Signed-off-by:

--- linux-2.6.14-rc3/include/asm-ia64/mmu_context.h	2005-10-26 10:54:53.000000000 -0400
+++ linux-2.6.14-rc3pmk/include/asm-ia64/mmu_context.h	2005-10-06 16:39:27.000000000 -0400
@@ -34,11 +34,13 @@
 	unsigned int next;	/* next context number to use */
 	unsigned int limit;	/* next >= limit => must call wrap_mmu_context() */
 	unsigned int max_ctx;	/* max. context value supported by all CPUs */
+	unsigned long *bitmap;	/* bitmap size is max_ctx+1 */
 };
 
 extern struct ia64_ctx ia64_ctx;
 DECLARE_PER_CPU(u8, ia64_need_tlb_flush);
 
+extern void mmu_context_init (void);
 extern void wrap_mmu_context (struct mm_struct *mm);
 
 static inline void
@@ -86,6 +88,7 @@
 				if (ia64_ctx.next >= ia64_ctx.limit)
 					wrap_mmu_context(mm);
 				mm->context = context = ia64_ctx.next++;
+	 			set_bit(context, ia64_ctx.bitmap);
 			}
 		}
 		spin_unlock_irqrestore(&ia64_ctx.lock, flags);
--- linux-2.6.14-rc3/include/asm-ia64/tlbflush.h	2005-08-28 19:41:01.000000000 -0400
+++ linux-2.6.14-rc3pmk/include/asm-ia64/tlbflush.h	2005-10-06 16:15:47.000000000 -0400
@@ -51,6 +51,7 @@
 	if (!mm)
 		return;
 
+	clear_bit(mm->context, ia64_ctx.bitmap);
 	mm->context = 0;
 
 	if (atomic_read(&mm->mm_users) == 0)
--- linux-2.6.14-rc3/arch/ia64/mm/tlb.c	2005-08-28 19:41:01.000000000 -0400
+++ linux-2.6.14-rc3pmk/arch/ia64/mm/tlb.c	2005-10-25 14:55:25.000000000 -0400
@@ -16,12 +16,14 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/bootmem.h>
 
 #include <asm/delay.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/pal.h>
 #include <asm/tlbflush.h>
+#include <asm/dma.h>
 
 static struct {
 	unsigned long mask;	/* mask of supported purge page-sizes */
@@ -38,13 +40,32 @@
 DEFINE_PER_CPU(u8, ia64_need_tlb_flush);
 
 /*
+ * Initializes the ia64_ctx.bitmap array based on max_ctx+1.
+ * Called after cpu_init() has setup ia64_ctx.max_ctx based on
+ * maximum RID that is supported by all CPUs.
+ */
+void __init
+mmu_context_init (void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ia64_ctx.lock, flags);
+	if (ia64_ctx.bitmap == NULL) {
+		ia64_ctx.bitmap = (unsigned long *)__alloc_bootmem(
+							(ia64_ctx.max_ctx+1)>>3,
+							PAGE_SIZE,
+							__pa(MAX_DMA_ADDRESS));
+	}
+	spin_unlock_irqrestore(&ia64_ctx.lock, flags);
+}
+
+/*
  * Acquire the ia64_ctx.lock before calling this function!
  */
 void
 wrap_mmu_context (struct mm_struct *mm)
 {
-	unsigned long tsk_context, max_ctx = ia64_ctx.max_ctx;
-	struct task_struct *tsk;
+	unsigned int next_ctx, max_ctx = ia64_ctx.max_ctx;
 	int i;
 
 	if (ia64_ctx.next > max_ctx)
@@ -52,28 +73,23 @@
 	ia64_ctx.limit = max_ctx + 1;
 
 	/*
-	 * Scan all the task's mm->context and set proper safe range
+	 * Scan the ia64_ctx bitmap and set proper safe range
 	 */
+repeat:
+	next_ctx = find_next_zero_bit(ia64_ctx.bitmap, ia64_ctx.limit, ia64_ctx.next);
+	if (next_ctx >= ia64_ctx.limit) {
+		smp_mb();
+		ia64_ctx.next = 300;	/* skip daemons */
+		goto repeat;
+	}
+	ia64_ctx.next = next_ctx;
 
-	read_lock(&tasklist_lock);
-  repeat:
-	for_each_process(tsk) {
-		if (!tsk->mm)
-			continue;
-		tsk_context = tsk->mm->context;
-		if (tsk_context == ia64_ctx.next) {
-			if (++ia64_ctx.next >= ia64_ctx.limit) {
-				/* empty range: reset the range limit and start over */
-				if (ia64_ctx.next > max_ctx)
-					ia64_ctx.next = 300;
-				ia64_ctx.limit = max_ctx + 1;
-				goto repeat;
-			}
-		}
-		if ((tsk_context > ia64_ctx.next) && (tsk_context < ia64_ctx.limit))
-			ia64_ctx.limit = tsk_context;
+	next_ctx = find_next_bit(ia64_ctx.bitmap, ia64_ctx.limit, ia64_ctx.next);
+	if (next_ctx >= ia64_ctx.limit) {
+		next_ctx = ia64_ctx.limit;
 	}
-	read_unlock(&tasklist_lock);
+	ia64_ctx.limit = next_ctx;
+
 	/* can't call flush_tlb_all() here because of race condition with O(1) scheduler [EF] */
 	{
 		int cpu = get_cpu(); /* prevent preemption/migration */
--- linux-2.6.14-rc3/arch/ia64/kernel/setup.c	2005-10-26 10:54:06.000000000 -0400
+++ linux-2.6.14-rc3pmk/arch/ia64/kernel/setup.c	2005-10-25 14:53:59.000000000 -0400
@@ -419,6 +419,7 @@
 #endif
 
 	cpu_init();	/* initialize the bootstrap CPU */
+	mmu_context_init();	/* initialize context_id bitmap */
 
 #ifdef CONFIG_ACPI
 	acpi_boot_init();
@@ -798,9 +799,13 @@
 #endif
 
 	/* set ia64_ctx.max_rid to the maximum RID that is supported by all CPUs: */
-	if (ia64_pal_vm_summary(NULL, &vmi) == 0)
+	if (ia64_pal_vm_summary(NULL, &vmi) == 0) {
 		max_ctx = (1U << (vmi.pal_vm_info_2_s.rid_size - 3)) - 1;
-	else {
+		if (max_ctx > (1U << 21)) {
+			max_ctx = (1U << 21) - 1;	/* limit to 2^21  */
+			printk(KERN_WARNING "cpu_init: max_ctx limited to 21 RID bits for bitmap size\n");
+		}
+	} else {
 		printk(KERN_WARNING "cpu_init: PAL VM summary failed, assuming 18 RID bits\n");
 		max_ctx = (1U << 15) - 1;	/* use architected minimum */
 	}