[PATCH v2 1/6] x86/unwind: add new unwind interface and implementations

[Josh Poimboeuf]

The x86 stack dump code is a bit of a mess.  dump_trace() uses
callbacks, and each user of it seems to have slightly different
requirements, so there are several slightly different callbacks floating
around.

Also there are some upcoming features which will need more changes to
the stack dump code, including the printing of stack pt_regs, reliable
stack detection for live patching, and a DWARF unwinder.  Each of those
features would at least need more callbacks and/or callback interfaces,
resulting in a much bigger mess than what we have today.

Before doing all that, we should try to clean things up and replace
dump_trace() with something cleaner and more flexible.

The new unwinder is a simple state machine which was heavily inspired by
a suggestion from Andy Lutomirski:

  https://lkml.kernel.org/r/CALCETrUbNTqaM2LRyXGRx=kVLRPeY5A3Pc6k4TtQxF320rUT=w@xxxxxxxxxxxxxx

It's also similar to the libunwind API:

  http://www.nongnu.org/libunwind/man/libunwind(3).html

Some if its advantages:

- Simplicity: no more callback sprawl and less code duplication.

- Flexibility: it allows the caller to stop and inspect the stack state
  at each step in the unwinding process.

- Modularity: the unwinder code, console stack dump code, and stack
  metadata analysis code are all better separated so that changing one
  of them shouldn't have much of an impact on any of the others.

Two implementations are added which conform to the new unwind interface:

- The frame pointer unwinder which is used for CONFIG_FRAME_POINTER=y.

- The "guess" unwinder which is used for CONFIG_FRAME_POINTER=n.  This
  isn't an "unwinder" per se.  All it does is scan the stack for kernel
  text addresses.  But with no frame pointers, guesses are better than
  nothing in most cases.

Suggested-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
 arch/x86/include/asm/unwind.h  | 73 +++++++++++++++++++++++++++++++++
 arch/x86/kernel/Makefile       |  6 +++
 arch/x86/kernel/unwind_frame.c | 93 ++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/unwind_guess.c | 43 +++++++++++++++++++
 4 files changed, 215 insertions(+)
 create mode 100644 arch/x86/include/asm/unwind.h
 create mode 100644 arch/x86/kernel/unwind_frame.c
 create mode 100644 arch/x86/kernel/unwind_guess.c

diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
new file mode 100644
index 0000000..c4b6d1c
--- /dev/null
+++ b/arch/x86/include/asm/unwind.h
@@ -0,0 +1,73 @@
+#ifndef _ASM_X86_UNWIND_H
+#define _ASM_X86_UNWIND_H
+
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+
+struct unwind_state {
+	struct stack_info stack_info;
+	unsigned long stack_mask;
+	struct task_struct *task;
+	int graph_idx;
+#ifdef CONFIG_FRAME_POINTER
+	unsigned long *bp;
+#else
+	unsigned long *sp;
+#endif
+};
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long *first_frame);
+
+bool unwind_next_frame(struct unwind_state *state);
+
+static inline bool unwind_done(struct unwind_state *state)
+{
+	return state->stack_info.type == STACK_TYPE_UNKNOWN;
+}
+
+static inline
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+		  struct pt_regs *regs, unsigned long *first_frame)
+{
+	first_frame = first_frame ? : get_stack_pointer(task, regs);
+
+	__unwind_start(state, task, regs, first_frame);
+}
+
+#ifdef CONFIG_FRAME_POINTER
+
+static inline
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return NULL;
+
+	return state->bp + 1;
+}
+
+unsigned long unwind_get_return_address(struct unwind_state *state);
+
+#else /* !CONFIG_FRAME_POINTER */
+
+static inline
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+	return NULL;
+}
+
+static inline
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return 0;
+
+	return ftrace_graph_ret_addr(state->task, &state->graph_idx,
+				     *state->sp, state->sp);
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+#endif /* _ASM_X86_UNWIND_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0503f5b..45257cf 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -125,6 +125,12 @@ obj-$(CONFIG_EFI)			+= sysfb_efi.o
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o
 
+ifdef CONFIG_FRAME_POINTER
+obj-y					+= unwind_frame.o
+else
+obj-y					+= unwind_guess.o
+endif
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
new file mode 100644
index 0000000..a2456d4
--- /dev/null
+++ b/arch/x86/kernel/unwind_frame.c
@@ -0,0 +1,93 @@
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+#include <asm/bitops.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+#define FRAME_HEADER_SIZE (sizeof(long) * 2)
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	unsigned long addr;
+	unsigned long *addr_p = unwind_get_return_address_ptr(state);
+
+	if (unwind_done(state))
+		return 0;
+
+	addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
+				     addr_p);
+
+	return __kernel_text_address(addr) ? addr : 0;
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+static bool update_stack_state(struct unwind_state *state, void *addr,
+			       size_t len)
+{
+	struct stack_info *info = &state->stack_info;
+
+	/*
+	 * If addr isn't on the current stack, switch to the next one.
+	 *
+	 * We may have to traverse multiple stacks to deal with the possibility
+	 * that 'info->next_sp' could point to an empty stack and 'addr' could
+	 * be on a subsequent stack.
+	 */
+	while (!on_stack(info, addr, len))
+		if (get_stack_info(info->next_sp, state->task, info,
+				   &state->stack_mask))
+			return false;
+
+	return true;
+}
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+	unsigned long *next_bp;
+
+	if (unwind_done(state))
+		return false;
+
+	next_bp = (unsigned long *)*state->bp;
+
+	/* make sure the next frame's data is accessible */
+	if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE))
+		return false;
+
+	/* move to the next frame */
+	state->bp = next_bp;
+	return true;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long *first_frame)
+{
+	memset(state, 0, sizeof(*state));
+	state->task = task;
+
+	/* don't even attempt to start from user mode regs */
+	if (regs && user_mode(regs)) {
+		state->stack_info.type = STACK_TYPE_UNKNOWN;
+		return;
+	}
+
+	/* set up the starting stack frame */
+	state->bp = get_frame_pointer(task, regs);
+
+	/* initialize stack info and make sure the frame data is accessible */
+	get_stack_info(state->bp, state->task, &state->stack_info,
+		       &state->stack_mask);
+	update_stack_state(state, state->bp, FRAME_HEADER_SIZE);
+
+	/*
+	 * The caller can provide the address of the first frame directly
+	 * (first_frame) or indirectly (regs->sp) to indicate which stack frame
+	 * to start unwinding at.  Skip ahead until we reach it.
+	 */
+	while (!unwind_done(state) &&
+	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
+			state->bp < first_frame))
+		unwind_next_frame(state);
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
new file mode 100644
index 0000000..b5a834c
--- /dev/null
+++ b/arch/x86/kernel/unwind_guess.c
@@ -0,0 +1,43 @@
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/bitops.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+	struct stack_info *info = &state->stack_info;
+
+	if (unwind_done(state))
+		return false;
+
+	do {
+		for (state->sp++; state->sp < info->end; state->sp++)
+			if (__kernel_text_address(*state->sp))
+				return true;
+
+		state->sp = info->next_sp;
+
+	} while (!get_stack_info(state->sp, state->task, info,
+				 &state->stack_mask));
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long *first_frame)
+{
+	memset(state, 0, sizeof(*state));
+
+	state->task = task;
+	state->sp   = first_frame;
+
+	get_stack_info(first_frame, state->task, &state->stack_info,
+		       &state->stack_mask);
+
+	if (!__kernel_text_address(*first_frame))
+		unwind_next_frame(state);
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
-- 
2.7.4