ARM: lockdep: fix unannotated irqs-on

CPU: Testing write buffer coherency: ok
------------[ cut here ]------------
WARNING: at kernel/lockdep.c:3145 check_flags+0xcc/0x1dc()
Modules linked in:
[<c0035120>] (unwind_backtrace+0x0/0xf8) from [<c0355374>] (dump_stack+0x20/0x24)
[<c0355374>] (dump_stack+0x20/0x24) from [<c0060c04>] (warn_slowpath_common+0x58/0x70)
[<c0060c04>] (warn_slowpath_common+0x58/0x70) from [<c0060c3c>] (warn_slowpath_null+0x20/0x24)
[<c0060c3c>] (warn_slowpath_null+0x20/0x24) from [<c008f224>] (check_flags+0xcc/0x1dc)
[<c008f224>] (check_flags+0xcc/0x1dc) from [<c00945dc>] (lock_acquire+0x50/0x140)
[<c00945dc>] (lock_acquire+0x50/0x140) from [<c0358434>] (_raw_spin_lock+0x50/0x88)
[<c0358434>] (_raw_spin_lock+0x50/0x88) from [<c00fd114>] (set_task_comm+0x2c/0x60)
[<c00fd114>] (set_task_comm+0x2c/0x60) from [<c007e184>] (kthreadd+0x30/0x108)
[<c007e184>] (kthreadd+0x30/0x108) from [<c0030104>] (kernel_thread_exit+0x0/0x8)
---[ end trace 1b75b31a2719ed1c ]---
possible reason: unannotated irqs-on.
irq event stamp: 3
hardirqs last  enabled at (2): [<c0059bb0>] finish_task_switch+0x48/0xb0
hardirqs last disabled at (3): [<c002f0b0>] ret_slow_syscall+0xc/0x1c
softirqs last  enabled at (0): [<c005f3e0>] copy_process+0x394/0xe5c
softirqs last disabled at (0): [<(null)>] (null)

Fix this by ensuring that the lockdep interrupt state is manipulated in
the appropriate places.  We essentially treat userspace as an entirely
separate environment which isn't relevant to lockdep (lockdep doesn't
monitor userspace.)  We don't tell lockdep that IRQs will be enabled
in that environment.

Instead, when creating kernel threads (which is a rare event compared
to entering/leaving userspace) we have to update the lockdep state.  Do
this by starting threads with IRQs disabled, and in the kthread helper,
tell lockdep that IRQs are enabled, and enable them.

This provides lockdep with a consistent view of the current IRQ state
in kernel space.

This also revert portions of 0d928b0b616d1c5c5fe76019a87cba171ca91633
which didn't fix the problem.

Tested-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7ee48e7..3fd7861 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -162,8 +162,6 @@
 	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
 	@
 	stmia	r5, {r0 - r4}
-
-	asm_trace_hardirqs_off
 	.endm
 
 	.align	5
@@ -204,7 +202,7 @@
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
-	disable_irq
+	disable_irq_notrace
 
 	@
 	@ restore SPSR and restart the instruction
@@ -218,6 +216,9 @@
 __irq_svc:
 	svc_entry
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
@@ -291,7 +292,7 @@
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
-1:	disable_irq
+1:	disable_irq_notrace
 
 	@
 	@ restore SPSR and restart the instruction
@@ -327,7 +328,7 @@
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
-	disable_irq
+	disable_irq_notrace
 
 	@
 	@ restore SPSR and restart the instruction
@@ -393,8 +394,6 @@
 	@ Clear FP to mark the first stack frame
 	@
 	zero_fp
-
-	asm_trace_hardirqs_off
 	.endm
 
 	.macro	kuser_cmpxchg_check
@@ -465,9 +464,6 @@
  THUMB(	movne	r0, #0		)
  THUMB(	strne	r0, [r0]	)
 #endif
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_on
-#endif
 
 	mov	why, #0
 	b	ret_to_user
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index acf5e6f..a4a9cc8 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -351,17 +351,21 @@
 
 /*
  * Shuffle the argument into the correct register before calling the
- * thread function.  r1 is the thread argument, r2 is the pointer to
- * the thread function, and r3 points to the exit function.
+ * thread function.  r4 is the thread argument, r5 is the pointer to
+ * the thread function, and r6 points to the exit function.
  */
 extern void kernel_thread_helper(void);
 asm(	".pushsection .text\n"
 "	.align\n"
 "	.type	kernel_thread_helper, #function\n"
 "kernel_thread_helper:\n"
-"	mov	r0, r1\n"
-"	mov	lr, r3\n"
-"	mov	pc, r2\n"
+#ifdef CONFIG_TRACE_IRQFLAGS
+"	bl	trace_hardirqs_on\n"
+#endif
+"	msr	cpsr_c, r7\n"
+"	mov	r0, r4\n"
+"	mov	lr, r6\n"
+"	mov	pc, r5\n"
 "	.size	kernel_thread_helper, . - kernel_thread_helper\n"
 "	.popsection");
 
@@ -391,11 +395,12 @@
 
 	memset(&regs, 0, sizeof(regs));
 
-	regs.ARM_r1 = (unsigned long)arg;
-	regs.ARM_r2 = (unsigned long)fn;
-	regs.ARM_r3 = (unsigned long)kernel_thread_exit;
+	regs.ARM_r4 = (unsigned long)arg;
+	regs.ARM_r5 = (unsigned long)fn;
+	regs.ARM_r6 = (unsigned long)kernel_thread_exit;
+	regs.ARM_r7 = SVC_MODE | PSR_ENDSTATE | PSR_ISETSTATE;
 	regs.ARM_pc = (unsigned long)kernel_thread_helper;
-	regs.ARM_cpsr = SVC_MODE | PSR_ENDSTATE | PSR_ISETSTATE;
+	regs.ARM_cpsr = regs.ARM_r7 | PSR_I_BIT;
 
 	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
 }