Merge remote-tracking branch 'stefanha/block' into staging

* stefanha/block:
  commit: Remove unused check
  qemu-iotests: Update test cases for commit active
  commit: Support commit active layer
  block: Add commit_active_start()
  mirror: Move base to MirrorBlockJob
  mirror: Don't close target
  qemu-iotests: drop duplicate virtio-blk initialization failure
  vmdk: Allow vmdk_create to work with protocol
  vmdk: Check VMFS extent line field number
  docs: updated qemu-img man page and qemu-doc to reflect VHDX support.
  block: vhdx - improve error message, and .bdrv_check implementation
  block/iscsi: Fix compilation for libiscsi 1.4.0 (API change)
  qapi-schema: fix QEMU 1.8 references
  dataplane: replace hostmem with memory_region_find
  dataplane: change vring API to use VirtQueueElement
  vring: factor common code for error exits
  vring: create a common function to parse descriptors
  sheepdog: fix dynamic grow for running qcow2 format

Message-id: 1387554416-5837-1-git-send-email-stefanha@redhat.com
Signed-off-by: Anthony Liguori <aliguori@amazon.com>

3 files changed, 165 insertions, 273 deletions

diff --git a/hw/virtio/dataplane/Makefile.objs b/hw/virtio/dataplane/Makefile.objs
index a91bf33c8b..9a8cfc0297 100644
--- a/hw/virtio/dataplane/Makefile.objs
+++ b/hw/virtio/dataplane/Makefile.objs
@@ -1 +1 @@
-common-obj-y += hostmem.o vring.o
+common-obj-y += vring.o
diff --git a/hw/virtio/dataplane/hostmem.c b/hw/virtio/dataplane/hostmem.c
deleted file mode 100644
index 901d98b8a0..0000000000
--- a/hw/virtio/dataplane/hostmem.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * Thread-safe guest to host memory mapping
- *
- * Copyright 2012 Red Hat, Inc. and/or its affiliates
- *
- * Authors:
- *   Stefan Hajnoczi <stefanha@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#include "exec/address-spaces.h"
-#include "hw/virtio/dataplane/hostmem.h"
-
-static int hostmem_lookup_cmp(const void *phys_, const void *region_)
-{
-    hwaddr phys = *(const hwaddr *)phys_;
-    const HostMemRegion *region = region_;
-
-    if (phys < region->guest_addr) {
-        return -1;
-    } else if (phys >= region->guest_addr + region->size) {
-        return 1;
-    } else {
-        return 0;
-    }
-}
-
-/**
- * Map guest physical address to host pointer
- */
-void *hostmem_lookup(HostMem *hostmem, hwaddr phys, hwaddr len, bool is_write)
-{
-    HostMemRegion *region;
-    void *host_addr = NULL;
-    hwaddr offset_within_region;
-
-    qemu_mutex_lock(&hostmem->current_regions_lock);
-    region = bsearch(&phys, hostmem->current_regions,
-                     hostmem->num_current_regions,
-                     sizeof(hostmem->current_regions[0]),
-                     hostmem_lookup_cmp);
-    if (!region) {
-        goto out;
-    }
-    if (is_write && region->readonly) {
-        goto out;
-    }
-    offset_within_region = phys - region->guest_addr;
-    if (len <= region->size - offset_within_region) {
-        host_addr = region->host_addr + offset_within_region;
-    }
-out:
-    qemu_mutex_unlock(&hostmem->current_regions_lock);
-
-    return host_addr;
-}
-
-/**
- * Install new regions list
- */
-static void hostmem_listener_commit(MemoryListener *listener)
-{
-    HostMem *hostmem = container_of(listener, HostMem, listener);
-    int i;
-
-    qemu_mutex_lock(&hostmem->current_regions_lock);
-    for (i = 0; i < hostmem->num_current_regions; i++) {
-        memory_region_unref(hostmem->current_regions[i].mr);
-    }
-    g_free(hostmem->current_regions);
-    hostmem->current_regions = hostmem->new_regions;
-    hostmem->num_current_regions = hostmem->num_new_regions;
-    qemu_mutex_unlock(&hostmem->current_regions_lock);
-
-    /* Reset new regions list */
-    hostmem->new_regions = NULL;
-    hostmem->num_new_regions = 0;
-}
-
-/**
- * Add a MemoryRegionSection to the new regions list
- */
-static void hostmem_append_new_region(HostMem *hostmem,
-                                      MemoryRegionSection *section)
-{
-    void *ram_ptr = memory_region_get_ram_ptr(section->mr);
-    size_t num = hostmem->num_new_regions;
-    size_t new_size = (num + 1) * sizeof(hostmem->new_regions[0]);
-
-    hostmem->new_regions = g_realloc(hostmem->new_regions, new_size);
-    hostmem->new_regions[num] = (HostMemRegion){
-        .host_addr = ram_ptr + section->offset_within_region,
-        .guest_addr = section->offset_within_address_space,
-        .size = int128_get64(section->size),
-        .readonly = section->readonly,
-        .mr = section->mr,
-    };
-    hostmem->num_new_regions++;
-
-    memory_region_ref(section->mr);
-}
-
-static void hostmem_listener_append_region(MemoryListener *listener,
-                                           MemoryRegionSection *section)
-{
-    HostMem *hostmem = container_of(listener, HostMem, listener);
-
-    /* Ignore non-RAM regions, we may not be able to map them */
-    if (!memory_region_is_ram(section->mr)) {
-        return;
-    }
-
-    /* Ignore regions with dirty logging, we cannot mark them dirty */
-    if (memory_region_is_logging(section->mr)) {
-        return;
-    }
-
-    hostmem_append_new_region(hostmem, section);
-}
-
-/* We don't implement most MemoryListener callbacks, use these nop stubs */
-static void hostmem_listener_dummy(MemoryListener *listener)
-{
-}
-
-static void hostmem_listener_section_dummy(MemoryListener *listener,
-                                           MemoryRegionSection *section)
-{
-}
-
-static void hostmem_listener_eventfd_dummy(MemoryListener *listener,
-                                           MemoryRegionSection *section,
-                                           bool match_data, uint64_t data,
-                                           EventNotifier *e)
-{
-}
-
-static void hostmem_listener_coalesced_mmio_dummy(MemoryListener *listener,
-                                                  MemoryRegionSection *section,
-                                                  hwaddr addr, hwaddr len)
-{
-}
-
-void hostmem_init(HostMem *hostmem)
-{
-    memset(hostmem, 0, sizeof(*hostmem));
-
-    qemu_mutex_init(&hostmem->current_regions_lock);
-
-    hostmem->listener = (MemoryListener){
-        .begin = hostmem_listener_dummy,
-        .commit = hostmem_listener_commit,
-        .region_add = hostmem_listener_append_region,
-        .region_del = hostmem_listener_section_dummy,
-        .region_nop = hostmem_listener_append_region,
-        .log_start = hostmem_listener_section_dummy,
-        .log_stop = hostmem_listener_section_dummy,
-        .log_sync = hostmem_listener_section_dummy,
-        .log_global_start = hostmem_listener_dummy,
-        .log_global_stop = hostmem_listener_dummy,
-        .eventfd_add = hostmem_listener_eventfd_dummy,
-        .eventfd_del = hostmem_listener_eventfd_dummy,
-        .coalesced_mmio_add = hostmem_listener_coalesced_mmio_dummy,
-        .coalesced_mmio_del = hostmem_listener_coalesced_mmio_dummy,
-        .priority = 10,
-    };
-
-    memory_listener_register(&hostmem->listener, &address_space_memory);
-    if (hostmem->num_new_regions > 0) {
-        hostmem_listener_commit(&hostmem->listener);
-    }
-}
-
-void hostmem_finalize(HostMem *hostmem)
-{
-    memory_listener_unregister(&hostmem->listener);
-    g_free(hostmem->new_regions);
-    g_free(hostmem->current_regions);
-    qemu_mutex_destroy(&hostmem->current_regions_lock);
-}
diff --git a/hw/virtio/dataplane/vring.c b/hw/virtio/dataplane/vring.c
index 351a343806..250d45ec3d 100644
--- a/hw/virtio/dataplane/vring.c
+++ b/hw/virtio/dataplane/vring.c
@@ -15,9 +15,53 @@
  */
 
 #include "trace.h"
+#include "hw/hw.h"
+#include "exec/memory.h"
+#include "exec/address-spaces.h"
 #include "hw/virtio/dataplane/vring.h"
 #include "qemu/error-report.h"
 
+/* vring_map can be coupled with vring_unmap or (if you still have the
+ * value returned in *mr) memory_region_unref.
+ */
+static void *vring_map(MemoryRegion **mr, hwaddr phys, hwaddr len,
+                       bool is_write)
+{
+    MemoryRegionSection section = memory_region_find(get_system_memory(), phys, len);
+
+    if (!section.mr || int128_get64(section.size) < len) {
+        goto out;
+    }
+    if (is_write && section.readonly) {
+        goto out;
+    }
+    if (!memory_region_is_ram(section.mr)) {
+        goto out;
+    }
+
+    /* Ignore regions with dirty logging, we cannot mark them dirty */
+    if (memory_region_is_logging(section.mr)) {
+        goto out;
+    }
+
+    *mr = section.mr;
+    return memory_region_get_ram_ptr(section.mr) + section.offset_within_region;
+
+out:
+    memory_region_unref(section.mr);
+    *mr = NULL;
+    return NULL;
+}
+
+static void vring_unmap(void *buffer, bool is_write)
+{
+    ram_addr_t addr;
+    MemoryRegion *mr;
+
+    mr = qemu_ram_addr_from_host(buffer, &addr);
+    memory_region_unref(mr);
+}
+
 /* Map the guest's vring to host memory */
 bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
 {
@@ -27,8 +71,7 @@ bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
 
     vring->broken = false;
 
-    hostmem_init(&vring->hostmem);
-    vring_ptr = hostmem_lookup(&vring->hostmem, vring_addr, vring_size, true);
+    vring_ptr = vring_map(&vring->mr, vring_addr, vring_size, true);
     if (!vring_ptr) {
         error_report("Failed to map vring "
                      "addr %#" HWADDR_PRIx " size %" HWADDR_PRIu,
@@ -54,7 +97,7 @@ void vring_teardown(Vring *vring, VirtIODevice *vdev, int n)
     virtio_queue_set_last_avail_idx(vdev, n, vring->last_avail_idx);
     virtio_queue_invalidate_signalled_used(vdev, n);
 
-    hostmem_finalize(&vring->hostmem);
+    memory_region_unref(vring->mr);
 }
 
 /* Disable guest->host notifies */
@@ -110,14 +153,61 @@ bool vring_should_notify(VirtIODevice *vdev, Vring *vring)
     return vring_need_event(vring_used_event(&vring->vr), new, old);
 }
 
+
+static int get_desc(Vring *vring, VirtQueueElement *elem,
+                    struct vring_desc *desc)
+{
+    unsigned *num;
+    struct iovec *iov;
+    hwaddr *addr;
+    MemoryRegion *mr;
+
+    if (desc->flags & VRING_DESC_F_WRITE) {
+        num = &elem->in_num;
+        iov = &elem->in_sg[*num];
+        addr = &elem->in_addr[*num];
+    } else {
+        num = &elem->out_num;
+        iov = &elem->out_sg[*num];
+        addr = &elem->out_addr[*num];
+
+        /* If it's an output descriptor, they're all supposed
+         * to come before any input descriptors. */
+        if (unlikely(elem->in_num)) {
+            error_report("Descriptor has out after in");
+            return -EFAULT;
+        }
+    }
+
+    /* Stop for now if there are not enough iovecs available. */
+    if (*num >= VIRTQUEUE_MAX_SIZE) {
+        return -ENOBUFS;
+    }
+
+    /* TODO handle non-contiguous memory across region boundaries */
+    iov->iov_base = vring_map(&mr, desc->addr, desc->len,
+                              desc->flags & VRING_DESC_F_WRITE);
+    if (!iov->iov_base) {
+        error_report("Failed to map descriptor addr %#" PRIx64 " len %u",
+                     (uint64_t)desc->addr, desc->len);
+        return -EFAULT;
+    }
+
+    /* The MemoryRegion is looked up again and unref'ed later, leave the
+     * ref in place.  */
+    iov->iov_len = desc->len;
+    *addr = desc->addr;
+    *num += 1;
+    return 0;
+}
+
 /* This is stolen from linux/drivers/vhost/vhost.c. */
-static int get_indirect(Vring *vring,
-                        struct iovec iov[], struct iovec *iov_end,
-                        unsigned int *out_num, unsigned int *in_num,
+static int get_indirect(Vring *vring, VirtQueueElement *elem,
                         struct vring_desc *indirect)
 {
     struct vring_desc desc;
     unsigned int i = 0, count, found = 0;
+    int ret;
 
     /* Sanity check */
     if (unlikely(indirect->len % sizeof(desc))) {
@@ -139,11 +229,12 @@ static int get_indirect(Vring *vring,
 
     do {
         struct vring_desc *desc_ptr;
+        MemoryRegion *mr;
 
         /* Translate indirect descriptor */
-        desc_ptr = hostmem_lookup(&vring->hostmem,
-                                  indirect->addr + found * sizeof(desc),
-                                  sizeof(desc), false);
+        desc_ptr = vring_map(&mr,
+                             indirect->addr + found * sizeof(desc),
+                             sizeof(desc), false);
         if (!desc_ptr) {
             error_report("Failed to map indirect descriptor "
                          "addr %#" PRIx64 " len %zu",
@@ -153,6 +244,7 @@ static int get_indirect(Vring *vring,
             return -EFAULT;
         }
         desc = *desc_ptr;
+        memory_region_unref(mr);
 
         /* Ensure descriptor has been loaded before accessing fields */
         barrier(); /* read_barrier_depends(); */
@@ -170,42 +262,35 @@ static int get_indirect(Vring *vring,
             return -EFAULT;
         }
 
-        /* Stop for now if there are not enough iovecs available. */
-        if (iov >= iov_end) {
-            return -ENOBUFS;
-        }
-
-        iov->iov_base = hostmem_lookup(&vring->hostmem, desc.addr, desc.len,
-                                       desc.flags & VRING_DESC_F_WRITE);
-        if (!iov->iov_base) {
-            error_report("Failed to map indirect descriptor"
-                         "addr %#" PRIx64 " len %u",
-                         (uint64_t)desc.addr, desc.len);
-            vring->broken = true;
-            return -EFAULT;
-        }
-        iov->iov_len = desc.len;
-        iov++;
-
-        /* If this is an input descriptor, increment that count. */
-        if (desc.flags & VRING_DESC_F_WRITE) {
-            *in_num += 1;
-        } else {
-            /* If it's an output descriptor, they're all supposed
-             * to come before any input descriptors. */
-            if (unlikely(*in_num)) {
-                error_report("Indirect descriptor "
-                             "has out after in: idx %u", i);
-                vring->broken = true;
-                return -EFAULT;
-            }
-            *out_num += 1;
+        ret = get_desc(vring, elem, &desc);
+        if (ret < 0) {
+            vring->broken |= (ret == -EFAULT);
+            return ret;
         }
         i = desc.next;
     } while (desc.flags & VRING_DESC_F_NEXT);
     return 0;
 }
 
+void vring_free_element(VirtQueueElement *elem)
+{
+    int i;
+
+    /* This assumes that the iovecs, if changed, are never moved past
+     * the end of the valid area.  This is true if iovec manipulations
+     * are done with iov_discard_front and iov_discard_back.
+     */
+    for (i = 0; i < elem->out_num; i++) {
+        vring_unmap(elem->out_sg[i].iov_base, false);
+    }
+
+    for (i = 0; i < elem->in_num; i++) {
+        vring_unmap(elem->in_sg[i].iov_base, true);
+    }
+
+    g_slice_free(VirtQueueElement, elem);
+}
+
 /* This looks in the virtqueue and for the first available buffer, and converts
  * it to an iovec for convenient access.  Since descriptors consist of some
  * number of output then some number of input descriptors, it's actually two
@@ -218,16 +303,18 @@ static int get_indirect(Vring *vring,
  * Stolen from linux/drivers/vhost/vhost.c.
  */
 int vring_pop(VirtIODevice *vdev, Vring *vring,
-              struct iovec iov[], struct iovec *iov_end,
-              unsigned int *out_num, unsigned int *in_num)
+              VirtQueueElement **p_elem)
 {
     struct vring_desc desc;
     unsigned int i, head, found = 0, num = vring->vr.num;
     uint16_t avail_idx, last_avail_idx;
+    VirtQueueElement *elem = NULL;
+    int ret;
 
     /* If there was a fatal error then refuse operation */
     if (vring->broken) {
-        return -EFAULT;
+        ret = -EFAULT;
+        goto out;
     }
 
     /* Check it isn't doing very strange things with descriptor numbers. */
@@ -238,13 +325,14 @@ int vring_pop(VirtIODevice *vdev, Vring *vring,
     if (unlikely((uint16_t)(avail_idx - last_avail_idx) > num)) {
         error_report("Guest moved used index from %u to %u",
                      last_avail_idx, avail_idx);
-        vring->broken = true;
-        return -EFAULT;
+        ret = -EFAULT;
+        goto out;
     }
 
     /* If there's nothing new since last we looked. */
     if (avail_idx == last_avail_idx) {
-        return -EAGAIN;
+        ret = -EAGAIN;
+        goto out;
     }
 
     /* Only get avail ring entries after they have been exposed by guest. */
@@ -254,32 +342,33 @@ int vring_pop(VirtIODevice *vdev, Vring *vring,
      * the index we've seen. */
     head = vring->vr.avail->ring[last_avail_idx % num];
 
+    elem = g_slice_new(VirtQueueElement);
+    elem->index = head;
+    elem->in_num = elem->out_num = 0;
+    
     /* If their number is silly, that's an error. */
     if (unlikely(head >= num)) {
         error_report("Guest says index %u > %u is available", head, num);
-        vring->broken = true;
-        return -EFAULT;
+        ret = -EFAULT;
+        goto out;
     }
 
     if (vdev->guest_features & (1 << VIRTIO_RING_F_EVENT_IDX)) {
         vring_avail_event(&vring->vr) = vring->vr.avail->idx;
     }
 
-    /* When we start there are none of either input nor output. */
-    *out_num = *in_num = 0;
-
     i = head;
     do {
         if (unlikely(i >= num)) {
             error_report("Desc index is %u > %u, head = %u", i, num, head);
-            vring->broken = true;
-            return -EFAULT;
+            ret = -EFAULT;
+            goto out;
         }
         if (unlikely(++found > num)) {
             error_report("Loop detected: last one at %u vq size %u head %u",
                          i, num, head);
-            vring->broken = true;
-            return -EFAULT;
+            ret = -EFAULT;
+            goto out;
         }
         desc = vring->vr.desc[i];
 
@@ -287,64 +376,50 @@ int vring_pop(VirtIODevice *vdev, Vring *vring,
         barrier();
 
         if (desc.flags & VRING_DESC_F_INDIRECT) {
-            int ret = get_indirect(vring, iov, iov_end, out_num, in_num, &desc);
+            int ret = get_indirect(vring, elem, &desc);
             if (ret < 0) {
-                return ret;
+                goto out;
             }
             continue;
         }
 
-        /* If there are not enough iovecs left, stop for now.  The caller
-         * should check if there are more descs available once they have dealt
-         * with the current set.
-         */
-        if (iov >= iov_end) {
-            return -ENOBUFS;
+        ret = get_desc(vring, elem, &desc);
+        if (ret < 0) {
+            goto out;
         }
 
-        /* TODO handle non-contiguous memory across region boundaries */
-        iov->iov_base = hostmem_lookup(&vring->hostmem, desc.addr, desc.len,
-                                       desc.flags & VRING_DESC_F_WRITE);
-        if (!iov->iov_base) {
-            error_report("Failed to map vring desc addr %#" PRIx64 " len %u",
-                         (uint64_t)desc.addr, desc.len);
-            vring->broken = true;
-            return -EFAULT;
-        }
-        iov->iov_len  = desc.len;
-        iov++;
-
-        if (desc.flags & VRING_DESC_F_WRITE) {
-            /* If this is an input descriptor,
-             * increment that count. */
-            *in_num += 1;
-        } else {
-            /* If it's an output descriptor, they're all supposed
-             * to come before any input descriptors. */
-            if (unlikely(*in_num)) {
-                error_report("Descriptor has out after in: idx %d", i);
-                vring->broken = true;
-                return -EFAULT;
-            }
-            *out_num += 1;
-        }
         i = desc.next;
     } while (desc.flags & VRING_DESC_F_NEXT);
 
     /* On success, increment avail index. */
     vring->last_avail_idx++;
+    *p_elem = elem;
     return head;
+
+out:
+    assert(ret < 0);
+    if (ret == -EFAULT) {
+        vring->broken = true;
+    }
+    if (elem) {
+        vring_free_element(elem);
+    }
+    *p_elem = NULL;
+    return ret;
 }
 
 /* After we've used one of their buffers, we tell them about it.
  *
  * Stolen from linux/drivers/vhost/vhost.c.
  */
-void vring_push(Vring *vring, unsigned int head, int len)
+void vring_push(Vring *vring, VirtQueueElement *elem, int len)
 {
     struct vring_used_elem *used;
+    unsigned int head = elem->index;
     uint16_t new;
 
+    vring_free_element(elem);
+
     /* Don't touch vring if a fatal error occurred */
     if (vring->broken) {
         return;