diff options
Diffstat (limited to 'fs')
65 files changed, 406 insertions, 1954 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 47af46a573ba..a6313a969bc5 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -367,7 +367,7 @@ source "fs/ceph/Kconfig" source "fs/cifs/Kconfig" source "fs/ksmbd/Kconfig" -config CIFS_COMMON +config SMBFS_COMMON tristate default y if CIFS=y default m if CIFS=m diff --git a/fs/Makefile b/fs/Makefile index 2f21300851ae..84c5e4cdfee5 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -17,7 +17,7 @@ obj-y := open.o read_write.o file_table.o super.o \ kernel_read_file.o remap_range.o ifeq ($(CONFIG_BLOCK),y) -obj-y += buffer.o block_dev.o direct-io.o mpage.o +obj-y += buffer.o direct-io.o mpage.o else obj-y += no-block.o endif @@ -96,7 +96,7 @@ obj-$(CONFIG_LOCKD) += lockd/ obj-$(CONFIG_NLS) += nls/ obj-$(CONFIG_UNICODE) += unicode/ obj-$(CONFIG_SYSV_FS) += sysv/ -obj-$(CONFIG_CIFS_COMMON) += cifs_common/ +obj-$(CONFIG_SMBFS_COMMON) += smbfs_common/ obj-$(CONFIG_CIFS) += cifs/ obj-$(CONFIG_SMB_SERVER) += ksmbd/ obj-$(CONFIG_HPFS_FS) += hpfs/ diff --git a/fs/block_dev.c b/fs/block_dev.c deleted file mode 100644 index 45df6cbccf12..000000000000 --- a/fs/block_dev.c +++ /dev/null @@ -1,1695 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE - * Copyright (C) 2016 - 2020 Christoph Hellwig - */ - -#include <linux/init.h> -#include <linux/mm.h> -#include <linux/fcntl.h> -#include <linux/slab.h> -#include <linux/kmod.h> -#include <linux/major.h> -#include <linux/device_cgroup.h> -#include <linux/highmem.h> -#include <linux/blkdev.h> -#include <linux/backing-dev.h> -#include <linux/module.h> -#include <linux/blkpg.h> -#include <linux/magic.h> -#include <linux/buffer_head.h> -#include <linux/swap.h> -#include <linux/pagevec.h> -#include <linux/writeback.h> -#include <linux/mpage.h> -#include <linux/mount.h> -#include <linux/pseudo_fs.h> -#include <linux/uio.h> -#include <linux/namei.h> -#include <linux/log2.h> -#include <linux/cleancache.h> -#include <linux/task_io_accounting_ops.h> -#include <linux/falloc.h> -#include <linux/part_stat.h> -#include <linux/uaccess.h> -#include <linux/suspend.h> -#include "internal.h" -#include "../block/blk.h" - -struct bdev_inode { - struct block_device bdev; - struct inode vfs_inode; -}; - -static const struct address_space_operations def_blk_aops; - -static inline struct bdev_inode *BDEV_I(struct inode *inode) -{ - return container_of(inode, struct bdev_inode, vfs_inode); -} - -struct block_device *I_BDEV(struct inode *inode) -{ - return &BDEV_I(inode)->bdev; -} -EXPORT_SYMBOL(I_BDEV); - -static void bdev_write_inode(struct block_device *bdev) -{ - struct inode *inode = bdev->bd_inode; - int ret; - - spin_lock(&inode->i_lock); - while (inode->i_state & I_DIRTY) { - spin_unlock(&inode->i_lock); - ret = write_inode_now(inode, true); - if (ret) { - char name[BDEVNAME_SIZE]; - pr_warn_ratelimited("VFS: Dirty inode writeback failed " - "for block device %s (err=%d).\n", - bdevname(bdev, name), ret); - } - spin_lock(&inode->i_lock); - } - spin_unlock(&inode->i_lock); -} - -/* Kill _all_ buffers and pagecache , dirty or not.. */ -static void kill_bdev(struct block_device *bdev) -{ - struct address_space *mapping = bdev->bd_inode->i_mapping; - - if (mapping_empty(mapping)) - return; - - invalidate_bh_lrus(); - truncate_inode_pages(mapping, 0); -} - -/* Invalidate clean unused buffers and pagecache. */ -void invalidate_bdev(struct block_device *bdev) -{ - struct address_space *mapping = bdev->bd_inode->i_mapping; - - if (mapping->nrpages) { - invalidate_bh_lrus(); - lru_add_drain_all(); /* make sure all lru add caches are flushed */ - invalidate_mapping_pages(mapping, 0, -1); - } - /* 99% of the time, we don't need to flush the cleancache on the bdev. - * But, for the strange corners, lets be cautious - */ - cleancache_invalidate_inode(mapping); -} -EXPORT_SYMBOL(invalidate_bdev); - -/* - * Drop all buffers & page cache for given bdev range. This function bails - * with error if bdev has other exclusive owner (such as filesystem). - */ -int truncate_bdev_range(struct block_device *bdev, fmode_t mode, - loff_t lstart, loff_t lend) -{ - /* - * If we don't hold exclusive handle for the device, upgrade to it - * while we discard the buffer cache to avoid discarding buffers - * under live filesystem. - */ - if (!(mode & FMODE_EXCL)) { - int err = bd_prepare_to_claim(bdev, truncate_bdev_range); - if (err) - goto invalidate; - } - - truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); - if (!(mode & FMODE_EXCL)) - bd_abort_claiming(bdev, truncate_bdev_range); - return 0; - -invalidate: - /* - * Someone else has handle exclusively open. Try invalidating instead. - * The 'end' argument is inclusive so the rounding is safe. - */ - return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, - lstart >> PAGE_SHIFT, - lend >> PAGE_SHIFT); -} - -static void set_init_blocksize(struct block_device *bdev) -{ - unsigned int bsize = bdev_logical_block_size(bdev); - loff_t size = i_size_read(bdev->bd_inode); - - while (bsize < PAGE_SIZE) { - if (size & bsize) - break; - bsize <<= 1; - } - bdev->bd_inode->i_blkbits = blksize_bits(bsize); -} - -int set_blocksize(struct block_device *bdev, int size) -{ - /* Size must be a power of two, and between 512 and PAGE_SIZE */ - if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) - return -EINVAL; - - /* Size cannot be smaller than the size supported by the device */ - if (size < bdev_logical_block_size(bdev)) - return -EINVAL; - - /* Don't change the size if it is same as current */ - if (bdev->bd_inode->i_blkbits != blksize_bits(size)) { - sync_blockdev(bdev); - bdev->bd_inode->i_blkbits = blksize_bits(size); - kill_bdev(bdev); - } - return 0; -} - -EXPORT_SYMBOL(set_blocksize); - -int sb_set_blocksize(struct super_block *sb, int size) -{ - if (set_blocksize(sb->s_bdev, size)) - return 0; - /* If we get here, we know size is power of two - * and it's value is between 512 and PAGE_SIZE */ - sb->s_blocksize = size; - sb->s_blocksize_bits = blksize_bits(size); - return sb->s_blocksize; -} - -EXPORT_SYMBOL(sb_set_blocksize); - -int sb_min_blocksize(struct super_block *sb, int size) -{ - int minsize = bdev_logical_block_size(sb->s_bdev); - if (size < minsize) - size = minsize; - return sb_set_blocksize(sb, size); -} - -EXPORT_SYMBOL(sb_min_blocksize); - -static int -blkdev_get_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh, int create) -{ - bh->b_bdev = I_BDEV(inode); - bh->b_blocknr = iblock; - set_buffer_mapped(bh); - return 0; -} - -static struct inode *bdev_file_inode(struct file *file) -{ - return file->f_mapping->host; -} - -static unsigned int dio_bio_write_op(struct kiocb *iocb) -{ - unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; - - /* avoid the need for a I/O completion work item */ - if (iocb->ki_flags & IOCB_DSYNC) - op |= REQ_FUA; - return op; -} - -#define DIO_INLINE_BIO_VECS 4 - -static void blkdev_bio_end_io_simple(struct bio *bio) -{ - struct task_struct *waiter = bio->bi_private; - - WRITE_ONCE(bio->bi_private, NULL); - blk_wake_io_task(waiter); -} - -static ssize_t -__blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, - unsigned int nr_pages) -{ - struct file *file = iocb->ki_filp; - struct block_device *bdev = I_BDEV(bdev_file_inode(file)); - struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs; - loff_t pos = iocb->ki_pos; - bool should_dirty = false; - struct bio bio; - ssize_t ret; - blk_qc_t qc; - - if ((pos | iov_iter_alignment(iter)) & - (bdev_logical_block_size(bdev) - 1)) - return -EINVAL; - - if (nr_pages <= DIO_INLINE_BIO_VECS) - vecs = inline_vecs; - else { - vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec), - GFP_KERNEL); - if (!vecs) - return -ENOMEM; - } - - bio_init(&bio, vecs, nr_pages); - bio_set_dev(&bio, bdev); - bio.bi_iter.bi_sector = pos >> 9; - bio.bi_write_hint = iocb->ki_hint; - bio.bi_private = current; - bio.bi_end_io = blkdev_bio_end_io_simple; - bio.bi_ioprio = iocb->ki_ioprio; - - ret = bio_iov_iter_get_pages(&bio, iter); - if (unlikely(ret)) - goto out; - ret = bio.bi_iter.bi_size; - - if (iov_iter_rw(iter) == READ) { - bio.bi_opf = REQ_OP_READ; - if (iter_is_iovec(iter)) - should_dirty = true; - } else { - bio.bi_opf = dio_bio_write_op(iocb); - task_io_account_write(ret); - } - if (iocb->ki_flags & IOCB_NOWAIT) - bio.bi_opf |= REQ_NOWAIT; - if (iocb->ki_flags & IOCB_HIPRI) - bio_set_polled(&bio, iocb); - - qc = submit_bio(&bio); - for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (!READ_ONCE(bio.bi_private)) - break; - if (!(iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(bdev_get_queue(bdev), qc, true)) - blk_io_schedule(); - } - __set_current_state(TASK_RUNNING); - - bio_release_pages(&bio, should_dirty); - if (unlikely(bio.bi_status)) - ret = blk_status_to_errno(bio.bi_status); - -out: - if (vecs != inline_vecs) - kfree(vecs); - - bio_uninit(&bio); - - return ret; -} - -struct blkdev_dio { - union { - struct kiocb *iocb; - struct task_struct *waiter; - }; - size_t size; - atomic_t ref; - bool multi_bio : 1; - bool should_dirty : 1; - bool is_sync : 1; - struct bio bio; -}; - -static struct bio_set blkdev_dio_pool; - -static int blkdev_iopoll(struct kiocb *kiocb, bool wait) -{ - struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host); - struct request_queue *q = bdev_get_queue(bdev); - - return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait); -} - -static void blkdev_bio_end_io(struct bio *bio) -{ - struct blkdev_dio *dio = bio->bi_private; - bool should_dirty = dio->should_dirty; - - if (bio->bi_status && !dio->bio.bi_status) - dio->bio.bi_status = bio->bi_status; - - if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { - if (!dio->is_sync) { - struct kiocb *iocb = dio->iocb; - ssize_t ret; - - if (likely(!dio->bio.bi_status)) { - ret = dio->size; - iocb->ki_pos += ret; - } else { - ret = blk_status_to_errno(dio->bio.bi_status); - } - - dio->iocb->ki_complete(iocb, ret, 0); - if (dio->multi_bio) - bio_put(&dio->bio); - } else { - struct task_struct *waiter = dio->waiter; - - WRITE_ONCE(dio->waiter, NULL); - blk_wake_io_task(waiter); - } - } - - if (should_dirty) { - bio_check_pages_dirty(bio); - } else { - bio_release_pages(bio, false); - bio_put(bio); - } -} - -static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - unsigned int nr_pages) -{ - struct file *file = iocb->ki_filp; - struct inode *inode = bdev_file_inode(file); - struct block_device *bdev = I_BDEV(inode); - struct blk_plug plug; - struct blkdev_dio *dio; - struct bio *bio; - bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; - bool is_read = (iov_iter_rw(iter) == READ), is_sync; - loff_t pos = iocb->ki_pos; - blk_qc_t qc = BLK_QC_T_NONE; - int ret = 0; - - if ((pos | iov_iter_alignment(iter)) & - (bdev_logical_block_size(bdev) - 1)) - return -EINVAL; - - bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool); - - dio = container_of(bio, struct blkdev_dio, bio); - dio->is_sync = is_sync = is_sync_kiocb(iocb); - if (dio->is_sync) { - dio->waiter = current; - bio_get(bio); - } else { - dio->iocb = iocb; - } - - dio->size = 0; - dio->multi_bio = false; - dio->should_dirty = is_read && iter_is_iovec(iter); - - /* - * Don't plug for HIPRI/polled IO, as those should go straight - * to issue - */ - if (!is_poll) - blk_start_plug(&plug); - - for (;;) { - bio_set_dev(bio, bdev); - bio->bi_iter.bi_sector = pos >> 9; - bio->bi_write_hint = iocb->ki_hint; - bio->bi_private = dio; - bio->bi_end_io = blkdev_bio_end_io; - bio->bi_ioprio = iocb->ki_ioprio; - - ret = bio_iov_iter_get_pages(bio, iter); - if (unlikely(ret)) { - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); - break; - } - - if (is_read) { - bio->bi_opf = REQ_OP_READ; - if (dio->should_dirty) - bio_set_pages_dirty(bio); - } else { - bio->bi_opf = dio_bio_write_op(iocb); - task_io_account_write(bio->bi_iter.bi_size); - } - if (iocb->ki_flags & IOCB_NOWAIT) - bio->bi_opf |= REQ_NOWAIT; - - dio->size += bio->bi_iter.bi_size; - pos += bio->bi_iter.bi_size; - - nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS); - if (!nr_pages) { - bool polled = false; - - if (iocb->ki_flags & IOCB_HIPRI) { - bio_set_polled(bio, iocb); - polled = true; - } - - qc = submit_bio(bio); - - if (polled) - WRITE_ONCE(iocb->ki_cookie, qc); - break; - } - - if (!dio->multi_bio) { - /* - * AIO needs an extra reference to ensure the dio - * structure which is embedded into the first bio - * stays around. - */ - if (!is_sync) - bio_get(bio); - dio->multi_bio = true; - atomic_set(&dio->ref, 2); - } else { - atomic_inc(&dio->ref); - } - - submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, nr_pages); - } - - if (!is_poll) - blk_finish_plug(&plug); - - if (!is_sync) - return -EIOCBQUEUED; - - for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (!READ_ONCE(dio->waiter)) - break; - - if (!(iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(bdev_get_queue(bdev), qc, true)) - blk_io_schedule(); - } - __set_current_state(TASK_RUNNING); - - if (!ret) - ret = blk_status_to_errno(dio->bio.bi_status); - if (likely(!ret)) - ret = dio->size; - - bio_put(&dio->bio); - return ret; -} - -static ssize_t -blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -{ - unsigned int nr_pages; - - if (!iov_iter_count(iter)) - return 0; - - nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); - if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS) - return __blkdev_direct_IO_simple(iocb, iter, nr_pages); - - return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages)); -} - -static __init int blkdev_init(void) -{ - return bioset_init(&blkdev_dio_pool, 4, - offsetof(struct blkdev_dio, bio), - BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE); -} -module_init(blkdev_init); - -int __sync_blockdev(struct block_device *bdev, int wait) -{ - if (!bdev) - return 0; - if (!wait) - return filemap_flush(bdev->bd_inode->i_mapping); - return filemap_write_and_wait(bdev->bd_inode->i_mapping); -} - -/* - * Write out and wait upon all the dirty data associated with a block - * device via its mapping. Does not take the superblock lock. - */ -int sync_blockdev(struct block_device *bdev) -{ - return __sync_blockdev(bdev, 1); -} -EXPORT_SYMBOL(sync_blockdev); - -/* - * Write out and wait upon all dirty data associated with this - * device. Filesystem data as well as the underlying block - * device. Takes the superblock lock. - */ -int fsync_bdev(struct block_device *bdev) -{ - struct super_block *sb = get_super(bdev); - if (sb) { - int res = sync_filesystem(sb); - drop_super(sb); - return res; - } - return sync_blockdev(bdev); -} -EXPORT_SYMBOL(fsync_bdev); - -/** - * freeze_bdev -- lock a filesystem and force it into a consistent state - * @bdev: blockdevice to lock - * - * If a superblock is found on this device, we take the s_umount semaphore - * on it to make sure nobody unmounts until the snapshot creation is done. - * The reference counter (bd_fsfreeze_count) guarantees that only the last - * unfreeze process can unfreeze the frozen filesystem actually when multiple - * freeze requests arrive simultaneously. It counts up in freeze_bdev() and - * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze - * actually. - */ -int freeze_bdev(struct block_device *bdev) -{ - struct super_block *sb; - int error = 0; - - mutex_lock(&bdev->bd_fsfreeze_mutex); - if (++bdev->bd_fsfreeze_count > 1) - goto done; - - sb = get_active_super(bdev); - if (!sb) - goto sync; - if (sb->s_op->freeze_super) - error = sb->s_op->freeze_super(sb); - else - error = freeze_super(sb); - deactivate_super(sb); - - if (error) { - bdev->bd_fsfreeze_count--; - goto done; - } - bdev->bd_fsfreeze_sb = sb; - -sync: - sync_blockdev(bdev); -done: - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return error; -} -EXPORT_SYMBOL(freeze_bdev); - -/** - * thaw_bdev -- unlock filesystem - * @bdev: blockdevice to unlock - * - * Unlocks the filesystem and marks it writeable again after freeze_bdev(). - */ -int thaw_bdev(struct block_device *bdev) -{ - struct super_block *sb; - int error = -EINVAL; - - mutex_lock(&bdev->bd_fsfreeze_mutex); - if (!bdev->bd_fsfreeze_count) - goto out; - - error = 0; - if (--bdev->bd_fsfreeze_count > 0) - goto out; - - sb = bdev->bd_fsfreeze_sb; - if (!sb) - goto out; - - if (sb->s_op->thaw_super) - error = sb->s_op->thaw_super(sb); - else - error = thaw_super(sb); - if (error) - bdev->bd_fsfreeze_count++; - else - bdev->bd_fsfreeze_sb = NULL; -out: - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return error; -} -EXPORT_SYMBOL(thaw_bdev); - -static int blkdev_writepage(struct page *page, struct writeback_control *wbc) -{ - return block_write_full_page(page, blkdev_get_block, wbc); -} - -static int blkdev_readpage(struct file * file, struct page * page) -{ - return block_read_full_page(page, blkdev_get_block); -} - -static void blkdev_readahead(struct readahead_control *rac) -{ - mpage_readahead(rac, blkdev_get_block); -} - -static int blkdev_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) -{ - return block_write_begin(mapping, pos, len, flags, pagep, - blkdev_get_block); -} - -static int blkdev_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - int ret; - ret = block_write_end(file, mapping, pos, len, copied, page, fsdata); - - unlock_page(page); - put_page(page); - - return ret; -} - -/* - * private llseek: - * for a block special file file_inode(file)->i_size is zero - * so we compute the size by hand (just as in block_read/write above) - */ -static loff_t block_llseek(struct file *file, loff_t offset, int whence) -{ - struct inode *bd_inode = bdev_file_inode(file); - loff_t retval; - - inode_lock(bd_inode); - retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode)); - inode_unlock(bd_inode); - return retval; -} - -static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, - int datasync) -{ - struct inode *bd_inode = bdev_file_inode(filp); - struct block_device *bdev = I_BDEV(bd_inode); - int error; - - error = file_write_and_wait_range(filp, start, end); - if (error) - return error; - - /* - * There is no need to serialise calls to blkdev_issue_flush with - * i_mutex and doing so causes performance issues with concurrent - * O_SYNC writers to a block device. - */ - error = blkdev_issue_flush(bdev); - if (error == -EOPNOTSUPP) - error = 0; - - return error; -} - -/** - * bdev_read_page() - Start reading a page from a block device - * @bdev: The device to read the page from - * @sector: The offset on the device to read the page to (need not be aligned) - * @page: The page to read - * - * On entry, the page should be locked. It will be unlocked when the page - * has been read. If the block driver implements rw_page synchronously, - * that will be true on exit from this function, but it need not be. - * - * Errors returned by this function are usually "soft", eg out of memory, or - * queue full; callers should try a different route to read this page rather - * than propagate an error back up the stack. - * - * Return: negative errno if an error occurs, 0 if submission was successful. - */ -int bdev_read_page(struct block_device *bdev, sector_t sector, - struct page *page) -{ - const struct block_device_operations *ops = bdev->bd_disk->fops; - int result = -EOPNOTSUPP; - - if (!ops->rw_page || bdev_get_integrity(bdev)) - return result; - - result = blk_queue_enter(bdev->bd_disk->queue, 0); - if (result) - return result; - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, - REQ_OP_READ); - blk_queue_exit(bdev->bd_disk->queue); - return result; -} - -/** - * bdev_write_page() - Start writing a page to a block device - * @bdev: The device to write the page to - * @sector: The offset on the device to write the page to (need not be aligned) - * @page: The page to write - * @wbc: The writeback_control for the write - * - * On entry, the page should be locked and not currently under writeback. - * On exit, if the write started successfully, the page will be unlocked and - * under writeback. If the write failed already (eg the driver failed to - * queue the page to the device), the page will still be locked. If the - * caller is a ->writepage implementation, it will need to unlock the page. - * - * Errors returned by this function are usually "soft", eg out of memory, or - * queue full; callers should try a different route to write this page rather - * than propagate an error back up the stack. - * - * Return: negative errno if an error occurs, 0 if submission was successful. - */ -int bdev_write_page(struct block_device *bdev, sector_t sector, - struct page *page, struct writeback_control *wbc) -{ - int result; - const struct block_device_operations *ops = bdev->bd_disk->fops; - - if (!ops->rw_page || bdev_get_integrity(bdev)) - return -EOPNOTSUPP; - result = blk_queue_enter(bdev->bd_disk->queue, 0); - if (result) - return result; - - set_page_writeback(page); - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, - REQ_OP_WRITE); - if (result) { - end_page_writeback(page); - } else { - clean_page_buffers(page); - unlock_page(page); - } - blk_queue_exit(bdev->bd_disk->queue); - return result; -} - -/* - * pseudo-fs - */ - -static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock); -static struct kmem_cache * bdev_cachep __read_mostly; - -static struct inode *bdev_alloc_inode(struct super_block *sb) -{ - struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL); - - if (!ei) - return NULL; - memset(&ei->bdev, 0, sizeof(ei->bdev)); - return &ei->vfs_inode; -} - -static void bdev_free_inode(struct inode *inode) -{ - struct block_device *bdev = I_BDEV(inode); - - free_percpu(bdev->bd_stats); - kfree(bdev->bd_meta_info); - - if (!bdev_is_partition(bdev)) { - if (bdev->bd_disk && bdev->bd_disk->bdi) - bdi_put(bdev->bd_disk->bdi); - kfree(bdev->bd_disk); - } - - if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR) - blk_free_ext_minor(MINOR(bdev->bd_dev)); - - kmem_cache_free(bdev_cachep, BDEV_I(inode)); -} - -static void init_once(void *data) -{ - struct bdev_inode *ei = data; - - inode_init_once(&ei->vfs_inode); -} - -static void bdev_evict_inode(struct inode *inode) -{ - truncate_inode_pages_final(&inode->i_data); - invalidate_inode_buffers(inode); /* is it needed here? */ - clear_inode(inode); -} - -static const struct super_operations bdev_sops = { - .statfs = simple_statfs, - .alloc_inode = bdev_alloc_inode, - .free_inode = bdev_free_inode, - .drop_inode = generic_delete_inode, - .evict_inode = bdev_evict_inode, -}; - -static int bd_init_fs_context(struct fs_context *fc) -{ - struct pseudo_fs_context *ctx = init_pseudo(fc, BDEVFS_MAGIC); - if (!ctx) - return -ENOMEM; - fc->s_iflags |= SB_I_CGROUPWB; - ctx->ops = &bdev_sops; - return 0; -} - -static struct file_system_type bd_type = { - .name = "bdev", - .init_fs_context = bd_init_fs_context, - .kill_sb = kill_anon_super, -}; - -struct super_block *blockdev_superblock __read_mostly; -EXPORT_SYMBOL_GPL(blockdev_superblock); - -void __init bdev_cache_init(void) -{ - int err; - static struct vfsmount *bd_mnt; - - bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), - 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC), - init_once); - err = register_filesystem(&bd_type); - if (err) - panic("Cannot register bdev pseudo-fs"); - bd_mnt = kern_mount(&bd_type); - if (IS_ERR(bd_mnt)) - panic("Cannot create bdev pseudo-fs"); - blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ -} - -struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) -{ - struct block_device *bdev; - struct inode *inode; - - inode = new_inode(blockdev_superblock); - if (!inode) - return NULL; - inode->i_mode = S_IFBLK; - inode->i_rdev = 0; - inode->i_data.a_ops = &def_blk_aops; - mapping_set_gfp_mask(&inode->i_data, GFP_USER); - - bdev = I_BDEV(inode); - mutex_init(&bdev->bd_fsfreeze_mutex); - spin_lock_init(&bdev->bd_size_lock); - bdev->bd_disk = disk; - bdev->bd_partno = partno; - bdev->bd_inode = inode; - bdev->bd_stats = alloc_percpu(struct disk_stats); - if (!bdev->bd_stats) { - iput(inode); - return NULL; - } - return bdev; -} - -void bdev_add(struct block_device *bdev, dev_t dev) -{ - bdev->bd_dev = dev; - bdev->bd_inode->i_rdev = dev; - bdev->bd_inode->i_ino = dev; - insert_inode_hash(bdev->bd_inode); -} - -long nr_blockdev_pages(void) -{ - struct inode *inode; - long ret = 0; - - spin_lock(&blockdev_superblock->s_inode_list_lock); - list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) - ret += inode->i_mapping->nrpages; - spin_unlock(&blockdev_superblock->s_inode_list_lock); - - return ret; -} - -/** - * bd_may_claim - test whether a block device can be claimed - * @bdev: block device of interest - * @whole: whole block device containing @bdev, may equal @bdev - * @holder: holder trying to claim @bdev - * - * Test whether @bdev can be claimed by @holder. - * - * CONTEXT: - * spin_lock(&bdev_lock). - * - * RETURNS: - * %true if @bdev can be claimed, %false otherwise. - */ -static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, - void *holder) -{ - if (bdev->bd_holder == holder) - return true; /* already a holder */ - else if (bdev->bd_holder != NULL) - return false; /* held by someone else */ - else if (whole == bdev) - return true; /* is a whole device which isn't held */ - - else if (whole->bd_holder == bd_may_claim) - return true; /* is a partition of a device that is being partitioned */ - else if (whole->bd_holder != NULL) - return false; /* is a partition of a held device */ - else - return true; /* is a partition of an un-held device */ -} - -/** - * bd_prepare_to_claim - claim a block device - * @bdev: block device of interest - * @holder: holder trying to claim @bdev - * - * Claim @bdev. This function fails if @bdev is already claimed by another - * holder and waits if another claiming is in progress. return, the caller - * has ownership of bd_claiming and bd_holder[s]. - * - * RETURNS: - * 0 if @bdev can be claimed, -EBUSY otherwise. - */ -int bd_prepare_to_claim(struct block_device *bdev, void *holder) -{ - struct block_device *whole = bdev_whole(bdev); - - if (WARN_ON_ONCE(!holder)) - return -EINVAL; -retry: - spin_lock(&bdev_lock); - /* if someone else claimed, fail */ - if (!bd_may_claim(bdev, whole, holder)) { - spin_unlock(&bdev_lock); - return -EBUSY; - } - - /* if claiming is already in progress, wait for it to finish */ - if (whole->bd_claiming) { - wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0); - DEFINE_WAIT(wait); - - prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); - spin_unlock(&bdev_lock); - schedule(); - finish_wait(wq, &wait); - goto retry; - } - - /* yay, all mine */ - whole->bd_claiming = holder; - spin_unlock(&bdev_lock); - return 0; -} -EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ - -static void bd_clear_claiming(struct block_device *whole, void *holder) -{ - lockdep_assert_held(&bdev_lock); - /* tell others that we're done */ - BUG_ON(whole->bd_claiming != holder); - whole->bd_claiming = NULL; - wake_up_bit(&whole->bd_claiming, 0); -} - -/** - * bd_finish_claiming - finish claiming of a block device - * @bdev: block device of interest - * @holder: holder that has claimed @bdev - * - * Finish exclusive open of a block device. Mark the device as exlusively - * open by the holder and wake up all waiters for exclusive open to finish. - */ -static void bd_finish_claiming(struct block_device *bdev, void *holder) -{ - struct block_device *whole = bdev_whole(bdev); - - spin_lock(&bdev_lock); - BUG_ON(!bd_may_claim(bdev, whole, holder)); - /* - * Note that for a whole device bd_holders will be incremented twice, - * and bd_holder will be set to bd_may_claim before being set to holder - */ - whole->bd_holders++; - whole->bd_holder = bd_may_claim; - bdev->bd_holders++; - bdev->bd_holder = holder; - bd_clear_claiming(whole, holder); - spin_unlock(&bdev_lock); -} - -/** - * bd_abort_claiming - abort claiming of a block device - * @bdev: block device of interest - * @holder: holder that has claimed @bdev - * - * Abort claiming of a block device when the exclusive open failed. This can be - * also used when exclusive open is not actually desired and we just needed - * to block other exclusive openers for a while. - */ -void bd_abort_claiming(struct block_device *bdev, void *holder) -{ - spin_lock(&bdev_lock); - bd_clear_claiming(bdev_whole(bdev), holder); - spin_unlock(&bdev_lock); -} -EXPORT_SYMBOL(bd_abort_claiming); - -static void blkdev_flush_mapping(struct block_device *bdev) -{ - WARN_ON_ONCE(bdev->bd_holders); - sync_blockdev(bdev); - kill_bdev(bdev); - bdev_write_inode(bdev); -} - -static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) -{ - struct gendisk *disk = bdev->bd_disk; - int ret = 0; - - if (disk->fops->open) { - ret = disk->fops->open(bdev, mode); - if (ret) { - /* avoid ghost partitions on a removed medium */ - if (ret == -ENOMEDIUM && - test_bit(GD_NEED_PART_SCAN, &disk->state)) - bdev_disk_changed(disk, true); - return ret; - } - } - - if (!bdev->bd_openers) - set_init_blocksize(bdev); - if (test_bit(GD_NEED_PART_SCAN, &disk->state)) - bdev_disk_changed(disk, false); - bdev->bd_openers++; - return 0;; -} - -static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) -{ - if (!--bdev->bd_openers) - blkdev_flush_mapping(bdev); - if (bdev->bd_disk->fops->release) - bdev->bd_disk->fops->release(bdev->bd_disk, mode); -} - -static int blkdev_get_part(struct block_device *part, fmode_t mode) -{ - struct gendisk *disk = part->bd_disk; - int ret; - - if (part->bd_openers) - goto done; - - ret = blkdev_get_whole(bdev_whole(part), mode); - if (ret) - return ret; - - ret = -ENXIO; - if (!bdev_nr_sectors(part)) - goto out_blkdev_put; - - disk->open_partitions++; - set_init_blocksize(part); -done: - part->bd_openers++; - return 0; - -out_blkdev_put: - blkdev_put_whole(bdev_whole(part), mode); - return ret; -} - -static void blkdev_put_part(struct block_device *part, fmode_t mode) -{ - struct block_device *whole = bdev_whole(part); - - if (--part->bd_openers) - return; - blkdev_flush_mapping(part); - whole->bd_disk->open_partitions--; - blkdev_put_whole(whole, mode); -} - -struct block_device *blkdev_get_no_open(dev_t dev) -{ - struct block_device *bdev; - struct inode *inode; - - inode = ilookup(blockdev_superblock, dev); - if (!inode) { - blk_request_module(dev); - inode = ilookup(blockdev_superblock, dev); - if (!inode) - return NULL; - } - - /* switch from the inode reference to a device mode one: */ - bdev = &BDEV_I(inode)->bdev; - if (!kobject_get_unless_zero(&bdev->bd_device.kobj)) - bdev = NULL; - iput(inode); - - if (!bdev) - return NULL; - if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) || - !try_module_get(bdev->bd_disk->fops->owner)) { - put_device(&bdev->bd_device); - return NULL; - } - - return bdev; -} - -void blkdev_put_no_open(struct block_device *bdev) -{ - module_put(bdev->bd_disk->fops->owner); - put_device(&bdev->bd_device); -} - -/** - * blkdev_get_by_dev - open a block device by device number - * @dev: device number of block device to open - * @mode: FMODE_* mask - * @holder: exclusive holder identifier - * - * Open the block device described by device number @dev. If @mode includes - * %FMODE_EXCL, the block device is opened with exclusive access. Specifying - * %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may nest for - * the same @holder. - * - * Use this interface ONLY if you really do not have anything better - i.e. when - * you are behind a truly sucky interface and all you are given is a device - * number. Everything else should use blkdev_get_by_path(). - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * Reference to the block_device on success, ERR_PTR(-errno) on failure. - */ -struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) -{ - bool unblock_events = true; - struct block_device *bdev; - struct gendisk *disk; - int ret; - - ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, - MAJOR(dev), MINOR(dev), - ((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) | - ((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0)); - if (ret) - return ERR_PTR(ret); - - bdev = blkdev_get_no_open(dev); - if (!bdev) - return ERR_PTR(-ENXIO); - disk = bdev->bd_disk; - - if (mode & FMODE_EXCL) { - ret = bd_prepare_to_claim(bdev, holder); - if (ret) - goto put_blkdev; - } - - disk_block_events(disk); - - mutex_lock(&disk->open_mutex); - ret = -ENXIO; - if (!disk_live(disk)) - goto abort_claiming; - if (bdev_is_partition(bdev)) - ret = blkdev_get_part(bdev, mode); - else - ret = blkdev_get_whole(bdev, mode); - if (ret) - goto abort_claiming; - if (mode & FMODE_EXCL) { - bd_finish_claiming(bdev, holder); - - /* - * Block event polling for write claims if requested. Any write - * holder makes the write_holder state stick until all are - * released. This is good enough and tracking individual - * writeable reference is too fragile given the way @mode is - * used in blkdev_get/put(). - */ - if ((mode & FMODE_WRITE) && !bdev->bd_write_holder && - (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { - bdev->bd_write_holder = true; - unblock_events = false; - } - } - mutex_unlock(&disk->open_mutex); - - if (unblock_events) - disk_unblock_events(disk); - return bdev; - -abort_claiming: - if (mode & FMODE_EXCL) - bd_abort_claiming(bdev, holder); - mutex_unlock(&disk->open_mutex); - disk_unblock_events(disk); -put_blkdev: - blkdev_put_no_open(bdev); - return ERR_PTR(ret); -} -EXPORT_SYMBOL(blkdev_get_by_dev); - -/** - * blkdev_get_by_path - open a block device by name - * @path: path to the block device to open - * @mode: FMODE_* mask - * @holder: exclusive holder identifier - * - * Open the block device described by the device file at @path. If @mode - * includes %FMODE_EXCL, the block device is opened with exclusive access. - * Specifying %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may - * nest for the same @holder. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * Reference to the block_device on success, ERR_PTR(-errno) on failure. - */ -struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder) -{ - struct block_device *bdev; - dev_t dev; - int error; - - error = lookup_bdev(path, &dev); - if (error) - return ERR_PTR(error); - - bdev = blkdev_get_by_dev(dev, mode, holder); - if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) { - blkdev_put(bdev, mode); - return ERR_PTR(-EACCES); - } - - return bdev; -} -EXPORT_SYMBOL(blkdev_get_by_path); - -static int blkdev_open(struct inode * inode, struct file * filp) -{ - struct block_device *bdev; - - /* - * Preserve backwards compatibility and allow large file access - * even if userspace doesn't ask for it explicitly. Some mkfs - * binary needs it. We might want to drop this workaround - * during an unstable branch. - */ - filp->f_flags |= O_LARGEFILE; - - filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; - - if (filp->f_flags & O_NDELAY) - filp->f_mode |= FMODE_NDELAY; - if (filp->f_flags & O_EXCL) - filp->f_mode |= FMODE_EXCL; - if ((filp->f_flags & O_ACCMODE) == 3) - filp->f_mode |= FMODE_WRITE_IOCTL; - - bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - filp->f_mapping = bdev->bd_inode->i_mapping; - filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); - return 0; -} - -void blkdev_put(struct block_device *bdev, fmode_t mode) -{ - struct gendisk *disk = bdev->bd_disk; - - /* - * Sync early if it looks like we're the last one. If someone else - * opens the block device between now and the decrement of bd_openers - * then we did a sync that we didn't need to, but that's not the end - * of the world and we want to avoid long (could be several minute) - * syncs while holding the mutex. - */ - if (bdev->bd_openers == 1) - sync_blockdev(bdev); - - mutex_lock(&disk->open_mutex); - if (mode & FMODE_EXCL) { - struct block_device *whole = bdev_whole(bdev); - bool bdev_free; - - /* - * Release a claim on the device. The holder fields - * are protected with bdev_lock. open_mutex is to - * synchronize disk_holder unlinking. - */ - spin_lock(&bdev_lock); - - WARN_ON_ONCE(--bdev->bd_holders < 0); - WARN_ON_ONCE(--whole->bd_holders < 0); - - if ((bdev_free = !bdev->bd_holders)) - bdev->bd_holder = NULL; - if (!whole->bd_holders) - whole->bd_holder = NULL; - - spin_unlock(&bdev_lock); - - /* - * If this was the last claim, remove holder link and - * unblock evpoll if it was a write holder. - */ - if (bdev_free && bdev->bd_write_holder) { - disk_unblock_events(disk); - bdev->bd_write_holder = false; - } - } - - /* - * Trigger event checking and tell drivers to flush MEDIA_CHANGE - * event. This is to ensure detection of media removal commanded - * from userland - e.g. eject(1). - */ - disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE); - - if (bdev_is_partition(bdev)) - blkdev_put_part(bdev, mode); - else - blkdev_put_whole(bdev, mode); - mutex_unlock(&disk->open_mutex); - - blkdev_put_no_open(bdev); -} -EXPORT_SYMBOL(blkdev_put); - -static int blkdev_close(struct inode * inode, struct file * filp) -{ - struct block_device *bdev = I_BDEV(bdev_file_inode(filp)); - blkdev_put(bdev, filp->f_mode); - return 0; -} - -static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) -{ - struct block_device *bdev = I_BDEV(bdev_file_inode(file)); - fmode_t mode = file->f_mode; - - /* - * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have - * to updated it before every ioctl. - */ - if (file->f_flags & O_NDELAY) - mode |= FMODE_NDELAY; - else - mode &= ~FMODE_NDELAY; - - return blkdev_ioctl(bdev, mode, cmd, arg); -} - -/* - * Write data to the block device. Only intended for the block device itself - * and the raw driver which basically is a fake block device. - * - * Does not take i_mutex for the write and thus is not for general purpose - * use. - */ -static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) -{ - struct file *file = iocb->ki_filp; - struct inode *bd_inode = bdev_file_inode(file); - loff_t size = i_size_read(bd_inode); - struct blk_plug plug; - size_t shorted = 0; - ssize_t ret; - - if (bdev_read_only(I_BDEV(bd_inode))) - return -EPERM; - - if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev)) - return -ETXTBSY; - - if (!iov_iter_count(from)) - return 0; - - if (iocb->ki_pos >= size) - return -ENOSPC; - - if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT) - return -EOPNOTSUPP; - - size -= iocb->ki_pos; - if (iov_iter_count(from) > size) { - shorted = iov_iter_count(from) - size; - iov_iter_truncate(from, size); - } - - blk_start_plug(&plug); - ret = __generic_file_write_iter(iocb, from); - if (ret > 0) - ret = generic_write_sync(iocb, ret); - iov_iter_reexpand(from, iov_iter_count(from) + shorted); - blk_finish_plug(&plug); - return ret; -} - -static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) -{ - struct file *file = iocb->ki_filp; - struct inode *bd_inode = bdev_file_inode(file); - loff_t size = i_size_read(bd_inode); - loff_t pos = iocb->ki_pos; - size_t shorted = 0; - ssize_t ret; - - if (pos >= size) - return 0; - - size -= pos; - if (iov_iter_count(to) > size) { - shorted = iov_iter_count(to) - size; - iov_iter_truncate(to, size); - } - - ret = generic_file_read_iter(iocb, to); - iov_iter_reexpand(to, iov_iter_count(to) + shorted); - return ret; -} - -static int blkdev_writepages(struct address_space *mapping, - struct writeback_control *wbc) -{ - return generic_writepages(mapping, wbc); -} - -static const struct address_space_operations def_blk_aops = { - .set_page_dirty = __set_page_dirty_buffers, - .readpage = blkdev_readpage, - .readahead = blkdev_readahead, - .writepage = blkdev_writepage, - .write_begin = blkdev_write_begin, - .write_end = blkdev_write_end, - .writepages = blkdev_writepages, - .direct_IO = blkdev_direct_IO, - .migratepage = buffer_migrate_page_norefs, - .is_dirty_writeback = buffer_check_dirty_writeback, -}; - -#define BLKDEV_FALLOC_FL_SUPPORTED \ - (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ - FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE) - -static long blkdev_fallocate(struct file *file, int mode, loff_t start, - loff_t len) -{ - struct block_device *bdev = I_BDEV(bdev_file_inode(file)); - loff_t end = start + len - 1; - loff_t isize; - int error; - - /* Fail if we don't recognize the flags. */ - if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED) - return -EOPNOTSUPP; - - /* Don't go off the end of the device. */ - isize = i_size_read(bdev->bd_inode); - if (start >= isize) - return -EINVAL; - if (end >= isize) { - if (mode & FALLOC_FL_KEEP_SIZE) { - len = isize - start; - end = start + len - 1; - } else - return -EINVAL; - } - - /* - * Don't allow IO that isn't aligned to logical block size. - */ - if ((start | len) & (bdev_logical_block_size(bdev) - 1)) - return -EINVAL; - - /* Invalidate the page cache, including dirty pages. */ - error = truncate_bdev_range(bdev, file->f_mode, start, end); - if (error) - return error; - - switch (mode) { - case FALLOC_FL_ZERO_RANGE: - case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: - error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, - GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); - break; - case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: - error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, - GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); - break; - case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: - error = blkdev_issue_discard(bdev, start >> 9, len >> 9, - GFP_KERNEL, 0); - break; - default: - return -EOPNOTSUPP; - } - if (error) - return error; - - /* - * Invalidate the page cache again; if someone wandered in and dirtied - * a page, we just discard it - userspace has no way of knowing whether - * the write happened before or after discard completing... - */ - return truncate_bdev_range(bdev, file->f_mode, start, end); -} - -const struct file_operations def_blk_fops = { - .open = blkdev_open, - .release = blkdev_close, - .llseek = block_llseek, - .read_iter = blkdev_read_iter, - .write_iter = blkdev_write_iter, - .iopoll = blkdev_iopoll, - .mmap = generic_file_mmap, - .fsync = blkdev_fsync, - .unlocked_ioctl = block_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = compat_blkdev_ioctl, -#endif - .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, - .fallocate = blkdev_fallocate, -}; - -/** - * lookup_bdev - lookup a struct block_device by name - * @pathname: special file representing the block device - * @dev: return value of the block device's dev_t - * - * Get a reference to the blockdevice at @pathname in the current - * namespace if possible and return it. Return ERR_PTR(error) - * otherwise. - */ -int lookup_bdev(const char *pathname, dev_t *dev) -{ - struct inode *inode; - struct path path; - int error; - - if (!pathname || !*pathname) - return -EINVAL; - - error = kern_path(pathname, LOOKUP_FOLLOW, &path); - if (error) - return error; - - inode = d_backing_inode(path.dentry); - error = -ENOTBLK; - if (!S_ISBLK(inode->i_mode)) - goto out_path_put; - error = -EACCES; - if (!may_open_dev(&path)) - goto out_path_put; - - *dev = inode->i_rdev; - error = 0; -out_path_put: - path_put(&path); - return error; -} -EXPORT_SYMBOL(lookup_bdev); - -int __invalidate_device(struct block_device *bdev, bool kill_dirty) -{ - struct super_block *sb = get_super(bdev); - int res = 0; - - if (sb) { - /* - * no need to lock the super, get_super holds the - * read mutex so the filesystem cannot go away - * under us (->put_super runs with the write lock - * hold). - */ - shrink_dcache_sb(sb); - res = invalidate_inodes(sb, kill_dirty); - drop_super(sb); - } - invalidate_bdev(bdev); - return res; -} -EXPORT_SYMBOL(__invalidate_device); - -void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) -{ - struct inode *inode, *old_inode = NULL; - - spin_lock(&blockdev_superblock->s_inode_list_lock); - list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { - struct address_space *mapping = inode->i_mapping; - struct block_device *bdev; - - spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || - mapping->nrpages == 0) { - spin_unlock(&inode->i_lock); - continue; - } - __iget(inode); - spin_unlock(&inode->i_lock); - spin_unlock(&blockdev_superblock->s_inode_list_lock); - /* - * We hold a reference to 'inode' so it couldn't have been - * removed from s_inodes list while we dropped the - * s_inode_list_lock We cannot iput the inode now as we can - * be holding the last reference and we cannot iput it under - * s_inode_list_lock. So we keep the reference and iput it - * later. - */ - iput(old_inode); - old_inode = inode; - bdev = I_BDEV(inode); - - mutex_lock(&bdev->bd_disk->open_mutex); - if (bdev->bd_openers) - func(bdev, arg); - mutex_unlock(&bdev->bd_disk->open_mutex); - - spin_lock(&blockdev_superblock->s_inode_list_lock); - } - spin_unlock(&blockdev_superblock->s_inode_list_lock); - iput(old_inode); -} diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index 8a3b30ec860c..8be57aaedab6 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cache.c - CIFS filesystem cache index structure definitions + * CIFS filesystem cache index structure definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 51a824fc926a..de2c12bcfa4b 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs_debug.c * * Copyright (C) International Business Machines Corp., 2000,2005 * diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 4fd788586399..f97407520ea1 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_fs_sb.h * * Copyright (c) International Business Machines Corp., 2002,2004 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index ef723be358af..b87cbbe6d2d4 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_ioctl.h * * Structure definitions for io control for cifs/smb3 * diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 8fa26a8530f8..353bd0dd7026 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifs_spnego.c -- SPNEGO upcall management for CIFS + * SPNEGO upcall management for CIFS * * Copyright (c) 2007 Red Hat, Inc. * Author(s): Jeff Layton (jlayton@redhat.com) diff --git a/fs/cifs/cifs_spnego.h b/fs/cifs/cifs_spnego.h index 31387d0ea32e..e6a0451877d4 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/cifs/cifs_spnego.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_spnego.h -- SPNEGO upcall management for CIFS + * SPNEGO upcall management for CIFS * * Copyright (c) 2007 Red Hat, Inc. * Author(s): Jeff Layton (jlayton@redhat.com) diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 171ad8b42107..e7582dd79179 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/cifs_unicode.c * * Copyright (c) International Business Machines Corp., 2000,2009 * Modified by Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 388eb536cff1..ee3aab3dd4ac 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsacl.c * * Copyright (C) International Business Machines Corp., 2007,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsacl.h b/fs/cifs/cifsacl.h index f8292bcf8594..ccbfc754bd3c 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/cifs/cifsacl.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsacl.h * * Copyright (c) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 6679e07e533e..d118282071b3 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsencrypt.c * * Encryption and hashing operations relating to NTLM, NTLMv2. See MS-NLMP * for more detailed information @@ -22,7 +21,7 @@ #include <linux/random.h> #include <linux/highmem.h> #include <linux/fips.h> -#include "../cifs_common/arc4.h" +#include "../smbfs_common/arc4.h" #include <crypto/aead.h> int __cifs_calc_signature(struct smb_rqst *rqst, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8c20bfa187ac..9fa930dfd78d 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsfs.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d25a4099b32e..b50da1901ebd 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsfs.h * * Copyright (c) International Business Machines Corp., 2002, 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index c068f7d8d879..e916470468ea 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsglob.h * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) @@ -1400,6 +1399,7 @@ struct cifsInodeInfo { #define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */ #define CIFS_INO_LOCK (5) /* lock bit for synchronization */ #define CIFS_INO_MODIFIED_ATTR (6) /* Indicate change in mtime/ctime */ +#define CIFS_INO_CLOSE_ON_LOCK (7) /* Not to defer the close when lock is set */ unsigned long flags; spinlock_t writers_lock; unsigned int writers; /* Number of writers on this inode */ diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index dc920e206336..d2ff438fd31f 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifspdu.h * * Copyright (c) International Business Machines Corp., 2002,2009 * Author(s): Steve French (sfrench@us.ibm.com) @@ -12,7 +11,7 @@ #include <net/sock.h> #include <asm/unaligned.h> -#include "smbfsctl.h" +#include "../smbfs_common/smbfsctl.h" #define CIFS_PROT 0 #define POSIX_PROT (CIFS_PROT+1) diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index f9740c21ca3d..d0f85b666662 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsproto.h * * Copyright (c) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) @@ -268,6 +267,9 @@ extern void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode); extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon); +extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon, + const char *path); + extern struct TCP_Server_Info *cifs_get_tcp_session(struct smb3_fs_context *ctx); extern void cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a8e41c1e80ca..243d17696f06 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifssmb.c * * Copyright (C) International Business Machines Corp., 2002,2010 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0db344807ef1..7881115cfbee 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/connect.c * * Copyright (C) International Business Machines Corp., 2002,2011 * Author(s): Steve French (sfrench@us.ibm.com) @@ -1090,7 +1089,7 @@ next_pdu: module_put_and_exit(0); } -/** +/* * Returns true if srcaddr isn't specified and rhs isn't specified, or * if srcaddr is specified and matches the IP address of the rhs argument */ @@ -1550,6 +1549,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) /** * cifs_setup_ipc - helper to setup the IPC tcon for the session + * @ses: smb session to issue the request on + * @ctx: the superblock configuration context to use for building the + * new tree connection for the IPC (interprocess communication RPC) * * A new IPC connection is made and stored in the session * tcon_ipc. The IPC tcon has the same lifetime as the session. @@ -1605,6 +1607,7 @@ out: /** * cifs_free_ipc - helper to release the session IPC tcon + * @ses: smb session to unmount the IPC from * * Needs to be called everytime a session is destroyed. * @@ -1855,6 +1858,8 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx __attribute__((unused)), /** * cifs_get_smb_ses - get a session matching @ctx data from @server + * @server: server to setup the session to + * @ctx: superblock configuration context to use to setup the session * * This function assumes it is being called from cifs_mount() where we * already got a server reference (server refcount +1). See @@ -2065,6 +2070,8 @@ cifs_put_tcon(struct cifs_tcon *tcon) /** * cifs_get_tcon - get a tcon matching @ctx data from @ses + * @ses: smb session to issue the request on + * @ctx: the superblock configuration context to use for building the * * - tcon refcount is the number of mount points using the tcon. * - ses refcount is the number of tcon using the session. @@ -3030,7 +3037,7 @@ build_unc_path_to_root(const struct smb3_fs_context *ctx, return full_path; } -/** +/* * expand_dfs_referral - Perform a dfs referral query and update the cifs_sb * * If a referral is found, cifs_sb->ctx->mount_options will be (re-)allocated diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 5f8a302ffcb2..6e8e7cc26ae2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/dir.c * * vfs operations that deal with dentries * diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 8c616aaeb7c4..0458d28d71aa 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/dns_resolve.c * * Copyright (c) 2007 Igor Mammedov * Author(s): Igor Mammedov (niallain@gmail.com) diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h index 9fa2807ef79e..afc0df381246 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/cifs/dns_resolve.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/dns_resolve.h -- DNS Resolver upcall management for CIFS DFS - * Handles host name to IP address resolution + * DNS Resolver upcall management for CIFS DFS + * Handles host name to IP address resolution * * Copyright (c) International Business Machines Corp., 2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/export.c b/fs/cifs/export.c index 747a540db954..37c28415df1e 100644 --- a/fs/cifs/export.c +++ b/fs/cifs/export.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/export.c * * Copyright (C) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index d0216472f1c6..6796fc73b304 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/file.c * * vfs operations that deal with files * @@ -883,6 +882,7 @@ int cifs_close(struct inode *inode, struct file *file) dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL); if ((cinode->oplock == CIFS_CACHE_RHW_FLG) && cinode->lease_granted && + !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) && dclose) { if (test_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { inode->i_ctime = inode->i_mtime = current_time(inode); @@ -1865,6 +1865,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag, tcon->ses->server); cifs_sb = CIFS_FILE_SB(file); + set_bit(CIFS_INO_CLOSE_ON_LOCK, &CIFS_I(d_inode(cfile->dentry))->flags); if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index fab47fa7df74..8eedd20c44ab 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/fscache.c - CIFS filesystem cache interface + * CIFS filesystem cache interface * * Copyright (c) 2010 Novell, Inc. * Author(s): Suresh Jayaraman <sjayaraman@suse.de> diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 82e856b9cf89..9baa1d0f22bd 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/fscache.h - CIFS filesystem cache interface definitions + * CIFS filesystem cache interface definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 50c01cff4c84..82848412ad85 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/inode.c * * Copyright (C) International Business Machines Corp., 2002,2010 * Author(s): Steve French (sfrench@us.ibm.com) @@ -1625,7 +1624,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } - cifs_close_deferred_file(CIFS_I(inode)); + cifs_close_deferred_file_under_dentry(tcon, full_path); if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = CIFSPOSIXDelFile(xid, tcon, full_path, @@ -2114,9 +2113,9 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, goto cifs_rename_exit; } - cifs_close_deferred_file(CIFS_I(d_inode(source_dentry))); + cifs_close_deferred_file_under_dentry(tcon, from_name); if (d_inode(target_dentry) != NULL) - cifs_close_deferred_file(CIFS_I(d_inode(target_dentry))); + cifs_close_deferred_file_under_dentry(tcon, to_name); rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 42c6a0bac6c8..0359b604bdbc 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/ioctl.c * * vfs operations that deal with io control * @@ -359,7 +358,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) if (pSMBFile == NULL) break; tcon = tlink_tcon(pSMBFile->tlink); - caps = le64_to_cpu(tcon->fsUnixInfo.Capability); + /* caps = le64_to_cpu(tcon->fsUnixInfo.Capability); */ if (get_user(ExtAttrBits, (int __user *)arg)) { rc = -EFAULT; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index f0a6d63bc08c..852e54ee82c2 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/link.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 9469f1cf0b46..03da00eb7c04 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/misc.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) @@ -736,7 +735,7 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) if (cancel_delayed_work(&cfile->deferred)) { tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) - continue; + break; tmp_list->cfile = cfile; list_add_tail(&tmp_list->list, &file_head); } @@ -767,7 +766,7 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) if (cancel_delayed_work(&cfile->deferred)) { tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) - continue; + break; tmp_list->cfile = cfile; list_add_tail(&tmp_list->list, &file_head); } @@ -781,6 +780,43 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) kfree(tmp_list); } } +void +cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) +{ + struct cifsFileInfo *cfile; + struct list_head *tmp; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; + void *page; + const char *full_path; + + INIT_LIST_HEAD(&file_head); + page = alloc_dentry_path(); + spin_lock(&tcon->open_file_lock); + list_for_each(tmp, &tcon->openFileList) { + cfile = list_entry(tmp, struct cifsFileInfo, tlist); + full_path = build_path_from_dentry(cfile->dentry, page); + if (strstr(full_path, path)) { + if (delayed_work_pending(&cfile->deferred)) { + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + break; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } + } + } + } + spin_unlock(&tcon->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); + } + free_dentry_path(page); +} /* parses DFS refferal V3 structure * caller is responsible for freeing target_nodes diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 0e728aac67e9..fa9fbd6a819c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/netmisc.c * * Copyright (c) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 378133ce8869..25a2b8ef88b9 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/ntlmssp.h * * Copyright (c) International Business Machines Corp., 2002,2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 54d77c99e21c..1929e80c09ee 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/readdir.c * * Directory search handling * diff --git a/fs/cifs/rfc1002pdu.h b/fs/cifs/rfc1002pdu.h index 137f7c95afd6..ae1d025da294 100644 --- a/fs/cifs/rfc1002pdu.h +++ b/fs/cifs/rfc1002pdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/rfc1002pdu.h * * Protocol Data Unit definitions for RFC 1001/1002 support * diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 118403fbeda2..23e02db7923f 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/sess.c * * SMB/CIFS session setup handling routines * diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index c9d8a50062b8..f5dcc4940b6d 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2file.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Author(s): Steve French (sfrench@us.ibm.com), diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index d0e9f3782bd9..ca692b2283cd 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2glob.h * * Definitions for various global variables and structures * diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 957b2594f02e..8297703492ee 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2inode.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 668f77108831..29b5554f6263 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2misc.c * * Copyright (C) International Business Machines Corp., 2002,2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index ddc0e8f97872..bda606dc72b1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -689,13 +689,19 @@ smb2_close_cached_fid(struct kref *ref) cifs_dbg(FYI, "clear cached root file handle\n"); SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid, cfid->fid->volatile_fid); - cfid->is_valid = false; - cfid->file_all_info_is_valid = false; - cfid->has_lease = false; - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } + } + + /* + * We only check validity above to send SMB2_close, + * but we still need to invalidate these entries + * when this function is called + */ + cfid->is_valid = false; + cfid->file_all_info_is_valid = false; + cfid->has_lease = false; + if (cfid->dentry) { + dput(cfid->dentry); + cfid->dentry = NULL; } } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b6d2e3591927..672ae78e866a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2pdu.c * * Copyright (C) International Business Machines Corp., 2009, 2013 * Etersoft, 2012 diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index e9cac7970b66..f32c99c9ba13 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2pdu.h * * Copyright (c) International Business Machines Corp., 2009, 2013 * Etersoft, 2012 diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 263767f644f8..547945443fa7 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2proto.h * * Copyright (c) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2status.h b/fs/cifs/smb2status.h index 0215ef36e240..a9e958166fc5 100644 --- a/fs/cifs/smb2status.h +++ b/fs/cifs/smb2status.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2status.h * * SMB2 Status code (network error) definitions * Definitions are from MS-ERREF diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 6f7952ea4941..f59b956f9d25 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2transport.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index 10047cc55286..4a0487753869 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -24,7 +24,7 @@ #include "cifsglob.h" #include "cifs_debug.h" #include "cifsproto.h" -#include "../cifs_common/md4.h" +#include "../smbfs_common/md4.h" #ifndef false #define false 0 diff --git a/fs/cifs/smberr.h b/fs/cifs/smberr.h index 60189efb3236..aeffdad829e2 100644 --- a/fs/cifs/smberr.h +++ b/fs/cifs/smberr.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smberr.h * * Copyright (c) International Business Machines Corp., 2002,2004 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 75a95de320cf..b7379329b741 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/transport.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/winucase.c b/fs/cifs/winucase.c index 59b6c577aa0a..2f075b5b50df 100644 --- a/fs/cifs/winucase.c +++ b/fs/cifs/winucase.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/winucase.c * * Copyright (c) Jeffrey Layton <jlayton@redhat.com>, 2013 * diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 9ed481e79ce0..7d8b72d67c80 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/xattr.c * * Copyright (c) International Business Machines Corp., 2003, 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/file.c b/fs/file.c index d8afa8266859..8627dacfc424 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1150,6 +1150,12 @@ int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) return new_fd; } +int receive_fd(struct file *file, unsigned int o_flags) +{ + return __receive_fd(file, NULL, o_flags); +} +EXPORT_SYMBOL_GPL(receive_fd); + static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 980d44fd3a36..3df07c0e32b3 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -165,7 +165,6 @@ int fs_lookup_param(struct fs_context *fc, return invalf(fc, "%s: not usable as path", param->key); } - f->refcnt++; /* filename_lookup() drops our ref. */ ret = filename_lookup(param->dirfd, f, flags, _path, NULL); if (ret < 0) { errorf(fc, "%s: Lookup failure for '%s'", param->key, f->name); diff --git a/fs/internal.h b/fs/internal.h index 68a2ae029a27..3cd065c8a66b 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -18,7 +18,7 @@ struct user_namespace; struct pipe_inode_info; /* - * block_dev.c + * block/bdev.c */ #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); diff --git a/fs/io-wq.c b/fs/io-wq.c index d80e4a735677..c2e0e8e80949 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -14,6 +14,7 @@ #include <linux/rculist_nulls.h> #include <linux/cpu.h> #include <linux/tracehook.h> +#include <uapi/linux/io_uring.h> #include "io-wq.h" @@ -176,7 +177,6 @@ static void io_worker_ref_put(struct io_wq *wq) static void io_worker_exit(struct io_worker *worker) { struct io_wqe *wqe = worker->wqe; - struct io_wqe_acct *acct = io_wqe_get_acct(worker); if (refcount_dec_and_test(&worker->ref)) complete(&worker->ref_done); @@ -186,7 +186,6 @@ static void io_worker_exit(struct io_worker *worker) if (worker->flags & IO_WORKER_F_FREE) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); - acct->nr_workers--; preempt_disable(); io_wqe_dec_running(worker); worker->flags = 0; @@ -246,8 +245,6 @@ static bool io_wqe_activate_free_worker(struct io_wqe *wqe, */ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) { - bool do_create = false; - /* * Most likely an attempt to queue unbounded work on an io_wq that * wasn't setup with any unbounded workers. @@ -256,18 +253,15 @@ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) pr_warn_once("io-wq is not configured for unbound workers"); raw_spin_lock(&wqe->lock); - if (acct->nr_workers < acct->max_workers) { - acct->nr_workers++; - do_create = true; + if (acct->nr_workers == acct->max_workers) { + raw_spin_unlock(&wqe->lock); + return true; } + acct->nr_workers++; raw_spin_unlock(&wqe->lock); - if (do_create) { - atomic_inc(&acct->nr_running); - atomic_inc(&wqe->wq->worker_refs); - return create_io_worker(wqe->wq, wqe, acct->index); - } - - return true; + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + return create_io_worker(wqe->wq, wqe, acct->index); } static void io_wqe_inc_running(struct io_worker *worker) @@ -574,6 +568,7 @@ loop: } /* timed out, exit unless we're the last worker */ if (last_timeout && acct->nr_workers > 1) { + acct->nr_workers--; raw_spin_unlock(&wqe->lock); __set_current_state(TASK_RUNNING); break; @@ -709,6 +704,7 @@ static void create_worker_cont(struct callback_head *cb) } raw_spin_unlock(&wqe->lock); io_worker_ref_put(wqe->wq); + kfree(worker); return; } @@ -725,6 +721,7 @@ static void io_workqueue_create(struct work_struct *work) if (!io_queue_worker_create(worker, acct, create_worker_cont)) { clear_bit_unlock(0, &worker->create_state); io_worker_release(worker); + kfree(worker); } } @@ -759,6 +756,7 @@ fail: if (!IS_ERR(tsk)) { io_init_new_worker(wqe, worker, tsk); } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + kfree(worker); goto fail; } else { INIT_WORK(&worker->work, io_workqueue_create); @@ -832,6 +830,11 @@ append: wq_list_add_after(&work->list, &tail->list, &acct->work_list); } +static bool io_wq_work_match_item(struct io_wq_work *work, void *data) +{ + return work == data; +} + static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) { struct io_wqe_acct *acct = io_work_get_acct(wqe, work); @@ -844,7 +847,6 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) */ if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) || (work->flags & IO_WQ_WORK_CANCEL)) { -run_cancel: io_run_cancel(work, wqe); return; } @@ -864,15 +866,22 @@ run_cancel: bool did_create; did_create = io_wqe_create_worker(wqe, acct); - if (unlikely(!did_create)) { - raw_spin_lock(&wqe->lock); - /* fatal condition, failed to create the first worker */ - if (!acct->nr_workers) { - raw_spin_unlock(&wqe->lock); - goto run_cancel; - } - raw_spin_unlock(&wqe->lock); + if (likely(did_create)) + return; + + raw_spin_lock(&wqe->lock); + /* fatal condition, failed to create the first worker */ + if (!acct->nr_workers) { + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_item, + .data = work, + .cancel_all = false, + }; + + if (io_acct_cancel_pending_work(wqe, acct, &match)) + raw_spin_lock(&wqe->lock); } + raw_spin_unlock(&wqe->lock); } } @@ -1122,7 +1131,7 @@ static bool io_task_work_match(struct callback_head *cb, void *data) { struct io_worker *worker; - if (cb->func != create_worker_cb || cb->func != create_worker_cont) + if (cb->func != create_worker_cb && cb->func != create_worker_cont) return false; worker = container_of(cb, struct io_worker, create_work); return worker->wqe->wq == data; @@ -1143,9 +1152,14 @@ static void io_wq_exit_workers(struct io_wq *wq) while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { struct io_worker *worker; + struct io_wqe_acct *acct; worker = container_of(cb, struct io_worker, create_work); - atomic_dec(&worker->wqe->acct[worker->create_index].nr_running); + acct = io_wqe_get_acct(worker); + atomic_dec(&acct->nr_running); + raw_spin_lock(&worker->wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&worker->wqe->lock); io_worker_ref_put(wq); clear_bit_unlock(0, &worker->create_state); io_worker_release(worker); @@ -1268,6 +1282,10 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count) { int i, node, prev = 0; + BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); + for (i = 0; i < 2; i++) { if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) new_count[i] = task_rlimit(current, RLIMIT_NPROC); diff --git a/fs/io_uring.c b/fs/io_uring.c index 855ea544807f..e372d5b9f6dc 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -712,6 +712,7 @@ struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; const struct iovec *free_iovec; struct iov_iter iter; + struct iov_iter_state iter_state; size_t bytes_done; struct wait_page_queue wpq; }; @@ -735,7 +736,6 @@ enum { REQ_F_BUFFER_SELECTED_BIT, REQ_F_COMPLETE_INLINE_BIT, REQ_F_REISSUE_BIT, - REQ_F_DONT_REISSUE_BIT, REQ_F_CREDS_BIT, REQ_F_REFCOUNT_BIT, REQ_F_ARM_LTIMEOUT_BIT, @@ -782,8 +782,6 @@ enum { REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), /* caller should reissue async */ REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), - /* don't attempt request reissue, see io_rw_reissue() */ - REQ_F_DONT_REISSUE = BIT(REQ_F_DONT_REISSUE_BIT), /* supports async reads */ REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT), /* supports async writes */ @@ -1482,6 +1480,8 @@ static void io_kill_timeout(struct io_kiocb *req, int status) struct io_timeout_data *io = req->async_data; if (hrtimer_try_to_cancel(&io->timer) != -1) { + if (status) + req_set_fail(req); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); @@ -1619,8 +1619,11 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) { + /* see waitqueue_active() comment */ + smp_mb(); + if (ctx->flags & IORING_SETUP_SQPOLL) { - if (wq_has_sleeper(&ctx->cq_wait)) + if (waitqueue_active(&ctx->cq_wait)) wake_up_all(&ctx->cq_wait); } if (io_should_trigger_evfd(ctx)) @@ -2439,13 +2442,6 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); - if (READ_ONCE(req->result) == -EAGAIN && - !(req->flags & REQ_F_DONT_REISSUE)) { - req->iopoll_completed = 0; - io_req_task_queue_reissue(req); - continue; - } - __io_cqring_fill_event(ctx, req->user_data, req->result, io_put_rw_kbuf(req)); (*nr_events)++; @@ -2608,8 +2604,7 @@ static bool io_resubmit_prep(struct io_kiocb *req) if (!rw) return !io_req_prep_async(req); - /* may have left rw->iter inconsistent on -EIOCBQUEUED */ - iov_iter_revert(&rw->iter, req->result - iov_iter_count(&rw->iter)); + iov_iter_restore(&rw->iter, &rw->iter_state); return true; } @@ -2709,10 +2704,9 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); if (unlikely(res != req->result)) { - if (!(res == -EAGAIN && io_rw_should_reissue(req) && - io_resubmit_prep(req))) { - req_set_fail(req); - req->flags |= REQ_F_DONT_REISSUE; + if (res == -EAGAIN && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; + return; } } @@ -2838,7 +2832,8 @@ static bool io_file_supports_nowait(struct io_kiocb *req, int rw) return __io_file_supports_nowait(req->file, rw); } -static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + int rw) { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; @@ -2860,8 +2855,13 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(ret)) return ret; - /* don't allow async punt for O_NONBLOCK or RWF_NOWAIT */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || (file->f_flags & O_NONBLOCK)) + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw))) req->flags |= REQ_F_NOWAIT; ioprio = READ_ONCE(sqe->ioprio); @@ -2926,7 +2926,6 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); struct io_async_rw *io = req->async_data; - bool check_reissue = kiocb->ki_complete == io_complete_rw; /* add previously done IO, if any */ if (io && io->bytes_done > 0) { @@ -2938,19 +2937,27 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; - if (ret >= 0 && check_reissue) + if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) __io_complete_rw(req, ret, 0, issue_flags); else io_rw_done(kiocb, ret); - if (check_reissue && (req->flags & REQ_F_REISSUE)) { + if (req->flags & REQ_F_REISSUE) { req->flags &= ~REQ_F_REISSUE; if (io_resubmit_prep(req)) { io_req_task_queue_reissue(req); } else { + unsigned int cflags = io_put_rw_kbuf(req); + struct io_ring_ctx *ctx = req->ctx; + req_set_fail(req); - __io_req_complete(req, issue_flags, ret, - io_put_rw_kbuf(req)); + if (issue_flags & IO_URING_F_NONBLOCK) { + mutex_lock(&ctx->uring_lock); + __io_req_complete(req, issue_flags, ret, cflags); + mutex_unlock(&ctx->uring_lock); + } else { + __io_req_complete(req, issue_flags, ret, cflags); + } } } } @@ -3258,12 +3265,15 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) ret = nr; break; } + if (!iov_iter_is_bvec(iter)) { + iov_iter_advance(iter, nr); + } else { + req->rw.len -= nr; + req->rw.addr += nr; + } ret += nr; if (nr != iovec.iov_len) break; - req->rw.len -= nr; - req->rw.addr += nr; - iov_iter_advance(iter, nr); } return ret; @@ -3310,12 +3320,17 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, if (!force && !io_op_defs[req->opcode].needs_async_setup) return 0; if (!req->async_data) { + struct io_async_rw *iorw; + if (io_alloc_async_data(req)) { kfree(iovec); return -ENOMEM; } io_req_map_rw(req, iovec, fast_iov, iter); + iorw = req->async_data; + /* we've copied and mapped the iter, ensure state is saved */ + iov_iter_save_state(&iorw->iter, &iorw->iter_state); } return 0; } @@ -3334,6 +3349,7 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) iorw->free_iovec = iov; if (iov) req->flags |= REQ_F_NEED_CLEANUP; + iov_iter_save_state(&iorw->iter, &iorw->iter_state); return 0; } @@ -3341,7 +3357,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - return io_prep_rw(req, sqe); + return io_prep_rw(req, sqe, READ); } /* @@ -3437,19 +3453,28 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; - ssize_t io_size, ret, ret2; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; if (rw) { iter = &rw->iter; + state = &rw->iter_state; + /* + * We come here from an earlier attempt, restore our state to + * match in case it doesn't. It's cheap enough that we don't + * need to make this conditional. + */ + iov_iter_restore(iter, state); iovec = NULL; } else { ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + state = &__state; + iov_iter_save_state(iter, state); } - io_size = iov_iter_count(iter); - req->result = io_size; + req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3463,7 +3488,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret ?: -EAGAIN; } - ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), io_size); + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) { kfree(iovec); return ret; @@ -3479,30 +3504,49 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) /* no retry on NONBLOCK nor RWF_NOWAIT */ if (req->flags & REQ_F_NOWAIT) goto done; - /* some cases will consume bytes even on error returns */ - iov_iter_reexpand(iter, iter->count + iter->truncated); - iov_iter_revert(iter, io_size - iov_iter_count(iter)); ret = 0; } else if (ret == -EIOCBQUEUED) { goto out_free; - } else if (ret <= 0 || ret == io_size || !force_nonblock || + } else if (ret <= 0 || ret == req->result || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { /* read all, failed, already did sync or don't want to retry */ goto done; } + /* + * Don't depend on the iter state matching what was consumed, or being + * untouched in case of error. Restore it and we'll advance it + * manually if we need to. + */ + iov_iter_restore(iter, state); + ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); if (ret2) return ret2; iovec = NULL; rw = req->async_data; - /* now use our persistent iterator, if we aren't already */ - iter = &rw->iter; + /* + * Now use our persistent iterator and state, if we aren't already. + * We've restored and mapped the iter to match. + */ + if (iter != &rw->iter) { + iter = &rw->iter; + state = &rw->iter_state; + } do { - io_size -= ret; + /* + * We end up here because of a partial read, either from + * above or inside this loop. Advance the iter by the bytes + * that were consumed. + */ + iov_iter_advance(iter, ret); + if (!iov_iter_count(iter)) + break; rw->bytes_done += ret; + iov_iter_save_state(iter, state); + /* if we can retry, do so with the callbacks armed */ if (!io_rw_should_retry(req)) { kiocb->ki_flags &= ~IOCB_WAITQ; @@ -3520,7 +3564,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return 0; /* we got some bytes, but not all. retry. */ kiocb->ki_flags &= ~IOCB_WAITQ; - } while (ret > 0 && ret < io_size); + iov_iter_restore(iter, state); + } while (ret > 0); done: kiocb_done(kiocb, ret, issue_flags); out_free: @@ -3534,7 +3579,7 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - return io_prep_rw(req, sqe); + return io_prep_rw(req, sqe, WRITE); } static int io_write(struct io_kiocb *req, unsigned int issue_flags) @@ -3543,19 +3588,24 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; - ssize_t ret, ret2, io_size; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; if (rw) { iter = &rw->iter; + state = &rw->iter_state; + iov_iter_restore(iter, state); iovec = NULL; } else { ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + state = &__state; + iov_iter_save_state(iter, state); } - io_size = iov_iter_count(iter); - req->result = io_size; + req->result = iov_iter_count(iter); + ret2 = 0; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3572,7 +3622,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) (req->flags & REQ_F_ISREG)) goto copy_iov; - ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), io_size); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) goto out_free; @@ -3619,9 +3669,9 @@ done: kiocb_done(kiocb, ret2, issue_flags); } else { copy_iov: - /* some cases will consume bytes even on error returns */ - iov_iter_reexpand(iter, iter->count + iter->truncated); - iov_iter_revert(iter, io_size - iov_iter_count(iter)); + iov_iter_restore(iter, state); + if (ret2 > 0) + iov_iter_advance(iter, ret2); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); return ret ?: -EAGAIN; } @@ -7510,6 +7560,14 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, break; } while (1); + if (uts) { + struct timespec64 ts; + + if (get_timespec64(&ts, uts)) + return -EFAULT; + timeout = timespec64_to_jiffies(&ts); + } + if (sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) @@ -7523,14 +7581,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } - if (uts) { - struct timespec64 ts; - - if (get_timespec64(&ts, uts)) - return -EFAULT; - timeout = timespec64_to_jiffies(&ts); - } - init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); @@ -8279,11 +8329,27 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } +static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, + struct io_rsrc_node *node, void *rsrc) +{ + struct io_rsrc_put *prsrc; + + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) + return -ENOMEM; + + prsrc->tag = *io_get_tag_slot(data, idx); + prsrc->rsrc = rsrc; + list_add(&prsrc->list, &node->rsrc_list); + return 0; +} + static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index) { struct io_ring_ctx *ctx = req->ctx; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_switch = false; struct io_fixed_file *file_slot; int ret = -EBADF; @@ -8299,9 +8365,22 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, slot_index = array_index_nospec(slot_index, ctx->nr_user_files); file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); - ret = -EBADF; - if (file_slot->file_ptr) - goto err; + + if (file_slot->file_ptr) { + struct file *old_file; + + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + + old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, slot_index, + ctx->rsrc_node, old_file); + if (ret) + goto err; + file_slot->file_ptr = 0; + needs_switch = true; + } *io_get_tag_slot(ctx->file_data, slot_index) = 0; io_fixed_file_set(file_slot, file); @@ -8313,27 +8392,14 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, ret = 0; err: + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->file_data); io_ring_submit_unlock(ctx, !force_nonblock); if (ret) fput(file); return ret; } -static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, - struct io_rsrc_node *node, void *rsrc) -{ - struct io_rsrc_put *prsrc; - - prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); - if (!prsrc) - return -ENOMEM; - - prsrc->tag = *io_get_tag_slot(data, idx); - prsrc->rsrc = rsrc; - list_add(&prsrc->list, &node->rsrc_list); - return 0; -} - static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_rsrc_update2 *up, unsigned nr_args) @@ -10550,8 +10616,17 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, if (ctx->flags & IORING_SETUP_SQPOLL) { sqd = ctx->sq_data; if (sqd) { + /* + * Observe the correct sqd->lock -> ctx->uring_lock + * ordering. Fine to drop uring_lock here, we hold + * a ref to the ctx. + */ + refcount_inc(&sqd->refs); + mutex_unlock(&ctx->uring_lock); mutex_lock(&sqd->lock); - tctx = sqd->thread->io_uring; + mutex_lock(&ctx->uring_lock); + if (sqd->thread) + tctx = sqd->thread->io_uring; } } else { tctx = current->io_uring; @@ -10565,16 +10640,20 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, if (ret) goto err; - if (sqd) + if (sqd) { mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } if (copy_to_user(arg, new_count, sizeof(new_count))) return -EFAULT; return 0; err: - if (sqd) + if (sqd) { mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } return ret; } @@ -10853,7 +10932,7 @@ static int __init io_uring_init(void) BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); - BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int)); + BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); diff --git a/fs/namei.c b/fs/namei.c index 95a881e0552b..1946d9667790 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -255,7 +255,7 @@ getname_kernel(const char * filename) void putname(struct filename *name) { - if (IS_ERR_OR_NULL(name)) + if (IS_ERR(name)) return; BUG_ON(name->refcnt <= 0); @@ -2467,7 +2467,7 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path return err; } -static int __filename_lookup(int dfd, struct filename *name, unsigned flags, +int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root) { int retval; @@ -2488,15 +2488,6 @@ static int __filename_lookup(int dfd, struct filename *name, unsigned flags, return retval; } -int filename_lookup(int dfd, struct filename *name, unsigned flags, - struct path *path, struct path *root) -{ - int retval = __filename_lookup(dfd, name, flags, path, root); - - putname(name); - return retval; -} - /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) @@ -2514,9 +2505,10 @@ static int path_parentat(struct nameidata *nd, unsigned flags, return err; } -static int __filename_parentat(int dfd, struct filename *name, - unsigned int flags, struct path *parent, - struct qstr *last, int *type) +/* Note: this does not consume "name" */ +static int filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type) { int retval; struct nameidata nd; @@ -2538,25 +2530,14 @@ static int __filename_parentat(int dfd, struct filename *name, return retval; } -static int filename_parentat(int dfd, struct filename *name, - unsigned int flags, struct path *parent, - struct qstr *last, int *type) -{ - int retval = __filename_parentat(dfd, name, flags, parent, last, type); - - putname(name); - return retval; -} - /* does lookup, returns the object with parent locked */ -struct dentry *kern_path_locked(const char *name, struct path *path) +static struct dentry *__kern_path_locked(struct filename *name, struct path *path) { struct dentry *d; struct qstr last; int type, error; - error = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path, - &last, &type); + error = filename_parentat(AT_FDCWD, name, 0, path, &last, &type); if (error) return ERR_PTR(error); if (unlikely(type != LAST_NORM)) { @@ -2572,10 +2553,23 @@ struct dentry *kern_path_locked(const char *name, struct path *path) return d; } +struct dentry *kern_path_locked(const char *name, struct path *path) +{ + struct filename *filename = getname_kernel(name); + struct dentry *res = __kern_path_locked(filename, path); + + putname(filename); + return res; +} + int kern_path(const char *name, unsigned int flags, struct path *path) { - return filename_lookup(AT_FDCWD, getname_kernel(name), - flags, path, NULL); + struct filename *filename = getname_kernel(name); + int ret = filename_lookup(AT_FDCWD, filename, flags, path, NULL); + + putname(filename); + return ret; + } EXPORT_SYMBOL(kern_path); @@ -2591,10 +2585,15 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { + struct filename *filename; struct path root = {.mnt = mnt, .dentry = dentry}; + int ret; + + filename = getname_kernel(name); /* the first argument of filename_lookup() is ignored with root */ - return filename_lookup(AT_FDCWD, getname_kernel(name), - flags , path, &root); + ret = filename_lookup(AT_FDCWD, filename, flags, path, &root); + putname(filename); + return ret; } EXPORT_SYMBOL(vfs_path_lookup); @@ -2798,8 +2797,11 @@ int path_pts(struct path *path) int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { - return filename_lookup(dfd, getname_flags(name, flags, empty), - flags, path, NULL); + struct filename *filename = getname_flags(name, flags, empty); + int ret = filename_lookup(dfd, filename, flags, path, NULL); + + putname(filename); + return ret; } EXPORT_SYMBOL(user_path_at_empty); @@ -3618,8 +3620,8 @@ struct file *do_file_open_root(const struct path *root, return file; } -static struct dentry *__filename_create(int dfd, struct filename *name, - struct path *path, unsigned int lookup_flags) +static struct dentry *filename_create(int dfd, struct filename *name, + struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; @@ -3634,7 +3636,7 @@ static struct dentry *__filename_create(int dfd, struct filename *name, */ lookup_flags &= LOOKUP_REVAL; - error = __filename_parentat(dfd, name, lookup_flags, path, &last, &type); + error = filename_parentat(dfd, name, lookup_flags, path, &last, &type); if (error) return ERR_PTR(error); @@ -3687,21 +3689,15 @@ out: return dentry; } -static inline struct dentry *filename_create(int dfd, struct filename *name, +struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { - struct dentry *res = __filename_create(dfd, name, path, lookup_flags); + struct filename *filename = getname_kernel(pathname); + struct dentry *res = filename_create(dfd, filename, path, lookup_flags); - putname(name); + putname(filename); return res; } - -struct dentry *kern_path_create(int dfd, const char *pathname, - struct path *path, unsigned int lookup_flags) -{ - return filename_create(dfd, getname_kernel(pathname), - path, lookup_flags); -} EXPORT_SYMBOL(kern_path_create); void done_path_create(struct path *path, struct dentry *dentry) @@ -3716,7 +3712,11 @@ EXPORT_SYMBOL(done_path_create); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { - return filename_create(dfd, getname(pathname), path, lookup_flags); + struct filename *filename = getname(pathname); + struct dentry *res = filename_create(dfd, filename, path, lookup_flags); + + putname(filename); + return res; } EXPORT_SYMBOL(user_path_create); @@ -3797,7 +3797,7 @@ static int do_mknodat(int dfd, struct filename *name, umode_t mode, if (error) goto out1; retry: - dentry = __filename_create(dfd, name, &path, lookup_flags); + dentry = filename_create(dfd, name, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out1; @@ -3897,7 +3897,7 @@ int do_mkdirat(int dfd, struct filename *name, umode_t mode) unsigned int lookup_flags = LOOKUP_DIRECTORY; retry: - dentry = __filename_create(dfd, name, &path, lookup_flags); + dentry = filename_create(dfd, name, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putname; @@ -3996,7 +3996,7 @@ int do_rmdir(int dfd, struct filename *name) int type; unsigned int lookup_flags = 0; retry: - error = __filename_parentat(dfd, name, lookup_flags, &path, &last, &type); + error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) goto exit1; @@ -4137,7 +4137,7 @@ int do_unlinkat(int dfd, struct filename *name) struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0; retry: - error = __filename_parentat(dfd, name, lookup_flags, &path, &last, &type); + error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) goto exit1; @@ -4266,7 +4266,7 @@ int do_symlinkat(struct filename *from, int newdfd, struct filename *to) goto out_putnames; } retry: - dentry = __filename_create(newdfd, to, &path, lookup_flags); + dentry = filename_create(newdfd, to, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putnames; @@ -4426,11 +4426,11 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: - error = __filename_lookup(olddfd, old, how, &old_path, NULL); + error = filename_lookup(olddfd, old, how, &old_path, NULL); if (error) goto out_putnames; - new_dentry = __filename_create(newdfd, new, &new_path, + new_dentry = filename_create(newdfd, new, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) @@ -4689,13 +4689,13 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd, target_flags = 0; retry: - error = __filename_parentat(olddfd, from, lookup_flags, &old_path, - &old_last, &old_type); + error = filename_parentat(olddfd, from, lookup_flags, &old_path, + &old_last, &old_type); if (error) goto put_names; - error = __filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, - &new_type); + error = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, + &new_type); if (error) goto exit1; diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 95006d1d29ab..fa1d99101f89 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -531,6 +531,7 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, /* Someone else created list structure for us */ if (inode) fsnotify_put_inode_ref(inode); + fsnotify_put_sb_connectors(conn); kmem_cache_free(fsnotify_mark_connector_cachep, conn); } diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c index a6ee23aadd28..2a66844b7ff8 100644 --- a/fs/qnx4/dir.c +++ b/fs/qnx4/dir.c @@ -15,13 +15,27 @@ #include <linux/buffer_head.h> #include "qnx4.h" +/* + * A qnx4 directory entry is an inode entry or link info + * depending on the status field in the last byte. The + * first byte is where the name start either way, and a + * zero means it's empty. + */ +union qnx4_directory_entry { + struct { + char de_name; + char de_pad[62]; + char de_status; + }; + struct qnx4_inode_entry inode; + struct qnx4_link_info link; +}; + static int qnx4_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); unsigned int offset; struct buffer_head *bh; - struct qnx4_inode_entry *de; - struct qnx4_link_info *le; unsigned long blknum; int ix, ino; int size; @@ -38,27 +52,30 @@ static int qnx4_readdir(struct file *file, struct dir_context *ctx) } ix = (ctx->pos >> QNX4_DIR_ENTRY_SIZE_BITS) % QNX4_INODES_PER_BLOCK; for (; ix < QNX4_INODES_PER_BLOCK; ix++, ctx->pos += QNX4_DIR_ENTRY_SIZE) { + union qnx4_directory_entry *de; + const char *name; + offset = ix * QNX4_DIR_ENTRY_SIZE; - de = (struct qnx4_inode_entry *) (bh->b_data + offset); - if (!de->di_fname[0]) + de = (union qnx4_directory_entry *) (bh->b_data + offset); + + if (!de->de_name) continue; - if (!(de->di_status & (QNX4_FILE_USED|QNX4_FILE_LINK))) + if (!(de->de_status & (QNX4_FILE_USED|QNX4_FILE_LINK))) continue; - if (!(de->di_status & QNX4_FILE_LINK)) - size = QNX4_SHORT_NAME_MAX; - else - size = QNX4_NAME_MAX; - size = strnlen(de->di_fname, size); - QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, de->di_fname)); - if (!(de->di_status & QNX4_FILE_LINK)) + if (!(de->de_status & QNX4_FILE_LINK)) { + size = sizeof(de->inode.di_fname); + name = de->inode.di_fname; ino = blknum * QNX4_INODES_PER_BLOCK + ix - 1; - else { - le = (struct qnx4_link_info*)de; - ino = ( le32_to_cpu(le->dl_inode_blk) - 1 ) * + } else { + size = sizeof(de->link.dl_fname); + name = de->link.dl_fname; + ino = ( le32_to_cpu(de->link.dl_inode_blk) - 1 ) * QNX4_INODES_PER_BLOCK + - le->dl_inode_ndx; + de->link.dl_inode_ndx; } - if (!dir_emit(ctx, de->di_fname, size, ino, DT_UNKNOWN)) { + size = strnlen(name, size); + QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, name)); + if (!dir_emit(ctx, name, size, ino, DT_UNKNOWN)) { brelse(bh); return 0; } diff --git a/fs/cifs_common/Makefile b/fs/smbfs_common/Makefile index 6fedd2f88a25..cafc61a3bfc3 100644 --- a/fs/cifs_common/Makefile +++ b/fs/smbfs_common/Makefile @@ -3,5 +3,5 @@ # Makefile for Linux filesystem routines that are shared by client and server. # -obj-$(CONFIG_CIFS_COMMON) += cifs_arc4.o -obj-$(CONFIG_CIFS_COMMON) += cifs_md4.o +obj-$(CONFIG_SMBFS_COMMON) += cifs_arc4.o +obj-$(CONFIG_SMBFS_COMMON) += cifs_md4.o diff --git a/fs/cifs_common/arc4.h b/fs/smbfs_common/arc4.h index 12e71ec033a1..12e71ec033a1 100644 --- a/fs/cifs_common/arc4.h +++ b/fs/smbfs_common/arc4.h diff --git a/fs/cifs_common/cifs_arc4.c b/fs/smbfs_common/cifs_arc4.c index b964cc682944..85ba15a60b13 100644 --- a/fs/cifs_common/cifs_arc4.c +++ b/fs/smbfs_common/cifs_arc4.c @@ -74,14 +74,14 @@ void cifs_arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int l EXPORT_SYMBOL_GPL(cifs_arc4_crypt); static int __init -init_cifs_common(void) +init_smbfs_common(void) { return 0; } static void __init -exit_cifs_common(void) +exit_smbfs_common(void) { } -module_init(init_cifs_common) -module_exit(exit_cifs_common) +module_init(init_smbfs_common) +module_exit(exit_smbfs_common) diff --git a/fs/cifs_common/cifs_md4.c b/fs/smbfs_common/cifs_md4.c index 50f78cfc6ce9..50f78cfc6ce9 100644 --- a/fs/cifs_common/cifs_md4.c +++ b/fs/smbfs_common/cifs_md4.c diff --git a/fs/cifs_common/md4.h b/fs/smbfs_common/md4.h index 5337becc699a..5337becc699a 100644 --- a/fs/cifs_common/md4.h +++ b/fs/smbfs_common/md4.h diff --git a/fs/cifs/smbfsctl.h b/fs/smbfs_common/smbfsctl.h index d0fc42061f49..926f87cd6af0 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/smbfs_common/smbfsctl.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: LGPL-2.1 */ +/* SPDX-License-Identifier: LGPL-2.1+ */ /* - * fs/cifs/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions + * SMB, CIFS, SMB2 FSCTL definitions * * Copyright (c) International Business Machines Corp., 2002,2013 * Author(s): Steve French (sfrench@us.ibm.com) @@ -19,11 +19,14 @@ * could be invoked from tools via a specialized hook into the VFS rather * than via the standard vfs entry points * - * See MS-SMB2 Section 2.2.31 (last checked June 2013, all of that list are + * See MS-SMB2 Section 2.2.31 (last checked September 2021, all of that list are * below). Additional detail on less common ones can be found in MS-FSCC * section 2.3. */ +#ifndef __SMBFSCTL_H +#define __SMBFSCTL_H + /* * FSCTL values are 32 bits and are constructed as * <device 16bits> <access 2bits> <function 12bits> <method 2bits> @@ -91,6 +94,7 @@ #define FSCTL_SET_ZERO_ON_DEALLOC 0x00090194 /* BB add struct */ #define FSCTL_SET_SHORT_NAME_BEHAVIOR 0x000901B4 /* BB add struct */ #define FSCTL_GET_INTEGRITY_INFORMATION 0x0009027C +#define FSCTL_GET_REFS_VOLUME_DATA 0x000902D8 /* See MS-FSCC 2.3.24 */ #define FSCTL_GET_RETRIEVAL_POINTERS_AND_REFCOUNT 0x000903d3 #define FSCTL_GET_RETRIEVAL_POINTER_COUNT 0x0009042b #define FSCTL_QUERY_ALLOCATED_RANGES 0x000940CF @@ -146,7 +150,13 @@ #define IO_REPARSE_TAG_LX_CHR 0x80000025 #define IO_REPARSE_TAG_LX_BLK 0x80000026 +#define IO_REPARSE_TAG_LX_SYMLINK_LE cpu_to_le32(0xA000001D) +#define IO_REPARSE_TAG_AF_UNIX_LE cpu_to_le32(0x80000023) +#define IO_REPARSE_TAG_LX_FIFO_LE cpu_to_le32(0x80000024) +#define IO_REPARSE_TAG_LX_CHR_LE cpu_to_le32(0x80000025) +#define IO_REPARSE_TAG_LX_BLK_LE cpu_to_le32(0x80000026) + /* fsctl flags */ /* If Flags is set to this value, the request is an FSCTL not ioctl request */ #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 - +#endif /* __SMBFSCTL_H */ |