[Qemu-devel] [v6][PATCH 10/10] xen, gfx passthrough: add opregion mapping

[Tiejun Chen <tiejun.chen@intel.com>]

The OpRegion shouldn't be mapped 1:1 because the address in the host
can't be used in the guest directly.

This patch traps read and write access to the opregion of the Intel
GPU config space (offset 0xfc).

The original patch is from Jean Guyader <jean.guyader@eu.citrix.com>

Signed-off-by: Tiejun Chen <tiejun.chen@intel.com>
Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
---
 hw/xen/xen_pt.h             |  6 +++-
 hw/xen/xen_pt_config_init.c | 52 ++++++++++++++++++++++++++--
 hw/xen/xen_pt_graphics.c    | 82 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 137 insertions(+), 3 deletions(-)

diff --git a/hw/xen/xen_pt.h b/hw/xen/xen_pt.h
index 94cde4a..56f6d74 100644
--- a/hw/xen/xen_pt.h
+++ b/hw/xen/xen_pt.h
@@ -37,6 +37,9 @@ typedef struct XenPTReg XenPTReg;
 
 typedef struct XenPCIPassthroughState XenPCIPassthroughState;
 
+uint32_t igd_read_opregion(XenPCIPassthroughState *s);
+void igd_write_opregion(XenPCIPassthroughState *s, uint32_t val);
+
 /* function type for config reg */
 typedef int (*xen_pt_conf_reg_init)
     (XenPCIPassthroughState *, XenPTRegInfo *, uint32_t real_offset,
@@ -63,8 +66,9 @@ typedef int (*xen_pt_conf_byte_read)
 #define XEN_PT_BAR_ALLF 0xFFFFFFFF
 #define XEN_PT_BAR_UNMAPPED (-1)
 
-#define PCI_CAP_MAX 48
+#define XEN_PCI_CAP_MAX 48
 
+#define XEN_PCI_INTEL_OPREGION 0xfc
 
 typedef enum {
     XEN_PT_GRP_TYPE_HARDWIRED = 0,  /* 0 Hardwired reg group */
diff --git a/hw/xen/xen_pt_config_init.c b/hw/xen/xen_pt_config_init.c
index de9a20f..e4e301a 100644
--- a/hw/xen/xen_pt_config_init.c
+++ b/hw/xen/xen_pt_config_init.c
@@ -575,6 +575,22 @@ static int xen_pt_exp_rom_bar_reg_write(XenPCIPassthroughState *s,
     return 0;
 }
 
+static int xen_pt_intel_opregion_read(XenPCIPassthroughState *s,
+                                      XenPTReg *cfg_entry,
+                                      uint32_t *value, uint32_t valid_mask)
+{
+    *value = igd_read_opregion(s);
+    return 0;
+}
+
+static int xen_pt_intel_opregion_write(XenPCIPassthroughState *s,
+                                       XenPTReg *cfg_entry, uint32_t *value,
+                                       uint32_t dev_value, uint32_t valid_mask)
+{
+    igd_write_opregion(s, *value);
+    return 0;
+}
+
 /* Header Type0 reg static information table */
 static XenPTRegInfo xen_pt_emu_reg_header0[] = {
     /* Vendor ID reg */
@@ -1440,6 +1456,20 @@ static XenPTRegInfo xen_pt_emu_reg_msix[] = {
     },
 };
 
+static XenPTRegInfo xen_pt_emu_reg_igd_opregion[] = {
+    /* Intel IGFX OpRegion reg */
+    {
+        .offset     = 0x0,
+        .size       = 4,
+        .init_val   = 0,
+        .no_wb      = 1,
+        .u.dw.read   = xen_pt_intel_opregion_read,
+        .u.dw.write  = xen_pt_intel_opregion_write,
+    },
+    {
+        .size = 0,
+    },
+};
 
 /****************************
  * Capabilities
@@ -1677,6 +1707,14 @@ static const XenPTRegGroupInfo xen_pt_emu_reg_grps[] = {
         .size_init   = xen_pt_msix_size_init,
         .emu_regs = xen_pt_emu_reg_msix,
     },
+    /* Intel IGD Opregion group */
+    {
+        .grp_id      = XEN_PCI_INTEL_OPREGION,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = 0x4,
+        .size_init   = xen_pt_reg_grp_size_init,
+        .emu_regs    = xen_pt_emu_reg_igd_opregion,
+    },
     {
         .grp_size = 0,
     },
@@ -1727,7 +1765,7 @@ out:
 static uint8_t find_cap_offset(XenPCIPassthroughState *s, uint8_t cap)
 {
     uint8_t id;
-    unsigned max_cap = PCI_CAP_MAX;
+    unsigned max_cap = XEN_PCI_CAP_MAX;
     uint8_t pos = PCI_CAPABILITY_LIST;
     uint8_t status = 0;
 
@@ -1806,7 +1844,8 @@ int xen_pt_config_init(XenPCIPassthroughState *s)
         uint32_t reg_grp_offset = 0;
         XenPTRegGroup *reg_grp_entry = NULL;
 
-        if (xen_pt_emu_reg_grps[i].grp_id != 0xFF) {
+        if (xen_pt_emu_reg_grps[i].grp_id != 0xFF
+            && xen_pt_emu_reg_grps[i].grp_id != XEN_PCI_INTEL_OPREGION) {
             if (xen_pt_hide_dev_cap(&s->real_device,
                                     xen_pt_emu_reg_grps[i].grp_id)) {
                 continue;
@@ -1819,6 +1858,15 @@ int xen_pt_config_init(XenPCIPassthroughState *s)
             }
         }
 
+        /*
+         * By default we will trap up to 0x40 in the cfg space.
+         * If an intel device is pass through we need to trap 0xfc,
+         * therefore the size should be 0xff.
+         */
+        if (xen_pt_emu_reg_grps[i].grp_id == XEN_PCI_INTEL_OPREGION) {
+            reg_grp_offset = XEN_PCI_INTEL_OPREGION;
+        }
+
         reg_grp_entry = g_new0(XenPTRegGroup, 1);
         QLIST_INIT(&reg_grp_entry->reg_tbl_list);
         QLIST_INSERT_HEAD(&s->reg_grps, reg_grp_entry, entries);
diff --git a/hw/xen/xen_pt_graphics.c b/hw/xen/xen_pt_graphics.c
index 227089b..372badf 100644
--- a/hw/xen/xen_pt_graphics.c
+++ b/hw/xen/xen_pt_graphics.c
@@ -6,6 +6,11 @@
 #include "hw/xen/xen_backend.h"
 #include "hw/pci/pci_bus.h"
 
+static unsigned long igd_guest_opregion;
+static unsigned long igd_host_opregion;
+
+#define XEN_PCI_INTEL_OPREGION_MASK 0xfff
+
 typedef struct VGARegion {
     int type;           /* Memory or port I/O */
     uint64_t guest_base_addr;
@@ -82,6 +87,7 @@ int xen_pt_register_vga_regions(XenHostPCIDevice *dev)
 int xen_pt_unregister_vga_regions(XenHostPCIDevice *dev)
 {
     int i = 0;
+    int ret = 0;
 
     if (!is_igd_vga_passthrough(dev)) {
         return 0;
@@ -108,6 +114,17 @@ int xen_pt_unregister_vga_regions(XenHostPCIDevice *dev)
         }
     }
 
+    if (igd_guest_opregion) {
+        ret = xc_domain_memory_mapping(xen_xc, xen_domid,
+                (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT),
+                (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+                3,
+                DPCI_REMOVE_MAPPING);
+        if (ret) {
+            return ret;
+        }
+    }
+
     return 0;
 }
 
@@ -260,3 +277,68 @@ err_out:
     XEN_PT_ERR(pci_dev, "Can't get pci_dev_host_bridge\n");
     return -1;
 }
+
+uint32_t igd_read_opregion(XenPCIPassthroughState *s)
+{
+    uint32_t val = 0;
+
+    if (!igd_guest_opregion) {
+        return val;
+    }
+
+    val = igd_guest_opregion;
+
+    XEN_PT_LOG(&s->dev, "Read opregion val=%x\n", val);
+    return val;
+}
+
+#define XEN_PCI_INTEL_OPREGION_PAGES 0x3
+#define XEN_PCI_INTEL_OPREGION_ENABLE_ACCESSED 0x1
+void igd_write_opregion(XenPCIPassthroughState *s, uint32_t val)
+{
+    int ret;
+
+    if (igd_guest_opregion) {
+        XEN_PT_LOG(&s->dev, "opregion register already been set, ignoring %x\n",
+                   val);
+        return;
+    }
+
+    /* We just work with LE. */
+    xen_host_pci_get_block(&s->real_device, XEN_PCI_INTEL_OPREGION,
+            (uint8_t *)&igd_host_opregion, 4);
+    igd_guest_opregion = (unsigned long)(val & ~XEN_PCI_INTEL_OPREGION_MASK)
+                            | (igd_host_opregion & XEN_PCI_INTEL_OPREGION_MASK);
+
+    ret = xc_domain_iomem_permission(xen_xc, xen_domid,
+            (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+            XEN_PCI_INTEL_OPREGION_PAGES,
+            XEN_PCI_INTEL_OPREGION_ENABLE_ACCESSED);
+
+    if (ret) {
+        XEN_PT_ERR(&s->dev, "[%d]:Can't enable to access IGD host opregion:"
+                    " 0x%lx.\n", ret,
+                    (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT)),
+        igd_guest_opregion = 0;
+        return;
+    }
+
+    ret = xc_domain_memory_mapping(xen_xc, xen_domid,
+            (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT),
+            (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+            XEN_PCI_INTEL_OPREGION_PAGES,
+            DPCI_ADD_MAPPING);
+
+    if (ret) {
+        XEN_PT_ERR(&s->dev, "[%d]:Can't map IGD host opregion:0x%lx to"
+                    " guest opregion:0x%lx.\n", ret,
+                    (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+                    (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT));
+        igd_guest_opregion = 0;
+        return;
+    }
+
+    XEN_PT_LOG(&s->dev, "Map OpRegion: 0x%lx -> 0x%lx\n",
+                    (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+                    (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT));
+}
-- 
1.9.1