1 files changed, 51 insertions, 5 deletions

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 2d3547c84235..74f80f6b6cf1 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -29,6 +29,49 @@
   #define tlb_fast_mode(tlb) 1
 #endif
 
+#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.
+ *
+ * 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().
+ *
+ */
+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
+
 /*
  * 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.
@@ -40,13 +83,13 @@
  */
 struct mmu_gather {
         struct mm_struct        *mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        struct mmu_table_batch  *batch;
+#endif
         unsigned int            nr;     /* set to ~0U means fast mode */
         unsigned int            max;    /* nr < max */
         unsigned int            need_flush;/* Really unmapped some ptes? */
         unsigned int            fullmm; /* non-zero means full mm flush */
-#ifdef HAVE_ARCH_MMU_GATHER
-        struct arch_mmu_gather  arch;
-#endif
         struct page             **pages;
         struct page             *local[MMU_GATHER_BUNDLE];
 };
@@ -82,8 +125,8 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 
         tlb->fullmm = fullmm;
 
-#ifdef HAVE_ARCH_MMU_GATHER
-        tlb->arch = ARCH_MMU_GATHER_INIT;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb->batch = NULL;
 #endif
 }
 
@@ -94,6 +137,9 @@ tlb_flush_mmu(struct mmu_gather *tlb)
                 return;
         tlb->need_flush = 0;
         tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb_table_flush(tlb);
+#endif
         if (!tlb_fast_mode(tlb)) {
                 free_pages_and_swap_cache(tlb->pages, tlb->nr);
                 tlb->nr = 0;