Merge remote-tracking branch 'remotes/powerpc/topic/ppc-kvm' into kvm…

…-ppc-next

This merges in the 'ppc-kvm' topic branch from the powerpc tree in
order to bring in some fixes which touch both powerpc and KVM code.

Signed-off-by: Paul Mackerras <[email protected]>

arch/powerpc/include/asm/kvm_book3s_asm.h

@@ -104,6 +104,10 @@ struct kvmppc_host_state {
 	u8 napping;
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/*
+	 * hwthread_req/hwthread_state pair is used to pull sibling threads
+	 * out of guest on pre-ISAv3.0B CPUs where threads share MMU.
+	 */
 	u8 hwthread_req;
 	u8 hwthread_state;
 	u8 host_ipi;

arch/powerpc/include/asm/pgtable.h

@@ -66,16 +66,8 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_large(pmd)		0
 #endif
-pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-				   bool *is_thp, unsigned *shift);
-static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-					       bool *is_thp, unsigned *shift)
-{
-	VM_WARN(!arch_irqs_disabled(),
-		"%s called with irq enabled\n", __func__);
-	return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift);
-}
 
+/* can we use this in kvm */
 unsigned long vmalloc_to_phys(void *vmalloc_addr);
 
 void pgtable_cache_add(unsigned shift, void (*ctor)(void *));

arch/powerpc/include/asm/pte-walk.h

@@ -0,0 +1,35 @@
+#ifndef _ASM_POWERPC_PTE_WALK_H
+#define _ASM_POWERPC_PTE_WALK_H
+
+#include <linux/sched.h>
+
+/* Don't use this directly */
+extern pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
+			       bool *is_thp, unsigned *hshift);
+
+static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea,
+				    bool *is_thp, unsigned *hshift)
+{
+	VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__);
+	return __find_linux_pte(pgdir, ea, is_thp, hshift);
+}
+
+static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift)
+{
+	pgd_t *pgdir = init_mm.pgd;
+	return __find_linux_pte(pgdir, ea, NULL, hshift);
+}
+/*
+ * This is what we should always use. Any other lockless page table lookup needs
+ * careful audit against THP split.
+ */
+static inline pte_t *find_current_mm_pte(pgd_t *pgdir, unsigned long ea,
+					 bool *is_thp, unsigned *hshift)
+{
+	VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__);
+	VM_WARN(pgdir != current->mm->pgd,
+		"%s lock less page table lookup called on wrong mm\n", __func__);
+	return __find_linux_pte(pgdir, ea, is_thp, hshift);
+}
+
+#endif /* _ASM_POWERPC_PTE_WALK_H */

arch/powerpc/kernel/eeh.c

@@ -44,6 +44,7 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 #include <asm/rtas.h>
+#include <asm/pte-walk.h>
 
 
 /** Overview:
@@ -352,8 +353,7 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
 	 * worried about _PAGE_SPLITTING/collapse. Also we will not hit
 	 * page table free, because of init_mm.
 	 */
-	ptep = __find_linux_pte_or_hugepte(init_mm.pgd, token,
-					   NULL, &hugepage_shift);
+	ptep = find_init_mm_pte(token, &hugepage_shift);
 	if (!ptep)
 		return token;
 	WARN_ON(hugepage_shift);

arch/powerpc/kernel/idle_book3s.S

@@ -242,13 +242,20 @@ enter_winkle:
 /*
  * r3 - PSSCR value corresponding to the requested stop state.
  */
-power_enter_stop:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're entering idle */
+power_enter_stop_kvm_rm:
+	/*
+	 * This is currently unused because POWER9 KVM does not have to
+	 * gather secondary threads into sibling mode, but the code is
+	 * here in case that function is required.
+	 *
+	 * Tell KVM we're entering idle.
+	 */
 	li	r4,KVM_HWTHREAD_IN_IDLE
 	/* DO THIS IN REAL MODE!  See comment above. */
 	stb	r4,HSTATE_HWTHREAD_STATE(r13)
 #endif
+power_enter_stop:
 /*
  * Check if we are executing the lite variant with ESL=EC=0
  */
@@ -411,6 +418,18 @@ pnv_powersave_wakeup_mce:
 
 	b	pnv_powersave_wakeup
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+kvm_start_guest_check:
+	li	r0,KVM_HWTHREAD_IN_KERNEL
+	stb	r0,HSTATE_HWTHREAD_STATE(r13)
+	/* Order setting hwthread_state vs. testing hwthread_req */
+	sync
+	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
+	cmpwi	r0,0
+	beqlr
+	b	kvm_start_guest
+#endif
+
 /*
  * Called from reset vector for powersave wakeups.
  * cr3 - set to gt if waking up with partial/complete hypervisor state loss
@@ -435,15 +454,9 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	mr	r3,r12
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	li	r0,KVM_HWTHREAD_IN_KERNEL
-	stb	r0,HSTATE_HWTHREAD_STATE(r13)
-	/* Order setting hwthread_state vs. testing hwthread_req */
-	sync
-	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
-	cmpwi	r0,0
-	beq	1f
-	b	kvm_start_guest
-1:
+BEGIN_FTR_SECTION
+	bl	kvm_start_guest_check
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 #endif
 
 	/* Return SRR1 from power7_nap() */

arch/powerpc/kernel/io-workarounds.c

@@ -19,6 +19,8 @@
 #include <asm/pgtable.h>
 #include <asm/ppc-pci.h>
 #include <asm/io-workarounds.h>
+#include <asm/pte-walk.h>
+
 
 #define IOWA_MAX_BUS	8
 
@@ -75,8 +77,7 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 		 * We won't find huge pages here (iomem). Also can't hit
 		 * a page table free due to init_mm
 		 */
-		ptep = __find_linux_pte_or_hugepte(init_mm.pgd, vaddr,
-						   NULL, &hugepage_shift);
+		ptep = find_init_mm_pte(vaddr, &hugepage_shift);
 		if (ptep == NULL)
 			paddr = 0;
 		else {

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))

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)

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;

arch/powerpc/kvm/book3s_hv.c

@@ -2117,6 +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 */
@@ -2151,10 +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)

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;