From: Dan Williams <dan.j.williams@intel.com>
To: linux-nvdimm@lists.01.org
Cc: "Michal Hocko" <mhocko@suse.com>,
jack@suse.cz, snitzer@redhat.com, david@fromorbit.com,
linux-kernel@vger.kernel.org, linux-xfs@vger.kernel.org,
"Jérôme Glisse" <jglisse@redhat.com>,
linux-fsdevel@vger.kernel.org, "Christoph Hellwig" <hch@lst.de>
Subject: [PATCH v8 11/18] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks
Date: Fri, 30 Mar 2018 21:03:08 -0700 [thread overview]
Message-ID: <152246898837.36038.26895928842345061.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <152246892890.36038.18436540150980653229.stgit@dwillia2-desk3.amr.corp.intel.com>
In order to resolve collisions between filesystem operations and DMA to
DAX mapped pages we need a callback when DMA completes. With a callback
we can hold off filesystem operations while DMA is in-flight and then
resume those operations when the last put_page() occurs on a DMA page.
Recall that the 'struct page' entries for DAX memory are created with
devm_memremap_pages(). That routine arranges for the pages to be
allocated, but never onlined, so a DAX page is DMA-idle when its
reference count reaches one.
Also recall that the HMM sub-system added infrastructure to trap the
page-idle (2-to-1 reference count) transition of the pages allocated by
devm_memremap_pages() and trigger a callback via the 'struct
dev_pagemap' associated with the page range. Whereas the HMM callbacks
are going to a device driver to manage bounce pages in device-memory in
the filesystem-dax case we will call back to filesystem specified
callback.
Since the callback is not known at devm_memremap_pages() time we arrange
for the filesystem to install it at mount time. No functional changes
are expected as this only registers a nop handler for the ->page_free()
event for device-mapped pages.
Cc: Michal Hocko <mhocko@suse.com>
Reviewed-by: "Jérôme Glisse" <jglisse@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/dax/super.c | 21 +++++++++++----------
drivers/nvdimm/pmem.c | 3 ++-
fs/ext2/super.c | 6 +++---
fs/ext4/super.c | 6 +++---
fs/xfs/xfs_super.c | 20 ++++++++++----------
include/linux/dax.h | 23 ++++++++++++++---------
6 files changed, 43 insertions(+), 36 deletions(-)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index c4cf284dfe1c..7d260f118a39 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -63,16 +63,6 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
}
EXPORT_SYMBOL(bdev_dax_pgoff);
-#if IS_ENABLED(CONFIG_FS_DAX)
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
-{
- if (!blk_queue_dax(bdev->bd_queue))
- return NULL;
- return fs_dax_get_by_host(bdev->bd_disk->disk_name);
-}
-EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
-#endif
-
/**
* __bdev_dax_supported() - Check if the device supports dax for filesystem
* @sb: The superblock of the device
@@ -579,6 +569,17 @@ struct dax_device *alloc_dax(void *private, const char *__host,
}
EXPORT_SYMBOL_GPL(alloc_dax);
+struct dax_device *alloc_dax_devmap(void *private, const char *host,
+ const struct dax_operations *ops, struct dev_pagemap *pgmap)
+{
+ struct dax_device *dax_dev = alloc_dax(private, host, ops);
+
+ if (dax_dev)
+ dax_dev->pgmap = pgmap;
+ return dax_dev;
+}
+EXPORT_SYMBOL_GPL(alloc_dax_devmap);
+
void put_dax(struct dax_device *dax_dev)
{
if (!dax_dev)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 06f8dcc52ca6..e6d7351f3379 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -408,7 +408,8 @@ static int pmem_attach_disk(struct device *dev,
nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res);
disk->bb = &pmem->bb;
- dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops);
+ dax_dev = alloc_dax_devmap(pmem, disk->disk_name, &pmem_dax_ops,
+ &pmem->pgmap);
if (!dax_dev) {
put_disk(disk);
return -ENOMEM;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 7666c065b96f..6ae20e319bc4 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -172,7 +172,7 @@ static void ext2_put_super (struct super_block * sb)
brelse (sbi->s_sbh);
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
- fs_put_dax(sbi->s_daxdev);
+ fs_dax_release(sbi->s_daxdev, sb);
kfree(sbi);
}
@@ -817,7 +817,7 @@ static unsigned long descriptor_loc(struct super_block *sb,
static int ext2_fill_super(struct super_block *sb, void *data, int silent)
{
- struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
+ struct dax_device *dax_dev = fs_dax_claim_bdev(sb->s_bdev, sb);
struct buffer_head * bh;
struct ext2_sb_info * sbi;
struct ext2_super_block * es;
@@ -1213,7 +1213,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
failed:
- fs_put_dax(dax_dev);
+ fs_dax_release(dax_dev, sb);
return ret;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 39bf464c35f1..315a323729e3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -952,7 +952,7 @@ static void ext4_put_super(struct super_block *sb)
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi->s_blockgroup_lock);
- fs_put_dax(sbi->s_daxdev);
+ fs_dax_release(sbi->s_daxdev, sb);
kfree(sbi);
}
@@ -3398,7 +3398,7 @@ static void ext4_set_resv_clusters(struct super_block *sb)
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
{
- struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
+ struct dax_device *dax_dev = fs_dax_claim_bdev(sb->s_bdev, sb);
char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
@@ -4408,7 +4408,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
out_free_base:
kfree(sbi);
kfree(orig_data);
- fs_put_dax(dax_dev);
+ fs_dax_release(dax_dev, sb);
return err ? err : ret;
}
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 93588ea3d3d2..ef7dd7148c0b 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -724,7 +724,7 @@ xfs_close_devices(
xfs_free_buftarg(mp, mp->m_logdev_targp);
xfs_blkdev_put(logdev);
- fs_put_dax(dax_logdev);
+ fs_dax_release(dax_logdev, mp);
}
if (mp->m_rtdev_targp) {
struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
@@ -732,10 +732,10 @@ xfs_close_devices(
xfs_free_buftarg(mp, mp->m_rtdev_targp);
xfs_blkdev_put(rtdev);
- fs_put_dax(dax_rtdev);
+ fs_dax_release(dax_rtdev, mp);
}
xfs_free_buftarg(mp, mp->m_ddev_targp);
- fs_put_dax(dax_ddev);
+ fs_dax_release(dax_ddev, mp);
}
/*
@@ -753,9 +753,9 @@ xfs_open_devices(
struct xfs_mount *mp)
{
struct block_device *ddev = mp->m_super->s_bdev;
- struct dax_device *dax_ddev = fs_dax_get_by_bdev(ddev);
- struct dax_device *dax_logdev = NULL, *dax_rtdev = NULL;
+ struct dax_device *dax_ddev = fs_dax_claim_bdev(ddev, mp);
struct block_device *logdev = NULL, *rtdev = NULL;
+ struct dax_device *dax_logdev = NULL, *dax_rtdev = NULL;
int error;
/*
@@ -765,7 +765,7 @@ xfs_open_devices(
error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
if (error)
goto out;
- dax_logdev = fs_dax_get_by_bdev(logdev);
+ dax_logdev = fs_dax_claim_bdev(logdev, mp);
}
if (mp->m_rtname) {
@@ -779,7 +779,7 @@ xfs_open_devices(
error = -EINVAL;
goto out_close_rtdev;
}
- dax_rtdev = fs_dax_get_by_bdev(rtdev);
+ dax_rtdev = fs_dax_claim_bdev(rtdev, mp);
}
/*
@@ -813,14 +813,14 @@ xfs_open_devices(
xfs_free_buftarg(mp, mp->m_ddev_targp);
out_close_rtdev:
xfs_blkdev_put(rtdev);
- fs_put_dax(dax_rtdev);
+ fs_dax_release(dax_rtdev, mp);
out_close_logdev:
if (logdev && logdev != ddev) {
xfs_blkdev_put(logdev);
- fs_put_dax(dax_logdev);
+ fs_dax_release(dax_logdev, mp);
}
out:
- fs_put_dax(dax_ddev);
+ fs_dax_release(dax_ddev, mp);
return error;
}
diff --git a/include/linux/dax.h b/include/linux/dax.h
index e9d59a6b06e1..a88ff009e2a1 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -32,6 +32,8 @@ extern struct attribute_group dax_attribute_group;
struct dax_device *dax_get_by_host(const char *host);
struct dax_device *alloc_dax(void *private, const char *host,
const struct dax_operations *ops);
+struct dax_device *alloc_dax_devmap(void *private, const char *host,
+ const struct dax_operations *ops, struct dev_pagemap *pgmap);
void put_dax(struct dax_device *dax_dev);
void kill_dax(struct dax_device *dax_dev);
void dax_write_cache(struct dax_device *dax_dev, bool wc);
@@ -50,6 +52,12 @@ static inline struct dax_device *alloc_dax(void *private, const char *host,
*/
return NULL;
}
+static inline struct dax_device *alloc_dax_devmap(void *private,
+ const char *host, const struct dax_operations *ops,
+ struct dev_pagemap *pgmap)
+{
+ return NULL;
+}
static inline void put_dax(struct dax_device *dax_dev)
{
}
@@ -79,12 +87,8 @@ static inline struct dax_device *fs_dax_get_by_host(const char *host)
return dax_get_by_host(host);
}
-static inline void fs_put_dax(struct dax_device *dax_dev)
-{
- put_dax(dax_dev);
-}
-
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
+struct dax_device *fs_dax_claim_bdev(struct block_device *bdev, void *owner);
+void fs_dax_release(struct dax_device *dax_dev, void *owner);
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc);
struct dax_device *fs_dax_claim(struct dax_device *dax_dev, void *owner);
@@ -100,13 +104,14 @@ static inline struct dax_device *fs_dax_get_by_host(const char *host)
return NULL;
}
-static inline void fs_put_dax(struct dax_device *dax_dev)
+static inline struct dax_device *fs_dax_claim_bdev(struct block_device *bdev,
+ void *owner)
{
+ return NULL;
}
-static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+static inline void fs_dax_release(struct dax_device *dax_dev, void *owner)
{
- return NULL;
}
static inline int dax_writeback_mapping_range(struct address_space *mapping,
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
next prev parent reply other threads:[~2018-03-31 4:13 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-31 4:02 [PATCH v8 00/18] dax: fix dma vs truncate/hole-punch Dan Williams
2018-03-31 4:02 ` [PATCH v8 01/18] dax: store pfns in the radix Dan Williams
2018-03-31 4:02 ` [PATCH v8 02/18] fs, dax: prepare for dax-specific address_space_operations Dan Williams
2018-03-31 4:02 ` [PATCH v8 03/18] block, dax: remove dead code in blkdev_writepages() Dan Williams
2018-03-31 4:02 ` [PATCH v8 04/18] xfs, dax: introduce xfs_dax_aops Dan Williams
2018-03-31 4:02 ` [PATCH v8 05/18] ext4, dax: introduce ext4_dax_aops Dan Williams
2018-04-03 11:50 ` Jan Kara
2018-03-31 4:02 ` [PATCH v8 06/18] ext2, dax: introduce ext2_dax_aops Dan Williams
2018-04-03 11:51 ` Jan Kara
2018-03-31 4:02 ` [PATCH v8 07/18] fs, dax: use page->mapping to warn if truncate collides with a busy page Dan Williams
2018-03-31 4:02 ` [PATCH v8 08/18] dax: introduce CONFIG_DAX_DRIVER Dan Williams
2018-03-31 4:02 ` [PATCH v8 09/18] dax, dm: allow device-mapper to operate without dax support Dan Williams
2018-03-31 4:03 ` [PATCH v8 10/18] dax, dm: introduce ->fs_{claim, release}() dax_device infrastructure Dan Williams
2018-04-03 18:24 ` Dan Williams
2018-04-03 19:39 ` Mike Snitzer
2018-04-03 19:47 ` Dan Williams
2018-04-03 20:36 ` [PATCH v9] " Dan Williams
2018-04-03 21:13 ` Mike Snitzer
2018-03-31 4:03 ` Dan Williams [this message]
2018-04-04 21:23 ` [v8, 11/18] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks Andrei Vagin
2018-04-04 21:27 ` Dan Williams
2018-04-04 21:35 ` Dan Williams
2018-04-04 23:19 ` Stephen Rothwell
2018-04-04 21:40 ` Andrei Vagin
2018-03-31 4:03 ` [PATCH v8 12/18] memremap: split devm_memremap_pages() and memremap() infrastructure Dan Williams
2018-03-31 4:03 ` [PATCH v8 13/18] mm, dev_pagemap: introduce CONFIG_DEV_PAGEMAP_OPS Dan Williams
2018-03-31 4:03 ` [PATCH v8 14/18] memremap: mark devm_memremap_pages() EXPORT_SYMBOL_GPL Dan Williams
2018-03-31 4:03 ` [PATCH v8 15/18] mm, fs, dax: handle layout changes to pinned dax mappings Dan Williams
2018-04-04 9:46 ` Jan Kara
2018-04-04 10:06 ` Jan Kara
2018-04-04 14:12 ` Dan Williams
2018-04-07 19:38 ` Dan Williams
2018-04-08 3:11 ` Paul E. McKenney
2018-04-09 16:39 ` Jan Kara
2018-04-09 18:14 ` Paul E. McKenney
2018-04-09 16:49 ` Jan Kara
2018-04-09 16:51 ` Dan Williams
2018-04-13 22:03 ` Dan Williams
2018-04-13 22:48 ` Paul E. McKenney
2018-04-19 10:44 ` Jan Kara
2018-04-20 3:00 ` Dan Williams
2018-03-31 4:03 ` [PATCH v8 16/18] xfs: prepare xfs_break_layouts() to be called with XFS_MMAPLOCK_EXCL Dan Williams
2018-03-31 4:03 ` [PATCH v8 17/18] xfs: prepare xfs_break_layouts() for another layout type Dan Williams
2018-03-31 4:03 ` [PATCH v8 18/18] xfs, dax: introduce xfs_break_dax_layouts() Dan Williams
2018-04-04 9:55 ` Jan Kara
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=152246898837.36038.26895928842345061.stgit@dwillia2-desk3.amr.corp.intel.com \
--to=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jglisse@redhat.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=linux-xfs@vger.kernel.org \
--cc=mhocko@suse.com \
--cc=snitzer@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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).