[IA64] Use bitmaps for efficient context allocation/free

Corrects the very inefficent method of finding free context_ids in
get_mmu_context().  Instead of walking the task_list of all processes,
2 bitmaps are used to efficently store and lookup state, inuse and
needs flushing. The entire rid address space is now used before calling
wrap_mmu_context and global tlb flushing.

Special thanks to Ken and Rohit for their review and modifications in
using a bit flushmap.

Signed-off-by: Peter Keilty <peter.keilty@hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

2 files changed, 16 insertions, 4 deletions

diff --git a/include/asm-ia64/mmu_context.h b/include/asm-ia64/mmu_context.h
index 8d6e72f7b08e..8d9b30b5f7d4 100644
--- a/include/asm-ia64/mmu_context.h
+++ b/include/asm-ia64/mmu_context.h
@@ -32,13 +32,17 @@
 struct ia64_ctx {
         spinlock_t lock;
         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 int limit;     /* available free range */
+        unsigned int max_ctx;   /* max. context value supported by all CPUs */
+                                /* call wrap_mmu_context when next >= max */
+        unsigned long *bitmap;  /* bitmap size is max_ctx+1 */
+        unsigned long *flushmap;/* pending rid to be flushed */
 };
 
 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
@@ -83,9 +87,16 @@ get_mmu_context (struct mm_struct *mm)
                         context = mm->context;
                         if (context == 0) {
                                 cpus_clear(mm->cpu_vm_mask);
-                                if (ia64_ctx.next >= ia64_ctx.limit)
-                                        wrap_mmu_context(mm);
+                                if (ia64_ctx.next >= ia64_ctx.limit) {
+                                        ia64_ctx.next = find_next_zero_bit(ia64_ctx.bitmap,
+                                                        ia64_ctx.max_ctx, ia64_ctx.next);
+                                        ia64_ctx.limit = find_next_bit(ia64_ctx.bitmap,
+                                                        ia64_ctx.max_ctx, ia64_ctx.next);
+                                        if (ia64_ctx.next >= ia64_ctx.max_ctx)
+                                                wrap_mmu_context(mm);
+                                }
                                 mm->context = context = ia64_ctx.next++;
+                                __set_bit(context, ia64_ctx.bitmap);
                         }
                 }
                 spin_unlock_irqrestore(&ia64_ctx.lock, flags);
diff --git a/include/asm-ia64/tlbflush.h b/include/asm-ia64/tlbflush.h
index b65c62702724..a35b323bae4c 100644
--- a/include/asm-ia64/tlbflush.h
+++ b/include/asm-ia64/tlbflush.h
@@ -51,6 +51,7 @@ flush_tlb_mm (struct mm_struct *mm)
         if (!mm)
                 return;
 
+        set_bit(mm->context, ia64_ctx.flushmap);
         mm->context = 0;
 
         if (atomic_read(&mm->mm_users) == 0)