fs: add RWF_DONTCACHE iocb and FOP_DONTCACHE file_operations flag

If a file system supports uncached buffered IO, it may set FOP_DONTCACHE
and enable support for RWF_DONTCACHE.  If RWF_DONTCACHE is attempted
without the file system supporting it, it'll get errored with -EOPNOTSUPP.

Link: https://lkml.kernel.org/r/20241220154831.1086649-8-axboe@kernel.dk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Cc: Brian Foster <bfoster@redhat.com>
Cc: Chris Mason <clm@meta.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7e29433c5ecce2d495ace23a7c4570ac7ad9e2b0..6a838b5479a697e921cabc0cd0c1991a7c6165aa 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -322,6 +322,7 @@ struct readahead_control;
 #define IOCB_NOWAIT            (__force int) RWF_NOWAIT
 #define IOCB_APPEND            (__force int) RWF_APPEND
 #define IOCB_ATOMIC            (__force int) RWF_ATOMIC
+#define IOCB_DONTCACHE         (__force int) RWF_DONTCACHE
 
 /* non-RWF related bits - start at 16 */
 #define IOCB_EVENTFD           (1 << 16)
@@ -356,7 +357,8 @@ struct readahead_control;
        { IOCB_SYNC,            "SYNC" }, \
        { IOCB_NOWAIT,          "NOWAIT" }, \
        { IOCB_APPEND,          "APPEND" }, \
-       { IOCB_ATOMIC,          "ATOMIC"}, \
+       { IOCB_ATOMIC,          "ATOMIC" }, \
+       { IOCB_DONTCACHE,       "DONTCACHE" }, \
        { IOCB_EVENTFD,         "EVENTFD"}, \
        { IOCB_DIRECT,          "DIRECT" }, \
        { IOCB_WRITE,           "WRITE" }, \
@@ -2127,6 +2129,8 @@ struct file_operations {
 #define FOP_UNSIGNED_OFFSET    ((__force fop_flags_t)(1 << 5))
 /* Supports asynchronous lock callbacks */
 #define FOP_ASYNC_LOCK         ((__force fop_flags_t)(1 << 6))
+/* File system supports uncached read/write buffered IO */
+#define FOP_DONTCACHE          ((__force fop_flags_t)(1 << 7))
 
 /* Wrap a directory iterator that needs exclusive inode access */
 int wrap_directory_iterator(struct file *, struct dir_context *,
@@ -3614,6 +3618,14 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags,
                if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE))
                        return -EOPNOTSUPP;
        }
+       if (flags & RWF_DONTCACHE) {
+               /* file system must support it */
+               if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE))
+                       return -EOPNOTSUPP;
+               /* DAX mappings not supported */
+               if (IS_DAX(ki->ki_filp->f_mapping->host))
+                       return -EOPNOTSUPP;
+       }
        kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
        if (flags & RWF_SYNC)
                kiocb_flags |= IOCB_DSYNC;

diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 7539717707337a8cb22396a869baba3bafa08371..56a4f93a08f4f816ecf8af12505f065ba4452149 100644 (file)
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -332,9 +332,13 @@ typedef int __bitwise __kernel_rwf_t;
 /* Atomic Write */
 #define RWF_ATOMIC     ((__force __kernel_rwf_t)0x00000040)
 
+/* buffered IO that drops the cache after reading or writing data */
+#define RWF_DONTCACHE  ((__force __kernel_rwf_t)0x00000080)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED  (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-                        RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
+                        RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
+                        RWF_DONTCACHE)
 
 #define PROCFS_IOCTL_MAGIC 'f'