powerpc/mm/radix: Improve TLB/PWC flushes

At the moment we have to rather sub-optimal flushing behaviours:

 - flush_tlb_mm() will flush the PWC which is unnecessary (for example
   when doing a fork)

 - A large unmap will call flush_tlb_pwc() multiple times causing us
   to perform that fairly expensive operation repeatedly. This happens
   often in batches of 3 on every new process.

So we change flush_tlb_mm() to only flush the TLB, and we use the
existing "need_flush_all" flag in struct mmu_gather to indicate
that the PWC needs flushing.

Unfortunately, flush_tlb_range() still needs to do a full flush
for now as it's used by the THP collapsing. We will fix that later.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/book3s/64/tlbflush-radix.h

@@ -22,22 +22,20 @@ extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end
 
 extern void radix__local_flush_tlb_mm(struct mm_struct *mm);
 extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 					      int psize);
 extern void radix__tlb_flush(struct mmu_gather *tlb);
 #ifdef CONFIG_SMP
 extern void radix__flush_tlb_mm(struct mm_struct *mm);
 extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 					int psize);
 #else
 #define radix__flush_tlb_mm(mm)		radix__local_flush_tlb_mm(mm)
 #define radix__flush_tlb_page(vma,addr)	radix__local_flush_tlb_page(vma,addr)
 #define radix__flush_tlb_page_psize(mm,addr,p) radix__local_flush_tlb_page_psize(mm,addr,p)
-#define radix__flush_tlb_pwc(tlb, addr)	radix__local_flush_tlb_pwc(tlb, addr)
 #endif
+extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
 				     unsigned long page_size);
 extern void radix__flush_tlb_lpid(unsigned long lpid);

arch/powerpc/mm/tlb-radix.c

@@ -68,17 +68,6 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
 }
 
-static inline void tlbiel_pwc(unsigned long pid)
-{
-	asm volatile("ptesync": : :"memory");
-
-	/* For PWC flush, we don't look at set number */
-	__tlbiel_pid(pid, 0, RIC_FLUSH_PWC);
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
-}
-
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -149,31 +138,23 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm)
 	preempt_disable();
 	pid = mm->context.id;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_pid(pid, RIC_FLUSH_ALL);
+		_tlbiel_pid(pid, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 
-void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+#ifndef CONFIG_SMP
+static void radix__local_flush_all_mm(struct mm_struct *mm)
 {
 	unsigned long pid;
-	struct mm_struct *mm = tlb->mm;
-	/*
-	 * If we are doing a full mm flush, we will do a tlb flush
-	 * with RIC_FLUSH_ALL later.
-	 */
-	if (tlb->fullmm)
-		return;
 
 	preempt_disable();
-
 	pid = mm->context.id;
 	if (pid != MMU_NO_CONTEXT)
-		tlbiel_pwc(pid);
-
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 	preempt_enable();
 }
-EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
+#endif /* CONFIG_SMP */
 
 void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 				       int psize)
@@ -211,38 +192,35 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 		goto no_context;
 
 	if (!mm_is_thread_local(mm))
-		_tlbie_pid(pid, RIC_FLUSH_ALL);
+		_tlbie_pid(pid, RIC_FLUSH_TLB);
 	else
-		_tlbiel_pid(pid, RIC_FLUSH_ALL);
+		_tlbiel_pid(pid, RIC_FLUSH_TLB);
 no_context:
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
-void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+static void radix__flush_all_mm(struct mm_struct *mm)
 {
 	unsigned long pid;
-	struct mm_struct *mm = tlb->mm;
 
-	/*
-	 * If we are doing a full mm flush, we will do a tlb flush
-	 * with RIC_FLUSH_ALL later.
-	 */
-	if (tlb->fullmm)
-		return;
 	preempt_disable();
-
 	pid = mm->context.id;
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto no_context;
 
 	if (!mm_is_thread_local(mm))
-		_tlbie_pid(pid, RIC_FLUSH_PWC);
+		_tlbie_pid(pid, RIC_FLUSH_ALL);
 	else
-		tlbiel_pwc(pid);
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 no_context:
 	preempt_enable();
 }
+
+void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+	tlb->need_flush_all = 1;
+}
 EXPORT_SYMBOL(radix__flush_tlb_pwc);
 
 void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
@@ -274,6 +252,8 @@ void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 }
 EXPORT_SYMBOL(radix__flush_tlb_page);
 
+#else /* CONFIG_SMP */
+#define radix__flush_all_mm radix__local_flush_all_mm
 #endif /* CONFIG_SMP */
 
 void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
@@ -291,7 +271,12 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 
 {
 	struct mm_struct *mm = vma->vm_mm;
-	radix__flush_tlb_mm(mm);
+
+	/*
+	 * This is currently used when collapsing THPs so we need to
+	 * flush the PWC. We should fix this.
+	 */
+	radix__flush_all_mm(mm);
 }
 EXPORT_SYMBOL(radix__flush_tlb_range);
 
@@ -322,7 +307,10 @@ void radix__tlb_flush(struct mmu_gather *tlb)
 	 */
 	if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all)
 		radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize);
-	else
+	else if (tlb->need_flush_all) {
+		tlb->need_flush_all = 0;
+		radix__flush_all_mm(mm);
+	} else
 		radix__flush_tlb_mm(mm);
 }