[PATCH] x86-64 TIF flags for debug regs and io bitmap in ctxsw

Hello,

Following my discussion with Andi. Here is a patch that introduces
two new TIF flags to simplify the context switch code in __switch_to().
The idea is to minimize the number of cache lines accessed in the common
case, i.e., when neither the debug registers nor the I/O bitmap are used.

This patch covers the x86-64 modifications. A patch for i386 follows.

Changelog:
	- add TIF_DEBUG to track when debug registers are active
	- add TIF_IO_BITMAP to track when I/O bitmap is used
	- modify __switch_to() to use the new TIF flags

<signed-off-by>: eranian@hpl.hp.com

Signed-off-by: Andi Kleen <ak@suse.de>

3 files changed, 49 insertions, 33 deletions

diff --git a/arch/x86_64/kernel/ioport.c b/arch/x86_64/kernel/ioport.c
index b816149..fe063d3 100644
--- a/arch/x86_64/kernel/ioport.c
+++ b/arch/x86_64/kernel/ioport.c
@@ -56,6 +56,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 
 		memset(bitmap, 0xff, IO_BITMAP_BYTES);
 		t->io_bitmap_ptr = bitmap;
+		set_thread_flag(TIF_IO_BITMAP);
 	}
 
 	/*
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index bb6745d..6e05276 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -350,6 +350,7 @@ void exit_thread(void)
 
 		kfree(t->io_bitmap_ptr);
 		t->io_bitmap_ptr = NULL;
+		clear_thread_flag(TIF_IO_BITMAP);
 		/*
 		 * Careful, clear this in the TSS too:
 		 */
@@ -369,6 +370,7 @@ void flush_thread(void)
 		if (t->flags & _TIF_IA32)
 			current_thread_info()->status |= TS_COMPAT;
 	}
+	t->flags &= ~_TIF_DEBUG;
 
 	tsk->thread.debugreg0 = 0;
 	tsk->thread.debugreg1 = 0;
@@ -461,7 +463,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp,
 	asm("mov %%es,%0" : "=m" (p->thread.es));
 	asm("mov %%ds,%0" : "=m" (p->thread.ds));
 
-	if (unlikely(me->thread.io_bitmap_ptr != NULL)) { 
+	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
 		if (!p->thread.io_bitmap_ptr) {
 			p->thread.io_bitmap_max = 0;
@@ -469,6 +471,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp,
 		}
 		memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr,
 				IO_BITMAP_BYTES);
+		set_tsk_thread_flag(p, TIF_IO_BITMAP);
 	} 
 
 	/*
@@ -498,6 +501,40 @@ out:
  */
 #define loaddebug(thread,r) set_debugreg(thread->debugreg ## r, r)
 
+static inline void __switch_to_xtra(struct task_struct *prev_p,
+			     	    struct task_struct *next_p,
+			     	    struct tss_struct *tss)
+{
+	struct thread_struct *prev, *next;
+
+	prev = &prev_p->thread,
+	next = &next_p->thread;
+
+	if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
+		loaddebug(next, 0);
+		loaddebug(next, 1);
+		loaddebug(next, 2);
+		loaddebug(next, 3);
+		/* no 4 and 5 */
+		loaddebug(next, 6);
+		loaddebug(next, 7);
+	}
+
+	if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
+		/*
+		 * Copy the relevant range of the IO bitmap.
+		 * Normally this is 128 bytes or less:
+		 */
+		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
+		       max(prev->io_bitmap_max, next->io_bitmap_max));
+	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
+		/*
+		 * Clear any possible leftover bits:
+		 */
+		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
+	}
+}
+
 /*
  *	switch_to(x,y) should switch tasks from x to y.
  *
@@ -586,37 +623,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		  task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
 
 	/*
-	 * Now maybe reload the debug registers
+	 * Now maybe reload the debug registers and handle I/O bitmaps
 	 */
-	if (unlikely(next->debugreg7)) {
-		loaddebug(next, 0);
-		loaddebug(next, 1);
-		loaddebug(next, 2);
-		loaddebug(next, 3);
-		/* no 4 and 5 */
-		loaddebug(next, 6);
-		loaddebug(next, 7);
-	}
-
-
-	/* 
-	 * Handle the IO bitmap 
-	 */ 
-	if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) {
-		if (next->io_bitmap_ptr)
-			/*
-			 * Copy the relevant range of the IO bitmap.
-			 * Normally this is 128 bytes or less:
- 			 */
-			memcpy(tss->io_bitmap, next->io_bitmap_ptr,
-				max(prev->io_bitmap_max, next->io_bitmap_max));
-		else {
-			/*
-			 * Clear any possible leftover bits:
-			 */
-			memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
-		}
-	}
+	if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW))
+	    || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP))
+		__switch_to_xtra(prev_p, next_p, tss);
 
 	return prev_p;
 }
diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c
index 2d50024..d35ec1b 100644
--- a/arch/x86_64/kernel/ptrace.c
+++ b/arch/x86_64/kernel/ptrace.c
@@ -420,9 +420,13 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 				if ((0x5554 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
 					break;
 			if (i == 4) {
-				child->thread.debugreg7 = data;
+			  child->thread.debugreg7 = data;
+			  if (data)
+			  	set_tsk_thread_flag(child, TIF_DEBUG);
+			  else
+			  	clear_tsk_thread_flag(child, TIF_DEBUG);
 			  ret = 0;
-		  }
+		  	}
 		  break;
 		}
 		break;