aboutsummaryrefslogtreecommitdiff
path: root/include/linux/fs.h
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2021-01-28 19:19:45 +0100
committerJan Kara <jack@suse.cz>2021-07-13 13:14:27 +0200
commit730633f0b7f951726e87f912a6323641f674ae34 (patch)
tree1c4a6eb5ddbc0c28e6d37a1418ec259cb6daef27 /include/linux/fs.h
parentc625b4cc57d078b03fd8aa4d86c99d584a1782be (diff)
mm: Protect operations adding pages to page cache with invalidate_lock
Currently, serializing operations such as page fault, read, or readahead against hole punching is rather difficult. The basic race scheme is like: fallocate(FALLOC_FL_PUNCH_HOLE) read / fault / .. truncate_inode_pages_range() <create pages in page cache here> <update fs block mapping and free blocks> Now the problem is in this way read / page fault / readahead can instantiate pages in page cache with potentially stale data (if blocks get quickly reused). Avoiding this race is not simple - page locks do not work because we want to make sure there are *no* pages in given range. inode->i_rwsem does not work because page fault happens under mmap_sem which ranks below inode->i_rwsem. Also using it for reads makes the performance for mixed read-write workloads suffer. So create a new rw_semaphore in the address_space - invalidate_lock - that protects adding of pages to page cache for page faults / reads / readahead. Reviewed-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jan Kara <jack@suse.cz>
Diffstat (limited to 'include/linux/fs.h')
-rw-r--r--include/linux/fs.h33
1 files changed, 33 insertions, 0 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 640574294216..90a80de37ad4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -436,6 +436,10 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
* struct address_space - Contents of a cacheable, mappable object.
* @host: Owner, either the inode or the block_device.
* @i_pages: Cached pages.
+ * @invalidate_lock: Guards coherency between page cache contents and
+ * file offset->disk block mappings in the filesystem during invalidates.
+ * It is also used to block modification of page cache contents through
+ * memory mappings.
* @gfp_mask: Memory allocation flags to use for allocating pages.
* @i_mmap_writable: Number of VM_SHARED mappings.
* @nr_thps: Number of THPs in the pagecache (non-shmem only).
@@ -453,6 +457,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
struct address_space {
struct inode *host;
struct xarray i_pages;
+ struct rw_semaphore invalidate_lock;
gfp_t gfp_mask;
atomic_t i_mmap_writable;
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
@@ -814,6 +819,33 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla
down_read_nested(&inode->i_rwsem, subclass);
}
+static inline void filemap_invalidate_lock(struct address_space *mapping)
+{
+ down_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock(struct address_space *mapping)
+{
+ up_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
+{
+ down_read(&mapping->invalidate_lock);
+}
+
+static inline int filemap_invalidate_trylock_shared(
+ struct address_space *mapping)
+{
+ return down_read_trylock(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock_shared(
+ struct address_space *mapping)
+{
+ up_read(&mapping->invalidate_lock);
+}
+
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);
@@ -2487,6 +2519,7 @@ struct file_system_type {
struct lock_class_key i_lock_key;
struct lock_class_key i_mutex_key;
+ struct lock_class_key invalidate_lock_key;
struct lock_class_key i_mutex_dir_key;
};