All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: akpm@linux-foundation.org
Cc: "Michal Hocko" <mhocko@suse.com>,
	jack@suse.cz, linux-nvdimm@lists.01.org,
	linux-xfs@vger.kernel.org, "Jérôme Glisse" <jglisse@redhat.com>,
	linux-fsdevel@vger.kernel.org, hch@lst.de
Subject: [PATCH v4 09/18] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks
Date: Sat, 23 Dec 2017 16:56:48 -0800	[thread overview]
Message-ID: <151407700867.38751.6057494992833550623.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <151407695916.38751.2866053440557472361.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: Christoph Hellwig <hch@lst.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/super.c      |   79 ++++++++++++++++++++++++++++++++++++++++------
 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      |   17 +++++-----
 include/linux/memremap.h |    8 +++++
 7 files changed, 103 insertions(+), 36 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 516124ae1ccf..e926e373a3a5 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];
@@ -62,16 +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
@@ -169,9 +160,66 @@ 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 */
+}
+
+struct dax_device *fs_dax_claim_bdev(struct block_device *bdev, void *owner)
+{
+	struct dax_device *dax_dev;
+	struct dev_pagemap *pgmap;
+
+	if (!blk_queue_dax(bdev->bd_queue))
+		return NULL;
+	dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	if (!dax_dev->pgmap)
+		return dax_dev;
+	pgmap = dax_dev->pgmap;
+
+	mutex_lock(&devmap_lock);
+	if ((pgmap->data && pgmap->data != owner) || 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;
+}
+EXPORT_SYMBOL_GPL(fs_dax_claim_bdev);
+
+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);
+}
+EXPORT_SYMBOL_GPL(fs_dax_release);
+#endif
+
 static ssize_t write_cache_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -505,6 +553,17 @@ 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 cf074b1ce219..bbe3044c1b26 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -407,7 +407,8 @@ 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 38f9222606ee..b0d6d9954945 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -171,7 +171,7 @@ 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);
 }
 
@@ -814,7 +814,7 @@ 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;
@@ -1210,7 +1210,7 @@ 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 18873ea89e08..238cad596733 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -950,7 +950,7 @@ 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);
 }
 
@@ -3396,7 +3396,7 @@ 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;
@@ -4406,7 +4406,7 @@ 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 5122d3021117..8ff821f3bcfb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -722,7 +722,7 @@ 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;
@@ -730,10 +730,10 @@ 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);
 }
 
 /*
@@ -751,9 +751,9 @@ 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;
 
 	/*
@@ -763,7 +763,7 @@ 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) {
@@ -777,7 +777,7 @@ 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);
 	}
 
 	/*
@@ -811,14 +811,14 @@ 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 5258346c558c..1c6ed44fe9fc 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -51,12 +51,8 @@ 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);
 #else
 static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
 {
@@ -68,13 +64,14 @@ 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;
 }
 #endif
 
@@ -82,6 +79,8 @@ int dax_read_lock(void);
 void dax_read_unlock(int id);
 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);
 bool dax_alive(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
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

WARNING: multiple messages have this Message-ID (diff)
From: Dan Williams <dan.j.williams@intel.com>
To: akpm@linux-foundation.org
Cc: "Michal Hocko" <mhocko@suse.com>,
	jack@suse.cz, linux-nvdimm@lists.01.org,
	linux-xfs@vger.kernel.org, "Jérôme Glisse" <jglisse@redhat.com>,
	linux-fsdevel@vger.kernel.org, ross.zwisler@linux.intel.com,
	hch@lst.de
Subject: [PATCH v4 09/18] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks
Date: Sat, 23 Dec 2017 16:56:48 -0800	[thread overview]
Message-ID: <151407700867.38751.6057494992833550623.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <151407695916.38751.2866053440557472361.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: Christoph Hellwig <hch@lst.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/super.c      |   79 ++++++++++++++++++++++++++++++++++++++++------
 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      |   17 +++++-----
 include/linux/memremap.h |    8 +++++
 7 files changed, 103 insertions(+), 36 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 516124ae1ccf..e926e373a3a5 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];
@@ -62,16 +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
@@ -169,9 +160,66 @@ 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 */
+}
+
+struct dax_device *fs_dax_claim_bdev(struct block_device *bdev, void *owner)
+{
+	struct dax_device *dax_dev;
+	struct dev_pagemap *pgmap;
+
+	if (!blk_queue_dax(bdev->bd_queue))
+		return NULL;
+	dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	if (!dax_dev->pgmap)
+		return dax_dev;
+	pgmap = dax_dev->pgmap;
+
+	mutex_lock(&devmap_lock);
+	if ((pgmap->data && pgmap->data != owner) || 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;
+}
+EXPORT_SYMBOL_GPL(fs_dax_claim_bdev);
+
+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);
+}
+EXPORT_SYMBOL_GPL(fs_dax_release);
+#endif
+
 static ssize_t write_cache_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -505,6 +553,17 @@ 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 cf074b1ce219..bbe3044c1b26 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -407,7 +407,8 @@ 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 38f9222606ee..b0d6d9954945 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -171,7 +171,7 @@ 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);
 }
 
@@ -814,7 +814,7 @@ 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;
@@ -1210,7 +1210,7 @@ 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 18873ea89e08..238cad596733 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -950,7 +950,7 @@ 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);
 }
 
@@ -3396,7 +3396,7 @@ 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;
@@ -4406,7 +4406,7 @@ 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 5122d3021117..8ff821f3bcfb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -722,7 +722,7 @@ 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;
@@ -730,10 +730,10 @@ 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);
 }
 
 /*
@@ -751,9 +751,9 @@ 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;
 
 	/*
@@ -763,7 +763,7 @@ 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) {
@@ -777,7 +777,7 @@ 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);
 	}
 
 	/*
@@ -811,14 +811,14 @@ 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 5258346c558c..1c6ed44fe9fc 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -51,12 +51,8 @@ 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);
 #else
 static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
 {
@@ -68,13 +64,14 @@ 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;
 }
 #endif
 
@@ -82,6 +79,8 @@ int dax_read_lock(void);
 void dax_read_unlock(int id);
 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);
 bool dax_alive(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
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,
 };
 
 /*

  parent reply	other threads:[~2017-12-24  1:00 UTC|newest]

Thread overview: 136+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-24  0:56 [PATCH v4 00/18] dax: fix dma vs truncate/hole-punch Dan Williams
2017-12-24  0:56 ` Dan Williams
2017-12-24  0:56 ` Dan Williams
2017-12-24  0:56 ` [PATCH v4 01/18] mm, dax: introduce pfn_t_special() Dan Williams
2017-12-24  0:56   ` Dan Williams
2018-01-04  8:16   ` Christoph Hellwig
2018-01-04  8:16     ` Christoph Hellwig
2017-12-24  0:56 ` [PATCH v4 02/18] ext4: auto disable dax instead of failing mount Dan Williams
2017-12-24  0:56   ` Dan Williams
2018-01-03 14:20   ` Jan Kara
2018-01-03 14:20     ` Jan Kara
2017-12-24  0:56 ` [PATCH v4 03/18] ext2: " Dan Williams
2017-12-24  0:56   ` Dan Williams
2018-01-03 14:21   ` Jan Kara
2018-01-03 14:21     ` Jan Kara
2017-12-24  0:56 ` [PATCH v4 04/18] dax: require 'struct page' by default for filesystem dax Dan Williams
2017-12-24  0:56   ` Dan Williams
2018-01-03 15:29   ` Jan Kara
2018-01-03 15:29     ` Jan Kara
2018-01-04  8:16   ` Christoph Hellwig
2018-01-04  8:16     ` Christoph Hellwig
2018-01-08 11:58   ` Gerald Schaefer
2018-01-08 11:58     ` Gerald Schaefer
2017-12-24  0:56 ` [PATCH v4 05/18] dax: stop using VM_MIXEDMAP for dax Dan Williams
2017-12-24  0:56   ` Dan Williams
2018-01-03 15:27   ` Jan Kara
2018-01-03 15:27     ` Jan Kara
2017-12-24  0:56 ` [PATCH v4 06/18] dax: stop using VM_HUGEPAGE " Dan Williams
2017-12-24  0:56   ` Dan Williams
2017-12-24  0:56 ` [PATCH v4 07/18] dax: store pfns in the radix Dan Williams
2017-12-24  0:56   ` Dan Williams
2017-12-27  0:17   ` Ross Zwisler
2017-12-27  0:17     ` Ross Zwisler
2018-01-02 20:15     ` Dan Williams
2018-01-02 20:15       ` Dan Williams
2018-01-03 15:39   ` Jan Kara
2018-01-03 15:39     ` Jan Kara
2017-12-24  0:56 ` [PATCH v4 08/18] tools/testing/nvdimm: add 'bio_delay' mechanism Dan Williams
2017-12-24  0:56   ` Dan Williams
2017-12-27 18:08   ` Ross Zwisler
2017-12-27 18:08     ` Ross Zwisler
2018-01-02 20:35     ` Dan Williams
2018-01-02 20:35       ` Dan Williams
2018-01-02 21:44   ` Dave Chinner
2018-01-02 21:44     ` Dave Chinner
2018-01-02 21:51     ` Dan Williams
2018-01-02 21:51       ` Dan Williams
2018-01-03 15:46       ` Jan Kara
2018-01-03 15:46         ` Jan Kara
2018-01-03 20:37         ` Jeff Moyer
2018-01-03 20:37           ` Jeff Moyer
2017-12-24  0:56 ` Dan Williams [this message]
2017-12-24  0:56   ` [PATCH v4 09/18] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks Dan Williams
2018-01-04  8:20   ` Christoph Hellwig
2018-01-04  8:20     ` Christoph Hellwig
2017-12-24  0:56 ` [PATCH v4 10/18] mm, dev_pagemap: introduce CONFIG_DEV_PAGEMAP_OPS Dan Williams
2017-12-24  0:56   ` Dan Williams
2018-01-04  8:25   ` Christoph Hellwig
2018-01-04  8:25     ` Christoph Hellwig
2017-12-24  0:56 ` [PATCH v4 11/18] fs, dax: introduce DEFINE_FSDAX_AOPS Dan Williams
2017-12-24  0:56   ` Dan Williams
2017-12-27  5:29   ` Matthew Wilcox
2017-12-27  5:29     ` Matthew Wilcox
2018-01-02 20:21     ` Dan Williams
2018-01-02 20:21       ` Dan Williams
2018-01-03 16:05       ` Jan Kara
2018-01-03 16:05         ` Jan Kara
2018-01-04  8:27         ` Christoph Hellwig
2018-01-04  8:27           ` Christoph Hellwig
2018-01-02 21:41   ` Dave Chinner
2018-01-02 21:41     ` Dave Chinner
2017-12-24  0:57 ` [PATCH v4 12/18] xfs: use DEFINE_FSDAX_AOPS Dan Williams
2017-12-24  0:57   ` Dan Williams
2018-01-02 21:15   ` Darrick J. Wong
2018-01-02 21:15     ` Darrick J. Wong
2018-01-02 21:40     ` Dan Williams
2018-01-02 21:40       ` Dan Williams
2018-01-03 16:09       ` Jan Kara
2018-01-03 16:09         ` Jan Kara
2018-01-04  8:28   ` Christoph Hellwig
2018-01-04  8:28     ` Christoph Hellwig
2017-12-24  0:57 ` [PATCH v4 13/18] ext4: " Dan Williams
2017-12-24  0:57   ` Dan Williams
2017-12-24  0:57   ` Dan Williams
2018-01-04  8:29   ` Christoph Hellwig
2018-01-04  8:29     ` Christoph Hellwig
2018-01-04  8:29     ` Christoph Hellwig
2017-12-24  0:57 ` [PATCH v4 14/18] ext2: " Dan Williams
2017-12-24  0:57   ` Dan Williams
2018-01-04  8:29   ` Christoph Hellwig
2018-01-04  8:29     ` Christoph Hellwig
2017-12-24  0:57 ` [PATCH v4 15/18] mm, fs, dax: use page->mapping to warn if dma collides with truncate Dan Williams
2017-12-24  0:57   ` Dan Williams
2018-01-04  8:30   ` Christoph Hellwig
2018-01-04  8:30     ` Christoph Hellwig
2018-01-04  9:39   ` Jan Kara
2018-01-04  9:39     ` Jan Kara
2017-12-24  0:57 ` [PATCH v4 16/18] wait_bit: introduce {wait_on,wake_up}_atomic_one Dan Williams
2017-12-24  0:57   ` Dan Williams
2018-01-04  8:30   ` Christoph Hellwig
2018-01-04  8:30     ` Christoph Hellwig
2017-12-24  0:57 ` [PATCH v4 17/18] mm, fs, dax: dax_flush_dma, handle dma vs block-map-change collisions Dan Williams
2017-12-24  0:57   ` Dan Williams
2018-01-04  8:31   ` Christoph Hellwig
2018-01-04  8:31     ` Christoph Hellwig
2018-01-04 11:12   ` Jan Kara
2018-01-04 11:12     ` Jan Kara
2018-01-07 21:58     ` Dan Williams
2018-01-07 21:58       ` Dan Williams
2018-01-08 13:50       ` Jan Kara
2018-01-08 13:50         ` Jan Kara
2018-03-08 17:02         ` Dan Williams
2018-03-08 17:02           ` Dan Williams
2018-03-09 12:56           ` Jan Kara
2018-03-09 12:56             ` Jan Kara
2018-03-09 16:15             ` Dan Williams
2018-03-09 16:15               ` Dan Williams
2018-03-09 17:26               ` Dan Williams
2018-03-09 17:26                 ` Dan Williams
2017-12-24  0:57 ` [PATCH v4 18/18] xfs, dax: wire up dax_flush_dma support via a new xfs_sync_dma helper Dan Williams
2017-12-24  0:57   ` Dan Williams
2018-01-02 21:07   ` Darrick J. Wong
2018-01-02 21:07     ` Darrick J. Wong
2018-01-02 23:00   ` Dave Chinner
2018-01-02 23:00     ` Dave Chinner
2018-01-03  2:21     ` Dan Williams
2018-01-03  2:21       ` Dan Williams
2018-01-03  7:51       ` Dave Chinner
2018-01-03  7:51         ` Dave Chinner
2018-01-04  8:34         ` Christoph Hellwig
2018-01-04  8:34           ` Christoph Hellwig
2018-01-04  8:33     ` Christoph Hellwig
2018-01-04  8:33       ` Christoph Hellwig
2018-01-04  8:17 ` [PATCH v4 00/18] dax: fix dma vs truncate/hole-punch Christoph Hellwig
2018-01-04  8:17   ` Christoph Hellwig
2018-01-04  8:17   ` Christoph Hellwig

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=151407700867.38751.6057494992833550623.stgit@dwillia2-desk3.amr.corp.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=akpm@linux-foundation.org \
    --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=linux-xfs@vger.kernel.org \
    --cc=mhocko@suse.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.