[PATCH 0/7] TLB flush update for radix

[PATCH 0/7] TLB flush update for radix

[Aneesh Kumar K.V]

Hi,

This patch series introduce range based tlb flush and use the same for radix
implementation. We still need to handle the mmu_gather related tlb flush.
That will be done in a later patch.

Aneesh Kumar K.V (7):
  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/powerpc/include/asm/book3s/64/hugetlb-radix.h | 15 +++++
 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/tlb.h                     | 13 ++++
 arch/powerpc/include/asm/tlbflush.h                |  1 -
 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                        | 78 ++++++++++++++++++----
 arch/powerpc/mm/tlb_hash32.c                       | 11 ---
 arch/powerpc/mm/tlb_nohash.c                       |  6 --
 mm/hugetlb.c                                       | 10 ++-
 14 files changed, 152 insertions(+), 77 deletions(-)

-- 
2.7.4

[PATCH 1/7] 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 2/7] 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 0fdaf93a3e09..5807f5d72e1b 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -152,12 +152,6 @@ 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 int 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 3/7] 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>
---
 .../powerpc/include/asm/book3s/64/tlbflush-radix.h |  4 ++
 arch/powerpc/include/asm/book3s/64/tlbflush.h      |  9 ++++
 arch/powerpc/mm/pgtable-book3s64.c                 |  4 +-
 arch/powerpc/mm/tlb-radix.c                        | 54 ++++++++++++++++++++++
 4 files changed, 69 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 13ef38828dfe..823528d34688 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -10,6 +10,10 @@ 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_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 d98424ae356c..f0d6c9d38916 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 5807f5d72e1b..fe2fc58d2e00 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -243,3 +243,57 @@ void radix__tlb_flush(struct mmu_gather *tlb)
 	struct mm_struct *mm = tlb->mm;
 	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 int 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);
+		else
+			_tlbie_pid(pid);
+		goto err_out;
+	}
+	for (addr = start; addr < end; addr += page_size) {
+
+		if (local)
+			_tlbiel_va(addr, pid, ap);
+		else {
+			if (lock_tlbie)
+				raw_spin_lock(&native_tlbie_lock);
+			_tlbie_va(addr, pid, ap);
+			if (lock_tlbie)
+				raw_spin_unlock(&native_tlbie_lock);
+		}
+	}
+err_out:
+	preempt_enable();
+}
+
+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 4/7] 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 823528d34688..07b2e0031dad 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -20,18 +20,18 @@ 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_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_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)
 #endif
 
 #endif
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 fe2fc58d2e00..b1dc4675925d 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -127,8 +127,8 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm)
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 
-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 int pid;
 
@@ -146,8 +146,8 @@ 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);
 
@@ -176,8 +176,8 @@ no_context:
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
-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 int pid;
 
@@ -205,8 +205,8 @@ 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 5/7] 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 07b2e0031dad..68839e6adcf1 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -21,13 +21,13 @@ 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_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_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 b1dc4675925d..7bc3d1402c63 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -128,9 +128,10 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm)
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 
 void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
-				       unsigned long ap)
+				       int psize)
 {
 	unsigned int pid;
+	unsigned long ap = mmu_get_ap(psize);
 
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
@@ -147,7 +148,7 @@ 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);
 
@@ -177,9 +178,10 @@ no_context:
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
 void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
-				 unsigned long ap)
+				 int psize)
 {
 	unsigned int pid;
+	unsigned long ap = mmu_get_ap(psize);
 
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
@@ -206,7 +208,7 @@ 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 6/7] 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 68839e6adcf1..73953a44d4e3 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 f0d6c9d38916..3b3e5e944af7 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 19d0d08b396f..076a57ee8790 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3893,6 +3893,14 @@ 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)
 {
@@ -3953,7 +3961,7 @@ 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 7/7] 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 3b3e5e944af7..ea29cc3318d2 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