Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

# gpg: Signature made Tue 22 Dec 2015 08:52:55 GMT using RSA key ID 81AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"

* remotes/stefanha/tags/block-pull-request:
  sdhci: add optional quirk property to disable card insertion/removal interrupts
  sdhci: don't raise a command index error for an unexpected response
  sd: sdhci: Delete over-zealous power check
  scripts/gdb: Fix a python exception in mtree.py
  parallels: add format spec
  block/mirror: replace IOV_MAX with blk_get_max_iov()
  block: replace IOV_MAX with BlockLimits.max_iov
  block-backend: add blk_get_max_iov()
  block: add BlockLimits.max_iov field
  virtio-blk: trivial code optimization

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

11 files changed, 272 insertions, 31 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 55a0fd8ae5..46bba68990 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1490,6 +1490,7 @@ M: Denis V. Lunev <den@openvz.org>
 L: qemu-block@nongnu.org
 S: Supported
 F: block/parallels.c
+F: docs/specs/parallels.txt
 
 qed
 M: Stefan Hajnoczi <stefanha@redhat.com>
diff --git a/block/block-backend.c b/block/block-backend.c
index 36ccc9e616..f41d326b3c 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1023,6 +1023,11 @@ int blk_get_max_transfer_length(BlockBackend *blk)
     }
 }
 
+int blk_get_max_iov(BlockBackend *blk)
+{
+    return blk->bs->bl.max_iov;
+}
+
 void blk_set_guest_block_size(BlockBackend *blk, int align)
 {
     blk->guest_block_size = align;
diff --git a/block/io.c b/block/io.c
index 841f5b503f..63e3678036 100644
--- a/block/io.c
+++ b/block/io.c
@@ -166,9 +166,13 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
         bs->bl.max_transfer_length = bs->file->bs->bl.max_transfer_length;
         bs->bl.min_mem_alignment = bs->file->bs->bl.min_mem_alignment;
         bs->bl.opt_mem_alignment = bs->file->bs->bl.opt_mem_alignment;
+        bs->bl.max_iov = bs->file->bs->bl.max_iov;
     } else {
         bs->bl.min_mem_alignment = 512;
         bs->bl.opt_mem_alignment = getpagesize();
+
+        /* Safe default since most protocols use readv()/writev()/etc */
+        bs->bl.max_iov = IOV_MAX;
     }
 
     if (bs->backing) {
@@ -189,6 +193,9 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
         bs->bl.min_mem_alignment =
             MAX(bs->bl.min_mem_alignment,
                 bs->backing->bs->bl.min_mem_alignment);
+        bs->bl.max_iov =
+            MIN(bs->bl.max_iov,
+                bs->backing->bs->bl.max_iov);
     }
 
     /* Then let the driver override it */
@@ -1882,7 +1889,8 @@ static int multiwrite_merge(BlockDriverState *bs, BlockRequest *reqs,
             merge = 1;
         }
 
-        if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 > IOV_MAX) {
+        if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 >
+            bs->bl.max_iov) {
             merge = 0;
         }
 
diff --git a/block/mirror.c b/block/mirror.c
index fc34a9c491..f201f2b18a 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -161,13 +161,15 @@ static void mirror_read_complete(void *opaque, int ret)
 static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
 {
     BlockDriverState *source = s->common.bs;
-    int nb_sectors, sectors_per_chunk, nb_chunks;
+    int nb_sectors, sectors_per_chunk, nb_chunks, max_iov;
     int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
     uint64_t delay_ns = 0;
     MirrorOp *op;
     int pnum;
     int64_t ret;
 
+    max_iov = MIN(source->bl.max_iov, s->target->bl.max_iov);
+
     s->sector_num = hbitmap_iter_next(&s->hbi);
     if (s->sector_num < 0) {
         bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
@@ -248,7 +250,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
             trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
             break;
         }
-        if (IOV_MAX < nb_chunks + added_chunks) {
+        if (max_iov < nb_chunks + added_chunks) {
             trace_mirror_break_iov_max(s, nb_chunks, added_chunks);
             break;
         }
diff --git a/docs/specs/parallels.txt b/docs/specs/parallels.txt
new file mode 100644
index 0000000000..b4fe2295fb
--- /dev/null
+++ b/docs/specs/parallels.txt
@@ -0,0 +1,228 @@
+= License =
+
+Copyright (c) 2015 Denis Lunev
+Copyright (c) 2015 Vladimir Sementsov-Ogievskiy
+
+This work is licensed under the terms of the GNU GPL, version 2 or later.
+See the COPYING file in the top-level directory.
+
+= Parallels Expandable Image File Format =
+
+A Parallels expandable image file consists of three consecutive parts:
+    * header
+    * BAT
+    * data area
+
+All numbers in a Parallels expandable image are stored in little-endian byte
+order.
+
+
+== Definitions ==
+
+    Sector    A 512-byte data chunk.
+
+    Cluster   A data chunk of the size specified in the image header.
+              Currently, the default size is 1MiB (2048 sectors). In previous
+              versions, cluster sizes of 63 sectors, 256 and 252 kilobytes were
+              used.
+
+    BAT       Block Allocation Table, an entity that contains information for
+              guest-to-host I/O data address translation.
+
+
+== Header ==
+
+The header is placed at the start of an image and contains the following
+fields:
+
+Bytes:
+   0 - 15:    magic
+              Must contain "WithoutFreeSpace" or "WithouFreSpacExt".
+
+  16 - 19:    version
+              Must be 2.
+
+  20 - 23:    heads
+              Disk geometry parameter for guest.
+
+  24 - 27:    cylinders
+              Disk geometry parameter for guest.
+
+  28 - 31:    tracks
+              Cluster size, in sectors.
+
+  32 - 35:    nb_bat_entries
+              Disk size, in clusters (BAT size).
+
+  36 - 43:    nb_sectors
+              Disk size, in sectors.
+
+              For "WithoutFreeSpace" images:
+              Only the lowest 4 bytes are used. The highest 4 bytes must be
+              cleared in this case.
+
+              For "WithouFreSpacExt" images, there are no such
+              restrictions.
+
+  44 - 47:    in_use
+              Set to 0x746F6E59 when the image is opened by software in R/W
+              mode; set to 0x312e3276 when the image is closed.
+
+              A zero in this field means that the image was opened by an old
+              version of the software that doesn't support Format Extension
+              (see below).
+
+              Other values are not allowed.
+
+  48 - 51:    data_off
+              An offset, in sectors, from the start of the file to the start of
+              the data area.
+
+              For "WithoutFreeSpace" images:
+              - If data_off is zero, the offset is calculated as the end of BAT
+                table plus some padding to ensure sector size alignment.
+              - If data_off is non-zero, the offset should be aligned to sector
+                size. However it is recommended to align it to cluster size for
+                newly created images.
+
+              For "WithouFreSpacExt" images:
+              data_off must be non-zero and aligned to cluster size.
+
+  52 - 55:    flags
+              Miscellaneous flags.
+
+              Bit 0: Empty Image bit. If set, the image should be
+                     considered clear.
+
+              Bits 2-31: Unused.
+
+  56 - 63:    ext_off
+              Format Extension offset, an offset, in sectors, from the start of
+              the file to the start of the Format Extension Cluster.
+
+              ext_off must meet the same requirements as cluster offsets
+              defined by BAT entries (see below).
+
+
+== BAT ==
+
+BAT is placed immediately after the image header. In the file, BAT is a
+contiguous array of 32-bit unsigned little-endian integers with
+(bat_entries * 4) bytes size.
+
+Each BAT entry contains an offset from the start of the file to the
+corresponding cluster. The offset set in clusters for "WithouFreSpacExt" images
+and in sectors for "WithoutFreeSpace" images.
+
+If a BAT entry is zero, the corresponding cluster is not allocated and should
+be considered as filled with zeroes.
+
+Cluster offsets specified by BAT entries must meet the following requirements:
+    - the value must not be lower than data offset (provided by header.data_off
+      or calculated as specified above),
+    - the value must be lower than the desired file size,
+    - the value must be unique among all BAT entries,
+    - the result of (cluster offset - data offset) must be aligned to cluster
+      size.
+
+
+== Data Area ==
+
+The data area is an area from the data offset (provided by header.data_off or
+calculated as specified above) to the end of the file. It represents a
+contiguous array of clusters. Most of them are allocated by the BAT, some may
+be allocated by the ext_off field in the header while other may be allocated by
+extensions. All clusters allocated by ext_off and extensions should meet the
+same requirements as clusters specified by BAT entries.
+
+
+== Format Extension ==
+
+The Format Extension is an area 1 cluster in size that provides additional
+format features. This cluster is addressed by the ext_off field in the header.
+The format of the Format Extension area is the following:
+
+   0 -  7:    magic
+              Must be 0xAB234CEF23DCEA87
+
+   8 - 23:    m_CheckSum
+              The MD5 checksum of the entire Header Extension cluster except
+              the first 24 bytes.
+
+    The above are followed by feature sections or "extensions". The last
+    extension must be "End of features" (see below).
+
+Each feature section has the following format:
+
+   0 -  7:    magic
+              The identifier of the feature:
+              0x0000000000000000 - End of features
+              0x20385FAE252CB34A - Dirty bitmap
+
+   8 - 15:    flags
+              External flags for extension:
+
+              Bit 0: NECESSARY
+                     If the software cannot load the extension (due to an
+                     unknown magic number or error), the file should not be
+                     changed. If this flag is unset and there is an error on
+                     loading the extension, said extension should be dropped.
+
+              Bit 1: TRANSIT
+                     If there is an unknown extension with this flag set,
+                     said extension should be left as is.
+
+              If neither NECESSARY nor TRANSIT are set, the extension should be
+              dropped.
+
+  16 - 19:    data_size
+              The size of the following feature data, in bytes.
+
+  20 - 23:    unused32
+              Align header to 8 bytes boundary.
+
+  variable:   data (data_size bytes)
+
+    The above is followed by padding to the next 8 bytes boundary, then the
+    next extension starts.
+
+    The last extension must be "End of features" with all the fields set to 0.
+
+
+=== Dirty bitmaps feature ===
+
+This feature provides a way of storing dirty bitmaps in the image. The fields
+of its data area are:
+
+   0 -  7:    size
+              The bitmap size, should be equal to disk size in sectors.
+
+   8 - 23:    id
+              An identifier for backup consistency checking.
+
+  24 - 27:    granularity
+              Bitmap granularity, in sectors. I.e., the number of sectors
+              corresponding to one bit of the bitmap. Granularity must be
+              a power of 2.
+
+  28 - 31:    l1_size
+              The number of entries in the L1 table of the bitmap.
+
+  variable:   l1 (64 * l1_size bytes)
+              L1 offset table (in bytes)
+
+A dirty bitmap is stored using a one-level structure for the mapping to host
+clusters - an L1 table.
+
+Given an offset in bytes into the bitmap data, the offset in bytes into the
+image file can be obtained as follows:
+
+    offset = l1_table[offset / cluster_size] + (offset % cluster_size)
+
+If an L1 table entry is 0, the corresponding cluster of the bitmap is assumed
+to be zero.
+
+If an L1 table entry is 1, the corresponding cluster of the bitmap is assumed
+to have all bits set.
+
+If an L1 table entry is not 0 or 1, it allocates a cluster from the data area.
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index b88b726be1..51f867b513 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -407,24 +407,16 @@ void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
     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) {
+            /*
+             * NOTE: We cannot merge the requests in below situations:
+             * 1. requests are not sequential
+             * 2. merge would exceed maximum number of IOVs
+             * 3. merge would exceed maximum transfer length of backend device
+             */
+            if (sector_num + nb_sectors != req->sector_num ||
+                niov > blk_get_max_iov(blk) - req->qiov.niov ||
+                req->qiov.size / BDRV_SECTOR_SIZE > max_xfer_len ||
+                nb_sectors > max_xfer_len - req->qiov.size / BDRV_SECTOR_SIZE) {
                 submit_requests(blk, mrb, start, num_reqs, niov);
                 num_reqs = 0;
             }
diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c
index 861276065f..7acb4d7928 100644
--- a/hw/sd/sdhci.c
+++ b/hw/sd/sdhci.c
@@ -193,7 +193,9 @@ static void sdhci_reset(SDHCIState *s)
      * initialization */
     memset(&s->sdmasysad, 0, (uintptr_t)&s->capareg - (uintptr_t)&s->sdmasysad);
 
-    sd_set_cb(s->card, s->ro_cb, s->eject_cb);
+    if (!s->noeject_quirk) {
+        sd_set_cb(s->card, s->ro_cb, s->eject_cb);
+    }
     s->data_count = 0;
     s->stopped_state = sdhc_not_stopped;
 }
@@ -243,9 +245,6 @@ static void sdhci_send_command(SDHCIState *s)
             (s->cmdreg & SDHC_CMD_RESPONSE) == SDHC_CMD_RSP_WITH_BUSY) {
             s->norintsts |= SDHC_NIS_TRSCMP;
         }
-    } else if (rlen != 0 && (s->errintstsen & SDHC_EISEN_CMDIDX)) {
-        s->errintsts |= SDHC_EIS_CMDIDX;
-        s->norintsts |= SDHC_NIS_ERR;
     }
 
     if (s->norintstsen & SDHC_NISEN_CMDCMP) {
@@ -831,7 +830,7 @@ static void sdhci_data_transfer(void *opaque)
 
 static bool sdhci_can_issue_command(SDHCIState *s)
 {
-    if (!SDHC_CLOCK_IS_ON(s->clkcon) || !(s->pwrcon & SDHC_POWER_ON) ||
+    if (!SDHC_CLOCK_IS_ON(s->clkcon) ||
         (((s->prnsts & SDHC_DATA_INHIBIT) || s->stopped_state) &&
         ((s->cmdreg & SDHC_CMD_DATA_PRESENT) ||
         ((s->cmdreg & SDHC_CMD_RESPONSE) == SDHC_CMD_RSP_WITH_BUSY &&
@@ -1279,6 +1278,7 @@ static Property sdhci_sysbus_properties[] = {
     DEFINE_PROP_UINT32("capareg", SDHCIState, capareg,
             SDHC_CAPAB_REG_DEFAULT),
     DEFINE_PROP_UINT32("maxcurr", SDHCIState, maxcurr, 0),
+    DEFINE_PROP_BOOL("noeject-quirk", SDHCIState, noeject_quirk, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 9a1c466c84..256609dd3d 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -330,6 +330,9 @@ typedef struct BlockLimits {
 
     /* memory alignment for bounce buffer */
     size_t opt_mem_alignment;
+
+    /* maximum number of iovec elements */
+    int max_iov;
 } BlockLimits;
 
 typedef struct BdrvOpBlocker BdrvOpBlocker;
diff --git a/include/hw/sd/sdhci.h b/include/hw/sd/sdhci.h
index e78d938570..ffd1f80891 100644
--- a/include/hw/sd/sdhci.h
+++ b/include/hw/sd/sdhci.h
@@ -77,6 +77,7 @@ typedef struct SDHCIState {
     uint32_t buf_maxsz;
     uint16_t data_count;   /* current element in FIFO buffer */
     uint8_t  stopped_state;/* Current SDHC state */
+    bool     noeject_quirk;/* Quirk to disable card insert/remove interrupts */
     /* Buffer Data Port Register - virtual access point to R and W buffers */
     /* Software Reset Register - always reads as 0 */
     /* Force Event Auto CMD12 Error Interrupt Reg - write only */
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index fb068ea47b..dc244760a1 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -146,6 +146,7 @@ void blk_lock_medium(BlockBackend *blk, bool locked);
 void blk_eject(BlockBackend *blk, bool eject_flag);
 int blk_get_flags(BlockBackend *blk);
 int blk_get_max_transfer_length(BlockBackend *blk);
+int blk_get_max_iov(BlockBackend *blk);
 void blk_set_guest_block_size(BlockBackend *blk, int align);
 void *blk_blockalign(BlockBackend *blk, size_t size);
 bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp);
diff --git a/scripts/qemugdb/mtree.py b/scripts/qemugdb/mtree.py
index 06011c30cc..cc8131c2e7 100644
--- a/scripts/qemugdb/mtree.py
+++ b/scripts/qemugdb/mtree.py
@@ -21,7 +21,7 @@ def isnull(ptr):
     return ptr == gdb.Value(0).cast(ptr.type)
 
 def int128(p):
-    return long(p['lo']) + (long(p['hi']) << 64)
+    return int(p['lo']) + (int(p['hi']) << 64)
 
 class MtreeCommand(gdb.Command):
     '''Display the memory tree hierarchy'''
@@ -40,11 +40,11 @@ class MtreeCommand(gdb.Command):
     def process_queue(self):
         while self.queue:
             ptr = self.queue.pop(0)
-            if long(ptr) in self.seen:
+            if int(ptr) in self.seen:
                 continue
             self.print_item(ptr)
     def print_item(self, ptr, offset = gdb.Value(0), level = 0):
-        self.seen.add(long(ptr))
+        self.seen.add(int(ptr))
         addr = ptr['addr']
         addr += offset
         size = int128(ptr['size'])
@@ -58,8 +58,8 @@ class MtreeCommand(gdb.Command):
             klass = ' (RAM)'
         gdb.write('%s%016x-%016x %s%s (@ %s)\n'
                   % ('  ' * level,
-                     long(addr),
-                     long(addr + (size - 1)),
+                     int(addr),
+                     int(addr + (size - 1)),
                      ptr['name'].string(),
                      klass,
                      ptr,