summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorJens Axboe <axboe@kernel.dk>2017-06-27 11:47:04 -0600
committerJens Axboe <axboe@kernel.dk>2017-06-27 12:05:22 -0600
commitc75b1d9421f80f4143e389d2d50ddfc8a28c8c35 (patch)
tree6fe665d5e9f8cfab50b764d418e732617a5d5129 /fs
parent12e9a6d62236dacb87a6b2dd84dd9c29bb5be1de (diff)
downloadop-kernel-dev-c75b1d9421f80f4143e389d2d50ddfc8a28c8c35.zip
op-kernel-dev-c75b1d9421f80f4143e389d2d50ddfc8a28c8c35.tar.gz
fs: add fcntl() interface for setting/getting write life time hints
Define a set of write life time hints: RWH_WRITE_LIFE_NOT_SET No hint information set RWH_WRITE_LIFE_NONE No hints about write life time RWH_WRITE_LIFE_SHORT Data written has a short life time RWH_WRITE_LIFE_MEDIUM Data written has a medium life time RWH_WRITE_LIFE_LONG Data written has a long life time RWH_WRITE_LIFE_EXTREME Data written has an extremely long life time The intent is for these values to be relative to each other, no absolute meaning should be attached to these flag names. Add an fcntl interface for querying these flags, and also for setting them as well: F_GET_RW_HINT Returns the read/write hint set on the underlying inode. F_SET_RW_HINT Set one of the above write hints on the underlying inode. F_GET_FILE_RW_HINT Returns the read/write hint set on the file descriptor. F_SET_FILE_RW_HINT Set one of the above write hints on the file descriptor. The user passes in a 64-bit pointer to get/set these values, and the interface returns 0/-1 on success/error. Sample program testing/implementing basic setting/getting of write hints is below. Add support for storing the write life time hint in the inode flags and in struct file as well, and pass them to the kiocb flags. If both a file and its corresponding inode has a write hint, then we use the one in the file, if available. The file hint can be used for sync/direct IO, for buffered writeback only the inode hint is available. This is in preparation for utilizing these hints in the block layer, to guide on-media data placement. /* * writehint.c: get or set an inode write hint */ #include <stdio.h> #include <fcntl.h> #include <stdlib.h> #include <unistd.h> #include <stdbool.h> #include <inttypes.h> #ifndef F_GET_RW_HINT #define F_LINUX_SPECIFIC_BASE 1024 #define F_GET_RW_HINT (F_LINUX_SPECIFIC_BASE + 11) #define F_SET_RW_HINT (F_LINUX_SPECIFIC_BASE + 12) #endif static char *str[] = { "RWF_WRITE_LIFE_NOT_SET", "RWH_WRITE_LIFE_NONE", "RWH_WRITE_LIFE_SHORT", "RWH_WRITE_LIFE_MEDIUM", "RWH_WRITE_LIFE_LONG", "RWH_WRITE_LIFE_EXTREME" }; int main(int argc, char *argv[]) { uint64_t hint; int fd, ret; if (argc < 2) { fprintf(stderr, "%s: file <hint>\n", argv[0]); return 1; } fd = open(argv[1], O_RDONLY); if (fd < 0) { perror("open"); return 2; } if (argc > 2) { hint = atoi(argv[2]); ret = fcntl(fd, F_SET_RW_HINT, &hint); if (ret < 0) { perror("fcntl: F_SET_RW_HINT"); return 4; } } ret = fcntl(fd, F_GET_RW_HINT, &hint); if (ret < 0) { perror("fcntl: F_GET_RW_HINT"); return 3; } printf("%s: hint %s\n", argv[1], str[hint]); close(fd); return 0; } Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs')
-rw-r--r--fs/fcntl.c62
-rw-r--r--fs/inode.c1
-rw-r--r--fs/open.c1
3 files changed, 64 insertions, 0 deletions
diff --git a/fs/fcntl.c b/fs/fcntl.c
index f4e7267..67bdc6e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -243,6 +243,62 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
}
#endif
+static bool rw_hint_valid(enum rw_hint hint)
+{
+ switch (hint) {
+ case RWF_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_rw_hint(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct inode *inode = file_inode(file);
+ u64 *argp = (u64 __user *)arg;
+ enum rw_hint hint;
+
+ switch (cmd) {
+ case F_GET_FILE_RW_HINT:
+ if (put_user(file_write_hint(file), argp))
+ return -EFAULT;
+ return 0;
+ case F_SET_FILE_RW_HINT:
+ if (get_user(hint, argp))
+ return -EFAULT;
+ if (!rw_hint_valid(hint))
+ return -EINVAL;
+
+ spin_lock(&file->f_lock);
+ file->f_write_hint = hint;
+ spin_unlock(&file->f_lock);
+ return 0;
+ case F_GET_RW_HINT:
+ if (put_user(inode->i_write_hint, argp))
+ return -EFAULT;
+ return 0;
+ case F_SET_RW_HINT:
+ if (get_user(hint, argp))
+ return -EFAULT;
+ if (!rw_hint_valid(hint))
+ return -EINVAL;
+
+ inode_lock(inode);
+ inode->i_write_hint = hint;
+ inode_unlock(inode);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
struct file *filp)
{
@@ -337,6 +393,12 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
case F_GET_SEALS:
err = shmem_fcntl(filp, cmd, arg);
break;
+ case F_GET_RW_HINT:
+ case F_SET_RW_HINT:
+ case F_GET_FILE_RW_HINT:
+ case F_SET_FILE_RW_HINT:
+ err = fcntl_rw_hint(filp, cmd, arg);
+ break;
default:
break;
}
diff --git a/fs/inode.c b/fs/inode.c
index db59147..f0e5fc7 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -146,6 +146,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
i_gid_write(inode, 0);
atomic_set(&inode->i_writecount, 0);
inode->i_size = 0;
+ inode->i_write_hint = WRITE_LIFE_NOT_SET;
inode->i_blocks = 0;
inode->i_bytes = 0;
inode->i_generation = 0;
diff --git a/fs/open.c b/fs/open.c
index cd0c5be..3fe0c4a 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -759,6 +759,7 @@ static int do_dentry_open(struct file *f,
likely(f->f_op->write || f->f_op->write_iter))
f->f_mode |= FMODE_CAN_WRITE;
+ f->f_write_hint = WRITE_LIFE_NOT_SET;
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
OpenPOWER on IntegriCloud