f2fs: Convert to using invalidate_lock

Use invalidate_lock instead of f2fs' private i_mmap_sem. The intended
purpose is exactly the same. By this conversion we fix a long standing
race between hole punching and read(2) / readahead(2) paths that can
lead to stale page cache contents.

CC: Jaegeuk Kim <jaegeuk@kernel.org>
CC: Chao Yu <yuchao0@huawei.com>
CC: linux-f2fs-devel@lists.sourceforge.net
Acked-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jan Kara <jack@suse.cz>

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d2cf48c5a2e4968b2321c1a2c9b302b76e012221..eb222b35edefa5eccc9b98afab567094012fd3bf 100644 (file)
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3187,12 +3187,12 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
        /* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
        if (to > i_size && !f2fs_verity_in_progress(inode)) {
                down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-               down_write(&F2FS_I(inode)->i_mmap_sem);
+               filemap_invalidate_lock(mapping);
 
                truncate_pagecache(inode, i_size);
                f2fs_truncate_blocks(inode, i_size, true);
 
-               up_write(&F2FS_I(inode)->i_mmap_sem);
+               filemap_invalidate_unlock(mapping);
                up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
        }
 }
@@ -3852,7 +3852,7 @@ static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk,
        int ret = 0;
 
        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(inode->i_mapping);
 
        set_inode_flag(inode, FI_ALIGNED_WRITE);
 
@@ -3894,7 +3894,7 @@ done:
        clear_inode_flag(inode, FI_DO_DEFRAG);
        clear_inode_flag(inode, FI_ALIGNED_WRITE);
 
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(inode->i_mapping);
        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
        return ret;

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ee8eb33e2c25ccb076a20269f7dabce513d496b9..906b2c4b50e78c0138c0de2d52c0036bf9ebd201 100644 (file)
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -754,7 +754,6 @@ struct f2fs_inode_info {
 
        /* avoid racing between foreground op and gc */
        struct rw_semaphore i_gc_rwsem[2];
-       struct rw_semaphore i_mmap_sem;
        struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
 
        int i_extra_isize;              /* size of extra space located in i_addr */

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6afd4562335fc0a3e6beb67d9ed6d041fffa19d9..1ff333755721efbaa123fe40806d9936ce822cff 100644 (file)
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -38,10 +38,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
        struct inode *inode = file_inode(vmf->vma->vm_file);
        vm_fault_t ret;
 
-       down_read(&F2FS_I(inode)->i_mmap_sem);
        ret = filemap_fault(vmf);
-       up_read(&F2FS_I(inode)->i_mmap_sem);
-
        if (!ret)
                f2fs_update_iostat(F2FS_I_SB(inode), APP_MAPPED_READ_IO,
                                                        F2FS_BLKSIZE);
@@ -101,7 +98,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
        f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
 
        file_update_time(vmf->vma->vm_file);
-       down_read(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock_shared(inode->i_mapping);
        lock_page(page);
        if (unlikely(page->mapping != inode->i_mapping ||
                        page_offset(page) > i_size_read(inode) ||
@@ -159,7 +156,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
        trace_f2fs_vm_page_mkwrite(page, DATA);
 out_sem:
-       up_read(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock_shared(inode->i_mapping);
 
        sb_end_pagefault(inode->i_sb);
 err:
@@ -940,7 +937,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
                }
 
                down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-               down_write(&F2FS_I(inode)->i_mmap_sem);
+               filemap_invalidate_lock(inode->i_mapping);
 
                truncate_setsize(inode, attr->ia_size);
 
@@ -950,7 +947,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
                 * do not trim all blocks after i_size if target size is
                 * larger than i_size.
                 */
-               up_write(&F2FS_I(inode)->i_mmap_sem);
+               filemap_invalidate_unlock(inode->i_mapping);
                up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
                if (err)
                        return err;
@@ -1095,7 +1092,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
                        blk_end = (loff_t)pg_end << PAGE_SHIFT;
 
                        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-                       down_write(&F2FS_I(inode)->i_mmap_sem);
+                       filemap_invalidate_lock(mapping);
 
                        truncate_inode_pages_range(mapping, blk_start,
                                        blk_end - 1);
@@ -1104,7 +1101,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
                        ret = f2fs_truncate_hole(inode, pg_start, pg_end);
                        f2fs_unlock_op(sbi);
 
-                       up_write(&F2FS_I(inode)->i_mmap_sem);
+                       filemap_invalidate_unlock(mapping);
                        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
                }
        }
@@ -1339,7 +1336,7 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
 
        /* avoid gc operation during block exchange */
        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(inode->i_mapping);
 
        f2fs_lock_op(sbi);
        f2fs_drop_extent_tree(inode);
@@ -1347,7 +1344,7 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
        ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
        f2fs_unlock_op(sbi);
 
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(inode->i_mapping);
        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
        return ret;
 }
@@ -1378,13 +1375,13 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
                return ret;
 
        /* write out all moved pages, if possible */
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(inode->i_mapping);
        filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
        truncate_pagecache(inode, offset);
 
        new_size = i_size_read(inode) - len;
        ret = f2fs_truncate_blocks(inode, new_size, true);
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(inode->i_mapping);
        if (!ret)
                f2fs_i_size_write(inode, new_size);
        return ret;
@@ -1484,7 +1481,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
                        pgoff_t end;
 
                        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-                       down_write(&F2FS_I(inode)->i_mmap_sem);
+                       filemap_invalidate_lock(mapping);
 
                        truncate_pagecache_range(inode,
                                (loff_t)index << PAGE_SHIFT,
@@ -1496,7 +1493,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
                        ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
                        if (ret) {
                                f2fs_unlock_op(sbi);
-                               up_write(&F2FS_I(inode)->i_mmap_sem);
+                               filemap_invalidate_unlock(mapping);
                                up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
                                goto out;
                        }
@@ -1508,7 +1505,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
                        f2fs_put_dnode(&dn);
 
                        f2fs_unlock_op(sbi);
-                       up_write(&F2FS_I(inode)->i_mmap_sem);
+                       filemap_invalidate_unlock(mapping);
                        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
                        f2fs_balance_fs(sbi, dn.node_changed);
@@ -1543,6 +1540,7 @@ out:
 static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 {
        struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+       struct address_space *mapping = inode->i_mapping;
        pgoff_t nr, pg_start, pg_end, delta, idx;
        loff_t new_size;
        int ret = 0;
@@ -1565,14 +1563,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
        f2fs_balance_fs(sbi, true);
 
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(mapping);
        ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(mapping);
        if (ret)
                return ret;
 
        /* write out all dirty pages from offset */
-       ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+       ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
        if (ret)
                return ret;
 
@@ -1583,7 +1581,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
        /* avoid gc operation during block exchange */
        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(mapping);
        truncate_pagecache(inode, offset);
 
        while (!ret && idx > pg_start) {
@@ -1599,14 +1597,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
                                        idx + delta, nr, false);
                f2fs_unlock_op(sbi);
        }
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(mapping);
        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
        /* write out all moved pages, if possible */
-       down_write(&F2FS_I(inode)->i_mmap_sem);
-       filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+       filemap_invalidate_lock(mapping);
+       filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
        truncate_pagecache(inode, offset);
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(mapping);
 
        if (!ret)
                f2fs_i_size_write(inode, new_size);
@@ -3440,7 +3438,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
                goto out;
 
        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(inode->i_mapping);
 
        last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 
@@ -3476,7 +3474,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
        }
 
        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(inode->i_mapping);
 out:
        inode_unlock(inode);
 
@@ -3593,7 +3591,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
        }
 
        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(inode->i_mapping);
 
        last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 
@@ -3629,7 +3627,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
        }
 
        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(inode->i_mapping);
 
        if (ret >= 0) {
                clear_inode_flag(inode, FI_COMPRESS_RELEASED);
@@ -3748,7 +3746,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
                goto err;
 
        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-       down_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_lock(mapping);
 
        ret = filemap_write_and_wait_range(mapping, range.start,
                        to_end ? LLONG_MAX : end_addr - 1);
@@ -3835,7 +3833,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
                ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
                                prev_block, len, range.flags);
 out:
-       up_write(&F2FS_I(inode)->i_mmap_sem);
+       filemap_invalidate_unlock(mapping);
        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 err:
        inode_unlock(inode);
@@ -4313,9 +4311,9 @@ write:
                /* if we couldn't write data, we should deallocate blocks. */
                if (preallocated && i_size_read(inode) < target_size) {
                        down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-                       down_write(&F2FS_I(inode)->i_mmap_sem);
+                       filemap_invalidate_lock(inode->i_mapping);
                        f2fs_truncate(inode);
-                       up_write(&F2FS_I(inode)->i_mmap_sem);
+                       filemap_invalidate_unlock(inode->i_mapping);
                        up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
                }
 

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8fecd3050ccd46aa7cf477545e91e939a7b4fbbf..ce2ab1b85c11dbef1d91d577ae527a25f44a0013 100644 (file)
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1289,7 +1289,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
        mutex_init(&fi->inmem_lock);
        init_rwsem(&fi->i_gc_rwsem[READ]);
        init_rwsem(&fi->i_gc_rwsem[WRITE]);
-       init_rwsem(&fi->i_mmap_sem);
        init_rwsem(&fi->i_xattr_sem);
 
        /* Will be used by directory only */