pcie: Add support for Single Root I/O Virtualization (SR/IOV)

This patch provides the building blocks for creating an SR/IOV
PCIe Extended Capability header and register/unregister
SR/IOV Virtual Functions.

Signed-off-by: Knut Omang <knuto@ifi.uio.no>
Message-Id: <20220217174504.1051716-2-lukasz.maniak@linux.intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

3 files changed, 86 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/pcie.h b/include/hw/pci/pcie.h
index 6063bee0ec..168950a83b 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"
diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h
new file mode 100644
index 0000000000..990cff0a1c
--- /dev/null
+++ b/include/hw/pci/pcie_sriov.h
@@ -0,0 +1,71 @@
+/*
+ * 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);
+
+#endif /* QEMU_PCIE_SRIOV_H */