Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches:

- block: AioContext management, part 2
- Avoid recursive block_status call (i.e. lseek() calls) if possible
- linux-aio: Drop unused BlockAIOCB submission method
- nvme: add Get/Set Feature Timestamp support
- Fix crash on commit job start with active I/O on base node
- Fix crash in bdrv_drained_end
- Fix integer overflow in qcow2 discard

# gpg: Signature made Tue 04 Jun 2019 16:20:02 BST
# gpg:                using RSA key 7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream: (29 commits)
  iotests: Fix duplicated diff output on failure
  iotests: test big qcow2 shrink
  block/io: bdrv_pdiscard: support int64_t bytes parameter
  block/qcow2-refcount: add trace-point to qcow2_process_discards
  block: Remove bdrv_set_aio_context()
  test-bdrv-drain: Use bdrv_try_set_aio_context()
  iotests: Attach new devices to node in non-default iothread
  virtio-scsi-test: Test attaching new overlay with iothreads
  block: Remove wrong bdrv_set_aio_context() calls
  blockdev: Use bdrv_try_set_aio_context() for monitor commands
  block: Move node without parents to main AioContext
  test-block-iothread: BlockBackend AioContext across root node change
  test-block-iothread: Test adding parent to iothread node
  block: Adjust AioContexts when attaching nodes
  scsi-disk: Use qdev_prop_drive_iothread
  block: Add qdev_prop_drive_iothread property type
  block: Add BlockBackend.ctx
  block: Add Error to blk_set_aio_context()
  nbd-server: Call blk_set_allow_aio_context_change()
  test-block-iothread: Check filter node in test_propagate_mirror
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

7 files changed, 123 insertions, 9 deletions

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 8c37bd314a..158c78f852 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -173,6 +173,7 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     unsigned i;
     unsigned nvqs = s->conf->num_queues;
+    Error *local_err = NULL;
     int r;
 
     if (vblk->dataplane_started || s->starting) {
@@ -212,7 +213,11 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
     vblk->dataplane_started = true;
     trace_virtio_blk_data_plane_start(s);
 
-    blk_set_aio_context(s->conf->conf.blk, s->ctx);
+    r = blk_set_aio_context(s->conf->conf.blk, s->ctx, &local_err);
+    if (r < 0) {
+        error_report_err(local_err);
+        goto fail_guest_notifiers;
+    }
 
     /* Kick right away to begin processing requests already in vring */
     for (i = 0; i < nvqs; i++) {
@@ -281,8 +286,9 @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
     aio_context_acquire(s->ctx);
     aio_wait_bh_oneshot(s->ctx, virtio_blk_data_plane_stop_bh, s);
 
-    /* Drain and switch bs back to the QEMU main loop */
-    blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());
+    /* Drain and try to switch bs back to the QEMU main loop. If other users
+     * keep the BlockBackend in the iothread, that's ok */
+    blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context(), NULL);
 
     aio_context_release(s->ctx);
 
diff --git a/hw/block/dataplane/xen-block.c b/hw/block/dataplane/xen-block.c
index bb8f1186e4..f7ad452bbd 100644
--- a/hw/block/dataplane/xen-block.c
+++ b/hw/block/dataplane/xen-block.c
@@ -682,7 +682,8 @@ void xen_block_dataplane_stop(XenBlockDataPlane *dataplane)
     }
 
     aio_context_acquire(dataplane->ctx);
-    blk_set_aio_context(dataplane->blk, qemu_get_aio_context());
+    /* Xen doesn't have multiple users for nodes, so this can't fail */
+    blk_set_aio_context(dataplane->blk, qemu_get_aio_context(), &error_abort);
     aio_context_release(dataplane->ctx);
 
     xendev = dataplane->xendev;
@@ -811,7 +812,8 @@ void xen_block_dataplane_start(XenBlockDataPlane *dataplane,
     }
 
     aio_context_acquire(dataplane->ctx);
-    blk_set_aio_context(dataplane->blk, dataplane->ctx);
+    /* If other users keep the BlockBackend in the iothread, that's ok */
+    blk_set_aio_context(dataplane->blk, dataplane->ctx, NULL);
     aio_context_release(dataplane->ctx);
     return;
 
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index 6f19f127a5..37ccedc9f7 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -538,7 +538,7 @@ static void floppy_drive_realize(DeviceState *qdev, Error **errp)
 
     if (!dev->conf.blk) {
         /* Anonymous BlockBackend for an empty drive */
-        dev->conf.blk = blk_new(0, BLK_PERM_ALL);
+        dev->conf.blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL);
         ret = blk_attach_dev(dev->conf.blk, qdev);
         assert(ret == 0);
     }
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 63a5b58849..30e50f7a38 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -219,6 +219,30 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
     return NVME_INVALID_FIELD | NVME_DNR;
 }
 
+static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+                                   uint64_t prp1, uint64_t prp2)
+{
+    QEMUSGList qsg;
+    QEMUIOVector iov;
+    uint16_t status = NVME_SUCCESS;
+
+    if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
+        return NVME_INVALID_FIELD | NVME_DNR;
+    }
+    if (qsg.nsg > 0) {
+        if (dma_buf_write(ptr, len, &qsg)) {
+            status = NVME_INVALID_FIELD | NVME_DNR;
+        }
+        qemu_sglist_destroy(&qsg);
+    } else {
+        if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) {
+            status = NVME_INVALID_FIELD | NVME_DNR;
+        }
+        qemu_iovec_destroy(&iov);
+    }
+    return status;
+}
+
 static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
     uint64_t prp1, uint64_t prp2)
 {
@@ -678,7 +702,6 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
     return ret;
 }
 
-
 static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
 {
     NvmeIdentify *c = (NvmeIdentify *)cmd;
@@ -696,6 +719,57 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
     }
 }
 
+static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
+{
+    trace_nvme_setfeat_timestamp(ts);
+
+    n->host_timestamp = le64_to_cpu(ts);
+    n->timestamp_set_qemu_clock_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
+}
+
+static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
+{
+    uint64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
+    uint64_t elapsed_time = current_time - n->timestamp_set_qemu_clock_ms;
+
+    union nvme_timestamp {
+        struct {
+            uint64_t timestamp:48;
+            uint64_t sync:1;
+            uint64_t origin:3;
+            uint64_t rsvd1:12;
+        };
+        uint64_t all;
+    };
+
+    union nvme_timestamp ts;
+    ts.all = 0;
+
+    /*
+     * If the sum of the Timestamp value set by the host and the elapsed
+     * time exceeds 2^48, the value returned should be reduced modulo 2^48.
+     */
+    ts.timestamp = (n->host_timestamp + elapsed_time) & 0xffffffffffff;
+
+    /* If the host timestamp is non-zero, set the timestamp origin */
+    ts.origin = n->host_timestamp ? 0x01 : 0x00;
+
+    trace_nvme_getfeat_timestamp(ts.all);
+
+    return cpu_to_le64(ts.all);
+}
+
+static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
+{
+    uint64_t prp1 = le64_to_cpu(cmd->prp1);
+    uint64_t prp2 = le64_to_cpu(cmd->prp2);
+
+    uint64_t timestamp = nvme_get_timestamp(n);
+
+    return nvme_dma_read_prp(n, (uint8_t *)&timestamp,
+                                 sizeof(timestamp), prp1, prp2);
+}
+
 static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
     uint32_t dw10 = le32_to_cpu(cmd->cdw10);
@@ -710,6 +784,9 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
         trace_nvme_getfeat_numq(result);
         break;
+    case NVME_TIMESTAMP:
+        return nvme_get_feature_timestamp(n, cmd);
+        break;
     default:
         trace_nvme_err_invalid_getfeat(dw10);
         return NVME_INVALID_FIELD | NVME_DNR;
@@ -719,6 +796,24 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     return NVME_SUCCESS;
 }
 
+static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
+{
+    uint16_t ret;
+    uint64_t timestamp;
+    uint64_t prp1 = le64_to_cpu(cmd->prp1);
+    uint64_t prp2 = le64_to_cpu(cmd->prp2);
+
+    ret = nvme_dma_write_prp(n, (uint8_t *)&timestamp,
+                                sizeof(timestamp), prp1, prp2);
+    if (ret != NVME_SUCCESS) {
+        return ret;
+    }
+
+    nvme_set_timestamp(n, timestamp);
+
+    return NVME_SUCCESS;
+}
+
 static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
     uint32_t dw10 = le32_to_cpu(cmd->cdw10);
@@ -735,6 +830,11 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         req->cqe.result =
             cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
         break;
+
+    case NVME_TIMESTAMP:
+        return nvme_set_feature_timestamp(n, cmd);
+        break;
+
     default:
         trace_nvme_err_invalid_setfeat(dw10);
         return NVME_INVALID_FIELD | NVME_DNR;
@@ -907,6 +1007,8 @@ static int nvme_start_ctrl(NvmeCtrl *n)
     nvme_init_sq(&n->admin_sq, n, n->bar.asq, 0, 0,
         NVME_AQA_ASQS(n->bar.aqa) + 1);
 
+    nvme_set_timestamp(n, 0ULL);
+
     return 0;
 }
 
@@ -1270,7 +1372,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     id->sqes = (0x6 << 4) | 0x6;
     id->cqes = (0x4 << 4) | 0x4;
     id->nn = cpu_to_le32(n->num_namespaces);
-    id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS);
+    id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP);
     id->psd[0].mp = cpu_to_le16(0x9c4);
     id->psd[0].enlat = cpu_to_le32(0x10);
     id->psd[0].exlat = cpu_to_le32(0x4);
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 56c9d4b4b1..557194ee19 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -79,6 +79,8 @@ typedef struct NvmeCtrl {
     uint32_t    cmbloc;
     uint8_t     *cmbuf;
     uint64_t    irq_status;
+    uint64_t    host_timestamp;                 /* Timestamp sent by the host */
+    uint64_t    timestamp_set_qemu_clock_ms;    /* QEMU clock time */
 
     char            *serial;
     NvmeNamespace   *namespaces;
diff --git a/hw/block/trace-events b/hw/block/trace-events
index b92039a573..97a17838ed 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -46,6 +46,8 @@ nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16""
 nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s"
 nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
 nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
+nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
+nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
 nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64""
 nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64""
 nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64""
diff --git a/hw/block/xen-block.c b/hw/block/xen-block.c
index ef635be4c2..31b0f5ccc8 100644
--- a/hw/block/xen-block.c
+++ b/hw/block/xen-block.c
@@ -609,7 +609,7 @@ static void xen_cdrom_realize(XenBlockDevice *blockdev, Error **errp)
         int rc;
 
         /* Set up an empty drive */
-        conf->blk = blk_new(0, BLK_PERM_ALL);
+        conf->blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL);
 
         rc = blk_attach_dev(conf->blk, DEVICE(blockdev));
         if (!rc) {