4 files changed, 46 insertions, 11 deletions
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index 01b8a13f0..391933296 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -26,7 +26,7 @@ extern u64 pnv_first_deep_stop_state;
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmp	cr0,r0,r0;					\
+1:	cmpd	cr0,r0,r0;					\
 	bne	1b;						\
 	IDLE_INST;						\
 	b	.
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index f6f68f73e..99e1397b7 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -52,11 +52,23 @@ static inline int mm_is_core_local(struct mm_struct *mm)
 	return cpumask_subset(mm_cpumask(mm),
 			      topology_sibling_cpumask(smp_processor_id()));
 }
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+	return cpumask_equal(mm_cpumask(mm),
+			      cpumask_of(smp_processor_id()));
+}
+
 #else
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
 	return 1;
 }
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+	return 1;
+}
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index bd739fed2..72dac0b58 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -90,6 +90,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
  * Threads will spin in HMT_LOW until the lock bit is cleared.
  * r14 - pointer to core_idle_state
  * r15 - used to load contents of core_idle_state
+ * r9  - used as a temporary variable
  */
 
 core_idle_lock_held:
@@ -99,6 +100,8 @@ core_idle_lock_held:
 	bne	3b
 	HMT_MEDIUM
 	lwarx	r15,0,r14
+	andi.	r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bne	core_idle_lock_held
 	blr
 
 /*
@@ -163,12 +166,6 @@ _GLOBAL(pnv_powersave_common)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're entering idle */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-
 	/*
 	 * Go to real mode to do the nap, as required by the architecture.
 	 * Also, we need to be in real mode before setting hwthread_state,
@@ -185,6 +182,26 @@ _GLOBAL(pnv_powersave_common)
 
 	.globl pnv_enter_arch207_idle_mode
 pnv_enter_arch207_idle_mode:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle */
+	li	r4,KVM_HWTHREAD_IN_IDLE
+	/******************************************************/
+	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
+	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
+	/* MUST occur in real mode, i.e. with the MMU off,    */
+	/* and the MMU must stay off until we clear this flag */
+	/* and test HSTATE_HWTHREAD_REQ(r13) in the system    */
+	/* reset interrupt vector in exceptions-64s.S.        */
+	/* The reason is that another thread can switch the   */
+	/* MMU to a guest context whenever this flag is set   */
+	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
+	/* that would potentially cause this thread to start  */
+	/* executing instructions from guest memory in        */
+	/* hypervisor mode, leading to a host crash or data   */
+	/* corruption, or worse.                              */
+	/******************************************************/
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
 	stb	r3,PACA_THREAD_IDLE_STATE(r13)
 	cmpwi	cr3,r3,PNV_THREAD_SLEEP
 	bge	cr3,2f
@@ -250,6 +267,12 @@ enter_winkle:
  * r3 - requested stop state
  */
 power_enter_stop:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* 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
 /*
  * Check if the requested state is a deep idle state.
  */
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 48df05ef5..d69606819 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -175,7 +175,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto no_context;
 
-	if (!mm_is_core_local(mm)) {
+	if (!mm_is_thread_local(mm)) {
 		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
@@ -201,7 +201,7 @@ void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto no_context;
 
-	if (!mm_is_core_local(mm)) {
+	if (!mm_is_thread_local(mm)) {
 		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
@@ -226,7 +226,7 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 	pid = mm ? mm->context.id : 0;
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto bail;
-	if (!mm_is_core_local(mm)) {
+	if (!mm_is_thread_local(mm)) {
 		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
@@ -321,7 +321,7 @@ void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
 {
 	unsigned long pid;
 	unsigned long addr;
-	int local = mm_is_core_local(mm);
+	int local = mm_is_thread_local(mm);
 	unsigned long ap = mmu_get_ap(psize);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 	unsigned long page_size = 1UL << mmu_psize_defs[psize].shift;