xen-hvm: stop faking I/O to access PCI config space

This patch removes the current hackery where IOREQ_TYPE_PCI_CONFIG
requests are handled by faking PIO to 0xcf8 and 0xcfc and replaces it
with direct calls to pci_host_config_read/write_common().
Doing so necessitates mapping BDFs to PCIDevices but maintaining a simple
QLIST in xen_device_realize/unrealize() will suffice.

NOTE: whilst config space accesses are currently limited to
      PCI_CONFIG_SPACE_SIZE, this patch paves the way to increasing the
      limit to PCIE_CONFIG_SPACE_SIZE when Xen gains the ability to
      emulate MCFG table accesses.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>

2 files changed, 84 insertions, 20 deletions

diff --git a/hw/i386/xen/trace-events b/hw/i386/xen/trace-events
index 38616b698f..8a9077cd4e 100644
--- a/hw/i386/xen/trace-events
+++ b/hw/i386/xen/trace-events
@@ -16,6 +16,8 @@ cpu_ioreq_pio_read_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "
 cpu_ioreq_pio_write_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "I/O=%p pio write reg data=0x%"PRIx64" port=0x%"PRIx64" size=%d"
 cpu_ioreq_move(void *req, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p copy dir=%d df=%d ptr=%d port=0x%"PRIx64" data=0x%"PRIx64" count=%d size=%d"
 xen_map_resource_ioreq(uint32_t id, void *addr) "id: %u addr: %p"
+cpu_ioreq_config_read(void *req, uint32_t sbdf, uint32_t reg, uint32_t size, uint32_t data) "I/O=%p sbdf=0x%x reg=%u size=%u data=0x%x"
+cpu_ioreq_config_write(void *req, uint32_t sbdf, uint32_t reg, uint32_t size, uint32_t data) "I/O=%p sbdf=0x%x reg=%u size=%u data=0x%x"
 
 # xen-mapcache.c
 xen_map_cache(uint64_t phys_addr) "want 0x%"PRIx64
diff --git a/hw/i386/xen/xen-hvm.c b/hw/i386/xen/xen-hvm.c
index 54f99abfea..935a3676c8 100644
--- a/hw/i386/xen/xen-hvm.c
+++ b/hw/i386/xen/xen-hvm.c
@@ -12,6 +12,7 @@
 
 #include "cpu.h"
 #include "hw/pci/pci.h"
+#include "hw/pci/pci_host.h"
 #include "hw/i386/pc.h"
 #include "hw/i386/apic-msidef.h"
 #include "hw/xen/xen_common.h"
@@ -88,6 +89,12 @@ typedef struct XenPhysmap {
 
 static QLIST_HEAD(, XenPhysmap) xen_physmap;
 
+typedef struct XenPciDevice {
+    PCIDevice *pci_dev;
+    uint32_t sbdf;
+    QLIST_ENTRY(XenPciDevice) entry;
+} XenPciDevice;
+
 typedef struct XenIOState {
     ioservid_t ioservid;
     shared_iopage_t *shared_page;
@@ -108,6 +115,7 @@ typedef struct XenIOState {
     struct xs_handle *xenstore;
     MemoryListener memory_listener;
     MemoryListener io_listener;
+    QLIST_HEAD(, XenPciDevice) dev_list;
     DeviceListener device_listener;
     hwaddr free_phys_offset;
     const XenPhysmap *log_for_dirtybit;
@@ -568,6 +576,12 @@ static void xen_device_realize(DeviceListener *listener,
 
     if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
         PCIDevice *pci_dev = PCI_DEVICE(dev);
+        XenPciDevice *xendev = g_new(XenPciDevice, 1);
+
+        xendev->pci_dev = pci_dev;
+        xendev->sbdf = PCI_BUILD_BDF(pci_dev_bus_num(pci_dev),
+                                     pci_dev->devfn);
+        QLIST_INSERT_HEAD(&state->dev_list, xendev, entry);
 
         xen_map_pcidev(xen_domid, state->ioservid, pci_dev);
     }
@@ -580,8 +594,17 @@ static void xen_device_unrealize(DeviceListener *listener,
 
     if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
         PCIDevice *pci_dev = PCI_DEVICE(dev);
+        XenPciDevice *xendev, *next;
 
         xen_unmap_pcidev(xen_domid, state->ioservid, pci_dev);
+
+        QLIST_FOREACH_SAFE(xendev, &state->dev_list, entry, next) {
+            if (xendev->pci_dev == pci_dev) {
+                QLIST_REMOVE(xendev, entry);
+                g_free(xendev);
+                break;
+            }
+        }
     }
 }
 
@@ -902,6 +925,62 @@ static void cpu_ioreq_move(ioreq_t *req)
     }
 }
 
+static void cpu_ioreq_config(XenIOState *state, ioreq_t *req)
+{
+    uint32_t sbdf = req->addr >> 32;
+    uint32_t reg = req->addr;
+    XenPciDevice *xendev;
+
+    if (req->size != sizeof(uint8_t) && req->size != sizeof(uint16_t) &&
+        req->size != sizeof(uint32_t)) {
+        hw_error("PCI config access: bad size (%u)", req->size);
+    }
+
+    if (req->count != 1) {
+        hw_error("PCI config access: bad count (%u)", req->count);
+    }
+
+    QLIST_FOREACH(xendev, &state->dev_list, entry) {
+        if (xendev->sbdf != sbdf) {
+            continue;
+        }
+
+        if (!req->data_is_ptr) {
+            if (req->dir == IOREQ_READ) {
+                req->data = pci_host_config_read_common(
+                    xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE,
+                    req->size);
+                trace_cpu_ioreq_config_read(req, xendev->sbdf, reg,
+                                            req->size, req->data);
+            } else if (req->dir == IOREQ_WRITE) {
+                trace_cpu_ioreq_config_write(req, xendev->sbdf, reg,
+                                             req->size, req->data);
+                pci_host_config_write_common(
+                    xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE,
+                    req->data, req->size);
+            }
+        } else {
+            uint32_t tmp;
+
+            if (req->dir == IOREQ_READ) {
+                tmp = pci_host_config_read_common(
+                    xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE,
+                    req->size);
+                trace_cpu_ioreq_config_read(req, xendev->sbdf, reg,
+                                            req->size, tmp);
+                write_phys_req_item(req->data, req, 0, &tmp);
+            } else if (req->dir == IOREQ_WRITE) {
+                read_phys_req_item(req->data, req, 0, &tmp);
+                trace_cpu_ioreq_config_write(req, xendev->sbdf, reg,
+                                             req->size, tmp);
+                pci_host_config_write_common(
+                    xendev->pci_dev, reg, PCI_CONFIG_SPACE_SIZE,
+                    tmp, req->size);
+            }
+        }
+    }
+}
+
 static void regs_to_cpu(vmware_regs_t *vmport_regs, ioreq_t *req)
 {
     X86CPU *cpu;
@@ -974,27 +1053,9 @@ static void handle_ioreq(XenIOState *state, ioreq_t *req)
         case IOREQ_TYPE_INVALIDATE:
             xen_invalidate_map_cache();
             break;
-        case IOREQ_TYPE_PCI_CONFIG: {
-            uint32_t sbdf = req->addr >> 32;
-            uint32_t val;
-
-            /* Fake a write to port 0xCF8 so that
-             * the config space access will target the
-             * correct device model.
-             */
-            val = (1u << 31) |
-                  ((req->addr & 0x0f00) << 16) |
-                  ((sbdf & 0xffff) << 8) |
-                  (req->addr & 0xfc);
-            do_outp(0xcf8, 4, val);
-
-            /* Now issue the config space access via
-             * port 0xCFC
-             */
-            req->addr = 0xcfc | (req->addr & 0x03);
-            cpu_ioreq_pio(req);
+        case IOREQ_TYPE_PCI_CONFIG:
+            cpu_ioreq_config(state, req);
             break;
-        }
         default:
             hw_error("Invalid ioreq type 0x%x\n", req->type);
     }
@@ -1415,6 +1476,7 @@ void xen_hvm_init(PCMachineState *pcms, MemoryRegion **ram_memory)
     memory_listener_register(&state->io_listener, &address_space_io);
 
     state->device_listener = xen_device_listener;
+    QLIST_INIT(&state->dev_list);
     device_listener_register(&state->device_listener);
 
     /* Initialize backend core & drivers */