Merge branch 'kvm-ppc-next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

KVM/PPC update for 4.14

There are various minor fixes and cleanups.  The only new feature is
that we now export information about storage key support to userspace,
so it can advertise it to the guest.

I have pulled in Michael Ellerman's topic/ppc-kvm branch from the
powerpc tree to get a couple of fixes that touch both KVM PPC code and
other PPC code.  That's why there is some arch/powerpc stuff in the
diffstat that isn't arch/powerpc/kvm.

9 files changed, 88 insertions, 35 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index b42812e014c0..7c62967d672c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,6 +37,7 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
+#include <asm/pte-walk.h>
 
 #include "trace_hv.h"
 
@@ -599,8 +600,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 * hugepage split and collapse.
 			 */
 			local_irq_save(flags);
-			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
-							 hva, NULL, NULL);
+			ptep = find_current_mm_pte(current->mm->pgd,
+						   hva, NULL, NULL);
 			if (ptep) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
 				if (__pte_write(pte))
@@ -1940,6 +1941,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
 	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
 	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
 	if (ret < 0) {
+		kfree(ctx);
 		kvm_put_kvm(kvm);
 		return ret;
 	}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index f6b3e67c5762..7d719c8aa0bb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -17,6 +17,7 @@
 #include <asm/mmu.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
 
 /*
  * Supported radix tree geometry.
@@ -359,8 +360,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		if (writing)
 			pgflags |= _PAGE_DIRTY;
 		local_irq_save(flags);
-		ptep = __find_linux_pte_or_hugepte(current->mm->pgd, hva,
-						   NULL, NULL);
+		ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL);
 		if (ptep) {
 			pte = READ_ONCE(*ptep);
 			if (pte_present(pte) &&
@@ -374,8 +374,12 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				spin_unlock(&kvm->mmu_lock);
 				return RESUME_GUEST;
 			}
-			ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable,
-							gpa, NULL, &shift);
+			/*
+			 * We are walking the secondary page table here. We can do this
+			 * without disabling irq.
+			 */
+			ptep = __find_linux_pte(kvm->arch.pgtable,
+						gpa, NULL, &shift);
 			if (ptep && pte_present(*ptep)) {
 				kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
 							gpa, shift);
@@ -427,8 +431,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			pgflags |= _PAGE_WRITE;
 		} else {
 			local_irq_save(flags);
-			ptep = __find_linux_pte_or_hugepte(current->mm->pgd,
-							hva, NULL, NULL);
+			ptep = find_current_mm_pte(current->mm->pgd,
+						   hva, NULL, NULL);
 			if (ptep && pte_write(*ptep) && pte_dirty(*ptep))
 				pgflags |= _PAGE_WRITE;
 			local_irq_restore(flags);
@@ -499,8 +503,7 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned int shift;
 	unsigned long old;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep)) {
 		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0,
 					      gpa, shift);
@@ -525,8 +528,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned int shift;
 	int ref = 0;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
 		kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
 					gpa, shift);
@@ -545,8 +547,7 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned int shift;
 	int ref = 0;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep))
 		ref = 1;
 	return ref;
@@ -562,8 +563,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
 	unsigned int shift;
 	int ret = 0;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
 		ret = 1;
 		if (shift)
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 3adfd2f5301c..c32e9bfe75b1 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -39,6 +39,7 @@
 #include <asm/udbg.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
+#include <asm/pte-walk.h>
 
 #ifdef CONFIG_BUG
 
@@ -353,7 +354,16 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
 	pte_t *ptep, pte;
 	unsigned shift = 0;
 
-	ptep = __find_linux_pte_or_hugepte(vcpu->arch.pgdir, ua, NULL, &shift);
+	/*
+	 * Called in real mode with MSR_EE = 0. We are safe here.
+	 * It is ok to do the lookup with arch.pgdir here, because
+	 * we are doing this on secondary cpus and current task there
+	 * is not the hypervisor. Also this is safe against THP in the
+	 * host, because an IPI to primary thread will wait for the secondary
+	 * to exit which will agains result in the below page table walk
+	 * to finish.
+	 */
+	ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift);
 	if (!ptep || !pte_present(*ptep))
 		return -ENXIO;
 	pte = *ptep;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 359c79cdf0cc..18e974a34fce 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -485,7 +485,13 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 
 	switch (subfunc) {
 	case H_VPA_REG_VPA:		/* register VPA */
-		if (len < sizeof(struct lppaca))
+		/*
+		 * The size of our lppaca is 1kB because of the way we align
+		 * it for the guest to avoid crossing a 4kB boundary. We only
+		 * use 640 bytes of the structure though, so we should accept
+		 * clients that set a size of 640.
+		 */
+		if (len < 640)
 			break;
 		vpap = &tvcpu->arch.vpa;
 		err = 0;
@@ -2111,6 +2117,15 @@ static int kvmppc_grab_hwthread(int cpu)
 	struct paca_struct *tpaca;
 	long timeout = 10000;
 
+	/*
+	 * ISA v3.0 idle routines do not set hwthread_state or test
+	 * hwthread_req, so they can not grab idle threads.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		WARN(1, "KVM: can not control sibling threads\n");
+		return -EBUSY;
+	}
+
 	tpaca = &paca[cpu];
 
 	/* Ensure the thread won't go into the kernel if it wakes */
@@ -2145,10 +2160,12 @@ static void kvmppc_release_hwthread(int cpu)
 	struct paca_struct *tpaca;
 
 	tpaca = &paca[cpu];
-	tpaca->kvm_hstate.hwthread_req = 0;
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
 	tpaca->kvm_hstate.kvm_vcore = NULL;
 	tpaca->kvm_hstate.kvm_split_mode = NULL;
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		tpaca->kvm_hstate.hwthread_req = 0;
+
 }
 
 static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
@@ -3325,6 +3342,14 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
 	if (radix_enabled())
 		return -EINVAL;
 
+	/*
+	 * POWER7, POWER8 and POWER9 all support 32 storage keys for data.
+	 * POWER7 doesn't support keys for instruction accesses,
+	 * POWER8 and POWER9 do.
+	 */
+	info->data_keys = 32;
+	info->instr_keys = cpu_has_feature(CPU_FTR_ARCH_207S) ? 32 : 0;
+
 	info->flags = KVM_PPC_PAGE_SIZES_REAL;
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		info->flags |= KVM_PPC_1T_SEGMENTS;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 584c74c8119f..4efe364f1188 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -22,6 +22,7 @@
 #include <asm/hvcall.h>
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
+#include <asm/pte-walk.h>
 
 /* Translate address of a vmalloc'd thing to a linear map address */
 static void *real_vmalloc_addr(void *x)
@@ -31,9 +32,9 @@ static void *real_vmalloc_addr(void *x)
 	/*
 	 * assume we don't have huge pages in vmalloc space...
 	 * So don't worry about THP collapse/split. Called
-	 * Only in realmode, hence won't need irq_save/restore.
+	 * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore.
 	 */
-	p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL, NULL);
+	p = find_init_mm_pte(addr, NULL);
 	if (!p || !pte_present(*p))
 		return NULL;
 	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
@@ -230,14 +231,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	 * If we had a page table table change after lookup, we would
 	 * retry via mmu_notifier_retry.
 	 */
-	if (realmode)
-		ptep = __find_linux_pte_or_hugepte(pgdir, hva, NULL,
-						   &hpage_shift);
-	else {
+	if (!realmode)
 		local_irq_save(irq_flags);
-		ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL,
-						 &hpage_shift);
-	}
+	/*
+	 * If called in real mode we have MSR_EE = 0. Otherwise
+	 * we disable irq above.
+	 */
+	ptep = __find_linux_pte(pgdir, hva, NULL, &hpage_shift);
 	if (ptep) {
 		pte_t pte;
 		unsigned int host_pte_size;
@@ -269,7 +269,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	if (!realmode)
 		local_irq_restore(irq_flags);
 
-	ptel &= ~(HPTE_R_PP0 - psize);
+	ptel &= HPTE_R_KEY | HPTE_R_PP0 | (psize-1);
 	ptel |= pa;
 
 	if (pa)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c52184a8efdf..9dd6b54a43dc 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -149,9 +149,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	subf	r4, r4, r3
 	mtspr	SPRN_DEC, r4
 
+BEGIN_FTR_SECTION
 	/* hwthread_req may have got set by cede or no vcpu, so clear it */
 	li	r0, 0
 	stb	r0, HSTATE_HWTHREAD_REQ(r13)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 
 	/*
 	 * For external interrupts we need to call the Linux
@@ -314,6 +316,7 @@ kvm_novcpu_exit:
  * Relocation is off and most register values are lost.
  * r13 points to the PACA.
  * r3 contains the SRR1 wakeup value, SRR1 is trashed.
+ * This is not used by ISAv3.0B processors.
  */
 	.globl	kvm_start_guest
 kvm_start_guest:
@@ -432,6 +435,9 @@ kvm_secondary_got_guest:
  * While waiting we also need to check if we get given a vcpu to run.
  */
 kvm_no_guest:
+BEGIN_FTR_SECTION
+	twi	31,0,0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r3, 0
 	bne	53f
@@ -976,7 +982,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 #ifdef CONFIG_KVM_XICS
 	/* We are entering the guest on that thread, push VCPU to XIVE */
 	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr0, r10, r0
+	cmpldi	cr0, r10, 0
 	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
@@ -1280,7 +1286,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
 	bne	2f
 	mfspr	r3,SPRN_HDEC
-	cmpwi	r3,0
+	EXTEND_HDEC(r3)
+	cmpdi	r3,0
 	mr	r4,r9
 	bge	fast_guest_return
 2:
@@ -2509,8 +2516,10 @@ kvm_do_nap:
 	clrrdi	r0, r0, 1
 	mtspr	SPRN_CTRLT, r0
 
+BEGIN_FTR_SECTION
 	li	r0,1
 	stb	r0,HSTATE_HWTHREAD_REQ(r13)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mfspr	r5,SPRN_LPCR
 	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
 BEGIN_FTR_SECTION
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 32fdab57d604..f9f6468f4171 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -455,16 +455,20 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
 	if (err)
 		goto free_vcpu;
 
-	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL) {
+		err = -ENOMEM;
 		goto uninit_vcpu;
+	}
 
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
 		goto uninit_id;
 
 	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
-	if (!vcpu->arch.shared)
+	if (!vcpu->arch.shared) {
+		err = -ENOMEM;
 		goto uninit_tlb;
+	}
 
 	return vcpu;
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 77fd043b3ecc..c6c734424c70 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -30,6 +30,7 @@
 #include <linux/vmalloc.h>
 #include <linux/hugetlb.h>
 #include <asm/kvm_ppc.h>
+#include <asm/pte-walk.h>
 
 #include "e500.h"
 #include "timing.h"
@@ -476,7 +477,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	 * can't run hence pfn won't change.
 	 */
 	local_irq_save(flags);
-	ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL, NULL);
+	ptep = find_linux_pte(pgdir, hva, NULL, NULL);
 	if (ptep) {
 		pte_t pte = READ_ONCE(*ptep);
 
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index f48a0c22e8f9..d0b6b5788afc 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -331,8 +331,10 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
 		goto uninit_vcpu;
 
 	vcpu->arch.shared = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-	if (!vcpu->arch.shared)
+	if (!vcpu->arch.shared) {
+		err = -ENOMEM;
 		goto uninit_tlb;
+	}
 
 	return vcpu;