The "Device DAX" core enables dax mappings of performance / feature
differentiated memory.  An open mapping or file handle keeps the backing
struct device live, but new mappings are only possible while the device
is enabled.   Faults are handled under rcu_read_lock to synchronize
with the enabled state of the device.

Similar to the filesystem-dax case the backing memory may optionally
have struct page entries.  However, unlike fs-dax there is no support
for private mappings, or mappings that are not backed by media (see
use of zero-page in fs-dax).

Mappings are always guaranteed to match the alignment of the dax_region.
If the dax_region is configured to have a 2MB alignment, all mappings
are guaranteed to be backed by a pmd entry.  Contrast this determinism
with the fs-dax case where pmd mappings are opportunistic.  If userspace
attempts to force a misaligned mapping, the driver will fail the mmap
attempt.  See dax_dev_check_vma() for other scenarios that are rejected,
like MAP_PRIVATE mappings.

Cc: Jeff Moyer <redacted>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ross Zwisler <redacted>
Signed-off-by: Dan Williams <redacted>
---
 drivers/dax/Kconfig |    1 
 drivers/dax/dax.c   |  316 +++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/huge_memory.c    |    1 
 mm/hugetlb.c        |    1 
 4 files changed, 319 insertions(+)

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 86ffbaa891ad..cedab7572de3 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig

@@ -1,6 +1,7 @@
 menuconfig DEV_DAX
 	tristate "DAX: direct access to differentiated memory"
 	default m if NVDIMM_DAX
+	depends on TRANSPARENT_HUGEPAGE
 	help
 	  Support raw access to differentiated (persistence, bandwidth,
 	  latency...) memory via an mmap(2) capable character

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 8207fb33a992..b2fe8a0ce866 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c

@@ -49,6 +49,7 @@ struct 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
  * @res - array of physical address ranges

@@ -57,6 +58,7 @@ struct dax_dev {
 	struct dax_region *region;
 	struct device *dev;
 	struct kref kref;
+	bool alive;
 	int id;
 	int num_resources;
 	struct resource res[0];

@@ -150,6 +152,10 @@ static void destroy_dax_dev(void *_dev)
 
 	dev_dbg(dev, "%s\n", __func__);
 
+	/* disable and flush fault handlers, TODO unmap inodes */
+	dax_dev->alive = false;
+	synchronize_rcu();
+

 	get_device(dev);
 	device_unregister(dev);
 	ida_simple_remove(&dax_region->ida, dax_dev->id);

@@ -173,6 +179,7 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 	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);
 

@@ -217,9 +224,318 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
 }
 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);
+

+
+	return rc;
+}
+
+static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
+		struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd,
+		unsigned int flags)
+{
+	unsigned long pmd_addr = addr & PMD_MASK;
+	struct device *dev = dax_dev->dev;
+	struct dax_region *dax_region;
+	phys_addr_t phys;
+	pgoff_t pgoff;
+	pfn_t pfn;
+
+	if (check_vma(dax_dev, vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dax_dev->region;
+	if (dax_region->align > PMD_SIZE) {
+		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	/* dax pmd mappings require pfn_t_devmap() */
+	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
+		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pgoff = linear_page_index(vma, pmd_addr);
+	phys = pgoff_to_phys(dax_dev, pgoff, PAGE_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+				pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	return vmf_insert_pfn_pmd(vma, addr, pmd, pfn,
+			flags & FAULT_FLAG_WRITE);
+}
+
+static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned int flags)
+{
+	int rc;
+	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__,
+			current->comm, (flags & FAULT_FLAG_WRITE)
+			? "write" : "read", vma->vm_start, vma->vm_end);
+
+	rcu_read_lock();
+	rc = __dax_dev_pmd_fault(dax_dev, vma, addr, pmd, flags);
+	rcu_read_unlock();
+
+	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_dev_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__);
+
+	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;
+
+}
+
 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,
 };
 
 static int __init dax_init(void)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86f9f8b82f8e..52ea012d8a80 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c

@@ -1013,6 +1013,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
 	return VM_FAULT_NOPAGE;
 }
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 19d0d08b396f..b14e98129b07 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c

@@ -624,6 +624,7 @@ pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
 {
 	return vma_hugecache_offset(hstate_vma(vma), vma, address);
 }
+EXPORT_SYMBOL_GPL(linear_hugepage_index);
 
 /*
  * Return the size of the pages allocated when backing a VMA. In the majority

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