[PATCH v6 07/18] asm-generic/tlb: Invert HAVE_RCU_TABLE_INVALIDATE

[Peter Zijlstra]

Make issuing a TLB invalidate for page-table pages the normal case.

The reason is twofold:

 - too many invalidates is safer than too few,
 - most architectures use the linux page-tables natively
   and would thus require this.

Make it an opt-out, instead of an opt-in.

Acked-by: Will Deacon <will.deacon@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 arch/Kconfig              |    2 +-
 arch/arm64/Kconfig        |    1 -
 arch/powerpc/Kconfig      |    1 +
 arch/sparc/Kconfig        |    1 +
 arch/x86/Kconfig          |    1 -
 include/asm-generic/tlb.h |    9 +++++----
 mm/mmu_gather.c           |    2 +-
 7 files changed, 9 insertions(+), 8 deletions(-)

--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -372,7 +372,7 @@ config HAVE_ARCH_JUMP_LABEL_RELATIVE
 config HAVE_RCU_TABLE_FREE
 	bool
 
-config HAVE_RCU_TABLE_INVALIDATE
+config HAVE_RCU_TABLE_NO_INVALIDATE
 	bool
 
 config HAVE_MMU_GATHER_PAGE_SIZE
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -147,7 +147,6 @@ config ARM64
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
-	select HAVE_RCU_TABLE_INVALIDATE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -218,6 +218,7 @@ config PPC
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
 	select HAVE_MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if PPC64 && CPU_LITTLE_ENDIAN
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -62,6 +62,7 @@ config SPARC64
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -183,7 +183,6 @@ config X86
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if PARAVIRT
-	select HAVE_RCU_TABLE_INVALIDATE	if HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_FUNCTION_ARG_ACCESS_API
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -135,11 +135,12 @@
  *  When used, an architecture is expected to provide __tlb_remove_table()
  *  which does the actual freeing of these pages.
  *
- *  HAVE_RCU_TABLE_INVALIDATE
+ *  HAVE_RCU_TABLE_NO_INVALIDATE
  *
- *  This makes HAVE_RCU_TABLE_FREE call tlb_flush_mmu_tlbonly() before freeing
- *  the page-table pages. Required if you use HAVE_RCU_TABLE_FREE and your
- *  architecture uses the Linux page-tables natively.
+ *  This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before
+ *  freeing the page-table pages. This can be avoided if you use
+ *  HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux
+ *  page-tables natively.
  *
  *  MMU_GATHER_NO_RANGE
  *
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -157,7 +157,7 @@ bool __tlb_remove_page_size(struct mmu_g
  */
 static inline void tlb_table_invalidate(struct mmu_gather *tlb)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
+#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
 	/*
 	 * Invalidate page-table caches used by hardware walkers. Then we still
 	 * need to RCU-sched wait while freeing the pages because software