* Fix the kmalloc flags used from within ext3, when we have an active journal handle If we do a kmalloc with GFP_KERNEL on system running low on memory, with an active journal handle, we might end up in cleaning up the fs cache flushing dirty inodes for some other filesystem. This would cause hitting a J_ASSERT() in : handle_t *journal_start(journal_t *journal, int nblocks) { handle_t *handle = journal_current_handle(); int err; [...] if (handle) { J_ASSERT(handle->h_transaction->t_journal == journal); Here are the places where we do kmalloc or may end up doing kmalloc, with __GFP_FS (through GFP_KERNEL) from ext3, while holding a journal handle. 1) fs/ext3/xattr.c :: ext3_xattr_block_set() : 2 occurences 2) fs/ext3/resize.c :: reserve_backup_gdb() 3) fs/ext3/resize.c :: add_new_gdb() 4) fs/ext3/acl.c :: ext3_init_acl() : There are quite a few points where we may endup calling the kmalloc() from ext3_init_acl() which is called with a handle() from ext3_new_inode(): a) Called direclty within ext3_init_acl() as: clone = posix_acl_clone(acl, GFP_KERNEL); b) With the following code path: ext3_init_acl()-> ext3_get_acl()-> ext3_acl_from_disk() -> posix_acl_alloc(GFP_KERNEL) c) Also ext3_init_acl()-> ext3_get_acl()-> kmalloc() also might call kmalloc() directly. 5) fs/ext3/acl.c :: ext3_acl_to_disk() which is called from ext3_set_acl(). Among these 4.b & 4.c may be called from a with or without handle case. There was a similar issue reported sometime back, early this year. http://lkml.org/lkml/2006/1/31/54 Attached patch fixes all the above invocatins to make use of GFP_NOFS instead of GFP_KERNEL. Signed-off-by: Suzuki K P Index: linux-2.6.20-rc1/fs/ext3/xattr.c =================================================================== --- linux-2.6.20-rc1.orig/fs/ext3/xattr.c 2006-12-13 17:14:23.000000000 -0800 +++ linux-2.6.20-rc1/fs/ext3/xattr.c 2006-12-19 11:41:35.000000000 -0800 @@ -718,7 +718,7 @@ ce = NULL; } ea_bdebug(bs->bh, "cloning"); - s->base = kmalloc(bs->bh->b_size, GFP_KERNEL); + s->base = kmalloc(bs->bh->b_size, GFP_NOFS); error = -ENOMEM; if (s->base == NULL) goto cleanup; @@ -730,7 +730,7 @@ } } else { /* Allocate a buffer where we construct the new block. */ - s->base = kmalloc(sb->s_blocksize, GFP_KERNEL); + s->base = kmalloc(sb->s_blocksize, GFP_NOFS); /* assert(header == s->base) */ error = -ENOMEM; if (s->base == NULL) Index: linux-2.6.20-rc1/fs/ext3/resize.c =================================================================== --- linux-2.6.20-rc1.orig/fs/ext3/resize.c 2006-12-13 17:14:23.000000000 -0800 +++ linux-2.6.20-rc1/fs/ext3/resize.c 2006-12-19 11:42:39.000000000 -0800 @@ -440,7 +440,7 @@ goto exit_dindj; n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *), - GFP_KERNEL); + GFP_NOFS); if (!n_group_desc) { err = -ENOMEM; ext3_warning (sb, __FUNCTION__, @@ -524,7 +524,7 @@ int res, i; int err; - primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_KERNEL); + primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_NOFS); if (!primary) return -ENOMEM; Index: linux-2.6.20-rc1/fs/ext3/acl.c =================================================================== --- linux-2.6.20-rc1.orig/fs/ext3/acl.c 2006-12-13 17:14:23.000000000 -0800 +++ linux-2.6.20-rc1/fs/ext3/acl.c 2006-12-19 11:45:35.000000000 -0800 @@ -37,7 +37,7 @@ return ERR_PTR(-EINVAL); if (count == 0) return NULL; - acl = posix_acl_alloc(count, GFP_KERNEL); + acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); for (n=0; n < count; n++) { @@ -91,7 +91,7 @@ *size = ext3_acl_size(acl->a_count); ext_acl = kmalloc(sizeof(ext3_acl_header) + acl->a_count * - sizeof(ext3_acl_entry), GFP_KERNEL); + sizeof(ext3_acl_entry), GFP_NOFS); if (!ext_acl) return ERR_PTR(-ENOMEM); ext_acl->a_version = cpu_to_le32(EXT3_ACL_VERSION); @@ -187,7 +187,7 @@ } retval = ext3_xattr_get(inode, name_index, "", NULL, 0); if (retval > 0) { - value = kmalloc(retval, GFP_KERNEL); + value = kmalloc(retval, GFP_NOFS); if (!value) return ERR_PTR(-ENOMEM); retval = ext3_xattr_get(inode, name_index, "", value, retval); @@ -335,7 +335,7 @@ if (error) goto cleanup; } - clone = posix_acl_clone(acl, GFP_KERNEL); + clone = posix_acl_clone(acl, GFP_NOFS); error = -ENOMEM; if (!clone) goto cleanup;