io_pgetevents & aio fsync V3

index 88d7927ffbc6..add46b06be86 100644
@@ -264,9 +264,6 @@ static int __init aio_setup(void)
 
 	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));
-
 	return 0;
 }
 __initcall(aio_setup);

index add46b06be86..7c1855afd723 100644
@@ -1107,15 +1107,6 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 		file_end_write(file);
 	}
 
-	/*
-	 * Special case handling for sync iocbs:
-	 *  - events go directly into the iocb for fast handling
-	 *  - the sync task with the iocb in its stack holds the single iocb
-	 *    ref, no other paths have a way to get another ref
-	 *  - the sync task helpfully left a reference to itself in the iocb
-	 */
-	BUG_ON(is_sync_kiocb(kiocb));
-
 	if (iocb->ki_list.next) {
 		unsigned long flags;
 

index 7c1855afd723..18507743757a 100644
@@ -553,13 +553,12 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 	struct kioctx *ctx = req->ki_ctx;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ctx->ctx_lock, flags);
-
-	if (!req->ki_list.next)
-		list_add(&req->ki_list, &ctx->active_reqs);
+	if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
+		return;
 
+	spin_lock_irqsave(&ctx->ctx_lock, flags);
+	list_add_tail(&req->ki_list, &ctx->active_reqs);
 	req->ki_cancel = cancel;
-
 	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);

@@ -1039,7 +1038,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 		goto out_put;
 
 	percpu_ref_get(&ctx->reqs);
-
+	INIT_LIST_HEAD(&req->ki_list);
 	req->ki_ctx = ctx;
 	return req;
 out_put:

@@ -1107,7 +1106,7 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 		file_end_write(file);
 	}
 
-	if (iocb->ki_list.next) {
+	if (!list_empty_careful(&iocb->ki_list)) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&ctx->ctx_lock, flags);

index 18507743757a..d7be32cdd1db 100644
@@ -1515,16 +1515,17 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 		return ret;
 	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret) {
-		req->ki_flags |= IOCB_WRITE;
-		file_start_write(file);
-		ret = aio_ret(req, call_write_iter(file, req, &iter));
 		/*
 		 * We release freeze protection in aio_complete().  Fool lockdep
 		 * by telling it the lock got released so that it doesn't
 		 * complain about held lock when we return to userspace.
 		 */
-		if (S_ISREG(file_inode(file)->i_mode))
+		if (S_ISREG(file_inode(file)->i_mode)) {
+			__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
 			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		}
+		req->ki_flags |= IOCB_WRITE;
+		ret = aio_ret(req, call_write_iter(file, req, &iter));
 	}
 	kfree(iovec);
 	return ret;

@@ -1599,7 +1600,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	req->ki_user_iocb = user_iocb;
 	req->ki_user_data = iocb->aio_data;
 
-	get_file(file);
 	switch (iocb->aio_lio_opcode) {
 	case IOCB_CMD_PREAD:
 		ret = aio_read(&req->common, iocb, false, compat);

@@ -1618,7 +1618,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		ret = -EINVAL;
 		break;
 	}
-	fput(file);
 
 	if (ret && ret != -EIOCBQUEUED)
 		goto out_put_req;

index d7be32cdd1db..d4dd002712c8 100644
@@ -170,7 +170,9 @@ struct kioctx {
 #define KIOCB_CANCELLED		((void *) (~0ULL))
 
 struct aio_kiocb {
-	struct kiocb		common;
+	union {
+		struct kiocb		rw;
+	};
 
 	struct kioctx		*ki_ctx;
 	kiocb_cancel_fn		*ki_cancel;

@@ -549,7 +551,7 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 
 void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 {
-	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common);
+	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
 	struct kioctx *ctx = req->ki_ctx;
 	unsigned long flags;
 

@@ -581,7 +583,7 @@ static int kiocb_cancel(struct aio_kiocb *kiocb)
 		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
 	} while (cancel != old);
 
-	return cancel(&kiocb->common);
+	return cancel(&kiocb->rw);
 }
 
 /*

@@ -1046,15 +1048,6 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 	return NULL;
 }
 
-static void kiocb_free(struct aio_kiocb *req)
-{
-	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);
-}
-
 static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 {
 	struct aio_ring __user *ring  = (void __user *)ctx_id;

@@ -1085,27 +1078,14 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
-static void aio_complete(struct kiocb *kiocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb, 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;
 	unsigned tail, pos, head;
 	unsigned long	flags;
 
-	if (kiocb->ki_flags & IOCB_WRITE) {
-		struct file *file = kiocb->ki_filp;
-
-		/*
-		 * Tell lockdep we inherited freeze protection from submission
-		 * thread.
-		 */
-		if (S_ISREG(file_inode(file)->i_mode))
-			__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
-		file_end_write(file);
-	}
-
 	if (!list_empty_careful(&iocb->ki_list)) {
 		unsigned long flags;
 

@@ -1167,11 +1147,12 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 	 * eventfd. The eventfd_signal() function is safe to be called
 	 * from IRQ context.
 	 */
-	if (iocb->ki_eventfd != NULL)
+	if (iocb->ki_eventfd) {
 		eventfd_signal(iocb->ki_eventfd, 1);
+		eventfd_ctx_put(iocb->ki_eventfd);
+	}
 
-	/* everything turned out well, dispose of the aiocb. */
-	kiocb_free(iocb);
+	kmem_cache_free(kiocb_cachep, iocb);
 
 	/*
 	 * We have to order our ring_info tail store above and test

@@ -1434,6 +1415,45 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	return -EINVAL;
 }
 
+static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);
+
+	if (kiocb->ki_flags & IOCB_WRITE) {
+		struct inode *inode = file_inode(kiocb->ki_filp);
+
+		/*
+		 * Tell lockdep we inherited freeze protection from submission
+		 * thread.
+		 */
+		if (S_ISREG(inode->i_mode))
+			__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+		file_end_write(kiocb->ki_filp);
+	}
+
+	fput(kiocb->ki_filp);
+	aio_complete(iocb, res, res2);
+}
+
+static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
+{
+	int ret;
+
+	req->ki_filp = fget(iocb->aio_fildes);
+	if (unlikely(!req->ki_filp))
+		return -EBADF;
+	req->ki_complete = aio_complete_rw;
+	req->ki_pos = iocb->aio_offset;
+	req->ki_flags = iocb_flags(req->ki_filp);
+	if (iocb->aio_flags & IOCB_FLAG_RESFD)
+		req->ki_flags |= IOCB_EVENTFD;
+	req->ki_hint = file_write_hint(req->ki_filp);
+	ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
+	if (unlikely(ret))
+		fput(req->ki_filp);
+	return ret;
+}
+
 static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
 		bool vectored, bool compat, struct iov_iter *iter)
 {

@@ -1453,7 +1473,7 @@ static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
 	return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
 }
 
-static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
+static inline ssize_t aio_rw_ret(struct kiocb *req, ssize_t ret)
 {
 	switch (ret) {
 	case -EIOCBQUEUED:

@@ -1469,7 +1489,7 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
 		ret = -EINTR;
 		/*FALLTHRU*/
 	default:
-		aio_complete(req, ret, 0);
+		aio_complete_rw(req, ret, 0);
 		return 0;
 	}
 }

@@ -1477,57 +1497,77 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
 static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
 		bool compat)
 {
-	struct file *file = req->ki_filp;
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
+	struct file *file;
 	ssize_t ret;
 
+	ret = aio_prep_rw(req, iocb);
+	if (ret)
+		return ret;
+	file = req->ki_filp;
+
+	ret = -EBADF;
 	if (unlikely(!(file->f_mode & FMODE_READ)))
-		return -EBADF;
+		goto out_fput;
+	ret = -EINVAL;
 	if (unlikely(!file->f_op->read_iter))
-		return -EINVAL;
+		goto out_fput;
 
 	ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
 	if (ret)
-		return ret;
+		goto out_fput;
 	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret)
-		ret = aio_ret(req, call_read_iter(file, req, &iter));
+		ret = aio_rw_ret(req, call_read_iter(file, req, &iter));
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret && ret != -EIOCBQUEUED))
+		fput(file);
 	return ret;
 }
 
 static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 		bool compat)
 {
-	struct file *file = req->ki_filp;
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
+	struct file *file;
 	ssize_t ret;
 
+	ret = aio_prep_rw(req, iocb);
+	if (ret)
+		return ret;
+	file = req->ki_filp;
+
+	ret = -EBADF;
 	if (unlikely(!(file->f_mode & FMODE_WRITE)))
-		return -EBADF;
+		goto out_fput;
+	ret = -EINVAL;
 	if (unlikely(!file->f_op->write_iter))
-		return -EINVAL;
+		goto out_fput;
 
 	ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
 	if (ret)
-		return ret;
+		goto out_fput;
 	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret) {
 		/*
-		 * We release freeze protection in aio_complete().  Fool lockdep
-		 * by telling it the lock got released so that it doesn't
-		 * complain about held lock when we return to userspace.
+		 * We release freeze protection in aio_complete_rw().  Fool
+		 * lockdep by telling it the lock got released so that it
+		 * doesn't complain about held lock when we return to userspace.
 		 */
 		if (S_ISREG(file_inode(file)->i_mode)) {
 			__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
 			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 		}
 		req->ki_flags |= IOCB_WRITE;
-		ret = aio_ret(req, call_write_iter(file, req, &iter));
+		ret = aio_rw_ret(req, call_write_iter(file, req, &iter));
 	}
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret && ret != -EIOCBQUEUED))
+		fput(file);
 	return ret;
 }
 

@@ -1535,7 +1575,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 struct iocb *iocb, bool compat)
 {
 	struct aio_kiocb *req;
-	struct file *file;
 	ssize_t ret;
 
 	/* enforce forwards compatibility on users */

@@ -1558,16 +1597,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	if (unlikely(!req))
 		return -EAGAIN;
 
-	req->common.ki_filp = file = 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 = iocb_flags(req->common.ki_filp);
-	req->common.ki_hint = file_write_hint(file);
-
 	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
 		/*
 		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an

@@ -1581,14 +1610,6 @@ 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 = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
-	if (unlikely(ret)) {
-		pr_debug("EINVAL: aio_rw_flags\n");
-		goto out_put_req;
 	}
 
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);

@@ -1602,16 +1623,16 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 
 	switch (iocb->aio_lio_opcode) {
 	case IOCB_CMD_PREAD:
-		ret = aio_read(&req->common, iocb, false, compat);
+		ret = aio_read(&req->rw, iocb, false, compat);
 		break;
 	case IOCB_CMD_PWRITE:
-		ret = aio_write(&req->common, iocb, false, compat);
+		ret = aio_write(&req->rw, iocb, false, compat);
 		break;
 	case IOCB_CMD_PREADV:
-		ret = aio_read(&req->common, iocb, true, compat);
+		ret = aio_read(&req->rw, iocb, true, compat);
 		break;
 	case IOCB_CMD_PWRITEV:
-		ret = aio_write(&req->common, iocb, true, compat);
+		ret = aio_write(&req->rw, iocb, true, compat);
 		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);

@@ -1625,7 +1646,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 out_put_req:
 	put_reqs_available(ctx, 1);
 	percpu_ref_put(&ctx->reqs);
-	kiocb_free(req);
+	if (req->ki_eventfd)
+		eventfd_ctx_put(req->ki_eventfd);
+	kmem_cache_free(kiocb_cachep, req);
 	return ret;
 }
 

index d4dd002712c8..de56496ba86c 100644
@@ -156,6 +156,12 @@ struct kioctx {
 	unsigned		id;
 };
 
+struct fsync_iocb {
+	struct work_struct	work;
+	struct file		*file;
+	bool			datasync;
+};
+
 /*
  * 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

@@ -172,6 +178,7 @@ struct kioctx {
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
+		struct fsync_iocb	fsync;
 	};
 
 	struct kioctx		*ki_ctx;

@@ -1571,6 +1578,36 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 	return ret;
 }
 
+static void aio_fsync_work(struct work_struct *work)
+{
+	struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
+	int ret;
+
+	ret = vfs_fsync(req->file, req->datasync);
+	fput(req->file);
+	aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+}
+
+static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
+{
+	if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
+			iocb->aio_rw_flags))
+		return -EINVAL;
+
+	req->file = fget(iocb->aio_fildes);
+	if (unlikely(!req->file))
+		return -EBADF;
+	if (unlikely(!req->file->f_op->fsync)) {
+		fput(req->file);
+		return -EINVAL;
+	}
+
+	req->datasync = datasync;
+	INIT_WORK(&req->work, aio_fsync_work);
+	schedule_work(&req->work);
+	return -EIOCBQUEUED;
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 struct iocb *iocb, bool compat)
 {

@@ -1634,6 +1671,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	case IOCB_CMD_PWRITEV:
 		ret = aio_write(&req->rw, iocb, true, compat);
 		break;
+	case IOCB_CMD_FSYNC:
+		ret = aio_fsync(&req->fsync, iocb, false);
+		break;
+	case IOCB_CMD_FDSYNC:
+		ret = aio_fsync(&req->fsync, iocb, true);
+		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
 		ret = -EINVAL;

140 lines not on this page · raw message

index f188eab10570..fdd068f192c1 100644
@@ -310,6 +310,7 @@ extern int put_compat_rusage(const struct rusage *,
 			     struct compat_rusage __user *);
 
 struct compat_siginfo;
+struct __compat_aio_sigset;
 
 struct compat_dirent {
 	u32		d_ino;

@@ -528,6 +529,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id,
 					compat_long_t nr,
 					struct io_event __user *events,
 					struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id,
+					compat_long_t min_nr,
+					compat_long_t nr,
+					struct io_event __user *events,
+					struct compat_timespec __user *timeout,
+					const struct __compat_aio_sigset __user *usig);
 
 /* fs/cookies.c */
 asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);

index b961184f597a..c40cf5ec24c9 100644
@@ -264,6 +264,12 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id,
 				long nr,
 				struct io_event __user *events,
 				struct timespec __user *timeout);
+asmlinkage long sys_io_pgetevents(aio_context_t ctx_id,
+				long min_nr,
+				long nr,
+				struct io_event __user *events,
+				struct timespec __user *timeout,
+				const struct __aio_sigset *sig);
 
 /* fs/xattr.c */
 asmlinkage long sys_setxattr(const char __user *path, const char __user *name,

index 8bcb186c6f67..42990676a55e 100644
@@ -732,9 +732,11 @@ __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 #define __NR_statx 291
 __SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 
 #undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls 293
 
 /*
  * 32 bit systems traditionally used different

index a04adbc70ddf..2c0a3415beee 100644
@@ -29,6 +29,7 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
+#include <linux/signal.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;

@@ -108,5 +109,10 @@ struct iocb {
 #undef IFBIG
 #undef IFLITTLE
 
+struct __aio_sigset {
+	sigset_t __user	*sigmask;
+	size_t		sigsetsize;
+};
+
 #endif /* __LINUX__AIO_ABI_H */
 

index 6cafc008f6db..7571cf9d7424 100644
@@ -33,7 +33,9 @@ COND_SYSCALL(io_submit);
 COND_SYSCALL_COMPAT(io_submit);
 COND_SYSCALL(io_cancel);
 COND_SYSCALL(io_getevents);
+COND_SYSCALL(io_pgetevents);
 COND_SYSCALL_COMPAT(io_getevents);
+COND_SYSCALL_COMPAT(io_pgetevents);
 
 /* fs/xattr.c */