[Qemu-devel] [RFC 1/2] block/file-posix: implement bdrv_co_invalidate_cache() on Linux

[Stefan Hajnoczi]

On Linux posix_fadvise(POSIX_FADV_DONTNEED) invalidates pages*.  Use
this to drop page cache on the destination host during shared storage
migration.  This way the destination host will read the latest copy of
the data and will not use stale data from the page cache.

The flow is as follows:

1. Source host writes out all dirty pages and inactivates drives.
2. QEMU_VM_EOF is sent on migration stream.
3. Destination host invalidates caches before accessing drives.

This patch enables live migration even with -drive cache.direct=off.

* Terms and conditions may apply, please see patch for details.

Signed-off-by: Stefan Hajnoczi <address@hidden>
---
 block/file-posix.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/block/file-posix.c b/block/file-posix.c
index 3794c0007a..df4f52919f 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -2236,6 +2236,42 @@ static int coroutine_fn 
raw_co_block_status(BlockDriverState *bs,
     return ret | BDRV_BLOCK_OFFSET_VALID;
 }
 
+static void coroutine_fn raw_co_invalidate_cache(BlockDriverState *bs,
+                                                 Error **errp)
+{
+    BDRVRawState *s = bs->opaque;
+    int ret;
+
+    ret = fd_open(bs);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "The file descriptor is not open");
+        return;
+    }
+
+    if (s->open_flags & O_DIRECT) {
+        return; /* No host kernel page cache */
+    }
+
+#if defined(__linux__)
+    /* This sets the scene for the next syscall... */
+    ret = bdrv_co_flush(bs);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "flush failed");
+        return;
+    }
+
+    /* Linux does not invalidate pages that are dirty, locked, or mmapped by a
+     * process.  These limitations are okay because we just fsynced the file,
+     * we don't use mmap, and the file should not be in use by other processes.
+     */
+    ret = posix_fadvise(s->fd, 0, 0, POSIX_FADV_DONTNEED);
+    if (ret != 0) { /* the return value is a positive errno */
+        error_setg_errno(errp, ret, "fadvise failed");
+        return;
+    }
+#endif /* __linux__ */
+}
+
 static coroutine_fn BlockAIOCB *raw_aio_pdiscard(BlockDriverState *bs,
     int64_t offset, int bytes,
     BlockCompletionFunc *cb, void *opaque)
@@ -2328,6 +2364,7 @@ BlockDriver bdrv_file = {
     .bdrv_co_create_opts = raw_co_create_opts,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_block_status = raw_co_block_status,
+    .bdrv_co_invalidate_cache = raw_co_invalidate_cache,
     .bdrv_co_pwrite_zeroes = raw_co_pwrite_zeroes,
 
     .bdrv_co_preadv         = raw_co_preadv,
@@ -2805,6 +2842,7 @@ static BlockDriver bdrv_host_device = {
     .bdrv_reopen_abort   = raw_reopen_abort,
     .bdrv_co_create_opts = hdev_co_create_opts,
     .create_opts         = &raw_create_opts,
+    .bdrv_co_invalidate_cache = raw_co_invalidate_cache,
     .bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes,
 
     .bdrv_co_preadv         = raw_co_preadv,
@@ -2927,6 +2965,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_reopen_abort   = raw_reopen_abort,
     .bdrv_co_create_opts = hdev_co_create_opts,
     .create_opts         = &raw_create_opts,
+    .bdrv_co_invalidate_cache = raw_co_invalidate_cache,
 
 
     .bdrv_co_preadv         = raw_co_preadv,
-- 
2.14.3