mm, powerpc: move the RCU page-table freeing into generic code
In case other architectures require RCU freed page-tables to implement
gup_fast() and software filled hashes and similar things, provide the
means to do so by moving the logic into generic code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Requested-by: David Miller <davem@davemloft.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Tony Luck <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 2d3547c..74f80f6 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->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 @@
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;