[PATCH v7 3/3] io_uring: enable per-io hinting capability

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



With F_SET_RW_HINT fcntl, user can set a hint on the file inode, and
all the subsequent writes on the file pass that hint value down.
This can be limiting for large files (and for block device) as all the
writes can be tagged with only one lifetime hint value.
Concurrent writes (with different hint values) are hard to manage.
Per-IO hinting solves that problem.

Allow userspace to pass additional metadata in the SQE.
The type of passed metadata is expressed by a new field

	__u16 meta_type;

At this point one type META_TYPE_LIFETIME_HINT is supported.
With this type, user can pass lifetime hint values in the new field

	__u64 lifetime_val;

This accepts all lifetime hint values that are possible with
F_SET_RW_HINT fcntl.

The write handlers (io_prep_rw, io_write) send the hint value to
lower-layer using kiocb. This is good for upporting direct IO,
but not when kiocb is not available (e.g., buffered IO).

When per-io hints are not passed, the per-inode hint values are set in
the kiocb (as before). Otherwise, these take the precedence on per-inode
hints.

Signed-off-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
---
 fs/fcntl.c                    | 22 ----------------------
 include/linux/rw_hint.h       | 24 ++++++++++++++++++++++++
 include/uapi/linux/io_uring.h | 19 +++++++++++++++++++
 io_uring/rw.c                 | 25 ++++++++++++++++++++++++-
 4 files changed, 67 insertions(+), 23 deletions(-)

diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22dd9dcce7ec..a390a05f4ef8 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -334,28 +334,6 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 }
 #endif
 
-static bool rw_hint_valid(u64 hint)
-{
-	BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET);
-	BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE);
-	BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT);
-	BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM);
-	BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG);
-	BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME);
-
-	switch (hint) {
-	case RWH_WRITE_LIFE_NOT_SET:
-	case RWH_WRITE_LIFE_NONE:
-	case RWH_WRITE_LIFE_SHORT:
-	case RWH_WRITE_LIFE_MEDIUM:
-	case RWH_WRITE_LIFE_LONG:
-	case RWH_WRITE_LIFE_EXTREME:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
 			      unsigned long arg)
 {
diff --git a/include/linux/rw_hint.h b/include/linux/rw_hint.h
index 309ca72f2dfb..f4373a71ffed 100644
--- a/include/linux/rw_hint.h
+++ b/include/linux/rw_hint.h
@@ -21,4 +21,28 @@ enum rw_hint {
 static_assert(sizeof(enum rw_hint) == 1);
 #endif
 
+#define	WRITE_LIFE_INVALID	(RWH_WRITE_LIFE_EXTREME + 1)
+
+static inline bool rw_hint_valid(u64 hint)
+{
+	BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET);
+	BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE);
+	BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT);
+	BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM);
+	BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG);
+	BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME);
+
+	switch (hint) {
+	case RWH_WRITE_LIFE_NOT_SET:
+	case RWH_WRITE_LIFE_NONE:
+	case RWH_WRITE_LIFE_SHORT:
+	case RWH_WRITE_LIFE_MEDIUM:
+	case RWH_WRITE_LIFE_LONG:
+	case RWH_WRITE_LIFE_EXTREME:
+		return true;
+	default:
+		return false;
+	}
+}
+
 #endif /* _LINUX_RW_HINT_H */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 86cb385fe0b5..951e35226229 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -92,12 +92,23 @@ struct io_uring_sqe {
 			__u16	addr_len;
 			__u16	__pad3[1];
 		};
+		struct {
+			/* Bit field to express 16 meta types */
+			__u16	meta_type;
+			__u16	__pad4[1];
+		};
 	};
 	union {
 		struct {
 			__u64	addr3;
 			__u64	__pad2[1];
 		};
+		struct {
+			/* First meta type specific fields */
+			__u64	lifetime_val;
+			/* For future use */
+			__u64	__pad5[1];
+		};
 		__u64	optval;
 		/*
 		 * If the ring is initialized with IORING_SETUP_SQE128, then
@@ -107,6 +118,14 @@ struct io_uring_sqe {
 	};
 };
 
+enum io_uring_sqe_meta_type_bits {
+	META_TYPE_LIFETIME_HINT_BIT
+};
+
+/* this meta type covers write hint values supported by F_SET_RW_HINT fcntl */
+#define META_TYPE_LIFETIME_HINT	(1U << META_TYPE_LIFETIME_HINT_BIT)
+
+
 /*
  * If sqe->file_index is set to this for opcodes that instantiate a new
  * direct descriptor (like openat/openat2/accept), then io_uring will allocate
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 510123d3d837..bf45ee8904a4 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -269,6 +269,24 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		rw->kiocb.ki_ioprio = get_current_ioprio();
 	}
 	rw->kiocb.dio_complete = NULL;
+	if (ddir == ITER_SOURCE) {
+		u16 mtype = READ_ONCE(sqe->meta_type);
+
+		rw->kiocb.ki_write_hint = WRITE_LIFE_INVALID;
+		if (mtype) {
+			u64 lhint = READ_ONCE(sqe->lifetime_val);
+
+			if (READ_ONCE(sqe->__pad4[0]) ||
+			    READ_ONCE(sqe->__pad5[0]))
+				return -EINVAL;
+
+			if (mtype != META_TYPE_LIFETIME_HINT ||
+			    !rw_hint_valid(lhint))
+				return -EINVAL;
+
+			rw->kiocb.ki_write_hint = lhint;
+		}
+	}
 
 	rw->addr = READ_ONCE(sqe->addr);
 	rw->len = READ_ONCE(sqe->len);
@@ -1023,7 +1041,12 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(ret))
 		return ret;
 	req->cqe.res = iov_iter_count(&io->iter);
-	rw->kiocb.ki_write_hint = file_write_hint(rw->kiocb.ki_filp);
+	/*
+	 * Use per-file hint only if per-io hint is not set.
+	 * We need per-io hint to get precedence.
+	 */
+	if (rw->kiocb.ki_write_hint == WRITE_LIFE_INVALID)
+		rw->kiocb.ki_write_hint = file_write_hint(rw->kiocb.ki_filp);
 
 	if (force_nonblock) {
 		/* If the file doesn't support async, just async punt */
-- 
2.25.1





[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [NTFS 3]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [NTFS 3]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux