From 79f5acf5d784492afe80723496624093079aed9c Mon Sep 17 00:00:00 2001 From: Adam Litke Date: Fri, 29 Sep 2006 01:58:43 -0700 Subject: [PATCH] mm: make filemap_nopage use NOPAGE_SIGBUS Don't open-code NOPAGE_SIGBUS. Signed-off-by: Adam Litke Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index afcdc72b5e9..3277f3b2352 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1471,7 +1471,7 @@ outside_data_content: * accessible.. */ if (area->vm_mm == current->mm) - return NULL; + return NOPAGE_SIGBUS; /* Fall through to the non-read-ahead case */ no_cached_page: /* @@ -1496,7 +1496,7 @@ no_cached_page: */ if (error == -ENOMEM) return NOPAGE_OOM; - return NULL; + return NOPAGE_SIGBUS; page_not_uptodate: if (!did_readaround) { @@ -1565,7 +1565,7 @@ page_not_uptodate: */ shrink_readahead_size_eio(file, ra); page_cache_release(page); - return NULL; + return NOPAGE_SIGBUS; } EXPORT_SYMBOL(filemap_nopage); -- cgit v1.2.3 From cf9a2ae8d49948f861b56e5333530e491a9da190 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:05:54 +0100 Subject: [PATCH] BLOCK: Move functions out of buffer code [try #6] Move some functions out of the buffering code that aren't strictly buffering specific. This is a precursor to being able to disable the block layer. (*) Moved some stuff out of fs/buffer.c: (*) The file sync and general sync stuff moved to fs/sync.c. (*) The superblock sync stuff moved to fs/super.c. (*) do_invalidatepage() moved to mm/truncate.c. (*) try_to_release_page() moved to mm/filemap.c. (*) Moved some related declarations between header files: (*) declarations for do_invalidatepage() and try_to_release_page() moved to linux/mm.h. (*) __set_page_dirty_buffers() moved to linux/buffer_head.h. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- fs/buffer.c | 174 -------------------------------------------- fs/super.c | 31 ++++++++ fs/sync.c | 113 ++++++++++++++++++++++++++++ include/linux/buffer_head.h | 3 +- include/linux/fs.h | 1 + include/linux/mm.h | 4 +- mm/filemap.c | 30 ++++++++ mm/page-writeback.c | 1 + mm/truncate.c | 24 ++++++ 9 files changed, 204 insertions(+), 177 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/buffer.c b/fs/buffer.c index 3b6d701073e..16cfbcd254f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -159,31 +159,6 @@ int sync_blockdev(struct block_device *bdev) } EXPORT_SYMBOL(sync_blockdev); -static void __fsync_super(struct super_block *sb) -{ - sync_inodes_sb(sb, 0); - DQUOT_SYNC(sb); - lock_super(sb); - if (sb->s_dirt && sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); - sync_blockdev(sb->s_bdev); - sync_inodes_sb(sb, 1); -} - -/* - * Write out and wait upon all dirty data associated with this - * superblock. Filesystem data as well as the underlying block - * device. Takes the superblock lock. - */ -int fsync_super(struct super_block *sb) -{ - __fsync_super(sb); - return sync_blockdev(sb->s_bdev); -} - /* * Write out and wait upon all dirty data associated with this * device. Filesystem data as well as the underlying block @@ -259,118 +234,6 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb) } EXPORT_SYMBOL(thaw_bdev); -/* - * sync everything. Start out by waking pdflush, because that writes back - * all queues in parallel. - */ -static void do_sync(unsigned long wait) -{ - wakeup_pdflush(0); - sync_inodes(0); /* All mappings, inodes and their blockdevs */ - DQUOT_SYNC(NULL); - sync_supers(); /* Write the superblocks */ - sync_filesystems(0); /* Start syncing the filesystems */ - sync_filesystems(wait); /* Waitingly sync the filesystems */ - sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */ - if (!wait) - printk("Emergency Sync complete\n"); - if (unlikely(laptop_mode)) - laptop_sync_completion(); -} - -asmlinkage long sys_sync(void) -{ - do_sync(1); - return 0; -} - -void emergency_sync(void) -{ - pdflush_operation(do_sync, 0); -} - -/* - * Generic function to fsync a file. - * - * filp may be NULL if called via the msync of a vma. - */ - -int file_fsync(struct file *filp, struct dentry *dentry, int datasync) -{ - struct inode * inode = dentry->d_inode; - struct super_block * sb; - int ret, err; - - /* sync the inode to buffers */ - ret = write_inode_now(inode, 0); - - /* sync the superblock to buffers */ - sb = inode->i_sb; - lock_super(sb); - if (sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - - /* .. finally sync the buffers to disk */ - err = sync_blockdev(sb->s_bdev); - if (!ret) - ret = err; - return ret; -} - -long do_fsync(struct file *file, int datasync) -{ - int ret; - int err; - struct address_space *mapping = file->f_mapping; - - if (!file->f_op || !file->f_op->fsync) { - /* Why? We can still call filemap_fdatawrite */ - ret = -EINVAL; - goto out; - } - - ret = filemap_fdatawrite(mapping); - - /* - * We need to protect against concurrent writers, which could cause - * livelocks in fsync_buffers_list(). - */ - mutex_lock(&mapping->host->i_mutex); - err = file->f_op->fsync(file, file->f_dentry, datasync); - if (!ret) - ret = err; - mutex_unlock(&mapping->host->i_mutex); - err = filemap_fdatawait(mapping); - if (!ret) - ret = err; -out: - return ret; -} - -static long __do_fsync(unsigned int fd, int datasync) -{ - struct file *file; - int ret = -EBADF; - - file = fget(fd); - if (file) { - ret = do_fsync(file, datasync); - fput(file); - } - return ret; -} - -asmlinkage long sys_fsync(unsigned int fd) -{ - return __do_fsync(fd, 0); -} - -asmlinkage long sys_fdatasync(unsigned int fd) -{ - return __do_fsync(fd, 1); -} - /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, @@ -1550,35 +1413,6 @@ static void discard_buffer(struct buffer_head * bh) unlock_buffer(bh); } -/** - * try_to_release_page() - release old fs-specific metadata on a page - * - * @page: the page which the kernel is trying to free - * @gfp_mask: memory allocation flags (and I/O mode) - * - * The address_space is to try to release any data against the page - * (presumably at page->private). If the release was successful, return `1'. - * Otherwise return zero. - * - * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). - * - * NOTE: @gfp_mask may go away, and this function may become non-blocking. - */ -int try_to_release_page(struct page *page, gfp_t gfp_mask) -{ - struct address_space * const mapping = page->mapping; - - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; - - if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(page, gfp_mask); - return try_to_free_buffers(page); -} -EXPORT_SYMBOL(try_to_release_page); - /** * block_invalidatepage - invalidate part of all of a buffer-backed page * @@ -1630,14 +1464,6 @@ out: } EXPORT_SYMBOL(block_invalidatepage); -void do_invalidatepage(struct page *page, unsigned long offset) -{ - void (*invalidatepage)(struct page *, unsigned long); - invalidatepage = page->mapping->a_ops->invalidatepage ? : - block_invalidatepage; - (*invalidatepage)(page, offset); -} - /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers diff --git a/fs/super.c b/fs/super.c index 6987824d0dc..15671cd048b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -220,6 +220,37 @@ static int grab_super(struct super_block *s) __releases(sb_lock) return 0; } +/* + * Write out and wait upon all dirty data associated with this + * superblock. Filesystem data as well as the underlying block + * device. Takes the superblock lock. Requires a second blkdev + * flush by the caller to complete the operation. + */ +void __fsync_super(struct super_block *sb) +{ + sync_inodes_sb(sb, 0); + DQUOT_SYNC(sb); + lock_super(sb); + if (sb->s_dirt && sb->s_op->write_super) + sb->s_op->write_super(sb); + unlock_super(sb); + if (sb->s_op->sync_fs) + sb->s_op->sync_fs(sb, 1); + sync_blockdev(sb->s_bdev); + sync_inodes_sb(sb, 1); +} + +/* + * Write out and wait upon all dirty data associated with this + * superblock. Filesystem data as well as the underlying block + * device. Takes the superblock lock. + */ +int fsync_super(struct super_block *sb) +{ + __fsync_super(sb); + return sync_blockdev(sb->s_bdev); +} + /** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill diff --git a/fs/sync.c b/fs/sync.c index 955aef04da2..1de747b5ddb 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -10,10 +10,123 @@ #include #include #include +#include +#include #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ SYNC_FILE_RANGE_WAIT_AFTER) +/* + * sync everything. Start out by waking pdflush, because that writes back + * all queues in parallel. + */ +static void do_sync(unsigned long wait) +{ + wakeup_pdflush(0); + sync_inodes(0); /* All mappings, inodes and their blockdevs */ + DQUOT_SYNC(NULL); + sync_supers(); /* Write the superblocks */ + sync_filesystems(0); /* Start syncing the filesystems */ + sync_filesystems(wait); /* Waitingly sync the filesystems */ + sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */ + if (!wait) + printk("Emergency Sync complete\n"); + if (unlikely(laptop_mode)) + laptop_sync_completion(); +} + +asmlinkage long sys_sync(void) +{ + do_sync(1); + return 0; +} + +void emergency_sync(void) +{ + pdflush_operation(do_sync, 0); +} + +/* + * Generic function to fsync a file. + * + * filp may be NULL if called via the msync of a vma. + */ +int file_fsync(struct file *filp, struct dentry *dentry, int datasync) +{ + struct inode * inode = dentry->d_inode; + struct super_block * sb; + int ret, err; + + /* sync the inode to buffers */ + ret = write_inode_now(inode, 0); + + /* sync the superblock to buffers */ + sb = inode->i_sb; + lock_super(sb); + if (sb->s_op->write_super) + sb->s_op->write_super(sb); + unlock_super(sb); + + /* .. finally sync the buffers to disk */ + err = sync_blockdev(sb->s_bdev); + if (!ret) + ret = err; + return ret; +} + +long do_fsync(struct file *file, int datasync) +{ + int ret; + int err; + struct address_space *mapping = file->f_mapping; + + if (!file->f_op || !file->f_op->fsync) { + /* Why? We can still call filemap_fdatawrite */ + ret = -EINVAL; + goto out; + } + + ret = filemap_fdatawrite(mapping); + + /* + * We need to protect against concurrent writers, which could cause + * livelocks in fsync_buffers_list(). + */ + mutex_lock(&mapping->host->i_mutex); + err = file->f_op->fsync(file, file->f_dentry, datasync); + if (!ret) + ret = err; + mutex_unlock(&mapping->host->i_mutex); + err = filemap_fdatawait(mapping); + if (!ret) + ret = err; +out: + return ret; +} + +static long __do_fsync(unsigned int fd, int datasync) +{ + struct file *file; + int ret = -EBADF; + + file = fget(fd); + if (file) { + ret = do_fsync(file, datasync); + fput(file); + } + return ret; +} + +asmlinkage long sys_fsync(unsigned int fd) +{ + return __do_fsync(fd, 0); +} + +asmlinkage long sys_fdatasync(unsigned int fd) +{ + return __do_fsync(fd, 1); +} + /* * sys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 737e407d0cd..64b508e35d2 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -190,9 +190,7 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -int try_to_release_page(struct page * page, gfp_t gfp_mask); void block_invalidatepage(struct page *page, unsigned long offset); -void do_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int block_read_full_page(struct page*, get_block_t*); @@ -302,4 +300,5 @@ static inline void lock_buffer(struct buffer_head *bh) __lock_buffer(bh); } +extern int __set_page_dirty_buffers(struct page *page); #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index d68c37af4df..1728142ec4b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1546,6 +1546,7 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); extern void sync_filesystems(int wait); +extern void __fsync_super(struct super_block *sb); extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b703b6d435..4edf1934e5c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -743,7 +743,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); -int __set_page_dirty_buffers(struct page *page); +extern int try_to_release_page(struct page * page, gfp_t gfp_mask); +extern void do_invalidatepage(struct page *page, unsigned long offset); + int __set_page_dirty_nobuffers(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); diff --git a/mm/filemap.c b/mm/filemap.c index 3277f3b2352..d6846de0888 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2491,3 +2491,33 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, } return retval; } + +/** + * try_to_release_page() - release old fs-specific metadata on a page + * + * @page: the page which the kernel is trying to free + * @gfp_mask: memory allocation flags (and I/O mode) + * + * The address_space is to try to release any data against the page + * (presumably at page->private). If the release was successful, return `1'. + * Otherwise return zero. + * + * The @gfp_mask argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). + * + * NOTE: @gfp_mask may go away, and this function may become non-blocking. + */ +int try_to_release_page(struct page *page, gfp_t gfp_mask) +{ + struct address_space * const mapping = page->mapping; + + BUG_ON(!PageLocked(page)); + if (PageWriteback(page)) + return 0; + + if (mapping && mapping->a_ops->releasepage) + return mapping->a_ops->releasepage(page, gfp_mask); + return try_to_free_buffers(page); +} + +EXPORT_SYMBOL(try_to_release_page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 488b7088557..9fdcc790395 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -30,6 +30,7 @@ #include #include #include +#include /* * The maximum number of pages to writeout in a single bdflush/kupdate diff --git a/mm/truncate.c b/mm/truncate.c index a654928323d..cd3e34b816d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -17,6 +17,30 @@ do_invalidatepage */ +/** + * do_invalidatepage - invalidate part of all of a page + * @page: the page which is affected + * @offset: the index of the truncation point + * + * do_invalidatepage() is called when all or part of the page has become + * invalidated by a truncate operation. + * + * do_invalidatepage() does not have to release all buffers, but it must + * ensure that no dirty buffer is left outside @offset and that no I/O + * is underway against any of the blocks which are outside the truncation + * point. Because the caller is about to free (and possibly reuse) those + * blocks on-disk. + */ +void do_invalidatepage(struct page *page, unsigned long offset) +{ + void (*invalidatepage)(struct page *, unsigned long); + invalidatepage = page->mapping->a_ops->invalidatepage; + if (!invalidatepage) + invalidatepage = block_invalidatepage; + if (invalidatepage) + (*invalidatepage)(page, offset); +} + static inline void truncate_partial_page(struct page *page, unsigned partial) { memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial); -- cgit v1.2.3 From 9361401eb7619c033e2394e4f9f6d410d6719ac7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 30 Sep 2006 20:45:40 +0200 Subject: [PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- block/Kconfig | 20 ++++++++++++++++++ block/Kconfig.iosched | 3 +++ block/Makefile | 2 +- drivers/block/Kconfig | 4 ++++ drivers/cdrom/Kconfig | 2 +- drivers/char/Kconfig | 1 + drivers/char/random.c | 4 ++++ drivers/ide/Kconfig | 4 ++++ drivers/md/Kconfig | 3 +++ drivers/message/i2o/Kconfig | 2 +- drivers/mmc/Kconfig | 2 +- drivers/mmc/Makefile | 3 ++- drivers/mtd/Kconfig | 12 +++++------ drivers/mtd/devices/Kconfig | 2 +- drivers/s390/block/Kconfig | 2 +- drivers/scsi/Kconfig | 2 ++ fs/Kconfig | 31 ++++++++++++++++++++------- fs/Makefile | 14 +++++++++---- fs/compat_ioctl.c | 18 ++++++++++++++++ fs/internal.h | 6 ++++++ fs/no-block.c | 22 +++++++++++++++++++ fs/partitions/Makefile | 2 +- fs/proc/proc_misc.c | 11 +++++++++- fs/quota.c | 44 ++++++++++++++++++++++++++------------ fs/super.c | 4 ++++ fs/xfs/Kconfig | 1 + include/linux/blkdev.h | 50 +++++++++++++++++++++++++++++++------------- include/linux/buffer_head.h | 16 ++++++++++++++ include/linux/compat_ioctl.h | 2 ++ include/linux/elevator.h | 3 +++ include/linux/fs.h | 25 +++++++++++++++++++--- include/linux/genhd.h | 4 ++++ include/linux/mpage.h | 3 +++ include/linux/raid/md.h | 3 +++ include/linux/raid/md_k.h | 3 +++ include/scsi/scsi_tcq.h | 3 ++- init/Kconfig | 2 +- init/do_mounts.c | 13 +++++++++++- kernel/sys_ni.c | 5 +++++ mm/Makefile | 2 +- mm/filemap.c | 4 ++++ mm/migrate.c | 2 ++ mm/page-writeback.c | 8 ++++--- mm/truncate.c | 2 ++ 44 files changed, 308 insertions(+), 63 deletions(-) create mode 100644 fs/no-block.c (limited to 'mm/filemap.c') diff --git a/block/Kconfig b/block/Kconfig index b6f5f0a7965..9af6c614dfd 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -1,6 +1,24 @@ # # Block layer core configuration # +config BLOCK + bool "Enable the block layer" + default y + help + This permits the block layer to be removed from the kernel if it's not + needed (on some embedded devices for example). If this option is + disabled, then blockdev files will become unusable and some + filesystems (such as ext3) will become unavailable. + + This option will also disable SCSI character devices and USB storage + since they make use of various block layer definitions and + facilities. + + Say Y here unless you know you really don't want to mount disks and + suchlike. + +if BLOCK + #XXX - it makes sense to enable this only for 32-bit subarch's, not for x86_64 #for instance. config LBD @@ -33,4 +51,6 @@ config LSF If unsure, say Y. +endif + source block/Kconfig.iosched diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 48d090e266f..903f0d3b685 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -1,3 +1,4 @@ +if BLOCK menu "IO Schedulers" @@ -67,3 +68,5 @@ config DEFAULT_IOSCHED default "noop" if DEFAULT_NOOP endmenu + +endif diff --git a/block/Makefile b/block/Makefile index c05de0e0037..4b84d0d5947 100644 --- a/block/Makefile +++ b/block/Makefile @@ -2,7 +2,7 @@ # Makefile for the kernel block layer # -obj-y := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o +obj-$(CONFIG_BLOCK) := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o obj-$(CONFIG_IOSCHED_AS) += as-iosched.o diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index b5382cedf0c..422e31d5f8e 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -2,6 +2,8 @@ # Block device driver configuration # +if BLOCK + menu "Block devices" config BLK_DEV_FD @@ -468,3 +470,5 @@ config ATA_OVER_ETH devices like the Coraid EtherDrive (R) Storage Blade. endmenu + +endif diff --git a/drivers/cdrom/Kconfig b/drivers/cdrom/Kconfig index ff5652d4061..4b12e9031fb 100644 --- a/drivers/cdrom/Kconfig +++ b/drivers/cdrom/Kconfig @@ -3,7 +3,7 @@ # menu "Old CD-ROM drivers (not SCSI, not IDE)" - depends on ISA + depends on ISA && BLOCK config CD_NO_IDESCSI bool "Support non-SCSI/IDE/ATAPI CDROM drives" diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 4cc619edf42..bde1c665d9f 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -1006,6 +1006,7 @@ config GPIO_VR41XX config RAW_DRIVER tristate "RAW driver (/dev/raw/rawN) (OBSOLETE)" + depends on BLOCK help The raw driver permits block devices to be bound to /dev/raw/rawN. Once bound, I/O against /dev/raw/rawN uses efficient zero-copy I/O. diff --git a/drivers/char/random.c b/drivers/char/random.c index 4c3a5ca9d8f..b430a12eb81 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -655,6 +655,7 @@ void add_interrupt_randomness(int irq) add_timer_randomness(irq_timer_state[irq], 0x100 + irq); } +#ifdef CONFIG_BLOCK void add_disk_randomness(struct gendisk *disk) { if (!disk || !disk->random) @@ -667,6 +668,7 @@ void add_disk_randomness(struct gendisk *disk) } EXPORT_SYMBOL(add_disk_randomness); +#endif #define EXTRACT_SIZE 10 @@ -918,6 +920,7 @@ void rand_initialize_irq(int irq) } } +#ifdef CONFIG_BLOCK void rand_initialize_disk(struct gendisk *disk) { struct timer_rand_state *state; @@ -932,6 +935,7 @@ void rand_initialize_disk(struct gendisk *disk) disk->random = state; } } +#endif static ssize_t random_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos) diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig index b6fb167e20f..69d627bd537 100644 --- a/drivers/ide/Kconfig +++ b/drivers/ide/Kconfig @@ -4,6 +4,8 @@ # Andre Hedrick # +if BLOCK + menu "ATA/ATAPI/MFM/RLL support" config IDE @@ -1082,3 +1084,5 @@ config BLK_DEV_HD endif endmenu + +endif diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index bf869ed03ee..6dd31a291d8 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -2,6 +2,8 @@ # Block device driver configuration # +if BLOCK + menu "Multi-device support (RAID and LVM)" config MD @@ -251,3 +253,4 @@ config DM_MULTIPATH_EMC endmenu +endif diff --git a/drivers/message/i2o/Kconfig b/drivers/message/i2o/Kconfig index fef67710388..6443392bfff 100644 --- a/drivers/message/i2o/Kconfig +++ b/drivers/message/i2o/Kconfig @@ -88,7 +88,7 @@ config I2O_BUS config I2O_BLOCK tristate "I2O Block OSM" - depends on I2O + depends on I2O && BLOCK ---help--- Include support for the I2O Block OSM. The Block OSM presents disk and other structured block devices to the operating system. If you diff --git a/drivers/mmc/Kconfig b/drivers/mmc/Kconfig index 45bcf098e76..f540bd88dc5 100644 --- a/drivers/mmc/Kconfig +++ b/drivers/mmc/Kconfig @@ -21,7 +21,7 @@ config MMC_DEBUG config MMC_BLOCK tristate "MMC block device driver" - depends on MMC + depends on MMC && BLOCK default y help Say Y here to enable the MMC block device driver support. diff --git a/drivers/mmc/Makefile b/drivers/mmc/Makefile index d2957e35cc6..b1f6e03e7aa 100644 --- a/drivers/mmc/Makefile +++ b/drivers/mmc/Makefile @@ -24,7 +24,8 @@ obj-$(CONFIG_MMC_AU1X) += au1xmmc.o obj-$(CONFIG_MMC_OMAP) += omap.o obj-$(CONFIG_MMC_AT91RM9200) += at91_mci.o -mmc_core-y := mmc.o mmc_queue.o mmc_sysfs.o +mmc_core-y := mmc.o mmc_sysfs.o +mmc_core-$(CONFIG_BLOCK) += mmc_queue.o ifeq ($(CONFIG_MMC_DEBUG),y) EXTRA_CFLAGS += -DDEBUG diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig index a03e862851d..a304b34c263 100644 --- a/drivers/mtd/Kconfig +++ b/drivers/mtd/Kconfig @@ -166,7 +166,7 @@ config MTD_CHAR config MTD_BLOCK tristate "Caching block device access to MTD devices" - depends on MTD + depends on MTD && BLOCK ---help--- Although most flash chips have an erase size too large to be useful as block devices, it is possible to use MTD devices which are based @@ -188,7 +188,7 @@ config MTD_BLOCK config MTD_BLOCK_RO tristate "Readonly block device access to MTD devices" - depends on MTD_BLOCK!=y && MTD + depends on MTD_BLOCK!=y && MTD && BLOCK help This allows you to mount read-only file systems (such as cramfs) from an MTD device, without the overhead (and danger) of the caching @@ -199,7 +199,7 @@ config MTD_BLOCK_RO config FTL tristate "FTL (Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the original Flash Translation Layer which is part of the PCMCIA specification. It uses a kind of pseudo- @@ -215,7 +215,7 @@ config FTL config NFTL tristate "NFTL (NAND Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the NAND Flash Translation Layer which is used on M-Systems' DiskOnChip devices. It uses a kind of pseudo- @@ -238,7 +238,7 @@ config NFTL_RW config INFTL tristate "INFTL (Inverse NAND Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the Inverse NAND Flash Translation Layer which is used on M-Systems' newer DiskOnChip devices. It @@ -255,7 +255,7 @@ config INFTL config RFD_FTL tristate "Resident Flash Disk (Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the flash translation layer known as the Resident Flash Disk (RFD), as used by the Embedded BIOS diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 16c02b5ccf7..440f6851da6 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -136,7 +136,7 @@ config MTDRAM_ABS_POS config MTD_BLOCK2MTD tristate "MTD using block device" - depends on MTD + depends on MTD && BLOCK help This driver allows a block device to appear as an MTD. It would generally be used in the following cases: diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index 929d6fff615..b250c535450 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -1,4 +1,4 @@ -if S390 +if S390 && BLOCK comment "S/390 block device drivers" depends on S390 diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index c4dfcc91ddd..dab082002e6 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -3,11 +3,13 @@ menu "SCSI device support" config RAID_ATTRS tristate "RAID Transport Class" default n + depends on BLOCK ---help--- Provides RAID config SCSI tristate "SCSI device support" + depends on BLOCK ---help--- If you want to use a SCSI hard disk, SCSI tape drive, SCSI CD-ROM or any other SCSI device under Linux, say Y and make sure that you know diff --git a/fs/Kconfig b/fs/Kconfig index 4fd9efac29a..1453d2d164f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -4,6 +4,8 @@ menu "File systems" +if BLOCK + config EXT2_FS tristate "Second extended fs support" help @@ -399,6 +401,8 @@ config ROMFS_FS If you don't know whether you need it, then you don't need it: answer N. +endif + config INOTIFY bool "Inotify file change notification support" default y @@ -530,6 +534,7 @@ config FUSE_FS If you want to develop a userspace FS, or if you want to use a filesystem based on FUSE, answer Y or M. +if BLOCK menu "CD-ROM/DVD Filesystems" config ISO9660_FS @@ -597,7 +602,9 @@ config UDF_NLS depends on (UDF_FS=m && NLS) || (UDF_FS=y && NLS=y) endmenu +endif +if BLOCK menu "DOS/FAT/NT Filesystems" config FAT_FS @@ -782,6 +789,7 @@ config NTFS_RW It is perfectly safe to say N here. endmenu +endif menu "Pseudo filesystems" @@ -939,7 +947,7 @@ menu "Miscellaneous filesystems" config ADFS_FS tristate "ADFS file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help The Acorn Disc Filing System is the standard file system of the RiscOS operating system which runs on Acorn's ARM-based Risc PC @@ -967,7 +975,7 @@ config ADFS_FS_RW config AFFS_FS tristate "Amiga FFS file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help The Fast File System (FFS) is the common file system used on hard disks by Amiga(tm) systems since AmigaOS Version 1.3 (34.20). Say Y @@ -989,7 +997,7 @@ config AFFS_FS config HFS_FS tristate "Apple Macintosh file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL select NLS help If you say Y here, you will be able to mount Macintosh-formatted @@ -1002,6 +1010,7 @@ config HFS_FS config HFSPLUS_FS tristate "Apple Extended HFS file system support" + depends on BLOCK select NLS select NLS_UTF8 help @@ -1015,7 +1024,7 @@ config HFSPLUS_FS config BEFS_FS tristate "BeOS file system (BeFS) support (read only) (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL select NLS help The BeOS File System (BeFS) is the native file system of Be, Inc's @@ -1042,7 +1051,7 @@ config BEFS_DEBUG config BFS_FS tristate "BFS file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help Boot File System (BFS) is a file system used under SCO UnixWare to allow the bootloader access to the kernel image and other important @@ -1064,7 +1073,7 @@ config BFS_FS config EFS_FS tristate "EFS file system support (read only) (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help EFS is an older file system used for non-ISO9660 CD-ROMs and hard disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer @@ -1079,7 +1088,7 @@ config EFS_FS config JFFS_FS tristate "Journalling Flash File System (JFFS) support" - depends on MTD + depends on MTD && BLOCK help JFFS is the Journaling Flash File System developed by Axis Communications in Sweden, aimed at providing a crash/powerdown-safe @@ -1264,6 +1273,7 @@ endchoice config CRAMFS tristate "Compressed ROM file system support (cramfs)" + depends on BLOCK select ZLIB_INFLATE help Saying Y here includes support for CramFs (Compressed ROM File @@ -1283,6 +1293,7 @@ config CRAMFS config VXFS_FS tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)" + depends on BLOCK help FreeVxFS is a file system driver that support the VERITAS VxFS(TM) file system format. VERITAS VxFS(TM) is the standard file system @@ -1300,6 +1311,7 @@ config VXFS_FS config HPFS_FS tristate "OS/2 HPFS file system support" + depends on BLOCK help OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS is the file system used for organizing files on OS/2 hard disk @@ -1316,6 +1328,7 @@ config HPFS_FS config QNX4FS_FS tristate "QNX4 file system support (read only)" + depends on BLOCK help This is the file system used by the real-time operating systems QNX 4 and QNX 6 (the latter is also called QNX RTP). @@ -1343,6 +1356,7 @@ config QNX4FS_RW config SYSV_FS tristate "System V/Xenix/V7/Coherent file system support" + depends on BLOCK help SCO, Xenix and Coherent are commercial Unix systems for Intel machines, and Version 7 was used on the DEC PDP-11. Saying Y @@ -1381,6 +1395,7 @@ config SYSV_FS config UFS_FS tristate "UFS file system support (read only)" + depends on BLOCK help BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD, OpenBSD and NeXTstep) use a file system called UFS. Some System V @@ -1959,11 +1974,13 @@ config GENERIC_ACL endmenu +if BLOCK menu "Partition Types" source "fs/partitions/Kconfig" endmenu +endif source "fs/nls/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index 46b8cfe497b..a503e6ce0f3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -5,12 +5,18 @@ # Rewritten to use lists instead of if-statements. # -obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \ - block_dev.o char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ +obj-y := open.o read_write.o file_table.o super.o \ + char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \ attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \ - seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \ - ioprio.o pnode.o drop_caches.o splice.o sync.o + seq_file.o xattr.o libfs.o fs-writeback.o \ + pnode.o drop_caches.o splice.o sync.o + +ifeq ($(CONFIG_BLOCK),y) +obj-y += buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o +else +obj-y += no-block.o +endif obj-$(CONFIG_INOTIFY) += inotify.o obj-$(CONFIG_INOTIFY_USER) += inotify_user.o diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index e1a56437040..64b34533ede 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -645,6 +645,7 @@ out: } #endif +#ifdef CONFIG_BLOCK struct hd_geometry32 { unsigned char heads; unsigned char sectors; @@ -869,6 +870,7 @@ static int sg_grt_trans(unsigned int fd, unsigned int cmd, unsigned long arg) } return err; } +#endif /* CONFIG_BLOCK */ struct sock_fprog32 { unsigned short len; @@ -992,6 +994,7 @@ static int ppp_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg) } +#ifdef CONFIG_BLOCK struct mtget32 { compat_long_t mt_type; compat_long_t mt_resid; @@ -1164,6 +1167,7 @@ static int cdrom_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long ar return err; } +#endif /* CONFIG_BLOCK */ #ifdef CONFIG_VT @@ -1491,6 +1495,7 @@ ret_einval(unsigned int fd, unsigned int cmd, unsigned long arg) return -EINVAL; } +#ifdef CONFIG_BLOCK static int broken_blkgetsize(unsigned int fd, unsigned int cmd, unsigned long arg) { /* The mkswap binary hard codes it to Intel value :-((( */ @@ -1525,12 +1530,14 @@ static int blkpg_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long ar return sys_ioctl(fd, cmd, (unsigned long)a); } +#endif static int ioc_settimeout(unsigned int fd, unsigned int cmd, unsigned long arg) { return rw_long(fd, AUTOFS_IOC_SETTIMEOUT, arg); } +#ifdef CONFIG_BLOCK /* Fix sizeof(sizeof()) breakage */ #define BLKBSZGET_32 _IOR(0x12,112,int) #define BLKBSZSET_32 _IOW(0x12,113,int) @@ -1551,6 +1558,7 @@ static int do_blkgetsize64(unsigned int fd, unsigned int cmd, { return sys_ioctl(fd, BLKGETSIZE64, (unsigned long)compat_ptr(arg)); } +#endif /* Bluetooth ioctls */ #define HCIUARTSETPROTO _IOW('U', 200, int) @@ -1571,6 +1579,7 @@ static int do_blkgetsize64(unsigned int fd, unsigned int cmd, #define HIDPGETCONNLIST _IOR('H', 210, int) #define HIDPGETCONNINFO _IOR('H', 211, int) +#ifdef CONFIG_BLOCK struct floppy_struct32 { compat_uint_t size; compat_uint_t sect; @@ -1895,6 +1904,7 @@ out: kfree(karg); return err; } +#endif struct mtd_oob_buf32 { u_int32_t start; @@ -1936,6 +1946,7 @@ static int mtd_rw_oob(unsigned int fd, unsigned int cmd, unsigned long arg) return err; } +#ifdef CONFIG_BLOCK struct raw32_config_request { compat_int_t raw_minor; @@ -2000,6 +2011,7 @@ static int raw_ioctl(unsigned fd, unsigned cmd, unsigned long arg) } return ret; } +#endif /* CONFIG_BLOCK */ struct serial_struct32 { compat_int_t type; @@ -2606,6 +2618,7 @@ HANDLE_IOCTL(SIOCBRDELIF, dev_ifsioc) HANDLE_IOCTL(SIOCRTMSG, ret_einval) HANDLE_IOCTL(SIOCGSTAMP, do_siocgstamp) #endif +#ifdef CONFIG_BLOCK HANDLE_IOCTL(HDIO_GETGEO, hdio_getgeo) HANDLE_IOCTL(BLKRAGET, w_long) HANDLE_IOCTL(BLKGETSIZE, w_long) @@ -2631,14 +2644,17 @@ HANDLE_IOCTL(FDGETFDCSTAT32, fd_ioctl_trans) HANDLE_IOCTL(FDWERRORGET32, fd_ioctl_trans) HANDLE_IOCTL(SG_IO,sg_ioctl_trans) HANDLE_IOCTL(SG_GET_REQUEST_TABLE, sg_grt_trans) +#endif HANDLE_IOCTL(PPPIOCGIDLE32, ppp_ioctl_trans) HANDLE_IOCTL(PPPIOCSCOMPRESS32, ppp_ioctl_trans) HANDLE_IOCTL(PPPIOCSPASS32, ppp_sock_fprog_ioctl_trans) HANDLE_IOCTL(PPPIOCSACTIVE32, ppp_sock_fprog_ioctl_trans) +#ifdef CONFIG_BLOCK HANDLE_IOCTL(MTIOCGET32, mt_ioctl_trans) HANDLE_IOCTL(MTIOCPOS32, mt_ioctl_trans) HANDLE_IOCTL(CDROMREADAUDIO, cdrom_ioctl_trans) HANDLE_IOCTL(CDROM_SEND_PACKET, cdrom_ioctl_trans) +#endif #define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93,0x64,unsigned int) HANDLE_IOCTL(AUTOFS_IOC_SETTIMEOUT32, ioc_settimeout) #ifdef CONFIG_VT @@ -2677,12 +2693,14 @@ HANDLE_IOCTL(SONET_SETFRAMING, do_atm_ioctl) HANDLE_IOCTL(SONET_GETFRAMING, do_atm_ioctl) HANDLE_IOCTL(SONET_GETFRSENSE, do_atm_ioctl) /* block stuff */ +#ifdef CONFIG_BLOCK HANDLE_IOCTL(BLKBSZGET_32, do_blkbszget) HANDLE_IOCTL(BLKBSZSET_32, do_blkbszset) HANDLE_IOCTL(BLKGETSIZE64_32, do_blkgetsize64) /* Raw devices */ HANDLE_IOCTL(RAW_SETBIND, raw_ioctl) HANDLE_IOCTL(RAW_GETBIND, raw_ioctl) +#endif /* Serial */ HANDLE_IOCTL(TIOCGSERIAL, serial_struct_ioctl) HANDLE_IOCTL(TIOCSSERIAL, serial_struct_ioctl) diff --git a/fs/internal.h b/fs/internal.h index f662b703bb9..f07147d6325 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -14,10 +14,16 @@ /* * block_dev.c */ +#ifdef CONFIG_BLOCK extern struct super_block *blockdev_superblock; extern void __init bdev_cache_init(void); #define sb_is_blkdev_sb(sb) ((sb) == blockdev_superblock) +#else +static inline void bdev_cache_init(void) {} + +#define sb_is_blkdev_sb(sb) 0 +#endif /* * char_dev.c diff --git a/fs/no-block.c b/fs/no-block.c new file mode 100644 index 00000000000..d269a93d346 --- /dev/null +++ b/fs/no-block.c @@ -0,0 +1,22 @@ +/* no-block.c: implementation of routines required for non-BLOCK configuration + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include + +static int no_blkdev_open(struct inode * inode, struct file * filp) +{ + return -ENODEV; +} + +const struct file_operations def_blk_fops = { + .open = no_blkdev_open, +}; diff --git a/fs/partitions/Makefile b/fs/partitions/Makefile index d713ce6b3e1..67e665fdb7f 100644 --- a/fs/partitions/Makefile +++ b/fs/partitions/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel. # -obj-y := check.o +obj-$(CONFIG_BLOCK) := check.o obj-$(CONFIG_ACORN_PARTITION) += acorn.o obj-$(CONFIG_AMIGA_PARTITION) += amiga.o diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 5bbd6089605..66bc425f2f3 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -277,12 +277,15 @@ static int devinfo_show(struct seq_file *f, void *v) if (i == 0) seq_printf(f, "Character devices:\n"); chrdev_show(f, i); - } else { + } +#ifdef CONFIG_BLOCK + else { i -= CHRDEV_MAJOR_HASH_SIZE; if (i == 0) seq_printf(f, "\nBlock devices:\n"); blkdev_show(f, i); } +#endif return 0; } @@ -355,6 +358,7 @@ static int stram_read_proc(char *page, char **start, off_t off, } #endif +#ifdef CONFIG_BLOCK extern struct seq_operations partitions_op; static int partitions_open(struct inode *inode, struct file *file) { @@ -378,6 +382,7 @@ static struct file_operations proc_diskstats_operations = { .llseek = seq_lseek, .release = seq_release, }; +#endif #ifdef CONFIG_MODULES extern struct seq_operations modules_op; @@ -695,7 +700,9 @@ void __init proc_misc_init(void) entry->proc_fops = &proc_kmsg_operations; create_seq_entry("devices", 0, &proc_devinfo_operations); create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations); +#ifdef CONFIG_BLOCK create_seq_entry("partitions", 0, &proc_partitions_operations); +#endif create_seq_entry("stat", 0, &proc_stat_operations); create_seq_entry("interrupts", 0, &proc_interrupts_operations); #ifdef CONFIG_SLAB @@ -707,7 +714,9 @@ void __init proc_misc_init(void) create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations); create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations); create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations); +#ifdef CONFIG_BLOCK create_seq_entry("diskstats", 0, &proc_diskstats_operations); +#endif #ifdef CONFIG_MODULES create_seq_entry("modules", 0, &proc_modules_operations); #endif diff --git a/fs/quota.c b/fs/quota.c index d6a2be826e2..b9dae76a0b6 100644 --- a/fs/quota.c +++ b/fs/quota.c @@ -337,6 +337,34 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, void return 0; } +/* + * look up a superblock on which quota ops will be performed + * - use the name of a block device to find the superblock thereon + */ +static inline struct super_block *quotactl_block(const char __user *special) +{ +#ifdef CONFIG_BLOCK + struct block_device *bdev; + struct super_block *sb; + char *tmp = getname(special); + + if (IS_ERR(tmp)) + return ERR_PTR(PTR_ERR(tmp)); + bdev = lookup_bdev(tmp); + putname(tmp); + if (IS_ERR(bdev)) + return ERR_PTR(PTR_ERR(bdev)); + sb = get_super(bdev); + bdput(bdev); + if (!sb) + return ERR_PTR(-ENODEV); + + return sb; +#else + return ERR_PTR(-ENODEV); +#endif +} + /* * This is the system call interface. This communicates with * the user-level programs. Currently this only supports diskquota @@ -347,25 +375,15 @@ asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, qid_t { uint cmds, type; struct super_block *sb = NULL; - struct block_device *bdev; - char *tmp; int ret; cmds = cmd >> SUBCMDSHIFT; type = cmd & SUBCMDMASK; if (cmds != Q_SYNC || special) { - tmp = getname(special); - if (IS_ERR(tmp)) - return PTR_ERR(tmp); - bdev = lookup_bdev(tmp); - putname(tmp); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - sb = get_super(bdev); - bdput(bdev); - if (!sb) - return -ENODEV; + sb = quotactl_block(special); + if (IS_ERR(sb)) + return PTR_ERR(sb); } ret = check_quotactl_valid(sb, type, cmds, id); diff --git a/fs/super.c b/fs/super.c index 15671cd048b..aec99ddbe53 100644 --- a/fs/super.c +++ b/fs/super.c @@ -571,8 +571,10 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) { int retval; +#ifdef CONFIG_BLOCK if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev)) return -EACCES; +#endif if (flags & MS_RDONLY) acct_auto_close(sb); shrink_dcache_sb(sb); @@ -692,6 +694,7 @@ void kill_litter_super(struct super_block *sb) EXPORT_SYMBOL(kill_litter_super); +#ifdef CONFIG_BLOCK static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; @@ -787,6 +790,7 @@ void kill_block_super(struct super_block *sb) } EXPORT_SYMBOL(kill_block_super); +#endif int get_sb_nodev(struct file_system_type *fs_type, int flags, void *data, diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 26b364c9d62..35115bca036 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -1,5 +1,6 @@ config XFS_FS tristate "XFS filesystem support" + depends on BLOCK help XFS is a high performance journaling filesystem which originated on the SGI IRIX platform. It is completely multi-threaded, can diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c01a90998a..3e36107d342 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -16,6 +16,22 @@ #include +#ifdef CONFIG_LBD +# include +# define sector_div(a, b) do_div(a, b) +#else +# define sector_div(n, b)( \ +{ \ + int _res; \ + _res = (n) % (b); \ + (n) /= (b); \ + _res; \ +} \ +) +#endif + +#ifdef CONFIG_BLOCK + struct scsi_ioctl_command; struct request_queue; @@ -818,24 +834,30 @@ struct work_struct; int kblockd_schedule_work(struct work_struct *work); void kblockd_flush(void); -#ifdef CONFIG_LBD -# include -# define sector_div(a, b) do_div(a, b) -#else -# define sector_div(n, b)( \ -{ \ - int _res; \ - _res = (n) % (b); \ - (n) /= (b); \ - _res; \ -} \ -) -#endif - #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") +#else /* CONFIG_BLOCK */ +/* + * stubs for when the block layer is configured out + */ +#define buffer_heads_over_limit 0 + +static inline long blk_congestion_wait(int rw, long timeout) +{ + return timeout; +} + +static inline long nr_blockdev_pages(void) +{ + return 0; +} + +static inline void exit_io_context(void) {} + +#endif /* CONFIG_BLOCK */ + #endif diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 64b508e35d2..131ffd37e71 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -14,6 +14,8 @@ #include #include +#ifdef CONFIG_BLOCK + enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ @@ -301,4 +303,18 @@ static inline void lock_buffer(struct buffer_head *bh) } extern int __set_page_dirty_buffers(struct page *page); + +#else /* CONFIG_BLOCK */ + +static inline void buffer_init(void) {} +static inline int try_to_free_buffers(struct page *page) { return 1; } +static inline int sync_blockdev(struct block_device *bdev) { return 0; } +static inline int inode_has_buffers(struct inode *inode) { return 0; } +static inline void invalidate_inode_buffers(struct inode *inode) {} +static inline int remove_inode_buffers(struct inode *inode) { return 1; } +static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +static inline void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers) {} + + +#endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 98d40e08ba6..d61ef595153 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -90,6 +90,7 @@ COMPATIBLE_IOCTL(FDTWADDLE) COMPATIBLE_IOCTL(FDFMTTRK) COMPATIBLE_IOCTL(FDRAWCMD) /* 0x12 */ +#ifdef CONFIG_BLOCK COMPATIBLE_IOCTL(BLKRASET) COMPATIBLE_IOCTL(BLKROSET) COMPATIBLE_IOCTL(BLKROGET) @@ -103,6 +104,7 @@ COMPATIBLE_IOCTL(BLKTRACESETUP) COMPATIBLE_IOCTL(BLKTRACETEARDOWN) ULONG_IOCTL(BLKRASET) ULONG_IOCTL(BLKFRASET) +#endif /* RAID */ COMPATIBLE_IOCTL(RAID_VERSION) COMPATIBLE_IOCTL(GET_ARRAY_INFO) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 9c5a04f6114..b3370ef5164 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -3,6 +3,8 @@ #include +#ifdef CONFIG_BLOCK + typedef int (elevator_merge_fn) (request_queue_t *, struct request **, struct bio *); @@ -203,4 +205,5 @@ enum { __val; \ }) +#endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index b73a47582db..5baf3a15340 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1482,6 +1482,7 @@ extern void __init vfs_caches_init(unsigned long); extern void putname(const char *name); #endif +#ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern int unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); @@ -1490,11 +1491,15 @@ extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, unsigned); extern struct block_device *open_partition_by_devnum(dev_t, unsigned); -extern const struct file_operations def_blk_fops; extern const struct address_space_operations def_blk_aops; +#else +static inline void bd_forget(struct inode *inode) {} +#endif +extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; extern const struct file_operations bad_sock_fops; extern const struct file_operations def_fifo_fops; +#ifdef CONFIG_BLOCK extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); @@ -1510,6 +1515,7 @@ extern void bd_release_from_disk(struct block_device *, struct gendisk *); #define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder) #define bd_release_from_disk(bdev, disk) bd_release(bdev) #endif +#endif /* fs/char_dev.c */ #define CHRDEV_MAJOR_HASH_SIZE 255 @@ -1523,14 +1529,19 @@ extern int chrdev_open(struct inode *, struct file *); extern void chrdev_show(struct seq_file *,off_t); /* fs/block_dev.c */ -#define BLKDEV_MAJOR_HASH_SIZE 255 #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ + +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_HASH_SIZE 255 extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern struct block_device *open_bdev_excl(const char *, int, void *); extern void close_bdev_excl(struct block_device *); extern void blkdev_show(struct seq_file *,off_t); +#else +#define BLKDEV_MAJOR_HASH_SIZE 0 +#endif extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -1544,6 +1555,7 @@ extern const struct file_operations rdwr_fifo_fops; extern int fs_may_remount_ro(struct super_block *); +#ifdef CONFIG_BLOCK /* * return READ, READA, or WRITE */ @@ -1555,9 +1567,10 @@ extern int fs_may_remount_ro(struct super_block *); #define bio_data_dir(bio) ((bio)->bi_rw & 1) extern int check_disk_change(struct block_device *); -extern int invalidate_inodes(struct super_block *); extern int __invalidate_device(struct block_device *); extern int invalidate_partition(struct gendisk *, int); +#endif +extern int invalidate_inodes(struct super_block *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); unsigned long invalidate_inode_pages(struct address_space *mapping); @@ -1590,7 +1603,9 @@ extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, void *data, int force); +#ifdef CONFIG_BLOCK extern sector_t bmap(struct inode *, sector_t); +#endif extern int notify_change(struct dentry *, struct iattr *); extern int permission(struct inode *, int, struct nameidata *); extern int generic_permission(struct inode *, int, @@ -1673,9 +1688,11 @@ static inline void insert_inode_hash(struct inode *inode) { extern struct file * get_empty_filp(void); extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); +#ifdef CONFIG_BLOCK struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); +#endif extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); @@ -1756,6 +1773,7 @@ static inline void do_generic_file_read(struct file * filp, loff_t *ppos, actor); } +#ifdef CONFIG_BLOCK ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, @@ -1793,6 +1811,7 @@ static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb, return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, nr_segs, get_block, end_io, DIO_OWN_LOCKING); } +#endif extern const struct file_operations generic_ro_fops; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e4af57e87c1..41f276fdd18 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -11,6 +11,8 @@ #include +#ifdef CONFIG_BLOCK + enum { /* These three have identical behaviour; use the second one if DOS FDISK gets confused about extended/logical partitions starting past cylinder 1023. */ @@ -420,3 +422,5 @@ static inline struct block_device *bdget_disk(struct gendisk *disk, int index) #endif #endif + +#endif diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 517c098fde2..cc5fb75af78 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -9,6 +9,7 @@ * (And no, it doesn't do the #ifdef __MPAGE_H thing, and it doesn't do * nested includes. Get it right in the .c file). */ +#ifdef CONFIG_BLOCK struct writeback_control; typedef int (writepage_t)(struct page *page, struct writeback_control *wbc); @@ -20,3 +21,5 @@ int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); + +#endif diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index eb3e547c8fe..c588709acbb 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -53,6 +53,8 @@ #include #include +#ifdef CONFIG_MD + /* * Different major versions are not compatible. * Different minor versions are only downward compatible. @@ -95,5 +97,6 @@ extern void md_new_event(mddev_t *mddev); extern void md_update_sb(mddev_t * mddev); +#endif /* CONFIG_MD */ #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index d2889029585..920b94fe31f 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -18,6 +18,8 @@ /* and dm-bio-list.h is not under include/linux because.... ??? */ #include "../../../drivers/md/dm-bio-list.h" +#ifdef CONFIG_BLOCK + #define LEVEL_MULTIPATH (-4) #define LEVEL_LINEAR (-1) #define LEVEL_FAULTY (-5) @@ -362,5 +364,6 @@ static inline void safe_put_page(struct page *p) if (p) put_page(p); } +#endif /* CONFIG_BLOCK */ #endif diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h index bbf66219b76..c247a28259b 100644 --- a/include/scsi/scsi_tcq.h +++ b/include/scsi/scsi_tcq.h @@ -6,7 +6,6 @@ #include #include - #define MSG_SIMPLE_TAG 0x20 #define MSG_HEAD_TAG 0x21 #define MSG_ORDERED_TAG 0x22 @@ -14,6 +13,7 @@ #define SCSI_NO_TAG (-1) /* identify no tag in use */ +#ifdef CONFIG_BLOCK /** * scsi_get_tag_type - get the type of tag the device supports @@ -144,4 +144,5 @@ static inline int scsi_init_shared_tag_map(struct Scsi_Host *shost, int depth) return shost->bqt ? 0 : -ENOMEM; } +#endif /* CONFIG_BLOCK */ #endif /* _SCSI_SCSI_TCQ_H */ diff --git a/init/Kconfig b/init/Kconfig index 4381006dd66..d2eb7a84a26 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -92,7 +92,7 @@ config LOCALVERSION_AUTO config SWAP bool "Support for paging of anonymous memory (swap)" - depends on MMU + depends on MMU && BLOCK default y help This option allows you to choose whether you want to have support diff --git a/init/do_mounts.c b/init/do_mounts.c index b290aadb1d3..dc1ec0803ef 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -285,7 +285,11 @@ void __init mount_block_root(char *name, int flags) { char *fs_names = __getname(); char *p; +#ifdef CONFIG_BLOCK char b[BDEVNAME_SIZE]; +#else + const char *b = name; +#endif get_fs_names(fs_names); retry: @@ -304,7 +308,9 @@ retry: * Allow the user to distinguish between failed sys_open * and bad superblock on root device. */ +#ifdef CONFIG_BLOCK __bdevname(ROOT_DEV, b); +#endif printk("VFS: Cannot open root device \"%s\" or %s\n", root_device_name, b); printk("Please append a correct \"root=\" boot option\n"); @@ -316,7 +322,10 @@ retry: for (p = fs_names; *p; p += strlen(p)+1) printk(" %s", p); printk("\n"); - panic("VFS: Unable to mount root fs on %s", __bdevname(ROOT_DEV, b)); +#ifdef CONFIG_BLOCK + __bdevname(ROOT_DEV, b); +#endif + panic("VFS: Unable to mount root fs on %s", b); out: putname(fs_names); } @@ -387,8 +396,10 @@ void __init mount_root(void) change_floppy("root floppy"); } #endif +#ifdef CONFIG_BLOCK create_dev("/dev/root", ROOT_DEV); mount_block_root("/dev/root", root_mountflags); +#endif } /* diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 6991bece67e..7a3b2e75f04 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -134,3 +134,8 @@ cond_syscall(sys_madvise); cond_syscall(sys_mremap); cond_syscall(sys_remap_file_pages); cond_syscall(compat_sys_move_pages); + +/* block-layer dependent */ +cond_syscall(sys_bdflush); +cond_syscall(sys_ioprio_set); +cond_syscall(sys_ioprio_get); diff --git a/mm/Makefile b/mm/Makefile index 4f2166a833b..12b3a4eee88 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -12,7 +12,7 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o \ prio_tree.o util.o mmzone.o vmstat.o $(mmu-y) -ifeq ($(CONFIG_MMU),y) +ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy) obj-y += bounce.o endif obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o diff --git a/mm/filemap.c b/mm/filemap.c index d6846de0888..c4fe97f5ace 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2020,6 +2020,7 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (unlikely(*pos + *count > inode->i_sb->s_maxbytes)) *count = inode->i_sb->s_maxbytes - *pos; } else { +#ifdef CONFIG_BLOCK loff_t isize; if (bdev_read_only(I_BDEV(inode))) return -EPERM; @@ -2031,6 +2032,9 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (*pos + *count > isize) *count = isize - *pos; +#else + return -EPERM; +#endif } return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index 7f50e3ff54c..ba2453f9483 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -409,6 +409,7 @@ int migrate_page(struct address_space *mapping, } EXPORT_SYMBOL(migrate_page); +#ifdef CONFIG_BLOCK /* * Migration function for pages with buffers. This function can only be used * if the underlying filesystem guarantees that no other references to "page" @@ -466,6 +467,7 @@ int buffer_migrate_page(struct address_space *mapping, return 0; } EXPORT_SYMBOL(buffer_migrate_page); +#endif /* * Writeback a page to clean the dirty state diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ecf27839c20..c0d4ce144de 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -807,9 +807,11 @@ int fastcall set_page_dirty(struct page *page) if (likely(mapping)) { int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; - if (spd) - return (*spd)(page); - return __set_page_dirty_buffers(page); +#ifdef CONFIG_BLOCK + if (!spd) + spd = __set_page_dirty_buffers; +#endif + return (*spd)(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) diff --git a/mm/truncate.c b/mm/truncate.c index cd3e34b816d..8fde6580657 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -35,8 +35,10 @@ void do_invalidatepage(struct page *page, unsigned long offset) { void (*invalidatepage)(struct page *, unsigned long); invalidatepage = page->mapping->a_ops->invalidatepage; +#ifdef CONFIG_BLOCK if (!invalidatepage) invalidatepage = block_invalidatepage; +#endif if (invalidatepage) (*invalidatepage)(page, offset); } -- cgit v1.2.3 From 027445c37282bc1ed26add45e573ad2d3e4860a5 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:46 -0700 Subject: [PATCH] Vectorize aio_read/aio_write fileop methods This patch vectorizes aio_read() and aio_write() methods to prepare for collapsing all aio & vectored operations into one interface - which is aio_read()/aio_write(). Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Cc: Michael Holzheu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 5 +-- Documentation/filesystems/vfs.txt | 4 +- arch/s390/hypfs/inode.c | 17 +++++++-- drivers/char/raw.c | 14 +------ drivers/usb/gadget/inode.c | 80 +++++++++++++++++++++++++++------------ fs/aio.c | 15 ++++++-- fs/block_dev.c | 10 +---- fs/cifs/cifsfs.c | 6 +-- fs/ext3/file.c | 5 ++- fs/nfs/direct.c | 26 ++++++++++--- fs/nfs/file.c | 34 +++++++++-------- fs/ntfs/file.c | 8 ++-- fs/ocfs2/file.c | 28 +++++++------- fs/read_write.c | 20 ++++++++-- fs/reiserfs/file.c | 4 +- fs/xfs/linux-2.6/xfs_file.c | 46 +++++++++++----------- include/linux/aio.h | 2 + include/linux/fs.h | 10 ++--- include/linux/nfs_fs.h | 10 +++-- include/net/sock.h | 1 - mm/filemap.c | 39 +++++++++---------- net/socket.c | 49 +++++++++++------------- 22 files changed, 242 insertions(+), 191 deletions(-) (limited to 'mm/filemap.c') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 247d7f619aa..eb1a6cad21e 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -356,10 +356,9 @@ The last two are called only from check_disk_change(). prototypes: loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, - loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 1cb7e8be927..cd07c21b840 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -699,9 +699,9 @@ This describes how the VFS can manipulate an open file. As of kernel struct file_operations { loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 813fc21358f..cd702ae45d6 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -134,12 +134,20 @@ static int hypfs_open(struct inode *inode, struct file *filp) return 0; } -static ssize_t hypfs_aio_read(struct kiocb *iocb, __user char *buf, - size_t count, loff_t offset) +static ssize_t hypfs_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t offset) { char *data; size_t len; struct file *filp = iocb->ki_filp; + /* XXX: temporary */ + char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; + + if (nr_segs != 1) { + count = -EINVAL; + goto out; + } data = filp->private_data; len = strlen(data); @@ -158,12 +166,13 @@ static ssize_t hypfs_aio_read(struct kiocb *iocb, __user char *buf, out: return count; } -static ssize_t hypfs_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t offset) { int rc; struct super_block *sb; struct hypfs_sb_info *fs_info; + size_t count = iov_length(iov, nr_segs); sb = iocb->ki_filp->f_dentry->d_inode->i_sb; fs_info = sb->s_fs_info; diff --git a/drivers/char/raw.c b/drivers/char/raw.c index c596a08c07b..173fb08555d 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -249,23 +249,11 @@ static ssize_t raw_file_write(struct file *file, const char __user *buf, return generic_file_write_nolock(file, &local_iov, 1, ppos); } -static ssize_t raw_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) -{ - struct iovec local_iov = { - .iov_base = (char __user *)buf, - .iov_len = count - }; - - return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); -} - - static const struct file_operations raw_fops = { .read = generic_file_read, .aio_read = generic_file_aio_read, .write = raw_file_write, - .aio_write = raw_file_aio_write, + .aio_write = generic_file_aio_write_nolock, .open = raw_open, .release= raw_release, .ioctl = raw_ioctl, diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 4a000d846a9..86924f9cdd7 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -533,7 +533,8 @@ struct kiocb_priv { struct usb_request *req; struct ep_data *epdata; void *buf; - char __user *ubuf; /* NULL for writes */ + const struct iovec *iv; + unsigned long nr_segs; unsigned actual; }; @@ -561,17 +562,32 @@ static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e) static ssize_t ep_aio_read_retry(struct kiocb *iocb) { struct kiocb_priv *priv = iocb->private; - ssize_t status = priv->actual; - - /* we "retry" to get the right mm context for this: */ - status = copy_to_user(priv->ubuf, priv->buf, priv->actual); - if (unlikely(0 != status)) - status = -EFAULT; - else - status = priv->actual; - kfree(priv->buf); - kfree(priv); - return status; + ssize_t len, total; + int i; + + /* we "retry" to get the right mm context for this: */ + + /* copy stuff into user buffers */ + total = priv->actual; + len = 0; + for (i=0; i < priv->nr_segs; i++) { + ssize_t this = min((ssize_t)(priv->iv[i].iov_len), total); + + if (copy_to_user(priv->iv[i].iov_base, priv->buf, this)) { + if (len == 0) + len = -EFAULT; + break; + } + + total -= this; + len += this; + if (total == 0) + break; + } + kfree(priv->buf); + kfree(priv); + aio_put_req(iocb); + return len; } static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) @@ -584,7 +600,7 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) spin_lock(&epdata->dev->lock); priv->req = NULL; priv->epdata = NULL; - if (priv->ubuf == NULL + if (priv->iv == NULL || unlikely(req->actual == 0) || unlikely(kiocbIsCancelled(iocb))) { kfree(req->buf); @@ -619,7 +635,8 @@ ep_aio_rwtail( char *buf, size_t len, struct ep_data *epdata, - char __user *ubuf + const struct iovec *iv, + unsigned long nr_segs ) { struct kiocb_priv *priv; @@ -634,7 +651,8 @@ fail: return value; } iocb->private = priv; - priv->ubuf = ubuf; + priv->iv = iv; + priv->nr_segs = nr_segs; value = get_ready_ep(iocb->ki_filp->f_flags, epdata); if (unlikely(value < 0)) { @@ -674,41 +692,53 @@ fail: kfree(priv); put_ep(epdata); } else - value = (ubuf ? -EIOCBRETRY : -EIOCBQUEUED); + value = (iv ? -EIOCBRETRY : -EIOCBQUEUED); return value; } static ssize_t -ep_aio_read(struct kiocb *iocb, char __user *ubuf, size_t len, loff_t o) +ep_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t o) { struct ep_data *epdata = iocb->ki_filp->private_data; char *buf; if (unlikely(epdata->desc.bEndpointAddress & USB_DIR_IN)) return -EINVAL; - buf = kmalloc(len, GFP_KERNEL); + + buf = kmalloc(iocb->ki_left, GFP_KERNEL); if (unlikely(!buf)) return -ENOMEM; + iocb->ki_retry = ep_aio_read_retry; - return ep_aio_rwtail(iocb, buf, len, epdata, ubuf); + return ep_aio_rwtail(iocb, buf, iocb->ki_left, epdata, iov, nr_segs); } static ssize_t -ep_aio_write(struct kiocb *iocb, const char __user *ubuf, size_t len, loff_t o) +ep_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t o) { struct ep_data *epdata = iocb->ki_filp->private_data; char *buf; + size_t len = 0; + int i = 0; if (unlikely(!(epdata->desc.bEndpointAddress & USB_DIR_IN))) return -EINVAL; - buf = kmalloc(len, GFP_KERNEL); + + buf = kmalloc(iocb->ki_left, GFP_KERNEL); if (unlikely(!buf)) return -ENOMEM; - if (unlikely(copy_from_user(buf, ubuf, len) != 0)) { - kfree(buf); - return -EFAULT; + + for (i=0; i < nr_segs; i++) { + if (unlikely(copy_from_user(&buf[len], iov[i].iov_base, + iov[i].iov_len) != 0)) { + kfree(buf); + return -EFAULT; + } + len += iov[i].iov_len; } - return ep_aio_rwtail(iocb, buf, len, epdata, NULL); + return ep_aio_rwtail(iocb, buf, len, epdata, NULL, 0); } /*----------------------------------------------------------------------*/ diff --git a/fs/aio.c b/fs/aio.c index 950630187ac..27ff56540c7 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -15,6 +15,7 @@ #include #include #include +#include #define DEBUG 0 @@ -1315,8 +1316,11 @@ static ssize_t aio_pread(struct kiocb *iocb) ssize_t ret = 0; do { - ret = file->f_op->aio_read(iocb, iocb->ki_buf, - iocb->ki_left, iocb->ki_pos); + iocb->ki_inline_vec.iov_base = iocb->ki_buf; + iocb->ki_inline_vec.iov_len = iocb->ki_left; + + ret = file->f_op->aio_read(iocb, &iocb->ki_inline_vec, + 1, iocb->ki_pos); /* * Can't just depend on iocb->ki_left to determine * whether we are done. This may have been a short read. @@ -1349,8 +1353,11 @@ static ssize_t aio_pwrite(struct kiocb *iocb) ssize_t ret = 0; do { - ret = file->f_op->aio_write(iocb, iocb->ki_buf, - iocb->ki_left, iocb->ki_pos); + iocb->ki_inline_vec.iov_base = iocb->ki_buf; + iocb->ki_inline_vec.iov_len = iocb->ki_left; + + ret = file->f_op->aio_write(iocb, &iocb->ki_inline_vec, + 1, iocb->ki_pos); if (ret > 0) { iocb->ki_buf += ret; iocb->ki_left -= ret; diff --git a/fs/block_dev.c b/fs/block_dev.c index 0c361ea7e5a..8c819117310 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1162,14 +1162,6 @@ static ssize_t blkdev_file_write(struct file *file, const char __user *buf, return generic_file_write_nolock(file, &local_iov, 1, ppos); } -static ssize_t blkdev_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) -{ - struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); -} - static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); @@ -1192,7 +1184,7 @@ const struct file_operations def_blk_fops = { .read = generic_file_read, .write = blkdev_file_write, .aio_read = generic_file_aio_read, - .aio_write = blkdev_file_aio_write, + .aio_write = generic_file_aio_write_nolock, .mmap = generic_file_mmap, .fsync = block_fsync, .unlocked_ioctl = block_ioctl, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 22bcf4d7e7a..5abb42a7c53 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -492,13 +492,13 @@ static ssize_t cifs_file_writev(struct file *file, const struct iovec *iov, return written; } -static ssize_t cifs_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_dentry->d_inode; ssize_t written; - written = generic_file_aio_write(iocb, buf, count, pos); + written = generic_file_aio_write(iocb, iov, nr_segs, pos); if (!CIFS_I(inode)->clientCanCacheAll) filemap_fdatawrite(inode->i_mapping); return written; diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 74ff20f9d09..5c762457bc8 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -48,14 +48,15 @@ static int ext3_release_file (struct inode * inode, struct file * filp) } static ssize_t -ext3_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +ext3_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_dentry->d_inode; ssize_t ret; int err; - ret = generic_file_aio_write(iocb, buf, count, pos); + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); /* * Skip flushing if there was an error, or if nothing was written. diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 377839bed17..9f7f8b9ea1e 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -707,8 +707,8 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz /** * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block - * @buf: user's buffer into which to read data - * @count: number of bytes to read + * @iov: vector of user buffers into which to read data + * @nr_segs: size of iov vector * @pos: byte offset in file where reading starts * * We use this function for direct reads instead of calling @@ -725,17 +725,24 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) +ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; + /* XXX: temporary */ + const char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; dprintk("nfs: direct read(%s/%s, %lu@%Ld)\n", file->f_dentry->d_parent->d_name.name, file->f_dentry->d_name.name, (unsigned long) count, (long long) pos); + if (nr_segs != 1) + return -EINVAL; + if (count < 0) goto out; retval = -EFAULT; @@ -760,8 +767,8 @@ out: /** * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block - * @buf: user's buffer from which to write data - * @count: number of bytes to write + * @iov: vector of user buffers from which to write data + * @nr_segs: size of iov vector * @pos: byte offset in file where writing starts * * We use this function for direct writes instead of calling @@ -782,17 +789,24 @@ out: * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { ssize_t retval; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; + /* XXX: temporary */ + const char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; dfprintk(VFS, "nfs: direct write(%s/%s, %lu@%Ld)\n", file->f_dentry->d_parent->d_name.name, file->f_dentry->d_name.name, (unsigned long) count, (long long) pos); + if (nr_segs != 1) + return -EINVAL; + retval = generic_write_checks(file, &pos, &count, 0); if (retval) goto out; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index be997d64912..cc93865cea9 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -41,8 +41,10 @@ static int nfs_file_release(struct inode *, struct file *); static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin); static int nfs_file_mmap(struct file *, struct vm_area_struct *); static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); -static ssize_t nfs_file_read(struct kiocb *, char __user *, size_t, loff_t); -static ssize_t nfs_file_write(struct kiocb *, const char __user *, size_t, loff_t); +static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); static int nfs_file_flush(struct file *, fl_owner_t id); static int nfs_fsync(struct file *, struct dentry *dentry, int datasync); static int nfs_check_flags(int flags); @@ -53,8 +55,8 @@ const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, .read = do_sync_read, .write = do_sync_write, - .aio_read = nfs_file_read, - .aio_write = nfs_file_write, + .aio_read = nfs_file_read, + .aio_write = nfs_file_write, .mmap = nfs_file_mmap, .open = nfs_file_open, .flush = nfs_file_flush, @@ -196,15 +198,17 @@ nfs_file_flush(struct file *file, fl_owner_t id) } static ssize_t -nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos) +nfs_file_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct dentry * dentry = iocb->ki_filp->f_dentry; struct inode * inode = dentry->d_inode; ssize_t result; + size_t count = iov_length(iov, nr_segs); #ifdef CONFIG_NFS_DIRECTIO if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_read(iocb, buf, count, pos); + return nfs_file_direct_read(iocb, iov, nr_segs, pos); #endif dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n", @@ -214,7 +218,7 @@ nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos) result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count); if (!result) - result = generic_file_aio_read(iocb, buf, count, pos); + result = generic_file_aio_read(iocb, iov, nr_segs, pos); return result; } @@ -336,24 +340,22 @@ const struct address_space_operations nfs_file_aops = { #endif }; -/* - * Write to a file (through the page cache). - */ -static ssize_t -nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct dentry * dentry = iocb->ki_filp->f_dentry; struct inode * inode = dentry->d_inode; ssize_t result; + size_t count = iov_length(iov, nr_segs); #ifdef CONFIG_NFS_DIRECTIO if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_write(iocb, buf, count, pos); + return nfs_file_direct_write(iocb, iov, nr_segs, pos); #endif - dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%lu)\n", + dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%Ld)\n", dentry->d_parent->d_name.name, dentry->d_name.name, - inode->i_ino, (unsigned long) count, (unsigned long) pos); + inode->i_ino, (unsigned long) count, (long long) pos); result = -EBUSY; if (IS_SWAPFILE(inode)) @@ -372,7 +374,7 @@ nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t goto out; nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count); - result = generic_file_aio_write(iocb, buf, count, pos); + result = generic_file_aio_write(iocb, iov, nr_segs, pos); out: return result; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 585a79d39c9..0c46f5c86b7 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2176,20 +2176,18 @@ out: /** * ntfs_file_aio_write - */ -static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = ntfs_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); + ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { int err = sync_page_range(inode, mapping, pos, ret); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 2bbfa17090c..d9ba0a931a0 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -961,25 +961,23 @@ static inline int ocfs2_write_should_remove_suid(struct inode *inode) } static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; int ret, rw_level = -1, meta_level = -1, have_alloc_sem = 0; u32 clusters; struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; loff_t newsize, saved_pos; - mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf, - (unsigned int)count, + mlog_entry("(0x%p, %u, '%.*s')\n", filp, + (unsigned int)nr_segs, filp->f_dentry->d_name.len, filp->f_dentry->d_name.name); /* happy write of zero bytes */ - if (count == 0) + if (iocb->ki_left == 0) return 0; if (!inode) { @@ -1048,7 +1046,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, } else { saved_pos = iocb->ki_pos; } - newsize = count + saved_pos; + newsize = iocb->ki_left + saved_pos; mlog(0, "pos=%lld newsize=%lld cursize=%lld\n", (long long) saved_pos, (long long) newsize, @@ -1081,7 +1079,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, if (!clusters) break; - ret = ocfs2_extend_file(inode, NULL, newsize, count); + ret = ocfs2_extend_file(inode, NULL, newsize, iocb->ki_left); if (ret < 0) { if (ret != -ENOSPC) mlog_errno(ret); @@ -1098,7 +1096,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb); - ret = generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); + ret = generic_file_aio_write_nolock(iocb, iov, nr_segs, iocb->ki_pos); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT)); @@ -1132,16 +1130,16 @@ out: } static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int ret = 0, rw_level = -1, have_alloc_sem = 0; struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; - mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf, - (unsigned int)count, + mlog_entry("(0x%p, %u, '%.*s')\n", filp, + (unsigned int)nr_segs, filp->f_dentry->d_name.len, filp->f_dentry->d_name.name); @@ -1185,7 +1183,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, } ocfs2_meta_unlock(inode, 0); - ret = generic_file_aio_read(iocb, buf, count, iocb->ki_pos); + ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos); if (ret == -EINVAL) mlog(ML_ERROR, "generic_file_aio_read returned -EINVAL\n"); diff --git a/fs/read_write.c b/fs/read_write.c index d4cb3183c99..679dd535380 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -227,14 +227,20 @@ static void wait_on_retry_sync_kiocb(struct kiocb *iocb) ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { + struct iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - while (-EIOCBRETRY == - (ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos))) + kiocb.ki_left = len; + + for (;;) { + ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; wait_on_retry_sync_kiocb(&kiocb); + } if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); @@ -279,14 +285,20 @@ EXPORT_SYMBOL(vfs_read); ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { + struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - while (-EIOCBRETRY == - (ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos))) + kiocb.ki_left = len; + + for (;;) { + ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; wait_on_retry_sync_kiocb(&kiocb); + } if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index c11f6118c9c..41f24369e47 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -1334,7 +1334,7 @@ static ssize_t reiserfs_file_write(struct file *file, /* the file we are going t if (err) return err; } - result = generic_file_write(file, buf, count, ppos); + result = do_sync_write(file, buf, count, ppos); if (after_file_end) { /* Now update i_size and remove the savelink */ struct reiserfs_transaction_handle th; @@ -1566,7 +1566,7 @@ static ssize_t reiserfs_file_write(struct file *file, /* the file we are going t } const struct file_operations reiserfs_file_operations = { - .read = generic_file_read, + .read = do_sync_read, .write = reiserfs_file_write, .ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 41cfcba7ce4..4737971c6a3 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -49,50 +49,49 @@ static struct vm_operations_struct xfs_dmapi_file_vm_ops; STATIC inline ssize_t __xfs_file_read( struct kiocb *iocb, - char __user *buf, + const struct iovec *iov, + unsigned long nr_segs, int ioflags, - size_t count, loff_t pos) { - struct iovec iov = {buf, count}; struct file *file = iocb->ki_filp; bhv_vnode_t *vp = vn_from_inode(file->f_dentry->d_inode); BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; - return bhv_vop_read(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL); + return bhv_vop_read(vp, iocb, iov, nr_segs, &iocb->ki_pos, + ioflags, NULL); } STATIC ssize_t xfs_file_aio_read( struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_read(iocb, buf, IO_ISAIO, count, pos); + return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO, pos); } STATIC ssize_t xfs_file_aio_read_invis( struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_read(iocb, buf, IO_ISAIO|IO_INVIS, count, pos); + return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } STATIC inline ssize_t __xfs_file_write( - struct kiocb *iocb, - const char __user *buf, - int ioflags, - size_t count, - loff_t pos) + struct kiocb *iocb, + const struct iovec *iov, + unsigned long nr_segs, + int ioflags, + loff_t pos) { - struct iovec iov = {(void __user *)buf, count}; struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; bhv_vnode_t *vp = vn_from_inode(inode); @@ -100,27 +99,28 @@ __xfs_file_write( BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; - return bhv_vop_write(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL); + return bhv_vop_write(vp, iocb, iov, nr_segs, &iocb->ki_pos, + ioflags, NULL); } STATIC ssize_t xfs_file_aio_write( struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_write(iocb, buf, IO_ISAIO, count, pos); + return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO, pos); } STATIC ssize_t xfs_file_aio_write_invis( struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_write(iocb, buf, IO_ISAIO|IO_INVIS, count, pos); + return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } STATIC inline ssize_t diff --git a/include/linux/aio.h b/include/linux/aio.h index 8a0193385a9..58349e58b74 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -4,6 +4,7 @@ #include #include #include +#include #include @@ -112,6 +113,7 @@ struct kiocb { long ki_retried; /* just for testing */ long ki_kicked; /* just for testing */ long ki_queued; /* just for testing */ + struct iovec ki_inline_vec; /* inline vector */ struct list_head ki_list; /* the aio core uses this * for cancellation */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 5baf3a15340..257bae16f54 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1097,9 +1097,9 @@ struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); @@ -1704,11 +1704,11 @@ extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); -extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, - unsigned long, loff_t *); + unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, loff_t *, size_t, size_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 98c9b9f667a..76ff54846ad 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -367,10 +367,12 @@ extern int nfs3_removexattr (struct dentry *, const char *name); */ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t, unsigned long); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, char __user *buf, - size_t count, loff_t pos); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos); +extern ssize_t nfs_file_direct_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); +extern ssize_t nfs_file_direct_write(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); /* * linux/fs/nfs/dir.c diff --git a/include/net/sock.h b/include/net/sock.h index edd4d73ce7f..40bb90ebb2d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -665,7 +665,6 @@ struct sock_iocb { struct sock *sk; struct scm_cookie *scm; struct msghdr *msg, async_msg; - struct iovec async_iov; struct kiocb *kiocb; }; diff --git a/mm/filemap.c b/mm/filemap.c index c4fe97f5ace..f6c1d22b504 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1226,12 +1226,11 @@ out: EXPORT_SYMBOL(__generic_file_aio_read); ssize_t -generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - BUG_ON(iocb->ki_pos != pos); - return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos); + return __generic_file_aio_read(iocb, iov, nr_segs, &iocb->ki_pos); } EXPORT_SYMBOL(generic_file_aio_read); @@ -2315,22 +2314,22 @@ out: current->backing_dev_info = NULL; return written ? written : err; } -EXPORT_SYMBOL(generic_file_aio_write_nolock); -ssize_t -generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - loff_t pos = *ppos; - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos); + BUG_ON(iocb->ki_pos != pos); + + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; + ssize_t err; err = sync_page_range_nolock(inode, mapping, pos, ret); if (err < 0) @@ -2338,6 +2337,7 @@ generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, } return ret; } +EXPORT_SYMBOL(generic_file_aio_write_nolock); static ssize_t __generic_file_write_nolock(struct file *file, const struct iovec *iov, @@ -2347,8 +2347,9 @@ __generic_file_write_nolock(struct file *file, const struct iovec *iov, ssize_t ret; init_sync_kiocb(&kiocb, file); + kiocb.ki_pos = *ppos; ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (ret == -EIOCBQUEUED) + if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); return ret; } @@ -2361,28 +2362,28 @@ generic_file_write_nolock(struct file *file, const struct iovec *iov, ssize_t ret; init_sync_kiocb(&kiocb, file); - ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); + kiocb.ki_pos = *ppos; + ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, *ppos); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; return ret; } EXPORT_SYMBOL(generic_file_write_nolock); -ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1, - &iocb->ki_pos); + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { diff --git a/net/socket.c b/net/socket.c index 1bc4167e0da..df92e425274 100644 --- a/net/socket.c +++ b/net/socket.c @@ -95,10 +95,10 @@ #include static int sock_no_open(struct inode *irrelevant, struct file *dontcare); -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *buf, - size_t size, loff_t pos); -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *buf, - size_t size, loff_t pos); +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); @@ -664,7 +664,6 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, } static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, - char __user *ubuf, size_t size, struct sock_iocb *siocb) { if (!is_sync_kiocb(iocb)) { @@ -675,16 +674,13 @@ static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, } siocb->kiocb = iocb; - siocb->async_iov.iov_base = ubuf; - siocb->async_iov.iov_len = size; - iocb->private = siocb; return siocb; } static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -715,32 +711,33 @@ static ssize_t sock_readv(struct file *file, const struct iovec *iov, init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; - ret = do_sock_read(&msg, &iocb, file, (struct iovec *)iov, nr_segs); + ret = do_sock_read(&msg, &iocb, file, iov, nr_segs); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&iocb); return ret; } -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, ubuf, count, &siocb); + + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -773,28 +770,28 @@ static ssize_t sock_writev(struct file *file, const struct iovec *iov, init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; - ret = do_sock_write(&msg, &iocb, file, (struct iovec *)iov, nr_segs); + ret = do_sock_write(&msg, &iocb, file, iov, nr_segs); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&iocb); return ret; } -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, (void __user *)ubuf, count, &siocb); + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } /* -- cgit v1.2.3 From ee0b3e671baff681d69fbf0db33b47603c0a8280 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:47 -0700 Subject: [PATCH] Remove readv/writev methods and use aio_read/aio_write instead This patch removes readv() and writev() methods and replaces them with aio_read()/aio_write() methods. Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/raw.c | 2 - drivers/net/tun.c | 37 +++++----------- fs/bad_inode.c | 2 - fs/block_dev.c | 2 - fs/cifs/cifsfs.c | 16 ------- fs/compat.c | 44 +++++-------------- fs/ext2/file.c | 2 - fs/ext3/file.c | 2 - fs/fat/file.c | 2 - fs/fuse/dev.c | 37 +++++----------- fs/hostfs/hostfs_kern.c | 2 - fs/jfs/file.c | 2 - fs/ntfs/file.c | 2 - fs/pipe.c | 59 ++++++++++---------------- fs/read_write.c | 101 +++++++++++++++++++++++++++++--------------- fs/read_write.h | 14 ++++++ fs/xfs/linux-2.6/xfs_file.c | 94 ----------------------------------------- include/linux/fs.h | 6 --- mm/filemap.c | 36 ---------------- net/socket.c | 40 ------------------ sound/core/pcm_native.c | 40 +++++++++--------- 21 files changed, 154 insertions(+), 388 deletions(-) create mode 100644 fs/read_write.h (limited to 'mm/filemap.c') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 173fb08555d..490db531e2d 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -257,8 +257,6 @@ static const struct file_operations raw_fops = { .open = raw_open, .release= raw_release, .ioctl = raw_ioctl, - .readv = generic_file_readv, - .writev = generic_file_writev, .owner = THIS_MODULE, }; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index de8da6dee1b..bc0face01d2 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -288,11 +288,10 @@ static inline size_t iov_total(const struct iovec *iv, unsigned long count) return len; } -/* Writev */ -static ssize_t tun_chr_writev(struct file * file, const struct iovec *iv, - unsigned long count, loff_t *pos) +static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) { - struct tun_struct *tun = file->private_data; + struct tun_struct *tun = iocb->ki_filp->private_data; if (!tun) return -EBADFD; @@ -302,14 +301,6 @@ static ssize_t tun_chr_writev(struct file * file, const struct iovec *iv, return tun_get_user(tun, (struct iovec *) iv, iov_total(iv, count)); } -/* Write */ -static ssize_t tun_chr_write(struct file * file, const char __user * buf, - size_t count, loff_t *pos) -{ - struct iovec iv = { (void __user *) buf, count }; - return tun_chr_writev(file, &iv, 1, pos); -} - /* Put packet to the user space buffer */ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, struct sk_buff *skb, @@ -343,10 +334,10 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, return total; } -/* Readv */ -static ssize_t tun_chr_readv(struct file *file, const struct iovec *iv, - unsigned long count, loff_t *pos) +static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) { + struct file *file = iocb->ki_filp; struct tun_struct *tun = file->private_data; DECLARE_WAITQUEUE(wait, current); struct sk_buff *skb; @@ -426,14 +417,6 @@ static ssize_t tun_chr_readv(struct file *file, const struct iovec *iv, return ret; } -/* Read */ -static ssize_t tun_chr_read(struct file * file, char __user * buf, - size_t count, loff_t *pos) -{ - struct iovec iv = { buf, count }; - return tun_chr_readv(file, &iv, 1, pos); -} - static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@ -764,10 +747,10 @@ static int tun_chr_close(struct inode *inode, struct file *file) static struct file_operations tun_fops = { .owner = THIS_MODULE, .llseek = no_llseek, - .read = tun_chr_read, - .readv = tun_chr_readv, - .write = tun_chr_write, - .writev = tun_chr_writev, + .read = do_sync_read, + .aio_read = tun_chr_aio_read, + .write = do_sync_write, + .aio_write = tun_chr_aio_write, .poll = tun_chr_poll, .ioctl = tun_chr_ioctl, .open = tun_chr_open, diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 80599ae3396..34e6d7b220c 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -40,8 +40,6 @@ static const struct file_operations bad_file_ops = .aio_fsync = EIO_ERROR, .fasync = EIO_ERROR, .lock = EIO_ERROR, - .readv = EIO_ERROR, - .writev = EIO_ERROR, .sendfile = EIO_ERROR, .sendpage = EIO_ERROR, .get_unmapped_area = EIO_ERROR, diff --git a/fs/block_dev.c b/fs/block_dev.c index 8c819117310..0f143094ef1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1191,8 +1191,6 @@ const struct file_operations def_blk_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif - .readv = generic_file_readv, - .writev = generic_file_write_nolock, .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5abb42a7c53..c00c654f2e1 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -480,18 +480,6 @@ cifs_get_sb(struct file_system_type *fs_type, return simple_set_mnt(mnt, sb); } -static ssize_t cifs_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct inode *inode = file->f_dentry->d_inode; - ssize_t written; - - written = generic_file_writev(file, iov, nr_segs, ppos); - if (!CIFS_I(inode)->clientCanCacheAll) - filemap_fdatawrite(inode->i_mapping); - return written; -} - static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -577,8 +565,6 @@ struct inode_operations cifs_symlink_inode_ops = { const struct file_operations cifs_file_ops = { .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = cifs_file_writev, .aio_read = generic_file_aio_read, .aio_write = cifs_file_aio_write, .open = cifs_open, @@ -620,8 +606,6 @@ const struct file_operations cifs_file_direct_ops = { const struct file_operations cifs_file_nobrl_ops = { .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = cifs_file_writev, .aio_read = generic_file_aio_read, .aio_write = cifs_file_aio_write, .open = cifs_open, diff --git a/fs/compat.c b/fs/compat.c index 122b4e3992b..6b90bf35f61 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -70,6 +70,8 @@ int compat_printk(const char *fmt, ...) return ret; } +#include "read_write.h" + /* * Not all architectures have sys_utime, so implement this in terms * of sys_utimes. @@ -1149,9 +1151,6 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, const struct compat_iovec __user *uvector, unsigned long nr_segs, loff_t *pos) { - typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); - typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *); - compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov=iovstack, *vector; @@ -1234,39 +1233,18 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->readv; + fnv = file->f_op->aio_read; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->writev; - } - if (fnv) { - ret = fnv(file, iov, nr_segs, pos); - goto out; + fnv = file->f_op->aio_write; } - /* Do it by hand, with file-ops */ - ret = 0; - vector = iov; - while (nr_segs > 0) { - void __user * base; - size_t len; - ssize_t nr; - - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(file, base, len, pos); + if (fnv) + ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, + pos, fnv); + else + ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); - if (nr < 0) { - if (!ret) ret = nr; - break; - } - ret += nr; - if (nr != len) - break; - } out: if (iov != iovstack) kfree(iov); @@ -1294,7 +1272,7 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign goto out; ret = -EINVAL; - if (!file->f_op || (!file->f_op->readv && !file->f_op->read)) + if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) goto out; ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos); @@ -1317,7 +1295,7 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig goto out; ret = -EINVAL; - if (!file->f_op || (!file->f_op->writev && !file->f_op->write)) + if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) goto out; ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index e8bbed9dd26..e893e2be9ed 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -53,8 +53,6 @@ const struct file_operations ext2_file_operations = { .open = generic_file_open, .release = ext2_release_file, .fsync = ext2_sync_file, - .readv = generic_file_readv, - .writev = generic_file_writev, .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 5c762457bc8..e96c388047e 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -112,8 +112,6 @@ const struct file_operations ext3_file_operations = { .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = ext3_file_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .ioctl = ext3_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext3_compat_ioctl, diff --git a/fs/fat/file.c b/fs/fat/file.c index d50fc47169c..f4b8f8b3fbd 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -127,8 +127,6 @@ const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4fc557c40cc..66571eafbb1 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -680,14 +680,15 @@ static int fuse_read_interrupt(struct fuse_conn *fc, struct fuse_req *req, * request_end(). Otherwise add it to the processing list, and set * the 'sent' flag. */ -static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *off) +static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int err; struct fuse_req *req; struct fuse_in *in; struct fuse_copy_state cs; unsigned reqsize; + struct file *file = iocb->ki_filp; struct fuse_conn *fc = fuse_get_conn(file); if (!fc) return -EPERM; @@ -761,15 +762,6 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, return err; } -static ssize_t fuse_dev_read(struct file *file, char __user *buf, - size_t nbytes, loff_t *off) -{ - struct iovec iov; - iov.iov_len = nbytes; - iov.iov_base = buf; - return fuse_dev_readv(file, &iov, 1, off); -} - /* Look up request on processing list by unique ID */ static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique) { @@ -814,15 +806,15 @@ static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out, * it from the list and copy the rest of the buffer to the request. * The request is finished by calling request_end() */ -static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *off) +static ssize_t fuse_dev_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int err; unsigned nbytes = iov_length(iov, nr_segs); struct fuse_req *req; struct fuse_out_header oh; struct fuse_copy_state cs; - struct fuse_conn *fc = fuse_get_conn(file); + struct fuse_conn *fc = fuse_get_conn(iocb->ki_filp); if (!fc) return -EPERM; @@ -898,15 +890,6 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, return err; } -static ssize_t fuse_dev_write(struct file *file, const char __user *buf, - size_t nbytes, loff_t *off) -{ - struct iovec iov; - iov.iov_len = nbytes; - iov.iov_base = (char __user *) buf; - return fuse_dev_writev(file, &iov, 1, off); -} - static unsigned fuse_dev_poll(struct file *file, poll_table *wait) { unsigned mask = POLLOUT | POLLWRNORM; @@ -1041,10 +1024,10 @@ static int fuse_dev_fasync(int fd, struct file *file, int on) const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, .llseek = no_llseek, - .read = fuse_dev_read, - .readv = fuse_dev_readv, - .write = fuse_dev_write, - .writev = fuse_dev_writev, + .read = do_sync_read, + .aio_read = fuse_dev_read, + .write = do_sync_write, + .aio_write = fuse_dev_write, .poll = fuse_dev_poll, .release = fuse_dev_release, .fasync = fuse_dev_fasync, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 322e876c35e..4908c38a588 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -389,8 +389,6 @@ static const struct file_operations hostfs_file_fops = { .sendfile = generic_file_sendfile, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .write = generic_file_write, .mmap = generic_file_mmap, .open = hostfs_file_open, diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 1c9745be5ad..f535f2911c1 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -108,8 +108,6 @@ const struct file_operations jfs_file_operations = { .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .readv = generic_file_readv, - .writev = generic_file_writev, .sendfile = generic_file_sendfile, .fsync = jfs_fsync, .release = jfs_release, diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 0c46f5c86b7..2f9b5a0953f 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2298,11 +2298,9 @@ const struct file_operations ntfs_file_ops = { .llseek = generic_file_llseek, /* Seek inside file. */ .read = generic_file_read, /* Read from file. */ .aio_read = generic_file_aio_read, /* Async read from file. */ - .readv = generic_file_readv, /* Read from file. */ #ifdef NTFS_RW .write = ntfs_file_write, /* Write to file. */ .aio_write = ntfs_file_aio_write, /* Async write to file. */ - .writev = ntfs_file_writev, /* Write to file. */ /*.release = ,*/ /* Last file is closed. See fs/ext2/file.c:: ext2_release_file() for diff --git a/fs/pipe.c b/fs/pipe.c index f3b6f71e9d0..2e60e1c8815 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -218,9 +218,10 @@ static struct pipe_buf_operations anon_pipe_buf_ops = { }; static ssize_t -pipe_readv(struct file *filp, const struct iovec *_iov, - unsigned long nr_segs, loff_t *ppos) +pipe_read(struct kiocb *iocb, const struct iovec *_iov, + unsigned long nr_segs, loff_t pos) { + struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; struct pipe_inode_info *pipe; int do_wakeup; @@ -330,17 +331,10 @@ redo: } static ssize_t -pipe_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec iov = { .iov_base = buf, .iov_len = count }; - - return pipe_readv(filp, &iov, 1, ppos); -} - -static ssize_t -pipe_writev(struct file *filp, const struct iovec *_iov, - unsigned long nr_segs, loff_t *ppos) +pipe_write(struct kiocb *iocb, const struct iovec *_iov, + unsigned long nr_segs, loff_t ppos) { + struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; struct pipe_inode_info *pipe; ssize_t ret; @@ -509,15 +503,6 @@ out: return ret; } -static ssize_t -pipe_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return pipe_writev(filp, &iov, 1, ppos); -} - static ssize_t bad_pipe_r(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { @@ -736,8 +721,8 @@ pipe_rdwr_open(struct inode *inode, struct file *filp) */ const struct file_operations read_fifo_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, + .read = do_sync_read, + .aio_read = pipe_read, .write = bad_pipe_w, .poll = pipe_poll, .ioctl = pipe_ioctl, @@ -749,8 +734,8 @@ const struct file_operations read_fifo_fops = { const struct file_operations write_fifo_fops = { .llseek = no_llseek, .read = bad_pipe_r, - .write = pipe_write, - .writev = pipe_writev, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_write_open, @@ -760,10 +745,10 @@ const struct file_operations write_fifo_fops = { const struct file_operations rdwr_fifo_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, - .write = pipe_write, - .writev = pipe_writev, + .read = do_sync_read, + .aio_read = pipe_read, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_rdwr_open, @@ -773,8 +758,8 @@ const struct file_operations rdwr_fifo_fops = { static struct file_operations read_pipe_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, + .read = do_sync_read, + .aio_read = pipe_read, .write = bad_pipe_w, .poll = pipe_poll, .ioctl = pipe_ioctl, @@ -786,8 +771,8 @@ static struct file_operations read_pipe_fops = { static struct file_operations write_pipe_fops = { .llseek = no_llseek, .read = bad_pipe_r, - .write = pipe_write, - .writev = pipe_writev, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_write_open, @@ -797,10 +782,10 @@ static struct file_operations write_pipe_fops = { static struct file_operations rdwr_pipe_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, - .write = pipe_write, - .writev = pipe_writev, + .read = do_sync_read, + .aio_read = pipe_read, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_rdwr_open, diff --git a/fs/read_write.c b/fs/read_write.c index 679dd535380..32d54cca9bd 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -15,6 +15,7 @@ #include #include #include +#include "read_write.h" #include #include @@ -450,6 +451,62 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_UNUSED_SYMBOL(iov_shorten); /* June 2006 */ +ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, + unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn) +{ + struct kiocb kiocb; + ssize_t ret; + + init_sync_kiocb(&kiocb, filp); + kiocb.ki_pos = *ppos; + kiocb.ki_left = len; + kiocb.ki_nbytes = len; + + for (;;) { + ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; + wait_on_retry_sync_kiocb(&kiocb); + } + + if (ret == -EIOCBQUEUED) + ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; + return ret; +} + +/* Do it by hand, with file-ops */ +ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, + unsigned long nr_segs, loff_t *ppos, io_fn_t fn) +{ + struct iovec *vector = iov; + ssize_t ret = 0; + + while (nr_segs > 0) { + void __user *base; + size_t len; + ssize_t nr; + + base = vector->iov_base; + len = vector->iov_len; + vector++; + nr_segs--; + + nr = fn(filp, base, len, ppos); + + if (nr < 0) { + if (!ret) + ret = nr; + break; + } + ret += nr; + if (nr != len) + break; + } + + return ret; +} + /* A write operation does a read from user space and vice versa */ #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) @@ -457,12 +514,9 @@ static ssize_t do_readv_writev(int type, struct file *file, const struct iovec __user * uvector, unsigned long nr_segs, loff_t *pos) { - typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); - typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *); - size_t tot_len; struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov=iovstack, *vector; + struct iovec *iov = iovstack; ssize_t ret; int seg; io_fn_t fn; @@ -532,39 +586,18 @@ static ssize_t do_readv_writev(int type, struct file *file, fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->readv; + fnv = file->f_op->aio_read; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->writev; - } - if (fnv) { - ret = fnv(file, iov, nr_segs, pos); - goto out; + fnv = file->f_op->aio_write; } - /* Do it by hand, with file-ops */ - ret = 0; - vector = iov; - while (nr_segs > 0) { - void __user * base; - size_t len; - ssize_t nr; - - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(file, base, len, pos); + if (fnv) + ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, + pos, fnv); + else + ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); - if (nr < 0) { - if (!ret) ret = nr; - break; - } - ret += nr; - if (nr != len) - break; - } out: if (iov != iovstack) kfree(iov); @@ -585,7 +618,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_READ)) return -EBADF; - if (!file->f_op || (!file->f_op->readv && !file->f_op->read)) + if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) return -EINVAL; return do_readv_writev(READ, file, vec, vlen, pos); @@ -598,7 +631,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_WRITE)) return -EBADF; - if (!file->f_op || (!file->f_op->writev && !file->f_op->write)) + if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) return -EINVAL; return do_readv_writev(WRITE, file, vec, vlen, pos); diff --git a/fs/read_write.h b/fs/read_write.h new file mode 100644 index 00000000000..d07b954c6e0 --- /dev/null +++ b/fs/read_write.h @@ -0,0 +1,14 @@ +/* + * This file is only for sharing some helpers from read_write.c with compat.c. + * Don't use anywhere else. + */ + + +typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); +typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *, + unsigned long, loff_t); + +ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, + unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn); +ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, + unsigned long nr_segs, loff_t *ppos, io_fn_t fn); diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 4737971c6a3..d93d8dd1958 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -123,96 +123,6 @@ xfs_file_aio_write_invis( return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } -STATIC inline ssize_t -__xfs_file_readv( - struct file *file, - const struct iovec *iov, - int ioflags, - unsigned long nr_segs, - loff_t *ppos) -{ - struct inode *inode = file->f_mapping->host; - bhv_vnode_t *vp = vn_from_inode(inode); - struct kiocb kiocb; - ssize_t rval; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - - if (unlikely(file->f_flags & O_DIRECT)) - ioflags |= IO_ISDIRECT; - rval = bhv_vop_read(vp, &kiocb, iov, nr_segs, - &kiocb.ki_pos, ioflags, NULL); - - *ppos = kiocb.ki_pos; - return rval; -} - -STATIC ssize_t -xfs_file_readv( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_readv(file, iov, 0, nr_segs, ppos); -} - -STATIC ssize_t -xfs_file_readv_invis( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_readv(file, iov, IO_INVIS, nr_segs, ppos); -} - -STATIC inline ssize_t -__xfs_file_writev( - struct file *file, - const struct iovec *iov, - int ioflags, - unsigned long nr_segs, - loff_t *ppos) -{ - struct inode *inode = file->f_mapping->host; - bhv_vnode_t *vp = vn_from_inode(inode); - struct kiocb kiocb; - ssize_t rval; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - if (unlikely(file->f_flags & O_DIRECT)) - ioflags |= IO_ISDIRECT; - - rval = bhv_vop_write(vp, &kiocb, iov, nr_segs, - &kiocb.ki_pos, ioflags, NULL); - - *ppos = kiocb.ki_pos; - return rval; -} - -STATIC ssize_t -xfs_file_writev( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_writev(file, iov, 0, nr_segs, ppos); -} - -STATIC ssize_t -xfs_file_writev_invis( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_writev(file, iov, IO_INVIS, nr_segs, ppos); -} - STATIC ssize_t xfs_file_sendfile( struct file *filp, @@ -540,8 +450,6 @@ const struct file_operations xfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = xfs_file_readv, - .writev = xfs_file_writev, .aio_read = xfs_file_aio_read, .aio_write = xfs_file_aio_write, .sendfile = xfs_file_sendfile, @@ -565,8 +473,6 @@ const struct file_operations xfs_invis_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = xfs_file_readv_invis, - .writev = xfs_file_writev_invis, .aio_read = xfs_file_aio_read_invis, .aio_write = xfs_file_aio_write_invis, .sendfile = xfs_file_sendfile_invis, diff --git a/include/linux/fs.h b/include/linux/fs.h index 257bae16f54..afb6e6f89a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1113,8 +1113,6 @@ struct file_operations { int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *); ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -1734,10 +1732,6 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); -ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); extern loff_t remote_llseek(struct file *file, loff_t offset, int origin); diff --git a/mm/filemap.c b/mm/filemap.c index f6c1d22b504..48497094ae8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2421,42 +2421,6 @@ ssize_t generic_file_write(struct file *file, const char __user *buf, } EXPORT_SYMBOL(generic_file_write); -ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_readv); - -ssize_t generic_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, iov, nr_segs, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_writev); - /* * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something * went wrong during pagecache shootdown. diff --git a/net/socket.c b/net/socket.c index df92e425274..01918f7a301 100644 --- a/net/socket.c +++ b/net/socket.c @@ -110,10 +110,6 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); -static ssize_t sock_readv(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); -static ssize_t sock_writev(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more); @@ -136,8 +132,6 @@ static struct file_operations socket_file_ops = { .open = sock_no_open, /* special open code to disallow open via /proc */ .release = sock_close, .fasync = sock_fasync, - .readv = sock_readv, - .writev = sock_writev, .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, }; @@ -700,23 +694,6 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags); } -static ssize_t sock_readv(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb iocb; - struct sock_iocb siocb; - struct msghdr msg; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_read(&msg, &iocb, file, iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -759,23 +736,6 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, return __sock_sendmsg(iocb, sock, msg, size); } -static ssize_t sock_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct msghdr msg; - struct kiocb iocb; - struct sock_iocb siocb; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_write(&msg, &iocb, file, iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 891d7140553..37b4b10850a 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2852,8 +2852,8 @@ static ssize_t snd_pcm_write(struct file *file, const char __user *buf, return result; } -static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, - unsigned long count, loff_t * offset) +static ssize_t snd_pcm_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct snd_pcm_file *pcm_file; @@ -2864,22 +2864,22 @@ static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, void __user **bufs; snd_pcm_uframes_t frames; - pcm_file = file->private_data; + pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; snd_assert(substream != NULL, return -ENXIO); runtime = substream->runtime; if (runtime->status->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; - if (count > 1024 || count != runtime->channels) + if (nr_segs > 1024 || nr_segs != runtime->channels) return -EINVAL; - if (!frame_aligned(runtime, _vector->iov_len)) + if (!frame_aligned(runtime, iov->iov_len)) return -EINVAL; - frames = bytes_to_samples(runtime, _vector->iov_len); - bufs = kmalloc(sizeof(void *) * count, GFP_KERNEL); + frames = bytes_to_samples(runtime, iov->iov_len); + bufs = kmalloc(sizeof(void *) * nr_segs, GFP_KERNEL); if (bufs == NULL) return -ENOMEM; - for (i = 0; i < count; ++i) - bufs[i] = _vector[i].iov_base; + for (i = 0; i < nr_segs; ++i) + bufs[i] = iov[i].iov_base; result = snd_pcm_lib_readv(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); @@ -2887,8 +2887,8 @@ static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, return result; } -static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, - unsigned long count, loff_t * offset) +static ssize_t snd_pcm_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; @@ -2898,7 +2898,7 @@ static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, void __user **bufs; snd_pcm_uframes_t frames; - pcm_file = file->private_data; + pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; snd_assert(substream != NULL, result = -ENXIO; goto end); runtime = substream->runtime; @@ -2906,17 +2906,17 @@ static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, result = -EBADFD; goto end; } - if (count > 128 || count != runtime->channels || - !frame_aligned(runtime, _vector->iov_len)) { + if (nr_segs > 128 || nr_segs != runtime->channels || + !frame_aligned(runtime, iov->iov_len)) { result = -EINVAL; goto end; } - frames = bytes_to_samples(runtime, _vector->iov_len); - bufs = kmalloc(sizeof(void *) * count, GFP_KERNEL); + frames = bytes_to_samples(runtime, iov->iov_len); + bufs = kmalloc(sizeof(void *) * nr_segs, GFP_KERNEL); if (bufs == NULL) return -ENOMEM; - for (i = 0; i < count; ++i) - bufs[i] = _vector[i].iov_base; + for (i = 0; i < nr_segs; ++i) + bufs[i] = iov[i].iov_base; result = snd_pcm_lib_writev(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); @@ -3426,7 +3426,7 @@ struct file_operations snd_pcm_f_ops[2] = { { .owner = THIS_MODULE, .write = snd_pcm_write, - .writev = snd_pcm_writev, + .aio_write = snd_pcm_aio_write, .open = snd_pcm_playback_open, .release = snd_pcm_release, .poll = snd_pcm_playback_poll, @@ -3438,7 +3438,7 @@ struct file_operations snd_pcm_f_ops[2] = { { .owner = THIS_MODULE, .read = snd_pcm_read, - .readv = snd_pcm_readv, + .aio_read = snd_pcm_aio_read, .open = snd_pcm_capture_open, .release = snd_pcm_release, .poll = snd_pcm_capture_poll, -- cgit v1.2.3 From 543ade1fc901db4c3dbe9fb27241fb977f1f3eea Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:48 -0700 Subject: [PATCH] Streamline generic_file_* interfaces and filemap cleanups This patch cleans up generic_file_*_read/write() interfaces. Christoph Hellwig gave me the idea for this clean ups. In a nutshell, all filesystems should set .aio_read/.aio_write methods and use do_sync_read/ do_sync_write() as their .read/.write methods. This allows us to cleanup all variants of generic_file_* routines. Final available interfaces: generic_file_aio_read() - read handler generic_file_aio_write() - write handler generic_file_aio_write_nolock() - no lock write handler __generic_file_aio_write_nolock() - internal worker routine Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/raw.c | 15 ++------ fs/adfs/file.c | 6 ++-- fs/affs/file.c | 6 ++-- fs/bfs/file.c | 6 ++-- fs/block_dev.c | 12 ++----- fs/ext2/file.c | 4 +-- fs/fuse/file.c | 6 ++-- fs/hfs/inode.c | 6 ++-- fs/hfsplus/inode.c | 6 ++-- fs/hostfs/hostfs_kern.c | 4 +-- fs/hpfs/file.c | 6 ++-- fs/jffs/inode-v23.c | 6 ++-- fs/jffs2/file.c | 6 ++-- fs/jfs/file.c | 4 +-- fs/minix/file.c | 6 ++-- fs/ntfs/file.c | 2 +- fs/qnx4/file.c | 6 ++-- fs/ramfs/file-mmu.c | 6 ++-- fs/ramfs/file-nommu.c | 6 ++-- fs/read_write.c | 3 +- fs/smbfs/file.c | 24 ++++++++----- fs/sysv/file.c | 6 ++-- fs/udf/file.c | 16 +++++---- fs/ufs/file.c | 6 ++-- fs/xfs/linux-2.6/xfs_lrw.c | 4 ++- include/linux/fs.h | 5 --- mm/filemap.c | 87 +++------------------------------------------- 27 files changed, 105 insertions(+), 165 deletions(-) (limited to 'mm/filemap.c') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 490db531e2d..89b718e326e 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -238,21 +238,10 @@ out: return err; } -static ssize_t raw_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec local_iov = { - .iov_base = (char __user *)buf, - .iov_len = count - }; - - return generic_file_write_nolock(file, &local_iov, 1, ppos); -} - static const struct file_operations raw_fops = { - .read = generic_file_read, + .read = do_sync_read, .aio_read = generic_file_aio_read, - .write = raw_file_write, + .write = do_sync_write, .aio_write = generic_file_aio_write_nolock, .open = raw_open, .release= raw_release, diff --git a/fs/adfs/file.c b/fs/adfs/file.c index 1014b9f2117..6101ea679cb 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -27,10 +27,12 @@ const struct file_operations adfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, .fsync = file_fsync, - .write = generic_file_write, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .sendfile = generic_file_sendfile, }; diff --git a/fs/affs/file.c b/fs/affs/file.c index 3de8590e4f6..05b5e22de75 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -27,8 +27,10 @@ static int affs_file_release(struct inode *inode, struct file *filp); const struct file_operations affs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .open = affs_file_open, .release = affs_file_release, diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 3d5aca28a0a..a9164a87f8d 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -19,8 +19,10 @@ const struct file_operations bfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, }; diff --git a/fs/block_dev.c b/fs/block_dev.c index 0f143094ef1..bc8f27cc448 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1154,14 +1154,6 @@ static int blkdev_close(struct inode * inode, struct file * filp) return blkdev_put(bdev); } -static ssize_t blkdev_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return generic_file_write_nolock(file, &local_iov, 1, ppos); -} - static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); @@ -1181,8 +1173,8 @@ const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, - .read = generic_file_read, - .write = blkdev_file_write, + .read = do_sync_read, + .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write_nolock, .mmap = generic_file_mmap, diff --git a/fs/ext2/file.c b/fs/ext2/file.c index e893e2be9ed..2dba473c524 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -41,8 +41,8 @@ static int ext2_release_file (struct inode * inode, struct file * filp) */ const struct file_operations ext2_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .ioctl = ext2_ioctl, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5c4fcd1dbf5..183626868ee 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -753,8 +753,10 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl) static const struct file_operations fuse_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = fuse_file_mmap, .open = fuse_open, .flush = fuse_flush, diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index d05641c35fc..02f5573e034 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -601,8 +601,10 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) static const struct file_operations hfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, .fsync = file_fsync, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 0eb1a609266..9e367524963 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -282,8 +282,10 @@ static struct inode_operations hfsplus_file_inode_operations = { static const struct file_operations hfsplus_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, .fsync = file_fsync, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 4908c38a588..b6bd33ca373 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -385,11 +385,11 @@ int hostfs_fsync(struct file *file, struct dentry *dentry, int datasync) static const struct file_operations hostfs_file_fops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, .sendfile = generic_file_sendfile, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, - .write = generic_file_write, + .write = do_sync_write, .mmap = generic_file_mmap, .open = hostfs_file_open, .release = NULL, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index d9eb19b7b8a..8b94d24855f 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -113,7 +113,7 @@ static ssize_t hpfs_file_write(struct file *file, const char __user *buf, { ssize_t retval; - retval = generic_file_write(file, buf, count, ppos); + retval = do_sync_write(file, buf, count, ppos); if (retval > 0) hpfs_i(file->f_dentry->d_inode)->i_dirty = 1; return retval; @@ -122,8 +122,10 @@ static ssize_t hpfs_file_write(struct file *file, const char __user *buf, const struct file_operations hpfs_file_ops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .write = hpfs_file_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .release = hpfs_file_release, .fsync = hpfs_file_fsync, diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index f5cf9c93e24..068ef0de8de 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -1632,8 +1632,10 @@ static const struct file_operations jffs_file_operations = { .open = generic_file_open, .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .ioctl = jffs_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs_fsync, diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 3ed6e3e120b..242875f77cb 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -42,8 +42,10 @@ const struct file_operations jffs2_file_operations = { .llseek = generic_file_llseek, .open = generic_file_open, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .ioctl = jffs2_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs2_fsync, diff --git a/fs/jfs/file.c b/fs/jfs/file.c index f535f2911c1..976e90dc2d1 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -103,8 +103,8 @@ struct inode_operations jfs_file_inode_operations = { const struct file_operations jfs_file_operations = { .open = jfs_open, .llseek = generic_file_llseek, - .write = generic_file_write, - .read = generic_file_read, + .write = do_sync_write, + .read = do_sync_read, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, diff --git a/fs/minix/file.c b/fs/minix/file.c index 420b32882a1..40eac2e60d2 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -17,8 +17,10 @@ int minix_sync_file(struct file *, struct dentry *, int); const struct file_operations minix_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = minix_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 2f9b5a0953f..ae2fe0016d2 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2296,7 +2296,7 @@ static int ntfs_file_fsync(struct file *filp, struct dentry *dentry, const struct file_operations ntfs_file_ops = { .llseek = generic_file_llseek, /* Seek inside file. */ - .read = generic_file_read, /* Read from file. */ + .read = do_sync_read, /* Read from file. */ .aio_read = generic_file_aio_read, /* Async read from file. */ #ifdef NTFS_RW .write = ntfs_file_write, /* Write to file. */ diff --git a/fs/qnx4/file.c b/fs/qnx4/file.c index 62af4b1348b..467e5ac7280 100644 --- a/fs/qnx4/file.c +++ b/fs/qnx4/file.c @@ -22,11 +22,13 @@ const struct file_operations qnx4_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, #ifdef CONFIG_QNX4FS_RW - .write = generic_file_write, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .fsync = qnx4_sync_file, #endif }; diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 86f14cacf64..0947fb57dcf 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -33,8 +33,10 @@ const struct address_space_operations ramfs_aops = { }; const struct file_operations ramfs_file_operations = { - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = simple_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 677139b48e0..bfe5dbf1002 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -36,8 +36,10 @@ const struct address_space_operations ramfs_aops = { const struct file_operations ramfs_file_operations = { .mmap = ramfs_nommu_mmap, .get_unmapped_area = ramfs_nommu_get_unmapped_area, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .fsync = simple_sync_file, .sendfile = generic_file_sendfile, .llseek = generic_file_llseek, diff --git a/fs/read_write.c b/fs/read_write.c index 32d54cca9bd..4ed839bcb91 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -22,7 +22,8 @@ const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_readonly_mmap, .sendfile = generic_file_sendfile, }; diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c index dae67048bab..50784d13c87 100644 --- a/fs/smbfs/file.c +++ b/fs/smbfs/file.c @@ -214,13 +214,15 @@ smb_updatepage(struct file *file, struct page *page, unsigned long offset, } static ssize_t -smb_file_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) +smb_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { + struct file * file = iocb->ki_filp; struct dentry * dentry = file->f_dentry; ssize_t status; VERBOSE("file %s/%s, count=%lu@%lu\n", DENTRY_PATH(dentry), - (unsigned long) count, (unsigned long) *ppos); + (unsigned long) iocb->ki_left, (unsigned long) pos); status = smb_revalidate_inode(dentry); if (status) { @@ -233,7 +235,7 @@ smb_file_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) (long)dentry->d_inode->i_size, dentry->d_inode->i_flags, dentry->d_inode->i_atime); - status = generic_file_read(file, buf, count, ppos); + status = generic_file_aio_read(iocb, iov, nr_segs, pos); out: return status; } @@ -317,14 +319,16 @@ const struct address_space_operations smb_file_aops = { * Write to a file (through the page cache). */ static ssize_t -smb_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +smb_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { + struct file * file = iocb->ki_filp; struct dentry * dentry = file->f_dentry; ssize_t result; VERBOSE("file %s/%s, count=%lu@%lu\n", DENTRY_PATH(dentry), - (unsigned long) count, (unsigned long) *ppos); + (unsigned long) iocb->ki_left, (unsigned long) pos); result = smb_revalidate_inode(dentry); if (result) { @@ -337,8 +341,8 @@ smb_file_write(struct file *file, const char __user *buf, size_t count, loff_t * if (result) goto out; - if (count > 0) { - result = generic_file_write(file, buf, count, ppos); + if (iocb->ki_left > 0) { + result = generic_file_aio_write(iocb, iov, nr_segs, pos); VERBOSE("pos=%ld, size=%ld, mtime=%ld, atime=%ld\n", (long) file->f_pos, (long) dentry->d_inode->i_size, dentry->d_inode->i_mtime, dentry->d_inode->i_atime); @@ -402,8 +406,10 @@ smb_file_permission(struct inode *inode, int mask, struct nameidata *nd) const struct file_operations smb_file_operations = { .llseek = remote_llseek, - .read = smb_file_read, - .write = smb_file_write, + .read = do_sync_read, + .aio_read = smb_file_aio_read, + .write = do_sync_write, + .aio_write = smb_file_aio_write, .ioctl = smb_ioctl, .mmap = smb_file_mmap, .open = smb_file_open, diff --git a/fs/sysv/file.c b/fs/sysv/file.c index a59e303135f..47a4b728f15 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -21,8 +21,10 @@ */ const struct file_operations sysv_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = sysv_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/udf/file.c b/fs/udf/file.c index a59e5f33daf..7aedd552cba 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -103,19 +103,21 @@ const struct address_space_operations udf_adinicb_aops = { .commit_write = udf_adinicb_commit_write, }; -static ssize_t udf_file_write(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t ppos) { ssize_t retval; + struct file *file = iocb->ki_filp; struct inode *inode = file->f_dentry->d_inode; int err, pos; + size_t count = iocb->ki_left; if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_IN_ICB) { if (file->f_flags & O_APPEND) pos = inode->i_size; else - pos = *ppos; + pos = ppos; if (inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + pos + count)) @@ -136,7 +138,7 @@ static ssize_t udf_file_write(struct file * file, const char __user * buf, } } - retval = generic_file_write(file, buf, count, ppos); + retval = generic_file_aio_write(iocb, iov, nr_segs, ppos); if (retval > 0) mark_inode_dirty(inode); @@ -249,11 +251,13 @@ static int udf_release_file(struct inode * inode, struct file * filp) } const struct file_operations udf_file_operations = { - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .ioctl = udf_ioctl, .open = generic_file_open, .mmap = generic_file_mmap, - .write = udf_file_write, + .write = do_sync_write, + .aio_write = udf_file_aio_write, .release = udf_release_file, .fsync = udf_fsync_file, .sendfile = generic_file_sendfile, diff --git a/fs/ufs/file.c b/fs/ufs/file.c index a9c6e5f04fa..1e096323bad 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -53,8 +53,10 @@ static int ufs_sync_file(struct file *file, struct dentry *dentry, int datasync) const struct file_operations ufs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .open = generic_file_open, .fsync = ufs_sync_file, diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index 55992b40353..fa842f1c9fa 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -279,7 +279,9 @@ xfs_read( xfs_rw_enter_trace(XFS_READ_ENTER, &ip->i_iocore, (void *)iovp, segs, *offset, ioflags); - ret = __generic_file_aio_read(iocb, iovp, segs, offset); + + iocb->ki_pos = *offset; + ret = generic_file_aio_read(iocb, iovp, segs, *offset); if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO)) ret = wait_on_sync_kiocb(iocb); if (ret > 0) diff --git a/include/linux/fs.h b/include/linux/fs.h index afb6e6f89a0..011129f8803 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1699,11 +1699,8 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); -extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, unsigned long, loff_t); @@ -1713,8 +1710,6 @@ extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, unsigned long, loff_t, loff_t *, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); -ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); extern void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *, struct file *, diff --git a/mm/filemap.c b/mm/filemap.c index 48497094ae8..ec469235985 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1149,13 +1149,14 @@ success: * that can use the page cache directly. */ ssize_t -__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; ssize_t retval; unsigned long seg; size_t count; + loff_t *ppos = &iocb->ki_pos; count = 0; for (seg = 0; seg < nr_segs; seg++) { @@ -1179,7 +1180,7 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { - loff_t pos = *ppos, size; + loff_t size; struct address_space *mapping; struct inode *inode; @@ -1223,32 +1224,8 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, out: return retval; } -EXPORT_SYMBOL(__generic_file_aio_read); - -ssize_t -generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - BUG_ON(iocb->ki_pos != pos); - return __generic_file_aio_read(iocb, iov, nr_segs, &iocb->ki_pos); -} EXPORT_SYMBOL(generic_file_aio_read); -ssize_t -generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_read); - int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size) { ssize_t written; @@ -2339,38 +2316,6 @@ ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, } EXPORT_SYMBOL(generic_file_aio_write_nolock); -static ssize_t -__generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} - -ssize_t -generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, *ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - *ppos = kiocb.ki_pos; - return ret; -} -EXPORT_SYMBOL(generic_file_write_nolock); - ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -2397,30 +2342,6 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } EXPORT_SYMBOL(generic_file_aio_write); -ssize_t generic_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, &local_iov, 1, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - ssize_t err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_write); - /* * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something * went wrong during pagecache shootdown. -- cgit v1.2.3