vfio-pci updates include:

- Destroy MemoryRegions on device teardown
  - Print warnings around PCI option ROM failures
  - Skip bogus mappings from 64bit BAR sizing
  - Act on DMA mapping failures
  - Fix alignment to avoid MSI-X table mapping
  - Fix debug macro typo
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJS58xzAAoJECObm247sIsiuqIP/24fhvWwRRwgc/gFpQ/7KbeP
 nUkQdx6TEOK6f0+HOQOD9HtQAiSytJhB6jZQVYfN8MWrp3QzizGH56enR6FOj86C
 9/bnpWYvjDpO/CkdxOdl7aEX/S4LMjoz/2+UmulTxrpt5cpJrsnBTqEuBiMfqwDP
 A50DHHk89uEZWaDkZvdUOc8cOFNAw4p+c20UY6DWIi/SSJlD2BPdH2FhxWE2sT9Z
 60qShybMBTYBYdom3PURzIX8g+DyY9Kzn0d2g108ereaVvYjjwOLcB3HM4W/dSJ6
 rKNGQH+lZHmL4LpWflXlqkZPn31OhOkkks6xncLnfGztRz8ghBs/wj9M+wd8hFKT
 tTf+iwmTCMFF/Lg8RIK4zUMmWgeGq0KN+9bgtJ02nuXe2q782xghxjowJPkbkuHr
 Z+ja+xmL84MyU0UD66oOubxO1RmkBPAzagBjzkJEzj/Kl0JgTqFLYhdo1bQJ1KlV
 3AbnhyR+7p+eHh7AayymhLbwdW1p6qNnEKEKc2yofsV58u4j5teed6WL/QOQQsR2
 lAdR2o6/BjELVQ/ibsbR6yqQxGoG2Y/FdPwiA3IiN+g5dw/oiYOEOHvTHAVB3f4C
 gMPCny+qO4v27Am0iuNrlA6udpc8zNMcgwrVFU+ZmCvePU08+6Jvu8PwgJLruSTx
 l29PsKGSk8fa4a2d0DJO
 =J3ON
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/awilliam/tags/vfio-pci-for-qemu-20140128.0' into staging

vfio-pci updates include:
 - Destroy MemoryRegions on device teardown
 - Print warnings around PCI option ROM failures
 - Skip bogus mappings from 64bit BAR sizing
 - Act on DMA mapping failures
 - Fix alignment to avoid MSI-X table mapping
 - Fix debug macro typo

# gpg: Signature made Tue 28 Jan 2014 15:27:47 GMT using RSA key ID 3BB08B22
# gpg: Can't check signature: public key not found

* remotes/awilliam/tags/vfio-pci-for-qemu-20140128.0:
  vfio: correct debug macro typo
  vfio: fix mapping of MSIX bar
  kvm: initialize qemu_host_page_size
  vfio-pci: Fail initfn on DMA mapping errors
  vfio: Filter out bogus mappings
  vfio: Do not reattempt a failed rom read
  vfio: warn if host device rom can't be read
  vfio: Destroy memory regions

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

hw/misc/vfio.c

@@ -135,12 +135,18 @@ enum {
 
 struct VFIOGroup;
 
+typedef struct VFIOType1 {
+    MemoryListener listener;
+    int error;
+    bool initialized;
+} VFIOType1;
+
 typedef struct VFIOContainer {
     int fd; /* /dev/vfio/vfio, empowered by the attached groups */
     struct {
         /* enable abstraction to support various iommu backends */
         union {
-            MemoryListener listener; /* Used by type1 iommu */
+            VFIOType1 type1;
         };
         void (*release)(struct VFIOContainer *);
     } iommu_data;
@@ -191,6 +197,7 @@ typedef struct VFIODevice {
     bool has_flr;
     bool has_pm_reset;
     bool needs_reset;
+    bool rom_read_failed;
 } VFIODevice;
 
 typedef struct VFIOGroup {
@@ -592,7 +599,7 @@ static void vfio_msi_interrupt(void *opaque)
         return;
     }
 
-#ifdef VFIO_DEBUG
+#ifdef DEBUG_VFIO
     MSIMessage msg;
 
     if (vdev->interrupt == VFIO_INT_MSIX) {
@@ -1125,6 +1132,14 @@ static void vfio_pci_load_rom(VFIODevice *vdev)
     vdev->rom_offset = reg_info.offset;
 
     if (!vdev->rom_size) {
+        vdev->rom_read_failed = true;
+        error_report("vfio-pci: Cannot read device rom at "
+                    "%04x:%02x:%02x.%x\n",
+                    vdev->host.domain, vdev->host.bus, vdev->host.slot,
+                    vdev->host.function);
+        error_printf("Device option ROM contents are probably invalid "
+                    "(check dmesg).\nSkip option ROM probe with rombar=0, "
+                    "or load from file with romfile=\n");
         return;
     }
 
@@ -1156,6 +1171,9 @@ static uint64_t vfio_rom_read(void *opaque, hwaddr addr, unsigned size)
     /* Load the ROM lazily when the guest tries to read it */
     if (unlikely(!vdev->rom)) {
         vfio_pci_load_rom(vdev);
+        if (unlikely(!vdev->rom && !vdev->rom_read_failed)) {
+            vfio_pci_load_rom(vdev);
+        }
     }
 
     memcpy(&val, vdev->rom + addr,
@@ -1223,6 +1241,7 @@ static void vfio_pci_size_rom(VFIODevice *vdev)
                      PCI_BASE_ADDRESS_SPACE_MEMORY, &vdev->pdev.rom);
 
     vdev->pdev.has_rom = true;
+    vdev->rom_read_failed = false;
 }
 
 static void vfio_vga_write(void *opaque, hwaddr addr,
@@ -1968,6 +1987,7 @@ static void vfio_vga_quirk_teardown(VFIODevice *vdev)
         while (!QLIST_EMPTY(&vdev->vga.region[i].quirks)) {
             VFIOQuirk *quirk = QLIST_FIRST(&vdev->vga.region[i].quirks);
             memory_region_del_subregion(&vdev->vga.region[i].mem, &quirk->mem);
+            memory_region_destroy(&quirk->mem);
             QLIST_REMOVE(quirk, next);
             g_free(quirk);
         }
@@ -1990,6 +2010,7 @@ static void vfio_bar_quirk_teardown(VFIODevice *vdev, int nr)
     while (!QLIST_EMPTY(&bar->quirks)) {
         VFIOQuirk *quirk = QLIST_FIRST(&bar->quirks);
         memory_region_del_subregion(&bar->mem, &quirk->mem);
+        memory_region_destroy(&quirk->mem);
         QLIST_REMOVE(quirk, next);
         g_free(quirk);
     }
@@ -2141,14 +2162,21 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
 
 static bool vfio_listener_skipped_section(MemoryRegionSection *section)
 {
-    return !memory_region_is_ram(section->mr);
+    return !memory_region_is_ram(section->mr) ||
+           /*
+            * Sizing an enabled 64-bit BAR can cause spurious mappings to
+            * addresses in the upper part of the 64-bit address space.  These
+            * are never accessed by the CPU and beyond the address width of
+            * some IOMMU hardware.  TODO: VFIO should tell us the IOMMU width.
+            */
+           section->offset_within_address_space & (1ULL << 63);
 }
 
 static void vfio_listener_region_add(MemoryListener *listener,
                                      MemoryRegionSection *section)
 {
     VFIOContainer *container = container_of(listener, VFIOContainer,
-                                            iommu_data.listener);
+                                            iommu_data.type1.listener);
     hwaddr iova, end;
     void *vaddr;
     int ret;
@@ -2190,6 +2218,19 @@ static void vfio_listener_region_add(MemoryListener *listener,
         error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                      "0x%"HWADDR_PRIx", %p) = %d (%m)",
                      container, iova, end - iova, vaddr, ret);
+
+        /*
+         * On the initfn path, store the first error in the container so we
+         * can gracefully fail.  Runtime, there's not much we can do other
+         * than throw a hardware error.
+         */
+        if (!container->iommu_data.type1.initialized) {
+            if (!container->iommu_data.type1.error) {
+                container->iommu_data.type1.error = ret;
+            }
+        } else {
+            hw_error("vfio: DMA mapping failed, unable to continue\n");
+        }
     }
 }
 
@@ -2197,7 +2238,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
                                      MemoryRegionSection *section)
 {
     VFIOContainer *container = container_of(listener, VFIOContainer,
-                                            iommu_data.listener);
+                                            iommu_data.type1.listener);
     hwaddr iova, end;
     int ret;
 
@@ -2242,7 +2283,7 @@ static MemoryListener vfio_memory_listener = {
 
 static void vfio_listener_release(VFIOContainer *container)
 {
-    memory_listener_unregister(&container->iommu_data.listener);
+    memory_listener_unregister(&container->iommu_data.type1.listener);
 }
 
 /*
@@ -2412,10 +2453,12 @@ static void vfio_unmap_bar(VFIODevice *vdev, int nr)
 
     memory_region_del_subregion(&bar->mem, &bar->mmap_mem);
     munmap(bar->mmap, memory_region_size(&bar->mmap_mem));
+    memory_region_destroy(&bar->mmap_mem);
 
     if (vdev->msix && vdev->msix->table_bar == nr) {
         memory_region_del_subregion(&bar->mem, &vdev->msix->mmap_mem);
         munmap(vdev->msix->mmap, memory_region_size(&vdev->msix->mmap_mem));
+        memory_region_destroy(&vdev->msix->mmap_mem);
     }
 
     memory_region_destroy(&bar->mem);
@@ -2501,7 +2544,7 @@ static void vfio_map_bar(VFIODevice *vdev, int nr)
      * potentially insert a direct-mapped subregion before and after it.
      */
     if (vdev->msix && vdev->msix->table_bar == nr) {
-        size = vdev->msix->table_offset & TARGET_PAGE_MASK;
+        size = vdev->msix->table_offset & qemu_host_page_mask;
     }
 
     strncat(name, " mmap", sizeof(name) - strlen(name) - 1);
@@ -2513,7 +2556,7 @@ static void vfio_map_bar(VFIODevice *vdev, int nr)
     if (vdev->msix && vdev->msix->table_bar == nr) {
         unsigned start;
 
-        start = TARGET_PAGE_ALIGN(vdev->msix->table_offset +
+        start = HOST_PAGE_ALIGN(vdev->msix->table_offset +
                                 (vdev->msix->entries * PCI_MSIX_ENTRY_SIZE));
 
         size = start < bar->size ? bar->size - start : 0;
@@ -3212,10 +3255,23 @@ static int vfio_connect_container(VFIOGroup *group)
             return -errno;
         }
 
-        container->iommu_data.listener = vfio_memory_listener;
+        container->iommu_data.type1.listener = vfio_memory_listener;
         container->iommu_data.release = vfio_listener_release;
 
-        memory_listener_register(&container->iommu_data.listener, &address_space_memory);
+        memory_listener_register(&container->iommu_data.type1.listener,
+                                 &address_space_memory);
+
+        if (container->iommu_data.type1.error) {
+            ret = container->iommu_data.type1.error;
+            vfio_listener_release(container);
+            g_free(container);
+            close(fd);
+            error_report("vfio: memory listener initialization failed for container\n");
+            return ret;
+        }
+
+        container->iommu_data.type1.initialized = true;
+
     } else {
         error_report("vfio: No available IOMMU models");
         g_free(container);

include/exec/exec-all.h

@@ -81,6 +81,7 @@ void cpu_gen_init(void);
 int cpu_gen_code(CPUArchState *env, struct TranslationBlock *tb,
                  int *gen_code_size_ptr);
 bool cpu_restore_state(CPUArchState *env, uintptr_t searched_pc);
+void page_size_init(void);
 
 void QEMU_NORETURN cpu_resume_from_signal(CPUArchState *env1, void *puc);
 void QEMU_NORETURN cpu_io_recompile(CPUArchState *env, uintptr_t retaddr);

kvm-all.c

@@ -1360,6 +1360,7 @@ int kvm_init(void)
      * page size for the system though.
      */
     assert(TARGET_PAGE_SIZE <= getpagesize());
+    page_size_init();
 
 #ifdef KVM_CAP_SET_GUEST_DEBUG
     QTAILQ_INIT(&s->kvm_sw_breakpoints);

translate-all.c

@@ -289,17 +289,15 @@ static inline void map_exec(void *addr, long size)
 }
 #endif
 
-static void page_init(void)
+void page_size_init(void)
 {
     /* NOTE: we can always suppose that qemu_host_page_size >=
        TARGET_PAGE_SIZE */
 #ifdef _WIN32
-    {
     SYSTEM_INFO system_info;
 
     GetSystemInfo(&system_info);
     qemu_real_host_page_size = system_info.dwPageSize;
-    }
 #else
     qemu_real_host_page_size = getpagesize();
 #endif
@@ -310,7 +308,11 @@ static void page_init(void)
         qemu_host_page_size = TARGET_PAGE_SIZE;
     }
     qemu_host_page_mask = ~(qemu_host_page_size - 1);
+}
 
+static void page_init(void)
+{
+    page_size_init();
 #if defined(CONFIG_BSD) && defined(CONFIG_USER_ONLY)
     {
 #ifdef HAVE_KINFO_GETVMMAP