Merge remote-tracking branch 'remotes/awilliam/tags/vfio-updates-20161031.0' into staging

VFIO updates 2016-10-31

 - Replace skip_dump with ram_device to denote device memory and mark
   as non-direct to avoid memcpy to MMIO - fixes RTL (Alex Williamson)
 - Skip zero-length sparse mmaps - avoids unnecessary warning
   (Alex Williamson)
 - Clear BARs on reset so guest doesn't assume programming on return
   from S3 (Ido Yariv)
 - Enable sub-page MMIO mmaps - performance improvement for devices
   with smaller BARs, iff both host and guest map them to full,
   aligned pages (Yongji Xie)

# gpg: Signature made Mon 31 Oct 2016 17:26:47 GMT
# gpg:                using RSA key 0x239B9B6E3BB08B22
# gpg: Good signature from "Alex Williamson <alex.williamson@redhat.com>"
# gpg:                 aka "Alex Williamson <alex@shazbot.org>"
# gpg:                 aka "Alex Williamson <alwillia@redhat.com>"
# gpg:                 aka "Alex Williamson <alex.l.williamson@gmail.com>"
# Primary key fingerprint: 42F6 C04E 540B D1A9 9E7B  8A90 239B 9B6E 3BB0 8B22

* remotes/awilliam/tags/vfio-updates-20161031.0:
  vfio: Add support for mmapping sub-page MMIO BARs
  vfio/pci: fix out-of-sync BAR information on reset
  vfio: Handle zero-length sparse mmap ranges
  memory: Don't use memcpy for ram_device regions
  memory: Replace skip_dump flag with "ram_device"

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

7 files changed, 218 insertions, 42 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 9505fb3..801578b 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -610,16 +610,16 @@ vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)
     return NULL;
 }
 
-static void vfio_setup_region_sparse_mmaps(VFIORegion *region,
-                                           struct vfio_region_info *info)
+static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
+                                          struct vfio_region_info *info)
 {
     struct vfio_info_cap_header *hdr;
     struct vfio_region_info_cap_sparse_mmap *sparse;
-    int i;
+    int i, j;
 
     hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
     if (!hdr) {
-        return;
+        return -ENODEV;
     }
 
     sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);
@@ -627,16 +627,24 @@ static void vfio_setup_region_sparse_mmaps(VFIORegion *region,
     trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
                                          region->nr, sparse->nr_areas);
 
-    region->nr_mmaps = sparse->nr_areas;
-    region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
+    region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);
 
-    for (i = 0; i < region->nr_mmaps; i++) {
-        region->mmaps[i].offset = sparse->areas[i].offset;
-        region->mmaps[i].size = sparse->areas[i].size;
-        trace_vfio_region_sparse_mmap_entry(i, region->mmaps[i].offset,
-                                            region->mmaps[i].offset +
-                                            region->mmaps[i].size);
+    for (i = 0, j = 0; i < sparse->nr_areas; i++) {
+        trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
+                                            sparse->areas[i].offset +
+                                            sparse->areas[i].size);
+
+        if (sparse->areas[i].size) {
+            region->mmaps[j].offset = sparse->areas[i].offset;
+            region->mmaps[j].size = sparse->areas[i].size;
+            j++;
+        }
     }
+
+    region->nr_mmaps = j;
+    region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));
+
+    return 0;
 }
 
 int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
@@ -662,12 +670,11 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
                               region, name, region->size);
 
         if (!vbasedev->no_mmap &&
-            region->flags & VFIO_REGION_INFO_FLAG_MMAP &&
-            !(region->size & ~qemu_real_host_page_mask)) {
+            region->flags & VFIO_REGION_INFO_FLAG_MMAP) {
 
-            vfio_setup_region_sparse_mmaps(region, info);
+            ret = vfio_setup_region_sparse_mmaps(region, info);
 
-            if (!region->nr_mmaps) {
+            if (ret) {
                 region->nr_mmaps = 1;
                 region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
                 region->mmaps[0].offset = 0;
@@ -724,12 +731,11 @@ int vfio_region_mmap(VFIORegion *region)
 
         name = g_strdup_printf("%s mmaps[%d]",
                                memory_region_name(region->mem), i);
-        memory_region_init_ram_ptr(&region->mmaps[i].mem,
-                                   memory_region_owner(region->mem),
-                                   name, region->mmaps[i].size,
-                                   region->mmaps[i].mmap);
+        memory_region_init_ram_device_ptr(&region->mmaps[i].mem,
+                                          memory_region_owner(region->mem),
+                                          name, region->mmaps[i].size,
+                                          region->mmaps[i].mmap);
         g_free(name);
-        memory_region_set_skip_dump(&region->mmaps[i].mem);
         memory_region_add_subregion(region->mem, region->mmaps[i].offset,
                                     &region->mmaps[i].mem);
 
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 65d30fd..d7dbe0e 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1071,6 +1071,55 @@ static const MemoryRegionOps vfio_vga_ops = {
 };
 
 /*
+ * Expand memory region of sub-page(size < PAGE_SIZE) MMIO BAR to page
+ * size if the BAR is in an exclusive page in host so that we could map
+ * this BAR to guest. But this sub-page BAR may not occupy an exclusive
+ * page in guest. So we should set the priority of the expanded memory
+ * region to zero in case of overlap with BARs which share the same page
+ * with the sub-page BAR in guest. Besides, we should also recover the
+ * size of this sub-page BAR when its base address is changed in guest
+ * and not page aligned any more.
+ */
+static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
+{
+    VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev);
+    VFIORegion *region = &vdev->bars[bar].region;
+    MemoryRegion *mmap_mr, *mr;
+    PCIIORegion *r;
+    pcibus_t bar_addr;
+    uint64_t size = region->size;
+
+    /* Make sure that the whole region is allowed to be mmapped */
+    if (region->nr_mmaps != 1 || !region->mmaps[0].mmap ||
+        region->mmaps[0].size != region->size) {
+        return;
+    }
+
+    r = &pdev->io_regions[bar];
+    bar_addr = r->addr;
+    mr = region->mem;
+    mmap_mr = &region->mmaps[0].mem;
+
+    /* If BAR is mapped and page aligned, update to fill PAGE_SIZE */
+    if (bar_addr != PCI_BAR_UNMAPPED &&
+        !(bar_addr & ~qemu_real_host_page_mask)) {
+        size = qemu_real_host_page_size;
+    }
+
+    memory_region_transaction_begin();
+
+    memory_region_set_size(mr, size);
+    memory_region_set_size(mmap_mr, size);
+    if (size != region->size && memory_region_is_mapped(mr)) {
+        memory_region_del_subregion(r->address_space, mr);
+        memory_region_add_subregion_overlap(r->address_space,
+                                            bar_addr, mr, 0);
+    }
+
+    memory_region_transaction_commit();
+}
+
+/*
  * PCI config space
  */
 uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
@@ -1153,6 +1202,24 @@ void vfio_pci_write_config(PCIDevice *pdev,
         } else if (was_enabled && !is_enabled) {
             vfio_msix_disable(vdev);
         }
+    } else if (ranges_overlap(addr, len, PCI_BASE_ADDRESS_0, 24) ||
+        range_covers_byte(addr, len, PCI_COMMAND)) {
+        pcibus_t old_addr[PCI_NUM_REGIONS - 1];
+        int bar;
+
+        for (bar = 0; bar < PCI_ROM_SLOT; bar++) {
+            old_addr[bar] = pdev->io_regions[bar].addr;
+        }
+
+        pci_default_write_config(pdev, addr, val, len);
+
+        for (bar = 0; bar < PCI_ROM_SLOT; bar++) {
+            if (old_addr[bar] != pdev->io_regions[bar].addr &&
+                pdev->io_regions[bar].size > 0 &&
+                pdev->io_regions[bar].size < qemu_real_host_page_size) {
+                vfio_sub_page_bar_update_mapping(pdev, bar);
+            }
+        }
     } else {
         /* Write everything to QEMU to keep emulated bits correct */
         pci_default_write_config(pdev, addr, val, len);
@@ -1922,11 +1989,23 @@ static void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
 static void vfio_pci_post_reset(VFIOPCIDevice *vdev)
 {
     Error *err = NULL;
+    int nr;
 
     vfio_intx_enable(vdev, &err);
     if (err) {
         error_reportf_err(err, ERR_PREFIX, vdev->vbasedev.name);
     }
+
+    for (nr = 0; nr < PCI_NUM_REGIONS - 1; ++nr) {
+        off_t addr = vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr);
+        uint32_t val = 0;
+        uint32_t len = sizeof(val);
+
+        if (pwrite(vdev->vbasedev.fd, &val, len, addr) != len) {
+            error_report("%s(%s) reset bar %d failed: %m", __func__,
+                         vdev->vbasedev.name, nr);
+        }
+    }
 }
 
 static bool vfio_pci_host_match(PCIHostDeviceAddress *addr, const char *name)
diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c
index 7443d34..4409bcc 100644
--- a/hw/vfio/spapr.c
+++ b/hw/vfio/spapr.c
@@ -25,7 +25,7 @@ static bool vfio_prereg_listener_skipped_section(MemoryRegionSection *section)
     }
 
     return !memory_region_is_ram(section->mr) ||
-            memory_region_is_skip_dump(section->mr);
+            memory_region_is_ram_device(section->mr);
 }
 
 static void *vfio_prereg_gpa_to_vaddr(MemoryRegionSection *section, hwaddr gpa)
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 79ccaab..9728a2f 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -209,7 +209,7 @@ struct MemoryRegion {
     void (*destructor)(MemoryRegion *mr);
     uint64_t align;
     bool terminates;
-    bool skip_dump;
+    bool ram_device;
     bool enabled;
     bool warning_printed; /* For reservations */
     uint8_t vga_logging_count;
@@ -449,6 +449,30 @@ void memory_region_init_ram_ptr(MemoryRegion *mr,
                                 void *ptr);
 
 /**
+ * memory_region_init_ram_device_ptr:  Initialize RAM device memory region from
+ *                                     a user-provided pointer.
+ *
+ * A RAM device represents a mapping to a physical device, such as to a PCI
+ * MMIO BAR of an vfio-pci assigned device.  The memory region may be mapped
+ * into the VM address space and access to the region will modify memory
+ * directly.  However, the memory region should not be included in a memory
+ * dump (device may not be enabled/mapped at the time of the dump), and
+ * operations incompatible with manipulating MMIO should be avoided.  Replaces
+ * skip_dump flag.
+ *
+ * @mr: the #MemoryRegion to be initialized.
+ * @owner: the object that tracks the region's reference count
+ * @name: the name of the region.
+ * @size: size of the region.
+ * @ptr: memory to be mapped; must contain at least @size bytes.
+ */
+void memory_region_init_ram_device_ptr(MemoryRegion *mr,
+                                       struct Object *owner,
+                                       const char *name,
+                                       uint64_t size,
+                                       void *ptr);
+
+/**
  * memory_region_init_alias: Initialize a memory region that aliases all or a
  *                           part of another memory region.
  *
@@ -574,22 +598,13 @@ static inline bool memory_region_is_ram(MemoryRegion *mr)
 }
 
 /**
- * memory_region_is_skip_dump: check whether a memory region should not be
- *                             dumped
- *
- * Returns %true is a memory region should not be dumped(e.g. VFIO BAR MMAP).
+ * memory_region_is_ram_device: check whether a memory region is a ram device
  *
- * @mr: the memory region being queried
- */
-bool memory_region_is_skip_dump(MemoryRegion *mr);
-
-/**
- * memory_region_set_skip_dump: Set skip_dump flag, dump will ignore this memory
- *                              region
+ * Returns %true is a memory region is a device backed ram region
  *
  * @mr: the memory region being queried
  */
-void memory_region_set_skip_dump(MemoryRegion *mr);
+bool memory_region_is_ram_device(MemoryRegion *mr);
 
 /**
  * memory_region_is_romd: check whether a memory region is in ROMD mode
@@ -1465,9 +1480,11 @@ void *qemu_map_ram_ptr(RAMBlock *ram_block, ram_addr_t addr);
 static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
 {
     if (is_write) {
-        return memory_region_is_ram(mr) && !mr->readonly;
+        return memory_region_is_ram(mr) &&
+               !mr->readonly && !memory_region_is_ram_device(mr);
     } else {
-        return memory_region_is_ram(mr) || memory_region_is_romd(mr);
+        return (memory_region_is_ram(mr) && !memory_region_is_ram_device(mr)) ||
+               memory_region_is_romd(mr);
     }
 }
 
diff --git a/memory.c b/memory.c
index edbc701..33110e9 100644
--- a/memory.c
+++ b/memory.c
@@ -1128,6 +1128,71 @@ const MemoryRegionOps unassigned_mem_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
+static uint64_t memory_region_ram_device_read(void *opaque,
+                                              hwaddr addr, unsigned size)
+{
+    MemoryRegion *mr = opaque;
+    uint64_t data = (uint64_t)~0;
+
+    switch (size) {
+    case 1:
+        data = *(uint8_t *)(mr->ram_block->host + addr);
+        break;
+    case 2:
+        data = *(uint16_t *)(mr->ram_block->host + addr);
+        break;
+    case 4:
+        data = *(uint32_t *)(mr->ram_block->host + addr);
+        break;
+    case 8:
+        data = *(uint64_t *)(mr->ram_block->host + addr);
+        break;
+    }
+
+    trace_memory_region_ram_device_read(get_cpu_index(), mr, addr, data, size);
+
+    return data;
+}
+
+static void memory_region_ram_device_write(void *opaque, hwaddr addr,
+                                           uint64_t data, unsigned size)
+{
+    MemoryRegion *mr = opaque;
+
+    trace_memory_region_ram_device_write(get_cpu_index(), mr, addr, data, size);
+
+    switch (size) {
+    case 1:
+        *(uint8_t *)(mr->ram_block->host + addr) = (uint8_t)data;
+        break;
+    case 2:
+        *(uint16_t *)(mr->ram_block->host + addr) = (uint16_t)data;
+        break;
+    case 4:
+        *(uint32_t *)(mr->ram_block->host + addr) = (uint32_t)data;
+        break;
+    case 8:
+        *(uint64_t *)(mr->ram_block->host + addr) = data;
+        break;
+    }
+}
+
+static const MemoryRegionOps ram_device_mem_ops = {
+    .read = memory_region_ram_device_read,
+    .write = memory_region_ram_device_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+        .unaligned = true,
+    },
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+        .unaligned = true,
+    },
+};
+
 bool memory_region_access_valid(MemoryRegion *mr,
                                 hwaddr addr,
                                 unsigned size,
@@ -1355,9 +1420,16 @@ void memory_region_init_ram_ptr(MemoryRegion *mr,
     mr->ram_block = qemu_ram_alloc_from_ptr(size, ptr, mr, &error_fatal);
 }
 
-void memory_region_set_skip_dump(MemoryRegion *mr)
+void memory_region_init_ram_device_ptr(MemoryRegion *mr,
+                                       Object *owner,
+                                       const char *name,
+                                       uint64_t size,
+                                       void *ptr)
 {
-    mr->skip_dump = true;
+    memory_region_init_ram_ptr(mr, owner, name, size, ptr);
+    mr->ram_device = true;
+    mr->ops = &ram_device_mem_ops;
+    mr->opaque = mr;
 }
 
 void memory_region_init_alias(MemoryRegion *mr,
@@ -1491,9 +1563,9 @@ const char *memory_region_name(const MemoryRegion *mr)
     return mr->name;
 }
 
-bool memory_region_is_skip_dump(MemoryRegion *mr)
+bool memory_region_is_ram_device(MemoryRegion *mr)
 {
-    return mr->skip_dump;
+    return mr->ram_device;
 }
 
 uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr)
diff --git a/memory_mapping.c b/memory_mapping.c
index e3e0d95..6a39d71 100644
--- a/memory_mapping.c
+++ b/memory_mapping.c
@@ -206,7 +206,7 @@ static void guest_phys_blocks_region_add(MemoryListener *listener,
 
     /* we only care about RAM */
     if (!memory_region_is_ram(section->mr) ||
-        memory_region_is_skip_dump(section->mr)) {
+        memory_region_is_ram_device(section->mr)) {
         return;
     }
 
diff --git a/trace-events b/trace-events
index 8ecded5..f74e1d3 100644
--- a/trace-events
+++ b/trace-events
@@ -121,6 +121,8 @@ memory_region_subpage_read(int cpu_index, void *mr, uint64_t offset, uint64_t va
 memory_region_subpage_write(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset %#"PRIx64" value %#"PRIx64" size %u"
 memory_region_tb_read(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
 memory_region_tb_write(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
+memory_region_ram_device_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
+memory_region_ram_device_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
 
 ### Guest events, keep at bottom