From f4e420dc423148fba637af1ab618fa8896dfb2d6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:56 +0200 Subject: clean up write_begin usage for directories in pagecache For filesystem that implement directories in pagecache we call block_write_begin with an already allocated page for this code, while the normal regular file write path uses the default block_write_begin behaviour. Get rid of the __foofs_write_begin helper and opencode the normal write_begin call in foofs_write_begin, while adding a new foofs_prepare_chunk helper for the directory code. The added benefit is that foofs_prepare_chunk has a much saner calling convention. Note that the interruptible flag passed into block_write_begin is always ignored if we already pass in a page (see next patch for details), and we never were doing truncations of exessive blocks for this case either so we can switch directly to block_write_begin_newtrunc. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/minix/dir.c | 21 +++++++-------------- fs/minix/inode.c | 11 +++++------ fs/minix/minix.h | 4 +--- 3 files changed, 13 insertions(+), 23 deletions(-) (limited to 'fs/minix') diff --git a/fs/minix/dir.c b/fs/minix/dir.c index 1dbf921..085a926 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -271,8 +271,7 @@ int minix_add_link(struct dentry *dentry, struct inode *inode) got_it: pos = page_offset(page) + p - (char *)page_address(page); - err = __minix_write_begin(NULL, page->mapping, pos, sbi->s_dirsize, - AOP_FLAG_UNINTERRUPTIBLE, &page, NULL); + err = minix_prepare_chunk(page, pos, sbi->s_dirsize); if (err) goto out_unlock; memcpy (namx, name, namelen); @@ -297,8 +296,7 @@ out_unlock: int minix_delete_entry(struct minix_dir_entry *de, struct page *page) { - struct address_space *mapping = page->mapping; - struct inode *inode = (struct inode*)mapping->host; + struct inode *inode = page->mapping->host; char *kaddr = page_address(page); loff_t pos = page_offset(page) + (char*)de - kaddr; struct minix_sb_info *sbi = minix_sb(inode->i_sb); @@ -306,8 +304,7 @@ int minix_delete_entry(struct minix_dir_entry *de, struct page *page) int err; lock_page(page); - err = __minix_write_begin(NULL, mapping, pos, len, - AOP_FLAG_UNINTERRUPTIBLE, &page, NULL); + err = minix_prepare_chunk(page, pos, len); if (err == 0) { if (sbi->s_version == MINIX_V3) ((minix3_dirent *) de)->inode = 0; @@ -325,16 +322,14 @@ int minix_delete_entry(struct minix_dir_entry *de, struct page *page) int minix_make_empty(struct inode *inode, struct inode *dir) { - struct address_space *mapping = inode->i_mapping; - struct page *page = grab_cache_page(mapping, 0); + struct page *page = grab_cache_page(inode->i_mapping, 0); struct minix_sb_info *sbi = minix_sb(inode->i_sb); char *kaddr; int err; if (!page) return -ENOMEM; - err = __minix_write_begin(NULL, mapping, 0, 2 * sbi->s_dirsize, - AOP_FLAG_UNINTERRUPTIBLE, &page, NULL); + err = minix_prepare_chunk(page, 0, 2 * sbi->s_dirsize); if (err) { unlock_page(page); goto fail; @@ -425,8 +420,7 @@ not_empty: void minix_set_link(struct minix_dir_entry *de, struct page *page, struct inode *inode) { - struct address_space *mapping = page->mapping; - struct inode *dir = mapping->host; + struct inode *dir = page->mapping->host; struct minix_sb_info *sbi = minix_sb(dir->i_sb); loff_t pos = page_offset(page) + (char *)de-(char*)page_address(page); @@ -434,8 +428,7 @@ void minix_set_link(struct minix_dir_entry *de, struct page *page, lock_page(page); - err = __minix_write_begin(NULL, mapping, pos, sbi->s_dirsize, - AOP_FLAG_UNINTERRUPTIBLE, &page, NULL); + err = minix_prepare_chunk(page, pos, sbi->s_dirsize); if (err == 0) { if (sbi->s_version == MINIX_V3) ((minix3_dirent *) de)->inode = inode->i_ino; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 756f8c9..f4abe45 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -357,12 +357,10 @@ static int minix_readpage(struct file *file, struct page *page) return block_read_full_page(page,minix_get_block); } -int __minix_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) +int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len) { - return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - minix_get_block); + return block_write_begin_newtrunc(NULL, page->mapping, pos, len, 0, + &page, NULL, minix_get_block); } static int minix_write_begin(struct file *file, struct address_space *mapping, @@ -370,7 +368,8 @@ static int minix_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { *pagep = NULL; - return __minix_write_begin(file, mapping, pos, len, flags, pagep, fsdata); + return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + minix_get_block); } static sector_t minix_bmap(struct address_space *mapping, sector_t block) diff --git a/fs/minix/minix.h b/fs/minix/minix.h index 111f34e..407b1c8 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -53,9 +53,7 @@ extern int minix_new_block(struct inode * inode); extern void minix_free_block(struct inode *inode, unsigned long block); extern unsigned long minix_count_free_blocks(struct minix_sb_info *sbi); extern int minix_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int __minix_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); +extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len); extern void V1_minix_truncate(struct inode *); extern void V2_minix_truncate(struct inode *); -- cgit v1.1 From 6e1db88d536adcbbfe562b2d4b7d6425784fff12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:57 +0200 Subject: introduce __block_write_begin Split up the block_write_begin implementation - __block_write_begin is a new trivial wrapper for block_prepare_write that always takes an already allocated page and can be either called from block_write_begin or filesystem code that already has a page allocated. Remove the handling of already allocated pages from block_write_begin after switching all callers that do it to __block_write_begin. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/minix/inode.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs/minix') diff --git a/fs/minix/inode.c b/fs/minix/inode.c index f4abe45..6b29e73 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -359,8 +359,7 @@ static int minix_readpage(struct file *file, struct page *page) int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len) { - return block_write_begin_newtrunc(NULL, page->mapping, pos, len, 0, - &page, NULL, minix_get_block); + return __block_write_begin(page, pos, len, minix_get_block); } static int minix_write_begin(struct file *file, struct address_space *mapping, -- cgit v1.1 From 155130a4f7848b1aac439cab6bda1a175507c71c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:58 +0200 Subject: get rid of block_write_begin_newtrunc Move the call to vmtruncate to get rid of accessive blocks to the callers in preparation of the new truncate sequence and rename the non-truncating version to block_write_begin. While we're at it also remove several unused arguments to block_write_begin. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/minix/inode.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'fs/minix') diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 6b29e73..125062f 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -366,9 +366,17 @@ static int minix_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - *pagep = NULL; - return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + int ret; + + ret = block_write_begin(mapping, pos, len, flags, pagep, minix_get_block); + if (unlikely(ret)) { + loff_t isize = mapping->host->i_size; + if (pos + len > isize) + vmtruncate(mapping->host, isize); + } + + return ret; } static sector_t minix_bmap(struct address_space *mapping, sector_t block) -- cgit v1.1 From d39aae9ec447dda84d9a2850743a78a535a71c90 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:59 +0200 Subject: add missing setattr methods For the new truncate sequence every filesystem that wants to truncate on-disk state needs a seattr method. Convert the remaining filesystems that implement the truncate inode operation to have its own setattr method. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/minix/file.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'fs/minix') diff --git a/fs/minix/file.c b/fs/minix/file.c index d5320ff..7a45dd1 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -23,7 +23,19 @@ const struct file_operations minix_file_operations = { .splice_read = generic_file_splice_read, }; +static int minix_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = dentry->d_inode; + int error; + + error = inode_change_ok(inode, attr); + if (error) + return error; + return inode_setattr(inode, attr); +} + const struct inode_operations minix_file_inode_operations = { .truncate = minix_truncate, + .setattr = minix_setattr, .getattr = minix_getattr, }; -- cgit v1.1 From 1025774ce411f2bd4b059ad7b53f0003569b74fa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:30:02 +0200 Subject: remove inode_setattr Replace inode_setattr with opencoded variants of it in all callers. This moves the remaining call to vmtruncate into the filesystem methods where it can be replaced with the proper truncate sequence. In a few cases it was obvious that we would never end up calling vmtruncate so it was left out in the opencoded variant: spufs: explicitly checks for ATTR_SIZE earlier btrfs,hugetlbfs,logfs,dlmfs: explicitly clears ATTR_SIZE earlier ufs: contains an opencoded simple_seattr + truncate that sets the filesize just above In addition to that ncpfs called inode_setattr with handcrafted iattrs, which allowed to trim down the opencoded variant. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/minix/file.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'fs/minix') diff --git a/fs/minix/file.c b/fs/minix/file.c index 7a45dd1..4493ce6 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -31,7 +31,17 @@ static int minix_setattr(struct dentry *dentry, struct iattr *attr) error = inode_change_ok(inode, attr); if (error) return error; - return inode_setattr(inode, attr); + + if ((attr->ia_valid & ATTR_SIZE) && + attr->ia_size != i_size_read(inode)) { + error = vmtruncate(inode, attr->ia_size); + if (error) + return error; + } + + setattr_copy(inode, attr); + mark_inode_dirty(inode); + return 0; } const struct inode_operations minix_file_inode_operations = { -- cgit v1.1 From 5ccb4a78d8c0e27985afec32cc4894d48e7b876e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 4 Jun 2010 22:27:38 -0400 Subject: switch minix to ->evict_inode(), fix write_inode/delete_inode race We need to wait for completion of possible writeback in progress before we clear on-disk inode during deletion. Signed-off-by: Al Viro --- fs/minix/bitmap.c | 6 ++---- fs/minix/inode.c | 15 ++++++++++----- 2 files changed, 12 insertions(+), 9 deletions(-) (limited to 'fs/minix') diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c index 482779f..3f32bcb 100644 --- a/fs/minix/bitmap.c +++ b/fs/minix/bitmap.c @@ -200,13 +200,13 @@ void minix_free_inode(struct inode * inode) ino = inode->i_ino; if (ino < 1 || ino > sbi->s_ninodes) { printk("minix_free_inode: inode 0 or nonexistent inode\n"); - goto out; + return; } bit = ino & ((1<>= k; if (ino >= sbi->s_imap_blocks) { printk("minix_free_inode: nonexistent imap in superblock\n"); - goto out; + return; } minix_clear_inode(inode); /* clear on-disk copy */ @@ -217,8 +217,6 @@ void minix_free_inode(struct inode * inode) printk("minix_free_inode: bit %lu already cleared\n", bit); spin_unlock(&bitmap_lock); mark_buffer_dirty(bh); - out: - clear_inode(inode); /* clear in-memory copy */ } struct inode *minix_new_inode(const struct inode *dir, int mode, int *error) diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 125062f..e39d6bf 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -24,12 +24,17 @@ static int minix_write_inode(struct inode *inode, static int minix_statfs(struct dentry *dentry, struct kstatfs *buf); static int minix_remount (struct super_block * sb, int * flags, char * data); -static void minix_delete_inode(struct inode *inode) +static void minix_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - inode->i_size = 0; - minix_truncate(inode); - minix_free_inode(inode); + if (!inode->i_nlink) { + inode->i_size = 0; + minix_truncate(inode); + } + invalidate_inode_buffers(inode); + end_writeback(inode); + if (!inode->i_nlink) + minix_free_inode(inode); } static void minix_put_super(struct super_block *sb) @@ -96,7 +101,7 @@ static const struct super_operations minix_sops = { .alloc_inode = minix_alloc_inode, .destroy_inode = minix_destroy_inode, .write_inode = minix_write_inode, - .delete_inode = minix_delete_inode, + .evict_inode = minix_evict_inode, .put_super = minix_put_super, .statfs = minix_statfs, .remount_fs = minix_remount, -- cgit v1.1