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

Block patches for 2.3

# gpg: Signature made Fri 06 Feb 2015 17:14:10 GMT using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (47 commits)
  block/raw-posix.c: Fix raw_getlength() on Mac OS X block devices
  block: Eliminate silly QERR_ macros used for encryption keys
  block: New bdrv_add_key(), convert monitor to use it
  blockdev: Eliminate silly QERR_BLOCK_JOB_NOT_ACTIVE macro
  blockdev: Give find_block_job() an Error ** parameter
  qcow2: Rewrite qcow2_alloc_bytes()
  block: Give always priority to unused entries in the qcow2 L2 cache
  nbd: fix max_discard/max_transfer_length
  block: introduce BDRV_REQUEST_MAX_SECTORS
  nbd: Improve error messages
  iotests: Fix 104 for NBD
  iotests: Fix 100 for nbd
  iotests: Fix 083
  block: fix off-by-one error in qcow and qcow2
  qemu-iotests: add 116 invalid QED input file tests
  qed: check for header size overflow
  block/dmg: improve zeroes handling
  block/dmg: support bzip2 block entry types
  block/dmg: factor out block type check
  block/dmg: use SectorNumber from BLKX header
  ...

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

6 files changed, 240 insertions, 98 deletions

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 39c5d7103c..be957d1117 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -96,9 +96,7 @@ static void handle_notify(EventNotifier *e)
     event_notifier_test_and_clear(&s->host_notifier);
     blk_io_plug(s->conf->conf.blk);
     for (;;) {
-        MultiReqBuffer mrb = {
-            .num_writes = 0,
-        };
+        MultiReqBuffer mrb = {};
         int ret;
 
         /* Disable guest->host notifies to avoid unnecessary vmexits */
@@ -120,7 +118,9 @@ static void handle_notify(EventNotifier *e)
             virtio_blk_handle_request(req, &mrb);
         }
 
-        virtio_submit_multiwrite(s->conf->conf.blk, &mrb);
+        if (mrb.num_reqs) {
+            virtio_blk_submit_multireq(s->conf->conf.blk, &mrb);
+        }
 
         if (likely(ret == -EAGAIN)) { /* vring emptied */
             /* Re-enable guest->host notifies and stop processing the vring.
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 4032fcae27..1a8a176dcc 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -34,6 +34,7 @@ VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s)
     req->dev = s;
     req->qiov.size = 0;
     req->next = NULL;
+    req->mr_next = NULL;
     return req;
 }
 
@@ -84,20 +85,32 @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
 
 static void virtio_blk_rw_complete(void *opaque, int ret)
 {
-    VirtIOBlockReq *req = opaque;
+    VirtIOBlockReq *next = opaque;
 
-    trace_virtio_blk_rw_complete(req, ret);
+    while (next) {
+        VirtIOBlockReq *req = next;
+        next = req->mr_next;
+        trace_virtio_blk_rw_complete(req, ret);
 
-    if (ret) {
-        int p = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
-        bool is_read = !(p & VIRTIO_BLK_T_OUT);
-        if (virtio_blk_handle_rw_error(req, -ret, is_read))
-            return;
-    }
+        if (req->qiov.nalloc != -1) {
+            /* If nalloc is != 1 req->qiov is a local copy of the original
+             * external iovec. It was allocated in submit_merged_requests
+             * to be able to merge requests. */
+            qemu_iovec_destroy(&req->qiov);
+        }
 
-    virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
-    block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
-    virtio_blk_free_request(req);
+        if (ret) {
+            int p = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
+            bool is_read = !(p & VIRTIO_BLK_T_OUT);
+            if (virtio_blk_handle_rw_error(req, -ret, is_read)) {
+                continue;
+            }
+        }
+
+        virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
+        block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
+        virtio_blk_free_request(req);
+    }
 }
 
 static void virtio_blk_flush_complete(void *opaque, int ret)
@@ -291,24 +304,127 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
     }
 }
 
-void virtio_submit_multiwrite(BlockBackend *blk, MultiReqBuffer *mrb)
+static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
+                                   int start, int num_reqs, int niov)
 {
-    int i, ret;
+    QEMUIOVector *qiov = &mrb->reqs[start]->qiov;
+    int64_t sector_num = mrb->reqs[start]->sector_num;
+    int nb_sectors = mrb->reqs[start]->qiov.size / BDRV_SECTOR_SIZE;
+    bool is_write = mrb->is_write;
+
+    if (num_reqs > 1) {
+        int i;
+        struct iovec *tmp_iov = qiov->iov;
+        int tmp_niov = qiov->niov;
+
+        /* mrb->reqs[start]->qiov was initialized from external so we can't
+         * modifiy it here. We need to initialize it locally and then add the
+         * external iovecs. */
+        qemu_iovec_init(qiov, niov);
+
+        for (i = 0; i < tmp_niov; i++) {
+            qemu_iovec_add(qiov, tmp_iov[i].iov_base, tmp_iov[i].iov_len);
+        }
 
-    if (!mrb->num_writes) {
+        for (i = start + 1; i < start + num_reqs; i++) {
+            qemu_iovec_concat(qiov, &mrb->reqs[i]->qiov, 0,
+                              mrb->reqs[i]->qiov.size);
+            mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
+            nb_sectors += mrb->reqs[i]->qiov.size / BDRV_SECTOR_SIZE;
+        }
+        assert(nb_sectors == qiov->size / BDRV_SECTOR_SIZE);
+
+        trace_virtio_blk_submit_multireq(mrb, start, num_reqs, sector_num,
+                                         nb_sectors, is_write);
+        block_acct_merge_done(blk_get_stats(blk),
+                              is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ,
+                              num_reqs - 1);
+    }
+
+    if (is_write) {
+        blk_aio_writev(blk, sector_num, qiov, nb_sectors,
+                       virtio_blk_rw_complete, mrb->reqs[start]);
+    } else {
+        blk_aio_readv(blk, sector_num, qiov, nb_sectors,
+                      virtio_blk_rw_complete, mrb->reqs[start]);
+    }
+}
+
+static int multireq_compare(const void *a, const void *b)
+{
+    const VirtIOBlockReq *req1 = *(VirtIOBlockReq **)a,
+                         *req2 = *(VirtIOBlockReq **)b;
+
+    /*
+     * Note that we can't simply subtract sector_num1 from sector_num2
+     * here as that could overflow the return value.
+     */
+    if (req1->sector_num > req2->sector_num) {
+        return 1;
+    } else if (req1->sector_num < req2->sector_num) {
+        return -1;
+    } else {
+        return 0;
+    }
+}
+
+void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
+{
+    int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0;
+    int max_xfer_len = 0;
+    int64_t sector_num = 0;
+
+    if (mrb->num_reqs == 1) {
+        submit_requests(blk, mrb, 0, 1, -1);
+        mrb->num_reqs = 0;
         return;
     }
 
-    ret = blk_aio_multiwrite(blk, mrb->blkreq, mrb->num_writes);
-    if (ret != 0) {
-        for (i = 0; i < mrb->num_writes; i++) {
-            if (mrb->blkreq[i].error) {
-                virtio_blk_rw_complete(mrb->blkreq[i].opaque, -EIO);
+    max_xfer_len = blk_get_max_transfer_length(mrb->reqs[0]->dev->blk);
+    max_xfer_len = MIN_NON_ZERO(max_xfer_len, BDRV_REQUEST_MAX_SECTORS);
+
+    qsort(mrb->reqs, mrb->num_reqs, sizeof(*mrb->reqs),
+          &multireq_compare);
+
+    for (i = 0; i < mrb->num_reqs; i++) {
+        VirtIOBlockReq *req = mrb->reqs[i];
+        if (num_reqs > 0) {
+            bool merge = true;
+
+            /* merge would exceed maximum number of IOVs */
+            if (niov + req->qiov.niov > IOV_MAX) {
+                merge = false;
+            }
+
+            /* merge would exceed maximum transfer length of backend device */
+            if (req->qiov.size / BDRV_SECTOR_SIZE + nb_sectors > max_xfer_len) {
+                merge = false;
+            }
+
+            /* requests are not sequential */
+            if (sector_num + nb_sectors != req->sector_num) {
+                merge = false;
+            }
+
+            if (!merge) {
+                submit_requests(blk, mrb, start, num_reqs, niov);
+                num_reqs = 0;
             }
         }
+
+        if (num_reqs == 0) {
+            sector_num = req->sector_num;
+            nb_sectors = niov = 0;
+            start = i;
+        }
+
+        nb_sectors += req->qiov.size / BDRV_SECTOR_SIZE;
+        niov += req->qiov.niov;
+        num_reqs++;
     }
 
-    mrb->num_writes = 0;
+    submit_requests(blk, mrb, start, num_reqs, niov);
+    mrb->num_reqs = 0;
 }
 
 static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
@@ -319,7 +435,9 @@ static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
     /*
      * Make sure all outstanding writes are posted to the backing device.
      */
-    virtio_submit_multiwrite(req->dev->blk, mrb);
+    if (mrb->is_write && mrb->num_reqs > 0) {
+        virtio_blk_submit_multireq(req->dev->blk, mrb);
+    }
     blk_aio_flush(req->dev->blk, virtio_blk_flush_complete, req);
 }
 
@@ -329,6 +447,9 @@ static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
     uint64_t nb_sectors = size >> BDRV_SECTOR_BITS;
     uint64_t total_sectors;
 
+    if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
+        return false;
+    }
     if (sector & dev->sector_mask) {
         return false;
     }
@@ -342,60 +463,6 @@ static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
     return true;
 }
 
-static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb)
-{
-    BlockRequest *blkreq;
-    uint64_t sector;
-
-    sector = virtio_ldq_p(VIRTIO_DEVICE(req->dev), &req->out.sector);
-
-    trace_virtio_blk_handle_write(req, sector, req->qiov.size / 512);
-
-    if (!virtio_blk_sect_range_ok(req->dev, sector, req->qiov.size)) {
-        virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
-        virtio_blk_free_request(req);
-        return;
-    }
-
-    block_acct_start(blk_get_stats(req->dev->blk), &req->acct, req->qiov.size,
-                     BLOCK_ACCT_WRITE);
-
-    if (mrb->num_writes == 32) {
-        virtio_submit_multiwrite(req->dev->blk, mrb);
-    }
-
-    blkreq = &mrb->blkreq[mrb->num_writes];
-    blkreq->sector = sector;
-    blkreq->nb_sectors = req->qiov.size / BDRV_SECTOR_SIZE;
-    blkreq->qiov = &req->qiov;
-    blkreq->cb = virtio_blk_rw_complete;
-    blkreq->opaque = req;
-    blkreq->error = 0;
-
-    mrb->num_writes++;
-}
-
-static void virtio_blk_handle_read(VirtIOBlockReq *req)
-{
-    uint64_t sector;
-
-    sector = virtio_ldq_p(VIRTIO_DEVICE(req->dev), &req->out.sector);
-
-    trace_virtio_blk_handle_read(req, sector, req->qiov.size / 512);
-
-    if (!virtio_blk_sect_range_ok(req->dev, sector, req->qiov.size)) {
-        virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
-        virtio_blk_free_request(req);
-        return;
-    }
-
-    block_acct_start(blk_get_stats(req->dev->blk), &req->acct, req->qiov.size,
-                     BLOCK_ACCT_READ);
-    blk_aio_readv(req->dev->blk, sector, &req->qiov,
-                  req->qiov.size / BDRV_SECTOR_SIZE,
-                  virtio_blk_rw_complete, req);
-}
-
 void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
 {
     uint32_t type;
@@ -430,11 +497,58 @@ void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
 
     type = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
 
-    if (type & VIRTIO_BLK_T_FLUSH) {
+    /* VIRTIO_BLK_T_OUT defines the command direction. VIRTIO_BLK_T_BARRIER
+     * is an optional flag. Altough a guest should not send this flag if
+     * not negotiated we ignored it in the past. So keep ignoring it. */
+    switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
+    case VIRTIO_BLK_T_IN:
+    {
+        bool is_write = type & VIRTIO_BLK_T_OUT;
+        req->sector_num = virtio_ldq_p(VIRTIO_DEVICE(req->dev),
+                                       &req->out.sector);
+
+        if (is_write) {
+            qemu_iovec_init_external(&req->qiov, iov, out_num);
+            trace_virtio_blk_handle_write(req, req->sector_num,
+                                          req->qiov.size / BDRV_SECTOR_SIZE);
+        } else {
+            qemu_iovec_init_external(&req->qiov, in_iov, in_num);
+            trace_virtio_blk_handle_read(req, req->sector_num,
+                                         req->qiov.size / BDRV_SECTOR_SIZE);
+        }
+
+        if (!virtio_blk_sect_range_ok(req->dev, req->sector_num,
+                                      req->qiov.size)) {
+            virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+            virtio_blk_free_request(req);
+            return;
+        }
+
+        block_acct_start(blk_get_stats(req->dev->blk),
+                         &req->acct, req->qiov.size,
+                         is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
+
+        /* merge would exceed maximum number of requests or IO direction
+         * changes */
+        if (mrb->num_reqs > 0 && (mrb->num_reqs == VIRTIO_BLK_MAX_MERGE_REQS ||
+                                  is_write != mrb->is_write ||
+                                  !req->dev->conf.request_merging)) {
+            virtio_blk_submit_multireq(req->dev->blk, mrb);
+        }
+
+        assert(mrb->num_reqs < VIRTIO_BLK_MAX_MERGE_REQS);
+        mrb->reqs[mrb->num_reqs++] = req;
+        mrb->is_write = is_write;
+        break;
+    }
+    case VIRTIO_BLK_T_FLUSH:
         virtio_blk_handle_flush(req, mrb);
-    } else if (type & VIRTIO_BLK_T_SCSI_CMD) {
+        break;
+    case VIRTIO_BLK_T_SCSI_CMD:
         virtio_blk_handle_scsi(req);
-    } else if (type & VIRTIO_BLK_T_GET_ID) {
+        break;
+    case VIRTIO_BLK_T_GET_ID:
+    {
         VirtIOBlock *s = req->dev;
 
         /*
@@ -448,14 +562,9 @@ void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
         iov_from_buf(in_iov, in_num, 0, serial, size);
         virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
         virtio_blk_free_request(req);
-    } else if (type & VIRTIO_BLK_T_OUT) {
-        qemu_iovec_init_external(&req->qiov, iov, out_num);
-        virtio_blk_handle_write(req, mrb);
-    } else if (type == VIRTIO_BLK_T_IN || type == VIRTIO_BLK_T_BARRIER) {
-        /* VIRTIO_BLK_T_IN is 0, so we can't just & it. */
-        qemu_iovec_init_external(&req->qiov, in_iov, in_num);
-        virtio_blk_handle_read(req);
-    } else {
+        break;
+    }
+    default:
         virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
         virtio_blk_free_request(req);
     }
@@ -465,9 +574,7 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 {
     VirtIOBlock *s = VIRTIO_BLK(vdev);
     VirtIOBlockReq *req;
-    MultiReqBuffer mrb = {
-        .num_writes = 0,
-    };
+    MultiReqBuffer mrb = {};
 
     /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
      * dataplane here instead of waiting for .set_status().
@@ -481,7 +588,9 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
         virtio_blk_handle_request(req, &mrb);
     }
 
-    virtio_submit_multiwrite(s->blk, &mrb);
+    if (mrb.num_reqs) {
+        virtio_blk_submit_multireq(s->blk, &mrb);
+    }
 
     /*
      * FIXME: Want to check for completions before returning to guest mode,
@@ -494,9 +603,7 @@ static void virtio_blk_dma_restart_bh(void *opaque)
 {
     VirtIOBlock *s = opaque;
     VirtIOBlockReq *req = s->rq;
-    MultiReqBuffer mrb = {
-        .num_writes = 0,
-    };
+    MultiReqBuffer mrb = {};
 
     qemu_bh_delete(s->bh);
     s->bh = NULL;
@@ -509,7 +616,9 @@ static void virtio_blk_dma_restart_bh(void *opaque)
         req = next;
     }
 
-    virtio_submit_multiwrite(s->blk, &mrb);
+    if (mrb.num_reqs) {
+        virtio_blk_submit_multireq(s->blk, &mrb);
+    }
 }
 
 static void virtio_blk_dma_restart_cb(void *opaque, int running,
@@ -842,6 +951,8 @@ static Property virtio_blk_properties[] = {
 #ifdef __linux__
     DEFINE_PROP_BIT("scsi", VirtIOBlock, conf.scsi, 0, true),
 #endif
+    DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0,
+                    true),
     DEFINE_PROP_BIT("x-data-plane", VirtIOBlock, conf.data_plane, 0, false),
     DEFINE_PROP_END_OF_LIST(),
 };
diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c
index a71e6e014f..1bf8b34528 100644
--- a/hw/ide/atapi.c
+++ b/hw/ide/atapi.c
@@ -394,6 +394,23 @@ static void ide_atapi_cmd_read(IDEState *s, int lba, int nb_sectors,
     }
 }
 
+
+/* Called by *_restart_bh when the transfer function points
+ * to ide_atapi_cmd
+ */
+void ide_atapi_dma_restart(IDEState *s)
+{
+    /*
+     * I'm not sure we have enough stored to restart the command
+     * safely, so give the guest an error it should recover from.
+     * I'm assuming most guests will try to recover from something
+     * listed as a medium error on a CD; it seems to work on Linux.
+     * This would be more of a problem if we did any other type of
+     * DMA operation.
+     */
+    ide_atapi_cmd_error(s, MEDIUM_ERROR, ASC_NO_SEEK_COMPLETE);
+}
+
 static inline uint8_t ide_atapi_set_profile(uint8_t *buf, uint8_t *index,
                                             uint16_t profile)
 {
diff --git a/hw/ide/core.c b/hw/ide/core.c
index d4af5e2eb1..ac3f015a8d 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -2417,6 +2417,7 @@ static int ide_drive_pio_post_load(void *opaque, int version_id)
     s->end_transfer_func = transfer_end_table[s->end_transfer_fn_idx];
     s->data_ptr = s->io_buffer + s->cur_io_buffer_offset;
     s->data_end = s->data_ptr + s->cur_io_buffer_len;
+    s->atapi_dma = s->feature & 1; /* as per cmd_packet */
 
     return 0;
 }
diff --git a/hw/ide/internal.h b/hw/ide/internal.h
index c998003bf3..ee9a57f039 100644
--- a/hw/ide/internal.h
+++ b/hw/ide/internal.h
@@ -289,6 +289,7 @@ typedef struct IDEDMAOps IDEDMAOps;
 #define ATAPI_INT_REASON_TAG            0xf8
 
 /* same constants as bochs */
+#define ASC_NO_SEEK_COMPLETE                 0x02
 #define ASC_ILLEGAL_OPCODE                   0x20
 #define ASC_LOGICAL_BLOCK_OOR                0x21
 #define ASC_INV_FIELD_IN_CMD_PACKET          0x24
@@ -530,6 +531,7 @@ void ide_dma_error(IDEState *s);
 
 void ide_atapi_cmd_ok(IDEState *s);
 void ide_atapi_cmd_error(IDEState *s, int sense_key, int asc);
+void ide_atapi_dma_restart(IDEState *s);
 void ide_atapi_io_error(IDEState *s, int ret);
 
 void ide_ioport_write(void *opaque, uint32_t addr, uint32_t val);
diff --git a/hw/ide/pci.c b/hw/ide/pci.c
index bee5ad39fe..e3f2054a90 100644
--- a/hw/ide/pci.c
+++ b/hw/ide/pci.c
@@ -235,6 +235,17 @@ static void bmdma_restart_bh(void *opaque)
         }
     } else if (error_status & IDE_RETRY_FLUSH) {
         ide_flush_cache(bmdma_active_if(bm));
+    } else {
+        IDEState *s = bmdma_active_if(bm);
+
+        /*
+         * We've not got any bits to tell us about ATAPI - but
+         * we do have the end_transfer_func that tells us what
+         * we're trying to do.
+         */
+        if (s->end_transfer_func == ide_atapi_cmd) {
+            ide_atapi_dma_restart(s);
+        }
     }
 }