1 files changed, 44 insertions, 333 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 7cd3cf3d366b..fa0e3a22cac0 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -15,11 +15,11 @@
 #include <linux/cma.h>
 #include <linux/bitops.h>
 
-#include <asm/asm-prototypes.h>
 #include <asm/cputable.h>
+#include <asm/interrupt.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
-#include <asm/archrandom.h>
+#include <asm/machdep.h>
 #include <asm/xics.h>
 #include <asm/xive.h>
 #include <asm/dbell.h>
@@ -32,21 +32,7 @@
 
 #include "book3s_xics.h"
 #include "book3s_xive.h"
-
-/*
- * The XIVE module will populate these when it loads
- */
-unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
-unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
-int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
-		       unsigned long mfrr);
-int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
-int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
-EXPORT_SYMBOL_GPL(__xive_vm_h_xirr);
-EXPORT_SYMBOL_GPL(__xive_vm_h_ipoll);
-EXPORT_SYMBOL_GPL(__xive_vm_h_ipi);
-EXPORT_SYMBOL_GPL(__xive_vm_h_cppr);
-EXPORT_SYMBOL_GPL(__xive_vm_h_eoi);
+#include "book3s_hv.h"
 
 /*
  * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
@@ -95,25 +81,17 @@ EXPORT_SYMBOL_GPL(kvm_free_hpt_cma);
 void __init kvm_cma_reserve(void)
 {
 	unsigned long align_size;
-	struct memblock_region *reg;
-	phys_addr_t selected_size = 0;
+	phys_addr_t selected_size;
 
 	/*
 	 * We need CMA reservation only when we are in HV mode
 	 */
 	if (!cpu_has_feature(CPU_FTR_HVMODE))
 		return;
-	/*
-	 * We cannot use memblock_phys_mem_size() here, because
-	 * memblock_analyze() has not been called yet.
-	 */
-	for_each_memblock(memory, reg)
-		selected_size += memblock_region_memory_end_pfn(reg) -
-				 memblock_region_memory_base_pfn(reg);
 
-	selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT;
+	selected_size = PAGE_ALIGN(memblock_phys_mem_size() * kvm_cma_resv_ratio / 100);
 	if (selected_size) {
-		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+		pr_info("%s: reserving %ld MiB for global area\n", __func__,
 			 (unsigned long)selected_size / SZ_1M);
 		align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
 		cma_declare_contiguous(0, selected_size, 0, align_size,
@@ -159,23 +137,23 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
  * 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 get/put_online_cpus().
+ * protect hv_vm_count with cpus_read_lock/unlock().
  */
 static atomic_t hv_vm_count;
 
 void kvm_hv_vm_activated(void)
 {
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_inc(&hv_vm_count);
-	put_online_cpus();
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(kvm_hv_vm_activated);
 
 void kvm_hv_vm_deactivated(void)
 {
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_dec(&hv_vm_count);
-	put_online_cpus();
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated);
 
@@ -199,21 +177,19 @@ EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode);
 
 int kvmppc_hwrng_present(void)
 {
-	return powernv_hwrng_present();
+	return ppc_md.get_random_seed != NULL;
 }
 EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
 
-long kvmppc_h_random(struct kvm_vcpu *vcpu)
+long kvmppc_rm_h_random(struct kvm_vcpu *vcpu)
 {
-	int r;
+	unsigned long rand;
 
-	/* Only need to do the expensive mfmsr() on radix */
-	if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
-		r = powernv_get_random_long(&vcpu->arch.regs.gpr[4]);
-	else
-		r = powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]);
-	if (r)
+	if (ppc_md.get_random_seed &&
+	    ppc_md.get_random_seed(&rand)) {
+		kvmppc_set_gpr(vcpu, 4, rand);
 		return H_SUCCESS;
+	}
 
 	return H_HARDWARE;
 }
@@ -228,15 +204,6 @@ void kvmhv_rm_send_ipi(int cpu)
 	void __iomem *xics_phys;
 	unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 
-	/* For a nested hypervisor, use the XICS via hcall */
-	if (kvmhv_on_pseries()) {
-		unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-		plpar_hcall_raw(H_IPI, retbuf, get_hard_smp_processor_id(cpu),
-				IPI_PRIORITY);
-		return;
-	}
-
 	/* 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);
@@ -285,8 +252,7 @@ void kvmhv_commence_exit(int trap)
 	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
 	int ptid = local_paca->kvm_hstate.ptid;
 	struct kvm_split_mode *sip = local_paca->kvm_hstate.kvm_split_mode;
-	int me, ee, i, t;
-	int cpu0;
+	int me, ee, i;
 
 	/* Set our bit in the threads-exiting-guest map in the 0xff00
 	   bits of vcore->entry_exit_map */
@@ -328,22 +294,6 @@ void kvmhv_commence_exit(int trap)
 		if ((ee >> 8) == 0)
 			kvmhv_interrupt_vcore(vc, ee);
 	}
-
-	/*
-	 * On POWER9 when running a HPT guest on a radix host (sip != NULL),
-	 * we have to interrupt inactive CPU threads to get them to
-	 * restore the host LPCR value.
-	 */
-	if (sip->lpcr_req) {
-		if (cmpxchg(&sip->do_restore, 0, 1) == 0) {
-			vc = local_paca->kvm_hstate.kvm_vcore;
-			cpu0 = vc->pcpu + ptid - local_paca->kvm_hstate.tid;
-			for (t = 1; t < threads_per_core; ++t) {
-				if (sip->napped[t])
-					kvmhv_rm_send_ipi(cpu0 + t);
-			}
-		}
-	}
 }
 
 struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv;
@@ -461,24 +411,17 @@ static long kvmppc_read_one_intr(bool *again)
 		return 1;
 
 	/* see if a host IPI is pending */
-	host_ipi = local_paca->kvm_hstate.host_ipi;
+	host_ipi = READ_ONCE(local_paca->kvm_hstate.host_ipi);
 	if (host_ipi)
 		return 1;
 
 	/* Now read the interrupt from the ICP */
-	if (kvmhv_on_pseries()) {
-		unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-		rc = plpar_hcall_raw(H_XIRR, retbuf, 0xFF);
-		xirr = cpu_to_be32(retbuf[0]);
-	} else {
-		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);
-	}
+	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;
 
@@ -507,13 +450,7 @@ static long kvmppc_read_one_intr(bool *again)
 	 */
 	if (xisr == XICS_IPI) {
 		rc = 0;
-		if (kvmhv_on_pseries()) {
-			unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-			plpar_hcall_raw(H_IPI, retbuf,
-					hard_smp_processor_id(), 0xff);
-			plpar_hcall_raw(H_EOI, retbuf, h_xirr);
-		} else if (xics_phys) {
+		if (xics_phys) {
 			__raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
 			__raw_rm_writel(xirr, xics_phys + XICS_XIRR);
 		} else {
@@ -534,18 +471,12 @@ static long kvmppc_read_one_intr(bool *again)
 		 * meantime. If it's clear, we bounce the interrupt to the
 		 * guest
 		 */
-		host_ipi = local_paca->kvm_hstate.host_ipi;
+		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 (kvmhv_on_pseries()) {
-				unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-				plpar_hcall_raw(H_IPI, retbuf,
-						hard_smp_processor_id(),
-						IPI_PRIORITY);
-			} else if (xics_phys)
+			if (xics_phys)
 				__raw_rm_writeb(IPI_PRIORITY,
 						xics_phys + XICS_MFRR);
 			else
@@ -564,197 +495,6 @@ static long kvmppc_read_one_intr(bool *again)
 	return kvmppc_check_passthru(xisr, xirr, again);
 }
 
-#ifdef CONFIG_KVM_XICS
-static inline bool is_rm(void)
-{
-	return !(mfmsr() & MSR_DR);
-}
-
-unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive()) {
-		if (is_rm())
-			return xive_rm_h_xirr(vcpu);
-		if (unlikely(!__xive_vm_h_xirr))
-			return H_NOT_AVAILABLE;
-		return __xive_vm_h_xirr(vcpu);
-	} else
-		return xics_rm_h_xirr(vcpu);
-}
-
-unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	vcpu->arch.regs.gpr[5] = get_tb();
-	if (xics_on_xive()) {
-		if (is_rm())
-			return xive_rm_h_xirr(vcpu);
-		if (unlikely(!__xive_vm_h_xirr))
-			return H_NOT_AVAILABLE;
-		return __xive_vm_h_xirr(vcpu);
-	} else
-		return xics_rm_h_xirr(vcpu);
-}
-
-unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive()) {
-		if (is_rm())
-			return xive_rm_h_ipoll(vcpu, server);
-		if (unlikely(!__xive_vm_h_ipoll))
-			return H_NOT_AVAILABLE;
-		return __xive_vm_h_ipoll(vcpu, server);
-	} else
-		return H_TOO_HARD;
-}
-
-int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
-		    unsigned long mfrr)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive()) {
-		if (is_rm())
-			return xive_rm_h_ipi(vcpu, server, mfrr);
-		if (unlikely(!__xive_vm_h_ipi))
-			return H_NOT_AVAILABLE;
-		return __xive_vm_h_ipi(vcpu, server, mfrr);
-	} else
-		return xics_rm_h_ipi(vcpu, server, mfrr);
-}
-
-int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive()) {
-		if (is_rm())
-			return xive_rm_h_cppr(vcpu, cppr);
-		if (unlikely(!__xive_vm_h_cppr))
-			return H_NOT_AVAILABLE;
-		return __xive_vm_h_cppr(vcpu, cppr);
-	} else
-		return xics_rm_h_cppr(vcpu, cppr);
-}
-
-int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
-{
-	if (!kvmppc_xics_enabled(vcpu))
-		return H_TOO_HARD;
-	if (xics_on_xive()) {
-		if (is_rm())
-			return xive_rm_h_eoi(vcpu, xirr);
-		if (unlikely(!__xive_vm_h_eoi))
-			return H_NOT_AVAILABLE;
-		return __xive_vm_h_eoi(vcpu, xirr);
-	} else
-		return xics_rm_h_eoi(vcpu, xirr);
-}
-#endif /* CONFIG_KVM_XICS */
-
-void kvmppc_bad_interrupt(struct pt_regs *regs)
-{
-	/*
-	 * 100 could happen at any time, 200 can happen due to invalid real
-	 * address access for example (or any time due to a hardware problem).
-	 */
-	if (TRAP(regs) == 0x100) {
-		get_paca()->in_nmi++;
-		system_reset_exception(regs);
-		get_paca()->in_nmi--;
-	} else if (TRAP(regs) == 0x200) {
-		machine_check_exception(regs);
-	} else {
-		die("Bad interrupt in KVM entry/exit code", regs, SIGABRT);
-	}
-	panic("Bad KVM trap");
-}
-
-/*
- * Functions used to switch LPCR HR and UPRT bits on all threads
- * when entering and exiting HPT guests on a radix host.
- */
-
-#define PHASE_REALMODE		1	/* in real mode */
-#define PHASE_SET_LPCR		2	/* have set LPCR */
-#define PHASE_OUT_OF_GUEST	4	/* have finished executing in guest */
-#define PHASE_RESET_LPCR	8	/* have reset LPCR to host value */
-
-#define ALL(p)		(((p) << 24) | ((p) << 16) | ((p) << 8) | (p))
-
-static void wait_for_sync(struct kvm_split_mode *sip, int phase)
-{
-	int thr = local_paca->kvm_hstate.tid;
-
-	sip->lpcr_sync.phase[thr] |= phase;
-	phase = ALL(phase);
-	while ((sip->lpcr_sync.allphases & phase) != phase) {
-		HMT_low();
-		barrier();
-	}
-	HMT_medium();
-}
-
-void kvmhv_p9_set_lpcr(struct kvm_split_mode *sip)
-{
-	unsigned long rb, set;
-
-	/* wait for every other thread to get to real mode */
-	wait_for_sync(sip, PHASE_REALMODE);
-
-	/* Set LPCR and LPIDR */
-	mtspr(SPRN_LPCR, sip->lpcr_req);
-	mtspr(SPRN_LPID, sip->lpidr_req);
-	isync();
-
-	/* Invalidate the TLB on thread 0 */
-	if (local_paca->kvm_hstate.tid == 0) {
-		sip->do_set = 0;
-		asm volatile("ptesync" : : : "memory");
-		for (set = 0; set < POWER9_TLB_SETS_RADIX; ++set) {
-			rb = TLBIEL_INVAL_SET_LPID +
-				(set << TLBIEL_INVAL_SET_SHIFT);
-			asm volatile(PPC_TLBIEL(%0, %1, 0, 0, 0) : :
-				     "r" (rb), "r" (0));
-		}
-		asm volatile("ptesync" : : : "memory");
-	}
-
-	/* indicate that we have done so and wait for others */
-	wait_for_sync(sip, PHASE_SET_LPCR);
-	/* order read of sip->lpcr_sync.allphases vs. sip->do_set */
-	smp_rmb();
-}
-
-/*
- * Called when a thread that has been in the guest needs
- * to reload the host LPCR value - but only on POWER9 when
- * running a HPT guest on a radix host.
- */
-void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip)
-{
-	/* we're out of the guest... */
-	wait_for_sync(sip, PHASE_OUT_OF_GUEST);
-
-	mtspr(SPRN_LPID, 0);
-	mtspr(SPRN_LPCR, sip->host_lpcr);
-	isync();
-
-	if (local_paca->kvm_hstate.tid == 0) {
-		sip->do_restore = 0;
-		smp_wmb();	/* order store of do_restore vs. phase */
-	}
-
-	wait_for_sync(sip, PHASE_RESET_LPCR);
-	smp_mb();
-	local_paca->kvm_hstate.kvm_split_mode = NULL;
-}
-
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.ceded = 0;
@@ -766,13 +506,16 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
 
 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;
-	vcpu->arch.shregs.msr = msr;
+	__kvmppc_set_msr_hv(vcpu, msr);
 	kvmppc_end_cede(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv);
@@ -810,7 +553,7 @@ static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
 	kvmppc_set_srr0(vcpu, pc);
 	kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags);
 	kvmppc_set_pc(vcpu, new_pc);
-	vcpu->arch.shregs.msr = new_msr;
+	__kvmppc_set_msr_hv(vcpu, new_msr);
 }
 
 void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
@@ -829,6 +572,8 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
 	int ext;
 	unsigned long 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);
@@ -862,57 +607,23 @@ static void flush_guest_tlb(struct kvm *kvm)
 	unsigned long rb, set;
 
 	rb = PPC_BIT(52);	/* IS = 2 */
-	if (kvm_is_radix(kvm)) {
-		/* R=1 PRS=1 RIC=2 */
+	for (set = 0; set < kvm->arch.tlb_sets; ++set) {
+		/* R=0 PRS=0 RIC=0 */
 		asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-			     : : "r" (rb), "i" (1), "i" (1), "i" (2),
+			     : : "r" (rb), "i" (0), "i" (0), "i" (0),
 			       "r" (0) : "memory");
-		for (set = 1; set < kvm->arch.tlb_sets; ++set) {
-			rb += PPC_BIT(51);	/* increment set number */
-			/* R=1 PRS=1 RIC=0 */
-			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-				     : : "r" (rb), "i" (1), "i" (1), "i" (0),
-				       "r" (0) : "memory");
-		}
-		asm volatile("ptesync": : :"memory");
-		asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
-	} else {
-		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
-			/* R=0 PRS=0 RIC=0 */
-			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-				     : : "r" (rb), "i" (0), "i" (0), "i" (0),
-				       "r" (0) : "memory");
-			rb += PPC_BIT(51);	/* increment set number */
-		}
-		asm volatile("ptesync": : :"memory");
-		asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
+		rb += PPC_BIT(51);	/* increment set number */
 	}
+	asm volatile("ptesync": : :"memory");
 }
 
-void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
-				 struct kvm_nested_guest *nested)
+void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu)
 {
-	cpumask_t *need_tlb_flush;
-
-	/*
-	 * On POWER9, individual threads can come in here, but the
-	 * TLB is shared between the 4 threads in a core, hence
-	 * invalidating on one thread invalidates for all.
-	 * Thus we make all 4 threads use the same bit.
-	 */
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		pcpu = cpu_first_thread_sibling(pcpu);
-
-	if (nested)
-		need_tlb_flush = &nested->need_tlb_flush;
-	else
-		need_tlb_flush = &kvm->arch.need_tlb_flush;
-
-	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
+	if (cpumask_test_cpu(pcpu, &kvm->arch.need_tlb_flush)) {
 		flush_guest_tlb(kvm);
 
 		/* Clear the bit after the TLB flush */
-		cpumask_clear_cpu(pcpu, need_tlb_flush);
+		cpumask_clear_cpu(pcpu, &kvm->arch.need_tlb_flush);
 	}
 }
 EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush);