Re: [PATCH] update fix X86_64 procfs provide stack information for threads

[Stefani Seibold <stefani@seibold.net>]

Hi Andi,

what do you think about this? The following patch implements a more
accurate KSTK_ESP. The usersp of the task will be updated in the device
and apci_timer interrupt. It would be easy to change other interrupts
too. The performance penalty should tiny. 

--- linux-2.6.32-rc5.old/arch/x86/include/asm/processor.h	2009-10-16 02:41:50.000000000 +0200
+++ linux-2.6.32-rc5.new/arch/x86/include/asm/processor.h	2009-11-04 23:02:53.705275836 +0100
@@ -1000,7 +1000,7 @@
 #define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
-#define KSTK_ESP(tsk)		-1 /* sorry. doesn't work for syscall. */
+extern unsigned long KSTK_ESP(struct task_struct *task);
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -1052,4 +1052,12 @@
 	return ratio;
 }
 
+#define update_usersp(regs)                                              \
+({                                                                       \
+	unsigned long __stk__ = (unsigned long)task_stack_page(current); \
+	unsigned long __stkp__ = (regs)->sp;                             \
+	if ((__stkp__ < __stk__) || (__stkp__ >= __stk__ + THREAD_SIZE)) \
+		current->thread.usersp = __stkp__;                       \
+})
+
 #endif /* _ASM_X86_PROCESSOR_H */
--- x/linux-2.6.32-rc5/arch/x86/kernel/process_64.c	2009-10-16 02:41:50.000000000 +0200
+++ linux-2.6.32-rc5/arch/x86/kernel/process_64.c	2009-11-03 10:11:11.202957393 +0100
@@ -664,3 +664,9 @@
 	return do_arch_prctl(current, code, addr);
 }
 
+unsigned long KSTK_ESP(struct task_struct *task)
+{
+	return (test_tsk_thread_flag(task, TIF_IA32)) ? \
+			(task_pt_regs(task)->sp) : \
+			((task)->thread.usersp);
+}
--- linux-2.6.32-rc5.old/arch/x86/kernel/irq_64.c	2009-10-16 02:41:50.000000000 +0200
+++ linux-2.6.32-rc5.new/arch/x86/kernel/irq_64.c	2009-11-04 22:29:55.762951577 +0100
@@ -53,6 +53,7 @@
 	struct irq_desc *desc;
 
 	stack_overflow_check(regs);
+	update_usersp(regs);
 
 	desc = irq_to_desc(irq);
 	if (unlikely(!desc))
--- linux-2.6.32-rc5.old/arch/x86/kernel/apic/apic.c	2009-10-16 02:41:50.000000000 +0200
+++ linux-2.6.32-rc5.new/arch/x86/kernel/apic/apic.c	2009-11-04 23:12:32.805086991 +0100
@@ -831,6 +831,9 @@
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
+#ifndef CONFIG_X86_32
+	update_usersp(regs);
+#endif
 	/*
 	 * NOTE! We'd better ACK the irq immediately,
 	 * because timer handling can be slow.

This works in my environment under load, but i have not the oversight if it work
under all circumstances. 

Stefani