Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

virtio, pc: fixes, cleanups

A bunch of fixes all over the place.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Thu 25 Jul 2019 16:19:33 BST
# gpg:                using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream:
  virtio-balloon: free pbp more aggressively
  virtio-balloon: don't track subpages for the PBP
  virtio-balloon: Use temporary PBP only
  virtio-balloon: Rework pbp tracking data
  virtio-balloon: Better names for offset variables in inflate/deflate code
  virtio-balloon: Simplify deflate with pbp
  virtio-balloon: Fix QEMU crashes on pagesize > BALLOON_PAGE_SIZE
  virtio-balloon: Fix wrong sign extension of PFNs
  i386/acpi: show PCI Express bus on pxb-pcie expanders
  ioapic: kvm: Skip route updates for masked pins
  i386/acpi: fix gint overflow in crs_range_compare
  docs: clarify multiqueue vs multiple virtqueues

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

5 files changed, 90 insertions, 70 deletions

diff --git a/docs/interop/vhost-user.rst b/docs/interop/vhost-user.rst
index 5750668aba..7827b710aa 100644
--- a/docs/interop/vhost-user.rst
+++ b/docs/interop/vhost-user.rst
@@ -324,6 +324,15 @@ must support changing some configuration aspects on the fly.
 Multiple queue support
 ----------------------
 
+Many devices have a fixed number of virtqueues.  In this case the master
+already knows the number of available virtqueues without communicating with the
+slave.
+
+Some devices do not have a fixed number of virtqueues.  Instead the maximum
+number of virtqueues is chosen by the slave.  The number can depend on host
+resource availability or slave implementation details.  Such devices are called
+multiple queue devices.
+
 Multiple queue support allows the slave to advertise the maximum number of
 queues.  This is treated as a protocol extension, hence the slave has to
 implement protocol features first. The multiple queues feature is supported
@@ -339,6 +348,14 @@ queue in the sent message to identify a specified queue.
 The master enables queues by sending message ``VHOST_USER_SET_VRING_ENABLE``.
 vhost-user-net has historically automatically enabled the first queue pair.
 
+Slaves should always implement the ``VHOST_USER_PROTOCOL_F_MQ`` protocol
+feature, even for devices with a fixed number of virtqueues, since it is simple
+to implement and offers a degree of introspection.
+
+Masters must not rely on the ``VHOST_USER_PROTOCOL_F_MQ`` protocol feature for
+devices with a fixed number of virtqueues.  Only true multiqueue devices
+require this protocol feature.
+
 Migration
 ---------
 
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index d281ffa89e..f3fdfefcd5 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -755,10 +755,16 @@ static void crs_range_set_free(CrsRangeSet *range_set)
 
 static gint crs_range_compare(gconstpointer a, gconstpointer b)
 {
-     CrsRangeEntry *entry_a = *(CrsRangeEntry **)a;
-     CrsRangeEntry *entry_b = *(CrsRangeEntry **)b;
+    CrsRangeEntry *entry_a = *(CrsRangeEntry **)a;
+    CrsRangeEntry *entry_b = *(CrsRangeEntry **)b;
 
-     return (int64_t)entry_a->base - (int64_t)entry_b->base;
+    if (entry_a->base < entry_b->base) {
+        return -1;
+    } else if (entry_a->base > entry_b->base) {
+        return 1;
+    } else {
+        return 0;
+    }
 }
 
 /*
@@ -1908,10 +1914,13 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
             scope = aml_scope("\\_SB");
             dev = aml_device("PC%.02X", bus_num);
             aml_append(dev, aml_name_decl("_UID", aml_int(bus_num)));
-            aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A03")));
             aml_append(dev, aml_name_decl("_BBN", aml_int(bus_num)));
             if (pci_bus_is_express(bus)) {
+                aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A08")));
+                aml_append(dev, aml_name_decl("_CID", aml_eisaid("PNP0A03")));
                 aml_append(dev, build_q35_osc_method());
+            } else {
+                aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A03")));
             }
 
             if (numa_node != NUMA_NODE_UNASSIGNED) {
diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c
index c408749876..e99c37cceb 100644
--- a/hw/intc/ioapic.c
+++ b/hw/intc/ioapic.c
@@ -197,9 +197,11 @@ static void ioapic_update_kvm_routes(IOAPICCommonState *s)
             MSIMessage msg;
             struct ioapic_entry_info info;
             ioapic_entry_parse(s->ioredtbl[i], &info);
-            msg.address = info.addr;
-            msg.data = info.data;
-            kvm_irqchip_update_msi_route(kvm_state, i, msg, NULL);
+            if (!info.masked) {
+                msg.address = info.addr;
+                msg.data = info.data;
+                kvm_irqchip_update_msi_route(kvm_state, i, msg, NULL);
+            }
         }
         kvm_irqchip_commit_routes(kvm_state);
     }
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index e85d1c0d5c..25de154307 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -34,31 +34,53 @@
 
 #define BALLOON_PAGE_SIZE  (1 << VIRTIO_BALLOON_PFN_SHIFT)
 
-struct PartiallyBalloonedPage {
-    RAMBlock *rb;
-    ram_addr_t base;
-    unsigned long bitmap[];
-};
+typedef struct PartiallyBalloonedPage {
+    ram_addr_t base_gpa;
+    unsigned long *bitmap;
+} PartiallyBalloonedPage;
+
+static void virtio_balloon_pbp_free(PartiallyBalloonedPage *pbp)
+{
+    if (!pbp->bitmap) {
+        return;
+    }
+    g_free(pbp->bitmap);
+    pbp->bitmap = NULL;
+}
+
+static void virtio_balloon_pbp_alloc(PartiallyBalloonedPage *pbp,
+                                     ram_addr_t base_gpa,
+                                     long subpages)
+{
+    pbp->base_gpa = base_gpa;
+    pbp->bitmap = bitmap_new(subpages);
+}
+
+static bool virtio_balloon_pbp_matches(PartiallyBalloonedPage *pbp,
+                                       ram_addr_t base_gpa)
+{
+    return pbp->base_gpa == base_gpa;
+}
 
 static void balloon_inflate_page(VirtIOBalloon *balloon,
-                                 MemoryRegion *mr, hwaddr offset)
+                                 MemoryRegion *mr, hwaddr mr_offset,
+                                 PartiallyBalloonedPage *pbp)
 {
-    void *addr = memory_region_get_ram_ptr(mr) + offset;
+    void *addr = memory_region_get_ram_ptr(mr) + mr_offset;
+    ram_addr_t rb_offset, rb_aligned_offset, base_gpa;
     RAMBlock *rb;
     size_t rb_page_size;
     int subpages;
-    ram_addr_t ram_offset, host_page_base;
 
     /* XXX is there a better way to get to the RAMBlock than via a
      * host address? */
-    rb = qemu_ram_block_from_host(addr, false, &ram_offset);
+    rb = qemu_ram_block_from_host(addr, false, &rb_offset);
     rb_page_size = qemu_ram_pagesize(rb);
-    host_page_base = ram_offset & ~(rb_page_size - 1);
 
     if (rb_page_size == BALLOON_PAGE_SIZE) {
         /* Easy case */
 
-        ram_block_discard_range(rb, ram_offset, rb_page_size);
+        ram_block_discard_range(rb, rb_offset, rb_page_size);
         /* We ignore errors from ram_block_discard_range(), because it
          * has already reported them, and failing to discard a balloon
          * page is not fatal */
@@ -74,81 +96,51 @@ static void balloon_inflate_page(VirtIOBalloon *balloon,
     warn_report_once(
 "Balloon used with backing page size > 4kiB, this may not be reliable");
 
+    rb_aligned_offset = QEMU_ALIGN_DOWN(rb_offset, rb_page_size);
     subpages = rb_page_size / BALLOON_PAGE_SIZE;
+    base_gpa = memory_region_get_ram_addr(mr) + mr_offset -
+               (rb_offset - rb_aligned_offset);
 
-    if (balloon->pbp
-        && (rb != balloon->pbp->rb
-            || host_page_base != balloon->pbp->base)) {
+    if (pbp->bitmap && !virtio_balloon_pbp_matches(pbp, base_gpa)) {
         /* We've partially ballooned part of a host page, but now
          * we're trying to balloon part of a different one.  Too hard,
          * give up on the old partial page */
-        g_free(balloon->pbp);
-        balloon->pbp = NULL;
+        virtio_balloon_pbp_free(pbp);
     }
 
-    if (!balloon->pbp) {
-        /* Starting on a new host page */
-        size_t bitlen = BITS_TO_LONGS(subpages) * sizeof(unsigned long);
-        balloon->pbp = g_malloc0(sizeof(PartiallyBalloonedPage) + bitlen);
-        balloon->pbp->rb = rb;
-        balloon->pbp->base = host_page_base;
+    if (!pbp->bitmap) {
+        virtio_balloon_pbp_alloc(pbp, base_gpa, subpages);
     }
 
-    bitmap_set(balloon->pbp->bitmap,
-               (ram_offset - balloon->pbp->base) / BALLOON_PAGE_SIZE,
-               subpages);
+    set_bit((rb_offset - rb_aligned_offset) / BALLOON_PAGE_SIZE,
+            pbp->bitmap);
 
-    if (bitmap_full(balloon->pbp->bitmap, subpages)) {
+    if (bitmap_full(pbp->bitmap, subpages)) {
         /* We've accumulated a full host page, we can actually discard
          * it now */
 
-        ram_block_discard_range(rb, balloon->pbp->base, rb_page_size);
+        ram_block_discard_range(rb, rb_aligned_offset, rb_page_size);
         /* We ignore errors from ram_block_discard_range(), because it
          * has already reported them, and failing to discard a balloon
          * page is not fatal */
-
-        g_free(balloon->pbp);
-        balloon->pbp = NULL;
+        virtio_balloon_pbp_free(pbp);
     }
 }
 
 static void balloon_deflate_page(VirtIOBalloon *balloon,
-                                 MemoryRegion *mr, hwaddr offset)
+                                 MemoryRegion *mr, hwaddr mr_offset)
 {
-    void *addr = memory_region_get_ram_ptr(mr) + offset;
+    void *addr = memory_region_get_ram_ptr(mr) + mr_offset;
+    ram_addr_t rb_offset;
     RAMBlock *rb;
     size_t rb_page_size;
-    ram_addr_t ram_offset, host_page_base;
     void *host_addr;
     int ret;
 
     /* XXX is there a better way to get to the RAMBlock than via a
      * host address? */
-    rb = qemu_ram_block_from_host(addr, false, &ram_offset);
+    rb = qemu_ram_block_from_host(addr, false, &rb_offset);
     rb_page_size = qemu_ram_pagesize(rb);
-    host_page_base = ram_offset & ~(rb_page_size - 1);
-
-    if (balloon->pbp
-        && rb == balloon->pbp->rb
-        && host_page_base == balloon->pbp->base) {
-        int subpages = rb_page_size / BALLOON_PAGE_SIZE;
-
-        /*
-         * This means the guest has asked to discard some of the 4kiB
-         * subpages of a host page, but then changed its mind and
-         * asked to keep them after all.  It's exceedingly unlikely
-         * for a guest to do this in practice, but handle it anyway,
-         * since getting it wrong could mean discarding memory the
-         * guest is still using. */
-        bitmap_clear(balloon->pbp->bitmap,
-                     (ram_offset - balloon->pbp->base) / BALLOON_PAGE_SIZE,
-                     subpages);
-
-        if (bitmap_empty(balloon->pbp->bitmap, subpages)) {
-            g_free(balloon->pbp);
-            balloon->pbp = NULL;
-        }
-    }
 
     host_addr = (void *)((uintptr_t)addr & ~(rb_page_size - 1));
 
@@ -335,16 +327,18 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
     MemoryRegionSection section;
 
     for (;;) {
+        PartiallyBalloonedPage pbp = {};
         size_t offset = 0;
         uint32_t pfn;
+
         elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
         if (!elem) {
-            return;
+            break;
         }
 
         while (iov_to_buf(elem->out_sg, elem->out_num, offset, &pfn, 4) == 4) {
+            unsigned int p = virtio_ldl_p(vdev, &pfn);
             hwaddr pa;
-            int p = virtio_ldl_p(vdev, &pfn);
 
             pa = (hwaddr) p << VIRTIO_BALLOON_PFN_SHIFT;
             offset += 4;
@@ -368,7 +362,7 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
             if (!qemu_balloon_is_inhibited()) {
                 if (vq == s->ivq) {
                     balloon_inflate_page(s, section.mr,
-                                         section.offset_within_region);
+                                         section.offset_within_region, &pbp);
                 } else if (vq == s->dvq) {
                     balloon_deflate_page(s, section.mr, section.offset_within_region);
                 } else {
@@ -381,6 +375,7 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
         virtqueue_push(vq, elem, offset);
         virtio_notify(vdev, vq);
         g_free(elem);
+        virtio_balloon_pbp_free(&pbp);
     }
 }
 
diff --git a/include/hw/virtio/virtio-balloon.h b/include/hw/virtio/virtio-balloon.h
index 5a99293a45..d1c968d237 100644
--- a/include/hw/virtio/virtio-balloon.h
+++ b/include/hw/virtio/virtio-balloon.h
@@ -33,8 +33,6 @@ typedef struct virtio_balloon_stat_modern {
        uint64_t val;
 } VirtIOBalloonStatModern;
 
-typedef struct PartiallyBalloonedPage PartiallyBalloonedPage;
-
 enum virtio_balloon_free_page_report_status {
     FREE_PAGE_REPORT_S_STOP = 0,
     FREE_PAGE_REPORT_S_REQUESTED = 1,
@@ -70,7 +68,6 @@ typedef struct VirtIOBalloon {
     int64_t stats_last_update;
     int64_t stats_poll_interval;
     uint32_t host_features;
-    PartiallyBalloonedPage *pbp;
 
     bool qemu_4_0_config_size;
 } VirtIOBalloon;