powerpc: Use RCU based pte freeing mechanism for all powerpc

Refactor the RCU based pte free code that was used on ppc64 to be used
on all powerpc.

Additionally refactor pte_free() & pte_free_kernel() into common code
between ppc32 & ppc64.

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
new file mode 100644
index 0000000..6d94116
--- /dev/null
+++ b/arch/powerpc/mm/pgtable.c
@@ -0,0 +1,117 @@
+/*
+ * This file contains common routines for dealing with free of page tables
+ *
+ *  Derived from arch/powerpc/mm/tlb_64.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  Dave Engebretsen <engebret@us.ibm.com>
+ *      Rework for PPC64 port.
+ *
+ *  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
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
+static unsigned long pte_freelist_forced_free;
+
+struct pte_freelist_batch
+{
+	struct rcu_head	rcu;
+	unsigned int	index;
+	pgtable_free_t	tables[0];
+};
+
+#define PTE_FREELIST_SIZE \
+	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
+	  / sizeof(pgtable_free_t))
+
+static void pte_free_smp_sync(void *arg)
+{
+	/* Do nothing, just ensure we sync with all CPUs */
+}
+
+/* This is only called when we are critically out of memory
+ * (and fail to get a page in pte_free_tlb).
+ */
+static void pgtable_free_now(pgtable_free_t pgf)
+{
+	pte_freelist_forced_free++;
+
+	smp_call_function(pte_free_smp_sync, NULL, 1);
+
+	pgtable_free(pgf);
+}
+
+static void pte_free_rcu_callback(struct rcu_head *head)
+{
+	struct pte_freelist_batch *batch =
+		container_of(head, struct pte_freelist_batch, rcu);
+	unsigned int i;
+
+	for (i = 0; i < batch->index; i++)
+		pgtable_free(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+static void pte_free_submit(struct pte_freelist_batch *batch)
+{
+	INIT_RCU_HEAD(&batch->rcu);
+	call_rcu(&batch->rcu, pte_free_rcu_callback);
+}
+
+void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+{
+	/* This is safe since tlb_gather_mmu has disabled preemption */
+        cpumask_t local_cpumask = cpumask_of_cpu(smp_processor_id());
+	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+
+	if (atomic_read(&tlb->mm->mm_users) < 2 ||
+	    cpus_equal(tlb->mm->cpu_vm_mask, local_cpumask)) {
+		pgtable_free(pgf);
+		return;
+	}
+
+	if (*batchp == NULL) {
+		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
+		if (*batchp == NULL) {
+			pgtable_free_now(pgf);
+			return;
+		}
+		(*batchp)->index = 0;
+	}
+	(*batchp)->tables[(*batchp)->index++] = pgf;
+	if ((*batchp)->index == PTE_FREELIST_SIZE) {
+		pte_free_submit(*batchp);
+		*batchp = NULL;
+	}
+}
+
+void pte_free_finish(void)
+{
+	/* This is safe since tlb_gather_mmu has disabled preemption */
+	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+
+	if (*batchp == NULL)
+		return;
+	pte_free_submit(*batchp);
+	*batchp = NULL;
+}