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

virtio,pc,pci: features, cleanups, fixes

vhost-user enabled on non-linux systems
beginning of nvme sriov support
bigger tx queue for vdpa
virtio iommu bypass
FADT flag to detect legacy keyboards

Fixes, cleanups all over the place

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

# gpg: Signature made Mon 07 Mar 2022 22:43:31 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# 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: (47 commits)
  hw/acpi/microvm: turn on 8042 bit in FADT boot architecture flags if present
  tests/acpi: i386: update FACP table differences
  hw/acpi: add indication for i8042 in IA-PC boot flags of the FADT table
  tests/acpi: i386: allow FACP acpi table changes
  docs: vhost-user: add subsection for non-Linux platforms
  configure, meson: allow enabling vhost-user on all POSIX systems
  vhost: use wfd on functions setting vring call fd
  event_notifier: add event_notifier_get_wfd()
  pci: drop COMPAT_PROP_PCP for 2.0 machine types
  hw/smbios: Add table 4 parameter, "processor-id"
  x86: cleanup unused compat_apic_id_mode
  vhost-vsock: detach the virqueue element in case of error
  pc: add option to disable PS/2 mouse/keyboard
  acpi: pcihp: pcie: set power on cap on parent slot
  pci: expose TYPE_XIO3130_DOWNSTREAM name
  pci: show id info when pci BDF conflict
  hw/misc/pvpanic: Use standard headers instead
  headers: Add pvpanic.h
  pci-bridge/xio3130_downstream: Fix error handling
  pci-bridge/xio3130_upstream: Fix error handling
  ...

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

# Conflicts:
#	docs/specs/index.rst

1 files changed, 79 insertions, 25 deletions

diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 5d30f9ca60..5cb1232e27 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -239,6 +239,9 @@ int pci_bar(PCIDevice *d, int reg)
 {
     uint8_t type;
 
+    /* PCIe virtual functions do not have their own BARs */
+    assert(!pci_is_vf(d));
+
     if (reg != PCI_ROM_SLOT)
         return PCI_BASE_ADDRESS_0 + reg * 4;
 
@@ -304,10 +307,30 @@ void pci_device_deassert_intx(PCIDevice *dev)
     }
 }
 
-static void pci_do_device_reset(PCIDevice *dev)
+static void pci_reset_regions(PCIDevice *dev)
 {
     int r;
+    if (pci_is_vf(dev)) {
+        return;
+    }
+
+    for (r = 0; r < PCI_NUM_REGIONS; ++r) {
+        PCIIORegion *region = &dev->io_regions[r];
+        if (!region->size) {
+            continue;
+        }
 
+        if (!(region->type & PCI_BASE_ADDRESS_SPACE_IO) &&
+            region->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+            pci_set_quad(dev->config + pci_bar(dev, r), region->type);
+        } else {
+            pci_set_long(dev->config + pci_bar(dev, r), region->type);
+        }
+    }
+}
+
+static void pci_do_device_reset(PCIDevice *dev)
+{
     pci_device_deassert_intx(dev);
     assert(dev->irq_state == 0);
 
@@ -323,19 +346,7 @@ static void pci_do_device_reset(PCIDevice *dev)
                               pci_get_word(dev->wmask + PCI_INTERRUPT_LINE) |
                               pci_get_word(dev->w1cmask + PCI_INTERRUPT_LINE));
     dev->config[PCI_CACHE_LINE_SIZE] = 0x0;
-    for (r = 0; r < PCI_NUM_REGIONS; ++r) {
-        PCIIORegion *region = &dev->io_regions[r];
-        if (!region->size) {
-            continue;
-        }
-
-        if (!(region->type & PCI_BASE_ADDRESS_SPACE_IO) &&
-            region->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-            pci_set_quad(dev->config + pci_bar(dev, r), region->type);
-        } else {
-            pci_set_long(dev->config + pci_bar(dev, r), region->type);
-        }
-    }
+    pci_reset_regions(dev);
     pci_update_mappings(dev);
 
     msi_reset(dev);
@@ -885,6 +896,16 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp)
     }
 
     /*
+     * With SR/IOV and ARI, a device at function 0 need not be a multifunction
+     * device, as it may just be a VF that ended up with function 0 in
+     * the legacy PCI interpretation. Avoid failing in such cases:
+     */
+    if (pci_is_vf(dev) &&
+        dev->exp.sriov_vf.pf->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
+        return;
+    }
+
+    /*
      * multifunction bit is interpreted in two ways as follows.
      *   - all functions must set the bit to 1.
      *     Example: Intel X53
@@ -1078,11 +1099,12 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev,
         return NULL;
     } else if (!pci_bus_devfn_available(bus, devfn)) {
         error_setg(errp, "PCI: slot %d function %d not available for %s,"
-                   " in use by %s",
+                   " in use by %s,id=%s",
                    PCI_SLOT(devfn), PCI_FUNC(devfn), name,
-                   bus->devices[devfn]->name);
+                   bus->devices[devfn]->name, bus->devices[devfn]->qdev.id);
         return NULL;
     } else if (dev->hotplugged &&
+               !pci_is_vf(pci_dev) &&
                pci_get_function_0(pci_dev)) {
         error_setg(errp, "PCI: slot %d function 0 already occupied by %s,"
                    " new func %s cannot be exposed to guest.",
@@ -1191,6 +1213,7 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
     pcibus_t size = memory_region_size(memory);
     uint8_t hdr_type;
 
+    assert(!pci_is_vf(pci_dev)); /* VFs must use pcie_sriov_vf_register_bar */
     assert(region_num >= 0);
     assert(region_num < PCI_NUM_REGIONS);
     assert(is_power_of_2(size));
@@ -1294,11 +1317,45 @@ pcibus_t pci_get_bar_addr(PCIDevice *pci_dev, int region_num)
     return pci_dev->io_regions[region_num].addr;
 }
 
-static pcibus_t pci_bar_address(PCIDevice *d,
-                                int reg, uint8_t type, pcibus_t size)
+static pcibus_t pci_config_get_bar_addr(PCIDevice *d, int reg,
+                                        uint8_t type, pcibus_t size)
+{
+    pcibus_t new_addr;
+    if (!pci_is_vf(d)) {
+        int bar = pci_bar(d, reg);
+        if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+            new_addr = pci_get_quad(d->config + bar);
+        } else {
+            new_addr = pci_get_long(d->config + bar);
+        }
+    } else {
+        PCIDevice *pf = d->exp.sriov_vf.pf;
+        uint16_t sriov_cap = pf->exp.sriov_cap;
+        int bar = sriov_cap + PCI_SRIOV_BAR + reg * 4;
+        uint16_t vf_offset =
+            pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_OFFSET);
+        uint16_t vf_stride =
+            pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_STRIDE);
+        uint32_t vf_num = (d->devfn - (pf->devfn + vf_offset)) / vf_stride;
+
+        if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+            new_addr = pci_get_quad(pf->config + bar);
+        } else {
+            new_addr = pci_get_long(pf->config + bar);
+        }
+        new_addr += vf_num * size;
+    }
+    /* The ROM slot has a specific enable bit, keep it intact */
+    if (reg != PCI_ROM_SLOT) {
+        new_addr &= ~(size - 1);
+    }
+    return new_addr;
+}
+
+pcibus_t pci_bar_address(PCIDevice *d,
+                         int reg, uint8_t type, pcibus_t size)
 {
     pcibus_t new_addr, last_addr;
-    int bar = pci_bar(d, reg);
     uint16_t cmd = pci_get_word(d->config + PCI_COMMAND);
     Object *machine = qdev_get_machine();
     ObjectClass *oc = object_get_class(machine);
@@ -1309,7 +1366,7 @@ static pcibus_t pci_bar_address(PCIDevice *d,
         if (!(cmd & PCI_COMMAND_IO)) {
             return PCI_BAR_UNMAPPED;
         }
-        new_addr = pci_get_long(d->config + bar) & ~(size - 1);
+        new_addr = pci_config_get_bar_addr(d, reg, type, size);
         last_addr = new_addr + size - 1;
         /* Check if 32 bit BAR wraps around explicitly.
          * TODO: make priorities correct and remove this work around.
@@ -1324,11 +1381,7 @@ static pcibus_t pci_bar_address(PCIDevice *d,
     if (!(cmd & PCI_COMMAND_MEMORY)) {
         return PCI_BAR_UNMAPPED;
     }
-    if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-        new_addr = pci_get_quad(d->config + bar);
-    } else {
-        new_addr = pci_get_long(d->config + bar);
-    }
+    new_addr = pci_config_get_bar_addr(d, reg, type, size);
     /* the ROM slot has a specific enable bit */
     if (reg == PCI_ROM_SLOT && !(new_addr & PCI_ROM_ADDRESS_ENABLE)) {
         return PCI_BAR_UNMAPPED;
@@ -1473,6 +1526,7 @@ void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int
 
     msi_write_config(d, addr, val_in, l);
     msix_write_config(d, addr, val_in, l);
+    pcie_sriov_config_write(d, addr, val_in, l);
 }
 
 /***********************************************************/