logfs: Propagate page parameter to __logfs_write_inode

During GC LogFS has to rewrite each valid block to a separate segment.
Rewrite operation reads data from an old segment and writes it to a
newly allocated segment. Since every write operation changes data
block pointers maintained in inode, inode should also be rewritten.

In GC path to avoid AB-BA deadlock LogFS marks a page with
PG_pre_locked in addition to locking the page (PG_locked). The page
lock is ignored iff the page is pre-locked.

LogFS uses a special file called segment file. The segment file
maintains an 8 bytes entry for every segment. It keeps track of erase
count, level etc. for every segment.

Bad things happen with a segment belonging to the segment file is GCed

 ------------[ cut here ]------------
kernel BUG at /home/prasad/logfs/readwrite.c:297!
invalid opcode: 0000 [#1] SMP
Modules linked in: logfs joydev usbhid hid psmouse e1000 i2c_piix4
		serio_raw [last unloaded: logfs]
Pid: 20161, comm: mount Not tainted 3.1.0-rc3+ #3 innotek GmbH
		VirtualBox
EIP: 0060:[<f809132a>] EFLAGS: 00010292 CPU: 0
EIP is at logfs_lock_write_page+0x6a/0x70 [logfs]
EAX: 00000027 EBX: f73f5b20 ECX: c16007c8 EDX: 00000094
ESI: 00000000 EDI: e59be6e4 EBP: c7337b28 ESP: c7337b18
DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
Process mount (pid: 20161, ti=c7336000 task=eb323f70 task.ti=c7336000)
Stack:
f8099a3d c7337b24 f73f5b20 00001002 c7337b50 f8091f6d f8099a4d f80994e4
00000003 00000000 c7337b68 00000000 c67e4400 00001000 c7337b80 f80935e5
00000000 00000000 00000000 00000000 e1fcf000 0000000f e59be618 c70bf900
Call Trace:
[<f8091f6d>] logfs_get_write_page.clone.16+0xdd/0x100 [logfs]
[<f80935e5>] logfs_mod_segment_entry+0x55/0x110 [logfs]
[<f809460d>] logfs_get_segment_entry+0x1d/0x20 [logfs]
[<f8091060>] ? logfs_cleanup_journal+0x50/0x50 [logfs]
[<f809521b>] ostore_get_erase_count+0x1b/0x40 [logfs]
[<f80965b8>] logfs_open_area+0xc8/0x150 [logfs]
[<c141a7ec>] ? kmemleak_alloc+0x2c/0x60
[<f809668e>] __logfs_segment_write.clone.16+0x4e/0x1b0 [logfs]
[<c10dd563>] ? mempool_kmalloc+0x13/0x20
[<c10dd563>] ? mempool_kmalloc+0x13/0x20
[<f809696f>] logfs_segment_write+0x17f/0x1d0 [logfs]
[<f8092e8c>] logfs_write_i0+0x11c/0x180 [logfs]
[<f8092f35>] logfs_write_direct+0x45/0x90 [logfs]
[<f80934cd>] __logfs_write_buf+0xbd/0xf0 [logfs]
[<c102900e>] ? kmap_atomic_prot+0x4e/0xe0
[<f809424b>] logfs_write_buf+0x3b/0x60 [logfs]
[<f80947a9>] __logfs_write_inode+0xa9/0x110 [logfs]
[<f8094cb0>] logfs_rewrite_block+0xc0/0x110 [logfs]
[<f8095300>] ? get_mapping_page+0x10/0x60 [logfs]
[<f8095aa0>] ? logfs_load_object_aliases+0x2e0/0x2f0 [logfs]
[<f808e57d>] logfs_gc_segment+0x2ad/0x310 [logfs]
[<f808e62a>] __logfs_gc_once+0x4a/0x80 [logfs]
[<f808ed43>] logfs_gc_pass+0x683/0x6a0 [logfs]
[<f8097a89>] logfs_mount+0x5a9/0x680 [logfs]
[<c1126b21>] mount_fs+0x21/0xd0
[<c10f6f6f>] ? __alloc_percpu+0xf/0x20
[<c113da41>] ? alloc_vfsmnt+0xb1/0x130
[<c113db4b>] vfs_kern_mount+0x4b/0xa0
[<c113e06e>] do_kern_mount+0x3e/0xe0
[<c113f60d>] do_mount+0x34d/0x670
[<c10f2749>] ? strndup_user+0x49/0x70
[<c113fcab>] sys_mount+0x6b/0xa0
[<c142d87c>] syscall_call+0x7/0xb
Code: f8 e8 8b 93 39 c9 8b 45 f8 3e 0f ba 28 00 19 d2 85 d2 74 ca eb d0 0f 0b 8d 45 fc 89 44 24 04 c7 04 24 3d 9a 09 f8 e8 09 92 39 c9 <0f> 0b 8d 74 26 00 55 89 e5 3e 8d 74 26 00 8b 10 80 e6 01 74 09
EIP: [<f809132a>] logfs_lock_write_page+0x6a/0x70 [logfs] SS:ESP 0068:c7337b18
---[ end trace 96e67d5b3aa3d6ca ]---

The patch passes locked page to __logfs_write_inode. It calls function
logfs_get_wblocks() to pre-lock the page. This ensures any further
attempts to lock the page are ignored (esp from get_erase_count).

Acked-by: Joern Engel <joern@logfs.org>
Signed-off-by: Prasad Joshi <prasadjoshi.linux@gmail.com>

diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index b7d7f67cee5acc60b254722c175bf35d5dcc021e..b6404898da83a89d8f1b12dcdfd42c87a0ee8665 100644 (file)
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -71,7 +71,7 @@ static int write_dir(struct inode *dir, struct logfs_disk_dentry *dd,
 
 static int write_inode(struct inode *inode)
 {
-       return __logfs_write_inode(inode, WF_LOCK);
+       return __logfs_write_inode(inode, NULL, WF_LOCK);
 }
 
 static s64 dir_seek_data(struct inode *inode, s64 pos)

diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index 388d7c5a7bedae58eaa8d5e2587a03ef16972299..7c42c132c1779c200184ce6c84e8f28241ea2d69 100644 (file)
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -287,7 +287,7 @@ static int logfs_write_inode(struct inode *inode, struct writeback_control *wbc)
        if (logfs_inode(inode)->li_flags & LOGFS_IF_STILLBORN)
                return 0;
 
-       ret = __logfs_write_inode(inode, flags);
+       ret = __logfs_write_inode(inode, NULL, flags);
        LOGFS_BUG_ON(ret, inode->i_sb);
        return ret;
 }

diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index bb4340850c1b9a3d6b3134702e997856b79ed4da..0dec29887a8a89b12cbef270af181892b4ea2cd0 100644 (file)
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -528,7 +528,7 @@ void logfs_destroy_inode_cache(void);
 void logfs_set_blocks(struct inode *inode, u64 no);
 /* these logically belong into inode.c but actually reside in readwrite.c */
 int logfs_read_inode(struct inode *inode);
-int __logfs_write_inode(struct inode *inode, long flags);
+int __logfs_write_inode(struct inode *inode, struct page *, long flags);
 void logfs_evict_inode(struct inode *inode);
 
 /* journal.c */

diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 7b10e8aecced2b1788b84c7090de55b8518f2cb5..88284c67ba9787ab23b58c2f55fe0f2216475129 100644 (file)
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -422,7 +422,7 @@ static void inode_write_block(struct logfs_block *block)
        if (inode->i_ino == LOGFS_INO_MASTER)
                logfs_write_anchor(inode->i_sb);
        else {
-               ret = __logfs_write_inode(inode, 0);
+               ret = __logfs_write_inode(inode, NULL, 0);
                /* see indirect_write_block comment */
                BUG_ON(ret);
        }
@@ -1629,7 +1629,7 @@ int logfs_rewrite_block(struct inode *inode, u64 bix, u64 ofs,
                        if (inode->i_ino == LOGFS_INO_MASTER)
                                logfs_write_anchor(inode->i_sb);
                        else {
-                               err = __logfs_write_inode(inode, flags);
+                               err = __logfs_write_inode(inode, page, flags);
                        }
                }
        }
@@ -1879,7 +1879,7 @@ int logfs_truncate(struct inode *inode, u64 target)
                logfs_get_wblocks(sb, NULL, 1);
                err = __logfs_truncate(inode, size);
                if (!err)
-                       err = __logfs_write_inode(inode, 0);
+                       err = __logfs_write_inode(inode, NULL, 0);
                logfs_put_wblocks(sb, NULL, 1);
        }
 
@@ -2119,14 +2119,14 @@ void logfs_set_segment_unreserved(struct super_block *sb, u32 segno, u32 ec)
                        ec_level);
 }
 
-int __logfs_write_inode(struct inode *inode, long flags)
+int __logfs_write_inode(struct inode *inode, struct page *page, long flags)
 {
        struct super_block *sb = inode->i_sb;
        int ret;
 
-       logfs_get_wblocks(sb, NULL, flags & WF_LOCK);
+       logfs_get_wblocks(sb, page, flags & WF_LOCK);
        ret = do_write_inode(inode);
-       logfs_put_wblocks(sb, NULL, flags & WF_LOCK);
+       logfs_put_wblocks(sb, page, flags & WF_LOCK);
        return ret;
 }