On Tue, Dec 11, 2018 at 11:38:18PM +0100, Cédric Le Goater wrote: > The interrupt modes supported by the hypervisor are advertised to the > guest with new bits definitions of the option vector 5 of property > "ibm,arch-vec-5-platform-support. The byte 23 bits 0-1 of the OV5 are > defined as follow : > > 0b00 PAPR 2.7 and earlier (Legacy systems) > 0b01 XIVE Exploitation mode only > 0b10 Either available > > If the client/guest selects the XIVE interrupt mode, it informs the > hypervisor by returning the value 0b01 in byte 23 bits 0-1. A 0b00 > value indicates the use of the XICS interrupt mode (Legacy systems). > > The sPAPR IRQ backend is extended with these definitions and the > values are directly used to populate the "ibm,arch-vec-5-platform-support" > property. The interrupt mode is advertised under TCG and under KVM. > Although a KVM XIVE device is not yet available, the machine can still > operate with kernel_irqchip=off. However, we apply a restriction on > the CPU which is required to be a POWER9 when a XIVE interrupt > controller is in use. > > Signed-off-by: Cédric Le Goater > --- > > Changes since v7: > > - improved commit log > - introduced a check on CPU type. > > include/hw/ppc/spapr.h | 6 ++++++ > include/hw/ppc/spapr_irq.h | 1 + > hw/ppc/spapr.c | 36 ++++++++++++++++++++++++++++++------ > hw/ppc/spapr_irq.c | 3 +++ > 4 files changed, 40 insertions(+), 6 deletions(-) > > diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h > index 6bf028a02fe2..06765b4e9d79 100644 > --- a/include/hw/ppc/spapr.h > +++ b/include/hw/ppc/spapr.h > @@ -824,5 +824,11 @@ int spapr_caps_post_migration(sPAPRMachineState *spapr); > > void spapr_check_pagesize(sPAPRMachineState *spapr, hwaddr pagesize, > Error **errp); > +/* > + * XIVE definitions > + */ > +#define SPAPR_OV5_XIVE_LEGACY 0x0 > +#define SPAPR_OV5_XIVE_EXPLOIT 0x40 > +#define SPAPR_OV5_XIVE_BOTH 0x80 /* Only to advertise on the platform */ > > #endif /* HW_SPAPR_H */ > diff --git a/include/hw/ppc/spapr_irq.h b/include/hw/ppc/spapr_irq.h > index 63061a009b4c..b34d5a00381b 100644 > --- a/include/hw/ppc/spapr_irq.h > +++ b/include/hw/ppc/spapr_irq.h > @@ -33,6 +33,7 @@ void spapr_irq_msi_reset(sPAPRMachineState *spapr); > typedef struct sPAPRIrq { > uint32_t nr_irqs; > uint32_t nr_msis; > + uint8_t ov5; > > void (*init)(sPAPRMachineState *spapr, Error **errp); > int (*claim)(sPAPRMachineState *spapr, int irq, bool lsi, Error **errp); > diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c > index 57c0066edd56..ff138f224a87 100644 > --- a/hw/ppc/spapr.c > +++ b/hw/ppc/spapr.c > @@ -1095,12 +1095,14 @@ static void spapr_dt_rtas(sPAPRMachineState *spapr, void *fdt) > spapr_dt_rtas_tokens(fdt, rtas); > } > > -/* Prepare ibm,arch-vec-5-platform-support, which indicates the MMU features > - * that the guest may request and thus the valid values for bytes 24..26 of > - * option vector 5: */ > -static void spapr_dt_ov5_platform_support(void *fdt, int chosen) > +/* Prepare ibm,arch-vec-5-platform-support, which indicates the MMU > + * and the XIVE features that the guest may request and thus the valid > + * values for bytes 23..26 of option vector 5: */ > +static void spapr_dt_ov5_platform_support(sPAPRMachineState *spapr, void *fdt, > + int chosen) > { > PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu); > + sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); > > char val[2 * 4] = { > 23, 0x00, /* Xive mode, filled in below. */ > @@ -1111,9 +1113,17 @@ static void spapr_dt_ov5_platform_support(void *fdt, int chosen) > > if (!ppc_check_compat(first_ppc_cpu, CPU_POWERPC_LOGICAL_3_00, 0, > first_ppc_cpu->compat_pvr)) { > - /* If we're in a pre POWER9 compat mode then the guest should do hash */ > + /* If we're in a pre POWER9 compat mode then the guest should do hash > + * and use the legacy interrupt mode > + */ > + val[1] = 0x00; /* XICS */ > val[3] = 0x00; /* Hash */ > } else if (kvm_enabled()) { > + /* If the KVM XIVE device is not available, the machine can > + * still operate with kernel_irqchip=off > + */ > + val[1] = smc->irq->ov5; I know it means another layer of if, but I'd prefer to rearrange this so setting the intc value is outside the if (kvm_enabled()).. > + > if (kvmppc_has_cap_mmu_radix() && kvmppc_has_cap_mmu_hash_v3()) { > val[3] = 0x80; /* OV5_MMU_BOTH */ > } else if (kvmppc_has_cap_mmu_radix()) { > @@ -1122,6 +1132,9 @@ static void spapr_dt_ov5_platform_support(void *fdt, int chosen) > val[3] = 0x00; /* Hash */ > } > } else { > + /* In TCG, the interrupt mode is defined by the pseries machine */ > + val[1] = smc->irq->ov5; ..rather than duplicated in each branch. > + > /* V3 MMU supports both hash and radix in tcg (with dynamic switching) */ > val[3] = 0xC0; > } > @@ -1189,7 +1202,7 @@ static void spapr_dt_chosen(sPAPRMachineState *spapr, void *fdt) > _FDT(fdt_setprop_string(fdt, chosen, "stdout-path", stdout_path)); > } > > - spapr_dt_ov5_platform_support(fdt, chosen); > + spapr_dt_ov5_platform_support(spapr, fdt, chosen); > > g_free(stdout_path); > g_free(bootlist); > @@ -2622,6 +2635,17 @@ static void spapr_machine_init(MachineState *machine) > /* advertise support for ibm,dyamic-memory-v2 */ > spapr_ovec_set(spapr->ov5, OV5_DRMEM_V2); > > + /* advertise XIVE on POWER9 machines */ > + if (smc->irq->ov5 & SPAPR_OV5_XIVE_EXPLOIT) { > + if (ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, > + 0, spapr->max_compat_pvr)) { > + spapr_ovec_set(spapr->ov5, OV5_XIVE_EXPLOIT); > + } else { > + error_report("XIVE-only machines require a POWER9 CPU"); > + exit(1); > + } > + } > + > /* init CPUs */ > spapr_init_cpus(spapr); > > diff --git a/hw/ppc/spapr_irq.c b/hw/ppc/spapr_irq.c > index f835ea939cbf..79f06308995b 100644 > --- a/hw/ppc/spapr_irq.c > +++ b/hw/ppc/spapr_irq.c > @@ -216,6 +216,7 @@ static int spapr_irq_post_load_xics(sPAPRMachineState *spapr, int version_id) > sPAPRIrq spapr_irq_xics = { > .nr_irqs = SPAPR_IRQ_XICS_NR_IRQS, > .nr_msis = SPAPR_IRQ_XICS_NR_MSIS, > + .ov5 = SPAPR_OV5_XIVE_LEGACY, > > .init = spapr_irq_init_xics, > .claim = spapr_irq_claim_xics, > @@ -342,6 +343,7 @@ static void spapr_irq_reset_xive(sPAPRMachineState *spapr, Error **errp) > sPAPRIrq spapr_irq_xive = { > .nr_irqs = SPAPR_IRQ_XIVE_NR_IRQS, > .nr_msis = SPAPR_IRQ_XIVE_NR_MSIS, > + .ov5 = SPAPR_OV5_XIVE_EXPLOIT, > > .init = spapr_irq_init_xive, > .claim = spapr_irq_claim_xive, > @@ -466,6 +468,7 @@ int spapr_irq_find(sPAPRMachineState *spapr, int num, bool align, Error **errp) > sPAPRIrq spapr_irq_xics_legacy = { > .nr_irqs = SPAPR_IRQ_XICS_LEGACY_NR_IRQS, > .nr_msis = SPAPR_IRQ_XICS_LEGACY_NR_IRQS, > + .ov5 = SPAPR_OV5_XIVE_LEGACY, > > .init = spapr_irq_init_xics, > .claim = spapr_irq_claim_xics, -- David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson