block: Move I/O status and error actions into BB

These options are only relevant for the user of a whole BDS tree (like a
guest device or a block job) and should thus be moved into the
BlockBackend.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

6 files changed, 141 insertions, 19 deletions

diff --git a/block/backup.c b/block/backup.c
index 5696431..ec01db8 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -21,6 +21,7 @@
 #include "block/blockjob.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
+#include "sysemu/block-backend.h"
 
 #define BACKUP_CLUSTER_BITS 16
 #define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
@@ -215,7 +216,9 @@ static void backup_iostatus_reset(BlockJob *job)
 {
     BackupBlockJob *s = container_of(job, BackupBlockJob, common);
 
-    bdrv_iostatus_reset(s->target);
+    if (s->target->blk) {
+        blk_iostatus_reset(s->target->blk);
+    }
 }
 
 static const BlockJobDriver backup_job_driver = {
@@ -360,8 +363,10 @@ static void coroutine_fn backup_run(void *opaque)
     job->bitmap = hbitmap_alloc(end, 0);
 
     bdrv_set_enable_write_cache(target, true);
-    bdrv_set_on_error(target, on_target_error, on_target_error);
-    bdrv_iostatus_enable(target);
+    if (target->blk) {
+        blk_set_on_error(target->blk, on_target_error, on_target_error);
+        blk_iostatus_enable(target->blk);
+    }
 
     bdrv_add_before_write_notifier(bs, &before_write);
 
@@ -451,7 +456,9 @@ static void coroutine_fn backup_run(void *opaque)
     }
     hbitmap_free(job->bitmap);
 
-    bdrv_iostatus_disable(target);
+    if (target->blk) {
+        blk_iostatus_disable(target->blk);
+    }
     bdrv_op_unblock_all(target, job->common.blocker);
 
     data = g_malloc(sizeof(*data));
@@ -480,7 +487,7 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
 
     if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
          on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
+        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
         error_setg(errp, QERR_INVALID_PARAMETER, "on-source-error");
         return;
     }
diff --git a/block/block-backend.c b/block/block-backend.c
index a52037b..2708ad1 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -12,7 +12,9 @@
 
 #include "sysemu/block-backend.h"
 #include "block/block_int.h"
+#include "block/blockjob.h"
 #include "sysemu/blockdev.h"
+#include "sysemu/sysemu.h"
 #include "qapi-event.h"
 
 /* Number of coroutines to reserve per attached device model */
@@ -37,6 +39,10 @@ struct BlockBackend {
 
     /* I/O stats (display with "info blockstats"). */
     BlockAcctStats stats;
+
+    BlockdevOnError on_read_error, on_write_error;
+    bool iostatus_enabled;
+    BlockDeviceIoStatus iostatus;
 };
 
 typedef struct BlockBackendAIOCB {
@@ -330,7 +336,7 @@ int blk_attach_dev(BlockBackend *blk, void *dev)
     }
     blk_ref(blk);
     blk->dev = dev;
-    bdrv_iostatus_reset(blk->bs);
+    blk_iostatus_reset(blk);
     return 0;
 }
 
@@ -462,7 +468,47 @@ void blk_dev_resize_cb(BlockBackend *blk)
 
 void blk_iostatus_enable(BlockBackend *blk)
 {
-    bdrv_iostatus_enable(blk->bs);
+    blk->iostatus_enabled = true;
+    blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
+}
+
+/* The I/O status is only enabled if the drive explicitly
+ * enables it _and_ the VM is configured to stop on errors */
+bool blk_iostatus_is_enabled(const BlockBackend *blk)
+{
+    return (blk->iostatus_enabled &&
+           (blk->on_write_error == BLOCKDEV_ON_ERROR_ENOSPC ||
+            blk->on_write_error == BLOCKDEV_ON_ERROR_STOP   ||
+            blk->on_read_error == BLOCKDEV_ON_ERROR_STOP));
+}
+
+BlockDeviceIoStatus blk_iostatus(const BlockBackend *blk)
+{
+    return blk->iostatus;
+}
+
+void blk_iostatus_disable(BlockBackend *blk)
+{
+    blk->iostatus_enabled = false;
+}
+
+void blk_iostatus_reset(BlockBackend *blk)
+{
+    if (blk_iostatus_is_enabled(blk)) {
+        blk->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
+        if (blk->bs && blk->bs->job) {
+            block_job_iostatus_reset(blk->bs->job);
+        }
+    }
+}
+
+void blk_iostatus_set_err(BlockBackend *blk, int error)
+{
+    assert(blk_iostatus_is_enabled(blk));
+    if (blk->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
+        blk->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
+                                          BLOCK_DEVICE_IO_STATUS_FAILED;
+    }
 }
 
 static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
@@ -738,21 +784,81 @@ void blk_drain_all(void)
     bdrv_drain_all();
 }
 
+void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error,
+                      BlockdevOnError on_write_error)
+{
+    blk->on_read_error = on_read_error;
+    blk->on_write_error = on_write_error;
+}
+
 BlockdevOnError blk_get_on_error(BlockBackend *blk, bool is_read)
 {
-    return bdrv_get_on_error(blk->bs, is_read);
+    return is_read ? blk->on_read_error : blk->on_write_error;
 }
 
 BlockErrorAction blk_get_error_action(BlockBackend *blk, bool is_read,
                                       int error)
 {
-    return bdrv_get_error_action(blk->bs, is_read, error);
+    BlockdevOnError on_err = blk_get_on_error(blk, is_read);
+
+    switch (on_err) {
+    case BLOCKDEV_ON_ERROR_ENOSPC:
+        return (error == ENOSPC) ?
+               BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
+    case BLOCKDEV_ON_ERROR_STOP:
+        return BLOCK_ERROR_ACTION_STOP;
+    case BLOCKDEV_ON_ERROR_REPORT:
+        return BLOCK_ERROR_ACTION_REPORT;
+    case BLOCKDEV_ON_ERROR_IGNORE:
+        return BLOCK_ERROR_ACTION_IGNORE;
+    default:
+        abort();
+    }
 }
 
+static void send_qmp_error_event(BlockBackend *blk,
+                                 BlockErrorAction action,
+                                 bool is_read, int error)
+{
+    IoOperationType optype;
+
+    optype = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
+    qapi_event_send_block_io_error(blk_name(blk), optype, action,
+                                   blk_iostatus_is_enabled(blk),
+                                   error == ENOSPC, strerror(error),
+                                   &error_abort);
+}
+
+/* This is done by device models because, while the block layer knows
+ * about the error, it does not know whether an operation comes from
+ * the device or the block layer (from a job, for example).
+ */
 void blk_error_action(BlockBackend *blk, BlockErrorAction action,
                       bool is_read, int error)
 {
-    bdrv_error_action(blk->bs, action, is_read, error);
+    assert(error >= 0);
+
+    if (action == BLOCK_ERROR_ACTION_STOP) {
+        /* First set the iostatus, so that "info block" returns an iostatus
+         * that matches the events raised so far (an additional error iostatus
+         * is fine, but not a lost one).
+         */
+        blk_iostatus_set_err(blk, error);
+
+        /* Then raise the request to stop the VM and the event.
+         * qemu_system_vmstop_request_prepare has two effects.  First,
+         * it ensures that the STOP event always comes after the
+         * BLOCK_IO_ERROR event.  Second, it ensures that even if management
+         * can observe the STOP event and do a "cont" before the STOP
+         * event is issued, the VM will not stop.  In this case, vm_start()
+         * also ensures that the STOP/RESUME pair of events is emitted.
+         */
+        qemu_system_vmstop_request_prepare();
+        send_qmp_error_event(blk, action, is_read, error);
+        qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
+    } else {
+        send_qmp_error_event(blk, action, is_read, error);
+    }
 }
 
 int blk_is_read_only(BlockBackend *blk)
diff --git a/block/commit.c b/block/commit.c
index d12e26f..fdebe87 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -17,6 +17,7 @@
 #include "block/blockjob.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
+#include "sysemu/block-backend.h"
 
 enum {
     /*
@@ -213,7 +214,7 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
 
     if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
          on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
+        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
         error_setg(errp, "Invalid parameter combination");
         return;
     }
diff --git a/block/mirror.c b/block/mirror.c
index 7e43511..b1252a1 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -14,6 +14,7 @@
 #include "trace.h"
 #include "block/blockjob.h"
 #include "block/block_int.h"
+#include "sysemu/block-backend.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
 #include "qemu/bitmap.h"
@@ -599,7 +600,9 @@ immediate_exit:
     g_free(s->cow_bitmap);
     g_free(s->in_flight_bitmap);
     bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
-    bdrv_iostatus_disable(s->target);
+    if (s->target->blk) {
+        blk_iostatus_disable(s->target->blk);
+    }
 
     data = g_malloc(sizeof(*data));
     data->ret = ret;
@@ -621,7 +624,9 @@ static void mirror_iostatus_reset(BlockJob *job)
 {
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
 
-    bdrv_iostatus_reset(s->target);
+    if (s->target->blk) {
+        blk_iostatus_reset(s->target->blk);
+    }
 }
 
 static void mirror_complete(BlockJob *job, Error **errp)
@@ -704,7 +709,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
 
     if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
          on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
+        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
         error_setg(errp, QERR_INVALID_PARAMETER, "on-source-error");
         return;
     }
@@ -740,8 +745,10 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
         return;
     }
     bdrv_set_enable_write_cache(s->target, true);
-    bdrv_set_on_error(s->target, on_target_error, on_target_error);
-    bdrv_iostatus_enable(s->target);
+    if (s->target->blk) {
+        blk_set_on_error(s->target->blk, on_target_error, on_target_error);
+        blk_iostatus_enable(s->target->blk);
+    }
     s->common.co = qemu_coroutine_create(mirror_run);
     trace_mirror_start(bs, s, s->common.co, opaque);
     qemu_coroutine_enter(s->common.co, s);
diff --git a/block/qapi.c b/block/qapi.c
index 7c8209b..3b46f97 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -301,9 +301,9 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
         info->tray_open = blk_dev_is_tray_open(blk);
     }
 
-    if (bdrv_iostatus_is_enabled(bs)) {
+    if (blk_iostatus_is_enabled(blk)) {
         info->has_io_status = true;
-        info->io_status = bs->iostatus;
+        info->io_status = blk_iostatus(blk);
     }
 
     if (!QLIST_EMPTY(&bs->dirty_bitmaps)) {
diff --git a/block/stream.c b/block/stream.c
index 3f64fa2..25af7ef 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -16,6 +16,7 @@
 #include "block/blockjob.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
+#include "sysemu/block-backend.h"
 
 enum {
     /*
@@ -222,7 +223,7 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
 
     if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
          on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
+        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
         error_setg(errp, QERR_INVALID_PARAMETER, "on-error");
         return;
     }