1 files changed, 86 insertions, 70 deletions

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index e43f9766259f..e58fa777fa09 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -5,6 +5,8 @@
  * Copyright 2001 Red Hat, Inc.
  * Based on code from mm/memory.c Copyright Linus Torvalds and others.
  *
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
@@ -17,97 +19,111 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 /*
- * For UP we don't need to worry about TLB flush
- * and page free order so much..
+ * Semi RCU freeing of the page directories.
+ *
+ * This is needed by some architectures to implement software pagetable walkers.
+ *
+ * gup_fast() and other software pagetable walkers do a lockless page-table
+ * walk and therefore needs some synchronization with the freeing of the page
+ * directories. The chosen means to accomplish that is by disabling IRQs over
+ * the walk.
+ *
+ * Architectures that use IPIs to flush TLBs will then automagically DTRT,
+ * since we unlink the page, flush TLBs, free the page. Since the disabling of
+ * IRQs delays the completion of the TLB flush we can never observe an already
+ * freed page.
+ *
+ * Architectures that do not have this (PPC) need to delay the freeing by some
+ * other means, this is that means.
+ *
+ * What we do is batch the freed directory pages (tables) and RCU free them.
+ * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
+ * holds off grace periods.
+ *
+ * However, in order to batch these pages we need to allocate storage, this
+ * allocation is deep inside the MM code and can thus easily fail on memory
+ * pressure. To guarantee progress we fall back to single table freeing, see
+ * the implementation of tlb_remove_table_one().
+ *
  */
-#ifdef CONFIG_SMP
-  #ifdef ARCH_FREE_PTR_NR
-    #define FREE_PTR_NR   ARCH_FREE_PTR_NR
-  #else
-    #define FREE_PTE_NR	506
-  #endif
-  #define tlb_fast_mode(tlb) ((tlb)->nr == ~0U)
-#else
-  #define FREE_PTE_NR	1
-  #define tlb_fast_mode(tlb) 1
+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);
+
 #endif
 
-/* struct mmu_gather is an opaque type used by the mm code for passing around
- * any data needed by arch specific code for tlb_remove_page.
+/*
+ * If we can't allocate a page to make a big batch of page pointers
+ * to work on, then just handle a few from the on-stack structure.
  */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		nr;	/* set to ~0U means fast mode */
-	unsigned int		need_flush;/* Really unmapped some ptes? */
-	unsigned int		fullmm; /* non-zero means full mm flush */
-	struct page *		pages[FREE_PTE_NR];
+#define MMU_GATHER_BUNDLE	8
+
+struct mmu_gather_batch {
+	struct mmu_gather_batch	*next;
+	unsigned int		nr;
+	unsigned int		max;
+	struct page		*pages[0];
 };
 
-/* Users of the generic TLB shootdown code must declare this storage space. */
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
+#define MAX_GATHER_BATCH	\
+	((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
 
-/* tlb_gather_mmu
- *	Return a pointer to an initialized struct mmu_gather.
+/* struct mmu_gather is an opaque type used by the mm code for passing around
+ * any data needed by arch specific code for tlb_remove_page.
  */
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
-{
-	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
-	tlb->mm = mm;
+struct mmu_gather {
+	struct mm_struct	*mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	struct mmu_table_batch	*batch;
+#endif
+	unsigned int		need_flush : 1,	/* Did free PTEs */
+				fast_mode  : 1; /* No batching   */
 
-	/* Use fast mode if only one CPU is online */
-	tlb->nr = num_online_cpus() > 1 ? 0U : ~0U;
+	unsigned int		fullmm;
 
-	tlb->fullmm = full_mm_flush;
+	struct mmu_gather_batch *active;
+	struct mmu_gather_batch	local;
+	struct page		*__pages[MMU_GATHER_BUNDLE];
+};
 
-	return tlb;
-}
+#define HAVE_GENERIC_MMU_GATHER
 
-static inline void
-tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+static inline int tlb_fast_mode(struct mmu_gather *tlb)
 {
-	if (!tlb->need_flush)
-		return;
-	tlb->need_flush = 0;
-	tlb_flush(tlb);
-	if (!tlb_fast_mode(tlb)) {
-		free_pages_and_swap_cache(tlb->pages, tlb->nr);
-		tlb->nr = 0;
-	}
+#ifdef CONFIG_SMP
+	return tlb->fast_mode;
+#else
+	/*
+	 * For UP we don't need to worry about TLB flush
+	 * and page free order so much..
+	 */
+	return 1;
+#endif
 }
 
-/* tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	tlb_flush_mmu(tlb, start, end);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	put_cpu_var(mmu_gathers);
-}
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm);
+void tlb_flush_mmu(struct mmu_gather *tlb);
+void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end);
+int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
 
 /* tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- *	handling the additional races in SMP caused by other CPUs caching valid
- *	mappings in their TLBs.
+ *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
+ *	required.
  */
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	tlb->need_flush = 1;
-	if (tlb_fast_mode(tlb)) {
-		free_page_and_swap_cache(page);
-		return;
-	}
-	tlb->pages[tlb->nr++] = page;
-	if (tlb->nr >= FREE_PTE_NR)
-		tlb_flush_mmu(tlb, 0, 0);
+	if (!__tlb_remove_page(tlb, page))
+		tlb_flush_mmu(tlb);
 }
 
 /**