[PATCH v2 2/4] mm: Add file_operations.get_mapping_order()

[Peter Xu <peterx@redhat.com>]

Add one new file operation, get_mapping_order().  It can be used by file
backends to report mapping order hints.

By default, Linux assumed we will map in PAGE_SIZE chunks.  With this hint,
the driver can report the possibility of mapping chunks that are larger
than PAGE_SIZE.  Then, the VA allocator will try to use that as alignment
when allocating the VA ranges.

This is useful because when chunks to be mapped are larger than PAGE_SIZE,
VA alignment matters and it needs to be aligned with the size of the chunk
to be mapped.

Said that, no matter what is the alignment used for the VA allocation, the
driver can still decide which size to map the chunks.  It is also not an
issue if it keeps mapping in PAGE_SIZE.

get_mapping_order() is defined to take three parameters.  Besides the 1st
parameter which will be the file object pointer, the 2nd + 3rd parameters
being the pgoff + size of the mmap() request.  Its retval is defined as the
order, which must be non-negative to enable the alignment.  When zero is
returned, it should behave like when the hint is not provided, IOW,
alignment will still be PAGE_SIZE.

When the order is too big, ignore the hint.  Normally drivers are trusted,
so it's more of an extra layer of safety measure.

Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 Documentation/filesystems/vfs.rst |  4 +++
 include/linux/fs.h                |  1 +
 mm/mmap.c                         | 59 +++++++++++++++++++++++++++----
 3 files changed, 57 insertions(+), 7 deletions(-)

diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 4f13b01e42eb5..b707ddbebbf52 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -1069,6 +1069,7 @@ This describes how the VFS can manipulate an open file.  As of kernel
 		int (*fasync) (int, struct file *, int);
 		int (*lock) (struct file *, int, struct file_lock *);
 		unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+		int (*get_mapping_order)(struct file *, unsigned long, size_t);
 		int (*check_flags)(int);
 		int (*flock) (struct file *, int, struct file_lock *);
 		ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
@@ -1165,6 +1166,9 @@ otherwise noted.
 ``get_unmapped_area``
 	called by the mmap(2) system call
 
+``get_mapping_order``
+	called by the mmap(2) system call to get mapping order hint
+
 ``check_flags``
 	called by the fcntl(2) system call for F_SETFL command
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dd3b57cfadeeb..5ba373576bfe5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2287,6 +2287,7 @@ struct file_operations {
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+	int (*get_mapping_order)(struct file *file, unsigned long pgoff, size_t len);
 	int (*check_flags)(int);
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
diff --git a/mm/mmap.c b/mm/mmap.c
index 8fa397a18252e..be3dd0623f00c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -808,6 +808,33 @@ unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *fi
 	return arch_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags);
 }
 
+static inline bool file_has_mmap_order_hint(struct file *file)
+{
+	return file && file->f_op && file->f_op->get_mapping_order;
+}
+
+static inline bool
+mmap_should_align(struct file *file, unsigned long addr, unsigned long len)
+{
+	/* When THP not enabled at all, skip */
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return false;
+
+	/* Never try any alignment if the mmap() address hint is provided */
+	if (addr)
+		return false;
+
+	/* Anonymous THP could use some better alignment when len aligned */
+	if (!file)
+		return IS_ALIGNED(len, PMD_SIZE);
+
+	/*
+	 * It's a file mapping, no address hint provided by caller, try any
+	 * alignment if the file backend would provide a hint
+	 */
+	return file_has_mmap_order_hint(file);
+}
+
 unsigned long
 __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
@@ -815,8 +842,9 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 	unsigned long (*get_area)(struct file *, unsigned long,
 				  unsigned long, unsigned long, unsigned long)
 				  = NULL;
-
 	unsigned long error = arch_mmap_check(addr, len, flags);
+	unsigned long align;
+
 	if (error)
 		return error;
 
@@ -841,13 +869,30 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 
 	if (get_area) {
 		addr = get_area(file, addr, len, pgoff, flags);
-	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file
-		   && !addr /* no hint */
-		   && IS_ALIGNED(len, PMD_SIZE)) {
-		/* Ensures that larger anonymous mappings are THP aligned. */
+	} else if (mmap_should_align(file, addr, len)) {
+		if (file_has_mmap_order_hint(file)) {
+			int order;
+			/*
+			 * Allow driver to opt-in on the order hint.
+			 *
+			 * Sanity check on the order returned. Treating
+			 * either negative or too big order to be invalid,
+			 * where alignment will be skipped.
+			 */
+			order = file->f_op->get_mapping_order(file, pgoff, len);
+			if (order < 0)
+				order = 0;
+			if (check_shl_overflow(PAGE_SIZE, order, &align))
+				/* No alignment applied */
+				align = PAGE_SIZE;
+		} else {
+			/* Default alignment for anonymous THPs */
+			align = PMD_SIZE;
+		}
+
 		addr = thp_get_unmapped_area_vmflags(file, addr, len,
-						     pgoff, flags, PMD_SIZE,
-						     vm_flags);
+						     pgoff, flags,
+						     align, vm_flags);
 	} else {
 		addr = mm_get_unmapped_area_vmflags(current->mm, file, addr, len,
 						    pgoff, flags, vm_flags);
-- 
2.50.1