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

Block layer patches (rebased Stefan's pull request)

# gpg: Signature made Thu 12 Nov 2015 15:34:16 GMT using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (43 commits)
  block: Update copyright of the accounting code
  scsi-disk: Account for failed operations
  macio: Account for failed operations
  ide: Account for failed and invalid operations
  atapi: Account for failed and invalid operations
  xen_disk: Account for failed and invalid operations
  virtio-blk: Account for failed and invalid operations
  nvme: Account for failed and invalid operations
  iotests: Add test for the block device statistics
  block: Use QEMU_CLOCK_VIRTUAL for the accounting code in qtest mode
  qemu-io: Account for failed, invalid and flush operations
  block: New option to define the intervals for collecting I/O statistics
  block: Add average I/O queue depth to BlockDeviceTimedStats
  block: Compute minimum, maximum and average I/O latencies
  block: Allow configuring whether to account failed and invalid ops
  block: Add statistics for failed and invalid I/O operations
  block: Add idle_time_ns to BlockDeviceStats
  util: Infrastructure for computing recent averages
  block: define 'clock_type' for the accounting code
  ide: Account for write operations correctly
  ...

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

7 files changed, 105 insertions, 38 deletions

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 5da41b23cf..169e4fa7a5 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -201,10 +201,11 @@ static void nvme_rw_cb(void *opaque, int ret)
     NvmeCtrl *n = sq->ctrl;
     NvmeCQueue *cq = n->cq[sq->cqid];
 
-    block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
     if (!ret) {
+        block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
         req->status = NVME_SUCCESS;
     } else {
+        block_acct_failed(blk_get_stats(n->conf.blk), &req->acct);
         req->status = NVME_INTERNAL_DEV_ERROR;
     }
     if (req->has_sg) {
@@ -238,18 +239,22 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     uint64_t data_size = (uint64_t)nlb << data_shift;
     uint64_t aio_slba  = slba << (data_shift - BDRV_SECTOR_BITS);
     int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0;
+    enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
 
     if ((slba + nlb) > ns->id_ns.nsze) {
+        block_acct_invalid(blk_get_stats(n->conf.blk), acct);
         return NVME_LBA_RANGE | NVME_DNR;
     }
+
     if (nvme_map_prp(&req->qsg, prp1, prp2, data_size, n)) {
+        block_acct_invalid(blk_get_stats(n->conf.blk), acct);
         return NVME_INVALID_FIELD | NVME_DNR;
     }
+
     assert((nlb << data_shift) == req->qsg.size);
 
     req->has_sg = true;
-    dma_acct_start(n->conf.blk, &req->acct, &req->qsg,
-                   is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
+    dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct);
     req->aiocb = is_write ?
         dma_blk_write(n->conf.blk, &req->qsg, aio_slba, nvme_rw_cb, req) :
         dma_blk_read(n->conf.blk, &req->qsg, aio_slba, nvme_rw_cb, req);
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 093e475dc9..e70fccf80c 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -76,7 +76,7 @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
         s->rq = req;
     } else if (action == BLOCK_ERROR_ACTION_REPORT) {
         virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
-        block_acct_done(blk_get_stats(s->blk), &req->acct);
+        block_acct_failed(blk_get_stats(s->blk), &req->acct);
         virtio_blk_free_request(req);
     }
 
@@ -536,6 +536,8 @@ void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
         if (!virtio_blk_sect_range_ok(req->dev, req->sector_num,
                                       req->qiov.size)) {
             virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+            block_acct_invalid(blk_get_stats(req->dev->blk),
+                               is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
             virtio_blk_free_request(req);
             return;
         }
diff --git a/hw/block/xen_disk.c b/hw/block/xen_disk.c
index 1bbc111939..02eda6efbc 100644
--- a/hw/block/xen_disk.c
+++ b/hw/block/xen_disk.c
@@ -537,7 +537,11 @@ static void qemu_aio_complete(void *opaque, int ret)
             break;
         }
     case BLKIF_OP_READ:
-        block_acct_done(blk_get_stats(ioreq->blkdev->blk), &ioreq->acct);
+        if (ioreq->status == BLKIF_RSP_OKAY) {
+            block_acct_done(blk_get_stats(ioreq->blkdev->blk), &ioreq->acct);
+        } else {
+            block_acct_failed(blk_get_stats(ioreq->blkdev->blk), &ioreq->acct);
+        }
         break;
     case BLKIF_OP_DISCARD:
     default:
@@ -576,7 +580,9 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
         }
 
         block_acct_start(blk_get_stats(blkdev->blk), &ioreq->acct,
-                         ioreq->v.size, BLOCK_ACCT_WRITE);
+                         ioreq->v.size,
+                         ioreq->req.operation == BLKIF_OP_WRITE ?
+                         BLOCK_ACCT_WRITE : BLOCK_ACCT_FLUSH);
         ioreq->aio_inflight++;
         blk_aio_writev(blkdev->blk, ioreq->start / BLOCK_SIZE,
                        &ioreq->v, ioreq->v.size / BLOCK_SIZE,
@@ -720,6 +726,23 @@ static void blk_handle_requests(struct XenBlkDev *blkdev)
 
         /* parse them */
         if (ioreq_parse(ioreq) != 0) {
+
+            switch (ioreq->req.operation) {
+            case BLKIF_OP_READ:
+                block_acct_invalid(blk_get_stats(blkdev->blk),
+                                   BLOCK_ACCT_READ);
+                break;
+            case BLKIF_OP_WRITE:
+                block_acct_invalid(blk_get_stats(blkdev->blk),
+                                   BLOCK_ACCT_WRITE);
+                break;
+            case BLKIF_OP_FLUSH_DISKCACHE:
+                block_acct_invalid(blk_get_stats(blkdev->blk),
+                                   BLOCK_ACCT_FLUSH);
+            default:
+                break;
+            };
+
             if (blk_send_response_one(ioreq)) {
                 xen_be_send_notify(&blkdev->xendev);
             }
diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c
index 747f46611e..cf0b78e3a4 100644
--- a/hw/ide/atapi.c
+++ b/hw/ide/atapi.c
@@ -108,27 +108,30 @@ static void cd_data_to_raw(uint8_t *buf, int lba)
 static int cd_read_sector(IDEState *s, int lba, uint8_t *buf, int sector_size)
 {
     int ret;
+    block_acct_start(blk_get_stats(s->blk), &s->acct,
+                     4 * BDRV_SECTOR_SIZE, BLOCK_ACCT_READ);
 
     switch(sector_size) {
     case 2048:
-        block_acct_start(blk_get_stats(s->blk), &s->acct,
-                         4 * BDRV_SECTOR_SIZE, BLOCK_ACCT_READ);
         ret = blk_read(s->blk, (int64_t)lba << 2, buf, 4);
-        block_acct_done(blk_get_stats(s->blk), &s->acct);
         break;
     case 2352:
-        block_acct_start(blk_get_stats(s->blk), &s->acct,
-                         4 * BDRV_SECTOR_SIZE, BLOCK_ACCT_READ);
         ret = blk_read(s->blk, (int64_t)lba << 2, buf + 16, 4);
-        block_acct_done(blk_get_stats(s->blk), &s->acct);
-        if (ret < 0)
-            return ret;
-        cd_data_to_raw(buf, lba);
+        if (ret >= 0) {
+            cd_data_to_raw(buf, lba);
+        }
         break;
     default:
-        ret = -EIO;
-        break;
+        block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_READ);
+        return -EIO;
+    }
+
+    if (ret < 0) {
+        block_acct_failed(blk_get_stats(s->blk), &s->acct);
+    } else {
+        block_acct_done(blk_get_stats(s->blk), &s->acct);
     }
+
     return ret;
 }
 
@@ -357,7 +360,11 @@ static void ide_atapi_cmd_read_dma_cb(void *opaque, int ret)
     return;
 
 eot:
-    block_acct_done(blk_get_stats(s->blk), &s->acct);
+    if (ret < 0) {
+        block_acct_failed(blk_get_stats(s->blk), &s->acct);
+    } else {
+        block_acct_done(blk_get_stats(s->blk), &s->acct);
+    }
     ide_set_inactive(s, false);
 }
 
diff --git a/hw/ide/core.c b/hw/ide/core.c
index 364ba21e0c..2725dd3b81 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -574,7 +574,6 @@ static void ide_sector_read_cb(void *opaque, int ret)
     if (ret == -ECANCELED) {
         return;
     }
-    block_acct_done(blk_get_stats(s->blk), &s->acct);
     if (ret != 0) {
         if (ide_handle_rw_error(s, -ret, IDE_RETRY_PIO |
                                 IDE_RETRY_READ)) {
@@ -582,6 +581,8 @@ static void ide_sector_read_cb(void *opaque, int ret)
         }
     }
 
+    block_acct_done(blk_get_stats(s->blk), &s->acct);
+
     n = s->nsector;
     if (n > s->req_nb_sectors) {
         n = s->req_nb_sectors;
@@ -621,6 +622,7 @@ static void ide_sector_read(IDEState *s)
 
     if (!ide_sect_range_ok(s, sector_num, n)) {
         ide_rw_error(s);
+        block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_READ);
         return;
     }
 
@@ -672,6 +674,7 @@ static int ide_handle_rw_error(IDEState *s, int error, int op)
         assert(s->bus->retry_unit == s->unit);
         s->bus->error_status = op;
     } else if (action == BLOCK_ERROR_ACTION_REPORT) {
+        block_acct_failed(blk_get_stats(s->blk), &s->acct);
         if (op & IDE_RETRY_DMA) {
             ide_dma_error(s);
         } else {
@@ -750,6 +753,7 @@ static void ide_dma_cb(void *opaque, int ret)
     if ((s->dma_cmd == IDE_DMA_READ || s->dma_cmd == IDE_DMA_WRITE) &&
         !ide_sect_range_ok(s, sector_num, n)) {
         ide_dma_error(s);
+        block_acct_invalid(blk_get_stats(s->blk), s->acct.type);
         return;
     }
 
@@ -826,7 +830,6 @@ static void ide_sector_write_cb(void *opaque, int ret)
     if (ret == -ECANCELED) {
         return;
     }
-    block_acct_done(blk_get_stats(s->blk), &s->acct);
 
     s->pio_aiocb = NULL;
     s->status &= ~BUSY_STAT;
@@ -837,6 +840,8 @@ static void ide_sector_write_cb(void *opaque, int ret)
         }
     }
 
+    block_acct_done(blk_get_stats(s->blk), &s->acct);
+
     n = s->nsector;
     if (n > s->req_nb_sectors) {
         n = s->req_nb_sectors;
@@ -887,6 +892,7 @@ static void ide_sector_write(IDEState *s)
 
     if (!ide_sect_range_ok(s, sector_num, n)) {
         ide_rw_error(s);
+        block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_WRITE);
         return;
     }
 
@@ -895,7 +901,7 @@ static void ide_sector_write(IDEState *s)
     qemu_iovec_init_external(&s->qiov, &s->iov, 1);
 
     block_acct_start(blk_get_stats(s->blk), &s->acct,
-                     n * BDRV_SECTOR_SIZE, BLOCK_ACCT_READ);
+                     n * BDRV_SECTOR_SIZE, BLOCK_ACCT_WRITE);
     s->pio_aiocb = blk_aio_writev(s->blk, sector_num, &s->qiov, n,
                                   ide_sector_write_cb, s);
 }
diff --git a/hw/ide/macio.c b/hw/ide/macio.c
index 893c9b9bae..3ee962f830 100644
--- a/hw/ide/macio.c
+++ b/hw/ide/macio.c
@@ -286,7 +286,11 @@ static void pmac_ide_atapi_transfer_cb(void *opaque, int ret)
     return;
 
 done:
-    block_acct_done(blk_get_stats(s->blk), &s->acct);
+    if (ret < 0) {
+        block_acct_failed(blk_get_stats(s->blk), &s->acct);
+    } else {
+        block_acct_done(blk_get_stats(s->blk), &s->acct);
+    }
     io->dma_end(opaque);
 
     return;
@@ -348,7 +352,11 @@ static void pmac_ide_transfer_cb(void *opaque, int ret)
 
 done:
     if (s->dma_cmd == IDE_DMA_READ || s->dma_cmd == IDE_DMA_WRITE) {
-        block_acct_done(blk_get_stats(s->blk), &s->acct);
+        if (ret < 0) {
+            block_acct_failed(blk_get_stats(s->blk), &s->acct);
+        } else {
+            block_acct_done(blk_get_stats(s->blk), &s->acct);
+        }
     }
     io->dma_end(opaque);
 }
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 707e7349a2..4797d83683 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -90,7 +90,7 @@ struct SCSIDiskState
     bool tray_locked;
 };
 
-static int scsi_handle_rw_error(SCSIDiskReq *r, int error);
+static int scsi_handle_rw_error(SCSIDiskReq *r, int error, bool acct_failed);
 
 static void scsi_free_request(SCSIRequest *req)
 {
@@ -169,18 +169,18 @@ static void scsi_aio_complete(void *opaque, int ret)
 
     assert(r->req.aiocb != NULL);
     r->req.aiocb = NULL;
-    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
     if (r->req.io_canceled) {
         scsi_req_cancel_complete(&r->req);
         goto done;
     }
 
     if (ret < 0) {
-        if (scsi_handle_rw_error(r, -ret)) {
+        if (scsi_handle_rw_error(r, -ret, true)) {
             goto done;
         }
     }
 
+    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
     scsi_req_complete(&r->req, GOOD);
 
 done:
@@ -247,7 +247,7 @@ static void scsi_dma_complete_noio(SCSIDiskReq *r, int ret)
     }
 
     if (ret < 0) {
-        if (scsi_handle_rw_error(r, -ret)) {
+        if (scsi_handle_rw_error(r, -ret, false)) {
             goto done;
         }
     }
@@ -273,7 +273,11 @@ static void scsi_dma_complete(void *opaque, int ret)
     assert(r->req.aiocb != NULL);
     r->req.aiocb = NULL;
 
-    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    if (ret < 0) {
+        block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    } else {
+        block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    }
     scsi_dma_complete_noio(r, ret);
 }
 
@@ -285,18 +289,18 @@ static void scsi_read_complete(void * opaque, int ret)
 
     assert(r->req.aiocb != NULL);
     r->req.aiocb = NULL;
-    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
     if (r->req.io_canceled) {
         scsi_req_cancel_complete(&r->req);
         goto done;
     }
 
     if (ret < 0) {
-        if (scsi_handle_rw_error(r, -ret)) {
+        if (scsi_handle_rw_error(r, -ret, true)) {
             goto done;
         }
     }
 
+    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
     DPRINTF("Data ready tag=0x%x len=%zd\n", r->req.tag, r->qiov.size);
 
     n = r->qiov.size / 512;
@@ -322,7 +326,7 @@ static void scsi_do_read(SCSIDiskReq *r, int ret)
     }
 
     if (ret < 0) {
-        if (scsi_handle_rw_error(r, -ret)) {
+        if (scsi_handle_rw_error(r, -ret, false)) {
             goto done;
         }
     }
@@ -355,7 +359,11 @@ static void scsi_do_read_cb(void *opaque, int ret)
     assert (r->req.aiocb != NULL);
     r->req.aiocb = NULL;
 
-    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    if (ret < 0) {
+        block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    } else {
+        block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    }
     scsi_do_read(opaque, ret);
 }
 
@@ -407,7 +415,7 @@ static void scsi_read_data(SCSIRequest *req)
  * scsi_handle_rw_error always manages its reference counts, independent
  * of the return value.
  */
-static int scsi_handle_rw_error(SCSIDiskReq *r, int error)
+static int scsi_handle_rw_error(SCSIDiskReq *r, int error, bool acct_failed)
 {
     bool is_read = (r->req.cmd.mode == SCSI_XFER_FROM_DEV);
     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
@@ -415,6 +423,9 @@ static int scsi_handle_rw_error(SCSIDiskReq *r, int error)
                                                    is_read, error);
 
     if (action == BLOCK_ERROR_ACTION_REPORT) {
+        if (acct_failed) {
+            block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct);
+        }
         switch (error) {
         case ENOMEDIUM:
             scsi_check_condition(r, SENSE_CODE(NO_MEDIUM));
@@ -452,7 +463,7 @@ static void scsi_write_complete_noio(SCSIDiskReq *r, int ret)
     }
 
     if (ret < 0) {
-        if (scsi_handle_rw_error(r, -ret)) {
+        if (scsi_handle_rw_error(r, -ret, false)) {
             goto done;
         }
     }
@@ -481,7 +492,11 @@ static void scsi_write_complete(void * opaque, int ret)
     assert (r->req.aiocb != NULL);
     r->req.aiocb = NULL;
 
-    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    if (ret < 0) {
+        block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    } else {
+        block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+    }
     scsi_write_complete_noio(r, ret);
 }
 
@@ -1592,7 +1607,7 @@ static void scsi_unmap_complete_noio(UnmapCBData *data, int ret)
     }
 
     if (ret < 0) {
-        if (scsi_handle_rw_error(r, -ret)) {
+        if (scsi_handle_rw_error(r, -ret, false)) {
             goto done;
         }
     }
@@ -1696,18 +1711,19 @@ static void scsi_write_same_complete(void *opaque, int ret)
 
     assert(r->req.aiocb != NULL);
     r->req.aiocb = NULL;
-    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
     if (r->req.io_canceled) {
         scsi_req_cancel_complete(&r->req);
         goto done;
     }
 
     if (ret < 0) {
-        if (scsi_handle_rw_error(r, -ret)) {
+        if (scsi_handle_rw_error(r, -ret, true)) {
             goto done;
         }
     }
 
+    block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+
     data->nb_sectors -= data->iov.iov_len / 512;
     data->sector += data->iov.iov_len / 512;
     data->iov.iov_len = MIN(data->nb_sectors * 512, data->iov.iov_len);