[PATCH v3 1/3] dax: masking off __GFP_FS in fs DAX handlers

[PATCH v3 1/3] dax: masking off __GFP_FS in fs DAX handlers

[Dave Jiang]

The caller into dax needs to clear __GFP_FS mask bit since it's
responsible for acquiring locks / transactions that blocks __GFP_FS
allocation.  The caller will restore the original mask when dax function
returns.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/dax.c          |    1 +
 fs/ext2/file.c    |    9 ++++++++-
 fs/ext4/file.c    |   10 +++++++++-
 fs/xfs/xfs_file.c |   14 +++++++++++++-
 4 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index d3fe880..6395bc6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1380,6 +1380,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
+	vmf.gfp_mask &= ~__GFP_FS;
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index b0f2415..8422d5f 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -92,16 +92,19 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct inode *inode = file_inode(vma->vm_file);
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	int ret;
+	gfp_t old_gfp = vmf->gfp_mask;
 
 	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
 		file_update_time(vma->vm_file);
 	}
+	vmf->gfp_mask &= ~__GFP_FS;
 	down_read(&ei->dax_sem);
 
 	ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
+	vmf->gfp_mask = old_gfp;
 	if (vmf->flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(inode->i_sb);
 	return ret;
@@ -114,6 +117,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	loff_t size;
 	int ret;
+	gfp_t old_gfp = vmf->gfp_mask;
 
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
@@ -123,8 +127,11 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
-	else
+	else {
+		vmf->gfp_mask &= ~__GFP_FS;
 		ret = dax_pfn_mkwrite(vma, vmf);
+		vmf->gfp_mask = old_gfp;
+	}
 
 	up_read(&ei->dax_sem);
 	sb_end_pagefault(inode->i_sb);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d663d3d..a3f2bf0 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -261,14 +261,17 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	gfp_t old_gfp = vmf->gfp_mask;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
 	}
+	vmf->gfp_mask &= ~__GFP_FS;
 	down_read(&EXT4_I(inode)->i_mmap_sem);
 	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
+	vmf->gfp_mask = old_gfp;
 	if (write)
 		sb_end_pagefault(sb);
 
@@ -320,8 +323,13 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
-	else
+	else {
+		gfp_t old_gfp = vmf->gfp_mask;
+
+		vmf->gfp_mask &= ~__GFP_FS;
 		ret = dax_pfn_mkwrite(vma, vmf);
+		vmf->gfp_mask = old_gfp;
+	}
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(sb);
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d818c16..52202b4 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1474,7 +1474,11 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
+		gfp_t old_gfp = vmf->gfp_mask;
+
+		vmf->gfp_mask &= ~__GFP_FS;
 		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
+		vmf->gfp_mask = old_gfp;
 	} else {
 		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
 		ret = block_page_mkwrite_return(ret);
@@ -1502,13 +1506,16 @@ xfs_filemap_fault(
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	if (IS_DAX(inode)) {
+		gfp_t old_gfp = vmf->gfp_mask;
 		/*
 		 * we do not want to trigger unwritten extent conversion on read
 		 * faults - that is unnecessary overhead and would also require
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
+		vmf->gfp_mask &= ~__GFP_FS;
 		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
+		vmf->gfp_mask = old_gfp;
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1581,8 +1588,13 @@ xfs_filemap_pfn_mkwrite(
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
-	else if (IS_DAX(inode))
+	else if (IS_DAX(inode)) {
+		gfp_t old_gfp = vmf->gfp_mask;
+
+		vmf->gfp_mask &= ~__GFP_FS;
 		ret = dax_pfn_mkwrite(vma, vmf);
+		vmf->gfp_mask = old_gfp;
+	}
 	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);
 	return ret;

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v3 2/3] mm, dax: make pmd_fault() and friends to be the same as fault()

[Dave Jiang]

Instead of passing in multiple parameters in the pmd_fault() handler,
a vmf can be passed in just like a fault() handler. This will simplify
code and remove the need for the actual pmd fault handlers to allocate a
vmf. Related functions are also modified to do the same.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 drivers/dax/dax.c             |   16 ++++++---------
 fs/dax.c                      |   45 ++++++++++++++++++-----------------------
 fs/ext4/file.c                |   14 ++++++++-----
 fs/xfs/xfs_file.c             |   14 +++++++------
 include/linux/dax.h           |    7 +++---
 include/linux/mm.h            |    3 +--
 include/trace/events/fs_dax.h |   15 ++++++--------
 mm/memory.c                   |    6 ++---
 8 files changed, 57 insertions(+), 63 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index c753a4c..947e49a 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -379,10 +379,9 @@ static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 
 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)
+		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	unsigned long pmd_addr = addr & PMD_MASK;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct device *dev = &dax_dev->dev;
 	struct dax_region *dax_region;
 	phys_addr_t phys;
@@ -414,23 +413,22 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 
 	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pmd(vma, addr, pmd, pfn,
-			flags & FAULT_FLAG_WRITE);
+	return vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
+			vmf->flags & FAULT_FLAG_WRITE);
 }
 
-static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, unsigned int flags)
+static int dax_dev_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	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)
+			current->comm, (vmf->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);
+	rc = __dax_dev_pmd_fault(dax_dev, vma, vmf);
 	rcu_read_unlock();
 
 	return rc;
diff --git a/fs/dax.c b/fs/dax.c
index 6395bc6..157f77f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1310,18 +1310,17 @@ static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
 	return VM_FAULT_FALLBACK;
 }
 
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops)
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+		struct iomap_ops *ops)
 {
 	struct address_space *mapping = vma->vm_file->f_mapping;
-	unsigned long pmd_addr = address & PMD_MASK;
-	bool write = flags & FAULT_FLAG_WRITE;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
 	struct inode *inode = mapping->host;
 	int result = VM_FAULT_FALLBACK;
 	struct iomap iomap = { 0 };
-	pgoff_t max_pgoff, pgoff;
-	struct vm_fault vmf;
+	pgoff_t max_pgoff, old_pgoff;
 	void *entry;
 	loff_t pos;
 	int error;
@@ -1331,10 +1330,11 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	 * supposed to hold locks serializing us with truncate / punch hole so
 	 * this is a reliable test.
 	 */
-	pgoff = linear_page_index(vma, pmd_addr);
+	old_pgoff = vmf->pgoff;
+	vmf->pgoff = linear_page_index(vma, pmd_addr);
 	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 
-	trace_dax_pmd_fault(inode, vma, address, flags, pgoff, max_pgoff, 0);
+	trace_dax_pmd_fault(inode, vma, vmf, max_pgoff, 0);
 
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED))
@@ -1346,13 +1346,13 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
 		goto fallback;
 
-	if (pgoff > max_pgoff) {
+	if (vmf->pgoff > max_pgoff) {
 		result = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
 	/* If the PMD would extend beyond the file size */
-	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
+	if ((vmf->pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
 	/*
@@ -1360,7 +1360,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	 * setting up a mapping, so really we're using iomap_begin() as a way
 	 * to look up our filesystem block.
 	 */
-	pos = (loff_t)pgoff << PAGE_SHIFT;
+	pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
 		goto fallback;
@@ -1370,29 +1370,24 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	 * the tree, for instance), it will return -EEXIST and we just fall
 	 * back to 4k entries.
 	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	entry = grab_mapping_entry(mapping, vmf->pgoff, RADIX_DAX_PMD);
 	if (IS_ERR(entry))
 		goto finish_iomap;
 
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto unlock_entry;
 
-	vmf.pgoff = pgoff;
-	vmf.flags = flags;
-	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
-	vmf.gfp_mask &= ~__GFP_FS;
-
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
-		result = dax_pmd_insert_mapping(vma, pmd, &vmf, address,
-				&iomap, pos, write, &entry);
+		result = dax_pmd_insert_mapping(vma, vmf->pmd, vmf,
+				vmf->address, &iomap, pos, write, &entry);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
 			goto unlock_entry;
-		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
-				&entry);
+		result = dax_pmd_load_hole(vma, vmf->pmd, vmf, vmf->address,
+				&iomap, &entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1400,7 +1395,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	}
 
  unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PMD_SIZE;
@@ -1418,12 +1413,12 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	}
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
-		split_huge_pmd(vma, pmd, address);
+		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
 out:
-	trace_dax_pmd_fault_done(inode, vma, address, flags, pgoff, max_pgoff,
-			result);
+	trace_dax_pmd_fault_done(inode, vma, vmf, max_pgoff, result);
+	vmf->pgoff = old_pgoff;
 	return result;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index a3f2bf0..e6cdb78 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -278,22 +278,26 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return result;
 }
 
-static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
+static int
+ext4_dax_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
-	bool write = flags & FAULT_FLAG_WRITE;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	gfp_t old_mask;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
 	}
+
+	old_mask = vmf->gfp_mask;
+	vmf->gfp_mask &= ~__GFP_FS;
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-				     &ext4_iomap_ops);
+	result = dax_iomap_pmd_fault(vma, vmf, &ext4_iomap_ops);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
+	vmf->gfp_mask = old_mask;
 	if (write)
 		sb_end_pagefault(sb);
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 52202b4..b1b8524 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1533,29 +1533,31 @@ xfs_filemap_fault(
 STATIC int
 xfs_filemap_pmd_fault(
 	struct vm_area_struct	*vma,
-	unsigned long		addr,
-	pmd_t			*pmd,
-	unsigned int		flags)
+	struct vm_fault *vmf)
 {
 	struct inode		*inode = file_inode(vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			ret;
+	gfp_t			old_mask;
 
 	if (!IS_DAX(inode))
 		return VM_FAULT_FALLBACK;
 
 	trace_xfs_filemap_pmd_fault(ip);
 
-	if (flags & FAULT_FLAG_WRITE) {
+	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
 		file_update_time(vma->vm_file);
 	}
 
+	old_mask = vmf->gfp_mask;
+	vmf->gfp_mask &= ~__GFP_FS;
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops);
+	ret = dax_iomap_pmd_fault(vma, vmf, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	vmf->gfp_mask = old_mask;
 
-	if (flags & FAULT_FLAG_WRITE)
+	if (vmf->flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(inode->i_sb);
 
 	return ret;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 6e36b11..9761c90 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -71,16 +71,15 @@ static inline unsigned int dax_radix_order(void *entry)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops);
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+		struct iomap_ops *ops);
 #else
 static inline unsigned int dax_radix_order(void *entry)
 {
 	return 0;
 }
 static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
-		unsigned long address, pmd_t *pmd, unsigned int flags,
-		struct iomap_ops *ops)
+		struct vm_fault *vmf, struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 30f416a..aef645b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -347,8 +347,7 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
-						pmd_t *, unsigned int flags);
+	int (*pmd_fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index c3b0aae..a98665b 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -8,9 +8,8 @@
 
 DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags, pgoff_t pgoff,
-		pgoff_t max_pgoff, int result),
-	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result),
+		struct vm_fault *vmf, pgoff_t max_pgoff, int result),
+	TP_ARGS(inode, vma, vmf, max_pgoff, result),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_start)
@@ -29,9 +28,9 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 		__entry->vm_start = vma->vm_start;
 		__entry->vm_end = vma->vm_end;
 		__entry->vm_flags = vma->vm_flags;
-		__entry->address = address;
-		__entry->flags = flags;
-		__entry->pgoff = pgoff;
+		__entry->address = vmf->address;
+		__entry->flags = vmf->flags;
+		__entry->pgoff = vmf->pgoff;
 		__entry->max_pgoff = max_pgoff;
 		__entry->result = result;
 	),
@@ -54,9 +53,9 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 #define DEFINE_PMD_FAULT_EVENT(name) \
 DEFINE_EVENT(dax_pmd_fault_class, name, \
 	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		unsigned long address, unsigned int flags, pgoff_t pgoff, \
+		struct vm_fault *vmf, \
 		pgoff_t max_pgoff, int result), \
-	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result))
+	TP_ARGS(inode, vma, vmf, max_pgoff, result))
 
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
diff --git a/mm/memory.c b/mm/memory.c
index e37250f..8ec36cf 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3447,8 +3447,7 @@ static int create_huge_pmd(struct vm_fault *vmf)
 	if (vma_is_anonymous(vma))
 		return do_huge_pmd_anonymous_page(vmf);
 	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, vmf->address, vmf->pmd,
-				vmf->flags);
+		return vma->vm_ops->pmd_fault(vma, vmf);
 	return VM_FAULT_FALLBACK;
 }
 
@@ -3457,8 +3456,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
 	if (vmf->vma->vm_ops->pmd_fault)
-		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf->address,
-				vmf->pmd, vmf->flags);
+		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf);
 
 	/* COW handled on pte level: split pmd */
 	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v3 3/3] mm, dax: move pmd_fault() to take only vmf parameter

[Dave Jiang]

pmd_fault() and related functions really only need the vmf parameter since
the additional parameters are all included in the vmf struct. Removing
additional parameter and simplify pmd_fault() and friends.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/dax/dax.c             |   18 +++++++-------
 fs/dax.c                      |   54 +++++++++++++++++++----------------------
 fs/ext4/file.c                |    8 +++---
 fs/xfs/xfs_file.c             |    7 ++---
 include/linux/dax.h           |    7 ++---
 include/linux/mm.h            |    2 +-
 include/trace/events/fs_dax.h |   54 +++++++++++++++++++----------------------
 mm/memory.c                   |    9 +++----
 8 files changed, 74 insertions(+), 85 deletions(-)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 947e49a..55160f8 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -378,8 +378,7 @@ static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return rc;
 }
 
-static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
-		struct vm_area_struct *vma, struct vm_fault *vmf)
+static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 {
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct device *dev = &dax_dev->dev;
@@ -388,7 +387,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 	pgoff_t pgoff;
 	pfn_t pfn;
 
-	if (check_vma(dax_dev, vma, __func__))
+	if (check_vma(dax_dev, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
 	dax_region = dax_dev->region;
@@ -403,7 +402,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 		return VM_FAULT_SIGBUS;
 	}
 
-	pgoff = linear_page_index(vma, pmd_addr);
+	pgoff = linear_page_index(vmf->vma, pmd_addr);
 	phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
 	if (phys == -1) {
 		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
@@ -413,22 +412,23 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 
 	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
+	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, pfn,
 			vmf->flags & FAULT_FLAG_WRITE);
 }
 
-static int dax_dev_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int dax_dev_pmd_fault(struct vm_fault *vmf)
 {
 	int rc;
-	struct file *filp = vma->vm_file;
+	struct file *filp = vmf->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, (vmf->flags & FAULT_FLAG_WRITE)
-			? "write" : "read", vma->vm_start, vma->vm_end);
+			? "write" : "read",
+			vmf->vma->vm_start, vmf->vma->vm_end);
 
 	rcu_read_lock();
-	rc = __dax_dev_pmd_fault(dax_dev, vma, vmf);
+	rc = __dax_dev_pmd_fault(dax_dev, vmf);
 	rcu_read_unlock();
 
 	return rc;
diff --git a/fs/dax.c b/fs/dax.c
index 157f77f..bc39809 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1226,11 +1226,10 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault);
  */
 #define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
 
-static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
-		struct vm_fault *vmf, unsigned long address,
-		struct iomap *iomap, loff_t pos, bool write, void **entryp)
+static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap,
+		loff_t pos, void **entryp)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	struct block_device *bdev = iomap->bdev;
 	struct inode *inode = mapping->host;
 	struct blk_dax_ctl dax = {
@@ -1257,31 +1256,30 @@ static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
 		goto fallback;
 	*entryp = ret;
 
-	trace_dax_pmd_insert_mapping(inode, vma, address, write, length,
-			dax.pfn, ret);
-	return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write);
+	trace_dax_pmd_insert_mapping(inode, vmf, length, dax.pfn, ret);
+	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
+			dax.pfn, vmf->flags & FAULT_FLAG_WRITE);
 
  unmap_fallback:
 	dax_unmap_atomic(bdev, &dax);
 fallback:
-	trace_dax_pmd_insert_mapping_fallback(inode, vma, address, write,
-			length, dax.pfn, ret);
+	trace_dax_pmd_insert_mapping_fallback(inode, vmf, length,
+			dax.pfn, ret);
 	return VM_FAULT_FALLBACK;
 }
 
-static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
-		struct vm_fault *vmf, unsigned long address,
-		struct iomap *iomap, void **entryp)
+static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
+		void **entryp)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	unsigned long pmd_addr = address & PMD_MASK;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct inode *inode = mapping->host;
 	struct page *zero_page;
 	void *ret = NULL;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
 
-	zero_page = mm_get_huge_zero_page(vma->vm_mm);
+	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
 
 	if (unlikely(!zero_page))
 		goto fallback;
@@ -1292,27 +1290,27 @@ static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
 		goto fallback;
 	*entryp = ret;
 
-	ptl = pmd_lock(vma->vm_mm, pmd);
-	if (!pmd_none(*pmd)) {
+	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
+	if (!pmd_none(*(vmf->pmd))) {
 		spin_unlock(ptl);
 		goto fallback;
 	}
 
-	pmd_entry = mk_pmd(zero_page, vma->vm_page_prot);
+	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
 	pmd_entry = pmd_mkhuge(pmd_entry);
-	set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry);
+	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
 	spin_unlock(ptl);
-	trace_dax_pmd_load_hole(inode, vma, address, zero_page, ret);
+	trace_dax_pmd_load_hole(inode, vmf, zero_page, ret);
 	return VM_FAULT_NOPAGE;
 
 fallback:
-	trace_dax_pmd_load_hole_fallback(inode, vma, address, zero_page, ret);
+	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret);
 	return VM_FAULT_FALLBACK;
 }
 
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-		struct iomap_ops *ops)
+int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -1334,7 +1332,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	vmf->pgoff = linear_page_index(vma, pmd_addr);
 	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 
-	trace_dax_pmd_fault(inode, vma, vmf, max_pgoff, 0);
+	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
 
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED))
@@ -1379,15 +1377,13 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
-		result = dax_pmd_insert_mapping(vma, vmf->pmd, vmf,
-				vmf->address, &iomap, pos, write, &entry);
+		result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
 			goto unlock_entry;
-		result = dax_pmd_load_hole(vma, vmf->pmd, vmf, vmf->address,
-				&iomap, &entry);
+		result = dax_pmd_load_hole(vmf, &iomap, &entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1417,7 +1413,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
 out:
-	trace_dax_pmd_fault_done(inode, vma, vmf, max_pgoff, result);
+	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
 	vmf->pgoff = old_pgoff;
 	return result;
 }
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index e6cdb78..2f4fd28 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -279,23 +279,23 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 
 static int
-ext4_dax_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+ext4_dax_pmd_fault(struct vm_fault *vmf)
 {
 	int result;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	gfp_t old_mask;
 
 	if (write) {
 		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
 	}
 
 	old_mask = vmf->gfp_mask;
 	vmf->gfp_mask &= ~__GFP_FS;
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_pmd_fault(vma, vmf, &ext4_iomap_ops);
+	result = dax_iomap_pmd_fault(vmf, &ext4_iomap_ops);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	vmf->gfp_mask = old_mask;
 	if (write)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index b1b8524..b548fc5 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1532,10 +1532,9 @@ xfs_filemap_fault(
  */
 STATIC int
 xfs_filemap_pmd_fault(
-	struct vm_area_struct	*vma,
 	struct vm_fault *vmf)
 {
-	struct inode		*inode = file_inode(vma->vm_file);
+	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			ret;
 	gfp_t			old_mask;
@@ -1547,13 +1546,13 @@ xfs_filemap_pmd_fault(
 
 	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
 	}
 
 	old_mask = vmf->gfp_mask;
 	vmf->gfp_mask &= ~__GFP_FS;
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_iomap_pmd_fault(vma, vmf, &xfs_iomap_ops);
+	ret = dax_iomap_pmd_fault(vmf, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	vmf->gfp_mask = old_mask;
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9761c90..1ffdb4d 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -71,15 +71,14 @@ static inline unsigned int dax_radix_order(void *entry)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-		struct iomap_ops *ops);
+int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops);
 #else
 static inline unsigned int dax_radix_order(void *entry)
 {
 	return 0;
 }
-static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
-		struct vm_fault *vmf, struct iomap_ops *ops)
+static inline int dax_iomap_pmd_fault(struct vm_fault *vmf,
+		struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index aef645b..795f03e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -347,7 +347,7 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-	int (*pmd_fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	int (*pmd_fault)(struct vm_fault *vmf);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index a98665b..c566ddc 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -7,9 +7,9 @@
 #include <linux/tracepoint.h>
 
 DECLARE_EVENT_CLASS(dax_pmd_fault_class,
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		struct vm_fault *vmf, pgoff_t max_pgoff, int result),
-	TP_ARGS(inode, vma, vmf, max_pgoff, result),
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		pgoff_t max_pgoff, int result),
+	TP_ARGS(inode, vmf, max_pgoff, result),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_start)
@@ -25,9 +25,9 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
-		__entry->vm_start = vma->vm_start;
-		__entry->vm_end = vma->vm_end;
-		__entry->vm_flags = vma->vm_flags;
+		__entry->vm_start = vmf->vma->vm_start;
+		__entry->vm_end = vmf->vma->vm_end;
+		__entry->vm_flags = vmf->vma->vm_flags;
 		__entry->address = vmf->address;
 		__entry->flags = vmf->flags;
 		__entry->pgoff = vmf->pgoff;
@@ -52,19 +52,18 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 
 #define DEFINE_PMD_FAULT_EVENT(name) \
 DEFINE_EVENT(dax_pmd_fault_class, name, \
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		struct vm_fault *vmf, \
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
 		pgoff_t max_pgoff, int result), \
-	TP_ARGS(inode, vma, vmf, max_pgoff, result))
+	TP_ARGS(inode, vmf, max_pgoff, result))
 
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
 DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
 
 DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		unsigned long address, struct page *zero_page,
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		struct page *zero_page,
 		void *radix_entry),
-	TP_ARGS(inode, vma, address, zero_page, radix_entry),
+	TP_ARGS(inode, vmf, zero_page, radix_entry),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_flags)
@@ -76,8 +75,8 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
-		__entry->vm_flags = vma->vm_flags;
-		__entry->address = address;
+		__entry->vm_flags = vmf->vma->vm_flags;
+		__entry->address = vmf->address;
 		__entry->zero_page = zero_page;
 		__entry->radix_entry = radix_entry;
 	),
@@ -95,19 +94,17 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
 
 #define DEFINE_PMD_LOAD_HOLE_EVENT(name) \
 DEFINE_EVENT(dax_pmd_load_hole_class, name, \
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		unsigned long address, struct page *zero_page, \
-		void *radix_entry), \
-	TP_ARGS(inode, vma, address, zero_page, radix_entry))
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
+		struct page *zero_page, void *radix_entry), \
+	TP_ARGS(inode, vmf, zero_page, radix_entry))
 
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
 
 DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
-		unsigned long address, int write, long length, pfn_t pfn,
-		void *radix_entry),
-	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry),
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		long length, pfn_t pfn, void *radix_entry),
+	TP_ARGS(inode, vmf, length, pfn, radix_entry),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_flags)
@@ -121,9 +118,9 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
 	TP_fast_assign(
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = inode->i_ino;
-		__entry->vm_flags = vma->vm_flags;
-		__entry->address = address;
-		__entry->write = write;
+		__entry->vm_flags = vmf->vma->vm_flags;
+		__entry->address = vmf->address;
+		__entry->write = vmf->flags & FAULT_FLAG_WRITE;
 		__entry->length = length;
 		__entry->pfn_val = pfn.val;
 		__entry->radix_entry = radix_entry;
@@ -146,10 +143,9 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
 
 #define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
 DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
-	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
-		unsigned long address, int write, long length, pfn_t pfn, \
-		void *radix_entry), \
-	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry))
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
+		long length, pfn_t pfn, void *radix_entry), \
+	TP_ARGS(inode, vmf, length, pfn, radix_entry))
 
 DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
 DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping_fallback);
diff --git a/mm/memory.c b/mm/memory.c
index 8ec36cf..e929c41 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3443,11 +3443,10 @@ static int do_numa_page(struct vm_fault *vmf)
 
 static int create_huge_pmd(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	if (vma_is_anonymous(vma))
+	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_anonymous_page(vmf);
-	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, vmf);
+	if (vmf->vma->vm_ops->pmd_fault)
+		return vmf->vma->vm_ops->pmd_fault(vmf);
 	return VM_FAULT_FALLBACK;
 }
 
@@ -3456,7 +3455,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
 	if (vmf->vma->vm_ops->pmd_fault)
-		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf);
+		return vmf->vma->vm_ops->pmd_fault(vmf);
 
 	/* COW handled on pte level: split pmd */
 	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v3 2/3] mm, dax: make pmd_fault() and friends to be the same as fault()

[Ross Zwisler]

On Thu, Dec 15, 2016 at 01:51:05PM -0700, Dave Jiang wrote:
> Instead of passing in multiple parameters in the pmd_fault() handler,
> a vmf can be passed in just like a fault() handler. This will simplify
> code and remove the need for the actual pmd fault handlers to allocate a
> vmf. Related functions are also modified to do the same.
> 
> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
> Reviewed-by: Jan Kara <jack@suse.cz>
> ---

> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index a3f2bf0..e6cdb78 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -278,22 +278,26 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
>  	return result;
>  }
>  
> -static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
> -						pmd_t *pmd, unsigned int flags)
> +static int
> +ext4_dax_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
>  {
>  	int result;
>  	struct inode *inode = file_inode(vma->vm_file);
>  	struct super_block *sb = inode->i_sb;
> -	bool write = flags & FAULT_FLAG_WRITE;
> +	bool write = vmf->flags & FAULT_FLAG_WRITE;
> +	gfp_t old_mask;
>  
>  	if (write) {
>  		sb_start_pagefault(sb);
>  		file_update_time(vma->vm_file);
>  	}
> +
> +	old_mask = vmf->gfp_mask;
> +	vmf->gfp_mask &= ~__GFP_FS;
>  	down_read(&EXT4_I(inode)->i_mmap_sem);
> -	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
> -				     &ext4_iomap_ops);
> +	result = dax_iomap_pmd_fault(vma, vmf, &ext4_iomap_ops);
>  	up_read(&EXT4_I(inode)->i_mmap_sem);
> +	vmf->gfp_mask = old_mask;
>  	if (write)
>  		sb_end_pagefault(sb);
>  
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 52202b4..b1b8524 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -1533,29 +1533,31 @@ xfs_filemap_fault(
>  STATIC int
>  xfs_filemap_pmd_fault(
>  	struct vm_area_struct	*vma,
> -	unsigned long		addr,
> -	pmd_t			*pmd,
> -	unsigned int		flags)
> +	struct vm_fault *vmf)
>  {
>  	struct inode		*inode = file_inode(vma->vm_file);
>  	struct xfs_inode	*ip = XFS_I(inode);
>  	int			ret;
> +	gfp_t			old_mask;
>  
>  	if (!IS_DAX(inode))
>  		return VM_FAULT_FALLBACK;
>  
>  	trace_xfs_filemap_pmd_fault(ip);
>  
> -	if (flags & FAULT_FLAG_WRITE) {
> +	if (vmf->flags & FAULT_FLAG_WRITE) {
>  		sb_start_pagefault(inode->i_sb);
>  		file_update_time(vma->vm_file);
>  	}
>  
> +	old_mask = vmf->gfp_mask;

One small nit for both xfs and ext4 - in patch 1 you named your local
'old_gfp' and set it when it was defined, but in this patch it's 'old_mask'
and it's set later.  Probably best to keep this patch consistent with the
first one.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v3 3/3] mm, dax: move pmd_fault() to take only vmf parameter

[Ross Zwisler]

On Thu, Dec 15, 2016 at 01:51:11PM -0700, Dave Jiang wrote:
> pmd_fault() and related functions really only need the vmf parameter since
> the additional parameters are all included in the vmf struct. Removing
> additional parameter and simplify pmd_fault() and friends.
> 
> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
 
This seems correct to me.

Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v3 3/3] mm, dax: move pmd_fault() to take only vmf parameter

[Jan Kara]

On Thu 15-12-16 13:51:11, Dave Jiang wrote:
> pmd_fault() and related functions really only need the vmf parameter since
> the additional parameters are all included in the vmf struct. Removing
> additional parameter and simplify pmd_fault() and friends.
> 
> Signed-off-by: Dave Jiang <dave.jiang@intel.com>

Looks good. You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

BTW, if you want to continue with this, it may be worthwhile to also
convert vmf_insert_pfn_pmd() to take only 'vmf' and 'pfn' arguments.

								Honza

> ---
>  drivers/dax/dax.c             |   18 +++++++-------
>  fs/dax.c                      |   54 +++++++++++++++++++----------------------
>  fs/ext4/file.c                |    8 +++---
>  fs/xfs/xfs_file.c             |    7 ++---
>  include/linux/dax.h           |    7 ++---
>  include/linux/mm.h            |    2 +-
>  include/trace/events/fs_dax.h |   54 +++++++++++++++++++----------------------
>  mm/memory.c                   |    9 +++----
>  8 files changed, 74 insertions(+), 85 deletions(-)
> 
> diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
> index 947e49a..55160f8 100644
> --- a/drivers/dax/dax.c
> +++ b/drivers/dax/dax.c
> @@ -378,8 +378,7 @@ static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
>  	return rc;
>  }
>  
> -static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
> -		struct vm_area_struct *vma, struct vm_fault *vmf)
> +static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
>  {
>  	unsigned long pmd_addr = vmf->address & PMD_MASK;
>  	struct device *dev = &dax_dev->dev;
> @@ -388,7 +387,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
>  	pgoff_t pgoff;
>  	pfn_t pfn;
>  
> -	if (check_vma(dax_dev, vma, __func__))
> +	if (check_vma(dax_dev, vmf->vma, __func__))
>  		return VM_FAULT_SIGBUS;
>  
>  	dax_region = dax_dev->region;
> @@ -403,7 +402,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
>  		return VM_FAULT_SIGBUS;
>  	}
>  
> -	pgoff = linear_page_index(vma, pmd_addr);
> +	pgoff = linear_page_index(vmf->vma, pmd_addr);
>  	phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
>  	if (phys == -1) {
>  		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
> @@ -413,22 +412,23 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
>  
>  	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
>  
> -	return vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
> +	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, pfn,
>  			vmf->flags & FAULT_FLAG_WRITE);
>  }
>  
> -static int dax_dev_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
> +static int dax_dev_pmd_fault(struct vm_fault *vmf)
>  {
>  	int rc;
> -	struct file *filp = vma->vm_file;
> +	struct file *filp = vmf->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, (vmf->flags & FAULT_FLAG_WRITE)
> -			? "write" : "read", vma->vm_start, vma->vm_end);
> +			? "write" : "read",
> +			vmf->vma->vm_start, vmf->vma->vm_end);
>  
>  	rcu_read_lock();
> -	rc = __dax_dev_pmd_fault(dax_dev, vma, vmf);
> +	rc = __dax_dev_pmd_fault(dax_dev, vmf);
>  	rcu_read_unlock();
>  
>  	return rc;
> diff --git a/fs/dax.c b/fs/dax.c
> index 157f77f..bc39809 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1226,11 +1226,10 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault);
>   */
>  #define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
>  
> -static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
> -		struct vm_fault *vmf, unsigned long address,
> -		struct iomap *iomap, loff_t pos, bool write, void **entryp)
> +static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap,
> +		loff_t pos, void **entryp)
>  {
> -	struct address_space *mapping = vma->vm_file->f_mapping;
> +	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
>  	struct block_device *bdev = iomap->bdev;
>  	struct inode *inode = mapping->host;
>  	struct blk_dax_ctl dax = {
> @@ -1257,31 +1256,30 @@ static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
>  		goto fallback;
>  	*entryp = ret;
>  
> -	trace_dax_pmd_insert_mapping(inode, vma, address, write, length,
> -			dax.pfn, ret);
> -	return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write);
> +	trace_dax_pmd_insert_mapping(inode, vmf, length, dax.pfn, ret);
> +	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
> +			dax.pfn, vmf->flags & FAULT_FLAG_WRITE);
>  
>   unmap_fallback:
>  	dax_unmap_atomic(bdev, &dax);
>  fallback:
> -	trace_dax_pmd_insert_mapping_fallback(inode, vma, address, write,
> -			length, dax.pfn, ret);
> +	trace_dax_pmd_insert_mapping_fallback(inode, vmf, length,
> +			dax.pfn, ret);
>  	return VM_FAULT_FALLBACK;
>  }
>  
> -static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
> -		struct vm_fault *vmf, unsigned long address,
> -		struct iomap *iomap, void **entryp)
> +static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
> +		void **entryp)
>  {
> -	struct address_space *mapping = vma->vm_file->f_mapping;
> -	unsigned long pmd_addr = address & PMD_MASK;
> +	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
> +	unsigned long pmd_addr = vmf->address & PMD_MASK;
>  	struct inode *inode = mapping->host;
>  	struct page *zero_page;
>  	void *ret = NULL;
>  	spinlock_t *ptl;
>  	pmd_t pmd_entry;
>  
> -	zero_page = mm_get_huge_zero_page(vma->vm_mm);
> +	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
>  
>  	if (unlikely(!zero_page))
>  		goto fallback;
> @@ -1292,27 +1290,27 @@ static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
>  		goto fallback;
>  	*entryp = ret;
>  
> -	ptl = pmd_lock(vma->vm_mm, pmd);
> -	if (!pmd_none(*pmd)) {
> +	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
> +	if (!pmd_none(*(vmf->pmd))) {
>  		spin_unlock(ptl);
>  		goto fallback;
>  	}
>  
> -	pmd_entry = mk_pmd(zero_page, vma->vm_page_prot);
> +	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
>  	pmd_entry = pmd_mkhuge(pmd_entry);
> -	set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry);
> +	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
>  	spin_unlock(ptl);
> -	trace_dax_pmd_load_hole(inode, vma, address, zero_page, ret);
> +	trace_dax_pmd_load_hole(inode, vmf, zero_page, ret);
>  	return VM_FAULT_NOPAGE;
>  
>  fallback:
> -	trace_dax_pmd_load_hole_fallback(inode, vma, address, zero_page, ret);
> +	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret);
>  	return VM_FAULT_FALLBACK;
>  }
>  
> -int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
> -		struct iomap_ops *ops)
> +int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
>  {
> +	struct vm_area_struct *vma = vmf->vma;
>  	struct address_space *mapping = vma->vm_file->f_mapping;
>  	unsigned long pmd_addr = vmf->address & PMD_MASK;
>  	bool write = vmf->flags & FAULT_FLAG_WRITE;
> @@ -1334,7 +1332,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
>  	vmf->pgoff = linear_page_index(vma, pmd_addr);
>  	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
>  
> -	trace_dax_pmd_fault(inode, vma, vmf, max_pgoff, 0);
> +	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
>  
>  	/* Fall back to PTEs if we're going to COW */
>  	if (write && !(vma->vm_flags & VM_SHARED))
> @@ -1379,15 +1377,13 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
>  
>  	switch (iomap.type) {
>  	case IOMAP_MAPPED:
> -		result = dax_pmd_insert_mapping(vma, vmf->pmd, vmf,
> -				vmf->address, &iomap, pos, write, &entry);
> +		result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
>  		break;
>  	case IOMAP_UNWRITTEN:
>  	case IOMAP_HOLE:
>  		if (WARN_ON_ONCE(write))
>  			goto unlock_entry;
> -		result = dax_pmd_load_hole(vma, vmf->pmd, vmf, vmf->address,
> -				&iomap, &entry);
> +		result = dax_pmd_load_hole(vmf, &iomap, &entry);
>  		break;
>  	default:
>  		WARN_ON_ONCE(1);
> @@ -1417,7 +1413,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
>  		count_vm_event(THP_FAULT_FALLBACK);
>  	}
>  out:
> -	trace_dax_pmd_fault_done(inode, vma, vmf, max_pgoff, result);
> +	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
>  	vmf->pgoff = old_pgoff;
>  	return result;
>  }
> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index e6cdb78..2f4fd28 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -279,23 +279,23 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
>  }
>  
>  static int
> -ext4_dax_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
> +ext4_dax_pmd_fault(struct vm_fault *vmf)
>  {
>  	int result;
> -	struct inode *inode = file_inode(vma->vm_file);
> +	struct inode *inode = file_inode(vmf->vma->vm_file);
>  	struct super_block *sb = inode->i_sb;
>  	bool write = vmf->flags & FAULT_FLAG_WRITE;
>  	gfp_t old_mask;
>  
>  	if (write) {
>  		sb_start_pagefault(sb);
> -		file_update_time(vma->vm_file);
> +		file_update_time(vmf->vma->vm_file);
>  	}
>  
>  	old_mask = vmf->gfp_mask;
>  	vmf->gfp_mask &= ~__GFP_FS;
>  	down_read(&EXT4_I(inode)->i_mmap_sem);
> -	result = dax_iomap_pmd_fault(vma, vmf, &ext4_iomap_ops);
> +	result = dax_iomap_pmd_fault(vmf, &ext4_iomap_ops);
>  	up_read(&EXT4_I(inode)->i_mmap_sem);
>  	vmf->gfp_mask = old_mask;
>  	if (write)
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index b1b8524..b548fc5 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -1532,10 +1532,9 @@ xfs_filemap_fault(
>   */
>  STATIC int
>  xfs_filemap_pmd_fault(
> -	struct vm_area_struct	*vma,
>  	struct vm_fault *vmf)
>  {
> -	struct inode		*inode = file_inode(vma->vm_file);
> +	struct inode		*inode = file_inode(vmf->vma->vm_file);
>  	struct xfs_inode	*ip = XFS_I(inode);
>  	int			ret;
>  	gfp_t			old_mask;
> @@ -1547,13 +1546,13 @@ xfs_filemap_pmd_fault(
>  
>  	if (vmf->flags & FAULT_FLAG_WRITE) {
>  		sb_start_pagefault(inode->i_sb);
> -		file_update_time(vma->vm_file);
> +		file_update_time(vmf->vma->vm_file);
>  	}
>  
>  	old_mask = vmf->gfp_mask;
>  	vmf->gfp_mask &= ~__GFP_FS;
>  	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
> -	ret = dax_iomap_pmd_fault(vma, vmf, &xfs_iomap_ops);
> +	ret = dax_iomap_pmd_fault(vmf, &xfs_iomap_ops);
>  	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
>  	vmf->gfp_mask = old_mask;
>  
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 9761c90..1ffdb4d 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -71,15 +71,14 @@ static inline unsigned int dax_radix_order(void *entry)
>  		return PMD_SHIFT - PAGE_SHIFT;
>  	return 0;
>  }
> -int dax_iomap_pmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
> -		struct iomap_ops *ops);
> +int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops);
>  #else
>  static inline unsigned int dax_radix_order(void *entry)
>  {
>  	return 0;
>  }
> -static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
> -		struct vm_fault *vmf, struct iomap_ops *ops)
> +static inline int dax_iomap_pmd_fault(struct vm_fault *vmf,
> +		struct iomap_ops *ops)
>  {
>  	return VM_FAULT_FALLBACK;
>  }
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index aef645b..795f03e 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -347,7 +347,7 @@ struct vm_operations_struct {
>  	void (*close)(struct vm_area_struct * area);
>  	int (*mremap)(struct vm_area_struct * area);
>  	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
> -	int (*pmd_fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
> +	int (*pmd_fault)(struct vm_fault *vmf);
>  	void (*map_pages)(struct vm_fault *vmf,
>  			pgoff_t start_pgoff, pgoff_t end_pgoff);
>  
> diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
> index a98665b..c566ddc 100644
> --- a/include/trace/events/fs_dax.h
> +++ b/include/trace/events/fs_dax.h
> @@ -7,9 +7,9 @@
>  #include <linux/tracepoint.h>
>  
>  DECLARE_EVENT_CLASS(dax_pmd_fault_class,
> -	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
> -		struct vm_fault *vmf, pgoff_t max_pgoff, int result),
> -	TP_ARGS(inode, vma, vmf, max_pgoff, result),
> +	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
> +		pgoff_t max_pgoff, int result),
> +	TP_ARGS(inode, vmf, max_pgoff, result),
>  	TP_STRUCT__entry(
>  		__field(unsigned long, ino)
>  		__field(unsigned long, vm_start)
> @@ -25,9 +25,9 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
>  	TP_fast_assign(
>  		__entry->dev = inode->i_sb->s_dev;
>  		__entry->ino = inode->i_ino;
> -		__entry->vm_start = vma->vm_start;
> -		__entry->vm_end = vma->vm_end;
> -		__entry->vm_flags = vma->vm_flags;
> +		__entry->vm_start = vmf->vma->vm_start;
> +		__entry->vm_end = vmf->vma->vm_end;
> +		__entry->vm_flags = vmf->vma->vm_flags;
>  		__entry->address = vmf->address;
>  		__entry->flags = vmf->flags;
>  		__entry->pgoff = vmf->pgoff;
> @@ -52,19 +52,18 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
>  
>  #define DEFINE_PMD_FAULT_EVENT(name) \
>  DEFINE_EVENT(dax_pmd_fault_class, name, \
> -	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
> -		struct vm_fault *vmf, \
> +	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
>  		pgoff_t max_pgoff, int result), \
> -	TP_ARGS(inode, vma, vmf, max_pgoff, result))
> +	TP_ARGS(inode, vmf, max_pgoff, result))
>  
>  DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
>  DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
>  
>  DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
> -	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
> -		unsigned long address, struct page *zero_page,
> +	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
> +		struct page *zero_page,
>  		void *radix_entry),
> -	TP_ARGS(inode, vma, address, zero_page, radix_entry),
> +	TP_ARGS(inode, vmf, zero_page, radix_entry),
>  	TP_STRUCT__entry(
>  		__field(unsigned long, ino)
>  		__field(unsigned long, vm_flags)
> @@ -76,8 +75,8 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
>  	TP_fast_assign(
>  		__entry->dev = inode->i_sb->s_dev;
>  		__entry->ino = inode->i_ino;
> -		__entry->vm_flags = vma->vm_flags;
> -		__entry->address = address;
> +		__entry->vm_flags = vmf->vma->vm_flags;
> +		__entry->address = vmf->address;
>  		__entry->zero_page = zero_page;
>  		__entry->radix_entry = radix_entry;
>  	),
> @@ -95,19 +94,17 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
>  
>  #define DEFINE_PMD_LOAD_HOLE_EVENT(name) \
>  DEFINE_EVENT(dax_pmd_load_hole_class, name, \
> -	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
> -		unsigned long address, struct page *zero_page, \
> -		void *radix_entry), \
> -	TP_ARGS(inode, vma, address, zero_page, radix_entry))
> +	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
> +		struct page *zero_page, void *radix_entry), \
> +	TP_ARGS(inode, vmf, zero_page, radix_entry))
>  
>  DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
>  DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
>  
>  DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
> -	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
> -		unsigned long address, int write, long length, pfn_t pfn,
> -		void *radix_entry),
> -	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry),
> +	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
> +		long length, pfn_t pfn, void *radix_entry),
> +	TP_ARGS(inode, vmf, length, pfn, radix_entry),
>  	TP_STRUCT__entry(
>  		__field(unsigned long, ino)
>  		__field(unsigned long, vm_flags)
> @@ -121,9 +118,9 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
>  	TP_fast_assign(
>  		__entry->dev = inode->i_sb->s_dev;
>  		__entry->ino = inode->i_ino;
> -		__entry->vm_flags = vma->vm_flags;
> -		__entry->address = address;
> -		__entry->write = write;
> +		__entry->vm_flags = vmf->vma->vm_flags;
> +		__entry->address = vmf->address;
> +		__entry->write = vmf->flags & FAULT_FLAG_WRITE;
>  		__entry->length = length;
>  		__entry->pfn_val = pfn.val;
>  		__entry->radix_entry = radix_entry;
> @@ -146,10 +143,9 @@ DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
>  
>  #define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
>  DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
> -	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
> -		unsigned long address, int write, long length, pfn_t pfn, \
> -		void *radix_entry), \
> -	TP_ARGS(inode, vma, address, write, length, pfn, radix_entry))
> +	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
> +		long length, pfn_t pfn, void *radix_entry), \
> +	TP_ARGS(inode, vmf, length, pfn, radix_entry))
>  
>  DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
>  DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping_fallback);
> diff --git a/mm/memory.c b/mm/memory.c
> index 8ec36cf..e929c41 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3443,11 +3443,10 @@ static int do_numa_page(struct vm_fault *vmf)
>  
>  static int create_huge_pmd(struct vm_fault *vmf)
>  {
> -	struct vm_area_struct *vma = vmf->vma;
> -	if (vma_is_anonymous(vma))
> +	if (vma_is_anonymous(vmf->vma))
>  		return do_huge_pmd_anonymous_page(vmf);
> -	if (vma->vm_ops->pmd_fault)
> -		return vma->vm_ops->pmd_fault(vma, vmf);
> +	if (vmf->vma->vm_ops->pmd_fault)
> +		return vmf->vma->vm_ops->pmd_fault(vmf);
>  	return VM_FAULT_FALLBACK;
>  }
>  
> @@ -3456,7 +3455,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
>  	if (vma_is_anonymous(vmf->vma))
>  		return do_huge_pmd_wp_page(vmf, orig_pmd);
>  	if (vmf->vma->vm_ops->pmd_fault)
> -		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf);
> +		return vmf->vma->vm_ops->pmd_fault(vmf);
>  
>  	/* COW handled on pte level: split pmd */
>  	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v3 1/3] dax: masking off __GFP_FS in fs DAX handlers

[Michal Hocko]

On Thu 15-12-16 13:50:59, Dave Jiang wrote:
> The caller into dax needs to clear __GFP_FS mask bit since it's
> responsible for acquiring locks / transactions that blocks __GFP_FS
> allocation.  The caller will restore the original mask when dax function
> returns.

Could you have a look at [1]. Does the new API look like a fit for your
use case here? It at least sounds a bit easier from the code POV to me.

[1] http://lkml.kernel.org/r/20161215140715.12732-1-mhocko@kernel.org

> 
> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
> Reviewed-by: Jan Kara <jack@suse.cz>
> ---
>  fs/dax.c          |    1 +
>  fs/ext2/file.c    |    9 ++++++++-
>  fs/ext4/file.c    |   10 +++++++++-
>  fs/xfs/xfs_file.c |   14 +++++++++++++-
>  4 files changed, 31 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index d3fe880..6395bc6 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1380,6 +1380,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
>  	vmf.pgoff = pgoff;
>  	vmf.flags = flags;
>  	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
> +	vmf.gfp_mask &= ~__GFP_FS;
>  
>  	switch (iomap.type) {
>  	case IOMAP_MAPPED:
> diff --git a/fs/ext2/file.c b/fs/ext2/file.c
> index b0f2415..8422d5f 100644
> --- a/fs/ext2/file.c
> +++ b/fs/ext2/file.c
> @@ -92,16 +92,19 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
>  	struct inode *inode = file_inode(vma->vm_file);
>  	struct ext2_inode_info *ei = EXT2_I(inode);
>  	int ret;
> +	gfp_t old_gfp = vmf->gfp_mask;
>  
>  	if (vmf->flags & FAULT_FLAG_WRITE) {
>  		sb_start_pagefault(inode->i_sb);
>  		file_update_time(vma->vm_file);
>  	}
> +	vmf->gfp_mask &= ~__GFP_FS;
>  	down_read(&ei->dax_sem);
>  
>  	ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops);
>  
>  	up_read(&ei->dax_sem);
> +	vmf->gfp_mask = old_gfp;
>  	if (vmf->flags & FAULT_FLAG_WRITE)
>  		sb_end_pagefault(inode->i_sb);
>  	return ret;
> @@ -114,6 +117,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
>  	struct ext2_inode_info *ei = EXT2_I(inode);
>  	loff_t size;
>  	int ret;
> +	gfp_t old_gfp = vmf->gfp_mask;
>  
>  	sb_start_pagefault(inode->i_sb);
>  	file_update_time(vma->vm_file);
> @@ -123,8 +127,11 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
>  	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
>  	if (vmf->pgoff >= size)
>  		ret = VM_FAULT_SIGBUS;
> -	else
> +	else {
> +		vmf->gfp_mask &= ~__GFP_FS;
>  		ret = dax_pfn_mkwrite(vma, vmf);
> +		vmf->gfp_mask = old_gfp;
> +	}
>  
>  	up_read(&ei->dax_sem);
>  	sb_end_pagefault(inode->i_sb);
> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index d663d3d..a3f2bf0 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -261,14 +261,17 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
>  	struct inode *inode = file_inode(vma->vm_file);
>  	struct super_block *sb = inode->i_sb;
>  	bool write = vmf->flags & FAULT_FLAG_WRITE;
> +	gfp_t old_gfp = vmf->gfp_mask;
>  
>  	if (write) {
>  		sb_start_pagefault(sb);
>  		file_update_time(vma->vm_file);
>  	}
> +	vmf->gfp_mask &= ~__GFP_FS;
>  	down_read(&EXT4_I(inode)->i_mmap_sem);
>  	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
>  	up_read(&EXT4_I(inode)->i_mmap_sem);
> +	vmf->gfp_mask = old_gfp;
>  	if (write)
>  		sb_end_pagefault(sb);
>  
> @@ -320,8 +323,13 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
>  	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
>  	if (vmf->pgoff >= size)
>  		ret = VM_FAULT_SIGBUS;
> -	else
> +	else {
> +		gfp_t old_gfp = vmf->gfp_mask;
> +
> +		vmf->gfp_mask &= ~__GFP_FS;
>  		ret = dax_pfn_mkwrite(vma, vmf);
> +		vmf->gfp_mask = old_gfp;
> +	}
>  	up_read(&EXT4_I(inode)->i_mmap_sem);
>  	sb_end_pagefault(sb);
>  
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index d818c16..52202b4 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -1474,7 +1474,11 @@ xfs_filemap_page_mkwrite(
>  	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
>  
>  	if (IS_DAX(inode)) {
> +		gfp_t old_gfp = vmf->gfp_mask;
> +
> +		vmf->gfp_mask &= ~__GFP_FS;
>  		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
> +		vmf->gfp_mask = old_gfp;
>  	} else {
>  		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
>  		ret = block_page_mkwrite_return(ret);
> @@ -1502,13 +1506,16 @@ xfs_filemap_fault(
>  
>  	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
>  	if (IS_DAX(inode)) {
> +		gfp_t old_gfp = vmf->gfp_mask;
>  		/*
>  		 * we do not want to trigger unwritten extent conversion on read
>  		 * faults - that is unnecessary overhead and would also require
>  		 * changes to xfs_get_blocks_direct() to map unwritten extent
>  		 * ioend for conversion on read-only mappings.
>  		 */
> +		vmf->gfp_mask &= ~__GFP_FS;
>  		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
> +		vmf->gfp_mask = old_gfp;
>  	} else
>  		ret = filemap_fault(vma, vmf);
>  	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
> @@ -1581,8 +1588,13 @@ xfs_filemap_pfn_mkwrite(
>  	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
>  	if (vmf->pgoff >= size)
>  		ret = VM_FAULT_SIGBUS;
> -	else if (IS_DAX(inode))
> +	else if (IS_DAX(inode)) {
> +		gfp_t old_gfp = vmf->gfp_mask;
> +
> +		vmf->gfp_mask &= ~__GFP_FS;
>  		ret = dax_pfn_mkwrite(vma, vmf);
> +		vmf->gfp_mask = old_gfp;
> +	}
>  	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
>  	sb_end_pagefault(inode->i_sb);
>  	return ret;
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>