Merge remote-tracking branch 'remotes/dg-gitlab/tags/ppc-for-6.1-20210709' into staging

ppc patch queue 2021-07-09 Here's a (probably) final pull request before the qemu-6.1 soft freeze. Includes: * Implementation of the new H_RPT_INVALIDATE hypercall * Virtual Open Firmware for pSeries and pegasos2 machine types. This is an experimental minimal Open Firmware implementation which works by delegating nearly everything to qemu itself via a special hypercall. * A number of cleanups to the ppc soft MMU code * Fix to handling of two-level radix mode translations for the powernv machine type * Update the H_GET_CPU_CHARACTERISTICS call with newly defined bits. This will allow more flexible handling of possible future CPU Spectre-like flaws * Correctly treat mtmsrd as an illegal instruction on BookE cpus * Firmware update for the ppce500 machine type # gpg: Signature made Fri 09 Jul 2021 06:16:42 BST # gpg: using RSA key 75F46586AE61A66CC44E87DC6C38CACA20D9B392 # gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>" [full] # gpg: aka "David Gibson (Red Hat) <dgibson@redhat.com>" [full] # gpg: aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>" [full] # gpg: aka "David Gibson (kernel.org) <dwg@kernel.org>" [unknown] # Primary key fingerprint: 75F4 6586 AE61 A66C C44E 87DC 6C38 CACA 20D9 B392 * remotes/dg-gitlab/tags/ppc-for-6.1-20210709: (33 commits) target/ppc: Support for H_RPT_INVALIDATE hcall linux-headers: Update spapr: Fix implementation of Open Firmware client interface target/ppc: Don't compile ppc_tlb_invalid_all without TCG ppc/pegasos2: Implement some RTAS functions with VOF ppc/pegasos2: Fix use of && instead of & ppc/pegasos2: Use Virtual Open Firmware as firmware replacement target/ppc/spapr: Update H_GET_CPU_CHARACTERISTICS L1D cache flush bits target/ppc: Allow virtual hypervisor on CPU without HV ppc/pegasos2: Introduce Pegasos2MachineState structure target/ppc: mtmsrd is an illegal instruction on BookE spapr: Implement Open Firmware client interface docs/system: ppc: Update ppce500 documentation with eTSEC support roms/u-boot: Bump ppce500 u-boot to v2021.07 to add eTSEC support target/ppc: change ppc_hash32_xlate to use mmu_idx target/ppc: introduce mmu-books.h target/ppc: changed ppc_hash64_xlate to use mmu_idx target/ppc: fix address translation bug for radix mmus target/ppc: Fix compilation with DEBUG_BATS debug option target/ppc: Fix compilation with FLUSH_ALL_TLBS debug option ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2026-07-06 00:20:22 -07:00 · 2021-07-10 16:06:24 +01:00
parent ebd1f71002 82123b756a
commit fc32b91a88
70 changed files with 3257 additions and 604 deletions
@@ -1360,6 +1360,18 @@ F: hw/pci-host/mv64361.c
 F: hw/pci-host/mv643xx.h
 F: include/hw/pci-host/mv64361.h

+Virtual Open Firmware (VOF)
+M: Alexey Kardashevskiy <aik@ozlabs.ru>
+R: David Gibson <david@gibson.dropbear.id.au>
+R: Greg Kurz <groug@kaod.org>
+L: qemu-ppc@nongnu.org
+S: Maintained
+F: hw/ppc/spapr_vof*
+F: hw/ppc/vof*
+F: include/hw/ppc/vof*
+F: pc-bios/vof/*
+F: pc-bios/vof*
+
 RISC-V Machines
 ---------------
 OpenTitan
@@ -14,7 +14,7 @@ CONFIG_SAM460EX=y
 CONFIG_MAC_OLDWORLD=y
 CONFIG_MAC_NEWWORLD=y

-CONFIG_PEGASOS2=n
+CONFIG_PEGASOS2=y

 # For PReP
 CONFIG_PREP=y
@@ -19,6 +19,7 @@ The ``ppce500`` machine supports the following devices:
 * Power-off functionality via one GPIO pin
 * 1 Freescale MPC8xxx PCI host controller
 * VirtIO devices via PCI bus
+* 1 Freescale Enhanced Triple Speed Ethernet controller (eTSEC)

 Hardware configuration information
 ----------------------------------
@@ -121,7 +122,7 @@ To boot the 32-bit Linux kernel:
 Running U-Boot
 --------------

-U-Boot mainline v2021.04 release is tested at the time of writing. To build a
+U-Boot mainline v2021.07 release is tested at the time of writing. To build a
 U-Boot mainline bootloader that can be booted by the ``ppce500`` machine, use
 the qemu-ppce500_defconfig with similar commands as described above for Linux:

@@ -154,3 +155,10 @@ interface at PCI address 0.1.0, but we can switch that to an e1000 NIC by:
                    -display none -serial stdio \
                    -bios u-boot \
                    -nic tap,ifname=tap0,script=no,downscript=no,model=e1000
+
+The QEMU ``ppce500`` machine can also dynamically instantiate an eTSEC device
+if “-device eTSEC” is given to QEMU:
+
+.. code-block:: bash
+
+  -netdev tap,ifname=tap0,script=no,downscript=no,id=net0 -device eTSEC,netdev=net0
@@ -13,6 +13,7 @@ config PSERIES
    select MSI_NONBROKEN
    select FDT_PPC
    select CHRP_NVRAM
+    select VOF

 config SPAPR_RNG
    bool
@@ -75,6 +76,7 @@ config PEGASOS2
    select VT82C686
    select IDE_VIA
    select SMBUS_EEPROM
+    select VOF
 # This should come with VT82C686
    select ACPI_X86

@@ -144,3 +146,6 @@ config FW_CFG_PPC

 config FDT_PPC
    bool
+
+config VOF
+    bool
@@ -84,4 +84,7 @@ ppc_ss.add(when: 'CONFIG_VIRTEX', if_true: files('virtex_ml507.c'))
 # Pegasos2
 ppc_ss.add(when: 'CONFIG_PEGASOS2', if_true: files('pegasos2.c'))

+ppc_ss.add(when: 'CONFIG_VOF', if_true: files('vof.c'))
+ppc_ss.add(when: ['CONFIG_VOF', 'CONFIG_PSERIES'], if_true: files('spapr_vof.c'))
+
 hw_arch += {'ppc': ppc_ss}
@@ -101,6 +101,7 @@
 #define FDT_MAX_ADDR            0x80000000 /* FDT must stay below that */
 #define FW_MAX_SIZE             0x400000
 #define FW_FILE_NAME            "slof.bin"
+#define FW_FILE_NAME_VOF        "vof.bin"
 #define FW_OVERHEAD             0x2800000
 #define KERNEL_LOAD_ADDR        FW_MAX_SIZE

@@ -880,6 +881,10 @@ static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt)
    add_str(hypertas, "hcall-copy");
    add_str(hypertas, "hcall-debug");
    add_str(hypertas, "hcall-vphn");
+    if (spapr_get_cap(spapr, SPAPR_CAP_RPT_INVALIDATE) == SPAPR_CAP_ON) {
+        add_str(hypertas, "hcall-rpt-invalidate");
+    }
+
    add_str(qemu_hypertas, "hcall-memop1");

    if (!kvm_enabled() || kvmppc_spapr_use_multitce()) {
@@ -919,9 +924,13 @@ static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt)
     *
     * The extra 8 bytes is required because Linux's FWNMI error log check
     * is off-by-one.
+     *
+     * RTAS_MIN_SIZE is required for the RTAS blob itself.
     */
-    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-size", RTAS_ERROR_LOG_MAX +
-			  ms->smp.max_cpus * sizeof(uint64_t)*2 + sizeof(uint64_t)));
+    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-size", RTAS_MIN_SIZE +
+                          RTAS_ERROR_LOG_MAX +
+                          ms->smp.max_cpus * sizeof(uint64_t) * 2 +
+                          sizeof(uint64_t)));
    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-error-log-max",
                          RTAS_ERROR_LOG_MAX));
    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-event-scan-rate",
@@ -1639,22 +1648,29 @@ static void spapr_machine_reset(MachineState *machine)
    fdt_addr = MIN(spapr->rma_size, FDT_MAX_ADDR) - FDT_MAX_SIZE;

    fdt = spapr_build_fdt(spapr, true, FDT_MAX_SIZE);
+    if (spapr->vof) {
+        spapr_vof_reset(spapr, fdt, &error_fatal);
+        /*
+         * Do not pack the FDT as the client may change properties.
+         * VOF client does not expect the FDT so we do not load it to the VM.
+         */
+    } else {
+        rc = fdt_pack(fdt);
+        /* Should only fail if we've built a corrupted tree */
+        assert(rc == 0);

-    rc = fdt_pack(fdt);
-
-    /* Should only fail if we've built a corrupted tree */
-    assert(rc == 0);
-
-    /* Load the fdt */
+        spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT,
+                                  0, fdt_addr, 0);
+        cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
+    }
    qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt));
-    cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
+
    g_free(spapr->fdt_blob);
    spapr->fdt_size = fdt_totalsize(fdt);
    spapr->fdt_initial_size = spapr->fdt_size;
    spapr->fdt_blob = fdt;

    /* Set up the entry state */
-    spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT, 0, fdt_addr, 0);
    first_ppc_cpu->env.gpr[5] = 0;

    spapr->fwnmi_system_reset_addr = -1;
@@ -2018,6 +2034,7 @@ static const VMStateDescription vmstate_spapr = {
        &vmstate_spapr_cap_ccf_assist,
        &vmstate_spapr_cap_fwnmi,
        &vmstate_spapr_fwnmi,
+        &vmstate_spapr_cap_rpt_invalidate,
        NULL
    }
 };
@@ -2657,7 +2674,8 @@ static void spapr_machine_init(MachineState *machine)
    SpaprMachineState *spapr = SPAPR_MACHINE(machine);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    MachineClass *mc = MACHINE_GET_CLASS(machine);
-    const char *bios_name = machine->firmware ?: FW_FILE_NAME;
+    const char *bios_default = spapr->vof ? FW_FILE_NAME_VOF : FW_FILE_NAME;
+    const char *bios_name = machine->firmware ?: bios_default;
    const char *kernel_filename = machine->kernel_filename;
    const char *initrd_filename = machine->initrd_filename;
    PCIHostState *phb;
@@ -3014,6 +3032,10 @@ static void spapr_machine_init(MachineState *machine)
    }

    qemu_cond_init(&spapr->fwnmi_machine_check_interlock_cond);
+    if (spapr->vof) {
+        spapr->vof->fw_size = fw_size; /* for claim() on itself */
+        spapr_register_hypercall(KVMPPC_H_VOF_CLIENT, spapr_h_vof_client);
+    }
 }

 #define DEFAULT_KVM_TYPE "auto"
@@ -3204,6 +3226,28 @@ static void spapr_set_resize_hpt(Object *obj, const char *value, Error **errp)
    }
 }

+static bool spapr_get_vof(Object *obj, Error **errp)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(obj);
+
+    return spapr->vof != NULL;
+}
+
+static void spapr_set_vof(Object *obj, bool value, Error **errp)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(obj);
+
+    if (spapr->vof) {
+        vof_cleanup(spapr->vof);
+        g_free(spapr->vof);
+        spapr->vof = NULL;
+    }
+    if (!value) {
+        return;
+    }
+    spapr->vof = g_malloc0(sizeof(*spapr->vof));
+}
+
 static char *spapr_get_ic_mode(Object *obj, Error **errp)
 {
    SpaprMachineState *spapr = SPAPR_MACHINE(obj);
@@ -3329,6 +3373,11 @@ static void spapr_instance_init(Object *obj)
                                    stringify(KERNEL_LOAD_ADDR)
                                    " for -kernel is the default");
    spapr->kernel_addr = KERNEL_LOAD_ADDR;
+
+    object_property_add_bool(obj, "x-vof", spapr_get_vof, spapr_set_vof);
+    object_property_set_description(obj, "x-vof",
+                                    "Enable Virtual Open Firmware (experimental)");
+
    /* The machine class defines the default interrupt controller mode */
    spapr->irq = smc->irq;
    object_property_add_str(obj, "ic-mode", spapr_get_ic_mode,
@@ -4492,6 +4541,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
    XICSFabricClass *xic = XICS_FABRIC_CLASS(oc);
    InterruptStatsProviderClass *ispc = INTERRUPT_STATS_PROVIDER_CLASS(oc);
    XiveFabricClass *xfc = XIVE_FABRIC_CLASS(oc);
+    VofMachineIfClass *vmc = VOF_MACHINE_CLASS(oc);

    mc->desc = "pSeries Logical Partition (PAPR compliant)";
    mc->ignore_boot_device_suffixes = true;
@@ -4573,6 +4623,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
    smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_ON;
    smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_ON;
    smc->default_caps.caps[SPAPR_CAP_FWNMI] = SPAPR_CAP_ON;
+    smc->default_caps.caps[SPAPR_CAP_RPT_INVALIDATE] = SPAPR_CAP_OFF;
    spapr_caps_add_properties(smc);
    smc->irq = &spapr_irq_dual;
    smc->dr_phb_enabled = true;
@@ -4580,6 +4631,9 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
    smc->smp_threads_vsmt = true;
    smc->nr_xirqs = SPAPR_NR_XIRQS;
    xfc->match_nvt = spapr_match_nvt;
+    vmc->client_architecture_support = spapr_vof_client_architecture_support;
+    vmc->quiesce = spapr_vof_quiesce;
+    vmc->setprop = spapr_vof_setprop;
 }

 static const TypeInfo spapr_machine_info = {
@@ -4599,6 +4653,7 @@ static const TypeInfo spapr_machine_info = {
        { TYPE_XICS_FABRIC },
        { TYPE_INTERRUPT_STATS_PROVIDER },
        { TYPE_XIVE_FABRIC },
+        { TYPE_VOF_MACHINE_IF },
        { }
    },
 };
@@ -582,6 +582,37 @@ static void cap_fwnmi_apply(SpaprMachineState *spapr, uint8_t val,
    }
 }

+static void cap_rpt_invalidate_apply(SpaprMachineState *spapr,
+                                     uint8_t val, Error **errp)
+{
+    ERRP_GUARD();
+
+    if (!val) {
+        /* capability disabled by default */
+        return;
+    }
+
+    if (tcg_enabled()) {
+        error_setg(errp, "No H_RPT_INVALIDATE support in TCG");
+        error_append_hint(errp,
+                          "Try appending -machine cap-rpt-invalidate=off\n");
+    } else if (kvm_enabled()) {
+        if (!kvmppc_has_cap_mmu_radix()) {
+            error_setg(errp, "H_RPT_INVALIDATE only supported on Radix");
+            return;
+        }
+
+        if (!kvmppc_has_cap_rpt_invalidate()) {
+            error_setg(errp,
+                       "KVM implementation does not support H_RPT_INVALIDATE");
+            error_append_hint(errp,
+                              "Try appending -machine cap-rpt-invalidate=off\n");
+        } else {
+            kvmppc_enable_h_rpt_invalidate();
+        }
+    }
+}
+
 SpaprCapabilityInfo capability_table[SPAPR_CAP_NUM] = {
    [SPAPR_CAP_HTM] = {
        .name = "htm",
@@ -690,6 +721,15 @@ SpaprCapabilityInfo capability_table[SPAPR_CAP_NUM] = {
        .type = "bool",
        .apply = cap_fwnmi_apply,
    },
+    [SPAPR_CAP_RPT_INVALIDATE] = {
+        .name = "rpt-invalidate",
+        .description = "Allow H_RPT_INVALIDATE",
+        .index = SPAPR_CAP_RPT_INVALIDATE,
+        .get = spapr_cap_get_bool,
+        .set = spapr_cap_set_bool,
+        .type = "bool",
+        .apply = cap_rpt_invalidate_apply,
+    },
 };

 static SpaprCapabilities default_caps_with_cpu(SpaprMachineState *spapr,
@@ -830,6 +870,7 @@ SPAPR_CAP_MIG_STATE(nested_kvm_hv, SPAPR_CAP_NESTED_KVM_HV);
 SPAPR_CAP_MIG_STATE(large_decr, SPAPR_CAP_LARGE_DECREMENTER);
 SPAPR_CAP_MIG_STATE(ccf_assist, SPAPR_CAP_CCF_ASSIST);
 SPAPR_CAP_MIG_STATE(fwnmi, SPAPR_CAP_FWNMI);
+SPAPR_CAP_MIG_STATE(rpt_invalidate, SPAPR_CAP_RPT_INVALIDATE);

 void spapr_caps_init(SpaprMachineState *spapr)
 {
@@ -1233,8 +1233,7 @@ target_ulong do_client_architecture_support(PowerPCCPU *cpu,
        spapr_setup_hpt(spapr);
    }

-    fdt = spapr_build_fdt(spapr, false, fdt_bufsize);
-
+    fdt = spapr_build_fdt(spapr, spapr->vof != NULL, fdt_bufsize);
    g_free(spapr->fdt_blob);
    spapr->fdt_size = fdt_totalsize(fdt);
    spapr->fdt_initial_size = spapr->fdt_size;
@@ -1277,6 +1276,25 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
    return ret;
 }

+target_ulong spapr_vof_client_architecture_support(MachineState *ms,
+                                                   CPUState *cs,
+                                                   target_ulong ovec_addr)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(ms);
+
+    target_ulong ret = do_client_architecture_support(POWERPC_CPU(cs), spapr,
+                                                      ovec_addr, FDT_MAX_SIZE);
+
+    /*
+     * This adds stdout and generates phandles for boottime and CAS FDTs.
+     * It is alright to update the FDT here as do_client_architecture_support()
+     * does not pack it.
+     */
+    spapr_vof_client_dt_finalize(spapr, spapr->fdt_blob);
+
+    return ret;
+}
+
 static target_ulong h_get_cpu_characteristics(PowerPCCPU *cpu,
                                              SpaprMachineState *spapr,
                                              target_ulong opcode,
@@ -1299,6 +1317,8 @@ static target_ulong h_get_cpu_characteristics(PowerPCCPU *cpu,
        behaviour |= H_CPU_BEHAV_L1D_FLUSH_PR;
        break;
    case SPAPR_CAP_FIXED:
+        behaviour |= H_CPU_BEHAV_NO_L1D_FLUSH_ENTRY;
+        behaviour |= H_CPU_BEHAV_NO_L1D_FLUSH_UACCESS;
        break;
    default: /* broken */
        assert(safe_cache == SPAPR_CAP_BROKEN);
@@ -0,0 +1,167 @@
+/*
+ * SPAPR machine hooks to Virtual Open Firmware,
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "qapi/error.h"
+#include "hw/ppc/spapr.h"
+#include "hw/ppc/spapr_vio.h"
+#include "hw/ppc/spapr_cpu_core.h"
+#include "hw/ppc/fdt.h"
+#include "hw/ppc/vof.h"
+#include "sysemu/sysemu.h"
+#include "qom/qom-qobject.h"
+#include "trace.h"
+
+target_ulong spapr_h_vof_client(PowerPCCPU *cpu, SpaprMachineState *spapr,
+                                target_ulong opcode, target_ulong *_args)
+{
+    int ret = vof_client_call(MACHINE(spapr), spapr->vof, spapr->fdt_blob,
+                              ppc64_phys_to_real(_args[0]));
+
+    if (ret) {
+        return H_PARAMETER;
+    }
+    return H_SUCCESS;
+}
+
+void spapr_vof_client_dt_finalize(SpaprMachineState *spapr, void *fdt)
+{
+    char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus);
+
+    vof_build_dt(fdt, spapr->vof);
+
+    if (spapr->vof->bootargs) {
+        int chosen;
+
+        _FDT(chosen = fdt_path_offset(fdt, "/chosen"));
+        /*
+         * If the client did not change "bootargs", spapr_dt_chosen() must have
+         * stored machine->kernel_cmdline in it before getting here.
+         */
+        _FDT(fdt_setprop_string(fdt, chosen, "bootargs", spapr->vof->bootargs));
+    }
+
+    /*
+     * SLOF-less setup requires an open instance of stdout for early
+     * kernel printk. By now all phandles are settled so we can open
+     * the default serial console.
+     */
+    if (stdout_path) {
+        _FDT(vof_client_open_store(fdt, spapr->vof, "/chosen", "stdout",
+                                   stdout_path));
+    }
+}
+
+void spapr_vof_reset(SpaprMachineState *spapr, void *fdt, Error **errp)
+{
+    target_ulong stack_ptr;
+    Vof *vof = spapr->vof;
+    PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu);
+
+    vof_init(vof, spapr->rma_size, errp);
+
+    stack_ptr = vof_claim(vof, 0, VOF_STACK_SIZE, VOF_STACK_SIZE);
+    if (stack_ptr == -1) {
+        error_setg(errp, "Memory allocation for stack failed");
+        return;
+    }
+    /* Stack grows downwards plus reserve space for the minimum stack frame */
+    stack_ptr += VOF_STACK_SIZE - 0x20;
+
+    if (spapr->kernel_size &&
+        vof_claim(vof, spapr->kernel_addr, spapr->kernel_size, 0) == -1) {
+        error_setg(errp, "Memory for kernel is in use");
+        return;
+    }
+
+    if (spapr->initrd_size &&
+        vof_claim(vof, spapr->initrd_base, spapr->initrd_size, 0) == -1) {
+        error_setg(errp, "Memory for initramdisk is in use");
+        return;
+    }
+
+    spapr_vof_client_dt_finalize(spapr, fdt);
+
+    spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT,
+                              stack_ptr, spapr->initrd_base,
+                              spapr->initrd_size);
+    /* VOF is 32bit BE so enforce MSR here */
+    first_ppc_cpu->env.msr &= ~((1ULL << MSR_SF) | (1ULL << MSR_LE));
+
+    /*
+     * At this point the expected allocation map is:
+     *
+     * 0..c38 - the initial firmware
+     * 8000..10000 - stack
+     * 400000.. - kernel
+     * 3ea0000.. - initramdisk
+     *
+     * We skip writing FDT as nothing expects it; OF client interface is
+     * going to be used for reading the device tree.
+     */
+}
+
+void spapr_vof_quiesce(MachineState *ms)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(ms);
+
+    spapr->fdt_size = fdt_totalsize(spapr->fdt_blob);
+    spapr->fdt_initial_size = spapr->fdt_size;
+}
+
+bool spapr_vof_setprop(MachineState *ms, const char *path, const char *propname,
+                       void *val, int vallen)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(ms);
+
+    /*
+     * We only allow changing properties which we know how to update in QEMU
+     * OR
+     * the ones which we know that they need to survive during "quiesce".
+     */
+
+    if (strcmp(path, "/rtas") == 0) {
+        if (strcmp(propname, "linux,rtas-base") == 0 ||
+            strcmp(propname, "linux,rtas-entry") == 0) {
+            /* These need to survive quiesce so let them store in the FDT */
+            return true;
+        }
+    }
+
+    if (strcmp(path, "/chosen") == 0) {
+        if (strcmp(propname, "bootargs") == 0) {
+            Vof *vof = spapr->vof;
+
+            g_free(vof->bootargs);
+            vof->bootargs = g_strndup(val, vallen);
+            return true;
+        }
+        if (strcmp(propname, "linux,initrd-start") == 0) {
+            if (vallen == sizeof(uint32_t)) {
+                spapr->initrd_base = ldl_be_p(val);
+                return true;
+            }
+            if (vallen == sizeof(uint64_t)) {
+                spapr->initrd_base = ldq_be_p(val);
+                return true;
+            }
+            return false;
+        }
+        if (strcmp(propname, "linux,initrd-end") == 0) {
+            if (vallen == sizeof(uint32_t)) {
+                spapr->initrd_size = ldl_be_p(val) - spapr->initrd_base;
+                return true;
+            }
+            if (vallen == sizeof(uint64_t)) {
+                spapr->initrd_size = ldq_be_p(val) - spapr->initrd_base;
+                return true;
+            }
+            return false;
+        }
+    }
+
+    return true;
+}
@@ -71,6 +71,30 @@ spapr_rtas_ibm_configure_connector_invalid(uint32_t index) "DRC index: 0x%"PRIx3
 spapr_vio_h_reg_crq(uint64_t reg, uint64_t queue_addr, uint64_t queue_len) "CRQ for dev 0x%" PRIx64 " registered at 0x%" PRIx64 "/0x%" PRIx64
 spapr_vio_free_crq(uint32_t reg) "CRQ for dev 0x%" PRIx32 " freed"

+# vof.c
+vof_error_str_truncated(const char *s, int len) "%s truncated to %d"
+vof_error_param(const char *method, int nargscheck, int nretcheck, int nargs, int nret) "%s takes/returns %d/%d, not %d/%d"
+vof_error_unknown_service(const char *service, int nargs, int nret) "\"%s\" args=%d rets=%d"
+vof_error_unknown_method(const char *method) "\"%s\""
+vof_error_unknown_ihandle_close(uint32_t ih) "ih=0x%x"
+vof_error_unknown_path(const char *path) "\"%s\""
+vof_error_write(uint32_t ih) "ih=0x%x"
+vof_finddevice(const char *path, uint32_t ph) "\"%s\" => ph=0x%x"
+vof_claim(uint32_t virt, uint32_t size, uint32_t align, uint32_t ret) "virt=0x%x size=0x%x align=0x%x => 0x%x"
+vof_release(uint32_t virt, uint32_t size, uint32_t ret) "virt=0x%x size=0x%x => 0x%x"
+vof_method(uint32_t ihandle, const char *method, uint32_t param, uint32_t ret, uint32_t ret2) "ih=0x%x \"%s\"(0x%x) => 0x%x 0x%x"
+vof_getprop(uint32_t ph, const char *prop, uint32_t ret, const char *val) "ph=0x%x \"%s\" => len=%d [%s]"
+vof_getproplen(uint32_t ph, const char *prop, uint32_t ret) "ph=0x%x \"%s\" => len=%d"
+vof_setprop(uint32_t ph, const char *prop, const char *val, uint32_t vallen, uint32_t ret) "ph=0x%x \"%s\" [%s] len=%d => ret=%d"
+vof_open(const char *path, uint32_t ph, uint32_t ih) "%s ph=0x%x => ih=0x%x"
+vof_interpret(const char *cmd, uint32_t param1, uint32_t param2, uint32_t ret, uint32_t ret2) "[%s] 0x%x 0x%x => 0x%x 0x%x"
+vof_package_to_path(uint32_t ph, const char *tmp, uint32_t ret) "ph=0x%x => %s len=%d"
+vof_instance_to_path(uint32_t ih, uint32_t ph, const char *tmp, uint32_t ret) "ih=0x%x ph=0x%x => %s len=%d"
+vof_instance_to_package(uint32_t ih, uint32_t ph) "ih=0x%x => ph=0x%x"
+vof_write(uint32_t ih, unsigned cb, const char *msg) "ih=0x%x [%u] \"%s\""
+vof_avail(uint64_t start, uint64_t end, uint64_t size) "0x%"PRIx64"..0x%"PRIx64" size=0x%"PRIx64
+vof_claimed(uint64_t start, uint64_t end, uint64_t size) "0x%"PRIx64"..0x%"PRIx64" size=0x%"PRIx64
+
 # ppc.c
 ppc_tb_adjust(uint64_t offs1, uint64_t offs2, int64_t diff, int64_t seconds) "adjusted from 0x%"PRIx64" to 0x%"PRIx64", diff %"PRId64" (%"PRId64"s)"

@@ -12,6 +12,7 @@
 #include "hw/ppc/spapr_xive.h"  /* For SpaprXive */
 #include "hw/ppc/xics.h"        /* For ICSState */
 #include "hw/ppc/spapr_tpm_proxy.h"
+#include "hw/ppc/vof.h"

 struct SpaprVioBus;
 struct SpaprPhbState;
@@ -74,8 +75,10 @@ typedef enum {
 #define SPAPR_CAP_CCF_ASSIST            0x09
 /* Implements PAPR FWNMI option */
 #define SPAPR_CAP_FWNMI                 0x0A
+/* Support H_RPT_INVALIDATE */
+#define SPAPR_CAP_RPT_INVALIDATE        0x0B
 /* Num Caps */
-#define SPAPR_CAP_NUM                   (SPAPR_CAP_FWNMI + 1)
+#define SPAPR_CAP_NUM                   (SPAPR_CAP_RPT_INVALIDATE + 1)

 /*
 * Capability Values
@@ -180,6 +183,7 @@ struct SpaprMachineState {
    uint64_t kernel_addr;
    uint32_t initrd_base;
    long initrd_size;
+    Vof *vof;
    uint64_t rtc_offset; /* Now used only during incoming migration */
    struct PPCTimebase tb;
    bool has_graphics;
@@ -398,10 +402,13 @@ struct SpaprMachineState {
 #define H_CPU_CHAR_THR_RECONF_TRIG              PPC_BIT(6)
 #define H_CPU_CHAR_CACHE_COUNT_DIS              PPC_BIT(7)
 #define H_CPU_CHAR_BCCTR_FLUSH_ASSIST           PPC_BIT(9)
+
 #define H_CPU_BEHAV_FAVOUR_SECURITY             PPC_BIT(0)
 #define H_CPU_BEHAV_L1D_FLUSH_PR                PPC_BIT(1)
 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR           PPC_BIT(2)
 #define H_CPU_BEHAV_FLUSH_COUNT_CACHE           PPC_BIT(5)
+#define H_CPU_BEHAV_NO_L1D_FLUSH_ENTRY          PPC_BIT(7)
+#define H_CPU_BEHAV_NO_L1D_FLUSH_UACCESS        PPC_BIT(8)

 /* Each control block has to be on a 4K boundary */
 #define H_CB_ALIGNMENT     4096
@@ -542,8 +549,9 @@ struct SpaprMachineState {
 #define H_SCM_UNBIND_MEM        0x3F0
 #define H_SCM_UNBIND_ALL        0x3FC
 #define H_SCM_HEALTH            0x400
+#define H_RPT_INVALIDATE        0x448

-#define MAX_HCALL_OPCODE        H_SCM_HEALTH
+#define MAX_HCALL_OPCODE        H_RPT_INVALIDATE

 /* The hcalls above are standardized in PAPR and implemented by pHyp
 * as well.
@@ -558,7 +566,9 @@ struct SpaprMachineState {
 /* Client Architecture support */
 #define KVMPPC_H_CAS            (KVMPPC_HCALL_BASE + 0x2)
 #define KVMPPC_H_UPDATE_DT      (KVMPPC_HCALL_BASE + 0x3)
-#define KVMPPC_HCALL_MAX        KVMPPC_H_UPDATE_DT
+/* 0x4 was used for KVMPPC_H_UPDATE_PHANDLE in SLOF */
+#define KVMPPC_H_VOF_CLIENT     (KVMPPC_HCALL_BASE + 0x5)
+#define KVMPPC_HCALL_MAX        KVMPPC_H_VOF_CLIENT

 /*
 * The hcall range 0xEF00 to 0xEF80 is reserved for use in facilitating
@@ -770,7 +780,7 @@ void spapr_load_rtas(SpaprMachineState *spapr, void *fdt, hwaddr addr);
 #define SPAPR_IS_PCI_LIOBN(liobn)   (!!((liobn) & 0x80000000))
 #define SPAPR_PCI_DMA_WINDOW_NUM(liobn) ((liobn) & 0xff)

-#define RTAS_SIZE               2048
+#define RTAS_MIN_SIZE           20 /* hv_rtas_size in SLOF */
 #define RTAS_ERROR_LOG_MAX      2048

 /* Offset from rtas-base where error log is placed */
@@ -932,6 +942,7 @@ extern const VMStateDescription vmstate_spapr_cap_nested_kvm_hv;
 extern const VMStateDescription vmstate_spapr_cap_large_decr;
 extern const VMStateDescription vmstate_spapr_cap_ccf_assist;
 extern const VMStateDescription vmstate_spapr_cap_fwnmi;
+extern const VMStateDescription vmstate_spapr_cap_rpt_invalidate;

 static inline uint8_t spapr_get_cap(SpaprMachineState *spapr, int cap)
 {
@@ -956,4 +967,16 @@ bool spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,
 void spapr_set_all_lpcrs(target_ulong value, target_ulong mask);
 hwaddr spapr_get_rtas_addr(void);
 bool spapr_memory_hot_unplug_supported(SpaprMachineState *spapr);
+
+void spapr_vof_reset(SpaprMachineState *spapr, void *fdt, Error **errp);
+void spapr_vof_quiesce(MachineState *ms);
+bool spapr_vof_setprop(MachineState *ms, const char *path, const char *propname,
+                       void *val, int vallen);
+target_ulong spapr_h_vof_client(PowerPCCPU *cpu, SpaprMachineState *spapr,
+                                target_ulong opcode, target_ulong *args);
+target_ulong spapr_vof_client_architecture_support(MachineState *ms,
+                                                   CPUState *cs,
+                                                   target_ulong ovec_addr);
+void spapr_vof_client_dt_finalize(SpaprMachineState *spapr, void *fdt);
+
 #endif /* HW_SPAPR_H */
@@ -0,0 +1,58 @@
+/*
+ * Virtual Open Firmware
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#ifndef HW_VOF_H
+#define HW_VOF_H
+
+typedef struct Vof {
+    uint64_t top_addr; /* copied from rma_size */
+    GArray *claimed; /* array of SpaprOfClaimed */
+    uint64_t claimed_base;
+    GHashTable *of_instances; /* ihandle -> SpaprOfInstance */
+    uint32_t of_instance_last;
+    char *bootargs;
+    long fw_size;
+} Vof;
+
+int vof_client_call(MachineState *ms, Vof *vof, void *fdt,
+                    target_ulong args_real);
+uint64_t vof_claim(Vof *vof, uint64_t virt, uint64_t size, uint64_t align);
+void vof_init(Vof *vof, uint64_t top_addr, Error **errp);
+void vof_cleanup(Vof *vof);
+void vof_build_dt(void *fdt, Vof *vof);
+uint32_t vof_client_open_store(void *fdt, Vof *vof, const char *nodename,
+                               const char *prop, const char *path);
+
+#define TYPE_VOF_MACHINE_IF "vof-machine-if"
+
+typedef struct VofMachineIfClass VofMachineIfClass;
+DECLARE_CLASS_CHECKERS(VofMachineIfClass, VOF_MACHINE, TYPE_VOF_MACHINE_IF)
+
+struct VofMachineIfClass {
+    InterfaceClass parent;
+    target_ulong (*client_architecture_support)(MachineState *ms, CPUState *cs,
+                                                target_ulong vec);
+    void (*quiesce)(MachineState *ms);
+    bool (*setprop)(MachineState *ms, const char *path, const char *propname,
+                    void *val, int vallen);
+};
+
+/*
+ * Initial stack size is from
+ * https://www.devicetree.org/open-firmware/bindings/ppc/release/ppc-2_1.html#REF27292
+ *
+ * "Client programs shall be invoked with a valid stack pointer (r1) with
+ * at least 32K bytes of memory available for stack growth".
+ */
+#define VOF_STACK_SIZE       0x8000
+
+#define VOF_MEM_READ(pa, buf, size) \
+    address_space_read(&address_space_memory, \
+    (pa), MEMTXATTRS_UNSPECIFIED, (buf), (size))
+#define VOF_MEM_WRITE(pa, buf, size) \
+    address_space_write(&address_space_memory, \
+    (pa), MEMTXATTRS_UNSPECIFIED, (buf), (size))
+
+#endif /* HW_VOF_H */
@@ -33,6 +33,8 @@
 #define KVM_FEATURE_PV_SCHED_YIELD	13
 #define KVM_FEATURE_ASYNC_PF_INT	14
 #define KVM_FEATURE_MSI_EXT_DEST_ID	15
+#define KVM_FEATURE_HC_MAP_GPA_RANGE	16
+#define KVM_FEATURE_MIGRATION_CONTROL	17

 #define KVM_HINTS_REALTIME      0

@@ -54,6 +56,7 @@
 #define MSR_KVM_POLL_CONTROL	0x4b564d05
 #define MSR_KVM_ASYNC_PF_INT	0x4b564d06
 #define MSR_KVM_ASYNC_PF_ACK	0x4b564d07
+#define MSR_KVM_MIGRATION_CONTROL	0x4b564d08

 struct kvm_steal_time {
 	uint64_t steal;
@@ -90,6 +93,16 @@ struct kvm_clock_pairing {
 /* MSR_KVM_ASYNC_PF_INT */
 #define KVM_ASYNC_PF_VEC_MASK			GENMASK(7, 0)

+/* MSR_KVM_MIGRATION_CONTROL */
+#define KVM_MIGRATION_READY		(1 << 0)
+
+/* KVM_HC_MAP_GPA_RANGE */
+#define KVM_MAP_GPA_RANGE_PAGE_SZ_4K	0
+#define KVM_MAP_GPA_RANGE_PAGE_SZ_2M	(1 << 0)
+#define KVM_MAP_GPA_RANGE_PAGE_SZ_1G	(1 << 1)
+#define KVM_MAP_GPA_RANGE_ENC_STAT(n)	(n << 4)
+#define KVM_MAP_GPA_RANGE_ENCRYPTED	KVM_MAP_GPA_RANGE_ENC_STAT(1)
+#define KVM_MAP_GPA_RANGE_DECRYPTED	KVM_MAP_GPA_RANGE_ENC_STAT(0)

 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1
@@ -167,6 +167,13 @@ extern "C" {
 #define DRM_FORMAT_RGBA1010102	fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */
 #define DRM_FORMAT_BGRA1010102	fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */

+/* 64 bpp RGB */
+#define DRM_FORMAT_XRGB16161616	fourcc_code('X', 'R', '4', '8') /* [63:0] x:R:G:B 16:16:16:16 little endian */
+#define DRM_FORMAT_XBGR16161616	fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */
+
+#define DRM_FORMAT_ARGB16161616	fourcc_code('A', 'R', '4', '8') /* [63:0] A:R:G:B 16:16:16:16 little endian */
+#define DRM_FORMAT_ABGR16161616	fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */
+
 /*
 * Floating point 64bpp RGB
 * IEEE 754-2008 binary16 half-precision float
@@ -233,7 +233,7 @@ enum tunable_id {
 	ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
 	/*
 	 * Add your fresh new tunable attribute above and remember to update
-	 * tunable_strings[] in net/core/ethtool.c
+	 * tunable_strings[] in net/ethtool/common.c
 	 */
 	__ETHTOOL_TUNABLE_COUNT,
 };
@@ -297,7 +297,7 @@ enum phy_tunable_id {
 	ETHTOOL_PHY_EDPD,
 	/*
 	 * Add your fresh new phy tunable attribute above and remember to update
-	 * phy_tunable_strings[] in net/core/ethtool.c
+	 * phy_tunable_strings[] in net/ethtool/common.c
 	 */
 	__ETHTOOL_PHY_TUNABLE_COUNT,
 };
@@ -611,6 +611,7 @@
 #define KEY_VOICECOMMAND		0x246	/* Listening Voice Command */
 #define KEY_ASSISTANT		0x247	/* AL Context-aware desktop assistant */
 #define KEY_KBD_LAYOUT_NEXT	0x248	/* AC Next Keyboard Layout Select */
+#define KEY_EMOJI_PICKER	0x249	/* Show/hide emoji picker (HUTRR101) */

 #define KEY_BRIGHTNESS_MIN		0x250	/* Set Brightness to Minimum */
 #define KEY_BRIGHTNESS_MAX		0x251	/* Set Brightness to Maximum */
@@ -54,7 +54,7 @@
 #define VIRTIO_ID_SOUND			25 /* virtio sound */
 #define VIRTIO_ID_FS			26 /* virtio filesystem */
 #define VIRTIO_ID_PMEM			27 /* virtio pmem */
-#define VIRTIO_ID_BT			28 /* virtio bluetooth */
 #define VIRTIO_ID_MAC80211_HWSIM	29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_BT			40 /* virtio bluetooth */

 #endif /* _LINUX_VIRTIO_IDS_H */
@@ -38,6 +38,9 @@
 #include "standard-headers/linux/virtio_ids.h"
 #include "standard-headers/linux/virtio_config.h"

+/* The feature bitmap for virtio vsock */
+#define VIRTIO_VSOCK_F_SEQPACKET	1	/* SOCK_SEQPACKET supported */
+
 struct virtio_vsock_config {
 	uint64_t guest_cid;
 } QEMU_PACKED;
@@ -65,6 +68,7 @@ struct virtio_vsock_hdr {

 enum virtio_vsock_type {
 	VIRTIO_VSOCK_TYPE_STREAM = 1,
+	VIRTIO_VSOCK_TYPE_SEQPACKET = 2,
 };

 enum virtio_vsock_op {
@@ -91,4 +95,9 @@ enum virtio_vsock_shutdown {
 	VIRTIO_VSOCK_SHUTDOWN_SEND = 2,
 };

+/* VIRTIO_VSOCK_OP_RW flags values */
+enum virtio_vsock_rw {
+	VIRTIO_VSOCK_SEQ_EOR = 1,
+};
+
 #endif /* _LINUX_VIRTIO_VSOCK_H */
--- a/Show More
+++ b/Show More