[PATCH] x86_64: reliable stack trace support (x86-64)

These are the x86_64-specific pieces to enable reliable stack traces. The
only restriction with this is that it currently cannot unwind across the
interrupt->normal stack boundary, as that transition is lacking proper
annotation.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 91 insertions, 7 deletions

diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index 9999d70..6c68bee 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -1089,3 +1089,36 @@ ENTRY(call_softirq)
 	ret
 	CFI_ENDPROC
 ENDPROC(call_softirq)
+
+#ifdef CONFIG_STACK_UNWIND
+ENTRY(arch_unwind_init_running)
+	CFI_STARTPROC
+	movq	%r15, R15(%rdi)
+	movq	%r14, R14(%rdi)
+	xchgq	%rsi, %rdx
+	movq	%r13, R13(%rdi)
+	movq	%r12, R12(%rdi)
+	xorl	%eax, %eax
+	movq	%rbp, RBP(%rdi)
+	movq	%rbx, RBX(%rdi)
+	movq	(%rsp), %rcx
+	movq	%rax, R11(%rdi)
+	movq	%rax, R10(%rdi)
+	movq	%rax, R9(%rdi)
+	movq	%rax, R8(%rdi)
+	movq	%rax, RAX(%rdi)
+	movq	%rax, RCX(%rdi)
+	movq	%rax, RDX(%rdi)
+	movq	%rax, RSI(%rdi)
+	movq	%rax, RDI(%rdi)
+	movq	%rax, ORIG_RAX(%rdi)
+	movq	%rcx, RIP(%rdi)
+	leaq	8(%rsp), %rcx
+	movq	$__KERNEL_CS, CS(%rdi)
+	movq	%rax, EFLAGS(%rdi)
+	movq	%rcx, RSP(%rdi)
+	movq	$__KERNEL_DS, SS(%rdi)
+	jmpq	*%rdx
+	CFI_ENDPROC
+ENDPROC(arch_unwind_init_running)
+#endif
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index dcb77b4..d6fa414 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -334,7 +334,7 @@ void show_regs(struct pt_regs *regs)
 {
 	printk("CPU %d:", smp_processor_id());
 	__show_regs(regs);
-	show_trace(&regs->rsp);
+	show_trace(NULL, regs, (void *)(regs + 1));
 }
 
 /*
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 9f8f1ef..eb1534f 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -29,6 +29,7 @@
 #include <linux/nmi.h>
 #include <linux/kprobes.h>
 #include <linux/kexec.h>
+#include <linux/unwind.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -39,7 +40,7 @@
 #include <asm/i387.h>
 #include <asm/kdebug.h>
 #include <asm/processor.h>
-
+#include <asm/unwind.h>
 #include <asm/smp.h>
 #include <asm/pgalloc.h>
 #include <asm/pda.h>
@@ -189,6 +190,23 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 	return NULL;
 }
 
+static void show_trace_unwind(struct unwind_frame_info *info, void *context)
+{
+	int i = 11;
+
+	while (unwind(info) == 0 && UNW_PC(info)) {
+		if (i > 50) {
+			printk("\n       ");
+			i = 7;
+		} else
+			i += printk(" ");
+		i += printk_address(UNW_PC(info));
+		if (arch_unw_user_mode(info))
+			break;
+	}
+	printk("\n");
+}
+
 /*
  * x86-64 can have upto three kernel stacks: 
  * process stack
@@ -196,15 +214,34 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-void show_trace(unsigned long *stack)
+void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * stack)
 {
 	const unsigned cpu = safe_smp_processor_id();
 	unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
 	int i;
 	unsigned used = 0;
+	struct unwind_frame_info info;
 
 	printk("\nCall Trace:");
 
+	if (!tsk)
+		tsk = current;
+
+	if (regs) {
+		if (unwind_init_frame_info(&info, tsk, regs) == 0) {
+			show_trace_unwind(&info, NULL);
+			return;
+		}
+	} else if (tsk == current) {
+		if (unwind_init_running(&info, show_trace_unwind, NULL) == 0)
+			return;
+	} else {
+		if (unwind_init_blocked(&info, tsk) == 0) {
+			show_trace_unwind(&info, NULL);
+			return;
+		}
+	}
+
 #define HANDLE_STACK(cond) \
 	do while (cond) { \
 		unsigned long addr = *stack++; \
@@ -262,7 +299,7 @@ void show_trace(unsigned long *stack)
 	printk("\n");
 }
 
-void show_stack(struct task_struct *tsk, unsigned long * rsp)
+static void _show_stack(struct task_struct *tsk, struct pt_regs *regs, unsigned long * rsp)
 {
 	unsigned long *stack;
 	int i;
@@ -296,7 +333,12 @@ void show_stack(struct task_struct *tsk, unsigned long * rsp)
 		printk("%016lx ", *stack++);
 		touch_nmi_watchdog();
 	}
-	show_trace((unsigned long *)rsp);
+	show_trace(tsk, regs, rsp);
+}
+
+void show_stack(struct task_struct *tsk, unsigned long * rsp)
+{
+	_show_stack(tsk, NULL, rsp);
 }
 
 /*
@@ -305,7 +347,7 @@ void show_stack(struct task_struct *tsk, unsigned long * rsp)
 void dump_stack(void)
 {
 	unsigned long dummy;
-	show_trace(&dummy);
+	show_trace(NULL, NULL, &dummy);
 }
 
 EXPORT_SYMBOL(dump_stack);
@@ -332,7 +374,7 @@ void show_registers(struct pt_regs *regs)
 	if (in_kernel) {
 
 		printk("Stack: ");
-		show_stack(NULL, (unsigned long*)rsp);
+		_show_stack(NULL, regs, (unsigned long*)rsp);
 
 		printk("\nCode: ");
 		if (regs->rip < PAGE_OFFSET)
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 5968c24..1c6a5f3 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -45,6 +45,15 @@ SECTIONS
 
   RODATA
 
+#ifdef CONFIG_STACK_UNWIND
+  . = ALIGN(8);
+  .eh_frame : AT(ADDR(.eh_frame) - LOAD_OFFSET) {
+	__start_unwind = .;
+  	*(.eh_frame)
+	__end_unwind = .;
+  }
+#endif
+
 				/* Data */
   .data : AT(ADDR(.data) - LOAD_OFFSET) {
 	*(.data)