diff options
Diffstat (limited to 'fs')
66 files changed, 1446 insertions, 933 deletions
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 <linux/pagemap.h> #include <linux/idr.h> #include <linux/sched.h> -#include <linux/aio.h> +#include <linux/uio.h> #include <net/9p/9p.h> #include <net/9p/client.h> diff --git a/fs/Makefile b/fs/Makefile index a88ac4838c9e..cb92fd4c3172 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -118,6 +118,7 @@ obj-$(CONFIG_HOSTFS) += hostfs/ obj-$(CONFIG_HPPFS) += hppfs/ obj-$(CONFIG_CACHEFILES) += cachefiles/ obj-$(CONFIG_DEBUG_FS) += debugfs/ +obj-$(CONFIG_TRACING) += tracefs/ obj-$(CONFIG_OCFS2_FS) += ocfs2/ obj-$(CONFIG_BTRFS_FS) += btrfs/ obj-$(CONFIG_GFS2_FS) += gfs2/ diff --git a/fs/affs/file.c b/fs/affs/file.c index a91795e01a7f..3aa7eb66547e 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -12,7 +12,7 @@ * affs regular file handling primitives */ -#include <linux/aio.h> +#include <linux/uio.h> #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 <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, @@ -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)); @@ -484,8 +516,9 @@ 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; @@ -500,7 +533,7 @@ 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; @@ -518,7 +551,7 @@ 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) @@ -554,13 +587,13 @@ 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); @@ -786,22 +819,6 @@ 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 @@ -956,9 +973,9 @@ 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); @@ -979,10 +996,10 @@ 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); @@ -1018,8 +1035,9 @@ 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; @@ -1033,13 +1051,7 @@ 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(kiocb)); if (iocb->ki_list.next) { unsigned long flags; @@ -1065,7 +1077,7 @@ 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; @@ -1074,7 +1086,7 @@ 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 @@ -1121,7 +1133,6 @@ 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 @@ -1349,46 +1360,19 @@ typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *, unsigned long, loff_t); typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *); -static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb, - int rw, char __user *buf, - unsigned long *nr_segs, - struct iovec **iovec, - bool compat) +static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len, + struct iovec **iovec, + bool compat, + struct iov_iter *iter) { - ssize_t ret; - - *nr_segs = kiocb->ki_nbytes; - #ifdef CONFIG_COMPAT if (compat) - ret = compat_rw_copy_check_uvector(rw, + return compat_import_iovec(rw, (struct compat_iovec __user *)buf, - *nr_segs, UIO_FASTIOV, *iovec, iovec); - else + len, UIO_FASTIOV, iovec, iter); #endif - ret = rw_copy_check_uvector(rw, - (struct iovec __user *)buf, - *nr_segs, UIO_FASTIOV, *iovec, iovec); - if (ret < 0) - return ret; - - /* ki_nbytes now reflect bytes instead of segs */ - kiocb->ki_nbytes = ret; - return 0; -} - -static ssize_t aio_setup_single_vector(struct kiocb *kiocb, - int rw, char __user *buf, - unsigned long *nr_segs, - struct iovec *iovec) -{ - if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes))) - return -EFAULT; - - iovec->iov_base = buf; - iovec->iov_len = kiocb->ki_nbytes; - *nr_segs = 1; - return 0; + return import_iovec(rw, (struct iovec __user *)buf, + len, UIO_FASTIOV, iovec, iter); } /* @@ -1396,11 +1380,10 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb, * Performs the initial checks and io submission. */ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, - char __user *buf, bool compat) + char __user *buf, size_t len, bool compat) { struct file *file = req->ki_filp; ssize_t ret; - unsigned long nr_segs; int rw; fmode_t mode; aio_rw_op *rw_op; @@ -1431,21 +1414,22 @@ rw_common: if (!rw_op && !iter_op) return -EINVAL; - ret = (opcode == IOCB_CMD_PREADV || - opcode == IOCB_CMD_PWRITEV) - ? aio_setup_vectored_rw(req, rw, buf, &nr_segs, - &iovec, compat) - : aio_setup_single_vector(req, rw, buf, &nr_segs, - iovec); + if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV) + ret = aio_setup_vectored_rw(rw, buf, len, + &iovec, compat, &iter); + else { + ret = import_single_range(rw, buf, len, iovec, &iter); + iovec = NULL; + } if (!ret) - ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); + ret = rw_verify_area(rw, file, &req->ki_pos, + iov_iter_count(&iter)); if (ret < 0) { - if (iovec != inline_vecs) - kfree(iovec); + kfree(iovec); return ret; } - req->ki_nbytes = ret; + len = ret; /* XXX: move/kill - rw_verify_area()? */ /* This matches the pread()/pwrite() logic */ @@ -1458,14 +1442,14 @@ rw_common: file_start_write(file); if (iter_op) { - iov_iter_init(&iter, rw, iovec, nr_segs, req->ki_nbytes); ret = iter_op(req, &iter); } else { - ret = rw_op(req, iovec, nr_segs, req->ki_pos); + ret = rw_op(req, iter.iov, iter.nr_segs, req->ki_pos); } if (rw == WRITE) file_end_write(file); + kfree(iovec); break; case IOCB_CMD_FDSYNC: @@ -1487,9 +1471,6 @@ rw_common: return -EINVAL; } - if (iovec != inline_vecs) - kfree(iovec); - if (ret != -EIOCBQUEUED) { /* * There's no easy way to restart the syscall since other AIO's @@ -1508,7 +1489,7 @@ 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 */ @@ -1531,11 +1512,14 @@ 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) { /* @@ -1550,6 +1534,8 @@ 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); @@ -1558,13 +1544,12 @@ 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; - req->ki_nbytes = iocb->aio_nbytes; - 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); if (ret) goto out_put_req; @@ -1651,10 +1636,10 @@ 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); @@ -1662,9 +1647,8 @@ 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; @@ -1684,7 +1668,7 @@ 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/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 <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/writeback.h> +#include <linux/uio.h> #include <asm/uaccess.h> #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 <linux/namei.h> #include <linux/log2.h> #include <linux/cleancache.h> -#include <linux/aio.h> #include <asm/uaccess.h> #include "internal.h" diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 30982bbd31c3..aee18f84e315 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -24,7 +24,6 @@ #include <linux/string.h> #include <linux/backing-dev.h> #include <linux/mpage.h> -#include <linux/aio.h> #include <linux/falloc.h> #include <linux/swap.h> #include <linux/writeback.h> @@ -32,6 +31,7 @@ #include <linux/compat.h> #include <linux/slab.h> #include <linux/btrfs.h> +#include <linux/uio.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d2e732d7af52..686331f22b15 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -32,7 +32,6 @@ #include <linux/writeback.h> #include <linux/statfs.h> #include <linux/compat.h> -#include <linux/aio.h> #include <linux/bit_spinlock.h> #include <linux/xattr.h> #include <linux/posix_acl.h> @@ -43,6 +42,7 @@ #include <linux/btrfs.h> #include <linux/blkdev.h> #include <linux/posix_acl_xattr.h> +#include <linux/uio.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d533075a823d..139f2fea91a0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -7,7 +7,6 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/writeback.h> -#include <linux/aio.h> #include <linux/falloc.h> #include "super.h" @@ -808,7 +807,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *filp = iocb->ki_filp; struct ceph_file_info *fi = filp->private_data; - size_t len = iocb->ki_nbytes; + size_t len = iov_iter_count(to); struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); struct page *pinned_page = NULL; diff --git a/fs/dcache.c b/fs/dcache.c index c71e3732e53b..d99736a63e3c 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2690,7 +2690,7 @@ static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL, *m2 = NULL; - int ret = -EBUSY; + int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) diff --git a/fs/direct-io.c b/fs/direct-io.c index e181b6b2e297..6fb00e3f1059 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -37,7 +37,6 @@ #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 @@ -265,7 +264,7 @@ 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 +1055,7 @@ 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/ecryptfs/file.c b/fs/ecryptfs/file.c index fd39bad6f1bd..79675089443d 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -31,7 +31,6 @@ #include <linux/security.h> #include <linux/compat.h> #include <linux/fs_stack.h> -#include <linux/aio.h> #include "ecryptfs_kernel.h" /** @@ -52,12 +51,6 @@ 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/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 <linux/mpage.h> #include <linux/fiemap.h> #include <linux/namei.h> -#include <linux/aio.h> +#include <linux/uio.h> #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 <linux/writeback.h> #include <linux/mpage.h> #include <linux/namei.h> -#include <linux/aio.h> +#include <linux/uio.h> #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 <linux/jbd2.h> #include <linux/mount.h> #include <linux/path.h> -#include <linux/aio.h> #include <linux/quotaops.h> #include <linux/pagevec.h> +#include <linux/uio.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 45fe924f82bc..740c7871c117 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -20,9 +20,9 @@ * (sct@redhat.com), 1993, 1998 */ -#include <linux/aio.h> #include "ext4_jbd2.h" #include "truncate.h" +#include <linux/uio.h> #include <trace/events/ext4.h> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5cb9a212b86f..a3f451370bef 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -37,7 +37,6 @@ #include <linux/printk.h> #include <linux/slab.h> #include <linux/ratelimit.h> -#include <linux/aio.h> #include <linux/bitops.h> #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 <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 985ed023a750..497f8515d205 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -12,12 +12,12 @@ #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> #include <linux/bio.h> #include <linux/prefetch.h> +#include <linux/uio.h> #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 <linux/mpage.h> #include <linux/buffer_head.h> #include <linux/mount.h> -#include <linux/aio.h> #include <linux/vfs.h> #include <linux/parser.h> #include <linux/uio.h> 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 <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> @@ -48,6 +47,7 @@ #include <linux/slab.h> #include <linux/stat.h> #include <linux/module.h> +#include <linux/uio.h> #include "fuse_i.h" diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 39706c57ad3c..95a2797eef66 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -19,7 +19,6 @@ #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 c01ec3bdcfd8..ff102cbf16ea 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -15,8 +15,8 @@ #include <linux/module.h> #include <linux/compat.h> #include <linux/swap.h> -#include <linux/aio.h> #include <linux/falloc.h> +#include <linux/uio.h> static const struct file_operations fuse_direct_io_file_operations; @@ -528,6 +528,17 @@ static void fuse_release_user_pages(struct fuse_req *req, int write) } } +static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io) +{ + if (io->err) + return io->err; + + if (io->bytes >= 0 && io->write) + return -EIO; + + return io->bytes < 0 ? io->size : io->bytes; +} + /** * In case of short read, the caller sets 'pos' to the position of * actual end of fuse request in IO request. Otherwise, if bytes_requested @@ -546,6 +557,7 @@ static void fuse_release_user_pages(struct fuse_req *req, int write) */ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) { + bool is_sync = is_sync_kiocb(io->iocb); int left; spin_lock(&io->lock); @@ -555,30 +567,24 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) io->bytes = pos; left = --io->reqs; + if (!left && is_sync) + complete(io->done); spin_unlock(&io->lock); - if (!left) { - long res; + if (!left && !is_sync) { + ssize_t res = fuse_get_res_by_io(io); - if (io->err) - res = io->err; - else if (io->bytes >= 0 && io->write) - res = -EIO; - else { - res = io->bytes < 0 ? io->size : io->bytes; + if (res >= 0) { + struct inode *inode = file_inode(io->iocb->ki_filp); + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); - if (!is_sync_kiocb(io->iocb)) { - struct inode *inode = file_inode(io->iocb->ki_filp); - struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); - - spin_lock(&fc->lock); - fi->attr_version = ++fc->attr_version; - spin_unlock(&fc->lock); - } + spin_lock(&fc->lock); + fi->attr_version = ++fc->attr_version; + spin_unlock(&fc->lock); } - aio_complete(io->iocb, res, 0); + io->iocb->ki_complete(io->iocb, res, 0); kfree(io); } } @@ -2801,6 +2807,7 @@ static ssize_t fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t offset) { + DECLARE_COMPLETION_ONSTACK(wait); ssize_t ret = 0; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; @@ -2852,6 +2859,9 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, if (!is_sync_kiocb(iocb) && (offset + count > i_size) && rw == WRITE) io->async = false; + if (io->async && is_sync_kiocb(iocb)) + io->done = &wait; + if (rw == WRITE) ret = __fuse_direct_write(io, iter, &pos); else @@ -2864,11 +2874,12 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; - ret = wait_on_sync_kiocb(iocb); - } else { - kfree(io); + wait_for_completion(&wait); + ret = fuse_get_res_by_io(io); } + kfree(io); + if (rw == WRITE) { if (ret > 0) fuse_write_update_size(inode, pos); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 1cdfb07c1376..7354dc142a50 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -263,6 +263,7 @@ struct fuse_io_priv { int err; struct kiocb *iocb; struct file *file; + struct completion *done; }; /** diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 7b3143064af1..1be3b061c05c 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -110,11 +110,7 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS); if (error) goto out; - - if (acl) - set_cached_acl(inode, type, acl); - else - forget_cached_acl(inode, type); + set_cached_acl(inode, type, acl); out: kfree(data); return error; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 4ad4f94edebe..a6e6990aea39 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -20,7 +20,7 @@ #include <linux/swap.h> #include <linux/gfs2_ondisk.h> #include <linux/backing-dev.h> -#include <linux/aio.h> +#include <linux/uio.h> #include <trace/events/writeback.h> #include "gfs2.h" @@ -671,12 +671,12 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, if (alloc_required) { struct gfs2_alloc_parms ap = { .aflags = 0, }; - error = gfs2_quota_lock_check(ip); + requested = data_blocks + ind_blocks; + ap.target = requested; + error = gfs2_quota_lock_check(ip, &ap); if (error) goto out_unlock; - requested = data_blocks + ind_blocks; - ap.target = requested; error = gfs2_inplace_reserve(ip, &ap); if (error) goto out_qunlock; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index f0b945ab853e..61296ecbd0e2 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1224,7 +1224,7 @@ static int do_grow(struct inode *inode, u64 size) if (gfs2_is_stuffed(ip) && (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) { - error = gfs2_quota_lock_check(ip); + error = gfs2_quota_lock_check(ip, &ap); if (error) return error; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 3e32bb8e2d7e..8ec43ab5babf 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -25,7 +25,6 @@ #include <asm/uaccess.h> #include <linux/dlm.h> #include <linux/dlm_plock.h> -#include <linux/aio.h> #include <linux/delay.h> #include "gfs2.h" @@ -429,11 +428,11 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (ret) goto out_unlock; - ret = gfs2_quota_lock_check(ip); - if (ret) - goto out_unlock; gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks); ap.target = data_blocks + ind_blocks; + ret = gfs2_quota_lock_check(ip, &ap); + if (ret) + goto out_unlock; ret = gfs2_inplace_reserve(ip, &ap); if (ret) goto out_quota_unlock; @@ -765,22 +764,30 @@ out: brelse(dibh); return error; } - -static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len, - unsigned int *data_blocks, unsigned int *ind_blocks) +/** + * calc_max_reserv() - Reverse of write_calc_reserv. Given a number of + * blocks, determine how many bytes can be written. + * @ip: The inode in question. + * @len: Max cap of bytes. What we return in *len must be <= this. + * @data_blocks: Compute and return the number of data blocks needed + * @ind_blocks: Compute and return the number of indirect blocks needed + * @max_blocks: The total blocks available to work with. + * + * Returns: void, but @len, @data_blocks and @ind_blocks are filled in. + */ +static void calc_max_reserv(struct gfs2_inode *ip, loff_t *len, + unsigned int *data_blocks, unsigned int *ind_blocks, + unsigned int max_blocks) { + loff_t max = *len; const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int max_blocks = ip->i_rgd->rd_free_clone; unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1); for (tmp = max_data; tmp > sdp->sd_diptrs;) { tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs); max_data -= tmp; } - /* This calculation isn't the exact reverse of gfs2_write_calc_reserve, - so it might end up with fewer data blocks */ - if (max_data <= *data_blocks) - return; + *data_blocks = max_data; *ind_blocks = max_blocks - max_data; *len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift; @@ -797,7 +804,7 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_alloc_parms ap = { .aflags = 0, }; unsigned int data_blocks = 0, ind_blocks = 0, rblocks; - loff_t bytes, max_bytes; + loff_t bytes, max_bytes, max_blks = UINT_MAX; int error; const loff_t pos = offset; const loff_t count = len; @@ -819,6 +826,9 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t gfs2_size_hint(file, offset, len); + gfs2_write_calc_reserv(ip, PAGE_SIZE, &data_blocks, &ind_blocks); + ap.min_target = data_blocks + ind_blocks; + while (len > 0) { if (len < bytes) bytes = len; @@ -827,27 +837,41 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t offset += bytes; continue; } - error = gfs2_quota_lock_check(ip); + + /* We need to determine how many bytes we can actually + * fallocate without exceeding quota or going over the + * end of the fs. We start off optimistically by assuming + * we can write max_bytes */ + max_bytes = (len > max_chunk_size) ? max_chunk_size : len; + + /* Since max_bytes is most likely a theoretical max, we + * calculate a more realistic 'bytes' to serve as a good + * starting point for the number of bytes we may be able + * to write */ + gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks); + ap.target = data_blocks + ind_blocks; + + error = gfs2_quota_lock_check(ip, &ap); if (error) return error; -retry: - gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks); + /* ap.allowed tells us how many blocks quota will allow + * us to write. Check if this reduces max_blks */ + if (ap.allowed && ap.allowed < max_blks) + max_blks = ap.allowed; - ap.target = data_blocks + ind_blocks; error = gfs2_inplace_reserve(ip, &ap); - if (error) { - if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) { - bytes >>= 1; - bytes &= bsize_mask; - if (bytes == 0) - bytes = sdp->sd_sb.sb_bsize; - goto retry; - } + if (error) goto out_qunlock; - } - max_bytes = bytes; - calc_max_reserv(ip, (len > max_chunk_size)? max_chunk_size: len, - &max_bytes, &data_blocks, &ind_blocks); + + /* check if the selected rgrp limits our max_blks further */ + if (ap.allowed && ap.allowed < max_blks) + max_blks = ap.allowed; + + /* Almost done. Calculate bytes that can be written using + * max_blks. We also recompute max_bytes, data_blocks and + * ind_blocks */ + calc_max_reserv(ip, &max_bytes, &data_blocks, + &ind_blocks, max_blks); rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA + RES_RG_HDR + gfs2_rg_blocks(ip, data_blocks + ind_blocks); @@ -931,6 +955,22 @@ out_uninit: return ret; } +static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe, + struct file *out, loff_t *ppos, + size_t len, unsigned int flags) +{ + int error; + struct gfs2_inode *ip = GFS2_I(out->f_mapping->host); + + error = gfs2_rs_alloc(ip); + if (error) + return (ssize_t)error; + + gfs2_size_hint(out, *ppos, len); + + return iter_file_splice_write(pipe, out, ppos, len, flags); +} + #ifdef CONFIG_GFS2_FS_LOCKING_DLM /** @@ -1077,7 +1117,7 @@ const struct file_operations gfs2_file_fops = { .lock = gfs2_lock, .flock = gfs2_flock, .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, + .splice_write = gfs2_file_splice_write, .setlease = simple_nosetlease, .fallocate = gfs2_fallocate, }; @@ -1107,7 +1147,7 @@ const struct file_operations gfs2_file_fops_nolock = { .release = gfs2_release, .fsync = gfs2_fsync, .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, + .splice_write = gfs2_file_splice_write, .setlease = generic_setlease, .fallocate = gfs2_fallocate, }; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index f42dffba056a..0fa8062f85a7 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2047,34 +2047,41 @@ static const struct file_operations gfs2_sbstats_fops = { int gfs2_create_debugfs_file(struct gfs2_sbd *sdp) { - sdp->debugfs_dir = debugfs_create_dir(sdp->sd_table_name, gfs2_root); - if (!sdp->debugfs_dir) - return -ENOMEM; - sdp->debugfs_dentry_glocks = debugfs_create_file("glocks", - S_IFREG | S_IRUGO, - sdp->debugfs_dir, sdp, - &gfs2_glocks_fops); - if (!sdp->debugfs_dentry_glocks) + struct dentry *dent; + + dent = debugfs_create_dir(sdp->sd_table_name, gfs2_root); + if (IS_ERR_OR_NULL(dent)) + goto fail; + sdp->debugfs_dir = dent; + + dent = debugfs_create_file("glocks", + S_IFREG | S_IRUGO, + sdp->debugfs_dir, sdp, + &gfs2_glocks_fops); + if (IS_ERR_OR_NULL(dent)) goto fail; + sdp->debugfs_dentry_glocks = dent; - sdp->debugfs_dentry_glstats = debugfs_create_file("glstats", - S_IFREG | S_IRUGO, - sdp->debugfs_dir, sdp, - &gfs2_glstats_fops); - if (!sdp->debugfs_dentry_glstats) + dent = debugfs_create_file("glstats", + S_IFREG | S_IRUGO, + sdp->debugfs_dir, sdp, + &gfs2_glstats_fops); + if (IS_ERR_OR_NULL(dent)) goto fail; + sdp->debugfs_dentry_glstats = dent; - sdp->debugfs_dentry_sbstats = debugfs_create_file("sbstats", - S_IFREG | S_IRUGO, - sdp->debugfs_dir, sdp, - &gfs2_sbstats_fops); - if (!sdp->debugfs_dentry_sbstats) + dent = debugfs_create_file("sbstats", + S_IFREG | S_IRUGO, + sdp->debugfs_dir, sdp, + &gfs2_sbstats_fops); + if (IS_ERR_OR_NULL(dent)) goto fail; + sdp->debugfs_dentry_sbstats = dent; return 0; fail: gfs2_delete_debugfs_file(sdp); - return -ENOMEM; + return dent ? PTR_ERR(dent) : -ENOMEM; } void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp) @@ -2100,6 +2107,8 @@ void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp) int gfs2_register_debugfs(void) { gfs2_root = debugfs_create_dir("gfs2", NULL); + if (IS_ERR(gfs2_root)) + return PTR_ERR(gfs2_root); return gfs2_root ? 0 : -ENOMEM; } diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 7a2dbbc0d634..58b75abf6ab2 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -301,8 +301,10 @@ struct gfs2_blkreserv { * to the allocation code. */ struct gfs2_alloc_parms { - u32 target; + u64 target; + u32 min_target; u32 aflags; + u64 allowed; }; enum { diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 73c72253faac..08bc84d7e768 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -382,7 +382,7 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags, unsigned *dblocks) struct gfs2_alloc_parms ap = { .target = *dblocks, .aflags = flags, }; int error; - error = gfs2_quota_lock_check(ip); + error = gfs2_quota_lock_check(ip, &ap); if (error) goto out; @@ -525,7 +525,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, int error; if (da->nr_blocks) { - error = gfs2_quota_lock_check(dip); + error = gfs2_quota_lock_check(dip, &ap); if (error) goto fail_quota_locks; @@ -953,7 +953,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (da.nr_blocks) { struct gfs2_alloc_parms ap = { .target = da.nr_blocks, }; - error = gfs2_quota_lock_check(dip); + error = gfs2_quota_lock_check(dip, &ap); if (error) goto out_gunlock; @@ -1470,7 +1470,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (da.nr_blocks) { struct gfs2_alloc_parms ap = { .target = da.nr_blocks, }; - error = gfs2_quota_lock_check(ndip); + error = gfs2_quota_lock_check(ndip, &ap); if (error) goto out_gunlock; @@ -1669,6 +1669,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) kuid_t ouid, nuid; kgid_t ogid, ngid; int error; + struct gfs2_alloc_parms ap; ouid = inode->i_uid; ogid = inode->i_gid; @@ -1696,9 +1697,11 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) if (error) goto out; + ap.target = gfs2_get_inode_blocks(&ip->i_inode); + if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) || !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) { - error = gfs2_quota_check(ip, nuid, ngid); + error = gfs2_quota_check(ip, nuid, ngid, &ap); if (error) goto out_gunlock_q; } @@ -1713,9 +1716,8 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) || !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) { - u64 blocks = gfs2_get_inode_blocks(&ip->i_inode); - gfs2_quota_change(ip, -blocks, ouid, ogid); - gfs2_quota_change(ip, blocks, nuid, ngid); + gfs2_quota_change(ip, -ap.target, ouid, ogid); + gfs2_quota_change(ip, ap.target, nuid, ngid); } out_end_trans: diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 3aa17d4d1cfc..5c27e48aa76f 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -923,6 +923,9 @@ restart: if (error) return error; + if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags)) + force_refresh = FORCE; + qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) { @@ -974,11 +977,8 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) sizeof(struct gfs2_quota_data *), sort_qd, NULL); for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - int force = NO_FORCE; qd = ip->i_res->rs_qa_qd[x]; - if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags)) - force = FORCE; - error = do_glock(qd, force, &ip->i_res->rs_qa_qd_ghs[x]); + error = do_glock(qd, NO_FORCE, &ip->i_res->rs_qa_qd_ghs[x]); if (error) break; } @@ -1094,14 +1094,33 @@ static int print_message(struct gfs2_quota_data *qd, char *type) return 0; } -int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) +/** + * gfs2_quota_check - check if allocating new blocks will exceed quota + * @ip: The inode for which this check is being performed + * @uid: The uid to check against + * @gid: The gid to check against + * @ap: The allocation parameters. ap->target contains the requested + * blocks. ap->min_target, if set, contains the minimum blks + * requested. + * + * Returns: 0 on success. + * min_req = ap->min_target ? ap->min_target : ap->target; + * quota must allow atleast min_req blks for success and + * ap->allowed is set to the number of blocks allowed + * + * -EDQUOT otherwise, quota violation. ap->allowed is set to number + * of blocks available. + */ +int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, + struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; - s64 value; + s64 value, warn, limit; unsigned int x; int error = 0; + ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ if (!test_bit(GIF_QD_LOCKED, &ip->i_flags)) return 0; @@ -1115,30 +1134,37 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) qid_eq(qd->qd_id, make_kqid_gid(gid)))) continue; + warn = (s64)be64_to_cpu(qd->qd_qb.qb_warn); + limit = (s64)be64_to_cpu(qd->qd_qb.qb_limit); value = (s64)be64_to_cpu(qd->qd_qb.qb_value); spin_lock(&qd_lock); value += qd->qd_change; spin_unlock(&qd_lock); - if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) { - print_message(qd, "exceeded"); - quota_send_warning(qd->qd_id, - sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN); - - error = -EDQUOT; - break; - } else if (be64_to_cpu(qd->qd_qb.qb_warn) && - (s64)be64_to_cpu(qd->qd_qb.qb_warn) < value && + if (limit > 0 && (limit - value) < ap->allowed) + ap->allowed = limit - value; + /* If we can't meet the target */ + if (limit && limit < (value + (s64)ap->target)) { + /* If no min_target specified or we don't meet + * min_target, return -EDQUOT */ + if (!ap->min_target || ap->min_target > ap->allowed) { + print_message(qd, "exceeded"); + quota_send_warning(qd->qd_id, + sdp->sd_vfs->s_dev, + QUOTA_NL_BHARDWARN); + error = -EDQUOT; + break; + } + } else if (warn && warn < value && time_after_eq(jiffies, qd->qd_last_warn + - gfs2_tune_get(sdp, - gt_quota_warn_period) * HZ)) { + gfs2_tune_get(sdp, gt_quota_warn_period) + * HZ)) { quota_send_warning(qd->qd_id, sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN); error = print_message(qd, "warning"); qd->qd_last_warn = jiffies; } } - return error; } diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 55d506eb3c4a..ad04b3acae2b 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -24,7 +24,8 @@ extern void gfs2_quota_unhold(struct gfs2_inode *ip); extern int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid); extern void gfs2_quota_unlock(struct gfs2_inode *ip); -extern int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid); +extern int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, + struct gfs2_alloc_parms *ap); extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change, kuid_t uid, kgid_t gid); @@ -37,7 +38,8 @@ extern int gfs2_quotad(void *data); extern void gfs2_wake_up_statfs(struct gfs2_sbd *sdp); -static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) +static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, + struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); int ret; @@ -48,7 +50,7 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) return ret; if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; - ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid); + ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid, ap); if (ret) gfs2_quota_unlock(ip); return ret; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 9150207f365c..6af2396a317c 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1946,10 +1946,18 @@ static inline int fast_to_acquire(struct gfs2_rgrpd *rgd) * @ip: the inode to reserve space for * @ap: the allocation parameters * - * Returns: errno + * We try our best to find an rgrp that has at least ap->target blocks + * available. After a couple of passes (loops == 2), the prospects of finding + * such an rgrp diminish. At this stage, we return the first rgrp that has + * atleast ap->min_target blocks available. Either way, we set ap->allowed to + * the number of blocks available in the chosen rgrp. + * + * Returns: 0 on success, + * -ENOMEM if a suitable rgrp can't be found + * errno otherwise */ -int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *ap) +int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *begin = NULL; @@ -2012,7 +2020,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a /* Skip unuseable resource groups */ if ((rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) || - (ap->target > rs->rs_rbm.rgd->rd_extfail_pt)) + (loops == 0 && ap->target > rs->rs_rbm.rgd->rd_extfail_pt)) goto skip_rgrp; if (sdp->sd_args.ar_rgrplvb) @@ -2027,11 +2035,13 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a goto check_rgrp; /* If rgrp has enough free space, use it */ - if (rs->rs_rbm.rgd->rd_free_clone >= ap->target) { + if (rs->rs_rbm.rgd->rd_free_clone >= ap->target || + (loops == 2 && ap->min_target && + rs->rs_rbm.rgd->rd_free_clone >= ap->min_target)) { ip->i_rgd = rs->rs_rbm.rgd; + ap->allowed = ip->i_rgd->rd_free_clone; return 0; } - check_rgrp: /* Check for unlinked inodes which can be reclaimed */ if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK) diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index b104f4af3afd..68972ecfbb01 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -41,7 +41,8 @@ extern void gfs2_rgrp_go_unlock(struct gfs2_holder *gh); extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); #define GFS2_AF_ORLOV 1 -extern int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *ap); +extern int gfs2_inplace_reserve(struct gfs2_inode *ip, + struct gfs2_alloc_parms *ap); extern void gfs2_inplace_release(struct gfs2_inode *ip); extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 0b81f783f787..fd260ce8869a 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -732,7 +732,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er, if (error) return error; - error = gfs2_quota_lock_check(ip); + error = gfs2_quota_lock_check(ip, &ap); if (error) return error; 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 <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> -#include <linux/aio.h> +#include <linux/uio.h> #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 <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index d72817ac51f6..762c7a3cf43d 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -195,7 +195,7 @@ static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_dat /* unchecked xdatum is chained with c->xattr_unchecked */ list_del_init(&xd->xindex); - dbg_xattr("success on verfying xdatum (xid=%u, version=%u)\n", + dbg_xattr("success on verifying xdatum (xid=%u, version=%u)\n", xd->xid, xd->version); return 0; 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 <linux/buffer_head.h> #include <linux/pagemap.h> #include <linux/quotaops.h> +#include <linux/uio.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/jfs/super.c b/fs/jfs/super.c index 5d30c56ae075..4cd9798f4948 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -102,7 +102,7 @@ void jfs_error(struct super_block *sb, const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - pr_err("ERROR: (device %s): %pf: %pV\n", + pr_err("ERROR: (device %s): %ps: %pV\n", sb->s_id, __builtin_return_address(0), &vaf); va_end(args); diff --git a/fs/namei.c b/fs/namei.c index c83145af4bfc..76fb76a0818b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -119,15 +119,14 @@ * 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) { - struct filename *result, *err; - int len; - long max; + struct filename *result; char *kname; + int len; result = audit_reusename(filename); if (result) @@ -136,22 +135,18 @@ getname_flags(const char __user *filename, int flags, int *empty) result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); - result->refcnt = 1; /* * 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; - max = EMBEDDED_NAME_MAX; -recopy: - len = strncpy_from_user(kname, filename, max); + len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); if (unlikely(len < 0)) { - err = ERR_PTR(len); - goto error; + __putname(result); + return ERR_PTR(len); } /* @@ -160,43 +155,49 @@ recopy: * names_cache allocation for the pathname, and re-do the copy from * userland. */ - if (len == EMBEDDED_NAME_MAX && max == EMBEDDED_NAME_MAX) { + if (unlikely(len == EMBEDDED_NAME_MAX)) { + const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; - result = kzalloc(sizeof(*result), GFP_KERNEL); - if (!result) { - err = ERR_PTR(-ENOMEM); - result = (struct filename *)kname; - goto error; + /* + * 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; - result->refcnt = 1; - max = PATH_MAX; - goto recopy; + len = strncpy_from_user(kname, filename, PATH_MAX); + if (unlikely(len < 0)) { + __putname(kname); + kfree(result); + return ERR_PTR(len); + } + if (unlikely(len == PATH_MAX)) { + __putname(kname); + kfree(result); + return ERR_PTR(-ENAMETOOLONG); + } } + result->refcnt = 1; /* The empty path is special. */ if (unlikely(!len)) { if (empty) *empty = 1; - err = ERR_PTR(-ENOENT); - if (!(flags & LOOKUP_EMPTY)) - goto error; + if (!(flags & LOOKUP_EMPTY)) { + putname(result); + return ERR_PTR(-ENOENT); + } } - err = ERR_PTR(-ENAMETOOLONG); - if (unlikely(len >= PATH_MAX)) - goto error; - result->uptr = filename; result->aname = NULL; audit_getname(result); return result; - -error: - putname(result); - return err; } struct filename * @@ -216,8 +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; @@ -227,7 +227,6 @@ getname_kernel(const char * filename) return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; - tmp->separate = true; result = tmp; } else { __putname(result); @@ -249,7 +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 @@ -1851,10 +1850,11 @@ static int link_path_walk(const char *name, struct nameidata *nd) return err; } -static int path_init(int dfd, const char *name, unsigned int flags, +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; @@ -1863,7 +1863,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; - if (*name) { + if (*s) { if (!d_can_lookup(root)) return -ENOTDIR; retval = inode_permission(inode, MAY_EXEC); @@ -1885,7 +1885,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, nd->root.mnt = NULL; nd->m_seq = read_seqbegin(&mount_lock); - if (*name=='/') { + if (*s == '/') { if (flags & LOOKUP_RCU) { rcu_read_lock(); nd->seq = set_root_rcu(nd); @@ -1919,7 +1919,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, dentry = f.file->f_path.dentry; - if (*name) { + if (*s) { if (!d_can_lookup(dentry)) { fdput(f); return -ENOTDIR; @@ -1949,7 +1949,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, return -ECHILD; done: current->total_link_count = 0; - return link_path_walk(name, nd); + return link_path_walk(s, nd); } static void path_cleanup(struct nameidata *nd) @@ -1972,7 +1972,7 @@ static inline int lookup_last(struct nameidata *nd, struct path *path) } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ -static int path_lookupat(int dfd, const char *name, +static int path_lookupat(int dfd, const struct filename *name, unsigned int flags, struct nameidata *nd) { struct path path; @@ -2027,31 +2027,17 @@ static int path_lookupat(int dfd, const char *name, static int filename_lookup(int dfd, struct filename *name, unsigned int flags, struct nameidata *nd) { - int retval = path_lookupat(dfd, name->name, flags | LOOKUP_RCU, nd); + int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd); if (unlikely(retval == -ECHILD)) - retval = path_lookupat(dfd, name->name, flags, nd); + retval = path_lookupat(dfd, name, flags, nd); if (unlikely(retval == -ESTALE)) - retval = path_lookupat(dfd, name->name, - flags | LOOKUP_REVAL, nd); + retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd); if (likely(!retval)) audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT); return retval; } -static int do_path_lookup(int dfd, const char *name, - unsigned int flags, struct nameidata *nd) -{ - struct filename *filename = getname_kernel(name); - int retval = PTR_ERR(filename); - - if (!IS_ERR(filename)) { - retval = filename_lookup(dfd, filename, flags, nd); - putname(filename); - } - return retval; -} - /* does lookup, returns the object with parent locked */ struct dentry *kern_path_locked(const char *name, struct path *path) { @@ -2089,9 +2075,15 @@ out: int kern_path(const char *name, unsigned int flags, struct path *path) { struct nameidata nd; - int res = do_path_lookup(AT_FDCWD, name, flags, &nd); - if (!res) - *path = nd.path; + struct filename *filename = getname_kernel(name); + int res = PTR_ERR(filename); + + if (!IS_ERR(filename)) { + res = filename_lookup(AT_FDCWD, filename, flags, &nd); + putname(filename); + if (!res) + *path = nd.path; + } return res; } EXPORT_SYMBOL(kern_path); @@ -2108,15 +2100,22 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { - struct nameidata nd; - int err; - nd.root.dentry = dentry; - nd.root.mnt = mnt; + struct filename *filename = getname_kernel(name); + int err = PTR_ERR(filename); + BUG_ON(flags & LOOKUP_PARENT); - /* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */ - err = do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, &nd); - if (!err) - *path = nd.path; + + /* the first argument of filename_lookup() is ignored with LOOKUP_ROOT */ + if (!IS_ERR(filename)) { + struct nameidata nd; + nd.root.dentry = dentry; + nd.root.mnt = mnt; + err = filename_lookup(AT_FDCWD, filename, + flags | LOOKUP_ROOT, &nd); + if (!err) + *path = nd.path; + putname(filename); + } return err; } EXPORT_SYMBOL(vfs_path_lookup); @@ -2138,9 +2137,7 @@ static struct dentry *lookup_hash(struct nameidata *nd) * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. Also note that by using this function the - * nameidata argument is passed to the filesystem methods and a filesystem - * using this helper needs to be prepared for that. + * not be called by generic code. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { @@ -2341,7 +2338,8 @@ out: * Returns 0 and "path" will be valid on success; Returns error otherwise. */ static int -path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags) +path_mountpoint(int dfd, const struct filename *name, struct path *path, + unsigned int flags) { struct nameidata nd; int err; @@ -2370,20 +2368,20 @@ out: } static int -filename_mountpoint(int dfd, struct filename *s, struct path *path, +filename_mountpoint(int dfd, struct filename *name, struct path *path, unsigned int flags) { int error; - if (IS_ERR(s)) - return PTR_ERR(s); - error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU); + if (IS_ERR(name)) + return PTR_ERR(name); + error = path_mountpoint(dfd, name, path, flags | LOOKUP_RCU); if (unlikely(error == -ECHILD)) - error = path_mountpoint(dfd, s->name, path, flags); + error = path_mountpoint(dfd, name, path, flags); if (unlikely(error == -ESTALE)) - error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_REVAL); + error = path_mountpoint(dfd, name, path, flags | LOOKUP_REVAL); if (likely(!error)) - audit_inode(s, path->dentry, 0); - putname(s); + audit_inode(name, path->dentry, 0); + putname(name); return error; } @@ -3156,7 +3154,7 @@ static int do_tmpfile(int dfd, struct filename *pathname, static const struct qstr name = QSTR_INIT("/", 1); struct dentry *dentry, *child; struct inode *dir; - int error = path_lookupat(dfd, pathname->name, + int error = path_lookupat(dfd, pathname, flags | LOOKUP_DIRECTORY, nd); if (unlikely(error)) return error; @@ -3229,7 +3227,7 @@ static struct file *path_openat(int dfd, struct filename *pathname, goto out; } - error = path_init(dfd, pathname->name, flags, nd); + error = path_init(dfd, pathname, flags, nd); if (unlikely(error)) goto out; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e907c8cf732e..c3929fb2ab26 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -265,7 +265,7 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t return -EINVAL; #else - VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE); + VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); if (rw == READ) return nfs_file_direct_read(iocb, iter, pos); @@ -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/fs/nfs/file.c b/fs/nfs/file.c index e679d24c39d3..37b15582e0de 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -26,7 +26,6 @@ #include <linux/nfs_mount.h> #include <linux/mm.h> #include <linux/pagemap.h> -#include <linux/aio.h> #include <linux/gfp.h> #include <linux/swap.h> 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 <linux/mpage.h> #include <linux/pagemap.h> #include <linux/writeback.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "nilfs.h" #include "btnode.h" #include "segment.h" diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile index 36ae529511c4..2ff263e6d363 100644 --- a/fs/ntfs/Makefile +++ b/fs/ntfs/Makefile @@ -8,7 +8,7 @@ ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \ ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o -ccflags-y := -DNTFS_VERSION=\"2.1.31\" +ccflags-y := -DNTFS_VERSION=\"2.1.32\" ccflags-$(CONFIG_NTFS_DEBUG) += -DDEBUG ccflags-$(CONFIG_NTFS_RW) += -DNTFS_RW diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 1da9b2d184dc..c1da78dad1af 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1,7 +1,7 @@ /* * file.c - NTFS kernel file operations. Part of the Linux-NTFS project. * - * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc. + * Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc. * * This program/include file is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as published @@ -28,7 +28,6 @@ #include <linux/swap.h> #include <linux/uio.h> #include <linux/writeback.h> -#include <linux/aio.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -329,62 +328,168 @@ err_out: return err; } -/** - * ntfs_fault_in_pages_readable - - * - * Fault a number of userspace pages into pagetables. - * - * Unlike include/linux/pagemap.h::fault_in_pages_readable(), this one copes - * with more than two userspace pages as well as handling the single page case - * elegantly. - * - * If you find this difficult to understand, then think of the while loop being - * the following code, except that we do without the integer variable ret: - * - * do { - * ret = __get_user(c, uaddr); - * uaddr += PAGE_SIZE; - * } while (!ret && uaddr < end); - * - * Note, the final __get_user() may well run out-of-bounds of the user buffer, - * but _not_ out-of-bounds of the page the user buffer belongs to, and since - * this is only a read and not a write, and since it is still in the same page, - * it should not matter and this makes the code much simpler. - */ -static inline void ntfs_fault_in_pages_readable(const char __user *uaddr, - int bytes) +static ssize_t ntfs_prepare_file_for_write(struct file *file, loff_t *ppos, + size_t *count) { - const char __user *end; - volatile char c; - - /* Set @end to the first byte outside the last page we care about. */ - end = (const char __user*)PAGE_ALIGN((unsigned long)uaddr + bytes); - - while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end)) - ; -} - -/** - * ntfs_fault_in_pages_readable_iovec - - * - * Same as ntfs_fault_in_pages_readable() but operates on an array of iovecs. - */ -static inline void ntfs_fault_in_pages_readable_iovec(const struct iovec *iov, - size_t iov_ofs, int bytes) -{ - do { - const char __user *buf; - unsigned len; + loff_t pos; + s64 end, ll; + ssize_t err; + unsigned long flags; + struct inode *vi = file_inode(file); + ntfs_inode *base_ni, *ni = NTFS_I(vi); + ntfs_volume *vol = ni->vol; - buf = iov->iov_base + iov_ofs; - len = iov->iov_len - iov_ofs; - if (len > bytes) - len = bytes; - ntfs_fault_in_pages_readable(buf, len); - bytes -= len; - iov++; - iov_ofs = 0; - } while (bytes); + ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos " + "0x%llx, count 0x%lx.", vi->i_ino, + (unsigned)le32_to_cpu(ni->type), + (unsigned long long)*ppos, (unsigned long)*count); + /* We can write back this queue in page reclaim. */ + current->backing_dev_info = inode_to_bdi(vi); + err = generic_write_checks(file, ppos, count, S_ISBLK(vi->i_mode)); + if (unlikely(err)) + goto out; + /* + * All checks have passed. Before we start doing any writing we want + * to abort any totally illegal writes. + */ + BUG_ON(NInoMstProtected(ni)); + BUG_ON(ni->type != AT_DATA); + /* If file is encrypted, deny access, just like NT4. */ + if (NInoEncrypted(ni)) { + /* Only $DATA attributes can be encrypted. */ + /* + * Reminder for later: Encrypted files are _always_ + * non-resident so that the content can always be encrypted. + */ + ntfs_debug("Denying write access to encrypted file."); + err = -EACCES; + goto out; + } + if (NInoCompressed(ni)) { + /* Only unnamed $DATA attribute can be compressed. */ + BUG_ON(ni->name_len); + /* + * Reminder for later: If resident, the data is not actually + * compressed. Only on the switch to non-resident does + * compression kick in. This is in contrast to encrypted files + * (see above). + */ + ntfs_error(vi->i_sb, "Writing to compressed files is not " + "implemented yet. Sorry."); + err = -EOPNOTSUPP; + goto out; + } + if (*count == 0) + goto out; + base_ni = ni; + if (NInoAttr(ni)) + base_ni = ni->ext.base_ntfs_ino; + err = file_remove_suid(file); + if (unlikely(err)) + goto out; + /* + * Our ->update_time method always succeeds thus file_update_time() + * cannot fail either so there is no need to check the return code. + */ + file_update_time(file); + pos = *ppos; + /* The first byte after the last cluster being written to. */ + end = (pos + *count + vol->cluster_size_mask) & + ~(u64)vol->cluster_size_mask; + /* + * If the write goes beyond the allocated size, extend the allocation + * to cover the whole of the write, rounded up to the nearest cluster. + */ + read_lock_irqsave(&ni->size_lock, flags); + ll = ni->allocated_size; + read_unlock_irqrestore(&ni->size_lock, flags); + if (end > ll) { + /* + * Extend the allocation without changing the data size. + * + * Note we ensure the allocation is big enough to at least + * write some data but we do not require the allocation to be + * complete, i.e. it may be partial. + */ + ll = ntfs_attr_extend_allocation(ni, end, -1, pos); + if (likely(ll >= 0)) { + BUG_ON(pos >= ll); + /* If the extension was partial truncate the write. */ + if (end > ll) { + ntfs_debug("Truncating write to inode 0x%lx, " + "attribute type 0x%x, because " + "the allocation was only " + "partially extended.", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type)); + *count = ll - pos; + } + } else { + err = ll; + read_lock_irqsave(&ni->size_lock, flags); + ll = ni->allocated_size; + read_unlock_irqrestore(&ni->size_lock, flags); + /* Perform a partial write if possible or fail. */ + if (pos < ll) { + ntfs_debug("Truncating write to inode 0x%lx " + "attribute type 0x%x, because " + "extending the allocation " + "failed (error %d).", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type), + (int)-err); + *count = ll - pos; + } else { + if (err != -ENOSPC) + ntfs_error(vi->i_sb, "Cannot perform " + "write to inode " + "0x%lx, attribute " + "type 0x%x, because " + "extending the " + "allocation failed " + "(error %ld).", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type), + (long)-err); + else + ntfs_debug("Cannot perform write to " + "inode 0x%lx, " + "attribute type 0x%x, " + "because there is not " + "space left.", + vi->i_ino, (unsigned) + le32_to_cpu(ni->type)); + goto out; + } + } + } + /* + * If the write starts beyond the initialized size, extend it up to the + * beginning of the write and initialize all non-sparse space between + * the old initialized size and the new one. This automatically also + * increments the vfs inode->i_size to keep it above or equal to the + * initialized_size. + */ + read_lock_irqsave(&ni->size_lock, flags); + ll = ni->initialized_size; + read_unlock_irqrestore(&ni->size_lock, flags); + if (pos > ll) { + /* + * Wait for ongoing direct i/o to complete before proceeding. + * New direct i/o cannot start as we hold i_mutex. + */ + inode_dio_wait(vi); + err = ntfs_attr_extend_initialized(ni, pos); + if (unlikely(err < 0)) + ntfs_error(vi->i_sb, "Cannot perform write to inode " + "0x%lx, attribute type 0x%x, because " + "extending the initialized size " + "failed (error %d).", vi->i_ino, + (unsigned)le32_to_cpu(ni->type), + (int)-err); + } +out: + return err; } /** @@ -421,8 +526,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, goto err_out; } } - err = add_to_page_cache_lru(*cached_page, mapping, index, - GFP_KERNEL); + err = add_to_page_cache_lru(*cached_page, mapping, + index, GFP_KERNEL); if (unlikely(err)) { if (err == -EEXIST) continue; @@ -1268,180 +1373,6 @@ rl_not_mapped_enoent: return err; } -/* - * Copy as much as we can into the pages and return the number of bytes which - * were successfully copied. If a fault is encountered then clear the pages - * out to (ofs + bytes) and return the number of bytes which were copied. - */ -static inline size_t ntfs_copy_from_user(struct page **pages, - unsigned nr_pages, unsigned ofs, const char __user *buf, - size_t bytes) -{ - struct page **last_page = pages + nr_pages; - char *addr; - size_t total = 0; - unsigned len; - int left; - - do { - len = PAGE_CACHE_SIZE - ofs; - if (len > bytes) - len = bytes; - addr = kmap_atomic(*pages); - left = __copy_from_user_inatomic(addr + ofs, buf, len); - kunmap_atomic(addr); - if (unlikely(left)) { - /* Do it the slow way. */ - addr = kmap(*pages); - left = __copy_from_user(addr + ofs, buf, len); - kunmap(*pages); - if (unlikely(left)) - goto err_out; - } - total += len; - bytes -= len; - if (!bytes) - break; - buf += len; - ofs = 0; - } while (++pages < last_page); -out: - return total; -err_out: - total += len - left; - /* Zero the rest of the target like __copy_from_user(). */ - while (++pages < last_page) { - bytes -= len; - if (!bytes) - break; - len = PAGE_CACHE_SIZE; - if (len > bytes) - len = bytes; - zero_user(*pages, 0, len); - } - goto out; -} - -static size_t __ntfs_copy_from_user_iovec_inatomic(char *vaddr, - const struct iovec *iov, size_t iov_ofs, size_t bytes) -{ - size_t total = 0; - - while (1) { - const char __user *buf = iov->iov_base + iov_ofs; - unsigned len; - size_t left; - - len = iov->iov_len - iov_ofs; - if (len > bytes) - len = bytes; - left = __copy_from_user_inatomic(vaddr, buf, len); - total += len; - bytes -= len; - vaddr += len; - if (unlikely(left)) { - total -= left; - break; - } - if (!bytes) - break; - iov++; - iov_ofs = 0; - } - return total; -} - -static inline void ntfs_set_next_iovec(const struct iovec **iovp, - size_t *iov_ofsp, size_t bytes) -{ - const struct iovec *iov = *iovp; - size_t iov_ofs = *iov_ofsp; - - while (bytes) { - unsigned len; - - len = iov->iov_len - iov_ofs; - if (len > bytes) - len = bytes; - bytes -= len; - iov_ofs += len; - if (iov->iov_len == iov_ofs) { - iov++; - iov_ofs = 0; - } - } - *iovp = iov; - *iov_ofsp = iov_ofs; -} - -/* - * This has the same side-effects and return value as ntfs_copy_from_user(). - * The difference is that on a fault we need to memset the remainder of the - * pages (out to offset + bytes), to emulate ntfs_copy_from_user()'s - * single-segment behaviour. - * - * We call the same helper (__ntfs_copy_from_user_iovec_inatomic()) both when - * atomic and when not atomic. This is ok because it calls - * __copy_from_user_inatomic() and it is ok to call this when non-atomic. In - * fact, the only difference between __copy_from_user_inatomic() and - * __copy_from_user() is that the latter calls might_sleep() and the former - * should not zero the tail of the buffer on error. And on many architectures - * __copy_from_user_inatomic() is just defined to __copy_from_user() so it - * makes no difference at all on those architectures. - */ -static inline size_t ntfs_copy_from_user_iovec(struct page **pages, - unsigned nr_pages, unsigned ofs, const struct iovec **iov, - size_t *iov_ofs, size_t bytes) -{ - struct page **last_page = pages + nr_pages; - char *addr; - size_t copied, len, total = 0; - - do { - len = PAGE_CACHE_SIZE - ofs; - if (len > bytes) - len = bytes; - addr = kmap_atomic(*pages); - copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs, - *iov, *iov_ofs, len); - kunmap_atomic(addr); - if (unlikely(copied != len)) { - /* Do it the slow way. */ - addr = kmap(*pages); - copied = __ntfs_copy_from_user_iovec_inatomic(addr + - ofs, *iov, *iov_ofs, len); - if (unlikely(copied != len)) - goto err_out; - kunmap(*pages); - } - total += len; - ntfs_set_next_iovec(iov, iov_ofs, len); - bytes -= len; - if (!bytes) - break; - ofs = 0; - } while (++pages < last_page); -out: - return total; -err_out: - BUG_ON(copied > len); - /* Zero the rest of the target like __copy_from_user(). */ - memset(addr + ofs + copied, 0, len - copied); - kunmap(*pages); - total += copied; - ntfs_set_next_iovec(iov, iov_ofs, copied); - while (++pages < last_page) { - bytes -= len; - if (!bytes) - break; - len = PAGE_CACHE_SIZE; - if (len > bytes) - len = bytes; - zero_user(*pages, 0, len); - } - goto out; -} - static inline void ntfs_flush_dcache_pages(struct page **pages, unsigned nr_pages) { @@ -1762,86 +1693,83 @@ err_out: return err; } -static void ntfs_write_failed(struct address_space *mapping, loff_t to) +/* + * Copy as much as we can into the pages and return the number of bytes which + * were successfully copied. If a fault is encountered then clear the pages + * out to (ofs + bytes) and return the number of bytes which were copied. + */ +static size_t ntfs_copy_from_user_iter(struct page **pages, unsigned nr_pages, + unsigned ofs, struct iov_iter *i, size_t bytes) { - struct inode *inode = mapping->host; + struct page **last_page = pages + nr_pages; + size_t total = 0; + struct iov_iter data = *i; + unsigned len, copied; - if (to > inode->i_size) { - truncate_pagecache(inode, inode->i_size); - ntfs_truncate_vfs(inode); - } + do { + len = PAGE_CACHE_SIZE - ofs; + if (len > bytes) + len = bytes; + copied = iov_iter_copy_from_user_atomic(*pages, &data, ofs, + len); + total += copied; + bytes -= copied; + if (!bytes) + break; + iov_iter_advance(&data, copied); + if (copied < len) + goto err; + ofs = 0; + } while (++pages < last_page); +out: + return total; +err: + /* Zero the rest of the target like __copy_from_user(). */ + len = PAGE_CACHE_SIZE - copied; + do { + if (len > bytes) + len = bytes; + zero_user(*pages, copied, len); + bytes -= len; + copied = 0; + len = PAGE_CACHE_SIZE; + } while (++pages < last_page); + goto out; } /** - * ntfs_file_buffered_write - - * - * Locking: The vfs is holding ->i_mutex on the inode. + * ntfs_perform_write - perform buffered write to a file + * @file: file to write to + * @i: iov_iter with data to write + * @pos: byte offset in file at which to begin writing to */ -static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, - loff_t pos, loff_t *ppos, size_t count) +static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i, + loff_t pos) { - struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *vi = mapping->host; ntfs_inode *ni = NTFS_I(vi); ntfs_volume *vol = ni->vol; struct page *pages[NTFS_MAX_PAGES_PER_CLUSTER]; struct page *cached_page = NULL; - char __user *buf = NULL; - s64 end, ll; VCN last_vcn; LCN lcn; - unsigned long flags; - size_t bytes, iov_ofs = 0; /* Offset in the current iovec. */ - ssize_t status, written; + size_t bytes; + ssize_t status, written = 0; unsigned nr_pages; - int err; - ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, " - "pos 0x%llx, count 0x%lx.", - vi->i_ino, (unsigned)le32_to_cpu(ni->type), - (unsigned long long)pos, (unsigned long)count); - if (unlikely(!count)) - return 0; - BUG_ON(NInoMstProtected(ni)); - /* - * If the attribute is not an index root and it is encrypted or - * compressed, we cannot write to it yet. Note we need to check for - * AT_INDEX_ALLOCATION since this is the type of both directory and - * index inodes. - */ - if (ni->type != AT_INDEX_ALLOCATION) { - /* If file is encrypted, deny access, just like NT4. */ - if (NInoEncrypted(ni)) { - /* - * Reminder for later: Encrypted files are _always_ - * non-resident so that the content can always be - * encrypted. - */ - ntfs_debug("Denying write access to encrypted file."); - return -EACCES; - } - if (NInoCompressed(ni)) { - /* Only unnamed $DATA attribute can be compressed. */ - BUG_ON(ni->type != AT_DATA); - BUG_ON(ni->name_len); - /* - * Reminder for later: If resident, the data is not - * actually compressed. Only on the switch to non- - * resident does compression kick in. This is in - * contrast to encrypted files (see above). - */ - ntfs_error(vi->i_sb, "Writing to compressed files is " - "not implemented yet. Sorry."); - return -EOPNOTSUPP; - } - } + ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos " + "0x%llx, count 0x%lx.", vi->i_ino, + (unsigned)le32_to_cpu(ni->type), + (unsigned long long)pos, + (unsigned long)iov_iter_count(i)); /* * If a previous ntfs_truncate() failed, repeat it and abort if it * fails again. */ if (unlikely(NInoTruncateFailed(ni))) { + int err; + inode_dio_wait(vi); err = ntfs_truncate(vi); if (err || NInoTruncateFailed(ni)) { @@ -1855,81 +1783,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, return err; } } - /* The first byte after the write. */ - end = pos + count; - /* - * If the write goes beyond the allocated size, extend the allocation - * to cover the whole of the write, rounded up to the nearest cluster. - */ - read_lock_irqsave(&ni->size_lock, flags); - ll = ni->allocated_size; - read_unlock_irqrestore(&ni->size_lock, flags); - if (end > ll) { - /* Extend the allocation without changing the data size. */ - ll = ntfs_attr_extend_allocation(ni, end, -1, pos); - if (likely(ll >= 0)) { - BUG_ON(pos >= ll); - /* If the extension was partial truncate the write. */ - if (end > ll) { - ntfs_debug("Truncating write to inode 0x%lx, " - "attribute type 0x%x, because " - "the allocation was only " - "partially extended.", - vi->i_ino, (unsigned) - le32_to_cpu(ni->type)); - end = ll; - count = ll - pos; - } - } else { - err = ll; - read_lock_irqsave(&ni->size_lock, flags); - ll = ni->allocated_size; - read_unlock_irqrestore(&ni->size_lock, flags); - /* Perform a partial write if possible or fail. */ - if (pos < ll) { - ntfs_debug("Truncating write to inode 0x%lx, " - "attribute type 0x%x, because " - "extending the allocation " - "failed (error code %i).", - vi->i_ino, (unsigned) - le32_to_cpu(ni->type), err); - end = ll; - count = ll - pos; - } else { - ntfs_error(vol->sb, "Cannot perform write to " - "inode 0x%lx, attribute type " - "0x%x, because extending the " - "allocation failed (error " - "code %i).", vi->i_ino, - (unsigned) - le32_to_cpu(ni->type), err); - return err; - } - } - } - written = 0; - /* - * If the write starts beyond the initialized size, extend it up to the - * beginning of the write and initialize all non-sparse space between - * the old initialized size and the new one. This automatically also - * increments the vfs inode->i_size to keep it above or equal to the - * initialized_size. - */ - read_lock_irqsave(&ni->size_lock, flags); - ll = ni->initialized_size; - read_unlock_irqrestore(&ni->size_lock, flags); - if (pos > ll) { - err = ntfs_attr_extend_initialized(ni, pos); - if (err < 0) { - ntfs_error(vol->sb, "Cannot perform write to inode " - "0x%lx, attribute type 0x%x, because " - "extending the initialized size " - "failed (error code %i).", vi->i_ino, - (unsigned)le32_to_cpu(ni->type), err); - status = err; - goto err_out; - } - } /* * Determine the number of pages per cluster for non-resident * attributes. @@ -1937,10 +1790,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, nr_pages = 1; if (vol->cluster_size > PAGE_CACHE_SIZE && NInoNonResident(ni)) nr_pages = vol->cluster_size >> PAGE_CACHE_SHIFT; - /* Finally, perform the actual write. */ last_vcn = -1; - if (likely(nr_segs == 1)) - buf = iov->iov_base; do { VCN vcn; pgoff_t idx, start_idx; @@ -1965,10 +1815,10 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, vol->cluster_size_bits, false); up_read(&ni->runlist.lock); if (unlikely(lcn < LCN_HOLE)) { - status = -EIO; if (lcn == LCN_ENOMEM) status = -ENOMEM; - else + else { + status = -EIO; ntfs_error(vol->sb, "Cannot " "perform write to " "inode 0x%lx, " @@ -1977,6 +1827,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, "is corrupt.", vi->i_ino, (unsigned) le32_to_cpu(ni->type)); + } break; } if (lcn == LCN_HOLE) { @@ -1989,8 +1840,9 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } } } - if (bytes > count) - bytes = count; + if (bytes > iov_iter_count(i)) + bytes = iov_iter_count(i); +again: /* * Bring in the user page(s) that we will copy from _first_. * Otherwise there is a nasty deadlock on copying from the same @@ -1999,10 +1851,10 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, * pages being swapped out between us bringing them into memory * and doing the actual copying. */ - if (likely(nr_segs == 1)) - ntfs_fault_in_pages_readable(buf, bytes); - else - ntfs_fault_in_pages_readable_iovec(iov, iov_ofs, bytes); + if (unlikely(iov_iter_fault_in_multipages_readable(i, bytes))) { + status = -EFAULT; + break; + } /* Get and lock @do_pages starting at index @start_idx. */ status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages, pages, &cached_page); @@ -2018,56 +1870,57 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, status = ntfs_prepare_pages_for_non_resident_write( pages, do_pages, pos, bytes); if (unlikely(status)) { - loff_t i_size; - do { unlock_page(pages[--do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); - /* - * The write preparation may have instantiated - * allocated space outside i_size. Trim this - * off again. We can ignore any errors in this - * case as we will just be waisting a bit of - * allocated space, which is not a disaster. - */ - i_size = i_size_read(vi); - if (pos + bytes > i_size) { - ntfs_write_failed(mapping, pos + bytes); - } break; } } u = (pos >> PAGE_CACHE_SHIFT) - pages[0]->index; - if (likely(nr_segs == 1)) { - copied = ntfs_copy_from_user(pages + u, do_pages - u, - ofs, buf, bytes); - buf += copied; - } else - copied = ntfs_copy_from_user_iovec(pages + u, - do_pages - u, ofs, &iov, &iov_ofs, - bytes); + copied = ntfs_copy_from_user_iter(pages + u, do_pages - u, ofs, + i, bytes); ntfs_flush_dcache_pages(pages + u, do_pages - u); - status = ntfs_commit_pages_after_write(pages, do_pages, pos, - bytes); - if (likely(!status)) { - written += copied; - count -= copied; - pos += copied; - if (unlikely(copied != bytes)) - status = -EFAULT; + status = 0; + if (likely(copied == bytes)) { + status = ntfs_commit_pages_after_write(pages, do_pages, + pos, bytes); + if (!status) + status = bytes; } do { unlock_page(pages[--do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); - if (unlikely(status)) + if (unlikely(status < 0)) break; - balance_dirty_pages_ratelimited(mapping); + copied = status; cond_resched(); - } while (count); -err_out: - *ppos = pos; + if (unlikely(!copied)) { + size_t sc; + + /* + * We failed to copy anything. Fall back to single + * segment length write. + * + * This is needed to avoid possible livelock in the + * case that all segments in the iov cannot be copied + * at once without a pagefault. + */ + sc = iov_iter_single_seg_count(i); + if (bytes > sc) + bytes = sc; + goto again; + } + iov_iter_advance(i, copied); + pos += copied; + written += copied; + balance_dirty_pages_ratelimited(mapping); + if (fatal_signal_pending(current)) { + status = -EINTR; + break; + } + } while (iov_iter_count(i)); if (cached_page) page_cache_release(cached_page); ntfs_debug("Done. Returning %s (written 0x%lx, status %li).", @@ -2077,59 +1930,56 @@ err_out: } /** - * ntfs_file_aio_write_nolock - + * ntfs_file_write_iter_nolock - write data to a file + * @iocb: IO state structure (file, offset, etc.) + * @from: iov_iter with data to write + * + * Basically the same as __generic_file_write_iter() except that it ends + * up calling ntfs_perform_write() instead of generic_perform_write() and that + * O_DIRECT is not implemented. */ -static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, loff_t *ppos) +static ssize_t ntfs_file_write_iter_nolock(struct kiocb *iocb, + struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - loff_t pos; - size_t count; /* after file limit checks */ - ssize_t written, err; + loff_t pos = iocb->ki_pos; + ssize_t written = 0; + ssize_t err; + size_t count = iov_iter_count(from); - count = iov_length(iov, nr_segs); - pos = *ppos; - /* We can write back this queue in page reclaim. */ - current->backing_dev_info = inode_to_bdi(inode); - written = 0; - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); - if (err) - goto out; - if (!count) - goto out; - err = file_remove_suid(file); - if (err) - goto out; - err = file_update_time(file); - if (err) - goto out; - written = ntfs_file_buffered_write(iocb, iov, nr_segs, pos, ppos, - count); -out: + err = ntfs_prepare_file_for_write(file, &pos, &count); + if (count && !err) { + iov_iter_truncate(from, count); + written = ntfs_perform_write(file, from, pos); + if (likely(written >= 0)) + iocb->ki_pos = pos + written; + } current->backing_dev_info = NULL; return written ? written : err; } /** - * ntfs_file_aio_write - + * ntfs_file_write_iter - simple wrapper for ntfs_file_write_iter_nolock() + * @iocb: IO state structure + * @from: iov_iter with data to write + * + * Basically the same as generic_file_write_iter() except that it ends up + * calling ntfs_file_write_iter_nolock() instead of + * __generic_file_write_iter(). */ -static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; + struct inode *vi = file_inode(file); ssize_t ret; - BUG_ON(iocb->ki_pos != pos); - - mutex_lock(&inode->i_mutex); - ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); - mutex_unlock(&inode->i_mutex); + mutex_lock(&vi->i_mutex); + ret = ntfs_file_write_iter_nolock(iocb, from); + mutex_unlock(&vi->i_mutex); if (ret > 0) { - int err = generic_write_sync(file, iocb->ki_pos - ret, ret); + ssize_t err; + + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } @@ -2197,37 +2047,17 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end, #endif /* NTFS_RW */ const struct file_operations ntfs_file_ops = { - .llseek = generic_file_llseek, /* Seek inside file. */ - .read = new_sync_read, /* Read from file. */ - .read_iter = generic_file_read_iter, /* Async read from file. */ + .llseek = generic_file_llseek, + .read = new_sync_read, + .read_iter = generic_file_read_iter, #ifdef NTFS_RW - .write = do_sync_write, /* Write to file. */ - .aio_write = ntfs_file_aio_write, /* Async write to file. */ - /*.release = ,*/ /* Last file is closed. See - fs/ext2/file.c:: - ext2_release_file() for - how to use this to discard - preallocated space for - write opened files. */ - .fsync = ntfs_file_fsync, /* Sync a file to disk. */ - /*.aio_fsync = ,*/ /* Sync all outstanding async - i/o operations on a - kiocb. */ + .write = new_sync_write, + .write_iter = ntfs_file_write_iter, + .fsync = ntfs_file_fsync, #endif /* NTFS_RW */ - /*.ioctl = ,*/ /* Perform function on the - mounted filesystem. */ - .mmap = generic_file_mmap, /* Mmap file. */ - .open = ntfs_file_open, /* Open file. */ - .splice_read = generic_file_splice_read /* Zero-copy data send with - the data source being on - the ntfs partition. We do - not need to care about the - data destination. */ - /*.sendpage = ,*/ /* Zero-copy data send with - the data destination being - on the ntfs partition. We - do not need to care about - the data source. */ + .mmap = generic_file_mmap, + .open = ntfs_file_open, + .splice_read = generic_file_splice_read, }; const struct inode_operations ntfs_file_inode_ops = { 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 <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 1b0463a92b17..8d2bc840c288 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -29,6 +29,7 @@ #include <linux/mpage.h> #include <linux/quotaops.h> #include <linux/blkdev.h> +#include <linux/uio.h> #include <cluster/masklog.h> 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 <linux/aio.h> +#include <linux/fs.h> handle_t *ocfs2_start_walk_page_trans(struct inode *inode, struct page *page, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index ba1790e52ff2..91f03ce98108 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2280,7 +2280,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, file->f_path.dentry->d_name.name, (unsigned int)from->nr_segs); /* GRRRRR */ - if (iocb->ki_nbytes == 0) + if (count == 0) return 0; appending = file->f_flags & O_APPEND ? 1 : 0; @@ -2330,8 +2330,7 @@ relock: } can_do_direct = direct_io; - ret = ocfs2_prepare_inode_for_write(file, ppos, - iocb->ki_nbytes, appending, + ret = ocfs2_prepare_inode_for_write(file, ppos, count, appending, &can_do_direct, &has_refcount); if (ret < 0) { mlog_errno(ret); @@ -2339,8 +2338,7 @@ relock: } if (direct_io && !is_sync_kiocb(iocb)) - unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_nbytes, - *ppos); + unaligned_dio = ocfs2_is_io_unaligned(inode, count, *ppos); /* * We can't complete the direct I/O as requested, fall back to diff --git a/fs/open.c b/fs/open.c index 33f9cbf2610b..6a83c47d5904 100644 --- a/fs/open.c +++ b/fs/open.c @@ -570,6 +570,7 @@ static int chown_common(struct path *path, uid_t user, gid_t group) uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); +retry_deleg: newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { if (!uid_valid(uid)) @@ -586,7 +587,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group) if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; -retry_deleg: mutex_lock(&inode->i_mutex); error = security_path_chown(path, uid, gid); if (!error) @@ -988,9 +988,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, return ERR_PTR(err); if (flags & O_CREAT) return ERR_PTR(-EINVAL); - if (!filename && (flags & O_DIRECTORY)) - if (!dentry->d_inode->i_op->lookup) - return ERR_PTR(-ENOTDIR); return do_file_open_root(dentry, mnt, filename, &op); } EXPORT_SYMBOL(file_open_root); 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 <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/pstore/ram.c b/fs/pstore/ram.c index 39d1373128e9..44a549beeafa 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -539,6 +539,9 @@ static int ramoops_probe(struct platform_device *pdev) mem_address = pdata->mem_address; record_size = pdata->record_size; dump_oops = pdata->dump_oops; + ramoops_console_size = pdata->console_size; + ramoops_pmsg_size = pdata->pmsg_size; + ramoops_ftrace_size = pdata->ftrace_size; pr_info("attached 0x%lx@0x%llx, ecc: %d/%d\n", cxt->size, (unsigned long long)cxt->phys_addr, diff --git a/fs/read_write.c b/fs/read_write.c index 8e1b68786d66..69128b378646 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -9,7 +9,6 @@ #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> -#include <linux/aio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> @@ -343,13 +342,10 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos) init_sync_kiocb(&kiocb, file); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = iov_iter_count(iter); 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; @@ -366,13 +362,10 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) init_sync_kiocb(&kiocb, file); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = iov_iter_count(iter); 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; @@ -426,11 +419,9 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; 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; } @@ -446,12 +437,10 @@ ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *p init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; 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; } @@ -510,11 +499,9 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; 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; } @@ -530,12 +517,10 @@ ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, lo init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; 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; } @@ -710,60 +695,47 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) } EXPORT_SYMBOL(iov_shorten); -static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iovec *iov, - unsigned long nr_segs, size_t len, loff_t *ppos, iter_fn_t fn) +static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, + loff_t *ppos, iter_fn_t fn) { struct kiocb kiocb; - struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; - iov_iter_init(&iter, rw, iov, nr_segs, len); - ret = fn(&kiocb, &iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); + ret = fn(&kiocb, iter); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } -static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn) +static ssize_t do_sync_readv_writev(struct file *filp, struct iov_iter *iter, + loff_t *ppos, iov_fn_t fn) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - kiocb.ki_nbytes = len; - ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); + ret = fn(&kiocb, iter->iov, iter->nr_segs, kiocb.ki_pos); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ -static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, - unsigned long nr_segs, loff_t *ppos, io_fn_t fn) +static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, + loff_t *ppos, io_fn_t fn) { - struct iovec *vector = iov; ssize_t ret = 0; - while (nr_segs > 0) { - void __user *base; - size_t len; + while (iov_iter_count(iter)) { + struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(filp, base, len, ppos); + nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos); if (nr < 0) { if (!ret) @@ -771,8 +743,9 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, break; } ret += nr; - if (nr != len) + if (nr != iovec.iov_len) break; + iov_iter_advance(iter, nr); } return ret; @@ -863,17 +836,20 @@ static ssize_t do_readv_writev(int type, struct file *file, size_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; + struct iov_iter iter; ssize_t ret; io_fn_t fn; iov_fn_t fnv; iter_fn_t iter_fn; - ret = rw_copy_check_uvector(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), iovstack, &iov); - if (ret <= 0) - goto out; + ret = import_iovec(type, uvector, nr_segs, + ARRAY_SIZE(iovstack), &iov, &iter); + if (ret < 0) + return ret; - tot_len = ret; + tot_len = iov_iter_count(&iter); + if (!tot_len) + goto out; ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; @@ -891,20 +867,17 @@ static ssize_t do_readv_writev(int type, struct file *file, } if (iter_fn) - ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len, - pos, iter_fn); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn); else if (fnv) - ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, - pos, fnv); + ret = do_sync_readv_writev(file, &iter, pos, fnv); else - ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn); if (type != READ) file_end_write(file); out: - if (iov != iovstack) - kfree(iov); + kfree(iov); if ((ret + (type == READ)) > 0) { if (type == READ) fsnotify_access(file); @@ -1043,17 +1016,20 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; + struct iov_iter iter; ssize_t ret; io_fn_t fn; iov_fn_t fnv; iter_fn_t iter_fn; - ret = compat_rw_copy_check_uvector(type, uvector, nr_segs, - UIO_FASTIOV, iovstack, &iov); - if (ret <= 0) - goto out; + ret = compat_import_iovec(type, uvector, nr_segs, + UIO_FASTIOV, &iov, &iter); + if (ret < 0) + return ret; - tot_len = ret; + tot_len = iov_iter_count(&iter); + if (!tot_len) + goto out; ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; @@ -1071,20 +1047,17 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, } if (iter_fn) - ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len, - pos, iter_fn); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn); else if (fnv) - ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, - pos, fnv); + ret = do_sync_readv_writev(file, &iter, pos, fnv); else - ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn); if (type != READ) file_end_write(file); out: - if (iov != iovstack) - kfree(iov); + kfree(iov); if ((ret + (type == READ)) > 0) { if (type == READ) fsnotify_access(file); 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 <linux/writeback.h> #include <linux/quotaops.h> #include <linux/swap.h> -#include <linux/aio.h> +#include <linux/uio.h> 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..41cbb16299e0 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -32,7 +32,6 @@ #include <linux/gfp.h> #include <linux/socket.h> #include <linux/compat.h> -#include <linux/aio.h> #include "internal.h" /* @@ -1534,34 +1533,29 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov, struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; - ssize_t count; pipe = get_pipe_info(file); if (!pipe) return -EBADF; - ret = rw_copy_check_uvector(READ, uiov, nr_segs, - ARRAY_SIZE(iovstack), iovstack, &iov); - if (ret <= 0) - goto out; - - count = ret; - iov_iter_init(&iter, READ, iov, nr_segs, count); + ret = import_iovec(READ, uiov, nr_segs, + ARRAY_SIZE(iovstack), &iov, &iter); + if (ret < 0) + return ret; + sd.total_len = iov_iter_count(&iter); sd.len = 0; - sd.total_len = count; sd.flags = flags; sd.u.data = &iter; sd.pos = 0; - pipe_lock(pipe); - ret = __splice_from_pipe(pipe, &sd, pipe_to_user); - pipe_unlock(pipe); - -out: - if (iov != iovstack) - kfree(iov); + if (sd.total_len) { + pipe_lock(pipe); + ret = __splice_from_pipe(pipe, &sd, pipe_to_user); + pipe_unlock(pipe); + } + kfree(iov); return ret; } 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/fs/tracefs/Makefile b/fs/tracefs/Makefile new file mode 100644 index 000000000000..82fa35b656c4 --- /dev/null +++ b/fs/tracefs/Makefile @@ -0,0 +1,4 @@ +tracefs-objs := inode.o + +obj-$(CONFIG_TRACING) += tracefs.o + diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c new file mode 100644 index 000000000000..d92bdf3b079a --- /dev/null +++ b/fs/tracefs/inode.c @@ -0,0 +1,650 @@ +/* + * inode.c - part of tracefs, a pseudo file system for activating tracing + * + * Based on debugfs by: Greg Kroah-Hartman <greg@kroah.com> + * + * Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + * + * tracefs is the file system that is used by the tracing infrastructure. + * + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/kobject.h> +#include <linux/namei.h> +#include <linux/tracefs.h> +#include <linux/fsnotify.h> +#include <linux/seq_file.h> +#include <linux/parser.h> +#include <linux/magic.h> +#include <linux/slab.h> + +#define TRACEFS_DEFAULT_MODE 0700 + +static struct vfsmount *tracefs_mount; +static int tracefs_mount_count; +static bool tracefs_registered; + +static ssize_t default_read_file(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + return 0; +} + +static ssize_t default_write_file(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + return count; +} + +static const struct file_operations tracefs_file_operations = { + .read = default_read_file, + .write = default_write_file, + .open = simple_open, + .llseek = noop_llseek, +}; + +static struct tracefs_dir_ops { + int (*mkdir)(const char *name); + int (*rmdir)(const char *name); +} tracefs_ops; + +static char *get_dname(struct dentry *dentry) +{ + const char *dname; + char *name; + int len = dentry->d_name.len; + + dname = dentry->d_name.name; + name = kmalloc(len + 1, GFP_KERNEL); + if (!name) + return NULL; + memcpy(name, dname, len); + name[len] = 0; + return name; +} + +static int tracefs_syscall_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode) +{ + char *name; + int ret; + + name = get_dname(dentry); + if (!name) + return -ENOMEM; + + /* + * The mkdir call can call the generic functions that create + * the files within the tracefs system. It is up to the individual + * mkdir routine to handle races. + */ + mutex_unlock(&inode->i_mutex); + ret = tracefs_ops.mkdir(name); + mutex_lock(&inode->i_mutex); + + kfree(name); + + return ret; +} + +static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry) +{ + char *name; + int ret; + + name = get_dname(dentry); + if (!name) + return -ENOMEM; + + /* + * The rmdir call can call the generic functions that create + * the files within the tracefs system. It is up to the individual + * rmdir routine to handle races. + * This time we need to unlock not only the parent (inode) but + * also the directory that is being deleted. + */ + mutex_unlock(&inode->i_mutex); + mutex_unlock(&dentry->d_inode->i_mutex); + + ret = tracefs_ops.rmdir(name); + + mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); + mutex_lock(&dentry->d_inode->i_mutex); + + kfree(name); + + return ret; +} + +static const struct inode_operations tracefs_dir_inode_operations = { + .lookup = simple_lookup, + .mkdir = tracefs_syscall_mkdir, + .rmdir = tracefs_syscall_rmdir, +}; + +static struct inode *tracefs_get_inode(struct super_block *sb) +{ + struct inode *inode = new_inode(sb); + if (inode) { + inode->i_ino = get_next_ino(); + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + } + return inode; +} + +struct tracefs_mount_opts { + kuid_t uid; + kgid_t gid; + umode_t mode; +}; + +enum { + Opt_uid, + Opt_gid, + Opt_mode, + Opt_err +}; + +static const match_table_t tokens = { + {Opt_uid, "uid=%u"}, + {Opt_gid, "gid=%u"}, + {Opt_mode, "mode=%o"}, + {Opt_err, NULL} +}; + +struct tracefs_fs_info { + struct tracefs_mount_opts mount_opts; +}; + +static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) +{ + substring_t args[MAX_OPT_ARGS]; + int option; + int token; + kuid_t uid; + kgid_t gid; + char *p; + + opts->mode = TRACEFS_DEFAULT_MODE; + + while ((p = strsep(&data, ",")) != NULL) { + if (!*p) + continue; + + token = match_token(p, tokens, args); + switch (token) { + case Opt_uid: + if (match_int(&args[0], &option)) + return -EINVAL; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) + return -EINVAL; + opts->uid = uid; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return -EINVAL; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) + return -EINVAL; + opts->gid = gid; + break; + case Opt_mode: + if (match_octal(&args[0], &option)) + return -EINVAL; + opts->mode = option & S_IALLUGO; + break; + /* + * We might like to report bad mount options here; + * but traditionally tracefs has ignored all mount options + */ + } + } + + return 0; +} + +static int tracefs_apply_options(struct super_block *sb) +{ + struct tracefs_fs_info *fsi = sb->s_fs_info; + struct inode *inode = sb->s_root->d_inode; + struct tracefs_mount_opts *opts = &fsi->mount_opts; + + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= opts->mode; + + inode->i_uid = opts->uid; + inode->i_gid = opts->gid; + + return 0; +} + +static int tracefs_remount(struct super_block *sb, int *flags, char *data) +{ + int err; + struct tracefs_fs_info *fsi = sb->s_fs_info; + + sync_filesystem(sb); + err = tracefs_parse_options(data, &fsi->mount_opts); + if (err) + goto fail; + + tracefs_apply_options(sb); + +fail: + return err; +} + +static int tracefs_show_options(struct seq_file *m, struct dentry *root) +{ + struct tracefs_fs_info *fsi = root->d_sb->s_fs_info; + struct tracefs_mount_opts *opts = &fsi->mount_opts; + + if (!uid_eq(opts->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->uid)); + if (!gid_eq(opts->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->gid)); + if (opts->mode != TRACEFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", opts->mode); + + return 0; +} + +static const struct super_operations tracefs_super_operations = { + .statfs = simple_statfs, + .remount_fs = tracefs_remount, + .show_options = tracefs_show_options, +}; + +static int trace_fill_super(struct super_block *sb, void *data, int silent) +{ + static struct tree_descr trace_files[] = {{""}}; + struct tracefs_fs_info *fsi; + int err; + + save_mount_options(sb, data); + + fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL); + sb->s_fs_info = fsi; + if (!fsi) { + err = -ENOMEM; + goto fail; + } + + err = tracefs_parse_options(data, &fsi->mount_opts); + if (err) + goto fail; + + err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files); + if (err) + goto fail; + + sb->s_op = &tracefs_super_operations; + + tracefs_apply_options(sb); + + return 0; + +fail: + kfree(fsi); + sb->s_fs_info = NULL; + return err; +} + +static struct dentry *trace_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data) +{ + return mount_single(fs_type, flags, data, trace_fill_super); +} + +static struct file_system_type trace_fs_type = { + .owner = THIS_MODULE, + .name = "tracefs", + .mount = trace_mount, + .kill_sb = kill_litter_super, +}; +MODULE_ALIAS_FS("tracefs"); + +static struct dentry *start_creating(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + int error; + + pr_debug("tracefs: creating file '%s'\n",name); + + error = simple_pin_fs(&trace_fs_type, &tracefs_mount, + &tracefs_mount_count); + if (error) + return ERR_PTR(error); + + /* If the parent is not specified, we create it in the root. + * We need the root dentry to do this, which is in the super + * block. A pointer to that is in the struct vfsmount that we + * have around. + */ + if (!parent) + parent = tracefs_mount->mnt_root; + + mutex_lock(&parent->d_inode->i_mutex); + dentry = lookup_one_len(name, parent, strlen(name)); + if (!IS_ERR(dentry) && dentry->d_inode) { + dput(dentry); + dentry = ERR_PTR(-EEXIST); + } + if (IS_ERR(dentry)) + mutex_unlock(&parent->d_inode->i_mutex); + return dentry; +} + +static struct dentry *failed_creating(struct dentry *dentry) +{ + mutex_unlock(&dentry->d_parent->d_inode->i_mutex); + dput(dentry); + simple_release_fs(&tracefs_mount, &tracefs_mount_count); + return NULL; +} + +static struct dentry *end_creating(struct dentry *dentry) +{ + mutex_unlock(&dentry->d_parent->d_inode->i_mutex); + return dentry; +} + +/** + * tracefs_create_file - create a file in the tracefs filesystem + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * file will be created in the root of the tracefs filesystem. + * @data: a pointer to something that the caller will want to get to later + * on. The inode.i_private pointer will point to this value on + * the open() call. + * @fops: a pointer to a struct file_operations that should be used for + * this file. + * + * This is the basic "create a file" function for tracefs. It allows for a + * wide range of flexibility in creating a file, or a directory (if you want + * to create a directory, the tracefs_create_dir() function is + * recommended to be used instead.) + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the tracefs_remove() function when the file is + * to be removed (no automatic cleanup happens if your module is unloaded, + * you are responsible here.) If an error occurs, %NULL will be returned. + * + * If tracefs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *tracefs_create_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops) +{ + struct dentry *dentry; + struct inode *inode; + + if (!(mode & S_IFMT)) + mode |= S_IFREG; + BUG_ON(!S_ISREG(mode)); + dentry = start_creating(name, parent); + + if (IS_ERR(dentry)) + return NULL; + + inode = tracefs_get_inode(dentry->d_sb); + if (unlikely(!inode)) + return failed_creating(dentry); + + inode->i_mode = mode; + inode->i_fop = fops ? fops : &tracefs_file_operations; + inode->i_private = data; + d_instantiate(dentry, inode); + fsnotify_create(dentry->d_parent->d_inode, dentry); + return end_creating(dentry); +} + +static struct dentry *__create_dir(const char *name, struct dentry *parent, + const struct inode_operations *ops) +{ + struct dentry *dentry = start_creating(name, parent); + struct inode *inode; + + if (IS_ERR(dentry)) + return NULL; + + inode = tracefs_get_inode(dentry->d_sb); + if (unlikely(!inode)) + return failed_creating(dentry); + + inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + inode->i_op = ops; + inode->i_fop = &simple_dir_operations; + + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + d_instantiate(dentry, inode); + inc_nlink(dentry->d_parent->d_inode); + fsnotify_mkdir(dentry->d_parent->d_inode, dentry); + return end_creating(dentry); +} + +/** + * tracefs_create_dir - create a directory in the tracefs filesystem + * @name: a pointer to a string containing the name of the directory to + * create. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * directory will be created in the root of the tracefs filesystem. + * + * This function creates a directory in tracefs with the given name. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the tracefs_remove() function when the file is + * to be removed. If an error occurs, %NULL will be returned. + * + * If tracing is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *tracefs_create_dir(const char *name, struct dentry *parent) +{ + return __create_dir(name, parent, &simple_dir_inode_operations); +} + +/** + * tracefs_create_instance_dir - create the tracing instances directory + * @name: The name of the instances directory to create + * @parent: The parent directory that the instances directory will exist + * @mkdir: The function to call when a mkdir is performed. + * @rmdir: The function to call when a rmdir is performed. + * + * Only one instances directory is allowed. + * + * The instances directory is special as it allows for mkdir and rmdir to + * to be done by userspace. When a mkdir or rmdir is performed, the inode + * locks are released and the methhods passed in (@mkdir and @rmdir) are + * called without locks and with the name of the directory being created + * within the instances directory. + * + * Returns the dentry of the instances directory. + */ +struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *parent, + int (*mkdir)(const char *name), + int (*rmdir)(const char *name)) +{ + struct dentry *dentry; + + /* Only allow one instance of the instances directory. */ + if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir)) + return NULL; + + dentry = __create_dir(name, parent, &tracefs_dir_inode_operations); + if (!dentry) + return NULL; + + tracefs_ops.mkdir = mkdir; + tracefs_ops.rmdir = rmdir; + + return dentry; +} + +static inline int tracefs_positive(struct dentry *dentry) +{ + return dentry->d_inode && !d_unhashed(dentry); +} + +static int __tracefs_remove(struct dentry *dentry, struct dentry *parent) +{ + int ret = 0; + + if (tracefs_positive(dentry)) { + if (dentry->d_inode) { + dget(dentry); + switch (dentry->d_inode->i_mode & S_IFMT) { + case S_IFDIR: + ret = simple_rmdir(parent->d_inode, dentry); + break; + default: + simple_unlink(parent->d_inode, dentry); + break; + } + if (!ret) + d_delete(dentry); + dput(dentry); + } + } + return ret; +} + +/** + * tracefs_remove - removes a file or directory from the tracefs filesystem + * @dentry: a pointer to a the dentry of the file or directory to be + * removed. + * + * This function removes a file or directory in tracefs that was previously + * created with a call to another tracefs function (like + * tracefs_create_file() or variants thereof.) + */ +void tracefs_remove(struct dentry *dentry) +{ + struct dentry *parent; + int ret; + + if (IS_ERR_OR_NULL(dentry)) + return; + + parent = dentry->d_parent; + if (!parent || !parent->d_inode) + return; + + mutex_lock(&parent->d_inode->i_mutex); + ret = __tracefs_remove(dentry, parent); + mutex_unlock(&parent->d_inode->i_mutex); + if (!ret) + simple_release_fs(&tracefs_mount, &tracefs_mount_count); +} + +/** + * tracefs_remove_recursive - recursively removes a directory + * @dentry: a pointer to a the dentry of the directory to be removed. + * + * This function recursively removes a directory tree in tracefs that + * was previously created with a call to another tracefs function + * (like tracefs_create_file() or variants thereof.) + */ +void tracefs_remove_recursive(struct dentry *dentry) +{ + struct dentry *child, *parent; + + if (IS_ERR_OR_NULL(dentry)) + return; + + parent = dentry->d_parent; + if (!parent || !parent->d_inode) + return; + + parent = dentry; + down: + mutex_lock(&parent->d_inode->i_mutex); + loop: + /* + * The parent->d_subdirs is protected by the d_lock. Outside that + * lock, the child can be unlinked and set to be freed which can + * use the d_u.d_child as the rcu head and corrupt this list. + */ + spin_lock(&parent->d_lock); + list_for_each_entry(child, &parent->d_subdirs, d_child) { + if (!tracefs_positive(child)) + continue; + + /* perhaps simple_empty(child) makes more sense */ + if (!list_empty(&child->d_subdirs)) { + spin_unlock(&parent->d_lock); + mutex_unlock(&parent->d_inode->i_mutex); + parent = child; + goto down; + } + + spin_unlock(&parent->d_lock); + + if (!__tracefs_remove(child, parent)) + simple_release_fs(&tracefs_mount, &tracefs_mount_count); + + /* + * The parent->d_lock protects agaist child from unlinking + * from d_subdirs. When releasing the parent->d_lock we can + * no longer trust that the next pointer is valid. + * Restart the loop. We'll skip this one with the + * tracefs_positive() check. + */ + goto loop; + } + spin_unlock(&parent->d_lock); + + mutex_unlock(&parent->d_inode->i_mutex); + child = parent; + parent = parent->d_parent; + mutex_lock(&parent->d_inode->i_mutex); + + if (child != dentry) + /* go up */ + goto loop; + + if (!__tracefs_remove(child, parent)) + simple_release_fs(&tracefs_mount, &tracefs_mount_count); + mutex_unlock(&parent->d_inode->i_mutex); +} + +/** + * tracefs_initialized - Tells whether tracefs has been registered + */ +bool tracefs_initialized(void) +{ + return tracefs_registered; +} + +static struct kobject *trace_kobj; + +static int __init tracefs_init(void) +{ + int retval; + + trace_kobj = kobject_create_and_add("tracing", kernel_kobj); + if (!trace_kobj) + return -EINVAL; + + retval = register_filesystem(&trace_fs_type); + if (!retval) + tracefs_registered = true; + + return retval; +} +core_initcall(tracefs_init); 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 <linux/aio.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/slab.h> diff --git a/fs/udf/file.c b/fs/udf/file.c index 08f3555fbeac..7f885cc8b0b7 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -34,7 +34,7 @@ #include <linux/errno.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> -#include <linux/aio.h> +#include <linux/uio.h> #include "udf_i.h" #include "udf_sb.h" @@ -122,7 +122,7 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); int err, pos; - size_t count = iocb->ki_nbytes; + size_t count = iov_iter_count(from); struct udf_inode_info *iinfo = UDF_I(inode); mutex_lock(&inode->i_mutex); 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 <linux/slab.h> #include <linux/crc-itu-t.h> #include <linux/mpage.h> -#include <linux/aio.h> +#include <linux/uio.h> #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 <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 a2e1cb8a568b..f44212fae653 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -38,7 +38,6 @@ #include "xfs_icache.h" #include "xfs_pnfs.h" -#include <linux/aio.h> #include <linux/dcache.h> #include <linux/falloc.h> #include <linux/pagevec.h> |