[PATCH v4 0/3] Add update_mmu_tlb_range() to simplify code

[PATCH v4 0/3] Add update_mmu_tlb_range() to simplify code

[Bang Li]

This series of commits mainly adds the update_mmu_tlb_range() to
batch update tlb in an address range and implement update_mmu_tlb()
using update_mmu_tlb_range().

After the commit 19eaf44954df ("mm: thp: support allocation of anonymous
multi-size THP"), We may need to batch update tlb of a certain address
range by calling update_mmu_tlb() in a loop. Using the
update_mmu_tlb_range(), we can simplify the code and possibly reduce the
execution of some unnecessary code in some architectures.

Thanks,
Bang

Changes since v3 [3]:
 - Add acked-by from David Hildenbrand (patch #2 and patch #3) - thanks!
 - Add reviewed-by from Lance Yang (patch #3) - thanks!
 - Move the general architecture update_mmu_tlb_range() from patch #2 to
   patch #1 (per David)
 - Update patch #2 commit log (per David)

Changes since v2 [2]:
 - Use generic architecture to implement update_mmu_tlb() (per Ryan)

Changes since v1 [1]:
 - Add __HAVE_ARCH_UPDATE_MMU_TLB_RANGE macro (per Lance Yang)

[1] https://lore.kernel.org/linux-mm/20240429103346.59115-1-libang.li@antgroup.com/
[2] https://lore.kernel.org/linux-mm/20240506155120.83105-1-libang.li@antgroup.com/
[3] https://lore.kernel.org/linux-mm/20240518074914.52170-1-libang.li@antgroup.com/

Bang Li (3):
  mm: Add update_mmu_tlb_range()
  mm: implement update_mmu_tlb() using update_mmu_tlb_range()
  mm: Use update_mmu_tlb_range() to simplify code

 arch/loongarch/include/asm/pgtable.h |  4 ++--
 arch/mips/include/asm/pgtable.h      |  4 ++--
 arch/riscv/include/asm/pgtable.h     |  4 ++--
 arch/xtensa/include/asm/pgtable.h    |  6 +++---
 arch/xtensa/mm/tlb.c                 |  6 +++---
 include/linux/pgtable.h              | 11 ++++++++---
 mm/memory.c                          |  4 +---
 7 files changed, 21 insertions(+), 18 deletions(-)

-- 
2.19.1.6.gb485710b

[PATCH v4 1/3] mm: Add update_mmu_tlb_range()

[Bang Li]

Added update_mmu_tlb_range(), we can batch update tlb of an
address range.

Signed-off-by: Bang Li <libang.li@antgroup.com>
---
 arch/loongarch/include/asm/pgtable.h | 2 ++
 arch/mips/include/asm/pgtable.h      | 2 ++
 arch/riscv/include/asm/pgtable.h     | 2 ++
 arch/xtensa/include/asm/pgtable.h    | 3 +++
 arch/xtensa/mm/tlb.c                 | 6 ++++++
 include/linux/pgtable.h              | 7 +++++++
 6 files changed, 22 insertions(+)

diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index af3acdf3481a..5ccc2a3a6f7a 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -469,6 +469,8 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 
 #define __HAVE_ARCH_UPDATE_MMU_TLB
 #define update_mmu_tlb	update_mmu_cache
+#define update_mmu_tlb_range(vma, addr, ptep, nr) \
+	update_mmu_cache_range(NULL, vma, addr, ptep, nr)
 
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmdp)
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index e27a4c83c548..0891ad7d43b6 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -596,6 +596,8 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 
 #define	__HAVE_ARCH_UPDATE_MMU_TLB
 #define update_mmu_tlb	update_mmu_cache
+#define update_mmu_tlb_range(vma, address, ptep, nr) \
+	update_mmu_cache_range(NULL, vma, address, ptep, nr)
 
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 	unsigned long address, pmd_t *pmdp)
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 55a7c3ec246b..4630815b0253 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -491,6 +491,8 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 
 #define __HAVE_ARCH_UPDATE_MMU_TLB
 #define update_mmu_tlb update_mmu_cache
+#define update_mmu_tlb_range(vma, addr, ptep, nr) \
+	update_mmu_cache_range(NULL, vma, addr, ptep, nr)
 
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmdp)
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 9a7e5e57ee9a..436158bd9030 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -413,6 +413,9 @@ typedef pte_t *pte_addr_t;
 void update_mmu_tlb(struct vm_area_struct *vma,
 		    unsigned long address, pte_t *ptep);
 #define __HAVE_ARCH_UPDATE_MMU_TLB
+void update_mmu_tlb_range(struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep, unsigned int nr);
+#define update_mmu_tlb_range update_mmu_tlb_range
 
 #endif /* !defined (__ASSEMBLY__) */
 
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index d8b60d6e50a8..05efba86b870 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -169,6 +169,12 @@ void update_mmu_tlb(struct vm_area_struct *vma,
 	local_flush_tlb_page(vma, address);
 }
 
+void update_mmu_tlb_range(struct vm_area_struct *vma,
+			unsigned long address, pte_t *ptep, unsigned int nr)
+{
+	local_flush_tlb_range(vma, address, address + PAGE_SIZE * nr);
+}
+
 #ifdef CONFIG_DEBUG_TLB_SANITY
 
 static unsigned get_pte_for_vaddr(unsigned vaddr)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 18019f037bae..17d1caee39ab 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -729,6 +729,13 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr,
  * fault. This function updates TLB only, do nothing with cache or others.
  * It is the difference with function update_mmu_cache.
  */
+#ifndef update_mmu_tlb_range
+static inline void update_mmu_tlb_range(struct vm_area_struct *vma,
+				unsigned long address, pte_t *ptep, unsigned int nr)
+{
+}
+#endif
+
 #ifndef __HAVE_ARCH_UPDATE_MMU_TLB
 static inline void update_mmu_tlb(struct vm_area_struct *vma,
 				unsigned long address, pte_t *ptep)
-- 
2.19.1.6.gb485710b

[PATCH v4 2/3] mm: implement update_mmu_tlb() using update_mmu_tlb_range()

[Bang Li]

Let's make update_mmu_tlb() simply a generic wrapper around
update_mmu_tlb_range(). Only the latter can now be overridden by the
architecture. We can now remove __HAVE_ARCH_UPDATE_MMU_TLB as well.

Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Bang Li <libang.li@antgroup.com>
---
 arch/loongarch/include/asm/pgtable.h | 2 --
 arch/mips/include/asm/pgtable.h      | 2 --
 arch/riscv/include/asm/pgtable.h     | 2 --
 arch/xtensa/include/asm/pgtable.h    | 3 ---
 arch/xtensa/mm/tlb.c                 | 6 ------
 include/linux/pgtable.h              | 4 +---
 6 files changed, 1 insertion(+), 18 deletions(-)

diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 5ccc2a3a6f7a..161dd6e10479 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -467,8 +467,6 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 #define update_mmu_cache(vma, addr, ptep) \
 	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
 
-#define __HAVE_ARCH_UPDATE_MMU_TLB
-#define update_mmu_tlb	update_mmu_cache
 #define update_mmu_tlb_range(vma, addr, ptep, nr) \
 	update_mmu_cache_range(NULL, vma, addr, ptep, nr)
 
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 0891ad7d43b6..c29a551eb0ca 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -594,8 +594,6 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 #define update_mmu_cache(vma, address, ptep) \
 	update_mmu_cache_range(NULL, vma, address, ptep, 1)
 
-#define	__HAVE_ARCH_UPDATE_MMU_TLB
-#define update_mmu_tlb	update_mmu_cache
 #define update_mmu_tlb_range(vma, address, ptep, nr) \
 	update_mmu_cache_range(NULL, vma, address, ptep, nr)
 
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 4630815b0253..ddfd6f8cdcb3 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -489,8 +489,6 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 #define update_mmu_cache(vma, addr, ptep) \
 	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
 
-#define __HAVE_ARCH_UPDATE_MMU_TLB
-#define update_mmu_tlb update_mmu_cache
 #define update_mmu_tlb_range(vma, addr, ptep, nr) \
 	update_mmu_cache_range(NULL, vma, addr, ptep, nr)
 
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 436158bd9030..1647a7cc3fbf 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -410,9 +410,6 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 
 typedef pte_t *pte_addr_t;
 
-void update_mmu_tlb(struct vm_area_struct *vma,
-		    unsigned long address, pte_t *ptep);
-#define __HAVE_ARCH_UPDATE_MMU_TLB
 void update_mmu_tlb_range(struct vm_area_struct *vma,
 		unsigned long address, pte_t *ptep, unsigned int nr);
 #define update_mmu_tlb_range update_mmu_tlb_range
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index 05efba86b870..0a1a815dc796 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -163,12 +163,6 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
-void update_mmu_tlb(struct vm_area_struct *vma,
-		    unsigned long address, pte_t *ptep)
-{
-	local_flush_tlb_page(vma, address);
-}
-
 void update_mmu_tlb_range(struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, unsigned int nr)
 {
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 17d1caee39ab..117b807e3f89 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -736,13 +736,11 @@ static inline void update_mmu_tlb_range(struct vm_area_struct *vma,
 }
 #endif
 
-#ifndef __HAVE_ARCH_UPDATE_MMU_TLB
 static inline void update_mmu_tlb(struct vm_area_struct *vma,
 				unsigned long address, pte_t *ptep)
 {
+	update_mmu_tlb_range(vma, address, ptep, 1);
 }
-#define __HAVE_ARCH_UPDATE_MMU_TLB
-#endif
 
 /*
  * Some architectures may be able to avoid expensive synchronization
-- 
2.19.1.6.gb485710b

[PATCH v4 3/3] mm: Use update_mmu_tlb_range() to simplify code

[Bang Li]

Let us simplify the code by update_mmu_tlb_range().

Reviewed-by: Lance Yang <ioworker0@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Bang Li <libang.li@antgroup.com>
---
 mm/memory.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index b5453b86ec4b..1297474546d6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4416,7 +4416,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	vm_fault_t ret = 0;
 	int nr_pages = 1;
 	pte_t entry;
-	int i;
 
 	/* File mapping without ->vm_ops ? */
 	if (vma->vm_flags & VM_SHARED)
@@ -4486,8 +4485,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 		update_mmu_tlb(vma, addr, vmf->pte);
 		goto release;
 	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
-		for (i = 0; i < nr_pages; i++)
-			update_mmu_tlb(vma, addr + PAGE_SIZE * i, vmf->pte + i);
+		update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages);
 		goto release;
 	}
 
-- 
2.19.1.6.gb485710b