shmem: get_unmapped_area align huge page

Provide a shmem_get_unmapped_area method in file_operations, called at
mmap time to decide the mapping address.  It could be conditional on
CONFIG_TRANSPARENT_HUGEPAGE, but save #ifdefs in other places by making
it unconditional.

shmem_get_unmapped_area() first calls the usual mm->get_unmapped_area
(which we treat as a black box, highly dependent on architecture and
config and executable layout).  Lots of conditions, and in most cases it
just goes with the address that chose; but when our huge stars are
rightly aligned, yet that did not provide a suitable address, go back to
ask for a larger arena, within which to align the mapping suitably.

There have to be some direct calls to shmem_get_unmapped_area(), not via
the file_operations: because of the way shmem_zero_setup() is called to
create a shmem object late in the mmap sequence, when MAP_SHARED is
requested with MAP_ANONYMOUS or /dev/zero.  Though this only matters
when /proc/sys/vm/shmem_huge has been set.

Link: http://lkml.kernel.org/r/1466021202-61880-29-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 112 insertions, 2 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index a41872c..86b18f3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -25,6 +25,7 @@
 #include <linux/personality.h>
 #include <linux/security.h>
 #include <linux/hugetlb.h>
+#include <linux/shmem_fs.h>
 #include <linux/profile.h>
 #include <linux/export.h>
 #include <linux/mount.h>
@@ -1897,8 +1898,19 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		return -ENOMEM;
 
 	get_area = current->mm->get_unmapped_area;
-	if (file && file->f_op->get_unmapped_area)
-		get_area = file->f_op->get_unmapped_area;
+	if (file) {
+		if (file->f_op->get_unmapped_area)
+			get_area = file->f_op->get_unmapped_area;
+	} else if (flags & MAP_SHARED) {
+		/*
+		 * mmap_region() will call shmem_zero_setup() to create a file,
+		 * so use shmem's get_unmapped_area in case it can be huge.
+		 * do_mmap_pgoff() will clear pgoff, so match alignment.
+		 */
+		pgoff = 0;
+		get_area = shmem_get_unmapped_area;
+	}
+
 	addr = get_area(file, addr, len, pgoff, flags);
 	if (IS_ERR_VALUE(addr))
 		return addr;
diff --git a/mm/shmem.c b/mm/shmem.c
index fd374f7..ab02b5b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1513,6 +1513,94 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return ret;
 }
 
+unsigned long shmem_get_unmapped_area(struct file *file,
+				      unsigned long uaddr, unsigned long len,
+				      unsigned long pgoff, unsigned long flags)
+{
+	unsigned long (*get_area)(struct file *,
+		unsigned long, unsigned long, unsigned long, unsigned long);
+	unsigned long addr;
+	unsigned long offset;
+	unsigned long inflated_len;
+	unsigned long inflated_addr;
+	unsigned long inflated_offset;
+
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	get_area = current->mm->get_unmapped_area;
+	addr = get_area(file, uaddr, len, pgoff, flags);
+
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return addr;
+	if (IS_ERR_VALUE(addr))
+		return addr;
+	if (addr & ~PAGE_MASK)
+		return addr;
+	if (addr > TASK_SIZE - len)
+		return addr;
+
+	if (shmem_huge == SHMEM_HUGE_DENY)
+		return addr;
+	if (len < HPAGE_PMD_SIZE)
+		return addr;
+	if (flags & MAP_FIXED)
+		return addr;
+	/*
+	 * Our priority is to support MAP_SHARED mapped hugely;
+	 * and support MAP_PRIVATE mapped hugely too, until it is COWed.
+	 * But if caller specified an address hint, respect that as before.
+	 */
+	if (uaddr)
+		return addr;
+
+	if (shmem_huge != SHMEM_HUGE_FORCE) {
+		struct super_block *sb;
+
+		if (file) {
+			VM_BUG_ON(file->f_op != &shmem_file_operations);
+			sb = file_inode(file)->i_sb;
+		} else {
+			/*
+			 * Called directly from mm/mmap.c, or drivers/char/mem.c
+			 * for "/dev/zero", to create a shared anonymous object.
+			 */
+			if (IS_ERR(shm_mnt))
+				return addr;
+			sb = shm_mnt->mnt_sb;
+		}
+		if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER)
+			return addr;
+	}
+
+	offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1);
+	if (offset && offset + len < 2 * HPAGE_PMD_SIZE)
+		return addr;
+	if ((addr & (HPAGE_PMD_SIZE-1)) == offset)
+		return addr;
+
+	inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE;
+	if (inflated_len > TASK_SIZE)
+		return addr;
+	if (inflated_len < len)
+		return addr;
+
+	inflated_addr = get_area(NULL, 0, inflated_len, 0, flags);
+	if (IS_ERR_VALUE(inflated_addr))
+		return addr;
+	if (inflated_addr & ~PAGE_MASK)
+		return addr;
+
+	inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1);
+	inflated_addr += offset - inflated_offset;
+	if (inflated_offset > offset)
+		inflated_addr += HPAGE_PMD_SIZE;
+
+	if (inflated_addr > TASK_SIZE - len)
+		return addr;
+	return inflated_addr;
+}
+
 #ifdef CONFIG_NUMA
 static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
 {
@@ -3261,6 +3349,7 @@ static const struct address_space_operations shmem_aops = {
 
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
+	.get_unmapped_area = shmem_get_unmapped_area,
 #ifdef CONFIG_TMPFS
 	.llseek		= shmem_file_llseek,
 	.read_iter	= shmem_file_read_iter,
@@ -3496,6 +3585,15 @@ void shmem_unlock_mapping(struct address_space *mapping)
 {
 }
 
+#ifdef CONFIG_MMU
+unsigned long shmem_get_unmapped_area(struct file *file,
+				      unsigned long addr, unsigned long len,
+				      unsigned long pgoff, unsigned long flags)
+{
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+#endif
+
 void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 {
 	truncate_inode_pages_range(inode->i_mapping, lstart, lend);