diff options
Diffstat (limited to 'fs')
120 files changed, 3023 insertions, 1634 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 0ad61c6a65a5..055562c580b4 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -33,6 +33,7 @@ #include <linux/pagemap.h> #include <linux/idr.h> #include <linux/sched.h> +#include <linux/aio.h> #include <net/9p/9p.h> #include <net/9p/client.h> diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index c2483e97beee..357260be9244 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -620,6 +620,7 @@ v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) lock_page(page); if (page->mapping != inode->i_mapping) goto out_unlock; + wait_for_stable_page(page); return VM_FAULT_LOCKED; out_unlock: diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index eb82ee53ee0b..d9a43674cb94 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -125,9 +125,8 @@ static void affs_fix_dcache(struct inode *inode, u32 entry_ino) { struct dentry *dentry; - struct hlist_node *p; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { dentry->d_fsdata = (void *)inode->i_ino; break; diff --git a/fs/afs/write.c b/fs/afs/write.c index 9aa52d93c73c..5151ea381c08 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/pagevec.h> +#include <linux/aio.h> #include "internal.h" static int afs_write_back_from_locked_page(struct afs_writeback *wb, @@ -8,6 +8,8 @@ * * See ../COPYING for licensing terms. */ +#define pr_fmt(fmt) "%s: " fmt, __func__ + #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> @@ -18,14 +20,14 @@ #include <linux/backing-dev.h> #include <linux/uio.h> -#define DEBUG 0 - #include <linux/sched.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> +#include <linux/bio.h> #include <linux/mmu_context.h> +#include <linux/percpu.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/aio.h> @@ -35,15 +37,94 @@ #include <linux/eventfd.h> #include <linux/blkdev.h> #include <linux/compat.h> +#include <linux/percpu-refcount.h> #include <asm/kmap_types.h> #include <asm/uaccess.h> -#if DEBUG > 1 -#define dprintk printk -#else -#define dprintk(x...) do { ; } while (0) -#endif +#define AIO_RING_MAGIC 0xa10a10a1 +#define AIO_RING_COMPAT_FEATURES 1 +#define AIO_RING_INCOMPAT_FEATURES 0 +struct aio_ring { + unsigned id; /* kernel internal index number */ + unsigned nr; /* number of io_events */ + unsigned head; + unsigned tail; + + unsigned magic; + unsigned compat_features; + unsigned incompat_features; + unsigned header_length; /* size of aio_ring */ + + + struct io_event io_events[0]; +}; /* 128 bytes + ring size */ + +#define AIO_RING_PAGES 8 + +struct kioctx_cpu { + unsigned reqs_available; +}; + +struct kioctx { + struct percpu_ref users; + + /* This needs improving */ + unsigned long user_id; + struct hlist_node list; + + struct __percpu kioctx_cpu *cpu; + + unsigned req_batch; + + unsigned nr; + + /* sys_io_setup currently limits this to an unsigned int */ + unsigned max_reqs; + + unsigned long mmap_base; + unsigned long mmap_size; + + struct page **ring_pages; + long nr_pages; + + struct rcu_head rcu_head; + struct work_struct rcu_work; + + struct { + atomic_t reqs_available; + } ____cacheline_aligned_in_smp; + + struct { + spinlock_t ctx_lock; + struct list_head active_reqs; /* used for cancellation */ + } ____cacheline_aligned_in_smp; + + struct { + struct mutex ring_lock; + wait_queue_head_t wait; + + /* + * Copy of the real tail, that aio_complete uses - to reduce + * cacheline bouncing. The real tail will tend to be much more + * contended - since typically events are delivered one at a + * time, and then aio_read_events() slurps them up a bunch at a + * time - so it's helpful if aio_read_events() isn't also + * contending for the tail. So, aio_complete() updates + * shadow_tail whenever it updates tail. + * + * Also needed because tail is used as a hacky lock and isn't + * always the real tail. + */ + unsigned shadow_tail; + } ____cacheline_aligned_in_smp; + + struct { + unsigned tail; + } ____cacheline_aligned_in_smp; + + struct page *internal_pages[AIO_RING_PAGES]; +}; /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); @@ -54,11 +135,6 @@ unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio request static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; -static struct workqueue_struct *aio_wq; - -static void aio_kick_handler(struct work_struct *); -static void aio_queue_work(struct kioctx *); - /* aio_setup * Creates the slab caches used by the aio routines, panic on * failure as this is done early during the boot sequence. @@ -68,10 +144,7 @@ static int __init aio_setup(void) kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); - aio_wq = alloc_workqueue("aio", 0, 1); /* used to limit concurrency */ - BUG_ON(!aio_wq); - - pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page)); + pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page)); return 0; } @@ -79,31 +152,29 @@ __initcall(aio_setup); static void aio_free_ring(struct kioctx *ctx) { - struct aio_ring_info *info = &ctx->ring_info; long i; - for (i=0; i<info->nr_pages; i++) - put_page(info->ring_pages[i]); + for (i = 0; i < ctx->nr_pages; i++) + put_page(ctx->ring_pages[i]); - if (info->mmap_size) { - BUG_ON(ctx->mm != current->mm); - vm_munmap(info->mmap_base, info->mmap_size); - } + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); - if (info->ring_pages && info->ring_pages != info->internal_pages) - kfree(info->ring_pages); - info->ring_pages = NULL; - info->nr = 0; + if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) + kfree(ctx->ring_pages); } static int aio_setup_ring(struct kioctx *ctx) { struct aio_ring *ring; - struct aio_ring_info *info = &ctx->ring_info; unsigned nr_events = ctx->max_reqs; - unsigned long size; + struct mm_struct *mm = current->mm; + unsigned long size, populate; int nr_pages; + nr_events = max(nr_events, num_possible_cpus() * 4); + nr_events *= 2; + /* Compensate for the ring buffer's head/tail overlap entry */ nr_events += 2; /* 1 is required, 2 for good luck */ @@ -116,43 +187,44 @@ static int aio_setup_ring(struct kioctx *ctx) nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event); - info->nr = 0; - info->ring_pages = info->internal_pages; + ctx->nr = 0; + ctx->ring_pages = ctx->internal_pages; if (nr_pages > AIO_RING_PAGES) { - info->ring_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); - if (!info->ring_pages) + ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), + GFP_KERNEL); + if (!ctx->ring_pages) return -ENOMEM; } - info->mmap_size = nr_pages * PAGE_SIZE; - dprintk("attempting mmap of %lu bytes\n", info->mmap_size); - down_write(&ctx->mm->mmap_sem); - info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size, - PROT_READ|PROT_WRITE, - MAP_ANONYMOUS|MAP_PRIVATE, 0); - if (IS_ERR((void *)info->mmap_base)) { - up_write(&ctx->mm->mmap_sem); - info->mmap_size = 0; + ctx->mmap_size = nr_pages * PAGE_SIZE; + pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size); + down_write(&mm->mmap_sem); + ctx->mmap_base = do_mmap_pgoff(NULL, 0, ctx->mmap_size, + PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_PRIVATE, 0, &populate); + if (IS_ERR((void *)ctx->mmap_base)) { + up_write(&mm->mmap_sem); + ctx->mmap_size = 0; aio_free_ring(ctx); return -EAGAIN; } - dprintk("mmap address: 0x%08lx\n", info->mmap_base); - info->nr_pages = get_user_pages(current, ctx->mm, - info->mmap_base, nr_pages, - 1, 0, info->ring_pages, NULL); - up_write(&ctx->mm->mmap_sem); + pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); + ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages, + 1, 0, ctx->ring_pages, NULL); + up_write(&mm->mmap_sem); - if (unlikely(info->nr_pages != nr_pages)) { + if (unlikely(ctx->nr_pages != nr_pages)) { aio_free_ring(ctx); return -EAGAIN; } + if (populate) + mm_populate(ctx->mmap_base, populate); - ctx->user_id = info->mmap_base; + ctx->user_id = ctx->mmap_base; + ctx->nr = nr_events; /* trusted copy */ - info->nr = nr_events; /* trusted copy */ - - ring = kmap_atomic(info->ring_pages[0]); + ring = kmap_atomic(ctx->ring_pages[0]); ring->nr = nr_events; /* user copy */ ring->id = ctx->user_id; ring->head = ring->tail = 0; @@ -161,72 +233,142 @@ static int aio_setup_ring(struct kioctx *ctx) ring->incompat_features = AIO_RING_INCOMPAT_FEATURES; ring->header_length = sizeof(struct aio_ring); kunmap_atomic(ring); + flush_dcache_page(ctx->ring_pages[0]); return 0; } - -/* aio_ring_event: returns a pointer to the event at the given index from - * kmap_atomic(). Release the pointer with put_aio_ring_event(); - */ #define AIO_EVENTS_PER_PAGE (PAGE_SIZE / sizeof(struct io_event)) #define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event)) #define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE) -#define aio_ring_event(info, nr) ({ \ - unsigned pos = (nr) + AIO_EVENTS_OFFSET; \ - struct io_event *__event; \ - __event = kmap_atomic( \ - (info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \ - __event += pos % AIO_EVENTS_PER_PAGE; \ - __event; \ -}) - -#define put_aio_ring_event(event) do { \ - struct io_event *__event = (event); \ - (void)__event; \ - kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK)); \ -} while(0) - -static void ctx_rcu_free(struct rcu_head *head) +void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) +{ + struct kioctx *ctx = req->ki_ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->ctx_lock, flags); + + if (!req->ki_list.next) + list_add(&req->ki_list, &ctx->active_reqs); + + req->ki_cancel = cancel; + + spin_unlock_irqrestore(&ctx->ctx_lock, flags); +} +EXPORT_SYMBOL(kiocb_set_cancel_fn); + +static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb, + struct io_event *res) +{ + kiocb_cancel_fn *old, *cancel; + int ret = -EINVAL; + + /* + * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it + * actually has a cancel function, hence the cmpxchg() + */ + + cancel = ACCESS_ONCE(kiocb->ki_cancel); + do { + if (!cancel || cancel == KIOCB_CANCELLED) + return ret; + + old = cancel; + cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED); + } while (cancel != old); + + atomic_inc(&kiocb->ki_users); + spin_unlock_irq(&ctx->ctx_lock); + + memset(res, 0, sizeof(*res)); + res->obj = (u64)(unsigned long)kiocb->ki_obj.user; + res->data = kiocb->ki_user_data; + ret = cancel(kiocb, res); + + spin_lock_irq(&ctx->ctx_lock); + + return ret; +} + +static void free_ioctx_rcu(struct rcu_head *head) { struct kioctx *ctx = container_of(head, struct kioctx, rcu_head); + + free_percpu(ctx->cpu); kmem_cache_free(kioctx_cachep, ctx); } -/* __put_ioctx - * Called when the last user of an aio context has gone away, - * and the struct needs to be freed. +/* + * When this function runs, the kioctx has been removed from the "hash table" + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. */ -static void __put_ioctx(struct kioctx *ctx) +static void free_ioctx(struct kioctx *ctx) { - unsigned nr_events = ctx->max_reqs; - BUG_ON(ctx->reqs_active); + struct aio_ring *ring; + struct io_event res; + struct kiocb *req; + unsigned cpu, head, avail; - cancel_delayed_work_sync(&ctx->wq); - aio_free_ring(ctx); - mmdrop(ctx->mm); - ctx->mm = NULL; - if (nr_events) { - spin_lock(&aio_nr_lock); - BUG_ON(aio_nr - nr_events > aio_nr); - aio_nr -= nr_events; - spin_unlock(&aio_nr_lock); + spin_lock_irq(&ctx->ctx_lock); + + while (!list_empty(&ctx->active_reqs)) { + req = list_first_entry(&ctx->active_reqs, + struct kiocb, ki_list); + + list_del_init(&req->ki_list); + kiocb_cancel(ctx, req, &res); } - pr_debug("__put_ioctx: freeing %p\n", ctx); - call_rcu(&ctx->rcu_head, ctx_rcu_free); -} -static inline int try_get_ioctx(struct kioctx *kioctx) -{ - return atomic_inc_not_zero(&kioctx->users); + spin_unlock_irq(&ctx->ctx_lock); + + for_each_possible_cpu(cpu) { + struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu); + + atomic_add(kcpu->reqs_available, &ctx->reqs_available); + kcpu->reqs_available = 0; + } + + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; + kunmap_atomic(ring); + + while (atomic_read(&ctx->reqs_available) < ctx->nr) { + wait_event(ctx->wait, head != ctx->shadow_tail); + + avail = (head < ctx->shadow_tail ? ctx->shadow_tail : ctx->nr) - head; + + atomic_add(avail, &ctx->reqs_available); + head += avail; + head %= ctx->nr; + } + + WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr); + + aio_free_ring(ctx); + + spin_lock(&aio_nr_lock); + BUG_ON(aio_nr - ctx->max_reqs > aio_nr); + aio_nr -= ctx->max_reqs; + spin_unlock(&aio_nr_lock); + + pr_debug("freeing %p\n", ctx); + + /* + * Here the call_rcu() is between the wait_event() for reqs_active to + * hit 0, and freeing the ioctx. + * + * aio_complete() decrements reqs_active, but it has to touch the ioctx + * after to issue a wakeup so we use rcu. + */ + call_rcu(&ctx->rcu_head, free_ioctx_rcu); } -static inline void put_ioctx(struct kioctx *kioctx) +static void put_ioctx(struct kioctx *ctx) { - BUG_ON(atomic_read(&kioctx->users) <= 0); - if (unlikely(atomic_dec_and_test(&kioctx->users))) - __put_ioctx(kioctx); + if (percpu_ref_put(&ctx->users)) + free_ioctx(ctx); } /* ioctx_alloc @@ -234,7 +376,7 @@ static inline void put_ioctx(struct kioctx *kioctx) */ static struct kioctx *ioctx_alloc(unsigned nr_events) { - struct mm_struct *mm; + struct mm_struct *mm = current->mm; struct kioctx *ctx; int err = -ENOMEM; @@ -253,21 +395,29 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) return ERR_PTR(-ENOMEM); ctx->max_reqs = nr_events; - mm = ctx->mm = current->mm; - atomic_inc(&mm->mm_count); - atomic_set(&ctx->users, 2); + percpu_ref_init(&ctx->users); + rcu_read_lock(); + percpu_ref_get(&ctx->users); + rcu_read_unlock(); + spin_lock_init(&ctx->ctx_lock); - spin_lock_init(&ctx->ring_info.ring_lock); + mutex_init(&ctx->ring_lock); init_waitqueue_head(&ctx->wait); INIT_LIST_HEAD(&ctx->active_reqs); - INIT_LIST_HEAD(&ctx->run_list); - INIT_DELAYED_WORK(&ctx->wq, aio_kick_handler); - if (aio_setup_ring(ctx) < 0) + ctx->cpu = alloc_percpu(struct kioctx_cpu); + if (!ctx->cpu) goto out_freectx; + if (aio_setup_ring(ctx) < 0) + goto out_freepcpu; + + atomic_set(&ctx->reqs_available, ctx->nr); + ctx->req_batch = ctx->nr / (num_possible_cpus() * 4); + BUG_ON(!ctx->req_batch); + /* limit the number of system wide aios */ spin_lock(&aio_nr_lock); if (aio_nr + nr_events > aio_max_nr || @@ -283,64 +433,58 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) hlist_add_head_rcu(&ctx->list, &mm->ioctx_list); spin_unlock(&mm->ioctx_lock); - dprintk("aio: allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", - ctx, ctx->user_id, current->mm, ctx->ring_info.nr); + pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", + ctx, ctx->user_id, mm, ctx->nr); return ctx; out_cleanup: err = -EAGAIN; aio_free_ring(ctx); +out_freepcpu: + free_percpu(ctx->cpu); out_freectx: - mmdrop(mm); kmem_cache_free(kioctx_cachep, ctx); - dprintk("aio: error allocating ioctx %d\n", err); + pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); } -/* kill_ctx - * Cancels all outstanding aio requests on an aio context. Used - * when the processes owning a context have all exited to encourage - * the rapid destruction of the kioctx. - */ -static void kill_ctx(struct kioctx *ctx) +static void kill_ioctx_work(struct work_struct *work) { - int (*cancel)(struct kiocb *, struct io_event *); - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - struct io_event res; + struct kioctx *ctx = container_of(work, struct kioctx, rcu_work); - spin_lock_irq(&ctx->ctx_lock); - ctx->dead = 1; - while (!list_empty(&ctx->active_reqs)) { - struct list_head *pos = ctx->active_reqs.next; - struct kiocb *iocb = list_kiocb(pos); - list_del_init(&iocb->ki_list); - cancel = iocb->ki_cancel; - kiocbSetCancelled(iocb); - if (cancel) { - iocb->ki_users++; - spin_unlock_irq(&ctx->ctx_lock); - cancel(iocb, &res); - spin_lock_irq(&ctx->ctx_lock); - } - } + wake_up_all(&ctx->wait); + put_ioctx(ctx); +} - if (!ctx->reqs_active) - goto out; +static void kill_ioctx_rcu(struct rcu_head *head) +{ + struct kioctx *ctx = container_of(head, struct kioctx, rcu_head); - add_wait_queue(&ctx->wait, &wait); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); - while (ctx->reqs_active) { - spin_unlock_irq(&ctx->ctx_lock); - io_schedule(); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); - spin_lock_irq(&ctx->ctx_lock); - } - __set_task_state(tsk, TASK_RUNNING); - remove_wait_queue(&ctx->wait, &wait); + INIT_WORK(&ctx->rcu_work, kill_ioctx_work); + schedule_work(&ctx->rcu_work); +} -out: - spin_unlock_irq(&ctx->ctx_lock); +/* kill_ioctx + * Cancels all outstanding aio requests on an aio context. Used + * when the processes owning a context have all exited to encourage + * the rapid destruction of the kioctx. + */ +static void kill_ioctx(struct kioctx *ctx) +{ + if (percpu_ref_kill(&ctx->users)) { + hlist_del_rcu(&ctx->list); + /* Between hlist_del_rcu() and dropping the initial ref */ + synchronize_rcu(); + + /* + * We can't punt to workqueue here because put_ioctx() -> + * free_ioctx() will unmap the ringbuffer, and that has to be + * done in the original process's context. kill_ioctx_rcu/work() + * exist for exit_aio(), as in that path free_ioctx() won't do + * the unmap. + */ + kill_ioctx_work(&ctx->rcu_work); + } } /* wait_on_sync_kiocb: @@ -348,9 +492,9 @@ out: */ ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { - while (iocb->ki_users) { + while (atomic_read(&iocb->ki_users)) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!iocb->ki_users) + if (!atomic_read(&iocb->ki_users)) break; io_schedule(); } @@ -359,28 +503,20 @@ ssize_t wait_on_sync_kiocb(struct kiocb *iocb) } EXPORT_SYMBOL(wait_on_sync_kiocb); -/* exit_aio: called when the last user of mm goes away. At this point, - * there is no way for any new requests to be submited or any of the - * io_* syscalls to be called on the context. However, there may be - * outstanding requests which hold references to the context; as they - * go away, they will call put_ioctx and release any pinned memory - * associated with the request (held via struct page * references). +/* + * exit_aio: called when the last user of mm goes away. At this point, there is + * no way for any new requests to be submited or any of the io_* syscalls to be + * called on the context. + * + * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on + * them. */ void exit_aio(struct mm_struct *mm) { struct kioctx *ctx; + struct hlist_node *n; - while (!hlist_empty(&mm->ioctx_list)) { - ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list); - hlist_del_rcu(&ctx->list); - - kill_ctx(ctx); - - if (1 != atomic_read(&ctx->users)) - printk(KERN_DEBUG - "exit_aio:ioctx still alive: %d %d %d\n", - atomic_read(&ctx->users), ctx->dead, - ctx->reqs_active); + hlist_for_each_entry_safe(ctx, n, &mm->ioctx_list, list) { /* * We don't need to bother with munmap() here - * exit_mmap(mm) is coming and it'll unmap everything. @@ -388,150 +524,95 @@ void exit_aio(struct mm_struct *mm) * as indicator that it needs to unmap the area, * just set it to 0; aio_free_ring() is the only * place that uses ->mmap_size, so it's safe. - * That way we get all munmap done to current->mm - - * all other callers have ctx->mm == current->mm. */ - ctx->ring_info.mmap_size = 0; - put_ioctx(ctx); + ctx->mmap_size = 0; + + if (percpu_ref_kill(&ctx->users)) { + hlist_del_rcu(&ctx->list); + call_rcu(&ctx->rcu_head, kill_ioctx_rcu); + } } } -/* aio_get_req - * Allocate a slot for an aio request. Increments the users count - * of the kioctx so that the kioctx stays around until all requests are - * complete. Returns NULL if no requests are free. - * - * Returns with kiocb->users set to 2. The io submit code path holds - * an extra reference while submitting the i/o. - * This prevents races between the aio code path referencing the - * req (after submitting it) and aio_complete() freeing the req. - */ -static struct kiocb *__aio_get_req(struct kioctx *ctx) +static void put_reqs_available(struct kioctx *ctx, unsigned nr) { - struct kiocb *req = NULL; - - req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL); - if (unlikely(!req)) - return NULL; + struct kioctx_cpu *kcpu; - req->ki_flags = 0; - req->ki_users = 2; - req->ki_key = 0; - req->ki_ctx = ctx; - req->ki_cancel = NULL; - req->ki_retry = NULL; - req->ki_dtor = NULL; - req->private = NULL; - req->ki_iovec = NULL; - INIT_LIST_HEAD(&req->ki_run_list); - req->ki_eventfd = NULL; - - return req; -} + preempt_disable(); + kcpu = this_cpu_ptr(ctx->cpu); -/* - * struct kiocb's are allocated in batches to reduce the number of - * times the ctx lock is acquired and released. - */ -#define KIOCB_BATCH_SIZE 32L -struct kiocb_batch { - struct list_head head; - long count; /* number of requests left to allocate */ -}; + kcpu->reqs_available += nr; + while (kcpu->reqs_available >= ctx->req_batch * 2) { + kcpu->reqs_available -= ctx->req_batch; + atomic_add(ctx->req_batch, &ctx->reqs_available); + } -static void kiocb_batch_init(struct kiocb_batch *batch, long total) -{ - INIT_LIST_HEAD(&batch->head); - batch->count = total; + preempt_enable(); } -static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch) +static bool get_reqs_available(struct kioctx *ctx) { - struct kiocb *req, *n; + struct kioctx_cpu *kcpu; + bool ret = false; - if (list_empty(&batch->head)) - return; + preempt_disable(); + kcpu = this_cpu_ptr(ctx->cpu); - spin_lock_irq(&ctx->ctx_lock); - list_for_each_entry_safe(req, n, &batch->head, ki_batch) { - list_del(&req->ki_batch); - list_del(&req->ki_list); - kmem_cache_free(kiocb_cachep, req); - ctx->reqs_active--; - } - if (unlikely(!ctx->reqs_active && ctx->dead)) - wake_up_all(&ctx->wait); - spin_unlock_irq(&ctx->ctx_lock); -} - -/* - * Allocate a batch of kiocbs. This avoids taking and dropping the - * context lock a lot during setup. - */ -static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch) -{ - unsigned short allocated, to_alloc; - long avail; - struct kiocb *req, *n; - struct aio_ring *ring; + if (!kcpu->reqs_available) { + int old, avail = atomic_read(&ctx->reqs_available); - to_alloc = min(batch->count, KIOCB_BATCH_SIZE); - for (allocated = 0; allocated < to_alloc; allocated++) { - req = __aio_get_req(ctx); - if (!req) - /* allocation failed, go with what we've got */ - break; - list_add(&req->ki_batch, &batch->head); - } + do { + if (avail < ctx->req_batch) + goto out; - if (allocated == 0) - goto out; + old = avail; + avail = atomic_cmpxchg(&ctx->reqs_available, + avail, avail - ctx->req_batch); + } while (avail != old); - spin_lock_irq(&ctx->ctx_lock); - ring = kmap_atomic(ctx->ring_info.ring_pages[0]); - - avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active; - BUG_ON(avail < 0); - if (avail < allocated) { - /* Trim back the number of requests. */ - list_for_each_entry_safe(req, n, &batch->head, ki_batch) { - list_del(&req->ki_batch); - kmem_cache_free(kiocb_cachep, req); - if (--allocated <= avail) - break; - } + kcpu->reqs_available += ctx->req_batch; } - batch->count -= allocated; - list_for_each_entry(req, &batch->head, ki_batch) { - list_add(&req->ki_list, &ctx->active_reqs); - ctx->reqs_active++; - } - - kunmap_atomic(ring); - spin_unlock_irq(&ctx->ctx_lock); - + ret = true; + kcpu->reqs_available--; out: - return allocated; + preempt_enable(); + return ret; } -static inline struct kiocb *aio_get_req(struct kioctx *ctx, - struct kiocb_batch *batch) +/* aio_get_req + * Allocate a slot for an aio request. Increments the ki_users count + * of the kioctx so that the kioctx stays around until all requests are + * complete. Returns NULL if no requests are free. + * + * Returns with kiocb->ki_users set to 2. The io submit code path holds + * an extra reference while submitting the i/o. + * This prevents races between the aio code path referencing the + * req (after submitting it) and aio_complete() freeing the req. + */ +static inline struct kiocb *aio_get_req(struct kioctx *ctx) { struct kiocb *req; - if (list_empty(&batch->head)) - if (kiocb_batch_refill(ctx, batch) == 0) - return NULL; - req = list_first_entry(&batch->head, struct kiocb, ki_batch); - list_del(&req->ki_batch); + if (!get_reqs_available(ctx)) + return NULL; + + req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO); + if (unlikely(!req)) + goto out_put; + + atomic_set(&req->ki_users, 2); + req->ki_ctx = ctx; return req; +out_put: + put_reqs_available(ctx, 1); + return NULL; } -static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) +static void kiocb_free(struct kiocb *req) { - assert_spin_locked(&ctx->ctx_lock); - + if (req->ki_filp) + fput(req->ki_filp); if (req->ki_eventfd != NULL) eventfd_ctx_put(req->ki_eventfd); if (req->ki_dtor) @@ -539,48 +620,12 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) if (req->ki_iovec != &req->ki_inline_vec) kfree(req->ki_iovec); kmem_cache_free(kiocb_cachep, req); - ctx->reqs_active--; - - if (unlikely(!ctx->reqs_active && ctx->dead)) - wake_up_all(&ctx->wait); } -/* __aio_put_req - * Returns true if this put was the last user of the request. - */ -static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) +void aio_put_req(struct kiocb *req) { - dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n", - req, atomic_long_read(&req->ki_filp->f_count)); - - assert_spin_locked(&ctx->ctx_lock); - - req->ki_users--; - BUG_ON(req->ki_users < 0); - if (likely(req->ki_users)) - return 0; - list_del(&req->ki_list); /* remove from active_reqs */ - req->ki_cancel = NULL; - req->ki_retry = NULL; - - fput(req->ki_filp); - req->ki_filp = NULL; - really_put_req(ctx, req); - return 1; -} - -/* aio_put_req - * Returns true if this put was the last user of the kiocb, - * false if the request is still in use. - */ -int aio_put_req(struct kiocb *req) -{ - struct kioctx *ctx = req->ki_ctx; - int ret; - spin_lock_irq(&ctx->ctx_lock); - ret = __aio_put_req(ctx, req); - spin_unlock_irq(&ctx->ctx_lock); - return ret; + if (atomic_dec_and_test(&req->ki_users)) + kiocb_free(req); } EXPORT_SYMBOL(aio_put_req); @@ -588,631 +633,355 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) { struct mm_struct *mm = current->mm; struct kioctx *ctx, *ret = NULL; - struct hlist_node *n; rcu_read_lock(); - hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) { - /* - * RCU protects us against accessing freed memory but - * we have to be careful not to get a reference when the - * reference count already dropped to 0 (ctx->dead test - * is unreliable because of races). - */ - if (ctx->user_id == ctx_id && !ctx->dead && try_get_ioctx(ctx)){ + hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) + if (ctx->user_id == ctx_id){ + percpu_ref_get(&ctx->users); ret = ctx; break; } - } rcu_read_unlock(); return ret; } -/* - * Queue up a kiocb to be retried. Assumes that the kiocb - * has already been marked as kicked, and places it on - * the retry run list for the corresponding ioctx, if it - * isn't already queued. Returns 1 if it actually queued - * the kiocb (to tell the caller to activate the work - * queue to process it), or 0, if it found that it was - * already queued. - */ -static inline int __queue_kicked_iocb(struct kiocb *iocb) +static inline unsigned kioctx_ring_put(struct kioctx *ctx, struct kiocb *req, + unsigned tail) { - struct kioctx *ctx = iocb->ki_ctx; - - assert_spin_locked(&ctx->ctx_lock); + struct io_event *ev_page, *event; + unsigned pos = tail + AIO_EVENTS_OFFSET; - if (list_empty(&iocb->ki_run_list)) { - list_add_tail(&iocb->ki_run_list, - &ctx->run_list); - return 1; - } - return 0; -} + if (++tail >= ctx->nr) + tail = 0; -/* aio_run_iocb - * This is the core aio execution routine. It is - * invoked both for initial i/o submission and - * subsequent retries via the aio_kick_handler. - * Expects to be invoked with iocb->ki_ctx->lock - * already held. The lock is released and reacquired - * as needed during processing. - * - * Calls the iocb retry method (already setup for the - * iocb on initial submission) for operation specific - * handling, but takes care of most of common retry - * execution details for a given iocb. The retry method - * needs to be non-blocking as far as possible, to avoid - * holding up other iocbs waiting to be serviced by the - * retry kernel thread. - * - * The trickier parts in this code have to do with - * ensuring that only one retry instance is in progress - * for a given iocb at any time. Providing that guarantee - * simplifies the coding of individual aio operations as - * it avoids various potential races. - */ -static ssize_t aio_run_iocb(struct kiocb *iocb) -{ - struct kioctx *ctx = iocb->ki_ctx; - ssize_t (*retry)(struct kiocb *); - ssize_t ret; + ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); + event = ev_page + pos % AIO_EVENTS_PER_PAGE; - if (!(retry = iocb->ki_retry)) { - printk("aio_run_iocb: iocb->ki_retry = NULL\n"); - return 0; - } + event->obj = (u64)(unsigned long)req->ki_obj.user; + event->data = req->ki_user_data; + event->res = req->ki_res; + event->res2 = req->ki_res2; - /* - * We don't want the next retry iteration for this - * operation to start until this one has returned and - * updated the iocb state. However, wait_queue functions - * can trigger a kick_iocb from interrupt context in the - * meantime, indicating that data is available for the next - * iteration. We want to remember that and enable the - * next retry iteration _after_ we are through with - * this one. - * - * So, in order to be able to register a "kick", but - * prevent it from being queued now, we clear the kick - * flag, but make the kick code *think* that the iocb is - * still on the run list until we are actually done. - * When we are done with this iteration, we check if - * the iocb was kicked in the meantime and if so, queue - * it up afresh. - */ + kunmap_atomic(ev_page); + flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); - kiocbClearKicked(iocb); + pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", + ctx, tail, req, req->ki_obj.user, req->ki_user_data, + req->ki_res, req->ki_res2); - /* - * This is so that aio_complete knows it doesn't need to - * pull the iocb off the run list (We can't just call - * INIT_LIST_HEAD because we don't want a kick_iocb to - * queue this on the run list yet) - */ - iocb->ki_run_list.next = iocb->ki_run_list.prev = NULL; - spin_unlock_irq(&ctx->ctx_lock); + return tail; +} - /* Quit retrying if the i/o has been cancelled */ - if (kiocbIsCancelled(iocb)) { - ret = -EINTR; - aio_complete(iocb, ret, 0); - /* must not access the iocb after this */ - goto out; - } +static inline unsigned kioctx_ring_lock(struct kioctx *ctx) +{ + unsigned tail; /* - * Now we are all set to call the retry method in async - * context. + * ctx->tail is both our lock and the canonical version of the tail + * pointer. */ - ret = retry(iocb); - - if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) { - /* - * There's no easy way to restart the syscall since other AIO's - * may be already running. Just fail this IO with EINTR. - */ - if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || - ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK)) - ret = -EINTR; - aio_complete(iocb, ret, 0); - } -out: - spin_lock_irq(&ctx->ctx_lock); - - if (-EIOCBRETRY == ret) { - /* - * OK, now that we are done with this iteration - * and know that there is more left to go, - * this is where we let go so that a subsequent - * "kick" can start the next iteration - */ - - /* will make __queue_kicked_iocb succeed from here on */ - INIT_LIST_HEAD(&iocb->ki_run_list); - /* we must queue the next iteration ourselves, if it - * has already been kicked */ - if (kiocbIsKicked(iocb)) { - __queue_kicked_iocb(iocb); + while ((tail = xchg(&ctx->tail, UINT_MAX)) == UINT_MAX) + cpu_relax(); - /* - * __queue_kicked_iocb will always return 1 here, because - * iocb->ki_run_list is empty at this point so it should - * be safe to unconditionally queue the context into the - * work queue. - */ - aio_queue_work(ctx); - } - } - return ret; + return tail; } -/* - * __aio_run_iocbs: - * Process all pending retries queued on the ioctx - * run list. - * Assumes it is operating within the aio issuer's mm - * context. - */ -static int __aio_run_iocbs(struct kioctx *ctx) +static inline void kioctx_ring_unlock(struct kioctx *ctx, unsigned tail) { - struct kiocb *iocb; - struct list_head run_list; + struct aio_ring *ring; - assert_spin_locked(&ctx->ctx_lock); + if (!ctx) + return; - list_replace_init(&ctx->run_list, &run_list); - while (!list_empty(&run_list)) { - iocb = list_entry(run_list.next, struct kiocb, - ki_run_list); - list_del(&iocb->ki_run_list); - /* - * Hold an extra reference while retrying i/o. - */ - iocb->ki_users++; /* grab extra reference */ - aio_run_iocb(iocb); - __aio_put_req(ctx, iocb); - } - if (!list_empty(&ctx->run_list)) - return 1; - return 0; -} + smp_wmb(); + /* make event visible before updating tail */ -static void aio_queue_work(struct kioctx * ctx) -{ - unsigned long timeout; - /* - * if someone is waiting, get the work started right - * away, otherwise, use a longer delay - */ - smp_mb(); - if (waitqueue_active(&ctx->wait)) - timeout = 1; - else - timeout = HZ/10; - queue_delayed_work(aio_wq, &ctx->wq, timeout); -} + ctx->shadow_tail = tail; -/* - * aio_run_all_iocbs: - * Process all pending retries queued on the ioctx - * run list, and keep running them until the list - * stays empty. - * Assumes it is operating within the aio issuer's mm context. - */ -static inline void aio_run_all_iocbs(struct kioctx *ctx) -{ - spin_lock_irq(&ctx->ctx_lock); - while (__aio_run_iocbs(ctx)) - ; - spin_unlock_irq(&ctx->ctx_lock); -} + ring = kmap_atomic(ctx->ring_pages[0]); + ring->tail = tail; + kunmap_atomic(ring); + flush_dcache_page(ctx->ring_pages[0]); -/* - * aio_kick_handler: - * Work queue handler triggered to process pending - * retries on an ioctx. Takes on the aio issuer's - * mm context before running the iocbs, so that - * copy_xxx_user operates on the issuer's address - * space. - * Run on aiod's context. - */ -static void aio_kick_handler(struct work_struct *work) -{ - struct kioctx *ctx = container_of(work, struct kioctx, wq.work); - mm_segment_t oldfs = get_fs(); - struct mm_struct *mm; - int requeue; + /* unlock, make new tail visible before checking waitlist */ + smp_mb(); - set_fs(USER_DS); - use_mm(ctx->mm); - spin_lock_irq(&ctx->ctx_lock); - requeue =__aio_run_iocbs(ctx); - mm = ctx->mm; - spin_unlock_irq(&ctx->ctx_lock); - unuse_mm(mm); - set_fs(oldfs); - /* - * we're in a worker thread already; no point using non-zero delay - */ - if (requeue) - queue_delayed_work(aio_wq, &ctx->wq, 0); -} + ctx->tail = tail; + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); +} -/* - * Called by kick_iocb to queue the kiocb for retry - * and if required activate the aio work queue to process - * it - */ -static void try_queue_kicked_iocb(struct kiocb *iocb) +void batch_complete_aio(struct batch_complete *batch) { - struct kioctx *ctx = iocb->ki_ctx; + struct kioctx *ctx = NULL; + struct eventfd_ctx *eventfd = NULL; + struct rb_node *n; unsigned long flags; - int run = 0; - - spin_lock_irqsave(&ctx->ctx_lock, flags); - /* set this inside the lock so that we can't race with aio_run_iocb() - * testing it and putting the iocb on the run list under the lock */ - if (!kiocbTryKick(iocb)) - run = __queue_kicked_iocb(iocb); - spin_unlock_irqrestore(&ctx->ctx_lock, flags); - if (run) - aio_queue_work(ctx); -} + unsigned tail = 0; -/* - * kick_iocb: - * Called typically from a wait queue callback context - * to trigger a retry of the iocb. - * The retry is usually executed by aio workqueue - * threads (See aio_kick_handler). - */ -void kick_iocb(struct kiocb *iocb) -{ - /* sync iocbs are easy: they can only ever be executing from a - * single context. */ - if (is_sync_kiocb(iocb)) { - kiocbSetKicked(iocb); - wake_up_process(iocb->ki_obj.tsk); + if (RB_EMPTY_ROOT(&batch->kiocb)) return; - } - - try_queue_kicked_iocb(iocb); -} -EXPORT_SYMBOL(kick_iocb); - -/* aio_complete - * Called when the io request on the given iocb is complete. - * Returns true if this is the last user of the request. The - * only other user of the request can be the cancellation code. - */ -int aio_complete(struct kiocb *iocb, long res, long res2) -{ - struct kioctx *ctx = iocb->ki_ctx; - struct aio_ring_info *info; - struct aio_ring *ring; - struct io_event *event; - unsigned long flags; - unsigned long tail; - int ret; /* - * Special case handling for sync iocbs: - * - events go directly into the iocb for fast handling - * - the sync task with the iocb in its stack holds the single iocb - * ref, no other paths have a way to get another ref - * - the sync task helpfully left a reference to itself in the iocb + * Take rcu_read_lock() in case the kioctx is being destroyed, as we + * need to issue a wakeup after incrementing reqs_available. */ - if (is_sync_kiocb(iocb)) { - BUG_ON(iocb->ki_users != 1); - iocb->ki_user_data = res; - iocb->ki_users = 0; - wake_up_process(iocb->ki_obj.tsk); - return 1; - } - - info = &ctx->ring_info; + rcu_read_lock(); + local_irq_save(flags); - /* add a completion event to the ring buffer. - * must be done holding ctx->ctx_lock to prevent - * other code from messing with the tail - * pointer since we might be called from irq - * context. - */ - spin_lock_irqsave(&ctx->ctx_lock, flags); + n = rb_first(&batch->kiocb); + while (n) { + struct kiocb *req = container_of(n, struct kiocb, ki_node); - if (iocb->ki_run_list.prev && !list_empty(&iocb->ki_run_list)) - list_del_init(&iocb->ki_run_list); + if (n->rb_right) { + n->rb_right->__rb_parent_color = n->__rb_parent_color; + n = n->rb_right; - /* - * cancelled requests don't get events, userland was given one - * when the event got cancelled. - */ - if (kiocbIsCancelled(iocb)) - goto put_rq; + while (n->rb_left) + n = n->rb_left; + } else { + n = rb_parent(n); + } - ring = kmap_atomic(info->ring_pages[0]); + if (unlikely(xchg(&req->ki_cancel, + KIOCB_CANCELLED) == KIOCB_CANCELLED)) { + /* + * Can't use the percpu reqs_available here - could race + * with free_ioctx() + */ + atomic_inc(&req->ki_ctx->reqs_available); + aio_put_req(req); + continue; + } - tail = info->tail; - event = aio_ring_event(info, tail); - if (++tail >= info->nr) - tail = 0; + if (unlikely(req->ki_eventfd != eventfd)) { + if (eventfd) { + /* Make event visible */ + kioctx_ring_unlock(ctx, tail); + ctx = NULL; - event->obj = (u64)(unsigned long)iocb->ki_obj.user; - event->data = iocb->ki_user_data; - event->res = res; - event->res2 = res2; + eventfd_signal(eventfd, 1); + eventfd_ctx_put(eventfd); + } - dprintk("aio_complete: %p[%lu]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data, - res, res2); + eventfd = req->ki_eventfd; + req->ki_eventfd = NULL; + } - /* after flagging the request as done, we - * must never even look at it again - */ - smp_wmb(); /* make event visible before updating tail */ + if (unlikely(req->ki_ctx != ctx)) { + kioctx_ring_unlock(ctx, tail); - info->tail = tail; - ring->tail = tail; + ctx = req->ki_ctx; + tail = kioctx_ring_lock(ctx); + } - put_aio_ring_event(event); - kunmap_atomic(ring); + tail = kioctx_ring_put(ctx, req, tail); + aio_put_req(req); + } - pr_debug("added to ring %p at [%lu]\n", iocb, tail); + kioctx_ring_unlock(ctx, tail); + local_irq_restore(flags); + rcu_read_unlock(); /* * Check if the user asked us to deliver the result through an * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ - if (iocb->ki_eventfd != NULL) - eventfd_signal(iocb->ki_eventfd, 1); + if (eventfd) { + eventfd_signal(eventfd, 1); + eventfd_ctx_put(eventfd); + } +} +EXPORT_SYMBOL(batch_complete_aio); + +/* aio_complete_batch + * Called when the io request on the given iocb is complete; @batch may be + * NULL. + */ +void aio_complete_batch(struct kiocb *req, long res, long res2, + struct batch_complete *batch) +{ + req->ki_res = res; + req->ki_res2 = res2; -put_rq: - /* everything turned out well, dispose of the aiocb. */ - ret = __aio_put_req(ctx, iocb); + if (req->ki_list.next) { + struct kioctx *ctx = req->ki_ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->ctx_lock, flags); + list_del(&req->ki_list); + spin_unlock_irqrestore(&ctx->ctx_lock, flags); + } /* - * We have to order our ring_info tail store above and test - * of the wait list below outside the wait lock. This is - * like in wake_up_bit() where clearing a bit has to be - * ordered with the unlocked test. + * Special case handling for sync iocbs: + * - events go directly into the iocb for fast handling + * - the sync task with the iocb in its stack holds the single iocb + * ref, no other paths have a way to get another ref + * - the sync task helpfully left a reference to itself in the iocb */ - smp_mb(); + if (is_sync_kiocb(req)) { + BUG_ON(atomic_read(&req->ki_users) != 1); + req->ki_user_data = req->ki_res; + atomic_set(&req->ki_users, 0); + wake_up_process(req->ki_obj.tsk); + } else if (batch) { + int res; + struct kiocb *t; + struct rb_node **n = &batch->kiocb.rb_node, *parent = NULL; + + while (*n) { + parent = *n; + t = container_of(*n, struct kiocb, ki_node); + + res = req->ki_ctx != t->ki_ctx + ? req->ki_ctx < t->ki_ctx + : req->ki_eventfd != t->ki_eventfd + ? req->ki_eventfd < t->ki_eventfd + : req < t; + + n = res ? &(*n)->rb_left : &(*n)->rb_right; + } - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); + rb_link_node(&req->ki_node, parent, n); + rb_insert_color(&req->ki_node, &batch->kiocb); + } else { + struct batch_complete batch_stack; - spin_unlock_irqrestore(&ctx->ctx_lock, flags); - return ret; + memset(&req->ki_node, 0, sizeof(req->ki_node)); + batch_stack.kiocb.rb_node = &req->ki_node; + + batch_complete_aio(&batch_stack); + } } -EXPORT_SYMBOL(aio_complete); +EXPORT_SYMBOL(aio_complete_batch); -/* aio_read_evt - * Pull an event off of the ioctx's event ring. Returns the number of - * events fetched (0 or 1 ;-) - * FIXME: make this use cmpxchg. - * TODO: make the ringbuffer user mmap()able (requires FIXME). +/* aio_read_events + * Pull an event off of the ioctx's event ring. Returns the number of + * events fetched */ -static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent) +static long aio_read_events_ring(struct kioctx *ctx, + struct io_event __user *event, long nr) { - struct aio_ring_info *info = &ioctx->ring_info; struct aio_ring *ring; - unsigned long head; - int ret = 0; - - ring = kmap_atomic(info->ring_pages[0]); - dprintk("in aio_read_evt h%lu t%lu m%lu\n", - (unsigned long)ring->head, (unsigned long)ring->tail, - (unsigned long)ring->nr); + unsigned head, pos; + long ret = 0; + int copy_ret; - if (ring->head == ring->tail) - goto out; + mutex_lock(&ctx->ring_lock); - spin_lock(&info->ring_lock); - - head = ring->head % info->nr; - if (head != ring->tail) { - struct io_event *evp = aio_ring_event(info, head); - *ent = *evp; - head = (head + 1) % info->nr; - smp_mb(); /* finish reading the event before updatng the head */ - ring->head = head; - ret = 1; - put_aio_ring_event(evp); - } - spin_unlock(&info->ring_lock); - -out: + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; kunmap_atomic(ring); - dprintk("leaving aio_read_evt: %d h%lu t%lu\n", ret, - (unsigned long)ring->head, (unsigned long)ring->tail); - return ret; -} -struct aio_timeout { - struct timer_list timer; - int timed_out; - struct task_struct *p; -}; - -static void timeout_func(unsigned long data) -{ - struct aio_timeout *to = (struct aio_timeout *)data; + pr_debug("h%u t%u m%u\n", head, ctx->shadow_tail, ctx->nr); - to->timed_out = 1; - wake_up_process(to->p); -} + if (head == ctx->shadow_tail) + goto out; -static inline void init_timeout(struct aio_timeout *to) -{ - setup_timer_on_stack(&to->timer, timeout_func, (unsigned long) to); - to->timed_out = 0; - to->p = current; -} + while (ret < nr) { + long avail = (head < ctx->shadow_tail + ? ctx->shadow_tail : ctx->nr) - head; + struct io_event *ev; + struct page *page; -static inline void set_timeout(long start_jiffies, struct aio_timeout *to, - const struct timespec *ts) -{ - to->timer.expires = start_jiffies + timespec_to_jiffies(ts); - if (time_after(to->timer.expires, jiffies)) - add_timer(&to->timer); - else - to->timed_out = 1; -} + if (head == ctx->shadow_tail) + break; -static inline void clear_timeout(struct aio_timeout *to) -{ - del_singleshot_timer_sync(&to->timer); -} + avail = min(avail, nr - ret); + avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - + ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE)); -static int read_events(struct kioctx *ctx, - long min_nr, long nr, - struct io_event __user *event, - struct timespec __user *timeout) -{ - long start_jiffies = jiffies; - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - int ret; - int i = 0; - struct io_event ent; - struct aio_timeout to; - int retry = 0; - - /* needed to zero any padding within an entry (there shouldn't be - * any, but C is fun! - */ - memset(&ent, 0, sizeof(ent)); -retry: - ret = 0; - while (likely(i < nr)) { - ret = aio_read_evt(ctx, &ent); - if (unlikely(ret <= 0)) - break; + pos = head + AIO_EVENTS_OFFSET; + page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]; + pos %= AIO_EVENTS_PER_PAGE; - dprintk("read event: %Lx %Lx %Lx %Lx\n", - ent.data, ent.obj, ent.res, ent.res2); + ev = kmap(page); + copy_ret = copy_to_user(event + ret, ev + pos, sizeof(*ev) * avail); + kunmap(page); - /* Could we split the check in two? */ - ret = -EFAULT; - if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) { - dprintk("aio: lost an event due to EFAULT.\n"); - break; + if (unlikely(copy_ret)) { + ret = -EFAULT; + goto out; } - ret = 0; - /* Good, event copied to userland, update counts. */ - event ++; - i ++; + ret += avail; + head += avail; + head %= ctx->nr; } - if (min_nr <= i) - return i; - if (ret) - return ret; - - /* End fast path */ + ring = kmap_atomic(ctx->ring_pages[0]); + ring->head = head; + kunmap_atomic(ring); + flush_dcache_page(ctx->ring_pages[0]); - /* racey check, but it gets redone */ - if (!retry && unlikely(!list_empty(&ctx->run_list))) { - retry = 1; - aio_run_all_iocbs(ctx); - goto retry; - } + pr_debug("%li h%u t%u\n", ret, head, ctx->shadow_tail); - init_timeout(&to); - if (timeout) { - struct timespec ts; - ret = -EFAULT; - if (unlikely(copy_from_user(&ts, timeout, sizeof(ts)))) - goto out; - - set_timeout(start_jiffies, &to, &ts); - } + put_reqs_available(ctx, ret); +out: + mutex_unlock(&ctx->ring_lock); - while (likely(i < nr)) { - add_wait_queue_exclusive(&ctx->wait, &wait); - do { - set_task_state(tsk, TASK_INTERRUPTIBLE); - ret = aio_read_evt(ctx, &ent); - if (ret) - break; - if (min_nr <= i) - break; - if (unlikely(ctx->dead)) { - ret = -EINVAL; - break; - } - if (to.timed_out) /* Only check after read evt */ - break; - /* Try to only show up in io wait if there are ops - * in flight */ - if (ctx->reqs_active) - io_schedule(); - else - schedule(); - if (signal_pending(tsk)) { - ret = -EINTR; - break; - } - /*ret = aio_read_evt(ctx, &ent);*/ - } while (1) ; + return ret; +} - set_task_state(tsk, TASK_RUNNING); - remove_wait_queue(&ctx->wait, &wait); +static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr, + struct io_event __user *event, long *i) +{ + long ret = aio_read_events_ring(ctx, event + *i, nr - *i); - if (unlikely(ret <= 0)) - break; + if (ret > 0) + *i += ret; - ret = -EFAULT; - if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) { - dprintk("aio: lost an event due to EFAULT.\n"); - break; - } + if (unlikely(percpu_ref_dead(&ctx->users))) + ret = -EINVAL; - /* Good, event copied to userland, update counts. */ - event ++; - i ++; - } + if (!*i) + *i = ret; - if (timeout) - clear_timeout(&to); -out: - destroy_timer_on_stack(&to.timer); - return i ? i : ret; + return ret < 0 || *i >= min_nr; } -/* Take an ioctx and remove it from the list of ioctx's. Protects - * against races with itself via ->dead. - */ -static void io_destroy(struct kioctx *ioctx) +static long read_events(struct kioctx *ctx, long min_nr, long nr, + struct io_event __user *event, + struct timespec __user *timeout) { - struct mm_struct *mm = current->mm; - int was_dead; + ktime_t until = { .tv64 = KTIME_MAX }; + long ret = 0; - /* delete the entry from the list is someone else hasn't already */ - spin_lock(&mm->ioctx_lock); - was_dead = ioctx->dead; - ioctx->dead = 1; - hlist_del_rcu(&ioctx->list); - spin_unlock(&mm->ioctx_lock); + if (timeout) { + struct timespec ts; - dprintk("aio_release(%p)\n", ioctx); - if (likely(!was_dead)) - put_ioctx(ioctx); /* twice for the list */ + if (unlikely(copy_from_user(&ts, timeout, sizeof(ts)))) + return -EFAULT; - kill_ctx(ioctx); + until = timespec_to_ktime(ts); + } /* - * Wake up any waiters. The setting of ctx->dead must be seen - * by other CPUs at this point. Right now, we rely on the - * locking done by the above calls to ensure this consistency. + * Note that aio_read_events() is being called as the conditional - i.e. + * we're calling it after prepare_to_wait() has set task state to + * TASK_INTERRUPTIBLE. + * + * But aio_read_events() can block, and if it blocks it's going to flip + * the task state back to TASK_RUNNING. + * + * This should be ok, provided it doesn't flip the state back to + * TASK_RUNNING and return 0 too much - that causes us to spin. That + * will only happen if the mutex_lock() call blocks, and we then find + * the ringbuffer empty. So in practice we should be ok, but it's + * something to be aware of when touching this code. */ - wake_up_all(&ioctx->wait); + wait_event_interruptible_hrtimeout(ctx->wait, + aio_read_events(ctx, min_nr, nr, event, &ret), until); + + if (!ret && signal_pending(current)) + ret = -EINTR; + + return ret; } /* sys_io_setup: @@ -1250,7 +1019,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) - io_destroy(ioctx); + kill_ioctx(ioctx); put_ioctx(ioctx); } @@ -1268,7 +1037,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { - io_destroy(ioctx); + kill_ioctx(ioctx); put_ioctx(ioctx); return 0; } @@ -1299,24 +1068,15 @@ static void aio_advance_iovec(struct kiocb *iocb, ssize_t ret) BUG_ON(ret > 0 && iocb->ki_left == 0); } -static ssize_t aio_rw_vect_retry(struct kiocb *iocb) +typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *, + unsigned long, loff_t); + +static ssize_t aio_rw_vect_retry(struct kiocb *iocb, int rw, aio_rw_op *rw_op) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - ssize_t (*rw_op)(struct kiocb *, const struct iovec *, - unsigned long, loff_t); ssize_t ret = 0; - unsigned short opcode; - - if ((iocb->ki_opcode == IOCB_CMD_PREADV) || - (iocb->ki_opcode == IOCB_CMD_PREAD)) { - rw_op = file->f_op->aio_read; - opcode = IOCB_CMD_PREADV; - } else { - rw_op = file->f_op->aio_write; - opcode = IOCB_CMD_PWRITEV; - } /* This matches the pread()/pwrite() logic */ if (iocb->ki_pos < 0) @@ -1332,7 +1092,7 @@ static ssize_t aio_rw_vect_retry(struct kiocb *iocb) /* retry all partial writes. retry partial reads as long as its a * regular file. */ } while (ret > 0 && iocb->ki_left > 0 && - (opcode == IOCB_CMD_PWRITEV || + (rw == WRITE || (!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode)))); /* This means we must have transferred all that we could */ @@ -1342,81 +1102,49 @@ static ssize_t aio_rw_vect_retry(struct kiocb *iocb) /* If we managed to write some out we return that, rather than * the eventual error. */ - if (opcode == IOCB_CMD_PWRITEV - && ret < 0 && ret != -EIOCBQUEUED && ret != -EIOCBRETRY + if (rw == WRITE + && ret < 0 && ret != -EIOCBQUEUED && iocb->ki_nbytes - iocb->ki_left) ret = iocb->ki_nbytes - iocb->ki_left; return ret; } -static ssize_t aio_fdsync(struct kiocb *iocb) -{ - struct file *file = iocb->ki_filp; - ssize_t ret = -EINVAL; - - if (file->f_op->aio_fsync) - ret = file->f_op->aio_fsync(iocb, 1); - return ret; -} - -static ssize_t aio_fsync(struct kiocb *iocb) -{ - struct file *file = iocb->ki_filp; - ssize_t ret = -EINVAL; - - if (file->f_op->aio_fsync) - ret = file->f_op->aio_fsync(iocb, 0); - return ret; -} - -static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat) +static ssize_t aio_setup_vectored_rw(int rw, struct kiocb *kiocb, bool compat) { ssize_t ret; + kiocb->ki_nr_segs = kiocb->ki_nbytes; + #ifdef CONFIG_COMPAT if (compat) - ret = compat_rw_copy_check_uvector(type, + ret = compat_rw_copy_check_uvector(rw, (struct compat_iovec __user *)kiocb->ki_buf, - kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, + kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec, &kiocb->ki_iovec); else #endif - ret = rw_copy_check_uvector(type, + ret = rw_copy_check_uvector(rw, (struct iovec __user *)kiocb->ki_buf, - kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, + kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec, &kiocb->ki_iovec); if (ret < 0) - goto out; - - ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret); - if (ret < 0) - goto out; + return ret; - kiocb->ki_nr_segs = kiocb->ki_nbytes; - kiocb->ki_cur_seg = 0; - /* ki_nbytes/left now reflect bytes instead of segs */ + /* ki_nbytes now reflect bytes instead of segs */ kiocb->ki_nbytes = ret; - kiocb->ki_left = ret; - - ret = 0; -out: - return ret; + return 0; } -static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb) +static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb) { - int bytes; - - bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left); - if (bytes < 0) - return bytes; + if (unlikely(!access_ok(!rw, kiocb->ki_buf, kiocb->ki_nbytes))) + return -EFAULT; kiocb->ki_iovec = &kiocb->ki_inline_vec; kiocb->ki_iovec->iov_base = kiocb->ki_buf; - kiocb->ki_iovec->iov_len = bytes; + kiocb->ki_iovec->iov_len = kiocb->ki_nbytes; kiocb->ki_nr_segs = 1; - kiocb->ki_cur_seg = 0; return 0; } @@ -1425,96 +1153,94 @@ static ssize_t aio_setup_single_vector(int type, struct file * file, struct kioc * Performs the initial checks and aio retry method * setup for the kiocb at the time of io submission. */ -static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) +static ssize_t aio_run_iocb(struct kiocb *req, bool compat) { - struct file *file = kiocb->ki_filp; - ssize_t ret = 0; + struct file *file = req->ki_filp; + ssize_t ret; + int rw; + fmode_t mode; + aio_rw_op *rw_op; - switch (kiocb->ki_opcode) { + switch (req->ki_opcode) { case IOCB_CMD_PREAD: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_READ))) - break; - ret = -EFAULT; - if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf, - kiocb->ki_left))) - break; - ret = aio_setup_single_vector(READ, file, kiocb); - if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_read) - kiocb->ki_retry = aio_rw_vect_retry; - break; - case IOCB_CMD_PWRITE: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_WRITE))) - break; - ret = -EFAULT; - if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf, - kiocb->ki_left))) - break; - ret = aio_setup_single_vector(WRITE, file, kiocb); - if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_write) - kiocb->ki_retry = aio_rw_vect_retry; - break; case IOCB_CMD_PREADV: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_READ))) - break; - ret = aio_setup_vectored_rw(READ, kiocb, compat); - if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_read) - kiocb->ki_retry = aio_rw_vect_retry; - break; + mode = FMODE_READ; + rw = READ; + rw_op = file->f_op->aio_read; + goto rw_common; + + case IOCB_CMD_PWRITE: case IOCB_CMD_PWRITEV: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_WRITE))) - break; - ret = aio_setup_vectored_rw(WRITE, kiocb, compat); + mode = FMODE_WRITE; + rw = WRITE; + rw_op = file->f_op->aio_write; + goto rw_common; +rw_common: + if (unlikely(!(file->f_mode & mode))) + return -EBADF; + + if (!rw_op) + return -EINVAL; + + ret = (req->ki_opcode == IOCB_CMD_PREADV || + req->ki_opcode == IOCB_CMD_PWRITEV) + ? aio_setup_vectored_rw(rw, req, compat) + : aio_setup_single_vector(rw, req); if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_write) - kiocb->ki_retry = aio_rw_vect_retry; + return ret; + + ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); + if (ret < 0) + return ret; + + req->ki_nbytes = ret; + req->ki_left = ret; + + ret = aio_rw_vect_retry(req, rw, rw_op); break; + case IOCB_CMD_FDSYNC: - ret = -EINVAL; - if (file->f_op->aio_fsync) - kiocb->ki_retry = aio_fdsync; + if (!file->f_op->aio_fsync) + return -EINVAL; + + ret = file->f_op->aio_fsync(req, 1); break; + case IOCB_CMD_FSYNC: - ret = -EINVAL; - if (file->f_op->aio_fsync) - kiocb->ki_retry = aio_fsync; + if (!file->f_op->aio_fsync) + return -EINVAL; + + ret = file->f_op->aio_fsync(req, 0); break; + default: - dprintk("EINVAL: io_submit: no operation provided\n"); - ret = -EINVAL; + pr_debug("EINVAL: no operation provided\n"); + return -EINVAL; } - if (!kiocb->ki_retry) - return ret; + if (ret != -EIOCBQUEUED) { + /* + * There's no easy way to restart the syscall since other AIO's + * may be already running. Just fail this IO with EINTR. + */ + if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || + ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK)) + ret = -EINTR; + aio_complete(req, ret, 0); + } return 0; } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, - struct iocb *iocb, struct kiocb_batch *batch, - bool compat) + struct iocb *iocb, bool compat) { struct kiocb *req; - struct file *file; ssize_t ret; /* enforce forwards compatibility on users */ if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) { - pr_debug("EINVAL: io_submit: reserve field set\n"); + pr_debug("EINVAL: reserve field set\n"); return -EINVAL; } @@ -1528,16 +1254,16 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, return -EINVAL; } - file = fget(iocb->aio_fildes); - if (unlikely(!file)) - return -EBADF; - - req = aio_get_req(ctx, batch); /* returns with 2 references to req */ - if (unlikely(!req)) { - fput(file); + req = aio_get_req(ctx); + if (unlikely(!req)) return -EAGAIN; + + req->ki_filp = fget(iocb->aio_fildes); + if (unlikely(!req->ki_filp)) { + ret = -EBADF; + goto out_put_req; } - req->ki_filp = file; + if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an @@ -1553,9 +1279,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, } } - ret = put_user(req->ki_key, &user_iocb->aio_key); + ret = put_user(KIOCB_KEY, &user_iocb->aio_key); if (unlikely(ret)) { - dprintk("EFAULT: aio_key\n"); + pr_debug("EFAULT: aio_key\n"); goto out_put_req; } @@ -1567,41 +1293,14 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->ki_left = req->ki_nbytes = iocb->aio_nbytes; req->ki_opcode = iocb->aio_lio_opcode; - ret = aio_setup_iocb(req, compat); - + ret = aio_run_iocb(req, compat); if (ret) goto out_put_req; - spin_lock_irq(&ctx->ctx_lock); - /* - * We could have raced with io_destroy() and are currently holding a - * reference to ctx which should be destroyed. We cannot submit IO - * since ctx gets freed as soon as io_submit() puts its reference. The - * check here is reliable: io_destroy() sets ctx->dead before waiting - * for outstanding IO and the barrier between these two is realized by - * unlock of mm->ioctx_lock and lock of ctx->ctx_lock. Analogously we - * increment ctx->reqs_active before checking for ctx->dead and the - * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we - * don't see ctx->dead set here, io_destroy() waits for our IO to - * finish. - */ - if (ctx->dead) { - spin_unlock_irq(&ctx->ctx_lock); - ret = -EINVAL; - goto out_put_req; - } - aio_run_iocb(req); - if (!list_empty(&ctx->run_list)) { - /* drain the run list */ - while (__aio_run_iocbs(ctx)) - ; - } - spin_unlock_irq(&ctx->ctx_lock); - aio_put_req(req); /* drop extra ref to req */ return 0; - out_put_req: + put_reqs_available(ctx, 1); aio_put_req(req); /* drop extra ref to req */ aio_put_req(req); /* drop i/o ref to req */ return ret; @@ -1614,7 +1313,6 @@ long do_io_submit(aio_context_t ctx_id, long nr, long ret = 0; int i = 0; struct blk_plug plug; - struct kiocb_batch batch; if (unlikely(nr < 0)) return -EINVAL; @@ -1627,12 +1325,10 @@ long do_io_submit(aio_context_t ctx_id, long nr, ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { - pr_debug("EINVAL: io_submit: invalid context id\n"); + pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } - kiocb_batch_init(&batch, nr); - blk_start_plug(&plug); /* @@ -1653,13 +1349,12 @@ long do_io_submit(aio_context_t ctx_id, long nr, break; } - ret = io_submit_one(ctx, user_iocb, &tmp, &batch, compat); + ret = io_submit_one(ctx, user_iocb, &tmp, compat); if (ret) break; } blk_finish_plug(&plug); - kiocb_batch_free(ctx, &batch); put_ioctx(ctx); return i ? i : ret; } @@ -1692,10 +1387,13 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, assert_spin_locked(&ctx->ctx_lock); + if (key != KIOCB_KEY) + return NULL; + /* TODO: use a hash or array, this sucks. */ list_for_each(pos, &ctx->active_reqs) { struct kiocb *kiocb = list_kiocb(pos); - if (kiocb->ki_obj.user == iocb && kiocb->ki_key == key) + if (kiocb->ki_obj.user == iocb) return kiocb; } return NULL; @@ -1714,7 +1412,7 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) { - int (*cancel)(struct kiocb *iocb, struct io_event *res); + struct io_event res; struct kioctx *ctx; struct kiocb *kiocb; u32 key; @@ -1729,32 +1427,22 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, return -EINVAL; spin_lock_irq(&ctx->ctx_lock); - ret = -EAGAIN; + kiocb = lookup_kiocb(ctx, iocb, key); - if (kiocb && kiocb->ki_cancel) { - cancel = kiocb->ki_cancel; - kiocb->ki_users ++; - kiocbSetCancelled(kiocb); - } else - cancel = NULL; + if (kiocb) + ret = kiocb_cancel(ctx, kiocb, &res); + else + ret = -EINVAL; + spin_unlock_irq(&ctx->ctx_lock); - if (NULL != cancel) { - struct io_event tmp; - pr_debug("calling cancel\n"); - memset(&tmp, 0, sizeof(tmp)); - tmp.obj = (u64)(unsigned long)kiocb->ki_obj.user; - tmp.data = kiocb->ki_user_data; - ret = cancel(kiocb, &tmp); - if (!ret) { - /* Cancellation succeeded -- copy the result - * into the user's buffer. - */ - if (copy_to_user(result, &tmp, sizeof(tmp))) - ret = -EFAULT; - } - } else - ret = -EINVAL; + if (!ret) { + /* Cancellation succeeded -- copy the result + * into the user's buffer. + */ + if (copy_to_user(result, &res, sizeof(res))) + ret = -EFAULT; + } put_ioctx(ctx); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index c93447604da8..847ee4dd72a4 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -587,7 +587,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) /* This allows root to remove symlinks */ if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (atomic_dec_and_test(&ino->count)) { p_ino = autofs4_dentry_ino(dentry->d_parent); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 6043567b95c2..692e75ca6415 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -256,8 +256,6 @@ static int load_aout_binary(struct linux_binprm * bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index da19fc7c00b2..d1777a445841 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -140,6 +140,25 @@ static int padzero(unsigned long elf_bss) #define ELF_BASE_PLATFORM NULL #endif +/* + * Use get_random_int() to implement AT_RANDOM while avoiding depletion + * of the entropy pool. + */ +static void get_atrandom_bytes(unsigned char *buf, size_t nbytes) +{ + unsigned char *p = buf; + + while (nbytes) { + unsigned int random_variable; + size_t chunk = min(nbytes, sizeof(random_variable)); + + random_variable = get_random_int(); + memcpy(p, &random_variable, chunk); + p += chunk; + nbytes -= chunk; + } +} + static int create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, unsigned long load_addr, unsigned long interp_load_addr) @@ -201,7 +220,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, /* * Generate 16 random bytes for userspace PRNG seeding. */ - get_random_bytes(k_rand_bytes, sizeof(k_rand_bytes)); + get_atrandom_bytes(k_rand_bytes, sizeof(k_rand_bytes)); u_rand_bytes = (elf_addr_t __user *) STACK_ALLOC(p, sizeof(k_rand_bytes)); if (__copy_to_user(u_rand_bytes, k_rand_bytes, sizeof(k_rand_bytes))) @@ -735,8 +754,6 @@ static int load_elf_binary(struct linux_binprm *bprm) /* Do this so that we can load the interpreter, if need be. We will change some of these later */ - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP), executable_stack); if (retval < 0) { @@ -1253,7 +1270,7 @@ static int writenote(struct memelfnote *men, struct file *file, #undef DUMP_WRITE static void fill_elf_header(struct elfhdr *elf, int segs, - u16 machine, u32 flags, u8 osabi) + u16 machine, u32 flags) { memset(elf, 0, sizeof(*elf)); @@ -1638,7 +1655,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, * Initialize the ELF file header. */ fill_elf_header(elf, phdrs, - view->e_machine, view->e_flags, view->ei_osabi); + view->e_machine, view->e_flags); /* * Allocate a structure for each thread. @@ -1878,7 +1895,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, elf_core_copy_regs(&info->prstatus->pr_reg, regs); /* Set up header */ - fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS, ELF_OSABI); + fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS); /* * Set up the notes in similar form to SVR4 core dumps made @@ -27,6 +27,7 @@ #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/cgroup.h> +#include <linux/aio.h> #include <scsi/sg.h> /* for struct sg_iovec */ #include <trace/events/block.h> @@ -1407,33 +1408,44 @@ void bio_flush_dcache_pages(struct bio *bi) EXPORT_SYMBOL(bio_flush_dcache_pages); #endif -/** - * bio_endio - end I/O on a bio - * @bio: bio - * @error: error, if any - * - * Description: - * bio_endio() will end I/O on the whole bio. bio_endio() is the - * preferred way to end I/O on a bio, it takes care of clearing - * BIO_UPTODATE on error. @error is 0 on success, and and one of the - * established -Exxxx (-EIO, for instance) error values in case - * something went wrong. No one should call bi_end_io() directly on a - * bio unless they own it and thus know that it has an end_io - * function. - **/ -void bio_endio(struct bio *bio, int error) +static inline void __bio_endio(struct bio *bio, struct batch_complete *batch) { - if (error) + if (bio->bi_error) clear_bit(BIO_UPTODATE, &bio->bi_flags); else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) - error = -EIO; + bio->bi_error = -EIO; + + if (bio_flagged(bio, BIO_BATCH_ENDIO)) + bio->bi_batch_end_io(bio, bio->bi_error, batch); + else if (bio->bi_end_io) + bio->bi_end_io(bio, bio->bi_error); +} + +void bio_endio_batch(struct bio *bio, int error, struct batch_complete *batch) +{ + if (error) + bio->bi_error = error; trace_block_bio_complete(bio, error); - if (bio->bi_end_io) - bio->bi_end_io(bio, error); + if (batch) + bio_list_add(&batch->bio, bio); + else + __bio_endio(bio, batch); + +} +EXPORT_SYMBOL(bio_endio_batch); + +void batch_complete(struct batch_complete *batch) +{ + struct bio *bio; + + while ((bio = bio_list_pop(&batch->bio))) + __bio_endio(bio, batch); + + batch_complete_aio(batch); } -EXPORT_SYMBOL(bio_endio); +EXPORT_SYMBOL(batch_complete); void bio_pair_release(struct bio_pair *bp) { diff --git a/fs/block_dev.c b/fs/block_dev.c index 172f8491a2bd..363ebe453455 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -27,6 +27,7 @@ #include <linux/namei.h> #include <linux/log2.h> #include <linux/cleancache.h> +#include <linux/aio.h> #include <asm/uaccess.h> #include "internal.h" @@ -616,11 +617,9 @@ void bd_forget(struct inode *inode) struct block_device *bdev = NULL; spin_lock(&bdev_lock); - if (inode->i_bdev) { - if (!sb_is_blkdev_sb(inode->i_sb)) - bdev = inode->i_bdev; - __bd_forget(inode); - } + if (!sb_is_blkdev_sb(inode->i_sb)) + bdev = inode->i_bdev; + __bd_forget(inode); spin_unlock(&bdev_lock); if (bdev) @@ -994,6 +993,7 @@ int revalidate_disk(struct gendisk *disk) mutex_lock(&bdev->bd_mutex); check_disk_size_change(disk, bdev); + bdev->bd_invalidated = 0; mutex_unlock(&bdev->bd_mutex); bdput(bdev); return ret; @@ -1032,7 +1032,9 @@ void bd_set_size(struct block_device *bdev, loff_t size) { unsigned bsize = bdev_logical_block_size(bdev); - bdev->bd_inode->i_size = size; + mutex_lock(&bdev->bd_inode->i_mutex); + i_size_write(bdev->bd_inode, size); + mutex_unlock(&bdev->bd_inode->i_mutex); while (bsize < PAGE_CACHE_SIZE) { if (size & bsize) break; @@ -1117,7 +1119,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret && !bdev->bd_openers) { + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); bdi = blk_get_backing_dev_info(bdev); if (bdi == NULL) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f76b1fd160d4..fcb7060aa1c2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -30,6 +30,7 @@ #include <linux/statfs.h> #include <linux/compat.h> #include <linux/slab.h> +#include <linux/aio.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index cc93b23ca352..ed7ea0afe9ad 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -39,6 +39,7 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/mount.h> +#include <linux/aio.h> #include "compat.h" #include "ctree.h" #include "disk-io.h" diff --git a/fs/buffer.c b/fs/buffer.c index 5a2915f5dbc4..b095a2ac1fdb 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2369,7 +2369,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, if (unlikely(ret < 0)) goto out_unlock; set_page_dirty(page); - wait_on_page_writeback(page); + wait_for_stable_page(page); return 0; out_unlock: unlock_page(page); @@ -3237,7 +3237,7 @@ static struct kmem_cache *bh_cachep __read_mostly; * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ -static int max_buffer_heads; +static unsigned long max_buffer_heads; int buffer_heads_over_limit; @@ -3353,7 +3353,7 @@ EXPORT_SYMBOL(bh_submit_read); void __init buffer_init(void) { - int nrpages; + unsigned long nrpages; bh_cachep = kmem_cache_create("buffer_head", sizeof(struct buffer_head), 0, diff --git a/fs/ceph/file.c b/fs/ceph/file.c index e51558fca3a3..3d03090c6ace 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -7,6 +7,7 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/writeback.h> +#include <linux/aio.h> #include "super.h" #include "mds_client.h" diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ed6208ff85a7..7a3f57f4f624 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -806,10 +806,9 @@ static bool inode_has_hashed_dentries(struct inode *inode) { struct dentry *dentry; - struct hlist_node *p; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; diff --git a/fs/compat.c b/fs/compat.c index fe40fde29111..ba323f8de6fc 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -48,6 +48,7 @@ #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/pagemap.h> +#include <linux/aio.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> diff --git a/fs/coredump.c b/fs/coredump.c index 177493272a61..57b9bd6da233 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -501,7 +501,7 @@ void do_coredump(siginfo_t *siginfo) * so we dump it as root in mode 2, and only into a controlled * environment (pipe handler or fully qualified path). */ - if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) { + if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) { /* Setuid core dump mode */ flag = O_EXCL; /* Stop rewrite attacks */ cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */ diff --git a/fs/dcache.c b/fs/dcache.c index 19153a0a810c..070b318202ec 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -675,11 +675,10 @@ EXPORT_SYMBOL(dget_parent); static struct dentry *__d_find_alias(struct inode *inode, int want_discon) { struct dentry *alias, *discon_alias; - struct hlist_node *p; again: discon_alias = NULL; - hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && @@ -730,10 +729,9 @@ EXPORT_SYMBOL(d_find_alias); void d_prune_aliases(struct inode *inode) { struct dentry *dentry; - struct hlist_node *p; restart: spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_count) { __dget_dlock(dentry); @@ -1440,14 +1438,13 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, int len = entry->d_name.len; const char *name = entry->d_name.name; unsigned int hash = entry->d_name.hash; - struct hlist_node *p; if (!inode) { __d_instantiate(entry, NULL); return NULL; } - hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or diff --git a/fs/direct-io.c b/fs/direct-io.c index cf5b44b10c67..55683f36a2f1 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -37,6 +37,7 @@ #include <linux/uio.h> #include <linux/atomic.h> #include <linux/prefetch.h> +#include <linux/aio.h> /* * How many user pages to map in one call to get_user_pages(). This determines @@ -229,7 +230,8 @@ static inline struct page *dio_get_page(struct dio *dio, * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async) +static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async, + struct batch_complete *batch) { ssize_t transferred = 0; @@ -261,9 +263,9 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is dio->end_io(dio->iocb, offset, transferred, dio->private, ret, is_async); } else { - if (is_async) - aio_complete(dio->iocb, ret, 0); inode_dio_done(dio->inode); + if (is_async) + aio_complete_batch(dio->iocb, ret, 0, batch); } return ret; @@ -273,7 +275,7 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio); /* * Asynchronous IO callback. */ -static void dio_bio_end_aio(struct bio *bio, int error) +static void dio_bio_end_aio(struct bio *bio, int error, struct batch_complete *batch) { struct dio *dio = bio->bi_private; unsigned long remaining; @@ -289,7 +291,7 @@ static void dio_bio_end_aio(struct bio *bio, int error) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - dio_complete(dio, dio->iocb->ki_pos, 0, true); + dio_complete(dio, dio->iocb->ki_pos, 0, true, batch); kmem_cache_free(dio_cache, dio); } } @@ -328,7 +330,7 @@ void dio_end_io(struct bio *bio, int error) struct dio *dio = bio->bi_private; if (dio->is_async) - dio_bio_end_aio(bio, error); + dio_bio_end_aio(bio, error, NULL); else dio_bio_end_io(bio, error); } @@ -349,9 +351,10 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, bio->bi_bdev = bdev; bio->bi_sector = first_sector; - if (dio->is_async) - bio->bi_end_io = dio_bio_end_aio; - else + if (dio->is_async) { + bio->bi_batch_end_io = dio_bio_end_aio; + bio->bi_flags |= 1 << BIO_BATCH_ENDIO; + } else bio->bi_end_io = dio_bio_end_io; sdio->bio = bio; @@ -1272,7 +1275,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, dio_await_completion(dio); if (drop_refcount(dio) == 0) { - retval = dio_complete(dio, offset, retval, false); + retval = dio_complete(dio, offset, retval, false, NULL); kmem_cache_free(dio_cache, dio); } else BUG_ON(retval != -EIOCBQUEUED); diff --git a/fs/dlm/config.c b/fs/dlm/config.c index a0387dd8b1f0..7d58d5b112b5 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -158,7 +158,7 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field, unsigned int x; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; x = simple_strtoul(buf, NULL, 0); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index f7501651762d..1b1146670c4b 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1183,7 +1183,7 @@ static void detach_lkb(struct dlm_lkb *lkb) static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) { struct dlm_lkb *lkb; - int rv, id; + int rv; lkb = dlm_allocate_lkb(ls); if (!lkb) @@ -1199,19 +1199,13 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) mutex_init(&lkb->lkb_cb_mutex); INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work); - retry: - rv = idr_pre_get(&ls->ls_lkbidr, GFP_NOFS); - if (!rv) - return -ENOMEM; - + idr_preload(GFP_NOFS); spin_lock(&ls->ls_lkbidr_spin); - rv = idr_get_new_above(&ls->ls_lkbidr, lkb, 1, &id); - if (!rv) - lkb->lkb_id = id; + rv = idr_alloc(&ls->ls_lkbidr, lkb, 1, 0, GFP_NOWAIT); + if (rv >= 0) + lkb->lkb_id = rv; spin_unlock(&ls->ls_lkbidr_spin); - - if (rv == -EAGAIN) - goto retry; + idr_preload_end(); if (rv < 0) { log_error(ls, "create_lkb idr error %d", rv); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 2e99fb0c9737..3ca79d3253b9 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -796,7 +796,6 @@ static int release_lockspace(struct dlm_ls *ls, int force) */ idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls); - idr_remove_all(&ls->ls_lkbidr); idr_destroy(&ls->ls_lkbidr); /* diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index dd87a31bcc21..036ecb5c17db 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -177,12 +177,11 @@ static inline int nodeid_hash(int nodeid) static struct connection *__find_con(int nodeid) { int r; - struct hlist_node *h; struct connection *con; r = nodeid_hash(nodeid); - hlist_for_each_entry(con, h, &connection_hash[r], list) { + hlist_for_each_entry(con, &connection_hash[r], list) { if (con->nodeid == nodeid) return con; } @@ -232,11 +231,11 @@ static struct connection *__nodeid2con(int nodeid, gfp_t alloc) static void foreach_conn(void (*conn_func)(struct connection *c)) { int i; - struct hlist_node *h, *n; + struct hlist_node *n; struct connection *con; for (i = 0; i < CONN_HASH_SIZE; i++) { - hlist_for_each_entry_safe(con, h, n, &connection_hash[i], list){ + hlist_for_each_entry_safe(con, n, &connection_hash[i], list){ conn_func(con); } } @@ -257,13 +256,12 @@ static struct connection *nodeid2con(int nodeid, gfp_t allocation) static struct connection *assoc2con(int assoc_id) { int i; - struct hlist_node *h; struct connection *con; mutex_lock(&connections_lock); for (i = 0 ; i < CONN_HASH_SIZE; i++) { - hlist_for_each_entry(con, h, &connection_hash[i], list) { + hlist_for_each_entry(con, &connection_hash[i], list) { if (con->sctp_assoc == assoc_id) { mutex_unlock(&connections_lock); return con; diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index aedea28a86a1..a6bc63f6e31b 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -305,27 +305,26 @@ static int recover_idr_empty(struct dlm_ls *ls) static int recover_idr_add(struct dlm_rsb *r) { struct dlm_ls *ls = r->res_ls; - int rv, id; - - rv = idr_pre_get(&ls->ls_recover_idr, GFP_NOFS); - if (!rv) - return -ENOMEM; + int rv; + idr_preload(GFP_NOFS); spin_lock(&ls->ls_recover_idr_lock); if (r->res_id) { - spin_unlock(&ls->ls_recover_idr_lock); - return -1; - } - rv = idr_get_new_above(&ls->ls_recover_idr, r, 1, &id); - if (rv) { - spin_unlock(&ls->ls_recover_idr_lock); - return rv; + rv = -1; + goto out_unlock; } - r->res_id = id; + rv = idr_alloc(&ls->ls_recover_idr, r, 1, 0, GFP_NOWAIT); + if (rv < 0) + goto out_unlock; + + r->res_id = rv; ls->ls_recover_list_count++; dlm_hold_rsb(r); + rv = 0; +out_unlock: spin_unlock(&ls->ls_recover_idr_lock); - return 0; + idr_preload_end(); + return rv; } static void recover_idr_del(struct dlm_rsb *r) @@ -351,24 +350,21 @@ static struct dlm_rsb *recover_idr_find(struct dlm_ls *ls, uint64_t id) return r; } -static int recover_idr_clear_rsb(int id, void *p, void *data) +static void recover_idr_clear(struct dlm_ls *ls) { - struct dlm_ls *ls = data; - struct dlm_rsb *r = p; + struct dlm_rsb *r; + int id; - r->res_id = 0; - r->res_recover_locks_count = 0; - ls->ls_recover_list_count--; + spin_lock(&ls->ls_recover_idr_lock); - dlm_put_rsb(r); - return 0; -} + idr_for_each_entry(&ls->ls_recover_idr, r, id) { + idr_remove(&ls->ls_recover_idr, id); + r->res_id = 0; + r->res_recover_locks_count = 0; + ls->ls_recover_list_count--; -static void recover_idr_clear(struct dlm_ls *ls) -{ - spin_lock(&ls->ls_recover_idr_lock); - idr_for_each(&ls->ls_recover_idr, recover_idr_clear_rsb, ls); - idr_remove_all(&ls->ls_recover_idr); + dlm_put_rsb(r); + } if (ls->ls_recover_list_count != 0) { log_error(ls, "warning: recover_list_count %d", diff --git a/fs/drop_caches.c b/fs/drop_caches.c index c00e055b6282..f23d2a7ed438 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -58,6 +58,8 @@ int drop_caches_sysctl_handler(ctl_table *table, int write, if (ret) return ret; if (write) { + printk(KERN_NOTICE "%s (%d): dropped kernel caches: %d\n", + current->comm, task_pid_nr(current), sysctl_drop_caches); if (sysctl_drop_caches & 1) iterate_supers(drop_pagecache_sb, NULL); if (sysctl_drop_caches & 2) diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index bfa52d2ef460..857d545c7ef7 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -31,6 +31,7 @@ #include <linux/security.h> #include <linux/compat.h> #include <linux/fs_stack.h> +#include <linux/aio.h> #include "ecryptfs_kernel.h" /** diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index 5fa2471796c2..8d7a577ae497 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -115,10 +115,9 @@ void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx) */ int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon) { - struct hlist_node *elem; int rc; - hlist_for_each_entry(*daemon, elem, + hlist_for_each_entry(*daemon, &ecryptfs_daemon_hash[ecryptfs_current_euid_hash()], euid_chain) { if (uid_eq((*daemon)->file->f_cred->euid, current_euid())) { @@ -445,7 +444,6 @@ void ecryptfs_release_messaging(void) mutex_unlock(&ecryptfs_msg_ctx_lists_mux); } if (ecryptfs_daemon_hash) { - struct hlist_node *elem; struct ecryptfs_daemon *daemon; int i; @@ -453,7 +451,7 @@ void ecryptfs_release_messaging(void) for (i = 0; i < (1 << ecryptfs_hash_bits); i++) { int rc; - hlist_for_each_entry(daemon, elem, + hlist_for_each_entry(daemon, &ecryptfs_daemon_hash[i], euid_chain) { rc = ecryptfs_exorcise_daemon(daemon); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9fec1836057a..5dcc470879c7 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -348,7 +348,7 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p) /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { - return op != EPOLL_CTL_DEL; + return op == EPOLL_CTL_ADD || op == EPOLL_CTL_MOD; } /* Initialize the poll safe wake up structure */ @@ -678,6 +678,36 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) return 0; } +/* + * Disables a "struct epitem" in the eventpoll set. Returns -EBUSY if the item + * had no event flags set, indicating that another thread may be currently + * handling that item's events (in the case that EPOLLONESHOT was being + * used). Otherwise a zero result indicates that the item has been disabled + * from receiving events. A disabled item may be re-enabled via + * EPOLL_CTL_MOD. Must be called with "mtx" held. + */ +static int ep_disable(struct eventpoll *ep, struct epitem *epi) +{ + int result = 0; + unsigned long flags; + + spin_lock_irqsave(&ep->lock, flags); + if (epi->event.events & EPOLLONESHOT) { + if (epi->event.events & ~EP_PRIVATE_BITS) { + if (ep_is_linked(&epi->rdllink)) + list_del_init(&epi->rdllink); + /* Ensure ep_poll_callback will not add epi back onto + ready list: */ + epi->event.events &= EP_PRIVATE_BITS; + } else + result = -EBUSY; + } else + result = -EINVAL; + spin_unlock_irqrestore(&ep->lock, flags); + + return result; +} + static void ep_free(struct eventpoll *ep) { struct rb_node *rbp; @@ -1048,8 +1078,6 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) rb_insert_color(&epi->rbn, &ep->rbr); } - - #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate @@ -1835,6 +1863,12 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } else error = -ENOENT; break; + case EPOLL_CTL_DISABLE: + if (epi) + error = ep_disable(ep, epi); + else + error = -ENOENT; + break; } mutex_unlock(&ep->mtx); diff --git a/fs/exec.c b/fs/exec.c index 20df02c1cc70..dc38755fe538 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -355,7 +355,7 @@ static bool valid_arg_len(struct linux_binprm *bprm, long len) * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */ -int bprm_mm_init(struct linux_binprm *bprm) +static int bprm_mm_init(struct linux_binprm *bprm) { int err; struct mm_struct *mm = NULL; @@ -1111,7 +1111,7 @@ void setup_new_exec(struct linux_binprm * bprm) current->sas_ss_sp = current->sas_ss_size = 0; if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid())) - set_dumpable(current->mm, SUID_DUMPABLE_ENABLED); + set_dumpable(current->mm, SUID_DUMP_USER); else set_dumpable(current->mm, suid_dumpable); @@ -1639,17 +1639,17 @@ EXPORT_SYMBOL(set_binfmt); void set_dumpable(struct mm_struct *mm, int value) { switch (value) { - case SUID_DUMPABLE_DISABLED: + case SUID_DUMP_DISABLE: clear_bit(MMF_DUMPABLE, &mm->flags); smp_wmb(); clear_bit(MMF_DUMP_SECURELY, &mm->flags); break; - case SUID_DUMPABLE_ENABLED: + case SUID_DUMP_USER: set_bit(MMF_DUMPABLE, &mm->flags); smp_wmb(); clear_bit(MMF_DUMP_SECURELY, &mm->flags); break; - case SUID_DUMPABLE_SAFE: + case SUID_DUMP_ROOT: set_bit(MMF_DUMP_SECURELY, &mm->flags); smp_wmb(); set_bit(MMF_DUMPABLE, &mm->flags); @@ -1662,7 +1662,7 @@ int __get_dumpable(unsigned long mm_flags) int ret; ret = mm_flags & MMF_DUMPABLE_MASK; - return (ret > SUID_DUMPABLE_ENABLED) ? SUID_DUMPABLE_SAFE : ret; + return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret; } int get_dumpable(struct mm_struct *mm) diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 5df4bb4aab14..262fc9940982 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -44,14 +44,13 @@ find_acceptable_alias(struct dentry *result, { struct dentry *dentry, *toput = NULL; struct inode *inode; - struct hlist_node *p; if (acceptable(context, result)) return result; inode = result->d_inode; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index c3881e56662e..43d72d0ec7e2 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -31,6 +31,7 @@ #include <linux/mpage.h> #include <linux/fiemap.h> #include <linux/namei.h> +#include <linux/aio.h> #include "ext2.h" #include "acl.h" #include "xip.h" diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index d512c4bc4ad7..eac4f041f5fc 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -27,6 +27,7 @@ #include <linux/writeback.h> #include <linux/mpage.h> #include <linux/namei.h> +#include <linux/aio.h> #include "ext3.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 0926fe46ae3e..5546ca225ffe 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2067,6 +2067,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal": test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered": "writeback"); + sb->s_flags |= MS_SNAP_STABLE; return 0; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index afaf9f15303e..fe2afd554622 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -23,6 +23,7 @@ #include <linux/jbd2.h> #include <linux/mount.h> #include <linux/path.h> +#include <linux/aio.h> #include <linux/quotaops.h> #include <linux/pagevec.h> #include "ext4.h" diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index bdd20231e66c..5ef1408276e3 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -20,6 +20,7 @@ * (sct@redhat.com), 1993, 1998 */ +#include <linux/aio.h> #include "ext4_jbd2.h" #include "truncate.h" #include "ext4_extents.h" /* Needed for EXT_MAX_BLOCKS */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d0da1f26f20d..4b8d3c6c168c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -37,6 +37,7 @@ #include <linux/printk.h> #include <linux/slab.h> #include <linux/ratelimit.h> +#include <linux/aio.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -4841,7 +4842,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) 0, len, NULL, ext4_bh_unmapped)) { /* Wait so that we don't change page under IO */ - wait_on_page_writeback(page); + wait_for_stable_page(page); ret = VM_FAULT_LOCKED; goto out; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 809b31003ecc..d9903af92e51 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -18,6 +18,7 @@ #include <linux/pagevec.h> #include <linux/mpage.h> #include <linux/namei.h> +#include <linux/aio.h> #include <linux/uio.h> #include <linux/bio.h> #include <linux/workqueue.h> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 7bd22a201125..d0ed4ba4b61b 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -12,6 +12,7 @@ #include <linux/f2fs_fs.h> #include <linux/buffer_head.h> #include <linux/mpage.h> +#include <linux/aio.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 58bf744dbf39..78dabf00f46f 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -484,10 +484,10 @@ parse_record: nr_slots = 0; if (de->name[0] == DELETED_FLAG) continue; + if (!de->name[0]) + goto end_of_dir; if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME)) continue; - if (de->attr != ATTR_EXT && IS_FREE(de->name)) - continue; if (de->attr == ATTR_EXT) { int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); @@ -608,8 +608,8 @@ parse_record: goto record_end; if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME)) goto record_end; - if (de->attr != ATTR_EXT && IS_FREE(de->name)) - goto record_end; + if (!de->name[0]) + goto end_of_dir; } else { if ((de->attr & ATTR_VOLUME) || IS_FREE(de->name)) goto record_end; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 12701a567752..e9cc3f0d58e2 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -95,6 +95,8 @@ struct msdos_sb_info { spinlock_t dir_hash_lock; struct hlist_head dir_hashtable[FAT_HASH_SIZE]; + + unsigned int dirty; /* fs state before mount */ }; #define FAT_CACHE_VALID 0 /* special case for valid cache */ diff --git a/fs/fat/inode.c b/fs/fat/inode.c index f8f491677a4a..d1d502a026a5 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -20,6 +20,7 @@ #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/mount.h> +#include <linux/aio.h> #include <linux/vfs.h> #include <linux/parser.h> #include <linux/uio.h> @@ -341,12 +342,11 @@ struct inode *fat_iget(struct super_block *sb, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); - struct hlist_node *_p; struct msdos_inode_info *i; struct inode *inode = NULL; spin_lock(&sbi->inode_hash_lock); - hlist_for_each_entry(i, _p, head, i_fat_hash) { + hlist_for_each_entry(i, head, i_fat_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_pos != i_pos) continue; @@ -488,10 +488,59 @@ static void fat_evict_inode(struct inode *inode) fat_detach(inode); } +static void fat_set_state(struct super_block *sb, + unsigned int set, unsigned int force) +{ + struct buffer_head *bh; + struct fat_boot_sector *b; + struct msdos_sb_info *sbi = sb->s_fs_info; + + /* do not change any thing if mounted read only */ + if ((sb->s_flags & MS_RDONLY) && !force) + return; + + /* do not change state if fs was dirty */ + if (sbi->dirty) { + /* warn only on set (mount). */ + if (set) + fat_msg(sb, KERN_WARNING, "Volume was not properly " + "unmounted. Some data may be corrupt. " + "Please run fsck."); + return; + } + + bh = sb_bread(sb, 0); + if (bh == NULL) { + fat_msg(sb, KERN_ERR, "unable to read boot sector " + "to mark fs as dirty"); + return; + } + + b = (struct fat_boot_sector *) bh->b_data; + + if (sbi->fat_bits == 32) { + if (set) + b->fat32.state |= FAT_STATE_DIRTY; + else + b->fat32.state &= ~FAT_STATE_DIRTY; + } else /* fat 16 and 12 */ { + if (set) + b->fat16.state |= FAT_STATE_DIRTY; + else + b->fat16.state &= ~FAT_STATE_DIRTY; + } + + mark_buffer_dirty(bh); + sync_dirty_buffer(bh); + brelse(bh); +} + static void fat_put_super(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); + fat_set_state(sb, 0, 0); + iput(sbi->fsinfo_inode); iput(sbi->fat_inode); @@ -566,8 +615,18 @@ static void __exit fat_destroy_inodecache(void) static int fat_remount(struct super_block *sb, int *flags, char *data) { + int new_rdonly; struct msdos_sb_info *sbi = MSDOS_SB(sb); *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME); + + /* make sure we update state on remount. */ + new_rdonly = *flags & MS_RDONLY; + if (new_rdonly != (sb->s_flags & MS_RDONLY)) { + if (new_rdonly) + fat_set_state(sb, 0, 0); + else + fat_set_state(sb, 1, 1); + } return 0; } @@ -1298,17 +1357,17 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, sbi->prev_free = FAT_START_ENT; sb->s_maxbytes = 0xffffffff; - if (!sbi->fat_length && b->fat32_length) { + if (!sbi->fat_length && b->fat32.length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; - sbi->fat_length = le32_to_cpu(b->fat32_length); - sbi->root_cluster = le32_to_cpu(b->root_cluster); + sbi->fat_length = le32_to_cpu(b->fat32.length); + sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster); /* MC - if info_sector is 0, don't multiply by 0 */ - sbi->fsinfo_sector = le16_to_cpu(b->info_sector); + sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector); if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; @@ -1362,6 +1421,12 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (sbi->fat_bits != 32) sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; + /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ + if (sbi->fat_bits == 32) + sbi->dirty = b->fat32.state & FAT_STATE_DIRTY; + else /* fat 16 or 12 */ + sbi->dirty = b->fat16.state & FAT_STATE_DIRTY; + /* check that FAT table does not overflow */ fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); @@ -1456,6 +1521,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, "the device does not support discard"); } + fat_set_state(sb, 1, 0); return 0; out_invalid: diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index ef4b5faba87b..499c10438ca2 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -21,13 +21,12 @@ static struct inode *fat_dget(struct super_block *sb, int i_logstart) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct hlist_head *head; - struct hlist_node *_p; struct msdos_inode_info *i; struct inode *inode = NULL; head = sbi->dir_hashtable + fat_dir_hash(i_logstart); spin_lock(&sbi->dir_hash_lock); - hlist_for_each_entry(i, _p, head, i_dir_hash) { + hlist_for_each_entry(i, head, i_dir_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_logstart != i_logstart) continue; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 8dcb114758e3..e2cba1f60c21 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -237,13 +237,12 @@ static int fscache_alloc_object(struct fscache_cache *cache, struct fscache_cookie *cookie) { struct fscache_object *object; - struct hlist_node *_n; int ret; _enter("%p,%p{%s}", cache, cookie, cookie->def->name); spin_lock(&cookie->lock); - hlist_for_each_entry(object, _n, &cookie->backing_objects, + hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) { if (object->cache == cache) goto object_already_extant; @@ -311,7 +310,6 @@ static int fscache_attach_object(struct fscache_cookie *cookie, { struct fscache_object *p; struct fscache_cache *cache = object->cache; - struct hlist_node *_n; int ret; _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); @@ -321,7 +319,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, /* there may be multiple initial creations of this object, but we only * want one */ ret = -EEXIST; - hlist_for_each_entry(p, _n, &cookie->backing_objects, cookie_link) { + hlist_for_each_entry(p, &cookie->backing_objects, cookie_link) { if (p->cache == object->cache) { if (p->state >= FSCACHE_OBJECT_DYING) ret = -ENOBUFS; @@ -331,7 +329,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, /* pin the parent object */ spin_lock_nested(&cookie->parent->lock, 1); - hlist_for_each_entry(p, _n, &cookie->parent->backing_objects, + hlist_for_each_entry(p, &cookie->parent->backing_objects, cookie_link) { if (p->cache == object->cache) { if (p->state >= FSCACHE_OBJECT_DYING) { @@ -435,7 +433,6 @@ EXPORT_SYMBOL(__fscache_wait_on_invalidate); void __fscache_update_cookie(struct fscache_cookie *cookie) { struct fscache_object *object; - struct hlist_node *_p; fscache_stat(&fscache_n_updates); @@ -452,7 +449,7 @@ void __fscache_update_cookie(struct fscache_cookie *cookie) spin_lock(&cookie->lock); /* update the index entry on disk in each cache backing this cookie */ - hlist_for_each_entry(object, _p, + hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) { fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE); } diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 6f96a8def147..06b5e086ab3a 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -38,6 +38,7 @@ #include <linux/device.h> #include <linux/file.h> #include <linux/fs.h> +#include <linux/aio.h> #include <linux/kdev_t.h> #include <linux/kthread.h> #include <linux/list.h> diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index cbae09e5a491..95de0a2b8f0b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -19,6 +19,7 @@ #include <linux/pipe_fs_i.h> #include <linux/swap.h> #include <linux/splice.h> +#include <linux/aio.h> MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a010585b0a74..3f95325a0312 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/compat.h> #include <linux/swap.h> +#include <linux/aio.h> static const struct file_operations fuse_direct_io_file_operations; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 24f414f0ce61..371bd144d802 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -20,6 +20,7 @@ #include <linux/swap.h> #include <linux/gfs2_ondisk.h> #include <linux/backing-dev.h> +#include <linux/aio.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 06b7092a3f25..2d42817442fb 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -25,6 +25,7 @@ #include <asm/uaccess.h> #include <linux/dlm.h> #include <linux/dlm_plock.h> +#include <linux/aio.h> #include "gfs2.h" #include "incore.h" @@ -483,7 +484,7 @@ out: gfs2_holder_uninit(&gh); if (ret == 0) { set_page_dirty(page); - wait_on_page_writeback(page); + wait_for_stable_page(page); } sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 462e84142759..eb81cef67fa3 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -103,7 +103,7 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len) int n = simple_strtol(buf, NULL, 0); if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; switch (n) { case 0: @@ -133,7 +133,7 @@ static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf) static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; @@ -148,7 +148,7 @@ static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; @@ -161,7 +161,7 @@ static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; @@ -177,7 +177,7 @@ static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf, u32 id; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; id = simple_strtoul(buf, NULL, 0); @@ -192,7 +192,7 @@ static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf, u32 id; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; id = simple_strtoul(buf, NULL, 0); @@ -211,7 +211,7 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len int rv; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; rv = sscanf(buf, "%u:%llu %15s", &gltype, &glnum, mode); @@ -500,7 +500,7 @@ static ssize_t quota_scale_store(struct gfs2_sbd *sdp, const char *buf, unsigned int x, y; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (sscanf(buf, "%u %u", &x, &y) != 2 || !y) return -EINVAL; @@ -519,7 +519,7 @@ static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field, unsigned int x; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; x = simple_strtoul(buf, NULL, 0); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index d47f11658c17..b2f3025827a1 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> +#include <linux/aio.h> #include "hfs_fs.h" #include "btree.h" diff --git a/fs/hfsplus/Makefile b/fs/hfsplus/Makefile index 3cc0df730156..09d278bb7b91 100644 --- a/fs/hfsplus/Makefile +++ b/fs/hfsplus/Makefile @@ -5,5 +5,5 @@ obj-$(CONFIG_HFSPLUS_FS) += hfsplus.o hfsplus-objs := super.o options.o inode.o ioctl.o extents.o catalog.o dir.o btree.o \ - bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o - + bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o \ + attributes.o xattr.o xattr_user.o xattr_security.o xattr_trusted.o diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c new file mode 100644 index 000000000000..8d691f124714 --- /dev/null +++ b/fs/hfsplus/attributes.c @@ -0,0 +1,399 @@ +/* + * linux/fs/hfsplus/attributes.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handling of records in attributes tree + */ + +#include "hfsplus_fs.h" +#include "hfsplus_raw.h" + +static struct kmem_cache *hfsplus_attr_tree_cachep; + +int hfsplus_create_attr_tree_cache(void) +{ + if (hfsplus_attr_tree_cachep) + return -EEXIST; + + hfsplus_attr_tree_cachep = + kmem_cache_create("hfsplus_attr_cache", + sizeof(hfsplus_attr_entry), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!hfsplus_attr_tree_cachep) + return -ENOMEM; + + return 0; +} + +void hfsplus_destroy_attr_tree_cache(void) +{ + kmem_cache_destroy(hfsplus_attr_tree_cachep); +} + +int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *k1, + const hfsplus_btree_key *k2) +{ + __be32 k1_cnid, k2_cnid; + + k1_cnid = k1->attr.cnid; + k2_cnid = k2->attr.cnid; + if (k1_cnid != k2_cnid) + return be32_to_cpu(k1_cnid) < be32_to_cpu(k2_cnid) ? -1 : 1; + + return hfsplus_strcmp( + (const struct hfsplus_unistr *)&k1->attr.key_name, + (const struct hfsplus_unistr *)&k2->attr.key_name); +} + +int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key, + u32 cnid, const char *name) +{ + int len; + + memset(key, 0, sizeof(struct hfsplus_attr_key)); + key->attr.cnid = cpu_to_be32(cnid); + if (name) { + len = strlen(name); + if (len > HFSPLUS_ATTR_MAX_STRLEN) { + printk(KERN_ERR "hfs: invalid xattr name's length\n"); + return -EINVAL; + } + hfsplus_asc2uni(sb, + (struct hfsplus_unistr *)&key->attr.key_name, + HFSPLUS_ATTR_MAX_STRLEN, name, len); + len = be16_to_cpu(key->attr.key_name.length); + } else { + key->attr.key_name.length = 0; + len = 0; + } + + /* The length of the key, as stored in key_len field, does not include + * the size of the key_len field itself. + * So, offsetof(hfsplus_attr_key, key_name) is a trick because + * it takes into consideration key_len field (__be16) of + * hfsplus_attr_key structure instead of length field (__be16) of + * hfsplus_attr_unistr structure. + */ + key->key_len = + cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) + + 2 * len); + + return 0; +} + +void hfsplus_attr_build_key_uni(hfsplus_btree_key *key, + u32 cnid, + struct hfsplus_attr_unistr *name) +{ + int ustrlen; + + memset(key, 0, sizeof(struct hfsplus_attr_key)); + ustrlen = be16_to_cpu(name->length); + key->attr.cnid = cpu_to_be32(cnid); + key->attr.key_name.length = cpu_to_be16(ustrlen); + ustrlen *= 2; + memcpy(key->attr.key_name.unicode, name->unicode, ustrlen); + + /* The length of the key, as stored in key_len field, does not include + * the size of the key_len field itself. + * So, offsetof(hfsplus_attr_key, key_name) is a trick because + * it takes into consideration key_len field (__be16) of + * hfsplus_attr_key structure instead of length field (__be16) of + * hfsplus_attr_unistr structure. + */ + key->key_len = + cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) + + ustrlen); +} + +hfsplus_attr_entry *hfsplus_alloc_attr_entry(void) +{ + return kmem_cache_alloc(hfsplus_attr_tree_cachep, GFP_KERNEL); +} + +void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry) +{ + if (entry) + kmem_cache_free(hfsplus_attr_tree_cachep, entry); +} + +#define HFSPLUS_INVALID_ATTR_RECORD -1 + +static int hfsplus_attr_build_record(hfsplus_attr_entry *entry, int record_type, + u32 cnid, const void *value, size_t size) +{ + if (record_type == HFSPLUS_ATTR_FORK_DATA) { + /* + * Mac OS X supports only inline data attributes. + * Do nothing + */ + memset(entry, 0, sizeof(*entry)); + return sizeof(struct hfsplus_attr_fork_data); + } else if (record_type == HFSPLUS_ATTR_EXTENTS) { + /* + * Mac OS X supports only inline data attributes. + * Do nothing. + */ + memset(entry, 0, sizeof(*entry)); + return sizeof(struct hfsplus_attr_extents); + } else if (record_type == HFSPLUS_ATTR_INLINE_DATA) { + u16 len; + + memset(entry, 0, sizeof(struct hfsplus_attr_inline_data)); + entry->inline_data.record_type = cpu_to_be32(record_type); + if (size <= HFSPLUS_MAX_INLINE_DATA_SIZE) + len = size; + else + return HFSPLUS_INVALID_ATTR_RECORD; + entry->inline_data.length = cpu_to_be16(len); + memcpy(entry->inline_data.raw_bytes, value, len); + /* + * Align len on two-byte boundary. + * It needs to add pad byte if we have odd len. + */ + len = round_up(len, 2); + return offsetof(struct hfsplus_attr_inline_data, raw_bytes) + + len; + } else /* invalid input */ + memset(entry, 0, sizeof(*entry)); + + return HFSPLUS_INVALID_ATTR_RECORD; +} + +int hfsplus_find_attr(struct super_block *sb, u32 cnid, + const char *name, struct hfs_find_data *fd) +{ + int err = 0; + + dprint(DBG_ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid); + + if (!HFSPLUS_SB(sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + if (name) { + err = hfsplus_attr_build_key(sb, fd->search_key, cnid, name); + if (err) + goto failed_find_attr; + err = hfs_brec_find(fd, hfs_find_rec_by_key); + if (err) + goto failed_find_attr; + } else { + err = hfsplus_attr_build_key(sb, fd->search_key, cnid, NULL); + if (err) + goto failed_find_attr; + err = hfs_brec_find(fd, hfs_find_1st_rec_by_cnid); + if (err) + goto failed_find_attr; + } + +failed_find_attr: + return err; +} + +int hfsplus_attr_exists(struct inode *inode, const char *name) +{ + int err = 0; + struct super_block *sb = inode->i_sb; + struct hfs_find_data fd; + + if (!HFSPLUS_SB(sb)->attr_tree) + return 0; + + err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd); + if (err) + return 0; + + err = hfsplus_find_attr(sb, inode->i_ino, name, &fd); + if (err) + goto attr_not_found; + + hfs_find_exit(&fd); + return 1; + +attr_not_found: + hfs_find_exit(&fd); + return 0; +} + +int hfsplus_create_attr(struct inode *inode, + const char *name, + const void *value, size_t size) +{ + struct super_block *sb = inode->i_sb; + struct hfs_find_data fd; + hfsplus_attr_entry *entry_ptr; + int entry_size; + int err; + + dprint(DBG_ATTR_MOD, "create_attr: %s,%ld\n", + name ? name : NULL, inode->i_ino); + + if (!HFSPLUS_SB(sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + entry_ptr = hfsplus_alloc_attr_entry(); + if (!entry_ptr) + return -ENOMEM; + + err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd); + if (err) + goto failed_init_create_attr; + + if (name) { + err = hfsplus_attr_build_key(sb, fd.search_key, + inode->i_ino, name); + if (err) + goto failed_create_attr; + } else { + err = -EINVAL; + goto failed_create_attr; + } + + /* Mac OS X supports only inline data attributes. */ + entry_size = hfsplus_attr_build_record(entry_ptr, + HFSPLUS_ATTR_INLINE_DATA, + inode->i_ino, + value, size); + if (entry_size == HFSPLUS_INVALID_ATTR_RECORD) { + err = -EINVAL; + goto failed_create_attr; + } + + err = hfs_brec_find(&fd, hfs_find_rec_by_key); + if (err != -ENOENT) { + if (!err) + err = -EEXIST; + goto failed_create_attr; + } + + err = hfs_brec_insert(&fd, entry_ptr, entry_size); + if (err) + goto failed_create_attr; + + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY); + +failed_create_attr: + hfs_find_exit(&fd); + +failed_init_create_attr: + hfsplus_destroy_attr_entry(entry_ptr); + return err; +} + +static int __hfsplus_delete_attr(struct inode *inode, u32 cnid, + struct hfs_find_data *fd) +{ + int err = 0; + __be32 found_cnid, record_type; + + hfs_bnode_read(fd->bnode, &found_cnid, + fd->keyoffset + + offsetof(struct hfsplus_attr_key, cnid), + sizeof(__be32)); + if (cnid != be32_to_cpu(found_cnid)) + return -ENOENT; + + hfs_bnode_read(fd->bnode, &record_type, + fd->entryoffset, sizeof(record_type)); + + switch (be32_to_cpu(record_type)) { + case HFSPLUS_ATTR_INLINE_DATA: + /* All is OK. Do nothing. */ + break; + case HFSPLUS_ATTR_FORK_DATA: + case HFSPLUS_ATTR_EXTENTS: + printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + return -EOPNOTSUPP; + default: + printk(KERN_ERR "hfs: invalid extended attribute record\n"); + return -ENOENT; + } + + err = hfs_brec_remove(fd); + if (err) + return err; + + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY); + return err; +} + +int hfsplus_delete_attr(struct inode *inode, const char *name) +{ + int err = 0; + struct super_block *sb = inode->i_sb; + struct hfs_find_data fd; + + dprint(DBG_ATTR_MOD, "delete_attr: %s,%ld\n", + name ? name : NULL, inode->i_ino); + + if (!HFSPLUS_SB(sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd); + if (err) + return err; + + if (name) { + err = hfsplus_attr_build_key(sb, fd.search_key, + inode->i_ino, name); + if (err) + goto out; + } else { + printk(KERN_ERR "hfs: invalid extended attribute name\n"); + err = -EINVAL; + goto out; + } + + err = hfs_brec_find(&fd, hfs_find_rec_by_key); + if (err) + goto out; + + err = __hfsplus_delete_attr(inode, inode->i_ino, &fd); + if (err) + goto out; + +out: + hfs_find_exit(&fd); + return err; +} + +int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid) +{ + int err = 0; + struct hfs_find_data fd; + + dprint(DBG_ATTR_MOD, "delete_all_attrs: %d\n", cnid); + + if (!HFSPLUS_SB(dir->i_sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + err = hfs_find_init(HFSPLUS_SB(dir->i_sb)->attr_tree, &fd); + if (err) + return err; + + for (;;) { + err = hfsplus_find_attr(dir->i_sb, cnid, NULL, &fd); + if (err) { + if (err != -ENOENT) + printk(KERN_ERR "hfs: xattr search failed.\n"); + goto end_delete_all; + } + + err = __hfsplus_delete_attr(dir, cnid, &fd); + if (err) + goto end_delete_all; + } + +end_delete_all: + hfs_find_exit(&fd); + return err; +} diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c index 5d799c13205f..d73c98d1ee99 100644 --- a/fs/hfsplus/bfind.c +++ b/fs/hfsplus/bfind.c @@ -24,7 +24,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - mutex_lock(&tree->tree_lock); + switch (tree->cnid) { + case HFSPLUS_CAT_CNID: + mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); + break; + case HFSPLUS_EXT_CNID: + mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); + break; + case HFSPLUS_ATTR_CNID: + mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); + break; + default: + BUG(); + } return 0; } @@ -38,15 +50,73 @@ void hfs_find_exit(struct hfs_find_data *fd) fd->tree = NULL; } -/* Find the record in bnode that best matches key (not greater than...)*/ -int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) +int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, + struct hfs_find_data *fd, + int *begin, + int *end, + int *cur_rec) +{ + __be32 cur_cnid, search_cnid; + + if (bnode->tree->cnid == HFSPLUS_EXT_CNID) { + cur_cnid = fd->key->ext.cnid; + search_cnid = fd->search_key->ext.cnid; + } else if (bnode->tree->cnid == HFSPLUS_CAT_CNID) { + cur_cnid = fd->key->cat.parent; + search_cnid = fd->search_key->cat.parent; + } else if (bnode->tree->cnid == HFSPLUS_ATTR_CNID) { + cur_cnid = fd->key->attr.cnid; + search_cnid = fd->search_key->attr.cnid; + } else + BUG(); + + if (cur_cnid == search_cnid) { + (*end) = (*cur_rec); + if ((*begin) == (*end)) + return 1; + } else { + if (be32_to_cpu(cur_cnid) < be32_to_cpu(search_cnid)) + (*begin) = (*cur_rec) + 1; + else + (*end) = (*cur_rec) - 1; + } + + return 0; +} + +int hfs_find_rec_by_key(struct hfs_bnode *bnode, + struct hfs_find_data *fd, + int *begin, + int *end, + int *cur_rec) { int cmpval; + + cmpval = bnode->tree->keycmp(fd->key, fd->search_key); + if (!cmpval) { + (*end) = (*cur_rec); + return 1; + } + if (cmpval < 0) + (*begin) = (*cur_rec) + 1; + else + *(end) = (*cur_rec) - 1; + + return 0; +} + +/* Find the record in bnode that best matches key (not greater than...)*/ +int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd, + search_strategy_t rec_found) +{ u16 off, len, keylen; int rec; int b, e; int res; + if (!rec_found) + BUG(); + b = 0; e = bnode->num_recs - 1; res = -ENOENT; @@ -59,17 +129,12 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); - cmpval = bnode->tree->keycmp(fd->key, fd->search_key); - if (!cmpval) { - e = rec; + if (rec_found(bnode, fd, &b, &e, &rec)) { res = 0; goto done; } - if (cmpval < 0) - b = rec + 1; - else - e = rec - 1; } while (b <= e); + if (rec != e && e >= 0) { len = hfs_brec_lenoff(bnode, e, &off); keylen = hfs_brec_keylen(bnode, e); @@ -79,19 +144,21 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) } hfs_bnode_read(bnode, fd->key, off, keylen); } + done: fd->record = e; fd->keyoffset = off; fd->keylength = keylen; fd->entryoffset = off + keylen; fd->entrylength = len - keylen; + fail: return res; } /* Traverse a B*Tree from the root to a leaf finding best fit to key */ /* Return allocated copy of node found, set recnum to best record */ -int hfs_brec_find(struct hfs_find_data *fd) +int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare) { struct hfs_btree *tree; struct hfs_bnode *bnode; @@ -122,7 +189,7 @@ int hfs_brec_find(struct hfs_find_data *fd) goto invalid; bnode->parent = parent; - res = __hfs_brec_find(bnode, fd); + res = __hfs_brec_find(bnode, fd, do_key_compare); if (!height) break; if (fd->record < 0) @@ -149,7 +216,7 @@ int hfs_brec_read(struct hfs_find_data *fd, void *rec, int rec_len) { int res; - res = hfs_brec_find(fd); + res = hfs_brec_find(fd, hfs_find_rec_by_key); if (res) return res; if (fd->entrylength > rec_len) diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 1c42cc5b899f..5c125ce6bd72 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -62,7 +62,8 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) tree = node->tree; if (node->type == HFS_NODE_LEAF || - tree->attributes & HFS_TREE_VARIDXKEYS) + tree->attributes & HFS_TREE_VARIDXKEYS || + node->tree->cnid == HFSPLUS_ATTR_CNID) key_len = hfs_bnode_read_u16(node, off) + 2; else key_len = tree->max_key_len + 2; @@ -314,7 +315,8 @@ void hfs_bnode_dump(struct hfs_bnode *node) if (i && node->type == HFS_NODE_INDEX) { int tmp; - if (node->tree->attributes & HFS_TREE_VARIDXKEYS) + if (node->tree->attributes & HFS_TREE_VARIDXKEYS || + node->tree->cnid == HFSPLUS_ATTR_CNID) tmp = hfs_bnode_read_u16(node, key_off) + 2; else tmp = node->tree->max_key_len + 2; diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 2a734cfccc92..298d4e45604b 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -36,7 +36,8 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) return 0; if ((node->type == HFS_NODE_INDEX) && - !(node->tree->attributes & HFS_TREE_VARIDXKEYS)) { + !(node->tree->attributes & HFS_TREE_VARIDXKEYS) && + (node->tree->cnid != HFSPLUS_ATTR_CNID)) { retval = node->tree->max_key_len + 2; } else { recoff = hfs_bnode_read_u16(node, @@ -151,12 +152,13 @@ skip: /* get index key */ hfs_bnode_read_key(new_node, fd->search_key, 14); - __hfs_brec_find(fd->bnode, fd); + __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key); hfs_bnode_put(new_node); new_node = NULL; - if (tree->attributes & HFS_TREE_VARIDXKEYS) + if ((tree->attributes & HFS_TREE_VARIDXKEYS) || + (tree->cnid == HFSPLUS_ATTR_CNID)) key_len = be16_to_cpu(fd->search_key->key_len) + 2; else { fd->search_key->key_len = @@ -201,7 +203,7 @@ again: hfs_bnode_put(node); node = fd->bnode = parent; - __hfs_brec_find(node, fd); + __hfs_brec_find(node, fd, hfs_find_rec_by_key); goto again; } hfs_bnode_write_u16(node, @@ -367,12 +369,13 @@ again: parent = hfs_bnode_find(tree, node->parent); if (IS_ERR(parent)) return PTR_ERR(parent); - __hfs_brec_find(parent, fd); + __hfs_brec_find(parent, fd, hfs_find_rec_by_key); hfs_bnode_dump(parent); rec = fd->record; /* size difference between old and new key */ - if (tree->attributes & HFS_TREE_VARIDXKEYS) + if ((tree->attributes & HFS_TREE_VARIDXKEYS) || + (tree->cnid == HFSPLUS_ATTR_CNID)) newkeylen = hfs_bnode_read_u16(node, 14) + 2; else fd->keylength = newkeylen = tree->max_key_len + 2; @@ -427,7 +430,7 @@ skip: hfs_bnode_read_key(new_node, fd->search_key, 14); cnid = cpu_to_be32(new_node->this); - __hfs_brec_find(fd->bnode, fd); + __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key); hfs_brec_insert(fd, &cnid, sizeof(cnid)); hfs_bnode_put(fd->bnode); hfs_bnode_put(new_node); @@ -495,13 +498,15 @@ static int hfs_btree_inc_height(struct hfs_btree *tree) /* insert old root idx into new root */ node->parent = tree->root; if (node->type == HFS_NODE_LEAF || - tree->attributes & HFS_TREE_VARIDXKEYS) + tree->attributes & HFS_TREE_VARIDXKEYS || + tree->cnid == HFSPLUS_ATTR_CNID) key_size = hfs_bnode_read_u16(node, 14) + 2; else key_size = tree->max_key_len + 2; hfs_bnode_copy(new_node, 14, node, 14, key_size); - if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) { + if (!(tree->attributes & HFS_TREE_VARIDXKEYS) && + (tree->cnid != HFSPLUS_ATTR_CNID)) { key_size = tree->max_key_len + 2; hfs_bnode_write_u16(new_node, 14, tree->max_key_len); } diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 685d07d0ed18..efb689c21a95 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -98,6 +98,14 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags); } break; + case HFSPLUS_ATTR_CNID: + if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) { + printk(KERN_ERR "hfs: invalid attributes max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + tree->keycmp = hfsplus_attr_bin_cmp_key; + break; default: printk(KERN_ERR "hfs: unknown B*Tree requested\n"); goto fail_page; diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 798d9c4c5e71..840d71edd193 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -45,7 +45,8 @@ void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key, key->cat.parent = cpu_to_be32(parent); if (str) { - hfsplus_asc2uni(sb, &key->cat.name, str->name, str->len); + hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN, + str->name, str->len); len = be16_to_cpu(key->cat.name.length); } else { key->cat.name.length = 0; @@ -167,7 +168,8 @@ static int hfsplus_fill_cat_thread(struct super_block *sb, entry->type = cpu_to_be16(type); entry->thread.reserved = 0; entry->thread.parentID = cpu_to_be32(parentid); - hfsplus_asc2uni(sb, &entry->thread.nodeName, str->name, str->len); + hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN, + str->name, str->len); return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2; } @@ -198,7 +200,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid, hfsplus_cat_build_key_uni(fd->search_key, be32_to_cpu(tmp.thread.parentID), &tmp.thread.nodeName); - return hfs_brec_find(fd); + return hfs_brec_find(fd, hfs_find_rec_by_key); } int hfsplus_create_cat(u32 cnid, struct inode *dir, @@ -221,7 +223,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, S_ISDIR(inode->i_mode) ? HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD, dir->i_ino, str); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; @@ -233,7 +235,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); entry_size = hfsplus_cat_build_record(&entry, cnid, inode); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { /* panic? */ if (!err) @@ -253,7 +255,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, err1: hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); - if (!hfs_brec_find(&fd)) + if (!hfs_brec_find(&fd, hfs_find_rec_by_key)) hfs_brec_remove(&fd); err2: hfs_find_exit(&fd); @@ -279,7 +281,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) int len; hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -296,7 +298,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) } else hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -326,7 +328,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) goto out; hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -337,6 +339,12 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) dir->i_size--; dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); + + if (type == HFSPLUS_FILE || type == HFSPLUS_FOLDER) { + if (HFSPLUS_SB(sb)->attr_tree) + hfsplus_delete_all_attrs(dir, cnid); + } + out: hfs_find_exit(&fd); @@ -363,7 +371,7 @@ int hfsplus_rename_cat(u32 cnid, /* find the old dir entry and read the data */ hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); - err = hfs_brec_find(&src_fd); + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) { @@ -376,7 +384,7 @@ int hfsplus_rename_cat(u32 cnid, /* create new dir entry with the data from the old entry */ hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name); - err = hfs_brec_find(&dst_fd); + err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; @@ -391,7 +399,7 @@ int hfsplus_rename_cat(u32 cnid, /* finally remove the old entry */ hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); - err = hfs_brec_find(&src_fd); + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; err = hfs_brec_remove(&src_fd); @@ -402,7 +410,7 @@ int hfsplus_rename_cat(u32 cnid, /* remove old thread entry */ hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL); - err = hfs_brec_find(&src_fd); + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; type = hfs_bnode_read_u16(src_fd.bnode, src_fd.entryoffset); @@ -414,7 +422,7 @@ int hfsplus_rename_cat(u32 cnid, hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL); entry_size = hfsplus_fill_cat_thread(sb, &entry, type, dst_dir->i_ino, dst_name); - err = hfs_brec_find(&dst_fd); + err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 6b9f921ef2fa..47699d87bc33 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -15,6 +15,7 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" +#include "xattr.h" static inline void hfsplus_instantiate(struct dentry *dentry, struct inode *inode, u32 cnid) @@ -138,7 +139,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) if (err) return err; hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -421,6 +422,15 @@ static int hfsplus_symlink(struct inode *dir, struct dentry *dentry, if (res) goto out_err; + res = hfsplus_init_inode_security(inode, dir, &dentry->d_name); + if (res == -EOPNOTSUPP) + res = 0; /* Operation is not supported. */ + else if (res) { + /* Try to delete anyway without error analysis. */ + hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name); + goto out_err; + } + hfsplus_instantiate(dentry, inode, inode->i_ino); mark_inode_dirty(inode); goto out; @@ -450,15 +460,26 @@ static int hfsplus_mknod(struct inode *dir, struct dentry *dentry, init_special_inode(inode, mode, rdev); res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode); - if (res) { - clear_nlink(inode); - hfsplus_delete_inode(inode); - iput(inode); - goto out; + if (res) + goto failed_mknod; + + res = hfsplus_init_inode_security(inode, dir, &dentry->d_name); + if (res == -EOPNOTSUPP) + res = 0; /* Operation is not supported. */ + else if (res) { + /* Try to delete anyway without error analysis. */ + hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name); + goto failed_mknod; } hfsplus_instantiate(dentry, inode, inode->i_ino); mark_inode_dirty(inode); + goto out; + +failed_mknod: + clear_nlink(inode); + hfsplus_delete_inode(inode); + iput(inode); out: mutex_unlock(&sbi->vh_mutex); return res; @@ -499,15 +520,19 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry, } const struct inode_operations hfsplus_dir_inode_operations = { - .lookup = hfsplus_lookup, - .create = hfsplus_create, - .link = hfsplus_link, - .unlink = hfsplus_unlink, - .mkdir = hfsplus_mkdir, - .rmdir = hfsplus_rmdir, - .symlink = hfsplus_symlink, - .mknod = hfsplus_mknod, - .rename = hfsplus_rename, + .lookup = hfsplus_lookup, + .create = hfsplus_create, + .link = hfsplus_link, + .unlink = hfsplus_unlink, + .mkdir = hfsplus_mkdir, + .rmdir = hfsplus_rmdir, + .symlink = hfsplus_symlink, + .mknod = hfsplus_mknod, + .rename = hfsplus_rename, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = hfsplus_listxattr, + .removexattr = hfsplus_removexattr, }; const struct file_operations hfsplus_dir_operations = { diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index eba76eab6d62..a94f0f779d5e 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -95,7 +95,7 @@ static void __hfsplus_ext_write_extent(struct inode *inode, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA); - res = hfs_brec_find(fd); + res = hfs_brec_find(fd, hfs_find_rec_by_key); if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) return; @@ -154,7 +154,7 @@ static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd, hfsplus_ext_build_key(fd->search_key, cnid, block, type); fd->key->ext.cnid = 0; - res = hfs_brec_find(fd); + res = hfs_brec_find(fd, hfs_find_rec_by_key); if (res && res != -ENOENT) return res; if (fd->key->ext.cnid != fd->search_key->ext.cnid || diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index a6da86b1b4c1..05b11f36024c 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -23,6 +23,7 @@ #define DBG_SUPER 0x00000010 #define DBG_EXTENT 0x00000020 #define DBG_BITMAP 0x00000040 +#define DBG_ATTR_MOD 0x00000080 #if 0 #define DBG_MASK (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD) @@ -46,6 +47,13 @@ typedef int (*btree_keycmp)(const hfsplus_btree_key *, #define NODE_HASH_SIZE 256 +/* B-tree mutex nested subclasses */ +enum hfsplus_btree_mutex_classes { + CATALOG_BTREE_MUTEX, + EXTENTS_BTREE_MUTEX, + ATTR_BTREE_MUTEX, +}; + /* An HFS+ BTree held in memory */ struct hfs_btree { struct super_block *sb; @@ -223,6 +231,7 @@ struct hfsplus_inode_info { #define HFSPLUS_I_CAT_DIRTY 1 /* has changes in the catalog tree */ #define HFSPLUS_I_EXT_DIRTY 2 /* has changes in the extent tree */ #define HFSPLUS_I_ALLOC_DIRTY 3 /* has changes in the allocation file */ +#define HFSPLUS_I_ATTR_DIRTY 4 /* has changes in the attributes tree */ #define HFSPLUS_IS_RSRC(inode) \ test_bit(HFSPLUS_I_RSRC, &HFSPLUS_I(inode)->flags) @@ -302,7 +311,7 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb) #define hfs_brec_remove hfsplus_brec_remove #define hfs_find_init hfsplus_find_init #define hfs_find_exit hfsplus_find_exit -#define __hfs_brec_find __hplusfs_brec_find +#define __hfs_brec_find __hfsplus_brec_find #define hfs_brec_find hfsplus_brec_find #define hfs_brec_read hfsplus_brec_read #define hfs_brec_goto hfsplus_brec_goto @@ -324,10 +333,33 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb) */ #define HFSPLUS_IOC_BLESS _IO('h', 0x80) +typedef int (*search_strategy_t)(struct hfs_bnode *, + struct hfs_find_data *, + int *, int *, int *); + /* * Functions in any *.c used in other files */ +/* attributes.c */ +int hfsplus_create_attr_tree_cache(void); +void hfsplus_destroy_attr_tree_cache(void); +hfsplus_attr_entry *hfsplus_alloc_attr_entry(void); +void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p); +int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *, + const hfsplus_btree_key *); +int hfsplus_attr_build_key(struct super_block *, hfsplus_btree_key *, + u32, const char *); +void hfsplus_attr_build_key_uni(hfsplus_btree_key *key, + u32 cnid, + struct hfsplus_attr_unistr *name); +int hfsplus_find_attr(struct super_block *, u32, + const char *, struct hfs_find_data *); +int hfsplus_attr_exists(struct inode *inode, const char *name); +int hfsplus_create_attr(struct inode *, const char *, const void *, size_t); +int hfsplus_delete_attr(struct inode *, const char *); +int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid); + /* bitmap.c */ int hfsplus_block_allocate(struct super_block *, u32, u32, u32 *); int hfsplus_block_free(struct super_block *, u32, u32); @@ -369,8 +401,15 @@ int hfs_brec_remove(struct hfs_find_data *); /* bfind.c */ int hfs_find_init(struct hfs_btree *, struct hfs_find_data *); void hfs_find_exit(struct hfs_find_data *); -int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *); -int hfs_brec_find(struct hfs_find_data *); +int hfs_find_1st_rec_by_cnid(struct hfs_bnode *, + struct hfs_find_data *, + int *, int *, int *); +int hfs_find_rec_by_key(struct hfs_bnode *, + struct hfs_find_data *, + int *, int *, int *); +int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *, + search_strategy_t); +int hfs_brec_find(struct hfs_find_data *, search_strategy_t); int hfs_brec_read(struct hfs_find_data *, void *, int); int hfs_brec_goto(struct hfs_find_data *, int); @@ -417,11 +456,6 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, /* ioctl.c */ long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); -int hfsplus_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size); -ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size); /* options.c */ int hfsplus_parse_options(char *, struct hfsplus_sb_info *); @@ -446,7 +480,7 @@ int hfsplus_strcmp(const struct hfsplus_unistr *, int hfsplus_uni2asc(struct super_block *, const struct hfsplus_unistr *, char *, int *); int hfsplus_asc2uni(struct super_block *, - struct hfsplus_unistr *, const char *, int); + struct hfsplus_unistr *, int, const char *, int); int hfsplus_hash_dentry(const struct dentry *dentry, const struct inode *inode, struct qstr *str); int hfsplus_compare_dentry(const struct dentry *parent, diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h index 921967e5abb1..452ede01b036 100644 --- a/fs/hfsplus/hfsplus_raw.h +++ b/fs/hfsplus/hfsplus_raw.h @@ -52,13 +52,23 @@ typedef __be32 hfsplus_cnid; typedef __be16 hfsplus_unichr; +#define HFSPLUS_MAX_STRLEN 255 +#define HFSPLUS_ATTR_MAX_STRLEN 127 + /* A "string" as used in filenames, etc. */ struct hfsplus_unistr { __be16 length; - hfsplus_unichr unicode[255]; + hfsplus_unichr unicode[HFSPLUS_MAX_STRLEN]; } __packed; -#define HFSPLUS_MAX_STRLEN 255 +/* + * A "string" is used in attributes file + * for name of extended attribute + */ +struct hfsplus_attr_unistr { + __be16 length; + hfsplus_unichr unicode[HFSPLUS_ATTR_MAX_STRLEN]; +} __packed; /* POSIX permissions */ struct hfsplus_perm { @@ -291,6 +301,8 @@ struct hfsplus_cat_file { /* File attribute bits */ #define HFSPLUS_FILE_LOCKED 0x0001 #define HFSPLUS_FILE_THREAD_EXISTS 0x0002 +#define HFSPLUS_XATTR_EXISTS 0x0004 +#define HFSPLUS_ACL_EXISTS 0x0008 /* HFS+ catalog thread (part of a cat_entry) */ struct hfsplus_cat_thread { @@ -327,11 +339,63 @@ struct hfsplus_ext_key { #define HFSPLUS_EXT_KEYLEN sizeof(struct hfsplus_ext_key) +#define HFSPLUS_XATTR_FINDER_INFO_NAME "com.apple.FinderInfo" +#define HFSPLUS_XATTR_ACL_NAME "com.apple.system.Security" + +#define HFSPLUS_ATTR_INLINE_DATA 0x10 +#define HFSPLUS_ATTR_FORK_DATA 0x20 +#define HFSPLUS_ATTR_EXTENTS 0x30 + +/* HFS+ attributes tree key */ +struct hfsplus_attr_key { + __be16 key_len; + __be16 pad; + hfsplus_cnid cnid; + __be32 start_block; + struct hfsplus_attr_unistr key_name; +} __packed; + +#define HFSPLUS_ATTR_KEYLEN sizeof(struct hfsplus_attr_key) + +/* HFS+ fork data attribute */ +struct hfsplus_attr_fork_data { + __be32 record_type; + __be32 reserved; + struct hfsplus_fork_raw the_fork; +} __packed; + +/* HFS+ extension attribute */ +struct hfsplus_attr_extents { + __be32 record_type; + __be32 reserved; + struct hfsplus_extent extents; +} __packed; + +#define HFSPLUS_MAX_INLINE_DATA_SIZE 3802 + +/* HFS+ attribute inline data */ +struct hfsplus_attr_inline_data { + __be32 record_type; + __be32 reserved1; + u8 reserved2[6]; + __be16 length; + u8 raw_bytes[HFSPLUS_MAX_INLINE_DATA_SIZE]; +} __packed; + +/* A data record in the attributes tree */ +typedef union { + __be32 record_type; + struct hfsplus_attr_fork_data fork_data; + struct hfsplus_attr_extents extents; + struct hfsplus_attr_inline_data inline_data; +} __packed hfsplus_attr_entry; + /* HFS+ generic BTree key */ typedef union { __be16 key_len; struct hfsplus_cat_key cat; struct hfsplus_ext_key ext; + struct hfsplus_attr_key attr; } __packed hfsplus_btree_key; #endif diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 799b336b59f9..0aff99fdeb16 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -14,9 +14,11 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> +#include <linux/aio.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" +#include "xattr.h" static int hfsplus_readpage(struct file *file, struct page *page) { @@ -348,6 +350,18 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, error = error2; } + if (test_and_clear_bit(HFSPLUS_I_ATTR_DIRTY, &hip->flags)) { + if (sbi->attr_tree) { + error2 = + filemap_write_and_wait( + sbi->attr_tree->inode->i_mapping); + if (!error) + error = error2; + } else { + printk(KERN_ERR "hfs: sync non-existent attributes tree\n"); + } + } + if (test_and_clear_bit(HFSPLUS_I_ALLOC_DIRTY, &hip->flags)) { error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping); if (!error) @@ -365,9 +379,10 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, static const struct inode_operations hfsplus_file_inode_operations = { .lookup = hfsplus_file_lookup, .setattr = hfsplus_setattr, - .setxattr = hfsplus_setxattr, - .getxattr = hfsplus_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = hfsplus_listxattr, + .removexattr = hfsplus_removexattr, }; static const struct file_operations hfsplus_file_operations = { diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 09addc8615fa..83a434d0c2e7 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -16,7 +16,6 @@ #include <linux/fs.h> #include <linux/mount.h> #include <linux/sched.h> -#include <linux/xattr.h> #include <asm/uaccess.h> #include "hfsplus_fs.h" @@ -151,110 +150,3 @@ long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return -ENOTTY; } } - -int hfsplus_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) -{ - struct inode *inode = dentry->d_inode; - struct hfs_find_data fd; - hfsplus_cat_entry entry; - struct hfsplus_cat_file *file; - int res; - - if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode)) - return -EOPNOTSUPP; - - res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); - if (res) - return res; - res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); - if (res) - goto out; - hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, - sizeof(struct hfsplus_cat_file)); - file = &entry.file; - - if (!strcmp(name, "hfs.type")) { - if (size == 4) - memcpy(&file->user_info.fdType, value, 4); - else - res = -ERANGE; - } else if (!strcmp(name, "hfs.creator")) { - if (size == 4) - memcpy(&file->user_info.fdCreator, value, 4); - else - res = -ERANGE; - } else - res = -EOPNOTSUPP; - if (!res) { - hfs_bnode_write(fd.bnode, &entry, fd.entryoffset, - sizeof(struct hfsplus_cat_file)); - hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); - } -out: - hfs_find_exit(&fd); - return res; -} - -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size) -{ - struct inode *inode = dentry->d_inode; - struct hfs_find_data fd; - hfsplus_cat_entry entry; - struct hfsplus_cat_file *file; - ssize_t res = 0; - - if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode)) - return -EOPNOTSUPP; - - if (size) { - res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); - if (res) - return res; - res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); - if (res) - goto out; - hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, - sizeof(struct hfsplus_cat_file)); - } - file = &entry.file; - - if (!strcmp(name, "hfs.type")) { - if (size >= 4) { - memcpy(value, &file->user_info.fdType, 4); - res = 4; - } else - res = size ? -ERANGE : 4; - } else if (!strcmp(name, "hfs.creator")) { - if (size >= 4) { - memcpy(value, &file->user_info.fdCreator, 4); - res = 4; - } else - res = size ? -ERANGE : 4; - } else - res = -EOPNOTSUPP; -out: - if (size) - hfs_find_exit(&fd); - return res; -} - -#define HFSPLUS_ATTRLIST_SIZE (sizeof("hfs.creator")+sizeof("hfs.type")) - -ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) -{ - struct inode *inode = dentry->d_inode; - - if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode)) - return -EOPNOTSUPP; - - if (!buffer || !size) - return HFSPLUS_ATTRLIST_SIZE; - if (size < HFSPLUS_ATTRLIST_SIZE) - return -ERANGE; - strcpy(buffer, "hfs.type"); - strcpy(buffer + sizeof("hfs.type"), "hfs.creator"); - - return HFSPLUS_ATTRLIST_SIZE; -} diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 796198d26553..974c26f96fae 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -20,6 +20,7 @@ static struct inode *hfsplus_alloc_inode(struct super_block *sb); static void hfsplus_destroy_inode(struct inode *inode); #include "hfsplus_fs.h" +#include "xattr.h" static int hfsplus_system_read_inode(struct inode *inode) { @@ -118,6 +119,7 @@ static int hfsplus_system_write_inode(struct inode *inode) case HFSPLUS_ATTR_CNID: fork = &vhdr->attr_file; tree = sbi->attr_tree; + break; default: return -EIO; } @@ -191,6 +193,12 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait) error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping); if (!error) error = error2; + if (sbi->attr_tree) { + error2 = + filemap_write_and_wait(sbi->attr_tree->inode->i_mapping); + if (!error) + error = error2; + } error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping); if (!error) error = error2; @@ -281,6 +289,7 @@ static void hfsplus_put_super(struct super_block *sb) hfsplus_sync_fs(sb, 1); } + hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); iput(sbi->alloc_file); @@ -477,12 +486,20 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) printk(KERN_ERR "hfs: failed to load catalog file\n"); goto out_close_ext_tree; } + if (vhdr->attr_file.total_blocks != 0) { + sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID); + if (!sbi->attr_tree) { + printk(KERN_ERR "hfs: failed to load attributes file\n"); + goto out_close_cat_tree; + } + } + sb->s_xattr = hfsplus_xattr_handlers; inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID); if (IS_ERR(inode)) { printk(KERN_ERR "hfs: failed to load allocation file\n"); err = PTR_ERR(inode); - goto out_close_cat_tree; + goto out_close_attr_tree; } sbi->alloc_file = inode; @@ -542,10 +559,27 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) } err = hfsplus_create_cat(sbi->hidden_dir->i_ino, root, &str, sbi->hidden_dir); - mutex_unlock(&sbi->vh_mutex); - if (err) + if (err) { + mutex_unlock(&sbi->vh_mutex); + goto out_put_hidden_dir; + } + + err = hfsplus_init_inode_security(sbi->hidden_dir, + root, &str); + if (err == -EOPNOTSUPP) + err = 0; /* Operation is not supported. */ + else if (err) { + /* + * Try to delete anyway without + * error analysis. + */ + hfsplus_delete_cat(sbi->hidden_dir->i_ino, + root, &str); + mutex_unlock(&sbi->vh_mutex); goto out_put_hidden_dir; + } + mutex_unlock(&sbi->vh_mutex); hfsplus_mark_inode_dirty(sbi->hidden_dir, HFSPLUS_I_CAT_DIRTY); } @@ -562,6 +596,8 @@ out_put_root: sb->s_root = NULL; out_put_alloc_file: iput(sbi->alloc_file); +out_close_attr_tree: + hfs_btree_close(sbi->attr_tree); out_close_cat_tree: hfs_btree_close(sbi->cat_tree); out_close_ext_tree: @@ -635,9 +671,20 @@ static int __init init_hfsplus_fs(void) hfsplus_init_once); if (!hfsplus_inode_cachep) return -ENOMEM; + err = hfsplus_create_attr_tree_cache(); + if (err) + goto destroy_inode_cache; err = register_filesystem(&hfsplus_fs_type); if (err) - kmem_cache_destroy(hfsplus_inode_cachep); + goto destroy_attr_tree_cache; + return 0; + +destroy_attr_tree_cache: + hfsplus_destroy_attr_tree_cache(); + +destroy_inode_cache: + kmem_cache_destroy(hfsplus_inode_cachep); + return err; } @@ -650,6 +697,7 @@ static void __exit exit_hfsplus_fs(void) * destroy cache. */ rcu_barrier(); + hfsplus_destroy_attr_tree_cache(); kmem_cache_destroy(hfsplus_inode_cachep); } diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c index a32998f29f0b..2c2e47dcfdd8 100644 --- a/fs/hfsplus/unicode.c +++ b/fs/hfsplus/unicode.c @@ -295,7 +295,8 @@ static inline u16 *decompose_unichar(wchar_t uc, int *size) return hfsplus_decompose_table + (off / 4); } -int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, +int hfsplus_asc2uni(struct super_block *sb, + struct hfsplus_unistr *ustr, int max_unistr_len, const char *astr, int len) { int size, dsize, decompose; @@ -303,7 +304,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, wchar_t c; decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags); - while (outlen < HFSPLUS_MAX_STRLEN && len > 0) { + while (outlen < max_unistr_len && len > 0) { size = asc2unichar(sb, astr, len, &c); if (decompose) @@ -311,7 +312,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, else dstr = NULL; if (dstr) { - if (outlen + dsize > HFSPLUS_MAX_STRLEN) + if (outlen + dsize > max_unistr_len) break; do { ustr->unicode[outlen++] = cpu_to_be16(*dstr++); diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c new file mode 100644 index 000000000000..e8a4b0815c61 --- /dev/null +++ b/fs/hfsplus/xattr.c @@ -0,0 +1,709 @@ +/* + * linux/fs/hfsplus/xattr.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Logic of processing extended attributes + */ + +#include "hfsplus_fs.h" +#include "xattr.h" + +const struct xattr_handler *hfsplus_xattr_handlers[] = { + &hfsplus_xattr_osx_handler, + &hfsplus_xattr_user_handler, + &hfsplus_xattr_trusted_handler, + &hfsplus_xattr_security_handler, + NULL +}; + +static int strcmp_xattr_finder_info(const char *name) +{ + if (name) { + return strncmp(name, HFSPLUS_XATTR_FINDER_INFO_NAME, + sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME)); + } + return -1; +} + +static int strcmp_xattr_acl(const char *name) +{ + if (name) { + return strncmp(name, HFSPLUS_XATTR_ACL_NAME, + sizeof(HFSPLUS_XATTR_ACL_NAME)); + } + return -1; +} + +static inline int is_known_namespace(const char *name) +{ + if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) && + strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && + strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && + strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) + return false; + + return true; +} + +static int can_set_xattr(struct inode *inode, const char *name, + const void *value, size_t value_len) +{ + if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) + return -EOPNOTSUPP; /* TODO: implement ACL support */ + + if (!strncmp(name, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN)) { + /* + * This makes sure that we aren't trying to set an + * attribute in a different namespace by prefixing it + * with "osx." + */ + if (is_known_namespace(name + XATTR_MAC_OSX_PREFIX_LEN)) + return -EOPNOTSUPP; + + return 0; + } + + /* + * Don't allow setting an attribute in an unknown namespace. + */ + if (strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) && + strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && + strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) + return -EOPNOTSUPP; + + return 0; +} + +int __hfsplus_setxattr(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + int err = 0; + struct hfs_find_data cat_fd; + hfsplus_cat_entry entry; + u16 cat_entry_flags, cat_entry_type; + u16 folder_finderinfo_len = sizeof(struct DInfo) + + sizeof(struct DXInfo); + u16 file_finderinfo_len = sizeof(struct FInfo) + + sizeof(struct FXInfo); + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + err = can_set_xattr(inode, name, value, size); + if (err) + return err; + + if (strncmp(name, XATTR_MAC_OSX_PREFIX, + XATTR_MAC_OSX_PREFIX_LEN) == 0) + name += XATTR_MAC_OSX_PREFIX_LEN; + + if (value == NULL) { + value = ""; + size = 0; + } + + err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return err; + } + + err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: catalog searching failed\n"); + goto end_setxattr; + } + + if (!strcmp_xattr_finder_info(name)) { + if (flags & XATTR_CREATE) { + printk(KERN_ERR "hfs: xattr exists yet\n"); + err = -EOPNOTSUPP; + goto end_setxattr; + } + hfs_bnode_read(cat_fd.bnode, &entry, cat_fd.entryoffset, + sizeof(hfsplus_cat_entry)); + if (be16_to_cpu(entry.type) == HFSPLUS_FOLDER) { + if (size == folder_finderinfo_len) { + memcpy(&entry.folder.user_info, value, + folder_finderinfo_len); + hfs_bnode_write(cat_fd.bnode, &entry, + cat_fd.entryoffset, + sizeof(struct hfsplus_cat_folder)); + hfsplus_mark_inode_dirty(inode, + HFSPLUS_I_CAT_DIRTY); + } else { + err = -ERANGE; + goto end_setxattr; + } + } else if (be16_to_cpu(entry.type) == HFSPLUS_FILE) { + if (size == file_finderinfo_len) { + memcpy(&entry.file.user_info, value, + file_finderinfo_len); + hfs_bnode_write(cat_fd.bnode, &entry, + cat_fd.entryoffset, + sizeof(struct hfsplus_cat_file)); + hfsplus_mark_inode_dirty(inode, + HFSPLUS_I_CAT_DIRTY); + } else { + err = -ERANGE; + goto end_setxattr; + } + } else { + err = -EOPNOTSUPP; + goto end_setxattr; + } + goto end_setxattr; + } + + if (!HFSPLUS_SB(inode->i_sb)->attr_tree) { + err = -EOPNOTSUPP; + goto end_setxattr; + } + + if (hfsplus_attr_exists(inode, name)) { + if (flags & XATTR_CREATE) { + printk(KERN_ERR "hfs: xattr exists yet\n"); + err = -EOPNOTSUPP; + goto end_setxattr; + } + err = hfsplus_delete_attr(inode, name); + if (err) + goto end_setxattr; + err = hfsplus_create_attr(inode, name, value, size); + if (err) + goto end_setxattr; + } else { + if (flags & XATTR_REPLACE) { + printk(KERN_ERR "hfs: cannot replace xattr\n"); + err = -EOPNOTSUPP; + goto end_setxattr; + } + err = hfsplus_create_attr(inode, name, value, size); + if (err) + goto end_setxattr; + } + + cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset); + if (cat_entry_type == HFSPLUS_FOLDER) { + cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode, + cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags)); + cat_entry_flags |= HFSPLUS_XATTR_EXISTS; + if (!strcmp_xattr_acl(name)) + cat_entry_flags |= HFSPLUS_ACL_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags), + cat_entry_flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else if (cat_entry_type == HFSPLUS_FILE) { + cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode, + cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags)); + cat_entry_flags |= HFSPLUS_XATTR_EXISTS; + if (!strcmp_xattr_acl(name)) + cat_entry_flags |= HFSPLUS_ACL_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags), + cat_entry_flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else { + printk(KERN_ERR "hfs: invalid catalog entry type\n"); + err = -EIO; + goto end_setxattr; + } + +end_setxattr: + hfs_find_exit(&cat_fd); + return err; +} + +static inline int is_osx_xattr(const char *xattr_name) +{ + return !is_known_namespace(xattr_name); +} + +static int name_len(const char *xattr_name, int xattr_name_len) +{ + int len = xattr_name_len + 1; + + if (is_osx_xattr(xattr_name)) + len += XATTR_MAC_OSX_PREFIX_LEN; + + return len; +} + +static int copy_name(char *buffer, const char *xattr_name, int name_len) +{ + int len = name_len; + int offset = 0; + + if (is_osx_xattr(xattr_name)) { + strncpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN); + offset += XATTR_MAC_OSX_PREFIX_LEN; + len += XATTR_MAC_OSX_PREFIX_LEN; + } + + strncpy(buffer + offset, xattr_name, name_len); + memset(buffer + offset + name_len, 0, 1); + len += 1; + + return len; +} + +static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry, + void *value, size_t size) +{ + ssize_t res = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + u16 entry_type; + u16 folder_rec_len = sizeof(struct DInfo) + sizeof(struct DXInfo); + u16 file_rec_len = sizeof(struct FInfo) + sizeof(struct FXInfo); + u16 record_len = max(folder_rec_len, file_rec_len); + u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)]; + u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)]; + + if (size >= record_len) { + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); + if (res) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return res; + } + res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); + if (res) + goto end_getxattr_finder_info; + entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset); + + if (entry_type == HFSPLUS_FOLDER) { + hfs_bnode_read(fd.bnode, folder_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_folder, user_info), + folder_rec_len); + memcpy(value, folder_finder_info, folder_rec_len); + res = folder_rec_len; + } else if (entry_type == HFSPLUS_FILE) { + hfs_bnode_read(fd.bnode, file_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_file, user_info), + file_rec_len); + memcpy(value, file_finder_info, file_rec_len); + res = file_rec_len; + } else { + res = -EOPNOTSUPP; + goto end_getxattr_finder_info; + } + } else + res = size ? -ERANGE : record_len; + +end_getxattr_finder_info: + if (size >= record_len) + hfs_find_exit(&fd); + return res; +} + +ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size) +{ + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + hfsplus_attr_entry *entry; + __be32 xattr_record_type; + u32 record_type; + u16 record_length = 0; + ssize_t res = 0; + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + if (strncmp(name, XATTR_MAC_OSX_PREFIX, + XATTR_MAC_OSX_PREFIX_LEN) == 0) { + /* skip "osx." prefix */ + name += XATTR_MAC_OSX_PREFIX_LEN; + /* + * Don't allow retrieving properly prefixed attributes + * by prepending them with "osx." + */ + if (is_known_namespace(name)) + return -EOPNOTSUPP; + } + + if (!strcmp_xattr_finder_info(name)) + return hfsplus_getxattr_finder_info(dentry, value, size); + + if (!HFSPLUS_SB(inode->i_sb)->attr_tree) + return -EOPNOTSUPP; + + entry = hfsplus_alloc_attr_entry(); + if (!entry) { + printk(KERN_ERR "hfs: can't allocate xattr entry\n"); + return -ENOMEM; + } + + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); + if (res) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + goto failed_getxattr_init; + } + + res = hfsplus_find_attr(inode->i_sb, inode->i_ino, name, &fd); + if (res) { + if (res == -ENOENT) + res = -ENODATA; + else + printk(KERN_ERR "hfs: xattr searching failed\n"); + goto out; + } + + hfs_bnode_read(fd.bnode, &xattr_record_type, + fd.entryoffset, sizeof(xattr_record_type)); + record_type = be32_to_cpu(xattr_record_type); + if (record_type == HFSPLUS_ATTR_INLINE_DATA) { + record_length = hfs_bnode_read_u16(fd.bnode, + fd.entryoffset + + offsetof(struct hfsplus_attr_inline_data, + length)); + if (record_length > HFSPLUS_MAX_INLINE_DATA_SIZE) { + printk(KERN_ERR "hfs: invalid xattr record size\n"); + res = -EIO; + goto out; + } + } else if (record_type == HFSPLUS_ATTR_FORK_DATA || + record_type == HFSPLUS_ATTR_EXTENTS) { + printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + res = -EOPNOTSUPP; + goto out; + } else { + printk(KERN_ERR "hfs: invalid xattr record\n"); + res = -EIO; + goto out; + } + + if (size) { + hfs_bnode_read(fd.bnode, entry, fd.entryoffset, + offsetof(struct hfsplus_attr_inline_data, + raw_bytes) + record_length); + } + + if (size >= record_length) { + memcpy(value, entry->inline_data.raw_bytes, record_length); + res = record_length; + } else + res = size ? -ERANGE : record_length; + +out: + hfs_find_exit(&fd); + +failed_getxattr_init: + hfsplus_destroy_attr_entry(entry); + return res; +} + +static inline int can_list(const char *xattr_name) +{ + if (!xattr_name) + return 0; + + return strncmp(xattr_name, XATTR_TRUSTED_PREFIX, + XATTR_TRUSTED_PREFIX_LEN) || + capable(CAP_SYS_ADMIN); +} + +static ssize_t hfsplus_listxattr_finder_info(struct dentry *dentry, + char *buffer, size_t size) +{ + ssize_t res = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + u16 entry_type; + u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)]; + u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)]; + unsigned long len, found_bit; + int xattr_name_len, symbols_count; + + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); + if (res) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return res; + } + + res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); + if (res) + goto end_listxattr_finder_info; + + entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset); + if (entry_type == HFSPLUS_FOLDER) { + len = sizeof(struct DInfo) + sizeof(struct DXInfo); + hfs_bnode_read(fd.bnode, folder_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_folder, user_info), + len); + found_bit = find_first_bit((void *)folder_finder_info, len*8); + } else if (entry_type == HFSPLUS_FILE) { + len = sizeof(struct FInfo) + sizeof(struct FXInfo); + hfs_bnode_read(fd.bnode, file_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_file, user_info), + len); + found_bit = find_first_bit((void *)file_finder_info, len*8); + } else { + res = -EOPNOTSUPP; + goto end_listxattr_finder_info; + } + + if (found_bit >= (len*8)) + res = 0; + else { + symbols_count = sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME) - 1; + xattr_name_len = + name_len(HFSPLUS_XATTR_FINDER_INFO_NAME, symbols_count); + if (!buffer || !size) { + if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME)) + res = xattr_name_len; + } else if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME)) { + if (size < xattr_name_len) + res = -ERANGE; + else { + res = copy_name(buffer, + HFSPLUS_XATTR_FINDER_INFO_NAME, + symbols_count); + } + } + } + +end_listxattr_finder_info: + hfs_find_exit(&fd); + + return res; +} + +ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + ssize_t err; + ssize_t res = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + u16 key_len = 0; + struct hfsplus_attr_key attr_key; + char strbuf[HFSPLUS_ATTR_MAX_STRLEN + + XATTR_MAC_OSX_PREFIX_LEN + 1] = {0}; + int xattr_name_len; + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + res = hfsplus_listxattr_finder_info(dentry, buffer, size); + if (res < 0) + return res; + else if (!HFSPLUS_SB(inode->i_sb)->attr_tree) + return (res == 0) ? -EOPNOTSUPP : res; + + err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); + if (err) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return err; + } + + err = hfsplus_find_attr(inode->i_sb, inode->i_ino, NULL, &fd); + if (err) { + if (err == -ENOENT) { + if (res == 0) + res = -ENODATA; + goto end_listxattr; + } else { + res = err; + goto end_listxattr; + } + } + + for (;;) { + key_len = hfs_bnode_read_u16(fd.bnode, fd.keyoffset); + if (key_len == 0 || key_len > fd.tree->max_key_len) { + printk(KERN_ERR "hfs: invalid xattr key length: %d\n", + key_len); + res = -EIO; + goto end_listxattr; + } + + hfs_bnode_read(fd.bnode, &attr_key, + fd.keyoffset, key_len + sizeof(key_len)); + + if (be32_to_cpu(attr_key.cnid) != inode->i_ino) + goto end_listxattr; + + xattr_name_len = HFSPLUS_ATTR_MAX_STRLEN; + if (hfsplus_uni2asc(inode->i_sb, + (const struct hfsplus_unistr *)&fd.key->attr.key_name, + strbuf, &xattr_name_len)) { + printk(KERN_ERR "hfs: unicode conversion failed\n"); + res = -EIO; + goto end_listxattr; + } + + if (!buffer || !size) { + if (can_list(strbuf)) + res += name_len(strbuf, xattr_name_len); + } else if (can_list(strbuf)) { + if (size < (res + name_len(strbuf, xattr_name_len))) { + res = -ERANGE; + goto end_listxattr; + } else + res += copy_name(buffer + res, + strbuf, xattr_name_len); + } + + if (hfs_brec_goto(&fd, 1)) + goto end_listxattr; + } + +end_listxattr: + hfs_find_exit(&fd); + return res; +} + +int hfsplus_removexattr(struct dentry *dentry, const char *name) +{ + int err = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data cat_fd; + u16 flags; + u16 cat_entry_type; + int is_xattr_acl_deleted = 0; + int is_all_xattrs_deleted = 0; + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + if (!HFSPLUS_SB(inode->i_sb)->attr_tree) + return -EOPNOTSUPP; + + err = can_set_xattr(inode, name, NULL, 0); + if (err) + return err; + + if (strncmp(name, XATTR_MAC_OSX_PREFIX, + XATTR_MAC_OSX_PREFIX_LEN) == 0) + name += XATTR_MAC_OSX_PREFIX_LEN; + + if (!strcmp_xattr_finder_info(name)) + return -EOPNOTSUPP; + + err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return err; + } + + err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: catalog searching failed\n"); + goto end_removexattr; + } + + err = hfsplus_delete_attr(inode, name); + if (err) + goto end_removexattr; + + is_xattr_acl_deleted = !strcmp_xattr_acl(name); + is_all_xattrs_deleted = !hfsplus_attr_exists(inode, NULL); + + if (!is_xattr_acl_deleted && !is_all_xattrs_deleted) + goto end_removexattr; + + cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset); + + if (cat_entry_type == HFSPLUS_FOLDER) { + flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags)); + if (is_xattr_acl_deleted) + flags &= ~HFSPLUS_ACL_EXISTS; + if (is_all_xattrs_deleted) + flags &= ~HFSPLUS_XATTR_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags), + flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else if (cat_entry_type == HFSPLUS_FILE) { + flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags)); + if (is_xattr_acl_deleted) + flags &= ~HFSPLUS_ACL_EXISTS; + if (is_all_xattrs_deleted) + flags &= ~HFSPLUS_XATTR_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags), + flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else { + printk(KERN_ERR "hfs: invalid catalog entry type\n"); + err = -EIO; + goto end_removexattr; + } + +end_removexattr: + hfs_find_exit(&cat_fd); + return err; +} + +static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + + XATTR_MAC_OSX_PREFIX_LEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); + strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + + XATTR_MAC_OSX_PREFIX_LEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); + strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +const struct xattr_handler hfsplus_xattr_osx_handler = { + .prefix = XATTR_MAC_OSX_PREFIX, + .list = hfsplus_osx_listxattr, + .get = hfsplus_osx_getxattr, + .set = hfsplus_osx_setxattr, +}; diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h new file mode 100644 index 000000000000..847b695b984d --- /dev/null +++ b/fs/hfsplus/xattr.h @@ -0,0 +1,60 @@ +/* + * linux/fs/hfsplus/xattr.h + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Logic of processing extended attributes + */ + +#ifndef _LINUX_HFSPLUS_XATTR_H +#define _LINUX_HFSPLUS_XATTR_H + +#include <linux/xattr.h> + +extern const struct xattr_handler hfsplus_xattr_osx_handler; +extern const struct xattr_handler hfsplus_xattr_user_handler; +extern const struct xattr_handler hfsplus_xattr_trusted_handler; +/*extern const struct xattr_handler hfsplus_xattr_acl_access_handler;*/ +/*extern const struct xattr_handler hfsplus_xattr_acl_default_handler;*/ +extern const struct xattr_handler hfsplus_xattr_security_handler; + +extern const struct xattr_handler *hfsplus_xattr_handlers[]; + +int __hfsplus_setxattr(struct inode *inode, const char *name, + const void *value, size_t size, int flags); + +static inline int hfsplus_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + return __hfsplus_setxattr(dentry->d_inode, name, value, size, flags); +} + +ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size); + +ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size); + +int hfsplus_removexattr(struct dentry *dentry, const char *name); + +int hfsplus_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr); + +static inline int hfsplus_init_acl(struct inode *inode, struct inode *dir) +{ + /*TODO: implement*/ + return 0; +} + +static inline int hfsplus_init_inode_security(struct inode *inode, + struct inode *dir, + const struct qstr *qstr) +{ + int err; + + err = hfsplus_init_acl(inode, dir); + if (!err) + err = hfsplus_init_security(inode, dir, qstr); + return err; +} + +#endif diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c new file mode 100644 index 000000000000..83b842f113c5 --- /dev/null +++ b/fs/hfsplus/xattr_security.c @@ -0,0 +1,104 @@ +/* + * linux/fs/hfsplus/xattr_trusted.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for storing security labels as extended attributes. + */ + +#include <linux/security.h> +#include "hfsplus_fs.h" +#include "xattr.h" + +static int hfsplus_security_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_SECURITY_PREFIX); + strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_security_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_SECURITY_PREFIX); + strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +static int hfsplus_initxattrs(struct inode *inode, + const struct xattr *xattr_array, + void *fs_info) +{ + const struct xattr *xattr; + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t xattr_name_len; + int err = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + xattr_name_len = strlen(xattr->name); + + if (xattr_name_len == 0) + continue; + + if (xattr_name_len + XATTR_SECURITY_PREFIX_LEN > + HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_SECURITY_PREFIX); + strcpy(xattr_name + + XATTR_SECURITY_PREFIX_LEN, xattr->name); + memset(xattr_name + + XATTR_SECURITY_PREFIX_LEN + xattr_name_len, 0, 1); + + err = __hfsplus_setxattr(inode, xattr_name, + xattr->value, xattr->value_len, 0); + if (err) + break; + } + return err; +} + +int hfsplus_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &hfsplus_initxattrs, NULL); +} + +const struct xattr_handler hfsplus_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .list = hfsplus_security_listxattr, + .get = hfsplus_security_getxattr, + .set = hfsplus_security_setxattr, +}; diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c new file mode 100644 index 000000000000..426cee277542 --- /dev/null +++ b/fs/hfsplus/xattr_trusted.c @@ -0,0 +1,63 @@ +/* + * linux/fs/hfsplus/xattr_trusted.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for trusted extended attributes. + */ + +#include "hfsplus_fs.h" +#include "xattr.h" + +static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_TRUSTED_PREFIX); + strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_TRUSTED_PREFIX); + strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +const struct xattr_handler hfsplus_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .list = hfsplus_trusted_listxattr, + .get = hfsplus_trusted_getxattr, + .set = hfsplus_trusted_setxattr, +}; diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c new file mode 100644 index 000000000000..e34016561ae0 --- /dev/null +++ b/fs/hfsplus/xattr_user.c @@ -0,0 +1,63 @@ +/* + * linux/fs/hfsplus/xattr_user.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for user extended attributes. + */ + +#include "hfsplus_fs.h" +#include "xattr.h" + +static int hfsplus_user_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_USER_PREFIX); + strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_user_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_USER_PREFIX); + strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +const struct xattr_handler hfsplus_xattr_user_handler = { + .prefix = XATTR_USER_PREFIX, + .list = hfsplus_user_listxattr, + .get = hfsplus_user_getxattr, + .set = hfsplus_user_setxattr, +}; diff --git a/fs/inode.c b/fs/inode.c index 14084b72b259..83a601c2ad55 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -798,11 +798,10 @@ static struct inode *find_inode(struct super_block *sb, int (*test)(struct inode *, void *), void *data) { - struct hlist_node *node; struct inode *inode = NULL; repeat: - hlist_for_each_entry(inode, node, head, i_hash) { + hlist_for_each_entry(inode, head, i_hash) { spin_lock(&inode->i_lock); if (inode->i_sb != sb) { spin_unlock(&inode->i_lock); @@ -830,11 +829,10 @@ repeat: static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino) { - struct hlist_node *node; struct inode *inode = NULL; repeat: - hlist_for_each_entry(inode, node, head, i_hash) { + hlist_for_each_entry(inode, head, i_hash) { spin_lock(&inode->i_lock); if (inode->i_ino != ino) { spin_unlock(&inode->i_lock); @@ -1132,11 +1130,10 @@ EXPORT_SYMBOL(iget_locked); static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); - struct hlist_node *node; struct inode *inode; spin_lock(&inode_hash_lock); - hlist_for_each_entry(inode, node, b, i_hash) { + hlist_for_each_entry(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) { spin_unlock(&inode_hash_lock); return 0; @@ -1291,10 +1288,9 @@ int insert_inode_locked(struct inode *inode) struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { - struct hlist_node *node; struct inode *old = NULL; spin_lock(&inode_hash_lock); - hlist_for_each_entry(old, node, head, i_hash) { + hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) @@ -1306,7 +1302,7 @@ int insert_inode_locked(struct inode *inode) } break; } - if (likely(!node)) { + if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head(&inode->i_hash, head); @@ -1334,11 +1330,10 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, struct hlist_head *head = inode_hashtable + hash(sb, hashval); while (1) { - struct hlist_node *node; struct inode *old = NULL; spin_lock(&inode_hash_lock); - hlist_for_each_entry(old, node, head, i_hash) { + hlist_for_each_entry(old, head, i_hash) { if (old->i_sb != sb) continue; if (!test(old, data)) @@ -1350,7 +1345,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, } break; } - if (likely(!node)) { + if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head(&inode->i_hash, head); diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index b7dc47ba675e..1781f06aa1c1 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -23,6 +23,7 @@ #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/writeback.h> +#include <linux/aio.h> #include "jfs_incore.h" #include "jfs_inode.h" #include "jfs_filsys.h" diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 0e17090c310f..abdd75d44dd4 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -32,15 +32,15 @@ static struct hlist_head nlm_server_hosts[NLM_HOST_NRHASH]; static struct hlist_head nlm_client_hosts[NLM_HOST_NRHASH]; -#define for_each_host(host, pos, chain, table) \ +#define for_each_host(host, chain, table) \ for ((chain) = (table); \ (chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \ - hlist_for_each_entry((host), (pos), (chain), h_hash) + hlist_for_each_entry((host), (chain), h_hash) -#define for_each_host_safe(host, pos, next, chain, table) \ +#define for_each_host_safe(host, next, chain, table) \ for ((chain) = (table); \ (chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \ - hlist_for_each_entry_safe((host), (pos), (next), \ + hlist_for_each_entry_safe((host), (next), \ (chain), h_hash) static unsigned long nrhosts; @@ -225,7 +225,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, .net = net, }; struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host; struct nsm_handle *nsm = NULL; struct lockd_net *ln = net_generic(net, lockd_net_id); @@ -237,7 +236,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, mutex_lock(&nlm_host_mutex); chain = &nlm_client_hosts[nlm_hash_address(sap)]; - hlist_for_each_entry(host, pos, chain, h_hash) { + hlist_for_each_entry(host, chain, h_hash) { if (host->net != net) continue; if (!rpc_cmp_addr(nlm_addr(host), sap)) @@ -322,7 +321,6 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp, const size_t hostname_len) { struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host = NULL; struct nsm_handle *nsm = NULL; struct sockaddr *src_sap = svc_daddr(rqstp); @@ -350,7 +348,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp, nlm_gc_hosts(net); chain = &nlm_server_hosts[nlm_hash_address(ni.sap)]; - hlist_for_each_entry(host, pos, chain, h_hash) { + hlist_for_each_entry(host, chain, h_hash) { if (host->net != net) continue; if (!rpc_cmp_addr(nlm_addr(host), ni.sap)) @@ -515,10 +513,9 @@ static struct nlm_host *next_host_state(struct hlist_head *cache, { struct nlm_host *host; struct hlist_head *chain; - struct hlist_node *pos; mutex_lock(&nlm_host_mutex); - for_each_host(host, pos, chain, cache) { + for_each_host(host, chain, cache) { if (host->h_nsmhandle == nsm && host->h_nsmstate != info->state) { host->h_nsmstate = info->state; @@ -570,7 +567,6 @@ void nlm_host_rebooted(const struct nlm_reboot *info) static void nlm_complain_hosts(struct net *net) { struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host; if (net) { @@ -587,7 +583,7 @@ static void nlm_complain_hosts(struct net *net) dprintk("lockd: %lu hosts left:\n", nrhosts); } - for_each_host(host, pos, chain, nlm_server_hosts) { + for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; dprintk(" %s (cnt %d use %d exp %ld net %p)\n", @@ -600,14 +596,13 @@ void nlm_shutdown_hosts_net(struct net *net) { struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host; mutex_lock(&nlm_host_mutex); /* First, make all hosts eligible for gc */ dprintk("lockd: nuking all hosts in net %p...\n", net); - for_each_host(host, pos, chain, nlm_server_hosts) { + for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; host->h_expires = jiffies - 1; @@ -644,11 +639,11 @@ static void nlm_gc_hosts(struct net *net) { struct hlist_head *chain; - struct hlist_node *pos, *next; + struct hlist_node *next; struct nlm_host *host; dprintk("lockd: host garbage collection for net %p\n", net); - for_each_host(host, pos, chain, nlm_server_hosts) { + for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; host->h_inuse = 0; @@ -657,7 +652,7 @@ nlm_gc_hosts(struct net *net) /* Mark all hosts that hold locks, blocks or shares */ nlmsvc_mark_resources(net); - for_each_host_safe(host, pos, next, chain, nlm_server_hosts) { + for_each_host_safe(host, next, chain, nlm_server_hosts) { if (net && host->net != net) continue; if (atomic_read(&host->h_count) || host->h_inuse diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 0deb5f6c9dd4..747d40591675 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -84,7 +84,6 @@ __be32 nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, struct nfs_fh *f) { - struct hlist_node *pos; struct nlm_file *file; unsigned int hash; __be32 nfserr; @@ -96,7 +95,7 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, /* Lock file table */ mutex_lock(&nlm_file_mutex); - hlist_for_each_entry(file, pos, &nlm_files[hash], f_list) + hlist_for_each_entry(file, &nlm_files[hash], f_list) if (!nfs_compare_fh(&file->f_handle, f)) goto found; @@ -248,13 +247,13 @@ static int nlm_traverse_files(void *data, nlm_host_match_fn_t match, int (*is_failover_file)(void *data, struct nlm_file *file)) { - struct hlist_node *pos, *next; + struct hlist_node *next; struct nlm_file *file; int i, ret = 0; mutex_lock(&nlm_file_mutex); for (i = 0; i < FILE_NRHASH; i++) { - hlist_for_each_entry_safe(file, pos, next, &nlm_files[i], f_list) { + hlist_for_each_entry_safe(file, next, &nlm_files[i], f_list) { if (is_failover_file && !is_failover_file(data, file)) continue; file->f_count++; diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 6958adfaff08..24a05ba3de26 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -819,7 +819,7 @@ long ncp_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case NCP_IOC_CONN_LOGGED_IN: case NCP_IOC_SETROOT: if (!capable(CAP_SYS_ADMIN)) { - ret = -EACCES; + ret = -EPERM; goto out; } break; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9f3c66438d0e..84d8eae203a7 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -197,7 +197,6 @@ error_0: EXPORT_SYMBOL_GPL(nfs_alloc_client); #if IS_ENABLED(CONFIG_NFS_V4) -/* idr_remove_all is not needed as all id's are removed by nfs_put_client */ void nfs_cleanup_cb_ident_idr(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 2e9779b58b7a..47d100872390 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -29,15 +29,14 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) if (clp->rpc_ops->version != 4 || minorversion != 0) return ret; -retry: - if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL)) - return -ENOMEM; + idr_preload(GFP_KERNEL); spin_lock(&nn->nfs_client_lock); - ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident); + ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT); + if (ret >= 0) + clp->cl_cb_ident = ret; spin_unlock(&nn->nfs_client_lock); - if (ret == -EAGAIN) - goto retry; - return ret; + idr_preload_end(); + return ret < 0 ? ret : 0; } #ifdef CONFIG_NFS_V4_1 diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index d35b62e83ea6..6da209bd9408 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -77,9 +77,8 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld, long hash) { struct nfs4_deviceid_node *d; - struct hlist_node *n; - hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node) + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) if (d->ld == ld && d->nfs_client == clp && !memcmp(&d->deviceid, id, sizeof(*id))) { if (atomic_read(&d->ref)) @@ -248,12 +247,11 @@ static void _deviceid_purge_client(const struct nfs_client *clp, long hash) { struct nfs4_deviceid_node *d; - struct hlist_node *n; HLIST_HEAD(tmp); spin_lock(&nfs4_deviceid_lock); rcu_read_lock(); - hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node) + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) if (d->nfs_client == clp && atomic_read(&d->ref)) { hlist_del_init_rcu(&d->node); hlist_add_head(&d->tmpnode, &tmp); @@ -291,12 +289,11 @@ void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp) { struct nfs4_deviceid_node *d; - struct hlist_node *n; int i; rcu_read_lock(); for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){ - hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[i], node) + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[i], node) if (d->nfs_client == clp) set_bit(NFS_DEVICEID_INVALID, &d->flags); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a6637de7ae13..b99ccde31d06 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -151,7 +151,7 @@ get_nfs4_file(struct nfs4_file *fi) } static int num_delegations; -unsigned int max_delegations; +unsigned long max_delegations; /* * Open owner state (share locks) @@ -700,8 +700,8 @@ static int nfsd4_get_drc_mem(int slotsize, u32 num) num = min_t(u32, num, NFSD_MAX_SLOTS_PER_SESSION); spin_lock(&nfsd_drc_lock); - avail = min_t(int, NFSD_MAX_MEM_PER_SESSION, - nfsd_drc_max_mem - nfsd_drc_mem_used); + avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, + nfsd_drc_max_mem - nfsd_drc_mem_used); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock); @@ -1060,7 +1060,6 @@ free_client(struct nfs4_client *clp) } free_svc_cred(&clp->cl_cred); kfree(clp->cl_name.data); - idr_remove_all(&clp->cl_stateids); idr_destroy(&clp->cl_stateids); kfree(clp); } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index d16a5d6435f2..35cdb934c663 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -246,7 +246,6 @@ static struct svc_cacherep * nfsd_cache_search(struct svc_rqst *rqstp) { struct svc_cacherep *rp; - struct hlist_node *hn; struct hlist_head *rh; __be32 xid = rqstp->rq_xid; u32 proto = rqstp->rq_prot, @@ -254,7 +253,7 @@ nfsd_cache_search(struct svc_rqst *rqstp) proc = rqstp->rq_proc; rh = &cache_hash[request_hash(xid)]; - hlist_for_each_entry(rp, hn, rh, c_hash) { + hlist_for_each_entry(rp, rh, c_hash) { if (xid == rp->c_xid && proc == rp->c_proc && proto == rp->c_prot && vers == rp->c_vers && rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) && diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index de23db255c69..07a473fd49bc 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -56,8 +56,8 @@ extern struct svc_version nfsd_version2, nfsd_version3, extern u32 nfsd_supported_minorversion; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; -extern unsigned int nfsd_drc_max_mem; -extern unsigned int nfsd_drc_mem_used; +extern unsigned long nfsd_drc_max_mem; +extern unsigned long nfsd_drc_mem_used; extern const struct seq_operations nfs_exports_op; @@ -106,7 +106,7 @@ static inline int nfsd_v4client(struct svc_rqst *rq) * NFSv4 State */ #ifdef CONFIG_NFSD_V4 -extern unsigned int max_delegations; +extern unsigned long max_delegations; void nfs4_state_init(void); int nfsd4_init_slabs(void); void nfsd4_free_slabs(void); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 40cb1cbaba4e..53e7f4585dc4 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -59,8 +59,8 @@ DEFINE_MUTEX(nfsd_mutex); * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage. */ spinlock_t nfsd_drc_lock; -unsigned int nfsd_drc_max_mem; -unsigned int nfsd_drc_mem_used; +unsigned long nfsd_drc_max_mem; +unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; @@ -342,7 +342,7 @@ static void set_max_drc(void) >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE; nfsd_drc_mem_used = 0; spin_lock_init(&nfsd_drc_lock); - dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem); + dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem); } static int nfsd_get_default_max_blksize(void) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 61946883025c..bec4af6eab13 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -126,7 +126,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_on_page_writeback(page); + wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6b49f14eac8c..1e92930d59c3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -25,7 +25,7 @@ #include <linux/gfp.h> #include <linux/mpage.h> #include <linux/writeback.h> -#include <linux/uio.h> +#include <linux/aio.h> #include "nilfs.h" #include "btnode.h" #include "segment.h" diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 6baadb5a8430..4bb21d67d9b1 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -52,7 +52,6 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt) void __fsnotify_update_child_dentry_flags(struct inode *inode) { struct dentry *alias; - struct hlist_node *p; int watched; if (!S_ISDIR(inode->i_mode)) @@ -64,7 +63,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index f31e90fc050d..74825be65b7b 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -36,12 +36,11 @@ static void fsnotify_recalc_inode_mask_locked(struct inode *inode) { struct fsnotify_mark *mark; - struct hlist_node *pos; __u32 new_mask = 0; assert_spin_locked(&inode->i_lock); - hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list) + hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) new_mask |= mark->mask; inode->i_fsnotify_mask = new_mask; } @@ -87,11 +86,11 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark) void fsnotify_clear_marks_by_inode(struct inode *inode) { struct fsnotify_mark *mark, *lmark; - struct hlist_node *pos, *n; + struct hlist_node *n; LIST_HEAD(free_list); spin_lock(&inode->i_lock); - hlist_for_each_entry_safe(mark, pos, n, &inode->i_fsnotify_marks, i.i_list) { + hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, i.i_list) { list_add(&mark->i.free_i_list, &free_list); hlist_del_init_rcu(&mark->i.i_list); fsnotify_get_mark(mark); @@ -129,11 +128,10 @@ static struct fsnotify_mark *fsnotify_find_inode_mark_locked( struct inode *inode) { struct fsnotify_mark *mark; - struct hlist_node *pos; assert_spin_locked(&inode->i_lock); - hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list) { + hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) { if (mark->group == group) { fsnotify_get_mark(mark); return mark; @@ -194,8 +192,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, struct inode *inode, int allow_dups) { - struct fsnotify_mark *lmark; - struct hlist_node *node, *last = NULL; + struct fsnotify_mark *lmark, *last = NULL; int ret = 0; mark->flags |= FSNOTIFY_MARK_FLAG_INODE; @@ -214,8 +211,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, } /* should mark be in the middle of the current list? */ - hlist_for_each_entry(lmark, node, &inode->i_fsnotify_marks, i.i_list) { - last = node; + hlist_for_each_entry(lmark, &inode->i_fsnotify_marks, i.i_list) { + last = lmark; if ((lmark->group == group) && !allow_dups) { ret = -EEXIST; @@ -235,7 +232,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ - hlist_add_after_rcu(last, &mark->i.i_list); + hlist_add_after_rcu(&last->i.i_list, &mark->i.i_list); out: fsnotify_recalc_inode_mask_locked(inode); spin_unlock(&inode->i_lock); diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 871569c7d609..4216308b81b4 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -197,7 +197,6 @@ static void inotify_free_group_priv(struct fsnotify_group *group) { /* ideally the idr is empty and we won't hit the BUG in the callback */ idr_for_each(&group->inotify_data.idr, idr_callback, group); - idr_remove_all(&group->inotify_data.idr); idr_destroy(&group->inotify_data.idr); atomic_dec(&group->inotify_data.user->inotify_devs); free_uid(group->inotify_data.user); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 228a2c2ad8d7..e0f7c1241a6a 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -364,22 +364,20 @@ static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock, { int ret; - do { - if (unlikely(!idr_pre_get(idr, GFP_KERNEL))) - return -ENOMEM; + idr_preload(GFP_KERNEL); + spin_lock(idr_lock); - spin_lock(idr_lock); - ret = idr_get_new_above(idr, i_mark, *last_wd + 1, - &i_mark->wd); + ret = idr_alloc(idr, i_mark, *last_wd + 1, 0, GFP_NOWAIT); + if (ret >= 0) { /* we added the mark to the idr, take a reference */ - if (!ret) { - *last_wd = i_mark->wd; - fsnotify_get_mark(&i_mark->fsn_mark); - } - spin_unlock(idr_lock); - } while (ret == -EAGAIN); + i_mark->wd = ret; + *last_wd = i_mark->wd; + fsnotify_get_mark(&i_mark->fsn_mark); + } - return ret; + spin_unlock(idr_lock); + idr_preload_end(); + return ret < 0 ? ret : 0; } static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group *group, @@ -576,8 +574,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); - if (unlikely(!(mask & IN_ALL_EVENTS))) - return -EINVAL; fsn_mark = fsnotify_find_inode_mark(group, inode); if (!fsn_mark) @@ -629,8 +625,6 @@ static int inotify_new_watch(struct fsnotify_group *group, /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); - if (unlikely(!(mask & IN_ALL_EVENTS))) - return -EINVAL; tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL); if (unlikely(!tmp_i_mark)) diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c index 4df58b8ea64a..68ca5a8704b5 100644 --- a/fs/notify/vfsmount_mark.c +++ b/fs/notify/vfsmount_mark.c @@ -33,12 +33,12 @@ void fsnotify_clear_marks_by_mount(struct vfsmount *mnt) { struct fsnotify_mark *mark, *lmark; - struct hlist_node *pos, *n; + struct hlist_node *n; struct mount *m = real_mount(mnt); LIST_HEAD(free_list); spin_lock(&mnt->mnt_root->d_lock); - hlist_for_each_entry_safe(mark, pos, n, &m->mnt_fsnotify_marks, m.m_list) { + hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, m.m_list) { list_add(&mark->m.free_m_list, &free_list); hlist_del_init_rcu(&mark->m.m_list); fsnotify_get_mark(mark); @@ -71,12 +71,11 @@ static void fsnotify_recalc_vfsmount_mask_locked(struct vfsmount *mnt) { struct mount *m = real_mount(mnt); struct fsnotify_mark *mark; - struct hlist_node *pos; __u32 new_mask = 0; assert_spin_locked(&mnt->mnt_root->d_lock); - hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list) + hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) new_mask |= mark->mask; m->mnt_fsnotify_mask = new_mask; } @@ -114,11 +113,10 @@ static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_ { struct mount *m = real_mount(mnt); struct fsnotify_mark *mark; - struct hlist_node *pos; assert_spin_locked(&mnt->mnt_root->d_lock); - hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list) { + hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) { if (mark->group == group) { fsnotify_get_mark(mark); return mark; @@ -153,8 +151,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, int allow_dups) { struct mount *m = real_mount(mnt); - struct fsnotify_mark *lmark; - struct hlist_node *node, *last = NULL; + struct fsnotify_mark *lmark, *last = NULL; int ret = 0; mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT; @@ -173,8 +170,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, } /* should mark be in the middle of the current list? */ - hlist_for_each_entry(lmark, node, &m->mnt_fsnotify_marks, m.m_list) { - last = node; + hlist_for_each_entry(lmark, &m->mnt_fsnotify_marks, m.m_list) { + last = lmark; if ((lmark->group == group) && !allow_dups) { ret = -EEXIST; @@ -194,7 +191,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ - hlist_add_after_rcu(last, &mark->m.m_list); + hlist_add_after_rcu(&last->m.m_list, &mark->m.m_list); out: fsnotify_recalc_vfsmount_mask_locked(mnt); spin_unlock(&mnt->mnt_root->d_lock); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 5b2d4f0853ac..600af8fbae56 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -27,6 +27,7 @@ #include <linux/swap.h> #include <linux/uio.h> #include <linux/writeback.h> +#include <linux/aio.h> #include <asm/page.h> #include <asm/uaccess.h> diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d3e118cc6ffa..2778b0255dc6 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -28,6 +28,7 @@ #include <linux/quotaops.h> #include <linux/slab.h> #include <linux/log2.h> +#include <linux/aio.h> #include "aops.h" #include "attrib.h" diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 657743254eb9..f6fff671bb34 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -593,9 +593,9 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, level = ocfs2_iocb_rw_locked_level(iocb); ocfs2_rw_unlock(inode, level); + inode_dio_done(inode); if (is_async) aio_complete(iocb, ret, 0); - inode_dio_done(inode); } /* @@ -1194,6 +1194,7 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, goto out; } } + wait_for_stable_page(wc->w_pages[i]); if (index == target_index) wc->w_target_page = wc->w_pages[i]; diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index ffb2da370a99..f671e49beb34 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -22,6 +22,8 @@ #ifndef OCFS2_AOPS_H #define OCFS2_AOPS_H +#include <linux/aio.h> + handle_t *ocfs2_start_walk_page_trans(struct inode *inode, struct page *page, unsigned from, diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index a1d83c58b296..33b892464d14 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -304,28 +304,22 @@ static u8 o2net_num_from_nn(struct o2net_node *nn) static int o2net_prep_nsw(struct o2net_node *nn, struct o2net_status_wait *nsw) { - int ret = 0; - - do { - if (!idr_pre_get(&nn->nn_status_idr, GFP_ATOMIC)) { - ret = -EAGAIN; - break; - } - spin_lock(&nn->nn_lock); - ret = idr_get_new(&nn->nn_status_idr, nsw, &nsw->ns_id); - if (ret == 0) - list_add_tail(&nsw->ns_node_item, - &nn->nn_status_list); - spin_unlock(&nn->nn_lock); - } while (ret == -EAGAIN); + int ret; - if (ret == 0) { - init_waitqueue_head(&nsw->ns_wq); - nsw->ns_sys_status = O2NET_ERR_NONE; - nsw->ns_status = 0; + spin_lock(&nn->nn_lock); + ret = idr_alloc(&nn->nn_status_idr, nsw, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + nsw->ns_id = ret; + list_add_tail(&nsw->ns_node_item, &nn->nn_status_list); } + spin_unlock(&nn->nn_lock); + if (ret < 0) + return ret; - return ret; + init_waitqueue_head(&nsw->ns_wq); + nsw->ns_sys_status = O2NET_ERR_NONE; + nsw->ns_status = 0; + return 0; } static void o2net_complete_nsw_locked(struct o2net_node *nn, diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 8db4b58b2e4b..ef999729e274 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -169,11 +169,10 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno, int skip_unhashed) { - struct hlist_node *p; struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 15d81adb8d77..ba1e68923b21 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2090,7 +2090,6 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm, u8 dead_node, u8 new_master) { int i; - struct hlist_node *hash_iter; struct hlist_head *bucket; struct dlm_lock_resource *res, *next; @@ -2121,7 +2120,7 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm, * if necessary */ for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_lockres_hash(dlm, i); - hlist_for_each_entry(res, hash_iter, bucket, hash_node) { + hlist_for_each_entry(res, bucket, hash_node) { if (!(res->state & DLM_LOCK_RES_RECOVERING)) continue; @@ -2280,7 +2279,6 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) { - struct hlist_node *iter; struct dlm_lock_resource *res; int i; struct hlist_head *bucket; @@ -2306,7 +2304,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) */ for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_lockres_hash(dlm, i); - hlist_for_each_entry(res, iter, bucket, hash_node) { + hlist_for_each_entry(res, bucket, hash_node) { /* always prune any $RECOVERY entries for dead nodes, * otherwise hangs can occur during later recovery */ if (dlm_is_recovery_lock(res->lockname.name, diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 4f7795fb5fc0..bad2583881c8 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2322,7 +2322,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, status = __ocfs2_cluster_lock(osb, lockres, level, dlm_flags, arg_flags, subclass, _RET_IP_); if (status < 0) { - if (status != -EAGAIN && status != -EIOCBRETRY) + if (status != -EAGAIN) mlog_errno(status); goto bail; } diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 88924a3133fa..c765bdf6d60e 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -28,6 +28,8 @@ #include "extent_map.h" +struct iocb; + /* OCFS2 Inode Private Data */ struct ocfs2_inode_info { diff --git a/fs/pipe.c b/fs/pipe.c index bd3479db4b62..dc86533457b2 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -21,6 +21,7 @@ #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> +#include <linux/aio.h> #include <asm/uaccess.h> #include <asm/ioctls.h> diff --git a/fs/proc/base.c b/fs/proc/base.c index 9b43ff77a51e..c6528c663df4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -73,6 +73,7 @@ #include <linux/security.h> #include <linux/ptrace.h> #include <linux/tracehook.h> +#include <linux/printk.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> @@ -952,7 +953,7 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf, * /proc/pid/oom_adj is provided for legacy purposes, ask users to use * /proc/pid/oom_score_adj instead. */ - printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", current->comm, task_pid_nr(current), task_pid_nr(task), task_pid_nr(task)); @@ -1711,7 +1712,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) return -ECHILD; if (!capable(CAP_SYS_ADMIN)) { - status = -EACCES; + status = -EPERM; goto out_notask; } @@ -1844,7 +1845,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, struct dentry *result; struct mm_struct *mm; - result = ERR_PTR(-EACCES); + result = ERR_PTR(-EPERM); if (!capable(CAP_SYS_ADMIN)) goto out; @@ -1900,7 +1901,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) ino_t ino; int ret; - ret = -EACCES; + ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto out; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 76ddae83daa5..d00072351cd5 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/printk.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/idr.h> @@ -132,11 +133,8 @@ __proc_file_read(struct file *file, char __user *buf, size_t nbytes, } if (start == NULL) { - if (n > PAGE_SIZE) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); + if (n > PAGE_SIZE) /* Apparent buffer overflow */ n = PAGE_SIZE; - } n -= *ppos; if (n <= 0) break; @@ -144,26 +142,19 @@ __proc_file_read(struct file *file, char __user *buf, size_t nbytes, n = count; start = page + *ppos; } else if (start < page) { - if (n > PAGE_SIZE) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); + if (n > PAGE_SIZE) /* Apparent buffer overflow */ n = PAGE_SIZE; - } if (n > count) { /* * Don't reduce n because doing so might * cut off part of a data block. */ - printk(KERN_WARNING - "proc_file_read: Read count exceeded\n"); + pr_warn("proc_file_read: count exceeded\n"); } } else /* start >= page */ { unsigned long startoff = (unsigned long)(start - page); - if (n > (PAGE_SIZE - startoff)) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); + if (n > (PAGE_SIZE - startoff)) /* buffer overflow? */ n = PAGE_SIZE - startoff; - } if (n > count) n = count; } @@ -576,7 +567,7 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp for (tmp = dir->subdir; tmp; tmp = tmp->next) if (strcmp(tmp->name, dp->name) == 0) { - WARN(1, KERN_WARNING "proc_dir_entry '%s/%s' already registered\n", + WARN(1, "proc_dir_entry '%s/%s' already registered\n", dir->name, dp->name); break; } @@ -837,7 +828,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) if (S_ISDIR(de->mode)) parent->nlink--; de->nlink = 0; - WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory " + WARN(de->subdir, "%s: removing non-empty directory " "'%s/%s', leaking at least '%s'\n", __func__, de->parent->name, de->name, de->subdir->name); pde_put(de); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 439ae6886507..7a59f50f64d6 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -13,6 +13,7 @@ #include <linux/stat.h> #include <linux/completion.h> #include <linux/poll.h> +#include <linux/printk.h> #include <linux/file.h> #include <linux/limits.h> #include <linux/init.h> @@ -486,6 +487,8 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) int proc_fill_super(struct super_block *s) { + struct inode *root_inode; + s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; @@ -494,11 +497,18 @@ int proc_fill_super(struct super_block *s) s->s_time_gran = 1; pde_get(&proc_root); - s->s_root = d_make_root(proc_get_inode(s, &proc_root)); - if (s->s_root) - return 0; + root_inode = proc_get_inode(s, &proc_root); + if (!root_inode) { + pr_warn("proc_fill_super: get root inode failed\n"); + pde_put(&proc_root); + return -ENOMEM; + } - printk("proc_read_super: get root inode failed\n"); - pde_put(&proc_root); - return -ENOMEM; + s->s_root = d_make_root(root_inode); + if (!s->s_root) { + pr_err("proc_fill_super: allocate dentry failed\n"); + return -ENOMEM; + } + + return 0; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 252544c05207..85ff3a4598b3 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -11,6 +11,7 @@ #include <linux/sched.h> #include <linux/proc_fs.h> +#include <linux/binfmts.h> struct ctl_table_header; struct mempolicy; @@ -108,7 +109,7 @@ static inline int task_dumpable(struct task_struct *task) if (mm) dumpable = get_dumpable(mm); task_unlock(task); - if (dumpable == SUID_DUMPABLE_ENABLED) + if (dumpable == SUID_DUMP_USER) return 1; return 0; } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e96d4f18ca3a..eda6f017f272 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -17,6 +17,7 @@ #include <linux/elfcore.h> #include <linux/vmalloc.h> #include <linux/highmem.h> +#include <linux/printk.h> #include <linux/bootmem.h> #include <linux/init.h> #include <linux/slab.h> @@ -619,7 +620,7 @@ static int __init proc_kcore_init(void) proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); if (!proc_root_kcore) { - printk(KERN_ERR "couldn't create /proc/kcore\n"); + pr_err("couldn't create /proc/kcore\n"); return 0; /* Always returns 0. */ } /* Store text area if it's special */ diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 80e4645f7990..1efaaa19c4f3 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) * sysctl_overcommit_ratio / 100) + total_swap_pages; cached = global_page_state(NR_FILE_PAGES) - - total_swapcache_pages - i.bufferram; + total_swapcache_pages() - i.bufferram; if (cached < 0) cached = 0; @@ -109,7 +109,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freeram), K(i.bufferram), K(cached), - K(total_swapcache_pages), + K(total_swapcache_pages()), K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]), K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]), K(pages[LRU_ACTIVE_ANON]), @@ -158,7 +158,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) vmi.used >> 10, vmi.largest_chunk >> 10 #ifdef CONFIG_MEMORY_FAILURE - ,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10) + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c index de20ec480fa0..30b590f5bd35 100644 --- a/fs/proc/proc_devtree.c +++ b/fs/proc/proc_devtree.c @@ -8,6 +8,7 @@ #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/printk.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/of.h> @@ -110,8 +111,8 @@ void proc_device_tree_update_prop(struct proc_dir_entry *pde, if (ent->data == oldprop) break; if (ent == NULL) { - printk(KERN_WARNING "device-tree: property \"%s\" " - " does not exist\n", oldprop->name); + pr_warn("device-tree: property \"%s\" does not exist\n", + oldprop->name); } else { ent->data = newprop; ent->size = newprop->length; @@ -153,8 +154,8 @@ static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de, realloc: fixed_name = kmalloc(fixup_len, GFP_KERNEL); if (fixed_name == NULL) { - printk(KERN_ERR "device-tree: Out of memory trying to fixup " - "name \"%s\"\n", name); + pr_err("device-tree: Out of memory trying to fixup " + "name \"%s\"\n", name); return name; } @@ -175,8 +176,8 @@ retry: goto retry; } - printk(KERN_WARNING "device-tree: Duplicate name in %s, " - "renamed to \"%s\"\n", np->full_name, fixed_name); + pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n", + np->full_name, fixed_name); return fixed_name; } diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 1827d88ad58b..6384b04175af 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -5,6 +5,7 @@ #include <linux/sysctl.h> #include <linux/poll.h> #include <linux/proc_fs.h> +#include <linux/printk.h> #include <linux/security.h> #include <linux/sched.h> #include <linux/namei.h> @@ -57,7 +58,7 @@ static void sysctl_print_dir(struct ctl_dir *dir) { if (dir->header.parent) sysctl_print_dir(dir->header.parent); - printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname); + pr_cont("%s/", dir->header.ctl_table[0].procname); } static int namecmp(const char *name1, int len1, const char *name2, int len2) @@ -134,9 +135,9 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) else if (cmp > 0) p = &(*p)->rb_right; else { - printk(KERN_ERR "sysctl duplicate entry: "); + pr_err("sysctl duplicate entry: "); sysctl_print_dir(head->parent); - printk(KERN_CONT "/%s\n", entry->procname); + pr_cont("/%s\n", entry->procname); return -EEXIST; } } @@ -927,9 +928,9 @@ found: subdir->header.nreg++; failed: if (unlikely(IS_ERR(subdir))) { - printk(KERN_ERR "sysctl could not get directory: "); + pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); - printk(KERN_CONT "/%*.*s %ld\n", + pr_cont("/%*.*s %ld\n", namelen, namelen, name, PTR_ERR(subdir)); } drop_sysctl_table(&dir->header); @@ -995,8 +996,8 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n", - path, table->procname, &vaf); + pr_err("sysctl table check failed: %s/%s %pV\n", + path, table->procname, &vaf); va_end(args); return -EINVAL; @@ -1510,9 +1511,9 @@ static void put_links(struct ctl_table_header *header) drop_sysctl_table(link_head); } else { - printk(KERN_ERR "sysctl link missing during unregister: "); + pr_err("sysctl link missing during unregister: "); sysctl_print_dir(parent); - printk(KERN_CONT "/%s\n", name); + pr_cont("/%s\n", name); } } } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 0d5071d29985..41dd018f72dd 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -15,6 +15,7 @@ #include <linux/export.h> #include <linux/slab.h> #include <linux/highmem.h> +#include <linux/printk.h> #include <linux/bootmem.h> #include <linux/init.h> #include <linux/crash_dump.h> @@ -553,8 +554,7 @@ static int __init parse_crash_elf64_headers(void) ehdr.e_ehsize != sizeof(Elf64_Ehdr) || ehdr.e_phentsize != sizeof(Elf64_Phdr) || ehdr.e_phnum == 0) { - printk(KERN_WARNING "Warning: Core image elf header is not" - "sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } @@ -609,8 +609,7 @@ static int __init parse_crash_elf32_headers(void) ehdr.e_ehsize != sizeof(Elf32_Ehdr) || ehdr.e_phentsize != sizeof(Elf32_Phdr) || ehdr.e_phnum == 0) { - printk(KERN_WARNING "Warning: Core image elf header is not" - "sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } @@ -653,8 +652,7 @@ static int __init parse_crash_elf_headers(void) if (rc < 0) return rc; if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) { - printk(KERN_WARNING "Warning: Core image elf header" - " not found\n"); + pr_warn("Warning: Core image elf header not found\n"); return -EINVAL; } @@ -673,8 +671,7 @@ static int __init parse_crash_elf_headers(void) /* Determine vmcore size. */ vmcore_size = get_vmcore_size_elf32(elfcorebuf); } else { - printk(KERN_WARNING "Warning: Core image elf header is not" - " sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } return 0; @@ -690,7 +687,7 @@ static int __init vmcore_init(void) return rc; rc = parse_crash_elf_headers(); if (rc) { - printk(KERN_WARNING "Kdump: vmcore not initialized\n"); + pr_warn("Kdump: vmcore not initialized\n"); return rc; } diff --git a/fs/read_write.c b/fs/read_write.c index bb34af315280..616bc3962bb0 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -15,6 +15,7 @@ #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> +#include <linux/aio.h> #include "read_write.h" #include <asm/uaccess.h> @@ -318,16 +319,6 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count return count > MAX_RW_COUNT ? MAX_RW_COUNT : count; } -static void wait_on_retry_sync_kiocb(struct kiocb *iocb) -{ - set_current_state(TASK_UNINTERRUPTIBLE); - if (!kiocbIsKicked(iocb)) - schedule(); - else - kiocbClearKicked(iocb); - __set_current_state(TASK_RUNNING); -} - ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = buf, .iov_len = len }; @@ -339,13 +330,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp kiocb.ki_left = len; kiocb.ki_nbytes = len; - for (;;) { - ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); - if (ret != -EIOCBRETRY) - break; - wait_on_retry_sync_kiocb(&kiocb); - } - + ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; @@ -395,13 +380,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof kiocb.ki_left = len; kiocb.ki_nbytes = len; - for (;;) { - ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); - if (ret != -EIOCBRETRY) - break; - wait_on_retry_sync_kiocb(&kiocb); - } - + ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; @@ -568,13 +547,7 @@ ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, kiocb.ki_left = len; kiocb.ki_nbytes = len; - for (;;) { - ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); - if (ret != -EIOCBRETRY) - break; - wait_on_retry_sync_kiocb(&kiocb); - } - + ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); if (ret == -EIOCBQUEUED) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 95d7680ead47..30195bcbbfc3 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -18,6 +18,7 @@ #include <linux/writeback.h> #include <linux/quotaops.h> #include <linux/swap.h> +#include <linux/aio.h> int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); diff --git a/fs/seq_file.c b/fs/seq_file.c index f2bc3dfd0b88..15c6304bab71 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -308,27 +308,27 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence) mutex_lock(&m->lock); m->version = file->f_version; switch (whence) { - case 1: - offset += file->f_pos; - case 0: - if (offset < 0) - break; - retval = offset; - if (offset != m->read_pos) { - while ((retval=traverse(m, offset)) == -EAGAIN) - ; - if (retval) { - /* with extreme prejudice... */ - file->f_pos = 0; - m->read_pos = 0; - m->version = 0; - m->index = 0; - m->count = 0; - } else { - m->read_pos = offset; - retval = file->f_pos = offset; - } + case SEEK_CUR: + offset += file->f_pos; + case SEEK_SET: + if (offset < 0) + break; + retval = offset; + if (offset != m->read_pos) { + while ((retval = traverse(m, offset)) == -EAGAIN) + ; + if (retval) { + /* with extreme prejudice... */ + file->f_pos = 0; + m->read_pos = 0; + m->version = 0; + m->index = 0; + m->count = 0; + } else { + m->read_pos = offset; + retval = file->f_pos = offset; } + } } file->f_version = m->version; mutex_unlock(&m->lock); diff --git a/fs/signalfd.c b/fs/signalfd.c index b53486961735..c723b5d56c8f 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -30,6 +30,7 @@ #include <linux/signalfd.h> #include <linux/syscalls.h> #include <linux/proc_fs.h> +#include <linux/compat.h> void signalfd_cleanup(struct sighand_struct *sighand) { @@ -74,6 +75,39 @@ static unsigned int signalfd_poll(struct file *file, poll_table *wait) } /* + * Copy a whole siginfo into userspace. + * The main idea of this format is that it should be enough + * for restoring siginfo back into the kernel. + */ +static int signalfd_copy_raw_info(struct signalfd_siginfo __user *siginfo, + siginfo_t *kinfo) +{ + siginfo_t __user *uinfo = (siginfo_t __user *)siginfo; + int err; + + BUILD_BUG_ON(sizeof(siginfo_t) != sizeof(struct signalfd_siginfo)); + + err = __clear_user(uinfo, sizeof(*uinfo)); + +#ifdef CONFIG_COMPAT + if (unlikely(is_compat_task())) { + compat_siginfo_t __user *compat_uinfo; + + compat_uinfo = (compat_siginfo_t __user *)siginfo; + err |= copy_siginfo_to_user32(compat_uinfo, kinfo); + err |= put_user(kinfo->si_code, &compat_uinfo->si_code); + + return err ? -EFAULT : sizeof(*compat_uinfo); + } +#endif + + err |= copy_siginfo_to_user(uinfo, kinfo); + err |= put_user(kinfo->si_code, &uinfo->si_code); + + return err ? -EFAULT : sizeof(*uinfo); +} + +/* * Copied from copy_siginfo_to_user() in kernel/signal.c */ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, @@ -205,6 +239,7 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, struct signalfd_ctx *ctx = file->private_data; struct signalfd_siginfo __user *siginfo; int nonblock = file->f_flags & O_NONBLOCK; + bool raw = file->f_flags & SFD_RAW; ssize_t ret, total = 0; siginfo_t info; @@ -217,7 +252,12 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, ret = signalfd_dequeue(ctx, &info, nonblock); if (unlikely(ret <= 0)) break; - ret = signalfd_copyinfo(siginfo, &info); + + if (raw) + ret = signalfd_copy_raw_info(siginfo, &info); + else + ret = signalfd_copyinfo(siginfo, &info); + if (ret < 0) break; siginfo++; @@ -262,7 +302,7 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK); - if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK)) + if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK | SFD_RAW)) return -EINVAL; if (sizemask != sizeof(sigset_t) || @@ -272,20 +312,35 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, signotset(&sigmask); if (ufd == -1) { + struct file *file; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->sigmask = sigmask; + ufd = get_unused_fd_flags(flags); + if (ufd < 0) { + kfree(ctx); + goto out; + } + /* * When we call this, the initialization must be complete, since * anon_inode_getfd() will install the fd. */ - ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx, + file = anon_inode_getfile("[signalfd]", &signalfd_fops, ctx, O_RDWR | (flags & (O_CLOEXEC | O_NONBLOCK))); - if (ufd < 0) + if (IS_ERR(file)) { + put_unused_fd(ufd); + ufd = PTR_ERR(file); kfree(ctx); + goto out; + } + + file->f_flags |= flags & SFD_RAW; + + fd_install(ufd, file); } else { struct fd f = fdget(ufd); if (!f.file) @@ -302,7 +357,7 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, wake_up(¤t->sighand->signalfd_wqh); fdput(f); } - +out: return ufd; } diff --git a/fs/super.c b/fs/super.c index 12f123712161..c290cca1069a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -447,14 +447,13 @@ struct super_block *sget(struct file_system_type *type, void *data) { struct super_block *s = NULL; - struct hlist_node *node; struct super_block *old; int err; retry: spin_lock(&sb_lock); if (test) { - hlist_for_each_entry(old, node, &type->fs_supers, s_instances) { + hlist_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (!grab_super(old)) @@ -554,10 +553,9 @@ void iterate_supers_type(struct file_system_type *type, void (*f)(struct super_block *, void *), void *arg) { struct super_block *sb, *p = NULL; - struct hlist_node *node; spin_lock(&sb_lock); - hlist_for_each_entry(sb, node, &type->fs_supers, s_instances) { + hlist_for_each_entry(sb, &type->fs_supers, s_instances) { sb->s_count++; spin_unlock(&sb_lock); diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 614b2b544880..f186e277a127 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -461,14 +461,13 @@ const struct file_operations bin_fops = { void unmap_bin_file(struct sysfs_dirent *attr_sd) { struct bin_buffer *bb; - struct hlist_node *tmp; if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR) return; mutex_lock(&sysfs_bin_lock); - hlist_for_each_entry(bb, tmp, &attr_sd->s_bin_attr.buffers, list) { + hlist_for_each_entry(bb, &attr_sd->s_bin_attr.buffers, list) { struct inode *inode = bb->file->f_path.dentry->d_inode; unmap_mapping_range(inode->i_mapping, 0, 0, 1); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 5bc77817f382..deaf954368ad 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -50,6 +50,7 @@ */ #include "ubifs.h" +#include <linux/aio.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/slab.h> @@ -1522,6 +1523,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma, ubifs_release_dirty_inode_budget(c, ui); } + wait_for_stable_page(page); unlock_page(page); return 0; diff --git a/fs/udf/file.c b/fs/udf/file.c index 77b5953eaac8..63e25fc83328 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -204,7 +204,7 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) goto out; case UDF_RELOCATE_BLOCKS: if (!capable(CAP_SYS_ADMIN)) { - result = -EACCES; + result = -EPERM; goto out; } if (get_user(old_block, (long __user *)arg)) { diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7a12e48ad819..b6d15d349810 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -38,6 +38,7 @@ #include <linux/slab.h> #include <linux/crc-itu-t.h> #include <linux/mpage.h> +#include <linux/aio.h> #include "udf_i.h" #include "udf_sb.h" diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5f707e537171..c24ce0e9c67c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -31,6 +31,7 @@ #include "xfs_vnodeops.h" #include "xfs_trace.h" #include "xfs_bmap.h" +#include <linux/aio.h> #include <linux/gfp.h> #include <linux/mpage.h> #include <linux/pagevec.h> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 67284edb84d7..a4d7ef78fd56 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -36,6 +36,7 @@ #include "xfs_ioctl.h" #include "xfs_trace.h" +#include <linux/aio.h> #include <linux/dcache.h> #include <linux/falloc.h> #include <linux/pagevec.h> diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 96fcbb85ff83..d1dba7ce75ae 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1442,9 +1442,8 @@ xlog_recover_find_tid( xlog_tid_t tid) { xlog_recover_t *trans; - struct hlist_node *n; - hlist_for_each_entry(trans, n, head, r_list) { + hlist_for_each_entry(trans, head, r_list) { if (trans->r_log_tid == tid) return trans; } |