io_uring: add support for pre-mapped user IO buffers

If we have fixed user buffers, we can map them into the kernel when we
setup the io_uring. That avoids the need to do get_user_pages() for
each and every IO.

To utilize this feature, the application must call io_uring_register()
after having setup an io_uring instance, passing in
IORING_REGISTER_BUFFERS as the opcode. The argument must be a pointer to
an iovec array, and the nr_args should contain how many iovecs the
application wishes to map.

If successful, these buffers are now mapped into the kernel, eligible
for IO. To use these fixed buffers, the application must use the
IORING_OP_READ_FIXED and IORING_OP_WRITE_FIXED opcodes, and then
set sqe->index to the desired buffer index. sqe->addr..sqe->addr+seq->len
must point to somewhere inside the indexed buffer.

The application may register buffers throughout the lifetime of the
io_uring instance. It can call io_uring_register() with
IORING_UNREGISTER_BUFFERS as the opcode to unregister the current set of
buffers, and then register a new set. The application need not
unregister buffers explicitly before shutting down the io_uring
instance.

It's perfectly valid to setup a larger buffer, and then sometimes only
use parts of it for an IO. As long as the range is within the originally
mapped region, it will work just fine.

For now, buffers must not be file backed. If file backed buffers are
passed in, the registration will fail with -1/EOPNOTSUPP. This
restriction may be relaxed in the future.

RLIMIT_MEMLOCK is used to check how much memory we can pin. A somewhat
arbitrary 1G per buffer size is also imposed.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 15 insertions, 2 deletions

diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 87871e7b7ea7..d346229a1eb0 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -744,9 +744,11 @@ __SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
 __SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
 #define __NR_io_uring_enter 426
 __SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
 
 #undef __NR_syscalls
-#define __NR_syscalls 427
+#define __NR_syscalls 428
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 5c457ea396e6..cf28f7a11f12 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -27,7 +27,10 @@ struct io_uring_sqe {
                 __u32           fsync_flags;
         };
         __u64   user_data;      /* data to be passed back at completion time */
-        __u64   __pad2[3];
+        union {
+                __u16   buf_index;      /* index into fixed buffers, if used */
+                __u64   __pad2[3];
+        };
 };
 
 /*
@@ -39,6 +42,8 @@ struct io_uring_sqe {
 #define IORING_OP_READV         1
 #define IORING_OP_WRITEV        2
 #define IORING_OP_FSYNC         3
+#define IORING_OP_READ_FIXED    4
+#define IORING_OP_WRITE_FIXED   5
 
 /*
  * sqe->fsync_flags
@@ -103,4 +108,10 @@ struct io_uring_params {
         struct io_cqring_offsets cq_off;
 };
 
+/*
+ * io_uring_register(2) opcodes and arguments
+ */
+#define IORING_REGISTER_BUFFERS         0
+#define IORING_UNREGISTER_BUFFERS       1
+
 #endif