[Qemu-devel] [PATCH] block/raw-posix: fix launching with failed disks

[Stefan Hajnoczi]

Since commit c25f53b06eba1575d5d0e92a0132455c97825b83 ("raw: Probe
required direct I/O alignment") QEMU has failed to launch if image files
produce I/O errors.

Previously, QEMU would launch successfully and the guest would see the
errors when attempting I/O.

This is a regression and may prevent multipath I/O inside the guest,
where QEMU must launch and let the guest figure out by itself which
disks are online.

Tweak the alignment probing code in raw-posix.c to explicitly look for
EINVAL on Linux instead of bailing.  The kernel refuses misaligned
requests with this error code and other error codes can be ignored.

Signed-off-by: Stefan Hajnoczi <address@hidden>
---
 block/raw-posix.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/block/raw-posix.c b/block/raw-posix.c
index b5f077a..6eb3925 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -218,6 +218,31 @@ static int raw_normalize_devicepath(const char **filename)
 }
 #endif
 
+/* Check if read is allowed with given memory buffer and length.
+ *
+ * This function is used to check O_DIRECT memory buffer and request alignment.
+ */
+static bool raw_is_io_aligned(int fd, void *buf, size_t len)
+{
+    ssize_t ret = pread(fd, buf, len, 0);
+
+    if (ret >= 0) {
+        return true;
+    }
+
+#ifdef __linux__
+    /* The Linux kernel returns EINVAL for misaligned O_DIRECT reads.  Ignore
+     * other errors (e.g. real I/O error), which could happen on a failed
+     * drive, since we only care about probing alignment.
+     */
+    if (errno != EINVAL) {
+        return true;
+    }
+#endif
+
+    return false;
+}
+
 static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp)
 {
     BDRVRawState *s = bs->opaque;
@@ -267,7 +292,7 @@ static void raw_probe_alignment(BlockDriverState *bs, int 
fd, Error **errp)
         size_t align;
         buf = qemu_memalign(MAX_BLOCKSIZE, 2 * MAX_BLOCKSIZE);
         for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
-            if (pread(fd, buf + align, MAX_BLOCKSIZE, 0) >= 0) {
+            if (raw_is_io_aligned(fd, buf + align, MAX_BLOCKSIZE)) {
                 s->buf_align = align;
                 break;
             }
@@ -279,7 +304,7 @@ static void raw_probe_alignment(BlockDriverState *bs, int 
fd, Error **errp)
         size_t align;
         buf = qemu_memalign(s->buf_align, MAX_BLOCKSIZE);
         for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
-            if (pread(fd, buf, align, 0) >= 0) {
+            if (raw_is_io_aligned(fd, buf, align)) {
                 bs->request_alignment = align;
                 break;
             }
-- 
2.1.0