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

pci, pc, virtio: fixes, cleanups, tests

Lots of work on tests: BiosTablesTest UEFI app,
vhost-user testing for non-Linux hosts.
Misc cleanups and fixes all over the place

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

# gpg: Signature made Fri 22 Feb 2019 15:51:40 GMT
# 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: (26 commits)
  pci: Sanity test minimum downstream LNKSTA
  hw/smbios: fix offset of type 3 sku field
  pci: Move NVIDIA vendor id to the rest of ids
  virtio-balloon: Safely handle BALLOON_PAGE_SIZE < host page size
  virtio-balloon: Use ram_block_discard_range() instead of raw madvise()
  virtio-balloon: Rework ballon_page() interface
  virtio-balloon: Corrections to address verification
  virtio-balloon: Remove unnecessary MADV_WILLNEED on deflate
  i386/kvm: ignore masked irqs when update msi routes
  contrib/vhost-user-blk: fix the compilation issue
  Revert "contrib/vhost-user-blk: fix the compilation issue"
  pc-dimm: use same mechanism for [get|set]_addr
  tests/data: introduce "uefi-boot-images" with the "bios-tables-test" ISOs
  tests/uefi-test-tools: add build scripts
  tests: introduce "uefi-test-tools" with the BiosTablesTest UEFI app
  roms: build the EfiRom utility from the roms/edk2 submodule
  roms: add the edk2 project as a git submodule
  vhost-user-test: create a temporary directory per TestServer
  vhost-user-test: small changes to init_hugepagefs
  vhost-user-test: create a main loop per TestServer
  ...

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

5 files changed, 114 insertions, 23 deletions

diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs
index d335dd0..a3eb8ed 100644
--- a/hw/virtio/Makefile.objs
+++ b/hw/virtio/Makefile.objs
@@ -2,15 +2,18 @@ ifeq ($(CONFIG_VIRTIO),y)
 common-obj-y += virtio-bus.o
 obj-y += virtio.o
 
+obj-$(call lor,$(CONFIG_VHOST_USER),$(CONFIG_VHOST_KERNEL)) += vhost.o vhost-backend.o
+common-obj-$(call lnot,$(call lor,$(CONFIG_VHOST_USER),$(CONFIG_VHOST_KERNEL))) += vhost-stub.o
+obj-$(CONFIG_VHOST_USER) += vhost-user.o
+
 common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o
 common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
 common-obj-$(CONFIG_VIRTIO_MMIO) += virtio-mmio.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio-balloon.o
 obj-$(CONFIG_VIRTIO_CRYPTO) += virtio-crypto.o
 obj-$(call land,$(CONFIG_VIRTIO_CRYPTO),$(CONFIG_VIRTIO_PCI)) += virtio-crypto-pci.o
-
-obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o
 obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o
+
 ifeq ($(CONFIG_VIRTIO_PCI),y)
 obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o
 obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk-pci.o
@@ -28,5 +31,4 @@ obj-$(CONFIG_VIRTIO_SERIAL) += virtio-serial-pci.o
 endif
 endif
 
-common-obj-$(call lnot,$(call land,$(CONFIG_VIRTIO),$(CONFIG_LINUX))) += vhost-stub.o
 common-obj-$(CONFIG_ALL) += vhost-stub.o
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 7f09efa..96b8d3c 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -9,11 +9,14 @@
  */
 
 #include "qemu/osdep.h"
-#include <linux/vhost.h>
-#include <sys/ioctl.h>
 #include "hw/virtio/vhost.h"
 #include "hw/virtio/vhost-backend.h"
 #include "qemu/error-report.h"
+#include "standard-headers/linux/vhost_types.h"
+
+#ifdef CONFIG_VHOST_KERNEL
+#include <linux/vhost.h>
+#include <sys/ioctl.h>
 
 static int vhost_kernel_call(struct vhost_dev *dev, unsigned long int request,
                              void *arg)
@@ -265,18 +268,23 @@ static const VhostOps kernel_ops = {
         .vhost_set_iotlb_callback = vhost_kernel_set_iotlb_callback,
         .vhost_send_device_iotlb_msg = vhost_kernel_send_device_iotlb_msg,
 };
+#endif
 
 int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
 {
     int r = 0;
 
     switch (backend_type) {
+#ifdef CONFIG_VHOST_KERNEL
     case VHOST_BACKEND_TYPE_KERNEL:
         dev->vhost_ops = &kernel_ops;
         break;
+#endif
+#ifdef CONFIG_VHOST_USER
     case VHOST_BACKEND_TYPE_USER:
         dev->vhost_ops = &user_ops;
         break;
+#endif
     default:
         error_report("Unknown vhost backend type");
         r = -1;
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 564a31d..0d6c64e 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -27,8 +27,12 @@
 #include <sys/ioctl.h>
 #include <sys/socket.h>
 #include <sys/un.h>
-#include <linux/vhost.h>
+
+#include "standard-headers/linux/vhost_types.h"
+
+#ifdef CONFIG_LINUX
 #include <linux/userfaultfd.h>
+#endif
 
 #define VHOST_MEMORY_MAX_NREGIONS    8
 #define VHOST_USER_F_PROTOCOL_FEATURES 30
@@ -1110,6 +1114,7 @@ out:
     return ret;
 }
 
+#ifdef CONFIG_LINUX
 /*
  * Called back from the postcopy fault thread when a fault is received on our
  * ufd.
@@ -1177,6 +1182,7 @@ static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
     trace_vhost_user_postcopy_waker_nomatch(qemu_ram_get_idstr(rb), offset);
     return 0;
 }
+#endif
 
 /*
  * Called at the start of an inbound postcopy on reception of the
@@ -1184,6 +1190,7 @@ static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
  */
 static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
 {
+#ifdef CONFIG_LINUX
     struct vhost_user *u = dev->opaque;
     CharBackend *chr = u->user->chr;
     int ufd;
@@ -1227,6 +1234,10 @@ static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
     u->postcopy_fd.idstr = "vhost-user"; /* Need to find unique name */
     postcopy_register_shared_ufd(&u->postcopy_fd);
     return 0;
+#else
+    error_setg(errp, "Postcopy not supported on non-Linux systems");
+    return -1;
+#endif
 }
 
 /*
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 569c405..311432f 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -21,7 +21,7 @@
 #include "qemu/range.h"
 #include "qemu/error-report.h"
 #include "qemu/memfd.h"
-#include <linux/vhost.h>
+#include "standard-headers/linux/vhost_types.h"
 #include "exec/address-spaces.h"
 #include "hw/virtio/virtio-bus.h"
 #include "hw/virtio/virtio-access.h"
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index a12677d..d3f2913 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -33,11 +33,81 @@
 
 #define BALLOON_PAGE_SIZE  (1 << VIRTIO_BALLOON_PFN_SHIFT)
 
-static void balloon_page(void *addr, int deflate)
+struct PartiallyBalloonedPage {
+    RAMBlock *rb;
+    ram_addr_t base;
+    unsigned long bitmap[];
+};
+
+static void balloon_inflate_page(VirtIOBalloon *balloon,
+                                 MemoryRegion *mr, hwaddr offset)
 {
-    if (!qemu_balloon_is_inhibited()) {
-        qemu_madvise(addr, BALLOON_PAGE_SIZE,
-                deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
+    void *addr = memory_region_get_ram_ptr(mr) + offset;
+    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_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);
+        /* We ignore errors from ram_block_discard_range(), because it
+         * has already reported them, and failing to discard a balloon
+         * page is not fatal */
+        return;
+    }
+
+    /* Hard case
+     *
+     * We've put a piece of a larger host page into the balloon - we
+     * need to keep track until we have a whole host page to
+     * discard
+     */
+    warn_report_once(
+"Balloon used with backing page size > 4kiB, this may not be reliable");
+
+    subpages = rb_page_size / BALLOON_PAGE_SIZE;
+
+    if (balloon->pbp
+        && (rb != balloon->pbp->rb
+            || host_page_base != balloon->pbp->base)) {
+        /* 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 */
+        free(balloon->pbp);
+        balloon->pbp = NULL;
+    }
+
+    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;
+    }
+
+    bitmap_set(balloon->pbp->bitmap,
+               (ram_offset - balloon->pbp->base) / BALLOON_PAGE_SIZE,
+               subpages);
+
+    if (bitmap_full(balloon->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);
+        /* We ignore errors from ram_block_discard_range(), because it
+         * has already reported them, and failing to discard a balloon
+         * page is not fatal */
+
+        free(balloon->pbp);
+        balloon->pbp = NULL;
     }
 }
 
@@ -222,17 +292,19 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
         }
 
         while (iov_to_buf(elem->out_sg, elem->out_num, offset, &pfn, 4) == 4) {
-            ram_addr_t pa;
-            ram_addr_t addr;
+            hwaddr pa;
             int p = virtio_ldl_p(vdev, &pfn);
 
-            pa = (ram_addr_t) p << VIRTIO_BALLOON_PFN_SHIFT;
+            pa = (hwaddr) p << VIRTIO_BALLOON_PFN_SHIFT;
             offset += 4;
 
-            /* FIXME: remove get_system_memory(), but how? */
-            section = memory_region_find(get_system_memory(), pa, 1);
-            if (!int128_nz(section.size) ||
-                !memory_region_is_ram(section.mr) ||
+            section = memory_region_find(get_system_memory(), pa,
+                                         BALLOON_PAGE_SIZE);
+            if (!section.mr) {
+                trace_virtio_balloon_bad_addr(pa);
+                continue;
+            }
+            if (!memory_region_is_ram(section.mr) ||
                 memory_region_is_rom(section.mr) ||
                 memory_region_is_romd(section.mr)) {
                 trace_virtio_balloon_bad_addr(pa);
@@ -242,11 +314,9 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 
             trace_virtio_balloon_handle_output(memory_region_name(section.mr),
                                                pa);
-            /* Using memory_region_get_ram_ptr is bending the rules a bit, but
-               should be OK because we only want a single page.  */
-            addr = section.offset_within_region;
-            balloon_page(memory_region_get_ram_ptr(section.mr) + addr,
-                         !!(vq == s->dvq));
+            if (!qemu_balloon_is_inhibited() && vq != s->dvq) {
+                balloon_inflate_page(s, section.mr, section.offset_within_region);
+            }
             memory_region_unref(section.mr);
         }