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

4 files changed, 94 insertions, 3 deletions

diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index c3f3c90473..3a32b8dd40 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -7,9 +7,6 @@
 /* PCI includes legacy ISA access.  */
 #include "hw/isa/isa.h"
 
-#include "hw/pci/pcie.h"
-#include "qom/object.h"
-
 extern bool pci_available;
 
 /* PCI bus */
@@ -157,6 +154,7 @@ enum {
 #define QEMU_PCI_VGA_IO_HI_SIZE 0x20
 
 #include "hw/pci/pci_regs.h"
+#include "hw/pci/pcie.h"
 
 /* PCI HEADER_TYPE */
 #define  PCI_HEADER_TYPE_MULTI_FUNCTION 0x80
@@ -499,6 +497,9 @@ typedef AddressSpace *(*PCIIOMMUFunc)(PCIBus *, void *, int);
 AddressSpace *pci_device_iommu_address_space(PCIDevice *dev);
 void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn, void *opaque);
 
+pcibus_t pci_bar_address(PCIDevice *d,
+                         int reg, uint8_t type, pcibus_t size);
+
 static inline void
 pci_set_byte(uint8_t *config, uint8_t val)
 {
@@ -779,6 +780,11 @@ static inline int pci_is_express_downstream_port(const PCIDevice *d)
     return type == PCI_EXP_TYPE_DOWNSTREAM || type == PCI_EXP_TYPE_ROOT_PORT;
 }
 
+static inline int pci_is_vf(const PCIDevice *d)
+{
+    return d->exp.sriov_vf.pf != NULL;
+}
+
 static inline uint32_t pci_config_size(const PCIDevice *d)
 {
     return pci_is_express(d) ? PCIE_CONFIG_SPACE_SIZE : PCI_CONFIG_SPACE_SIZE;
diff --git a/include/hw/pci/pci_regs.h b/include/hw/pci/pci_regs.h
index 77ba64b931..a590140962 100644
--- a/include/hw/pci/pci_regs.h
+++ b/include/hw/pci/pci_regs.h
@@ -4,5 +4,6 @@
 #include "standard-headers/linux/pci_regs.h"
 
 #define  PCI_PM_CAP_VER_1_1     0x0002  /* PCI PM spec ver. 1.1 */
+#define  PCI_PM_CAP_VER_1_2     0x0003  /* PCI PM spec ver. 1.2 */
 
 #endif
diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h
index 6063bee0ec..798a262a0a 100644
--- a/include/hw/pci/pcie.h
+++ b/include/hw/pci/pcie.h
@@ -24,6 +24,7 @@
 #include "hw/pci/pci_regs.h"
 #include "hw/pci/pcie_regs.h"
 #include "hw/pci/pcie_aer.h"
+#include "hw/pci/pcie_sriov.h"
 #include "hw/hotplug.h"
 
 typedef enum {
@@ -81,6 +82,11 @@ struct PCIExpressDevice {
 
     /* ACS */
     uint16_t acs_cap;
+
+    /* SR/IOV */
+    uint16_t sriov_cap;
+    PCIESriovPF sriov_pf;
+    PCIESriovVF sriov_vf;
 };
 
 #define COMPAT_PROP_PCP "power_controller_present"
@@ -112,6 +118,7 @@ void pcie_cap_slot_write_config(PCIDevice *dev,
                                 uint32_t addr, uint32_t val, int len);
 int pcie_cap_slot_post_load(void *opaque, int version_id);
 void pcie_cap_slot_push_attention_button(PCIDevice *dev);
+void pcie_cap_slot_enable_power(PCIDevice *dev);
 
 void pcie_cap_root_init(PCIDevice *dev);
 void pcie_cap_root_reset(PCIDevice *dev);
diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h
new file mode 100644
index 0000000000..80f5c84e75
--- /dev/null
+++ b/include/hw/pci/pcie_sriov.h
@@ -0,0 +1,77 @@
+/*
+ * pcie_sriov.h:
+ *
+ * Implementation of SR/IOV emulation support.
+ *
+ * Copyright (c) 2015 Knut Omang <knut.omang@oracle.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_PCIE_SRIOV_H
+#define QEMU_PCIE_SRIOV_H
+
+struct PCIESriovPF {
+    uint16_t num_vfs;   /* Number of virtual functions created */
+    uint8_t vf_bar_type[PCI_NUM_REGIONS];   /* Store type for each VF bar */
+    const char *vfname; /* Reference to the device type used for the VFs */
+    PCIDevice **vf;     /* Pointer to an array of num_vfs VF devices */
+};
+
+struct PCIESriovVF {
+    PCIDevice *pf;      /* Pointer back to owner physical function */
+    uint16_t vf_number; /* Logical VF number of this function */
+};
+
+void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
+                        const char *vfname, uint16_t vf_dev_id,
+                        uint16_t init_vfs, uint16_t total_vfs,
+                        uint16_t vf_offset, uint16_t vf_stride);
+void pcie_sriov_pf_exit(PCIDevice *dev);
+
+/* Set up a VF bar in the SR/IOV bar area */
+void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
+                               uint8_t type, dma_addr_t size);
+
+/* Instantiate a bar for a VF */
+void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
+                                MemoryRegion *memory);
+
+/*
+ * Default (minimal) page size support values
+ * as required by the SR/IOV standard:
+ * 0x553 << 12 = 0x553000 = 4K + 8K + 64K + 256K + 1M + 4M
+ */
+#define SRIOV_SUP_PGSIZE_MINREQ 0x553
+
+/*
+ * Optionally add supported page sizes to the mask of supported page sizes
+ * Page size values are interpreted as opt_sup_pgsize << 12.
+ */
+void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize);
+
+/* SR/IOV capability config write handler */
+void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
+                             uint32_t val, int len);
+
+/* Reset SR/IOV VF Enable bit to unregister all VFs */
+void pcie_sriov_pf_disable_vfs(PCIDevice *dev);
+
+/* Get logical VF number of a VF - only valid for VFs */
+uint16_t pcie_sriov_vf_number(PCIDevice *dev);
+
+/*
+ * Get the physical function that owns this VF.
+ * Returns NULL if dev is not a virtual function
+ */
+PCIDevice *pcie_sriov_get_pf(PCIDevice *dev);
+
+/*
+ * Get the n-th VF of this physical function - only valid for PF.
+ * Returns NULL if index is invalid
+ */
+PCIDevice *pcie_sriov_get_vf_at_index(PCIDevice *dev, int n);
+
+#endif /* QEMU_PCIE_SRIOV_H */