mmu_gather: Remove per arch tlb_{start,end}_vma()

Scattered across the archs are 3 basic forms of tlb_{start,end}_vma().
Provide two new MMU_GATHER_knobs to enumerate them and remove the per
arch tlb_{start,end}_vma() implementations.

 - MMU_GATHER_NO_FLUSH_CACHE indicates the arch has flush_cache_range()
   but does *NOT* want to call it for each VMA.

 - MMU_GATHER_MERGE_VMAS indicates the arch wants to merge the
   invalidate across multiple VMAs if possible.

With these it is possible to capture the three forms:

  1) empty stubs;
     select MMU_GATHER_NO_FLUSH_CACHE and MMU_GATHER_MERGE_VMAS

  2) start: flush_cache_range(), end: empty;
     select MMU_GATHER_MERGE_VMAS

  3) start: flush_cache_range(), end: flush_tlb_range();
     default

Obviously, if the architecture does not have flush_cache_range() then
it also doesn't need to select MMU_GATHER_NO_FLUSH_CACHE.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will@kernel.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

12 files changed, 13 insertions, 33 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index fcf9a41a4ef5..71b9272acb28 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -438,6 +438,13 @@ config MMU_GATHER_PAGE_SIZE
 
 config MMU_GATHER_NO_RANGE
 	bool
+	select MMU_GATHER_MERGE_VMAS
+
+config MMU_GATHER_NO_FLUSH_CACHE
+	bool
+
+config MMU_GATHER_MERGE_VMAS
+	bool
 
 config MMU_GATHER_NO_GATHER
 	bool
diff --git a/arch/csky/include/asm/tlb.h b/arch/csky/include/asm/tlb.h
index 3498e65f59f8..750d041938d8 100644
--- a/arch/csky/include/asm/tlb.h
+++ b/arch/csky/include/asm/tlb.h
@@ -4,19 +4,6 @@
 #define __ASM_CSKY_TLB_H
 
 #include <asm/cacheflush.h>
-
-#define tlb_start_vma(tlb, vma) \
-	do { \
-		if (!(tlb)->fullmm) \
-			flush_cache_range(vma, (vma)->vm_start, (vma)->vm_end); \
-	}  while (0)
-
-#define tlb_end_vma(tlb, vma) \
-	do { \
-		if (!(tlb)->fullmm) \
-			flush_tlb_range(vma, (vma)->vm_start, (vma)->vm_end); \
-	}  while (0)
-
 #define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
 
 #include <asm-generic/tlb.h>
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 53a912befb62..b57daee98b89 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -108,6 +108,7 @@ config LOONGARCH
 	select TRACE_IRQFLAGS_SUPPORT
 	select USE_PERCPU_NUMA_NODE_ID
 	select ZONE_DMA32
+	select MMU_GATHER_MERGE_VMAS if MMU
 
 config 32BIT
 	bool
diff --git a/arch/loongarch/include/asm/tlb.h b/arch/loongarch/include/asm/tlb.h
index 4f629ae9d5a9..dd24f5898f65 100644
--- a/arch/loongarch/include/asm/tlb.h
+++ b/arch/loongarch/include/asm/tlb.h
@@ -137,16 +137,6 @@ static inline void invtlb_all(u32 op, u32 info, u64 addr)
 		);
 }
 
-/*
- * LoongArch doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for area to be unmapped.
- */
-#define tlb_start_vma(tlb, vma)					\
-	do {							\
-		if (!(tlb)->fullmm)				\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	}  while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 
 static void tlb_flush(struct mmu_gather *tlb);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 7aa12e88c580..c235648fae23 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -256,6 +256,7 @@ config PPC
 	select IRQ_FORCED_THREADING
 	select MMU_GATHER_PAGE_SIZE
 	select MMU_GATHER_RCU_TABLE_FREE
+	select MMU_GATHER_MERGE_VMAS
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE		if PPC64 || NOT_COHERENT_CACHE
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK	if PPC64
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 09a9ae5f3656..b3de6102a907 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -19,8 +19,6 @@
 
 #include <linux/pagemap.h>
 
-#define tlb_start_vma(tlb, vma)	do { } while (0)
-#define tlb_end_vma(tlb, vma)	do { } while (0)
 #define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
 
 #define tlb_flush tlb_flush
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8cd9e56c629b..5a1a8dfda6f8 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -204,6 +204,7 @@ config S390
 	select IOMMU_SUPPORT		if PCI
 	select MMU_GATHER_NO_GATHER
 	select MMU_GATHER_RCU_TABLE_FREE
+	select MMU_GATHER_MERGE_VMAS
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE	if PCI
 	select NEED_SG_DMA_LENGTH	if PCI
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index fe6407f0eb1b..3a5c8fb590e5 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -27,9 +27,6 @@ static inline void tlb_flush(struct mmu_gather *tlb);
 static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
 					  struct page *page, int page_size);
 
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-
 #define tlb_flush tlb_flush
 #define pte_free_tlb pte_free_tlb
 #define pmd_free_tlb pmd_free_tlb
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index ba449c47effd..4f7d1dfbc608 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -67,6 +67,8 @@ config SPARC64
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select MMU_GATHER_RCU_TABLE_FREE if SMP
+	select MMU_GATHER_MERGE_VMAS
+	select MMU_GATHER_NO_FLUSH_CACHE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index 779a5a0f0608..3037187482db 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -22,8 +22,6 @@ void smp_flush_tlb_mm(struct mm_struct *mm);
 void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
 void flush_tlb_pending(void);
 
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma)	do { } while (0)
 #define tlb_flush(tlb)	flush_tlb_pending()
 
 /*
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e58798f636d4..7fff10e15969 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -245,6 +245,7 @@ config X86
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select MMU_GATHER_RCU_TABLE_FREE	if PARAVIRT
+	select MMU_GATHER_MERGE_VMAS
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if UNWINDER_ORC || STACK_VALIDATION
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 1bfe979bb9bc..580636cdc257 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -2,9 +2,6 @@
 #ifndef _ASM_X86_TLB_H
 #define _ASM_X86_TLB_H
 
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-
 #define tlb_flush tlb_flush
 static inline void tlb_flush(struct mmu_gather *tlb);