From 66ee59af630fd8d5f4f56fb28162857e629aa0ab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Feb 2015 19:56:46 +0100 Subject: fs: remove ki_nbytes There is no need to pass the total request length in the kiocb, as we already get passed in through the iov_iter argument. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/aio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index d9c92daa3944..132d1ecba435 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -42,7 +42,6 @@ struct kiocb { __u64 ki_user_data; /* user's data for completion */ loff_t ki_pos; - size_t ki_nbytes; /* copy of iocb->aio_nbytes */ struct list_head ki_list; /* the aio core uses this * for cancellation */ -- cgit v1.2.3 From 599bd19bdc4c6b20fd91d50f2f79dececbaf80c1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Feb 2015 19:59:44 +0100 Subject: fs: don't allow to complete sync iocbs through aio_complete The AIO interface is fairly complex because it tries to allow filesystems to always work async and then wakeup a synchronous caller through aio_complete. It turns out that basically no one was doing this to avoid the complexity and context switches, and we've already fixed up the remaining users and can now get rid of this case. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/aio.c | 24 +----------------------- fs/ecryptfs/file.c | 6 ------ fs/read_write.c | 26 ++++++++------------------ include/linux/aio.h | 4 ---- net/socket.c | 9 +++------ 5 files changed, 12 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/fs/aio.c b/fs/aio.c index 667054c7c067..8ca8df1c3550 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -778,22 +778,6 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, return 0; } -/* wait_on_sync_kiocb: - * Waits on the given sync kiocb to complete. - */ -ssize_t wait_on_sync_kiocb(struct kiocb *req) -{ - while (!req->ki_ctx) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (req->ki_ctx) - break; - io_schedule(); - } - __set_current_state(TASK_RUNNING); - return req->ki_user_data; -} -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 @@ -1025,13 +1009,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) * ref, no other paths have a way to get another ref * - the sync task helpfully left a reference to itself in the iocb */ - if (is_sync_kiocb(iocb)) { - iocb->ki_user_data = res; - smp_wmb(); - iocb->ki_ctx = ERR_PTR(-EXDEV); - wake_up_process(iocb->ki_obj.tsk); - return; - } + BUG_ON(is_sync_kiocb(iocb)); if (iocb->ki_list.next) { unsigned long flags; diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 6f4e659f508f..a36da8841e0c 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -52,12 +52,6 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb, struct file *file = iocb->ki_filp; rc = generic_file_read_iter(iocb, to); - /* - * Even though this is a async interface, we need to wait - * for IO to finish to update atime - */ - if (-EIOCBQUEUED == rc) - rc = wait_on_sync_kiocb(iocb); if (rc >= 0) { path = ecryptfs_dentry_to_lower_path(file->f_path.dentry); touch_atime(path); diff --git a/fs/read_write.c b/fs/read_write.c index f8b8fc1316ab..76e324e8ce8d 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -346,9 +346,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos) iter->type |= READ; ret = file->f_op->read_iter(&kiocb, iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - + BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; return ret; @@ -368,9 +366,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) iter->type |= WRITE; ret = file->f_op->write_iter(&kiocb, iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - + BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; return ret; @@ -426,8 +422,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp kiocb.ki_pos = *ppos; ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -446,8 +441,7 @@ ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *p iov_iter_init(&iter, READ, &iov, 1, len); ret = filp->f_op->read_iter(&kiocb, &iter); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -508,8 +502,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof kiocb.ki_pos = *ppos; ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -528,8 +521,7 @@ ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, lo iov_iter_init(&iter, WRITE, &iov, 1, len); ret = filp->f_op->write_iter(&kiocb, &iter); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -716,8 +708,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iove iov_iter_init(&iter, rw, iov, nr_segs, len); ret = fn(&kiocb, &iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -732,8 +723,7 @@ static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, kiocb.ki_pos = *ppos; ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } diff --git a/include/linux/aio.h b/include/linux/aio.h index 132d1ecba435..f8516430490d 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -37,7 +37,6 @@ struct kiocb { union { void __user *user; - struct task_struct *tsk; } ki_obj; __u64 ki_user_data; /* user's data for completion */ @@ -63,13 +62,11 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) *kiocb = (struct kiocb) { .ki_ctx = NULL, .ki_filp = filp, - .ki_obj.tsk = current, }; } /* prototypes */ #ifdef CONFIG_AIO -extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); extern void aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); @@ -77,7 +74,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else -static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline void aio_complete(struct kiocb *iocb, long res, long res2) { } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } diff --git a/net/socket.c b/net/socket.c index f92145554f34..f6c519d7b3ba 100644 --- a/net/socket.c +++ b/net/socket.c @@ -633,8 +633,7 @@ static int do_sock_sendmsg(struct socket *sock, struct msghdr *msg, init_sync_kiocb(&iocb, NULL); ret = nosec ? __sock_sendmsg_nosec(&iocb, sock, msg, size) : __sock_sendmsg(&iocb, sock, msg, size); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); + BUG_ON(ret == -EIOCBQUEUED); return ret; } @@ -766,8 +765,7 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, init_sync_kiocb(&iocb, NULL); ret = __sock_recvmsg(&iocb, sock, msg, size, flags); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); + BUG_ON(ret == -EIOCBQUEUED); return ret; } EXPORT_SYMBOL(sock_recvmsg); @@ -780,8 +778,7 @@ static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, init_sync_kiocb(&iocb, NULL); ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); + BUG_ON(ret == -EIOCBQUEUED); return ret; } -- cgit v1.2.3 From 04b2fa9f8f36ec6fb6fd1c9dc9df6fff0cd27323 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 2 Feb 2015 14:49:06 +0100 Subject: fs: split generic and aio kiocb Most callers in the kernel want to perform synchronous file I/O, but still have to bloat the stack with a full struct kiocb. Split out the parts needed in filesystem code from those in the aio code, and only allocate those needed to pass down argument on the stack. The aio code embedds the generic iocb in the one it allocates and can easily get back to it by using container_of. Also add a ->ki_complete method to struct kiocb, this is used to call into the aio code and thus removes the dependency on aio for filesystems impementing asynchronous operations. It will also allow other callers to substitute their own completion callback. We also add a new ->ki_flags field to work around the nasty layering violation recently introduced in commit 5e33f6 ("usb: gadget: ffs: add eventfd notification about ffs events"). Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- drivers/usb/gadget/function/f_fs.c | 5 +- drivers/usb/gadget/legacy/inode.c | 5 +- fs/aio.c | 94 ++++++++++++++++++++++++++------------ fs/direct-io.c | 4 +- fs/fuse/file.c | 2 +- fs/nfs/direct.c | 2 +- include/linux/aio.h | 46 +++---------------- 7 files changed, 81 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 175c9956cbe3..b64538b498dc 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -655,9 +655,10 @@ static void ffs_user_copy_worker(struct work_struct *work) unuse_mm(io_data->mm); } - aio_complete(io_data->kiocb, ret, ret); + io_data->kiocb->ki_complete(io_data->kiocb, ret, ret); - if (io_data->ffs->ffs_eventfd && !io_data->kiocb->ki_eventfd) + if (io_data->ffs->ffs_eventfd && + !(io_data->kiocb->ki_flags & IOCB_EVENTFD)) eventfd_signal(io_data->ffs->ffs_eventfd, 1); usb_ep_free_request(io_data->ep, io_data->req); diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 200f9a584064..a4a80694f607 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -469,7 +469,7 @@ static void ep_user_copy_worker(struct work_struct *work) ret = -EFAULT; /* completing the iocb can drop the ctx and mm, don't touch mm after */ - aio_complete(iocb, ret, ret); + iocb->ki_complete(iocb, ret, ret); kfree(priv->buf); kfree(priv->to_free); @@ -497,7 +497,8 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) kfree(priv); iocb->private = NULL; /* aio_complete() reports bytes-transferred _and_ faults */ - aio_complete(iocb, req->actual ? req->actual : req->status, + + iocb->ki_complete(iocb, req->actual ? req->actual : req->status, req->status); } else { /* ep_copy_to_user() won't report both; we hide some faults */ diff --git a/fs/aio.c b/fs/aio.c index 8ca8df1c3550..958286536a10 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -151,6 +151,38 @@ struct kioctx { unsigned id; }; +/* + * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either + * cancelled or completed (this makes a certain amount of sense because + * successful cancellation - io_cancel() - does deliver the completion to + * userspace). + * + * And since most things don't implement kiocb cancellation and we'd really like + * kiocb completion to be lockless when possible, we use ki_cancel to + * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED + * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel(). + */ +#define KIOCB_CANCELLED ((void *) (~0ULL)) + +struct aio_kiocb { + struct kiocb common; + + struct kioctx *ki_ctx; + kiocb_cancel_fn *ki_cancel; + + struct iocb __user *ki_user_iocb; /* user's aiocb */ + __u64 ki_user_data; /* user's data for completion */ + + struct list_head ki_list; /* the aio core uses this + * for cancellation */ + + /* + * If the aio_resfd field of the userspace iocb is not zero, + * this is the underlying eventfd context to deliver events to. + */ + struct eventfd_ctx *ki_eventfd; +}; + /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); unsigned long aio_nr; /* current system wide number of aio requests */ @@ -220,7 +252,7 @@ static int __init aio_setup(void) if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); - kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); + kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page)); @@ -480,8 +512,9 @@ static int aio_setup_ring(struct kioctx *ctx) #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) -void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) +void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { + struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common); struct kioctx *ctx = req->ki_ctx; unsigned long flags; @@ -496,7 +529,7 @@ void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) } EXPORT_SYMBOL(kiocb_set_cancel_fn); -static int kiocb_cancel(struct kiocb *kiocb) +static int kiocb_cancel(struct aio_kiocb *kiocb) { kiocb_cancel_fn *old, *cancel; @@ -514,7 +547,7 @@ static int kiocb_cancel(struct kiocb *kiocb) cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED); } while (cancel != old); - return cancel(kiocb); + return cancel(&kiocb->common); } static void free_ioctx(struct work_struct *work) @@ -550,13 +583,13 @@ static void free_ioctx_reqs(struct percpu_ref *ref) static void free_ioctx_users(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, users); - struct kiocb *req; + struct aio_kiocb *req; spin_lock_irq(&ctx->ctx_lock); while (!list_empty(&ctx->active_reqs)) { req = list_first_entry(&ctx->active_reqs, - struct kiocb, ki_list); + struct aio_kiocb, ki_list); list_del_init(&req->ki_list); kiocb_cancel(req); @@ -932,9 +965,9 @@ static void user_refill_reqs_available(struct kioctx *ctx) * Allocate a slot for an aio request. * Returns NULL if no requests are free. */ -static inline struct kiocb *aio_get_req(struct kioctx *ctx) +static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { - struct kiocb *req; + struct aio_kiocb *req; if (!get_reqs_available(ctx)) { user_refill_reqs_available(ctx); @@ -955,10 +988,10 @@ out_put: return NULL; } -static void kiocb_free(struct kiocb *req) +static void kiocb_free(struct aio_kiocb *req) { - if (req->ki_filp) - fput(req->ki_filp); + if (req->common.ki_filp) + fput(req->common.ki_filp); if (req->ki_eventfd != NULL) eventfd_ctx_put(req->ki_eventfd); kmem_cache_free(kiocb_cachep, req); @@ -994,8 +1027,9 @@ out: /* aio_complete * Called when the io request on the given iocb is complete. */ -void aio_complete(struct kiocb *iocb, long res, long res2) +static void aio_complete(struct kiocb *kiocb, long res, long res2) { + struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common); struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; @@ -1009,7 +1043,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) * ref, no other paths have a way to get another ref * - the sync task helpfully left a reference to itself in the iocb */ - BUG_ON(is_sync_kiocb(iocb)); + BUG_ON(is_sync_kiocb(kiocb)); if (iocb->ki_list.next) { unsigned long flags; @@ -1035,7 +1069,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; - event->obj = (u64)(unsigned long)iocb->ki_obj.user; + event->obj = (u64)(unsigned long)iocb->ki_user_iocb; event->data = iocb->ki_user_data; event->res = res; event->res2 = res2; @@ -1044,7 +1078,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data, + ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data, res, res2); /* after flagging the request as done, we @@ -1091,7 +1125,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2) percpu_ref_put(&ctx->reqs); } -EXPORT_SYMBOL(aio_complete); /* aio_read_events_ring * Pull an event off of the ioctx's event ring. Returns the number of @@ -1480,7 +1513,7 @@ rw_common: static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, struct iocb *iocb, bool compat) { - struct kiocb *req; + struct aio_kiocb *req; ssize_t ret; /* enforce forwards compatibility on users */ @@ -1503,11 +1536,14 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, if (unlikely(!req)) return -EAGAIN; - req->ki_filp = fget(iocb->aio_fildes); - if (unlikely(!req->ki_filp)) { + req->common.ki_filp = fget(iocb->aio_fildes); + if (unlikely(!req->common.ki_filp)) { ret = -EBADF; goto out_put_req; } + req->common.ki_pos = iocb->aio_offset; + req->common.ki_complete = aio_complete; + req->common.ki_flags = 0; if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* @@ -1522,6 +1558,8 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->ki_eventfd = NULL; goto out_put_req; } + + req->common.ki_flags |= IOCB_EVENTFD; } ret = put_user(KIOCB_KEY, &user_iocb->aio_key); @@ -1530,11 +1568,10 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, goto out_put_req; } - req->ki_obj.user = user_iocb; + req->ki_user_iocb = user_iocb; req->ki_user_data = iocb->aio_data; - req->ki_pos = iocb->aio_offset; - ret = aio_run_iocb(req, iocb->aio_lio_opcode, + ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode, (char __user *)(unsigned long)iocb->aio_buf, iocb->aio_nbytes, compat); @@ -1623,10 +1660,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, /* lookup_kiocb * Finds a given iocb for cancellation. */ -static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, - u32 key) +static struct aio_kiocb * +lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, u32 key) { - struct list_head *pos; + struct aio_kiocb *kiocb; assert_spin_locked(&ctx->ctx_lock); @@ -1634,9 +1671,8 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, 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) + list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { + if (kiocb->ki_user_iocb == iocb) return kiocb; } return NULL; @@ -1656,7 +1692,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) { struct kioctx *ctx; - struct kiocb *kiocb; + struct aio_kiocb *kiocb; u32 key; int ret; diff --git a/fs/direct-io.c b/fs/direct-io.c index e181b6b2e297..c38b460776e6 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -265,7 +265,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, ret = err; } - aio_complete(dio->iocb, ret, 0); + dio->iocb->ki_complete(dio->iocb, ret, 0); } kmem_cache_free(dio_cache, dio); @@ -1056,7 +1056,7 @@ static inline int drop_refcount(struct dio *dio) * operation. AIO can if it was a broken operation described above or * in fact if all the bios race to complete before we get here. In * that case dio_complete() translates the EIOCBQUEUED into the proper - * return code that the caller will hand to aio_complete(). + * return code that the caller will hand to ->complete(). * * This is managed by the bio_lock instead of being an atomic_t so that * completion paths can drop their ref and use the remaining count to diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f81d83eb9758..a5c5e38b3ff8 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -584,7 +584,7 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) spin_unlock(&fc->lock); } - aio_complete(io->iocb, res, 0); + io->iocb->ki_complete(io->iocb, res, 0); kfree(io); } } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 27cebf164070..5db3385fc108 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -393,7 +393,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write) long res = (long) dreq->error; if (!res) res = (long) dreq->count; - aio_complete(dreq->iocb, res, 0); + dreq->iocb->ki_complete(dreq->iocb, res, 0); } complete_all(&dreq->completion); diff --git a/include/linux/aio.h b/include/linux/aio.h index f8516430490d..5c40b61285ac 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -14,67 +14,38 @@ struct kiocb; #define KIOCB_KEY 0 -/* - * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either - * cancelled or completed (this makes a certain amount of sense because - * successful cancellation - io_cancel() - does deliver the completion to - * userspace). - * - * And since most things don't implement kiocb cancellation and we'd really like - * kiocb completion to be lockless when possible, we use ki_cancel to - * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED - * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel(). - */ -#define KIOCB_CANCELLED ((void *) (~0ULL)) - typedef int (kiocb_cancel_fn)(struct kiocb *); +#define IOCB_EVENTFD (1 << 0) + struct kiocb { struct file *ki_filp; - struct kioctx *ki_ctx; /* NULL for sync ops */ - kiocb_cancel_fn *ki_cancel; - void *private; - - union { - void __user *user; - } ki_obj; - - __u64 ki_user_data; /* user's data for completion */ loff_t ki_pos; - - struct list_head ki_list; /* the aio core uses this - * for cancellation */ - - /* - * If the aio_resfd field of the userspace iocb is not zero, - * this is the underlying eventfd context to deliver events to. - */ - struct eventfd_ctx *ki_eventfd; + void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); + void *private; + int ki_flags; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { - return kiocb->ki_ctx == NULL; + return kiocb->ki_complete == NULL; } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { - .ki_ctx = NULL, .ki_filp = filp, }; } /* prototypes */ #ifdef CONFIG_AIO -extern void aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else -static inline void aio_complete(struct kiocb *iocb, long res, long res2) { } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, @@ -84,11 +55,6 @@ static inline void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ -static inline struct kiocb *list_kiocb(struct list_head *h) -{ - return list_entry(h, struct kiocb, ki_list); -} - /* for sysctl: */ extern unsigned long aio_nr; extern unsigned long aio_max_nr; -- cgit v1.2.3 From e2e40f2c1ed433c5e224525c8c862fd32e5d3df2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 22 Feb 2015 08:58:50 -0800 Subject: fs: move struct kiocb to fs.h struct kiocb now is a generic I/O container, so move it to fs.h. Also do a #include diet for aio.h while we're at it. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- arch/s390/hypfs/inode.c | 2 +- drivers/char/mem.c | 2 +- drivers/char/tile-srom.c | 1 - drivers/infiniband/hw/ipath/ipath_file_ops.c | 1 - drivers/infiniband/hw/qib/qib_file_ops.c | 1 - drivers/misc/mei/amthif.c | 1 - drivers/misc/mei/main.c | 1 - drivers/misc/mei/pci-me.c | 1 - drivers/scsi/sg.c | 2 +- drivers/staging/unisys/include/timskmod.h | 1 - drivers/usb/gadget/function/f_fs.c | 1 + drivers/usb/gadget/legacy/inode.c | 1 + fs/9p/vfs_addr.c | 2 +- fs/affs/file.c | 2 +- fs/afs/write.c | 1 - fs/bfs/inode.c | 1 + fs/block_dev.c | 1 - fs/btrfs/file.c | 2 +- fs/btrfs/inode.c | 2 +- fs/ceph/file.c | 1 - fs/direct-io.c | 1 - fs/ecryptfs/file.c | 1 - fs/ext2/inode.c | 2 +- fs/ext3/inode.c | 2 +- fs/ext4/file.c | 2 +- fs/ext4/indirect.c | 2 +- fs/ext4/inode.c | 1 - fs/ext4/page-io.c | 1 - fs/f2fs/data.c | 2 +- fs/fat/inode.c | 1 - fs/fuse/cuse.c | 2 +- fs/fuse/dev.c | 1 - fs/fuse/file.c | 2 +- fs/gfs2/aops.c | 2 +- fs/gfs2/file.c | 1 - fs/hfs/inode.c | 2 +- fs/hfsplus/inode.c | 2 +- fs/jfs/inode.c | 2 +- fs/nfs/file.c | 1 - fs/nilfs2/inode.c | 2 +- fs/ntfs/file.c | 1 - fs/ntfs/inode.c | 1 - fs/ocfs2/aops.c | 1 + fs/ocfs2/aops.h | 2 +- fs/pipe.c | 1 - fs/read_write.c | 1 - fs/reiserfs/inode.c | 2 +- fs/splice.c | 1 - fs/ubifs/file.c | 1 - fs/udf/file.c | 2 +- fs/udf/inode.c | 2 +- fs/xfs/xfs_aops.c | 1 - fs/xfs/xfs_file.c | 1 - include/linux/aio.h | 31 +--------------------------- include/linux/fs.h | 22 ++++++++++++++++++++ include/net/sock.h | 1 - kernel/printk/printk.c | 2 +- kernel/sysctl.c | 1 + mm/filemap.c | 1 - mm/page_io.c | 2 +- mm/shmem.c | 2 +- net/ipv4/raw.c | 1 - sound/core/pcm_native.c | 2 +- 63 files changed, 55 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 4c8008dd938e..ad66b07f742e 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include "hypfs.h" diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 297110c12635..9c4fd7a8e2e5 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include diff --git a/drivers/char/tile-srom.c b/drivers/char/tile-srom.c index 02e76ac6d282..69f6b4acc377 100644 --- a/drivers/char/tile-srom.c +++ b/drivers/char/tile-srom.c @@ -27,7 +27,6 @@ #include /* size_t */ #include #include /* O_ACCMODE */ -#include #include #include #include diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c index 6d7f453b4d05..aed8afee56da 100644 --- a/drivers/infiniband/hw/ipath/ipath_file_ops.c +++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c @@ -40,7 +40,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index b15e34eeef68..826c17ee4c7d 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -39,7 +39,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c index c4cb9a984a5f..40ea639fa413 100644 --- a/drivers/misc/mei/amthif.c +++ b/drivers/misc/mei/amthif.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 3c019c0e60eb..47680c84801c 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index bd3039ab8f98..af44ee26075d 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 0cbc1fb45f10..c78a6f7bbc20 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -33,7 +33,6 @@ static int sg_version_num = 30536; /* 2 digits for each component */ #include #include #include -#include #include #include #include @@ -51,6 +50,7 @@ static int sg_version_num = 30536; /* 2 digits for each component */ #include #include #include +#include #include "scsi.h" #include diff --git a/drivers/staging/unisys/include/timskmod.h b/drivers/staging/unisys/include/timskmod.h index 4019a0d63645..52648d4d9922 100644 --- a/drivers/staging/unisys/include/timskmod.h +++ b/drivers/staging/unisys/include/timskmod.h @@ -46,7 +46,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index b64538b498dc..a12315a78248 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index a4a80694f607..662ef2c1c62b 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index eb14e055ea83..ff1a5bac4200 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include diff --git a/fs/affs/file.c b/fs/affs/file.c index d2468bf95669..33eaa67bb026 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -12,7 +12,7 @@ * affs regular file handling primitives */ -#include +#include #include "affs.h" static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext); diff --git a/fs/afs/write.c b/fs/afs/write.c index c13cb08964ed..0714abcd7f32 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -14,7 +14,6 @@ #include #include #include -#include #include "internal.h" static int afs_write_back_from_locked_page(struct afs_writeback *wb, diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 90bc079d9982..fdcb4d69f430 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include "bfs.h" diff --git a/fs/block_dev.c b/fs/block_dev.c index 975266be67d3..2e522aed6584 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include "internal.h" diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b78bbbac900d..69c9508d2c7e 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include @@ -32,6 +31,7 @@ #include #include #include +#include #include "ctree.h" #include "disk-io.h" #include "transaction.h" diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 54bcf639d1cf..b214ab178f3a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -32,7 +32,6 @@ #include #include #include -#include #include #include #include @@ -43,6 +42,7 @@ #include #include #include +#include #include "ctree.h" #include "disk-io.h" #include "transaction.h" diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 081c4e3f9e49..98e257c1b5b1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include "super.h" diff --git a/fs/direct-io.c b/fs/direct-io.c index c38b460776e6..6fb00e3f1059 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -37,7 +37,6 @@ #include #include #include -#include /* * How many user pages to map in one call to get_user_pages(). This determines diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index a36da8841e0c..273d36e3f0c0 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -31,7 +31,6 @@ #include #include #include -#include #include "ecryptfs_kernel.h" /** diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 6434bc000125..df9d6afbc5d5 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include #include "ext2.h" #include "acl.h" #include "xattr.h" diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 2c6ccc49ba27..db07ffbe7c85 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -27,7 +27,7 @@ #include #include #include -#include +#include #include "ext3.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 33a09da16c9c..598abbbe6786 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -23,9 +23,9 @@ #include #include #include -#include #include #include +#include #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 6b9878a24182..8611640856d3 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -20,9 +20,9 @@ * (sct@redhat.com), 1993, 1998 */ -#include #include "ext4_jbd2.h" #include "truncate.h" +#include #include diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 85404f15e53a..6325d2c1a65c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include "ext4_jbd2.h" diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index b24a2541a9ba..464984261e69 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 985ed023a750..497f8515d205 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -12,12 +12,12 @@ #include #include #include -#include #include #include #include #include #include +#include #include "f2fs.h" #include "node.h" diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 497c7c5263c7..8521207de229 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 28d0c7abba1c..b3fa05032234 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -38,7 +38,6 @@ #include #include #include -#include #include #include #include @@ -48,6 +47,7 @@ #include #include #include +#include #include "fuse_i.h" diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index ed19a7d622fa..8c92c727ddd6 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -19,7 +19,6 @@ #include #include #include -#include MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a5c5e38b3ff8..ff102cbf16ea 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -15,8 +15,8 @@ #include #include #include -#include #include +#include static const struct file_operations fuse_direct_io_file_operations; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 4ad4f94edebe..fe6634d25d1d 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include "gfs2.h" diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 3e32bb8e2d7e..f6fc412b1100 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include "gfs2.h" diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index d0929bc81782..98d4ea45bb70 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include "hfs_fs.h" #include "btree.h" diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 0cf786f2d046..f541196d4ee9 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include "hfsplus_fs.h" #include "hfsplus_raw.h" diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index bd3df1ca3c9b..3197aed10614 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -22,8 +22,8 @@ #include #include #include +#include #include -#include #include "jfs_incore.h" #include "jfs_inode.h" #include "jfs_filsys.h" diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 94712fc781fa..5d8b89cb13c0 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 8b5969538f39..ab4987bc637f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include "nilfs.h" #include "btnode.h" #include "segment.h" diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 1da9b2d184dc..f16f2d8401fe 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 898b9949d363..1d0c21df0d80 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -28,7 +28,6 @@ #include #include #include -#include #include "aops.h" #include "attrib.h" diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 44db1808cdb5..e1bf18c5d25e 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -29,6 +29,7 @@ #include #include #include +#include #include diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 6cae155d54df..dd59599b022d 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -22,7 +22,7 @@ #ifndef OCFS2_AOPS_H #define OCFS2_AOPS_H -#include +#include handle_t *ocfs2_start_walk_page_trans(struct inode *inode, struct page *page, diff --git a/fs/pipe.c b/fs/pipe.c index 21981e58e2a6..2d084f2d0b83 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include diff --git a/fs/read_write.c b/fs/read_write.c index 76e324e8ce8d..99a6ef946d01 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index e72401e1f995..9312b7842e03 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); diff --git a/fs/splice.c b/fs/splice.c index 7968da96bebb..4bbfa95b5bfe 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -32,7 +32,6 @@ #include #include #include -#include #include "internal.h" /* diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index e627c0acf626..c3d15fe83403 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -50,7 +50,6 @@ */ #include "ubifs.h" -#include #include #include #include diff --git a/fs/udf/file.c b/fs/udf/file.c index 9c0b6da9dbb3..7f885cc8b0b7 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include "udf_i.h" #include "udf_sb.h" diff --git a/fs/udf/inode.c b/fs/udf/inode.c index a445d599098d..9c1fbd23913d 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include "udf_i.h" #include "udf_sb.h" diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3a9b7a1b8704..4f8cdc59bc38 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -31,7 +31,6 @@ #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" -#include #include #include #include diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1cdba95c78cb..f527618cb42b 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -37,7 +37,6 @@ #include "xfs_log.h" #include "xfs_icache.h" -#include #include #include #include diff --git a/include/linux/aio.h b/include/linux/aio.h index 5c40b61285ac..9eb42dbc5582 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -1,52 +1,23 @@ #ifndef __LINUX__AIO_H #define __LINUX__AIO_H -#include -#include #include -#include -#include - -#include struct kioctx; struct kiocb; +struct mm_struct; #define KIOCB_KEY 0 typedef int (kiocb_cancel_fn)(struct kiocb *); -#define IOCB_EVENTFD (1 << 0) - -struct kiocb { - struct file *ki_filp; - loff_t ki_pos; - void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); - void *private; - int ki_flags; -}; - -static inline bool is_sync_kiocb(struct kiocb *kiocb) -{ - return kiocb->ki_complete == NULL; -} - -static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) -{ - *kiocb = (struct kiocb) { - .ki_filp = filp, - }; -} - /* prototypes */ #ifdef CONFIG_AIO -struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else -struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user * __user *iocbpp, diff --git a/include/linux/fs.h b/include/linux/fs.h index 447932aed1e1..48c1472bde4a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -314,6 +314,28 @@ struct page; struct address_space; struct writeback_control; +#define IOCB_EVENTFD (1 << 0) + +struct kiocb { + struct file *ki_filp; + loff_t ki_pos; + void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); + void *private; + int ki_flags; +}; + +static inline bool is_sync_kiocb(struct kiocb *kiocb) +{ + return kiocb->ki_complete == NULL; +} + +static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + }; +} + /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet diff --git a/include/net/sock.h b/include/net/sock.h index ab186b1d31ff..71c1300025e2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -57,7 +57,6 @@ #include #include #include -#include #include #include diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 60b2aa2a2da9..40d50cc4c686 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -32,7 +32,6 @@ #include #include #include -#include #include #include #include @@ -46,6 +45,7 @@ #include #include #include +#include #include diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 88ea2d6e0031..83d907afb4a6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -19,6 +19,7 @@ */ #include +#include #include #include #include diff --git a/mm/filemap.c b/mm/filemap.c index ad7242043bdb..876f4e6f3ed6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/mm/page_io.c b/mm/page_io.c index 7ef21577856c..a96c8562d835 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -20,8 +20,8 @@ #include #include #include -#include #include +#include #include static struct bio *get_swap_bio(gfp_t gfp_flags, diff --git a/mm/shmem.c b/mm/shmem.c index a63031fa3e0c..944b94079bb0 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include static struct vfsmount *shm_mnt; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index f027a708b7e0..4a356b7c081b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -46,7 +46,6 @@ #include #include #include -#include #include #include #include diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index b03a638b420c..9ecff240a39b 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include @@ -35,6 +34,7 @@ #include #include #include +#include /* * Compatibility -- cgit v1.2.3 From bc917be8105993c256338ad1189650364a741483 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 21 Mar 2015 17:45:43 -0400 Subject: saner iov_iter initialization primitives iovec-backed iov_iter instances are assumed to satisfy several properties: * no more than UIO_MAXIOV elements in iovec array * total size of all ranges is no more than MAX_RW_COUNT * all ranges pass access_ok(). The problem is, invariants of data structures should be established in the primitives creating those data structures, not in the code using those primitives. And iov_iter_init() violates that principle. For a while we managed to get away with that, but once the use of iov_iter started to spread, it didn't take long for shit to hit the fan - missed check in sys_sendto() had introduced a roothole. We _do_ have primitives for importing and validating iovecs (both native and compat ones) and those primitives are almost always followed by shoving the resulting iovec into iov_iter. Life would be considerably simpler (and safer) if we combined those primitives with initializing iov_iter. That gives us two new primitives - import_iovec() and compat_import_iovec(). Calling conventions: iovec = iov_array; err = import_iovec(direction, uvec, nr_segs, ARRAY_SIZE(iov_array), &iovec, &iter); imports user vector into kernel space (into iov_array if it fits, allocated if it doesn't fit or if iovec was NULL), validates it and sets iter up to refer to it. On success 0 is returned and allocated kernel copy (or NULL if the array had fit into caller-supplied one) is returned via iovec. On failure all allocations are undone and -E... is returned. If the total size of ranges exceeds MAX_RW_COUNT, the excess is silently truncated. compat_import_iovec() expects uvec to be a pointer to user array of compat_iovec; otherwise it's identical to import_iovec(). Finally, import_single_range() sets iov_iter backed by single-element iovec covering a user-supplied range - err = import_single_range(direction, address, size, iovec, &iter); does validation and sets iter up. Again, size in excess of MAX_RW_COUNT gets silently truncated. Next commits will be switching the things up to use of those and reducing the amount of iov_iter_init() instances. Signed-off-by: Al Viro --- include/linux/uio.h | 14 +++++++++++++ lib/iov_iter.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 71880299ed48..1f4a37f1f025 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -139,4 +139,18 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); +int import_iovec(int type, const struct iovec __user * uvector, + unsigned nr_segs, unsigned fast_segs, + struct iovec **iov, struct iov_iter *i); + +#ifdef CONFIG_COMPAT +struct compat_iovec; +int compat_import_iovec(int type, const struct compat_iovec __user * uvector, + unsigned nr_segs, unsigned fast_segs, + struct iovec **iov, struct iov_iter *i); +#endif + +int import_single_range(int type, void __user *buf, size_t len, + struct iovec *iov, struct iov_iter *i); + #endif diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9d96e283520c..fc6e33f6b7f3 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -766,3 +766,60 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) flags); } EXPORT_SYMBOL(dup_iter); + +int import_iovec(int type, const struct iovec __user * uvector, + unsigned nr_segs, unsigned fast_segs, + struct iovec **iov, struct iov_iter *i) +{ + ssize_t n; + struct iovec *p; + n = rw_copy_check_uvector(type, uvector, nr_segs, fast_segs, + *iov, &p); + if (n < 0) { + if (p != *iov) + kfree(p); + *iov = NULL; + return n; + } + iov_iter_init(i, type, p, nr_segs, n); + *iov = p == *iov ? NULL : p; + return 0; +} +EXPORT_SYMBOL(import_iovec); + +#ifdef CONFIG_COMPAT +#include + +int compat_import_iovec(int type, const struct compat_iovec __user * uvector, + unsigned nr_segs, unsigned fast_segs, + struct iovec **iov, struct iov_iter *i) +{ + ssize_t n; + struct iovec *p; + n = compat_rw_copy_check_uvector(type, uvector, nr_segs, fast_segs, + *iov, &p); + if (n < 0) { + if (p != *iov) + kfree(p); + *iov = NULL; + return n; + } + iov_iter_init(i, type, p, nr_segs, n); + *iov = p == *iov ? NULL : p; + return 0; +} +#endif + +int import_single_range(int rw, void __user *buf, size_t len, + struct iovec *iov, struct iov_iter *i) +{ + if (len > MAX_RW_COUNT) + len = MAX_RW_COUNT; + if (unlikely(!access_ok(!rw, buf, len))) + return -EFAULT; + + iov->iov_base = buf; + iov->iov_len = len; + iov_iter_init(i, rw, iov, 1, len); + return 0; +} -- cgit v1.2.3 From fd2f7cb5bcac58b63717cd45366bff9a6ab961c6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 22 Feb 2015 20:07:13 -0500 Subject: kill struct filename.separate just make const char iname[] the last member and compare name->name with name->iname instead of checking name->separate We need to make sure that out-of-line name doesn't end up allocated adjacent to struct filename refering to it; fortunately, it's easy to achieve - just allocate that struct filename with one byte in ->iname[], so that ->iname[0] will be inside the same object and thus have an address different from that of out-of-line name [spotted by Boqun Feng ] Signed-off-by: Al Viro --- fs/namei.c | 29 ++++++++++++++++------------- include/linux/fs.h | 2 +- 2 files changed, 17 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 2c4b68c12550..6218e62a0534 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -119,7 +119,7 @@ * PATH_MAX includes the nul terminator --RR. */ -#define EMBEDDED_NAME_MAX (PATH_MAX - sizeof(struct filename)) +#define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * getname_flags(const char __user *filename, int flags, int *empty) @@ -140,9 +140,8 @@ getname_flags(const char __user *filename, int flags, int *empty) * First, try to embed the struct filename inside the names_cache * allocation */ - kname = (char *)result + sizeof(*result); + kname = (char *)result->iname; result->name = kname; - result->separate = false; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); if (unlikely(len < 0)) { @@ -157,15 +156,20 @@ getname_flags(const char __user *filename, int flags, int *empty) * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) { + const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; - result = kzalloc(sizeof(*result), GFP_KERNEL); + /* + * size is chosen that way we to guarantee that + * result->iname[0] is within the same object and that + * kname can't be equal to result->iname, no matter what. + */ + result = kzalloc(size, GFP_KERNEL); if (unlikely(!result)) { __putname(kname); return ERR_PTR(-ENOMEM); } result->name = kname; - result->separate = true; len = strncpy_from_user(kname, filename, PATH_MAX); if (unlikely(len < 0)) { __putname(kname); @@ -213,8 +217,7 @@ getname_kernel(const char * filename) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { - result->name = (char *)(result) + sizeof(*result); - result->separate = false; + result->name = (char *)result->iname; } else if (len <= PATH_MAX) { struct filename *tmp; @@ -224,7 +227,6 @@ getname_kernel(const char * filename) return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; - tmp->separate = true; result = tmp; } else { __putname(result); @@ -246,7 +248,7 @@ void putname(struct filename *name) if (--name->refcnt > 0) return; - if (name->separate) { + if (name->name != name->iname) { __putname(name->name); kfree(name); } else @@ -1852,6 +1854,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags, struct nameidata *nd) { int retval = 0; + const char *s = name->name; nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT; @@ -1860,7 +1863,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags, if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; - if (name->name[0]) { + if (*s) { if (!d_can_lookup(root)) return -ENOTDIR; retval = inode_permission(inode, MAY_EXEC); @@ -1882,7 +1885,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags, nd->root.mnt = NULL; nd->m_seq = read_seqbegin(&mount_lock); - if (name->name[0] == '/') { + if (*s == '/') { if (flags & LOOKUP_RCU) { rcu_read_lock(); nd->seq = set_root_rcu(nd); @@ -1916,7 +1919,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags, dentry = f.file->f_path.dentry; - if (name->name[0]) { + if (*s) { if (!d_can_lookup(dentry)) { fdput(f); return -ENOTDIR; @@ -1946,7 +1949,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags, return -ECHILD; done: current->total_link_count = 0; - return link_path_walk(name->name, nd); + return link_path_walk(s, nd); } static void path_cleanup(struct nameidata *nd) diff --git a/include/linux/fs.h b/include/linux/fs.h index b4d71b5e1ff2..d70e333988f1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2144,7 +2144,7 @@ struct filename { const __user char *uptr; /* original userland pointer */ struct audit_names *aname; int refcnt; - bool separate; /* should "name" be freed? */ + const char iname[]; }; extern long vfs_truncate(struct path *, loff_t); -- cgit v1.2.3 From 3f7036a071b879da017eddaedb10fba173fdf1ff Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 8 Mar 2015 19:28:30 -0400 Subject: switch security_inode_getattr() to struct path * Signed-off-by: Al Viro --- fs/stat.c | 2 +- include/linux/security.h | 7 +++---- security/apparmor/lsm.c | 6 +++--- security/capability.c | 2 +- security/security.c | 6 +++--- security/selinux/hooks.c | 12 +++--------- security/smack/smack_lsm.c | 13 +++++-------- security/tomoyo/common.h | 2 +- security/tomoyo/file.c | 4 ++-- security/tomoyo/tomoyo.c | 5 ++--- 10 files changed, 24 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/fs/stat.c b/fs/stat.c index ae0c3cef9927..19636af5e75c 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -66,7 +66,7 @@ int vfs_getattr(struct path *path, struct kstat *stat) { int retval; - retval = security_inode_getattr(path->mnt, path->dentry); + retval = security_inode_getattr(path); if (retval) return retval; return vfs_getattr_nosec(path, stat); diff --git a/include/linux/security.h b/include/linux/security.h index a1b7dbd127ff..4e14e3d6309f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1556,7 +1556,7 @@ struct security_operations { int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd); int (*inode_permission) (struct inode *inode, int mask); int (*inode_setattr) (struct dentry *dentry, struct iattr *attr); - int (*inode_getattr) (struct vfsmount *mnt, struct dentry *dentry); + int (*inode_getattr) (const struct path *path); int (*inode_setxattr) (struct dentry *dentry, const char *name, const void *value, size_t size, int flags); void (*inode_post_setxattr) (struct dentry *dentry, const char *name, @@ -1843,7 +1843,7 @@ int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); int security_inode_permission(struct inode *inode, int mask); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); -int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry); +int security_inode_getattr(const struct path *path); int security_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); void security_inode_post_setxattr(struct dentry *dentry, const char *name, @@ -2259,8 +2259,7 @@ static inline int security_inode_setattr(struct dentry *dentry, return 0; } -static inline int security_inode_getattr(struct vfsmount *mnt, - struct dentry *dentry) +static inline int security_inode_getattr(const struct path *path) { return 0; } diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 107db88b1d5f..dd56bffd6500 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -364,12 +364,12 @@ static int apparmor_path_chown(struct path *path, kuid_t uid, kgid_t gid) return common_perm(OP_CHOWN, path, AA_MAY_CHOWN, &cond); } -static int apparmor_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) +static int apparmor_inode_getattr(const struct path *path) { - if (!mediated_filesystem(dentry)) + if (!mediated_filesystem(path->dentry)) return 0; - return common_perm_mnt_dentry(OP_GETATTR, mnt, dentry, + return common_perm_mnt_dentry(OP_GETATTR, path->mnt, path->dentry, AA_MAY_META_READ); } diff --git a/security/capability.c b/security/capability.c index 070dd46f62f4..bdf22034a961 100644 --- a/security/capability.c +++ b/security/capability.c @@ -225,7 +225,7 @@ static int cap_inode_setattr(struct dentry *dentry, struct iattr *iattr) return 0; } -static int cap_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) +static int cap_inode_getattr(const struct path *path) { return 0; } diff --git a/security/security.c b/security/security.c index e81d5bbe7363..ed890c6d31c5 100644 --- a/security/security.c +++ b/security/security.c @@ -608,11 +608,11 @@ int security_inode_setattr(struct dentry *dentry, struct iattr *attr) } EXPORT_SYMBOL_GPL(security_inode_setattr); -int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) +int security_inode_getattr(const struct path *path) { - if (unlikely(IS_PRIVATE(dentry->d_inode))) + if (unlikely(IS_PRIVATE(path->dentry->d_inode))) return 0; - return security_ops->inode_getattr(mnt, dentry); + return security_ops->inode_getattr(path); } int security_inode_setxattr(struct dentry *dentry, const char *name, diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4d1a54190388..e119cdcffc87 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1623,7 +1623,7 @@ static inline int dentry_has_perm(const struct cred *cred, the path to help the auditing code to more easily generate the pathname if needed. */ static inline int path_has_perm(const struct cred *cred, - struct path *path, + const struct path *path, u32 av) { struct inode *inode = path->dentry->d_inode; @@ -2954,15 +2954,9 @@ static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) return dentry_has_perm(cred, dentry, av); } -static int selinux_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) +static int selinux_inode_getattr(const struct path *path) { - const struct cred *cred = current_cred(); - struct path path; - - path.dentry = dentry; - path.mnt = mnt; - - return path_has_perm(cred, &path, FILE__GETATTR); + return path_has_perm(current_cred(), path, FILE__GETATTR); } static int selinux_inode_setotherxattr(struct dentry *dentry, const char *name) diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index c934311812f1..1511965549b8 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1034,19 +1034,16 @@ static int smack_inode_setattr(struct dentry *dentry, struct iattr *iattr) * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) +static int smack_inode_getattr(const struct path *path) { struct smk_audit_info ad; - struct path path; + struct inode *inode = path->dentry->d_inode; int rc; - path.dentry = dentry; - path.mnt = mnt; - smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH); - smk_ad_setfield_u_fs_path(&ad, path); - rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad); - rc = smk_bu_inode(dentry->d_inode, MAY_READ, rc); + smk_ad_setfield_u_fs_path(&ad, *path); + rc = smk_curacc(smk_of_inode(inode), MAY_READ, &ad); + rc = smk_bu_inode(inode, MAY_READ, rc); return rc; } diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h index 6627102c24af..f9c9fb1d56b4 100644 --- a/security/tomoyo/common.h +++ b/security/tomoyo/common.h @@ -978,7 +978,7 @@ int tomoyo_path2_perm(const u8 operation, struct path *path1, struct path *path2); int tomoyo_path_number_perm(const u8 operation, struct path *path, unsigned long number); -int tomoyo_path_perm(const u8 operation, struct path *path, +int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target); unsigned int tomoyo_poll_control(struct file *file, poll_table *wait); unsigned int tomoyo_poll_log(struct file *file, poll_table *wait); diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c index c151a1869597..2367b100cc62 100644 --- a/security/tomoyo/file.c +++ b/security/tomoyo/file.c @@ -145,7 +145,7 @@ static void tomoyo_add_slash(struct tomoyo_path_info *buf) * * Returns true on success, false otherwise. */ -static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, struct path *path) +static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, const struct path *path) { buf->name = tomoyo_realpath_from_path(path); if (buf->name) { @@ -782,7 +782,7 @@ int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, * * Returns 0 on success, negative value otherwise. */ -int tomoyo_path_perm(const u8 operation, struct path *path, const char *target) +int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index f0b756e27fed..57c88d52ffa5 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -144,10 +144,9 @@ static int tomoyo_bprm_check_security(struct linux_binprm *bprm) * * Returns 0 on success, negative value otherwise. */ -static int tomoyo_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) +static int tomoyo_inode_getattr(const struct path *path) { - struct path path = { mnt, dentry }; - return tomoyo_path_perm(TOMOYO_TYPE_GETATTR, &path, NULL); + return tomoyo_path_perm(TOMOYO_TYPE_GETATTR, path, NULL); } /** -- cgit v1.2.3 From 171a02032bf1e1bb35442a38d6e25e0dcbb85c63 Mon Sep 17 00:00:00 2001 From: Anton Altaparmakov Date: Wed, 11 Mar 2015 10:43:31 -0400 Subject: VFS: Add iov_iter_fault_in_multipages_readable() simillar to iov_iter_fault_in_readable() but differs in that it is not limited to faulting in the first iovec and instead faults in "bytes" bytes iterating over the iovecs as necessary. Also, instead of only faulting in the first and last page of the range, all pages are faulted in. This function is needed by NTFS when it does multi page file writes. Signed-off-by: Anton Altaparmakov Signed-off-by: Al Viro --- include/linux/uio.h | 1 + lib/iov_iter.c | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 71880299ed48..a69ed25af07f 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -76,6 +76,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); +int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9d96e283520c..b80f84376b91 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -317,6 +317,32 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) } EXPORT_SYMBOL(iov_iter_fault_in_readable); +/* + * Fault in one or more iovecs of the given iov_iter, to a maximum length of + * bytes. For each iovec, fault in each page that constitutes the iovec. + * + * Return 0 on success, or non-zero if the memory could not be accessed (i.e. + * because it is an invalid address). + */ +int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes) +{ + size_t skip = i->iov_offset; + const struct iovec *iov; + int err; + struct iovec v; + + if (!(i->type & (ITER_BVEC|ITER_KVEC))) { + iterate_iovec(i, bytes, v, iov, skip, ({ + err = fault_in_multipages_readable(v.iov_base, + v.iov_len); + if (unlikely(err)) + return err; + 0;})) + } + return 0; +} +EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable); + void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) -- cgit v1.2.3