powerpc/mm/book3s64/radix: Remove unused code.

mm_tlb_flush_nested change was added in the mmu gather tlb flush to
handle the case of parallel pte invalidate happening with mmap_sem
held in read mode. This fix was done by commit
02390f66 ("powerpc/64s/radix: Fix MADV_[FREE|DONTNEED] TLB flush
miss problem with THP") and the problem is explained in detail in
commit 99baac21 ("mm: fix MADV_[FREE|DONTNEED] TLB flush miss
problem")

This was later updated by commit 7a30df49 ("mm: mmu_gather: remove
__tlb_reset_range() for force flush") to do a full mm flush rather
than a range flush. By commit dd2283f2 ("mm: mmap: zap pages with
read mmap_sem in munmap") we are also now allowing a page table free
in mmap_sem read mode which means we should do a PWC flush too. Our
current full mm flush imply a PWC flush.

With all the above change the mm_tlb_flush_nested(mm) branch in
radix__tlb_flush will never be taken because for the nested case we
would have taken the if (tlb->fullmm) branch. This patch removes the
unused code. Also, remove the gflush change in
__radix__flush_tlb_range that was added to handle the range tlb flush
code. We only check for THP there because hugetlb is flushed via a
different code path where page size is explicitly specified.

This is a partial revert of commit 02390f66 ("powerpc/64s/radix:
Fix MADV_[FREE|DONTNEED] TLB flush miss problem with THP")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191024075801.22434-1-aneesh.kumar@linux.ibm.com

arch/powerpc/mm/book3s64/radix_tlb.c

@@ -832,8 +832,7 @@ static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
 static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
 
 static inline void __radix__flush_tlb_range(struct mm_struct *mm,
-					unsigned long start, unsigned long end,
-					bool flush_all_sizes)
+					    unsigned long start, unsigned long end)
 
 {
 	unsigned long pid;
@@ -879,26 +878,16 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 			}
 		}
 	} else {
-		bool hflush = flush_all_sizes;
-		bool gflush = flush_all_sizes;
+		bool hflush = false;
 		unsigned long hstart, hend;
-		unsigned long gstart, gend;
 
-		if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
-			hflush = true;
-
-		if (hflush) {
+		if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 			hstart = (start + PMD_SIZE - 1) & PMD_MASK;
 			hend = end & PMD_MASK;
 			if (hstart == hend)
 				hflush = false;
-		}
-
-		if (gflush) {
-			gstart = (start + PUD_SIZE - 1) & PUD_MASK;
-			gend = end & PUD_MASK;
-			if (gstart == gend)
-				gflush = false;
+			else
+				hflush = true;
 		}
 
 		if (local) {
@@ -907,9 +896,6 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 			if (hflush)
 				__tlbiel_va_range(hstart, hend, pid,
 						PMD_SIZE, MMU_PAGE_2M);
-			if (gflush)
-				__tlbiel_va_range(gstart, gend, pid,
-						PUD_SIZE, MMU_PAGE_1G);
 			asm volatile("ptesync": : :"memory");
 		} else if (cputlb_use_tlbie()) {
 			asm volatile("ptesync": : :"memory");
@@ -917,10 +903,6 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 			if (hflush)
 				__tlbie_va_range(hstart, hend, pid,
 						PMD_SIZE, MMU_PAGE_2M);
-			if (gflush)
-				__tlbie_va_range(gstart, gend, pid,
-						PUD_SIZE, MMU_PAGE_1G);
-
 			asm volatile("eieio; tlbsync; ptesync": : :"memory");
 		} else {
 			_tlbiel_va_range_multicast(mm,
@@ -928,9 +910,6 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 			if (hflush)
 				_tlbiel_va_range_multicast(mm,
 					hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, false);
-			if (gflush)
-				_tlbiel_va_range_multicast(mm,
-					gstart, gend, pid, PUD_SIZE, MMU_PAGE_1G, false);
 		}
 	}
 	preempt_enable();
@@ -945,7 +924,7 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		return radix__flush_hugetlb_tlb_range(vma, start, end);
 #endif
 
-	__radix__flush_tlb_range(vma->vm_mm, start, end, false);
+	__radix__flush_tlb_range(vma->vm_mm, start, end);
 }
 EXPORT_SYMBOL(radix__flush_tlb_range);
 
@@ -1023,39 +1002,6 @@ void radix__tlb_flush(struct mmu_gather *tlb)
 	 */
 	if (tlb->fullmm) {
 		__flush_all_mm(mm, true);
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
-	} else if (mm_tlb_flush_nested(mm)) {
-		/*
-		 * If there is a concurrent invalidation that is clearing ptes,
-		 * then it's possible this invalidation will miss one of those
-		 * cleared ptes and miss flushing the TLB. If this invalidate
-		 * returns before the other one flushes TLBs, that can result
-		 * in it returning while there are still valid TLBs inside the
-		 * range to be invalidated.
-		 *
-		 * See mm/memory.c:tlb_finish_mmu() for more details.
-		 *
-		 * The solution to this is ensure the entire range is always
-		 * flushed here. The problem for powerpc is that the flushes
-		 * are page size specific, so this "forced flush" would not
-		 * do the right thing if there are a mix of page sizes in
-		 * the range to be invalidated. So use __flush_tlb_range
-		 * which invalidates all possible page sizes in the range.
-		 *
-		 * PWC flush probably is not be required because the core code
-		 * shouldn't free page tables in this path, but accounting
-		 * for the possibility makes us a bit more robust.
-		 *
-		 * need_flush_all is an uncommon case because page table
-		 * teardown should be done with exclusive locks held (but
-		 * after locks are dropped another invalidate could come
-		 * in), it could be optimized further if necessary.
-		 */
-		if (!tlb->need_flush_all)
-			__radix__flush_tlb_range(mm, start, end, true);
-		else
-			radix__flush_all_mm(mm);
-#endif
 	} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
 		if (!tlb->need_flush_all)
 			radix__flush_tlb_mm(mm);