/* * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206) * should be power of 2.
*/ #define HPT_ALIGN_PAGES ((1 << 18) >> PAGE_SHIFT) /* 256k */ /* * By default we reserve 5% of memory for hash pagetable allocation.
*/ staticunsignedlong kvm_cma_resv_ratio = 5;
/** * kvm_cma_reserve() - reserve area for kvm hash pagetable * * This function reserves memory from early allocator. It should be * called by arch specific code once the memblock allocator * has been activated and all other subsystems have already allocated/reserved * memory.
*/ void __init kvm_cma_reserve(void)
{ unsignedlong align_size;
phys_addr_t selected_size;
/* * We need CMA reservation only when we are in HV mode
*/ if (!cpu_has_feature(CPU_FTR_HVMODE)) return;
/* * Real-mode H_CONFER implementation. * We check if we are the only vcpu out of this virtual core * still running in the guest and not ceded. If so, we pop up * to the virtual-mode implementation; if not, just return to * the guest.
*/ longint kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target, unsignedint yield_count)
{ struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore; int ptid = local_paca->kvm_hstate.ptid; int threads_running; int threads_ceded; int threads_conferring;
u64 stop = get_tb() + 10 * tb_ticks_per_usec; int rv = H_SUCCESS; /* => don't yield */
/* * When running HV mode KVM we need to block certain operations while KVM VMs * exist in the system. We use a counter of VMs to track this. * * One of the operations we need to block is onlining of secondaries, so we * protect hv_vm_count with cpus_read_lock/unlock().
*/ static atomic_t hv_vm_count;
/* * Send an interrupt or message to another CPU. * The caller needs to include any barrier needed to order writes * to memory vs. the IPI/message.
*/ void kvmhv_rm_send_ipi(int cpu)
{ void __iomem *xics_phys; unsignedlong msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
/* On POWER9 we can use msgsnd for any destination cpu. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
msg |= get_hard_smp_processor_id(cpu);
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg)); return;
}
/* On POWER8 for IPIs to threads in the same core, use msgsnd. */ if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
cpu_first_thread_sibling(cpu) ==
cpu_first_thread_sibling(raw_smp_processor_id())) {
msg |= cpu_thread_in_core(cpu);
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg)); return;
}
/* We should never reach this */ if (WARN_ON_ONCE(xics_on_xive())) return;
/* Else poke the target with an IPI */
xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys; if (xics_phys)
__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR); else
opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
}
/* * The following functions are called from the assembly code * in book3s_hv_rmhandlers.S.
*/ staticvoid kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active)
{ int cpu = vc->pcpu;
/* Order setting of exit map vs. msgsnd/IPI */
smp_mb(); for (; active; active >>= 1, ++cpu) if (active & 1)
kvmhv_rm_send_ipi(cpu);
}
/* Set our bit in the threads-exiting-guest map in the 0xff00
bits of vcore->entry_exit_map */
me = 0x100 << ptid; do {
ee = vc->entry_exit_map;
} while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee);
/* Are we the first here? */ if ((ee >> 8) != 0) return;
/* * Trigger the other threads in this vcore to exit the guest. * If this is a hypervisor decrementer interrupt then they * will be already on their way out of the guest.
*/ if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
/* * If we are doing dynamic micro-threading, interrupt the other * subcores to pull them out of their guests too.
*/ if (!sip) return;
for (i = 0; i < MAX_SUBCORES; ++i) {
vc = sip->vc[i]; if (!vc) break; do {
ee = vc->entry_exit_map; /* Already asked to exit? */ if ((ee >> 8) != 0) break;
} while (cmpxchg(&vc->entry_exit_map, ee,
ee | VCORE_EXIT_REQ) != ee); if ((ee >> 8) == 0)
kvmhv_interrupt_vcore(vc, ee);
}
}
/* * We access the mapped array here without a lock. That * is safe because we never reduce the number of entries * in the array and we never change the v_hwirq field of * an entry once it is set. * * We have also carefully ordered the stores in the writer * and the loads here in the reader, so that if we find a matching * hwirq here, the associated GSI and irq_desc fields are valid.
*/ for (i = 0; i < pimap->n_mapped; i++) { if (xisr == pimap->mapped[i].r_hwirq) { /* * Order subsequent reads in the caller to serialize * with the writer.
*/
smp_rmb(); return &pimap->mapped[i];
}
} return NULL;
}
/* * If we have an interrupt that's not an IPI, check if we have a * passthrough adapter and if so, check if this external interrupt * is for the adapter. * We will attempt to deliver the IRQ directly to the target VCPU's * ICP, the virtual ICP (based on affinity - the xive value in ICS). * * If the delivery fails or if this is not for a passthrough adapter, * return to the host to handle this interrupt. We earlier * saved a copy of the XIRR in the PACA, it will be picked up by * the host ICP driver.
*/ staticint kvmppc_check_passthru(u32 xisr, __be32 xirr, bool *again)
{ struct kvmppc_passthru_irqmap *pimap; struct kvmppc_irq_map *irq_map; struct kvm_vcpu *vcpu;
vcpu = local_paca->kvm_hstate.kvm_vcpu; if (!vcpu) return 1;
pimap = kvmppc_get_passthru_irqmap(vcpu->kvm); if (!pimap) return 1;
irq_map = get_irqmap(pimap, xisr); if (!irq_map) return 1;
/* We're handling this interrupt, generic code doesn't need to */
local_paca->kvm_hstate.saved_xirr = 0;
/* * Determine what sort of external interrupt is pending (if any). * Returns: * 0 if no interrupt is pending * 1 if an interrupt is pending that needs to be handled by the host * 2 Passthrough that needs completion in the host * -1 if there was a guest wakeup IPI (which has now been cleared) * -2 if there is PCI passthrough external interrupt that was handled
*/ staticlong kvmppc_read_one_intr(bool *again);
long kvmppc_read_intr(void)
{ long ret = 0; long rc; bool again;
if (xive_enabled()) return 1;
do {
again = false;
rc = kvmppc_read_one_intr(&again); if (rc && (ret == 0 || rc > ret))
ret = rc;
} while (again); return ret;
}
/* see if a host IPI is pending */
host_ipi = READ_ONCE(local_paca->kvm_hstate.host_ipi); if (host_ipi) return 1;
/* Now read the interrupt from the ICP */
xics_phys = local_paca->kvm_hstate.xics_phys;
rc = 0; if (!xics_phys)
rc = opal_int_get_xirr(&xirr, false); else
xirr = __raw_rm_readl(xics_phys + XICS_XIRR); if (rc < 0) return 1;
/* * Save XIRR for later. Since we get control in reverse endian * on LE systems, save it byte reversed and fetch it back in * host endian. Note that xirr is the value read from the * XIRR register, while h_xirr is the host endian version.
*/
h_xirr = be32_to_cpu(xirr);
local_paca->kvm_hstate.saved_xirr = h_xirr;
xisr = h_xirr & 0xffffff; /* * Ensure that the store/load complete to guarantee all side * effects of loading from XIRR has completed
*/
smp_mb();
/* if nothing pending in the ICP */ if (!xisr) return 0;
/* We found something in the ICP... * * If it is an IPI, clear the MFRR and EOI it.
*/ if (xisr == XICS_IPI) {
rc = 0; if (xics_phys) {
__raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
__raw_rm_writel(xirr, xics_phys + XICS_XIRR);
} else {
opal_int_set_mfrr(hard_smp_processor_id(), 0xff);
rc = opal_int_eoi(h_xirr);
} /* If rc > 0, there is another interrupt pending */
*again = rc > 0;
/* * Need to ensure side effects of above stores * complete before proceeding.
*/
smp_mb();
/* * We need to re-check host IPI now in case it got set in the * meantime. If it's clear, we bounce the interrupt to the * guest
*/
host_ipi = READ_ONCE(local_paca->kvm_hstate.host_ipi); if (unlikely(host_ipi != 0)) { /* We raced with the host, * we need to resend that IPI, bummer
*/ if (xics_phys)
__raw_rm_writeb(IPI_PRIORITY,
xics_phys + XICS_MFRR); else
opal_int_set_mfrr(hard_smp_processor_id(),
IPI_PRIORITY); /* Let side effects complete */
smp_mb(); return 1;
}
/* OK, it's an IPI for us */
local_paca->kvm_hstate.saved_xirr = 0; return -1;
}
void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
{ /* Guest must always run with ME enabled, HV disabled. */
msr = (msr | MSR_ME) & ~MSR_HV;
/* * Check for illegal transactional state bit combination * and if we find it, force the TS field to a safe state.
*/ if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
msr &= ~MSR_TS_MASK;
__kvmppc_set_msr_hv(vcpu, msr);
kvmppc_end_cede(vcpu);
}
EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv);
/* If transactional, change to suspend mode on IRQ delivery */ if (MSR_TM_TRANSACTIONAL(msr))
new_msr |= MSR_TS_S; else
new_msr |= msr & MSR_TS_MASK;
/* * Perform MSR and PC adjustment for LPCR[AIL]=3 if it is set and * applicable. AIL=2 is not supported. * * AIL does not apply to SRESET, MCE, or HMI (which is never * delivered to the guest), and does not apply if IR=0 or DR=0.
*/ if (vec != BOOK3S_INTERRUPT_SYSTEM_RESET &&
vec != BOOK3S_INTERRUPT_MACHINE_CHECK &&
(vcpu->arch.vcore->lpcr & LPCR_AIL) == LPCR_AIL_3 &&
(msr & (MSR_IR|MSR_DR)) == (MSR_IR|MSR_DR) ) {
new_msr |= MSR_IR | MSR_DR;
new_pc += 0xC000000000004000ULL;
}
/* * Is there a PRIV_DOORBELL pending for the guest (on POWER9)? * Can we inject a Decrementer or a External interrupt?
*/ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
{ int ext; unsignedlong lpcr;
WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300));
/* Insert EXTERNAL bit into LPCR at the MER bit position */
ext = (vcpu->arch.pending_exceptions >> BOOK3S_IRQPRIO_EXTERNAL) & 1;
lpcr = mfspr(SPRN_LPCR);
lpcr |= ext << LPCR_MER_SH;
mtspr(SPRN_LPCR, lpcr);
isync();
if (vcpu->arch.shregs.msr & MSR_EE) { if (ext) {
inject_interrupt(vcpu, BOOK3S_INTERRUPT_EXTERNAL, 0);
} else { longint dec = mfspr(SPRN_DEC); if (!(lpcr & LPCR_LD))
dec = (int) dec; if (dec < 0)
inject_interrupt(vcpu,
BOOK3S_INTERRUPT_DECREMENTER, 0);
}
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.