Merge tag 'for-upstream' of https://repo.or.cz/qemu/kevin into staging

Block layer patches

- SCSI passthrough: Fix errors on temporarily suspended dm-multipath

# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCgAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmkxxnERHGt3b2xmQHJl
# ZGhhdC5jb20ACgkQfwmycsiPL9YH0Q//QWDBVYFM+3+OW2cXXj9BmWS1xEUmq4L2
# DVkOOOHx2U7SxRvSlCo+4l9Lo4P3+tHimm+ApqEgWES4MOGZG1qCE1gnfA6tvNaR
# qkq67DoZ9VShiP5FQwyhXkAUm4cPHFFb8ZIpqc8sH1LGxcoA7hq7bI32RzGsiE3U
# pyOD+11z4ARQYqU/YRF8fKqTqwudhgVSIJInBcUCYzuIaUjxl4ZjHxvjRdFMQc2F
# OIhJVNAOJ4cpvPspmAmTrwKFU81xjX6ymIqHenjX+ZJ3QtSLtuPaDDYJdGmXu8F9
# Me9OMnZfP4lu4I6L5kO2JpVAnzHppUSUsJcescs1q+dsqhGCR+tPgPUsYCmMlro5
# yoMIxCdAX7aAWI2wjg4TjYrYNI3FRB9+IL2qqHvW2cthkA6C6Ef+/26EIEkMGzsN
# rAqyjHa8Bo64JPdW8PUyeg+N27qf9ZwSut8KFR/++hM+sHbm2SImSgqJ+WepgYKx
# gIzsXGOOeVQUdbCGXfwzhnzGbOLZMg4nUZDTSnHVvNF/JfdJsgxkm//zFll6PJcH
# 3vF7XiA+RoBSea5WiWBaBPWDvDaxsRrkOE/j1GQ/GM8vt6ZK+qplPMBMihXOyfE2
# KS9RwNzhgOAl0XrRpmTVLTLPvZocd9g7XTFiicxIFqJNoMrPNWBSmKEibDMbD5jP
# eo87nHrXS0s=
# =H7YD
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 04 Dec 2025 11:35:45 AM CST
# gpg:                using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg:                issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [unknown]
# gpg: WARNING: The key's User ID is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* tag 'for-upstream' of https://repo.or.cz/qemu/kevin:
  file-posix: Handle suspended dm-multipath better for SG_IO

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

block/file-posix.c

@@ -4288,25 +4288,8 @@ hdev_open_Mac_error:
 static bool coroutine_fn sgio_path_error(int ret, sg_io_hdr_t *io_hdr)
 {
     if (ret < 0) {
-        switch (ret) {
-        case -ENODEV:
-            return true;
-        case -EAGAIN:
-            /*
-             * The device is probably suspended. This happens while the dm table
-             * is reloaded, e.g. because a path is added or removed. This is an
-             * operation that should complete within 1ms, so just wait a bit and
-             * retry.
-             *
-             * If the device was suspended for another reason, we'll wait and
-             * retry SG_IO_MAX_RETRIES times. This is a tolerable delay before
-             * we return an error and potentially stop the VM.
-             */
-            qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000);
-            return true;
-        default:
-            return false;
-        }
+        /* Path errors sometimes result in -ENODEV */
+        return ret == -ENODEV;
     }
 
     if (io_hdr->host_status != SCSI_HOST_OK) {
@@ -4375,6 +4358,7 @@ hdev_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
 {
     BDRVRawState *s = bs->opaque;
     RawPosixAIOData acb;
+    uint64_t eagain_sleep_ns = 1 * SCALE_MS;
     int retries = SG_IO_MAX_RETRIES;
     int ret;
 
@@ -4403,9 +4387,37 @@ hdev_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
         },
     };
 
-    do {
-        ret = raw_thread_pool_submit(handle_aiocb_ioctl, &acb);
-    } while (req == SG_IO && retries-- && hdev_co_ioctl_sgio_retry(&acb, ret));
+retry:
+    ret = raw_thread_pool_submit(handle_aiocb_ioctl, &acb);
+    if (req == SG_IO && s->use_mpath) {
+        if (ret == -EAGAIN && eagain_sleep_ns < NANOSECONDS_PER_SECOND) {
+            /*
+             * If this is a multipath device, it is probably suspended.
+             *
+             * This can happen while the dm table is reloaded, e.g. because a
+             * path is added or removed. This is an operation that should
+             * complete within 1ms, so just wait a bit and retry.
+             *
+             * There are also some cases in which libmpathpersist must recover
+             * from path failure during its operation, which can leave the
+             * device suspended for a bit longer while the library brings back
+             * reservations into the expected state.
+             *
+             * Use increasing delays to cover both cases without waiting
+             * excessively, and stop after a bit more than a second (1023 ms).
+             * This is a tolerable delay before we return an error and
+             * potentially stop the VM.
+             */
+            qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, eagain_sleep_ns);
+            eagain_sleep_ns *= 2;
+            goto retry;
+        }
+
+        /* Even for ret == 0, the SG_IO header can contain an error */
+        if (retries-- && hdev_co_ioctl_sgio_retry(&acb, ret)) {
+            goto retry;
+        }
+    }
 
     return ret;
 }