1 files changed, 202 insertions, 161 deletions

diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 4e29b619578c..9e1f6558d026 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -127,21 +127,6 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static __always_inline void __tlbie_pid_lpid(unsigned long pid,
-					     unsigned long lpid,
-					     unsigned long ric)
-{
-	unsigned long rb, rs, prs, r;
-
-	rb = PPC_BIT(53); /* IS = 1 */
-	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
-	prs = 1; /* process scoped */
-	r = 1;   /* radix format */
-
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
-}
 static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -202,23 +187,6 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
-					    unsigned long lpid,
-					    unsigned long ap, unsigned long ric)
-{
-	unsigned long rb, rs, prs, r;
-
-	rb = va & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
-	prs = 1; /* process scoped */
-	r = 1;   /* radix format */
-
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
-}
-
 static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
 					    unsigned long ap, unsigned long ric)
 {
@@ -264,22 +232,6 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
 	}
 }
 
-static inline void fixup_tlbie_va_range_lpid(unsigned long va,
-					     unsigned long pid,
-					     unsigned long lpid,
-					     unsigned long ap)
-{
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
-	}
-
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
-	}
-}
-
 static inline void fixup_tlbie_pid(unsigned long pid)
 {
 	/*
@@ -299,26 +251,6 @@ static inline void fixup_tlbie_pid(unsigned long pid)
 	}
 }
 
-static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
-{
-	/*
-	 * We can use any address for the invalidation, pick one which is
-	 * probably unused as an optimisation.
-	 */
-	unsigned long va = ((1UL << 52) - 1);
-
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
-	}
-
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
-				RIC_FLUSH_TLB);
-	}
-}
-
 static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
 				       unsigned long ap)
 {
@@ -416,31 +348,6 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
-				   unsigned long ric)
-{
-	asm volatile("ptesync" : : : "memory");
-
-	/*
-	 * Workaround the fact that the "ric" argument to __tlbie_pid
-	 * must be a compile-time contraint to match the "i" constraint
-	 * in the asm statement.
-	 */
-	switch (ric) {
-	case RIC_FLUSH_TLB:
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
-		fixup_tlbie_pid_lpid(pid, lpid);
-		break;
-	case RIC_FLUSH_PWC:
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
-		break;
-	case RIC_FLUSH_ALL:
-	default:
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
-		fixup_tlbie_pid_lpid(pid, lpid);
-	}
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-}
 struct tlbiel_pid {
 	unsigned long pid;
 	unsigned long ric;
@@ -566,20 +473,6 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
 	fixup_tlbie_va_range(addr - page_size, pid, ap);
 }
 
-static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
-					 unsigned long pid, unsigned long lpid,
-					 unsigned long page_size,
-					 unsigned long psize)
-{
-	unsigned long addr;
-	unsigned long ap = mmu_get_ap(psize);
-
-	for (addr = start; addr < end; addr += page_size)
-		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
-
-	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
-}
-
 static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
 				      unsigned long psize, unsigned long ric)
 {
@@ -660,18 +553,6 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
-					unsigned long pid, unsigned long lpid,
-					unsigned long page_size,
-					unsigned long psize, bool also_pwc)
-{
-	asm volatile("ptesync" : : : "memory");
-	if (also_pwc)
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
-	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-}
-
 static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
 				unsigned long start, unsigned long end,
 				unsigned long pid, unsigned long page_size,
@@ -700,12 +581,13 @@ static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
  */
 void radix__local_flush_tlb_mm(struct mm_struct *mm)
 {
-	unsigned long pid;
+	unsigned long pid = mm->context.id;
+
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
+		return;
 
 	preempt_disable();
-	pid = mm->context.id;
-	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_pid(pid, RIC_FLUSH_TLB);
+	_tlbiel_pid(pid, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
@@ -713,12 +595,13 @@ EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 #ifndef CONFIG_SMP
 void radix__local_flush_all_mm(struct mm_struct *mm)
 {
-	unsigned long pid;
+	unsigned long pid = mm->context.id;
+
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
+		return;
 
 	preempt_disable();
-	pid = mm->context.id;
-	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_pid(pid, RIC_FLUSH_ALL);
+	_tlbiel_pid(pid, RIC_FLUSH_ALL);
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_all_mm);
@@ -732,12 +615,13 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
 void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 				       int psize)
 {
-	unsigned long pid;
+	unsigned long pid = mm->context.id;
+
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
+		return;
 
 	preempt_disable();
-	pid = mm->context.id;
-	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
+	_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 
@@ -792,12 +676,20 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush)
 		goto out;
 
 	if (current->active_mm == mm) {
+		unsigned long flags;
+
 		WARN_ON_ONCE(current->mm != NULL);
-		/* Is a kernel thread and is using mm as the lazy tlb */
-		mmgrab(&init_mm);
+		/*
+		 * It is a kernel thread and is using mm as the lazy tlb, so
+		 * switch it to init_mm. This is not always called from IPI
+		 * (e.g., flush_type_needed), so must disable irqs.
+		 */
+		local_irq_save(flags);
+		mmgrab_lazy_tlb(&init_mm);
 		current->active_mm = &init_mm;
 		switch_mm_irqs_off(mm, &init_mm, current);
-		mmdrop(mm);
+		mmdrop_lazy_tlb(mm);
+		local_irq_restore(flags);
 	}
 
 	/*
@@ -809,7 +701,7 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush)
 	 * that's what the caller expects.
 	 */
 	if (cpumask_test_cpu(cpu, mm_cpumask(mm))) {
-		atomic_dec(&mm->context.active_cpus);
+		dec_mm_active_cpus(mm);
 		cpumask_clear_cpu(cpu, mm_cpumask(mm));
 		always_flush = true;
 	}
@@ -945,7 +837,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 	enum tlb_flush_type type;
 
 	pid = mm->context.id;
-	if (unlikely(pid == MMU_NO_CONTEXT))
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
 		return;
 
 	preempt_disable();
@@ -976,6 +868,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 		}
 	}
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
@@ -985,7 +878,7 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
 	enum tlb_flush_type type;
 
 	pid = mm->context.id;
-	if (unlikely(pid == MMU_NO_CONTEXT))
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
 		return;
 
 	preempt_disable();
@@ -1009,6 +902,7 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
 			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
 	}
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
 void radix__flush_all_mm(struct mm_struct *mm)
@@ -1024,7 +918,7 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 	enum tlb_flush_type type;
 
 	pid = mm->context.id;
-	if (unlikely(pid == MMU_NO_CONTEXT))
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
 		return;
 
 	preempt_disable();
@@ -1104,6 +998,9 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
 }
 EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
 
+/*
+ * Doesn't appear to be used anywhere. Remove.
+ */
 #define TLB_FLUSH_ALL -1UL
 
 /*
@@ -1125,23 +1022,22 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 	unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
 	unsigned long page_size = 1UL << page_shift;
 	unsigned long nr_pages = (end - start) >> page_shift;
-	bool fullmm = (end == TLB_FLUSH_ALL);
 	bool flush_pid, flush_pwc = false;
 	enum tlb_flush_type type;
 
 	pid = mm->context.id;
-	if (unlikely(pid == MMU_NO_CONTEXT))
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
 		return;
 
+	WARN_ON_ONCE(end == TLB_FLUSH_ALL);
+
 	preempt_disable();
 	smp_mb(); /* see radix__flush_tlb_mm */
-	type = flush_type_needed(mm, fullmm);
+	type = flush_type_needed(mm, false);
 	if (type == FLUSH_TYPE_NONE)
 		goto out;
 
-	if (fullmm)
-		flush_pid = true;
-	else if (type == FLUSH_TYPE_GLOBAL)
+	if (type == FLUSH_TYPE_GLOBAL)
 		flush_pid = nr_pages > tlb_single_page_flush_ceiling;
 	else
 		flush_pid = nr_pages > tlb_local_single_page_flush_ceiling;
@@ -1179,15 +1075,12 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 			}
 		}
 	} else {
-		bool hflush = false;
+		bool hflush;
 		unsigned long hstart, hend;
 
-		if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
-			hstart = (start + PMD_SIZE - 1) & PMD_MASK;
-			hend = end & PMD_MASK;
-			if (hstart < hend)
-				hflush = true;
-		}
+		hstart = (start + PMD_SIZE - 1) & PMD_MASK;
+		hend = end & PMD_MASK;
+		hflush = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hstart < hend;
 
 		if (type == FLUSH_TYPE_LOCAL) {
 			asm volatile("ptesync": : :"memory");
@@ -1218,6 +1111,7 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 	}
 out:
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
 void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -1302,8 +1196,29 @@ void radix__tlb_flush(struct mmu_gather *tlb)
 	 * that flushes the process table entry cache upon process teardown.
 	 * See the comment for radix in arch_exit_mmap().
 	 */
-	if (tlb->fullmm || tlb->need_flush_all) {
-		__flush_all_mm(mm, true);
+	if (tlb->fullmm) {
+		if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) {
+			/*
+			 * Shootdown based lazy tlb mm refcounting means we
+			 * have to IPI everyone in the mm_cpumask anyway soon
+			 * when the mm goes away, so might as well do it as
+			 * part of the final flush now.
+			 *
+			 * If lazy shootdown was improved to reduce IPIs (e.g.,
+			 * by batching), then it may end up being better to use
+			 * tlbies here instead.
+			 */
+			preempt_disable();
+
+			smp_mb(); /* see radix__flush_tlb_mm */
+			exit_flush_lazy_tlbs(mm);
+			__flush_all_mm(mm, true);
+
+			preempt_enable();
+		} else {
+			__flush_all_mm(mm, true);
+		}
+
 	} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
 		if (!tlb->freed_tables)
 			radix__flush_tlb_mm(mm);
@@ -1325,25 +1240,22 @@ static void __radix__flush_tlb_range_psize(struct mm_struct *mm,
 	unsigned int page_shift = mmu_psize_defs[psize].shift;
 	unsigned long page_size = 1UL << page_shift;
 	unsigned long nr_pages = (end - start) >> page_shift;
-	bool fullmm = (end == TLB_FLUSH_ALL);
 	bool flush_pid;
 	enum tlb_flush_type type;
 
 	pid = mm->context.id;
-	if (unlikely(pid == MMU_NO_CONTEXT))
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
 		return;
 
-	fullmm = (end == TLB_FLUSH_ALL);
+	WARN_ON_ONCE(end == TLB_FLUSH_ALL);
 
 	preempt_disable();
 	smp_mb(); /* see radix__flush_tlb_mm */
-	type = flush_type_needed(mm, fullmm);
+	type = flush_type_needed(mm, false);
 	if (type == FLUSH_TYPE_NONE)
 		goto out;
 
-	if (fullmm)
-		flush_pid = true;
-	else if (type == FLUSH_TYPE_GLOBAL)
+	if (type == FLUSH_TYPE_GLOBAL)
 		flush_pid = nr_pages > tlb_single_page_flush_ceiling;
 	else
 		flush_pid = nr_pages > tlb_local_single_page_flush_ceiling;
@@ -1385,6 +1297,7 @@ static void __radix__flush_tlb_range_psize(struct mm_struct *mm,
 	}
 out:
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
 void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
@@ -1406,7 +1319,7 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
 	enum tlb_flush_type type;
 
 	pid = mm->context.id;
-	if (unlikely(pid == MMU_NO_CONTEXT))
+	if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT))
 		return;
 
 	/* 4k page size, just blow the world */
@@ -1454,6 +1367,13 @@ void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL(radix__flush_pmd_tlb_range);
 
+void radix__flush_pud_tlb_range(struct vm_area_struct *vma,
+				unsigned long start, unsigned long end)
+{
+	radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_1G);
+}
+EXPORT_SYMBOL(radix__flush_pud_tlb_range);
+
 void radix__flush_tlb_all(void)
 {
 	unsigned long rb,prs,r,rs;
@@ -1479,6 +1399,127 @@ void radix__flush_tlb_all(void)
 }
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static __always_inline void __tlbie_pid_lpid(unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = PPC_BIT(53); /* IS = 1 */
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
+					    unsigned long lpid,
+					    unsigned long ap, unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
+{
+	/*
+	 * We can use any address for the invalidation, pick one which is
+	 * probably unused as an optimisation.
+	 */
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
+				RIC_FLUSH_TLB);
+	}
+}
+
+static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
+				   unsigned long ric)
+{
+	asm volatile("ptesync" : : : "memory");
+
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
+		fixup_tlbie_pid_lpid(pid, lpid);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
+		fixup_tlbie_pid_lpid(pid, lpid);
+	}
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+
+static inline void fixup_tlbie_va_range_lpid(unsigned long va,
+					     unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ap)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
+	}
+}
+
+static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					 unsigned long pid, unsigned long lpid,
+					 unsigned long page_size,
+					 unsigned long psize)
+{
+	unsigned long addr;
+	unsigned long ap = mmu_get_ap(psize);
+
+	for (addr = start; addr < end; addr += page_size)
+		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
+
+	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
+}
+
+static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					unsigned long pid, unsigned long lpid,
+					unsigned long page_size,
+					unsigned long psize, bool also_pwc)
+{
+	asm volatile("ptesync" : : : "memory");
+	if (also_pwc)
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+
 /*
  * Performs process-scoped invalidations for a given LPID
  * as part of H_RPT_INVALIDATE hcall.