Blob Blame Raw
From bbd8cc516329f84b70d38a75820f36f2ecd0abda Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Fri, 29 Sep 2017 21:46:14 +0200
Subject: [PATCH 15/27] vfio: Enable sparse mmap capability

RH-Author: Alex Williamson <alex.williamson@redhat.com>
Message-id: <20170929214614.16765.48627.stgit@gimli.home>
Patchwork-id: 76773
O-Subject: [RHEL-7.5 qemu-kvm PATCH 15/16] vfio: Enable sparse mmap capability
Bugzilla: 1494181
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Auger Eric <eric.auger@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>

Upstream: b53b0f696b10828f6393155f44a352c019e673fd
RHEL: Roll in required linux-headers update

The sparse mmap capability in a vfio region info allows vfio to tell
us which sub-areas of a region may be mmap'd.  Thus rather than
assuming a single mmap covers the entire region and later frobbing it
ourselves for things like the PCI MSI-X vector table, we can read that
directly from vfio.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Gerd Hoffmann <kraxel@redhat.com>
Tested-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
 hw/misc/vfio.c             | 67 +++++++++++++++++++++++++++++++++++++++++++---
 linux-headers/linux/vfio.h | 53 +++++++++++++++++++++++++++++++++++-
 trace-events               |  2 ++
 3 files changed, 117 insertions(+), 5 deletions(-)

diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c
index d634531..a27698b 100644
--- a/hw/misc/vfio.c
+++ b/hw/misc/vfio.c
@@ -2602,6 +2602,54 @@ static void vfio_unmap_bar(VFIOPCIDevice *vdev, int nr)
     vfio_region_finalize(&bar->region);
 }
 
+static struct vfio_info_cap_header *
+vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)
+{
+    struct vfio_info_cap_header *hdr;
+    void *ptr = info;
+
+    if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) {
+        return NULL;
+    }
+
+    for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
+        if (hdr->id == id) {
+            return hdr;
+        }
+    }
+
+    return NULL;
+}
+
+static void 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;
+
+    hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
+    if (!hdr) {
+        return;
+    }
+
+    sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);
+
+    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);
+
+    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);
+    }
+}
+
 static int vfio_region_setup(Object *obj, VFIODevice *vbasedev,
                              VFIORegion *region, int index, const char *name)
 {
@@ -2628,11 +2676,14 @@ static int vfio_region_setup(Object *obj, VFIODevice *vbasedev,
             region->flags & VFIO_REGION_INFO_FLAG_MMAP &&
             !(region->size & ~TARGET_PAGE_MASK)) {
 
-            region->nr_mmaps = 1;
-            region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
+            vfio_setup_region_sparse_mmaps(region, info);
 
-            region->mmaps[0].offset = 0;
-            region->mmaps[0].size = region->size;
+            if (!region->nr_mmaps) {
+                region->nr_mmaps = 1;
+                region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
+                region->mmaps[0].offset = 0;
+                region->mmaps[0].size = region->size;
+            }
         }
     }
 
@@ -3796,6 +3847,7 @@ static int vfio_get_region_info(VFIODevice *vbasedev, int index,
     *info = g_malloc0(argsz);
 
     (*info)->index = index;
+retry:
     (*info)->argsz = argsz;
 
     if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
@@ -3803,6 +3855,13 @@ static int vfio_get_region_info(VFIODevice *vbasedev, int index,
         return -errno;
     }
 
+    if ((*info)->argsz > argsz) {
+        argsz = (*info)->argsz;
+        *info = g_realloc(*info, argsz);
+
+        goto retry;
+    }
+
     return 0;
 }
 
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index d197fd4..8995a34 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -38,6 +38,33 @@
 #define VFIO_TYPE	(';')
 #define VFIO_BASE	100
 
+/*
+ * For extension of INFO ioctls, VFIO makes use of a capability chain
+ * designed after PCI/e capabilities.  A flag bit indicates whether
+ * this capability chain is supported and a field defined in the fixed
+ * structure defines the offset of the first capability in the chain.
+ * This field is only valid when the corresponding bit in the flags
+ * bitmap is set.  This offset field is relative to the start of the
+ * INFO buffer, as is the next field within each capability header.
+ * The id within the header is a shared address space per INFO ioctl,
+ * while the version field is specific to the capability id.  The
+ * contents following the header are specific to the capability id.
+ */
+struct vfio_info_cap_header {
+	__u16	id;		/* Identifies capability */
+	__u16	version;	/* Version specific to the capability ID */
+	__u32	next;		/* Offset of next capability */
+};
+
+/*
+ * Callers of INFO ioctls passing insufficiently sized buffers will see
+ * the capability chain flag bit set, a zero value for the first capability
+ * offset (if available within the provided argsz), and argsz will be
+ * updated to report the necessary buffer size.  For compatibility, the
+ * INFO ioctl will not report error in this case, but the capability chain
+ * will not be available.
+ */
+
 /* -------- IOCTLs for VFIO file descriptor (/dev/vfio/vfio) -------- */
 
 /**
@@ -171,13 +198,37 @@ struct vfio_region_info {
 #define VFIO_REGION_INFO_FLAG_READ	(1 << 0) /* Region supports read */
 #define VFIO_REGION_INFO_FLAG_WRITE	(1 << 1) /* Region supports write */
 #define VFIO_REGION_INFO_FLAG_MMAP	(1 << 2) /* Region supports mmap */
+#define VFIO_REGION_INFO_FLAG_CAPS	(1 << 3) /* Info supports caps */
 	__u32	index;		/* Region index */
-	__u32	resv;		/* Reserved for alignment */
+	__u32	cap_offset;	/* Offset within info struct of first cap */
 	__u64	size;		/* Region size (bytes) */
 	__u64	offset;		/* Region offset from start of device fd */
 };
 #define VFIO_DEVICE_GET_REGION_INFO	_IO(VFIO_TYPE, VFIO_BASE + 8)
 
+/*
+ * The sparse mmap capability allows finer granularity of specifying areas
+ * within a region with mmap support.  When specified, the user should only
+ * mmap the offset ranges specified by the areas array.  mmaps outside of the
+ * areas specified may fail (such as the range covering a PCI MSI-X table) or
+ * may result in improper device behavior.
+ *
+ * The structures below define version 1 of this capability.
+ */
+#define VFIO_REGION_INFO_CAP_SPARSE_MMAP        1
+
+struct vfio_region_sparse_mmap_area {
+	__u64	offset;	/* Offset of mmap'able area within region */
+	__u64	size;	/* Size of mmap'able area */
+};
+
+struct vfio_region_info_cap_sparse_mmap {
+	struct vfio_info_cap_header header;
+	__u32	nr_areas;
+	__u32	reserved;
+	struct vfio_region_sparse_mmap_area areas[];
+};
+
 /**
  * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
  *				    struct vfio_irq_info)
diff --git a/trace-events b/trace-events
index cc62b0b..fa2618d 100644
--- a/trace-events
+++ b/trace-events
@@ -1164,3 +1164,5 @@ vfio_region_mmap(const char *name, unsigned long offset, unsigned long end) "Reg
 vfio_region_exit(const char *name, int index) "Device %s, region %d"
 vfio_region_finalize(const char *name, int index) "Device %s, region %d"
 vfio_region_mmaps_set_enabled(const char *name, bool enabled) "Region %s mmaps enabled: %d"
+vfio_region_sparse_mmap_header(const char *name, int index, int nr_areas) "Device %s region %d: %d sparse mmap entries"
+vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end) "sparse entry %d [0x%lx - 0x%lx]"
-- 
1.8.3.1