[PATCH v5 1/2] tmpfs: Add per-superblock i_ino support

[Chris Down]

get_next_ino has a number of problems:

- It uses and returns a uint, which is susceptible to become overflowed
  if a lot of volatile inodes that use get_next_ino are created.
- It's global, with no specificity per-sb or even per-filesystem. This
  means it's not that difficult to cause inode number wraparounds on a
  single device, which can result in having multiple distinct inodes
  with the same inode number.

This patch adds a per-superblock counter that mitigates the second case.
This design also allows us to later have a specific i_ino size
per-device, for example, allowing users to choose whether to use 32- or
64-bit inodes for each tmpfs mount. This is implemented in the next
commit.

Signed-off-by: Chris Down <chris@xxxxxxxxxxxxxx>
Reviewed-by: Amir Goldstein <amir73il@xxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Jeff Layton <jlayton@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: linux-fsdevel@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: kernel-team@xxxxxx
---
 include/linux/shmem_fs.h |  1 +
 mm/shmem.c               | 30 +++++++++++++++++++++++++++++-
 2 files changed, 30 insertions(+), 1 deletion(-)

v5: Nothing in code, just resending with correct linux-mm domain.

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index de8e4b71e3ba..7fac91f490dc 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -35,6 +35,7 @@ struct shmem_sb_info {
 	unsigned char huge;	    /* Whether to try for hugepages */
 	kuid_t uid;		    /* Mount uid for root directory */
 	kgid_t gid;		    /* Mount gid for root directory */
+	ino_t next_ino;		    /* The next per-sb inode number to use */
 	struct mempolicy *mpol;     /* default memory policy for mappings */
 	spinlock_t shrinklist_lock;   /* Protects shrinklist */
 	struct list_head shrinklist;  /* List of shinkable inodes */
diff --git a/mm/shmem.c b/mm/shmem.c
index 8793e8cc1a48..9e97ba972225 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2236,6 +2236,12 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+/*
+ * shmem_get_inode - reserve, allocate, and initialise a new inode
+ *
+ * If this tmpfs is from kern_mount we use get_next_ino, which is global, since
+ * inum churn there is low and this avoids taking locks.
+ */
 static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir,
 				     umode_t mode, dev_t dev, unsigned long flags)
 {
@@ -2248,7 +2254,28 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 
 	inode = new_inode(sb);
 	if (inode) {
-		inode->i_ino = get_next_ino();
+		if (sb->s_flags & SB_KERNMOUNT) {
+			/*
+			 * __shmem_file_setup, one of our callers, is lock-free:
+			 * it doesn't hold stat_lock in shmem_reserve_inode
+			 * since max_inodes is always 0, and is called from
+			 * potentially unknown contexts. As such, use the global
+			 * allocator which doesn't require the per-sb stat_lock.
+			 */
+			inode->i_ino = get_next_ino();
+		} else {
+			spin_lock(&sbinfo->stat_lock);
+			if (unlikely(sbinfo->next_ino > UINT_MAX)) {
+				/*
+				 * Emulate get_next_ino uint wraparound for
+				 * compatibility
+				 */
+				sbinfo->next_ino = 1;
+			}
+			inode->i_ino = sbinfo->next_ino++;
+			spin_unlock(&sbinfo->stat_lock);
+		}
+
 		inode_init_owner(inode, dir, mode);
 		inode->i_blocks = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
@@ -3662,6 +3689,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 #else
 	sb->s_flags |= SB_NOUSER;
 #endif
+	sbinfo->next_ino = 1;
 	sbinfo->max_blocks = ctx->blocks;
 	sbinfo->free_inodes = sbinfo->max_inodes = ctx->inodes;
 	sbinfo->uid = ctx->uid;
-- 
2.24.1