Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1485258 > unrolled thread

[PATCH v2 0/6] x86/dumpstack: replace dump_trace() with a new unwinder

Started byJosh Poimboeuf <jpoimboe@redhat.com>
First post2016-09-16 21:20 +0200
Last post2016-09-20 17:10 +0200
Articles 7 — 2 participants

Back to article view | Back to linux.kernel

Contents

  [PATCH v2 0/6] x86/dumpstack: replace dump_trace() with a new unwinder Josh Poimboeuf <jpoimboe@redhat.com> - 2016-09-16 21:20 +0200
    [PATCH v2 3/6] x86/stacktrace: convert save_stack_trace_*() to use the new unwinder Josh Poimboeuf <jpoimboe@redhat.com> - 2016-09-16 21:20 +0200
      [tip:x86/asm] x86/stacktrace: Convert save_stack_trace_*() to use  the new unwinder tip-bot for Josh Poimboeuf <tipbot@zytor.com> - 2016-09-20 17:10 +0200
    [PATCH v2 1/6] x86/unwind: add new unwind interface and implementations Josh Poimboeuf <jpoimboe@redhat.com> - 2016-09-16 21:20 +0200
      [tip:x86/asm] x86/unwind: Add new unwind interface and  implementations tip-bot for Josh Poimboeuf <tipbot@zytor.com> - 2016-09-20 17:10 +0200
    [PATCH v2 2/6] perf/x86: convert perf_callchain_kernel() to use the new unwinder Josh Poimboeuf <jpoimboe@redhat.com> - 2016-09-16 21:30 +0200
      [tip:x86/asm] perf/x86: Convert perf_callchain_kernel() to use the  new unwinder tip-bot for Josh Poimboeuf <tipbot@zytor.com> - 2016-09-20 17:10 +0200

#1485258 — [PATCH v2 0/6] x86/dumpstack: replace dump_trace() with a new unwinder

FromJosh Poimboeuf <jpoimboe@redhat.com>
Date2016-09-16 21:20 +0200
Subject[PATCH v2 0/6] x86/dumpstack: replace dump_trace() with a new unwinder
Message-ID<si6Q1-uW-9@gated-at.bofh.it>
v2:
- rebase on latest tip
- remove NULL task pointer convention

---

The last version was posted as part of a much larger patch set:

  https://lkml.kernel.org/r/cover.1471525031.git.jpoimboe@redhat.com

People complained about the set being too big, so it was split up into
more digestible pieces.  All the prerequisite patches for the unwinder
have now been merged.

See patch 1/6 for the background and justification for this change.

Josh Poimboeuf (6):
  x86/unwind: add new unwind interface and implementations
  perf/x86: convert perf_callchain_kernel() to use the new unwinder
  x86/stacktrace: convert save_stack_trace_*() to use the new unwinder
  oprofile/x86: convert x86_backtrace() to use the new unwinder
  x86/dumpstack: convert show_trace_log_lvl() to use the new unwinder
  x86/dumpstack: remove dump_trace() and related callbacks

 arch/x86/events/core.c            |  33 +++-----
 arch/x86/include/asm/stacktrace.h |  46 +----------
 arch/x86/include/asm/unwind.h     |  73 ++++++++++++++++
 arch/x86/kernel/Makefile          |   6 ++
 arch/x86/kernel/dumpstack.c       | 170 +++++++++++++++++---------------------
 arch/x86/kernel/dumpstack_32.c    |  44 +---------
 arch/x86/kernel/dumpstack_64.c    |  78 +----------------
 arch/x86/kernel/stacktrace.c      |  74 +++++++----------
 arch/x86/kernel/unwind_frame.c    |  93 +++++++++++++++++++++
 arch/x86/kernel/unwind_guess.c    |  43 ++++++++++
 arch/x86/oprofile/backtrace.c     |  39 ++++-----
 11 files changed, 357 insertions(+), 342 deletions(-)
 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

-- 
2.7.4

[toc] | [next] | [standalone]

#1485259 — [PATCH v2 3/6] x86/stacktrace: convert save_stack_trace_*() to use the new unwinder

FromJosh Poimboeuf <jpoimboe@redhat.com>
Date2016-09-16 21:20 +0200
Subject[PATCH v2 3/6] x86/stacktrace: convert save_stack_trace_*() to use the new unwinder
Message-ID<si6Q2-uW-21@gated-at.bofh.it>
In reply to#1485258
Convert save_stack_trace_*() to use the new unwinder.  dump_trace() has
been deprecated.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/kernel/stacktrace.c | 74 +++++++++++++++++---------------------------
 1 file changed, 29 insertions(+), 45 deletions(-)

diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 23fa81e..0653788 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -8,73 +8,59 @@
 #include <linux/export.h>
 #include <linux/uaccess.h>
 #include <asm/stacktrace.h>
+#include <asm/unwind.h>
 
-static int save_stack_stack(void *data, const char *name)
+static int save_stack_address(struct stack_trace *trace, unsigned long addr,
+			      bool nosched)
 {
-	return 0;
-}
-
-static int
-__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)
-{
-	struct stack_trace *trace = data;
-#ifdef CONFIG_FRAME_POINTER
-	if (!reliable)
-		return 0;
-#endif
 	if (nosched && in_sched_functions(addr))
 		return 0;
+
 	if (trace->skip > 0) {
 		trace->skip--;
 		return 0;
 	}
-	if (trace->nr_entries < trace->max_entries) {
-		trace->entries[trace->nr_entries++] = addr;
-		return 0;
-	} else {
-		return -1; /* no more room, stop walking the stack */
-	}
-}
 
-static int save_stack_address(void *data, unsigned long addr, int reliable)
-{
-	return __save_stack_address(data, addr, reliable, false);
+	if (trace->nr_entries >= trace->max_entries)
+		return -1;
+
+	trace->entries[trace->nr_entries++] = addr;
+	return 0;
 }
 
-static int
-save_stack_address_nosched(void *data, unsigned long addr, int reliable)
+static void __save_stack_trace(struct stack_trace *trace,
+			       struct task_struct *task, struct pt_regs *regs,
+			       bool nosched)
 {
-	return __save_stack_address(data, addr, reliable, true);
-}
+	struct unwind_state state;
+	unsigned long addr;
 
-static const struct stacktrace_ops save_stack_ops = {
-	.stack		= save_stack_stack,
-	.address	= save_stack_address,
-	.walk_stack	= print_context_stack,
-};
+	if (regs)
+		save_stack_address(trace, regs->ip, nosched);
 
-static const struct stacktrace_ops save_stack_ops_nosched = {
-	.stack		= save_stack_stack,
-	.address	= save_stack_address_nosched,
-	.walk_stack	= print_context_stack,
-};
+	for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
+	     unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || save_stack_address(trace, addr, nosched))
+			break;
+	}
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
 
 /*
  * Save stack-backtrace addresses into a stack_trace buffer.
  */
 void save_stack_trace(struct stack_trace *trace)
 {
-	dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	__save_stack_trace(trace, current, NULL, false);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 {
-	dump_trace(current, regs, NULL, 0, &save_stack_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	__save_stack_trace(trace, current, regs, false);
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
@@ -82,9 +68,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	if (!try_get_task_stack(tsk))
 		return;
 
-	dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	__save_stack_trace(trace, tsk, NULL, true);
 
 	put_task_stack(tsk);
 }
-- 
2.7.4

[toc] | [prev] | [next] | [standalone]

#1487420 — [tip:x86/asm] x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder

Fromtip-bot for Josh Poimboeuf <tipbot@zytor.com>
Date2016-09-20 17:10 +0200
Subject[tip:x86/asm] x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder
Message-ID<sjuQi-4Gm-29@gated-at.bofh.it>
In reply to#1485259
Commit-ID:  49a612c6b06defbd6e6d334c683fea28006728e3
Gitweb:     http://git.kernel.org/tip/49a612c6b06defbd6e6d334c683fea28006728e3
Author:     Josh Poimboeuf <jpoimboe@redhat.com>
AuthorDate: Fri, 16 Sep 2016 14:18:14 -0500
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 20 Sep 2016 08:29:33 +0200

x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder

Convert save_stack_trace_*() to use the new unwinder.  dump_trace() has
been deprecated.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nilay Vaish <nilayvaish@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/815494c627d89887db0ce56ceffd58ad16ee6c21.1474045023.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/stacktrace.c | 74 +++++++++++++++++---------------------------
 1 file changed, 29 insertions(+), 45 deletions(-)

diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 23fa81e..0653788 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -8,73 +8,59 @@
 #include <linux/export.h>
 #include <linux/uaccess.h>
 #include <asm/stacktrace.h>
+#include <asm/unwind.h>
 
-static int save_stack_stack(void *data, const char *name)
+static int save_stack_address(struct stack_trace *trace, unsigned long addr,
+			      bool nosched)
 {
-	return 0;
-}
-
-static int
-__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)
-{
-	struct stack_trace *trace = data;
-#ifdef CONFIG_FRAME_POINTER
-	if (!reliable)
-		return 0;
-#endif
 	if (nosched && in_sched_functions(addr))
 		return 0;
+
 	if (trace->skip > 0) {
 		trace->skip--;
 		return 0;
 	}
-	if (trace->nr_entries < trace->max_entries) {
-		trace->entries[trace->nr_entries++] = addr;
-		return 0;
-	} else {
-		return -1; /* no more room, stop walking the stack */
-	}
-}
 
-static int save_stack_address(void *data, unsigned long addr, int reliable)
-{
-	return __save_stack_address(data, addr, reliable, false);
+	if (trace->nr_entries >= trace->max_entries)
+		return -1;
+
+	trace->entries[trace->nr_entries++] = addr;
+	return 0;
 }
 
-static int
-save_stack_address_nosched(void *data, unsigned long addr, int reliable)
+static void __save_stack_trace(struct stack_trace *trace,
+			       struct task_struct *task, struct pt_regs *regs,
+			       bool nosched)
 {
-	return __save_stack_address(data, addr, reliable, true);
-}
+	struct unwind_state state;
+	unsigned long addr;
 
-static const struct stacktrace_ops save_stack_ops = {
-	.stack		= save_stack_stack,
-	.address	= save_stack_address,
-	.walk_stack	= print_context_stack,
-};
+	if (regs)
+		save_stack_address(trace, regs->ip, nosched);
 
-static const struct stacktrace_ops save_stack_ops_nosched = {
-	.stack		= save_stack_stack,
-	.address	= save_stack_address_nosched,
-	.walk_stack	= print_context_stack,
-};
+	for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
+	     unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || save_stack_address(trace, addr, nosched))
+			break;
+	}
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
 
 /*
  * Save stack-backtrace addresses into a stack_trace buffer.
  */
 void save_stack_trace(struct stack_trace *trace)
 {
-	dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	__save_stack_trace(trace, current, NULL, false);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 {
-	dump_trace(current, regs, NULL, 0, &save_stack_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	__save_stack_trace(trace, current, regs, false);
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
@@ -82,9 +68,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	if (!try_get_task_stack(tsk))
 		return;
 
-	dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	__save_stack_trace(trace, tsk, NULL, true);
 
 	put_task_stack(tsk);
 }

[toc] | [prev] | [next] | [standalone]

#1485261 — [PATCH v2 1/6] x86/unwind: add new unwind interface and implementations

FromJosh Poimboeuf <jpoimboe@redhat.com>
Date2016-09-16 21:20 +0200
Subject[PATCH v2 1/6] x86/unwind: add new unwind interface and implementations
Message-ID<si6Q2-uW-29@gated-at.bofh.it>
In reply to#1485258
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@mail.gmail.com

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@amacapital.net>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 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

[toc] | [prev] | [next] | [standalone]

#1487419 — [tip:x86/asm] x86/unwind: Add new unwind interface and implementations

Fromtip-bot for Josh Poimboeuf <tipbot@zytor.com>
Date2016-09-20 17:10 +0200
Subject[tip:x86/asm] x86/unwind: Add new unwind interface and implementations
Message-ID<sjuQi-4Gm-23@gated-at.bofh.it>
In reply to#1485261
Commit-ID:  7c7900f89770d7fba96100d8a9e18043a1af3973
Gitweb:     http://git.kernel.org/tip/7c7900f89770d7fba96100d8a9e18043a1af3973
Author:     Josh Poimboeuf <jpoimboe@redhat.com>
AuthorDate: Fri, 16 Sep 2016 14:18:12 -0500
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 20 Sep 2016 08:29:33 +0200

x86/unwind: Add new unwind interface and implementations

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@mail.gmail.com

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@amacapital.net>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nilay Vaish <nilayvaish@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/6dc2f909c47533d213d0505f0a113e64585bec82.1474045023.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 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(+)

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);

[toc] | [prev] | [next] | [standalone]

#1485263 — [PATCH v2 2/6] perf/x86: convert perf_callchain_kernel() to use the new unwinder

FromJosh Poimboeuf <jpoimboe@redhat.com>
Date2016-09-16 21:30 +0200
Subject[PATCH v2 2/6] perf/x86: convert perf_callchain_kernel() to use the new unwinder
Message-ID<si6ZH-ym-13@gated-at.bofh.it>
In reply to#1485258
Convert perf_callchain_kernel() to use the new unwinder.  dump_trace()
has been deprecated.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/events/core.c | 33 ++++++++++-----------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index dd3a1dc..d31735f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -37,6 +37,7 @@
 #include <asm/timer.h>
 #include <asm/desc.h>
 #include <asm/ldt.h>
+#include <asm/unwind.h>
 
 #include "perf_event.h"
 
@@ -2267,31 +2268,12 @@ void arch_perf_update_userpage(struct perf_event *event,
 	cyc2ns_read_end(data);
 }
 
-/*
- * callchain support
- */
-
-static int backtrace_stack(void *data, const char *name)
-{
-	return 0;
-}
-
-static int backtrace_address(void *data, unsigned long addr, int reliable)
-{
-	struct perf_callchain_entry_ctx *entry = data;
-
-	return perf_callchain_store(entry, addr);
-}
-
-static const struct stacktrace_ops backtrace_ops = {
-	.stack			= backtrace_stack,
-	.address		= backtrace_address,
-	.walk_stack		= print_context_stack_bp,
-};
-
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	struct unwind_state state;
+	unsigned long addr;
+
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
@@ -2300,7 +2282,12 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	if (perf_callchain_store(entry, regs->ip))
 		return;
 
-	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
+	for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
+	     unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
 }
 
 static inline int
-- 
2.7.4

[toc] | [prev] | [next] | [standalone]

#1487423 — [tip:x86/asm] perf/x86: Convert perf_callchain_kernel() to use the new unwinder

Fromtip-bot for Josh Poimboeuf <tipbot@zytor.com>
Date2016-09-20 17:10 +0200
Subject[tip:x86/asm] perf/x86: Convert perf_callchain_kernel() to use the new unwinder
Message-ID<sjuQi-4Gm-33@gated-at.bofh.it>
In reply to#1485263
Commit-ID:  35f4d9b32527c08c3da3982aedae5198dc663ce8
Gitweb:     http://git.kernel.org/tip/35f4d9b32527c08c3da3982aedae5198dc663ce8
Author:     Josh Poimboeuf <jpoimboe@redhat.com>
AuthorDate: Fri, 16 Sep 2016 14:18:13 -0500
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 20 Sep 2016 08:29:33 +0200

perf/x86: Convert perf_callchain_kernel() to use the new unwinder

Convert perf_callchain_kernel() to use the new unwinder.  dump_trace()
has been deprecated.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nilay Vaish <nilayvaish@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a2df0c4f09b3d438e11b41681f10b0775a819a7f.1474045023.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/core.c | 33 ++++++++++-----------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 477dc38..0a8bd7f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -37,6 +37,7 @@
 #include <asm/timer.h>
 #include <asm/desc.h>
 #include <asm/ldt.h>
+#include <asm/unwind.h>
 
 #include "perf_event.h"
 
@@ -2247,31 +2248,12 @@ void arch_perf_update_userpage(struct perf_event *event,
 	cyc2ns_read_end(data);
 }
 
-/*
- * callchain support
- */
-
-static int backtrace_stack(void *data, const char *name)
-{
-	return 0;
-}
-
-static int backtrace_address(void *data, unsigned long addr, int reliable)
-{
-	struct perf_callchain_entry_ctx *entry = data;
-
-	return perf_callchain_store(entry, addr);
-}
-
-static const struct stacktrace_ops backtrace_ops = {
-	.stack			= backtrace_stack,
-	.address		= backtrace_address,
-	.walk_stack		= print_context_stack_bp,
-};
-
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	struct unwind_state state;
+	unsigned long addr;
+
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
@@ -2280,7 +2262,12 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	if (perf_callchain_store(entry, regs->ip))
 		return;
 
-	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
+	for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
+	     unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
 }
 
 static inline int

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web