Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pci, pc, virtio: fixes, features

VTD fixes
IR and split irqchip are now the default for Q35
ACPI refactoring
hotplug refactoring
new names for virtio devices
multiple pcie link width/speeds
PCI fixes

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Thu 20 Dec 2018 18:26:03 GMT
# gpg:                using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (44 commits)
  x86-iommu: turn on IR by default if proper
  x86-iommu: switch intr_supported to OnOffAuto type
  q35: set split kernel irqchip as default
  pci: Adjust PCI config limit based on bus topology
  spapr_pci: perform unplug via the hotplug handler
  pci/shpc: perform unplug via the hotplug handler
  pci: Reuse pci-bridge hotplug handler handlers for pcie-pci-bridge
  pci/pcie: perform unplug via the hotplug handler
  pci/pcihp: perform unplug via the hotplug handler
  pci/pcihp: overwrite hotplug handler recursively from the start
  pci/pcihp: perform check for bus capability in pre_plug handler
  s390x/pci: rename hotplug handler callbacks
  pci/shpc: rename hotplug handler callbacks
  pci/pcie: rename hotplug handler callbacks
  hw/i386: Remove deprecated machines pc-0.10 and pc-0.11
  hw: acpi: Remove AcpiRsdpDescriptor and fix tests
  hw: acpi: Export and share the ARM RSDP build
  hw: arm: Support both legacy and current RSDP build
  hw: arm: Convert the RSDP build to the buid_append_foo() API
  hw: arm: Carry RSDP specific data through AcpiRsdpData
  ...

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

6 files changed, 197 insertions, 24 deletions

diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index efb5ce196f..d831fa0a36 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -1353,6 +1353,10 @@ uint32_t pci_default_read_config(PCIDevice *d,
 {
     uint32_t val = 0;
 
+    if (pci_is_express_downstream_port(d) &&
+        ranges_overlap(address, len, d->exp.exp_cap + PCI_EXP_LNKSTA, 2)) {
+        pcie_sync_bridge_lnk(d);
+    }
     memcpy(&val, d->config + address, len);
     return le32_to_cpu(val);
 }
diff --git a/hw/pci/pci_bridge.c b/hw/pci/pci_bridge.c
index ee9dff2d3a..b9143ac88b 100644
--- a/hw/pci/pci_bridge.c
+++ b/hw/pci/pci_bridge.c
@@ -241,9 +241,9 @@ void pci_bridge_update_mappings(PCIBridge *br)
      * while another accesses an unaffected region. */
     memory_region_transaction_begin();
     pci_bridge_region_del(br, br->windows);
+    pci_bridge_region_cleanup(br, w);
     br->windows = pci_bridge_region_init(br);
     memory_region_transaction_commit();
-    pci_bridge_region_cleanup(br, w);
 }
 
 /* default write_config function for PCI-to-PCI bridge */
diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c
index 5eaa935cb5..5f5345dbac 100644
--- a/hw/pci/pci_host.c
+++ b/hw/pci/pci_host.c
@@ -20,6 +20,7 @@
 
 #include "qemu/osdep.h"
 #include "hw/pci/pci.h"
+#include "hw/pci/pci_bridge.h"
 #include "hw/pci/pci_host.h"
 #include "hw/pci/pci_bus.h"
 #include "trace.h"
@@ -50,9 +51,29 @@ static inline PCIDevice *pci_dev_find_by_addr(PCIBus *bus, uint32_t addr)
     return pci_find_device(bus, bus_num, devfn);
 }
 
+static void pci_adjust_config_limit(PCIBus *bus, uint32_t *limit)
+{
+    if (*limit > PCI_CONFIG_SPACE_SIZE) {
+        if (!pci_bus_is_express(bus)) {
+            *limit = PCI_CONFIG_SPACE_SIZE;
+            return;
+        }
+
+        if (!pci_bus_is_root(bus)) {
+            PCIDevice *bridge = pci_bridge_get_device(bus);
+            pci_adjust_config_limit(pci_get_bus(bridge), limit);
+        }
+    }
+}
+
 void pci_host_config_write_common(PCIDevice *pci_dev, uint32_t addr,
                                   uint32_t limit, uint32_t val, uint32_t len)
 {
+    pci_adjust_config_limit(pci_get_bus(pci_dev), &limit);
+    if (limit <= addr) {
+        return;
+    }
+
     assert(len <= 4);
     /* non-zero functions are only exposed when function 0 is present,
      * allowing direct removal of unexposed functions.
@@ -71,6 +92,11 @@ uint32_t pci_host_config_read_common(PCIDevice *pci_dev, uint32_t addr,
 {
     uint32_t ret;
 
+    pci_adjust_config_limit(pci_get_bus(pci_dev), &limit);
+    if (limit <= addr) {
+        return ~0x0;
+    }
+
     assert(len <= 4);
     /* non-zero functions are only exposed when function 0 is present,
      * allowing direct removal of unexposed functions.
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index 6c91bd44a0..2d3d8a047b 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -27,6 +27,7 @@
 #include "hw/pci/msi.h"
 #include "hw/pci/pci_bus.h"
 #include "hw/pci/pcie_regs.h"
+#include "hw/pci/pcie_port.h"
 #include "qemu/range.h"
 
 //#define DEBUG_PCIE
@@ -68,11 +69,12 @@ pcie_cap_v1_fill(PCIDevice *dev, uint8_t port, uint8_t type, uint8_t version)
     pci_set_long(exp_cap + PCI_EXP_LNKCAP,
                  (port << PCI_EXP_LNKCAP_PN_SHIFT) |
                  PCI_EXP_LNKCAP_ASPMS_0S |
-                 PCI_EXP_LNK_MLW_1 |
-                 PCI_EXP_LNK_LS_25);
+                 QEMU_PCI_EXP_LNKCAP_MLW(QEMU_PCI_EXP_LNK_X1) |
+                 QEMU_PCI_EXP_LNKCAP_MLS(QEMU_PCI_EXP_LNK_2_5GT));
 
     pci_set_word(exp_cap + PCI_EXP_LNKSTA,
-                 PCI_EXP_LNK_MLW_1 | PCI_EXP_LNK_LS_25);
+                 QEMU_PCI_EXP_LNKSTA_NLW(QEMU_PCI_EXP_LNK_X1) |
+                 QEMU_PCI_EXP_LNKSTA_CLS(QEMU_PCI_EXP_LNK_2_5GT));
 
     if (dev->cap_present & QEMU_PCIE_LNKSTA_DLLLA) {
         pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKSTA,
@@ -86,6 +88,76 @@ pcie_cap_v1_fill(PCIDevice *dev, uint8_t port, uint8_t type, uint8_t version)
     pci_set_word(cmask + PCI_EXP_LNKSTA, 0);
 }
 
+static void pcie_cap_fill_slot_lnk(PCIDevice *dev)
+{
+    PCIESlot *s = (PCIESlot *)object_dynamic_cast(OBJECT(dev), TYPE_PCIE_SLOT);
+    uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
+
+    /* Skip anything that isn't a PCIESlot */
+    if (!s) {
+        return;
+    }
+
+    /* Clear and fill LNKCAP from what was configured above */
+    pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKCAP,
+                                 PCI_EXP_LNKCAP_MLW | PCI_EXP_LNKCAP_SLS);
+    pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
+                               QEMU_PCI_EXP_LNKCAP_MLW(s->width) |
+                               QEMU_PCI_EXP_LNKCAP_MLS(s->speed));
+
+    /*
+     * Link bandwidth notification is required for all root ports and
+     * downstream ports supporting links wider than x1 or multiple link
+     * speeds.
+     */
+    if (s->width > QEMU_PCI_EXP_LNK_X1 ||
+        s->speed > QEMU_PCI_EXP_LNK_2_5GT) {
+        pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
+                                   PCI_EXP_LNKCAP_LBNC);
+    }
+
+    if (s->speed > QEMU_PCI_EXP_LNK_2_5GT) {
+        /*
+         * Hot-plug capable downstream ports and downstream ports supporting
+         * link speeds greater than 5GT/s must hardwire PCI_EXP_LNKCAP_DLLLARC
+         * to 1b.  PCI_EXP_LNKCAP_DLLLARC implies PCI_EXP_LNKSTA_DLLLA, which
+         * we also hardwire to 1b here.  2.5GT/s hot-plug slots should also
+         * technically implement this, but it's not done here for compatibility.
+         */
+        pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP,
+                                   PCI_EXP_LNKCAP_DLLLARC);
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKSTA,
+                                   PCI_EXP_LNKSTA_DLLLA);
+
+        /*
+         * Target Link Speed defaults to the highest link speed supported by
+         * the component.  2.5GT/s devices are permitted to hardwire to zero.
+         */
+        pci_word_test_and_clear_mask(exp_cap + PCI_EXP_LNKCTL2,
+                                     PCI_EXP_LNKCTL2_TLS);
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKCTL2,
+                                   QEMU_PCI_EXP_LNKCAP_MLS(s->speed) &
+                                   PCI_EXP_LNKCTL2_TLS);
+    }
+
+    /*
+     * 2.5 & 5.0GT/s can be fully described by LNKCAP, but 8.0GT/s is
+     * actually a reference to the highest bit supported in this register.
+     * We assume the device supports all link speeds.
+     */
+    if (s->speed > QEMU_PCI_EXP_LNK_5GT) {
+        pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKCAP2, ~0U);
+        pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2,
+                                   PCI_EXP_LNKCAP2_SLS_2_5GB |
+                                   PCI_EXP_LNKCAP2_SLS_5_0GB |
+                                   PCI_EXP_LNKCAP2_SLS_8_0GB);
+        if (s->speed > QEMU_PCI_EXP_LNK_8GT) {
+            pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2,
+                                       PCI_EXP_LNKCAP2_SLS_16_0GB);
+        }
+    }
+}
+
 int pcie_cap_init(PCIDevice *dev, uint8_t offset,
                   uint8_t type, uint8_t port,
                   Error **errp)
@@ -107,6 +179,9 @@ int pcie_cap_init(PCIDevice *dev, uint8_t offset,
     /* Filling values common with v1 */
     pcie_cap_v1_fill(dev, port, type, PCI_EXP_FLAGS_VER2);
 
+    /* Fill link speed and width options */
+    pcie_cap_fill_slot_lnk(dev);
+
     /* Filling v2 specific values */
     pci_set_long(exp_cap + PCI_EXP_DEVCAP2,
                  PCI_EXP_DEVCAP2_EFF | PCI_EXP_DEVCAP2_EETLPP);
@@ -315,9 +390,8 @@ static void pcie_cap_slot_event(PCIDevice *dev, PCIExpressHotPlugEvent event)
     hotplug_event_notify(dev);
 }
 
-static void pcie_cap_slot_hotplug_common(PCIDevice *hotplug_dev,
-                                         DeviceState *dev,
-                                         uint8_t **exp_cap, Error **errp)
+static void pcie_cap_slot_plug_common(PCIDevice *hotplug_dev, DeviceState *dev,
+                                      uint8_t **exp_cap, Error **errp)
 {
     *exp_cap = hotplug_dev->config + hotplug_dev->exp.exp_cap;
     uint16_t sltsta = pci_get_word(*exp_cap + PCI_EXP_SLTSTA);
@@ -331,13 +405,13 @@ static void pcie_cap_slot_hotplug_common(PCIDevice *hotplug_dev,
     }
 }
 
-void pcie_cap_slot_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
-                              Error **errp)
+void pcie_cap_slot_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
+                           Error **errp)
 {
     uint8_t *exp_cap;
     PCIDevice *pci_dev = PCI_DEVICE(dev);
 
-    pcie_cap_slot_hotplug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
+    pcie_cap_slot_plug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
 
     /* Don't send event when device is enabled during qemu machine creation:
      * it is present on boot, no hotplug event is necessary. We do send an
@@ -345,6 +419,10 @@ void pcie_cap_slot_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
     if (!dev->hotplugged) {
         pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
                                    PCI_EXP_SLTSTA_PDS);
+        if (pci_dev->cap_present & QEMU_PCIE_LNKSTA_DLLLA) {
+            pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKSTA,
+                                       PCI_EXP_LNKSTA_DLLLA);
+        }
         return;
     }
 
@@ -355,24 +433,36 @@ void pcie_cap_slot_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
     if (pci_get_function_0(pci_dev)) {
         pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
                                    PCI_EXP_SLTSTA_PDS);
+        if (pci_dev->cap_present & QEMU_PCIE_LNKSTA_DLLLA) {
+            pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKSTA,
+                                       PCI_EXP_LNKSTA_DLLLA);
+        }
         pcie_cap_slot_event(PCI_DEVICE(hotplug_dev),
                             PCI_EXP_HP_EV_PDC | PCI_EXP_HP_EV_ABP);
     }
 }
 
-static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque)
+void pcie_cap_slot_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
+                             Error **errp)
 {
     object_unparent(OBJECT(dev));
 }
 
-void pcie_cap_slot_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
-                                         DeviceState *dev, Error **errp)
+static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque)
+{
+    HotplugHandler *hotplug_ctrl = qdev_get_hotplug_handler(DEVICE(dev));
+
+    hotplug_handler_unplug(hotplug_ctrl, DEVICE(dev), &error_abort);
+}
+
+void pcie_cap_slot_unplug_request_cb(HotplugHandler *hotplug_dev,
+                                     DeviceState *dev, Error **errp)
 {
     uint8_t *exp_cap;
     PCIDevice *pci_dev = PCI_DEVICE(dev);
     PCIBus *bus = pci_get_bus(pci_dev);
 
-    pcie_cap_slot_hotplug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
+    pcie_cap_slot_plug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
 
     /* In case user cancel the operation of multi-function hot-add,
      * remove the function that is unexposed to guest individually,
@@ -531,6 +621,10 @@ void pcie_cap_slot_write_config(PCIDevice *dev,
 
         pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
                                      PCI_EXP_SLTSTA_PDS);
+        if (dev->cap_present & QEMU_PCIE_LNKSTA_DLLLA) {
+            pci_word_test_and_clear_mask(exp_cap + PCI_EXP_LNKSTA,
+                                         PCI_EXP_LNKSTA_DLLLA);
+        }
         pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
                                        PCI_EXP_SLTSTA_PDC);
     }
@@ -728,6 +822,45 @@ void pcie_add_capability(PCIDevice *dev,
     memset(dev->cmask + offset, 0xFF, size);
 }
 
+/*
+ * Sync the PCIe Link Status negotiated speed and width of a bridge with the
+ * downstream device.  If downstream device is not present, re-write with the
+ * Link Capability fields.  Limit width and speed to bridge capabilities for
+ * compatibility.  Use config_read to access the downstream device since it
+ * could be an assigned device with volatile link information.
+ */
+void pcie_sync_bridge_lnk(PCIDevice *bridge_dev)
+{
+    PCIBridge *br = PCI_BRIDGE(bridge_dev);
+    PCIBus *bus = pci_bridge_get_sec_bus(br);
+    PCIDevice *target = bus->devices[0];
+    uint8_t *exp_cap = bridge_dev->config + bridge_dev->exp.exp_cap;
+    uint16_t lnksta, lnkcap = pci_get_word(exp_cap + PCI_EXP_LNKCAP);
+
+    if (!target || !target->exp.exp_cap) {
+        lnksta = lnkcap;
+    } else {
+        lnksta = target->config_read(target,
+                                     target->exp.exp_cap + PCI_EXP_LNKSTA,
+                                     sizeof(lnksta));
+
+        if ((lnksta & PCI_EXP_LNKSTA_NLW) > (lnkcap & PCI_EXP_LNKCAP_MLW)) {
+            lnksta &= ~PCI_EXP_LNKSTA_NLW;
+            lnksta |= lnkcap & PCI_EXP_LNKCAP_MLW;
+        }
+
+        if ((lnksta & PCI_EXP_LNKSTA_CLS) > (lnkcap & PCI_EXP_LNKCAP_SLS)) {
+            lnksta &= ~PCI_EXP_LNKSTA_CLS;
+            lnksta |= lnkcap & PCI_EXP_LNKCAP_SLS;
+        }
+    }
+
+    pci_word_test_and_clear_mask(exp_cap + PCI_EXP_LNKSTA,
+                                 PCI_EXP_LNKSTA_CLS | PCI_EXP_LNKSTA_NLW);
+    pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKSTA, lnksta &
+                               (PCI_EXP_LNKSTA_CLS | PCI_EXP_LNKSTA_NLW));
+}
+
 /**************************************************************************
  * pci express extended capability helper functions
  */
diff --git a/hw/pci/pcie_port.c b/hw/pci/pcie_port.c
index 6432b9ac1f..bc07abc31b 100644
--- a/hw/pci/pcie_port.c
+++ b/hw/pci/pcie_port.c
@@ -154,8 +154,9 @@ static void pcie_slot_class_init(ObjectClass *oc, void *data)
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
 
     dc->props = pcie_slot_props;
-    hc->plug = pcie_cap_slot_hotplug_cb;
-    hc->unplug_request = pcie_cap_slot_hot_unplug_request_cb;
+    hc->plug = pcie_cap_slot_plug_cb;
+    hc->unplug = pcie_cap_slot_unplug_cb;
+    hc->unplug_request = pcie_cap_slot_unplug_request_cb;
 }
 
 static const TypeInfo pcie_slot_type_info = {
diff --git a/hw/pci/shpc.c b/hw/pci/shpc.c
index 96a43d2f70..45053b39b9 100644
--- a/hw/pci/shpc.c
+++ b/hw/pci/shpc.c
@@ -238,6 +238,7 @@ static void shpc_invalid_command(SHPCDevice *shpc)
 
 static void shpc_free_devices_in_slot(SHPCDevice *shpc, int slot)
 {
+    HotplugHandler *hotplug_ctrl;
     int devfn;
     int pci_slot = SHPC_IDX_TO_PCI(slot);
     for (devfn = PCI_DEVFN(pci_slot, 0);
@@ -245,7 +246,9 @@ static void shpc_free_devices_in_slot(SHPCDevice *shpc, int slot)
          ++devfn) {
         PCIDevice *affected_dev = shpc->sec_bus->devices[devfn];
         if (affected_dev) {
-            object_unparent(OBJECT(affected_dev));
+            hotplug_ctrl = qdev_get_hotplug_handler(DEVICE(affected_dev));
+            hotplug_handler_unplug(hotplug_ctrl, DEVICE(affected_dev),
+                                   &error_abort);
         }
     }
 }
@@ -482,8 +485,8 @@ static const MemoryRegionOps shpc_mmio_ops = {
         .max_access_size = 4,
     },
 };
-static void shpc_device_hotplug_common(PCIDevice *affected_dev, int *slot,
-                                       SHPCDevice *shpc, Error **errp)
+static void shpc_device_plug_common(PCIDevice *affected_dev, int *slot,
+                                    SHPCDevice *shpc, Error **errp)
 {
     int pci_slot = PCI_SLOT(affected_dev->devfn);
     *slot = SHPC_PCI_TO_IDX(pci_slot);
@@ -497,7 +500,7 @@ static void shpc_device_hotplug_common(PCIDevice *affected_dev, int *slot,
     }
 }
 
-void shpc_device_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
+void shpc_device_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
                             Error **errp)
 {
     Error *local_err = NULL;
@@ -505,7 +508,7 @@ void shpc_device_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
     SHPCDevice *shpc = pci_hotplug_dev->shpc;
     int slot;
 
-    shpc_device_hotplug_common(PCI_DEVICE(dev), &slot, shpc, &local_err);
+    shpc_device_plug_common(PCI_DEVICE(dev), &slot, shpc, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         return;
@@ -540,8 +543,14 @@ void shpc_device_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
     shpc_interrupt_update(pci_hotplug_dev);
 }
 
-void shpc_device_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
-                                       DeviceState *dev, Error **errp)
+void shpc_device_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
+                           Error **errp)
+{
+    object_unparent(OBJECT(dev));
+}
+
+void shpc_device_unplug_request_cb(HotplugHandler *hotplug_dev,
+                                   DeviceState *dev, Error **errp)
 {
     Error *local_err = NULL;
     PCIDevice *pci_hotplug_dev = PCI_DEVICE(hotplug_dev);
@@ -550,7 +559,7 @@ void shpc_device_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
     uint8_t led;
     int slot;
 
-    shpc_device_hotplug_common(PCI_DEVICE(dev), &slot, shpc, &local_err);
+    shpc_device_plug_common(PCI_DEVICE(dev), &slot, shpc, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         return;