() to grow file before mapping for file growing writes Vivek Goyal
2018-12-11  6:13   ` kbuild test robot
2018-12-11  6:20   ` kbuild test robot
2018-12-10 17:12 ` [PATCH 29/52] fuse: add DAX mmap support Vivek Goyal
2018-12-10 17:12 ` [PATCH 30/52] fuse: delete dentry if timeout is zero Vivek Goyal
2018-12-10 17:12 ` [PATCH 31/52] dax: Pass dax_dev to dax_writeback_mapping_range() Vivek Goyal
2018-12-11  6:12   ` kbuild test robot
2018-12-11 17:38   ` kbuild test robot
2018-12-10 17:12 ` [PATCH 32/52] fuse: Define dax address space operations Vivek Goyal
2018-12-10 17:12 ` [PATCH 33/52] fuse, dax: Take ->i_mmap_sem lock during dax page fault Vivek Goyal
2018-12-10 17:13 ` [PATCH 34/52] fuse: Add logic to free up a memory range Vivek Goyal
2018-12-10 17:13 ` [PATCH 35/52] fuse: Add logic to do direct reclaim of memory Vivek Goyal
2018-12-10 17:13 ` [PATCH 36/52] fuse: Kick worker when free memory drops below 20% of total ranges Vivek Goyal
2018-12-10 17:13 ` [PATCH 37/52] fuse: multiplex cached/direct_io/dax file operations Vivek Goyal
2018-12-10 17:13 ` [PATCH 38/52] Dispatch FORGET requests later instead of dropping them Vivek Goyal
2018-12-10 17:13 ` [PATCH 39/52] Release file in process context Vivek Goyal
2018-12-10 17:13 ` [PATCH 40/52] fuse: Do not block on inode lock while freeing memory range Vivek Goyal
2018-12-10 17:13 ` [PATCH 41/52] fuse: Reschedule dax free work if too many EAGAIN attempts Vivek Goyal
2018-12-10 17:13 ` [PATCH 42/52] fuse: Wait for memory ranges to become free Vivek Goyal
2018-12-10 17:13 ` [PATCH 43/52] fuse: Take inode lock for dax inode truncation Vivek Goyal
2018-12-10 17:13 ` [PATCH 44/52] fuse: Clear setuid bit even in direct I/O path Vivek Goyal
2018-12-10 17:13 ` [PATCH 45/52] virtio: Free fuse devices on umount Vivek Goyal
2018-12-10 17:13 ` [PATCH 46/52] virtio-fs: Retrieve shm capabilities for version table Vivek Goyal
2018-12-10 17:13 ` [PATCH 47/52] virtio-fs: Map using the values from the capabilities Vivek Goyal
2018-12-10 17:13 ` [PATCH 48/52] virtio-fs: pass version table pointer to fuse Vivek Goyal
2018-12-10 17:13 ` [PATCH 49/52] fuse: don't crash if version table is NULL Vivek Goyal
2018-12-10 17:13 ` [PATCH 50/52] fuse: add shared version support (virtio-fs only) Vivek Goyal
2018-12-10 17:13 ` [PATCH 51/52] fuse: shared version cleanups Vivek Goyal
2018-12-10 17:13 ` [PATCH 52/52] fuse: fix fuse_permission() for the default_permissions case Vivek Goyal
2018-12-19 21:25   ` kbuild test robot
2018-12-11 12:54 ` [PATCH 00/52] [RFC] virtio-fs: shared file system for virtual machines Stefan Hajnoczi
2018-12-12 20:30 ` Konrad Rzeszutek Wilk
2018-12-12 21:22   ` Vivek Goyal
2019-02-12 15:56 ` Aneesh Kumar K.V
2019-02-12 18:57   ` 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=20181210171318.16998-16-vgoyal@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    --cc=stefanha@redhat.com \
    --cc=sweil@redhat.com \
    --cc=swhiteho@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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

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


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


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