[PATCH] lockdep: irqtrace subsystem, i386 support

Add irqflags-tracing support to i386.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/Kconfig.debug

@@ -1,5 +1,9 @@
 menu "Kernel hacking"
 
+config TRACE_IRQFLAGS_SUPPORT
+	bool
+	default y
+
 source "lib/Kconfig.debug"
 
 config EARLY_PRINTK

arch/i386/kernel/entry.S

@@ -42,6 +42,7 @@
 
 #include <linux/linkage.h>
 #include <asm/thread_info.h>
+#include <asm/irqflags.h>
 #include <asm/errno.h>
 #include <asm/segment.h>
 #include <asm/smp.h>
@@ -76,12 +77,21 @@ NT_MASK		= 0x00004000
 VM_MASK		= 0x00020000
 
 #ifdef CONFIG_PREEMPT
-#define preempt_stop		cli
+#define preempt_stop		cli; TRACE_IRQS_OFF
 #else
 #define preempt_stop
 #define resume_kernel		restore_nocheck
 #endif
 
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+	testl $IF_MASK,EFLAGS(%esp)     # interrupts off?
+	jz 1f
+	TRACE_IRQS_ON
+1:
+#endif
+.endm
+
 #ifdef CONFIG_VM86
 #define resume_userspace_sig	check_userspace
 #else
@@ -257,6 +267,10 @@ ENTRY(sysenter_entry)
 	CFI_REGISTER esp, ebp
 	movl TSS_sysenter_esp0(%esp),%esp
 sysenter_past_esp:
+	/*
+	 * No need to follow this irqs on/off section: the syscall
+	 * disabled irqs and here we enable it straight after entry:
+	 */
 	sti
 	pushl $(__USER_DS)
 	CFI_ADJUST_CFA_OFFSET 4
@@ -303,6 +317,7 @@ sysenter_past_esp:
 	call *sys_call_table(,%eax,4)
 	movl %eax,EAX(%esp)
 	cli
+	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
 	testw $_TIF_ALLWORK_MASK, %cx
 	jne syscall_exit_work
@@ -310,6 +325,7 @@ sysenter_past_esp:
 	movl EIP(%esp), %edx
 	movl OLDESP(%esp), %ecx
 	xorl %ebp,%ebp
+	TRACE_IRQS_ON
 	sti
 	sysexit
 	CFI_ENDPROC
@@ -339,6 +355,7 @@ syscall_exit:
 	cli				# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
 					# between sampling and the iret
+	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
 	testw $_TIF_ALLWORK_MASK, %cx	# current->work
 	jne syscall_exit_work
@@ -355,12 +372,15 @@ restore_all:
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
 restore_nocheck:
+	TRACE_IRQS_IRET
+restore_nocheck_notrace:
 	RESTORE_REGS
 	addl $4, %esp
 	CFI_ADJUST_CFA_OFFSET -4
 1:	iret
 .section .fixup,"ax"
 iret_exc:
+	TRACE_IRQS_ON
 	sti
 	pushl $0			# no error code
 	pushl $do_iret_error
@@ -386,11 +406,13 @@ ldt_ss:
 	subl $8, %esp		# reserve space for switch16 pointer
 	CFI_ADJUST_CFA_OFFSET 8
 	cli
+	TRACE_IRQS_OFF
 	movl %esp, %eax
 	/* Set up the 16bit stack frame with switch32 pointer on top,
 	 * and a switch16 pointer on top of the current frame. */
 	call setup_x86_bogus_stack
 	CFI_ADJUST_CFA_OFFSET -8	# frame has moved
+	TRACE_IRQS_IRET
 	RESTORE_REGS
 	lss 20+4(%esp), %esp	# switch to 16bit stack
 1:	iret
@@ -411,6 +433,7 @@ work_resched:
 	cli				# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
 					# between sampling and the iret
+	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
 	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done other
 					# than syscall tracing?
@@ -462,6 +485,7 @@ syscall_trace_entry:
 syscall_exit_work:
 	testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl
 	jz work_pending
+	TRACE_IRQS_ON
 	sti				# could let do_syscall_trace() call
 					# schedule() instead
 	movl %esp, %eax
@@ -535,9 +559,14 @@ ENTRY(irq_entries_start)
 vector=vector+1
 .endr
 
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
 	ALIGN
 common_interrupt:
 	SAVE_ALL
+	TRACE_IRQS_OFF
 	movl %esp,%eax
 	call do_IRQ
 	jmp ret_from_intr
@@ -549,9 +578,10 @@ ENTRY(name)				\
 	pushl $~(nr);			\
 	CFI_ADJUST_CFA_OFFSET 4;	\
 	SAVE_ALL;			\
+	TRACE_IRQS_OFF			\
 	movl %esp,%eax;			\
 	call smp_/**/name;		\
-	jmp ret_from_intr;	\
+	jmp ret_from_intr;		\
 	CFI_ENDPROC
 
 /* The include is where all of the SMP etc. interrupts come from */
@@ -726,7 +756,7 @@ nmi_stack_correct:
 	xorl %edx,%edx		# zero error code
 	movl %esp,%eax		# pt_regs pointer
 	call do_nmi
-	jmp restore_all
+	jmp restore_nocheck_notrace
 	CFI_ENDPROC
 
 nmi_stack_fixup:

arch/i386/kernel/irq.c

@@ -166,7 +166,7 @@ void irq_ctx_init(int cpu)
 	irqctx->tinfo.task              = NULL;
 	irqctx->tinfo.exec_domain       = NULL;
 	irqctx->tinfo.cpu               = cpu;
-	irqctx->tinfo.preempt_count     = SOFTIRQ_OFFSET;
+	irqctx->tinfo.preempt_count     = 0;
 	irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
 
 	softirq_ctx[cpu] = irqctx;
@@ -211,6 +211,10 @@ asmlinkage void do_softirq(void)
 			: "0"(isp)
 			: "memory", "cc", "edx", "ecx", "eax"
 		);
+		/*
+		 * Shouldnt happen, we returned above if in_interrupt():
+	 	 */
+		WARN_ON_ONCE(softirq_count());
 	}
 
 	local_irq_restore(flags);

include/asm-i386/irqflags.h

@@ -0,0 +1,56 @@
+/*
+ * include/asm-i386/irqflags.h
+ *
+ * IRQ flags handling
+ *
+ * This file gets included from lowlevel asm headers too, to provide
+ * wrapped versions of the local_irq_*() APIs, based on the
+ * raw_local_irq_*() macros from the lowlevel headers.
+ */
+#ifndef _ASM_IRQFLAGS_H
+#define _ASM_IRQFLAGS_H
+
+#define raw_local_save_flags(x)	do { typecheck(unsigned long,x); __asm__ __volatile__("pushfl ; popl %0":"=g" (x): /* no input */); } while (0)
+#define raw_local_irq_restore(x) do { typecheck(unsigned long,x); __asm__ __volatile__("pushl %0 ; popfl": /* no output */ :"g" (x):"memory", "cc"); } while (0)
+#define raw_local_irq_disable()	__asm__ __volatile__("cli": : :"memory")
+#define raw_local_irq_enable()	__asm__ __volatile__("sti": : :"memory")
+/* used in the idle loop; sti takes one instruction cycle to complete */
+#define raw_safe_halt()		__asm__ __volatile__("sti; hlt": : :"memory")
+/* used when interrupts are already enabled or to shutdown the processor */
+#define halt()			__asm__ __volatile__("hlt": : :"memory")
+
+#define raw_irqs_disabled_flags(flags)	(!((flags) & (1<<9)))
+
+/* For spinlocks etc */
+#define raw_local_irq_save(x)	__asm__ __volatile__("pushfl ; popl %0 ; cli":"=g" (x): /* no input */ :"memory")
+
+/*
+ * Do the CPU's IRQ-state tracing from assembly code. We call a
+ * C function, so save all the C-clobbered registers:
+ */
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+# define TRACE_IRQS_ON				\
+	pushl %eax;				\
+	pushl %ecx;				\
+	pushl %edx;				\
+	call trace_hardirqs_on;			\
+	popl %edx;				\
+	popl %ecx;				\
+	popl %eax;
+
+# define TRACE_IRQS_OFF				\
+	pushl %eax;				\
+	pushl %ecx;				\
+	pushl %edx;				\
+	call trace_hardirqs_off;		\
+	popl %edx;				\
+	popl %ecx;				\
+	popl %eax;
+
+#else
+# define TRACE_IRQS_ON
+# define TRACE_IRQS_OFF
+#endif
+
+#endif

include/asm-i386/spinlock.h

@@ -31,6 +31,11 @@
 	"jmp 1b\n" \
 	"3:\n\t"
 
+/*
+ * NOTE: there's an irqs-on section here, which normally would have to be
+ * irq-traced, but on CONFIG_TRACE_IRQFLAGS we never use
+ * __raw_spin_lock_string_flags().
+ */
 #define __raw_spin_lock_string_flags \
 	"\n1:\t" \
 	"lock ; decb %0\n\t" \

include/asm-i386/system.h

@@ -456,25 +456,7 @@ static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long l
 
 #define set_wmb(var, value) do { var = value; wmb(); } while (0)
 
-/* interrupt control.. */
+#include <linux/irqflags.h>
-#define local_save_flags(x)	do { typecheck(unsigned long,x); __asm__ __volatile__("pushfl ; popl %0":"=g" (x): /* no input */); } while (0)
-#define local_irq_restore(x) 	do { typecheck(unsigned long,x); __asm__ __volatile__("pushl %0 ; popfl": /* no output */ :"g" (x):"memory", "cc"); } while (0)
-#define local_irq_disable() 	__asm__ __volatile__("cli": : :"memory")
-#define local_irq_enable()	__asm__ __volatile__("sti": : :"memory")
-/* used in the idle loop; sti takes one instruction cycle to complete */
-#define safe_halt()		__asm__ __volatile__("sti; hlt": : :"memory")
-/* used when interrupts are already enabled or to shutdown the processor */
-#define halt()			__asm__ __volatile__("hlt": : :"memory")
-
-#define irqs_disabled()			\
-({					\
-	unsigned long flags;		\
-	local_save_flags(flags);	\
-	!(flags & (1<<9));		\
-})
-
-/* For spinlocks etc */
-#define local_irq_save(x)	__asm__ __volatile__("pushfl ; popl %0 ; cli":"=g" (x): /* no input */ :"memory")
 
 /*
  * disable hlt during certain critical i/o operations