Merge branch 'work.aio' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull aio iopriority support from Al Viro:
 "The rest of aio stuff for this cycle - Adam's aio ioprio series"

* 'work.aio' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  fs: aio ioprio use ioprio_check_cap ret val
  fs: aio ioprio add explicit block layer dependence
  fs: iomap dio set bio prio from kiocb prio
  fs: blkdev set bio prio from kiocb prio
  fs: Add aio iopriority support
  fs: Convert kiocb rw_hint from enum to u16
  block: add ioprio_check_cap function

Author: torvalds

block/ioprio.c

@@ -61,15 +61,10 @@ int set_task_ioprio(struct task_struct *task, int ioprio)
 }
 EXPORT_SYMBOL_GPL(set_task_ioprio);
 
-SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
+int ioprio_check_cap(int ioprio)
 {
 	int class = IOPRIO_PRIO_CLASS(ioprio);
 	int data = IOPRIO_PRIO_DATA(ioprio);
-	struct task_struct *p, *g;
-	struct user_struct *user;
-	struct pid *pgrp;
-	kuid_t uid;
-	int ret;
 
 	switch (class) {
 		case IOPRIO_CLASS_RT:
@@ -92,6 +87,21 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 			return -EINVAL;
 	}
 
+	return 0;
+}
+
+SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
+{
+	struct task_struct *p, *g;
+	struct user_struct *user;
+	struct pid *pgrp;
+	kuid_t uid;
+	int ret;
+
+	ret = ioprio_check_cap(ioprio);
+	if (ret)
+		return ret;
+
 	ret = -ESRCH;
 	rcu_read_lock();
 	switch (which) {

drivers/block/loop.c

@@ -76,6 +76,8 @@
 #include <linux/miscdevice.h>
 #include <linux/falloc.h>
 #include <linux/uio.h>
+#include <linux/ioprio.h>
+
 #include "loop.h"
 
 #include <linux/uaccess.h>
@@ -559,6 +561,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	cmd->iocb.ki_filp = file;
 	cmd->iocb.ki_complete = lo_rw_aio_complete;
 	cmd->iocb.ki_flags = IOCB_DIRECT;
+	cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
 	if (cmd->css)
 		kthread_associate_blkcg(cmd->css);
 

fs/aio.c

@@ -1434,7 +1434,23 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
 	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);
+	req->ki_hint = ki_hint_validate(file_write_hint(req->ki_filp));
+	if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
+		/*
+		 * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then
+		 * aio_reqprio is interpreted as an I/O scheduling
+		 * class and priority.
+		 */
+		ret = ioprio_check_cap(iocb->aio_reqprio);
+		if (ret) {
+			pr_debug("aio ioprio check cap error: %d\n", ret);
+			return ret;
+		}
+
+		req->ki_ioprio = iocb->aio_reqprio;
+	} else
+		req->ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+
 	ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
 	if (unlikely(ret))
 		fput(req->ki_filp);

fs/block_dev.c

@@ -216,6 +216,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	bio.bi_write_hint = iocb->ki_hint;
 	bio.bi_private = current;
 	bio.bi_end_io = blkdev_bio_end_io_simple;
+	bio.bi_ioprio = iocb->ki_ioprio;
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
 	if (unlikely(ret))
@@ -355,6 +356,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 		bio->bi_write_hint = iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = blkdev_bio_end_io;
+		bio->bi_ioprio = iocb->ki_ioprio;
 
 		ret = bio_iov_iter_get_pages(bio, iter);
 		if (unlikely(ret)) {

fs/iomap.c

@@ -1046,6 +1046,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		bio_set_dev(bio, iomap->bdev);
 		bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
 		bio->bi_write_hint = dio->iocb->ki_hint;
+		bio->bi_ioprio = dio->iocb->ki_ioprio;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
 

include/linux/fs.h

@@ -36,6 +36,7 @@
 #include <linux/delayed_call.h>
 #include <linux/uuid.h>
 #include <linux/errseq.h>
+#include <linux/ioprio.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -299,7 +300,8 @@ struct kiocb {
 	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
 	void			*private;
 	int			ki_flags;
-	enum rw_hint		ki_hint;
+	u16			ki_hint;
+	u16			ki_ioprio; /* See linux/ioprio.h */
 } __randomize_layout;
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -1934,12 +1936,22 @@ static inline enum rw_hint file_write_hint(struct file *file)
 
 static inline int iocb_flags(struct file *file);
 
+static inline u16 ki_hint_validate(enum rw_hint hint)
+{
+	typeof(((struct kiocb *)0)->ki_hint) max_hint = -1;
+
+	if (hint <= max_hint)
+		return hint;
+	return 0;
+}
+
 static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 {
 	*kiocb = (struct kiocb) {
 		.ki_filp = filp,
 		.ki_flags = iocb_flags(filp),
-		.ki_hint = file_write_hint(filp),
+		.ki_hint = ki_hint_validate(file_write_hint(filp)),
+		.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0),
 	};
 }
 

include/linux/ioprio.h

@@ -77,4 +77,13 @@ extern int ioprio_best(unsigned short aprio, unsigned short bprio);
 
 extern int set_task_ioprio(struct task_struct *task, int ioprio);
 
+#ifdef CONFIG_BLOCK
+extern int ioprio_check_cap(int ioprio);
+#else
+static inline int ioprio_check_cap(int ioprio)
+{
+	return -ENOTBLK;
+}
+#endif /* CONFIG_BLOCK */
+
 #endif

include/uapi/linux/aio_abi.h

@@ -53,6 +53,7 @@ enum {
  *                   is valid.
  */
 #define IOCB_FLAG_RESFD		(1 << 0)
+#define IOCB_FLAG_IOPRIO	(1 << 1)
 
 /* read() from /dev/aio returns these structures. */
 struct io_event {