[PATCH v2 7/7] Flush page-table pages before freeing them

["Nikunj A. Dadhania" <nikunj@linux.vnet.ibm.com>]

From: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com>

Certain architecture(viz. x86, arm, s390) have hardware page-table
walkers(#PF). So during the RCU page-table teardown process make sure
we do a tlb flush of page-table pages on all relevant CPUs to
synchronize against hardware walkers, and then free the pages.

Moreover, the (mm_users < 2) condition does not hold good for the above
architectures, as the hardware engine is one of the user.

Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com>
---
 arch/Kconfig     |    3 +++
 arch/x86/Kconfig |   12 ++++++++++++
 mm/memory.c      |   24 ++++++++++++++++++++++--
 3 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 684eb5a..abc3739 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -196,6 +196,9 @@ config HAVE_ARCH_MUTEX_CPU_RELAX
 config HAVE_RCU_TABLE_FREE
 	bool
 
+config ARCH_HW_WALKS_PAGE_TABLE
+       bool
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a9ec0da..b0a9f11 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -617,6 +617,18 @@ config PARAVIRT_SPINLOCKS
 
 	  If you are unsure how to answer this question, answer N.
 
+config PARAVIRT_TLB_FLUSH
+	bool "Paravirtualization layer for TLB Flush"
+	depends on PARAVIRT && SMP && EXPERIMENTAL
+	select HAVE_RCU_TABLE_FREE
+	select ARCH_HW_WALKS_PAGE_TABLE
+	---help---
+	  Paravirtualized Flush TLB replace the native implementation
+	  with something virtualization-friendly (for example, set a
+	  flag for sleeping vcpu and do not wait for it).
+
+	  If you are unsure how to answer this question, answer N.
+
 config PARAVIRT_CLOCK
 	bool
 
diff --git a/mm/memory.c b/mm/memory.c
index c12685d..acfadb8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -335,11 +335,27 @@ static void tlb_remove_table_rcu(struct rcu_head *head)
 	free_page((unsigned long)batch);
 }
 
+#ifdef CONFIG_ARCH_HW_WALKS_PAGE_TABLE
+/*
+ * Some architectures(x86, arm, s390) HW walks the page tables when
+ * the page-table tear down might be happening. So make sure that
+ * before freeing the page-table pages, flush their tlbs
+ */
+static inline void tlb_table_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu(tlb);
+}
+
+#else
+#define tlb_table_flush_mmu(tlb) do {} while (0)
+#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;
 	}
@@ -351,18 +367,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 
 	tlb->need_flush = 1;
 
+#ifndef CONFIG_ARCH_HW_WALKS_PAGE_TABLE
 	/*
-	 * When there's less then two users of this mm there cannot be a
-	 * concurrent page-table walk.
+	 * When there's less then two users of this mm there cannot be
+	 * a concurrent page-table walk for architectures that do not
+	 * have hardware page-table walkers.
 	 */
 	if (atomic_read(&tlb->mm->mm_users) < 2) {
 		__tlb_remove_table(table);
 		return;
 	}
+#endif
 
 	if (*batch == NULL) {
 		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		if (*batch == NULL) {
+			tlb_table_flush_mmu(tlb);
 			tlb_remove_table_one(table);
 			return;
 		}