[PATCH v5 0/5] AIO add per-command iopriority

From: Adam Manzanares <redacted>

This is the per-I/O equivalent of the ioprio_set system call.
See the following link for performance implications on a SATA HDD:
https://lkml.org/lkml/2016/12/6/495

First patch factors ioprio_check_cap function out of ioprio_set system call to
also be used by the aio ioprio interface.

Second patch converts kiocb ki_hint field to a u16 to avoid kiocb bloat.

Third patch passes ioprio hint from aio iocb to kiocb and inititalizes kiocb
ioprio value appropriately when it is not explicitly set.

Fourth patch enables the feature for blkdev.

Fifth patch enables the feature for iomap direct IO

Note: this work is based on top of linux-vfs/for-next

v2: merge patches
    use IOCB_FLAG_IOPRIO
    validate intended use with IOCB_IOPRIO
    add linux-api and linux-block to cc

v3: add ioprio_check_cap function
    convert kiocb ki_hint to u16
    use ioprio_check_cap when adding ioprio to kiocb in aio.c

v4: handle IOCB_IOPRIO in aio_prep_rw
    note patch 3 depends on patch 1 in commit msg

v5: rename ki_hint_valid -> ki_hint_validate 
	remove ki_hint_validate comment and whitespace
	remove IOCB_IOPRIO flag
	initialize kiocb to have no priority 

Adam Manzanares (5):
  block: add ioprio_check_cap function
  fs: Convert kiocb rw_hint from enum to u16
  fs: Add aio iopriority support
  fs: blkdev set bio prio from kiocb prio
  fs: iomap dio set bio prio from kiocb prio

 block/ioprio.c               | 22 ++++++++++++++++------
 drivers/block/loop.c         |  3 +++
 fs/aio.c                     | 16 ++++++++++++++++
 fs/block_dev.c               |  1 +
 fs/iomap.c                   |  1 +
 include/linux/fs.h           | 16 ++++++++++++++--
 include/linux/ioprio.h       |  2 ++
 include/uapi/linux/aio_abi.h |  1 +
 8 files changed, 54 insertions(+), 8 deletions(-)

-- 
2.15.1

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

From: Adam Manzanares <redacted>

Aio per command iopriority support introduces a second interface between
userland and the kernel capable of passing iopriority. The aio interface also
needs the ability to verify that the submitting context has sufficient
priviledges to submit IOPRIO_RT commands. This patch creates the
ioprio_check_cap function to be used by the ioprio_set system call and also by
the aio interface.

Signed-off-by: Adam Manzanares <redacted>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 block/ioprio.c         | 22 ++++++++++++++++------
 include/linux/ioprio.h |  2 ++
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/block/ioprio.c b/block/ioprio.c
index 6f5d0b6625e3..f9821080c92c 100644
--- a/block/ioprio.c
+++ b/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) {

diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index 627efac73e6d..4a28cec49ec3 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h

@@ -77,4 +77,6 @@ extern int ioprio_best(unsigned short aprio, unsigned short bprio);
 
 extern int set_task_ioprio(struct task_struct *task, int ioprio);
 
+extern int ioprio_check_cap(int ioprio);
+
 #endif

-- 
2.15.1

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

From: Adam Manzanares <redacted>

This is the per-I/O equivalent of the ioprio_set system call.

When IOCB_FLAG_IOPRIO is set on the iocb aio_flags field, then we set the
newly added kiocb ki_ioprio field to the value in the iocb aio_reqprio field.

We set the blkdev bio iopriority unconditionally, so we need to guarantee the 
kiocb is initialized properly. Added changes to the loopback driver and 
init_sync_kiocb to achieve this.

This patch depends on block: add ioprio_check_cap function.

Signed-off-by: Adam Manzanares <redacted>
---
 drivers/block/loop.c         |  3 +++
 fs/aio.c                     | 16 ++++++++++++++++
 include/linux/fs.h           |  3 +++
 include/uapi/linux/aio_abi.h |  1 +
 4 files changed, 23 insertions(+)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 5d4e31655d96..dd98dfd97f5e 100644
--- a/drivers/block/loop.c
+++ b/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);
 

diff --git a/fs/aio.c b/fs/aio.c
index f3eae5d5771b..44b4572be524 100644
--- a/fs/aio.c
+++ b/fs/aio.c

@@ -1451,6 +1451,22 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
 	if (iocb->aio_flags & IOCB_FLAG_RESFD)
 		req->ki_flags |= IOCB_EVENTFD;
 	req->ki_hint = 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\n");
+			return -EINVAL;
+		}
+
+		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);

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 50de40dbbb85..73b749ed3ea1 100644
--- a/include/linux/fs.h
+++ b/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>

@@ -302,6 +303,7 @@ struct kiocb {
 	void			*private;
 	int			ki_flags;
 	u16			ki_hint;
+	u16			ki_ioprio; /* See linux/ioprio.h */
 } __randomize_layout;
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)

@@ -1942,6 +1944,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 		.ki_filp = filp,
 		.ki_flags = iocb_flags(filp),
 		.ki_hint = ki_hint_validate(file_write_hint(filp)),
+		.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0),
 	};
 }
 

diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index 2c0a3415beee..d4e768d55d14 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h

@@ -55,6 +55,7 @@ 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 {

-- 
2.15.1

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

From: Adam Manzanares <redacted>

In order to avoid kiocb bloat for per command iopriority support, rw_hint
is converted from enum to a u16. Added a guard around ki_hint assigment.

Signed-off-by: Adam Manzanares <redacted>
---
 include/linux/fs.h | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7f07977bdfd7..50de40dbbb85 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h

@@ -284,6 +284,8 @@ enum rw_hint {
 	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
 };
 
+#define MAX_KI_HINT		((1 << 16) - 1) /* ki_hint type is u16 */
+
 #define IOCB_EVENTFD		(1 << 0)
 #define IOCB_APPEND		(1 << 1)
 #define IOCB_DIRECT		(1 << 2)

@@ -299,7 +301,7 @@ 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;
 } __randomize_layout;
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)

@@ -1927,12 +1929,19 @@ 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)
+{
+	if (hint > MAX_KI_HINT)
+		return 0;
+	return hint;
+}
+
 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)),
 	};
 }
 

-- 
2.15.1

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

From: Adam Manzanares <redacted>

Now that kiocb has an ioprio field copy this over to the bio when it is
created from the kiocb.

Signed-off-by: Adam Manzanares <redacted>
---
 fs/block_dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7ec920e27065..da1e94d2bb75 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c

@@ -355,6 +355,7 @@ __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)) {

-- 
2.15.1

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

From: Adam Manzanares <redacted>

Now that kiocb has an ioprio field copy this over to the bio when it is
created from the kiocb during direct IO.

Signed-off-by: Adam Manzanares <redacted>
---
 fs/iomap.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/iomap.c b/fs/iomap.c
index afd163586aa0..65aae194aeca 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c

@@ -919,6 +919,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		bio->bi_iter.bi_sector =
 			(iomap->addr + pos - iomap->offset) >> 9;
 		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;
 

-- 
2.15.1

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

On Mon, May 21, 2018 at 09:01:44AM -0700, adam.manzanares@wdc.com wrote:

From: Adam Manzanares <redacted>

In order to avoid kiocb bloat for per command iopriority support, rw_hint
is converted from enum to a u16. Added a guard around ki_hint assigment.

Signed-off-by: Adam Manzanares <redacted>

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>

Hi Adam,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on next-20180517]
[cannot apply to linus/master block/for-next v4.17-rc6 v4.17-rc5 v4.17-rc4 v4.17-rc6]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/adam-manzanares-wdc-com/AIO-add-per-command-iopriority/20180522-232203
config: x86_64-randconfig-s0-05230027 (attached as .config)
compiler: gcc-6 (Debian 6.4.0-9) 6.4.0 20171026
reproduce:
        # save the attached .config to linux build tree
        make ARCH=x86_64 

All errors (new ones prefixed by >>):

   fs/aio.o: In function `aio_prep_rw':

quoted

fs/aio.c:1460: undefined reference to `ioprio_check_cap'

vim +1460 fs/aio.c

  1440	
  1441	static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
  1442	{
  1443		int ret;
  1444	
  1445		req->ki_filp = fget(iocb->aio_fildes);
  1446		if (unlikely(!req->ki_filp))
  1447			return -EBADF;
  1448		req->ki_complete = aio_complete_rw;
  1449		req->ki_pos = iocb->aio_offset;
  1450		req->ki_flags = iocb_flags(req->ki_filp);
  1451		if (iocb->aio_flags & IOCB_FLAG_RESFD)
  1452			req->ki_flags |= IOCB_EVENTFD;
  1453		req->ki_hint = file_write_hint(req->ki_filp);
  1454		if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
  1455			/*
  1456			 * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then
  1457			 * aio_reqprio is interpreted as an I/O scheduling
  1458			 * class and priority.
  1459			 */

1460			ret = ioprio_check_cap(iocb->aio_reqprio);

  1461			if (ret) {
  1462				pr_debug("aio ioprio check cap error\n");
  1463				return -EINVAL;
  1464			}
  1465	
  1466			req->ki_ioprio = iocb->aio_reqprio;
  1467		} else
  1468			req->ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
  1469	
  1470		ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
  1471		if (unlikely(ret))
  1472			fput(req->ki_filp);
  1473		return ret;
  1474	}
  1475	

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation