diff options
Diffstat (limited to 'hw')
| -rw-r--r-- | hw/acpi/aml-build.c | 89 | ||||
| -rw-r--r-- | hw/arm/boot.c | 13 | ||||
| -rw-r--r-- | hw/arm/sbsa-ref.c | 2 | ||||
| -rw-r--r-- | hw/arm/virt-acpi-build.c | 117 | ||||
| -rw-r--r-- | hw/arm/virt.c | 71 | ||||
| -rw-r--r-- | hw/core/loader.c | 60 | ||||
| -rw-r--r-- | hw/intc/spapr_xive.c | 2 | ||||
| -rw-r--r-- | hw/intc/spapr_xive_kvm.c | 14 | ||||
| -rw-r--r-- | hw/intc/xive.c | 8 | ||||
| -rw-r--r-- | hw/net/vhost_net-stub.c | 4 | ||||
| -rw-r--r-- | hw/net/vhost_net.c | 55 | ||||
| -rw-r--r-- | hw/net/virtio-net.c | 201 | ||||
| -rw-r--r-- | hw/pci-host/mv64361.c | 1 | ||||
| -rw-r--r-- | hw/pci/pci_bridge.c | 10 | ||||
| -rw-r--r-- | hw/ppc/pegasos2.c | 162 | ||||
| -rw-r--r-- | hw/ppc/ppc.c | 6 | ||||
| -rw-r--r-- | hw/ppc/ppc4xx_pci.c | 8 | ||||
| -rw-r--r-- | hw/ppc/spapr_softmmu.c | 15 | ||||
| -rw-r--r-- | hw/virtio/Kconfig | 5 | ||||
| -rw-r--r-- | hw/virtio/meson.build | 2 | ||||
| -rw-r--r-- | hw/virtio/trace-events | 1 | ||||
| -rw-r--r-- | hw/virtio/vhost-user-rng-pci.c | 79 | ||||
| -rw-r--r-- | hw/virtio/vhost-user-rng.c | 289 | ||||
| -rw-r--r-- | hw/virtio/vhost-user.c | 5 | ||||
| -rw-r--r-- | hw/virtio/vhost-vdpa.c | 140 | ||||
| -rw-r--r-- | hw/virtio/virtio-iommu-pci.c | 4 |
26 files changed, 1070 insertions, 293 deletions
diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index 76af0ebaf9..b3b3310df3 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -1964,6 +1964,95 @@ void build_slit(GArray *table_data, BIOSLinker *linker, MachineState *ms, acpi_table_end(linker, &table); } +/* + * ACPI spec, Revision 6.3 + * 5.2.29.1 Processor hierarchy node structure (Type 0) + */ +static void build_processor_hierarchy_node(GArray *tbl, uint32_t flags, + uint32_t parent, uint32_t id, + uint32_t *priv_rsrc, + uint32_t priv_num) +{ + int i; + + build_append_byte(tbl, 0); /* Type 0 - processor */ + build_append_byte(tbl, 20 + priv_num * 4); /* Length */ + build_append_int_noprefix(tbl, 0, 2); /* Reserved */ + build_append_int_noprefix(tbl, flags, 4); /* Flags */ + build_append_int_noprefix(tbl, parent, 4); /* Parent */ + build_append_int_noprefix(tbl, id, 4); /* ACPI Processor ID */ + + /* Number of private resources */ + build_append_int_noprefix(tbl, priv_num, 4); + + /* Private resources[N] */ + if (priv_num > 0) { + assert(priv_rsrc); + for (i = 0; i < priv_num; i++) { + build_append_int_noprefix(tbl, priv_rsrc[i], 4); + } + } +} + +/* + * ACPI spec, Revision 6.3 + * 5.2.29 Processor Properties Topology Table (PPTT) + */ +void build_pptt(GArray *table_data, BIOSLinker *linker, MachineState *ms, + const char *oem_id, const char *oem_table_id) +{ + int pptt_start = table_data->len; + int uid = 0; + int socket; + AcpiTable table = { .sig = "PPTT", .rev = 2, + .oem_id = oem_id, .oem_table_id = oem_table_id }; + + acpi_table_begin(&table, table_data); + + for (socket = 0; socket < ms->smp.sockets; socket++) { + uint32_t socket_offset = table_data->len - pptt_start; + int core; + + build_processor_hierarchy_node( + table_data, + /* + * Physical package - represents the boundary + * of a physical package + */ + (1 << 0), + 0, socket, NULL, 0); + + for (core = 0; core < ms->smp.cores; core++) { + uint32_t core_offset = table_data->len - pptt_start; + int thread; + + if (ms->smp.threads > 1) { + build_processor_hierarchy_node( + table_data, + (0 << 0), /* not a physical package */ + socket_offset, core, NULL, 0); + + for (thread = 0; thread < ms->smp.threads; thread++) { + build_processor_hierarchy_node( + table_data, + (1 << 1) | /* ACPI Processor ID valid */ + (1 << 2) | /* Processor is a Thread */ + (1 << 3), /* Node is a Leaf */ + core_offset, uid++, NULL, 0); + } + } else { + build_processor_hierarchy_node( + table_data, + (1 << 1) | /* ACPI Processor ID valid */ + (1 << 3), /* Node is a Leaf */ + socket_offset, uid++, NULL, 0); + } + } + } + + acpi_table_end(linker, &table); +} + /* build rev1/rev3/rev5.1 FADT */ void build_fadt(GArray *tbl, BIOSLinker *linker, const AcpiFadtData *f, const char *oem_id, const char *oem_table_id) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index 57efb61ee4..74ad397b1f 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -599,10 +599,23 @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, } g_strfreev(node_path); + /* + * We drop all the memory nodes which correspond to empty NUMA nodes + * from the device tree, because the Linux NUMA binding document + * states they should not be generated. Linux will get the NUMA node + * IDs of the empty NUMA nodes from the distance map if they are needed. + * This means QEMU users may be obliged to provide command lines which + * configure distance maps when the empty NUMA node IDs are needed and + * Linux's default distance map isn't sufficient. + */ if (ms->numa_state != NULL && ms->numa_state->num_nodes > 0) { mem_base = binfo->loader_start; for (i = 0; i < ms->numa_state->num_nodes; i++) { mem_len = ms->numa_state->nodes[i].node_mem; + if (!mem_len) { + continue; + } + rc = fdt_add_memory_node(fdt, acells, mem_base, scells, mem_len, i); if (rc < 0) { diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index 509c5f09b4..358714bd3e 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -670,7 +670,7 @@ static void sbsa_ref_init(MachineState *machine) int n, sbsa_max_cpus; if (!cpu_type_valid(machine->cpu_type)) { - error_report("mach-virt: CPU type %s not supported", machine->cpu_type); + error_report("sbsa-ref: CPU type %s not supported", machine->cpu_type); exit(1); } diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 6cec97352b..674f902652 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -241,19 +241,20 @@ static void acpi_dsdt_add_tpm(Aml *scope, VirtMachineState *vms) #endif #define ID_MAPPING_ENTRY_SIZE 20 -#define SMMU_V3_ENTRY_SIZE 60 -#define ROOT_COMPLEX_ENTRY_SIZE 32 +#define SMMU_V3_ENTRY_SIZE 68 +#define ROOT_COMPLEX_ENTRY_SIZE 36 #define IORT_NODE_OFFSET 48 static void build_iort_id_mapping(GArray *table_data, uint32_t input_base, uint32_t id_count, uint32_t out_ref) { - /* Identity RID mapping covering the whole input RID range */ + /* Table 4 ID mapping format */ build_append_int_noprefix(table_data, input_base, 4); /* Input base */ build_append_int_noprefix(table_data, id_count, 4); /* Number of IDs */ build_append_int_noprefix(table_data, input_base, 4); /* Output base */ build_append_int_noprefix(table_data, out_ref, 4); /* Output Reference */ - build_append_int_noprefix(table_data, 0, 4); /* Flags */ + /* Flags */ + build_append_int_noprefix(table_data, 0 /* Single mapping (disabled) */, 4); } struct AcpiIortIdMapping { @@ -298,7 +299,7 @@ static int iort_idmap_compare(gconstpointer a, gconstpointer b) /* * Input Output Remapping Table (IORT) * Conforms to "IO Remapping Table System Software on ARM Platforms", - * Document number: ARM DEN 0049B, October 2015 + * Document number: ARM DEN 0049E.b, Feb 2021 */ static void build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) @@ -307,10 +308,11 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) const uint32_t iort_node_offset = IORT_NODE_OFFSET; size_t node_size, smmu_offset = 0; AcpiIortIdMapping *idmap; + uint32_t id = 0; GArray *smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); GArray *its_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); - AcpiTable table = { .sig = "IORT", .rev = 0, .oem_id = vms->oem_id, + AcpiTable table = { .sig = "IORT", .rev = 3, .oem_id = vms->oem_id, .oem_table_id = vms->oem_table_id }; /* Table 2 The IORT */ acpi_table_begin(&table, table_data); @@ -358,12 +360,12 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) build_append_int_noprefix(table_data, IORT_NODE_OFFSET, 4); build_append_int_noprefix(table_data, 0, 4); /* Reserved */ - /* 3.1.1.3 ITS group node */ + /* Table 12 ITS Group Format */ build_append_int_noprefix(table_data, 0 /* ITS Group */, 1); /* Type */ node_size = 20 /* fixed header size */ + 4 /* 1 GIC ITS Identifier */; build_append_int_noprefix(table_data, node_size, 2); /* Length */ - build_append_int_noprefix(table_data, 0, 1); /* Revision */ - build_append_int_noprefix(table_data, 0, 4); /* Reserved */ + build_append_int_noprefix(table_data, 1, 1); /* Revision */ + build_append_int_noprefix(table_data, id++, 4); /* Identifier */ build_append_int_noprefix(table_data, 0, 4); /* Number of ID mappings */ build_append_int_noprefix(table_data, 0, 4); /* Reference to ID Array */ build_append_int_noprefix(table_data, 1, 4); /* Number of ITSs */ @@ -374,19 +376,19 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) int irq = vms->irqmap[VIRT_SMMU] + ARM_SPI_BASE; smmu_offset = table_data->len - table.table_offset; - /* 3.1.1.2 SMMUv3 */ + /* Table 9 SMMUv3 Format */ build_append_int_noprefix(table_data, 4 /* SMMUv3 */, 1); /* Type */ node_size = SMMU_V3_ENTRY_SIZE + ID_MAPPING_ENTRY_SIZE; build_append_int_noprefix(table_data, node_size, 2); /* Length */ - build_append_int_noprefix(table_data, 0, 1); /* Revision */ - build_append_int_noprefix(table_data, 0, 4); /* Reserved */ + build_append_int_noprefix(table_data, 4, 1); /* Revision */ + build_append_int_noprefix(table_data, id++, 4); /* Identifier */ build_append_int_noprefix(table_data, 1, 4); /* Number of ID mappings */ /* Reference to ID Array */ build_append_int_noprefix(table_data, SMMU_V3_ENTRY_SIZE, 4); /* Base address */ build_append_int_noprefix(table_data, vms->memmap[VIRT_SMMU].base, 8); /* Flags */ - build_append_int_noprefix(table_data, 1 /* COHACC OverrideNote */, 4); + build_append_int_noprefix(table_data, 1 /* COHACC Override */, 4); build_append_int_noprefix(table_data, 0, 4); /* Reserved */ build_append_int_noprefix(table_data, 0, 8); /* VATOS address */ /* Model */ @@ -395,35 +397,43 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) build_append_int_noprefix(table_data, irq + 1, 4); /* PRI */ build_append_int_noprefix(table_data, irq + 3, 4); /* GERR */ build_append_int_noprefix(table_data, irq + 2, 4); /* Sync */ + build_append_int_noprefix(table_data, 0, 4); /* Proximity domain */ + /* DeviceID mapping index (ignored since interrupts are GSIV based) */ + build_append_int_noprefix(table_data, 0, 4); /* output IORT node is the ITS group node (the first node) */ build_iort_id_mapping(table_data, 0, 0xFFFF, IORT_NODE_OFFSET); } - /* Table 16 Root Complex Node */ + /* Table 17 Root Complex Node */ build_append_int_noprefix(table_data, 2 /* Root complex */, 1); /* Type */ node_size = ROOT_COMPLEX_ENTRY_SIZE + ID_MAPPING_ENTRY_SIZE * rc_mapping_count; build_append_int_noprefix(table_data, node_size, 2); /* Length */ - build_append_int_noprefix(table_data, 0, 1); /* Revision */ - build_append_int_noprefix(table_data, 0, 4); /* Reserved */ + build_append_int_noprefix(table_data, 3, 1); /* Revision */ + build_append_int_noprefix(table_data, id++, 4); /* Identifier */ /* Number of ID mappings */ build_append_int_noprefix(table_data, rc_mapping_count, 4); /* Reference to ID Array */ build_append_int_noprefix(table_data, ROOT_COMPLEX_ENTRY_SIZE, 4); - /* Table 13 Memory access properties */ + /* Table 14 Memory access properties */ /* CCA: Cache Coherent Attribute */ build_append_int_noprefix(table_data, 1 /* fully coherent */, 4); build_append_int_noprefix(table_data, 0, 1); /* AH: Note Allocation Hints */ build_append_int_noprefix(table_data, 0, 2); /* Reserved */ - /* MAF: Note Memory Access Flags */ - build_append_int_noprefix(table_data, 0x3 /* CCA = CPM = DCAS = 1 */, 1); + /* Table 15 Memory Access Flags */ + build_append_int_noprefix(table_data, 0x3 /* CCA = CPM = DACS = 1 */, 1); build_append_int_noprefix(table_data, 0, 4); /* ATS Attribute */ /* MCFG pci_segment */ build_append_int_noprefix(table_data, 0, 4); /* PCI Segment number */ + /* Memory address size limit */ + build_append_int_noprefix(table_data, 64, 1); + + build_append_int_noprefix(table_data, 0, 3); /* Reserved */ + /* Output Reference */ if (vms->iommu == VIRT_IOMMU_SMMUV3) { AcpiIortIdMapping *range; @@ -616,6 +626,64 @@ build_gtdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) acpi_table_end(linker, &table); } +/* Debug Port Table 2 (DBG2) */ +static void +build_dbg2(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) +{ + AcpiTable table = { .sig = "DBG2", .rev = 0, .oem_id = vms->oem_id, + .oem_table_id = vms->oem_table_id }; + int dbg2devicelength; + const char name[] = "COM0"; + const int namespace_length = sizeof(name); + + acpi_table_begin(&table, table_data); + + dbg2devicelength = 22 + /* BaseAddressRegister[] offset */ + 12 + /* BaseAddressRegister[] */ + 4 + /* AddressSize[] */ + namespace_length /* NamespaceString[] */; + + /* OffsetDbgDeviceInfo */ + build_append_int_noprefix(table_data, 44, 4); + /* NumberDbgDeviceInfo */ + build_append_int_noprefix(table_data, 1, 4); + + /* Table 2. Debug Device Information structure format */ + build_append_int_noprefix(table_data, 0, 1); /* Revision */ + build_append_int_noprefix(table_data, dbg2devicelength, 2); /* Length */ + /* NumberofGenericAddressRegisters */ + build_append_int_noprefix(table_data, 1, 1); + /* NameSpaceStringLength */ + build_append_int_noprefix(table_data, namespace_length, 2); + build_append_int_noprefix(table_data, 38, 2); /* NameSpaceStringOffset */ + build_append_int_noprefix(table_data, 0, 2); /* OemDataLength */ + /* OemDataOffset (0 means no OEM data) */ + build_append_int_noprefix(table_data, 0, 2); + + /* Port Type */ + build_append_int_noprefix(table_data, 0x8000 /* Serial */, 2); + /* Port Subtype */ + build_append_int_noprefix(table_data, 0x3 /* ARM PL011 UART */, 2); + build_append_int_noprefix(table_data, 0, 2); /* Reserved */ + /* BaseAddressRegisterOffset */ + build_append_int_noprefix(table_data, 22, 2); + /* AddressSizeOffset */ + build_append_int_noprefix(table_data, 34, 2); + + /* BaseAddressRegister[] */ + build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 8, 0, 1, + vms->memmap[VIRT_UART].base); + + /* AddressSize[] */ + build_append_int_noprefix(table_data, + vms->memmap[VIRT_UART].size, 4); + + /* NamespaceString[] */ + g_array_append_vals(table_data, name, namespace_length); + + acpi_table_end(linker, &table); +}; + /* * ACPI spec, Revision 5.1 Errata A * 5.2.12 Multiple APIC Description Table (MADT) @@ -875,13 +943,19 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) dsdt = tables_blob->len; build_dsdt(tables_blob, tables->linker, vms); - /* FADT MADT GTDT MCFG SPCR pointed to by RSDT */ + /* FADT MADT PPTT GTDT MCFG SPCR DBG2 pointed to by RSDT */ acpi_add_table(table_offsets, tables_blob); build_fadt_rev5(tables_blob, tables->linker, vms, dsdt); acpi_add_table(table_offsets, tables_blob); build_madt(tables_blob, tables->linker, vms); + if (!vmc->no_cpu_topology) { + acpi_add_table(table_offsets, tables_blob); + build_pptt(tables_blob, tables->linker, ms, + vms->oem_id, vms->oem_table_id); + } + acpi_add_table(table_offsets, tables_blob); build_gtdt(tables_blob, tables->linker, vms); @@ -898,6 +972,9 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) acpi_add_table(table_offsets, tables_blob); build_spcr(tables_blob, tables->linker, vms); + acpi_add_table(table_offsets, tables_blob); + build_dbg2(tables_blob, tables->linker, vms); + if (vms->ras) { build_ghes_error_table(tables->hardware_errors, tables->linker); acpi_add_table(table_offsets, tables_blob); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 4160d49688..ca433adb5b 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -351,20 +351,21 @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms) int cpu; int addr_cells = 1; const MachineState *ms = MACHINE(vms); + const VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); int smp_cpus = ms->smp.cpus; /* - * From Documentation/devicetree/bindings/arm/cpus.txt - * On ARM v8 64-bit systems value should be set to 2, - * that corresponds to the MPIDR_EL1 register size. - * If MPIDR_EL1[63:32] value is equal to 0 on all CPUs - * in the system, #address-cells can be set to 1, since - * MPIDR_EL1[63:32] bits are not used for CPUs - * identification. + * See Linux Documentation/devicetree/bindings/arm/cpus.yaml + * On ARM v8 64-bit systems value should be set to 2, + * that corresponds to the MPIDR_EL1 register size. + * If MPIDR_EL1[63:32] value is equal to 0 on all CPUs + * in the system, #address-cells can be set to 1, since + * MPIDR_EL1[63:32] bits are not used for CPUs + * identification. * - * Here we actually don't know whether our system is 32- or 64-bit one. - * The simplest way to go is to examine affinity IDs of all our CPUs. If - * at least one of them has Aff3 populated, we set #address-cells to 2. + * Here we actually don't know whether our system is 32- or 64-bit one. + * The simplest way to go is to examine affinity IDs of all our CPUs. If + * at least one of them has Aff3 populated, we set #address-cells to 2. */ for (cpu = 0; cpu < smp_cpus; cpu++) { ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu)); @@ -407,8 +408,57 @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms) ms->possible_cpus->cpus[cs->cpu_index].props.node_id); } + if (!vmc->no_cpu_topology) { + qemu_fdt_setprop_cell(ms->fdt, nodename, "phandle", + qemu_fdt_alloc_phandle(ms->fdt)); + } + g_free(nodename); } + + if (!vmc->no_cpu_topology) { + /* + * Add vCPU topology description through fdt node cpu-map. + * + * See Linux Documentation/devicetree/bindings/cpu/cpu-topology.txt + * In a SMP system, the hierarchy of CPUs can be defined through + * four entities that are used to describe the layout of CPUs in + * the system: socket/cluster/core/thread. + * + * A socket node represents the boundary of system physical package + * and its child nodes must be one or more cluster nodes. A system + * can contain several layers of clustering within a single physical + * package and cluster nodes can be contained in parent cluster nodes. + * + * Given that cluster is not yet supported in the vCPU topology, + * we currently generate one cluster node within each socket node + * by default. + */ + qemu_fdt_add_subnode(ms->fdt, "/cpus/cpu-map"); + + for (cpu = smp_cpus - 1; cpu >= 0; cpu--) { + char *cpu_path = g_strdup_printf("/cpus/cpu@%d", cpu); + char *map_path; + + if (ms->smp.threads > 1) { + map_path = g_strdup_printf( + "/cpus/cpu-map/socket%d/cluster0/core%d/thread%d", + cpu / (ms->smp.cores * ms->smp.threads), + (cpu / ms->smp.threads) % ms->smp.cores, + cpu % ms->smp.threads); + } else { + map_path = g_strdup_printf( + "/cpus/cpu-map/socket%d/cluster0/core%d", + cpu / ms->smp.cores, + cpu % ms->smp.cores); + } + qemu_fdt_add_path(ms->fdt, map_path); + qemu_fdt_setprop_phandle(ms->fdt, map_path, "cpu", cpu_path); + + g_free(map_path); + g_free(cpu_path); + } + } } static void fdt_add_its_gic_node(VirtMachineState *vms) @@ -2816,6 +2866,7 @@ static void virt_machine_6_1_options(MachineClass *mc) virt_machine_6_2_options(mc); compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); mc->smp_props.prefer_sockets = true; + vmc->no_cpu_topology = true; /* qemu ITS was introduced with 6.2 */ vmc->no_tcg_its = true; diff --git a/hw/core/loader.c b/hw/core/loader.c index c623318b73..c7f97fdce8 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -326,7 +326,7 @@ static void *load_at(int fd, off_t offset, size_t size) #define SZ 64 #include "hw/elf_ops.h" -const char *load_elf_strerror(int error) +const char *load_elf_strerror(ssize_t error) { switch (error) { case 0: @@ -402,12 +402,12 @@ fail: } /* return < 0 if error, otherwise the number of bytes loaded in memory */ -int load_elf(const char *filename, - uint64_t (*elf_note_fn)(void *, void *, bool), - uint64_t (*translate_fn)(void *, uint64_t), - void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr, - uint64_t *highaddr, uint32_t *pflags, int big_endian, - int elf_machine, int clear_lsb, int data_swab) +ssize_t load_elf(const char *filename, + uint64_t (*elf_note_fn)(void *, void *, bool), + uint64_t (*translate_fn)(void *, uint64_t), + void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr, + uint64_t *highaddr, uint32_t *pflags, int big_endian, + int elf_machine, int clear_lsb, int data_swab) { return load_elf_as(filename, elf_note_fn, translate_fn, translate_opaque, pentry, lowaddr, highaddr, pflags, big_endian, @@ -415,12 +415,13 @@ int load_elf(const char *filename, } /* return < 0 if error, otherwise the number of bytes loaded in memory */ -int load_elf_as(const char *filename, - uint64_t (*elf_note_fn)(void *, void *, bool), - uint64_t (*translate_fn)(void *, uint64_t), - void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr, - uint64_t *highaddr, uint32_t *pflags, int big_endian, - int elf_machine, int clear_lsb, int data_swab, AddressSpace *as) +ssize_t load_elf_as(const char *filename, + uint64_t (*elf_note_fn)(void *, void *, bool), + uint64_t (*translate_fn)(void *, uint64_t), + void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr, + uint64_t *highaddr, uint32_t *pflags, int big_endian, + int elf_machine, int clear_lsb, int data_swab, + AddressSpace *as) { return load_elf_ram(filename, elf_note_fn, translate_fn, translate_opaque, pentry, lowaddr, highaddr, pflags, big_endian, @@ -428,13 +429,13 @@ int load_elf_as(const char *filename, } /* return < 0 if error, otherwise the number of bytes loaded in memory */ -int load_elf_ram(const char *filename, - uint64_t (*elf_note_fn)(void *, void *, bool), - uint64_t (*translate_fn)(void *, uint64_t), - void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr, - uint64_t *highaddr, uint32_t *pflags, int big_endian, - int elf_machine, int clear_lsb, int data_swab, - AddressSpace *as, bool load_rom) +ssize_t load_elf_ram(const char *filename, + uint64_t (*elf_note_fn)(void *, void *, bool), + uint64_t (*translate_fn)(void *, uint64_t), + void *translate_opaque, uint64_t *pentry, + uint64_t *lowaddr, uint64_t *highaddr, uint32_t *pflags, + int big_endian, int elf_machine, int clear_lsb, + int data_swab, AddressSpace *as, bool load_rom) { return load_elf_ram_sym(filename, elf_note_fn, translate_fn, translate_opaque, @@ -444,16 +445,17 @@ int load_elf_ram(const char *filename, } /* return < 0 if error, otherwise the number of bytes loaded in memory */ -int load_elf_ram_sym(const char *filename, - uint64_t (*elf_note_fn)(void *, void *, bool), - uint64_t (*translate_fn)(void *, uint64_t), - void *translate_opaque, uint64_t *pentry, - uint64_t *lowaddr, uint64_t *highaddr, uint32_t *pflags, - int big_endian, int elf_machine, - int clear_lsb, int data_swab, - AddressSpace *as, bool load_rom, symbol_fn_t sym_cb) +ssize_t load_elf_ram_sym(const char *filename, + uint64_t (*elf_note_fn)(void *, void *, bool), + uint64_t (*translate_fn)(void *, uint64_t), + void *translate_opaque, uint64_t *pentry, + uint64_t *lowaddr, uint64_t *highaddr, + uint32_t *pflags, int big_endian, int elf_machine, + int clear_lsb, int data_swab, + AddressSpace *as, bool load_rom, symbol_fn_t sym_cb) { - int fd, data_order, target_data_order, must_swab, ret = ELF_LOAD_FAILED; + int fd, data_order, target_data_order, must_swab; + ssize_t ret = ELF_LOAD_FAILED; uint8_t e_ident[EI_NIDENT]; fd = open(filename, O_RDONLY | O_BINARY); diff --git a/hw/intc/spapr_xive.c b/hw/intc/spapr_xive.c index 89cfa018f5..4ec659b93e 100644 --- a/hw/intc/spapr_xive.c +++ b/hw/intc/spapr_xive.c @@ -185,7 +185,7 @@ static void spapr_xive_pic_print_info(SpaprXive *xive, Monitor *mon) xive_source_irq_is_lsi(xsrc, i) ? "LSI" : "MSI", pq & XIVE_ESB_VAL_P ? 'P' : '-', pq & XIVE_ESB_VAL_Q ? 'Q' : '-', - xsrc->status[i] & XIVE_STATUS_ASSERTED ? 'A' : ' ', + xive_source_is_asserted(xsrc, i) ? 'A' : ' ', xive_eas_is_masked(eas) ? "M" : " ", (int) xive_get_field64(EAS_END_DATA, eas->w)); diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c index 6d4909d0a8..61fe7bd2d3 100644 --- a/hw/intc/spapr_xive_kvm.c +++ b/hw/intc/spapr_xive_kvm.c @@ -242,7 +242,7 @@ int kvmppc_xive_source_reset_one(XiveSource *xsrc, int srcno, Error **errp) if (xive_source_irq_is_lsi(xsrc, srcno)) { state |= KVM_XIVE_LEVEL_SENSITIVE; - if (xsrc->status[srcno] & XIVE_STATUS_ASSERTED) { + if (xive_source_is_asserted(xsrc, srcno)) { state |= KVM_XIVE_LEVEL_ASSERTED; } } @@ -301,9 +301,7 @@ static uint8_t xive_esb_read(XiveSource *xsrc, int srcno, uint32_t offset) static void kvmppc_xive_esb_trigger(XiveSource *xsrc, int srcno) { - uint64_t *addr = xsrc->esb_mmap + xive_source_esb_page(xsrc, srcno); - - *addr = 0x0; + xive_esb_rw(xsrc, srcno, 0, 0, true); } uint64_t kvmppc_xive_esb_rw(XiveSource *xsrc, int srcno, uint32_t offset, @@ -321,7 +319,7 @@ uint64_t kvmppc_xive_esb_rw(XiveSource *xsrc, int srcno, uint32_t offset, if (xive_source_irq_is_lsi(xsrc, srcno) && offset == XIVE_ESB_LOAD_EOI) { xive_esb_read(xsrc, srcno, XIVE_ESB_SET_PQ_00); - if (xsrc->status[srcno] & XIVE_STATUS_ASSERTED) { + if (xive_source_is_asserted(xsrc, srcno)) { kvmppc_xive_esb_trigger(xsrc, srcno); } return 0; @@ -359,11 +357,7 @@ void kvmppc_xive_source_set_irq(void *opaque, int srcno, int val) return; } } else { - if (val) { - xsrc->status[srcno] |= XIVE_STATUS_ASSERTED; - } else { - xsrc->status[srcno] &= ~XIVE_STATUS_ASSERTED; - } + xive_source_set_asserted(xsrc, srcno, val); } kvmppc_xive_esb_trigger(xsrc, srcno); diff --git a/hw/intc/xive.c b/hw/intc/xive.c index 6c82326ec7..190194d27f 100644 --- a/hw/intc/xive.c +++ b/hw/intc/xive.c @@ -875,7 +875,7 @@ static bool xive_source_lsi_trigger(XiveSource *xsrc, uint32_t srcno) { uint8_t old_pq = xive_source_esb_get(xsrc, srcno); - xsrc->status[srcno] |= XIVE_STATUS_ASSERTED; + xive_source_set_asserted(xsrc, srcno, true); switch (old_pq) { case XIVE_ESB_RESET: @@ -923,7 +923,7 @@ static bool xive_source_esb_eoi(XiveSource *xsrc, uint32_t srcno) * notification */ if (xive_source_irq_is_lsi(xsrc, srcno) && - xsrc->status[srcno] & XIVE_STATUS_ASSERTED) { + xive_source_is_asserted(xsrc, srcno)) { ret = xive_source_lsi_trigger(xsrc, srcno); } @@ -1104,7 +1104,7 @@ void xive_source_set_irq(void *opaque, int srcno, int val) if (val) { notify = xive_source_lsi_trigger(xsrc, srcno); } else { - xsrc->status[srcno] &= ~XIVE_STATUS_ASSERTED; + xive_source_set_asserted(xsrc, srcno, false); } } else { if (val) { @@ -1133,7 +1133,7 @@ void xive_source_pic_print_info(XiveSource *xsrc, uint32_t offset, Monitor *mon) xive_source_irq_is_lsi(xsrc, i) ? "LSI" : "MSI", pq & XIVE_ESB_VAL_P ? 'P' : '-', pq & XIVE_ESB_VAL_Q ? 'Q' : '-', - xsrc->status[i] & XIVE_STATUS_ASSERTED ? 'A' : ' '); + xive_source_is_asserted(xsrc, i) ? 'A' : ' '); } } diff --git a/hw/net/vhost_net-stub.c b/hw/net/vhost_net-stub.c index a7f4252630..89d71cfb8e 100644 --- a/hw/net/vhost_net-stub.c +++ b/hw/net/vhost_net-stub.c @@ -33,13 +33,13 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { return -ENOSYS; } void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { } diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 386ec2eaa2..0d888f29a6 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -231,9 +231,11 @@ fail: return NULL; } -static void vhost_net_set_vq_index(struct vhost_net *net, int vq_index) +static void vhost_net_set_vq_index(struct vhost_net *net, int vq_index, + int last_index) { net->dev.vq_index = vq_index; + net->dev.last_index = last_index; } static int vhost_net_start_one(struct vhost_net *net, @@ -315,25 +317,37 @@ static void vhost_net_stop_one(struct vhost_net *net, } int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev))); VirtioBusState *vbus = VIRTIO_BUS(qbus); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); + int total_notifiers = data_queue_pairs * 2 + cvq; + VirtIONet *n = VIRTIO_NET(dev); + int nvhosts = data_queue_pairs + cvq; struct vhost_net *net; - int r, e, i; + int r, e, i, last_index = data_queue_pairs * 2; NetClientState *peer; + if (!cvq) { + last_index -= 1; + } + if (!k->set_guest_notifiers) { error_report("binding does not support guest notifiers"); return -ENOSYS; } - for (i = 0; i < total_queues; i++) { + for (i = 0; i < nvhosts; i++) { + + if (i < data_queue_pairs) { + peer = qemu_get_peer(ncs, i); + } else { /* Control Virtqueue */ + peer = qemu_get_peer(ncs, n->max_queue_pairs); + } - peer = qemu_get_peer(ncs, i); net = get_vhost_net(peer); - vhost_net_set_vq_index(net, i * 2); + vhost_net_set_vq_index(net, i * 2, last_index); /* Suppress the masking guest notifiers on vhost user * because vhost user doesn't interrupt masking/unmasking @@ -344,14 +358,18 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, } } - r = k->set_guest_notifiers(qbus->parent, total_queues * 2, true); + r = k->set_guest_notifiers(qbus->parent, total_notifiers, true); if (r < 0) { error_report("Error binding guest notifier: %d", -r); goto err; } - for (i = 0; i < total_queues; i++) { - peer = qemu_get_peer(ncs, i); + for (i = 0; i < nvhosts; i++) { + if (i < data_queue_pairs) { + peer = qemu_get_peer(ncs, i); + } else { + peer = qemu_get_peer(ncs, n->max_queue_pairs); + } r = vhost_net_start_one(get_vhost_net(peer), dev); if (r < 0) { @@ -375,7 +393,7 @@ err_start: peer = qemu_get_peer(ncs , i); vhost_net_stop_one(get_vhost_net(peer), dev); } - e = k->set_guest_notifiers(qbus->parent, total_queues * 2, false); + e = k->set_guest_notifiers(qbus->parent, total_notifiers, false); if (e < 0) { fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", e); fflush(stderr); @@ -385,18 +403,27 @@ err: } void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev))); VirtioBusState *vbus = VIRTIO_BUS(qbus); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); + VirtIONet *n = VIRTIO_NET(dev); + NetClientState *peer; + int total_notifiers = data_queue_pairs * 2 + cvq; + int nvhosts = data_queue_pairs + cvq; int i, r; - for (i = 0; i < total_queues; i++) { - vhost_net_stop_one(get_vhost_net(ncs[i].peer), dev); + for (i = 0; i < nvhosts; i++) { + if (i < data_queue_pairs) { + peer = qemu_get_peer(ncs, i); + } else { + peer = qemu_get_peer(ncs, n->max_queue_pairs); + } + vhost_net_stop_one(get_vhost_net(peer), dev); } - r = k->set_guest_notifiers(qbus->parent, total_queues * 2, false); + r = k->set_guest_notifiers(qbus->parent, total_notifiers, false); if (r < 0) { fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", r); fflush(stderr); diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 09e173a558..f2014d5ea0 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -54,7 +54,7 @@ #define VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE 256 #define VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE 256 -/* for now, only allow larger queues; with virtio-1, guest can downsize */ +/* for now, only allow larger queue_pairs; with virtio-1, guest can downsize */ #define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE #define VIRTIO_NET_TX_QUEUE_MIN_SIZE VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE @@ -131,7 +131,7 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) int ret = 0; memset(&netcfg, 0 , sizeof(struct virtio_net_config)); virtio_stw_p(vdev, &netcfg.status, n->status); - virtio_stw_p(vdev, &netcfg.max_virtqueue_pairs, n->max_queues); + virtio_stw_p(vdev, &netcfg.max_virtqueue_pairs, n->max_queue_pairs); virtio_stw_p(vdev, &netcfg.mtu, n->net_conf.mtu); memcpy(netcfg.mac, n->mac, ETH_ALEN); virtio_stl_p(vdev, &netcfg.speed, n->net_conf.speed); @@ -243,7 +243,8 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) { VirtIODevice *vdev = VIRTIO_DEVICE(n); NetClientState *nc = qemu_get_queue(n->nic); - int queues = n->multiqueue ? n->max_queues : 1; + int queue_pairs = n->multiqueue ? n->max_queue_pairs : 1; + int cvq = n->max_ncs - n->max_queue_pairs; if (!get_vhost_net(nc->peer)) { return; @@ -266,7 +267,7 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) /* Any packets outstanding? Purge them to avoid touching rings * when vhost is running. */ - for (i = 0; i < queues; i++) { + for (i = 0; i < queue_pairs; i++) { NetClientState *qnc = qemu_get_subqueue(n->nic, i); /* Purge both directions: TX and RX. */ @@ -285,14 +286,14 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) } n->vhost_started = 1; - r = vhost_net_start(vdev, n->nic->ncs, queues); + r = vhost_net_start(vdev, n->nic->ncs, queue_pairs, cvq); if (r < 0) { error_report("unable to start vhost net: %d: " "falling back on userspace virtio", -r); n->vhost_started = 0; } } else { - vhost_net_stop(vdev, n->nic->ncs, queues); + vhost_net_stop(vdev, n->nic->ncs, queue_pairs, cvq); n->vhost_started = 0; } } @@ -309,11 +310,11 @@ static int virtio_net_set_vnet_endian_one(VirtIODevice *vdev, } static bool virtio_net_set_vnet_endian(VirtIODevice *vdev, NetClientState *ncs, - int queues, bool enable) + int queue_pairs, bool enable) { int i; - for (i = 0; i < queues; i++) { + for (i = 0; i < queue_pairs; i++) { if (virtio_net_set_vnet_endian_one(vdev, ncs[i].peer, enable) < 0 && enable) { while (--i >= 0) { @@ -330,7 +331,7 @@ static bool virtio_net_set_vnet_endian(VirtIODevice *vdev, NetClientState *ncs, static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status) { VirtIODevice *vdev = VIRTIO_DEVICE(n); - int queues = n->multiqueue ? n->max_queues : 1; + int queue_pairs = n->multiqueue ? n->max_queue_pairs : 1; if (virtio_net_started(n, status)) { /* Before using the device, we tell the network backend about the @@ -339,14 +340,14 @@ static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status) * virtio-net code. */ n->needs_vnet_hdr_swap = virtio_net_set_vnet_endian(vdev, n->nic->ncs, - queues, true); + queue_pairs, true); } else if (virtio_net_started(n, vdev->status)) { /* After using the device, we need to reset the network backend to * the default (guest native endianness), otherwise the guest may * lose network connectivity if it is rebooted into a different * endianness. */ - virtio_net_set_vnet_endian(vdev, n->nic->ncs, queues, false); + virtio_net_set_vnet_endian(vdev, n->nic->ncs, queue_pairs, false); } } @@ -368,12 +369,12 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) virtio_net_vnet_endian_status(n, status); virtio_net_vhost_status(n, status); - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { NetClientState *ncs = qemu_get_subqueue(n->nic, i); bool queue_started; q = &n->vqs[i]; - if ((!n->multiqueue && i != 0) || i >= n->curr_queues) { + if ((!n->multiqueue && i != 0) || i >= n->curr_queue_pairs) { queue_status = 0; } else { queue_status = status; @@ -540,7 +541,7 @@ static void virtio_net_reset(VirtIODevice *vdev) n->nouni = 0; n->nobcast = 0; /* multiqueue is disabled by default */ - n->curr_queues = 1; + n->curr_queue_pairs = 1; timer_del(n->announce_timer.tm); n->announce_timer.round = 0; n->status &= ~VIRTIO_NET_S_ANNOUNCE; @@ -556,7 +557,7 @@ static void virtio_net_reset(VirtIODevice *vdev) memset(n->vlans, 0, MAX_VLAN >> 3); /* Flush any async TX */ - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { NetClientState *nc = qemu_get_subqueue(n->nic, i); if (nc->peer) { @@ -610,7 +611,7 @@ static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs, sizeof(struct virtio_net_hdr); } - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { nc = qemu_get_subqueue(n->nic, i); if (peer_has_vnet_hdr(n) && @@ -655,7 +656,7 @@ static int peer_attach(VirtIONet *n, int index) return 0; } - if (n->max_queues == 1) { + if (n->max_queue_pairs == 1) { return 0; } @@ -681,7 +682,7 @@ static int peer_detach(VirtIONet *n, int index) return tap_disable(nc->peer); } -static void virtio_net_set_queues(VirtIONet *n) +static void virtio_net_set_queue_pairs(VirtIONet *n) { int i; int r; @@ -690,8 +691,8 @@ static void virtio_net_set_queues(VirtIONet *n) return; } - for (i = 0; i < n->max_queues; i++) { - if (i < n->curr_queues) { + for (i = 0; i < n->max_queue_pairs; i++) { + if (i < n->curr_queue_pairs) { r = peer_attach(n, i); assert(!r); } else { @@ -905,7 +906,7 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) virtio_net_apply_guest_offloads(n); } - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { NetClientState *nc = qemu_get_subqueue(n->nic, i); if (!get_vhost_net(nc->peer)) { @@ -1232,7 +1233,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, VirtIODevice *vdev = VIRTIO_DEVICE(n); struct virtio_net_rss_config cfg; size_t s, offset = 0, size_get; - uint16_t queues, i; + uint16_t queue_pairs, i; struct { uint16_t us; uint8_t b; @@ -1274,7 +1275,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, } n->rss_data.default_queue = do_rss ? virtio_lduw_p(vdev, &cfg.unclassified_queue) : 0; - if (n->rss_data.default_queue >= n->max_queues) { + if (n->rss_data.default_queue >= n->max_queue_pairs) { err_msg = "Invalid default queue"; err_value = n->rss_data.default_queue; goto error; @@ -1303,14 +1304,14 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, size_get = sizeof(temp); s = iov_to_buf(iov, iov_cnt, offset, &temp, size_get); if (s != size_get) { - err_msg = "Can't get queues"; + err_msg = "Can't get queue_pairs"; err_value = (uint32_t)s; goto error; } - queues = do_rss ? virtio_lduw_p(vdev, &temp.us) : n->curr_queues; - if (queues == 0 || queues > n->max_queues) { - err_msg = "Invalid number of queues"; - err_value = queues; + queue_pairs = do_rss ? virtio_lduw_p(vdev, &temp.us) : n->curr_queue_pairs; + if (queue_pairs == 0 || queue_pairs > n->max_queue_pairs) { + err_msg = "Invalid number of queue_pairs"; + err_value = queue_pairs; goto error; } if (temp.b > VIRTIO_NET_RSS_MAX_KEY_SIZE) { @@ -1325,7 +1326,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, } if (!temp.b && !n->rss_data.hash_types) { virtio_net_disable_rss(n); - return queues; + return queue_pairs; } offset += size_get; size_get = temp.b; @@ -1358,7 +1359,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, trace_virtio_net_rss_enable(n->rss_data.hash_types, n->rss_data.indirections_len, temp.b); - return queues; + return queue_pairs; error: trace_virtio_net_rss_error(err_msg, err_value); virtio_net_disable_rss(n); @@ -1369,15 +1370,15 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, struct iovec *iov, unsigned int iov_cnt) { VirtIODevice *vdev = VIRTIO_DEVICE(n); - uint16_t queues; + uint16_t queue_pairs; virtio_net_disable_rss(n); if (cmd == VIRTIO_NET_CTRL_MQ_HASH_CONFIG) { - queues = virtio_net_handle_rss(n, iov, iov_cnt, false); - return queues ? VIRTIO_NET_OK : VIRTIO_NET_ERR; + queue_pairs = virtio_net_handle_rss(n, iov, iov_cnt, false); + return queue_pairs ? VIRTIO_NET_OK : VIRTIO_NET_ERR; } if (cmd == VIRTIO_NET_CTRL_MQ_RSS_CONFIG) { - queues = virtio_net_handle_rss(n, iov, iov_cnt, true); + queue_pairs = virtio_net_handle_rss(n, iov, iov_cnt, true); } else if (cmd == VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET) { struct virtio_net_ctrl_mq mq; size_t s; @@ -1388,24 +1389,24 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, if (s != sizeof(mq)) { return VIRTIO_NET_ERR; } - queues = virtio_lduw_p(vdev, &mq.virtqueue_pairs); + queue_pairs = virtio_lduw_p(vdev, &mq.virtqueue_pairs); } else { return VIRTIO_NET_ERR; } - if (queues < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || - queues > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX || - queues > n->max_queues || + if (queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || + queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX || + queue_pairs > n->max_queue_pairs || !n->multiqueue) { return VIRTIO_NET_ERR; } - n->curr_queues = queues; - /* stop the backend before changing the number of queues to avoid handling a + n->curr_queue_pairs = queue_pairs; + /* stop the backend before changing the number of queue_pairs to avoid handling a * disabled queue */ virtio_net_set_status(vdev, vdev->status); - virtio_net_set_queues(n); + virtio_net_set_queue_pairs(n); return VIRTIO_NET_OK; } @@ -1483,7 +1484,7 @@ static bool virtio_net_can_receive(NetClientState *nc) return false; } - if (nc->queue_index >= n->curr_queues) { + if (nc->queue_index >= n->curr_queue_pairs) { return false; } @@ -2763,11 +2764,11 @@ static void virtio_net_del_queue(VirtIONet *n, int index) virtio_del_queue(vdev, index * 2 + 1); } -static void virtio_net_change_num_queues(VirtIONet *n, int new_max_queues) +static void virtio_net_change_num_queue_pairs(VirtIONet *n, int new_max_queue_pairs) { VirtIODevice *vdev = VIRTIO_DEVICE(n); int old_num_queues = virtio_get_num_queues(vdev); - int new_num_queues = new_max_queues * 2 + 1; + int new_num_queues = new_max_queue_pairs * 2 + 1; int i; assert(old_num_queues >= 3); @@ -2800,12 +2801,12 @@ static void virtio_net_change_num_queues(VirtIONet *n, int new_max_queues) static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue) { - int max = multiqueue ? n->max_queues : 1; + int max = multiqueue ? n->max_queue_pairs : 1; n->multiqueue = multiqueue; - virtio_net_change_num_queues(n, max); + virtio_net_change_num_queue_pairs(n, max); - virtio_net_set_queues(n); + virtio_net_set_queue_pairs(n); } static int virtio_net_post_load_device(void *opaque, int version_id) @@ -2838,7 +2839,7 @@ static int virtio_net_post_load_device(void *opaque, int version_id) */ n->saved_guest_offloads = n->curr_guest_offloads; - virtio_net_set_queues(n); + virtio_net_set_queue_pairs(n); /* Find the first multicast entry in the saved MAC filter */ for (i = 0; i < n->mac_table.in_use; i++) { @@ -2851,7 +2852,7 @@ static int virtio_net_post_load_device(void *opaque, int version_id) /* nc.link_down can't be migrated, so infer link_down according * to link status bit in n->status */ link_down = (n->status & VIRTIO_NET_S_LINK_UP) == 0; - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { qemu_get_subqueue(n->nic, i)->link_down = link_down; } @@ -2916,9 +2917,9 @@ static const VMStateDescription vmstate_virtio_net_queue_tx_waiting = { }, }; -static bool max_queues_gt_1(void *opaque, int version_id) +static bool max_queue_pairs_gt_1(void *opaque, int version_id) { - return VIRTIO_NET(opaque)->max_queues > 1; + return VIRTIO_NET(opaque)->max_queue_pairs > 1; } static bool has_ctrl_guest_offloads(void *opaque, int version_id) @@ -2943,13 +2944,13 @@ static bool mac_table_doesnt_fit(void *opaque, int version_id) struct VirtIONetMigTmp { VirtIONet *parent; VirtIONetQueue *vqs_1; - uint16_t curr_queues_1; + uint16_t curr_queue_pairs_1; uint8_t has_ufo; uint32_t has_vnet_hdr; }; /* The 2nd and subsequent tx_waiting flags are loaded later than - * the 1st entry in the queues and only if there's more than one + * the 1st entry in the queue_pairs and only if there's more than one * entry. We use the tmp mechanism to calculate a temporary * pointer and count and also validate the count. */ @@ -2959,9 +2960,9 @@ static int virtio_net_tx_waiting_pre_save(void *opaque) struct VirtIONetMigTmp *tmp = opaque; tmp->vqs_1 = tmp->parent->vqs + 1; - tmp->curr_queues_1 = tmp->parent->curr_queues - 1; - if (tmp->parent->curr_queues == 0) { - tmp->curr_queues_1 = 0; + tmp->curr_queue_pairs_1 = tmp->parent->curr_queue_pairs - 1; + if (tmp->parent->curr_queue_pairs == 0) { + tmp->curr_queue_pairs_1 = 0; } return 0; @@ -2974,9 +2975,9 @@ static int virtio_net_tx_waiting_pre_load(void *opaque) /* Reuse the pointer setup from save */ virtio_net_tx_waiting_pre_save(opaque); - if (tmp->parent->curr_queues > tmp->parent->max_queues) { - error_report("virtio-net: curr_queues %x > max_queues %x", - tmp->parent->curr_queues, tmp->parent->max_queues); + if (tmp->parent->curr_queue_pairs > tmp->parent->max_queue_pairs) { + error_report("virtio-net: curr_queue_pairs %x > max_queue_pairs %x", + tmp->parent->curr_queue_pairs, tmp->parent->max_queue_pairs); return -EINVAL; } @@ -2990,7 +2991,7 @@ static const VMStateDescription vmstate_virtio_net_tx_waiting = { .pre_save = virtio_net_tx_waiting_pre_save, .fields = (VMStateField[]) { VMSTATE_STRUCT_VARRAY_POINTER_UINT16(vqs_1, struct VirtIONetMigTmp, - curr_queues_1, + curr_queue_pairs_1, vmstate_virtio_net_queue_tx_waiting, struct VirtIONetQueue), VMSTATE_END_OF_LIST() @@ -3132,9 +3133,9 @@ static const VMStateDescription vmstate_virtio_net_device = { VMSTATE_UINT8(nobcast, VirtIONet), VMSTATE_WITH_TMP(VirtIONet, struct VirtIONetMigTmp, vmstate_virtio_net_has_ufo), - VMSTATE_SINGLE_TEST(max_queues, VirtIONet, max_queues_gt_1, 0, + VMSTATE_SINGLE_TEST(max_queue_pairs, VirtIONet, max_queue_pairs_gt_1, 0, vmstate_info_uint16_equal, uint16_t), - VMSTATE_UINT16_TEST(curr_queues, VirtIONet, max_queues_gt_1), + VMSTATE_UINT16_TEST(curr_queue_pairs, VirtIONet, max_queue_pairs_gt_1), VMSTATE_WITH_TMP(VirtIONet, struct VirtIONetMigTmp, vmstate_virtio_net_tx_waiting), VMSTATE_UINT64_TEST(curr_guest_offloads, VirtIONet, @@ -3299,19 +3300,41 @@ static bool failover_hide_primary_device(DeviceListener *listener, if (!device_opts) { return false; } - standby_id = qdict_get_try_str(device_opts, "failover_pair_id"); - if (g_strcmp0(standby_id, n->netclient_name) != 0) { + + if (!qdict_haskey(device_opts, "failover_pair_id")) { return false; } - if (n->primary_opts) { - error_setg(errp, "Cannot attach more than one primary device to '%s'", - n->netclient_name); + if (!qdict_haskey(device_opts, "id")) { + error_setg(errp, "Device with failover_pair_id needs to have id"); return false; } - n->primary_opts = qdict_clone_shallow(device_opts); - n->primary_opts_from_json = from_json; + standby_id = qdict_get_str(device_opts, "failover_pair_id"); + if (g_strcmp0(standby_id, n->netclient_name) != 0) { + return false; + } + + /* + * The hide helper can be called several times for a given device. + * Check there is only one primary for a virtio-net device but + * don't duplicate the qdict several times if it's called for the same + * device. + */ + if (n->primary_opts) { + const char *old, *new; + /* devices with failover_pair_id always have an id */ + old = qdict_get_str(n->primary_opts, "id"); + new = qdict_get_str(device_opts, "id"); + if (strcmp(old, new) != 0) { + error_setg(errp, "Cannot attach more than one primary device to " + "'%s': '%s' and '%s'", n->netclient_name, old, new); + return false; + } + } else { + n->primary_opts = qdict_clone_shallow(device_opts); + n->primary_opts_from_json = from_json; + } /* failover_primary_hidden is set during feature negotiation */ return qatomic_read(&n->failover_primary_hidden); @@ -3389,16 +3412,30 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) return; } - n->max_queues = MAX(n->nic_conf.peers.queues, 1); - if (n->max_queues * 2 + 1 > VIRTIO_QUEUE_MAX) { - error_setg(errp, "Invalid number of queues (= %" PRIu32 "), " + n->max_ncs = MAX(n->nic_conf.peers.queues, 1); + + /* + * Figure out the datapath queue pairs since the backend could + * provide control queue via peers as well. + */ + if (n->nic_conf.peers.queues) { + for (i = 0; i < n->max_ncs; i++) { + if (n->nic_conf.peers.ncs[i]->is_datapath) { + ++n->max_queue_pairs; + } + } + } + n->max_queue_pairs = MAX(n->max_queue_pairs, 1); + + if (n->max_queue_pairs * 2 + 1 > VIRTIO_QUEUE_MAX) { + error_setg(errp, "Invalid number of queue pairs (= %" PRIu32 "), " "must be a positive integer less than %d.", - n->max_queues, (VIRTIO_QUEUE_MAX - 1) / 2); + n->max_queue_pairs, (VIRTIO_QUEUE_MAX - 1) / 2); virtio_cleanup(vdev); return; } - n->vqs = g_malloc0(sizeof(VirtIONetQueue) * n->max_queues); - n->curr_queues = 1; + n->vqs = g_malloc0(sizeof(VirtIONetQueue) * n->max_queue_pairs); + n->curr_queue_pairs = 1; n->tx_timeout = n->net_conf.txtimer; if (n->net_conf.tx && strcmp(n->net_conf.tx, "timer") @@ -3412,7 +3449,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) n->net_conf.tx_queue_size = MIN(virtio_net_max_tx_queue_size(n), n->net_conf.tx_queue_size); - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { virtio_net_add_queue(n, i); } @@ -3436,13 +3473,13 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) object_get_typename(OBJECT(dev)), dev->id, n); } - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { n->nic->ncs[i].do_not_pad = true; } peer_test_vnet_hdr(n); if (peer_has_vnet_hdr(n)) { - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { qemu_using_vnet_hdr(qemu_get_subqueue(n->nic, i)->peer, true); } n->host_hdr_len = sizeof(struct virtio_net_hdr); @@ -3484,7 +3521,7 @@ static void virtio_net_device_unrealize(DeviceState *dev) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIONet *n = VIRTIO_NET(dev); - int i, max_queues; + int i, max_queue_pairs; if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) { virtio_net_unload_ebpf(n); @@ -3509,12 +3546,12 @@ static void virtio_net_device_unrealize(DeviceState *dev) assert(n->primary_opts == NULL); } - max_queues = n->multiqueue ? n->max_queues : 1; - for (i = 0; i < max_queues; i++) { + max_queue_pairs = n->multiqueue ? n->max_queue_pairs : 1; + for (i = 0; i < max_queue_pairs; i++) { virtio_net_del_queue(n, i); } /* delete also control vq */ - virtio_del_queue(vdev, max_queues * 2); + virtio_del_queue(vdev, max_queue_pairs * 2); qemu_announce_timer_del(&n->announce_timer, false); g_free(n->vqs); qemu_del_nic(n->nic); diff --git a/hw/pci-host/mv64361.c b/hw/pci-host/mv64361.c index 92b0f5d047..00b3ff7d90 100644 --- a/hw/pci-host/mv64361.c +++ b/hw/pci-host/mv64361.c @@ -869,6 +869,7 @@ static void mv64361_realize(DeviceState *dev, Error **errp) s->base_addr_enable = 0x1fffff; memory_region_init_io(&s->regs, OBJECT(s), &mv64361_ops, s, TYPE_MV64361, 0x10000); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->regs); for (i = 0; i < 2; i++) { g_autofree char *name = g_strdup_printf("pcihost%d", i); object_initialize_child(OBJECT(dev), name, &s->pci[i], diff --git a/hw/pci/pci_bridge.c b/hw/pci/pci_bridge.c index d1f902ee86..da34c8ebcd 100644 --- a/hw/pci/pci_bridge.c +++ b/hw/pci/pci_bridge.c @@ -448,11 +448,11 @@ int pci_bridge_qemu_reserve_cap_init(PCIDevice *dev, int cap_offset, PCIBridgeQemuCap cap = { .len = cap_len, .type = REDHAT_PCI_CAP_RESOURCE_RESERVE, - .bus_res = res_reserve.bus, - .io = res_reserve.io, - .mem = res_reserve.mem_non_pref, - .mem_pref_32 = res_reserve.mem_pref_32, - .mem_pref_64 = res_reserve.mem_pref_64 + .bus_res = cpu_to_le32(res_reserve.bus), + .io = cpu_to_le64(res_reserve.io), + .mem = cpu_to_le32(res_reserve.mem_non_pref), + .mem_pref_32 = cpu_to_le32(res_reserve.mem_pref_32), + .mem_pref_64 = cpu_to_le64(res_reserve.mem_pref_64) }; int offset = pci_add_capability(dev, PCI_CAP_ID_VNDR, diff --git a/hw/ppc/pegasos2.c b/hw/ppc/pegasos2.c index b8ce859f1a..e427ac2fe0 100644 --- a/hw/ppc/pegasos2.c +++ b/hw/ppc/pegasos2.c @@ -22,6 +22,7 @@ #include "hw/i2c/smbus_eeprom.h" #include "hw/qdev-properties.h" #include "sysemu/reset.h" +#include "sysemu/runstate.h" #include "hw/boards.h" #include "hw/loader.h" #include "hw/fw-path-provider.h" @@ -31,6 +32,8 @@ #include "sysemu/kvm.h" #include "kvm_ppc.h" #include "exec/address-spaces.h" +#include "qom/qom-qobject.h" +#include "qapi/qmp/qdict.h" #include "trace.h" #include "qemu/datadir.h" #include "sysemu/device_tree.h" @@ -52,11 +55,13 @@ #define BUS_FREQ_HZ 133333333 +#define PCI0_CFG_ADDR 0xcf8 #define PCI0_MEM_BASE 0xc0000000 #define PCI0_MEM_SIZE 0x20000000 #define PCI0_IO_BASE 0xf8000000 #define PCI0_IO_SIZE 0x10000 +#define PCI1_CFG_ADDR 0xc78 #define PCI1_MEM_BASE 0x80000000 #define PCI1_MEM_SIZE 0x40000000 #define PCI1_IO_BASE 0xfe000000 @@ -117,6 +122,10 @@ static void pegasos2_init(MachineState *machine) qemu_register_reset(pegasos2_cpu_reset, pm->cpu); /* RAM */ + if (machine->ram_size > 2 * GiB) { + error_report("RAM size more than 2 GiB is not supported"); + exit(1); + } memory_region_add_subregion(get_system_memory(), 0, machine->ram); /* allocate and load firmware */ @@ -190,62 +199,58 @@ static void pegasos2_init(MachineState *machine) if (!pm->vof) { warn_report("Option -kernel may be ineffective with -bios."); } + } else if (pm->vof) { + warn_report("Using Virtual OpenFirmware but no -kernel option."); } + if (!pm->vof && machine->kernel_cmdline && machine->kernel_cmdline[0]) { warn_report("Option -append may be ineffective with -bios."); } } -static uint32_t pegasos2_pci_config_read(AddressSpace *as, int bus, +static uint32_t pegasos2_mv_reg_read(Pegasos2MachineState *pm, + uint32_t addr, uint32_t len) +{ + MemoryRegion *r = sysbus_mmio_get_region(SYS_BUS_DEVICE(pm->mv), 0); + uint64_t val = 0xffffffffULL; + memory_region_dispatch_read(r, addr, &val, size_memop(len) | MO_LE, + MEMTXATTRS_UNSPECIFIED); + return val; +} + +static void pegasos2_mv_reg_write(Pegasos2MachineState *pm, uint32_t addr, + uint32_t len, uint32_t val) +{ + MemoryRegion *r = sysbus_mmio_get_region(SYS_BUS_DEVICE(pm->mv), 0); + memory_region_dispatch_write(r, addr, val, size_memop(len) | MO_LE, + MEMTXATTRS_UNSPECIFIED); +} + +static uint32_t pegasos2_pci_config_read(Pegasos2MachineState *pm, int bus, uint32_t addr, uint32_t len) { - hwaddr pcicfg = (bus ? 0xf1000c78 : 0xf1000cf8); - uint32_t val = 0xffffffff; - - stl_le_phys(as, pcicfg, addr | BIT(31)); - switch (len) { - case 4: - val = ldl_le_phys(as, pcicfg + 4); - break; - case 2: - val = lduw_le_phys(as, pcicfg + 4); - break; - case 1: - val = ldub_phys(as, pcicfg + 4); - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid length\n", __func__); - break; + hwaddr pcicfg = bus ? PCI1_CFG_ADDR : PCI0_CFG_ADDR; + uint64_t val = 0xffffffffULL; + + if (len <= 4) { + pegasos2_mv_reg_write(pm, pcicfg, 4, addr | BIT(31)); + val = pegasos2_mv_reg_read(pm, pcicfg + 4, len); } return val; } -static void pegasos2_pci_config_write(AddressSpace *as, int bus, uint32_t addr, - uint32_t len, uint32_t val) +static void pegasos2_pci_config_write(Pegasos2MachineState *pm, int bus, + uint32_t addr, uint32_t len, uint32_t val) { - hwaddr pcicfg = (bus ? 0xf1000c78 : 0xf1000cf8); - - stl_le_phys(as, pcicfg, addr | BIT(31)); - switch (len) { - case 4: - stl_le_phys(as, pcicfg + 4, val); - break; - case 2: - stw_le_phys(as, pcicfg + 4, val); - break; - case 1: - stb_phys(as, pcicfg + 4, val); - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid length\n", __func__); - break; - } + hwaddr pcicfg = bus ? PCI1_CFG_ADDR : PCI0_CFG_ADDR; + + pegasos2_mv_reg_write(pm, pcicfg, 4, addr | BIT(31)); + pegasos2_mv_reg_write(pm, pcicfg + 4, len, val); } static void pegasos2_machine_reset(MachineState *machine) { Pegasos2MachineState *pm = PEGASOS2_MACHINE(machine); - AddressSpace *as = CPU(pm->cpu)->as; void *fdt; uint64_t d[2]; int sz; @@ -256,51 +261,51 @@ static void pegasos2_machine_reset(MachineState *machine) } /* Otherwise, set up devices that board firmware would normally do */ - stl_le_phys(as, 0xf1000000, 0x28020ff); - stl_le_phys(as, 0xf1000278, 0xa31fc); - stl_le_phys(as, 0xf100f300, 0x11ff0400); - stl_le_phys(as, 0xf100f10c, 0x80000000); - stl_le_phys(as, 0xf100001c, 0x8000000); - pegasos2_pci_config_write(as, 0, PCI_COMMAND, 2, PCI_COMMAND_IO | + pegasos2_mv_reg_write(pm, 0, 4, 0x28020ff); + pegasos2_mv_reg_write(pm, 0x278, 4, 0xa31fc); + pegasos2_mv_reg_write(pm, 0xf300, 4, 0x11ff0400); + pegasos2_mv_reg_write(pm, 0xf10c, 4, 0x80000000); + pegasos2_mv_reg_write(pm, 0x1c, 4, 0x8000000); + pegasos2_pci_config_write(pm, 0, PCI_COMMAND, 2, PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); - pegasos2_pci_config_write(as, 1, PCI_COMMAND, 2, PCI_COMMAND_IO | + pegasos2_pci_config_write(pm, 1, PCI_COMMAND, 2, PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 0) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 0) << 8) | PCI_INTERRUPT_LINE, 2, 0x9); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 0) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 0) << 8) | 0x50, 1, 0x2); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 1) << 8) | PCI_INTERRUPT_LINE, 2, 0x109); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 1) << 8) | PCI_CLASS_PROG, 1, 0xf); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 1) << 8) | 0x40, 1, 0xb); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 1) << 8) | 0x50, 4, 0x17171717); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 1) << 8) | PCI_COMMAND, 2, 0x87); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 2) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 2) << 8) | PCI_INTERRUPT_LINE, 2, 0x409); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 3) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 3) << 8) | PCI_INTERRUPT_LINE, 2, 0x409); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 4) << 8) | PCI_INTERRUPT_LINE, 2, 0x9); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 4) << 8) | 0x48, 4, 0xf00); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 4) << 8) | 0x40, 4, 0x558020); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 4) << 8) | 0x90, 4, 0xd00); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 5) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 5) << 8) | PCI_INTERRUPT_LINE, 2, 0x309); - pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 6) << 8) | + pegasos2_pci_config_write(pm, 1, (PCI_DEVFN(12, 6) << 8) | PCI_INTERRUPT_LINE, 2, 0x309); /* Device tree and VOF set up */ @@ -362,6 +367,29 @@ static target_ulong pegasos2_rtas(PowerPCCPU *cpu, Pegasos2MachineState *pm, return H_PARAMETER; } switch (token) { + case RTAS_GET_TIME_OF_DAY: + { + QObject *qo = object_property_get_qobject(qdev_get_machine(), + "rtc-time", &error_fatal); + QDict *qd = qobject_to(QDict, qo); + + if (nargs != 0 || nrets != 8 || !qd) { + stl_be_phys(as, rets, -1); + qobject_unref(qo); + return H_PARAMETER; + } + + stl_be_phys(as, rets, 0); + stl_be_phys(as, rets + 4, qdict_get_int(qd, "tm_year") + 1900); + stl_be_phys(as, rets + 8, qdict_get_int(qd, "tm_mon") + 1); + stl_be_phys(as, rets + 12, qdict_get_int(qd, "tm_mday")); + stl_be_phys(as, rets + 16, qdict_get_int(qd, "tm_hour")); + stl_be_phys(as, rets + 20, qdict_get_int(qd, "tm_min")); + stl_be_phys(as, rets + 24, qdict_get_int(qd, "tm_sec")); + stl_be_phys(as, rets + 28, 0); + qobject_unref(qo); + return H_SUCCESS; + } case RTAS_READ_PCI_CONFIG: { uint32_t addr, len, val; @@ -372,7 +400,7 @@ static target_ulong pegasos2_rtas(PowerPCCPU *cpu, Pegasos2MachineState *pm, } addr = ldl_be_phys(as, args); len = ldl_be_phys(as, args + 4); - val = pegasos2_pci_config_read(as, !(addr >> 24), + val = pegasos2_pci_config_read(pm, !(addr >> 24), addr & 0x0fffffff, len); stl_be_phys(as, rets, 0); stl_be_phys(as, rets + 4, val); @@ -389,7 +417,7 @@ static target_ulong pegasos2_rtas(PowerPCCPU *cpu, Pegasos2MachineState *pm, addr = ldl_be_phys(as, args); len = ldl_be_phys(as, args + 4); val = ldl_be_phys(as, args + 8); - pegasos2_pci_config_write(as, !(addr >> 24), + pegasos2_pci_config_write(pm, !(addr >> 24), addr & 0x0fffffff, len, val); stl_be_phys(as, rets, 0); return H_SUCCESS; @@ -402,6 +430,16 @@ static target_ulong pegasos2_rtas(PowerPCCPU *cpu, Pegasos2MachineState *pm, qemu_log_mask(LOG_UNIMP, "%c", ldl_be_phys(as, args)); stl_be_phys(as, rets, 0); return H_SUCCESS; + case RTAS_POWER_OFF: + { + if (nargs != 2 || nrets != 1) { + stl_be_phys(as, rets, -1); + return H_PARAMETER; + } + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + stl_be_phys(as, rets, 0); + return H_SUCCESS; + } default: qemu_log_mask(LOG_UNIMP, "Unknown RTAS token %u (args=%u, rets=%u)\n", token, nargs, nrets); diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c index f5d012f860..e8127599c9 100644 --- a/hw/ppc/ppc.c +++ b/hw/ppc/ppc.c @@ -336,6 +336,8 @@ void store_40x_dbcr0(CPUPPCState *env, uint32_t val) { PowerPCCPU *cpu = env_archcpu(env); + qemu_mutex_lock_iothread(); + switch ((val >> 28) & 0x3) { case 0x0: /* No action */ @@ -353,6 +355,8 @@ void store_40x_dbcr0(CPUPPCState *env, uint32_t val) ppc40x_system_reset(cpu); break; } + + qemu_mutex_unlock_iothread(); } /* PowerPC 40x internal IRQ controller */ @@ -848,7 +852,7 @@ static void __cpu_ppc_store_decr(PowerPCCPU *cpu, uint64_t *nextp, * On MSB edge based DEC implementations the MSB going from 0 -> 1 triggers * an edge interrupt, so raise it here too. */ - if ((signed_value < 3) || + if ((value < 3) || ((tb_env->flags & PPC_DECR_UNDERFLOW_LEVEL) && signed_value < 0) || ((tb_env->flags & PPC_DECR_UNDERFLOW_TRIGGERED) && signed_value < 0 && signed_decr >= 0)) { diff --git a/hw/ppc/ppc4xx_pci.c b/hw/ppc/ppc4xx_pci.c index 8147ba6f94..304a29349c 100644 --- a/hw/ppc/ppc4xx_pci.c +++ b/hw/ppc/ppc4xx_pci.c @@ -48,12 +48,14 @@ OBJECT_DECLARE_SIMPLE_TYPE(PPC4xxPCIState, PPC4xx_PCI_HOST_BRIDGE) #define PPC4xx_PCI_NR_PMMS 3 #define PPC4xx_PCI_NR_PTMS 2 +#define PPC4xx_PCI_NUM_DEVS 5 + struct PPC4xxPCIState { PCIHostState parent_obj; struct PCIMasterMap pmm[PPC4xx_PCI_NR_PMMS]; struct PCITargetMap ptm[PPC4xx_PCI_NR_PTMS]; - qemu_irq irq[PCI_NUM_PINS]; + qemu_irq irq[PPC4xx_PCI_NUM_DEVS]; MemoryRegion container; MemoryRegion iomem; @@ -246,7 +248,7 @@ static int ppc4xx_pci_map_irq(PCIDevice *pci_dev, int irq_num) trace_ppc4xx_pci_map_irq(pci_dev->devfn, irq_num, slot); - return slot - 1; + return slot > 0 ? slot - 1 : PPC4xx_PCI_NUM_DEVS - 1; } static void ppc4xx_pci_set_irq(void *opaque, int irq_num, int level) @@ -254,7 +256,7 @@ static void ppc4xx_pci_set_irq(void *opaque, int irq_num, int level) qemu_irq *pci_irqs = opaque; trace_ppc4xx_pci_set_irq(irq_num); - assert(irq_num >= 0); + assert(irq_num >= 0 && irq_num < PPC4xx_PCI_NUM_DEVS); qemu_set_irq(pci_irqs[irq_num], level); } diff --git a/hw/ppc/spapr_softmmu.c b/hw/ppc/spapr_softmmu.c index 6c6b86dd3c..f8924270ef 100644 --- a/hw/ppc/spapr_softmmu.c +++ b/hw/ppc/spapr_softmmu.c @@ -1,25 +1,10 @@ #include "qemu/osdep.h" #include "qemu/cutils.h" -#include "qapi/error.h" -#include "sysemu/hw_accel.h" -#include "sysemu/runstate.h" -#include "qemu/log.h" -#include "qemu/main-loop.h" -#include "qemu/module.h" -#include "qemu/error-report.h" #include "cpu.h" -#include "exec/exec-all.h" #include "helper_regs.h" #include "hw/ppc/spapr.h" -#include "hw/ppc/spapr_cpu_core.h" #include "mmu-hash64.h" -#include "cpu-models.h" -#include "trace.h" -#include "kvm_ppc.h" -#include "hw/ppc/fdt.h" -#include "hw/ppc/spapr_ovec.h" #include "mmu-book3s-v3.h" -#include "hw/mem/memory-device.h" static inline bool valid_ptex(PowerPCCPU *cpu, target_ulong ptex) { diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig index 35ab45e209..c144d42f9b 100644 --- a/hw/virtio/Kconfig +++ b/hw/virtio/Kconfig @@ -63,3 +63,8 @@ config VHOST_USER_I2C bool default y depends on VIRTIO && VHOST_USER + +config VHOST_USER_RNG + bool + default y + depends on VIRTIO && VHOST_USER diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build index bc352a6009..521f7d64a8 100644 --- a/hw/virtio/meson.build +++ b/hw/virtio/meson.build @@ -27,6 +27,8 @@ virtio_ss.add(when: 'CONFIG_VIRTIO_IOMMU', if_true: files('virtio-iommu.c')) virtio_ss.add(when: 'CONFIG_VIRTIO_MEM', if_true: files('virtio-mem.c')) virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c')) virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c')) +virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c')) +virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c')) virtio_pci_ss = ss.source_set() virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c')) diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 8ed19e9d0c..650e521e35 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -52,6 +52,7 @@ vhost_vdpa_set_vring_call(void *dev, unsigned int index, int fd) "dev: %p index: vhost_vdpa_get_features(void *dev, uint64_t features) "dev: %p features: 0x%"PRIx64 vhost_vdpa_set_owner(void *dev) "dev: %p" vhost_vdpa_vq_get_addr(void *dev, void *vq, uint64_t desc_user_addr, uint64_t avail_user_addr, uint64_t used_user_addr) "dev: %p vq: %p desc_user_addr: 0x%"PRIx64" avail_user_addr: 0x%"PRIx64" used_user_addr: 0x%"PRIx64 +vhost_vdpa_get_iova_range(void *dev, uint64_t first, uint64_t last) "dev: %p first: 0x%"PRIx64" last: 0x%"PRIx64 # virtio.c virtqueue_alloc_element(void *elem, size_t sz, unsigned in_num, unsigned out_num) "elem %p size %zd in_num %u out_num %u" diff --git a/hw/virtio/vhost-user-rng-pci.c b/hw/virtio/vhost-user-rng-pci.c new file mode 100644 index 0000000000..c83dc86813 --- /dev/null +++ b/hw/virtio/vhost-user-rng-pci.c @@ -0,0 +1,79 @@ +/* + * Vhost-user RNG virtio device PCI glue + * + * Copyright (c) 2021 Mathieu Poirier <mathieu.poirier@linaro.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/vhost-user-rng.h" +#include "virtio-pci.h" + +struct VHostUserRNGPCI { + VirtIOPCIProxy parent_obj; + VHostUserRNG vdev; +}; + +typedef struct VHostUserRNGPCI VHostUserRNGPCI; + +#define TYPE_VHOST_USER_RNG_PCI "vhost-user-rng-pci-base" + +DECLARE_INSTANCE_CHECKER(VHostUserRNGPCI, VHOST_USER_RNG_PCI, + TYPE_VHOST_USER_RNG_PCI) + +static Property vhost_user_rng_pci_properties[] = { + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, + DEV_NVECTORS_UNSPECIFIED), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vhost_user_rng_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostUserRNGPCI *dev = VHOST_USER_RNG_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = 1; + } + + qdev_realize(vdev, BUS(&vpci_dev->bus), errp); +} + +static void vhost_user_rng_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = vhost_user_rng_pci_realize; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + device_class_set_props(dc, vhost_user_rng_pci_properties); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = 0; /* Set by virtio-pci based on virtio id */ + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_OTHERS; +} + +static void vhost_user_rng_pci_instance_init(Object *obj) +{ + VHostUserRNGPCI *dev = VHOST_USER_RNG_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_USER_RNG); +} + +static const VirtioPCIDeviceTypeInfo vhost_user_rng_pci_info = { + .base_name = TYPE_VHOST_USER_RNG_PCI, + .non_transitional_name = "vhost-user-rng-pci", + .instance_size = sizeof(VHostUserRNGPCI), + .instance_init = vhost_user_rng_pci_instance_init, + .class_init = vhost_user_rng_pci_class_init, +}; + +static void vhost_user_rng_pci_register(void) +{ + virtio_pci_types_register(&vhost_user_rng_pci_info); +} + +type_init(vhost_user_rng_pci_register); diff --git a/hw/virtio/vhost-user-rng.c b/hw/virtio/vhost-user-rng.c new file mode 100644 index 0000000000..209ee5bf9a --- /dev/null +++ b/hw/virtio/vhost-user-rng.c @@ -0,0 +1,289 @@ +/* + * Vhost-user RNG virtio device + * + * Copyright (c) 2021 Mathieu Poirier <mathieu.poirier@linaro.org> + * + * Implementation seriously tailored on vhost-user-i2c.c + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/vhost-user-rng.h" +#include "qemu/error-report.h" +#include "standard-headers/linux/virtio_ids.h" + +static void vu_rng_start(VirtIODevice *vdev) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + int ret; + int i; + + if (!k->set_guest_notifiers) { + error_report("binding does not support guest notifiers"); + return; + } + + ret = vhost_dev_enable_notifiers(&rng->vhost_dev, vdev); + if (ret < 0) { + error_report("Error enabling host notifiers: %d", -ret); + return; + } + + ret = k->set_guest_notifiers(qbus->parent, rng->vhost_dev.nvqs, true); + if (ret < 0) { + error_report("Error binding guest notifier: %d", -ret); + goto err_host_notifiers; + } + + rng->vhost_dev.acked_features = vdev->guest_features; + ret = vhost_dev_start(&rng->vhost_dev, vdev); + if (ret < 0) { + error_report("Error starting vhost-user-rng: %d", -ret); + goto err_guest_notifiers; + } + + /* + * guest_notifier_mask/pending not used yet, so just unmask + * everything here. virtio-pci will do the right thing by + * enabling/disabling irqfd. + */ + for (i = 0; i < rng->vhost_dev.nvqs; i++) { + vhost_virtqueue_mask(&rng->vhost_dev, vdev, i, false); + } + + return; + +err_guest_notifiers: + k->set_guest_notifiers(qbus->parent, rng->vhost_dev.nvqs, false); +err_host_notifiers: + vhost_dev_disable_notifiers(&rng->vhost_dev, vdev); +} + +static void vu_rng_stop(VirtIODevice *vdev) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + int ret; + + if (!k->set_guest_notifiers) { + return; + } + + vhost_dev_stop(&rng->vhost_dev, vdev); + + ret = k->set_guest_notifiers(qbus->parent, rng->vhost_dev.nvqs, false); + if (ret < 0) { + error_report("vhost guest notifier cleanup failed: %d", ret); + return; + } + + vhost_dev_disable_notifiers(&rng->vhost_dev, vdev); +} + +static void vu_rng_set_status(VirtIODevice *vdev, uint8_t status) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK; + + if (!vdev->vm_running) { + should_start = false; + } + + if (rng->vhost_dev.started == should_start) { + return; + } + + if (should_start) { + vu_rng_start(vdev); + } else { + vu_rng_stop(vdev); + } +} + +static uint64_t vu_rng_get_features(VirtIODevice *vdev, + uint64_t requested_features, Error **errp) +{ + /* No feature bits used yet */ + return requested_features; +} + +static void vu_rng_handle_output(VirtIODevice *vdev, VirtQueue *vq) +{ + /* + * Not normally called; it's the daemon that handles the queue; + * however virtio's cleanup path can call this. + */ +} + +static void vu_rng_guest_notifier_mask(VirtIODevice *vdev, int idx, bool mask) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + vhost_virtqueue_mask(&rng->vhost_dev, vdev, idx, mask); +} + +static bool vu_rng_guest_notifier_pending(VirtIODevice *vdev, int idx) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + return vhost_virtqueue_pending(&rng->vhost_dev, idx); +} + +static void vu_rng_connect(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + if (rng->connected) { + return; + } + + rng->connected = true; + + /* restore vhost state */ + if (virtio_device_started(vdev, vdev->status)) { + vu_rng_start(vdev); + } +} + +static void vu_rng_disconnect(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + if (!rng->connected) { + return; + } + + rng->connected = false; + + if (rng->vhost_dev.started) { + vu_rng_stop(vdev); + } +} + +static void vu_rng_event(void *opaque, QEMUChrEvent event) +{ + DeviceState *dev = opaque; + + switch (event) { + case CHR_EVENT_OPENED: + vu_rng_connect(dev); + break; + case CHR_EVENT_CLOSED: + vu_rng_disconnect(dev); + break; + case CHR_EVENT_BREAK: + case CHR_EVENT_MUX_IN: + case CHR_EVENT_MUX_OUT: + /* Ignore */ + break; + } +} + +static void vu_rng_device_realize(DeviceState *dev, Error **errp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(dev); + int ret; + + if (!rng->chardev.chr) { + error_setg(errp, "missing chardev"); + return; + } + + if (!vhost_user_init(&rng->vhost_user, &rng->chardev, errp)) { + return; + } + + virtio_init(vdev, "vhost-user-rng", VIRTIO_ID_RNG, 0); + + rng->req_vq = virtio_add_queue(vdev, 4, vu_rng_handle_output); + if (!rng->req_vq) { + error_setg_errno(errp, -1, "virtio_add_queue() failed"); + goto virtio_add_queue_failed; + } + + rng->vhost_dev.nvqs = 1; + rng->vhost_dev.vqs = g_new0(struct vhost_virtqueue, rng->vhost_dev.nvqs); + ret = vhost_dev_init(&rng->vhost_dev, &rng->vhost_user, + VHOST_BACKEND_TYPE_USER, 0, errp); + if (ret < 0) { + error_setg_errno(errp, -ret, "vhost_dev_init() failed"); + goto vhost_dev_init_failed; + } + + qemu_chr_fe_set_handlers(&rng->chardev, NULL, NULL, vu_rng_event, NULL, + dev, NULL, true); + + return; + +vhost_dev_init_failed: + virtio_delete_queue(rng->req_vq); +virtio_add_queue_failed: + virtio_cleanup(vdev); + vhost_user_cleanup(&rng->vhost_user); +} + +static void vu_rng_device_unrealize(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(dev); + + vu_rng_set_status(vdev, 0); + + vhost_dev_cleanup(&rng->vhost_dev); + g_free(rng->vhost_dev.vqs); + rng->vhost_dev.vqs = NULL; + virtio_delete_queue(rng->req_vq); + virtio_cleanup(vdev); + vhost_user_cleanup(&rng->vhost_user); +} + +static const VMStateDescription vu_rng_vmstate = { + .name = "vhost-user-rng", + .unmigratable = 1, +}; + +static Property vu_rng_properties[] = { + DEFINE_PROP_CHR("chardev", VHostUserRNG, chardev), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vu_rng_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + + device_class_set_props(dc, vu_rng_properties); + dc->vmsd = &vu_rng_vmstate; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + + vdc->realize = vu_rng_device_realize; + vdc->unrealize = vu_rng_device_unrealize; + vdc->get_features = vu_rng_get_features; + vdc->set_status = vu_rng_set_status; + vdc->guest_notifier_mask = vu_rng_guest_notifier_mask; + vdc->guest_notifier_pending = vu_rng_guest_notifier_pending; +} + +static const TypeInfo vu_rng_info = { + .name = TYPE_VHOST_USER_RNG, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(VHostUserRNG), + .class_init = vu_rng_class_init, +}; + +static void vu_rng_register_types(void) +{ + type_register_static(&vu_rng_info); +} + +type_init(vu_rng_register_types) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 2c8556237f..bf6e50223c 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -1526,8 +1526,9 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev, name = g_strdup_printf("vhost-user/host-notifier@%p mmaps[%d]", user, queue_idx); - memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name, - page_size, addr); + if (!n->mr.ram) /* Don't init again after suspend. */ + memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name, + page_size, addr); g_free(name); if (virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true)) { diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 47d7a5a23d..12661fd5b1 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -24,19 +24,49 @@ #include "trace.h" #include "qemu-common.h" -static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section) +/* + * Return one past the end of the end of section. Be careful with uint64_t + * conversions! + */ +static Int128 vhost_vdpa_section_end(const MemoryRegionSection *section) +{ + Int128 llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + return llend; +} + +static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section, + uint64_t iova_min, + uint64_t iova_max) { - return (!memory_region_is_ram(section->mr) && - !memory_region_is_iommu(section->mr)) || - /* vhost-vDPA doesn't allow MMIO to be mapped */ - memory_region_is_ram_device(section->mr) || - /* - * Sizing an enabled 64-bit BAR can cause spurious mappings to - * addresses in the upper part of the 64-bit address space. These - * are never accessed by the CPU and beyond the address width of - * some IOMMU hardware. TODO: VDPA should tell us the IOMMU width. - */ - section->offset_within_address_space & (1ULL << 63); + Int128 llend; + + if ((!memory_region_is_ram(section->mr) && + !memory_region_is_iommu(section->mr)) || + memory_region_is_protected(section->mr) || + /* vhost-vDPA doesn't allow MMIO to be mapped */ + memory_region_is_ram_device(section->mr)) { + return true; + } + + if (section->offset_within_address_space < iova_min) { + error_report("RAM section out of device range (min=0x%" PRIx64 + ", addr=0x%" HWADDR_PRIx ")", + iova_min, section->offset_within_address_space); + return true; + } + + llend = vhost_vdpa_section_end(section); + if (int128_gt(llend, int128_make64(iova_max))) { + error_report("RAM section out of device range (max=0x%" PRIx64 + ", end addr=0x%" PRIx64 ")", + iova_max, int128_get64(llend)); + return true; + } + + return false; } static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, @@ -148,7 +178,8 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, void *vaddr; int ret; - if (vhost_vdpa_listener_skipped_section(section)) { + if (vhost_vdpa_listener_skipped_section(section, v->iova_range.first, + v->iova_range.last)) { return; } @@ -159,10 +190,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, } iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); - + llend = vhost_vdpa_section_end(section); if (int128_ge(int128_make64(iova), llend)) { return; } @@ -209,7 +237,8 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, Int128 llend, llsize; int ret; - if (vhost_vdpa_listener_skipped_section(section)) { + if (vhost_vdpa_listener_skipped_section(section, v->iova_range.first, + v->iova_range.last)) { return; } @@ -220,9 +249,7 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, } iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + llend = vhost_vdpa_section_end(section); trace_vhost_vdpa_listener_region_del(v, iova, int128_get64(llend)); @@ -279,6 +306,26 @@ static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status) vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &s); } +static void vhost_vdpa_get_iova_range(struct vhost_vdpa *v) +{ + int ret = vhost_vdpa_call(v->dev, VHOST_VDPA_GET_IOVA_RANGE, + &v->iova_range); + if (ret != 0) { + v->iova_range.first = 0; + v->iova_range.last = UINT64_MAX; + } + + trace_vhost_vdpa_get_iova_range(v->dev, v->iova_range.first, + v->iova_range.last); +} + +static bool vhost_vdpa_one_time_request(struct vhost_dev *dev) +{ + struct vhost_vdpa *v = dev->opaque; + + return v->index != 0; +} + static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) { struct vhost_vdpa *v; @@ -291,6 +338,12 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) v->listener = vhost_vdpa_memory_listener; v->msg_type = VHOST_IOTLB_MSG_V2; + vhost_vdpa_get_iova_range(v); + + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER); @@ -401,6 +454,10 @@ static int vhost_vdpa_memslots_limit(struct vhost_dev *dev) static int vhost_vdpa_set_mem_table(struct vhost_dev *dev, struct vhost_memory *mem) { + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + trace_vhost_vdpa_set_mem_table(dev, mem->nregions, mem->padding); if (trace_event_get_state_backends(TRACE_VHOST_VDPA_SET_MEM_TABLE) && trace_event_get_state_backends(TRACE_VHOST_VDPA_DUMP_REGIONS)) { @@ -424,6 +481,11 @@ static int vhost_vdpa_set_features(struct vhost_dev *dev, uint64_t features) { int ret; + + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + trace_vhost_vdpa_set_features(dev, features); ret = vhost_vdpa_call(dev, VHOST_SET_FEATURES, &features); uint8_t status = 0; @@ -448,9 +510,12 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) } features &= f; - r = vhost_vdpa_call(dev, VHOST_SET_BACKEND_FEATURES, &features); - if (r) { - return -EFAULT; + + if (vhost_vdpa_one_time_request(dev)) { + r = vhost_vdpa_call(dev, VHOST_SET_BACKEND_FEATURES, &features); + if (r) { + return -EFAULT; + } } dev->backend_cap = features; @@ -481,8 +546,8 @@ static int vhost_vdpa_get_vq_index(struct vhost_dev *dev, int idx) { assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); - trace_vhost_vdpa_get_vq_index(dev, idx, idx - dev->vq_index); - return idx - dev->vq_index; + trace_vhost_vdpa_get_vq_index(dev, idx, idx); + return idx; } static int vhost_vdpa_set_vring_ready(struct vhost_dev *dev) @@ -559,11 +624,21 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) { struct vhost_vdpa *v = dev->opaque; trace_vhost_vdpa_dev_start(dev, started); + if (started) { - uint8_t status = 0; - memory_listener_register(&v->listener, &address_space_memory); vhost_vdpa_host_notifiers_init(dev); vhost_vdpa_set_vring_ready(dev); + } else { + vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); + } + + if (dev->vq_index + dev->nvqs != dev->last_index) { + return 0; + } + + if (started) { + uint8_t status = 0; + memory_listener_register(&v->listener, &address_space_memory); vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status); @@ -572,7 +647,6 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) vhost_vdpa_reset_device(dev); vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER); - vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); memory_listener_unregister(&v->listener); return 0; @@ -582,6 +656,10 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, struct vhost_log *log) { + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + trace_vhost_vdpa_set_log_base(dev, base, log->size, log->refcnt, log->fd, log->log); return vhost_vdpa_call(dev, VHOST_SET_LOG_BASE, &base); @@ -647,6 +725,10 @@ static int vhost_vdpa_get_features(struct vhost_dev *dev, static int vhost_vdpa_set_owner(struct vhost_dev *dev) { + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + trace_vhost_vdpa_set_owner(dev); return vhost_vdpa_call(dev, VHOST_SET_OWNER, NULL); } diff --git a/hw/virtio/virtio-iommu-pci.c b/hw/virtio/virtio-iommu-pci.c index 770c286be7..a160ae6b41 100644 --- a/hw/virtio/virtio-iommu-pci.c +++ b/hw/virtio/virtio-iommu-pci.c @@ -98,9 +98,7 @@ static void virtio_iommu_pci_instance_init(Object *obj) } static const VirtioPCIDeviceTypeInfo virtio_iommu_pci_info = { - .base_name = TYPE_VIRTIO_IOMMU_PCI, - .generic_name = "virtio-iommu-pci", - .non_transitional_name = "virtio-iommu-pci-non-transitional", + .generic_name = TYPE_VIRTIO_IOMMU_PCI, .instance_size = sizeof(VirtIOIOMMUPCI), .instance_init = virtio_iommu_pci_instance_init, .class_init = virtio_iommu_pci_class_init, |