[PATCH 0/7] dax: unified host inode for device-dax mappings

[PATCH 0/7] dax: unified host inode for device-dax mappings

[Dan Williams]

There are two scenarios where we need mappings of a /dev/dax device to
share a single host inode, invalidating mappings at device shutdown, and
coordinating resize of an actively mapped device.  This series addresses
the unmap-on-shutdown case and includes reworks, like the cdev api
conversion, to prepare for a dynamic resize / allocation capability.

Recall that device-DAX, introduced in v4.7 [1], is a mechanism to
provide deterministic mapping behavior for performance- /
feature-differentiated memory ranges.

[1]: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=ab68f2622136

---

Dan Williams (7):
      dax: cleanup needlessly global symbol warnings
      dax: reorder dax_fops function definitions
      dax: rename fops from dax_dev_ to dax_
      dax: embed a struct device in dax_dev
      dax: convert to the cdev api
      dax: define a unified inode/address_space for device-dax mappings
      dax: unmap/truncate on device shutdown


 drivers/dax/Kconfig        |    5 
 drivers/dax/dax.c          |  555 ++++++++++++++++++++++++++------------------
 drivers/dax/pmem.c         |    2 
 fs/char_dev.c              |    1 
 include/uapi/linux/magic.h |    1 
 5 files changed, 337 insertions(+), 227 deletions(-)
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

[PATCH 1/7] dax: cleanup needlessly global symbol warnings

[Dan Williams]

drivers/dax/dax.c:75:6: warning: symbol 'dax_region_put' was not declared.
drivers/dax/dax.c:95:19: warning: symbol 'alloc_dax_region' was not declared.
drivers/dax/dax.c:173:5: warning: symbol 'devm_create_dax_dev' was not declared.
drivers/dax/pmem.c:27:17: warning: symbol 'to_dax_pmem' was not declared.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax.c  |    1 +
 drivers/dax/pmem.c |    2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 803f3953b341..736c03830fd0 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -18,6 +18,7 @@
 #include <linux/dax.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include "dax.h"
 
 static int dax_major;
 static struct class *dax_class;
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index dfb168568af1..59b75c5972bb 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -24,7 +24,7 @@ struct dax_pmem {
 	struct completion cmp;
 };
 
-struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
+static struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
 {
 	return container_of(ref, struct dax_pmem, ref);
 }

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

[PATCH 2/7] dax: reorder dax_fops function definitions

[Dan Williams]

In order to convert devm_create_dax_dev() to use cdev, it will need
access to dax_fops. Move dax_fops and related function definitions
before devm_create_dax_dev().

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax.c |  337 ++++++++++++++++++++++++++---------------------------
 1 file changed, 168 insertions(+), 169 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 736c03830fd0..3774fc9709bb 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -145,175 +145,6 @@ static const struct attribute_group *dax_attribute_groups[] = {
 	NULL,
 };
 
-static void unregister_dax_dev(void *_dev)
-{
-	struct device *dev = _dev;
-	struct dax_dev *dax_dev = dev_get_drvdata(dev);
-	struct dax_region *dax_region = dax_dev->region;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	/*
-	 * Note, rcu is not protecting the liveness of dax_dev, rcu is
-	 * ensuring that any fault handlers that might have seen
-	 * dax_dev->alive == true, have completed.  Any fault handlers
-	 * that start after synchronize_rcu() has started will abort
-	 * upon seeing dax_dev->alive == false.
-	 */
-	dax_dev->alive = false;
-	synchronize_rcu();
-
-	get_device(dev);
-	device_unregister(dev);
-	ida_simple_remove(&dax_region->ida, dax_dev->id);
-	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
-	put_device(dev);
-	dax_dev_put(dax_dev);
-}
-
-int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
-		int count)
-{
-	struct device *parent = dax_region->dev;
-	struct dax_dev *dax_dev;
-	struct device *dev;
-	int rc, minor;
-	dev_t dev_t;
-
-	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
-	if (!dax_dev)
-		return -ENOMEM;
-	memcpy(dax_dev->res, res, sizeof(*res) * count);
-	dax_dev->num_resources = count;
-	kref_init(&dax_dev->kref);
-	dax_dev->alive = true;
-	dax_dev->region = dax_region;
-	kref_get(&dax_region->kref);
-
-	dax_dev->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
-	if (dax_dev->id < 0) {
-		rc = dax_dev->id;
-		goto err_id;
-	}
-
-	minor = ida_simple_get(&dax_minor_ida, 0, 0, GFP_KERNEL);
-	if (minor < 0) {
-		rc = minor;
-		goto err_minor;
-	}
-
-	dev_t = MKDEV(dax_major, minor);
-	dev = device_create_with_groups(dax_class, parent, dev_t, dax_dev,
-			dax_attribute_groups, "dax%d.%d", dax_region->id,
-			dax_dev->id);
-	if (IS_ERR(dev)) {
-		rc = PTR_ERR(dev);
-		goto err_create;
-	}
-	dax_dev->dev = dev;
-
-	rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
-	if (rc)
-		return rc;
-
-	return 0;
-
- err_create:
-	ida_simple_remove(&dax_minor_ida, minor);
- err_minor:
-	ida_simple_remove(&dax_region->ida, dax_dev->id);
- err_id:
-	dax_dev_put(dax_dev);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(devm_create_dax_dev);
-
-/* return an unmapped area aligned to the dax region specified alignment */
-static unsigned long dax_dev_get_unmapped_area(struct file *filp,
-		unsigned long addr, unsigned long len, unsigned long pgoff,
-		unsigned long flags)
-{
-	unsigned long off, off_end, off_align, len_align, addr_align, align;
-	struct dax_dev *dax_dev = filp ? filp->private_data : NULL;
-	struct dax_region *dax_region;
-
-	if (!dax_dev || addr)
-		goto out;
-
-	dax_region = dax_dev->region;
-	align = dax_region->align;
-	off = pgoff << PAGE_SHIFT;
-	off_end = off + len;
-	off_align = round_up(off, align);
-
-	if ((off_end <= off_align) || ((off_end - off_align) < align))
-		goto out;
-
-	len_align = len + align;
-	if ((off + len_align) < off)
-		goto out;
-
-	addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
-			pgoff, flags);
-	if (!IS_ERR_VALUE(addr_align)) {
-		addr_align += (off - addr_align) & (align - 1);
-		return addr_align;
-	}
- out:
-	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
-}
-
-static int __match_devt(struct device *dev, const void *data)
-{
-	const dev_t *devt = data;
-
-	return dev->devt == *devt;
-}
-
-static struct device *dax_dev_find(dev_t dev_t)
-{
-	return class_find_device(dax_class, NULL, &dev_t, __match_devt);
-}
-
-static int dax_dev_open(struct inode *inode, struct file *filp)
-{
-	struct dax_dev *dax_dev = NULL;
-	struct device *dev;
-
-	dev = dax_dev_find(inode->i_rdev);
-	if (!dev)
-		return -ENXIO;
-
-	device_lock(dev);
-	dax_dev = dev_get_drvdata(dev);
-	if (dax_dev) {
-		dev_dbg(dev, "%s\n", __func__);
-		filp->private_data = dax_dev;
-		kref_get(&dax_dev->kref);
-		inode->i_flags = S_DAX;
-	}
-	device_unlock(dev);
-
-	if (!dax_dev) {
-		put_device(dev);
-		return -ENXIO;
-	}
-	return 0;
-}
-
-static int dax_dev_release(struct inode *inode, struct file *filp)
-{
-	struct dax_dev *dax_dev = filp->private_data;
-	struct device *dev = dax_dev->dev;
-
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
-	dax_dev_put(dax_dev);
-	put_device(dev);
-
-	return 0;
-}
-
 static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 		const char *func)
 {
@@ -531,7 +362,91 @@ static int dax_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 	vma->vm_ops = &dax_dev_vm_ops;
 	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	return 0;
+}
+
+/* return an unmapped area aligned to the dax region specified alignment */
+static unsigned long dax_dev_get_unmapped_area(struct file *filp,
+		unsigned long addr, unsigned long len, unsigned long pgoff,
+		unsigned long flags)
+{
+	unsigned long off, off_end, off_align, len_align, addr_align, align;
+	struct dax_dev *dax_dev = filp ? filp->private_data : NULL;
+	struct dax_region *dax_region;
+
+	if (!dax_dev || addr)
+		goto out;
+
+	dax_region = dax_dev->region;
+	align = dax_region->align;
+	off = pgoff << PAGE_SHIFT;
+	off_end = off + len;
+	off_align = round_up(off, align);
+
+	if ((off_end <= off_align) || ((off_end - off_align) < align))
+		goto out;
+
+	len_align = len + align;
+	if ((off + len_align) < off)
+		goto out;
+
+	addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
+			pgoff, flags);
+	if (!IS_ERR_VALUE(addr_align)) {
+		addr_align += (off - addr_align) & (align - 1);
+		return addr_align;
+	}
+ out:
+	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+}
+
+static int __match_devt(struct device *dev, const void *data)
+{
+	const dev_t *devt = data;
+
+	return dev->devt == *devt;
+}
+
+static struct device *dax_dev_find(dev_t dev_t)
+{
+	return class_find_device(dax_class, NULL, &dev_t, __match_devt);
+}
+
+static int dax_dev_open(struct inode *inode, struct file *filp)
+{
+	struct dax_dev *dax_dev = NULL;
+	struct device *dev;
+
+	dev = dax_dev_find(inode->i_rdev);
+	if (!dev)
+		return -ENXIO;
+
+	device_lock(dev);
+	dax_dev = dev_get_drvdata(dev);
+	if (dax_dev) {
+		dev_dbg(dev, "%s\n", __func__);
+		filp->private_data = dax_dev;
+		kref_get(&dax_dev->kref);
+		inode->i_flags = S_DAX;
+	}
+	device_unlock(dev);
+
+	if (!dax_dev) {
+		put_device(dev);
+		return -ENXIO;
+	}
+	return 0;
+}
 
+static int dax_dev_release(struct inode *inode, struct file *filp)
+{
+	struct dax_dev *dax_dev = filp->private_data;
+	struct device *dev = dax_dev->dev;
+
+	dev_dbg(dax_dev->dev, "%s\n", __func__);
+	dax_dev_put(dax_dev);
+	put_device(dev);
+
+	return 0;
 }
 
 static const struct file_operations dax_fops = {
@@ -543,6 +458,90 @@ static const struct file_operations dax_fops = {
 	.mmap = dax_dev_mmap,
 };
 
+static void unregister_dax_dev(void *_dev)
+{
+	struct device *dev = _dev;
+	struct dax_dev *dax_dev = dev_get_drvdata(dev);
+	struct dax_region *dax_region = dax_dev->region;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	/*
+	 * Note, rcu is not protecting the liveness of dax_dev, rcu is
+	 * ensuring that any fault handlers that might have seen
+	 * dax_dev->alive == true, have completed.  Any fault handlers
+	 * that start after synchronize_rcu() has started will abort
+	 * upon seeing dax_dev->alive == false.
+	 */
+	dax_dev->alive = false;
+	synchronize_rcu();
+
+	get_device(dev);
+	device_unregister(dev);
+	ida_simple_remove(&dax_region->ida, dax_dev->id);
+	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
+	put_device(dev);
+	dax_dev_put(dax_dev);
+}
+
+int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
+		int count)
+{
+	struct device *parent = dax_region->dev;
+	struct dax_dev *dax_dev;
+	struct device *dev;
+	int rc, minor;
+	dev_t dev_t;
+
+	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
+	if (!dax_dev)
+		return -ENOMEM;
+	memcpy(dax_dev->res, res, sizeof(*res) * count);
+	dax_dev->num_resources = count;
+	kref_init(&dax_dev->kref);
+	dax_dev->alive = true;
+	dax_dev->region = dax_region;
+	kref_get(&dax_region->kref);
+
+	dax_dev->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
+	if (dax_dev->id < 0) {
+		rc = dax_dev->id;
+		goto err_id;
+	}
+
+	minor = ida_simple_get(&dax_minor_ida, 0, 0, GFP_KERNEL);
+	if (minor < 0) {
+		rc = minor;
+		goto err_minor;
+	}
+
+	dev_t = MKDEV(dax_major, minor);
+	dev = device_create_with_groups(dax_class, parent, dev_t, dax_dev,
+			dax_attribute_groups, "dax%d.%d", dax_region->id,
+			dax_dev->id);
+	if (IS_ERR(dev)) {
+		rc = PTR_ERR(dev);
+		goto err_create;
+	}
+	dax_dev->dev = dev;
+
+	rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
+	if (rc)
+		return rc;
+
+	return 0;
+
+ err_create:
+	ida_simple_remove(&dax_minor_ida, minor);
+ err_minor:
+	ida_simple_remove(&dax_region->ida, dax_dev->id);
+ err_id:
+	dax_dev_put(dax_dev);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(devm_create_dax_dev);
+
 static int __init dax_init(void)
 {
 	int rc;

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

[PATCH 3/7] dax: rename fops from dax_dev_ to dax_

[Dan Williams]

Shorten the prefix of the file operations to distinguish them from
operations on the struct device associated with the dax_dev.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax.c |   16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 3774fc9709bb..994dfa507dfb 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -347,7 +347,7 @@ static const struct vm_operations_struct dax_dev_vm_ops = {
 	.close = dax_dev_vm_close,
 };
 
-static int dax_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct dax_dev *dax_dev = filp->private_data;
 	int rc;
@@ -365,7 +365,7 @@ static int dax_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 }
 
 /* return an unmapped area aligned to the dax region specified alignment */
-static unsigned long dax_dev_get_unmapped_area(struct file *filp,
+static unsigned long dax_get_unmapped_area(struct file *filp,
 		unsigned long addr, unsigned long len, unsigned long pgoff,
 		unsigned long flags)
 {
@@ -411,7 +411,7 @@ static struct device *dax_dev_find(dev_t dev_t)
 	return class_find_device(dax_class, NULL, &dev_t, __match_devt);
 }
 
-static int dax_dev_open(struct inode *inode, struct file *filp)
+static int dax_open(struct inode *inode, struct file *filp)
 {
 	struct dax_dev *dax_dev = NULL;
 	struct device *dev;
@@ -437,7 +437,7 @@ static int dax_dev_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int dax_dev_release(struct inode *inode, struct file *filp)
+static int dax_release(struct inode *inode, struct file *filp)
 {
 	struct dax_dev *dax_dev = filp->private_data;
 	struct device *dev = dax_dev->dev;
@@ -452,10 +452,10 @@ static int dax_dev_release(struct inode *inode, struct file *filp)
 static const struct file_operations dax_fops = {
 	.llseek = noop_llseek,
 	.owner = THIS_MODULE,
-	.open = dax_dev_open,
-	.release = dax_dev_release,
-	.get_unmapped_area = dax_dev_get_unmapped_area,
-	.mmap = dax_dev_mmap,
+	.open = dax_open,
+	.release = dax_release,
+	.get_unmapped_area = dax_get_unmapped_area,
+	.mmap = dax_mmap,
 };
 
 static void unregister_dax_dev(void *_dev)

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

[PATCH 4/7] dax: embed a struct device in dax_dev

[Dan Williams]

The kref in dax_dev can be made redundant if the final put_device() on
the device associated with the dax_dev frees the dax_dev.  This can be
accomplished by embedding a struct device in struct dax_dev, open coding
device_create() and specifying a custom release method.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax.c |  130 ++++++++++++++++++-----------------------------------
 1 file changed, 45 insertions(+), 85 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 994dfa507dfb..181d2a5a21e4 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -49,7 +49,6 @@ struct dax_region {
  * struct dax_dev - subdivision of a dax region
  * @region - parent region
  * @dev - device backing the character device
- * @kref - enable this data to be tracked in filp->private_data
  * @alive - !alive + rcu grace period == no new mappings can be established
  * @id - child id in the region
  * @num_resources - number of physical address extents in this device
@@ -57,8 +56,7 @@ struct dax_region {
  */
 struct dax_dev {
 	struct dax_region *region;
-	struct device *dev;
-	struct kref kref;
+	struct device dev;
 	bool alive;
 	int id;
 	int num_resources;
@@ -79,20 +77,6 @@ void dax_region_put(struct dax_region *dax_region)
 }
 EXPORT_SYMBOL_GPL(dax_region_put);
 
-static void dax_dev_free(struct kref *kref)
-{
-	struct dax_dev *dax_dev;
-
-	dax_dev = container_of(kref, struct dax_dev, kref);
-	dax_region_put(dax_dev->region);
-	kfree(dax_dev);
-}
-
-static void dax_dev_put(struct dax_dev *dax_dev)
-{
-	kref_put(&dax_dev->kref, dax_dev_free);
-}
-
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, unsigned int align, void *addr,
 		unsigned long pfn_flags)
@@ -117,10 +101,15 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 }
 EXPORT_SYMBOL_GPL(alloc_dax_region);
 
+static struct dax_dev *to_dax_dev(struct device *dev)
+{
+	return container_of(dev, struct dax_dev, dev);
+}
+
 static ssize_t size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct dax_dev *dax_dev = dev_get_drvdata(dev);
+	struct dax_dev *dax_dev = to_dax_dev(dev);
 	unsigned long long size = 0;
 	int i;
 
@@ -149,7 +138,7 @@ static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 		const char *func)
 {
 	struct dax_region *dax_region = dax_dev->region;
-	struct device *dev = dax_dev->dev;
+	struct device *dev = &dax_dev->dev;
 	unsigned long mask;
 
 	if (!dax_dev->alive)
@@ -214,7 +203,7 @@ static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
 	unsigned long vaddr = (unsigned long) vmf->virtual_address;
-	struct device *dev = dax_dev->dev;
+	struct device *dev = &dax_dev->dev;
 	struct dax_region *dax_region;
 	int rc = VM_FAULT_SIGBUS;
 	phys_addr_t phys;
@@ -254,7 +243,7 @@ static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct file *filp = vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
-	dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
 			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
 			? "write" : "read", vma->vm_start, vma->vm_end);
 	rcu_read_lock();
@@ -269,7 +258,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 		unsigned int flags)
 {
 	unsigned long pmd_addr = addr & PMD_MASK;
-	struct device *dev = dax_dev->dev;
+	struct device *dev = &dax_dev->dev;
 	struct dax_region *dax_region;
 	phys_addr_t phys;
 	pgoff_t pgoff;
@@ -311,7 +300,7 @@ static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	struct file *filp = vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
-	dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
 			current->comm, (flags & FAULT_FLAG_WRITE)
 			? "write" : "read", vma->vm_start, vma->vm_end);
 
@@ -322,29 +311,9 @@ static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return rc;
 }
 
-static void dax_dev_vm_open(struct vm_area_struct *vma)
-{
-	struct file *filp = vma->vm_file;
-	struct dax_dev *dax_dev = filp->private_data;
-
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
-	kref_get(&dax_dev->kref);
-}
-
-static void dax_dev_vm_close(struct vm_area_struct *vma)
-{
-	struct file *filp = vma->vm_file;
-	struct dax_dev *dax_dev = filp->private_data;
-
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
-	dax_dev_put(dax_dev);
-}
-
 static const struct vm_operations_struct dax_dev_vm_ops = {
 	.fault = dax_dev_fault,
 	.pmd_fault = dax_dev_pmd_fault,
-	.open = dax_dev_vm_open,
-	.close = dax_dev_vm_close,
 };
 
 static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
@@ -352,13 +321,12 @@ static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct dax_dev *dax_dev = filp->private_data;
 	int rc;
 
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
+	dev_dbg(&dax_dev->dev, "%s\n", __func__);
 
 	rc = check_vma(dax_dev, vma, __func__);
 	if (rc)
 		return rc;
 
-	kref_get(&dax_dev->kref);
 	vma->vm_ops = &dax_dev_vm_ops;
 	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	return 0;
@@ -420,30 +388,20 @@ static int dax_open(struct inode *inode, struct file *filp)
 	if (!dev)
 		return -ENXIO;
 
-	device_lock(dev);
-	dax_dev = dev_get_drvdata(dev);
-	if (dax_dev) {
-		dev_dbg(dev, "%s\n", __func__);
-		filp->private_data = dax_dev;
-		kref_get(&dax_dev->kref);
-		inode->i_flags = S_DAX;
-	}
-	device_unlock(dev);
+	dax_dev = to_dax_dev(dev);
+	dev_dbg(dev, "%s\n", __func__);
+	filp->private_data = dax_dev;
+	inode->i_flags = S_DAX;
 
-	if (!dax_dev) {
-		put_device(dev);
-		return -ENXIO;
-	}
 	return 0;
 }
 
 static int dax_release(struct inode *inode, struct file *filp)
 {
 	struct dax_dev *dax_dev = filp->private_data;
-	struct device *dev = dax_dev->dev;
+	struct device *dev = &dax_dev->dev;
 
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
-	dax_dev_put(dax_dev);
+	dev_dbg(dev, "%s\n", __func__);
 	put_device(dev);
 
 	return 0;
@@ -458,12 +416,21 @@ static const struct file_operations dax_fops = {
 	.mmap = dax_mmap,
 };
 
-static void unregister_dax_dev(void *_dev)
+static void dax_dev_release(struct device *dev)
 {
-	struct device *dev = _dev;
-	struct dax_dev *dax_dev = dev_get_drvdata(dev);
+	struct dax_dev *dax_dev = to_dax_dev(dev);
 	struct dax_region *dax_region = dax_dev->region;
 
+	ida_simple_remove(&dax_region->ida, dax_dev->id);
+	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
+	dax_region_put(dax_region);
+	kfree(dax_dev);
+}
+
+static void unregister_dax_dev(void *dev)
+{
+	struct dax_dev *dax_dev = to_dax_dev(dev);
+
 	dev_dbg(dev, "%s\n", __func__);
 
 	/*
@@ -475,13 +442,7 @@ static void unregister_dax_dev(void *_dev)
 	 */
 	dax_dev->alive = false;
 	synchronize_rcu();
-
-	get_device(dev);
 	device_unregister(dev);
-	ida_simple_remove(&dax_region->ida, dax_dev->id);
-	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
-	put_device(dev);
-	dax_dev_put(dax_dev);
 }
 
 int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
@@ -498,7 +459,6 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 		return -ENOMEM;
 	memcpy(dax_dev->res, res, sizeof(*res) * count);
 	dax_dev->num_resources = count;
-	kref_init(&dax_dev->kref);
 	dax_dev->alive = true;
 	dax_dev->region = dax_region;
 	kref_get(&dax_region->kref);
@@ -516,27 +476,27 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 	}
 
 	dev_t = MKDEV(dax_major, minor);
-	dev = device_create_with_groups(dax_class, parent, dev_t, dax_dev,
-			dax_attribute_groups, "dax%d.%d", dax_region->id,
-			dax_dev->id);
-	if (IS_ERR(dev)) {
-		rc = PTR_ERR(dev);
-		goto err_create;
-	}
-	dax_dev->dev = dev;
 
-	rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
-	if (rc)
+	dev = &dax_dev->dev;
+	device_initialize(dev);
+	dev->devt = dev_t;
+	dev->class = dax_class;
+	dev->parent = parent;
+	dev->groups = dax_attribute_groups;
+	dev->release = dax_dev_release;
+	dev_set_name(dev, "dax%d.%d", dax_region->id, dax_dev->id);
+	rc = device_add(dev);
+	if (rc) {
+		put_device(dev);
 		return rc;
+	}
 
-	return 0;
+	return devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
 
- err_create:
-	ida_simple_remove(&dax_minor_ida, minor);
  err_minor:
 	ida_simple_remove(&dax_region->ida, dax_dev->id);
  err_id:
-	dax_dev_put(dax_dev);
+	kfree(dax_dev);
 
 	return rc;
 }

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

[PATCH 5/7] dax: convert to the cdev api

[Dan Williams]

A goal of the device-DAX interface is to be able to support many
exclusive allocations (partitions) of performance / feature
differentiated memory.  This count may exceed the default minors limit
of 256.

As a result of switching to an embedded cdev the inode-to-dax_dev
conversion is simplified, as well as reference counting which can switch
to the cdev kobject lifetime.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/Kconfig |    5 +++
 drivers/dax/dax.c   |   82 ++++++++++++++++++++++++++-------------------------
 2 files changed, 46 insertions(+), 41 deletions(-)

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index cedab7572de3..daadd20aa936 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -23,4 +23,9 @@ config DEV_DAX_PMEM
 
 	  Say Y if unsure
 
+config NR_DEV_DAX
+	int "Maximum number of Device-DAX instances"
+	default 32768
+	range 256 2147483647
+
 endif
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 181d2a5a21e4..17715773c097 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -14,15 +14,19 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/pfn_t.h>
+#include <linux/cdev.h>
 #include <linux/slab.h>
 #include <linux/dax.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include "dax.h"
 
-static int dax_major;
+static dev_t dax_devt;
 static struct class *dax_class;
 static DEFINE_IDA(dax_minor_ida);
+static int nr_dax = CONFIG_NR_DEV_DAX;
+module_param(nr_dax, int, S_IRUGO);
+MODULE_PARM_DESC(nr_dax, "max number of device-dax instances");
 
 /**
  * struct dax_region - mapping infrastructure for dax devices
@@ -49,6 +53,7 @@ struct dax_region {
  * struct dax_dev - subdivision of a dax region
  * @region - parent region
  * @dev - device backing the character device
+ * @cdev - core chardev data
  * @alive - !alive + rcu grace period == no new mappings can be established
  * @id - child id in the region
  * @num_resources - number of physical address extents in this device
@@ -57,6 +62,7 @@ struct dax_region {
 struct dax_dev {
 	struct dax_region *region;
 	struct device dev;
+	struct cdev cdev;
 	bool alive;
 	int id;
 	int num_resources;
@@ -367,29 +373,12 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
 }
 
-static int __match_devt(struct device *dev, const void *data)
-{
-	const dev_t *devt = data;
-
-	return dev->devt == *devt;
-}
-
-static struct device *dax_dev_find(dev_t dev_t)
-{
-	return class_find_device(dax_class, NULL, &dev_t, __match_devt);
-}
-
 static int dax_open(struct inode *inode, struct file *filp)
 {
-	struct dax_dev *dax_dev = NULL;
-	struct device *dev;
-
-	dev = dax_dev_find(inode->i_rdev);
-	if (!dev)
-		return -ENXIO;
+	struct dax_dev *dax_dev;
 
-	dax_dev = to_dax_dev(dev);
-	dev_dbg(dev, "%s\n", __func__);
+	dax_dev = container_of(inode->i_cdev, struct dax_dev, cdev);
+	dev_dbg(&dax_dev->dev, "%s\n", __func__);
 	filp->private_data = dax_dev;
 	inode->i_flags = S_DAX;
 
@@ -399,11 +388,8 @@ static int dax_open(struct inode *inode, struct file *filp)
 static int dax_release(struct inode *inode, struct file *filp)
 {
 	struct dax_dev *dax_dev = filp->private_data;
-	struct device *dev = &dax_dev->dev;
-
-	dev_dbg(dev, "%s\n", __func__);
-	put_device(dev);
 
+	dev_dbg(&dax_dev->dev, "%s\n", __func__);
 	return 0;
 }
 
@@ -430,6 +416,7 @@ static void dax_dev_release(struct device *dev)
 static void unregister_dax_dev(void *dev)
 {
 	struct dax_dev *dax_dev = to_dax_dev(dev);
+	struct cdev *cdev = &dax_dev->cdev;
 
 	dev_dbg(dev, "%s\n", __func__);
 
@@ -442,6 +429,7 @@ static void unregister_dax_dev(void *dev)
 	 */
 	dax_dev->alive = false;
 	synchronize_rcu();
+	cdev_del(cdev);
 	device_unregister(dev);
 }
 
@@ -451,17 +439,13 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 	struct device *parent = dax_region->dev;
 	struct dax_dev *dax_dev;
 	struct device *dev;
+	struct cdev *cdev;
 	int rc, minor;
 	dev_t dev_t;
 
 	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
 	if (!dax_dev)
 		return -ENOMEM;
-	memcpy(dax_dev->res, res, sizeof(*res) * count);
-	dax_dev->num_resources = count;
-	dax_dev->alive = true;
-	dax_dev->region = dax_region;
-	kref_get(&dax_region->kref);
 
 	dax_dev->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
 	if (dax_dev->id < 0) {
@@ -475,10 +459,26 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 		goto err_minor;
 	}
 
-	dev_t = MKDEV(dax_major, minor);
-
+	/* device_initialize() so cdev can reference kobj parent */
+	dev_t = MKDEV(MAJOR(dax_devt), minor);
 	dev = &dax_dev->dev;
 	device_initialize(dev);
+
+	cdev = &dax_dev->cdev;
+	cdev_init(cdev, &dax_fops);
+	cdev->owner = parent->driver->owner;
+	cdev->kobj.parent = &dev->kobj;
+	rc = cdev_add(&dax_dev->cdev, dev_t, 1);
+	if (rc)
+		goto err_cdev;
+
+	/* from here on we're committed to teardown via dax_dev_release() */
+	memcpy(dax_dev->res, res, sizeof(*res) * count);
+	dax_dev->num_resources = count;
+	dax_dev->alive = true;
+	dax_dev->region = dax_region;
+	kref_get(&dax_region->kref);
+
 	dev->devt = dev_t;
 	dev->class = dax_class;
 	dev->parent = parent;
@@ -493,6 +493,8 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 
 	return devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
 
+ err_cdev:
+	ida_simple_remove(&dax_minor_ida, minor);
  err_minor:
 	ida_simple_remove(&dax_region->ida, dax_dev->id);
  err_id:
@@ -506,24 +508,22 @@ static int __init dax_init(void)
 {
 	int rc;
 
-	rc = register_chrdev(0, "dax", &dax_fops);
-	if (rc < 0)
+	nr_dax = max(nr_dax, 256);
+	rc = alloc_chrdev_region(&dax_devt, 0, nr_dax, "dax");
+	if (rc)
 		return rc;
-	dax_major = rc;
 
 	dax_class = class_create(THIS_MODULE, "dax");
-	if (IS_ERR(dax_class)) {
-		unregister_chrdev(dax_major, "dax");
-		return PTR_ERR(dax_class);
-	}
+	if (IS_ERR(dax_class))
+		unregister_chrdev_region(dax_devt, nr_dax);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(dax_class);
 }
 
 static void __exit dax_exit(void)
 {
 	class_destroy(dax_class);
-	unregister_chrdev(dax_major, "dax");
+	unregister_chrdev_region(dax_devt, nr_dax);
 	ida_destroy(&dax_minor_ida);
 }
 

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

[PATCH 6/7] dax: define a unified inode/address_space for device-dax mappings

[Dan Williams]

In support of enabling resize / truncate of device-dax instances, define
a pseudo-fs to provide a unified inode/address space for vm operations.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax.c          |  150 +++++++++++++++++++++++++++++++++++++++++++-
 fs/char_dev.c              |    1 
 include/uapi/linux/magic.h |    1 
 3 files changed, 148 insertions(+), 4 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 17715773c097..e8b9319aeadb 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -13,7 +13,9 @@
 #include <linux/pagemap.h>
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/mount.h>
 #include <linux/pfn_t.h>
+#include <linux/hash.h>
 #include <linux/cdev.h>
 #include <linux/slab.h>
 #include <linux/dax.h>
@@ -26,6 +28,9 @@ static struct class *dax_class;
 static DEFINE_IDA(dax_minor_ida);
 static int nr_dax = CONFIG_NR_DEV_DAX;
 module_param(nr_dax, int, S_IRUGO);
+static struct vfsmount *dax_mnt;
+static struct kmem_cache *dax_cache __read_mostly;
+static struct super_block *dax_superblock __read_mostly;
 MODULE_PARM_DESC(nr_dax, "max number of device-dax instances");
 
 /**
@@ -61,6 +66,7 @@ struct dax_region {
  */
 struct dax_dev {
 	struct dax_region *region;
+	struct inode *inode;
 	struct device dev;
 	struct cdev cdev;
 	bool alive;
@@ -69,6 +75,117 @@ struct dax_dev {
 	struct resource res[0];
 };
 
+static struct inode *dax_alloc_inode(struct super_block *sb)
+{
+	return kmem_cache_alloc(dax_cache, GFP_KERNEL);
+}
+
+static void dax_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+
+	kmem_cache_free(dax_cache, inode);
+}
+
+static void dax_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, dax_i_callback);
+}
+
+static const struct super_operations dax_sops = {
+	.statfs = simple_statfs,
+	.alloc_inode = dax_alloc_inode,
+	.destroy_inode = dax_destroy_inode,
+	.drop_inode = generic_delete_inode,
+};
+
+static struct dentry *dax_mount(struct file_system_type *fs_type,
+		int flags, const char *dev_name, void *data)
+{
+	return mount_pseudo(fs_type, "dax:", &dax_sops, NULL, DAXFS_MAGIC);
+}
+
+static struct file_system_type dax_type = {
+	.name = "dax",
+	.mount = dax_mount,
+	.kill_sb = kill_anon_super,
+};
+
+static int dax_test(struct inode *inode, void *data)
+{
+	return inode->i_cdev == data;
+}
+
+static int dax_set(struct inode *inode, void *data)
+{
+	inode->i_cdev = data;
+	return 0;
+}
+
+static struct inode *dax_inode_get(struct cdev *cdev, dev_t devt)
+{
+	struct inode *inode;
+
+	inode = iget5_locked(dax_superblock, hash_32(devt + DAXFS_MAGIC, 31),
+			dax_test, dax_set, cdev);
+
+	if (!inode)
+		return NULL;
+
+	if (inode->i_state & I_NEW) {
+		inode->i_mode = S_IFCHR;
+		inode->i_flags = S_DAX;
+		inode->i_rdev = devt;
+		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
+		unlock_new_inode(inode);
+	}
+	return inode;
+}
+
+static void init_once(void *inode)
+{
+	inode_init_once(inode);
+}
+
+static int dax_inode_init(void)
+{
+	int rc;
+
+	dax_cache = kmem_cache_create("dax_cache", sizeof(struct inode), 0,
+			(SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
+			 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+			init_once);
+	if (!dax_cache)
+		return -ENOMEM;
+
+	rc = register_filesystem(&dax_type);
+	if (rc)
+		goto err_register_fs;
+
+	dax_mnt = kern_mount(&dax_type);
+	if (IS_ERR(dax_mnt)) {
+		rc = PTR_ERR(dax_mnt);
+		goto err_mount;
+	}
+	dax_superblock = dax_mnt->mnt_sb;
+
+	return 0;
+
+ err_mount:
+	unregister_filesystem(&dax_type);
+ err_register_fs:
+	kmem_cache_destroy(dax_cache);
+
+	return rc;
+}
+
+static void dax_inode_exit(void)
+{
+	kern_unmount(dax_mnt);
+	unregister_filesystem(&dax_type);
+	kmem_cache_destroy(dax_cache);
+}
+
 static void dax_region_free(struct kref *kref)
 {
 	struct dax_region *dax_region;
@@ -379,6 +496,9 @@ static int dax_open(struct inode *inode, struct file *filp)
 
 	dax_dev = container_of(inode->i_cdev, struct dax_dev, cdev);
 	dev_dbg(&dax_dev->dev, "%s\n", __func__);
+	inode->i_mapping = dax_dev->inode->i_mapping;
+	inode->i_mapping->host = dax_dev->inode;
+	filp->f_mapping = inode->i_mapping;
 	filp->private_data = dax_dev;
 	inode->i_flags = S_DAX;
 
@@ -410,6 +530,7 @@ static void dax_dev_release(struct device *dev)
 	ida_simple_remove(&dax_region->ida, dax_dev->id);
 	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
 	dax_region_put(dax_region);
+	iput(dax_dev->inode);
 	kfree(dax_dev);
 }
 
@@ -459,6 +580,12 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 		goto err_minor;
 	}
 
+	dax_dev->inode = dax_inode_get(&dax_dev->cdev, dev_t);
+	if (!dax_dev->inode) {
+		rc = -ENOMEM;
+		goto err_inode;
+	}
+
 	/* device_initialize() so cdev can reference kobj parent */
 	dev_t = MKDEV(MAJOR(dax_devt), minor);
 	dev = &dax_dev->dev;
@@ -494,6 +621,8 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 	return devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
 
  err_cdev:
+	iput(dax_dev->inode);
+ err_inode:
 	ida_simple_remove(&dax_minor_ida, minor);
  err_minor:
 	ida_simple_remove(&dax_region->ida, dax_dev->id);
@@ -508,16 +637,28 @@ static int __init dax_init(void)
 {
 	int rc;
 
+	rc = dax_inode_init();
+	if (rc)
+		return rc;
+
 	nr_dax = max(nr_dax, 256);
 	rc = alloc_chrdev_region(&dax_devt, 0, nr_dax, "dax");
 	if (rc)
-		return rc;
+		goto err_chrdev;
 
 	dax_class = class_create(THIS_MODULE, "dax");
-	if (IS_ERR(dax_class))
-		unregister_chrdev_region(dax_devt, nr_dax);
+	if (IS_ERR(dax_class)) {
+		rc = PTR_ERR(dax_class);
+		goto err_class;
+	}
 
-	return PTR_ERR_OR_ZERO(dax_class);
+	return 0;
+
+ err_class:
+	unregister_chrdev_region(dax_devt, nr_dax);
+ err_chrdev:
+	dax_inode_exit();
+	return rc;
 }
 
 static void __exit dax_exit(void)
@@ -525,6 +666,7 @@ static void __exit dax_exit(void)
 	class_destroy(dax_class);
 	unregister_chrdev_region(dax_devt, nr_dax);
 	ida_destroy(&dax_minor_ida);
+	dax_inode_exit();
 }
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 6edd825231c5..44a240c4bb65 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -406,6 +406,7 @@ void cd_forget(struct inode *inode)
 	spin_lock(&cdev_lock);
 	list_del_init(&inode->i_devices);
 	inode->i_cdev = NULL;
+	inode->i_mapping = &inode->i_data;
 	spin_unlock(&cdev_lock);
 }
 
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index e398beac67b8..9bd559472c92 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -65,6 +65,7 @@
 #define V9FS_MAGIC		0x01021997
 
 #define BDEVFS_MAGIC            0x62646576
+#define DAXFS_MAGIC             0x64646178
 #define BINFMTFS_MAGIC          0x42494e4d
 #define DEVPTS_SUPER_MAGIC	0x1cd1
 #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA

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

[PATCH 7/7] dax: unmap/truncate on device shutdown

[Dan Williams]

Invalidate all mappings of a device-dax instance when the device is
unregistered.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax.c |    1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index e8b9319aeadb..0a7899d5c65c 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -550,6 +550,7 @@ static void unregister_dax_dev(void *dev)
 	 */
 	dax_dev->alive = false;
 	synchronize_rcu();
+	unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1);
 	cdev_del(cdev);
 	device_unregister(dev);
 }

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