Subject: DWARF2 EH-frame based stack unwinding
From: jbeulich@novell.com
Patch-mainline: no

Automatically created from "patches.suse/stack-unwind" by xen-port-patches.py

--- sle11-2009-05-14.orig/arch/x86/kernel/entry_32-xen.S	2009-05-14 11:20:49.000000000 +0200
+++ sle11-2009-05-14/arch/x86/kernel/entry_32-xen.S	2009-05-14 11:29:34.000000000 +0200
@@ -1290,6 +1290,38 @@ ENTRY(fixup_4gb_segment)
 	CFI_ENDPROC
 END(spurious_interrupt_bug)
 
+#ifdef CONFIG_STACK_UNWIND
+ENTRY(arch_unwind_init_running)
+	CFI_STARTPROC
+	movl	4(%esp), %edx
+	movl	(%esp), %ecx
+	leal	4(%esp), %eax
+	movl	%ebx, PT_EBX(%edx)
+	xorl	%ebx, %ebx
+	movl	%ebx, PT_ECX(%edx)
+	movl	%ebx, PT_EDX(%edx)
+	movl	%esi, PT_ESI(%edx)
+	movl	%edi, PT_EDI(%edx)
+	movl	%ebp, PT_EBP(%edx)
+	movl	%ebx, PT_EAX(%edx)
+	movl	$__USER_DS, PT_DS(%edx)
+	movl	$__USER_DS, PT_ES(%edx)
+	movl	$__KERNEL_PERCPU, PT_FS(%edx)
+	movl	%ebx, PT_ORIG_EAX(%edx)
+	movl	%ecx, PT_EIP(%edx)
+	movl	12(%esp), %ecx
+	movl	$__KERNEL_CS, PT_CS(%edx)
+	movl	%ebx, PT_EFLAGS(%edx)
+	movl	%eax, PT_OLDESP(%edx)
+	movl	8(%esp), %eax
+	movl	%ecx, 8(%esp)
+	movl	PT_EBX(%edx), %ebx
+	movl	$__KERNEL_DS, PT_OLDSS(%edx)
+	jmpl	*%eax
+	CFI_ENDPROC
+ENDPROC(arch_unwind_init_running)
+#endif
+
 ENTRY(kernel_thread_helper)
 	pushl $0		# fake return address for unwinder
 	CFI_STARTPROC
--- sle11-2009-05-14.orig/arch/x86/kernel/entry_64-xen.S	2009-03-16 16:38:16.000000000 +0100
+++ sle11-2009-05-14/arch/x86/kernel/entry_64-xen.S	2008-11-25 13:17:09.000000000 +0100
@@ -1419,3 +1419,36 @@ KPROBE_ENTRY(ignore_sysret)
 	HYPERVISOR_IRET 0
 	CFI_ENDPROC
 ENDPROC(ignore_sysret)
+
+#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
--- sle11-2009-05-14.orig/arch/x86/kernel/traps_32-xen.c	2008-11-25 13:17:06.000000000 +0100
+++ sle11-2009-05-14/arch/x86/kernel/traps_32-xen.c	2008-11-25 13:17:09.000000000 +0100
@@ -86,6 +86,11 @@ int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
 int kstack_depth_to_print = 24;
 static unsigned int code_bytes = 64;
+#ifdef CONFIG_STACK_UNWIND
+static int call_trace = 1;
+#else
+#define call_trace (-1)
+#endif
 static int ignore_nmis;
 static int die_counter;
 
@@ -156,6 +161,33 @@ print_context_stack(struct thread_info *
 	return bp;
 }
 
+struct ops_and_data {
+	const struct stacktrace_ops *ops;
+	void *data;
+};
+
+static asmlinkage int
+dump_trace_unwind(struct unwind_frame_info *info, void *data)
+{
+	struct ops_and_data *oad = (struct ops_and_data *)data;
+	int n = 0;
+	unsigned long sp = UNW_SP(info);
+
+	if (arch_unw_user_mode(info))
+		return -1;
+	while (unwind(info) == 0 && UNW_PC(info)) {
+		n++;
+		oad->ops->address(oad->data, UNW_PC(info), 1);
+		if (arch_unw_user_mode(info))
+			break;
+		if ((sp & ~(PAGE_SIZE - 1)) == (UNW_SP(info) & ~(PAGE_SIZE - 1))
+		    && sp > UNW_SP(info))
+			break;
+		sp = UNW_SP(info);
+	}
+	return n;
+}
+
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
@@ -163,6 +195,40 @@ void dump_trace(struct task_struct *task
 	if (!task)
 		task = current;
 
+	if (call_trace >= 0) {
+		int unw_ret = 0;
+		struct unwind_frame_info info;
+		struct ops_and_data oad = { .ops = ops, .data = data };
+
+		if (regs) {
+			if (unwind_init_frame_info(&info, task, regs) == 0)
+				unw_ret = dump_trace_unwind(&info, &oad);
+		} else if (task == current)
+			unw_ret = unwind_init_running(&info, dump_trace_unwind, &oad);
+		else {
+			if (unwind_init_blocked(&info, task) == 0)
+				unw_ret = dump_trace_unwind(&info, &oad);
+		}
+		if (unw_ret > 0) {
+			if (call_trace == 1 && !arch_unw_user_mode(&info)) {
+				ops->warning_symbol(data, "DWARF2 unwinder stuck at %s\n",
+					     UNW_PC(&info));
+				if (UNW_SP(&info) >= PAGE_OFFSET) {
+					ops->warning(data, "Leftover inexact backtrace:\n");
+					stack = (void *)UNW_SP(&info);
+					if (!stack)
+						return;
+					bp = UNW_FP(&info);
+				} else
+					ops->warning(data, "Full inexact backtrace again:\n");
+			} else if (call_trace >= 1)
+				return;
+			else
+				ops->warning(data, "Full inexact backtrace again:\n");
+		} else
+			ops->warning(data, "Inexact backtrace:\n");
+	}
+
 	if (!stack) {
 		unsigned long dummy;
 		stack = &dummy;
@@ -1226,3 +1292,19 @@ static int __init code_bytes_setup(char 
 	return 1;
 }
 __setup("code_bytes=", code_bytes_setup);
+
+#ifdef CONFIG_STACK_UNWIND
+static int __init call_trace_setup(char *s)
+{
+	if (strcmp(s, "old") == 0)
+		call_trace = -1;
+	else if (strcmp(s, "both") == 0)
+		call_trace = 0;
+	else if (strcmp(s, "newfallback") == 0)
+		call_trace = 1;
+	else if (strcmp(s, "new") == 2)
+		call_trace = 2;
+	return 1;
+}
+__setup("call_trace=", call_trace_setup);
+#endif
--- sle11-2009-05-14.orig/arch/x86/kernel/traps_64-xen.c	2008-11-25 13:17:06.000000000 +0100
+++ sle11-2009-05-14/arch/x86/kernel/traps_64-xen.c	2008-11-25 13:17:09.000000000 +0100
@@ -59,6 +59,11 @@ int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
 int kstack_depth_to_print = 12;
 static unsigned int code_bytes = 64;
+#ifdef CONFIG_STACK_UNWIND
+static int call_trace = 1;
+#else
+#define call_trace (-1)
+#endif
 static int ignore_nmis;
 static int die_counter;
 
@@ -165,6 +170,32 @@ static unsigned long *in_exception_stack
 	return NULL;
 }
 
+struct ops_and_data {
+	const struct stacktrace_ops *ops;
+	void *data;
+};
+
+static int dump_trace_unwind(struct unwind_frame_info *info, void *context)
+{
+	struct ops_and_data *oad = (struct ops_and_data *)context;
+	int n = 0;
+	unsigned long sp = UNW_SP(info);
+
+	if (arch_unw_user_mode(info))
+		return -1;
+	while (unwind(info) == 0 && UNW_PC(info)) {
+		n++;
+		oad->ops->address(oad->data, UNW_PC(info), 1);
+		if (arch_unw_user_mode(info))
+			break;
+		if ((sp & ~(PAGE_SIZE - 1)) == (UNW_SP(info) & ~(PAGE_SIZE - 1))
+		    && sp > UNW_SP(info))
+			break;
+		sp = UNW_SP(info);
+	}
+	return n;
+}
+
 /*
  * x86-64 can have up to three kernel stacks:
  * process stack
@@ -229,6 +260,42 @@ void dump_trace(struct task_struct *task
 	if (!task)
 		task = current;
 
+	if (call_trace >= 0) {
+		int unw_ret = 0;
+		struct unwind_frame_info info;
+		struct ops_and_data oad = { .ops = ops, .data = data };
+
+		if (regs) {
+			if (unwind_init_frame_info(&info, task, regs) == 0)
+				unw_ret = dump_trace_unwind(&info, &oad);
+		} else if (task == current)
+			unw_ret = unwind_init_running(&info, dump_trace_unwind, &oad);
+		else {
+			if (unwind_init_blocked(&info, task) == 0)
+				unw_ret = dump_trace_unwind(&info, &oad);
+		}
+		if (unw_ret > 0) {
+			if (call_trace == 1 && !arch_unw_user_mode(&info)) {
+				ops->warning_symbol(data, "DWARF2 unwinder stuck at %s\n",
+					     UNW_PC(&info));
+				if ((long)UNW_SP(&info) < 0) {
+					ops->warning(data, "Leftover inexact backtrace:\n");
+					stack = (unsigned long *)UNW_SP(&info);
+					if (!stack) {
+						put_cpu();
+						return;
+					}
+				} else
+					ops->warning(data, "Full inexact backtrace again:\n");
+			} else if (call_trace >= 1) {
+				put_cpu();
+				return;
+			} else
+				ops->warning(data, "Full inexact backtrace again:\n");
+		} else
+			ops->warning(data, "Inexact backtrace:\n");
+	}
+
 	if (!stack) {
 		unsigned long dummy;
 		stack = &dummy;
@@ -1242,3 +1309,21 @@ static int __init code_bytes_setup(char 
 	return 1;
 }
 __setup("code_bytes=", code_bytes_setup);
+
+#ifdef CONFIG_STACK_UNWIND
+static int __init call_trace_setup(char *s)
+{
+	if (!s)
+		return -EINVAL;
+	if (strcmp(s, "old") == 0)
+		call_trace = -1;
+	else if (strcmp(s, "both") == 0)
+		call_trace = 0;
+	else if (strcmp(s, "newfallback") == 0)
+		call_trace = 1;
+	else if (strcmp(s, "new") == 0)
+		call_trace = 2;
+	return 0;
+}
+early_param("call_trace", call_trace_setup);
+#endif