[PATCH for-4.8_set2 00/13] TLB flush changes

[PATCH for-4.8_set2 00/13] TLB flush changes

[Aneesh Kumar K.V]

Hi,

This patch series add changes to support tracking page size during tlb flush
and use the same in ppc64 so that we can do a tlbie with va range. First
three patches are already in -mm tree.

Aneesh Kumar K.V (13):
  mm/hugetlb: Simplify hugetlb unmap
  mm: Change the interface for __tlb_remove_page
  mm/mmu_gather: Track page size with mmu gather and force flush if page
    size change
  powerpc/mm/radix: Implement tlb mmu gather flush efficiently
  powerpc/mm: Make MMU_FTR_RADIX a MMU family feature
  powerpc/mm/hash: Add helper for finding SLBE LLP encoding
  powerpc/mm: Use hugetlb flush functions
  powerpc/mm: Drop multiple definition of mm_is_core_local
  powerpc/mm/radix: Add tlb flush of THP ptes
  powerpc/mm/radix: Rename function and drop unused arg
  powerpc/mm/radix/hugetlb: Add helper for finding page size from hstate
  powerpc/mm/hugetlb: Add flush_hugetlb_tlb_range
  powerpc/mm: remove flush_tlb_page_nohash

 arch/arm/include/asm/tlb.h                         | 29 ++++++-
 arch/ia64/include/asm/tlb.h                        | 31 ++++++--
 arch/powerpc/include/asm/book3s/64/hugetlb-radix.h | 15 ++++
 arch/powerpc/include/asm/book3s/64/mmu-hash.h      |  9 +++
 arch/powerpc/include/asm/book3s/64/mmu.h           |  3 +-
 arch/powerpc/include/asm/book3s/64/tlbflush-hash.h |  5 --
 .../powerpc/include/asm/book3s/64/tlbflush-radix.h | 16 ++--
 arch/powerpc/include/asm/book3s/64/tlbflush.h      | 27 +++++--
 arch/powerpc/include/asm/hugetlb.h                 |  2 +-
 arch/powerpc/include/asm/kvm_book3s_64.h           |  3 +-
 arch/powerpc/include/asm/mmu.h                     | 16 ++--
 arch/powerpc/include/asm/tlb.h                     | 13 ++++
 arch/powerpc/include/asm/tlbflush.h                |  1 -
 arch/powerpc/kernel/entry_64.S                     |  2 +-
 arch/powerpc/kernel/exceptions-64s.S               |  8 +-
 arch/powerpc/kernel/prom.c                         |  4 +-
 arch/powerpc/mm/hash_native_64.c                   |  6 +-
 arch/powerpc/mm/hugetlbpage-radix.c                | 39 ++++------
 arch/powerpc/mm/pgtable-book3s64.c                 |  4 +-
 arch/powerpc/mm/pgtable.c                          |  2 +-
 arch/powerpc/mm/tlb-radix.c                        | 90 ++++++++++++++++++----
 arch/powerpc/mm/tlb_hash32.c                       | 11 ---
 arch/powerpc/mm/tlb_nohash.c                       |  6 --
 arch/s390/include/asm/tlb.h                        | 22 +++++-
 arch/sh/include/asm/tlb.h                          | 20 ++++-
 arch/um/include/asm/tlb.h                          | 20 ++++-
 include/asm-generic/tlb.h                          | 59 +++++++++++---
 mm/huge_memory.c                                   |  2 +-
 mm/hugetlb.c                                       | 64 ++++++++-------
 mm/memory.c                                        | 27 +++++--
 30 files changed, 390 insertions(+), 166 deletions(-)

-- 
2.7.4

[PATCH for-4.8 01/13] mm/hugetlb: Simplify hugetlb unmap

[Aneesh Kumar K.V]

For hugetlb like THP (and unlike regular page), we do tlb flush after
dropping ptl. Because of the above, we don't need to track force_flush
like we do now. Instead we can simply call tlb_remove_page() which
will do the flush if needed.

No functionality change in this patch.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
NOTE: This patch is already applied to -mm tree

 mm/hugetlb.c | 54 +++++++++++++++++++++---------------------------------
 1 file changed, 21 insertions(+), 33 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c1f3c0be150a..0352296502b1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3177,7 +3177,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			    unsigned long start, unsigned long end,
 			    struct page *ref_page)
 {
-	int force_flush = 0;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
 	pte_t *ptep;
@@ -3196,19 +3195,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	address = start;
-again:
 	for (; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
 
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep))
-			goto unlock;
+		if (huge_pmd_unshare(mm, &address, ptep)) {
+			spin_unlock(ptl);
+			continue;
+		}
 
 		pte = huge_ptep_get(ptep);
-		if (huge_pte_none(pte))
-			goto unlock;
+		if (huge_pte_none(pte)) {
+			spin_unlock(ptl);
+			continue;
+		}
 
 		/*
 		 * Migrating hugepage or HWPoisoned hugepage is already
@@ -3216,7 +3218,8 @@ again:
 		 */
 		if (unlikely(!pte_present(pte))) {
 			huge_pte_clear(mm, address, ptep);
-			goto unlock;
+			spin_unlock(ptl);
+			continue;
 		}
 
 		page = pte_page(pte);
@@ -3226,9 +3229,10 @@ again:
 		 * are about to unmap is the actual page of interest.
 		 */
 		if (ref_page) {
-			if (page != ref_page)
-				goto unlock;
-
+			if (page != ref_page) {
+				spin_unlock(ptl);
+				continue;
+			}
 			/*
 			 * Mark the VMA as having unmapped its page so that
 			 * future faults in this VMA will fail rather than
@@ -3244,30 +3248,14 @@ again:
 
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		page_remove_rmap(page, true);
-		force_flush = !__tlb_remove_page(tlb, page);
-		if (force_flush) {
-			address += sz;
-			spin_unlock(ptl);
-			break;
-		}
-		/* Bail out after unmapping reference page if supplied */
-		if (ref_page) {
-			spin_unlock(ptl);
-			break;
-		}
-unlock:
+
 		spin_unlock(ptl);
-	}
-	/*
-	 * mmu_gather ran out of room to batch pages, we break out of
-	 * the PTE lock to avoid doing the potential expensive TLB invalidate
-	 * and page-free while holding it.
-	 */
-	if (force_flush) {
-		force_flush = 0;
-		tlb_flush_mmu(tlb);
-		if (address < end && !ref_page)
-			goto again;
+		tlb_remove_page(tlb, page);
+		/*
+		 * Bail out after unmapping reference page if supplied
+		 */
+		if (ref_page)
+			break;
 	}
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	tlb_end_vma(tlb, vma);
-- 
2.7.4

[PATCH for-4.8 02/13] mm: Change the interface for __tlb_remove_page

[Aneesh Kumar K.V]

This update the generic and arch specific implementation to return true
if we need to do a tlb flush. That means if a __tlb_remove_page indicate
a flush is needed, the page we try to remove need to be tracked and
added again after the flush. We need to track it because we have already
update the pte to none and we can't just loop back.

This changes is done to enable us to do a tlb_flush when we try to flush
a range that consists of different page sizes. For architectures like
ppc64, we can do a range based tlb flush and we need to track page size
for that. When we try to remove a huge page, we will force a tlb flush
and starts a new mmu gather.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
NOTE: This patch is already applied to -mm tree

 arch/arm/include/asm/tlb.h  | 17 +++++++++++++----
 arch/ia64/include/asm/tlb.h | 19 ++++++++++++++-----
 arch/s390/include/asm/tlb.h |  9 +++++++--
 arch/sh/include/asm/tlb.h   |  8 +++++++-
 arch/um/include/asm/tlb.h   |  8 +++++++-
 include/asm-generic/tlb.h   | 44 +++++++++++++++++++++++++++++++++-----------
 mm/memory.c                 | 19 +++++++++++++------
 7 files changed, 94 insertions(+), 30 deletions(-)

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 3cadb726ec88..a9d2aee3826f 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -209,17 +209,26 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 		tlb_flush(tlb);
 }
 
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
+	if (tlb->nr == tlb->max)
+		return true;
 	tlb->pages[tlb->nr++] = page;
-	VM_BUG_ON(tlb->nr > tlb->max);
-	return tlb->max - tlb->nr;
+	return false;
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	if (!__tlb_remove_page(tlb, page))
+	if (__tlb_remove_page(tlb, page)) {
 		tlb_flush_mmu(tlb);
+		__tlb_remove_page(tlb, page);
+	}
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+					 struct page *page)
+{
+	return __tlb_remove_page(tlb, page);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 39d64e0df1de..e7da41aa9110 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -205,17 +205,18 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
  * must be delayed until after the TLB has been flushed (see comments at the beginning of
  * this file).
  */
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
+	if (tlb->nr == tlb->max)
+		return true;
+
 	tlb->need_flush = 1;
 
 	if (!tlb->nr && tlb->pages == tlb->local)
 		__tlb_alloc_page(tlb);
 
 	tlb->pages[tlb->nr++] = page;
-	VM_BUG_ON(tlb->nr > tlb->max);
-
-	return tlb->max - tlb->nr;
+	return false;
 }
 
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
@@ -235,8 +236,16 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	if (!__tlb_remove_page(tlb, page))
+	if (__tlb_remove_page(tlb, page)) {
 		tlb_flush_mmu(tlb);
+		__tlb_remove_page(tlb, page);
+	}
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+					 struct page *page)
+{
+	return __tlb_remove_page(tlb, page);
 }
 
 /*
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 7a92e69c50bc..30759b560849 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -87,10 +87,10 @@ static inline void tlb_finish_mmu(struct mmu_gather *tlb,
  * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
  * has already been freed, so just do free_page_and_swap_cache.
  */
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	free_page_and_swap_cache(page);
-	return 1; /* avoid calling tlb_flush_mmu */
+	return false; /* avoid calling tlb_flush_mmu */
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -98,6 +98,11 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	free_page_and_swap_cache(page);
 }
 
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+					 struct page *page)
+{
+	return __tlb_remove_page(tlb, page);
+}
 /*
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 62f80d2a9df9..21ae8f5546b2 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -101,7 +101,7 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	free_page_and_swap_cache(page);
-	return 1; /* avoid calling tlb_flush_mmu */
+	return false; /* avoid calling tlb_flush_mmu */
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -109,6 +109,12 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__tlb_remove_page(tlb, page);
 }
 
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+					 struct page *page)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
 #define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 16eb63fac57d..3dc4cbb3c2c0 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -102,7 +102,7 @@ static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	tlb->need_flush = 1;
 	free_page_and_swap_cache(page);
-	return 1; /* avoid calling tlb_flush_mmu */
+	return false; /* avoid calling tlb_flush_mmu */
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -110,6 +110,12 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__tlb_remove_page(tlb, page);
 }
 
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+					 struct page *page)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 9dbb739cafa0..7b899a46a4cb 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -107,6 +107,11 @@ struct mmu_gather {
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
 	unsigned int		batch_count;
+	/*
+	 * __tlb_adjust_range  will track the new addr here,
+	 * that that we can adjust the range after the flush
+	 */
+	unsigned long addr;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
@@ -115,23 +120,19 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
 							unsigned long end);
-int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
-
-/* tlb_remove_page
- *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
- *	required.
- */
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (!__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
+bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address)
 {
 	tlb->start = min(tlb->start, address);
 	tlb->end = max(tlb->end, address + PAGE_SIZE);
+	/*
+	 * Track the last address with which we adjusted the range. This
+	 * will be used later to adjust again after a mmu_flush due to
+	 * failed __tlb_remove_page
+	 */
+	tlb->addr = address;
 }
 
 static inline void __tlb_reset_range(struct mmu_gather *tlb)
@@ -144,6 +145,27 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+/* tlb_remove_page
+ *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
+ *	required.
+ */
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	if (__tlb_remove_page(tlb, page)) {
+		tlb_flush_mmu(tlb);
+		__tlb_adjust_range(tlb, tlb->addr);
+		__tlb_remove_page(tlb, page);
+	}
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page)
+{
+	/* active->nr should be zero when we call this */
+	VM_BUG_ON_PAGE(tlb->active->nr, page);
+	__tlb_adjust_range(tlb, tlb->addr);
+	return __tlb_remove_page(tlb, page);
+}
+
 /*
  * In the case of tlb vma handling, we can optimise these away in the
  * case where we're doing a full MM flush.  When we're doing a munmap,
diff --git a/mm/memory.c b/mm/memory.c
index cd1f29e4897e..2554c82981cb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -292,23 +292,24 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
  *	handling the additional races in SMP caused by other CPUs caching valid
  *	mappings in their TLBs. Returns the number of free page slots left.
  *	When out of page slots we must call tlb_flush_mmu().
+ *returns true if the caller should flush.
  */
-int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
 
 	batch = tlb->active;
-	batch->pages[batch->nr++] = page;
 	if (batch->nr == batch->max) {
 		if (!tlb_next_batch(tlb))
-			return 0;
+			return true;
 		batch = tlb->active;
 	}
 	VM_BUG_ON_PAGE(batch->nr > batch->max, page);
 
-	return batch->max - batch->nr;
+	batch->pages[batch->nr++] = page;
+	return false;
 }
 
 #endif /* HAVE_GENERIC_MMU_GATHER */
@@ -1109,6 +1110,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	pte_t *start_pte;
 	pte_t *pte;
 	swp_entry_t entry;
+	struct page *pending_page = NULL;
 
 again:
 	init_rss_vec(rss);
@@ -1160,8 +1162,9 @@ again:
 			page_remove_rmap(page, false);
 			if (unlikely(page_mapcount(page) < 0))
 				print_bad_pte(vma, addr, ptent, page);
-			if (unlikely(!__tlb_remove_page(tlb, page))) {
+			if (unlikely(__tlb_remove_page(tlb, page))) {
 				force_flush = 1;
+				pending_page = page;
 				addr += PAGE_SIZE;
 				break;
 			}
@@ -1202,7 +1205,11 @@ again:
 	if (force_flush) {
 		force_flush = 0;
 		tlb_flush_mmu_free(tlb);
-
+		if (pending_page) {
+			/* remove the page with new size */
+			__tlb_remove_pte_page(tlb, pending_page);
+			pending_page = NULL;
+		}
 		if (addr != end)
 			goto again;
 	}
-- 
2.7.4

[PATCH for-4.8 03/13] mm/mmu_gather: Track page size with mmu gather and force flush if page size change

[Aneesh Kumar K.V]

This allows arch which need to do special handing with respect to
different page size when flushing tlb to implement the same in mmu gather

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---

NOTE: This patch is already applied to -mm tree

 arch/arm/include/asm/tlb.h  | 12 ++++++++++++
 arch/ia64/include/asm/tlb.h | 12 ++++++++++++
 arch/s390/include/asm/tlb.h | 13 +++++++++++++
 arch/sh/include/asm/tlb.h   | 12 ++++++++++++
 arch/um/include/asm/tlb.h   | 12 ++++++++++++
 include/asm-generic/tlb.h   | 27 +++++++++++++++++++++------
 mm/huge_memory.c            |  2 +-
 mm/hugetlb.c                |  2 +-
 mm/memory.c                 | 10 +++++++++-
 9 files changed, 93 insertions(+), 9 deletions(-)

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index a9d2aee3826f..1e25cd80589e 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -225,12 +225,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	}
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	unsigned long addr)
 {
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index e7da41aa9110..77e541cf0e5d 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -242,12 +242,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	}
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 /*
  * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
  * PTE, not just those pointing to (normal) physical memory.
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 30759b560849..15711de10403 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -98,11 +98,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	free_page_and_swap_cache(page);
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 /*
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 21ae8f5546b2..025cdb1032f6 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -109,12 +109,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__tlb_remove_page(tlb, page);
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
 #define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 3dc4cbb3c2c0..821ff0acfe17 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -110,12 +110,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__tlb_remove_page(tlb, page);
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 7b899a46a4cb..c6d667187608 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -112,6 +112,7 @@ struct mmu_gather {
 	 * that that we can adjust the range after the flush
 	 */
 	unsigned long addr;
+	int page_size;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
@@ -120,7 +121,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
 							unsigned long end);
-bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address)
@@ -145,23 +147,36 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	if (__tlb_remove_page_size(tlb, page, page_size)) {
+		tlb_flush_mmu(tlb);
+		tlb->page_size = page_size;
+		__tlb_adjust_range(tlb, tlb->addr);
+		__tlb_remove_page_size(tlb, page, page_size);
+	}
+}
+
+static bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	return __tlb_remove_page_size(tlb, page, PAGE_SIZE);
+}
+
 /* tlb_remove_page
  *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
  *	required.
  */
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	if (__tlb_remove_page(tlb, page)) {
-		tlb_flush_mmu(tlb);
-		__tlb_adjust_range(tlb, tlb->addr);
-		__tlb_remove_page(tlb, page);
-	}
+	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
 
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page)
 {
 	/* active->nr should be zero when we call this */
 	VM_BUG_ON_PAGE(tlb->active->nr, page);
+	tlb->page_size = PAGE_SIZE;
 	__tlb_adjust_range(tlb, tlb->addr);
 	return __tlb_remove_page(tlb, page);
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9ed58530f695..a5711093a829 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1694,7 +1694,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
 		atomic_long_dec(&tlb->mm->nr_ptes);
 		spin_unlock(ptl);
-		tlb_remove_page(tlb, page);
+		tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE);
 	}
 	return 1;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0352296502b1..f4b9e73efbc9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3250,7 +3250,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		page_remove_rmap(page, true);
 
 		spin_unlock(ptl);
-		tlb_remove_page(tlb, page);
+		tlb_remove_page_size(tlb, page, huge_page_size(h));
 		/*
 		 * Bail out after unmapping reference page if supplied
 		 */
diff --git a/mm/memory.c b/mm/memory.c
index 2554c82981cb..c6d42908fcf0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -233,6 +233,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
 #endif
+	tlb->page_size = 0;
 
 	__tlb_reset_range(tlb);
 }
@@ -294,12 +295,19 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
  *	When out of page slots we must call tlb_flush_mmu().
  *returns true if the caller should flush.
  */
-bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
 {
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
 
+	if (!tlb->page_size)
+		tlb->page_size = page_size;
+	else {
+		if (page_size != tlb->page_size)
+			return true;
+	}
+
 	batch = tlb->active;
 	if (batch->nr == batch->max) {
 		if (!tlb_next_batch(tlb))
-- 
2.7.4

[PATCH for-4.8 04/13] powerpc/mm/radix: Implement tlb mmu gather flush efficiently

[Aneesh Kumar K.V]

Now that we track page size in mmu_gather, we can use address based
tlbie format when doing a tlb_flush(). We don't do this if we are
invalidating the full address space.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 .../powerpc/include/asm/book3s/64/tlbflush-radix.h |  2 +
 arch/powerpc/mm/tlb-radix.c                        | 59 +++++++++++++++++++++-
 2 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 00703e7e4c94..7ee9a195fa9c 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -10,6 +10,8 @@ static inline int mmu_get_ap(int psize)
 	return mmu_psize_defs[psize].ap;
 }
 
+extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
+					 unsigned long end, int psize);
 extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end);
 extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end);
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index e1f22700fb16..6de05c59b375 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -299,8 +299,65 @@ static int radix_get_mmu_psize(int page_size)
 
 void radix__tlb_flush(struct mmu_gather *tlb)
 {
+	int psize = 0;
 	struct mm_struct *mm = tlb->mm;
-	radix__flush_tlb_mm(mm);
+	int page_size = tlb->page_size;
+
+	psize = radix_get_mmu_psize(page_size);
+	/*
+	 * if page size is not something we understand, do a full mm flush
+	 */
+	if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all)
+		radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize);
+	else
+		radix__flush_tlb_mm(mm);
+}
+
+#define TLB_FLUSH_ALL -1UL
+/*
+ * Number of pages above which we will do a bcast tlbie. Just a
+ * number at this point copied from x86
+ */
+static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
+
+void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
+				  unsigned long end, int psize)
+{
+	unsigned long pid;
+	unsigned long addr;
+	int local = mm_is_core_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;
+
+
+	preempt_disable();
+	pid = mm ? mm->context.id : 0;
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		goto err_out;
+
+	if (end == TLB_FLUSH_ALL ||
+	    (end - start) > tlb_single_page_flush_ceiling * page_size) {
+		if (local)
+			_tlbiel_pid(pid, RIC_FLUSH_TLB);
+		else
+			_tlbie_pid(pid, RIC_FLUSH_TLB);
+		goto err_out;
+	}
+	for (addr = start; addr < end; addr += page_size) {
+
+		if (local)
+			_tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
+		else {
+			if (lock_tlbie)
+				raw_spin_lock(&native_tlbie_lock);
+			_tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
+			if (lock_tlbie)
+				raw_spin_unlock(&native_tlbie_lock);
+		}
+	}
+err_out:
+	preempt_enable();
 }
 
 void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
-- 
2.7.4

[PATCH for-4.8 05/13] powerpc/mm: Make MMU_FTR_RADIX a MMU family feature

[Aneesh Kumar K.V]

MMU feature bits are defined such that we use the lower half to
present MMU family features. Remove the strict split of half and
also move Radix to a mmu family feature. Radix introduce a new MMU
model and strictly speaking it is a new MMU family. This also free
up bits which can be used for individual features later.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/mmu.h |  3 +--
 arch/powerpc/include/asm/mmu.h           | 16 +++++++---------
 arch/powerpc/kernel/entry_64.S           |  2 +-
 arch/powerpc/kernel/exceptions-64s.S     |  8 ++++----
 arch/powerpc/kernel/prom.c               |  4 ++--
 5 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index d4eda6420523..6d8306d9aa7a 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -24,12 +24,11 @@ struct mmu_psize_def {
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 
 #ifdef CONFIG_PPC_RADIX_MMU
-#define radix_enabled() mmu_has_feature(MMU_FTR_RADIX)
+#define radix_enabled() mmu_has_feature(MMU_FTR_TYPE_RADIX)
 #else
 #define radix_enabled() (0)
 #endif
 
-
 #endif /* __ASSEMBLY__ */
 
 /* 64-bit classic hash table MMU */
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 54471228f7b8..0e7c1a262075 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -12,7 +12,7 @@
  */
 
 /*
- * First half is MMU families
+ * MMU families
  */
 #define MMU_FTR_HPTE_TABLE		ASM_CONST(0x00000001)
 #define MMU_FTR_TYPE_8xx		ASM_CONST(0x00000002)
@@ -20,9 +20,12 @@
 #define MMU_FTR_TYPE_44x		ASM_CONST(0x00000008)
 #define MMU_FTR_TYPE_FSL_E		ASM_CONST(0x00000010)
 #define MMU_FTR_TYPE_47x		ASM_CONST(0x00000020)
-
 /*
- * This is individual features
+ * Radix page table available
+ */
+#define MMU_FTR_TYPE_RADIX		ASM_CONST(0x00000040)
+/*
+ * individual features
  */
 /*
  * We need to clear top 16bits of va (from the remaining 64 bits )in
@@ -93,11 +96,6 @@
  */
 #define MMU_FTR_1T_SEGMENT		ASM_CONST(0x40000000)
 
-/*
- * Radix page table available
- */
-#define MMU_FTR_RADIX			ASM_CONST(0x80000000)
-
 /* MMU feature bit sets for various CPUs */
 #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	\
 	MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2
@@ -131,7 +129,7 @@ enum {
 		MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
 		MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
 #ifdef CONFIG_PPC_RADIX_MMU
-		MMU_FTR_RADIX |
+		MMU_FTR_TYPE_RADIX |
 #endif
 		0,
 };
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2e0c565754aa..0bdceef11e75 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -532,7 +532,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 #ifdef CONFIG_PPC_STD_MMU_64
 BEGIN_MMU_FTR_SECTION
 	b	2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 BEGIN_FTR_SECTION
 	clrrdi	r6,r8,28	/* get its ESID */
 	clrrdi	r9,r1,28	/* get current sp ESID */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 8bcc1b457115..2747e901fb99 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -945,7 +945,7 @@ BEGIN_MMU_FTR_SECTION
 	b	do_hash_page		/* Try to handle as hpte fault */
 MMU_FTR_SECTION_ELSE
 	b	handle_page_fault
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	.align  7
 	.globl  h_data_storage_common
@@ -976,7 +976,7 @@ BEGIN_MMU_FTR_SECTION
 	b	do_hash_page		/* Try to handle as hpte fault */
 MMU_FTR_SECTION_ELSE
 	b	handle_page_fault
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception)
 
@@ -1390,7 +1390,7 @@ slb_miss_realmode:
 #ifdef CONFIG_PPC_STD_MMU_64
 BEGIN_MMU_FTR_SECTION
 	bl	slb_allocate_realmode
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 #endif
 	/* All done -- return from exception. */
 
@@ -1404,7 +1404,7 @@ BEGIN_MMU_FTR_SECTION
 	beq-	2f
 FTR_SECTION_ELSE
 	b	2f
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 
 .machine	push
 .machine	"power4"
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 022540b9366d..60572c9cda43 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -168,7 +168,7 @@ static struct ibm_pa_feature {
 	 */
 	{CPU_FTR_TM_COMP, 0, 0,
 	 PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0},
-	{0, MMU_FTR_RADIX, 0, 0,		40, 0, 0},
+	{0, MMU_FTR_TYPE_RADIX, 0, 0,		40, 0, 0},
 };
 
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
@@ -751,7 +751,7 @@ void __init early_init_devtree(void *params)
 	 * now fixup radix MMU mode based on kernel command line
 	 */
 	if (disable_radix)
-		cur_cpu_spec->mmu_features &= ~MMU_FTR_RADIX;
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 
 	DBG(" <- early_init_devtree()\n");
 }
-- 
2.7.4

[PATCH for-4.8 06/13] powerpc/mm/hash: Add helper for finding SLBE LLP encoding

[Aneesh Kumar K.V]

Replace opencoding of the same at multiple places with the helper.
No functional change with this patch.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/mmu-hash.h | 9 +++++++++
 arch/powerpc/include/asm/kvm_book3s_64.h      | 3 +--
 arch/powerpc/mm/hash_native_64.c              | 6 ++----
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 2c2d55580ae2..6ec21aad8ccc 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -151,6 +151,15 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 	BUG();
 }
 
+static inline unsigned long get_sllp_encoding(int psize)
+{
+	unsigned long sllp;
+
+	sllp = ((mmu_psize_defs[psize].sllp & SLB_VSID_L) >> 6) |
+		((mmu_psize_defs[psize].sllp & SLB_VSID_LP) >> 4);
+	return sllp;
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 1f4497fb5b83..88d17b4ea9c8 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -181,8 +181,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 
 	switch (b_psize) {
 	case MMU_PAGE_4K:
-		sllp = ((mmu_psize_defs[a_psize].sllp & SLB_VSID_L) >> 6) |
-			((mmu_psize_defs[a_psize].sllp & SLB_VSID_LP) >> 4);
+		sllp = get_sllp_encoding(a_psize);
 		rb |= sllp << 5;	/*  AP field */
 		rb |= (va_low & 0x7ff) << 12;	/* remaining 11 bits of AVA */
 		break;
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index cb3b4c98b637..277047528a3a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -72,8 +72,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 		/* clear out bits after (52) [0....52.....63] */
 		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
-		sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
-			((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+		sllp = get_sllp_encoding(apsize);
 		va |= sllp << 5;
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
@@ -122,8 +121,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 		/* clear out bits after(52) [0....52.....63] */
 		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
-		sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
-			((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+		sllp = get_sllp_encoding(apsize);
 		va |= sllp << 5;
 		asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
 			     : : "r"(va) : "memory");
-- 
2.7.4

[PATCH for-4.8 07/13] powerpc/mm: Use hugetlb flush functions

[Aneesh Kumar K.V]

Use flush_hugetlb_page instead of flush_tlb_page when we clear flush the
pte.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/hugetlb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index e2d9f4996e5c..c5517f463ec7 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -147,7 +147,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 	pte_t pte;
 	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
-	flush_tlb_page(vma, addr);
+	flush_hugetlb_page(vma, addr);
 }
 
 static inline int huge_pte_none(pte_t pte)
-- 
2.7.4

[PATCH for-4.8 08/13] powerpc/mm: Drop multiple definition of mm_is_core_local

[Aneesh Kumar K.V]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/tlb.h | 13 +++++++++++++
 arch/powerpc/mm/tlb-radix.c    |  6 ------
 arch/powerpc/mm/tlb_nohash.c   |  6 ------
 3 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 20733fa518ae..f6f68f73e858 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -46,5 +46,18 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
 #endif
 }
 
+#ifdef CONFIG_SMP
+static inline int mm_is_core_local(struct mm_struct *mm)
+{
+	return cpumask_subset(mm_cpumask(mm),
+			      topology_sibling_cpumask(smp_processor_id()));
+}
+#else
+static inline int mm_is_core_local(struct mm_struct *mm)
+{
+	return 1;
+}
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_TLB_H */
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 6de05c59b375..4d0f03ad0996 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -165,12 +165,6 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd
 EXPORT_SYMBOL(radix__local_flush_tlb_page);
 
 #ifdef CONFIG_SMP
-static int mm_is_core_local(struct mm_struct *mm)
-{
-	return cpumask_subset(mm_cpumask(mm),
-			      topology_sibling_cpumask(smp_processor_id()));
-}
-
 void radix__flush_tlb_mm(struct mm_struct *mm)
 {
 	unsigned long pid;
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index f4668488512c..050badc0ebd3 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -215,12 +215,6 @@ EXPORT_SYMBOL(local_flush_tlb_page);
 
 static DEFINE_RAW_SPINLOCK(tlbivax_lock);
 
-static int mm_is_core_local(struct mm_struct *mm)
-{
-	return cpumask_subset(mm_cpumask(mm),
-			      topology_sibling_cpumask(smp_processor_id()));
-}
-
 struct tlb_flush_param {
 	unsigned long addr;
 	unsigned int pid;
-- 
2.7.4

[PATCH for-4.8 09/13] powerpc/mm/radix: Add tlb flush of THP ptes

[Aneesh Kumar K.V]

Instead of flushing the entire mm, implement a flush_pmd_tlb_range

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/tlbflush-radix.h | 2 ++
 arch/powerpc/include/asm/book3s/64/tlbflush.h       | 9 +++++++++
 arch/powerpc/mm/pgtable-book3s64.c                  | 4 ++--
 arch/powerpc/mm/tlb-radix.c                         | 7 +++++++
 4 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 7ee9a195fa9c..30fad5d78e30 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -12,6 +12,8 @@ static inline int mmu_get_ap(int psize)
 
 extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
 					 unsigned long end, int psize);
+extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end);
 extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end);
 extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end);
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index 96e5769b18b0..0790c4e92a64 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -7,6 +7,15 @@
 #include <asm/book3s/64/tlbflush-hash.h>
 #include <asm/book3s/64/tlbflush-radix.h>
 
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+static inline void flush_pmd_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		return radix__flush_pmd_tlb_range(vma, start, end);
+	return hash__flush_tlb_range(vma, start, end);
+}
+
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 670318766545..7bb8acffe876 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -33,7 +33,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	changed = !pmd_same(*(pmdp), entry);
 	if (changed) {
 		__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
-		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+		flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	}
 	return changed;
 }
@@ -66,7 +66,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
 	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
-	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
 	 * to prevent a parallel THP split work as expected.
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 4d0f03ad0996..456c155fe76c 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -391,3 +391,10 @@ void radix__flush_tlb_lpid(unsigned long lpid)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 EXPORT_SYMBOL(radix__flush_tlb_lpid);
+
+void radix__flush_pmd_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_2M);
+}
+EXPORT_SYMBOL(radix__flush_pmd_tlb_range);
-- 
2.7.4

[PATCH for-4.8 10/13] powerpc/mm/radix: Rename function and drop unused arg

[Aneesh Kumar K.V]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/tlbflush-radix.h | 10 +++++-----
 arch/powerpc/mm/hugetlbpage-radix.c                 |  4 ++--
 arch/powerpc/mm/tlb-radix.c                         | 16 ++++++++--------
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 30fad5d78e30..a0c7f76c13b3 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -20,20 +20,20 @@ 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_page(struct mm_struct *mm, unsigned long vmaddr,
-				    unsigned long ap, int nid);
 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,
+					      unsigned long ap);
 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_page(struct mm_struct *mm, unsigned long vmaddr,
-			      unsigned long ap, int nid);
 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,
+					unsigned long ap);
 #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(mm,addr,p,i)	radix___local_flush_tlb_page(mm,addr,p,i)
+#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_lpid_va(unsigned long lpid, unsigned long gpa,
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c
index 1e11559e1aac..0dfa1816f0c6 100644
--- a/arch/powerpc/mm/hugetlbpage-radix.c
+++ b/arch/powerpc/mm/hugetlbpage-radix.c
@@ -20,7 +20,7 @@ void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 		WARN(1, "Wrong huge page shift\n");
 		return ;
 	}
-	radix___flush_tlb_page(vma->vm_mm, vmaddr, ap, 0);
+	radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, ap);
 }
 
 void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
@@ -37,7 +37,7 @@ void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long v
 		WARN(1, "Wrong huge page shift\n");
 		return ;
 	}
-	radix___local_flush_tlb_page(vma->vm_mm, vmaddr, ap, 0);
+	radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, ap);
 }
 
 /*
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 456c155fe76c..fb9974abdde7 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -140,8 +140,8 @@ void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
 
-void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
-			    unsigned long ap, int nid)
+void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
+				       unsigned long ap)
 {
 	unsigned long pid;
 
@@ -159,8 +159,8 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd
 	if (vma && is_vm_hugetlb_page(vma))
 		return __local_flush_hugetlb_page(vma, vmaddr);
 #endif
-	radix___local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
-			       mmu_get_ap(mmu_virtual_psize), 0);
+	radix__local_flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
+					  mmu_get_ap(mmu_virtual_psize));
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_page);
 
@@ -215,8 +215,8 @@ no_context:
 }
 EXPORT_SYMBOL(radix__flush_tlb_pwc);
 
-void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
-		       unsigned long ap, int nid)
+void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
+				 unsigned long ap)
 {
 	unsigned long pid;
 
@@ -244,8 +244,8 @@ void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 	if (vma && is_vm_hugetlb_page(vma))
 		return flush_hugetlb_page(vma, vmaddr);
 #endif
-	radix___flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
-			 mmu_get_ap(mmu_virtual_psize), 0);
+	radix__flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
+				    mmu_get_ap(mmu_virtual_psize));
 }
 EXPORT_SYMBOL(radix__flush_tlb_page);
 
-- 
2.7.4

[PATCH for-4.8 11/13] powerpc/mm/radix/hugetlb: Add helper for finding page size from hstate

[Aneesh Kumar K.V]

Use the helper instead of open coding the same at multiple place

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/hugetlb-radix.h | 15 +++++++++++
 .../powerpc/include/asm/book3s/64/tlbflush-radix.h |  4 +--
 arch/powerpc/mm/hugetlbpage-radix.c                | 29 ++++++----------------
 arch/powerpc/mm/tlb-radix.c                        | 10 +++++---
 4 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h b/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h
index 60f47649306f..c45189aa7476 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h
@@ -11,4 +11,19 @@ extern unsigned long
 radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				unsigned long len, unsigned long pgoff,
 				unsigned long flags);
+
+static inline int hstate_get_psize(struct hstate *hstate)
+{
+	unsigned long shift;
+
+	shift = huge_page_shift(hstate);
+	if (shift == mmu_psize_defs[MMU_PAGE_2M].shift)
+		return MMU_PAGE_2M;
+	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
+		return MMU_PAGE_1G;
+	else {
+		WARN(1, "Wrong huge page shift\n");
+		return mmu_virtual_psize;
+	}
+}
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index a0c7f76c13b3..10eb0d1e3140 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -22,14 +22,14 @@ 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,
-					      unsigned long ap);
+					      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,
-					unsigned long ap);
+					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)
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c
index 0dfa1816f0c6..1eca0deaf89b 100644
--- a/arch/powerpc/mm/hugetlbpage-radix.c
+++ b/arch/powerpc/mm/hugetlbpage-radix.c
@@ -5,39 +5,24 @@
 #include <asm/cacheflush.h>
 #include <asm/machdep.h>
 #include <asm/mman.h>
+#include <asm/tlb.h>
 
 void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
-	unsigned long ap, shift;
+	int psize;
 	struct hstate *hstate = hstate_file(vma->vm_file);
 
-	shift = huge_page_shift(hstate);
-	if (shift == mmu_psize_defs[MMU_PAGE_2M].shift)
-		ap = mmu_get_ap(MMU_PAGE_2M);
-	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
-		ap = mmu_get_ap(MMU_PAGE_1G);
-	else {
-		WARN(1, "Wrong huge page shift\n");
-		return ;
-	}
-	radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, ap);
+	psize = hstate_get_psize(hstate);
+	radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, psize);
 }
 
 void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
-	unsigned long ap, shift;
+	int psize;
 	struct hstate *hstate = hstate_file(vma->vm_file);
 
-	shift = huge_page_shift(hstate);
-	if (shift == mmu_psize_defs[MMU_PAGE_2M].shift)
-		ap = mmu_get_ap(MMU_PAGE_2M);
-	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
-		ap = mmu_get_ap(MMU_PAGE_1G);
-	else {
-		WARN(1, "Wrong huge page shift\n");
-		return ;
-	}
-	radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, ap);
+	psize = hstate_get_psize(hstate);
+	radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, psize);
 }
 
 /*
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index fb9974abdde7..48df05ef5231 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -141,9 +141,10 @@ void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
 EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
 
 void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
-				       unsigned long ap)
+				       int psize)
 {
 	unsigned long pid;
+	unsigned long ap = mmu_get_ap(psize);
 
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
@@ -160,7 +161,7 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd
 		return __local_flush_hugetlb_page(vma, vmaddr);
 #endif
 	radix__local_flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
-					  mmu_get_ap(mmu_virtual_psize));
+					  mmu_virtual_psize);
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_page);
 
@@ -216,9 +217,10 @@ no_context:
 EXPORT_SYMBOL(radix__flush_tlb_pwc);
 
 void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
-				 unsigned long ap)
+				 int psize)
 {
 	unsigned long pid;
+	unsigned long ap = mmu_get_ap(psize);
 
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
@@ -245,7 +247,7 @@ void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 		return flush_hugetlb_page(vma, vmaddr);
 #endif
 	radix__flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
-				    mmu_get_ap(mmu_virtual_psize));
+				    mmu_virtual_psize);
 }
 EXPORT_SYMBOL(radix__flush_tlb_page);
 
-- 
2.7.4

[PATCH for-4.8 12/13] powerpc/mm/hugetlb: Add flush_hugetlb_tlb_range

[Aneesh Kumar K.V]

Some archs like ppc64 need to do special things when flushing tlb for
hugepage. Add a new helper to flush hugetlb tlb range. This helps us to
avoid flushing the entire tlb mapping for the pid.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/tlbflush-radix.h |  2 ++
 arch/powerpc/include/asm/book3s/64/tlbflush.h       | 10 ++++++++++
 arch/powerpc/mm/hugetlbpage-radix.c                 | 10 ++++++++++
 mm/hugetlb.c                                        | 10 +++++++++-
 4 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 10eb0d1e3140..65037762b120 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -10,6 +10,8 @@ static inline int mmu_get_ap(int psize)
 	return mmu_psize_defs[psize].ap;
 }
 
+extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					   unsigned long start, unsigned long end);
 extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
 					 unsigned long end, int psize);
 extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index 0790c4e92a64..146b269de8fa 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -16,6 +16,16 @@ static inline void flush_pmd_tlb_range(struct vm_area_struct *vma,
 	return hash__flush_tlb_range(vma, start, end);
 }
 
+#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					   unsigned long start,
+					   unsigned long end)
+{
+	if (radix_enabled())
+		return radix__flush_hugetlb_tlb_range(vma, start, end);
+	return hash__flush_tlb_range(vma, start, end);
+}
+
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c
index 1eca0deaf89b..35254a678456 100644
--- a/arch/powerpc/mm/hugetlbpage-radix.c
+++ b/arch/powerpc/mm/hugetlbpage-radix.c
@@ -25,6 +25,16 @@ void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long v
 	radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, psize);
 }
 
+void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start,
+				   unsigned long end)
+{
+	int psize;
+	struct hstate *hstate = hstate_file(vma->vm_file);
+
+	psize = hstate_get_psize(hstate);
+	radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
+}
+
 /*
  * A vairant of hugetlb_get_unmapped_area doing topdown search
  * FIXME!! should we do as x86 does or non hugetlb area does ?
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f4b9e73efbc9..5c0555ac76f5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3936,6 +3936,14 @@ same_page:
 	return i ? i : -EFAULT;
 }
 
+#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+/*
+ * ARCHes with special requirements for evicting HUGETLB backing TLB entries can
+ * implement this.
+ */
+#define flush_hugetlb_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
+#endif
+
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot)
 {
@@ -3996,7 +4004,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * once we release i_mmap_rwsem, another task can do the final put_page
 	 * and that page table be reused and filled with junk.
 	 */
-	flush_tlb_range(vma, start, end);
+	flush_hugetlb_tlb_range(vma, start, end);
 	mmu_notifier_invalidate_range(mm, start, end);
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	mmu_notifier_invalidate_range_end(mm, start, end);
-- 
2.7.4

[PATCH for-4.8 13/13] powerpc/mm: remove flush_tlb_page_nohash

[Aneesh Kumar K.V]

This should be same as flush_tlb_page except for hash32. For hash32
I guess the existing code is wrong, because we don't seem to be
flushing tlb for Hash != 0 case at all. Fix this by switching to
calling flush_tlb_page() which does the right thing by flushing
tlb for both hash and nohash case with hash32

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/tlbflush-hash.h |  5 -----
 arch/powerpc/include/asm/book3s/64/tlbflush.h      |  8 --------
 arch/powerpc/include/asm/tlbflush.h                |  1 -
 arch/powerpc/mm/pgtable.c                          |  2 +-
 arch/powerpc/mm/tlb_hash32.c                       | 11 -----------
 5 files changed, 1 insertion(+), 26 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
index f12ddf5e8de5..2f6373144e2c 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
@@ -75,11 +75,6 @@ static inline void hash__flush_tlb_page(struct vm_area_struct *vma,
 {
 }
 
-static inline void hash__flush_tlb_page_nohash(struct vm_area_struct *vma,
-					   unsigned long vmaddr)
-{
-}
-
 static inline void hash__flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index 146b269de8fa..72b925f97bab 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -57,14 +57,6 @@ static inline void local_flush_tlb_page(struct vm_area_struct *vma,
 	return hash__local_flush_tlb_page(vma, vmaddr);
 }
 
-static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
-					 unsigned long vmaddr)
-{
-	if (radix_enabled())
-		return radix__flush_tlb_page(vma, vmaddr);
-	return hash__flush_tlb_page_nohash(vma, vmaddr);
-}
-
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (radix_enabled())
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 1b38eea28e5a..13dbcd41885e 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -54,7 +54,6 @@ extern void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 #define flush_tlb_page(vma,addr)	local_flush_tlb_page(vma,addr)
 #define __flush_tlb_page(mm,addr,p,i)	__local_flush_tlb_page(mm,addr,p,i)
 #endif
-#define flush_tlb_page_nohash(vma,addr)	flush_tlb_page(vma,addr)
 
 #elif defined(CONFIG_PPC_STD_MMU_32)
 
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 88a307504b5a..0b6fb244d0a1 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -225,7 +225,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 		if (!is_vm_hugetlb_page(vma))
 			assert_pte_locked(vma->vm_mm, address);
 		__ptep_set_access_flags(ptep, entry);
-		flush_tlb_page_nohash(vma, address);
+		flush_tlb_page(vma, address);
 	}
 	return changed;
 }
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index 558e30cce33e..702d7689d714 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -49,17 +49,6 @@ void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr)
 EXPORT_SYMBOL(flush_hash_entry);
 
 /*
- * Called by ptep_set_access_flags, must flush on CPUs for which the
- * DSI handler can't just "fixup" the TLB on a write fault
- */
-void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr)
-{
-	if (Hash != 0)
-		return;
-	_tlbie(addr);
-}
-
-/*
  * Called at the end of a mmu_gather operation to make sure the
  * TLB flush is completely done.
  */
-- 
2.7.4