@@ -675,10 +675,11 @@ EXPORT_SYMBOL(iov_shorten);
static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
loff_t *ppos, int type, int flags)
{
+ struct inode *inode = file_inode(filp);
struct kiocb kiocb;
ssize_t ret;
- if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC))
+ if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_WRITE_LIFE_MASK))
return -EOPNOTSUPP;
init_sync_kiocb(&kiocb, filp);
@@ -688,6 +689,15 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
kiocb.ki_flags |= IOCB_DSYNC;
if (flags & RWF_SYNC)
kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+ if ((flags & RWF_WRITE_LIFE_MASK) ||
+ mask_to_write_hint(inode->i_flags, S_WRITE_LIFE_SHIFT)) {
+ enum write_hint hint;
+
+ hint = mask_to_write_hint(flags, RWF_WRITE_LIFE_SHIFT);
+
+ inode_set_write_hint(inode, hint);
+ kiocb.ki_flags |= write_hint_to_mask(hint, IOCB_WRITE_LIFE_SHIFT);
+ }
kiocb.ki_pos = *ppos;
if (type == READ)
@@ -269,6 +269,12 @@ struct writeback_control;
#define IOCB_SYNC (1 << 5)
#define IOCB_WRITE (1 << 6)
+/*
+ * Steal 3 bits for stream information, this allows 8 valid streams
+ */
+#define IOCB_WRITE_LIFE_SHIFT 7
+#define IOCB_WRITE_LIFE_MASK (BIT(7) | BIT(8) | BIT(9))
+
struct kiocb {
struct file *ki_filp;
loff_t ki_pos;
@@ -292,6 +298,12 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
};
}
+static inline int iocb_write_hint(const struct kiocb *iocb)
+{
+ return (iocb->ki_flags & IOCB_WRITE_LIFE_MASK) >>
+ IOCB_WRITE_LIFE_SHIFT;
+}
+
/*
* "descriptor" for what we're up to with a read.
* This allows us to use the same read code yet
@@ -374,4 +374,14 @@ enum write_hint {
#define RWF_DSYNC 0x00000002 /* per-IO O_DSYNC */
#define RWF_SYNC 0x00000004 /* per-IO O_SYNC */
+/*
+ * Data life time write flags, steal 3 bits for that
+ */
+#define RWF_WRITE_LIFE_SHIFT 4
+#define RWF_WRITE_LIFE_MASK 0x00000070 /* 3 bits of write hints */
+#define RWF_WRITE_LIFE_SHORT (WRITE_HINT_SHORT << RWF_WRITE_LIFE_SHIFT)
+#define RWF_WRITE_LIFE_MEDIUM (WRITE_HINT_MEDIUM << RWF_WRITE_LIFE_SHIFT)
+#define RWF_WRITE_LIFE_LONG (WRITE_HINT_LONG << RWF_WRITE_LIFE_SHIFT)
+#define RWF_WRITE_LIFE_EXTREME (WRITE_HINT_EXTREME << RWF_WRITE_LIFE_SHIFT)
+
#endif /* _UAPI_LINUX_FS_H */
Add four flags for the pwritev2(2) system call, allowing an application to give the kernel a hint about what on-media life times can be expected from a given write. The intent is for these values to be relative to each other, no absolute meaning should be attached to these flag names. Set aside 3 bits in the iocb flags structure to carry this information over from the pwritev2 RWF_WRITE_LIFE_* flags. Signed-off-by: Jens Axboe <axboe@kernel.dk> --- fs/read_write.c | 12 +++++++++++- include/linux/fs.h | 12 ++++++++++++ include/uapi/linux/fs.h | 10 ++++++++++ 3 files changed, 33 insertions(+), 1 deletion(-)