diff mbox

[v3,1/6] powerpc/mm: update ptep_set_access_flag to not do full mm tlb flush

Message ID 20161121183322.14585-1-aneesh.kumar@linux.vnet.ibm.com (mailing list archive)
State Changes Requested
Headers show

Commit Message

Aneesh Kumar K.V Nov. 21, 2016, 6:33 p.m. UTC
When we are updating pte, we just need to flush the tlb mapping for
that pte. Right now we do a full mm flush because we don't track page
size. Update the interface to track the page size and use that to
do the right tlb flush.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/32/pgtable.h |  4 +++-
 arch/powerpc/include/asm/book3s/64/pgtable.h |  7 +++++--
 arch/powerpc/include/asm/book3s/64/radix.h   | 14 +++++++-------
 arch/powerpc/include/asm/nohash/32/pgtable.h |  4 +++-
 arch/powerpc/include/asm/nohash/64/pgtable.h |  4 +++-
 arch/powerpc/mm/pgtable-book3s64.c           |  3 ++-
 arch/powerpc/mm/pgtable-radix.c              | 16 ++++++++++++++++
 arch/powerpc/mm/pgtable.c                    | 10 ++++++++--
 arch/powerpc/mm/tlb-radix.c                  | 15 ---------------
 9 files changed, 47 insertions(+), 30 deletions(-)

Comments

Balbir Singh Nov. 22, 2016, 2:55 a.m. UTC | #1
On 22/11/16 05:33, Aneesh Kumar K.V wrote:
> When we are updating pte, we just need to flush the tlb mapping for
> that pte. Right now we do a full mm flush because we don't track page
> size. Update the interface to track the page size and use that to
> do the right tlb flush.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> ---
>  arch/powerpc/include/asm/book3s/32/pgtable.h |  4 +++-
>  arch/powerpc/include/asm/book3s/64/pgtable.h |  7 +++++--
>  arch/powerpc/include/asm/book3s/64/radix.h   | 14 +++++++-------
>  arch/powerpc/include/asm/nohash/32/pgtable.h |  4 +++-
>  arch/powerpc/include/asm/nohash/64/pgtable.h |  4 +++-
>  arch/powerpc/mm/pgtable-book3s64.c           |  3 ++-
>  arch/powerpc/mm/pgtable-radix.c              | 16 ++++++++++++++++
>  arch/powerpc/mm/pgtable.c                    | 10 ++++++++--
>  arch/powerpc/mm/tlb-radix.c                  | 15 ---------------
>  9 files changed, 47 insertions(+), 30 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
> index 6b8b2d57fdc8..0713626e9189 100644
> --- a/arch/powerpc/include/asm/book3s/32/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
> @@ -224,7 +224,9 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
>  
>  
>  static inline void __ptep_set_access_flags(struct mm_struct *mm,
> -					   pte_t *ptep, pte_t entry)
> +					   pte_t *ptep, pte_t entry,
> +					   unsigned long address,
> +					   unsigned long pg_sz)

I wonder if the change can be limited in scope by passing the struct vma instead
of struct mm as the first argument and not passing pg_sz (I don't like that
name at all, page_size if we decide to do it, please). Then extract the mm from
vma->mm


Balbir Singh.
Aneesh Kumar K.V Nov. 22, 2016, 5:57 a.m. UTC | #2
Balbir Singh <bsingharora@gmail.com> writes:

> On 22/11/16 05:33, Aneesh Kumar K.V wrote:
>> When we are updating pte, we just need to flush the tlb mapping for
>> that pte. Right now we do a full mm flush because we don't track page
>> size. Update the interface to track the page size and use that to
>> do the right tlb flush.
>> 
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
>> ---
>>  arch/powerpc/include/asm/book3s/32/pgtable.h |  4 +++-
>>  arch/powerpc/include/asm/book3s/64/pgtable.h |  7 +++++--
>>  arch/powerpc/include/asm/book3s/64/radix.h   | 14 +++++++-------
>>  arch/powerpc/include/asm/nohash/32/pgtable.h |  4 +++-
>>  arch/powerpc/include/asm/nohash/64/pgtable.h |  4 +++-
>>  arch/powerpc/mm/pgtable-book3s64.c           |  3 ++-
>>  arch/powerpc/mm/pgtable-radix.c              | 16 ++++++++++++++++
>>  arch/powerpc/mm/pgtable.c                    | 10 ++++++++--
>>  arch/powerpc/mm/tlb-radix.c                  | 15 ---------------
>>  9 files changed, 47 insertions(+), 30 deletions(-)
>> 
>> diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
>> index 6b8b2d57fdc8..0713626e9189 100644
>> --- a/arch/powerpc/include/asm/book3s/32/pgtable.h
>> +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
>> @@ -224,7 +224,9 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
>>  
>>  
>>  static inline void __ptep_set_access_flags(struct mm_struct *mm,
>> -					   pte_t *ptep, pte_t entry)
>> +					   pte_t *ptep, pte_t entry,
>> +					   unsigned long address,
>> +					   unsigned long pg_sz)
>
> I wonder if the change can be limited in scope by passing the struct vma instead
> of struct mm as the first argument and not passing pg_sz (I don't like that
> name at all, page_size if we decide to do it, please). Then extract the mm from
> vma->mm
>

https://lkml.kernel.org/r/20161114152020.4608-1-aneesh.kumar@linux.vnet.ibm.com

That patch series go on top of this series. The idea of splitting this
into two is to make it easy to backport this series if needed to older
kernels.


-aneesh
diff mbox

Patch

diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 6b8b2d57fdc8..0713626e9189 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -224,7 +224,9 @@  static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 
 
 static inline void __ptep_set_access_flags(struct mm_struct *mm,
-					   pte_t *ptep, pte_t entry)
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address,
+					   unsigned long pg_sz)
 {
 	unsigned long set = pte_val(entry) &
 		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 86870c11917b..46d739457d68 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -580,10 +580,13 @@  static inline bool check_pte_access(unsigned long access, unsigned long ptev)
  */
 
 static inline void __ptep_set_access_flags(struct mm_struct *mm,
-					   pte_t *ptep, pte_t entry)
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address,
+					   unsigned long pg_sz)
 {
 	if (radix_enabled())
-		return radix__ptep_set_access_flags(mm, ptep, entry);
+		return radix__ptep_set_access_flags(mm, ptep, entry,
+						    address, pg_sz);
 	return hash__ptep_set_access_flags(ptep, entry);
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 2a46dea8e1b1..279b2f68e00f 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -110,6 +110,7 @@ 
 #define RADIX_PUD_TABLE_SIZE	(sizeof(pud_t) << RADIX_PUD_INDEX_SIZE)
 #define RADIX_PGD_TABLE_SIZE	(sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE)
 
+extern int radix_get_mmu_psize(unsigned long pg_sz);
 static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
 					       unsigned long set)
 {
@@ -167,7 +168,9 @@  static inline unsigned long radix__pte_update(struct mm_struct *mm,
  * function doesn't need to invalidate tlb.
  */
 static inline void radix__ptep_set_access_flags(struct mm_struct *mm,
-						pte_t *ptep, pte_t entry)
+						pte_t *ptep, pte_t entry,
+						unsigned long address,
+						unsigned long pg_sz)
 {
 
 	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED |
@@ -175,6 +178,7 @@  static inline void radix__ptep_set_access_flags(struct mm_struct *mm,
 
 	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
 
+		int psize;
 		unsigned long old_pte, new_pte;
 
 		old_pte = __radix_pte_update(ptep, ~0, 0);
@@ -183,12 +187,8 @@  static inline void radix__ptep_set_access_flags(struct mm_struct *mm,
 		 * new value of pte
 		 */
 		new_pte = old_pte | set;
-
-		/*
-		 * For now let's do heavy pid flush
-		 * radix__flush_tlb_page_psize(mm, addr, mmu_virtual_psize);
-		 */
-		radix__flush_tlb_mm(mm);
+		psize = radix_get_mmu_psize(pg_sz);
+		radix__flush_tlb_page_psize(mm, address, psize);
 
 		__radix_pte_update(ptep, 0, new_pte);
 	} else
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index c219ef7be53b..24ee66bf7223 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -268,7 +268,9 @@  static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 
 
 static inline void __ptep_set_access_flags(struct mm_struct *mm,
-					   pte_t *ptep, pte_t entry)
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address,
+					   unsigned long pg_sz)
 {
 	unsigned long set = pte_val(entry) &
 		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 653a1838469d..86d49dc60ec6 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -301,7 +301,9 @@  static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
  * function doesn't need to flush the hash entry
  */
 static inline void __ptep_set_access_flags(struct mm_struct *mm,
-					   pte_t *ptep, pte_t entry)
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address,
+					   unsigned long pg_sz)
 {
 	unsigned long bits = pte_val(entry) &
 		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index f4f437cbabf1..5c7c501b7cae 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -35,7 +35,8 @@  int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 #endif
 	changed = !pmd_same(*(pmdp), entry);
 	if (changed) {
-		__ptep_set_access_flags(vma->vm_mm, pmdp_ptep(pmdp), pmd_pte(entry));
+		__ptep_set_access_flags(vma->vm_mm, pmdp_ptep(pmdp), pmd_pte(entry),
+					address, HPAGE_PMD_SIZE);
 		flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	}
 	return changed;
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 688b54517655..416918005395 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -222,6 +222,22 @@  static int __init get_idx_from_shift(unsigned int shift)
 	return idx;
 }
 
+int radix_get_mmu_psize(unsigned long page_size)
+{
+	int psize;
+
+	if (page_size == (1UL << mmu_psize_defs[mmu_virtual_psize].shift))
+		psize = mmu_virtual_psize;
+	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_2M].shift))
+		psize = MMU_PAGE_2M;
+	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_1G].shift))
+		psize = MMU_PAGE_1G;
+	else
+		return -1;
+	return psize;
+}
+
+
 static int __init radix_dt_scan_page_sizes(unsigned long node,
 					   const char *uname, int depth,
 					   void *data)
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 911fdfb63ec1..a9ec0d8f1bcf 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -219,12 +219,18 @@  int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 			  pte_t *ptep, pte_t entry, int dirty)
 {
 	int changed;
+	unsigned long pg_sz;
+
 	entry = set_access_flags_filter(entry, vma, dirty);
 	changed = !pte_same(*(ptep), entry);
 	if (changed) {
-		if (!is_vm_hugetlb_page(vma))
+		if (!is_vm_hugetlb_page(vma)) {
+			pg_sz = PAGE_SIZE;
 			assert_pte_locked(vma->vm_mm, address);
-		__ptep_set_access_flags(vma->vm_mm, ptep, entry);
+		} else
+			pg_sz = huge_page_size(hstate_vma(vma));
+		__ptep_set_access_flags(vma->vm_mm, ptep, entry,
+					address, pg_sz);
 		flush_tlb_page(vma, address);
 	}
 	return changed;
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 3493cf4e0452..81a9f6390f64 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -282,21 +282,6 @@  void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 }
 EXPORT_SYMBOL(radix__flush_tlb_range);
 
-static int radix_get_mmu_psize(int page_size)
-{
-	int psize;
-
-	if (page_size == (1UL << mmu_psize_defs[mmu_virtual_psize].shift))
-		psize = mmu_virtual_psize;
-	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_2M].shift))
-		psize = MMU_PAGE_2M;
-	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_1G].shift))
-		psize = MMU_PAGE_1G;
-	else
-		return -1;
-	return psize;
-}
-
 void radix__tlb_flush(struct mmu_gather *tlb)
 {
 	int psize = 0;