nvdimm.lists.linux.dev archive mirror
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: snitzer@redhat.com
Cc: "Jan Kara" <jack@suse.cz>,
	"Matthew Wilcox" <mawilcox@microsoft.com>,
	linux-nvdimm@lists.01.org, dm-devel@redhat.com,
	"Jérôme Glisse" <jglisse@redhat.com>,
	linux-fsdevel@vger.kernel.org, "Christoph Hellwig" <hch@lst.de>,
	"Alasdair Kergon" <agk@redhat.com>
Subject: [PATCH v9] dax, dm: introduce ->fs_{claim, release}() dax_device infrastructure
Date: Tue, 03 Apr 2018 13:36:55 -0700	[thread overview]
Message-ID: <152278769715.7139.9560094354006725491.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <CAPcyv4gSh29g7ZSuWnZVTdgXXS_027qvQNLgAUA+JrFwefXW+w@mail.gmail.com>

In preparation for allowing filesystems to augment the dev_pagemap
associated with a dax_device, add an ->fs_claim() callback. The
->fs_claim() callback is leveraged by the device-mapper dax
implementation to iterate all member devices in the map and repeat the
claim operation across the array.

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.
The ->fs_claim() operation arranges for this callback to be registered,
although that implementation is saved for a later patch.

Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
Changes since v8:
* make __fs_dax_claim and __fs_dax_release private to
  drivers/dax/super.c

* rename dm_dax_iterate to dm_dax_interate_devices (Mike)

* drop the return value from dm_dax_interate_devices since nothing uses
  it (Mike)

 drivers/dax/super.c      |   74 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/dm.c          |   57 +++++++++++++++++++++++++++++++++++
 include/linux/dax.h      |   48 ++++++++++++++++++++++++++++++
 include/linux/memremap.h |    8 +++++
 4 files changed, 187 insertions(+)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 2b2332b605e4..c45ded5e93e7 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -29,6 +29,7 @@ static struct vfsmount *dax_mnt;
 static DEFINE_IDA(dax_minor_ida);
 static struct kmem_cache *dax_cache __read_mostly;
 static struct super_block *dax_superblock __read_mostly;
+static DEFINE_MUTEX(devmap_lock);
 
 #define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head))
 static struct hlist_head dax_host_list[DAX_HASH_SIZE];
@@ -169,9 +170,82 @@ struct dax_device {
 	const char *host;
 	void *private;
 	unsigned long flags;
+	struct dev_pagemap *pgmap;
 	const struct dax_operations *ops;
 };
 
+#if IS_ENABLED(CONFIG_FS_DAX)
+static void generic_dax_pagefree(struct page *page, void *data)
+{
+	/* TODO: wakeup page-idle waiters */
+}
+
+static struct dax_device *__fs_dax_claim(struct dax_device *dax_dev,
+		void *owner)
+{
+	struct dev_pagemap *pgmap;
+
+	if (!dax_dev->pgmap)
+		return dax_dev;
+	pgmap = dax_dev->pgmap;
+
+	mutex_lock(&devmap_lock);
+	if (pgmap->data && pgmap->data == owner) {
+		/* dm might try to claim the same device more than once... */
+		mutex_unlock(&devmap_lock);
+		return dax_dev;
+	} else if (pgmap->page_free || pgmap->page_fault
+			|| pgmap->type != MEMORY_DEVICE_HOST) {
+		put_dax(dax_dev);
+		mutex_unlock(&devmap_lock);
+		return NULL;
+	}
+
+	pgmap->type = MEMORY_DEVICE_FS_DAX;
+	pgmap->page_free = generic_dax_pagefree;
+	pgmap->data = owner;
+	mutex_unlock(&devmap_lock);
+
+	return dax_dev;
+}
+
+struct dax_device *fs_dax_claim(struct dax_device *dax_dev, void *owner)
+{
+	if (dax_dev->ops->fs_claim)
+		return dax_dev->ops->fs_claim(dax_dev, owner);
+	else
+		return __fs_dax_claim(dax_dev, owner);
+}
+EXPORT_SYMBOL_GPL(fs_dax_claim);
+
+static void __fs_dax_release(struct dax_device *dax_dev, void *owner)
+{
+	struct dev_pagemap *pgmap = dax_dev ? dax_dev->pgmap : NULL;
+
+	put_dax(dax_dev);
+	if (!pgmap)
+		return;
+	if (!pgmap->data)
+		return;
+
+	mutex_lock(&devmap_lock);
+	WARN_ON(pgmap->data != owner);
+	pgmap->type = MEMORY_DEVICE_HOST;
+	pgmap->page_free = NULL;
+	pgmap->data = NULL;
+	mutex_unlock(&devmap_lock);
+}
+
+void fs_dax_release(struct dax_device *dax_dev, void *owner)
+{
+	if (dax_dev->ops->fs_release)
+		dax_dev->ops->fs_release(dax_dev, owner);
+	else
+		__fs_dax_release(dax_dev, owner);
+}
+EXPORT_SYMBOL_GPL(fs_dax_release);
+#endif
+
 static ssize_t write_cache_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ffc93aecc02a..cb8ddeb3373f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1090,6 +1090,61 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static int dm_dax_dev_claim(struct dm_target *ti, struct dm_dev *dev,
+		sector_t start, sector_t len, void *owner)
+{
+	if (fs_dax_claim(dev->dax_dev, owner))
+		return 0;
+	/*
+	 * Outside of a kernel bug there is no reason a dax_dev should
+	 * fail a claim attempt. Device-mapper should have exclusive
+	 * ownership of the dm_dev and the filesystem should have
+	 * exclusive ownership of the dm_target.
+	 */
+	WARN_ON_ONCE(1);
+	return -ENXIO;
+}
+
+static int dm_dax_dev_release(struct dm_target *ti, struct dm_dev *dev,
+		sector_t start, sector_t len, void *owner)
+{
+	fs_dax_release(dev->dax_dev, owner);
+	return 0;
+}
+
+static void dm_dax_iterate_devices(struct dax_device *dax_dev,
+		iterate_devices_callout_fn fn, void *arg)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	struct dm_table *map;
+	struct dm_target *ti;
+	int i, srcu_idx;
+
+	map = dm_get_live_table(md, &srcu_idx);
+
+	for (i = 0; i < dm_table_get_num_targets(map); i++) {
+		ti = dm_table_get_target(map, i);
+
+		if (ti->type->iterate_devices)
+			ti->type->iterate_devices(ti, fn, arg);
+	}
+
+	dm_put_live_table(md, srcu_idx);
+}
+
+static struct dax_device *dm_dax_fs_claim(struct dax_device *dax_dev,
+		void *owner)
+{
+	dm_dax_iterate_devices(dax_dev, dm_dax_dev_claim, owner);
+	/* see comment in dm_dax_dev_claim about this unconditional return */
+	return dax_dev;
+}
+
+static void dm_dax_fs_release(struct dax_device *dax_dev, void *owner)
+{
+	dm_dax_iterate_devices(dax_dev, dm_dax_dev_release, owner);
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
@@ -3111,6 +3166,8 @@ static const struct block_device_operations dm_blk_dops = {
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
 	.copy_from_iter = dm_dax_copy_from_iter,
+	.fs_claim = dm_dax_fs_claim,
+	.fs_release = dm_dax_fs_release,
 };
 
 /*
diff --git a/include/linux/dax.h b/include/linux/dax.h
index f9eb22ad341e..af02f93c943a 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -4,6 +4,7 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/blkdev.h>
 #include <linux/radix-tree.h>
 #include <asm/pgtable.h>
 
@@ -20,6 +21,10 @@ struct dax_operations {
 	/* copy_from_iter: required operation for fs-dax direct-i/o */
 	size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
 			struct iov_iter *);
+	/* fs_claim: setup filesytem parameters for the device's dev_pagemap */
+	struct dax_device *(*fs_claim)(struct dax_device *, void *);
+	/* fs_release: restore device's dev_pagemap to its default state */
+	void (*fs_release)(struct dax_device *, void *);
 };
 
 extern struct attribute_group dax_attribute_group;
@@ -83,6 +88,26 @@ static inline void fs_put_dax(struct dax_device *dax_dev)
 struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
 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);
+#ifdef CONFIG_BLOCK
+static inline struct dax_device *fs_dax_claim_bdev(struct block_device *bdev,
+		void *owner)
+{
+	struct dax_device *dax_dev;
+
+	if (!blk_queue_dax(bdev->bd_queue))
+		return NULL;
+	dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	return fs_dax_claim(dax_dev, owner);
+}
+#else
+static inline struct dax_device *fs_dax_claim_bdev(struct block_device *bdev,
+		void *owner)
+{
+	return NULL;
+}
+#endif
+void fs_dax_release(struct dax_device *dax_dev, void *owner);
 #else
 static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
 {
@@ -108,6 +133,29 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline struct dax_device *fs_dax_claim(struct dax_device *dax_dev,
+		void *owner)
+{
+	return NULL;
+}
+
+#ifdef CONFIG_BLOCK
+static inline struct dax_device *fs_dax_claim_bdev(struct block_device *bdev,
+		void *owner)
+{
+	return fs_dax_get_by_host(bdev->bd_disk->disk_name);
+}
+#else
+static inline struct dax_device *fs_dax_claim_bdev(struct block_device *bdev,
+		void *owner)
+{
+	return NULL;
+}
+#endif
+static inline void fs_dax_release(struct dax_device *dax_dev, void *owner)
+{
+}
 #endif
 
 int dax_read_lock(void);
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 7b4899c06f49..02d6d042ee7f 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -53,11 +53,19 @@ struct vmem_altmap {
  * driver can hotplug the device memory using ZONE_DEVICE and with that memory
  * type. Any page of a process can be migrated to such memory. However no one
  * should be allow to pin such memory so that it can always be evicted.
+ *
+ * MEMORY_DEVICE_FS_DAX:
+ * When MEMORY_DEVICE_HOST memory is represented by a device that can
+ * host a filesystem, for example /dev/pmem0, that filesystem can
+ * register for a callback when a page is idled. For the filesystem-dax
+ * case page idle callbacks are used to coordinate DMA vs
+ * hole-punch/truncate.
  */
 enum memory_type {
 	MEMORY_DEVICE_HOST = 0,
 	MEMORY_DEVICE_PRIVATE,
 	MEMORY_DEVICE_PUBLIC,
+	MEMORY_DEVICE_FS_DAX,
 };
 
 /*

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

  reply	other threads:[~2018-04-03 20:46 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         ` Dan Williams [this message]
2018-04-03 21:13           ` [PATCH v9] " Mike Snitzer
2018-03-31  4:03 ` [PATCH v8 11/18] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks Dan Williams
2018-04-04 21:23   ` [v8, " 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=152278769715.7139.9560094354006725491.stgit@dwillia2-desk3.amr.corp.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=agk@redhat.com \
    --cc=dm-devel@redhat.com \
    --cc=hch@lst.de \
    --cc=jack@suse.cz \
    --cc=jglisse@redhat.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=mawilcox@microsoft.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).