1 files changed, 72 insertions, 48 deletions

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 2b10036fefd0..f391f6b500b4 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -56,6 +56,15 @@
  *    Defaults to flushing at tlb_end_vma() to reset the range; helps when
  *    there's large holes between the VMAs.
  *
+ *  - tlb_remove_table()
+ *
+ *    tlb_remove_table() is the basic primitive to free page-table directories
+ *    (__p*_free_tlb()).  In it's most primitive form it is an alias for
+ *    tlb_remove_page() below, for when page directories are pages and have no
+ *    additional constraints.
+ *
+ *    See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE.
+ *
  *  - tlb_remove_page() / __tlb_remove_page()
  *  - tlb_remove_page_size() / __tlb_remove_page_size()
  *
@@ -121,65 +130,53 @@
  *
  * Additionally there are a few opt-in features:
  *
- *  HAVE_MMU_GATHER_PAGE_SIZE
+ *  MMU_GATHER_PAGE_SIZE
  *
  *  This ensures we call tlb_flush() every time tlb_change_page_size() actually
  *  changes the size and provides mmu_gather::page_size to tlb_flush().
  *
- *  HAVE_RCU_TABLE_FREE
+ *  This might be useful if your architecture has size specific TLB
+ *  invalidation instructions.
+ *
+ *  MMU_GATHER_TABLE_FREE
  *
  *  This provides tlb_remove_table(), to be used instead of tlb_remove_page()
- *  for page directores (__p*_free_tlb()). This provides separate freeing of
- *  the page-table pages themselves in a semi-RCU fashion (see comment below).
- *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
- *  and therefore doesn't naturally serialize with software page-table walkers.
+ *  for page directores (__p*_free_tlb()).
+ *
+ *  Useful if your architecture has non-page page directories.
  *
  *  When used, an architecture is expected to provide __tlb_remove_table()
  *  which does the actual freeing of these pages.
  *
- *  HAVE_RCU_TABLE_NO_INVALIDATE
+ *  MMU_GATHER_RCU_TABLE_FREE
  *
- *  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.
+ *  Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see
+ *  comment below).
+ *
+ *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ *  and therefore doesn't naturally serialize with software page-table walkers.
  *
  *  MMU_GATHER_NO_RANGE
  *
  *  Use this if your architecture lacks an efficient flush_tlb_range().
- */
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-/*
- * 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.
+ *  MMU_GATHER_NO_GATHER
  *
- * 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().
+ *  If the option is set the mmu_gather will not track individual pages for
+ *  delayed page free anymore. A platform that enables the option needs to
+ *  provide its own implementation of the __tlb_remove_page_size() function to
+ *  free pages.
  *
+ *  This is useful if your architecture already flushes TLB entries in the
+ *  various ptep_get_and_clear() functions.
  */
+
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
+
 struct mmu_table_batch {
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
 	struct rcu_head		rcu;
+#endif
 	unsigned int		nr;
 	void			*tables[0];
 };
@@ -189,9 +186,35 @@ struct mmu_table_batch {
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
+#else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */
+
+/*
+ * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based
+ * page directories and we can use the normal page batching to free them.
+ */
+#define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page))
+
+#endif /* CONFIG_MMU_GATHER_TABLE_FREE */
+
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
+/*
+ * This allows an architecture that does not use the linux page-tables for
+ * hardware to skip the TLBI when freeing page tables.
+ */
+#ifndef tlb_needs_table_invalidate
+#define tlb_needs_table_invalidate() (true)
 #endif
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#else
+
+#ifdef tlb_needs_table_invalidate
+#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
+#endif
+
+#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
+
+
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 /*
  * 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.
@@ -227,7 +250,7 @@ extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 struct mmu_gather {
 	struct mm_struct	*mm;
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
 
@@ -266,22 +289,18 @@ struct mmu_gather {
 
 	unsigned int		batch_count;
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
 
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	unsigned int page_size;
 #endif
 #endif
 };
 
-void arch_tlb_gather_mmu(struct mmu_gather *tlb,
-	struct mm_struct *mm, unsigned long start, unsigned long end);
 void tlb_flush_mmu(struct mmu_gather *tlb);
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			 unsigned long start, unsigned long end, bool force);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address,
@@ -394,7 +413,12 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
 
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
+	/*
+	 * Anything calling __tlb_adjust_range() also sets at least one of
+	 * these bits.
+	 */
+	if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds ||
+	      tlb->cleared_puds || tlb->cleared_p4ds))
 		return;
 
 	tlb_flush(tlb);
@@ -426,7 +450,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 static inline void tlb_change_page_size(struct mmu_gather *tlb,
 						     unsigned int page_size)
 {
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	if (tlb->page_size && tlb->page_size != page_size) {
 		if (!tlb->fullmm && !tlb->need_flush_all)
 			tlb_flush_mmu(tlb);