Series comparison

-[Qemu-devel] [PULL 0/2] Block patches
+[Qemu-devel] [PULL 0/4] Block patches
-The following changes since commit 577caa2672ccde7352fda3ef17e44993de862f0e:
+The following changes since commit 20d6c7312f1b812bb9c750f4087f69ac8485cc90:
-  Merge remote-tracking branch 'remotes/edgar/tags/edgar/mmio-exec-v2.for-upstream' into staging (2017-06-27 16:56:55 +0100)
+  Merge remote-tracking branch 'remotes/palmer/tags/riscv-for-master-3.2-part1' into staging (2019-01-03 13:26:30 +0000)
-are available in the git repository at:
+are available in the Git repository at:
   git://github.com/stefanha/qemu.git tags/block-pull-request
-for you to fetch changes up to 439778e6b4a20c8fe6a6a92a17013b09c4ae55d0:
+for you to fetch changes up to 39a0408e768cd00142f5b57d27ab234282bf4df5:
-  virtio-pci: use ioeventfd even when KVM is disabled (2017-06-28 13:18:53 +0100)
+  dmg: don't skip zero chunk (2019-01-04 11:15:09 +0000)
 ----------------------------------------------------------------
 Pull request
 Bug fixes for the .dmg image file format.
 ----------------------------------------------------------------
-----------------------------------------------------------------
+Julio Faracco (1):
   dmg: Fixing wrong dmg block type value for block terminator.
-Stefan Hajnoczi (2):
+yuchenlin (3):
-  virtio-blk: trace vdev so devices can be distinguished
+  dmg: fix binary search
-  virtio-pci: use ioeventfd even when KVM is disabled
+  dmg: use enumeration type instead of hard coding number
   dmg: don't skip zero chunk
- hw/block/virtio-blk.c  | 12 +++++++-----
+ block/dmg.c | 31 ++++++++++++++++++++-----------
- hw/virtio/virtio-pci.c |  2 +-
+file changed, 20 insertions(+), 11 deletions(-)
  hw/block/trace-events  | 10 +++++-----
 files changed, 13 insertions(+), 11 deletions(-)
 --
-.9.4
+.20.1

-New patch
+[Qemu-devel] [PULL 1/4] dmg: Fixing wrong dmg block type value for block terminator.
+From: Julio Faracco <jcfaracco@gmail.com>
+This is a trivial patch to fix a wrong value for block terminator.
+The old value was 0x7fffffff which is wrong. It was not affecting the
+code because QEMU dmg block is not handling block terminator right now.
+Neverthless, it should be fixed.
+Signed-off-by: Julio Faracco <jcfaracco@gmail.com>
+Reviewed-by: yuchenlin <yuchenlin@synology.com>
+Message-id: 20181228145055.18039-1-jcfaracco@gmail.com
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+---
+ block/dmg.c | 2 +-
+file changed, 1 insertion(+), 1 deletion(-)
+diff --git a/block/dmg.c b/block/dmg.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block/dmg.c
++++ b/block/dmg.c
+@@ -XXX,XX +XXX,XX @@ enum {
+     UDBZ,
+     ULFO,
+     UDCM = 0x7ffffffe, /* Comments */
+-    UDLE               /* Last Entry */
++    UDLE = 0xffffffff  /* Last Entry */
+ };
+ static int dmg_probe(const uint8_t *buf, int buf_size, const char *filename)
+--
+.20.1

-[Qemu-devel] [PULL 2/2] virtio-pci: use ioeventfd even when KVM is disabled
+[Qemu-devel] [PULL 2/4] dmg: fix binary search
-Old kvm.ko versions only supported a tiny number of ioeventfds so
+From: yuchenlin <npes87184@gmail.com>
 virtio-pci avoids ioeventfds when kvm_has_many_ioeventfds() returns 0.
-Do not check kvm_has_many_ioeventfds() when KVM is disabled since it
+There is a possible hang in original binary search implementation. That is
-always returns 0.  Since commit 8c56c1a592b5092d91da8d8943c17777d6462a6f
+if chunk1 = 4, chunk2 = 5, chunk3 = 4, and we go else case.
 ("memory: emulate ioeventfd") it has been possible to use ioeventfds in
 qtest or TCG mode.
-This patch makes -device virtio-blk-pci,iothread=iothread0 work even
+The chunk1 will be still 4, and so on.
 when KVM is disabled.
-I have tested that virtio-blk-pci works under TCG both with and without
+Signed-off-by: yuchenlin <npes87184@gmail.com>
-iothread.
+Message-id: 20190103114700.9686-2-npes87184@gmail.com
 This patch fixes qemu-iotests 068, which was accidentally merged early
 despite the dependency on ioeventfd.
 Cc: Michael S. Tsirkin <mst@redhat.com>
 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
 Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
 Message-id: 20170615163813.7255-2-stefanha@redhat.com
 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
 ---
- hw/virtio/virtio-pci.c | 2 +-
+ block/dmg.c | 10 +++++++---
-file changed, 1 insertion(+), 1 deletion(-)
+file changed, 7 insertions(+), 3 deletions(-)
-diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
+diff --git a/block/dmg.c b/block/dmg.c
 index XXXXXXX..XXXXXXX 100644
---- a/hw/virtio/virtio-pci.c
+--- a/block/dmg.c
-+++ b/hw/virtio/virtio-pci.c
++++ b/block/dmg.c
-@@ -XXX,XX +XXX,XX @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
+@@ -XXX,XX +XXX,XX @@ static inline uint32_t search_chunk(BDRVDMGState *s, uint64_t sector_num)
-     bool pcie_port = pci_bus_is_express(pci_dev->bus) &&
+ {
-                      !pci_bus_is_root(pci_dev->bus);
+     /* binary search */
+     uint32_t chunk1 = 0, chunk2 = s->n_chunks, chunk3;
--    if (!kvm_has_many_ioeventfds()) {
+-    while (chunk1 != chunk2) {
-+    if (kvm_enabled() && !kvm_has_many_ioeventfds()) {
++    while (chunk1 <= chunk2) {
-         proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD;
+         chunk3 = (chunk1 + chunk2) / 2;
          if (s->sectors[chunk3] > sector_num) {
 -            chunk2 = chunk3;
 +            if (chunk3 == 0) {
 +                goto err;
 +            }
 +            chunk2 = chunk3 - 1;
          } else if (s->sectors[chunk3] + s->sectorcounts[chunk3] > sector_num) {
              return chunk3;
          } else {
 -            chunk1 = chunk3;
 +            chunk1 = chunk3 + 1;
          }
      }
++err:
+     return s->n_chunks; /* error */
+ }
 --
-.9.4
+.20.1

-New patch
+[Qemu-devel] [PULL 3/4] dmg: use enumeration type instead of hard coding number
+From: yuchenlin <npes87184@gmail.com>
+Signed-off-by: yuchenlin <npes87184@gmail.com>
+Reviewed-by: Julio Faracco <jcfaracco@gmail.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Message-id: 20190103114700.9686-3-npes87184@gmail.com
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+---
+ block/dmg.c | 4 ++--
+file changed, 2 insertions(+), 2 deletions(-)
+diff --git a/block/dmg.c b/block/dmg.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block/dmg.c
++++ b/block/dmg.c
+@@ -XXX,XX +XXX,XX @@ static int dmg_read_mish_block(BDRVDMGState *s, DmgHeaderState *ds,
+         /* all-zeroes sector (type 2) does not need to be "uncompressed" and can
+          * therefore be unbounded. */
+-        if (s->types[i] != 2 && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
++        if (s->types[i] != UDIG && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
+             error_report("sector count %" PRIu64 " for chunk %" PRIu32
+                          " is larger than max (%u)",
+                          s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
+@@ -XXX,XX +XXX,XX @@ dmg_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+         /* Special case: current chunk is all zeroes. Do not perform a memcpy as
+          * s->uncompressed_chunk may be too small to cover the large all-zeroes
+          * section. dmg_read_chunk is called to find s->current_chunk */
+-        if (s->types[s->current_chunk] == 2) { /* all zeroes block entry */
++        if (s->types[s->current_chunk] == UDIG) { /* all zeroes block entry */
+             qemu_iovec_memset(qiov, i * 512, 0, 512);
+             continue;
+         }
+--
+.20.1

-[Qemu-devel] [PULL 1/2] virtio-blk: trace vdev so devices can be distinguished
+[Qemu-devel] [PULL 4/4] dmg: don't skip zero chunk
-It is hard to analyze trace logs with multiple virtio-blk devices
+From: yuchenlin <npes87184@gmail.com>
 because none of the trace events include the VirtIODevice *vdev.
-This patch adds vdev so it's clear which device a request is associated
+The dmg file has many tables which describe: "start from sector XXX to
-with.
+sector XXX, the compression method is XXX and where the compressed data
 resides on".
-I considered using VirtIOBlock *s instead but VirtIODevice *vdev is more
+Each sector in the expanded file should be covered by a table. The table
-general and may be correlated with generic virtio trace events like
+will describe the offset of compressed data (or raw depends on the type)
-virtio_set_status.
+in the dmg.
-Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+For example:
-Reviewed-by: Fam Zheng <famz@redhat.com>
-Message-id: 20170614092930.11234-1-stefanha@redhat.com
+[-----------The expanded file------------]
 [---bzip table ---]/* zeros */[---zlib---]
     ^
     | if we want to read this sector.
 we will find bzip table which contains this sector, and get the
 compressed data offset, read it from dmg, uncompress it, finally write to
 expanded file.
 If we skip zero chunk (table), some sector cannot find the table which
 will cause search_chunk() return s->n_chunks, dmg_read_chunk() return -1
 and finally causing dmg_co_preadv() return EIO.
 See:
 [-----------The expanded file------------]
 [---bzip table ---]/* zeros */[---zlib---]
                     ^
                     | if we want to read this sector.
 Oops, we cannot find the table contains it...
 In the original implementation, we don't have zero table. When we try to
 read sector inside the zero chunk. We will get EIO, and skip reading.
 After this patch, we treat zero chunk the same as ignore chunk, it will
 directly write zero and avoid some sector may not find the table.
 After this patch:
 [-----------The expanded file------------]
 [---bzip table ---][--zeros--][---zlib---]
 Signed-off-by: yuchenlin <npes87184@gmail.com>
 Reviewed-by: Julio Faracco <jcfaracco@gmail.com>
 Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
 Message-id: 20190103114700.9686-4-npes87184@gmail.com
 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
 ---
- hw/block/virtio-blk.c | 12 +++++++-----
+ block/dmg.c | 19 ++++++++++++-------
- hw/block/trace-events | 10 +++++-----
+file changed, 12 insertions(+), 7 deletions(-)
 files changed, 12 insertions(+), 10 deletions(-)
-diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
+diff --git a/block/dmg.c b/block/dmg.c
 index XXXXXXX..XXXXXXX 100644
---- a/hw/block/virtio-blk.c
+--- a/block/dmg.c
-+++ b/hw/block/virtio-blk.c
++++ b/block/dmg.c
-@@ -XXX,XX +XXX,XX @@ static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
+@@ -XXX,XX +XXX,XX @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
-     VirtIOBlock *s = req->dev;
+     case UDRW: /* copy */
-     VirtIODevice *vdev = VIRTIO_DEVICE(s);
+         uncompressed_sectors = DIV_ROUND_UP(s->lengths[chunk], 512);
+         break;
--    trace_virtio_blk_req_complete(req, status);
+-    case UDIG: /* zero */
-+    trace_virtio_blk_req_complete(vdev, req, status);
++    case UDZE: /* zero */
++    case UDIG: /* ignore */
-     stb_p(&req->in->status, status);
+         /* as the all-zeroes block may be large, it is treated specially: the
-     virtqueue_push(req->vq, &req->elem, req->in_len);
+          * sector is not copied from a large buffer, a simple memset is used
-@@ -XXX,XX +XXX,XX @@ static void virtio_blk_rw_complete(void *opaque, int ret)
+          * instead. Therefore uncompressed_sectors does not need to be set. */
@@ -XXX,XX +XXX,XX @@ typedef struct DmgHeaderState {
  static bool dmg_is_known_block_type(uint32_t entry_type)
  {
-     VirtIOBlockReq *next = opaque;
+     switch (entry_type) {
-     VirtIOBlock *s = next->dev;
++    case UDZE:    /* zeros */
-+    VirtIODevice *vdev = VIRTIO_DEVICE(s);
+     case UDRW:    /* uncompressed */
+-    case UDIG:    /* zeroes */
-     aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
++    case UDIG:    /* ignore */
-     while (next) {
+     case UDZO:    /* zlib */
-         VirtIOBlockReq *req = next;
+         return true;
-         next = req->mr_next;
+     case UDBZ:    /* bzip2 */
--        trace_virtio_blk_rw_complete(req, ret);
+@@ -XXX,XX +XXX,XX @@ static int dmg_read_mish_block(BDRVDMGState *s, DmgHeaderState *ds,
-+        trace_virtio_blk_rw_complete(vdev, req, ret);
+         /* sector count */
+         s->sectorcounts[i] = buff_read_uint64(buffer, offset + 0x10);
-         if (req->qiov.nalloc != -1) {
-             /* If nalloc is != 1 req->qiov is a local copy of the original
+-        /* all-zeroes sector (type 2) does not need to be "uncompressed" and can
-@@ -XXX,XX +XXX,XX @@ static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
+-         * therefore be unbounded. */
-             mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
+-        if (s->types[i] != UDIG && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
 +        /* all-zeroes sector (type UDZE and UDIG) does not need to be
 +         * "uncompressed" and can therefore be unbounded. */
 +        if (s->types[i] != UDZE && s->types[i] != UDIG
 +            && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
              error_report("sector count %" PRIu64 " for chunk %" PRIu32
                           " is larger than max (%u)",
                           s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
@@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
                  return -1;
              }
              break;
 -        case UDIG: /* zero */
 +        case UDZE: /* zeros */
 +        case UDIG: /* ignore */
              /* see dmg_read, it is treated specially. No buffer needs to be
               * pre-filled, the zeroes can be set directly. */
              break;
@@ -XXX,XX +XXX,XX @@ dmg_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
          /* Special case: current chunk is all zeroes. Do not perform a memcpy as
           * s->uncompressed_chunk may be too small to cover the large all-zeroes
           * section. dmg_read_chunk is called to find s->current_chunk */
 -        if (s->types[s->current_chunk] == UDIG) { /* all zeroes block entry */
 +        if (s->types[s->current_chunk] == UDZE
 +            || s->types[s->current_chunk] == UDIG) { /* all zeroes block entry */
              qemu_iovec_memset(qiov, i * 512, 0, 512);
              continue;
          }
--        trace_virtio_blk_submit_multireq(mrb, start, num_reqs,
-+        trace_virtio_blk_submit_multireq(VIRTIO_DEVICE(mrb->reqs[start]->dev),
-+                                         mrb, start, num_reqs,
-                                          sector_num << BDRV_SECTOR_BITS,
-                                          qiov->size, is_write);
-         block_acct_merge_done(blk_get_stats(blk),
-@@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
-         if (is_write) {
-             qemu_iovec_init_external(&req->qiov, iov, out_num);
--            trace_virtio_blk_handle_write(req, req->sector_num,
-+            trace_virtio_blk_handle_write(vdev, 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,
-+            trace_virtio_blk_handle_read(vdev, req, req->sector_num,
-                                          req->qiov.size / BDRV_SECTOR_SIZE);
-         }
-diff --git a/hw/block/trace-events b/hw/block/trace-events
-index XXXXXXX..XXXXXXX 100644
---- a/hw/block/trace-events
-+++ b/hw/block/trace-events
-@@ -XXX,XX +XXX,XX @@
- # See docs/tracing.txt for syntax documentation.
- # hw/block/virtio-blk.c
--virtio_blk_req_complete(void *req, int status) "req %p status %d"
--virtio_blk_rw_complete(void *req, int ret) "req %p ret %d"
--virtio_blk_handle_write(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
--virtio_blk_handle_read(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
--virtio_blk_submit_multireq(void *mrb, int start, int num_reqs, uint64_t offset, size_t size, bool is_write) "mrb %p start %d num_reqs %d offset %"PRIu64" size %zu is_write %d"
-+virtio_blk_req_complete(void *vdev, void *req, int status) "vdev %p req %p status %d"
-+virtio_blk_rw_complete(void *vdev, void *req, int ret) "vdev %p req %p ret %d"
-+virtio_blk_handle_write(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
-+virtio_blk_handle_read(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
-+virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint64_t offset, size_t size, bool is_write) "vdev %p mrb %p start %d num_reqs %d offset %"PRIu64" size %zu is_write %d"
- # hw/block/hd-geometry.c
- hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d"
 --
-.9.4
+.20.1

It is hard to analyze trace logs with multiple virtio-blk devices
because none of the trace events include the VirtIODevice *vdev.

This patch adds vdev so it's clear which device a request is associated
with.

I considered using VirtIOBlock *s instead but VirtIODevice *vdev is more
general and may be correlated with generic virtio trace events like
virtio_set_status.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Message-id: 20170614092930.11234-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/block/virtio-blk.c | 12 +++++++-----
 hw/block/trace-events | 10 +++++-----
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -XXX,XX +XXX,XX @@ static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
     VirtIOBlock *s = req->dev;
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
 
-    trace_virtio_blk_req_complete(req, status);
+    trace_virtio_blk_req_complete(vdev, req, status);
 
     stb_p(&req->in->status, status);
     virtqueue_push(req->vq, &req->elem, req->in_len);
@@ -XXX,XX +XXX,XX @@ static void virtio_blk_rw_complete(void *opaque, int ret)
 {
     VirtIOBlockReq *next = opaque;
     VirtIOBlock *s = next->dev;
+    VirtIODevice *vdev = VIRTIO_DEVICE(s);
 
     aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
     while (next) {
         VirtIOBlockReq *req = next;
         next = req->mr_next;
-        trace_virtio_blk_rw_complete(req, ret);
+        trace_virtio_blk_rw_complete(vdev, req, ret);
 
         if (req->qiov.nalloc != -1) {
             /* If nalloc is != 1 req->qiov is a local copy of the original
@@ -XXX,XX +XXX,XX @@ static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
             mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
         }
 
-        trace_virtio_blk_submit_multireq(mrb, start, num_reqs,
+        trace_virtio_blk_submit_multireq(VIRTIO_DEVICE(mrb->reqs[start]->dev),
+                                         mrb, start, num_reqs,
                                          sector_num << BDRV_SECTOR_BITS,
                                          qiov->size, is_write);
         block_acct_merge_done(blk_get_stats(blk),
@@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
 
         if (is_write) {
             qemu_iovec_init_external(&req->qiov, iov, out_num);
-            trace_virtio_blk_handle_write(req, req->sector_num,
+            trace_virtio_blk_handle_write(vdev, 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,
+            trace_virtio_blk_handle_read(vdev, req, req->sector_num,
                                          req->qiov.size / BDRV_SECTOR_SIZE);
         }
 
diff --git a/hw/block/trace-events b/hw/block/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -XXX,XX +XXX,XX @@
 # See docs/tracing.txt for syntax documentation.
 
 # hw/block/virtio-blk.c
-virtio_blk_req_complete(void *req, int status) "req %p status %d"
-virtio_blk_rw_complete(void *req, int ret) "req %p ret %d"
-virtio_blk_handle_write(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
-virtio_blk_handle_read(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
-virtio_blk_submit_multireq(void *mrb, int start, int num_reqs, uint64_t offset, size_t size, bool is_write) "mrb %p start %d num_reqs %d offset %"PRIu64" size %zu is_write %d"
+virtio_blk_req_complete(void *vdev, void *req, int status) "vdev %p req %p status %d"
+virtio_blk_rw_complete(void *vdev, void *req, int ret) "vdev %p req %p ret %d"
+virtio_blk_handle_write(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
+virtio_blk_handle_read(void *vdev, void *req, uint64_t sector, size_t nsectors) "vdev %p req %p sector %"PRIu64" nsectors %zu"
+virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint64_t offset, size_t size, bool is_write) "vdev %p mrb %p start %d num_reqs %d offset %"PRIu64" size %zu is_write %d"
 
 # hw/block/hd-geometry.c
 hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d"
-- 
2.9.4

Old kvm.ko versions only supported a tiny number of ioeventfds so
virtio-pci avoids ioeventfds when kvm_has_many_ioeventfds() returns 0.

Do not check kvm_has_many_ioeventfds() when KVM is disabled since it
always returns 0.  Since commit 8c56c1a592b5092d91da8d8943c17777d6462a6f
("memory: emulate ioeventfd") it has been possible to use ioeventfds in
qtest or TCG mode.

This patch makes -device virtio-blk-pci,iothread=iothread0 work even
when KVM is disabled.

I have tested that virtio-blk-pci works under TCG both with and without
iothread.

This patch fixes qemu-iotests 068, which was accidentally merged early
despite the dependency on ioeventfd.

Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-id: 20170615163813.7255-2-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/virtio/virtio-pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -XXX,XX +XXX,XX @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
     bool pcie_port = pci_bus_is_express(pci_dev->bus) &&
                      !pci_bus_is_root(pci_dev->bus);
 
-    if (!kvm_has_many_ioeventfds()) {
+    if (kvm_enabled() && !kvm_has_many_ioeventfds()) {
         proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD;
     }
 
-- 
2.9.4

From: yuchenlin <npes87184@gmail.com>

There is a possible hang in original binary search implementation. That is
if chunk1 = 4, chunk2 = 5, chunk3 = 4, and we go else case.

The chunk1 will be still 4, and so on.

Signed-off-by: yuchenlin <npes87184@gmail.com>
Message-id: 20190103114700.9686-2-npes87184@gmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/dmg.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/block/dmg.c b/block/dmg.c
index XXXXXXX..XXXXXXX 100644
--- a/block/dmg.c
+++ b/block/dmg.c
@@ -XXX,XX +XXX,XX @@ static inline uint32_t search_chunk(BDRVDMGState *s, uint64_t sector_num)
 {
     /* binary search */
     uint32_t chunk1 = 0, chunk2 = s->n_chunks, chunk3;
-    while (chunk1 != chunk2) {
+    while (chunk1 <= chunk2) {
         chunk3 = (chunk1 + chunk2) / 2;
         if (s->sectors[chunk3] > sector_num) {
-            chunk2 = chunk3;
+            if (chunk3 == 0) {
+                goto err;
+            }
+            chunk2 = chunk3 - 1;
         } else if (s->sectors[chunk3] + s->sectorcounts[chunk3] > sector_num) {
             return chunk3;
         } else {
-            chunk1 = chunk3;
+            chunk1 = chunk3 + 1;
         }
     }
+err:
     return s->n_chunks; /* error */
 }
 
-- 
2.20.1

From: yuchenlin <npes87184@gmail.com>

Signed-off-by: yuchenlin <npes87184@gmail.com>
Reviewed-by: Julio Faracco <jcfaracco@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20190103114700.9686-3-npes87184@gmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/dmg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/block/dmg.c b/block/dmg.c
index XXXXXXX..XXXXXXX 100644
--- a/block/dmg.c
+++ b/block/dmg.c
@@ -XXX,XX +XXX,XX @@ static int dmg_read_mish_block(BDRVDMGState *s, DmgHeaderState *ds,
 
         /* all-zeroes sector (type 2) does not need to be "uncompressed" and can
          * therefore be unbounded. */
-        if (s->types[i] != 2 && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
+        if (s->types[i] != UDIG && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
             error_report("sector count %" PRIu64 " for chunk %" PRIu32
                          " is larger than max (%u)",
                          s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
@@ -XXX,XX +XXX,XX @@ dmg_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
         /* Special case: current chunk is all zeroes. Do not perform a memcpy as
          * s->uncompressed_chunk may be too small to cover the large all-zeroes
          * section. dmg_read_chunk is called to find s->current_chunk */
-        if (s->types[s->current_chunk] == 2) { /* all zeroes block entry */
+        if (s->types[s->current_chunk] == UDIG) { /* all zeroes block entry */
             qemu_iovec_memset(qiov, i * 512, 0, 512);
             continue;
         }
-- 
2.20.1

From: yuchenlin <npes87184@gmail.com>

The dmg file has many tables which describe: "start from sector XXX to
sector XXX, the compression method is XXX and where the compressed data
resides on".

Each sector in the expanded file should be covered by a table. The table
will describe the offset of compressed data (or raw depends on the type)
in the dmg.

For example:

[-----------The expanded file------------]
[---bzip table ---]/* zeros */[---zlib---]
    ^
    | if we want to read this sector.

we will find bzip table which contains this sector, and get the
compressed data offset, read it from dmg, uncompress it, finally write to
expanded file.

If we skip zero chunk (table), some sector cannot find the table which
will cause search_chunk() return s->n_chunks, dmg_read_chunk() return -1
and finally causing dmg_co_preadv() return EIO.

See:

[-----------The expanded file------------]
[---bzip table ---]/* zeros */[---zlib---]
                    ^
                    | if we want to read this sector.

Oops, we cannot find the table contains it...

In the original implementation, we don't have zero table. When we try to
read sector inside the zero chunk. We will get EIO, and skip reading.

After this patch, we treat zero chunk the same as ignore chunk, it will
directly write zero and avoid some sector may not find the table.

After this patch:

[-----------The expanded file------------]
[---bzip table ---][--zeros--][---zlib---]

Signed-off-by: yuchenlin <npes87184@gmail.com>
Reviewed-by: Julio Faracco <jcfaracco@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20190103114700.9686-4-npes87184@gmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/dmg.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/block/dmg.c b/block/dmg.c
index XXXXXXX..XXXXXXX 100644
--- a/block/dmg.c
+++ b/block/dmg.c
@@ -XXX,XX +XXX,XX @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
     case UDRW: /* copy */
         uncompressed_sectors = DIV_ROUND_UP(s->lengths[chunk], 512);
         break;
-    case UDIG: /* zero */
+    case UDZE: /* zero */
+    case UDIG: /* ignore */
         /* as the all-zeroes block may be large, it is treated specially: the
          * sector is not copied from a large buffer, a simple memset is used
          * instead. Therefore uncompressed_sectors does not need to be set. */
@@ -XXX,XX +XXX,XX @@ typedef struct DmgHeaderState {
 static bool dmg_is_known_block_type(uint32_t entry_type)
 {
     switch (entry_type) {
+    case UDZE:    /* zeros */
     case UDRW:    /* uncompressed */
-    case UDIG:    /* zeroes */
+    case UDIG:    /* ignore */
     case UDZO:    /* zlib */
         return true;
     case UDBZ:    /* bzip2 */
@@ -XXX,XX +XXX,XX @@ static int dmg_read_mish_block(BDRVDMGState *s, DmgHeaderState *ds,
         /* sector count */
         s->sectorcounts[i] = buff_read_uint64(buffer, offset + 0x10);
 
-        /* all-zeroes sector (type 2) does not need to be "uncompressed" and can
-         * therefore be unbounded. */
-        if (s->types[i] != UDIG && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
+        /* all-zeroes sector (type UDZE and UDIG) does not need to be
+         * "uncompressed" and can therefore be unbounded. */
+        if (s->types[i] != UDZE && s->types[i] != UDIG
+            && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
             error_report("sector count %" PRIu64 " for chunk %" PRIu32
                          " is larger than max (%u)",
                          s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
@@ -XXX,XX +XXX,XX @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
                 return -1;
             }
             break;
-        case UDIG: /* zero */
+        case UDZE: /* zeros */
+        case UDIG: /* ignore */
             /* see dmg_read, it is treated specially. No buffer needs to be
              * pre-filled, the zeroes can be set directly. */
             break;
@@ -XXX,XX +XXX,XX @@ dmg_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
         /* Special case: current chunk is all zeroes. Do not perform a memcpy as
          * s->uncompressed_chunk may be too small to cover the large all-zeroes
          * section. dmg_read_chunk is called to find s->current_chunk */
-        if (s->types[s->current_chunk] == UDIG) { /* all zeroes block entry */
+        if (s->types[s->current_chunk] == UDZE
+            || s->types[s->current_chunk] == UDIG) { /* all zeroes block entry */
             qemu_iovec_memset(qiov, i * 512, 0, 512);
             continue;
         }
-- 
2.20.1