How about something like this

---
Subject: mm: Add missing TLB invalidate to RCU page-table freeing
From: Peter Zijlstra <redacted>
Date: Thu Jun 28 00:49:33 CEST 2012

For normal systems we need a TLB invalidate before freeing the
page-tables, the generic RCU based page-table freeing code lacked
this.

This is because this code originally came from ppc where the hardware
never walks the linux page-tables and thus this invalidate is not
required.

Others, notably s390 which ran into this problem in cd94154cc6a
("[S390] fix tlb flushing for page table pages"), do very much need
this TLB invalidation.

Therefore add it, with a Kconfig option to disable it so as to not
unduly slow down PPC and SPARC64 which neither of them need it.

Signed-off-by: Peter Zijlstra <redacted>
---
 arch/Kconfig         |    3 +++
 arch/powerpc/Kconfig |    1 +
 arch/sparc/Kconfig   |    1 +
 mm/memory.c          |   18 ++++++++++++++++++
 4 files changed, 23 insertions(+)

--- a/arch/Kconfig
+++ b/arch/Kconfig

@@ -231,6 +231,9 @@ config HAVE_ARCH_MUTEX_CPU_RELAX
 config HAVE_RCU_TABLE_FREE
 	bool
 
+config STRICT_TLB_FILL
+	bool
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig

@@ -127,6 +127,7 @@ config PPC
 	select GENERIC_IRQ_SHOW_LEVEL
 	select IRQ_FORCED_THREADING
 	select HAVE_RCU_TABLE_FREE if SMP
+	select STRICT_TLB_FILL
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_BPF_JIT if PPC64
 	select HAVE_ARCH_JUMP_LABEL
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig

@@ -52,6 +52,7 @@ config SPARC64
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP
+	select STRICT_TLB_FILL
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_SYSCALL_WRAPPERS
--- a/mm/memory.c
+++ b/mm/memory.c

@@ -329,11 +329,27 @@ static void tlb_remove_table_rcu(struct 
 	free_page((unsigned long)batch);
 }
 
+#ifdef CONFIG_STRICT_TLB_FILL
+/*
+ * Some archictures (sparc64, ppc) cannot refill TLBs after the they've removed
+ * the PTE entries from their hash-table. Their hardware never looks at the
+ * linux page-table structures, so they don't need a hardware TLB invalidate
+ * when tearing down the page-table structure itself.
+ */
+static inline void tlb_table_flush_mmu(struct mmu_gather *tlb) { }
+#else
+static inline void tlb_table_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu(tlb);
+}
+#endif
+
 void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
 	if (*batch) {
+		tlb_table_flush_mmu(tlb);
 		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
 		*batch = NULL;
 	}

@@ -345,6 +361,7 @@ void tlb_remove_table(struct mmu_gather 
 
 	tlb->need_flush = 1;
 
+#ifdef CONFIG_STRICT_TLB_FILL
 	/*
 	 * When there's less then two users of this mm there cannot be a
 	 * concurrent page-table walk.

@@ -353,6 +370,7 @@ void tlb_remove_table(struct mmu_gather 
 		__tlb_remove_table(table);
 		return;
 	}
+#endif
 
 	if (*batch == NULL) {
 		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);

--

To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>