arm: mm: enable HAVE_RCU_TABLE_FREE logic

In order to implement fast_get_user_pages we need to ensure that the page
table walker is protected from page table pages being freed from under it.

This patch enables HAVE_RCU_TABLE_FREE, any page table pages belonging to
address spaces with multiple users will be call_rcu_sched freed.  Meaning
that disabling interrupts will block the free and protect the fast gup
page walker.
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dann Frazier <dann.frazier@canonical.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/arm/Kconfig

@@ -62,6 +62,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16

arch/arm/include/asm/tlb.h

@@ -35,12 +35,39 @@
 
 #define MMU_GATHER_BUNDLE	8
 
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+static inline void __tlb_remove_table(void *_table)
+{
+	free_page_and_swap_cache((struct page *)_table);
+}
+
+struct mmu_table_batch {
+	struct rcu_head		rcu;
+	unsigned int		nr;
+	void			*tables[0];
+};
+
+#define MAX_TABLE_BATCH		\
+	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
+#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
+#else
+#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * TLB handling.  This allows us to remove pages from the page
  * tables, and efficiently handle the TLB issues.
  */
 struct mmu_gather {
 	struct mm_struct	*mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	struct mmu_table_batch	*batch;
+	unsigned int		need_flush;
+#endif
 	unsigned int		fullmm;
 	struct vm_area_struct	*vma;
 	unsigned long		start, end;
@@ -101,6 +128,9 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
 }
 
 static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
@@ -129,6 +159,10 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 	tlb->pages = tlb->local;
 	tlb->nr = 0;
 	__tlb_alloc_page(tlb);
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
 }
 
 static inline void
@@ -205,7 +239,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb_add_flush(tlb, addr + SZ_1M);
 #endif
 
-	tlb_remove_page(tlb, pte);
+	tlb_remove_entry(tlb, pte);
 }
 
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
@@ -213,7 +247,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 {
 #ifdef CONFIG_ARM_LPAE
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, virt_to_page(pmdp));
+	tlb_remove_entry(tlb, virt_to_page(pmdp));
 #endif
 }