diff options
Diffstat (limited to 'fs')
137 files changed, 2390 insertions, 1777 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 7385e54be4b9..312393f32948 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -96,6 +96,7 @@ endif # BLOCK menu "Pseudo filesystems" source "fs/proc/Kconfig" +source "fs/kernfs/Kconfig" source "fs/sysfs/Kconfig" config TMPFS diff --git a/fs/Makefile b/fs/Makefile index 47ac07bb4acc..f9cb9876e466 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -52,7 +52,8 @@ obj-$(CONFIG_FHANDLE) += fhandle.o obj-y += quota/ obj-$(CONFIG_PROC_FS) += proc/ -obj-$(CONFIG_SYSFS) += sysfs/ kernfs/ +obj-$(CONFIG_KERNFS) += kernfs/ +obj-$(CONFIG_SYSFS) += sysfs/ obj-$(CONFIG_CONFIGFS_FS) += configfs/ obj-y += devpts/ diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 6621f8008122..be75b500005d 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -75,6 +75,7 @@ struct afs_call { const struct afs_call_type *type; /* type of call */ const struct afs_wait_mode *wait_mode; /* completion wait mode */ wait_queue_head_t waitq; /* processes awaiting completion */ + work_func_t async_workfn; struct work_struct async_work; /* asynchronous work processor */ struct work_struct work; /* actual work processor */ struct sk_buff_head rx_queue; /* received packets */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 8ad8c2a0703a..ef943df73b8c 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -644,7 +644,7 @@ static void afs_process_async_call(struct work_struct *work) /* we can't just delete the call because the work item may be * queued */ - PREPARE_WORK(&call->async_work, afs_delete_async_call); + call->async_workfn = afs_delete_async_call; queue_work(afs_async_calls, &call->async_work); } @@ -663,6 +663,13 @@ void afs_transfer_reply(struct afs_call *call, struct sk_buff *skb) call->reply_size += len; } +static void afs_async_workfn(struct work_struct *work) +{ + struct afs_call *call = container_of(work, struct afs_call, async_work); + + call->async_workfn(work); +} + /* * accept the backlog of incoming calls */ @@ -685,7 +692,8 @@ static void afs_collect_incoming_call(struct work_struct *work) return; } - INIT_WORK(&call->async_work, afs_process_async_call); + call->async_workfn = afs_process_async_call; + INIT_WORK(&call->async_work, afs_async_workfn); call->wait_mode = &afs_async_incoming_call; call->type = &afs_RXCMxxxx; init_waitqueue_head(&call->waitq); diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 24084732b1d0..80ef38c73e5a 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -41,19 +41,8 @@ static const struct dentry_operations anon_inodefs_dentry_operations = { static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - struct dentry *root; - root = mount_pseudo(fs_type, "anon_inode:", NULL, + return mount_pseudo(fs_type, "anon_inode:", NULL, &anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC); - if (!IS_ERR(root)) { - struct super_block *s = root->d_sb; - anon_inode_inode = alloc_anon_inode(s); - if (IS_ERR(anon_inode_inode)) { - dput(root); - deactivate_locked_super(s); - root = ERR_CAST(anon_inode_inode); - } - } - return root; } static struct file_system_type anon_inode_fs_type = { @@ -175,22 +164,15 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd); static int __init anon_inode_init(void) { - int error; - - error = register_filesystem(&anon_inode_fs_type); - if (error) - goto err_exit; anon_inode_mnt = kern_mount(&anon_inode_fs_type); - if (IS_ERR(anon_inode_mnt)) { - error = PTR_ERR(anon_inode_mnt); - goto err_unregister_filesystem; - } - return 0; + if (IS_ERR(anon_inode_mnt)) + panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); -err_unregister_filesystem: - unregister_filesystem(&anon_inode_fs_type); -err_exit: - panic(KERN_ERR "anon_inode_init() failed (%d)\n", error); + anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); + if (IS_ERR(anon_inode_inode)) + panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); + + return 0; } fs_initcall(anon_inode_init); diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 0bad24ddc2e7..29696b78d1f4 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -114,6 +114,14 @@ void bio_integrity_free(struct bio *bio) } EXPORT_SYMBOL(bio_integrity_free); +static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip) +{ + if (bip->bip_slab == BIO_POOL_NONE) + return BIP_INLINE_VECS; + + return bvec_nr_vecs(bip->bip_slab); +} + /** * bio_integrity_add_page - Attach integrity metadata * @bio: bio to update @@ -129,7 +137,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, struct bio_integrity_payload *bip = bio->bi_integrity; struct bio_vec *iv; - if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) { + if (bip->bip_vcnt >= bip_integrity_vecs(bip)) { printk(KERN_ERR "%s: bip_vec full\n", __func__); return 0; } @@ -226,7 +234,8 @@ unsigned int bio_integrity_tag_size(struct bio *bio) } EXPORT_SYMBOL(bio_integrity_tag_size); -int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, int set) +static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, + int set) { struct bio_integrity_payload *bip = bio->bi_integrity; struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); @@ -292,25 +301,25 @@ int bio_integrity_get_tag(struct bio *bio, void *tag_buf, unsigned int len) EXPORT_SYMBOL(bio_integrity_get_tag); /** - * bio_integrity_generate - Generate integrity metadata for a bio - * @bio: bio to generate integrity metadata for - * - * Description: Generates integrity metadata for a bio by calling the - * block device's generation callback function. The bio must have a - * bip attached with enough room to accommodate the generated - * integrity metadata. + * bio_integrity_generate_verify - Generate/verify integrity metadata for a bio + * @bio: bio to generate/verify integrity metadata for + * @operate: operate number, 1 for generate, 0 for verify */ -static void bio_integrity_generate(struct bio *bio) +static int bio_integrity_generate_verify(struct bio *bio, int operate) { struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); struct blk_integrity_exchg bix; struct bio_vec bv; struct bvec_iter iter; - sector_t sector = bio->bi_iter.bi_sector; - unsigned int sectors, total; + sector_t sector; + unsigned int sectors, ret = 0; void *prot_buf = bio->bi_integrity->bip_buf; - total = 0; + if (operate) + sector = bio->bi_iter.bi_sector; + else + sector = bio->bi_integrity->bip_iter.bi_sector; + bix.disk_name = bio->bi_bdev->bd_disk->disk_name; bix.sector_size = bi->sector_size; @@ -321,16 +330,37 @@ static void bio_integrity_generate(struct bio *bio) bix.prot_buf = prot_buf; bix.sector = sector; - bi->generate_fn(&bix); + if (operate) { + bi->generate_fn(&bix); + } else { + ret = bi->verify_fn(&bix); + if (ret) { + kunmap_atomic(kaddr); + return ret; + } + } sectors = bv.bv_len / bi->sector_size; sector += sectors; prot_buf += sectors * bi->tuple_size; - total += sectors * bi->tuple_size; - BUG_ON(total > bio->bi_integrity->bip_iter.bi_size); kunmap_atomic(kaddr); } + return ret; +} + +/** + * bio_integrity_generate - Generate integrity metadata for a bio + * @bio: bio to generate integrity metadata for + * + * Description: Generates integrity metadata for a bio by calling the + * block device's generation callback function. The bio must have a + * bip attached with enough room to accommodate the generated + * integrity metadata. + */ +static void bio_integrity_generate(struct bio *bio) +{ + bio_integrity_generate_verify(bio, 1); } static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi) @@ -445,43 +475,7 @@ EXPORT_SYMBOL(bio_integrity_prep); */ static int bio_integrity_verify(struct bio *bio) { - struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); - struct blk_integrity_exchg bix; - struct bio_vec *bv; - sector_t sector = bio->bi_integrity->bip_iter.bi_sector; - unsigned int sectors, total, ret; - void *prot_buf = bio->bi_integrity->bip_buf; - int i; - - ret = total = 0; - bix.disk_name = bio->bi_bdev->bd_disk->disk_name; - bix.sector_size = bi->sector_size; - - bio_for_each_segment_all(bv, bio, i) { - void *kaddr = kmap_atomic(bv->bv_page); - - bix.data_buf = kaddr + bv->bv_offset; - bix.data_size = bv->bv_len; - bix.prot_buf = prot_buf; - bix.sector = sector; - - ret = bi->verify_fn(&bix); - - if (ret) { - kunmap_atomic(kaddr); - return ret; - } - - sectors = bv->bv_len / bi->sector_size; - sector += sectors; - prot_buf += sectors * bi->tuple_size; - total += sectors * bi->tuple_size; - BUG_ON(total > bio->bi_integrity->bip_iter.bi_size); - - kunmap_atomic(kaddr); - } - - return ret; + return bio_integrity_generate_verify(bio, 0); } /** @@ -116,7 +116,6 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) if (!slab) goto out_unlock; - printk(KERN_INFO "bio: create slab <%s> at %d\n", bslab->name, entry); bslab->slab = slab; bslab->slab_ref = 1; bslab->slab_size = sz; @@ -611,7 +610,6 @@ EXPORT_SYMBOL(bio_clone_fast); struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, struct bio_set *bs) { - unsigned nr_iovecs = 0; struct bvec_iter iter; struct bio_vec bv; struct bio *bio; @@ -638,10 +636,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, * __bio_clone_fast() anyways. */ - bio_for_each_segment(bv, bio_src, iter) - nr_iovecs++; - - bio = bio_alloc_bioset(gfp_mask, nr_iovecs, bs); + bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs); if (!bio) return NULL; @@ -650,9 +645,18 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; + if (bio->bi_rw & REQ_DISCARD) + goto integrity_clone; + + if (bio->bi_rw & REQ_WRITE_SAME) { + bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; + goto integrity_clone; + } + bio_for_each_segment(bv, bio_src, iter) bio->bi_io_vec[bio->bi_vcnt++] = bv; +integrity_clone: if (bio_integrity(bio_src)) { int ret; diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 49a62b4dda3b..0e8388e72d8d 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -92,11 +92,11 @@ #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/mutex.h> -#include <linux/crc32c.h> #include <linux/genhd.h> #include <linux/blkdev.h> #include "ctree.h" #include "disk-io.h" +#include "hash.h" #include "transaction.h" #include "extent_io.h" #include "volumes.h" @@ -1823,7 +1823,7 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state, size_t sublen = i ? PAGE_CACHE_SIZE : (PAGE_CACHE_SIZE - BTRFS_CSUM_SIZE); - crc = crc32c(crc, data, sublen); + crc = btrfs_crc32c(crc, data, sublen); } btrfs_csum_final(crc, csum); if (memcmp(csum, h->csum, state->csum_size)) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index e2600cdb6c25..b01fb6c527e3 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -1010,6 +1010,8 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start, bytes = min(bytes, working_bytes); kaddr = kmap_atomic(page_out); memcpy(kaddr + *pg_offset, buf + buf_offset, bytes); + if (*pg_index == (vcnt - 1) && *pg_offset == 0) + memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes); kunmap_atomic(kaddr); flush_dcache_page(page_out); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0e69295d0031..81ea55314b1f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -26,7 +26,6 @@ #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/freezer.h> -#include <linux/crc32c.h> #include <linux/slab.h> #include <linux/migrate.h> #include <linux/ratelimit.h> @@ -35,6 +34,7 @@ #include <asm/unaligned.h> #include "ctree.h" #include "disk-io.h" +#include "hash.h" #include "transaction.h" #include "btrfs_inode.h" #include "volumes.h" @@ -244,7 +244,7 @@ out: u32 btrfs_csum_data(char *data, u32 seed, size_t len) { - return crc32c(seed, data, len); + return btrfs_crc32c(seed, data, len); } void btrfs_csum_final(u32 crc, char *result) @@ -3839,7 +3839,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, rb_erase(&ref->rb_node, &head->ref_root); atomic_dec(&delayed_refs->num_entries); btrfs_put_delayed_ref(ref); - cond_resched_lock(&head->lock); } if (head->must_insert_reserved) pin_bytes = true; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9c9ecc93ae2c..32312e09f0f5 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2385,6 +2385,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, spin_unlock(&delayed_refs->lock); locked_ref = NULL; cond_resched(); + count++; continue; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5c4ab9c18940..d3d44486290b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2629,7 +2629,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) EXTENT_DEFRAG, 1, cached_state); if (ret) { u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item); - if (last_snapshot >= BTRFS_I(inode)->generation) + if (0 && last_snapshot >= BTRFS_I(inode)->generation) /* the inode is shared */ new = record_old_file_extents(inode, ordered_extent); @@ -5154,7 +5154,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, return ERR_CAST(inode); } - return d_splice_alias(inode, dentry); + return d_materialise_unique(dentry, inode); } unsigned char btrfs_filetype_table[] = { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b0134892dc70..a6d8efa46bfe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3537,20 +3537,6 @@ out: return ret; } -static long btrfs_ioctl_global_rsv(struct btrfs_root *root, void __user *arg) -{ - struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv; - u64 reserved; - - spin_lock(&block_rsv->lock); - reserved = block_rsv->reserved; - spin_unlock(&block_rsv->lock); - - if (arg && copy_to_user(arg, &reserved, sizeof(reserved))) - return -EFAULT; - return 0; -} - /* * there are many ways the trans_start and trans_end ioctls can lead * to deadlocks. They should only be used by applications that @@ -4525,7 +4511,7 @@ static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg) spin_lock(&root->fs_info->super_lock); strcpy(super_block->label, label); spin_unlock(&root->fs_info->super_lock); - ret = btrfs_end_transaction(trans, root); + ret = btrfs_commit_transaction(trans, root); out_unlock: mnt_drop_write_file(file); @@ -4668,7 +4654,7 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg) if (ret) return ret; - trans = btrfs_start_transaction(root, 1); + trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -4689,7 +4675,7 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg) btrfs_set_super_incompat_flags(super_block, newflags); spin_unlock(&root->fs_info->super_lock); - return btrfs_end_transaction(trans, root); + return btrfs_commit_transaction(trans, root); } long btrfs_ioctl(struct file *file, unsigned int @@ -4757,8 +4743,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_logical_to_ino(root, argp); case BTRFS_IOC_SPACE_INFO: return btrfs_ioctl_space_info(root, argp); - case BTRFS_IOC_GLOBAL_RSV: - return btrfs_ioctl_global_rsv(root, argp); case BTRFS_IOC_SYNC: { int ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 730dce395858..9dde9717c1b9 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -24,12 +24,12 @@ #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> #include <linux/radix-tree.h> -#include <linux/crc32c.h> #include <linux/vmalloc.h> #include <linux/string.h> #include "send.h" #include "backref.h" +#include "hash.h" #include "locking.h" #include "disk-io.h" #include "btrfs_inode.h" @@ -620,7 +620,7 @@ static int send_cmd(struct send_ctx *sctx) hdr->len = cpu_to_le32(sctx->send_size - sizeof(*hdr)); hdr->crc = 0; - crc = crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size); + crc = btrfs_crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size); hdr->crc = cpu_to_le32(crc); ret = write_buf(sctx->send_filp, sctx->send_buf, sctx->send_size, @@ -1332,6 +1332,16 @@ verbose_printk(KERN_DEBUG "btrfs: find_extent_clone: data_offset=%llu, " } if (cur_clone_root) { + if (compressed != BTRFS_COMPRESS_NONE) { + /* + * Offsets given by iterate_extent_inodes() are relative + * to the start of the extent, we need to add logical + * offset from the file extent item. + * (See why at backref.c:check_extent_in_eb()) + */ + cur_clone_root->offset += btrfs_file_extent_offset(eb, + fi); + } *found = cur_clone_root; ret = 0; } else { @@ -2774,8 +2784,6 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino) return 0; } -#ifdef CONFIG_BTRFS_ASSERT - static int del_waiting_dir_move(struct send_ctx *sctx, u64 ino) { struct rb_node *n = sctx->waiting_dir_moves.rb_node; @@ -2796,8 +2804,6 @@ static int del_waiting_dir_move(struct send_ctx *sctx, u64 ino) return -ENOENT; } -#endif - static int add_pending_dir_move(struct send_ctx *sctx, u64 parent_ino) { struct rb_node **p = &sctx->pending_dir_moves.rb_node; @@ -2902,7 +2908,9 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) } sctx->send_progress = sctx->cur_ino + 1; - ASSERT(del_waiting_dir_move(sctx, pm->ino) == 0); + ret = del_waiting_dir_move(sctx, pm->ino); + ASSERT(ret == 0); + ret = get_cur_path(sctx, pm->ino, pm->gen, to_path); if (ret < 0) goto out; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c02f63356895..d04db817be5c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -566,7 +566,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) kfree(num); if (info->max_inline) { - info->max_inline = max_t(u64, + info->max_inline = min_t(u64, info->max_inline, root->sectorsize); } @@ -855,6 +855,7 @@ static struct dentry *get_default_root(struct super_block *sb, struct btrfs_path *path; struct btrfs_key location; struct inode *inode; + struct dentry *dentry; u64 dir_id; int new = 0; @@ -925,7 +926,13 @@ setup_root: return dget(sb->s_root); } - return d_obtain_alias(inode); + dentry = d_obtain_alias(inode); + if (!IS_ERR(dentry)) { + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_DISCONNECTED; + spin_unlock(&dentry->d_lock); + } + return dentry; } static int btrfs_fill_super(struct super_block *sb, @@ -1996,7 +2003,7 @@ static void __exit exit_btrfs_fs(void) btrfs_hash_exit(); } -module_init(init_btrfs_fs) +late_initcall(init_btrfs_fs); module_exit(exit_btrfs_fs) MODULE_LICENSE("GPL"); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 782374d8fd19..865f4cf9a769 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -578,8 +578,14 @@ static int add_device_membership(struct btrfs_fs_info *fs_info) return -ENOMEM; list_for_each_entry(dev, &fs_devices->devices, dev_list) { - struct hd_struct *disk = dev->bdev->bd_part; - struct kobject *disk_kobj = &part_to_dev(disk)->kobj; + struct hd_struct *disk; + struct kobject *disk_kobj; + + if (!dev->bdev) + continue; + + disk = dev->bdev->bd_part; + disk_kobj = &part_to_dev(disk)->kobj; error = sysfs_create_link(fs_info->device_dir_kobj, disk_kobj, disk_kobj->name); diff --git a/fs/buffer.c b/fs/buffer.c index 651dba10b9c2..27265a8b43c1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -654,14 +654,16 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); static void __set_page_dirty(struct page *page, struct address_space *mapping, int warn) { - spin_lock_irq(&mapping->tree_lock); + unsigned long flags; + + spin_lock_irqsave(&mapping->tree_lock, flags); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); account_page_dirtied(page, mapping); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 4c2d452c4bfc..21887d63dad5 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -54,11 +54,6 @@ static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode, return acl; } -void ceph_forget_all_cached_acls(struct inode *inode) -{ - forget_all_cached_acls(inode); -} - struct posix_acl *ceph_get_acl(struct inode *inode, int type) { int size; @@ -160,11 +155,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) goto out_dput; } - if (value) - ret = __ceph_setxattr(dentry, name, value, size, 0); - else - ret = __ceph_removexattr(dentry, name); - + ret = __ceph_setxattr(dentry, name, value, size, 0); if (ret) { if (new_mode != old_mode) { newattrs.ia_mode = old_mode; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 6da4df84ba30..45eda6d7a40c 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -100,6 +100,14 @@ static unsigned fpos_off(loff_t p) return p & 0xffffffff; } +static int fpos_cmp(loff_t l, loff_t r) +{ + int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r)); + if (v) + return v; + return (int)(fpos_off(l) - fpos_off(r)); +} + /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on @@ -156,7 +164,7 @@ more: if (!d_unhashed(dentry) && dentry->d_inode && ceph_snap(dentry->d_inode) != CEPH_SNAPDIR && ceph_ino(dentry->d_inode) != CEPH_INO_CEPH && - ctx->pos <= di->offset) + fpos_cmp(ctx->pos, di->offset) <= 0) break; dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry, dentry->d_name.len, dentry->d_name.name, di->offset, @@ -695,9 +703,8 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry, ceph_mdsc_put_request(req); if (!err) - err = ceph_init_acl(dentry, dentry->d_inode, dir); - - if (err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } @@ -735,7 +742,9 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, if (!err && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); ceph_mdsc_put_request(req); - if (err) + if (!err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } @@ -776,7 +785,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) err = ceph_handle_notrace_create(dir, dentry); ceph_mdsc_put_request(req); out: - if (err < 0) + if (!err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index dfd2ce3419f8..09c7afe32e49 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -286,6 +286,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, } else { dout("atomic_open finish_open on dn %p\n", dn); if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) { + ceph_init_acl(dentry, dentry->d_inode, dir); *opened |= FILE_CREATED; } err = finish_open(file, dentry, ceph_open, opened); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 2df963f1cf5a..10a4ccbf38da 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -144,7 +144,11 @@ enum { Opt_ino32, Opt_noino32, Opt_fscache, - Opt_nofscache + Opt_nofscache, +#ifdef CONFIG_CEPH_FS_POSIX_ACL + Opt_acl, +#endif + Opt_noacl }; static match_table_t fsopt_tokens = { @@ -172,6 +176,10 @@ static match_table_t fsopt_tokens = { {Opt_noino32, "noino32"}, {Opt_fscache, "fsc"}, {Opt_nofscache, "nofsc"}, +#ifdef CONFIG_CEPH_FS_POSIX_ACL + {Opt_acl, "acl"}, +#endif + {Opt_noacl, "noacl"}, {-1, NULL} }; @@ -271,6 +279,14 @@ static int parse_fsopt_token(char *c, void *private) case Opt_nofscache: fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; break; +#ifdef CONFIG_CEPH_FS_POSIX_ACL + case Opt_acl: + fsopt->sb_flags |= MS_POSIXACL; + break; +#endif + case Opt_noacl: + fsopt->sb_flags &= ~MS_POSIXACL; + break; default: BUG_ON(token); } @@ -438,6 +454,13 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) else seq_puts(m, ",nofsc"); +#ifdef CONFIG_CEPH_FS_POSIX_ACL + if (fsopt->sb_flags & MS_POSIXACL) + seq_puts(m, ",acl"); + else + seq_puts(m, ",noacl"); +#endif + if (fsopt->wsize) seq_printf(m, ",wsize=%d", fsopt->wsize); if (fsopt->rsize != CEPH_RSIZE_DEFAULT) @@ -819,9 +842,6 @@ static int ceph_set_super(struct super_block *s, void *data) s->s_flags = fsc->mount_options->sb_flags; s->s_maxbytes = 1ULL << 40; /* temp value until we get mdsmap */ -#ifdef CONFIG_CEPH_FS_POSIX_ACL - s->s_flags |= MS_POSIXACL; -#endif s->s_xattr = ceph_xattr_handlers; s->s_fs_info = fsc; @@ -911,6 +931,10 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, struct ceph_options *opt = NULL; dout("ceph_mount\n"); + +#ifdef CONFIG_CEPH_FS_POSIX_ACL + flags |= MS_POSIXACL; +#endif err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path); if (err < 0) { res = ERR_PTR(err); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 19793b56d0a7..d8801a95b685 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -13,6 +13,7 @@ #include <linux/wait.h> #include <linux/writeback.h> #include <linux/slab.h> +#include <linux/posix_acl.h> #include <linux/ceph/libceph.h> @@ -743,7 +744,11 @@ extern const struct xattr_handler *ceph_xattr_handlers[]; struct posix_acl *ceph_get_acl(struct inode *, int); int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type); int ceph_init_acl(struct dentry *, struct inode *, struct inode *); -void ceph_forget_all_cached_acls(struct inode *inode); + +static inline void ceph_forget_all_cached_acls(struct inode *inode) +{ + forget_all_cached_acls(inode); +} #else diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 898b6565ad3e..a55ec37378c6 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -12,6 +12,9 @@ #define XATTR_CEPH_PREFIX "ceph." #define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1) +static int __remove_xattr(struct ceph_inode_info *ci, + struct ceph_inode_xattr *xattr); + /* * List of handlers for synthetic system.* attributes. Other * attributes are handled directly. @@ -319,8 +322,7 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode, static int __set_xattr(struct ceph_inode_info *ci, const char *name, int name_len, const char *val, int val_len, - int dirty, - int should_free_name, int should_free_val, + int flags, int update_xattr, struct ceph_inode_xattr **newxattr) { struct rb_node **p; @@ -349,12 +351,31 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr = NULL; } + if (update_xattr) { + int err = 0; + if (xattr && (flags & XATTR_CREATE)) + err = -EEXIST; + else if (!xattr && (flags & XATTR_REPLACE)) + err = -ENODATA; + if (err) { + kfree(name); + kfree(val); + return err; + } + if (update_xattr < 0) { + if (xattr) + __remove_xattr(ci, xattr); + kfree(name); + return 0; + } + } + if (!xattr) { new = 1; xattr = *newxattr; xattr->name = name; xattr->name_len = name_len; - xattr->should_free_name = should_free_name; + xattr->should_free_name = update_xattr; ci->i_xattrs.count++; dout("__set_xattr count=%d\n", ci->i_xattrs.count); @@ -364,7 +385,7 @@ static int __set_xattr(struct ceph_inode_info *ci, if (xattr->should_free_val) kfree((void *)xattr->val); - if (should_free_name) { + if (update_xattr) { kfree((void *)name); name = xattr->name; } @@ -379,8 +400,8 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr->val = ""; xattr->val_len = val_len; - xattr->dirty = dirty; - xattr->should_free_val = (val && should_free_val); + xattr->dirty = update_xattr; + xattr->should_free_val = (val && update_xattr); if (new) { rb_link_node(&xattr->node, parent, p); @@ -442,7 +463,7 @@ static int __remove_xattr(struct ceph_inode_info *ci, struct ceph_inode_xattr *xattr) { if (!xattr) - return -EOPNOTSUPP; + return -ENODATA; rb_erase(&xattr->node, &ci->i_xattrs.index); @@ -588,7 +609,7 @@ start: p += len; err = __set_xattr(ci, name, namelen, val, len, - 0, 0, 0, &xattrs[numattr]); + 0, 0, &xattrs[numattr]); if (err < 0) goto bad; @@ -850,6 +871,9 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name, dout("setxattr value=%.*s\n", (int)size, value); + if (!value) + flags |= CEPH_XATTR_REMOVE; + /* do request */ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR, USE_AUTH_MDS); @@ -892,7 +916,7 @@ int __ceph_setxattr(struct dentry *dentry, const char *name, struct ceph_inode_info *ci = ceph_inode(inode); int issued; int err; - int dirty; + int dirty = 0; int name_len = strlen(name); int val_len = size; char *newname = NULL; @@ -953,12 +977,14 @@ retry: goto retry; } - err = __set_xattr(ci, newname, name_len, newval, - val_len, 1, 1, 1, &xattr); + err = __set_xattr(ci, newname, name_len, newval, val_len, + flags, value ? 1 : -1, &xattr); - dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); - ci->i_xattrs.dirty = true; - inode->i_ctime = CURRENT_TIME; + if (!err) { + dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); + ci->i_xattrs.dirty = true; + inode->i_ctime = CURRENT_TIME; + } spin_unlock(&ci->i_ceph_lock); if (dirty) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 8f9b4f710d4a..7ff866dbb89e 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -865,8 +865,8 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, return rc; } -static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, - __u16 fid, u32 *pacllen) +struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, + const struct cifs_fid *cifsfid, u32 *pacllen) { struct cifs_ntsd *pntsd = NULL; unsigned int xid; @@ -877,7 +877,8 @@ static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, return ERR_CAST(tlink); xid = get_xid(); - rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), fid, &pntsd, pacllen); + rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd, + pacllen); free_xid(xid); cifs_put_tlink(tlink); @@ -946,7 +947,7 @@ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, if (!open_file) return get_cifs_acl_by_path(cifs_sb, path, pacllen); - pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->fid.netfid, pacllen); + pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen); cifsFileInfo_put(open_file); return pntsd; } @@ -1006,19 +1007,31 @@ out: /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */ int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, - struct inode *inode, const char *path, const __u16 *pfid) + struct inode *inode, const char *path, + const struct cifs_fid *pfid) { struct cifs_ntsd *pntsd = NULL; u32 acllen = 0; int rc = 0; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + struct cifs_tcon *tcon; cifs_dbg(NOISY, "converting ACL to mode for %s\n", path); - if (pfid) - pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen); - else - pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + if (pfid && (tcon->ses->server->ops->get_acl_by_fid)) + pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid, + &acllen); + else if (tcon->ses->server->ops->get_acl) + pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, + &acllen); + else { + cifs_put_tlink(tlink); + return -EOPNOTSUPP; + } /* if we can retrieve the ACL, now parse Access Control Entries, ACEs */ if (IS_ERR(pntsd)) { rc = PTR_ERR(pntsd); @@ -1030,6 +1043,8 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, cifs_dbg(VFS, "parse sec desc failed rc = %d\n", rc); } + cifs_put_tlink(tlink); + return rc; } @@ -1043,15 +1058,30 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, __u32 secdesclen = 0; struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */ struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + struct cifs_tcon *tcon; + + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); cifs_dbg(NOISY, "set ACL from mode for %s\n", path); /* Get the security descriptor */ - pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen); + + if (tcon->ses->server->ops->get_acl == NULL) { + cifs_put_tlink(tlink); + return -EOPNOTSUPP; + } + + pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, + &secdesclen); if (IS_ERR(pntsd)) { rc = PTR_ERR(pntsd); cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); - goto out; + cifs_put_tlink(tlink); + return rc; } /* @@ -1064,6 +1094,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, pnntsd = kmalloc(secdesclen, GFP_KERNEL); if (!pnntsd) { kfree(pntsd); + cifs_put_tlink(tlink); return -ENOMEM; } @@ -1072,14 +1103,18 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc); + if (tcon->ses->server->ops->set_acl == NULL) + rc = -EOPNOTSUPP; + if (!rc) { /* Set the security descriptor */ - rc = set_cifs_acl(pnntsd, secdesclen, inode, path, aclflag); + rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode, + path, aclflag); cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); } + cifs_put_tlink(tlink); kfree(pnntsd); kfree(pntsd); -out: return rc; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index a245d1809ed8..c0f3718b77a8 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -323,7 +323,8 @@ struct smb_version_operations { /* async read from the server */ int (*async_readv)(struct cifs_readdata *); /* async write to the server */ - int (*async_writev)(struct cifs_writedata *); + int (*async_writev)(struct cifs_writedata *, + void (*release)(struct kref *)); /* sync read from the server */ int (*sync_read)(const unsigned int, struct cifsFileInfo *, struct cifs_io_parms *, unsigned int *, char **, @@ -395,6 +396,12 @@ struct smb_version_operations { int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *, const char *, const void *, const __u16, const struct nls_table *, int); + struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *, + const char *, u32 *); + struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *, + const struct cifs_fid *, u32 *); + int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, + int); }; struct smb_version_values { @@ -506,7 +513,7 @@ struct cifs_mnt_data { static inline unsigned int get_rfc1002_length(void *buf) { - return be32_to_cpu(*((__be32 *)buf)); + return be32_to_cpu(*((__be32 *)buf)) & 0xffffff; } static inline void @@ -1064,7 +1071,7 @@ struct cifs_writedata { unsigned int pagesz; unsigned int tailsz; unsigned int nr_pages; - struct page *pages[1]; + struct page *pages[]; }; /* diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 79e6e9a93a8c..acc4ee8ed075 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -151,7 +151,7 @@ extern struct inode *cifs_iget(struct super_block *sb, extern int cifs_get_inode_info(struct inode **inode, const char *full_path, FILE_ALL_INFO *data, struct super_block *sb, - int xid, const __u16 *fid); + int xid, const struct cifs_fid *fid); extern int cifs_get_inode_info_unix(struct inode **pinode, const unsigned char *search_path, struct super_block *sb, unsigned int xid); @@ -162,11 +162,13 @@ extern int cifs_rename_pending_delete(const char *full_path, const unsigned int xid); extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, struct inode *inode, - const char *path, const __u16 *pfid); + const char *path, const struct cifs_fid *pfid); extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64, kuid_t, kgid_t); extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *, const char *, u32 *); +extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *, + const struct cifs_fid *, u32 *); extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *, const char *, int); @@ -488,7 +490,8 @@ void cifs_readdata_release(struct kref *refcount); int cifs_async_readv(struct cifs_readdata *rdata); int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid); -int cifs_async_writev(struct cifs_writedata *wdata); +int cifs_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)); void cifs_writev_complete(struct work_struct *work); struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 4d881c35eeca..f3264bd7a83d 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1910,7 +1910,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) do { server = tlink_tcon(wdata->cfile->tlink)->ses->server; - rc = server->ops->async_writev(wdata); + rc = server->ops->async_writev(wdata, cifs_writedata_release); } while (rc == -EAGAIN); for (i = 0; i < wdata->nr_pages; i++) { @@ -1962,15 +1962,9 @@ cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete) { struct cifs_writedata *wdata; - /* this would overflow */ - if (nr_pages == 0) { - cifs_dbg(VFS, "%s: called with nr_pages == 0!\n", __func__); - return NULL; - } - /* writedata + number of page pointers */ wdata = kzalloc(sizeof(*wdata) + - sizeof(struct page *) * (nr_pages - 1), GFP_NOFS); + sizeof(struct page *) * nr_pages, GFP_NOFS); if (wdata != NULL) { kref_init(&wdata->refcount); INIT_LIST_HEAD(&wdata->list); @@ -2031,7 +2025,8 @@ cifs_writev_callback(struct mid_q_entry *mid) /* cifs_async_writev - send an async write, and set up mid to handle result */ int -cifs_async_writev(struct cifs_writedata *wdata) +cifs_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)) { int rc = -EACCES; WRITE_REQ *smb = NULL; @@ -2105,7 +2100,7 @@ cifs_async_writev(struct cifs_writedata *wdata) if (rc == 0) cifs_stats_inc(&tcon->stats.cifs_stats.num_writes); else - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, release); async_writev_out: cifs_small_buf_release(smb); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index d3a6796caa5a..3db0c5fd9a11 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -378,7 +378,7 @@ cifs_create_get_file_info: xid); else { rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb, - xid, &fid->netfid); + xid, fid); if (newinode) { if (server->ops->set_lease_key) server->ops->set_lease_key(newinode, fid); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 853d6d1cc822..834fce759d80 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -244,7 +244,7 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, xid); else rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb, - xid, &fid->netfid); + xid, fid); out: kfree(buf); @@ -2043,7 +2043,8 @@ retry: } wdata->pid = wdata->cfile->pid; server = tlink_tcon(wdata->cfile->tlink)->ses->server; - rc = server->ops->async_writev(wdata); + rc = server->ops->async_writev(wdata, + cifs_writedata_release); } while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN); for (i = 0; i < nr_pages; ++i) @@ -2331,9 +2332,20 @@ size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len) } static void -cifs_uncached_writev_complete(struct work_struct *work) +cifs_uncached_writedata_release(struct kref *refcount) { int i; + struct cifs_writedata *wdata = container_of(refcount, + struct cifs_writedata, refcount); + + for (i = 0; i < wdata->nr_pages; i++) + put_page(wdata->pages[i]); + cifs_writedata_release(refcount); +} + +static void +cifs_uncached_writev_complete(struct work_struct *work) +{ struct cifs_writedata *wdata = container_of(work, struct cifs_writedata, work); struct inode *inode = wdata->cfile->dentry->d_inode; @@ -2347,12 +2359,7 @@ cifs_uncached_writev_complete(struct work_struct *work) complete(&wdata->done); - if (wdata->result != -EAGAIN) { - for (i = 0; i < wdata->nr_pages; i++) - put_page(wdata->pages[i]); - } - - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, cifs_uncached_writedata_release); } /* attempt to send write to server, retry on any -EAGAIN errors */ @@ -2370,7 +2377,8 @@ cifs_uncached_retry_writev(struct cifs_writedata *wdata) if (rc != 0) continue; } - rc = server->ops->async_writev(wdata); + rc = server->ops->async_writev(wdata, + cifs_uncached_writedata_release); } while (rc == -EAGAIN); return rc; @@ -2381,7 +2389,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, unsigned long nr_segs, loff_t *poffset) { unsigned long nr_pages, i; - size_t copied, len, cur_len; + size_t bytes, copied, len, cur_len; ssize_t total_written = 0; loff_t offset; struct iov_iter it; @@ -2436,14 +2444,45 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, save_len = cur_len; for (i = 0; i < nr_pages; i++) { - copied = min_t(const size_t, cur_len, PAGE_SIZE); + bytes = min_t(const size_t, cur_len, PAGE_SIZE); copied = iov_iter_copy_from_user(wdata->pages[i], &it, - 0, copied); + 0, bytes); cur_len -= copied; iov_iter_advance(&it, copied); + /* + * If we didn't copy as much as we expected, then that + * may mean we trod into an unmapped area. Stop copying + * at that point. On the next pass through the big + * loop, we'll likely end up getting a zero-length + * write and bailing out of it. + */ + if (copied < bytes) + break; } cur_len = save_len - cur_len; + /* + * If we have no data to send, then that probably means that + * the copy above failed altogether. That's most likely because + * the address in the iovec was bogus. Set the rc to -EFAULT, + * free anything we allocated and bail out. + */ + if (!cur_len) { + for (i = 0; i < nr_pages; i++) + put_page(wdata->pages[i]); + kfree(wdata); + rc = -EFAULT; + break; + } + + /* + * i + 1 now represents the number of pages we actually used in + * the copy phase above. Bring nr_pages down to that, and free + * any pages that we didn't use. + */ + for ( ; nr_pages > i + 1; nr_pages--) + put_page(wdata->pages[nr_pages - 1]); + wdata->sync_mode = WB_SYNC_ALL; wdata->nr_pages = nr_pages; wdata->offset = (__u64)offset; @@ -2454,7 +2493,8 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE); rc = cifs_uncached_retry_writev(wdata); if (rc) { - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, + cifs_uncached_writedata_release); break; } @@ -2496,7 +2536,7 @@ restart_loop: } } list_del_init(&wdata->list); - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, cifs_uncached_writedata_release); } if (total_written > 0) @@ -2539,31 +2579,19 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov, struct cifsInodeInfo *cinode = CIFS_I(inode); struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; ssize_t rc = -EACCES; + loff_t lock_pos = pos; - BUG_ON(iocb->ki_pos != pos); - + if (file->f_flags & O_APPEND) + lock_pos = i_size_read(inode); /* * We need to hold the sem to be sure nobody modifies lock list * with a brlock that prevents writing. */ down_read(&cinode->lock_sem); - if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs), + if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs), server->vals->exclusive_lock_type, NULL, - CIFS_WRITE_OP)) { - mutex_lock(&inode->i_mutex); - rc = __generic_file_aio_write(iocb, iov, nr_segs, - &iocb->ki_pos); - mutex_unlock(&inode->i_mutex); - } - - if (rc > 0) { - ssize_t err; - - err = generic_write_sync(file, pos, rc); - if (err < 0 && rc > 0) - rc = err; - } - + CIFS_WRITE_OP)) + rc = generic_file_aio_write(iocb, iov, nr_segs, pos); up_read(&cinode->lock_sem); return rc; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9cb9679d7357..aadc2b68678b 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -527,10 +527,15 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path, return PTR_ERR(tlink); tcon = tlink_tcon(tlink); - rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS", - ea_value, 4 /* size of buf */, cifs_sb->local_nls, - cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + if (tcon->ses->server->ops->query_all_EAs == NULL) { + cifs_put_tlink(tlink); + return -EOPNOTSUPP; + } + + rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path, + "SETFILEBITS", ea_value, 4 /* size of buf */, + cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); cifs_put_tlink(tlink); if (rc < 0) return (int)rc; @@ -672,7 +677,7 @@ cgfi_exit: int cifs_get_inode_info(struct inode **inode, const char *full_path, FILE_ALL_INFO *data, struct super_block *sb, int xid, - const __u16 *fid) + const struct cifs_fid *fid) { bool validinum = false; __u16 srchflgs; diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 9ac5bfc9cc56..526fb89f9230 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1067,6 +1067,15 @@ struct smb_version_operations smb1_operations = { .query_mf_symlink = cifs_query_mf_symlink, .create_mf_symlink = cifs_create_mf_symlink, .is_read_op = cifs_is_read_op, +#ifdef CONFIG_CIFS_XATTR + .query_all_EAs = CIFSSMBQAllEAs, + .set_EA = CIFSSMBSetEA, +#endif /* CIFS_XATTR */ +#ifdef CONFIG_CIFS_ACL + .get_acl = get_cifs_acl, + .get_acl_by_fid = get_cifs_acl_by_fid, + .set_acl = set_cifs_acl, +#endif /* CIFS_ACL */ }; struct smb_version_values smb1_values = { diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index c38350851b08..bc0bb9c34f72 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -57,4 +57,7 @@ #define SMB2_CMACAES_SIZE (16) #define SMB3_SIGNKEY_SIZE (16) +/* Maximum buffer size value we can send with 1 credit */ +#define SMB2_MAX_BUFFER_SIZE 65536 + #endif /* _SMB2_GLOB_H */ diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 757da3e54d3d..192f51a12cf1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -182,11 +182,8 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) /* start with specified wsize, or default */ wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE; wsize = min_t(unsigned int, wsize, server->max_write); - /* - * limit write size to 2 ** 16, because we don't support multicredit - * requests now. - */ - wsize = min_t(unsigned int, wsize, 2 << 15); + /* set it to the maximum buffer size value we can send with 1 credit */ + wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE); return wsize; } @@ -200,11 +197,8 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) /* start with specified rsize, or default */ rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE; rsize = min_t(unsigned int, rsize, server->max_read); - /* - * limit write size to 2 ** 16, because we don't support multicredit - * requests now. - */ - rsize = min_t(unsigned int, rsize, 2 << 15); + /* set it to the maximum buffer size value we can send with 1 credit */ + rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE); return rsize; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2013234b73ad..860344701067 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -413,7 +413,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) /* SMB2 only has an extended negflavor */ server->negflavor = CIFS_NEGFLAVOR_EXTENDED; - server->maxBuf = le32_to_cpu(rsp->MaxTransactSize); + /* set it to the maximum buffer size value we can send with 1 credit */ + server->maxBuf = min_t(unsigned int, le32_to_cpu(rsp->MaxTransactSize), + SMB2_MAX_BUFFER_SIZE); server->max_read = le32_to_cpu(rsp->MaxReadSize); server->max_write = le32_to_cpu(rsp->MaxWriteSize); /* BB Do we need to validate the SecurityMode? */ @@ -1890,7 +1892,8 @@ smb2_writev_callback(struct mid_q_entry *mid) /* smb2_async_writev - send an async write, and set up mid to handle result */ int -smb2_async_writev(struct cifs_writedata *wdata) +smb2_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)) { int rc = -EACCES; struct smb2_write_req *req = NULL; @@ -1938,7 +1941,7 @@ smb2_async_writev(struct cifs_writedata *wdata) smb2_writev_callback, wdata, 0); if (rc) { - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, release); cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); } diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 93adc64666f3..0ce48db20a65 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -123,7 +123,8 @@ extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, extern int smb2_async_readv(struct cifs_readdata *rdata); extern int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, char **buf, int *buf_type); -extern int smb2_async_writev(struct cifs_writedata *wdata); +extern int smb2_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)); extern int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, struct kvec *iov, int n_vec); extern int SMB2_echo(struct TCP_Server_Info *server); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b37570952846..18cd5650a5fc 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -270,6 +270,26 @@ cifs_rqst_page_to_kvec(struct smb_rqst *rqst, unsigned int idx, iov->iov_len = rqst->rq_pagesz; } +static unsigned long +rqst_len(struct smb_rqst *rqst) +{ + unsigned int i; + struct kvec *iov = rqst->rq_iov; + unsigned long buflen = 0; + + /* total up iov array first */ + for (i = 0; i < rqst->rq_nvec; i++) + buflen += iov[i].iov_len; + + /* add in the page array if there is one */ + if (rqst->rq_npages) { + buflen += rqst->rq_pagesz * (rqst->rq_npages - 1); + buflen += rqst->rq_tailsz; + } + + return buflen; +} + static int smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) { @@ -277,6 +297,7 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base); + unsigned long send_length; unsigned int i; size_t total_len = 0, sent; struct socket *ssocket = server->ssocket; @@ -285,6 +306,14 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) if (ssocket == NULL) return -ENOTSOCK; + /* sanity check send length */ + send_length = rqst_len(rqst); + if (send_length != smb_buf_length + 4) { + WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n", + send_length, smb_buf_length); + return -EIO; + } + cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length); dump_smb(iov[0].iov_base, iov[0].iov_len); diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 95c43bb20335..5ac836a86b18 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -176,8 +176,12 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, rc = -ENOMEM; } else { memcpy(pacl, ea_value, value_size); - rc = set_cifs_acl(pacl, value_size, - direntry->d_inode, full_path, CIFS_ACL_DACL); + if (pTcon->ses->server->ops->set_acl) + rc = pTcon->ses->server->ops->set_acl(pacl, + value_size, direntry->d_inode, + full_path, CIFS_ACL_DACL); + else + rc = -EOPNOTSUPP; if (rc == 0) /* force revalidate of the inode */ CIFS_I(direntry->d_inode)->time = 0; kfree(pacl); @@ -323,8 +327,11 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, u32 acllen; struct cifs_ntsd *pacl; - pacl = get_cifs_acl(cifs_sb, direntry->d_inode, - full_path, &acllen); + if (pTcon->ses->server->ops->get_acl == NULL) + goto get_ea_exit; /* rc already EOPNOTSUPP */ + + pacl = pTcon->ses->server->ops->get_acl(cifs_sb, + direntry->d_inode, full_path, &acllen); if (IS_ERR(pacl)) { rc = PTR_ERR(pacl); cifs_dbg(VFS, "%s: error %zd getting sec desc\n", diff --git a/fs/compat.c b/fs/compat.c index 62092f433759..f86df85dff61 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -72,8 +72,8 @@ int compat_printk(const char *fmt, ...) * Not all architectures have sys_utime, so implement this in terms * of sys_utimes. */ -asmlinkage long compat_sys_utime(const char __user *filename, - struct compat_utimbuf __user *t) +COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, + struct compat_utimbuf __user *, t) { struct timespec tv[2]; @@ -87,7 +87,7 @@ asmlinkage long compat_sys_utime(const char __user *filename, return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0); } -asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, struct compat_timespec __user *t, int flags) +COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags) { struct timespec tv[2]; @@ -102,7 +102,7 @@ asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filena return do_utimes(dfd, filename, t ? tv : NULL, flags); } -asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct compat_timeval __user *t) +COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t) { struct timespec tv[2]; @@ -121,7 +121,7 @@ asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filena return do_utimes(dfd, filename, t ? tv : NULL, 0); } -asmlinkage long compat_sys_utimes(const char __user *filename, struct compat_timeval __user *t) +COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t) { return compat_sys_futimesat(AT_FDCWD, filename, t); } @@ -159,8 +159,8 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; } -asmlinkage long compat_sys_newstat(const char __user * filename, - struct compat_stat __user *statbuf) +COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, + struct compat_stat __user *, statbuf) { struct kstat stat; int error; @@ -171,8 +171,8 @@ asmlinkage long compat_sys_newstat(const char __user * filename, return cp_compat_stat(&stat, statbuf); } -asmlinkage long compat_sys_newlstat(const char __user * filename, - struct compat_stat __user *statbuf) +COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, + struct compat_stat __user *, statbuf) { struct kstat stat; int error; @@ -184,9 +184,9 @@ asmlinkage long compat_sys_newlstat(const char __user * filename, } #ifndef __ARCH_WANT_STAT64 -asmlinkage long compat_sys_newfstatat(unsigned int dfd, - const char __user *filename, - struct compat_stat __user *statbuf, int flag) +COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, + const char __user *, filename, + struct compat_stat __user *, statbuf, int, flag) { struct kstat stat; int error; @@ -198,8 +198,8 @@ asmlinkage long compat_sys_newfstatat(unsigned int dfd, } #endif -asmlinkage long compat_sys_newfstat(unsigned int fd, - struct compat_stat __user * statbuf) +COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, + struct compat_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); @@ -247,7 +247,7 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs * * The following statfs calls are copies of code from fs/statfs.c and * should be checked against those from time to time */ -asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf) +COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf) { struct kstatfs tmp; int error = user_statfs(pathname, &tmp); @@ -256,7 +256,7 @@ asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_sta return error; } -asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf) +COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf) { struct kstatfs tmp; int error = fd_statfs(fd, &tmp); @@ -298,7 +298,7 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat return 0; } -asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf) +COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf) { struct kstatfs tmp; int error; @@ -312,7 +312,7 @@ asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t s return error; } -asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf) +COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf) { struct kstatfs tmp; int error; @@ -331,7 +331,7 @@ asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct c * Given how simple this syscall is that apporach is more maintainable * than the various conversion hacks. */ -asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u) +COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u) { struct compat_ustat tmp; struct kstatfs sbuf; @@ -399,8 +399,8 @@ static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *u } #endif -asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, - unsigned long arg) +COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg) { mm_segment_t old_fs; struct flock f; @@ -468,16 +468,15 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, return ret; } -asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, - unsigned long arg) +COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg) { if ((cmd == F_GETLK64) || (cmd == F_SETLK64) || (cmd == F_SETLKW64)) return -EINVAL; return compat_sys_fcntl64(fd, cmd, arg); } -asmlinkage long -compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p) +COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_reqs, u32 __user *, ctx32p) { long ret; aio_context_t ctx64; @@ -496,32 +495,24 @@ compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p) return ret; } -asmlinkage long -compat_sys_io_getevents(aio_context_t ctx_id, - unsigned long min_nr, - unsigned long nr, - struct io_event __user *events, - struct compat_timespec __user *timeout) +COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id, + compat_long_t, min_nr, + compat_long_t, nr, + struct io_event __user *, events, + struct compat_timespec __user *, timeout) { - long ret; struct timespec t; struct timespec __user *ut = NULL; - ret = -EFAULT; - if (unlikely(!access_ok(VERIFY_WRITE, events, - nr * sizeof(struct io_event)))) - goto out; if (timeout) { if (compat_get_timespec(&t, timeout)) - goto out; + return -EFAULT; ut = compat_alloc_user_space(sizeof(*ut)); if (copy_to_user(ut, &t, sizeof(t)) ) - goto out; + return -EFAULT; } - ret = sys_io_getevents(ctx_id, min_nr, nr, events, ut); -out: - return ret; + return sys_io_getevents(ctx_id, min_nr, nr, events, ut); } /* A write operation does a read from user space and vice versa */ @@ -617,8 +608,8 @@ copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64) #define MAX_AIO_SUBMITS (PAGE_SIZE/sizeof(struct iocb *)) -asmlinkage long -compat_sys_io_submit(aio_context_t ctx_id, int nr, u32 __user *iocb) +COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, + int, nr, u32 __user *, iocb) { struct iocb __user * __user *iocb64; long ret; @@ -770,10 +761,10 @@ static int do_nfs4_super_data_conv(void *raw_data) #define NCPFS_NAME "ncpfs" #define NFS4_NAME "nfs4" -asmlinkage long compat_sys_mount(const char __user * dev_name, - const char __user * dir_name, - const char __user * type, unsigned long flags, - const void __user * data) +COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, + const char __user *, dir_name, + const char __user *, type, compat_ulong_t, flags, + const void __user *, data) { char *kernel_type; unsigned long data_page; @@ -869,8 +860,8 @@ efault: return -EFAULT; } -asmlinkage long compat_sys_old_readdir(unsigned int fd, - struct compat_old_linux_dirent __user *dirent, unsigned int count) +COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, + struct compat_old_linux_dirent __user *, dirent, unsigned int, count) { int error; struct fd f = fdget(fd); @@ -948,8 +939,8 @@ efault: return -EFAULT; } -asmlinkage long compat_sys_getdents(unsigned int fd, - struct compat_linux_dirent __user *dirent, unsigned int count) +COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, + struct compat_linux_dirent __user *, dirent, unsigned int, count) { struct fd f; struct compat_linux_dirent __user * lastdirent; @@ -981,7 +972,7 @@ asmlinkage long compat_sys_getdents(unsigned int fd, return error; } -#ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64 +#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64 struct compat_getdents_callback64 { struct dir_context ctx; @@ -1033,8 +1024,8 @@ efault: return -EFAULT; } -asmlinkage long compat_sys_getdents64(unsigned int fd, - struct linux_dirent64 __user * dirent, unsigned int count) +COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd, + struct linux_dirent64 __user *, dirent, unsigned int, count) { struct fd f; struct linux_dirent64 __user * lastdirent; @@ -1066,7 +1057,7 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, fdput(f); return error; } -#endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */ +#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */ /* * Exactly like fs/open.c:sys_open(), except that it doesn't set the @@ -1287,9 +1278,9 @@ out_nofds: return ret; } -asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timeval __user *tvp) +COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, + compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, + struct compat_timeval __user *, tvp) { struct timespec end_time, *to = NULL; struct compat_timeval tv; @@ -1320,7 +1311,7 @@ struct compat_sel_arg_struct { compat_uptr_t tvp; }; -asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg) +COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { struct compat_sel_arg_struct a; @@ -1381,9 +1372,9 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp, return ret; } -asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timespec __user *tsp, void __user *sig) +COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, + compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, + struct compat_timespec __user *, tsp, void __user *, sig) { compat_size_t sigsetsize = 0; compat_uptr_t up = 0; @@ -1400,9 +1391,9 @@ asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, sigsetsize); } -asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, - unsigned int nfds, struct compat_timespec __user *tsp, - const compat_sigset_t __user *sigmask, compat_size_t sigsetsize) +COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, + unsigned int, nfds, struct compat_timespec __user *, tsp, + const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { compat_sigset_t ss32; sigset_t ksigmask, sigsaved; diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index a81147e2e4ef..4d24d17bcfc1 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -88,6 +88,11 @@ static void cputime_to_compat_timeval(const cputime_t cputime, #define ELF_HWCAP COMPAT_ELF_HWCAP #endif +#ifdef COMPAT_ELF_HWCAP2 +#undef ELF_HWCAP2 +#define ELF_HWCAP2 COMPAT_ELF_HWCAP2 +#endif + #ifdef COMPAT_ARCH_DLINFO #undef ARCH_DLINFO #define ARCH_DLINFO COMPAT_ARCH_DLINFO diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 3881610b6438..e82289047272 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1538,9 +1538,10 @@ static int compat_ioctl_check_table(unsigned int xcmd) return ioctl_pointer[i] == xcmd; } -asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, - unsigned long arg) +COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg32) { + unsigned long arg = arg32; struct fd f = fdget(fd); int error = -EBADF; if (!f.file) diff --git a/fs/dcache.c b/fs/dcache.c index 265e0ce9769c..ca02c13a84aa 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2833,9 +2833,9 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name) u32 dlen = ACCESS_ONCE(name->len); char *p; - if (*buflen < dlen + 1) - return -ENAMETOOLONG; *buflen -= dlen + 1; + if (*buflen < 0) + return -ENAMETOOLONG; p = *buffer -= dlen + 1; *p++ = '/'; while (dlen--) { diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 8dd524f32284..cdb2971192a5 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -21,7 +21,7 @@ static ssize_t efivarfs_file_write(struct file *file, u32 attributes; struct inode *inode = file->f_mapping->host; unsigned long datasize = count - sizeof(attributes); - ssize_t bytes = 0; + ssize_t bytes; bool set = false; if (count < sizeof(attributes)) @@ -33,14 +33,9 @@ static ssize_t efivarfs_file_write(struct file *file, if (attributes & ~(EFI_VARIABLE_MASK)) return -EINVAL; - data = kmalloc(datasize, GFP_KERNEL); - if (!data) - return -ENOMEM; - - if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) { - bytes = -EFAULT; - goto out; - } + data = memdup_user(userbuf + sizeof(attributes), datasize); + if (IS_ERR(data)) + return PTR_ERR(data); bytes = efivar_entry_set_get_size(var, attributes, &datasize, data, &set); diff --git a/fs/exec.c b/fs/exec.c index e1529b4c79b1..4f59402fdda5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -748,11 +748,10 @@ EXPORT_SYMBOL(setup_arg_pages); #endif /* CONFIG_MMU */ -struct file *open_exec(const char *name) +static struct file *do_open_exec(struct filename *name) { struct file *file; int err; - struct filename tmp = { .name = name }; static const struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC | MAY_OPEN, @@ -760,7 +759,7 @@ struct file *open_exec(const char *name) .lookup_flags = LOOKUP_FOLLOW, }; - file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags); + file = do_filp_open(AT_FDCWD, name, &open_exec_flags); if (IS_ERR(file)) goto out; @@ -784,6 +783,12 @@ exit: fput(file); return ERR_PTR(err); } + +struct file *open_exec(const char *name) +{ + struct filename tmp = { .name = name }; + return do_open_exec(&tmp); +} EXPORT_SYMBOL(open_exec); int kernel_read(struct file *file, loff_t offset, @@ -1162,7 +1167,7 @@ int prepare_bprm_creds(struct linux_binprm *bprm) return -ENOMEM; } -void free_bprm(struct linux_binprm *bprm) +static void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { @@ -1432,7 +1437,7 @@ static int exec_binprm(struct linux_binprm *bprm) /* * sys_execve() executes a new program. */ -static int do_execve_common(const char *filename, +static int do_execve_common(struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp) { @@ -1441,6 +1446,9 @@ static int do_execve_common(const char *filename, struct files_struct *displaced; int retval; + if (IS_ERR(filename)) + return PTR_ERR(filename); + /* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs @@ -1473,7 +1481,7 @@ static int do_execve_common(const char *filename, check_unsafe_exec(bprm); current->in_execve = 1; - file = open_exec(filename); + file = do_open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) goto out_unmark; @@ -1481,8 +1489,7 @@ static int do_execve_common(const char *filename, sched_exec(); bprm->file = file; - bprm->filename = filename; - bprm->interp = filename; + bprm->filename = bprm->interp = filename->name; retval = bprm_mm_init(bprm); if (retval) @@ -1523,6 +1530,7 @@ static int do_execve_common(const char *filename, acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); + putname(filename); if (displaced) put_files_struct(displaced); return retval; @@ -1544,10 +1552,11 @@ out_files: if (displaced) reset_files_struct(displaced); out_ret: + putname(filename); return retval; } -int do_execve(const char *filename, +int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { @@ -1557,7 +1566,7 @@ int do_execve(const char *filename, } #ifdef CONFIG_COMPAT -static int compat_do_execve(const char *filename, +static int compat_do_execve(struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp) { @@ -1607,25 +1616,13 @@ SYSCALL_DEFINE3(execve, const char __user *const __user *, argv, const char __user *const __user *, envp) { - struct filename *path = getname(filename); - int error = PTR_ERR(path); - if (!IS_ERR(path)) { - error = do_execve(path->name, argv, envp); - putname(path); - } - return error; + return do_execve(getname(filename), argv, envp); } #ifdef CONFIG_COMPAT -asmlinkage long compat_sys_execve(const char __user * filename, - const compat_uptr_t __user * argv, - const compat_uptr_t __user * envp) +COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename, + const compat_uptr_t __user *, argv, + const compat_uptr_t __user *, envp) { - struct filename *path = getname(filename); - int error = PTR_ERR(path); - if (!IS_ERR(path)) { - error = compat_do_execve(path->name, argv, envp); - putname(path); - } - return error; + return compat_do_execve(getname(filename), argv, envp); } #endif diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ece55565b9cd..d3a534fdc5ff 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -771,6 +771,8 @@ do { \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ (einode)->xtime.tv_sec = \ (signed)le32_to_cpu((raw_inode)->xtime); \ + else \ + (einode)->xtime.tv_sec = 0; \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \ ext4_decode_extra_time(&(einode)->xtime, \ raw_inode->xtime ## _extra); \ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 10cff4736b11..74bc2d549c58 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3906,6 +3906,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, } else err = ret; map->m_flags |= EXT4_MAP_MAPPED; + map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 43e64f6022eb..1a5073959f32 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -152,7 +152,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, if (ret > 0) { ssize_t err; - err = generic_write_sync(file, pos, ret); + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0 && ret > 0) ret = err; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6e39895a91b8..24bfd7ff3049 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -38,6 +38,7 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/aio.h> +#include <linux/bitops.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -3921,18 +3922,20 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) void ext4_set_inode_flags(struct inode *inode) { unsigned int flags = EXT4_I(inode)->i_flags; + unsigned int new_fl = 0; - inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); if (flags & EXT4_SYNC_FL) - inode->i_flags |= S_SYNC; + new_fl |= S_SYNC; if (flags & EXT4_APPEND_FL) - inode->i_flags |= S_APPEND; + new_fl |= S_APPEND; if (flags & EXT4_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; + new_fl |= S_IMMUTABLE; if (flags & EXT4_NOATIME_FL) - inode->i_flags |= S_NOATIME; + new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) - inode->i_flags |= S_DIRSYNC; + new_fl |= S_DIRSYNC; + set_mask_bits(&inode->i_flags, + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl); } /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */ diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 6bea80614d77..a2a837f00407 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -140,7 +140,7 @@ static long swap_inode_boot_loader(struct super_block *sb, handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; - goto swap_boot_out; + goto journal_err_out; } /* Protect extent tree against block allocations via delalloc */ @@ -198,6 +198,7 @@ static long swap_inode_boot_loader(struct super_block *sb, ext4_double_up_write_data_sem(inode, inode_bl); +journal_err_out: ext4_inode_resume_unlocked_dio(inode); ext4_inode_resume_unlocked_dio(inode_bl); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c5adbb318a90..f3b84cd9de56 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -243,6 +243,7 @@ static int ext4_alloc_group_tables(struct super_block *sb, ext4_group_t group; ext4_group_t last_group; unsigned overhead; + __u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0; BUG_ON(flex_gd->count == 0 || group_data == NULL); @@ -266,7 +267,7 @@ next_group: src_group++; for (; src_group <= last_group; src_group++) { overhead = ext4_group_overhead_blocks(sb, src_group); - if (overhead != 0) + if (overhead == 0) last_blk += group_data[src_group - group].blocks_count; else break; @@ -280,8 +281,7 @@ next_group: group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; - if (flexbg_size > 1) - flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT; + flex_gd->bg_flags[group] &= uninit_mask; } /* Allocate inode bitmaps */ @@ -292,22 +292,30 @@ next_group: group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; - if (flexbg_size > 1) - flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT; + flex_gd->bg_flags[group] &= uninit_mask; } /* Allocate inode tables */ for (; it_index < flex_gd->count; it_index++) { - if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk) + unsigned int itb = EXT4_SB(sb)->s_itb_per_group; + ext4_fsblk_t next_group_start; + + if (start_blk + itb > last_blk) goto next_group; group_data[it_index].inode_table = start_blk; - group = ext4_get_group_number(sb, start_blk - 1); + group = ext4_get_group_number(sb, start_blk); + next_group_start = ext4_group_first_block_no(sb, group + 1); group -= group_data[0].group; - group_data[group].free_blocks_count -= - EXT4_SB(sb)->s_itb_per_group; - if (flexbg_size > 1) - flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT; + if (start_blk + itb > next_group_start) { + flex_gd->bg_flags[group + 1] &= uninit_mask; + overhead = start_blk + itb - next_group_start; + group_data[group + 1].free_blocks_count -= overhead; + itb -= overhead; + } + + group_data[group].free_blocks_count -= itb; + flex_gd->bg_flags[group] &= uninit_mask; start_blk += EXT4_SB(sb)->s_itb_per_group; } @@ -401,7 +409,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, start = ext4_group_first_block_no(sb, group); group -= flex_gd->groups[0].group; - count2 = sb->s_blocksize * 8 - (block - start); + count2 = EXT4_BLOCKS_PER_GROUP(sb) - (block - start); if (count2 > count) count2 = count; @@ -620,7 +628,7 @@ handle_ib: if (err) goto out; count = group_table_count[j]; - start = group_data[i].block_bitmap; + start = (&group_data[i].block_bitmap)[j]; block = start; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1f7784de05b6..710fed2377d4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3695,16 +3695,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; - i = le32_to_cpu(es->s_flags); - if (i & EXT2_FLAGS_UNSIGNED_HASH) - sbi->s_hash_unsigned = 3; - else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { + if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + i = le32_to_cpu(es->s_flags); + if (i & EXT2_FLAGS_UNSIGNED_HASH) + sbi->s_hash_unsigned = 3; + else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { #ifdef __CHAR_UNSIGNED__ - es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); - sbi->s_hash_unsigned = 3; + if (!(sb->s_flags & MS_RDONLY)) + es->s_flags |= + cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); + sbi->s_hash_unsigned = 3; #else - es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); + if (!(sb->s_flags & MS_RDONLY)) + es->s_flags |= + cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); #endif + } } /* Handle clustersize */ diff --git a/fs/file.c b/fs/file.c index 771578b33fb6..b61293badfb1 100644 --- a/fs/file.c +++ b/fs/file.c @@ -34,7 +34,7 @@ static void *alloc_fdmem(size_t size) * vmalloc() if the allocation size will be considered "large" by the VM. */ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN); + void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY); if (data != NULL) return data; } @@ -497,7 +497,7 @@ repeat: error = fd; #if 1 /* Sanity check */ - if (rcu_dereference_raw(fdt->fd[fd]) != NULL) { + if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } @@ -683,35 +683,54 @@ EXPORT_SYMBOL(fget_raw); * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ -struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed) +static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; - *fput_needed = 0; if (atomic_read(&files->count) == 1) { file = __fcheck_files(files, fd); - if (file && (file->f_mode & mask)) - file = NULL; + if (!file || unlikely(file->f_mode & mask)) + return 0; + return (unsigned long)file; } else { file = __fget(fd, mask); - if (file) - *fput_needed = 1; + if (!file) + return 0; + return FDPUT_FPUT | (unsigned long)file; } - - return file; } -struct file *fget_light(unsigned int fd, int *fput_needed) +unsigned long __fdget(unsigned int fd) { - return __fget_light(fd, FMODE_PATH, fput_needed); + return __fget_light(fd, FMODE_PATH); } -EXPORT_SYMBOL(fget_light); +EXPORT_SYMBOL(__fdget); -struct file *fget_raw_light(unsigned int fd, int *fput_needed) +unsigned long __fdget_raw(unsigned int fd) { - return __fget_light(fd, 0, fput_needed); + return __fget_light(fd, 0); } +unsigned long __fdget_pos(unsigned int fd) +{ + unsigned long v = __fdget(fd); + struct file *file = (struct file *)(v & ~3); + + if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file_count(file) > 1) { + v |= FDPUT_POS_UNLOCK; + mutex_lock(&file->f_pos_lock); + } + } + return v; +} + +/* + * We only lock f_pos if we have threads or if the file might be + * shared with another process. In both cases we'll have an elevated + * file count (done either by fdget() or by fork()). + */ + void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; diff --git a/fs/file_table.c b/fs/file_table.c index 5fff9030be34..5b24008ea4f6 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -135,6 +135,7 @@ struct file *get_empty_filp(void) atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); + mutex_init(&f->f_pos_lock); eventpoll_init_file(f); /* f->f_version: 0 */ return f; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e0259a163f98..d754e3cf99a8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -40,18 +40,13 @@ struct wb_writeback_work { long nr_pages; struct super_block *sb; - /* - * Write only inodes dirtied before this time. Don't forget to set - * older_than_this_is_set when you set this. - */ - unsigned long older_than_this; + unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ - unsigned int older_than_this_is_set:1; enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ @@ -252,10 +247,10 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; - WARN_ON_ONCE(!work->older_than_this_is_set); while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (inode_dirtied_after(inode, work->older_than_this)) + if (work->older_than_this && + inode_dirtied_after(inode, *work->older_than_this)) break; list_move(&inode->i_wb_list, &tmp); moved++; @@ -742,8 +737,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, - .older_than_this = jiffies, - .older_than_this_is_set = 1, }; spin_lock(&wb->list_lock); @@ -802,13 +795,12 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; + unsigned long oldest_jif; struct inode *inode; long progress; - if (!work->older_than_this_is_set) { - work->older_than_this = jiffies; - work->older_than_this_is_set = 1; - } + oldest_jif = jiffies; + work->older_than_this = &oldest_jif; spin_lock(&wb->list_lock); for (;;) { @@ -842,10 +834,10 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - work->older_than_this = jiffies - + oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - work->older_than_this = jiffies; + oldest_jif = jiffies; trace_writeback_start(wb->bdi, work); if (list_empty(&wb->b_io)) @@ -1357,21 +1349,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages - * @sb: the superblock - * @older_than_this: timestamp + * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this - * superblock that has been dirtied before given timestamp. + * super_block. */ -void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this) +void sync_inodes_sb(struct super_block *sb) { DECLARE_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, - .older_than_this = older_than_this, - .older_than_this_is_set = 1, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index e1959efad64f..b5ebc2d7d80d 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -50,6 +50,8 @@ void fscache_objlist_add(struct fscache_object *obj) struct fscache_object *xobj; struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL; + ASSERT(RB_EMPTY_NODE(&obj->objlist_link)); + write_lock(&fscache_object_list_lock); while (*p) { @@ -75,6 +77,9 @@ void fscache_objlist_add(struct fscache_object *obj) */ void fscache_objlist_remove(struct fscache_object *obj) { + if (RB_EMPTY_NODE(&obj->objlist_link)) + return; + write_lock(&fscache_object_list_lock); BUG_ON(RB_EMPTY_ROOT(&fscache_object_list)); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 53d35c504240..d3b4539f1651 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -314,6 +314,9 @@ void fscache_object_init(struct fscache_object *object, object->cache = cache; object->cookie = cookie; object->parent = NULL; +#ifdef CONFIG_FSCACHE_OBJECT_LIST + RB_CLEAR_NODE(&object->objlist_link); +#endif object->oob_event_mask = 0; for (t = object->oob_table; t->events; t++) diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 968ce411db53..32602c667b4a 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -103,6 +103,8 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, folder = &entry->folder; memset(folder, 0, sizeof(*folder)); folder->type = cpu_to_be16(HFSPLUS_FOLDER); + if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) + folder->flags |= cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT); folder->id = cpu_to_be32(inode->i_ino); HFSPLUS_I(inode)->create_date = folder->create_date = @@ -203,6 +205,36 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid, return hfs_brec_find(fd, hfs_find_rec_by_key); } +static void hfsplus_subfolders_inc(struct inode *dir) +{ + struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); + + if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) { + /* + * Increment subfolder count. Note, the value is only meaningful + * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set. + */ + HFSPLUS_I(dir)->subfolders++; + } +} + +static void hfsplus_subfolders_dec(struct inode *dir) +{ + struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); + + if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) { + /* + * Decrement subfolder count. Note, the value is only meaningful + * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set. + * + * Check for zero. Some subfolders may have been created + * by an implementation ignorant of this counter. + */ + if (HFSPLUS_I(dir)->subfolders) + HFSPLUS_I(dir)->subfolders--; + } +} + int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct inode *inode) { @@ -247,6 +279,8 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, goto err1; dir->i_size++; + if (S_ISDIR(inode->i_mode)) + hfsplus_subfolders_inc(dir); dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); @@ -336,6 +370,8 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) goto out; dir->i_size--; + if (type == HFSPLUS_FOLDER) + hfsplus_subfolders_dec(dir); dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); @@ -380,6 +416,7 @@ int hfsplus_rename_cat(u32 cnid, hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset, src_fd.entrylength); + type = be16_to_cpu(entry.type); /* create new dir entry with the data from the old entry */ hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name); @@ -394,6 +431,8 @@ int hfsplus_rename_cat(u32 cnid, if (err) goto out; dst_dir->i_size++; + if (type == HFSPLUS_FOLDER) + hfsplus_subfolders_inc(dst_dir); dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC; /* finally remove the old entry */ @@ -405,6 +444,8 @@ int hfsplus_rename_cat(u32 cnid, if (err) goto out; src_dir->i_size--; + if (type == HFSPLUS_FOLDER) + hfsplus_subfolders_dec(src_dir); src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC; /* remove old thread entry */ diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 08846425b67f..62d571eb69ba 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -242,6 +242,7 @@ struct hfsplus_inode_info { */ sector_t fs_blocks; u8 userflags; /* BSD user file flags */ + u32 subfolders; /* Subfolder count (HFSX only) */ struct list_head open_dir_list; loff_t phys_size; diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h index 8ffb3a8ffe75..5a126828d85e 100644 --- a/fs/hfsplus/hfsplus_raw.h +++ b/fs/hfsplus/hfsplus_raw.h @@ -261,7 +261,7 @@ struct hfsplus_cat_folder { struct DInfo user_info; struct DXInfo finder_info; __be32 text_encoding; - u32 reserved; + __be32 subfolders; /* Subfolder count in HFSX. Reserved in HFS+. */ } __packed; /* HFS file info (stolen from hfs.h) */ @@ -301,11 +301,13 @@ struct hfsplus_cat_file { struct hfsplus_fork_raw rsrc_fork; } __packed; -/* File attribute bits */ +/* File and folder flag bits */ #define HFSPLUS_FILE_LOCKED 0x0001 #define HFSPLUS_FILE_THREAD_EXISTS 0x0002 #define HFSPLUS_XATTR_EXISTS 0x0004 #define HFSPLUS_ACL_EXISTS 0x0008 +#define HFSPLUS_HAS_FOLDER_COUNT 0x0010 /* Folder has subfolder count + * (HFSX only) */ /* HFS+ catalog thread (part of a cat_entry) */ struct hfsplus_cat_thread { diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index fa929f325f87..a4f45bd88a63 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -375,6 +375,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) hip->extent_state = 0; hip->flags = 0; hip->userflags = 0; + hip->subfolders = 0; memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec)); memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec)); hip->alloc_blocks = 0; @@ -494,6 +495,10 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date); HFSPLUS_I(inode)->create_date = folder->create_date; HFSPLUS_I(inode)->fs_blocks = 0; + if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) { + HFSPLUS_I(inode)->subfolders = + be32_to_cpu(folder->subfolders); + } inode->i_op = &hfsplus_dir_inode_operations; inode->i_fop = &hfsplus_dir_operations; } else if (type == HFSPLUS_FILE) { @@ -566,6 +571,10 @@ int hfsplus_cat_write_inode(struct inode *inode) folder->content_mod_date = hfsp_ut2mt(inode->i_mtime); folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime); folder->valence = cpu_to_be32(inode->i_size - 2); + if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) { + folder->subfolders = + cpu_to_be32(HFSPLUS_I(inode)->subfolders); + } hfs_bnode_write(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_folder)); } else if (HFSPLUS_IS_RSRC(inode)) { diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 968eab5bc1f5..68537e8b7a09 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -75,7 +75,7 @@ int hfsplus_parse_options_remount(char *input, int *force) int token; if (!input) - return 0; + return 1; while ((p = strsep(&input, ",")) != NULL) { if (!*p) diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c index cdb84a838068..58b5106186d0 100644 --- a/fs/hpfs/alloc.c +++ b/fs/hpfs/alloc.c @@ -8,6 +8,58 @@ #include "hpfs_fn.h" +static void hpfs_claim_alloc(struct super_block *s, secno sec) +{ + struct hpfs_sb_info *sbi = hpfs_sb(s); + if (sbi->sb_n_free != (unsigned)-1) { + if (unlikely(!sbi->sb_n_free)) { + hpfs_error(s, "free count underflow, allocating sector %08x", sec); + sbi->sb_n_free = -1; + return; + } + sbi->sb_n_free--; + } +} + +static void hpfs_claim_free(struct super_block *s, secno sec) +{ + struct hpfs_sb_info *sbi = hpfs_sb(s); + if (sbi->sb_n_free != (unsigned)-1) { + if (unlikely(sbi->sb_n_free >= sbi->sb_fs_size)) { + hpfs_error(s, "free count overflow, freeing sector %08x", sec); + sbi->sb_n_free = -1; + return; + } + sbi->sb_n_free++; + } +} + +static void hpfs_claim_dirband_alloc(struct super_block *s, secno sec) +{ + struct hpfs_sb_info *sbi = hpfs_sb(s); + if (sbi->sb_n_free_dnodes != (unsigned)-1) { + if (unlikely(!sbi->sb_n_free_dnodes)) { + hpfs_error(s, "dirband free count underflow, allocating sector %08x", sec); + sbi->sb_n_free_dnodes = -1; + return; + } + sbi->sb_n_free_dnodes--; + } +} + +static void hpfs_claim_dirband_free(struct super_block *s, secno sec) +{ + struct hpfs_sb_info *sbi = hpfs_sb(s); + if (sbi->sb_n_free_dnodes != (unsigned)-1) { + if (unlikely(sbi->sb_n_free_dnodes >= sbi->sb_dirband_size / 4)) { + hpfs_error(s, "dirband free count overflow, freeing sector %08x", sec); + sbi->sb_n_free_dnodes = -1; + return; + } + sbi->sb_n_free_dnodes++; + } +} + /* * Check if a sector is allocated in bitmap * This is really slow. Turned on only if chk==2 @@ -203,9 +255,15 @@ secno hpfs_alloc_sector(struct super_block *s, secno near, unsigned n, int forwa } sec = 0; ret: + if (sec) { + i = 0; + do + hpfs_claim_alloc(s, sec + i); + while (unlikely(++i < n)); + } if (sec && f_p) { for (i = 0; i < forward; i++) { - if (!hpfs_alloc_if_possible(s, sec + i + 1)) { + if (!hpfs_alloc_if_possible(s, sec + n + i)) { hpfs_error(s, "Prealloc doesn't work! Wanted %d, allocated at %08x, can't allocate %d", forward, sec, i); sec = 0; break; @@ -228,6 +286,7 @@ static secno alloc_in_dirband(struct super_block *s, secno near) nr >>= 2; sec = alloc_in_bmp(s, (~0x3fff) | nr, 1, 0); if (!sec) return 0; + hpfs_claim_dirband_alloc(s, sec); return ((sec & 0x3fff) << 2) + sbi->sb_dirband_start; } @@ -242,6 +301,7 @@ int hpfs_alloc_if_possible(struct super_block *s, secno sec) bmp[(sec & 0x3fff) >> 5] &= cpu_to_le32(~(1 << (sec & 0x1f))); hpfs_mark_4buffers_dirty(&qbh); hpfs_brelse4(&qbh); + hpfs_claim_alloc(s, sec); return 1; } hpfs_brelse4(&qbh); @@ -275,6 +335,7 @@ void hpfs_free_sectors(struct super_block *s, secno sec, unsigned n) return; } bmp[(sec & 0x3fff) >> 5] |= cpu_to_le32(1 << (sec & 0x1f)); + hpfs_claim_free(s, sec); if (!--n) { hpfs_mark_4buffers_dirty(&qbh); hpfs_brelse4(&qbh); @@ -359,6 +420,7 @@ void hpfs_free_dnode(struct super_block *s, dnode_secno dno) bmp[ssec >> 5] |= cpu_to_le32(1 << (ssec & 0x1f)); hpfs_mark_4buffers_dirty(&qbh); hpfs_brelse4(&qbh); + hpfs_claim_dirband_free(s, dno); } } @@ -366,7 +428,7 @@ struct dnode *hpfs_alloc_dnode(struct super_block *s, secno near, dnode_secno *dno, struct quad_buffer_head *qbh) { struct dnode *d; - if (hpfs_count_one_bitmap(s, hpfs_sb(s)->sb_dmap) > FREE_DNODES_ADD) { + if (hpfs_get_free_dnodes(s) > FREE_DNODES_ADD) { if (!(*dno = alloc_in_dirband(s, near))) if (!(*dno = hpfs_alloc_sector(s, near, 4, 0))) return NULL; } else { diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c index 4d0a1afa058c..139ef1684d07 100644 --- a/fs/hpfs/buffer.c +++ b/fs/hpfs/buffer.c @@ -86,7 +86,6 @@ void *hpfs_get_sector(struct super_block *s, unsigned secno, struct buffer_head void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffer_head *qbh, int ahead) { - struct buffer_head *bh; char *data; hpfs_lock_assert(s); @@ -100,34 +99,32 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe hpfs_prefetch_sectors(s, secno, 4 + ahead); + if (!(qbh->bh[0] = sb_bread(s, secno + 0))) goto bail0; + if (!(qbh->bh[1] = sb_bread(s, secno + 1))) goto bail1; + if (!(qbh->bh[2] = sb_bread(s, secno + 2))) goto bail2; + if (!(qbh->bh[3] = sb_bread(s, secno + 3))) goto bail3; + + if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) && + likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) && + likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) { + return qbh->data = qbh->bh[0]->b_data; + } + qbh->data = data = kmalloc(2048, GFP_NOFS); if (!data) { printk("HPFS: hpfs_map_4sectors: out of memory\n"); - goto bail; + goto bail4; } - qbh->bh[0] = bh = sb_bread(s, secno); - if (!bh) - goto bail0; - memcpy(data, bh->b_data, 512); - - qbh->bh[1] = bh = sb_bread(s, secno + 1); - if (!bh) - goto bail1; - memcpy(data + 512, bh->b_data, 512); - - qbh->bh[2] = bh = sb_bread(s, secno + 2); - if (!bh) - goto bail2; - memcpy(data + 2 * 512, bh->b_data, 512); - - qbh->bh[3] = bh = sb_bread(s, secno + 3); - if (!bh) - goto bail3; - memcpy(data + 3 * 512, bh->b_data, 512); + memcpy(data + 0 * 512, qbh->bh[0]->b_data, 512); + memcpy(data + 1 * 512, qbh->bh[1]->b_data, 512); + memcpy(data + 2 * 512, qbh->bh[2]->b_data, 512); + memcpy(data + 3 * 512, qbh->bh[3]->b_data, 512); return data; + bail4: + brelse(qbh->bh[3]); bail3: brelse(qbh->bh[2]); bail2: @@ -135,9 +132,6 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe bail1: brelse(qbh->bh[0]); bail0: - kfree(data); - printk("HPFS: hpfs_map_4sectors: read error\n"); - bail: return NULL; } @@ -155,44 +149,54 @@ void *hpfs_get_4sectors(struct super_block *s, unsigned secno, return NULL; } - /*return hpfs_map_4sectors(s, secno, qbh, 0);*/ + if (!hpfs_get_sector(s, secno + 0, &qbh->bh[0])) goto bail0; + if (!hpfs_get_sector(s, secno + 1, &qbh->bh[1])) goto bail1; + if (!hpfs_get_sector(s, secno + 2, &qbh->bh[2])) goto bail2; + if (!hpfs_get_sector(s, secno + 3, &qbh->bh[3])) goto bail3; + + if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) && + likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) && + likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) { + return qbh->data = qbh->bh[0]->b_data; + } + if (!(qbh->data = kmalloc(2048, GFP_NOFS))) { printk("HPFS: hpfs_get_4sectors: out of memory\n"); - return NULL; + goto bail4; } - if (!(hpfs_get_sector(s, secno, &qbh->bh[0]))) goto bail0; - if (!(hpfs_get_sector(s, secno + 1, &qbh->bh[1]))) goto bail1; - if (!(hpfs_get_sector(s, secno + 2, &qbh->bh[2]))) goto bail2; - if (!(hpfs_get_sector(s, secno + 3, &qbh->bh[3]))) goto bail3; - memcpy(qbh->data, qbh->bh[0]->b_data, 512); - memcpy(qbh->data + 512, qbh->bh[1]->b_data, 512); - memcpy(qbh->data + 2*512, qbh->bh[2]->b_data, 512); - memcpy(qbh->data + 3*512, qbh->bh[3]->b_data, 512); return qbh->data; - bail3: brelse(qbh->bh[2]); - bail2: brelse(qbh->bh[1]); - bail1: brelse(qbh->bh[0]); - bail0: +bail4: + brelse(qbh->bh[3]); +bail3: + brelse(qbh->bh[2]); +bail2: + brelse(qbh->bh[1]); +bail1: + brelse(qbh->bh[0]); +bail0: return NULL; } void hpfs_brelse4(struct quad_buffer_head *qbh) { - brelse(qbh->bh[3]); - brelse(qbh->bh[2]); - brelse(qbh->bh[1]); + if (unlikely(qbh->data != qbh->bh[0]->b_data)) + kfree(qbh->data); brelse(qbh->bh[0]); - kfree(qbh->data); + brelse(qbh->bh[1]); + brelse(qbh->bh[2]); + brelse(qbh->bh[3]); } void hpfs_mark_4buffers_dirty(struct quad_buffer_head *qbh) { - memcpy(qbh->bh[0]->b_data, qbh->data, 512); - memcpy(qbh->bh[1]->b_data, qbh->data + 512, 512); - memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512); - memcpy(qbh->bh[3]->b_data, qbh->data + 3 * 512, 512); + if (unlikely(qbh->data != qbh->bh[0]->b_data)) { + memcpy(qbh->bh[0]->b_data, qbh->data + 0 * 512, 512); + memcpy(qbh->bh[1]->b_data, qbh->data + 1 * 512, 512); + memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512); + memcpy(qbh->bh[3]->b_data, qbh->data + 3 * 512, 512); + } mark_buffer_dirty(qbh->bh[0]); mark_buffer_dirty(qbh->bh[1]); mark_buffer_dirty(qbh->bh[2]); diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 6797bf80f6e2..3ba49c080e42 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -312,7 +312,7 @@ static inline struct hpfs_sb_info *hpfs_sb(struct super_block *sb) __printf(2, 3) void hpfs_error(struct super_block *, const char *, ...); int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *); -unsigned hpfs_count_one_bitmap(struct super_block *, secno); +unsigned hpfs_get_free_dnodes(struct super_block *); /* * local time (HPFS) to GMT (Unix) diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index b8d01ef6f531..4534ff688b76 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -121,7 +121,7 @@ static void hpfs_put_super(struct super_block *s) call_rcu(&hpfs_sb(s)->rcu, lazy_free_sbi); } -unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno) +static unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno) { struct quad_buffer_head qbh; unsigned long *bits; @@ -129,7 +129,7 @@ unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno) bits = hpfs_map_4sectors(s, secno, &qbh, 0); if (!bits) - return 0; + return (unsigned)-1; count = bitmap_weight(bits, 2048 * BITS_PER_BYTE); hpfs_brelse4(&qbh); return count; @@ -144,30 +144,45 @@ static unsigned count_bitmaps(struct super_block *s) hpfs_prefetch_bitmap(s, n); } for (n = 0; n < n_bands; n++) { + unsigned c; hpfs_prefetch_bitmap(s, n + COUNT_RD_AHEAD); - count += hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n])); + c = hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n])); + if (c != (unsigned)-1) + count += c; } return count; } +unsigned hpfs_get_free_dnodes(struct super_block *s) +{ + struct hpfs_sb_info *sbi = hpfs_sb(s); + if (sbi->sb_n_free_dnodes == (unsigned)-1) { + unsigned c = hpfs_count_one_bitmap(s, sbi->sb_dmap); + if (c == (unsigned)-1) + return 0; + sbi->sb_n_free_dnodes = c; + } + return sbi->sb_n_free_dnodes; +} + static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(s); u64 id = huge_encode_dev(s->s_bdev->bd_dev); + hpfs_lock(s); - /*if (sbi->sb_n_free == -1) {*/ + if (sbi->sb_n_free == (unsigned)-1) sbi->sb_n_free = count_bitmaps(s); - sbi->sb_n_free_dnodes = hpfs_count_one_bitmap(s, sbi->sb_dmap); - /*}*/ + buf->f_type = s->s_magic; buf->f_bsize = 512; buf->f_blocks = sbi->sb_fs_size; buf->f_bfree = sbi->sb_n_free; buf->f_bavail = sbi->sb_n_free; buf->f_files = sbi->sb_dirband_size / 4; - buf->f_ffree = sbi->sb_n_free_dnodes; + buf->f_ffree = hpfs_get_free_dnodes(s); buf->f_fsid.val[0] = (u32)id; buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = 254; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 8360674c85bc..60bb365f54a5 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -514,11 +514,13 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, * similarly constrained call sites */ ret = start_this_handle(journal, handle, GFP_NOFS); - if (ret < 0) + if (ret < 0) { jbd2_journal_free_reserved(handle); + return ret; + } handle->h_type = type; handle->h_line_no = line_no; - return ret; + return 0; } EXPORT_SYMBOL(jbd2_journal_start_reserved); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index e973b85d6afd..5a8ea16eedbc 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -86,6 +86,8 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, rc = posix_acl_equiv_mode(acl, &inode->i_mode); if (rc < 0) return rc; + inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); if (rc == 0) acl = NULL; break; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 3bd5ee45f7b3..46325d5c34fc 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -854,9 +854,6 @@ int jfs_setxattr(struct dentry *dentry, const char *name, const void *value, int rc; tid_t tid; - if ((rc = can_set_xattr(inode, name, value, value_len))) - return rc; - /* * If this is a request for a synthetic attribute in the system.* * namespace use the generic infrastructure to resolve a handler @@ -865,6 +862,9 @@ int jfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_setxattr(dentry, name, value, value_len, flags); + if ((rc = can_set_xattr(inode, name, value, value_len))) + return rc; + if (value == NULL) { /* empty EA, do not remove */ value = ""; value_len = 0; @@ -1034,9 +1034,6 @@ int jfs_removexattr(struct dentry *dentry, const char *name) int rc; tid_t tid; - if ((rc = can_set_xattr(inode, name, NULL, 0))) - return rc; - /* * If this is a request for a synthetic attribute in the system.* * namespace use the generic infrastructure to resolve a handler @@ -1045,6 +1042,9 @@ int jfs_removexattr(struct dentry *dentry, const char *name) if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return generic_removexattr(dentry, name); + if ((rc = can_set_xattr(inode, name, NULL, 0))) + return rc; + tid = txBegin(inode->i_sb, 0); mutex_lock(&ji->commit_mutex); rc = __jfs_setxattr(tid, dentry->d_inode, name, NULL, 0, XATTR_REPLACE); @@ -1061,7 +1061,7 @@ int jfs_removexattr(struct dentry *dentry, const char *name) * attributes are handled directly. */ const struct xattr_handler *jfs_xattr_handlers[] = { -#ifdef JFS_POSIX_ACL +#ifdef CONFIG_JFS_POSIX_ACL &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, #endif diff --git a/fs/kernfs/Kconfig b/fs/kernfs/Kconfig new file mode 100644 index 000000000000..397b5f7a7a16 --- /dev/null +++ b/fs/kernfs/Kconfig @@ -0,0 +1,7 @@ +# +# KERNFS should be selected by its users +# + +config KERNFS + bool + default n diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 5104cf5d25c5..0bd05ab26003 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -8,6 +8,7 @@ * This file is released under the GPLv2. */ +#include <linux/sched.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/idr.h> @@ -18,9 +19,161 @@ #include "kernfs-internal.h" DEFINE_MUTEX(kernfs_mutex); +static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ +static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by rename_lock */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) +static bool kernfs_active(struct kernfs_node *kn) +{ + lockdep_assert_held(&kernfs_mutex); + return atomic_read(&kn->active) >= 0; +} + +static bool kernfs_lockdep(struct kernfs_node *kn) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + return kn->flags & KERNFS_LOCKDEP; +#else + return false; +#endif +} + +static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) +{ + return strlcpy(buf, kn->parent ? kn->name : "/", buflen); +} + +static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf, + size_t buflen) +{ + char *p = buf + buflen; + int len; + + *--p = '\0'; + + do { + len = strlen(kn->name); + if (p - buf < len + 1) { + buf[0] = '\0'; + p = NULL; + break; + } + p -= len; + memcpy(p, kn->name, len); + *--p = '/'; + kn = kn->parent; + } while (kn && kn->parent); + + return p; +} + +/** + * kernfs_name - obtain the name of a given node + * @kn: kernfs_node of interest + * @buf: buffer to copy @kn's name into + * @buflen: size of @buf + * + * Copies the name of @kn into @buf of @buflen bytes. The behavior is + * similar to strlcpy(). It returns the length of @kn's name and if @buf + * isn't long enough, it's filled upto @buflen-1 and nul terminated. + * + * This function can be called from any context. + */ +int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&kernfs_rename_lock, flags); + ret = kernfs_name_locked(kn, buf, buflen); + spin_unlock_irqrestore(&kernfs_rename_lock, flags); + return ret; +} + +/** + * kernfs_path - build full path of a given node + * @kn: kernfs_node of interest + * @buf: buffer to copy @kn's name into + * @buflen: size of @buf + * + * Builds and returns the full path of @kn in @buf of @buflen bytes. The + * path is built from the end of @buf so the returned pointer usually + * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated + * and %NULL is returned. + */ +char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) +{ + unsigned long flags; + char *p; + + spin_lock_irqsave(&kernfs_rename_lock, flags); + p = kernfs_path_locked(kn, buf, buflen); + spin_unlock_irqrestore(&kernfs_rename_lock, flags); + return p; +} + +/** + * pr_cont_kernfs_name - pr_cont name of a kernfs_node + * @kn: kernfs_node of interest + * + * This function can be called from any context. + */ +void pr_cont_kernfs_name(struct kernfs_node *kn) +{ + unsigned long flags; + + spin_lock_irqsave(&kernfs_rename_lock, flags); + + kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); + pr_cont("%s", kernfs_pr_cont_buf); + + spin_unlock_irqrestore(&kernfs_rename_lock, flags); +} + +/** + * pr_cont_kernfs_path - pr_cont path of a kernfs_node + * @kn: kernfs_node of interest + * + * This function can be called from any context. + */ +void pr_cont_kernfs_path(struct kernfs_node *kn) +{ + unsigned long flags; + char *p; + + spin_lock_irqsave(&kernfs_rename_lock, flags); + + p = kernfs_path_locked(kn, kernfs_pr_cont_buf, + sizeof(kernfs_pr_cont_buf)); + if (p) + pr_cont("%s", p); + else + pr_cont("<name too long>"); + + spin_unlock_irqrestore(&kernfs_rename_lock, flags); +} + +/** + * kernfs_get_parent - determine the parent node and pin it + * @kn: kernfs_node of interest + * + * Determines @kn's parent, pins and returns it. This function can be + * called from any context. + */ +struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) +{ + struct kernfs_node *parent; + unsigned long flags; + + spin_lock_irqsave(&kernfs_rename_lock, flags); + parent = kn->parent; + kernfs_get(parent); + spin_unlock_irqrestore(&kernfs_rename_lock, flags); + + return parent; +} + /** * kernfs_name_hash * @name: Null terminated string to hash @@ -37,7 +190,7 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns) hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31)); hash &= 0x7fffffffU; /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ - if (hash < 1) + if (hash < 2) hash += 2; if (hash >= INT_MAX) hash = INT_MAX - 1; @@ -105,18 +258,24 @@ static int kernfs_link_sibling(struct kernfs_node *kn) * kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree * @kn: kernfs_node of interest * - * Unlink @kn from its sibling rbtree which starts from - * kn->parent->dir.children. + * Try to unlink @kn from its sibling rbtree which starts from + * kn->parent->dir.children. Returns %true if @kn was actually + * removed, %false if @kn wasn't on the rbtree. * * Locking: * mutex_lock(kernfs_mutex) */ -static void kernfs_unlink_sibling(struct kernfs_node *kn) +static bool kernfs_unlink_sibling(struct kernfs_node *kn) { + if (RB_EMPTY_NODE(&kn->rb)) + return false; + if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs--; rb_erase(&kn->rb, &kn->parent->dir.children); + RB_CLEAR_NODE(&kn->rb); + return true; } /** @@ -137,7 +296,7 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) if (!atomic_inc_unless_negative(&kn->active)) return NULL; - if (kn->flags & KERNFS_LOCKDEP) + if (kernfs_lockdep(kn)) rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_); return kn; } @@ -151,55 +310,57 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) */ void kernfs_put_active(struct kernfs_node *kn) { + struct kernfs_root *root = kernfs_root(kn); int v; if (unlikely(!kn)) return; - if (kn->flags & KERNFS_LOCKDEP) + if (kernfs_lockdep(kn)) rwsem_release(&kn->dep_map, 1, _RET_IP_); v = atomic_dec_return(&kn->active); if (likely(v != KN_DEACTIVATED_BIAS)) return; - /* - * atomic_dec_return() is a mb(), we'll always see the updated - * kn->u.completion. - */ - complete(kn->u.completion); + wake_up_all(&root->deactivate_waitq); } /** - * kernfs_deactivate - deactivate kernfs_node - * @kn: kernfs_node to deactivate + * kernfs_drain - drain kernfs_node + * @kn: kernfs_node to drain * - * Deny new active references and drain existing ones. + * Drain existing usages and nuke all existing mmaps of @kn. Mutiple + * removers may invoke this function concurrently on @kn and all will + * return after draining is complete. */ -static void kernfs_deactivate(struct kernfs_node *kn) +static void kernfs_drain(struct kernfs_node *kn) + __releases(&kernfs_mutex) __acquires(&kernfs_mutex) { - DECLARE_COMPLETION_ONSTACK(wait); - int v; + struct kernfs_root *root = kernfs_root(kn); - BUG_ON(!(kn->flags & KERNFS_REMOVED)); + lockdep_assert_held(&kernfs_mutex); + WARN_ON_ONCE(kernfs_active(kn)); - if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF)) - return; + mutex_unlock(&kernfs_mutex); - kn->u.completion = (void *)&wait; + if (kernfs_lockdep(kn)) { + rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); + if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS) + lock_contended(&kn->dep_map, _RET_IP_); + } - rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); - /* atomic_add_return() is a mb(), put_active() will always see - * the updated kn->u.completion. - */ - v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active); + /* but everyone should wait for draining */ + wait_event(root->deactivate_waitq, + atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); - if (v != KN_DEACTIVATED_BIAS) { - lock_contended(&kn->dep_map, _RET_IP_); - wait_for_completion(&wait); + if (kernfs_lockdep(kn)) { + lock_acquired(&kn->dep_map, _RET_IP_); + rwsem_release(&kn->dep_map, 1, _RET_IP_); } - lock_acquired(&kn->dep_map, _RET_IP_); - rwsem_release(&kn->dep_map, 1, _RET_IP_); + kernfs_unmap_bin_file(kn); + + mutex_lock(&kernfs_mutex); } /** @@ -230,13 +391,15 @@ void kernfs_put(struct kernfs_node *kn) return; root = kernfs_root(kn); repeat: - /* Moving/renaming is always done while holding reference. + /* + * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ parent = kn->parent; - WARN(!(kn->flags & KERNFS_REMOVED), "kernfs: free using entry: %s/%s\n", - parent ? parent->name : "", kn->name); + WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, + "kernfs_put: %s/%s: released with incorrect active_ref %d\n", + parent ? parent->name : "", kn->name, atomic_read(&kn->active)); if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); @@ -278,8 +441,8 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) kn = dentry->d_fsdata; mutex_lock(&kernfs_mutex); - /* The kernfs node has been deleted */ - if (kn->flags & KERNFS_REMOVED) + /* The kernfs node has been deactivated */ + if (!kernfs_active(kn)) goto out_bad; /* The kernfs node has been moved? */ @@ -324,6 +487,24 @@ const struct dentry_operations kernfs_dops = { .d_release = kernfs_dop_release, }; +/** + * kernfs_node_from_dentry - determine kernfs_node associated with a dentry + * @dentry: the dentry in question + * + * Return the kernfs_node associated with @dentry. If @dentry is not a + * kernfs one, %NULL is returned. + * + * While the returned kernfs_node will stay accessible as long as @dentry + * is accessible, the returned node can be in any state and the caller is + * fully responsible for determining what's accessible. + */ +struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) +{ + if (dentry->d_sb->s_op == &kernfs_sops) + return dentry->d_fsdata; + return NULL; +} + static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, const char *name, umode_t mode, unsigned flags) @@ -348,11 +529,12 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, kn->ino = ret; atomic_set(&kn->count, 1); - atomic_set(&kn->active, 0); + atomic_set(&kn->active, KN_DEACTIVATED_BIAS); + RB_CLEAR_NODE(&kn->rb); kn->name = name; kn->mode = mode; - kn->flags = flags | KERNFS_REMOVED; + kn->flags = flags; return kn; @@ -378,69 +560,44 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, } /** - * kernfs_addrm_start - prepare for kernfs_node add/remove - * @acxt: pointer to kernfs_addrm_cxt to be used - * - * This function is called when the caller is about to add or remove - * kernfs_node. This function acquires kernfs_mutex. @acxt is used - * to keep and pass context to other addrm functions. - * - * LOCKING: - * Kernel thread context (may sleep). kernfs_mutex is locked on - * return. - */ -void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt) - __acquires(kernfs_mutex) -{ - memset(acxt, 0, sizeof(*acxt)); - - mutex_lock(&kernfs_mutex); -} - -/** * kernfs_add_one - add kernfs_node to parent without warning - * @acxt: addrm context to use * @kn: kernfs_node to be added * * The caller must already have initialized @kn->parent. This * function increments nlink of the parent's inode if @kn is a * directory and link into the children list of the parent. * - * This function should be called between calls to - * kernfs_addrm_start() and kernfs_addrm_finish() and should be passed - * the same @acxt as passed to kernfs_addrm_start(). - * - * LOCKING: - * Determined by kernfs_addrm_start(). - * * RETURNS: * 0 on success, -EEXIST if entry with the given name already * exists. */ -int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn) +int kernfs_add_one(struct kernfs_node *kn) { struct kernfs_node *parent = kn->parent; - bool has_ns = kernfs_ns_enabled(parent); struct kernfs_iattrs *ps_iattr; + bool has_ns; int ret; - if (has_ns != (bool)kn->ns) { - WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", - has_ns ? "required" : "invalid", parent->name, kn->name); - return -EINVAL; - } + mutex_lock(&kernfs_mutex); + + ret = -EINVAL; + has_ns = kernfs_ns_enabled(parent); + if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", + has_ns ? "required" : "invalid", parent->name, kn->name)) + goto out_unlock; if (kernfs_type(parent) != KERNFS_DIR) - return -EINVAL; + goto out_unlock; - if (parent->flags & KERNFS_REMOVED) - return -ENOENT; + ret = -ENOENT; + if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent)) + goto out_unlock; kn->hash = kernfs_name_hash(kn->name, kn->ns); ret = kernfs_link_sibling(kn); if (ret) - return ret; + goto out_unlock; /* Update timestamps on the parent */ ps_iattr = parent->iattr; @@ -449,82 +606,22 @@ int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn) ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME; } - /* Mark the entry added into directory tree */ - kn->flags &= ~KERNFS_REMOVED; - - return 0; -} - -/** - * kernfs_remove_one - remove kernfs_node from parent - * @acxt: addrm context to use - * @kn: kernfs_node to be removed - * - * Mark @kn removed and drop nlink of parent inode if @kn is a - * directory. @kn is unlinked from the children list. - * - * This function should be called between calls to - * kernfs_addrm_start() and kernfs_addrm_finish() and should be - * passed the same @acxt as passed to kernfs_addrm_start(). - * - * LOCKING: - * Determined by kernfs_addrm_start(). - */ -static void kernfs_remove_one(struct kernfs_addrm_cxt *acxt, - struct kernfs_node *kn) -{ - struct kernfs_iattrs *ps_iattr; + mutex_unlock(&kernfs_mutex); /* - * Removal can be called multiple times on the same node. Only the - * first invocation is effective and puts the base ref. + * Activate the new node unless CREATE_DEACTIVATED is requested. + * If not activated here, the kernfs user is responsible for + * activating the node with kernfs_activate(). A node which hasn't + * been activated is not visible to userland and its removal won't + * trigger deactivation. */ - if (kn->flags & KERNFS_REMOVED) - return; - - if (kn->parent) { - kernfs_unlink_sibling(kn); - - /* Update timestamps on the parent */ - ps_iattr = kn->parent->iattr; - if (ps_iattr) { - ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME; - ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME; - } - } - - kn->flags |= KERNFS_REMOVED; - kn->u.removed_list = acxt->removed; - acxt->removed = kn; -} + if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) + kernfs_activate(kn); + return 0; -/** - * kernfs_addrm_finish - finish up kernfs_node add/remove - * @acxt: addrm context to finish up - * - * Finish up kernfs_node add/remove. Resources acquired by - * kernfs_addrm_start() are released and removed kernfs_nodes are - * cleaned up. - * - * LOCKING: - * kernfs_mutex is released. - */ -void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt) - __releases(kernfs_mutex) -{ - /* release resources acquired by kernfs_addrm_start() */ +out_unlock: mutex_unlock(&kernfs_mutex); - - /* kill removed kernfs_nodes */ - while (acxt->removed) { - struct kernfs_node *kn = acxt->removed; - - acxt->removed = kn->u.removed_list; - - kernfs_deactivate(kn); - kernfs_unmap_bin_file(kn); - kernfs_put(kn); - } + return ret; } /** @@ -595,13 +692,15 @@ EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** * kernfs_create_root - create a new kernfs hierarchy - * @kdops: optional directory syscall operations for the hierarchy + * @scops: optional syscall operations for the hierarchy + * @flags: KERNFS_ROOT_* flags * @priv: opaque data associated with the new directory * * Returns the root of the new hierarchy on success, ERR_PTR() value on * failure. */ -struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv) +struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, + unsigned int flags, void *priv) { struct kernfs_root *root; struct kernfs_node *kn; @@ -620,12 +719,16 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv) return ERR_PTR(-ENOMEM); } - kn->flags &= ~KERNFS_REMOVED; kn->priv = priv; kn->dir.root = root; - root->dir_ops = kdops; + root->syscall_ops = scops; + root->flags = flags; root->kn = kn; + init_waitqueue_head(&root->deactivate_waitq); + + if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) + kernfs_activate(kn); return root; } @@ -656,7 +759,6 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, void *priv, const void *ns) { - struct kernfs_addrm_cxt acxt; struct kernfs_node *kn; int rc; @@ -670,10 +772,7 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, kn->priv = priv; /* link in */ - kernfs_addrm_start(&acxt); - rc = kernfs_add_one(&acxt, kn); - kernfs_addrm_finish(&acxt); - + rc = kernfs_add_one(kn); if (!rc) return kn; @@ -699,7 +798,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, kn = kernfs_find_ns(parent, dentry->d_name.name, ns); /* no such entry */ - if (!kn) { + if (!kn || !kernfs_active(kn)) { ret = NULL; goto out_unlock; } @@ -724,23 +823,37 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct kernfs_node *parent = dir->i_private; - struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops; + struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops; + int ret; - if (!kdops || !kdops->mkdir) + if (!scops || !scops->mkdir) return -EPERM; - return kdops->mkdir(parent, dentry->d_name.name, mode); + if (!kernfs_get_active(parent)) + return -ENODEV; + + ret = scops->mkdir(parent, dentry->d_name.name, mode); + + kernfs_put_active(parent); + return ret; } static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) { struct kernfs_node *kn = dentry->d_fsdata; - struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops; + struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; + int ret; - if (!kdops || !kdops->rmdir) + if (!scops || !scops->rmdir) return -EPERM; - return kdops->rmdir(kn); + if (!kernfs_get_active(kn)) + return -ENODEV; + + ret = scops->rmdir(kn); + + kernfs_put_active(kn); + return ret; } static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry, @@ -748,12 +861,25 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry, { struct kernfs_node *kn = old_dentry->d_fsdata; struct kernfs_node *new_parent = new_dir->i_private; - struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops; + struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; + int ret; - if (!kdops || !kdops->rename) + if (!scops || !scops->rename) return -EPERM; - return kdops->rename(kn, new_parent, new_dentry->d_name.name); + if (!kernfs_get_active(kn)) + return -ENODEV; + + if (!kernfs_get_active(new_parent)) { + kernfs_put_active(kn); + return -ENODEV; + } + + ret = scops->rename(kn, new_parent, new_dentry->d_name.name); + + kernfs_put_active(new_parent); + kernfs_put_active(kn); + return ret; } const struct inode_operations kernfs_dir_iops = { @@ -826,23 +952,104 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, return pos->parent; } -static void __kernfs_remove(struct kernfs_addrm_cxt *acxt, - struct kernfs_node *kn) +/** + * kernfs_activate - activate a node which started deactivated + * @kn: kernfs_node whose subtree is to be activated + * + * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node + * needs to be explicitly activated. A node which hasn't been activated + * isn't visible to userland and deactivation is skipped during its + * removal. This is useful to construct atomic init sequences where + * creation of multiple nodes should either succeed or fail atomically. + * + * The caller is responsible for ensuring that this function is not called + * after kernfs_remove*() is invoked on @kn. + */ +void kernfs_activate(struct kernfs_node *kn) { - struct kernfs_node *pos, *next; + struct kernfs_node *pos; - if (!kn) + mutex_lock(&kernfs_mutex); + + pos = NULL; + while ((pos = kernfs_next_descendant_post(pos, kn))) { + if (!pos || (pos->flags & KERNFS_ACTIVATED)) + continue; + + WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb)); + WARN_ON_ONCE(atomic_read(&pos->active) != KN_DEACTIVATED_BIAS); + + atomic_sub(KN_DEACTIVATED_BIAS, &pos->active); + pos->flags |= KERNFS_ACTIVATED; + } + + mutex_unlock(&kernfs_mutex); +} + +static void __kernfs_remove(struct kernfs_node *kn) +{ + struct kernfs_node *pos; + + lockdep_assert_held(&kernfs_mutex); + + /* + * Short-circuit if non-root @kn has already finished removal. + * This is for kernfs_remove_self() which plays with active ref + * after removal. + */ + if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb))) return; pr_debug("kernfs %s: removing\n", kn->name); - next = NULL; + /* prevent any new usage under @kn by deactivating all nodes */ + pos = NULL; + while ((pos = kernfs_next_descendant_post(pos, kn))) + if (kernfs_active(pos)) + atomic_add(KN_DEACTIVATED_BIAS, &pos->active); + + /* deactivate and unlink the subtree node-by-node */ do { - pos = next; - next = kernfs_next_descendant_post(pos, kn); - if (pos) - kernfs_remove_one(acxt, pos); - } while (next); + pos = kernfs_leftmost_descendant(kn); + + /* + * kernfs_drain() drops kernfs_mutex temporarily and @pos's + * base ref could have been put by someone else by the time + * the function returns. Make sure it doesn't go away + * underneath us. + */ + kernfs_get(pos); + + /* + * Drain iff @kn was activated. This avoids draining and + * its lockdep annotations for nodes which have never been + * activated and allows embedding kernfs_remove() in create + * error paths without worrying about draining. + */ + if (kn->flags & KERNFS_ACTIVATED) + kernfs_drain(pos); + else + WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); + + /* + * kernfs_unlink_sibling() succeeds once per node. Use it + * to decide who's responsible for cleanups. + */ + if (!pos->parent || kernfs_unlink_sibling(pos)) { + struct kernfs_iattrs *ps_iattr = + pos->parent ? pos->parent->iattr : NULL; + + /* update timestamps on the parent */ + if (ps_iattr) { + ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME; + ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME; + } + + kernfs_put(pos); + } + + kernfs_put(pos); + } while (pos != kn); } /** @@ -853,11 +1060,140 @@ static void __kernfs_remove(struct kernfs_addrm_cxt *acxt, */ void kernfs_remove(struct kernfs_node *kn) { - struct kernfs_addrm_cxt acxt; + mutex_lock(&kernfs_mutex); + __kernfs_remove(kn); + mutex_unlock(&kernfs_mutex); +} + +/** + * kernfs_break_active_protection - break out of active protection + * @kn: the self kernfs_node + * + * The caller must be running off of a kernfs operation which is invoked + * with an active reference - e.g. one of kernfs_ops. Each invocation of + * this function must also be matched with an invocation of + * kernfs_unbreak_active_protection(). + * + * This function releases the active reference of @kn the caller is + * holding. Once this function is called, @kn may be removed at any point + * and the caller is solely responsible for ensuring that the objects it + * dereferences are accessible. + */ +void kernfs_break_active_protection(struct kernfs_node *kn) +{ + /* + * Take out ourself out of the active ref dependency chain. If + * we're called without an active ref, lockdep will complain. + */ + kernfs_put_active(kn); +} + +/** + * kernfs_unbreak_active_protection - undo kernfs_break_active_protection() + * @kn: the self kernfs_node + * + * If kernfs_break_active_protection() was called, this function must be + * invoked before finishing the kernfs operation. Note that while this + * function restores the active reference, it doesn't and can't actually + * restore the active protection - @kn may already or be in the process of + * being removed. Once kernfs_break_active_protection() is invoked, that + * protection is irreversibly gone for the kernfs operation instance. + * + * While this function may be called at any point after + * kernfs_break_active_protection() is invoked, its most useful location + * would be right before the enclosing kernfs operation returns. + */ +void kernfs_unbreak_active_protection(struct kernfs_node *kn) +{ + /* + * @kn->active could be in any state; however, the increment we do + * here will be undone as soon as the enclosing kernfs operation + * finishes and this temporary bump can't break anything. If @kn + * is alive, nothing changes. If @kn is being deactivated, the + * soon-to-follow put will either finish deactivation or restore + * deactivated state. If @kn is already removed, the temporary + * bump is guaranteed to be gone before @kn is released. + */ + atomic_inc(&kn->active); + if (kernfs_lockdep(kn)) + rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_); +} + +/** + * kernfs_remove_self - remove a kernfs_node from its own method + * @kn: the self kernfs_node to remove + * + * The caller must be running off of a kernfs operation which is invoked + * with an active reference - e.g. one of kernfs_ops. This can be used to + * implement a file operation which deletes itself. + * + * For example, the "delete" file for a sysfs device directory can be + * implemented by invoking kernfs_remove_self() on the "delete" file + * itself. This function breaks the circular dependency of trying to + * deactivate self while holding an active ref itself. It isn't necessary + * to modify the usual removal path to use kernfs_remove_self(). The + * "delete" implementation can simply invoke kernfs_remove_self() on self + * before proceeding with the usual removal path. kernfs will ignore later + * kernfs_remove() on self. + * + * kernfs_remove_self() can be called multiple times concurrently on the + * same kernfs_node. Only the first one actually performs removal and + * returns %true. All others will wait until the kernfs operation which + * won self-removal finishes and return %false. Note that the losers wait + * for the completion of not only the winning kernfs_remove_self() but also + * the whole kernfs_ops which won the arbitration. This can be used to + * guarantee, for example, all concurrent writes to a "delete" file to + * finish only after the whole operation is complete. + */ +bool kernfs_remove_self(struct kernfs_node *kn) +{ + bool ret; + + mutex_lock(&kernfs_mutex); + kernfs_break_active_protection(kn); + + /* + * SUICIDAL is used to arbitrate among competing invocations. Only + * the first one will actually perform removal. When the removal + * is complete, SUICIDED is set and the active ref is restored + * while holding kernfs_mutex. The ones which lost arbitration + * waits for SUICDED && drained which can happen only after the + * enclosing kernfs operation which executed the winning instance + * of kernfs_remove_self() finished. + */ + if (!(kn->flags & KERNFS_SUICIDAL)) { + kn->flags |= KERNFS_SUICIDAL; + __kernfs_remove(kn); + kn->flags |= KERNFS_SUICIDED; + ret = true; + } else { + wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq; + DEFINE_WAIT(wait); + + while (true) { + prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE); - kernfs_addrm_start(&acxt); - __kernfs_remove(&acxt, kn); - kernfs_addrm_finish(&acxt); + if ((kn->flags & KERNFS_SUICIDED) && + atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) + break; + + mutex_unlock(&kernfs_mutex); + schedule(); + mutex_lock(&kernfs_mutex); + } + finish_wait(waitq, &wait); + WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); + ret = false; + } + + /* + * This must be done while holding kernfs_mutex; otherwise, waiting + * for SUICIDED && deactivated could finish prematurely. + */ + kernfs_unbreak_active_protection(kn); + + mutex_unlock(&kernfs_mutex); + return ret; } /** @@ -872,7 +1208,6 @@ void kernfs_remove(struct kernfs_node *kn) int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns) { - struct kernfs_addrm_cxt acxt; struct kernfs_node *kn; if (!parent) { @@ -881,13 +1216,13 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, return -ENOENT; } - kernfs_addrm_start(&acxt); + mutex_lock(&kernfs_mutex); kn = kernfs_find_ns(parent, name, ns); if (kn) - __kernfs_remove(&acxt, kn); + __kernfs_remove(kn); - kernfs_addrm_finish(&acxt); + mutex_unlock(&kernfs_mutex); if (kn) return 0; @@ -905,12 +1240,18 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { + struct kernfs_node *old_parent; + const char *old_name = NULL; int error; + /* can't move or rename root */ + if (!kn->parent) + return -EINVAL; + mutex_lock(&kernfs_mutex); error = -ENOENT; - if ((kn->flags | new_parent->flags) & KERNFS_REMOVED) + if (!kernfs_active(kn) || !kernfs_active(new_parent)) goto out; error = 0; @@ -928,13 +1269,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, new_name = kstrdup(new_name, GFP_KERNEL); if (!new_name) goto out; - - if (kn->flags & KERNFS_STATIC_NAME) - kn->flags &= ~KERNFS_STATIC_NAME; - else - kfree(kn->name); - - kn->name = new_name; + } else { + new_name = NULL; } /* @@ -942,12 +1278,29 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, */ kernfs_unlink_sibling(kn); kernfs_get(new_parent); - kernfs_put(kn->parent); + + /* rename_lock protects ->parent and ->name accessors */ + spin_lock_irq(&kernfs_rename_lock); + + old_parent = kn->parent; + kn->parent = new_parent; + kn->ns = new_ns; + if (new_name) { + if (!(kn->flags & KERNFS_STATIC_NAME)) + old_name = kn->name; + kn->flags &= ~KERNFS_STATIC_NAME; + kn->name = new_name; + } + + spin_unlock_irq(&kernfs_rename_lock); + kn->hash = kernfs_name_hash(kn->name, kn->ns); - kn->parent = new_parent; kernfs_link_sibling(kn); + kernfs_put(old_parent); + kfree(old_name); + error = 0; out: mutex_unlock(&kernfs_mutex); @@ -970,7 +1323,7 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos) { if (pos) { - int valid = !(pos->flags & KERNFS_REMOVED) && + int valid = kernfs_active(pos) && pos->parent == parent && hash == pos->hash; kernfs_put(pos); if (!valid) @@ -989,8 +1342,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, break; } } - /* Skip over entries in the wrong namespace */ - while (pos && pos->ns != ns) { + /* Skip over entries which are dying/dead or in the wrong namespace */ + while (pos && (!kernfs_active(pos) || pos->ns != ns)) { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; @@ -1004,14 +1357,15 @@ static struct kernfs_node *kernfs_dir_next_pos(const void *ns, struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos) { pos = kernfs_dir_pos(ns, parent, ino, pos); - if (pos) + if (pos) { do { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); - } while (pos && pos->ns != ns); + } while (pos && (!kernfs_active(pos) || pos->ns != ns)); + } return pos; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index dbf397bfdff2..8034706a7af8 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -252,10 +252,18 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct kernfs_open_file *of = kernfs_of(file); - ssize_t len = min_t(size_t, count, PAGE_SIZE); const struct kernfs_ops *ops; + size_t len; char *buf; + if (of->atomic_write_len) { + len = count; + if (len > of->atomic_write_len) + return -E2BIG; + } else { + len = min_t(size_t, count, PAGE_SIZE); + } + buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -653,6 +661,12 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) of->file = file; /* + * Write path needs to atomic_write_len outside active reference. + * Cache it in open_file. See kernfs_fop_write() for details. + */ + of->atomic_write_len = ops->atomic_write_len; + + /* * Always instantiate seq_file even if read access doesn't use * seq_file or is not requested. This unifies private data access * and readable regular files are the vast majority anyway. @@ -820,7 +834,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, bool name_is_static, struct lock_class_key *key) { - struct kernfs_addrm_cxt acxt; struct kernfs_node *kn; unsigned flags; int rc; @@ -855,10 +868,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; - kernfs_addrm_start(&acxt); - rc = kernfs_add_one(&acxt, kn); - kernfs_addrm_finish(&acxt); - + rc = kernfs_add_one(kn); if (rc) { kernfs_put(kn); return ERR_PTR(rc); diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index eb536b76374a..8be13b2a079b 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -26,7 +26,8 @@ struct kernfs_iattrs { struct simple_xattrs xattrs; }; -#define KN_DEACTIVATED_BIAS INT_MIN +/* +1 to avoid triggering overflow warning when negating it */ +#define KN_DEACTIVATED_BIAS (INT_MIN + 1) /* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */ @@ -45,13 +46,6 @@ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) } /* - * Context structure to be used while adding/removing nodes. - */ -struct kernfs_addrm_cxt { - struct kernfs_node *removed; -}; - -/* * mount.c */ struct kernfs_super_info { @@ -71,6 +65,7 @@ struct kernfs_super_info { }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) +extern const struct super_operations kernfs_sops; extern struct kmem_cache *kernfs_node_cache; /* @@ -100,9 +95,7 @@ extern const struct inode_operations kernfs_dir_iops; struct kernfs_node *kernfs_get_active(struct kernfs_node *kn); void kernfs_put_active(struct kernfs_node *kn); -void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt); -int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn); -void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt); +int kernfs_add_one(struct kernfs_node *kn); struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, unsigned flags); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 0d6ce895a9ee..6a5f04ac8704 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -19,12 +19,49 @@ struct kmem_cache *kernfs_node_cache; -static const struct super_operations kernfs_sops = { +static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data) +{ + struct kernfs_root *root = kernfs_info(sb)->root; + struct kernfs_syscall_ops *scops = root->syscall_ops; + + if (scops && scops->remount_fs) + return scops->remount_fs(root, flags, data); + return 0; +} + +static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) +{ + struct kernfs_root *root = kernfs_root(dentry->d_fsdata); + struct kernfs_syscall_ops *scops = root->syscall_ops; + + if (scops && scops->show_options) + return scops->show_options(sf, root); + return 0; +} + +const struct super_operations kernfs_sops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .evict_inode = kernfs_evict_inode, + + .remount_fs = kernfs_sop_remount_fs, + .show_options = kernfs_sop_show_options, }; +/** + * kernfs_root_from_sb - determine kernfs_root associated with a super_block + * @sb: the super_block in question + * + * Return the kernfs_root associated with @sb. If @sb is not a kernfs one, + * %NULL is returned. + */ +struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) +{ + if (sb->s_op == &kernfs_sops) + return kernfs_info(sb)->root; + return NULL; +} + static int kernfs_fill_super(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); @@ -94,6 +131,7 @@ const void *kernfs_super_ns(struct super_block *sb) * @fs_type: file_system_type of the fs being mounted * @flags: mount flags specified for the mount * @root: kernfs_root of the hierarchy being mounted + * @new_sb_created: tell the caller if we allocated a new superblock * @ns: optional namespace tag of the mount * * This is to be called from each kernfs user's file_system_type->mount() @@ -104,7 +142,8 @@ const void *kernfs_super_ns(struct super_block *sb) * The return value can be passed to the vfs layer verbatim. */ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, const void *ns) + struct kernfs_root *root, bool *new_sb_created, + const void *ns) { struct super_block *sb; struct kernfs_super_info *info; @@ -122,6 +161,10 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, kfree(info); if (IS_ERR(sb)) return ERR_CAST(sb); + + if (new_sb_created) + *new_sb_created = !sb->s_root; + if (!sb->s_root) { error = kernfs_fill_super(sb); if (error) { diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 4d457055acb9..8a198898e39a 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -27,7 +27,6 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, struct kernfs_node *target) { struct kernfs_node *kn; - struct kernfs_addrm_cxt acxt; int error; kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK); @@ -39,10 +38,7 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, kn->symlink.target_kn = target; kernfs_get(target); /* ref owned by symlink */ - kernfs_addrm_start(&acxt); - error = kernfs_add_one(&acxt, kn); - kernfs_addrm_finish(&acxt); - + error = kernfs_add_one(kn); if (!error) return kn; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index e066a3902973..ab798a88ec1d 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -779,6 +779,7 @@ nlmsvc_grant_blocked(struct nlm_block *block) struct nlm_file *file = block->b_file; struct nlm_lock *lock = &block->b_call->a_args.lock; int error; + loff_t fl_start, fl_end; dprintk("lockd: grant blocked lock %p\n", block); @@ -796,9 +797,16 @@ nlmsvc_grant_blocked(struct nlm_block *block) } /* Try the lock operation again */ + /* vfs_lock_file() can mangle fl_start and fl_end, but we need + * them unchanged for the GRANT_MSG + */ lock->fl.fl_flags |= FL_SLEEP; + fl_start = lock->fl.fl_start; + fl_end = lock->fl.fl_end; error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL); lock->fl.fl_flags &= ~FL_SLEEP; + lock->fl.fl_start = fl_start; + lock->fl.fl_end = fl_end; switch (error) { case 0: diff --git a/fs/mount.h b/fs/mount.h index a17458ca6f29..b29e42f05f34 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -19,13 +19,13 @@ struct mnt_pcp { }; struct mountpoint { - struct list_head m_hash; + struct hlist_node m_hash; struct dentry *m_dentry; int m_count; }; struct mount { - struct list_head mnt_hash; + struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; diff --git a/fs/namei.c b/fs/namei.c index d580df2e6804..4b491b431990 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -196,6 +196,7 @@ recopy: goto error; result->uptr = filename; + result->aname = NULL; audit_getname(result); return result; @@ -210,6 +211,35 @@ getname(const char __user * filename) return getname_flags(filename, 0, NULL); } +/* + * The "getname_kernel()" interface doesn't do pathnames longer + * than EMBEDDED_NAME_MAX. Deal with it - you're a kernel user. + */ +struct filename * +getname_kernel(const char * filename) +{ + struct filename *result; + char *kname; + int len; + + len = strlen(filename); + if (len >= EMBEDDED_NAME_MAX) + return ERR_PTR(-ENAMETOOLONG); + + result = __getname(); + if (unlikely(!result)) + return ERR_PTR(-ENOMEM); + + kname = (char *)result + sizeof(*result); + result->name = kname; + result->uptr = NULL; + result->aname = NULL; + result->separate = false; + + strlcpy(kname, filename, EMBEDDED_NAME_MAX); + return result; +} + #ifdef CONFIG_AUDITSYSCALL void putname(struct filename *name) { @@ -1079,7 +1109,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, return false; if (!d_mountpoint(path->dentry)) - break; + return true; mounted = __lookup_mnt(path->mnt, path->dentry); if (!mounted) @@ -1095,20 +1125,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, */ *inode = path->dentry->d_inode; } - return true; -} - -static void follow_mount_rcu(struct nameidata *nd) -{ - while (d_mountpoint(nd->path.dentry)) { - struct mount *mounted; - mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry); - if (!mounted) - break; - nd->path.mnt = &mounted->mnt; - nd->path.dentry = mounted->mnt.mnt_root; - nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); - } + return read_seqretry(&mount_lock, nd->m_seq); } static int follow_dotdot_rcu(struct nameidata *nd) @@ -1136,7 +1153,17 @@ static int follow_dotdot_rcu(struct nameidata *nd) break; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } - follow_mount_rcu(nd); + while (d_mountpoint(nd->path.dentry)) { + struct mount *mounted; + mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry); + if (!mounted) + break; + nd->path.mnt = &mounted->mnt; + nd->path.dentry = mounted->mnt.mnt_root; + nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); + if (!read_seqretry(&mount_lock, nd->m_seq)) + goto failed; + } nd->inode = nd->path.dentry->d_inode; return 0; @@ -1854,7 +1881,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, nd->path = f.file->f_path; if (flags & LOOKUP_RCU) { - if (f.need_put) + if (f.flags & FDPUT_FPUT) *fp = f.file; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); rcu_read_lock(); diff --git a/fs/namespace.c b/fs/namespace.c index 22e536705c45..2ffc5a2905d4 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -23,11 +23,34 @@ #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> +#include <linux/bootmem.h> #include "pnode.h" #include "internal.h" -#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head)) -#define HASH_SIZE (1UL << HASH_SHIFT) +static unsigned int m_hash_mask __read_mostly; +static unsigned int m_hash_shift __read_mostly; +static unsigned int mp_hash_mask __read_mostly; +static unsigned int mp_hash_shift __read_mostly; + +static __initdata unsigned long mhash_entries; +static int __init set_mhash_entries(char *str) +{ + if (!str) + return 0; + mhash_entries = simple_strtoul(str, &str, 0); + return 1; +} +__setup("mhash_entries=", set_mhash_entries); + +static __initdata unsigned long mphash_entries; +static int __init set_mphash_entries(char *str) +{ + if (!str) + return 0; + mphash_entries = simple_strtoul(str, &str, 0); + return 1; +} +__setup("mphash_entries=", set_mphash_entries); static int event; static DEFINE_IDA(mnt_id_ida); @@ -36,8 +59,8 @@ static DEFINE_SPINLOCK(mnt_id_lock); static int mnt_id_start = 0; static int mnt_group_start = 1; -static struct list_head *mount_hashtable __read_mostly; -static struct list_head *mountpoint_hashtable __read_mostly; +static struct hlist_head *mount_hashtable __read_mostly; +static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); @@ -55,12 +78,19 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); -static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) +static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); - tmp = tmp + (tmp >> HASH_SHIFT); - return tmp & (HASH_SIZE - 1); + tmp = tmp + (tmp >> m_hash_shift); + return &mount_hashtable[tmp & m_hash_mask]; +} + +static inline struct hlist_head *mp_hash(struct dentry *dentry) +{ + unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); + tmp = tmp + (tmp >> mp_hash_shift); + return &mountpoint_hashtable[tmp & mp_hash_mask]; } /* @@ -187,7 +217,7 @@ static struct mount *alloc_vfsmnt(const char *name) mnt->mnt_writers = 0; #endif - INIT_LIST_HEAD(&mnt->mnt_hash); + INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); @@ -575,10 +605,10 @@ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { - struct list_head *head = mount_hashtable + hash(mnt, dentry); + struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; - list_for_each_entry_rcu(p, head, mnt_hash) + hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; @@ -590,13 +620,17 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) */ struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) { - struct list_head *head = mount_hashtable + hash(mnt, dentry); - struct mount *p; - - list_for_each_entry_reverse(p, head, mnt_hash) - if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) - return p; - return NULL; + struct mount *p, *res; + res = p = __lookup_mnt(mnt, dentry); + if (!p) + goto out; + hlist_for_each_entry_continue(p, mnt_hash) { + if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) + break; + res = p; + } +out: + return res; } /* @@ -633,11 +667,11 @@ struct vfsmount *lookup_mnt(struct path *path) static struct mountpoint *new_mountpoint(struct dentry *dentry) { - struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry); + struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; int ret; - list_for_each_entry(mp, chain, m_hash) { + hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) @@ -659,7 +693,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry) mp->m_dentry = dentry; mp->m_count = 1; - list_add(&mp->m_hash, chain); + hlist_add_head(&mp->m_hash, chain); return mp; } @@ -670,7 +704,7 @@ static void put_mountpoint(struct mountpoint *mp) spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); - list_del(&mp->m_hash); + hlist_del(&mp->m_hash); kfree(mp); } } @@ -712,7 +746,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path) mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); - list_del_init(&mnt->mnt_hash); + hlist_del_init_rcu(&mnt->mnt_hash); put_mountpoint(mnt->mnt_mp); mnt->mnt_mp = NULL; } @@ -739,15 +773,14 @@ static void attach_mnt(struct mount *mnt, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); - list_add_tail(&mnt->mnt_hash, mount_hashtable + - hash(&parent->mnt, mp->m_dentry)); + hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /* * vfsmount lock must be held for write */ -static void commit_tree(struct mount *mnt) +static void commit_tree(struct mount *mnt, struct mount *shadows) { struct mount *parent = mnt->mnt_parent; struct mount *m; @@ -762,8 +795,11 @@ static void commit_tree(struct mount *mnt) list_splice(&head, n->list.prev); - list_add_tail(&mnt->mnt_hash, mount_hashtable + - hash(&parent->mnt, mnt->mnt_mountpoint)); + if (shadows) + hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash); + else + hlist_add_head_rcu(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); touch_mnt_namespace(n); } @@ -1153,26 +1189,28 @@ int may_umount(struct vfsmount *mnt) EXPORT_SYMBOL(may_umount); -static LIST_HEAD(unmounted); /* protected by namespace_sem */ +static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static void namespace_unlock(void) { struct mount *mnt; - LIST_HEAD(head); + struct hlist_head head = unmounted; - if (likely(list_empty(&unmounted))) { + if (likely(hlist_empty(&head))) { up_write(&namespace_sem); return; } - list_splice_init(&unmounted, &head); + head.first->pprev = &head.first; + INIT_HLIST_HEAD(&unmounted); + up_write(&namespace_sem); synchronize_rcu(); - while (!list_empty(&head)) { - mnt = list_first_entry(&head, struct mount, mnt_hash); - list_del_init(&mnt->mnt_hash); + while (!hlist_empty(&head)) { + mnt = hlist_entry(head.first, struct mount, mnt_hash); + hlist_del_init(&mnt->mnt_hash); if (mnt->mnt_ex_mountpoint.mnt) path_put(&mnt->mnt_ex_mountpoint); mntput(&mnt->mnt); @@ -1193,16 +1231,19 @@ static inline void namespace_lock(void) */ void umount_tree(struct mount *mnt, int how) { - LIST_HEAD(tmp_list); + HLIST_HEAD(tmp_list); struct mount *p; + struct mount *last = NULL; - for (p = mnt; p; p = next_mnt(p, mnt)) - list_move(&p->mnt_hash, &tmp_list); + for (p = mnt; p; p = next_mnt(p, mnt)) { + hlist_del_init_rcu(&p->mnt_hash); + hlist_add_head(&p->mnt_hash, &tmp_list); + } if (how) propagate_umount(&tmp_list); - list_for_each_entry(p, &tmp_list, mnt_hash) { + hlist_for_each_entry(p, &tmp_list, mnt_hash) { list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); __touch_mnt_namespace(p->mnt_ns); @@ -1220,8 +1261,13 @@ void umount_tree(struct mount *mnt, int how) p->mnt_mp = NULL; } change_mnt_propagation(p, MS_PRIVATE); + last = p; + } + if (last) { + last->mnt_hash.next = unmounted.first; + unmounted.first = tmp_list.first; + unmounted.first->pprev = &unmounted.first; } - list_splice(&tmp_list, &unmounted); } static void shrink_submounts(struct mount *mnt); @@ -1605,24 +1651,23 @@ static int attach_recursive_mnt(struct mount *source_mnt, struct mountpoint *dest_mp, struct path *parent_path) { - LIST_HEAD(tree_list); + HLIST_HEAD(tree_list); struct mount *child, *p; + struct hlist_node *n; int err; if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; - } - err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); - if (err) - goto out_cleanup_ids; - - lock_mount_hash(); - - if (IS_MNT_SHARED(dest_mnt)) { + err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); + if (err) + goto out_cleanup_ids; + lock_mount_hash(); for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); + } else { + lock_mount_hash(); } if (parent_path) { detach_mnt(source_mnt, parent_path); @@ -1630,20 +1675,22 @@ static int attach_recursive_mnt(struct mount *source_mnt, touch_mnt_namespace(source_mnt->mnt_ns); } else { mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); - commit_tree(source_mnt); + commit_tree(source_mnt, NULL); } - list_for_each_entry_safe(child, p, &tree_list, mnt_hash) { - list_del_init(&child->mnt_hash); - commit_tree(child); + hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { + struct mount *q; + hlist_del_init(&child->mnt_hash); + q = __lookup_mnt_last(&child->mnt_parent->mnt, + child->mnt_mountpoint); + commit_tree(child, q); } unlock_mount_hash(); return 0; out_cleanup_ids: - if (IS_MNT_SHARED(dest_mnt)) - cleanup_group_ids(source_mnt, NULL); + cleanup_group_ids(source_mnt, NULL); out: return err; } @@ -2777,18 +2824,24 @@ void __init mnt_init(void) mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC); - mountpoint_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC); + mount_hashtable = alloc_large_system_hash("Mount-cache", + sizeof(struct hlist_head), + mhash_entries, 19, + 0, + &m_hash_shift, &m_hash_mask, 0, 0); + mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", + sizeof(struct hlist_head), + mphash_entries, 19, + 0, + &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); - printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE); - - for (u = 0; u < HASH_SIZE; u++) - INIT_LIST_HEAD(&mount_hashtable[u]); - for (u = 0; u < HASH_SIZE; u++) - INIT_LIST_HEAD(&mountpoint_hashtable[u]); + for (u = 0; u <= m_hash_mask; u++) + INIT_HLIST_HEAD(&mount_hashtable[u]); + for (u = 0; u <= mp_hash_mask; u++) + INIT_HLIST_HEAD(&mountpoint_hashtable[u]); kernfs_init(); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index ef792f29f831..5d8ccecf5f5c 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -659,16 +659,19 @@ int nfs_async_inode_return_delegation(struct inode *inode, rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation == NULL) + goto out_enoent; - if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) { - rcu_read_unlock(); - return -ENOENT; - } + if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) + goto out_enoent; nfs_mark_return_delegation(server, delegation); rcu_read_unlock(); nfs_delegation_run_state_manager(clp); return 0; +out_enoent: + rcu_read_unlock(); + return -ENOENT; } static struct inode * diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index be38b573495a..4a48fe4b84b6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1846,6 +1846,11 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) GFP_KERNEL)) { SetPageUptodate(page); unlock_page(page); + /* + * add_to_page_cache_lru() grabs an extra page refcount. + * Drop it here to avoid leaking this page later. + */ + page_cache_release(page); } else __free_page(page); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 28a0a3cbd3b7..360114ae8b82 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -164,17 +164,16 @@ static void nfs_zap_caches_locked(struct inode *inode) if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { nfs_fscache_invalidate(inode); nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_LABEL | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_PAGECACHE; } else nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_LABEL | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_PAGECACHE; + nfs_zap_label_cache_locked(nfsi); } void nfs_zap_caches(struct inode *inode) @@ -266,6 +265,13 @@ nfs_init_locked(struct inode *inode, void *opaque) } #ifdef CONFIG_NFS_V4_SECURITY_LABEL +static void nfs_clear_label_invalid(struct inode *inode) +{ + spin_lock(&inode->i_lock); + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL; + spin_unlock(&inode->i_lock); +} + void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label) { @@ -283,6 +289,7 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, __func__, (char *)label->label, label->len, error); + nfs_clear_label_invalid(inode); } } @@ -1648,7 +1655,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_blocks = fattr->du.nfs2.blocks; /* Update attrtimeo value if we're out of the unstable period */ - if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) { + if (invalid & NFS_INO_INVALID_ATTR) { nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; @@ -1661,7 +1668,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } } invalid &= ~NFS_INO_INVALID_ATTR; - invalid &= ~NFS_INO_INVALID_LABEL; /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 8b5cc04a8611..b46cf5a67329 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -176,7 +176,8 @@ extern struct nfs_server *nfs4_create_server( extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, struct nfs_fh *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen); + struct sockaddr *sap, size_t salen, + struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, @@ -279,9 +280,18 @@ static inline void nfs4_label_free(struct nfs4_label *label) } return; } + +static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) +{ + if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) + nfsi->cache_validity |= NFS_INO_INVALID_LABEL; +} #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } static inline void nfs4_label_free(void *label) {} +static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) +{ +} #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 9a5ca03fa539..871d6eda8dba 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -80,7 +80,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) } if (res.acl_access != NULL) { - if (posix_acl_equiv_mode(res.acl_access, NULL) || + if ((posix_acl_equiv_mode(res.acl_access, NULL) == 0) || res.acl_access->a_count == 0) { posix_acl_release(res.acl_access); res.acl_access = NULL; @@ -113,7 +113,7 @@ getout: return ERR_PTR(status); } -int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, +static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, struct posix_acl *dfacl) { struct nfs_server *server = NFS_SERVER(inode); @@ -198,6 +198,15 @@ out: return status; } +int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl) +{ + int ret; + ret = __nfs3_proc_setacls(inode, acl, dfacl); + return (ret == -EOPNOTSUPP) ? 0 : ret; + +} + int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type) { struct posix_acl *alloc = NULL, *dfacl = NULL; @@ -225,7 +234,7 @@ int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (IS_ERR(alloc)) goto fail; } - status = nfs3_proc_setacls(inode, acl, dfacl); + status = __nfs3_proc_setacls(inode, acl, dfacl); posix_acl_release(alloc); return status; @@ -233,25 +242,6 @@ fail: return PTR_ERR(alloc); } -int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - umode_t mode) -{ - struct posix_acl *default_acl, *acl; - int error; - - error = posix_acl_create(dir, &mode, &default_acl, &acl); - if (error) - return (error == -EOPNOTSUPP) ? 0 : error; - - error = nfs3_proc_setacls(inode, acl, default_acl); - - if (acl) - posix_acl_release(acl); - if (default_acl) - posix_acl_release(default_acl); - return error; -} - const struct xattr_handler *nfs3_xattr_handlers[] = { &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index aa9bc973f36a..a462ef0fb5d6 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -18,6 +18,7 @@ #include <linux/lockd/bind.h> #include <linux/nfs_mount.h> #include <linux/freezer.h> +#include <linux/xattr.h> #include "iostat.h" #include "internal.h" diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index dbb3e1f30c68..0e46d3d1b6cc 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -170,7 +170,7 @@ void nfs41_shutdown_client(struct nfs_client *clp) void nfs40_shutdown_client(struct nfs_client *clp) { if (clp->cl_slot_tbl) { - nfs4_release_slot_table(clp->cl_slot_tbl); + nfs4_shutdown_slot_table(clp->cl_slot_tbl); kfree(clp->cl_slot_tbl); } } @@ -1135,6 +1135,7 @@ static int nfs_probe_destination(struct nfs_server *server) * @hostname: new end-point's hostname * @sap: new end-point's socket address * @salen: size of "sap" + * @net: net namespace * * The nfs_server must be quiescent before this function is invoked. * Either its session is drained (NFSv4.1+), or its transport is @@ -1143,13 +1144,13 @@ static int nfs_probe_destination(struct nfs_server *server) * Returns zero on success, or a negative errno value. */ int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen) + struct sockaddr *sap, size_t salen, struct net *net) { struct nfs_client *clp = server->nfs_client; struct rpc_clnt *clnt = server->client; struct xprt_create xargs = { .ident = clp->cl_proto, - .net = &init_net, + .net = net, .dstaddr = sap, .addrlen = salen, .servername = hostname, @@ -1189,7 +1190,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, error = nfs4_set_client(server, hostname, sap, salen, buf, clp->cl_rpcclient->cl_auth->au_flavor, clp->cl_proto, clnt->cl_timeout, - clp->cl_minorversion, clp->cl_net); + clp->cl_minorversion, net); nfs_put_client(clp); if (error != 0) { nfs_server_insert_lists(server); diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 12c8132ad408..b9a35c05b60f 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -324,8 +324,9 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data) &rdata->res.seq_res, task)) return; - nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context, - rdata->args.lock_context, FMODE_READ); + if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context, + rdata->args.lock_context, FMODE_READ) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ } static void filelayout_read_call_done(struct rpc_task *task, void *data) @@ -435,8 +436,9 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data) &wdata->res.seq_res, task)) return; - nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context, - wdata->args.lock_context, FMODE_WRITE); + if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context, + wdata->args.lock_context, FMODE_WRITE) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ } static void filelayout_write_call_done(struct rpc_task *task, void *data) diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 4e7f05d3e9db..3d5dbf80d46a 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -121,9 +121,8 @@ static int nfs4_validate_fspath(struct dentry *dentry, } static size_t nfs_parse_server_name(char *string, size_t len, - struct sockaddr *sa, size_t salen, struct nfs_server *server) + struct sockaddr *sa, size_t salen, struct net *net) { - struct net *net = rpc_net_ns(server->client); ssize_t ret; ret = rpc_pton(net, string, len, sa, salen); @@ -223,6 +222,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, const struct nfs4_fs_location *location) { const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client); struct vfsmount *mnt = ERR_PTR(-ENOENT); char *mnt_path; unsigned int maxbuflen; @@ -248,8 +248,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, continue; mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len, - mountdata->addr, addr_bufsize, - NFS_SB(mountdata->sb)); + mountdata->addr, addr_bufsize, net); if (mountdata->addrlen == 0) continue; @@ -419,6 +418,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, const struct nfs4_fs_location *location) { const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct net *net = rpc_net_ns(server->client); struct sockaddr *sap; unsigned int s; size_t salen; @@ -440,7 +440,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, continue; salen = nfs_parse_server_name(buf->data, buf->len, - sap, addr_bufsize, server); + sap, addr_bufsize, net); if (salen == 0) continue; rpc_set_port(sap, NFS_PORT); @@ -450,7 +450,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, if (hostname == NULL) break; - error = nfs4_update_server(server, hostname, sap, salen); + error = nfs4_update_server(server, hostname, sap, salen, net); kfree(hostname); if (error == 0) break; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 42da6af77587..450bfedbe2f4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1620,15 +1620,15 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata) { struct nfs4_opendata *data = calldata; - nfs40_setup_sequence(data->o_arg.server, &data->o_arg.seq_args, - &data->o_res.seq_res, task); + nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args, + &data->c_res.seq_res, task); } static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) { struct nfs4_opendata *data = calldata; - nfs40_sequence_done(task, &data->o_res.seq_res); + nfs40_sequence_done(task, &data->c_res.seq_res); data->rpc_status = task->tk_status; if (data->rpc_status == 0) { @@ -1686,7 +1686,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) }; int status; - nfs4_init_sequence(&data->o_arg.seq_args, &data->o_res.seq_res, 1); + nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1); kref_get(&data->kref); data->rpc_done = 0; data->rpc_status = 0; @@ -2398,13 +2398,16 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) { /* Use that stateid */ - } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) { + } else if (truncate && state != NULL) { struct nfs_lockowner lockowner = { .l_owner = current->files, .l_pid = current->tgid, }; - nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE, - &lockowner); + if (!nfs4_valid_open_stateid(state)) + return -EBADF; + if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE, + &lockowner) == -EIO) + return -EBADF; } else nfs4_stateid_copy(&arg.stateid, &zero_stateid); @@ -4011,8 +4014,9 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid, { nfs4_stateid current_stateid; - if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode)) - return false; + /* If the current stateid represents a lost lock, then exit */ + if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode) == -EIO) + return true; return nfs4_stateid_match(stateid, ¤t_stateid); } @@ -5828,8 +5832,7 @@ struct nfs_release_lockowner_data { struct nfs4_lock_state *lsp; struct nfs_server *server; struct nfs_release_lockowner_args args; - struct nfs4_sequence_args seq_args; - struct nfs4_sequence_res seq_res; + struct nfs_release_lockowner_res res; unsigned long timestamp; }; @@ -5837,7 +5840,7 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata { struct nfs_release_lockowner_data *data = calldata; nfs40_setup_sequence(data->server, - &data->seq_args, &data->seq_res, task); + &data->args.seq_args, &data->res.seq_res, task); data->timestamp = jiffies; } @@ -5846,7 +5849,7 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) struct nfs_release_lockowner_data *data = calldata; struct nfs_server *server = data->server; - nfs40_sequence_done(task, &data->seq_res); + nfs40_sequence_done(task, &data->res.seq_res); switch (task->tk_status) { case 0: @@ -5887,7 +5890,6 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st data = kmalloc(sizeof(*data), GFP_NOFS); if (!data) return -ENOMEM; - nfs4_init_sequence(&data->seq_args, &data->seq_res, 0); data->lsp = lsp; data->server = server; data->args.lock_owner.clientid = server->nfs_client->cl_clientid; @@ -5895,6 +5897,8 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st data->args.lock_owner.s_dev = server->s_dev; msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data); return 0; } diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index cf883c7ae053..e799dc3c3b1d 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -231,14 +231,23 @@ out: return ret; } +/* + * nfs4_release_slot_table - release all slot table entries + */ +static void nfs4_release_slot_table(struct nfs4_slot_table *tbl) +{ + nfs4_shrink_slot_table(tbl, 0); +} + /** - * nfs4_release_slot_table - release resources attached to a slot table + * nfs4_shutdown_slot_table - release resources attached to a slot table * @tbl: slot table to shut down * */ -void nfs4_release_slot_table(struct nfs4_slot_table *tbl) +void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl) { - nfs4_shrink_slot_table(tbl, 0); + nfs4_release_slot_table(tbl); + rpc_destroy_wait_queue(&tbl->slot_tbl_waitq); } /** @@ -422,7 +431,7 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl, spin_unlock(&tbl->slot_tbl_lock); } -static void nfs4_destroy_session_slot_tables(struct nfs4_session *session) +static void nfs4_release_session_slot_tables(struct nfs4_session *session) { nfs4_release_slot_table(&session->fc_slot_table); nfs4_release_slot_table(&session->bc_slot_table); @@ -450,7 +459,7 @@ int nfs4_setup_session_slot_tables(struct nfs4_session *ses) if (status && tbl->slots == NULL) /* Fore and back channel share a connection so get * both slot tables or neither */ - nfs4_destroy_session_slot_tables(ses); + nfs4_release_session_slot_tables(ses); return status; } @@ -470,6 +479,12 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp) return session; } +static void nfs4_destroy_session_slot_tables(struct nfs4_session *session) +{ + nfs4_shutdown_slot_table(&session->fc_slot_table); + nfs4_shutdown_slot_table(&session->bc_slot_table); +} + void nfs4_destroy_session(struct nfs4_session *session) { struct rpc_xprt *xprt; diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 232306100651..b34ada9bc6a2 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -74,7 +74,7 @@ enum nfs4_session_state { extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, unsigned int max_reqs, const char *queue); -extern void nfs4_release_slot_table(struct nfs4_slot_table *tbl); +extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl); extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl); extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e5be72518bd7..0deb32105ccf 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -974,9 +974,6 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst, else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) { nfs4_stateid_copy(dst, &lsp->ls_stateid); ret = 0; - smp_rmb(); - if (!list_empty(&lsp->ls_seqid.list)) - ret = -EWOULDBLOCK; } spin_unlock(&state->state_lock); nfs4_put_lock_state(lsp); @@ -984,10 +981,9 @@ out: return ret; } -static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) +static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) { const nfs4_stateid *src; - int ret; int seq; do { @@ -996,12 +992,7 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) if (test_bit(NFS_OPEN_STATE, &state->flags)) src = &state->open_stateid; nfs4_stateid_copy(dst, src); - ret = 0; - smp_rmb(); - if (!list_empty(&state->owner->so_seqid.list)) - ret = -EWOULDBLOCK; } while (read_seqretry(&state->seqlock, seq)); - return ret; } /* @@ -1015,15 +1006,19 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state, if (ret == -EIO) /* A lost lock - don't even consider delegations */ goto out; - if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) + /* returns true if delegation stateid found and copied */ + if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) { + ret = 0; goto out; + } if (ret != -ENOENT) /* nfs4_copy_delegation_stateid() didn't over-write * dst, so it still has the lock stateid which we now * choose to use. */ goto out; - ret = nfs4_copy_open_stateid(dst, state); + nfs4_copy_open_stateid(dst, state); + ret = 0; out: if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41)) dst->seqid = 0; diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index d3a587144222..d190e33d0ec2 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -151,17 +151,15 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL); if (IS_ERR(pacl)) return PTR_ERR(pacl); - /* allocate for worst case: one (deny, allow) pair each: */ - size += 2 * pacl->a_count; } + /* allocate for worst case: one (deny, allow) pair each: */ + size += 2 * pacl->a_count; if (S_ISDIR(inode->i_mode)) { flags = NFS4_ACL_DIR; dpacl = get_acl(inode, ACL_TYPE_DEFAULT); if (dpacl) size += 2 * dpacl->a_count; - } else { - dpacl = NULL; } *acl = nfs4_acl_new(size); @@ -170,8 +168,7 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, goto out; } - if (pacl) - _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT); + _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT); if (dpacl) _posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 017d3cb5e99b..6d7be3f80356 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -449,6 +449,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, fh_lock(fhp); host_err = notify_change(dentry, iap, NULL); fh_unlock(fhp); + err = nfserrno(host_err); out_put_write_access: if (size_change) diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 0b9ff4395e6a..abc8cbcfe90e 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -86,7 +86,7 @@ static int dnotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 0e792f5e3147..dc638f786d5c 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -147,7 +147,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *fanotify_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { int ret = 0; struct fanotify_event_info *event; @@ -192,10 +192,12 @@ static int fanotify_handle_event(struct fsnotify_group *group, ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge); if (ret) { - BUG_ON(mask & FAN_ALL_PERM_EVENTS); + /* Permission events shouldn't be merged */ + BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS); /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); - ret = 0; + + return 0; } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index b6175fa11bf8..287a22c04149 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -698,6 +698,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) struct fsnotify_group *group; int f_flags, fd; struct user_struct *user; + struct fanotify_event_info *oevent; pr_debug("%s: flags=%d event_f_flags=%d\n", __func__, flags, event_f_flags); @@ -730,8 +731,20 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user; atomic_inc(&user->fanotify_listeners); + oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL); + if (unlikely(!oevent)) { + fd = -ENOMEM; + goto out_destroy_group; + } + group->overflow_event = &oevent->fse; + fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + oevent->tgid = get_pid(task_tgid(current)); + oevent->path.mnt = NULL; + oevent->path.dentry = NULL; + group->fanotify_data.f_flags = event_f_flags; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + oevent->response = 0; mutex_init(&group->fanotify_data.access_mutex); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 1d4e1ea2f37c..9d3e9c50066a 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -179,7 +179,7 @@ static int send_to_group(struct inode *to_tell, return group->ops->handle_event(group, to_tell, inode_mark, vfsmount_mark, mask, data, data_is, - file_name); + file_name, cookie); } /* diff --git a/fs/notify/group.c b/fs/notify/group.c index ee674fe2cec7..ad1995980456 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -55,6 +55,13 @@ void fsnotify_destroy_group(struct fsnotify_group *group) /* clear the notification queue of all events */ fsnotify_flush_notify(group); + /* + * Destroy overflow event (we cannot use fsnotify_destroy_event() as + * that deliberately ignores overflow events. + */ + if (group->overflow_event) + group->ops->free_event(group->overflow_event); + fsnotify_put_group(group); } @@ -99,7 +106,6 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) INIT_LIST_HEAD(&group->marks_list); group->ops = ops; - fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW); return group; } diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 485eef3f4407..ed855ef6f077 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -27,6 +27,6 @@ extern int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name); + const unsigned char *file_name, u32 cookie); extern const struct fsnotify_ops inotify_fsnotify_ops; diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index d5ee56348bb8..43ab1e1a07a2 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -67,7 +67,7 @@ int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { struct inotify_inode_mark *i_mark; struct inotify_event_info *event; @@ -103,6 +103,7 @@ int inotify_handle_event(struct fsnotify_group *group, fsn_event = &event->fse; fsnotify_init_event(fsn_event, inode, mask); event->wd = i_mark->wd; + event->sync_cookie = cookie; event->name_len = len; if (len) strcpy(event->name, file_name); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 497395c8274b..78a2ca3966c3 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -495,7 +495,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, /* Queue ignore event for the watch */ inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED, - NULL, FSNOTIFY_EVENT_NONE, NULL); + NULL, FSNOTIFY_EVENT_NONE, NULL, 0); i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); /* remove this mark from the idr */ @@ -633,11 +633,23 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod static struct fsnotify_group *inotify_new_group(unsigned int max_events) { struct fsnotify_group *group; + struct inotify_event_info *oevent; group = fsnotify_alloc_group(&inotify_fsnotify_ops); if (IS_ERR(group)) return group; + oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL); + if (unlikely(!oevent)) { + fsnotify_destroy_group(group); + return ERR_PTR(-ENOMEM); + } + group->overflow_event = &oevent->fse; + fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + oevent->wd = -1; + oevent->sync_cookie = 0; + oevent->name_len = 0; + group->max_events = max_events; spin_lock_init(&group->inotify_data.idr_lock); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 18b3c4427dca..1e58402171a5 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -80,7 +80,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, /* * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was - * added to the queue, 1 if the event was merged with some other queued event. + * added to the queue, 1 if the event was merged with some other queued event, + * 2 if the queue of events has overflown. */ int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -95,10 +96,14 @@ int fsnotify_add_notify_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); if (group->q_len >= group->max_events) { + ret = 2; /* Queue overflow event only if it isn't already queued */ - if (list_empty(&group->overflow_event.list)) - event = &group->overflow_event; - ret = 1; + if (!list_empty(&group->overflow_event->list)) { + mutex_unlock(&group->notification_mutex); + return ret; + } + event = group->overflow_event; + goto queue; } if (!list_empty(list) && merge) { @@ -109,6 +114,7 @@ int fsnotify_add_notify_event(struct fsnotify_group *group, } } +queue: group->q_len++; list_add_tail(&event->list, list); mutex_unlock(&group->notification_mutex); @@ -132,7 +138,11 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group event = list_first_entry(&group->notification_list, struct fsnotify_event, list); - list_del(&event->list); + /* + * We need to init list head for the case of overflow event so that + * check in fsnotify_add_notify_events() works + */ + list_del_init(&event->list); group->q_len--; return event; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index ea4ba9daeb47..db9bd8a31725 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2134,7 +2134,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0) { - int err = generic_write_sync(file, pos, ret); + int err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 8750ae1b8636..e2edff38be52 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -4742,6 +4742,7 @@ int ocfs2_add_clusters_in_btree(handle_t *handle, enum ocfs2_alloc_restarted *reason_ret) { int status = 0, err = 0; + int need_free = 0; int free_extents; enum ocfs2_alloc_restarted reason = RESTART_NONE; u32 bit_off, num_bits; @@ -4796,7 +4797,8 @@ int ocfs2_add_clusters_in_btree(handle_t *handle, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); - goto leave; + need_free = 1; + goto bail; } block = ocfs2_clusters_to_blocks(osb->sb, bit_off); @@ -4807,7 +4809,8 @@ int ocfs2_add_clusters_in_btree(handle_t *handle, num_bits, flags, meta_ac); if (status < 0) { mlog_errno(status); - goto leave; + need_free = 1; + goto bail; } ocfs2_journal_dirty(handle, et->et_root_bh); @@ -4821,6 +4824,19 @@ int ocfs2_add_clusters_in_btree(handle_t *handle, reason = RESTART_TRANS; } +bail: + if (need_free) { + if (data_ac->ac_which == OCFS2_AC_USE_LOCAL) + ocfs2_free_local_alloc_bits(osb, handle, data_ac, + bit_off, num_bits); + else + ocfs2_free_clusters(handle, + data_ac->ac_inode, + data_ac->ac_bh, + ocfs2_clusters_to_blocks(osb->sb, bit_off), + num_bits); + } + leave: if (reason_ret) *reason_ret = reason; @@ -6805,6 +6821,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, struct buffer_head *di_bh) { int ret, i, has_data, num_pages = 0; + int need_free = 0; + u32 bit_off, num; handle_t *handle; u64 uninitialized_var(block); struct ocfs2_inode_info *oi = OCFS2_I(inode); @@ -6850,7 +6868,6 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, } if (has_data) { - u32 bit_off, num; unsigned int page_end; u64 phys; @@ -6886,6 +6903,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages); if (ret) { mlog_errno(ret); + need_free = 1; goto out_commit; } @@ -6896,6 +6914,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, ret = ocfs2_read_inline_data(inode, pages[0], di_bh); if (ret) { mlog_errno(ret); + need_free = 1; goto out_commit; } @@ -6927,6 +6946,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, ret = ocfs2_insert_extent(handle, &et, 0, block, 1, 0, NULL); if (ret) { mlog_errno(ret); + need_free = 1; goto out_commit; } @@ -6938,6 +6958,18 @@ out_commit: dquot_free_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, 1)); + if (need_free) { + if (data_ac->ac_which == OCFS2_AC_USE_LOCAL) + ocfs2_free_local_alloc_bits(osb, handle, data_ac, + bit_off, num); + else + ocfs2_free_clusters(handle, + data_ac->ac_inode, + data_ac->ac_bh, + ocfs2_clusters_to_blocks(osb->sb, bit_off), + num); + } + ocfs2_commit_trans(osb, handle); out_unlock: @@ -7126,7 +7158,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, if (end > i_size_read(inode)) end = i_size_read(inode); - BUG_ON(start >= end); + BUG_ON(start > end); if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) || !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) || diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index d77d71ead8d1..51632c40e896 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -185,6 +185,9 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, file->f_path.dentry->d_name.name, (unsigned long long)datasync); + if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + return -EROFS; + err = filemap_write_and_wait_range(inode->i_mapping, start, end); if (err) return err; @@ -474,11 +477,6 @@ static int ocfs2_truncate_file(struct inode *inode, goto bail; } - /* lets handle the simple truncate cases before doing any more - * cluster locking. */ - if (new_i_size == le64_to_cpu(fe->i_size)) - goto bail; - down_write(&OCFS2_I(inode)->ip_alloc_sem); ocfs2_resv_discard(&osb->osb_la_resmap, @@ -718,7 +716,8 @@ leave: * While a write will already be ordering the data, a truncate will not. * Thus, we need to explicitly order the zeroed pages. */ -static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode) +static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode, + struct buffer_head *di_bh) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); handle_t *handle = NULL; @@ -735,7 +734,14 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode) } ret = ocfs2_jbd2_file_inode(handle, inode); - if (ret < 0) + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) mlog_errno(ret); out: @@ -751,7 +757,7 @@ out: * to be too fragile to do exactly what we need without us having to * worry about recursive locking in ->write_begin() and ->write_end(). */ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, - u64 abs_to) + u64 abs_to, struct buffer_head *di_bh) { struct address_space *mapping = inode->i_mapping; struct page *page; @@ -759,6 +765,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, handle_t *handle = NULL; int ret = 0; unsigned zero_from, zero_to, block_start, block_end; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; BUG_ON(abs_from >= abs_to); BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT)); @@ -801,7 +808,8 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, } if (!handle) { - handle = ocfs2_zero_start_ordered_transaction(inode); + handle = ocfs2_zero_start_ordered_transaction(inode, + di_bh); if (IS_ERR(handle)) { ret = PTR_ERR(handle); handle = NULL; @@ -818,8 +826,22 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, ret = 0; } - if (handle) + if (handle) { + /* + * fs-writeback will release the dirty pages without page lock + * whose offset are over inode size, the release happens at + * block_write_full_page_endio(). + */ + i_size_write(inode, abs_to); + inode->i_blocks = ocfs2_inode_sector_count(inode); + di->i_size = cpu_to_le64((u64)i_size_read(inode)); + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); + di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + di->i_mtime_nsec = di->i_ctime_nsec; + ocfs2_journal_dirty(handle, di_bh); ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); + } out_unlock: unlock_page(page); @@ -915,7 +937,7 @@ out: * has made sure that the entire range needs zeroing. */ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, - u64 range_end) + u64 range_end, struct buffer_head *di_bh) { int rc = 0; u64 next_pos; @@ -931,7 +953,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE; if (next_pos > range_end) next_pos = range_end; - rc = ocfs2_write_zero_page(inode, zero_pos, next_pos); + rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh); if (rc < 0) { mlog_errno(rc); break; @@ -977,7 +999,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, range_end = zero_to_size; ret = ocfs2_zero_extend_range(inode, range_start, - range_end); + range_end, di_bh); if (ret) { mlog_errno(ret); break; @@ -1145,14 +1167,14 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) goto bail_unlock_rw; } - if (size_change && attr->ia_size != i_size_read(inode)) { + if (size_change) { status = inode_newsize_ok(inode, attr->ia_size); if (status) goto bail_unlock; inode_dio_wait(inode); - if (i_size_read(inode) > attr->ia_size) { + if (i_size_read(inode) >= attr->ia_size) { if (ocfs2_should_order_data(inode)) { status = ocfs2_begin_ordered_truncate(inode, attr->ia_size); @@ -2371,8 +2393,8 @@ out_dio: if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || ((file->f_flags & O_DIRECT) && !direct_io)) { - ret = filemap_fdatawrite_range(file->f_mapping, pos, - pos + count - 1); + ret = filemap_fdatawrite_range(file->f_mapping, *ppos, + *ppos + count - 1); if (ret < 0) written = ret; @@ -2385,8 +2407,8 @@ out_dio: } if (!ret) - ret = filemap_fdatawait_range(file->f_mapping, pos, - pos + count - 1); + ret = filemap_fdatawait_range(file->f_mapping, *ppos, + *ppos + count - 1); } /* diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index cd5496b7a0a3..044013455621 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -781,6 +781,48 @@ bail: return status; } +int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb, + handle_t *handle, + struct ocfs2_alloc_context *ac, + u32 bit_off, + u32 num_bits) +{ + int status, start; + u32 clear_bits; + struct inode *local_alloc_inode; + void *bitmap; + struct ocfs2_dinode *alloc; + struct ocfs2_local_alloc *la; + + BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL); + + local_alloc_inode = ac->ac_inode; + alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; + la = OCFS2_LOCAL_ALLOC(alloc); + + bitmap = la->la_bitmap; + start = bit_off - le32_to_cpu(la->la_bm_off); + clear_bits = num_bits; + + status = ocfs2_journal_access_di(handle, + INODE_CACHE(local_alloc_inode), + osb->local_alloc_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (status < 0) { + mlog_errno(status); + goto bail; + } + + while (clear_bits--) + ocfs2_clear_bit(start++, bitmap); + + le32_add_cpu(&alloc->id1.bitmap1.i_used, -num_bits); + ocfs2_journal_dirty(handle, osb->local_alloc_bh); + +bail: + return status; +} + static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc) { u32 count; diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h index 1be9b5864460..44a7d1fb2dec 100644 --- a/fs/ocfs2/localalloc.h +++ b/fs/ocfs2/localalloc.h @@ -55,6 +55,12 @@ int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb, u32 *bit_off, u32 *num_bits); +int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb, + handle_t *handle, + struct ocfs2_alloc_context *ac, + u32 bit_off, + u32 num_bits); + void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb, unsigned int num_clusters); void ocfs2_la_enable_worker(struct work_struct *work); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index f4d609be9400..3683643f3f0e 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -664,6 +664,7 @@ static int ocfs2_link(struct dentry *old_dentry, struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; + u64 old_de_ino; trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno, old_dentry->d_name.len, old_dentry->d_name.name, @@ -686,6 +687,22 @@ static int ocfs2_link(struct dentry *old_dentry, goto out; } + err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name, + old_dentry->d_name.len, &old_de_ino); + if (err) { + err = -ENOENT; + goto out; + } + + /* + * Check whether another node removed the source inode while we + * were in the vfs. + */ + if (old_de_ino != OCFS2_I(inode)->ip_blkno) { + err = -ENOENT; + goto out; + } + err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name, dentry->d_name.len); if (err) diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index aaa50611ec66..d7b5108789e2 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot) */ if (status < 0) mlog_errno(status); + /* + * Clear dq_off so that we search for the structure in quota file next + * time we acquire it. The structure might be deleted and reallocated + * elsewhere by another node while our dquot structure is on freelist. + */ + dquot->dq_off = 0; clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_trans: ocfs2_commit_trans(osb, handle); @@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot) status = ocfs2_lock_global_qf(info, 1); if (status < 0) goto out; - if (!test_bit(DQ_READ_B, &dquot->dq_flags)) { - status = ocfs2_qinfo_lock(info, 0); - if (status < 0) - goto out_dq; - status = qtree_read_dquot(&info->dqi_gi, dquot); - ocfs2_qinfo_unlock(info, 0); - if (status < 0) - goto out_dq; - } - set_bit(DQ_READ_B, &dquot->dq_flags); + status = ocfs2_qinfo_lock(info, 0); + if (status < 0) + goto out_dq; + /* + * We always want to read dquot structure from disk because we don't + * know what happened with it while it was on freelist. + */ + status = qtree_read_dquot(&info->dqi_gi, dquot); + ocfs2_qinfo_unlock(info, 0); + if (status < 0) + goto out_dq; OCFS2_DQUOT(dquot)->dq_use_count++; OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 2e4344be3b96..2001862bf2b1 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot) ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh); out: - /* Clear the read bit so that next time someone uses this - * dquot he reads fresh info from disk and allocates local - * dquot structure */ - clear_bit(DQ_READ_B, &dquot->dq_flags); return status; } diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 1324e6600e57..ca5ce14cbddc 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -346,7 +346,9 @@ int ocfs2_cluster_connect(const char *stack_name, strlcpy(new_conn->cc_name, group, GROUP_NAME_MAX + 1); new_conn->cc_namelen = grouplen; - strlcpy(new_conn->cc_cluster_name, cluster_name, CLUSTER_NAME_MAX + 1); + if (cluster_name_len) + strlcpy(new_conn->cc_cluster_name, cluster_name, + CLUSTER_NAME_MAX + 1); new_conn->cc_cluster_name_len = cluster_name_len; new_conn->cc_recovery_handler = recovery_handler; new_conn->cc_recovery_data = recovery_data; diff --git a/fs/open.c b/fs/open.c index 4b3e1edf2fe4..b9ed8b25c108 100644 --- a/fs/open.c +++ b/fs/open.c @@ -705,6 +705,10 @@ static int do_dentry_open(struct file *f, return 0; } + /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ + if (S_ISREG(inode->i_mode)) + f->f_mode |= FMODE_ATOMIC_POS; + f->f_op = fops_get(inode->i_fop); if (unlikely(WARN_ON(!f->f_op))) { error = -ENODEV; diff --git a/fs/pnode.c b/fs/pnode.c index c7221bb19801..88396df725b4 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -220,14 +220,14 @@ static struct mount *get_source(struct mount *dest, * @tree_list : list of heads of trees to be attached. */ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, - struct mount *source_mnt, struct list_head *tree_list) + struct mount *source_mnt, struct hlist_head *tree_list) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mount *m, *child; int ret = 0; struct mount *prev_dest_mnt = dest_mnt; struct mount *prev_src_mnt = source_mnt; - LIST_HEAD(tmp_list); + HLIST_HEAD(tmp_list); for (m = propagation_next(dest_mnt, dest_mnt); m; m = propagation_next(m, dest_mnt)) { @@ -246,27 +246,29 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, child = copy_tree(source, source->mnt.mnt_root, type); if (IS_ERR(child)) { ret = PTR_ERR(child); - list_splice(tree_list, tmp_list.prev); + tmp_list = *tree_list; + tmp_list.first->pprev = &tmp_list.first; + INIT_HLIST_HEAD(tree_list); goto out; } if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) { mnt_set_mountpoint(m, dest_mp, child); - list_add_tail(&child->mnt_hash, tree_list); + hlist_add_head(&child->mnt_hash, tree_list); } else { /* * This can happen if the parent mount was bind mounted * on some subdirectory of a shared/slave mount. */ - list_add_tail(&child->mnt_hash, &tmp_list); + hlist_add_head(&child->mnt_hash, &tmp_list); } prev_dest_mnt = m; prev_src_mnt = child; } out: lock_mount_hash(); - while (!list_empty(&tmp_list)) { - child = list_first_entry(&tmp_list, struct mount, mnt_hash); + while (!hlist_empty(&tmp_list)) { + child = hlist_entry(tmp_list.first, struct mount, mnt_hash); umount_tree(child, 0); } unlock_mount_hash(); @@ -338,8 +340,10 @@ static void __propagate_umount(struct mount *mnt) * umount the child only if the child has no * other children */ - if (child && list_empty(&child->mnt_mounts)) - list_move_tail(&child->mnt_hash, &mnt->mnt_hash); + if (child && list_empty(&child->mnt_mounts)) { + hlist_del_init_rcu(&child->mnt_hash); + hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash); + } } } @@ -350,11 +354,11 @@ static void __propagate_umount(struct mount *mnt) * * vfsmount lock must be held for write */ -int propagate_umount(struct list_head *list) +int propagate_umount(struct hlist_head *list) { struct mount *mnt; - list_for_each_entry(mnt, list, mnt_hash) + hlist_for_each_entry(mnt, list, mnt_hash) __propagate_umount(mnt); return 0; } diff --git a/fs/pnode.h b/fs/pnode.h index 59e7eda1851e..fc28a27fa892 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -36,8 +36,8 @@ static inline void set_mnt_shared(struct mount *mnt) void change_mnt_propagation(struct mount *, int); int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, - struct list_head *); -int propagate_umount(struct list_head *); + struct hlist_head *); +int propagate_umount(struct hlist_head *); int propagate_mount_busy(struct mount *, int); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 38bae5a0ea25..11c54fd51e16 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -521,8 +521,11 @@ posix_acl_chmod(struct inode *inode, umode_t mode) return -EOPNOTSUPP; acl = get_acl(inode, ACL_TYPE_ACCESS); - if (IS_ERR_OR_NULL(acl)) + if (IS_ERR_OR_NULL(acl)) { + if (acl == ERR_PTR(-EOPNOTSUPP)) + return 0; return PTR_ERR(acl); + } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) @@ -544,14 +547,15 @@ posix_acl_create(struct inode *dir, umode_t *mode, goto no_acl; p = get_acl(dir, ACL_TYPE_DEFAULT); - if (IS_ERR(p)) + if (IS_ERR(p)) { + if (p == ERR_PTR(-EOPNOTSUPP)) + goto apply_umask; return PTR_ERR(p); - - if (!p) { - *mode &= ~current_umask(); - goto no_acl; } + if (!p) + goto apply_umask; + *acl = posix_acl_clone(p, GFP_NOFS); if (!*acl) return -ENOMEM; @@ -575,6 +579,8 @@ posix_acl_create(struct inode *dir, umode_t *mode, } return 0; +apply_umask: + *mode &= ~current_umask(); no_acl: *default_acl = NULL; *acl = NULL; diff --git a/fs/proc/base.c b/fs/proc/base.c index 51507065263b..b9760628e1fd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1824,6 +1824,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path) if (rc) goto out_mmput; + rc = -ENOENT; down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { diff --git a/fs/proc/page.c b/fs/proc/page.c index 02174a610315..e647c55275d9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -121,9 +121,8 @@ u64 stable_page_flags(struct page *page) * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && - (PageLRU(compound_trans_head(page)) || - PageAnon(compound_trans_head(page)))) + else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || + PageAnon(compound_head(page)))) u |= 1 << KPF_THP; /* diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 6f599c62f0cc..9d231e9e5f0e 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -9,7 +9,7 @@ #include <linux/slab.h> #include <linux/time.h> #include <linux/irqnr.h> -#include <asm/cputime.h> +#include <linux/cputime.h> #include <linux/tick.h> #ifndef arch_irq_stat_cpu diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 7141b8d0ca9e..33de567c25af 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -5,7 +5,7 @@ #include <linux/seq_file.h> #include <linux/time.h> #include <linux/kernel_stat.h> -#include <asm/cputime.h> +#include <linux/cputime.h> static int uptime_proc_show(struct seq_file *m, void *v) { diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 2ca7ba047f04..88d4585b30f1 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -468,17 +468,24 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr) return rc; } nhdr_ptr = notes_section; - while (real_sz < max_sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf64_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz); } kfree(notes_section); phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + return -EINVAL; + } } return 0; @@ -648,17 +655,24 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr) return rc; } nhdr_ptr = notes_section; - while (real_sz < max_sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf32_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz); } kfree(notes_section); phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + return -EINVAL; + } } return 0; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 831d49a4111f..cfc8dcc16043 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -581,9 +581,17 @@ int dquot_scan_active(struct super_block *sb, dqstats_inc(DQST_LOOKUPS); dqput(old_dquot); old_dquot = dquot; - ret = fn(dquot, priv); - if (ret < 0) - goto out; + /* + * ->release_dquot() can be racing with us. Our reference + * protects us from new calls to it so just wait for any + * outstanding call and recheck the DQ_ACTIVE_B after that. + */ + wait_on_dquot(dquot); + if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + ret = fn(dquot, priv); + if (ret < 0) + goto out; + } spin_lock(&dq_list_lock); /* We are safe to continue now because our dquot could not * be moved out of the inuse list while we hold the reference */ diff --git a/fs/read_write.c b/fs/read_write.c index edc5746a902a..31c6efa43183 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -264,10 +264,22 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(vfs_llseek); +static inline struct fd fdget_pos(int fd) +{ + return __to_fd(__fdget_pos(fd)); +} + +static inline void fdput_pos(struct fd f) +{ + if (f.flags & FDPUT_POS_UNLOCK) + mutex_unlock(&f.file->f_pos_lock); + fdput(f); +} + SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { off_t retval; - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); if (!f.file) return -EBADF; @@ -278,7 +290,7 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } - fdput(f); + fdput_pos(f); return retval; } @@ -295,7 +307,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned int, whence) { int retval; - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); loff_t offset; if (!f.file) @@ -315,7 +327,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, retval = 0; } out_putf: - fdput(f); + fdput_pos(f); return retval; } #endif @@ -498,7 +510,7 @@ static inline void file_pos_write(struct file *file, loff_t pos) SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -506,7 +518,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) ret = vfs_read(f.file, buf, count, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } return ret; } @@ -514,7 +526,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -522,7 +534,7 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, ret = vfs_write(f.file, buf, count, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } return ret; @@ -797,7 +809,7 @@ EXPORT_SYMBOL(vfs_writev); SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -805,7 +817,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, ret = vfs_readv(f.file, vec, vlen, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } if (ret > 0) @@ -817,7 +829,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { @@ -825,7 +837,7 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, ret = vfs_writev(f.file, vec, vlen, &pos); if (ret >= 0) file_pos_write(f.file, pos); - fdput(f); + fdput_pos(f); } if (ret > 0) @@ -968,7 +980,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret; loff_t pos; @@ -978,13 +990,13 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, ret = compat_readv(f.file, vec, vlen, &pos); if (ret >= 0) f.file->f_pos = pos; - fdput(f); + fdput_pos(f); return ret; } -COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, - const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos) +static long __compat_sys_preadv64(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos) { struct fd f; ssize_t ret; @@ -1001,12 +1013,22 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, return ret; } +#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 +COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, + const struct compat_iovec __user *,vec, + unsigned long, vlen, loff_t, pos) +{ + return __compat_sys_preadv64(fd, vec, vlen, pos); +} +#endif + COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; - return compat_sys_preadv64(fd, vec, vlen, pos); + + return __compat_sys_preadv64(fd, vec, vlen, pos); } static size_t compat_writev(struct file *file, @@ -1035,7 +1057,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, const struct compat_iovec __user *, vec, compat_ulong_t, vlen) { - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); ssize_t ret; loff_t pos; @@ -1045,13 +1067,13 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, ret = compat_writev(f.file, vec, vlen, &pos); if (ret >= 0) f.file->f_pos = pos; - fdput(f); + fdput_pos(f); return ret; } -COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, - const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos) +static long __compat_sys_pwritev64(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos) { struct fd f; ssize_t ret; @@ -1068,12 +1090,22 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, return ret; } +#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 +COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, + const struct compat_iovec __user *,vec, + unsigned long, vlen, loff_t, pos) +{ + return __compat_sys_pwritev64(fd, vec, vlen, pos); +} +#endif + COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; - return compat_sys_pwritev64(fd, vec, vlen, pos); + + return __compat_sys_pwritev64(fd, vec, vlen, pos); } #endif diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c index 2b7882b508db..9a3c68cf6026 100644 --- a/fs/reiserfs/do_balan.c +++ b/fs/reiserfs/do_balan.c @@ -324,23 +324,17 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h switch (flag) { case M_INSERT: /* insert item into L[0] */ - if (item_pos == tb->lnum[0] - 1 - && tb->lbytes != -1) { + if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) { /* part of new item falls into L[0] */ int new_item_len; int version; - ret_val = - leaf_shift_left(tb, tb->lnum[0] - 1, - -1); + ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, -1); /* Calculate item length to insert to S[0] */ - new_item_len = - ih_item_len(ih) - tb->lbytes; + new_item_len = ih_item_len(ih) - tb->lbytes; /* Calculate and check item length to insert to L[0] */ - put_ih_item_len(ih, - ih_item_len(ih) - - new_item_len); + put_ih_item_len(ih, ih_item_len(ih) - new_item_len); RFALSE(ih_item_len(ih) <= 0, "PAP-12080: there is nothing to insert into L[0]: ih_item_len=%d", @@ -349,30 +343,18 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* Insert new item into L[0] */ buffer_info_init_left(tb, &bi); leaf_insert_into_buf(&bi, - n + item_pos - - ret_val, ih, body, - zeros_num > - ih_item_len(ih) ? - ih_item_len(ih) : - zeros_num); + n + item_pos - ret_val, ih, body, + zeros_num > ih_item_len(ih) ? ih_item_len(ih) : zeros_num); version = ih_version(ih); /* Calculate key component, item length and body to insert into S[0] */ - set_le_ih_k_offset(ih, - le_ih_k_offset(ih) + - (tb-> - lbytes << - (is_indirect_le_ih - (ih) ? tb->tb_sb-> - s_blocksize_bits - - UNFM_P_SHIFT : - 0))); + set_le_ih_k_offset(ih, le_ih_k_offset(ih) + + (tb-> lbytes << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0))); put_ih_item_len(ih, new_item_len); if (tb->lbytes > zeros_num) { - body += - (tb->lbytes - zeros_num); + body += (tb->lbytes - zeros_num); zeros_num = 0; } else zeros_num -= tb->lbytes; @@ -383,15 +365,10 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h } else { /* new item in whole falls into L[0] */ /* Shift lnum[0]-1 items to L[0] */ - ret_val = - leaf_shift_left(tb, tb->lnum[0] - 1, - tb->lbytes); + ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, tb->lbytes); /* Insert new item into L[0] */ buffer_info_init_left(tb, &bi); - leaf_insert_into_buf(&bi, - n + item_pos - - ret_val, ih, body, - zeros_num); + leaf_insert_into_buf(&bi, n + item_pos - ret_val, ih, body, zeros_num); tb->insert_size[0] = 0; zeros_num = 0; } @@ -399,264 +376,117 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h case M_PASTE: /* append item in L[0] */ - if (item_pos == tb->lnum[0] - 1 - && tb->lbytes != -1) { + if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) { /* we must shift the part of the appended item */ - if (is_direntry_le_ih - (B_N_PITEM_HEAD(tbS0, item_pos))) { + if (is_direntry_le_ih(B_N_PITEM_HEAD(tbS0, item_pos))) { RFALSE(zeros_num, "PAP-12090: invalid parameter in case of a directory"); /* directory item */ if (tb->lbytes > pos_in_item) { /* new directory entry falls into L[0] */ - struct item_head - *pasted; - int l_pos_in_item = - pos_in_item; + struct item_head *pasted; + int l_pos_in_item = pos_in_item; /* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 entries from given directory item */ - ret_val = - leaf_shift_left(tb, - tb-> - lnum - [0], - tb-> - lbytes - - - 1); - if (ret_val - && !item_pos) { - pasted = - B_N_PITEM_HEAD - (tb->L[0], - B_NR_ITEMS - (tb-> - L[0]) - - 1); - l_pos_in_item += - I_ENTRY_COUNT - (pasted) - - (tb-> - lbytes - - 1); + ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes-1); + if (ret_val && !item_pos) { + pasted = B_N_PITEM_HEAD(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1); + l_pos_in_item += I_ENTRY_COUNT(pasted) - (tb->lbytes -1); } /* Append given directory entry to directory item */ buffer_info_init_left(tb, &bi); - leaf_paste_in_buffer - (&bi, - n + item_pos - - ret_val, - l_pos_in_item, - tb->insert_size[0], - body, zeros_num); + leaf_paste_in_buffer(&bi, n + item_pos - ret_val, l_pos_in_item, tb->insert_size[0], body, zeros_num); /* previous string prepared space for pasting new entry, following string pastes this entry */ /* when we have merge directory item, pos_in_item has been changed too */ /* paste new directory entry. 1 is entry number */ - leaf_paste_entries(&bi, - n + - item_pos - - - ret_val, - l_pos_in_item, - 1, - (struct - reiserfs_de_head - *) - body, - body - + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, n + item_pos - ret_val, l_pos_in_item, + 1, (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); tb->insert_size[0] = 0; } else { /* new directory item doesn't fall into L[0] */ /* Shift lnum[0]-1 items in whole. Shift lbytes directory entries from directory item number lnum[0] */ - leaf_shift_left(tb, - tb-> - lnum[0], - tb-> - lbytes); + leaf_shift_left(tb, tb->lnum[0], tb->lbytes); } /* Calculate new position to append in item body */ pos_in_item -= tb->lbytes; } else { /* regular object */ - RFALSE(tb->lbytes <= 0, - "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", - tb->lbytes); - RFALSE(pos_in_item != - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)), + RFALSE(tb->lbytes <= 0, "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", tb->lbytes); + RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)), "PAP-12100: incorrect position to paste: item_len=%d, pos_in_item=%d", - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)), - pos_in_item); + ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),pos_in_item); if (tb->lbytes >= pos_in_item) { /* appended item will be in L[0] in whole */ int l_n; /* this bytes number must be appended to the last item of L[h] */ - l_n = - tb->lbytes - - pos_in_item; + l_n = tb->lbytes - pos_in_item; /* Calculate new insert_size[0] */ - tb->insert_size[0] -= - l_n; + tb->insert_size[0] -= l_n; - RFALSE(tb-> - insert_size[0] <= - 0, + RFALSE(tb->insert_size[0] <= 0, "PAP-12105: there is nothing to paste into L[0]. insert_size=%d", - tb-> - insert_size[0]); - ret_val = - leaf_shift_left(tb, - tb-> - lnum - [0], - ih_item_len - (B_N_PITEM_HEAD - (tbS0, - item_pos))); + tb->insert_size[0]); + ret_val = leaf_shift_left(tb, tb->lnum[0], ih_item_len + (B_N_PITEM_HEAD(tbS0, item_pos))); /* Append to body of item in L[0] */ buffer_info_init_left(tb, &bi); leaf_paste_in_buffer - (&bi, - n + item_pos - - ret_val, - ih_item_len - (B_N_PITEM_HEAD - (tb->L[0], - n + item_pos - - ret_val)), l_n, - body, - zeros_num > - l_n ? l_n : - zeros_num); + (&bi, n + item_pos - ret_val, ih_item_len + (B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val)), + l_n, body, + zeros_num > l_n ? l_n : zeros_num); /* 0-th item in S0 can be only of DIRECT type when l_n != 0 */ { int version; - int temp_l = - l_n; - - RFALSE - (ih_item_len - (B_N_PITEM_HEAD - (tbS0, - 0)), + int temp_l = l_n; + + RFALSE(ih_item_len(B_N_PITEM_HEAD(tbS0, 0)), "PAP-12106: item length must be 0"); - RFALSE - (comp_short_le_keys - (B_N_PKEY - (tbS0, 0), - B_N_PKEY - (tb->L[0], - n + - item_pos - - - ret_val)), + RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY + (tb->L[0], n + item_pos - ret_val)), "PAP-12107: items must be of the same file"); if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val))) { - temp_l = - l_n - << - (tb-> - tb_sb-> - s_blocksize_bits - - - UNFM_P_SHIFT); + temp_l = l_n << (tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT); } /* update key of first item in S0 */ - version = - ih_version - (B_N_PITEM_HEAD - (tbS0, 0)); - set_le_key_k_offset - (version, - B_N_PKEY - (tbS0, 0), - le_key_k_offset - (version, - B_N_PKEY - (tbS0, - 0)) + - temp_l); + version = ih_version(B_N_PITEM_HEAD(tbS0, 0)); + set_le_key_k_offset(version, B_N_PKEY(tbS0, 0), + le_key_k_offset(version,B_N_PKEY(tbS0, 0)) + temp_l); /* update left delimiting key */ - set_le_key_k_offset - (version, - B_N_PDELIM_KEY - (tb-> - CFL[0], - tb-> - lkey[0]), - le_key_k_offset - (version, - B_N_PDELIM_KEY - (tb-> - CFL[0], - tb-> - lkey[0])) - + temp_l); + set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), + le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0])) + temp_l); } /* Calculate new body, position in item and insert_size[0] */ if (l_n > zeros_num) { - body += - (l_n - - zeros_num); + body += (l_n - zeros_num); zeros_num = 0; } else - zeros_num -= - l_n; + zeros_num -= l_n; pos_in_item = 0; - RFALSE - (comp_short_le_keys - (B_N_PKEY(tbS0, 0), - B_N_PKEY(tb->L[0], - B_NR_ITEMS - (tb-> - L[0]) - - 1)) - || - !op_is_left_mergeable - (B_N_PKEY(tbS0, 0), - tbS0->b_size) - || - !op_is_left_mergeable - (B_N_PDELIM_KEY - (tb->CFL[0], - tb->lkey[0]), - tbS0->b_size), + RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1)) + || !op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size) + || !op_is_left_mergeable(B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), tbS0->b_size), "PAP-12120: item must be merge-able with left neighboring item"); } else { /* only part of the appended item will be in L[0] */ /* Calculate position in item for append in S[0] */ - pos_in_item -= - tb->lbytes; + pos_in_item -= tb->lbytes; - RFALSE(pos_in_item <= 0, - "PAP-12125: no place for paste. pos_in_item=%d", - pos_in_item); + RFALSE(pos_in_item <= 0, "PAP-12125: no place for paste. pos_in_item=%d", pos_in_item); /* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */ - leaf_shift_left(tb, - tb-> - lnum[0], - tb-> - lbytes); + leaf_shift_left(tb, tb->lnum[0], tb->lbytes); } } } else { /* appended item will be in L[0] in whole */ @@ -665,52 +495,30 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h if (!item_pos && op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)) { /* if we paste into first item of S[0] and it is left mergable */ /* then increment pos_in_item by the size of the last item in L[0] */ - pasted = - B_N_PITEM_HEAD(tb->L[0], - n - 1); + pasted = B_N_PITEM_HEAD(tb->L[0], n - 1); if (is_direntry_le_ih(pasted)) - pos_in_item += - ih_entry_count - (pasted); + pos_in_item += ih_entry_count(pasted); else - pos_in_item += - ih_item_len(pasted); + pos_in_item += ih_item_len(pasted); } /* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */ - ret_val = - leaf_shift_left(tb, tb->lnum[0], - tb->lbytes); + ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes); /* Append to body of item in L[0] */ buffer_info_init_left(tb, &bi); - leaf_paste_in_buffer(&bi, - n + item_pos - - ret_val, + leaf_paste_in_buffer(&bi, n + item_pos - ret_val, pos_in_item, tb->insert_size[0], body, zeros_num); /* if appended item is directory, paste entry */ - pasted = - B_N_PITEM_HEAD(tb->L[0], - n + item_pos - - ret_val); + pasted = B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val); if (is_direntry_le_ih(pasted)) - leaf_paste_entries(&bi, - n + - item_pos - - ret_val, - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, n + item_pos - ret_val, + pos_in_item, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, + tb->insert_size[0]); /* if appended item is indirect item, put unformatted node into un list */ if (is_indirect_le_ih(pasted)) set_ih_free_space(pasted, 0); @@ -722,13 +530,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h reiserfs_panic(tb->tb_sb, "PAP-12130", "lnum > 0: unexpected mode: " " %s(%d)", - (flag == - M_DELETE) ? "DELETE" : ((flag == - M_CUT) - ? "CUT" - : - "UNKNOWN"), - flag); + (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag); } } else { /* new item doesn't fall into L[0] */ @@ -748,14 +550,12 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h case M_INSERT: /* insert item */ if (n - tb->rnum[0] < item_pos) { /* new item or its part falls to R[0] */ if (item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) { /* part of new item falls into R[0] */ - loff_t old_key_comp, old_len, - r_zeros_number; + loff_t old_key_comp, old_len, r_zeros_number; const char *r_body; int version; loff_t offset; - leaf_shift_right(tb, tb->rnum[0] - 1, - -1); + leaf_shift_right(tb, tb->rnum[0] - 1, -1); version = ih_version(ih); /* Remember key component and item length */ @@ -763,29 +563,17 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h old_len = ih_item_len(ih); /* Calculate key component and item length to insert into R[0] */ - offset = - le_ih_k_offset(ih) + - ((old_len - - tb-> - rbytes) << (is_indirect_le_ih(ih) - ? tb->tb_sb-> - s_blocksize_bits - - UNFM_P_SHIFT : 0)); + offset = le_ih_k_offset(ih) + ((old_len - tb->rbytes) << (is_indirect_le_ih(ih) ? tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT : 0)); set_le_ih_k_offset(ih, offset); put_ih_item_len(ih, tb->rbytes); /* Insert part of the item into R[0] */ buffer_info_init_right(tb, &bi); if ((old_len - tb->rbytes) > zeros_num) { r_zeros_number = 0; - r_body = - body + (old_len - - tb->rbytes) - - zeros_num; + r_body = body + (old_len - tb->rbytes) - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - (old_len - - tb->rbytes); + r_zeros_number = zeros_num - (old_len - tb->rbytes); zeros_num -= r_zeros_number; } @@ -798,25 +586,18 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* Calculate key component and item length to insert into S[0] */ set_le_ih_k_offset(ih, old_key_comp); - put_ih_item_len(ih, - old_len - tb->rbytes); + put_ih_item_len(ih, old_len - tb->rbytes); tb->insert_size[0] -= tb->rbytes; } else { /* whole new item falls into R[0] */ /* Shift rnum[0]-1 items to R[0] */ - ret_val = - leaf_shift_right(tb, - tb->rnum[0] - 1, - tb->rbytes); + ret_val = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes); /* Insert new item into R[0] */ buffer_info_init_right(tb, &bi); - leaf_insert_into_buf(&bi, - item_pos - n + - tb->rnum[0] - 1, - ih, body, - zeros_num); + leaf_insert_into_buf(&bi, item_pos - n + tb->rnum[0] - 1, + ih, body, zeros_num); if (item_pos - n + tb->rnum[0] - 1 == 0) { replace_key(tb, tb->CFR[0], @@ -841,200 +622,97 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h RFALSE(zeros_num, "PAP-12145: invalid parameter in case of a directory"); - entry_count = - I_ENTRY_COUNT(B_N_PITEM_HEAD - (tbS0, - item_pos)); + entry_count = I_ENTRY_COUNT(B_N_PITEM_HEAD + (tbS0, item_pos)); if (entry_count - tb->rbytes < pos_in_item) /* new directory entry falls into R[0] */ { int paste_entry_position; - RFALSE(tb->rbytes - 1 >= - entry_count - || !tb-> - insert_size[0], + RFALSE(tb->rbytes - 1 >= entry_count || !tb-> insert_size[0], "PAP-12150: no enough of entries to shift to R[0]: rbytes=%d, entry_count=%d", - tb->rbytes, - entry_count); + tb->rbytes, entry_count); /* Shift rnum[0]-1 items in whole. Shift rbytes-1 directory entries from directory item number rnum[0] */ - leaf_shift_right(tb, - tb-> - rnum - [0], - tb-> - rbytes - - 1); + leaf_shift_right(tb, tb->rnum[0], tb->rbytes - 1); /* Paste given directory entry to directory item */ - paste_entry_position = - pos_in_item - - entry_count + - tb->rbytes - 1; + paste_entry_position = pos_in_item - entry_count + tb->rbytes - 1; buffer_info_init_right(tb, &bi); - leaf_paste_in_buffer - (&bi, 0, - paste_entry_position, - tb->insert_size[0], - body, zeros_num); + leaf_paste_in_buffer(&bi, 0, paste_entry_position, tb->insert_size[0], body, zeros_num); /* paste entry */ - leaf_paste_entries(&bi, - 0, - paste_entry_position, - 1, - (struct - reiserfs_de_head - *) - body, - body - + - DEH_SIZE, - tb-> - insert_size - [0] - ); - - if (paste_entry_position - == 0) { + leaf_paste_entries(&bi, 0, paste_entry_position, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); + + if (paste_entry_position == 0) { /* change delimiting keys */ - replace_key(tb, - tb-> - CFR - [0], - tb-> - rkey - [0], - tb-> - R - [0], - 0); + replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0],0); } tb->insert_size[0] = 0; pos_in_item++; } else { /* new directory entry doesn't fall into R[0] */ - leaf_shift_right(tb, - tb-> - rnum - [0], - tb-> - rbytes); + leaf_shift_right(tb, tb->rnum[0], tb->rbytes); } } else { /* regular object */ - int n_shift, n_rem, - r_zeros_number; + int n_shift, n_rem, r_zeros_number; const char *r_body; /* Calculate number of bytes which must be shifted from appended item */ - if ((n_shift = - tb->rbytes - - tb->insert_size[0]) < 0) + if ((n_shift = tb->rbytes - tb->insert_size[0]) < 0) n_shift = 0; - RFALSE(pos_in_item != - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)), + RFALSE(pos_in_item != ih_item_len + (B_N_PITEM_HEAD(tbS0, item_pos)), "PAP-12155: invalid position to paste. ih_item_len=%d, pos_in_item=%d", - pos_in_item, - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos))); - - leaf_shift_right(tb, - tb->rnum[0], - n_shift); + pos_in_item, ih_item_len + (B_N_PITEM_HEAD(tbS0, item_pos))); + + leaf_shift_right(tb, tb->rnum[0], n_shift); /* Calculate number of bytes which must remain in body after appending to R[0] */ - if ((n_rem = - tb->insert_size[0] - - tb->rbytes) < 0) + if ((n_rem = tb->insert_size[0] - tb->rbytes) < 0) n_rem = 0; { int version; - unsigned long temp_rem = - n_rem; - - version = - ih_version - (B_N_PITEM_HEAD - (tb->R[0], 0)); - if (is_indirect_le_key - (version, - B_N_PKEY(tb->R[0], - 0))) { - temp_rem = - n_rem << - (tb->tb_sb-> - s_blocksize_bits - - - UNFM_P_SHIFT); + unsigned long temp_rem = n_rem; + + version = ih_version(B_N_PITEM_HEAD(tb->R[0], 0)); + if (is_indirect_le_key(version, B_N_PKEY(tb->R[0], 0))) { + temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT); } - set_le_key_k_offset - (version, - B_N_PKEY(tb->R[0], - 0), - le_key_k_offset - (version, - B_N_PKEY(tb->R[0], - 0)) + - temp_rem); - set_le_key_k_offset - (version, - B_N_PDELIM_KEY(tb-> - CFR - [0], - tb-> - rkey - [0]), - le_key_k_offset - (version, - B_N_PDELIM_KEY - (tb->CFR[0], - tb->rkey[0])) + - temp_rem); + set_le_key_k_offset(version, B_N_PKEY(tb->R[0], 0), + le_key_k_offset(version, B_N_PKEY(tb->R[0], 0)) + temp_rem); + set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]), + le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0])) + temp_rem); } /* k_offset (B_N_PKEY(tb->R[0],0)) += n_rem; k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/ - do_balance_mark_internal_dirty - (tb, tb->CFR[0], 0); + do_balance_mark_internal_dirty(tb, tb->CFR[0], 0); /* Append part of body into R[0] */ buffer_info_init_right(tb, &bi); if (n_rem > zeros_num) { r_zeros_number = 0; - r_body = - body + n_rem - - zeros_num; + r_body = body + n_rem - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - n_rem; - zeros_num -= - r_zeros_number; + r_zeros_number = zeros_num - n_rem; + zeros_num -= r_zeros_number; } - leaf_paste_in_buffer(&bi, 0, - n_shift, - tb-> - insert_size - [0] - - n_rem, - r_body, - r_zeros_number); - - if (is_indirect_le_ih - (B_N_PITEM_HEAD - (tb->R[0], 0))) { + leaf_paste_in_buffer(&bi, 0, n_shift, + tb->insert_size[0] - n_rem, + r_body, r_zeros_number); + + if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->R[0], 0))) { #if 0 RFALSE(n_rem, "PAP-12160: paste more than one unformatted node pointer"); #endif - set_ih_free_space - (B_N_PITEM_HEAD - (tb->R[0], 0), 0); + set_ih_free_space(B_N_PITEM_HEAD(tb->R[0], 0), 0); } tb->insert_size[0] = n_rem; if (!n_rem) @@ -1044,58 +722,28 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h struct item_head *pasted; - ret_val = - leaf_shift_right(tb, tb->rnum[0], - tb->rbytes); + ret_val = leaf_shift_right(tb, tb->rnum[0], tb->rbytes); /* append item in R[0] */ if (pos_in_item >= 0) { buffer_info_init_right(tb, &bi); - leaf_paste_in_buffer(&bi, - item_pos - - n + - tb-> - rnum[0], - pos_in_item, - tb-> - insert_size - [0], body, - zeros_num); + leaf_paste_in_buffer(&bi, item_pos - n + tb->rnum[0], pos_in_item, + tb->insert_size[0], body, zeros_num); } /* paste new entry, if item is directory item */ - pasted = - B_N_PITEM_HEAD(tb->R[0], - item_pos - n + - tb->rnum[0]); - if (is_direntry_le_ih(pasted) - && pos_in_item >= 0) { - leaf_paste_entries(&bi, - item_pos - - n + - tb->rnum[0], - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] - ); + pasted = B_N_PITEM_HEAD(tb->R[0], item_pos - n + tb->rnum[0]); + if (is_direntry_le_ih(pasted) && pos_in_item >= 0) { + leaf_paste_entries(&bi, item_pos - n + tb->rnum[0], + pos_in_item, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); if (!pos_in_item) { - RFALSE(item_pos - n + - tb->rnum[0], + RFALSE(item_pos - n + tb->rnum[0], "PAP-12165: directory item must be first item of node when pasting is in 0th position"); /* update delimiting keys */ - replace_key(tb, - tb->CFR[0], - tb->rkey[0], - tb->R[0], - 0); + replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0); } } @@ -1111,22 +759,16 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h default: /* cases d and t */ reiserfs_panic(tb->tb_sb, "PAP-12175", "rnum > 0: unexpected mode: %s(%d)", - (flag == - M_DELETE) ? "DELETE" : ((flag == - M_CUT) ? "CUT" - : "UNKNOWN"), - flag); + (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag); } } /* tb->rnum[0] > 0 */ RFALSE(tb->blknum[0] > 3, - "PAP-12180: blknum can not be %d. It must be <= 3", - tb->blknum[0]); + "PAP-12180: blknum can not be %d. It must be <= 3", tb->blknum[0]); RFALSE(tb->blknum[0] < 0, - "PAP-12185: blknum can not be %d. It must be >= 0", - tb->blknum[0]); + "PAP-12185: blknum can not be %d. It must be >= 0", tb->blknum[0]); /* if while adding to a node we discover that it is possible to split it in two, and merge the left part into the left neighbor and the @@ -1177,8 +819,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h if (n - snum[i] < item_pos) { /* new item or it's part falls to first new node S_new[i] */ if (item_pos == n - snum[i] + 1 && sbytes[i] != -1) { /* part of new item falls into S_new[i] */ - int old_key_comp, old_len, - r_zeros_number; + int old_key_comp, old_len, r_zeros_number; const char *r_body; int version; @@ -1192,15 +833,8 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h old_len = ih_item_len(ih); /* Calculate key component and item length to insert into S_new[i] */ - set_le_ih_k_offset(ih, - le_ih_k_offset(ih) + - ((old_len - - sbytes[i]) << - (is_indirect_le_ih - (ih) ? tb->tb_sb-> - s_blocksize_bits - - UNFM_P_SHIFT : - 0))); + set_le_ih_k_offset(ih, le_ih_k_offset(ih) + + ((old_len - sbytes[i]) << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0))); put_ih_item_len(ih, sbytes[i]); @@ -1209,39 +843,29 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h if ((old_len - sbytes[i]) > zeros_num) { r_zeros_number = 0; - r_body = - body + (old_len - - sbytes[i]) - - zeros_num; + r_body = body + (old_len - sbytes[i]) - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - (old_len - - sbytes[i]); + r_zeros_number = zeros_num - (old_len - sbytes[i]); zeros_num -= r_zeros_number; } - leaf_insert_into_buf(&bi, 0, ih, r_body, - r_zeros_number); + leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeros_number); /* Calculate key component and item length to insert into S[i] */ set_le_ih_k_offset(ih, old_key_comp); - put_ih_item_len(ih, - old_len - sbytes[i]); + put_ih_item_len(ih, old_len - sbytes[i]); tb->insert_size[0] -= sbytes[i]; } else { /* whole new item falls into S_new[i] */ /* Shift snum[0] - 1 items to S_new[i] (sbytes[i] of split item) */ leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, - snum[i] - 1, sbytes[i], - S_new[i]); + snum[i] - 1, sbytes[i], S_new[i]); /* Insert new item into S_new[i] */ buffer_info_init_bh(tb, &bi, S_new[i]); - leaf_insert_into_buf(&bi, - item_pos - n + - snum[i] - 1, ih, - body, zeros_num); + leaf_insert_into_buf(&bi, item_pos - n + snum[i] - 1, + ih, body, zeros_num); zeros_num = tb->insert_size[0] = 0; } @@ -1268,150 +892,73 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h int entry_count; - entry_count = - ih_entry_count(aux_ih); + entry_count = ih_entry_count(aux_ih); - if (entry_count - sbytes[i] < - pos_in_item - && pos_in_item <= - entry_count) { + if (entry_count - sbytes[i] < pos_in_item && pos_in_item <= entry_count) { /* new directory entry falls into S_new[i] */ - RFALSE(!tb-> - insert_size[0], - "PAP-12215: insert_size is already 0"); - RFALSE(sbytes[i] - 1 >= - entry_count, + RFALSE(!tb->insert_size[0], "PAP-12215: insert_size is already 0"); + RFALSE(sbytes[i] - 1 >= entry_count, "PAP-12220: there are no so much entries (%d), only %d", - sbytes[i] - 1, - entry_count); + sbytes[i] - 1, entry_count); /* Shift snum[i]-1 items in whole. Shift sbytes[i] directory entries from directory item number snum[i] */ - leaf_move_items - (LEAF_FROM_S_TO_SNEW, - tb, snum[i], - sbytes[i] - 1, - S_new[i]); + leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i] - 1, S_new[i]); /* Paste given directory entry to directory item */ buffer_info_init_bh(tb, &bi, S_new[i]); - leaf_paste_in_buffer - (&bi, 0, - pos_in_item - - entry_count + - sbytes[i] - 1, - tb->insert_size[0], - body, zeros_num); + leaf_paste_in_buffer(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, + tb->insert_size[0], body, zeros_num); /* paste new directory entry */ - leaf_paste_entries(&bi, - 0, - pos_in_item - - - entry_count - + - sbytes - [i] - - 1, 1, - (struct - reiserfs_de_head - *) - body, - body - + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); tb->insert_size[0] = 0; pos_in_item++; } else { /* new directory entry doesn't fall into S_new[i] */ - leaf_move_items - (LEAF_FROM_S_TO_SNEW, - tb, snum[i], - sbytes[i], - S_new[i]); + leaf_move_items(LEAF_FROM_S_TO_SNEW,tb, snum[i], sbytes[i], S_new[i]); } } else { /* regular object */ - int n_shift, n_rem, - r_zeros_number; + int n_shift, n_rem, r_zeros_number; const char *r_body; - RFALSE(pos_in_item != - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)) - || tb->insert_size[0] <= - 0, + RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)) || tb->insert_size[0] <= 0, "PAP-12225: item too short or insert_size <= 0"); /* Calculate number of bytes which must be shifted from appended item */ - n_shift = - sbytes[i] - - tb->insert_size[0]; + n_shift = sbytes[i] - tb->insert_size[0]; if (n_shift < 0) n_shift = 0; - leaf_move_items - (LEAF_FROM_S_TO_SNEW, tb, - snum[i], n_shift, - S_new[i]); + leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], n_shift, S_new[i]); /* Calculate number of bytes which must remain in body after append to S_new[i] */ - n_rem = - tb->insert_size[0] - - sbytes[i]; + n_rem = tb->insert_size[0] - sbytes[i]; if (n_rem < 0) n_rem = 0; /* Append part of body into S_new[0] */ buffer_info_init_bh(tb, &bi, S_new[i]); if (n_rem > zeros_num) { r_zeros_number = 0; - r_body = - body + n_rem - - zeros_num; + r_body = body + n_rem - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - n_rem; - zeros_num -= - r_zeros_number; + r_zeros_number = zeros_num - n_rem; + zeros_num -= r_zeros_number; } - leaf_paste_in_buffer(&bi, 0, - n_shift, - tb-> - insert_size - [0] - - n_rem, - r_body, - r_zeros_number); + leaf_paste_in_buffer(&bi, 0, n_shift, + tb->insert_size[0] - n_rem, + r_body, r_zeros_number); { struct item_head *tmp; - tmp = - B_N_PITEM_HEAD(S_new - [i], - 0); + tmp = B_N_PITEM_HEAD(S_new[i], 0); if (is_indirect_le_ih (tmp)) { - set_ih_free_space - (tmp, 0); - set_le_ih_k_offset - (tmp, - le_ih_k_offset - (tmp) + - (n_rem << - (tb-> - tb_sb-> - s_blocksize_bits - - - UNFM_P_SHIFT))); + set_ih_free_space(tmp, 0); + set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + (n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT))); } else { - set_le_ih_k_offset - (tmp, - le_ih_k_offset - (tmp) + - n_rem); + set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + n_rem); } } @@ -1426,8 +973,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h struct item_head *pasted; #ifdef CONFIG_REISERFS_CHECK - struct item_head *ih_check = - B_N_PITEM_HEAD(tbS0, item_pos); + struct item_head *ih_check = B_N_PITEM_HEAD(tbS0, item_pos); if (!is_direntry_le_ih(ih_check) && (pos_in_item != ih_item_len(ih_check) @@ -1439,8 +985,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h "to ih_item_len"); #endif /* CONFIG_REISERFS_CHECK */ - leaf_mi = - leaf_move_items(LEAF_FROM_S_TO_SNEW, + leaf_mi = leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i], S_new[i]); @@ -1452,30 +997,19 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* paste into item */ buffer_info_init_bh(tb, &bi, S_new[i]); leaf_paste_in_buffer(&bi, - item_pos - n + - snum[i], + item_pos - n + snum[i], pos_in_item, tb->insert_size[0], body, zeros_num); - pasted = - B_N_PITEM_HEAD(S_new[i], - item_pos - n + - snum[i]); + pasted = B_N_PITEM_HEAD(S_new[i], item_pos - n + snum[i]); if (is_direntry_le_ih(pasted)) { leaf_paste_entries(&bi, - item_pos - - n + snum[i], - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] + item_pos - n + snum[i], + pos_in_item, 1, + (struct reiserfs_de_head *)body, + body + DEH_SIZE, + tb->insert_size[0] ); } @@ -1495,11 +1029,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h default: /* cases d and t */ reiserfs_panic(tb->tb_sb, "PAP-12245", "blknum > 2: unexpected mode: %s(%d)", - (flag == - M_DELETE) ? "DELETE" : ((flag == - M_CUT) ? "CUT" - : "UNKNOWN"), - flag); + (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag); } memcpy(insert_key + i, B_N_PKEY(S_new[i], 0), KEY_SIZE); @@ -1524,9 +1054,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* If we insert the first key change the delimiting key */ if (item_pos == 0) { if (tb->CFL[0]) /* can be 0 in reiserfsck */ - replace_key(tb, tb->CFL[0], tb->lkey[0], - tbS0, 0); - + replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0); } break; @@ -1536,53 +1064,27 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h pasted = B_N_PITEM_HEAD(tbS0, item_pos); /* when directory, may be new entry already pasted */ if (is_direntry_le_ih(pasted)) { - if (pos_in_item >= 0 && - pos_in_item <= - ih_entry_count(pasted)) { + if (pos_in_item >= 0 && pos_in_item <= ih_entry_count(pasted)) { RFALSE(!tb->insert_size[0], "PAP-12260: insert_size is 0 already"); /* prepare space */ buffer_info_init_tbS0(tb, &bi); - leaf_paste_in_buffer(&bi, - item_pos, - pos_in_item, - tb-> - insert_size - [0], body, + leaf_paste_in_buffer(&bi, item_pos, pos_in_item, + tb->insert_size[0], body, zeros_num); /* paste entry */ - leaf_paste_entries(&bi, - item_pos, - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, item_pos, pos_in_item, 1, + (struct reiserfs_de_head *)body, + body + DEH_SIZE, + tb->insert_size[0]); if (!item_pos && !pos_in_item) { - RFALSE(!tb->CFL[0] - || !tb->L[0], + RFALSE(!tb->CFL[0] || !tb->L[0], "PAP-12270: CFL[0]/L[0] must be specified"); - if (tb->CFL[0]) { - replace_key(tb, - tb-> - CFL - [0], - tb-> - lkey - [0], - tbS0, - 0); - - } + if (tb->CFL[0]) + replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0); } tb->insert_size[0] = 0; } @@ -1593,13 +1095,8 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h "PAP-12275: insert size must not be %d", tb->insert_size[0]); buffer_info_init_tbS0(tb, &bi); - leaf_paste_in_buffer(&bi, - item_pos, - pos_in_item, - tb-> - insert_size - [0], body, - zeros_num); + leaf_paste_in_buffer(&bi, item_pos, pos_in_item, + tb->insert_size[0], body, zeros_num); if (is_indirect_le_ih(pasted)) { #if 0 @@ -1611,8 +1108,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h tb-> insert_size[0]); #endif - set_ih_free_space - (pasted, 0); + set_ih_free_space(pasted, 0); } tb->insert_size[0] = 0; } @@ -1620,8 +1116,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h else { if (tb->insert_size[0]) { print_cur_tb("12285"); - reiserfs_panic(tb-> - tb_sb, + reiserfs_panic(tb->tb_sb, "PAP-12285", "insert_size " "must be 0 " diff --git a/fs/sync.c b/fs/sync.c index f15537452231..b28d1dd10e8b 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -27,11 +27,10 @@ * wait == 1 case since in that case write_inode() functions do * sync_dirty_buffer() and thus effectively write one block at a time. */ -static int __sync_filesystem(struct super_block *sb, int wait, - unsigned long start) +static int __sync_filesystem(struct super_block *sb, int wait) { if (wait) - sync_inodes_sb(sb, start); + sync_inodes_sb(sb); else writeback_inodes_sb(sb, WB_REASON_SYNC); @@ -48,7 +47,6 @@ static int __sync_filesystem(struct super_block *sb, int wait, int sync_filesystem(struct super_block *sb) { int ret; - unsigned long start = jiffies; /* * We need to be protected against the filesystem going from @@ -62,17 +60,17 @@ int sync_filesystem(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return 0; - ret = __sync_filesystem(sb, 0, start); + ret = __sync_filesystem(sb, 0); if (ret < 0) return ret; - return __sync_filesystem(sb, 1, start); + return __sync_filesystem(sb, 1); } EXPORT_SYMBOL_GPL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!(sb->s_flags & MS_RDONLY)) - sync_inodes_sb(sb, *((unsigned long *)arg)); + sync_inodes_sb(sb); } static void sync_fs_one_sb(struct super_block *sb, void *arg) @@ -104,10 +102,9 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg) SYSCALL_DEFINE0(sync) { int nowait = 0, wait = 1; - unsigned long start = jiffies; wakeup_flusher_threads(0, WB_REASON_SYNC); - iterate_supers(sync_inodes_one_sb, &start); + iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); iterate_bdevs(fdatawrite_one_bdev, NULL); @@ -222,23 +219,6 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd) return do_fsync(fd, 1); } -/** - * generic_write_sync - perform syncing after a write if file / inode is sync - * @file: file to which the write happened - * @pos: offset where the write started - * @count: length of the write - * - * This is just a simple wrapper about our general syncing function. - */ -int generic_write_sync(struct file *file, loff_t pos, loff_t count) -{ - if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host)) - return 0; - return vfs_fsync_range(file, pos, pos + count - 1, - (file->f_flags & __O_SYNC) ? 0 : 1); -} -EXPORT_SYMBOL(generic_write_sync); - /* * sys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is diff --git a/fs/sysfs/Kconfig b/fs/sysfs/Kconfig index 8c41feacbac5..b2756014508c 100644 --- a/fs/sysfs/Kconfig +++ b/fs/sysfs/Kconfig @@ -1,6 +1,7 @@ config SYSFS bool "sysfs file system support" if EXPERT default y + select KERNFS help The sysfs filesystem is a virtual filesystem that the kernel uses to export internal kernel objects, their attributes, and their diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index ee0d761c3179..0b45ff42f374 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -19,39 +19,18 @@ DEFINE_SPINLOCK(sysfs_symlink_target_lock); -/** - * sysfs_pathname - return full path to sysfs dirent - * @kn: kernfs_node whose path we want - * @path: caller allocated buffer of size PATH_MAX - * - * Gives the name "/" to the sysfs_root entry; any path returned - * is relative to wherever sysfs is mounted. - */ -static char *sysfs_pathname(struct kernfs_node *kn, char *path) -{ - if (kn->parent) { - sysfs_pathname(kn->parent, path); - strlcat(path, "/", PATH_MAX); - } - strlcat(path, kn->name, PATH_MAX); - return path; -} - void sysfs_warn_dup(struct kernfs_node *parent, const char *name) { - char *path; + char *buf, *path = NULL; - path = kzalloc(PATH_MAX, GFP_KERNEL); - if (path) { - sysfs_pathname(parent, path); - strlcat(path, "/", PATH_MAX); - strlcat(path, name, PATH_MAX); - } + buf = kzalloc(PATH_MAX, GFP_KERNEL); + if (buf) + path = kernfs_path(parent, buf, PATH_MAX); - WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s'\n", - path ? path : name); + WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s/%s'\n", + path, name); - kfree(path); + kfree(buf); } /** @@ -122,9 +101,13 @@ void sysfs_remove_dir(struct kobject *kobj) int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, const void *new_ns) { - struct kernfs_node *parent = kobj->sd->parent; + struct kernfs_node *parent; + int ret; - return kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); + parent = kernfs_get_parent(kobj->sd); + ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); + kernfs_put(parent); + return ret; } int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, @@ -133,7 +116,6 @@ int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, struct kernfs_node *kn = kobj->sd; struct kernfs_node *new_parent; - BUG_ON(!kn->parent); new_parent = new_parent_kobj && new_parent_kobj->sd ? new_parent_kobj->sd : sysfs_root_kn; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 810cf6e613e5..1b8b91b67fdb 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -372,6 +372,29 @@ void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, } EXPORT_SYMBOL_GPL(sysfs_remove_file_ns); +/** + * sysfs_remove_file_self - remove an object attribute from its own method + * @kobj: object we're acting for + * @attr: attribute descriptor + * + * See kernfs_remove_self() for details. + */ +bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) +{ + struct kernfs_node *parent = kobj->sd; + struct kernfs_node *kn; + bool ret; + + kn = kernfs_find_and_get(parent, attr->name); + if (WARN_ON_ONCE(!kn)) + return false; + + ret = kernfs_remove_self(kn); + + kernfs_put(kn); + return ret; +} + void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr) { int i; diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 6b579387c67a..aa0406895b53 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -70,8 +70,11 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj, if (grp->bin_attrs) { for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { if (update) - sysfs_remove_bin_file(kobj, *bin_attr); - error = sysfs_create_bin_file(kobj, *bin_attr); + kernfs_remove_by_name(parent, + (*bin_attr)->attr.name); + error = sysfs_add_file_mode_ns(parent, + &(*bin_attr)->attr, true, + (*bin_attr)->attr.mode, NULL); if (error) break; } diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 6211230814fd..a66ad6196f59 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -27,6 +27,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, { struct dentry *root; void *ns; + bool new_sb; if (!(flags & MS_KERNMOUNT)) { if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) @@ -37,8 +38,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, } ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); - root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns); - if (IS_ERR(root)) + root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns); + if (IS_ERR(root) || !new_sb) kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); return root; } @@ -62,7 +63,7 @@ int __init sysfs_init(void) { int err; - sysfs_root = kernfs_create_root(NULL, NULL); + sysfs_root = kernfs_create_root(NULL, 0, NULL); if (IS_ERR(sysfs_root)) return PTR_ERR(sysfs_root); diff --git a/fs/timerfd.c b/fs/timerfd.c index 929312180dd0..0013142c0475 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -317,6 +317,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) (clockid != CLOCK_MONOTONIC && clockid != CLOCK_REALTIME && clockid != CLOCK_REALTIME_ALARM && + clockid != CLOCK_BOOTTIME && clockid != CLOCK_BOOTTIME_ALARM)) return -EINVAL; diff --git a/fs/udf/file.c b/fs/udf/file.c index c02a27a19c6d..1037637957c7 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -144,6 +144,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, size_t count = iocb->ki_nbytes; struct udf_inode_info *iinfo = UDF_I(inode); + mutex_lock(&inode->i_mutex); down_write(&iinfo->i_data_sem); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { if (file->f_flags & O_APPEND) @@ -156,6 +157,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, pos + count)) { err = udf_expand_file_adinicb(inode); if (err) { + mutex_unlock(&inode->i_mutex); udf_debug("udf_expand_adinicb: err=%d\n", err); return err; } @@ -169,9 +171,17 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } else up_write(&iinfo->i_data_sem); - retval = generic_file_aio_write(iocb, iov, nr_segs, ppos); - if (retval > 0) + retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + mutex_unlock(&inode->i_mutex); + + if (retval > 0) { + ssize_t err; + mark_inode_dirty(inode); + err = generic_write_sync(file, iocb->ki_pos - retval, retval); + if (err < 0) + retval = err; + } return retval; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 062b7925bca0..982ce05c87ed 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -265,6 +265,7 @@ int udf_expand_file_adinicb(struct inode *inode) .nr_to_write = 1, }; + WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex)); if (!iinfo->i_lenAlloc) { if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 2e7989e3a2d6..64b48eade91d 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -799,7 +799,7 @@ xfs_file_aio_write( XFS_STATS_ADD(xs_write_bytes, ret); /* Handle various SYNC-type writes */ - err = generic_write_sync(file, pos, ret); + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f35d5c953ff9..9ddfb8190ca1 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -705,7 +705,6 @@ xfs_setattr_size( { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); - int mask = iattr->ia_valid; xfs_off_t oldsize, newsize; struct xfs_trans *tp; int error; @@ -726,8 +725,8 @@ xfs_setattr_size( ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); - ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| - ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| + ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; @@ -736,7 +735,7 @@ xfs_setattr_size( * Short circuit the truncate case for zero length files. */ if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) { - if (!(mask & (ATTR_CTIME|ATTR_MTIME))) + if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME))) return 0; /* @@ -824,10 +823,11 @@ xfs_setattr_size( * these flags set. For all other operations the VFS set these flags * explicitly if it wants a timestamp update. */ - if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) { + if (newsize != oldsize && + !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) { iattr->ia_ctime = iattr->ia_mtime = current_fs_time(inode->i_sb); - mask |= ATTR_CTIME | ATTR_MTIME; + iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME; } /* @@ -863,9 +863,9 @@ xfs_setattr_size( xfs_inode_clear_eofblocks_tag(ip); } - if (mask & ATTR_MODE) + if (iattr->ia_valid & ATTR_MODE) xfs_setattr_mode(ip, iattr); - if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) + if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) xfs_setattr_time(ip, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index cdebd832c3db..4ef6fdbced78 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -205,16 +205,25 @@ xlog_cil_insert_format_items( /* * We 64-bit align the length of each iovec so that the start * of the next one is naturally aligned. We'll need to - * account for that slack space here. + * account for that slack space here. Then round nbytes up + * to 64-bit alignment so that the initial buffer alignment is + * easy to calculate and verify. */ nbytes += niovecs * sizeof(uint64_t); + nbytes = round_up(nbytes, sizeof(uint64_t)); /* grab the old item if it exists for reservation accounting */ old_lv = lip->li_lv; - /* calc buffer size */ - buf_size = sizeof(struct xfs_log_vec) + nbytes + - niovecs * sizeof(struct xfs_log_iovec); + /* + * The data buffer needs to start 64-bit aligned, so round up + * that space to ensure we can align it appropriately and not + * overrun the buffer. + */ + buf_size = nbytes + + round_up((sizeof(struct xfs_log_vec) + + niovecs * sizeof(struct xfs_log_iovec)), + sizeof(uint64_t)); /* compare to existing item size */ if (lip->li_lv && buf_size <= lip->li_lv->lv_size) { @@ -251,6 +260,8 @@ xlog_cil_insert_format_items( /* The allocated data region lies beyond the iovec region */ lv->lv_buf_len = 0; lv->lv_buf = (char *)lv + buf_size - nbytes; + ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t))); + lip->li_ops->iop_format(lip, lv); insert: ASSERT(lv->lv_buf_len <= nbytes); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 02df7b408a26..f96c05669a9e 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -282,22 +282,29 @@ xfs_readsb( struct xfs_sb *sbp = &mp->m_sb; int error; int loud = !(flags & XFS_MFSI_QUIET); + const struct xfs_buf_ops *buf_ops; ASSERT(mp->m_sb_bp == NULL); ASSERT(mp->m_ddev_targp != NULL); /* + * For the initial read, we must guess at the sector + * size based on the block device. It's enough to + * get the sb_sectsize out of the superblock and + * then reread with the proper length. + * We don't verify it yet, because it may not be complete. + */ + sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); + buf_ops = NULL; + + /* * Allocate a (locked) buffer to hold the superblock. * This will be kept around at all times to optimize * access to the superblock. */ - sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); - reread: bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, - BTOBB(sector_size), 0, - loud ? &xfs_sb_buf_ops - : &xfs_sb_quiet_buf_ops); + BTOBB(sector_size), 0, buf_ops); if (!bp) { if (loud) xfs_warn(mp, "SB buffer read failed"); @@ -328,12 +335,13 @@ reread: } /* - * If device sector size is smaller than the superblock size, - * re-read the superblock so the buffer is correctly sized. + * Re-read the superblock so the buffer is correctly sized, + * and properly verified. */ - if (sector_size < sbp->sb_sectsize) { + if (buf_ops == NULL) { xfs_buf_relse(bp); sector_size = sbp->sb_sectsize; + buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops; goto reread; } diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index b7c9aea77f8f..1e116794bb66 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -295,8 +295,7 @@ xfs_mount_validate_sb( sbp->sb_dblocks == 0 || sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) || sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) { - XFS_CORRUPTION_ERROR("SB sanity check failed", - XFS_ERRLEVEL_LOW, mp, sbp); + xfs_notice(mp, "SB sanity check failed"); return XFS_ERROR(EFSCORRUPTED); } @@ -611,10 +610,10 @@ xfs_sb_read_verify( XFS_SB_VERSION_5) || dsb->sb_crc != 0)) { - if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize), + if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length), offsetof(struct xfs_sb, sb_crc))) { /* Only fail bad secondaries on a known V5 filesystem */ - if (bp->b_bn != XFS_SB_DADDR && + if (bp->b_bn == XFS_SB_DADDR || xfs_sb_version_hascrc(&mp->m_sb)) { error = EFSCORRUPTED; goto out_error; @@ -625,7 +624,7 @@ xfs_sb_read_verify( out_error: if (error) { - if (error != EWRONGFS) + if (error == EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); xfs_buf_ioerror(bp, error); @@ -644,7 +643,6 @@ xfs_sb_quiet_read_verify( { struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp); - if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) { /* XFS filesystem, verify noisily! */ xfs_sb_read_verify(bp); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f317488263dd..d971f4932b5d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -913,7 +913,7 @@ xfs_flush_inodes( struct super_block *sb = mp->m_super; if (down_read_trylock(&sb->s_umount)) { - sync_inodes_sb(sb, jiffies); + sync_inodes_sb(sb); up_read(&sb->s_umount); } } |