diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2018-04-06 14:34:03 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2018-04-06 14:34:03 +1000 |
commit | 7fe49def0616c1aec742b3ac1b4fdcab57f37f5f (patch) | |
tree | 7e2a074bf8212d50a3942d3e0406a15effce3535 /fs | |
parent | 9a7624add6adeff97a3168c54bea59170ae6d65f (diff) | |
parent | f3edcb47a8f6924f77bbb4f68ddbc47b0f8e74ef (diff) |
Merge branch 'akpm-current/current'
Diffstat (limited to 'fs')
61 files changed, 942 insertions, 801 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 8fb89ddc6cc7..e622f0f10502 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -292,6 +292,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); v9ses->cachetag = match_strdup(&args[0]); + if (!v9ses->cachetag) { + ret = -ENOMEM; + goto free_and_return; + } #endif break; case Opt_cache: @@ -471,6 +475,9 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, return fid; err_clnt: +#ifdef CONFIG_9P_FSCACHE + kfree(v9ses->cachetag); +#endif p9_client_destroy(v9ses->clnt); err_names: kfree(v9ses->uname); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index bdabb2765d1b..9ee534159cc6 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -579,6 +579,24 @@ static int v9fs_at_to_dotl_flags(int flags) } /** + * v9fs_dec_count - helper functon to drop i_nlink. + * + * If a directory had nlink <= 2 (including . and ..), then we should not drop + * the link count, which indicates the underlying exported fs doesn't maintain + * nlink accurately. e.g. + * - overlayfs sets nlink to 1 for merged dir + * - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more + * than EXT4_LINK_MAX (65000) links. + * + * @inode: inode whose nlink is being dropped + */ +static void v9fs_dec_count(struct inode *inode) +{ + if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) + drop_nlink(inode); +} + +/** * v9fs_remove - helper function to remove files and directories * @dir: directory inode that is being deleted * @dentry: dentry that is being deleted @@ -621,9 +639,9 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) */ if (flags & AT_REMOVEDIR) { clear_nlink(inode); - drop_nlink(dir); + v9fs_dec_count(dir); } else - drop_nlink(inode); + v9fs_dec_count(inode); v9fs_invalidate_inode_attr(inode); v9fs_invalidate_inode_attr(dir); @@ -1024,12 +1042,12 @@ clunk_newdir: if (S_ISDIR(new_inode->i_mode)) clear_nlink(new_inode); else - drop_nlink(new_inode); + v9fs_dec_count(new_inode); } if (S_ISDIR(old_inode->i_mode)) { if (!new_inode) inc_nlink(new_dir); - drop_nlink(old_dir); + v9fs_dec_count(old_dir); } v9fs_invalidate_inode_attr(old_inode); v9fs_invalidate_inode_attr(old_dir); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index af03c2a901eb..48ce50484e80 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -94,7 +94,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, if (v9ses->cache) sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE; - sb->s_flags |= SB_ACTIVE | SB_DIRSYNC | SB_NOATIME; + sb->s_flags |= SB_ACTIVE | SB_DIRSYNC; if (!v9ses->cache) sb->s_flags |= SB_SYNCHRONOUS; diff --git a/fs/Kconfig b/fs/Kconfig index bc821a86d965..8b344110b2cd 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -203,6 +203,9 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS +config MEMFD_CREATE + def_bool TMPFS || HUGETLBFS + config ARCH_HAS_GIGANTIC_PAGE bool diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index a0c57c37fa21..be9c3dc048ab 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -19,9 +19,6 @@ */ static autofs_wqt_t autofs4_next_wait_queue = 1; -/* These are the signals we allow interrupting a pending mount */ -#define SHUTDOWN_SIGS (sigmask(SIGKILL) | sigmask(SIGINT) | sigmask(SIGQUIT)) - void autofs4_catatonic_mode(struct autofs_sb_info *sbi) { struct autofs_wait_queue *wq, *nwq; @@ -486,29 +483,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, * wq->name.name is NULL iff the lock is already released * or the mount has been made catatonic. */ - if (wq->name.name) { - /* Block all but "shutdown" signals while waiting */ - unsigned long shutdown_sigs_mask; - unsigned long irqflags; - sigset_t oldset; - - spin_lock_irqsave(¤t->sighand->siglock, irqflags); - oldset = current->blocked; - shutdown_sigs_mask = SHUTDOWN_SIGS & ~oldset.sig[0]; - siginitsetinv(¤t->blocked, shutdown_sigs_mask); - recalc_sigpending(); - spin_unlock_irqrestore(¤t->sighand->siglock, irqflags); - - wait_event_interruptible(wq->queue, wq->name.name == NULL); - - spin_lock_irqsave(¤t->sighand->siglock, irqflags); - current->blocked = oldset; - recalc_sigpending(); - spin_unlock_irqrestore(¤t->sighand->siglock, irqflags); - } else { - pr_debug("skipped sleeping\n"); - } - + wait_event_killable(wq->queue, wq->name.name == NULL); status = wq->status; /* @@ -574,7 +549,7 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok kfree(wq->name.name); wq->name.name = NULL; /* Do not wait on this queue */ wq->status = status; - wake_up_interruptible(&wq->queue); + wake_up(&wq->queue); if (!--wq->wait_ctr) kfree(wq); mutex_unlock(&sbi->wq_mutex); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index ce1824f47ba6..c3deb2e35f20 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -330,6 +330,7 @@ beyond_if: #ifdef __alpha__ regs->gp = ex.a_gpvalue; #endif + finalize_exec(bprm); start_thread(regs, ex.a_entry, current->mm->start_stack); return 0; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index bdb201230bae..3edca6cb9a33 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1155,6 +1155,7 @@ static int load_elf_binary(struct linux_binprm *bprm) ELF_PLAT_INIT(regs, reloc_func_desc); #endif + finalize_exec(bprm); start_thread(regs, elf_entry, bprm->p); retval = 0; out: diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 429326b6e2e7..d90993adeffa 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -463,6 +463,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) dynaddr); #endif + finalize_exec(bprm); /* everything is now ready... get the userspace context ready to roll */ entryaddr = interp_params.entry_addr ?: exec_params.entry_addr; start_thread(regs, entryaddr, current->mm->start_stack); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 5d6b94475f27..82a48e830018 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -994,6 +994,7 @@ static int load_flat_binary(struct linux_binprm *bprm) FLAT_PLAT_INIT(regs); #endif + finalize_exec(bprm); pr_debug("start_thread(regs=0x%p, entry=0x%lx, start_stack=0x%lx)\n", regs, start_addr, current->mm->start_stack); start_thread(regs, start_addr, current->mm->start_stack); diff --git a/fs/block_dev.c b/fs/block_dev.c index 19406e489cb3..b54966679833 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1323,7 +1323,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty) * @bdev: struct bdev to adjust. * * This routine checks to see if the bdev size does not match the disk size - * and adjusts it if it differs. + * and adjusts it if it differs. When shrinking the bdev size, its all caches + * are freed. */ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev) { @@ -1336,7 +1337,8 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev) "%s: detected capacity change from %lld to %lld\n", disk->disk_name, bdev_size, disk_size); i_size_write(bdev->bd_inode, disk_size); - flush_disk(bdev, false); + if (bdev_size > disk_size) + flush_disk(bdev, false); } } EXPORT_SYMBOL(check_disk_size_change); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 8d40e7dd8c30..29c2274959bd 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -335,7 +335,8 @@ static int check_dir_item(struct btrfs_fs_info *fs_info, */ if (key->type == BTRFS_DIR_ITEM_KEY || key->type == BTRFS_XATTR_ITEM_KEY) { - char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)]; + char namebuf[const_max(BTRFS_NAME_LEN, + XATTR_NAME_MAX)]; read_extent_buffer(leaf, namebuf, (unsigned long)(di + 1), name_len); diff --git a/fs/buffer.c b/fs/buffer.c index 3b2b415f1fcd..17f13191a552 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1511,7 +1511,7 @@ void block_invalidatepage(struct page *page, unsigned int offset, * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ - if (offset == 0) + if (length == PAGE_SIZE) try_to_release_page(page, 0); out: return; diff --git a/fs/dcache.c b/fs/dcache.c index 593079176123..ad0c715f10b8 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -257,11 +257,25 @@ static void __d_free(struct rcu_head *head) kmem_cache_free(dentry_cache, dentry); } +static void __d_free_external_name(struct rcu_head *head) +{ + struct external_name *name = container_of(head, struct external_name, + u.head); + + mod_node_page_state(page_pgdat(virt_to_page(name)), + NR_INDIRECTLY_RECLAIMABLE_BYTES, + -ksize(name)); + + kfree(name); +} + static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - kfree(external_name(dentry)); - kmem_cache_free(dentry_cache, dentry); + + __d_free_external_name(&external_name(dentry)->u.head); + + kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) @@ -278,7 +292,8 @@ void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry spin_unlock(&dentry->d_lock); name->name = p->name; } else { - memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN); + memcpy(name->inline_name, dentry->d_iname, + dentry->d_name.len + 1); spin_unlock(&dentry->d_lock); name->name = name->inline_name; } @@ -291,7 +306,7 @@ void release_dentry_name_snapshot(struct name_snapshot *name) struct external_name *p; p = container_of(name->name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) - kfree_rcu(p, u.head); + call_rcu(&p->u.head, __d_free_external_name); } } EXPORT_SYMBOL(release_dentry_name_snapshot); @@ -1617,6 +1632,7 @@ EXPORT_SYMBOL(d_invalidate); struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { + struct external_name *ext = NULL; struct dentry *dentry; char *dname; int err; @@ -1637,14 +1653,14 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); - struct external_name *p = kmalloc(size + name->len, - GFP_KERNEL_ACCOUNT); - if (!p) { + + ext = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT); + if (!ext) { kmem_cache_free(dentry_cache, dentry); return NULL; } - atomic_set(&p->u.count, 1); - dname = p->name; + atomic_set(&ext->u.count, 1); + dname = ext->name; } else { dname = dentry->d_iname; } @@ -1683,6 +1699,12 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) } } + if (unlikely(ext)) { + pg_data_t *pgdat = page_pgdat(virt_to_page(ext)); + mod_node_page_state(pgdat, NR_INDIRECTLY_RECLAIMABLE_BYTES, + ksize(ext)); + } + this_cpu_inc(nr_dentry); return dentry; @@ -2770,7 +2792,7 @@ static void copy_name(struct dentry *dentry, struct dentry *target) dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) - kfree_rcu(old_name, u.head); + call_rcu(&old_name->u.head, __d_free_external_name); } /* diff --git a/fs/direct-io.c b/fs/direct-io.c index ba12ee659673..874607bb6e02 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1177,9 +1177,9 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, unsigned blkbits = i_blkbits; unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; - size_t count = iov_iter_count(iter); + const size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; - loff_t end = offset + count; + const loff_t end = offset + count; struct dio *dio; struct dio_submit sdio = { 0, }; struct buffer_head map_bh = { 0, }; @@ -1200,7 +1200,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, } /* watch out for a 0 len io from a tricksy fs */ - if (iov_iter_rw(iter) == READ && !iov_iter_count(iter)) + if (iov_iter_rw(iter) == READ && !count) return 0; dio = kmem_cache_alloc(dio_cache, GFP_KERNEL); @@ -1315,8 +1315,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, dio->should_dirty = (iter->type == ITER_IOVEC); sdio.iter = iter; - sdio.final_block_in_request = - (offset + iov_iter_count(iter)) >> blkbits; + sdio.final_block_in_request = end >> blkbits; /* * In case of non-aligned buffers, we may need 2 more diff --git a/fs/exec.c b/fs/exec.c index a919a827d181..32eea4c65909 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -257,7 +257,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, * to work from. */ limit = _STK_LIM / 4 * 3; - limit = min(limit, rlimit(RLIMIT_STACK) / 4); + limit = min(limit, bprm->rlim_stack.rlim_cur / 4); if (size > limit) goto fail; } @@ -411,6 +411,11 @@ static int bprm_mm_init(struct linux_binprm *bprm) if (!mm) goto err; + /* Save current stack limit for all calculations made during exec. */ + task_lock(current->group_leader); + bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; + task_unlock(current->group_leader); + err = __bprm_mm_init(bprm); if (err) goto err; @@ -697,7 +702,7 @@ int setup_arg_pages(struct linux_binprm *bprm, #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ - stack_base = rlimit_max(RLIMIT_STACK); + stack_base = bprm->rlim_stack.rlim_max; if (stack_base > STACK_SIZE_MAX) stack_base = STACK_SIZE_MAX; @@ -770,7 +775,7 @@ int setup_arg_pages(struct linux_binprm *bprm, * Align this down to a page boundary as expand_stack * will align it up. */ - rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK; + rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK; #ifdef CONFIG_STACK_GROWSUP if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_start + rlim_stack; @@ -1333,6 +1338,7 @@ void setup_new_exec(struct linux_binprm * bprm) if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ current->pdeath_signal = 0; + current->signal->pdeath_signal_proc = 0; /* * For secureexec, reset the stack limit to sane default to @@ -1341,11 +1347,11 @@ void setup_new_exec(struct linux_binprm * bprm) * RLIMIT_STACK, but after the point of no return to avoid * needing to clean up the change on failure. */ - if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM) - current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM; + if (bprm->rlim_stack.rlim_cur > _STK_LIM) + bprm->rlim_stack.rlim_cur = _STK_LIM; } - arch_pick_mmap_layout(current->mm); + arch_pick_mmap_layout(current->mm, &bprm->rlim_stack); current->sas_ss_sp = current->sas_ss_size = 0; @@ -1378,6 +1384,16 @@ void setup_new_exec(struct linux_binprm * bprm) } EXPORT_SYMBOL(setup_new_exec); +/* Runs immediately before start_thread() takes over. */ +void finalize_exec(struct linux_binprm *bprm) +{ + /* Store any stack rlimit changes before starting thread. */ + task_lock(current->group_leader); + current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack; + task_unlock(current->group_leader); +} +EXPORT_SYMBOL(finalize_exec); + /* * Prepare credentials and lock ->cred_guard_mutex. * install_exec_creds() commits the new creds and drops the lock. diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 3c6a9c156b7a..cfa862ea19d2 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -146,68 +146,82 @@ int _ore_get_io_state(struct ore_layout *layout, struct ore_io_state **pios) { struct ore_io_state *ios; - struct page **pages; - struct osd_sg_entry *sgilist; + size_t size_ios, size_extra, size_total; + void *ios_extra; + + /* + * The desired layout looks like this, with the extra_allocation + * items pointed at from fields within ios or per_dev: + struct __alloc_all_io_state { struct ore_io_state ios; struct ore_per_dev_state per_dev[numdevs]; union { struct osd_sg_entry sglist[sgs_per_dev * numdevs]; struct page *pages[num_par_pages]; - }; - } *_aios; - - if (likely(sizeof(*_aios) <= PAGE_SIZE)) { - _aios = kzalloc(sizeof(*_aios), GFP_KERNEL); - if (unlikely(!_aios)) { - ORE_DBGMSG("Failed kzalloc bytes=%zd\n", - sizeof(*_aios)); + } extra_allocation; + } whole_allocation; + + */ + + /* This should never happen, so abort early if it ever does. */ + if (sgs_per_dev && num_par_pages) { + ORE_DBGMSG("Tried to use both pages and sglist\n"); + *pios = NULL; + return -EINVAL; + } + + if (numdevs > (INT_MAX - sizeof(*ios)) / + sizeof(struct ore_per_dev_state)) + return -ENOMEM; + size_ios = sizeof(*ios) + sizeof(struct ore_per_dev_state) * numdevs; + + if (sgs_per_dev * numdevs > INT_MAX / sizeof(struct osd_sg_entry)) + return -ENOMEM; + if (num_par_pages > INT_MAX / sizeof(struct page *)) + return -ENOMEM; + size_extra = max(sizeof(struct osd_sg_entry) * (sgs_per_dev * numdevs), + sizeof(struct page *) * num_par_pages); + + size_total = size_ios + size_extra; + + if (likely(size_total <= PAGE_SIZE)) { + ios = kzalloc(size_total, GFP_KERNEL); + if (unlikely(!ios)) { + ORE_DBGMSG("Failed kzalloc bytes=%zd\n", size_total); *pios = NULL; return -ENOMEM; } - pages = num_par_pages ? _aios->pages : NULL; - sgilist = sgs_per_dev ? _aios->sglist : NULL; - ios = &_aios->ios; + ios_extra = (char *)ios + size_ios; } else { - struct __alloc_small_io_state { - struct ore_io_state ios; - struct ore_per_dev_state per_dev[numdevs]; - } *_aio_small; - union __extra_part { - struct osd_sg_entry sglist[sgs_per_dev * numdevs]; - struct page *pages[num_par_pages]; - } *extra_part; - - _aio_small = kzalloc(sizeof(*_aio_small), GFP_KERNEL); - if (unlikely(!_aio_small)) { + ios = kzalloc(size_ios, GFP_KERNEL); + if (unlikely(!ios)) { ORE_DBGMSG("Failed alloc first part bytes=%zd\n", - sizeof(*_aio_small)); + size_ios); *pios = NULL; return -ENOMEM; } - extra_part = kzalloc(sizeof(*extra_part), GFP_KERNEL); - if (unlikely(!extra_part)) { + ios_extra = kzalloc(size_extra, GFP_KERNEL); + if (unlikely(!ios_extra)) { ORE_DBGMSG("Failed alloc second part bytes=%zd\n", - sizeof(*extra_part)); - kfree(_aio_small); + size_extra); + kfree(ios); *pios = NULL; return -ENOMEM; } - pages = num_par_pages ? extra_part->pages : NULL; - sgilist = sgs_per_dev ? extra_part->sglist : NULL; /* In this case the per_dev[0].sgilist holds the pointer to * be freed */ - ios = &_aio_small->ios; ios->extra_part_alloc = true; } - if (pages) { - ios->parity_pages = pages; + if (num_par_pages) { + ios->parity_pages = ios_extra; ios->max_par_pages = num_par_pages; } - if (sgilist) { + if (sgs_per_dev) { + struct osd_sg_entry *sgilist = ios_extra; unsigned d; for (d = 0; d < numdevs; ++d) { diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c index 27cbdb697649..659129d5e9f7 100644 --- a/fs/exofs/ore_raid.c +++ b/fs/exofs/ore_raid.c @@ -71,6 +71,11 @@ static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width, { struct __stripe_pages_2d *sp2d; unsigned data_devs = group_width - parity; + + /* + * Desired allocation layout is, though when larger than PAGE_SIZE, + * each struct __alloc_1p_arrays is separately allocated: + struct _alloc_all_bytes { struct __alloc_stripe_pages_2d { struct __stripe_pages_2d sp2d; @@ -82,55 +87,85 @@ static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width, char page_is_read[data_devs]; } __a1pa[pages_in_unit]; } *_aab; + struct __alloc_1p_arrays *__a1pa; struct __alloc_1p_arrays *__a1pa_end; - const unsigned sizeof__a1pa = sizeof(_aab->__a1pa[0]); + + */ + + char *__a1pa; + char *__a1pa_end; + + const size_t sizeof_stripe_pages_2d = + sizeof(struct __stripe_pages_2d) + + sizeof(struct __1_page_stripe) * pages_in_unit; + const size_t sizeof__a1pa = + ALIGN(sizeof(struct page *) * (2 * group_width) + data_devs, + sizeof(void *)); + const size_t sizeof__a1pa_arrays = sizeof__a1pa * pages_in_unit; + const size_t alloc_total = sizeof_stripe_pages_2d + + sizeof__a1pa_arrays; + unsigned num_a1pa, alloc_size, i; /* FIXME: check these numbers in ore_verify_layout */ - BUG_ON(sizeof(_aab->__asp2d) > PAGE_SIZE); + BUG_ON(sizeof_stripe_pages_2d > PAGE_SIZE); BUG_ON(sizeof__a1pa > PAGE_SIZE); - if (sizeof(*_aab) > PAGE_SIZE) { - num_a1pa = (PAGE_SIZE - sizeof(_aab->__asp2d)) / sizeof__a1pa; - alloc_size = sizeof(_aab->__asp2d) + sizeof__a1pa * num_a1pa; + /* + * If alloc_total would be larger than PAGE_SIZE, only allocate + * as many a1pa items as would fill the rest of the page, instead + * of the full pages_in_unit count. + */ + if (alloc_total > PAGE_SIZE) { + num_a1pa = (PAGE_SIZE - sizeof_stripe_pages_2d) / sizeof__a1pa; + alloc_size = sizeof_stripe_pages_2d + sizeof__a1pa * num_a1pa; } else { num_a1pa = pages_in_unit; - alloc_size = sizeof(*_aab); + alloc_size = alloc_total; } - _aab = kzalloc(alloc_size, GFP_KERNEL); - if (unlikely(!_aab)) { + *psp2d = sp2d = kzalloc(alloc_size, GFP_KERNEL); + if (unlikely(!sp2d)) { ORE_DBGMSG("!! Failed to alloc sp2d size=%d\n", alloc_size); return -ENOMEM; } + /* From here Just call _sp2d_free */ - sp2d = &_aab->__asp2d.sp2d; - *psp2d = sp2d; /* From here Just call _sp2d_free */ - - __a1pa = _aab->__a1pa; - __a1pa_end = __a1pa + num_a1pa; + /* Find start of a1pa area. */ + __a1pa = (char *)sp2d + sizeof_stripe_pages_2d; + /* Find end of the _allocated_ a1pa area. */ + __a1pa_end = __a1pa + alloc_size; + /* Allocate additionally needed a1pa items in PAGE_SIZE chunks. */ for (i = 0; i < pages_in_unit; ++i) { if (unlikely(__a1pa >= __a1pa_end)) { num_a1pa = min_t(unsigned, PAGE_SIZE / sizeof__a1pa, pages_in_unit - i); + alloc_size = sizeof__a1pa * num_a1pa; - __a1pa = kcalloc(num_a1pa, sizeof__a1pa, GFP_KERNEL); + __a1pa = kzalloc(alloc_size, GFP_KERNEL); if (unlikely(!__a1pa)) { ORE_DBGMSG("!! Failed to _alloc_1p_arrays=%d\n", num_a1pa); return -ENOMEM; } - __a1pa_end = __a1pa + num_a1pa; + __a1pa_end = __a1pa + alloc_size; /* First *pages is marked for kfree of the buffer */ sp2d->_1p_stripes[i].alloc = true; } - sp2d->_1p_stripes[i].pages = __a1pa->pages; - sp2d->_1p_stripes[i].scribble = __a1pa->scribble ; - sp2d->_1p_stripes[i].page_is_read = __a1pa->page_is_read; - ++__a1pa; + /* + * Attach all _lp_stripes pointers to the allocation for + * it which was either part of the original PAGE_SIZE + * allocation or the subsequent allocation in this loop. + */ + sp2d->_1p_stripes[i].pages = (void *)__a1pa; + sp2d->_1p_stripes[i].scribble = + sp2d->_1p_stripes[i].pages + group_width; + sp2d->_1p_stripes[i].page_is_read = + (char *)(sp2d->_1p_stripes[i].scribble + group_width); + __a1pa += sizeof__a1pa; } sp2d->parity = parity; diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 179cd5c2f52a..f3c29e9326f1 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -549,27 +549,26 @@ static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev, static int __alloc_dev_table(struct exofs_sb_info *sbi, unsigned numdevs, struct exofs_dev **peds) { - struct __alloc_ore_devs_and_exofs_devs { - /* Twice bigger table: See exofs_init_comps() and comment at - * exofs_read_lookup_dev_table() - */ - struct ore_dev *oreds[numdevs * 2 - 1]; - struct exofs_dev eds[numdevs]; - } *aoded; + /* Twice bigger table: See exofs_init_comps() and comment at + * exofs_read_lookup_dev_table() + */ + size_t numores = numdevs * 2 - 1; struct exofs_dev *eds; unsigned i; - aoded = kzalloc(sizeof(*aoded), GFP_KERNEL); - if (unlikely(!aoded)) { + sbi->oc.ods = kzalloc(numores * sizeof(struct ore_dev *) + + numdevs * sizeof(struct exofs_dev), GFP_KERNEL); + if (unlikely(!sbi->oc.ods)) { EXOFS_ERR("ERROR: failed allocating Device array[%d]\n", numdevs); return -ENOMEM; } - sbi->oc.ods = aoded->oreds; - *peds = eds = aoded->eds; + /* Start of allocated struct exofs_dev entries */ + *peds = eds = (void *)sbi->oc.ods[numores]; + /* Initialize pointers into struct exofs_dev */ for (i = 0; i < numdevs; ++i) - aoded->oreds[i] = &eds[i].ored; + sbi->oc.ods[i] = &eds[i].ored; return 0; } diff --git a/fs/fcntl.c b/fs/fcntl.c index d737ff082472..f93deb1fa16a 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -23,7 +23,7 @@ #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> -#include <linux/shmem_fs.h> +#include <linux/memfd.h> #include <linux/compat.h> #include <linux/poll.h> diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b9a254dcc0e7..d508c7844681 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -138,10 +138,14 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) /* * page based offset in vm_pgoff could be sufficiently large to - * overflow a (l)off_t when converted to byte offset. + * overflow a loff_t when converted to byte offset. This can + * only happen on architectures where sizeof(loff_t) == + * sizeof(unsigned long). So, only check in those instances. */ - if (vma->vm_pgoff & PGOFF_LOFFT_MAX) - return -EINVAL; + if (sizeof(unsigned long) == sizeof(loff_t)) { + if (vma->vm_pgoff & PGOFF_LOFFT_MAX) + return -EINVAL; + } /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 9a876bb07cac..0f157bbd3e0f 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7119,7 +7119,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, goto out_commit; did_quota = 1; - data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv; + data_ac->ac_resv = &oi->ip_la_data_resv; ret = ocfs2_claim_clusters(handle, data_ac, 1, &bit_off, &num); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index e8e205bf2e41..302cd7caa4a7 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -346,7 +346,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) unlock = 0; out_alloc: - up_read(&OCFS2_I(inode)->ip_alloc_sem); + up_read(&oi->ip_alloc_sem); out_inode_unlock: ocfs2_inode_unlock(inode, 0); out: @@ -2213,7 +2213,7 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, down_write(&oi->ip_alloc_sem); if (first_get_block) { - if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) + if (ocfs2_sparse_alloc(osb)) ret = ocfs2_zero_tail(inode, di_bh, pos); else ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 8614ff069d99..3494a62ed749 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -78,7 +78,7 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level) /* * Using a named enum representing lock types in terms of #N bit stored in * iocb->private, which is going to be used for communication between - * ocfs2_dio_end_io() and ocfs2_file_aio_write/read(). + * ocfs2_dio_end_io() and ocfs2_file_write/read_iter(). */ enum ocfs2_iocb_lock_bits { OCFS2_IOCB_RW_LOCK = 0, diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index ea8c551bcd7e..91a8889abf9b 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -570,7 +570,16 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg, current_page, vec_len, vec_start); len = bio_add_page(bio, page, vec_len, vec_start); - if (len != vec_len) break; + if (len != vec_len) { + mlog(ML_ERROR, "Adding page[%d] to bio failed, " + "page %p, len %d, vec_len %u, vec_start %u, " + "bi_sector %llu\n", current_page, page, len, + vec_len, vec_start, + (unsigned long long)bio->bi_iter.bi_sector); + bio_put(bio); + bio = ERR_PTR(-EIO); + return bio; + } cs += vec_len / (PAGE_SIZE/spp); vec_start = 0; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 977763d4c27d..b048d4fa3959 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3072,7 +3072,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, * We need to return the correct block within the * cluster which should hold our entry. */ - off = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb), + off = ocfs2_dx_dir_hash_idx(osb, &lookup->dl_hinfo); get_bh(dx_leaves[off]); lookup->dl_dx_leaf_bh = dx_leaves[off]; diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index fd6bbbbd7d78..39831fc2fd52 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -224,14 +224,12 @@ void dlm_do_local_ast(struct dlm_ctxt *dlm, struct dlm_lock_resource *res, struct dlm_lock *lock) { dlm_astlockfunc_t *fn; - struct dlm_lockstatus *lksb; mlog(0, "%s: res %.*s, lock %u:%llu, Local AST\n", dlm->name, res->lockname.len, res->lockname.name, dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie))); - lksb = lock->lksb; fn = lock->ast; BUG_ON(lock->ml.node != dlm->node_num); diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index e9f3705c4c9f..d06e27ec4be4 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -140,6 +140,7 @@ struct dlm_ctxt u8 node_num; u32 key; u8 joining_node; + u8 migrate_done; /* set to 1 means node has migrated all lock resources */ wait_queue_head_t dlm_join_events; unsigned long live_nodes_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; unsigned long domain_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; @@ -960,13 +961,10 @@ static inline int dlm_send_proxy_ast(struct dlm_ctxt *dlm, void dlm_print_one_lock_resource(struct dlm_lock_resource *res); void __dlm_print_one_lock_resource(struct dlm_lock_resource *res); -u8 dlm_nm_this_node(struct dlm_ctxt *dlm); void dlm_kick_thread(struct dlm_ctxt *dlm, struct dlm_lock_resource *res); void __dlm_dirty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res); -int dlm_nm_init(struct dlm_ctxt *dlm); -int dlm_heartbeat_init(struct dlm_ctxt *dlm); void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data); void dlm_hb_node_up_cb(struct o2nm_node *node, int idx, void *data); diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index e1fea149f50b..425081be6161 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -461,6 +461,19 @@ redo_bucket: cond_resched_lock(&dlm->spinlock); num += n; } + + if (!num) { + if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { + mlog(0, "%s: perhaps there are more lock resources " + "need to be migrated after dlm recovery\n", dlm->name); + ret = -EAGAIN; + } else { + mlog(0, "%s: we won't do dlm recovery after migrating " + "all lock resources\n", dlm->name); + dlm->migrate_done = 1; + } + } + spin_unlock(&dlm->spinlock); wake_up(&dlm->dlm_thread_wq); @@ -675,20 +688,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm) spin_unlock(&dlm->spinlock); } -int dlm_shutting_down(struct dlm_ctxt *dlm) -{ - int ret = 0; - - spin_lock(&dlm_domain_lock); - - if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN) - ret = 1; - - spin_unlock(&dlm_domain_lock); - - return ret; -} - void dlm_unregister_domain(struct dlm_ctxt *dlm) { int leave = 0; @@ -2052,6 +2051,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN; init_waitqueue_head(&dlm->dlm_join_events); + dlm->migrate_done = 0; + dlm->reco.new_master = O2NM_INVALID_NODE_NUM; dlm->reco.dead_node = O2NM_INVALID_NODE_NUM; diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h index fd6122a38dbd..8a9281411c18 100644 --- a/fs/ocfs2/dlm/dlmdomain.h +++ b/fs/ocfs2/dlm/dlmdomain.h @@ -28,7 +28,30 @@ extern spinlock_t dlm_domain_lock; extern struct list_head dlm_domains; -int dlm_shutting_down(struct dlm_ctxt *dlm); +static inline int dlm_joined(struct dlm_ctxt *dlm) +{ + int ret = 0; + + spin_lock(&dlm_domain_lock); + if (dlm->dlm_state == DLM_CTXT_JOINED) + ret = 1; + spin_unlock(&dlm_domain_lock); + + return ret; +} + +static inline int dlm_shutting_down(struct dlm_ctxt *dlm) +{ + int ret = 0; + + spin_lock(&dlm_domain_lock); + if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN) + ret = 1; + spin_unlock(&dlm_domain_lock); + + return ret; +} + void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm, int node_num); diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 66c2a491f68d..74962315794e 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -77,8 +77,7 @@ int dlm_init_lock_cache(void) void dlm_destroy_lock_cache(void) { - if (dlm_lock_cache) - kmem_cache_destroy(dlm_lock_cache); + kmem_cache_destroy(dlm_lock_cache); } /* Tell us whether we can grant a new lock request. diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index a7df226f9449..aaca0949fe53 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -414,8 +414,7 @@ int dlm_init_mle_cache(void) void dlm_destroy_mle_cache(void) { - if (dlm_mle_cache) - kmem_cache_destroy(dlm_mle_cache); + kmem_cache_destroy(dlm_mle_cache); } static void dlm_mle_release(struct kref *kref) @@ -472,15 +471,11 @@ bail: void dlm_destroy_master_caches(void) { - if (dlm_lockname_cache) { - kmem_cache_destroy(dlm_lockname_cache); - dlm_lockname_cache = NULL; - } + kmem_cache_destroy(dlm_lockname_cache); + dlm_lockname_cache = NULL; - if (dlm_lockres_cache) { - kmem_cache_destroy(dlm_lockres_cache); - dlm_lockres_cache = NULL; - } + kmem_cache_destroy(dlm_lockres_cache); + dlm_lockres_cache = NULL; } static void dlm_lockres_release(struct kref *kref) @@ -2495,13 +2490,13 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data) } /* - * A migrateable resource is one that is : + * A migratable resource is one that is : * 1. locally mastered, and, * 2. zero local locks, and, * 3. one or more non-local locks, or, one or more references * Returns 1 if yes, 0 if not. */ -static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm, +static int dlm_is_lockres_migratable(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { enum dlm_lockres_list idx; @@ -2532,7 +2527,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm, continue; } cookie = be64_to_cpu(lock->ml.cookie); - mlog(0, "%s: Not migrateable res %.*s, lock %u:%llu on " + mlog(0, "%s: Not migratable res %.*s, lock %u:%llu on " "%s list\n", dlm->name, res->lockname.len, res->lockname.name, dlm_get_lock_cookie_node(cookie), @@ -2548,7 +2543,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm, return 0; } - mlog(0, "%s: res %.*s, Migrateable\n", dlm->name, res->lockname.len, + mlog(0, "%s: res %.*s, Migratable\n", dlm->name, res->lockname.len, res->lockname.name); return 1; @@ -2792,7 +2787,7 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) assert_spin_locked(&dlm->spinlock); spin_lock(&res->spinlock); - if (dlm_is_lockres_migrateable(dlm, res)) + if (dlm_is_lockres_migratable(dlm, res)) target = dlm_pick_migration_target(dlm, res); spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index ec8f75813beb..802636d50365 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -62,7 +62,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node); static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node); static int dlm_request_all_locks(struct dlm_ctxt *dlm, u8 request_from, u8 dead_node); -static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node); +static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm); static inline int dlm_num_locks_in_lockres(struct dlm_lock_resource *res); static void dlm_init_migratable_lockres(struct dlm_migratable_lockres *mres, @@ -423,12 +423,11 @@ void dlm_wait_for_recovery(struct dlm_ctxt *dlm) static void dlm_begin_recovery(struct dlm_ctxt *dlm) { - spin_lock(&dlm->spinlock); + assert_spin_locked(&dlm->spinlock); BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE); printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n", dlm->name, dlm->reco.dead_node); dlm->reco.state |= DLM_RECO_STATE_ACTIVE; - spin_unlock(&dlm->spinlock); } static void dlm_end_recovery(struct dlm_ctxt *dlm) @@ -456,6 +455,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) spin_lock(&dlm->spinlock); + if (dlm->migrate_done) { + mlog(0, "%s: no need do recovery after migrating all " + "lock resources\n", dlm->name); + spin_unlock(&dlm->spinlock); + return 0; + } + /* check to see if the new master has died */ if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM && test_bit(dlm->reco.new_master, dlm->recovery_map)) { @@ -490,12 +496,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) mlog(0, "%s(%d):recovery thread found node %u in the recovery map!\n", dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.dead_node); - spin_unlock(&dlm->spinlock); /* take write barrier */ /* (stops the list reshuffling thread, proxy ast handling) */ dlm_begin_recovery(dlm); + spin_unlock(&dlm->spinlock); + if (dlm->reco.new_master == dlm->node_num) goto master_here; @@ -739,7 +746,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) } if (destroy) - dlm_destroy_recovery_area(dlm, dead_node); + dlm_destroy_recovery_area(dlm); return status; } @@ -764,7 +771,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node) ndata = kzalloc(sizeof(*ndata), GFP_NOFS); if (!ndata) { - dlm_destroy_recovery_area(dlm, dead_node); + dlm_destroy_recovery_area(dlm); return -ENOMEM; } ndata->node_num = num; @@ -778,7 +785,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node) return 0; } -static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node) +static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm) { struct dlm_reco_node_data *ndata, *next; LIST_HEAD(tmplist); @@ -1378,6 +1385,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, if (!dlm_grab(dlm)) return -EINVAL; + if (!dlm_joined(dlm)) { + mlog(ML_ERROR, "Domain %s not joined! " + "lockres %.*s, master %u\n", + dlm->name, mres->lockname_len, + mres->lockname, mres->master); + dlm_put(dlm); + return -EINVAL; + } + BUG_ON(!(mres->flags & (DLM_MRES_RECOVERY|DLM_MRES_MIGRATION))); real_master = mres->master; @@ -1807,7 +1823,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, int i, j, bad; struct dlm_lock *lock; u8 from = O2NM_MAX_NODES; - unsigned int added = 0; __be64 c; mlog(0, "running %d locks for this lockres\n", mres->num_locks); @@ -1823,7 +1838,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); dlm_lockres_set_refmap_bit(dlm, res, from); spin_unlock(&res->spinlock); - added++; break; } BUG_ON(ml->highest_blocked != LKM_IVMODE); @@ -1911,7 +1925,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, /* do not alter lock refcount. switching lists. */ list_move_tail(&lock->list, queue); spin_unlock(&res->spinlock); - added++; mlog(0, "just reordered a local lock!\n"); continue; @@ -2037,7 +2050,6 @@ skip_lvb: "setting refmap bit\n", dlm->name, res->lockname.len, res->lockname.name, ml->node); dlm_lockres_set_refmap_bit(dlm, res, ml->node); - added++; } spin_unlock(&res->spinlock); } @@ -2331,13 +2343,6 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, __dlm_dirty_lockres(dlm, res); } -/* if this node is the recovery master, and there are no - * locks for a given lockres owned by this node that are in - * either PR or EX mode, zero out the lvb before requesting. - * - */ - - static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) { struct dlm_lock_resource *res; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index b552d1f8508c..ce33ac354602 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1756,8 +1756,7 @@ int ocfs2_rw_lock(struct inode *inode, int write) level = write ? DLM_LOCK_EX : DLM_LOCK_PR; - status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, level, 0, - 0); + status = ocfs2_cluster_lock(osb, lockres, level, 0, 0); if (status < 0) mlog_errno(status); @@ -1796,7 +1795,7 @@ void ocfs2_rw_unlock(struct inode *inode, int write) write ? "EXMODE" : "PRMODE"); if (!ocfs2_mount_local(osb)) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level); + ocfs2_cluster_unlock(osb, lockres, level); } /* @@ -1816,8 +1815,7 @@ int ocfs2_open_lock(struct inode *inode) lockres = &OCFS2_I(inode)->ip_open_lockres; - status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, - DLM_LOCK_PR, 0, 0); + status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_PR, 0, 0); if (status < 0) mlog_errno(status); @@ -1854,8 +1852,7 @@ int ocfs2_try_open_lock(struct inode *inode, int write) * other nodes and the -EAGAIN will indicate to the caller that * this inode is still in use. */ - status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, - level, DLM_LKF_NOQUEUE, 0); + status = ocfs2_cluster_lock(osb, lockres, level, DLM_LKF_NOQUEUE, 0); out: return status; @@ -1876,11 +1873,9 @@ void ocfs2_open_unlock(struct inode *inode) goto out; if(lockres->l_ro_holders) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, - DLM_LOCK_PR); + ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_PR); if(lockres->l_ex_holders) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, - DLM_LOCK_EX); + ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX); out: return; @@ -2601,9 +2596,9 @@ void ocfs2_inode_unlock(struct inode *inode, (unsigned long long)OCFS2_I(inode)->ip_blkno, ex ? "EXMODE" : "PRMODE"); - if (!ocfs2_is_hard_readonly(OCFS2_SB(inode->i_sb)) && + if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb)) - ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level); + ocfs2_cluster_unlock(osb, lockres, level); } /* @@ -3539,7 +3534,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb, * we can recover correctly from node failure. Otherwise, we may get * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set. */ - if (!ocfs2_is_o2cb_active() && + if (ocfs2_userspace_stack(osb) && lockres->l_ops->flags & LOCK_TYPE_USES_LVB) lvb = 1; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 5d1784a365a3..6ee94bc23f5b 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -101,7 +101,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file) struct ocfs2_inode_info *oi = OCFS2_I(inode); trace_ocfs2_file_open(inode, file, file->f_path.dentry, - (unsigned long long)OCFS2_I(inode)->ip_blkno, + (unsigned long long)oi->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, mode); @@ -116,7 +116,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file) /* Check that the inode hasn't been wiped from disk by another * node. If it hasn't then we're safe as long as we hold the * spin lock until our increment of open count. */ - if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED) { + if (oi->ip_flags & OCFS2_INODE_DELETED) { spin_unlock(&oi->ip_lock); status = -ENOENT; @@ -190,7 +190,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, bool needs_barrier = false; trace_ocfs2_sync_file(inode, file, file->f_path.dentry, - OCFS2_I(inode)->ip_blkno, + oi->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, (unsigned long long)datasync); @@ -296,7 +296,7 @@ int ocfs2_update_inode_atime(struct inode *inode, ocfs2_journal_dirty(handle, bh); out_commit: - ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); + ocfs2_commit_trans(osb, handle); out: return ret; } @@ -2257,7 +2257,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0; - trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry, + trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, @@ -2405,7 +2405,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0; - trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry, + trace_ocfs2_file_read_iter(inode, filp, filp->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, filp->f_path.dentry->d_name.len, filp->f_path.dentry->d_name.name, @@ -2448,7 +2448,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, * * Take and drop the meta data lock to update inode fields * like i_size. This allows the checks down below - * generic_file_aio_read() a chance of actually working. + * generic_file_read_iter() a chance of actually working. */ ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level, !nowait); @@ -2460,7 +2460,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, ocfs2_inode_unlock(inode, lock_level); ret = generic_file_read_iter(iocb, to); - trace_generic_file_aio_read_ret(ret); + trace_generic_file_read_iter_ret(ret); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index 6b92cb241138..f65f2b2f594d 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -53,36 +53,6 @@ static const char * const ocfs2_filecheck_errs[] = { "UNSUPPORTED" }; -static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock); -static LIST_HEAD(ocfs2_filecheck_sysfs_list); - -struct ocfs2_filecheck { - struct list_head fc_head; /* File check entry list head */ - spinlock_t fc_lock; - unsigned int fc_max; /* Maximum number of entry in list */ - unsigned int fc_size; /* Current entry count in list */ - unsigned int fc_done; /* Finished entry count in list */ -}; - -struct ocfs2_filecheck_sysfs_entry { /* sysfs entry per mounting */ - struct list_head fs_list; - atomic_t fs_count; - struct super_block *fs_sb; - struct kset *fs_devicekset; - struct kset *fs_fcheckkset; - struct ocfs2_filecheck *fs_fcheck; -}; - -#define OCFS2_FILECHECK_MAXSIZE 100 -#define OCFS2_FILECHECK_MINSIZE 10 - -/* File check operation type */ -enum { - OCFS2_FILECHECK_TYPE_CHK = 0, /* Check a file(inode) */ - OCFS2_FILECHECK_TYPE_FIX, /* Fix a file(inode) */ - OCFS2_FILECHECK_TYPE_SET = 100 /* Set entry list maximum size */ -}; - struct ocfs2_filecheck_entry { struct list_head fe_list; unsigned long fe_ino; @@ -110,35 +80,84 @@ ocfs2_filecheck_error(int errno) return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1]; } -static ssize_t ocfs2_filecheck_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf); -static ssize_t ocfs2_filecheck_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count); -static struct kobj_attribute ocfs2_attr_filecheck_chk = +static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf); +static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count); +static struct kobj_attribute ocfs2_filecheck_attr_chk = __ATTR(check, S_IRUSR | S_IWUSR, - ocfs2_filecheck_show, - ocfs2_filecheck_store); -static struct kobj_attribute ocfs2_attr_filecheck_fix = + ocfs2_filecheck_attr_show, + ocfs2_filecheck_attr_store); +static struct kobj_attribute ocfs2_filecheck_attr_fix = __ATTR(fix, S_IRUSR | S_IWUSR, - ocfs2_filecheck_show, - ocfs2_filecheck_store); -static struct kobj_attribute ocfs2_attr_filecheck_set = + ocfs2_filecheck_attr_show, + ocfs2_filecheck_attr_store); +static struct kobj_attribute ocfs2_filecheck_attr_set = __ATTR(set, S_IRUSR | S_IWUSR, - ocfs2_filecheck_show, - ocfs2_filecheck_store); + ocfs2_filecheck_attr_show, + ocfs2_filecheck_attr_store); +static struct attribute *ocfs2_filecheck_attrs[] = { + &ocfs2_filecheck_attr_chk.attr, + &ocfs2_filecheck_attr_fix.attr, + &ocfs2_filecheck_attr_set.attr, + NULL +}; + +static void ocfs2_filecheck_release(struct kobject *kobj) +{ + struct ocfs2_filecheck_sysfs_entry *entry = container_of(kobj, + struct ocfs2_filecheck_sysfs_entry, fs_kobj); + + complete(&entry->fs_kobj_unregister); +} + +static ssize_t +ocfs2_filecheck_show(struct kobject *kobj, struct attribute *attr, char *buf) +{ + ssize_t ret = -EIO; + struct kobj_attribute *kattr = container_of(attr, + struct kobj_attribute, attr); + + kobject_get(kobj); + if (kattr->show) + ret = kattr->show(kobj, kattr, buf); + kobject_put(kobj); + return ret; +} + +static ssize_t +ocfs2_filecheck_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + ssize_t ret = -EIO; + struct kobj_attribute *kattr = container_of(attr, + struct kobj_attribute, attr); + + kobject_get(kobj); + if (kattr->store) + ret = kattr->store(kobj, kattr, buf, count); + kobject_put(kobj); + return ret; +} + +static const struct sysfs_ops ocfs2_filecheck_ops = { + .show = ocfs2_filecheck_show, + .store = ocfs2_filecheck_store, +}; + +static struct kobj_type ocfs2_ktype_filecheck = { + .default_attrs = ocfs2_filecheck_attrs, + .sysfs_ops = &ocfs2_filecheck_ops, + .release = ocfs2_filecheck_release, +}; static void ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry) { struct ocfs2_filecheck_entry *p; - if (!atomic_dec_and_test(&entry->fs_count)) { - wait_var_event(&entry->fs_count, - !atomic_read(&entry->fs_count)); - } - spin_lock(&entry->fs_fcheck->fc_lock); while (!list_empty(&entry->fs_fcheck->fc_head)) { p = list_first_entry(&entry->fs_fcheck->fc_head, @@ -149,151 +168,48 @@ ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry) } spin_unlock(&entry->fs_fcheck->fc_lock); - kset_unregister(entry->fs_fcheckkset); - kset_unregister(entry->fs_devicekset); kfree(entry->fs_fcheck); - kfree(entry); -} - -static void -ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry) -{ - spin_lock(&ocfs2_filecheck_sysfs_lock); - list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list); - spin_unlock(&ocfs2_filecheck_sysfs_lock); + entry->fs_fcheck = NULL; } -static int ocfs2_filecheck_sysfs_del(const char *devname) +int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb) { - struct ocfs2_filecheck_sysfs_entry *p; - - spin_lock(&ocfs2_filecheck_sysfs_lock); - list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) { - if (!strcmp(p->fs_sb->s_id, devname)) { - list_del(&p->fs_list); - spin_unlock(&ocfs2_filecheck_sysfs_lock); - ocfs2_filecheck_sysfs_free(p); - return 0; - } - } - spin_unlock(&ocfs2_filecheck_sysfs_lock); - return 1; -} - -static void -ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry) -{ - if (atomic_dec_and_test(&entry->fs_count)) - wake_up_var(&entry->fs_count); -} - -static struct ocfs2_filecheck_sysfs_entry * -ocfs2_filecheck_sysfs_get(const char *devname) -{ - struct ocfs2_filecheck_sysfs_entry *p = NULL; - - spin_lock(&ocfs2_filecheck_sysfs_lock); - list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) { - if (!strcmp(p->fs_sb->s_id, devname)) { - atomic_inc(&p->fs_count); - spin_unlock(&ocfs2_filecheck_sysfs_lock); - return p; - } - } - spin_unlock(&ocfs2_filecheck_sysfs_lock); - return NULL; -} - -int ocfs2_filecheck_create_sysfs(struct super_block *sb) -{ - int ret = 0; - struct kset *device_kset = NULL; - struct kset *fcheck_kset = NULL; - struct ocfs2_filecheck *fcheck = NULL; - struct ocfs2_filecheck_sysfs_entry *entry = NULL; - struct attribute **attrs = NULL; - struct attribute_group attrgp; - - if (!ocfs2_kset) - return -ENOMEM; - - attrs = kmalloc(sizeof(struct attribute *) * 4, GFP_NOFS); - if (!attrs) { - ret = -ENOMEM; - goto error; - } else { - attrs[0] = &ocfs2_attr_filecheck_chk.attr; - attrs[1] = &ocfs2_attr_filecheck_fix.attr; - attrs[2] = &ocfs2_attr_filecheck_set.attr; - attrs[3] = NULL; - memset(&attrgp, 0, sizeof(attrgp)); - attrgp.attrs = attrs; - } + int ret; + struct ocfs2_filecheck *fcheck; + struct ocfs2_filecheck_sysfs_entry *entry = &osb->osb_fc_ent; fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS); - if (!fcheck) { - ret = -ENOMEM; - goto error; - } else { - INIT_LIST_HEAD(&fcheck->fc_head); - spin_lock_init(&fcheck->fc_lock); - fcheck->fc_max = OCFS2_FILECHECK_MINSIZE; - fcheck->fc_size = 0; - fcheck->fc_done = 0; - } - - if (strlen(sb->s_id) <= 0) { - mlog(ML_ERROR, - "Cannot get device basename when create filecheck sysfs\n"); - ret = -ENODEV; - goto error; - } - - device_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj); - if (!device_kset) { - ret = -ENOMEM; - goto error; - } - - fcheck_kset = kset_create_and_add("filecheck", NULL, - &device_kset->kobj); - if (!fcheck_kset) { - ret = -ENOMEM; - goto error; - } - - ret = sysfs_create_group(&fcheck_kset->kobj, &attrgp); - if (ret) - goto error; + if (!fcheck) + return -ENOMEM; - entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS); - if (!entry) { - ret = -ENOMEM; - goto error; - } else { - atomic_set(&entry->fs_count, 1); - entry->fs_sb = sb; - entry->fs_devicekset = device_kset; - entry->fs_fcheckkset = fcheck_kset; - entry->fs_fcheck = fcheck; - ocfs2_filecheck_sysfs_add(entry); + INIT_LIST_HEAD(&fcheck->fc_head); + spin_lock_init(&fcheck->fc_lock); + fcheck->fc_max = OCFS2_FILECHECK_MINSIZE; + fcheck->fc_size = 0; + fcheck->fc_done = 0; + + entry->fs_kobj.kset = osb->osb_dev_kset; + init_completion(&entry->fs_kobj_unregister); + ret = kobject_init_and_add(&entry->fs_kobj, &ocfs2_ktype_filecheck, + NULL, "filecheck"); + if (ret) { + kfree(fcheck); + return ret; } - kfree(attrs); + entry->fs_fcheck = fcheck; return 0; - -error: - kfree(attrs); - kfree(entry); - kfree(fcheck); - kset_unregister(fcheck_kset); - kset_unregister(device_kset); - return ret; } -int ocfs2_filecheck_remove_sysfs(struct super_block *sb) +void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb) { - return ocfs2_filecheck_sysfs_del(sb->s_id); + if (!osb->osb_fc_ent.fs_fcheck) + return; + + kobject_del(&osb->osb_fc_ent.fs_kobj); + kobject_put(&osb->osb_fc_ent.fs_kobj); + wait_for_completion(&osb->osb_fc_ent.fs_kobj_unregister); + ocfs2_filecheck_sysfs_free(&osb->osb_fc_ent); } static int @@ -310,7 +226,7 @@ ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent, spin_lock(&ent->fs_fcheck->fc_lock); if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) { - mlog(ML_ERROR, + mlog(ML_NOTICE, "Cannot set online file check maximum entry number " "to %u due to too many pending entries(%u)\n", len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done); @@ -387,7 +303,7 @@ ocfs2_filecheck_args_parse(const char *name, const char *buf, size_t count, return 0; } -static ssize_t ocfs2_filecheck_show(struct kobject *kobj, +static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -395,19 +311,12 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj, ssize_t ret = 0, total = 0, remain = PAGE_SIZE; unsigned int type; struct ocfs2_filecheck_entry *p; - struct ocfs2_filecheck_sysfs_entry *ent; + struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj, + struct ocfs2_filecheck_sysfs_entry, fs_kobj); if (ocfs2_filecheck_type_parse(attr->attr.name, &type)) return -EINVAL; - ent = ocfs2_filecheck_sysfs_get(kobj->parent->name); - if (!ent) { - mlog(ML_ERROR, - "Cannot get the corresponding entry via device basename %s\n", - kobj->name); - return -ENODEV; - } - if (type == OCFS2_FILECHECK_TYPE_SET) { spin_lock(&ent->fs_fcheck->fc_lock); total = snprintf(buf, remain, "%u\n", ent->fs_fcheck->fc_max); @@ -441,11 +350,26 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj, spin_unlock(&ent->fs_fcheck->fc_lock); exit: - ocfs2_filecheck_sysfs_put(ent); return total; } -static int +static inline int +ocfs2_filecheck_is_dup_entry(struct ocfs2_filecheck_sysfs_entry *ent, + unsigned long ino) +{ + struct ocfs2_filecheck_entry *p; + + list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) { + if (!p->fe_done) { + if (p->fe_ino == ino) + return 1; + } + } + + return 0; +} + +static inline int ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent) { struct ocfs2_filecheck_entry *p; @@ -484,21 +408,21 @@ static void ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent, struct ocfs2_filecheck_entry *entry) { - entry->fe_done = 1; spin_lock(&ent->fs_fcheck->fc_lock); + entry->fe_done = 1; ent->fs_fcheck->fc_done++; spin_unlock(&ent->fs_fcheck->fc_lock); } static unsigned int -ocfs2_filecheck_handle(struct super_block *sb, +ocfs2_filecheck_handle(struct ocfs2_super *osb, unsigned long ino, unsigned int flags) { unsigned int ret = OCFS2_FILECHECK_ERR_SUCCESS; struct inode *inode = NULL; int rc; - inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0); + inode = ocfs2_iget(osb, ino, flags, 0); if (IS_ERR(inode)) { rc = (int)(-(long)inode); if (rc >= OCFS2_FILECHECK_ERR_START && @@ -516,11 +440,14 @@ static void ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent, struct ocfs2_filecheck_entry *entry) { + struct ocfs2_super *osb = container_of(ent, struct ocfs2_super, + osb_fc_ent); + if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK) - entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb, + entry->fe_status = ocfs2_filecheck_handle(osb, entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK); else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX) - entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb, + entry->fe_status = ocfs2_filecheck_handle(osb, entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX); else entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED; @@ -528,30 +455,21 @@ ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent, ocfs2_filecheck_done_entry(ent, entry); } -static ssize_t ocfs2_filecheck_store(struct kobject *kobj, +static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { + ssize_t ret = 0; struct ocfs2_filecheck_args args; struct ocfs2_filecheck_entry *entry; - struct ocfs2_filecheck_sysfs_entry *ent; - ssize_t ret = 0; + struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj, + struct ocfs2_filecheck_sysfs_entry, fs_kobj); if (count == 0) return count; - if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) { - mlog(ML_ERROR, "Invalid arguments for online file check\n"); + if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) return -EINVAL; - } - - ent = ocfs2_filecheck_sysfs_get(kobj->parent->name); - if (!ent) { - mlog(ML_ERROR, - "Cannot get the corresponding entry via device basename %s\n", - kobj->parent->name); - return -ENODEV; - } if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) { ret = ocfs2_filecheck_adjust_max(ent, args.fa_len); @@ -565,13 +483,16 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj, } spin_lock(&ent->fs_fcheck->fc_lock); - if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) && - (ent->fs_fcheck->fc_done == 0)) { - mlog(ML_ERROR, + if (ocfs2_filecheck_is_dup_entry(ent, args.fa_ino)) { + ret = -EEXIST; + kfree(entry); + } else if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) && + (ent->fs_fcheck->fc_done == 0)) { + mlog(ML_NOTICE, "Cannot do more file check " "since file check queue(%u) is full now\n", ent->fs_fcheck->fc_max); - ret = -EBUSY; + ret = -EAGAIN; kfree(entry); } else { if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) && @@ -596,6 +517,5 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj, ocfs2_filecheck_handle_entry(ent, entry); exit: - ocfs2_filecheck_sysfs_put(ent); return (!ret ? count : ret); } diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h index e5cd002a2c09..6a22ee79e8d0 100644 --- a/fs/ocfs2/filecheck.h +++ b/fs/ocfs2/filecheck.h @@ -43,7 +43,32 @@ enum { #define OCFS2_FILECHECK_ERR_START OCFS2_FILECHECK_ERR_FAILED #define OCFS2_FILECHECK_ERR_END OCFS2_FILECHECK_ERR_UNSUPPORTED -int ocfs2_filecheck_create_sysfs(struct super_block *sb); -int ocfs2_filecheck_remove_sysfs(struct super_block *sb); +struct ocfs2_filecheck { + struct list_head fc_head; /* File check entry list head */ + spinlock_t fc_lock; + unsigned int fc_max; /* Maximum number of entry in list */ + unsigned int fc_size; /* Current entry count in list */ + unsigned int fc_done; /* Finished entry count in list */ +}; + +#define OCFS2_FILECHECK_MAXSIZE 100 +#define OCFS2_FILECHECK_MINSIZE 10 + +/* File check operation type */ +enum { + OCFS2_FILECHECK_TYPE_CHK = 0, /* Check a file(inode) */ + OCFS2_FILECHECK_TYPE_FIX, /* Fix a file(inode) */ + OCFS2_FILECHECK_TYPE_SET = 100 /* Set entry list maximum size */ +}; + +struct ocfs2_filecheck_sysfs_entry { /* sysfs entry per partition */ + struct kobject fs_kobj; + struct completion fs_kobj_unregister; + struct ocfs2_filecheck *fs_fcheck; +}; + + +int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb); +void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb); #endif /* FILECHECK_H */ diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index d51b80edd972..ddc3e9470c87 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1135,7 +1135,7 @@ static void ocfs2_clear_inode(struct inode *inode) trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno, inode->i_nlink); - mlog_bug_on_msg(OCFS2_SB(inode->i_sb) == NULL, + mlog_bug_on_msg(osb == NULL, "Inode=%lu\n", inode->i_ino); dquot_drop(inode); @@ -1150,7 +1150,7 @@ static void ocfs2_clear_inode(struct inode *inode) ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres); ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres); - ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap, + ocfs2_resv_discard(&osb->osb_la_resmap, &oi->ip_la_data_resv); ocfs2_resv_init_once(&oi->ip_la_data_resv); @@ -1160,7 +1160,7 @@ static void ocfs2_clear_inode(struct inode *inode) * exception here are successfully wiped inodes - their * metadata can now be considered to be part of the system * inodes from which it came. */ - if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED)) + if (!(oi->ip_flags & OCFS2_INODE_DELETED)) ocfs2_checkpoint_inode(inode); mlog_bug_on_msg(!list_empty(&oi->ip_io_markers), @@ -1223,7 +1223,7 @@ static void ocfs2_clear_inode(struct inode *inode) * the journal is flushed before journal shutdown. Thus it is safe to * have inodes get cleaned up after journal shutdown. */ - jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal, + jbd2_journal_release_jbd_inode(osb->journal->j_journal, &oi->ip_jinode); } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index e5dcea6cee5f..b63c97f4318e 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1378,15 +1378,23 @@ static int __ocfs2_recovery_thread(void *arg) int rm_quota_used = 0, i; struct ocfs2_quota_recovery *qrec; + /* Whether the quota supported. */ + int quota_enabled = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, + OCFS2_FEATURE_RO_COMPAT_USRQUOTA) + || OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, + OCFS2_FEATURE_RO_COMPAT_GRPQUOTA); + status = ocfs2_wait_on_mount(osb); if (status < 0) { goto bail; } - rm_quota = kzalloc(osb->max_slots * sizeof(int), GFP_NOFS); - if (!rm_quota) { - status = -ENOMEM; - goto bail; + if (quota_enabled) { + rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS); + if (!rm_quota) { + status = -ENOMEM; + goto bail; + } } restart: status = ocfs2_super_lock(osb, 1); @@ -1422,9 +1430,14 @@ restart: * then quota usage would be out of sync until some node takes * the slot. So we remember which nodes need quota recovery * and when everything else is done, we recover quotas. */ - for (i = 0; i < rm_quota_used && rm_quota[i] != slot_num; i++); - if (i == rm_quota_used) - rm_quota[rm_quota_used++] = slot_num; + if (quota_enabled) { + for (i = 0; i < rm_quota_used + && rm_quota[i] != slot_num; i++) + ; + + if (i == rm_quota_used) + rm_quota[rm_quota_used++] = slot_num; + } status = ocfs2_recover_node(osb, node_num, slot_num); skip_recovery: @@ -1452,16 +1465,19 @@ skip_recovery: /* Now it is right time to recover quotas... We have to do this under * superblock lock so that no one can start using the slot (and crash) * before we recover it */ - for (i = 0; i < rm_quota_used; i++) { - qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]); - if (IS_ERR(qrec)) { - status = PTR_ERR(qrec); - mlog_errno(status); - continue; + if (quota_enabled) { + for (i = 0; i < rm_quota_used; i++) { + qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]); + if (IS_ERR(qrec)) { + status = PTR_ERR(qrec); + mlog_errno(status); + continue; + } + ocfs2_queue_recovery_completion(osb->journal, + rm_quota[i], + NULL, NULL, qrec, + ORPHAN_NEED_TRUNCATE); } - ocfs2_queue_recovery_completion(osb->journal, rm_quota[i], - NULL, NULL, qrec, - ORPHAN_NEED_TRUNCATE); } ocfs2_super_unlock(osb, 1); @@ -1483,7 +1499,8 @@ bail: mutex_unlock(&osb->recovery_lock); - kfree(rm_quota); + if (quota_enabled) + kfree(rm_quota); /* no one is callint kthread_stop() for us so the kthread() api * requires that we call do_exit(). And it isn't exported, but diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index c801eddc4bf3..8dd6f703c819 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -525,7 +525,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, * these are used by the support functions here and in * callers. */ inode->i_ino = ino_from_blkno(osb->sb, fe_blkno); - OCFS2_I(inode)->ip_blkno = fe_blkno; + oi->ip_blkno = fe_blkno; spin_lock(&osb->osb_lock); inode->i_generation = osb->s_next_generation++; spin_unlock(&osb->osb_lock); @@ -1186,8 +1186,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } trace_ocfs2_double_lock_end( - (unsigned long long)OCFS2_I(inode1)->ip_blkno, - (unsigned long long)OCFS2_I(inode2)->ip_blkno); + (unsigned long long)oi1->ip_blkno, + (unsigned long long)oi2->ip_blkno); bail: if (status) diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 6867eef2e06b..4f86ac0027b5 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -50,6 +50,8 @@ #include "reservations.h" +#include "filecheck.h" + /* Caching of metadata buffers */ /* Most user visible OCFS2 inodes will have very few pieces of @@ -472,6 +474,12 @@ struct ocfs2_super * workqueue and schedule on our own. */ struct workqueue_struct *ocfs2_wq; + + /* sysfs directory per partition */ + struct kset *osb_dev_kset; + + /* file check related stuff */ + struct ocfs2_filecheck_sysfs_entry osb_fc_ent; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index e2a11aaece10..2ee76a90ba8f 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -1311,11 +1311,11 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_release); DEFINE_OCFS2_FILE_OPS(ocfs2_sync_file); -DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_write); +DEFINE_OCFS2_FILE_OPS(ocfs2_file_write_iter); DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write); -DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_read); +DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter); DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file); @@ -1467,7 +1467,7 @@ TRACE_EVENT(ocfs2_prepare_inode_for_write, __entry->saved_pos, __entry->count, __entry->wait) ); -DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret); +DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret); /* End of trace events for fs/ocfs2/file.c. */ diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index ab156e35ec00..01c6b3894406 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -573,7 +573,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode, BUG_ON(ocfs2_is_refcount_inode(inode)); trace_ocfs2_create_refcount_tree( - (unsigned long long)OCFS2_I(inode)->ip_blkno); + (unsigned long long)oi->ip_blkno); ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac); if (ret) { @@ -3359,7 +3359,7 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context) unsigned int ext_flags; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) { + if (!ocfs2_refcount_tree(osb)) { return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n", inode->i_ino); } @@ -3707,7 +3707,7 @@ int ocfs2_add_refcount_flag(struct inode *inode, trace_ocfs2_add_refcount_flag(ref_blocks, credits); if (ref_blocks) { - ret = ocfs2_reserve_new_metadata_blocks(OCFS2_SB(inode->i_sb), + ret = ocfs2_reserve_new_metadata_blocks(osb, ref_blocks, &meta_ac); if (ret) { mlog_errno(ret); @@ -4766,8 +4766,8 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode, *bh2 = *bh1; trace_ocfs2_double_lock_end( - (unsigned long long)OCFS2_I(inode1)->ip_blkno, - (unsigned long long)OCFS2_I(inode2)->ip_blkno); + (unsigned long long)oi1->ip_blkno, + (unsigned long long)oi2->ip_blkno); return 0; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index d6c350ba25b9..c4b029c43464 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -48,12 +48,6 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; */ static struct ocfs2_stack_plugin *active_stack; -inline int ocfs2_is_o2cb_active(void) -{ - return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB); -} -EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active); - static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index e3036e1790e8..f2dce10fae54 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -298,9 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); -/* In ocfs2_downconvert_lock(), we need to know which stack we are using */ -int ocfs2_is_o2cb_active(void); - extern struct kset *ocfs2_kset; #endif /* STACKGLUE_H */ diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index d8f5f6ce99dc..f7c972fbed6a 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -79,8 +79,6 @@ static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res) return ocfs2_which_suballoc_group(res->sr_blkno, res->sr_bit_offset); } -static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg); -static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe); static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl); static int ocfs2_block_group_fill(handle_t *handle, struct inode *alloc_inode, @@ -387,7 +385,7 @@ static int ocfs2_block_group_fill(handle_t *handle, memset(bg, 0, sb->s_blocksize); strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE); - bg->bg_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation); + bg->bg_generation = cpu_to_le32(osb->fs_generation); bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb, 1, osb->s_feature_incompat)); bg->bg_chain = cpu_to_le16(my_chain); @@ -1521,7 +1519,7 @@ static int ocfs2_cluster_group_search(struct inode *inode, OCFS2_I(inode)->ip_clusters, max_bits); } - ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), + ret = ocfs2_block_group_find_clear_bits(osb, group_bh, bits_wanted, max_bits, res); if (ret) @@ -2626,53 +2624,6 @@ int ocfs2_release_clusters(handle_t *handle, _ocfs2_clear_bit); } -static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg) -{ - printk("Block Group:\n"); - printk("bg_signature: %s\n", bg->bg_signature); - printk("bg_size: %u\n", bg->bg_size); - printk("bg_bits: %u\n", bg->bg_bits); - printk("bg_free_bits_count: %u\n", bg->bg_free_bits_count); - printk("bg_chain: %u\n", bg->bg_chain); - printk("bg_generation: %u\n", le32_to_cpu(bg->bg_generation)); - printk("bg_next_group: %llu\n", - (unsigned long long)bg->bg_next_group); - printk("bg_parent_dinode: %llu\n", - (unsigned long long)bg->bg_parent_dinode); - printk("bg_blkno: %llu\n", - (unsigned long long)bg->bg_blkno); -} - -static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe) -{ - int i; - - printk("Suballoc Inode %llu:\n", (unsigned long long)fe->i_blkno); - printk("i_signature: %s\n", fe->i_signature); - printk("i_size: %llu\n", - (unsigned long long)fe->i_size); - printk("i_clusters: %u\n", fe->i_clusters); - printk("i_generation: %u\n", - le32_to_cpu(fe->i_generation)); - printk("id1.bitmap1.i_used: %u\n", - le32_to_cpu(fe->id1.bitmap1.i_used)); - printk("id1.bitmap1.i_total: %u\n", - le32_to_cpu(fe->id1.bitmap1.i_total)); - printk("id2.i_chain.cl_cpg: %u\n", fe->id2.i_chain.cl_cpg); - printk("id2.i_chain.cl_bpc: %u\n", fe->id2.i_chain.cl_bpc); - printk("id2.i_chain.cl_count: %u\n", fe->id2.i_chain.cl_count); - printk("id2.i_chain.cl_next_free_rec: %u\n", - fe->id2.i_chain.cl_next_free_rec); - for(i = 0; i < fe->id2.i_chain.cl_next_free_rec; i++) { - printk("fe->id2.i_chain.cl_recs[%d].c_free: %u\n", i, - fe->id2.i_chain.cl_recs[i].c_free); - printk("fe->id2.i_chain.cl_recs[%d].c_total: %u\n", i, - fe->id2.i_chain.cl_recs[i].c_total); - printk("fe->id2.i_chain.cl_recs[%d].c_blkno: %llu\n", i, - (unsigned long long)fe->id2.i_chain.cl_recs[i].c_blkno); - } -} - /* * For a given allocation, determine which allocators will need to be * accessed, and lock them, reserving the appropriate number of bits. diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index ffa4952d432b..3415e0b09398 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -423,10 +423,10 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait) ocfs2_schedule_truncate_log_flush(osb, 0); } - if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal, + if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) { if (wait) - jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal, + jbd2_log_wait_commit(osb->journal->j_journal, target); } return 0; @@ -1161,6 +1161,23 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) ocfs2_complete_mount_recovery(osb); + osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL, + &ocfs2_kset->kobj); + if (!osb->osb_dev_kset) { + status = -ENOMEM; + mlog(ML_ERROR, "Unable to create device kset %s.\n", sb->s_id); + goto read_super_error; + } + + /* Create filecheck sysfs related directories/files at + * /sys/fs/ocfs2/<devname>/filecheck */ + if (ocfs2_filecheck_create_sysfs(osb)) { + status = -ENOMEM; + mlog(ML_ERROR, "Unable to create filecheck sysfs directory at " + "/sys/fs/ocfs2/%s/filecheck.\n", sb->s_id); + goto read_super_error; + } + if (ocfs2_mount_local(osb)) snprintf(nodestr, sizeof(nodestr), "local"); else @@ -1199,9 +1216,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) /* Start this when the mount is almost sure of being successful */ ocfs2_orphan_scan_start(osb); - /* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */ - ocfs2_filecheck_create_sysfs(sb); - return status; read_super_error: @@ -1653,7 +1667,6 @@ static void ocfs2_put_super(struct super_block *sb) ocfs2_sync_blockdev(sb); ocfs2_dismount_volume(sb, 0); - ocfs2_filecheck_remove_sysfs(sb); } static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf) @@ -1768,12 +1781,9 @@ static int ocfs2_initialize_mem_caches(void) NULL); if (!ocfs2_inode_cachep || !ocfs2_dquot_cachep || !ocfs2_qf_chunk_cachep) { - if (ocfs2_inode_cachep) - kmem_cache_destroy(ocfs2_inode_cachep); - if (ocfs2_dquot_cachep) - kmem_cache_destroy(ocfs2_dquot_cachep); - if (ocfs2_qf_chunk_cachep) - kmem_cache_destroy(ocfs2_qf_chunk_cachep); + kmem_cache_destroy(ocfs2_inode_cachep); + kmem_cache_destroy(ocfs2_dquot_cachep); + kmem_cache_destroy(ocfs2_qf_chunk_cachep); return -ENOMEM; } @@ -1787,16 +1797,13 @@ static void ocfs2_free_mem_caches(void) * destroy cache. */ rcu_barrier(); - if (ocfs2_inode_cachep) - kmem_cache_destroy(ocfs2_inode_cachep); + kmem_cache_destroy(ocfs2_inode_cachep); ocfs2_inode_cachep = NULL; - if (ocfs2_dquot_cachep) - kmem_cache_destroy(ocfs2_dquot_cachep); + kmem_cache_destroy(ocfs2_dquot_cachep); ocfs2_dquot_cachep = NULL; - if (ocfs2_qf_chunk_cachep) - kmem_cache_destroy(ocfs2_qf_chunk_cachep); + kmem_cache_destroy(ocfs2_qf_chunk_cachep); ocfs2_qf_chunk_cachep = NULL; } @@ -1899,6 +1906,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) osb = OCFS2_SB(sb); BUG_ON(!osb); + /* Remove file check sysfs related directores/files, + * and wait for the pending file check operations */ + ocfs2_filecheck_remove_sysfs(osb); + + kset_unregister(osb->osb_dev_kset); + debugfs_remove(osb->osb_ctxt); /* Orphan scan should be stopped as early as possible */ diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c index 82e17b076ce7..78f09c76ab3c 100644 --- a/fs/ocfs2/uptodate.c +++ b/fs/ocfs2/uptodate.c @@ -633,6 +633,5 @@ int __init init_ocfs2_uptodate_cache(void) void exit_ocfs2_uptodate_cache(void) { - if (ocfs2_uptodate_cachep) - kmem_cache_destroy(ocfs2_uptodate_cachep); + kmem_cache_destroy(ocfs2_uptodate_cachep); } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index c261c1dfd374..3a24ce3deb01 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3564,7 +3564,7 @@ int ocfs2_xattr_set(struct inode *inode, .not_found = -ENODATA, }; - if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb))) + if (!ocfs2_supports_xattr(osb)) return -EOPNOTSUPP; /* diff --git a/fs/proc/array.c b/fs/proc/array.c index 598803576e4c..ae2c807fd719 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -141,25 +141,12 @@ static inline const char *get_task_state(struct task_struct *tsk) return task_state_array[task_state_index(tsk)]; } -static inline int get_task_umask(struct task_struct *tsk) -{ - struct fs_struct *fs; - int umask = -ENOENT; - - task_lock(tsk); - fs = tsk->fs; - if (fs) - umask = fs->umask; - task_unlock(tsk); - return umask; -} - static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *p) { struct user_namespace *user_ns = seq_user_ns(m); struct group_info *group_info; - int g, umask; + int g, umask = -1; struct task_struct *tracer; const struct cred *cred; pid_t ppid, tpid = 0, tgid, ngid; @@ -177,17 +164,18 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, ngid = task_numa_group_id(p); cred = get_task_cred(p); - umask = get_task_umask(p); - if (umask >= 0) - seq_printf(m, "Umask:\t%#04o\n", umask); - task_lock(p); + if (p->fs) + umask = p->fs->umask; if (p->files) max_fds = files_fdtable(p->files)->max_fds; task_unlock(p); rcu_read_unlock(); - seq_printf(m, "State:\t%s", get_task_state(p)); + if (umask >= 0) + seq_printf(m, "Umask:\t%#04o\n", umask); + seq_puts(m, "State:\t"); + seq_puts(m, get_task_state(p)); seq_put_decimal_ull(m, "\nTgid:\t", tgid); seq_put_decimal_ull(m, "\nNgid:\t", ngid); @@ -313,8 +301,8 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_puts(m, header); CAP_FOR_EACH_U32(__capi) { - seq_printf(m, "%08x", - a->cap[CAP_LAST_U32 - __capi]); + seq_put_hex_ll(m, NULL, + a->cap[CAP_LAST_U32 - __capi], 8); } seq_putc(m, '\n'); } @@ -368,7 +356,8 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) { - seq_printf(m, "CoreDumping:\t%d\n", !!mm->core_state); + seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state); + seq_putc(m, '\n'); } int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, @@ -504,7 +493,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* convert nsec -> ticks */ start_time = nsec_to_clock_t(task->real_start_time); - seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); + seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); + seq_puts(m, " ("); + seq_puts(m, tcomm); + seq_puts(m, ") "); + seq_putc(m, state); seq_put_decimal_ll(m, " ", ppid); seq_put_decimal_ll(m, " ", pgid); seq_put_decimal_ll(m, " ", sid); diff --git a/fs/proc/base.c b/fs/proc/base.c index d53246863cfb..eafa39a3a88c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -388,14 +388,17 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, unsigned long wchan; char symname[KSYM_NAME_LEN]; - wchan = get_wchan(task); + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) + goto print0; - if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS) - && !lookup_symbol_name(wchan, symname)) - seq_printf(m, "%s", symname); - else - seq_putc(m, '0'); + wchan = get_wchan(task); + if (wchan && !lookup_symbol_name(wchan, symname)) { + seq_puts(m, symname); + return 0; + } +print0: + seq_putc(m, '0'); return 0; } #endif /* CONFIG_KALLSYMS */ @@ -1910,6 +1913,8 @@ static int dname_to_vma_addr(struct dentry *dentry, unsigned long long sval, eval; unsigned int len; + if (str[0] == '0' && str[1] != '-') + return -EINVAL; len = _parse_integer(str, 16, &sval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; @@ -1921,6 +1926,8 @@ static int dname_to_vma_addr(struct dentry *dentry, return -EINVAL; str++; + if (str[0] == '0' && str[1]) + return -EINVAL; len = _parse_integer(str, 16, &eval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; @@ -2204,6 +2211,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) } } up_read(&mm->mmap_sem); + mmput(mm); for (i = 0; i < nr_files; i++) { char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */ @@ -2221,7 +2229,6 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) } if (fa) flex_array_free(fa); - mmput(mm); out_put_task: put_task_struct(task); diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c index 403cbb12a6e9..8233e7af9389 100644 --- a/fs/proc/cmdline.c +++ b/fs/proc/cmdline.c @@ -6,7 +6,8 @@ static int cmdline_proc_show(struct seq_file *m, void *v) { - seq_printf(m, "%s\n", saved_command_line); + seq_puts(m, saved_command_line); + seq_putc(m, '\n'); return 0; } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 5d709fa8f3a2..2078e70e1595 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -8,12 +8,14 @@ * Copyright (C) 1997 Theodore Ts'o */ +#include <linux/cache.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/namei.h> #include <linux/slab.h> #include <linux/printk.h> #include <linux/mount.h> @@ -28,6 +30,17 @@ static DEFINE_RWLOCK(proc_subdir_lock); +struct kmem_cache *proc_dir_entry_cache __ro_after_init; + +void pde_free(struct proc_dir_entry *pde) +{ + if (S_ISLNK(pde->mode)) + kfree(pde->data); + if (pde->name != pde->inline_name) + kfree(pde->name); + kmem_cache_free(proc_dir_entry_cache, pde); +} + static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len) { if (len < de->namelen) @@ -40,8 +53,8 @@ static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir) { - return rb_entry_safe(rb_first_cached(&dir->subdir), - struct proc_dir_entry, subdir_node); + return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry, + subdir_node); } static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir) @@ -54,7 +67,7 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, const char *name, unsigned int len) { - struct rb_node *node = dir->subdir.rb_root.rb_node; + struct rb_node *node = dir->subdir.rb_node; while (node) { struct proc_dir_entry *de = rb_entry(node, @@ -75,9 +88,8 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, static bool pde_subdir_insert(struct proc_dir_entry *dir, struct proc_dir_entry *de) { - struct rb_root_cached *root = &dir->subdir; - struct rb_node **new = &root->rb_root.rb_node, *parent = NULL; - bool leftmost = true; + struct rb_root *root = &dir->subdir; + struct rb_node **new = &root->rb_node, *parent = NULL; /* Figure out where to put new node */ while (*new) { @@ -89,16 +101,15 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, parent = *new; if (result < 0) new = &(*new)->rb_left; - else if (result > 0) { + else if (result > 0) new = &(*new)->rb_right; - leftmost = false; - } else + else return false; } /* Add new node and rebalance tree. */ rb_link_node(&de->subdir_node, parent, new); - rb_insert_color_cached(&de->subdir_node, root, leftmost); + rb_insert_color(&de->subdir_node, root); return true; } @@ -207,6 +218,26 @@ void proc_free_inum(unsigned int inum) ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); } +static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0) + return 0; /* revalidate */ + return 1; +} + +static int proc_misc_d_delete(const struct dentry *dentry) +{ + return atomic_read(&PDE(d_inode(dentry))->in_use) < 0; +} + +static const struct dentry_operations proc_misc_dentry_ops = { + .d_revalidate = proc_misc_d_revalidate, + .d_delete = proc_misc_d_delete, +}; + /* * Don't create negative dentries here, return -ENOENT by hand * instead. @@ -224,7 +255,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &simple_dentry_operations); + d_set_d_op(dentry, &proc_misc_dentry_ops); d_add(dentry, inode); return NULL; } @@ -354,6 +385,14 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, WARN(1, "name len %u\n", qstr.len); return NULL; } + if (qstr.len == 1 && fn[0] == '.') { + WARN(1, "name '.'\n"); + return NULL; + } + if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') { + WARN(1, "name '..'\n"); + return NULL; + } if (*parent == &proc_root && name_to_int(&qstr) != ~0U) { WARN(1, "create '/proc/%s' by hand\n", qstr.name); return NULL; @@ -363,16 +402,26 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, return NULL; } - ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL); + ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!ent) goto out; + if (qstr.len + 1 <= sizeof(ent->inline_name)) { + ent->name = ent->inline_name; + } else { + ent->name = kmalloc(qstr.len + 1, GFP_KERNEL); + if (!ent->name) { + pde_free(ent); + return NULL; + } + } + memcpy(ent->name, fn, qstr.len + 1); ent->namelen = qstr.len; ent->mode = mode; ent->nlink = nlink; - ent->subdir = RB_ROOT_CACHED; - atomic_set(&ent->count, 1); + ent->subdir = RB_ROOT; + refcount_set(&ent->refcnt, 1); spin_lock_init(&ent->pde_unload_lock); INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); @@ -395,12 +444,11 @@ struct proc_dir_entry *proc_symlink(const char *name, strcpy((char*)ent->data,dest); ent->proc_iops = &proc_link_inode_operations; if (proc_register(parent, ent) < 0) { - kfree(ent->data); - kfree(ent); + pde_free(ent); ent = NULL; } } else { - kfree(ent); + pde_free(ent); ent = NULL; } } @@ -423,7 +471,7 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent->proc_iops = &proc_dir_inode_operations; parent->nlink++; if (proc_register(parent, ent) < 0) { - kfree(ent); + pde_free(ent); parent->nlink--; ent = NULL; } @@ -458,7 +506,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent->proc_iops = NULL; parent->nlink++; if (proc_register(parent, ent) < 0) { - kfree(ent); + pde_free(ent); parent->nlink--; ent = NULL; } @@ -495,7 +543,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, goto out_free; return pde; out_free: - kfree(pde); + pde_free(pde); out: return NULL; } @@ -522,19 +570,12 @@ void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) } EXPORT_SYMBOL(proc_set_user); -static void free_proc_entry(struct proc_dir_entry *de) -{ - proc_free_inum(de->low_ino); - - if (S_ISLNK(de->mode)) - kfree(de->data); - kfree(de); -} - void pde_put(struct proc_dir_entry *pde) { - if (atomic_dec_and_test(&pde->count)) - free_proc_entry(pde); + if (refcount_dec_and_test(&pde->refcnt)) { + proc_free_inum(pde->low_ino); + pde_free(pde); + } } /* @@ -555,7 +596,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) de = pde_subdir_find(parent, fn, len); if (de) - rb_erase_cached(&de->subdir_node, &parent->subdir); + rb_erase(&de->subdir_node, &parent->subdir); write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); @@ -592,13 +633,13 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) write_unlock(&proc_subdir_lock); return -ENOENT; } - rb_erase_cached(&root->subdir_node, &parent->subdir); + rb_erase(&root->subdir_node, &parent->subdir); de = root; while (1) { next = pde_subdir_first(de); if (next) { - rb_erase_cached(&next->subdir_node, &de->subdir); + rb_erase(&next->subdir_node, &de->subdir); de = next; continue; } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 6e8724958116..2cf3b74391ca 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -54,6 +54,7 @@ static void proc_evict_inode(struct inode *inode) } static struct kmem_cache *proc_inode_cachep __ro_after_init; +static struct kmem_cache *pde_opener_cache __ro_after_init; static struct inode *proc_alloc_inode(struct super_block *sb) { @@ -92,7 +93,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -void __init proc_init_inodecache(void) +void __init proc_init_kmemcache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), @@ -100,6 +101,13 @@ void __init proc_init_inodecache(void) SLAB_MEM_SPREAD|SLAB_ACCOUNT| SLAB_PANIC), init_once); + pde_opener_cache = + kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0, + SLAB_ACCOUNT|SLAB_PANIC, NULL); + proc_dir_entry_cache = kmem_cache_create_usercopy( + "proc_dir_entry", sizeof(struct proc_dir_entry), 0, SLAB_PANIC, + offsetof(struct proc_dir_entry, inline_name), + sizeof_field(struct proc_dir_entry, inline_name), NULL); } static int proc_show_options(struct seq_file *seq, struct dentry *root) @@ -138,7 +146,7 @@ static void unuse_pde(struct proc_dir_entry *pde) complete(pde->pde_unload_completion); } -/* pde is locked */ +/* pde is locked on entry, unlocked on exit */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) { /* @@ -157,9 +165,10 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->c = &c; spin_unlock(&pde->pde_unload_lock); wait_for_completion(&c); - spin_lock(&pde->pde_unload_lock); } else { struct file *file; + struct completion *c; + pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); file = pdeo->file; @@ -167,9 +176,11 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) spin_lock(&pde->pde_unload_lock); /* After ->release. */ list_del(&pdeo->lh); - if (unlikely(pdeo->c)) - complete(pdeo->c); - kfree(pdeo); + c = pdeo->c; + spin_unlock(&pde->pde_unload_lock); + if (unlikely(c)) + complete(c); + kmem_cache_free(pde_opener_cache, pdeo); } } @@ -188,6 +199,7 @@ void proc_entry_rundown(struct proc_dir_entry *de) struct pde_opener *pdeo; pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh); close_pdeo(de, pdeo); + spin_lock(&de->pde_unload_lock); } spin_unlock(&de->pde_unload_lock); } @@ -338,31 +350,36 @@ static int proc_reg_open(struct inode *inode, struct file *file) * * Save every "struct file" with custom ->release hook. */ - pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL); - if (!pdeo) - return -ENOMEM; - - if (!use_pde(pde)) { - kfree(pdeo); + if (!use_pde(pde)) return -ENOENT; - } - open = pde->proc_fops->open; + release = pde->proc_fops->release; + if (release) { + pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); + if (!pdeo) { + rv = -ENOMEM; + goto out_unuse; + } + } + open = pde->proc_fops->open; if (open) rv = open(inode, file); - if (rv == 0 && release) { - /* To know what to release. */ - pdeo->file = file; - pdeo->closing = false; - pdeo->c = NULL; - spin_lock(&pde->pde_unload_lock); - list_add(&pdeo->lh, &pde->pde_openers); - spin_unlock(&pde->pde_unload_lock); - } else - kfree(pdeo); + if (release) { + if (rv == 0) { + /* To know what to release. */ + pdeo->file = file; + pdeo->closing = false; + pdeo->c = NULL; + spin_lock(&pde->pde_unload_lock); + list_add(&pdeo->lh, &pde->pde_openers); + spin_unlock(&pde->pde_unload_lock); + } else + kmem_cache_free(pde_opener_cache, pdeo); + } +out_unuse: unuse_pde(pde); return rv; } @@ -375,7 +392,7 @@ static int proc_reg_release(struct inode *inode, struct file *file) list_for_each_entry(pdeo, &pde->pde_openers, lh) { if (pdeo->file == file) { close_pdeo(pde, pdeo); - break; + return 0; } } spin_unlock(&pde->pde_unload_lock); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index d697c8ab0a14..0f1692e63cb6 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -11,6 +11,7 @@ #include <linux/proc_fs.h> #include <linux/proc_ns.h> +#include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/binfmts.h> @@ -36,7 +37,7 @@ struct proc_dir_entry { * negative -> it's going away RSN */ atomic_t in_use; - atomic_t count; /* use count */ + refcount_t refcnt; struct list_head pde_openers; /* who did ->open, but not ->release */ /* protects ->pde_openers and all struct pde_opener instances */ spinlock_t pde_unload_lock; @@ -50,13 +51,22 @@ struct proc_dir_entry { kgid_t gid; loff_t size; struct proc_dir_entry *parent; - struct rb_root_cached subdir; + struct rb_root subdir; struct rb_node subdir_node; + char *name; umode_t mode; u8 namelen; - char name[]; +#ifdef CONFIG_64BIT +#define SIZEOF_PDE_INLINE_NAME (192-139) +#else +#define SIZEOF_PDE_INLINE_NAME (128-87) +#endif + char inline_name[SIZEOF_PDE_INLINE_NAME]; } __randomize_layout; +extern struct kmem_cache *proc_dir_entry_cache; +void pde_free(struct proc_dir_entry *pde); + union proc_op { int (*proc_get_link)(struct dentry *, struct path *); int (*proc_show)(struct seq_file *m, @@ -159,7 +169,7 @@ int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry * static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde) { - atomic_inc(&pde->count); + refcount_inc(&pde->refcnt); return pde; } extern void pde_put(struct proc_dir_entry *); @@ -177,12 +187,12 @@ struct pde_opener { struct list_head lh; bool closing; struct completion *c; -}; +} __randomize_layout; extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; -extern void proc_init_inodecache(void); +void proc_init_kmemcache(void); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); extern int proc_fill_super(struct super_block *, void *data, int flags); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 6bb20f864259..65a72ab57471 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -26,20 +26,7 @@ void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) static void show_val_kb(struct seq_file *m, const char *s, unsigned long num) { - char v[32]; - static const char blanks[7] = {' ', ' ', ' ', ' ',' ', ' ', ' '}; - int len; - - len = num_to_str(v, sizeof(v), num << (PAGE_SHIFT - 10)); - - seq_write(m, s, 16); - - if (len > 0) { - if (len < 8) - seq_write(m, blanks, 8 - len); - - seq_write(m, v, len); - } + seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8); seq_write(m, " kB\n", 4); } diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 68c06ae7888c..1763f370489d 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -192,15 +192,16 @@ static __net_init int proc_net_ns_init(struct net *net) int err; err = -ENOMEM; - netd = kzalloc(sizeof(*netd) + 4, GFP_KERNEL); + netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) goto out; - netd->subdir = RB_ROOT_CACHED; + netd->subdir = RB_ROOT; netd->data = net; netd->nlink = 2; netd->namelen = 3; netd->parent = &proc_root; + netd->name = netd->inline_name; memcpy(netd->name, "net", 4); uid = make_kuid(net->user_ns, 0); @@ -223,7 +224,7 @@ static __net_init int proc_net_ns_init(struct net *net) return 0; free_net: - kfree(netd); + pde_free(netd); out: return err; } @@ -231,7 +232,7 @@ out: static __net_exit void proc_net_ns_exit(struct net *net) { remove_proc_entry("stat", net->proc_net); - kfree(net->proc_net); + pde_free(net->proc_net); } static struct pernet_operations __net_initdata proc_net_ns_ops = { diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c41ab261397d..8989936f2995 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -707,14 +707,14 @@ static bool proc_sys_link_fill_cache(struct file *file, struct ctl_table *table) { bool ret = true; + head = sysctl_head_grab(head); + if (IS_ERR(head)) + return false; - if (S_ISLNK(table->mode)) { - /* It is not an error if we can not follow the link ignore it */ - int err = sysctl_follow_link(&head, &table); - if (err) - goto out; - } + /* It is not an error if we can not follow the link ignore it */ + if (sysctl_follow_link(&head, &table)) + goto out; ret = proc_sys_fill_cache(file, ctx, head, table); out: @@ -1086,7 +1086,7 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table) if ((table->proc_handler == proc_douintvec) || (table->proc_handler == proc_douintvec_minmax)) { if (table->maxlen != sizeof(unsigned int)) - err |= sysctl_err(path, table, "array now allowed"); + err |= sysctl_err(path, table, "array not allowed"); } return err; diff --git a/fs/proc/root.c b/fs/proc/root.c index ede8e64974be..61b7340b357a 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -123,23 +123,13 @@ static struct file_system_type proc_fs_type = { void __init proc_root_init(void) { - int err; - - proc_init_inodecache(); + proc_init_kmemcache(); set_proc_pid_nlink(); - err = register_filesystem(&proc_fs_type); - if (err) - return; - proc_self_init(); proc_thread_self_init(); proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); - -#ifdef CONFIG_SYSVIPC - proc_mkdir("sysvipc", NULL); -#endif proc_mkdir("fs", NULL); proc_mkdir("driver", NULL); proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */ @@ -150,6 +140,8 @@ void __init proc_root_init(void) proc_tty_init(); proc_mkdir("bus", NULL); proc_sys_init(); + + register_filesystem(&proc_fs_type); } static int proc_root_getattr(const struct path *path, struct kstat *stat, @@ -207,12 +199,13 @@ struct proc_dir_entry proc_root = { .namelen = 5, .mode = S_IFDIR | S_IRUGO | S_IXUGO, .nlink = 2, - .count = ATOMIC_INIT(1), + .refcnt = REFCOUNT_INIT(1), .proc_iops = &proc_root_inode_operations, .proc_fops = &proc_root_operations, .parent = &proc_root, - .subdir = RB_ROOT_CACHED, - .name = "/proc", + .subdir = RB_ROOT, + .name = proc_root.inline_name, + .inline_name = "/proc", }; int pid_ns_prepare_proc(struct pid_namespace *ns) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ec6d2983a5cb..65ae54659833 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -24,6 +24,8 @@ #include <asm/tlbflush.h> #include "internal.h" +#define SEQ_PUT_DEC(str, val) \ + seq_put_decimal_ull_width(m, str, (val) << (PAGE_SHIFT-10), 8) void task_mem(struct seq_file *m, struct mm_struct *mm) { unsigned long text, lib, swap, anon, file, shmem; @@ -53,39 +55,28 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) lib = (mm->exec_vm << PAGE_SHIFT) - text; swap = get_mm_counter(mm, MM_SWAPENTS); - seq_printf(m, - "VmPeak:\t%8lu kB\n" - "VmSize:\t%8lu kB\n" - "VmLck:\t%8lu kB\n" - "VmPin:\t%8lu kB\n" - "VmHWM:\t%8lu kB\n" - "VmRSS:\t%8lu kB\n" - "RssAnon:\t%8lu kB\n" - "RssFile:\t%8lu kB\n" - "RssShmem:\t%8lu kB\n" - "VmData:\t%8lu kB\n" - "VmStk:\t%8lu kB\n" - "VmExe:\t%8lu kB\n" - "VmLib:\t%8lu kB\n" - "VmPTE:\t%8lu kB\n" - "VmSwap:\t%8lu kB\n", - hiwater_vm << (PAGE_SHIFT-10), - total_vm << (PAGE_SHIFT-10), - mm->locked_vm << (PAGE_SHIFT-10), - mm->pinned_vm << (PAGE_SHIFT-10), - hiwater_rss << (PAGE_SHIFT-10), - total_rss << (PAGE_SHIFT-10), - anon << (PAGE_SHIFT-10), - file << (PAGE_SHIFT-10), - shmem << (PAGE_SHIFT-10), - mm->data_vm << (PAGE_SHIFT-10), - mm->stack_vm << (PAGE_SHIFT-10), - text >> 10, - lib >> 10, - mm_pgtables_bytes(mm) >> 10, - swap << (PAGE_SHIFT-10)); + SEQ_PUT_DEC("VmPeak:\t", hiwater_vm); + SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm); + SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm); + SEQ_PUT_DEC(" kB\nVmPin:\t", mm->pinned_vm); + SEQ_PUT_DEC(" kB\nVmHWM:\t", hiwater_rss); + SEQ_PUT_DEC(" kB\nVmRSS:\t", total_rss); + SEQ_PUT_DEC(" kB\nRssAnon:\t", anon); + SEQ_PUT_DEC(" kB\nRssFile:\t", file); + SEQ_PUT_DEC(" kB\nRssShmem:\t", shmem); + SEQ_PUT_DEC(" kB\nVmData:\t", mm->data_vm); + SEQ_PUT_DEC(" kB\nVmStk:\t", mm->stack_vm); + seq_put_decimal_ull_width(m, + " kB\nVmExe:\t", text >> 10, 8); + seq_put_decimal_ull_width(m, + " kB\nVmLib:\t", lib >> 10, 8); + seq_put_decimal_ull_width(m, + " kB\nVmPTE:\t", mm_pgtables_bytes(mm) >> 10, 8); + SEQ_PUT_DEC(" kB\nVmSwap:\t", swap); + seq_puts(m, " kB\n"); hugetlb_report_usage(m, mm); } +#undef SEQ_PUT_DEC unsigned long task_vsize(struct mm_struct *mm) { @@ -287,15 +278,18 @@ static void show_vma_header_prefix(struct seq_file *m, dev_t dev, unsigned long ino) { seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); - seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", - start, - end, - flags & VM_READ ? 'r' : '-', - flags & VM_WRITE ? 'w' : '-', - flags & VM_EXEC ? 'x' : '-', - flags & VM_MAYSHARE ? 's' : 'p', - pgoff, - MAJOR(dev), MINOR(dev), ino); + seq_put_hex_ll(m, NULL, start, 8); + seq_put_hex_ll(m, "-", end, 8); + seq_putc(m, ' '); + seq_putc(m, flags & VM_READ ? 'r' : '-'); + seq_putc(m, flags & VM_WRITE ? 'w' : '-'); + seq_putc(m, flags & VM_EXEC ? 'x' : '-'); + seq_putc(m, flags & VM_MAYSHARE ? 's' : 'p'); + seq_put_hex_ll(m, " ", pgoff, 8); + seq_put_hex_ll(m, " ", MAJOR(dev), 2); + seq_put_hex_ll(m, ":", MINOR(dev), 2); + seq_put_decimal_ull(m, " ", ino); + seq_putc(m, ' '); } static void @@ -694,8 +688,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) if (!mnemonics[i][0]) continue; if (vma->vm_flags & (1UL << i)) { - seq_printf(m, "%c%c ", - mnemonics[i][0], mnemonics[i][1]); + seq_putc(m, mnemonics[i][0]); + seq_putc(m, mnemonics[i][1]); + seq_putc(m, ' '); } } seq_putc(m, '\n'); @@ -736,6 +731,8 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) { } +#define SEQ_PUT_DEC(str, val) \ + seq_put_decimal_ull_width(m, str, (val) >> 10, 8) static int show_smap(struct seq_file *m, void *v, int is_pid) { struct proc_maps_private *priv = m->private; @@ -809,51 +806,34 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) ret = SEQ_SKIP; } - if (!rollup_mode) - seq_printf(m, - "Size: %8lu kB\n" - "KernelPageSize: %8lu kB\n" - "MMUPageSize: %8lu kB\n", - (vma->vm_end - vma->vm_start) >> 10, - vma_kernel_pagesize(vma) >> 10, - vma_mmu_pagesize(vma) >> 10); - - - if (!rollup_mode || last_vma) - seq_printf(m, - "Rss: %8lu kB\n" - "Pss: %8lu kB\n" - "Shared_Clean: %8lu kB\n" - "Shared_Dirty: %8lu kB\n" - "Private_Clean: %8lu kB\n" - "Private_Dirty: %8lu kB\n" - "Referenced: %8lu kB\n" - "Anonymous: %8lu kB\n" - "LazyFree: %8lu kB\n" - "AnonHugePages: %8lu kB\n" - "ShmemPmdMapped: %8lu kB\n" - "Shared_Hugetlb: %8lu kB\n" - "Private_Hugetlb: %7lu kB\n" - "Swap: %8lu kB\n" - "SwapPss: %8lu kB\n" - "Locked: %8lu kB\n", - mss->resident >> 10, - (unsigned long)(mss->pss >> (10 + PSS_SHIFT)), - mss->shared_clean >> 10, - mss->shared_dirty >> 10, - mss->private_clean >> 10, - mss->private_dirty >> 10, - mss->referenced >> 10, - mss->anonymous >> 10, - mss->lazyfree >> 10, - mss->anonymous_thp >> 10, - mss->shmem_thp >> 10, - mss->shared_hugetlb >> 10, - mss->private_hugetlb >> 10, - mss->swap >> 10, - (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)), - (unsigned long)(mss->pss >> (10 + PSS_SHIFT))); + if (!rollup_mode) { + SEQ_PUT_DEC("Size: ", vma->vm_end - vma->vm_start); + SEQ_PUT_DEC(" kB\nKernelPageSize: ", vma_kernel_pagesize(vma)); + SEQ_PUT_DEC(" kB\nMMUPageSize: ", vma_mmu_pagesize(vma)); + seq_puts(m, " kB\n"); + } + if (!rollup_mode || last_vma) { + SEQ_PUT_DEC("Rss: ", mss->resident); + SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean); + SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty); + SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean); + SEQ_PUT_DEC(" kB\nPrivate_Dirty: ", mss->private_dirty); + SEQ_PUT_DEC(" kB\nReferenced: ", mss->referenced); + SEQ_PUT_DEC(" kB\nAnonymous: ", mss->anonymous); + SEQ_PUT_DEC(" kB\nLazyFree: ", mss->lazyfree); + SEQ_PUT_DEC(" kB\nAnonHugePages: ", mss->anonymous_thp); + SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp); + SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb); + seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ", + mss->private_hugetlb >> 10, 7); + SEQ_PUT_DEC(" kB\nSwap: ", mss->swap); + SEQ_PUT_DEC(" kB\nSwapPss: ", + mss->swap_pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nLocked: ", mss->pss >> PSS_SHIFT); + seq_puts(m, " kB\n"); + } if (!rollup_mode) { arch_show_smap(m, vma); show_smap_vma_flags(m, vma); @@ -861,6 +841,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) m_cache_vma(m, vma); return ret; } +#undef SEQ_PUT_DEC static int show_pid_smap(struct seq_file *m, void *v) { diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 70057359fbaf..23148c3ed675 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2643,7 +2643,7 @@ static int journal_init_dev(struct super_block *super, if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; - reiserfs_warning(super, + reiserfs_warning(super, "sh-457", "journal_init_dev: Cannot open '%s': %i", jdev_name, result); return result; diff --git a/fs/seq_file.c b/fs/seq_file.c index eea09f6d8830..8389da9d0eb8 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -6,6 +6,7 @@ * initial implementation -- AV, Oct 2001. */ +#include <linux/cache.h> #include <linux/fs.h> #include <linux/export.h> #include <linux/seq_file.h> @@ -19,6 +20,8 @@ #include <linux/uaccess.h> #include <asm/page.h> +static struct kmem_cache *seq_file_cache __ro_after_init; + static void seq_set_overflow(struct seq_file *m) { m->count = m->size; @@ -26,7 +29,7 @@ static void seq_set_overflow(struct seq_file *m) static void *seq_buf_alloc(unsigned long size) { - return kvmalloc(size, GFP_KERNEL); + return kvmalloc(size, GFP_KERNEL_ACCOUNT); } /** @@ -51,7 +54,7 @@ int seq_open(struct file *file, const struct seq_operations *op) WARN_ON(file->private_data); - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kmem_cache_zalloc(seq_file_cache, GFP_KERNEL); if (!p) return -ENOMEM; @@ -366,7 +369,7 @@ int seq_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; kvfree(m->buf); - kfree(m); + kmem_cache_free(seq_file_cache, m); return 0; } EXPORT_SYMBOL(seq_release); @@ -563,7 +566,7 @@ static void single_stop(struct seq_file *p, void *v) int single_open(struct file *file, int (*show)(struct seq_file *, void *), void *data) { - struct seq_operations *op = kmalloc(sizeof(*op), GFP_KERNEL); + struct seq_operations *op = kmalloc(sizeof(*op), GFP_KERNEL_ACCOUNT); int res = -ENOMEM; if (op) { @@ -625,7 +628,7 @@ void *__seq_open_private(struct file *f, const struct seq_operations *ops, void *private; struct seq_file *seq; - private = kzalloc(psize, GFP_KERNEL); + private = kzalloc(psize, GFP_KERNEL_ACCOUNT); if (private == NULL) goto out; @@ -673,37 +676,40 @@ void seq_puts(struct seq_file *m, const char *s) } EXPORT_SYMBOL(seq_puts); -/* +/** * A helper routine for putting decimal numbers without rich format of printf(). * only 'unsigned long long' is supported. - * This routine will put strlen(delimiter) + number into seq_file. + * @m: seq_file identifying the buffer to which data should be written + * @delimiter: a string which is printed before the number + * @num: the number + * @width: a minimum field width + * + * This routine will put strlen(delimiter) + number into seq_filed. * This routine is very quick when you show lots of numbers. * In usual cases, it will be better to use seq_printf(). It's easier to read. */ -void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, - unsigned long long num) +void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, + unsigned long long num, unsigned int width) { int len; if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */ goto overflow; - len = strlen(delimiter); - if (m->count + len >= m->size) - goto overflow; + if (delimiter && delimiter[0]) { + if (delimiter[1] == 0) + seq_putc(m, delimiter[0]); + else + seq_puts(m, delimiter); + } - memcpy(m->buf + m->count, delimiter, len); - m->count += len; + if (!width) + width = 1; - if (m->count + 1 >= m->size) + if (m->count + width >= m->size) goto overflow; - if (num < 10) { - m->buf[m->count++] = num + '0'; - return; - } - - len = num_to_str(m->buf + m->count, m->size - m->count, num); + len = num_to_str(m->buf + m->count, m->size - m->count, num, width); if (!len) goto overflow; @@ -713,8 +719,60 @@ void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, overflow: seq_set_overflow(m); } + +void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, + unsigned long long num) +{ + return seq_put_decimal_ull_width(m, delimiter, num, 0); +} EXPORT_SYMBOL(seq_put_decimal_ull); +/** + * seq_put_hex_ll - put a number in hexadecimal notation + * @m: seq_file identifying the buffer to which data should be written + * @delimiter: a string which is printed before the number + * @v: the number + * @width: a minimum field width + * + * seq_put_hex_ll(m, "", v, 8) is equal to seq_printf(m, "%08llx", v) + * + * This routine is very quick when you show lots of numbers. + * In usual cases, it will be better to use seq_printf(). It's easier to read. + */ +void seq_put_hex_ll(struct seq_file *m, const char *delimiter, + unsigned long long v, unsigned int width) +{ + unsigned int len; + int i; + + if (delimiter && delimiter[0]) { + if (delimiter[1] == 0) + seq_putc(m, delimiter[0]); + else + seq_puts(m, delimiter); + } + + /* If x is 0, the result of __builtin_clzll is undefined */ + if (v == 0) + len = 1; + else + len = (sizeof(v) * 8 - __builtin_clzll(v) + 3) / 4; + + if (len < width) + len = width; + + if (m->count + len > m->size) { + seq_set_overflow(m); + return; + } + + for (i = len - 1; i >= 0; i--) { + m->buf[m->count + i] = hex_asc[0xf & v]; + v = v >> 4; + } + m->count += len; +} + void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num) { int len; @@ -722,12 +780,12 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num if (m->count + 3 >= m->size) /* we'll write 2 bytes at least */ goto overflow; - len = strlen(delimiter); - if (m->count + len >= m->size) - goto overflow; - - memcpy(m->buf + m->count, delimiter, len); - m->count += len; + if (delimiter && delimiter[0]) { + if (delimiter[1] == 0) + seq_putc(m, delimiter[0]); + else + seq_puts(m, delimiter); + } if (m->count + 2 >= m->size) goto overflow; @@ -737,12 +795,7 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num num = -num; } - if (num < 10) { - m->buf[m->count++] = num + '0'; - return; - } - - len = num_to_str(m->buf + m->count, m->size - m->count, num); + len = num_to_str(m->buf + m->count, m->size - m->count, num, 0); if (!len) goto overflow; @@ -782,8 +835,14 @@ EXPORT_SYMBOL(seq_write); void seq_pad(struct seq_file *m, char c) { int size = m->pad_until - m->count; - if (size > 0) - seq_printf(m, "%*s", size, ""); + if (size > 0) { + if (size + m->count > m->size) { + seq_set_overflow(m); + return; + } + memset(m->buf + m->count, ' ', size); + m->count += size; + } if (c) seq_putc(m, c); } @@ -1040,3 +1099,8 @@ seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head, return NULL; } EXPORT_SYMBOL(seq_hlist_next_percpu); + +void __init seq_file_init(void) +{ + seq_file_cache = KMEM_CACHE(seq_file, SLAB_ACCOUNT|SLAB_PANIC); +} |