[PATCH v2 0/5] ARM: Convert to ARCH_STACKWALK

[PATCH v2 0/5] ARM: Convert to ARCH_STACKWALK

[Li Huafei]

This series mainly updates the ARM stack trace code to use the newer and
simpler arch_stack_walk() interface. Two issues were fixed before that
(see patch 1 and 2), as well as allowing stack_trace_save_tsk() to
trace non-current tasks (see patch 3).

v2:
 - As suggested by Mark, the commit logs for patch 4 and 5 were
   refined for easy review.

v1: https://lore.kernel.org/lkml/20220712021527.109921-1-lihuafei1@huawei.com/

Li Huafei (5):
  ARM: stacktrace: Skip frame pointer boundary check for
    call_with_stack()
  ARM: stacktrace: Avoid duplicate saving of exception PC value
  ARM: stacktrace: Allow stack trace saving for non-current tasks
  ARM: stacktrace: Make stack walk callback consistent with generic code
  ARM: stacktrace: Convert stacktrace to generic ARCH_STACKWALK

 arch/arm/Kconfig                  |   1 +
 arch/arm/include/asm/stacktrace.h |   8 +-
 arch/arm/kernel/perf_callchain.c  |   9 +-
 arch/arm/kernel/return_address.c  |   9 +-
 arch/arm/kernel/stacktrace.c      | 195 +++++++++++++-----------------
 arch/arm/lib/call_with_stack.S    |   2 +
 6 files changed, 105 insertions(+), 119 deletions(-)

-- 
2.17.1

[PATCH v2 1/5] ARM: stacktrace: Skip frame pointer boundary check for call_with_stack()

[Li Huafei]

When using the frame pointer unwinder, it was found that the stack trace
output of stack_trace_save() is incomplete if the stack contains
call_with_stack():

 [0x7f00002c] dump_stack_task+0x2c/0x90 [hrtimer]
 [0x7f0000a0] hrtimer_hander+0x10/0x18 [hrtimer]
 [0x801a67f0] __hrtimer_run_queues+0x1b0/0x3b4
 [0x801a7350] hrtimer_run_queues+0xc4/0xd8
 [0x801a597c] update_process_times+0x3c/0x88
 [0x801b5a98] tick_periodic+0x50/0xd8
 [0x801b5bf4] tick_handle_periodic+0x24/0x84
 [0x8010ffc4] twd_handler+0x38/0x48
 [0x8017d220] handle_percpu_devid_irq+0xa8/0x244
 [0x80176e9c] generic_handle_domain_irq+0x2c/0x3c
 [0x8052e3a8] gic_handle_irq+0x7c/0x90
 [0x808ab15c] generic_handle_arch_irq+0x60/0x80
 [0x8051191c] call_with_stack+0x1c/0x20

For the frame pointer unwinder, unwind_frame() checks stackframe::fp by
stackframe::sp. Since call_with_stack() switches the SP from one stack
to another, stackframe::fp and stackframe: :sp will point to different
stacks, so we can no longer check stackframe::fp by stackframe::sp. Skip
checking stackframe::fp at this point to avoid this problem.

Signed-off-by: Li Huafei <lihuafei1@huawei.com>
---
 arch/arm/kernel/stacktrace.c   | 40 ++++++++++++++++++++++++++++------
 arch/arm/lib/call_with_stack.S |  2 ++
 2 files changed, 35 insertions(+), 7 deletions(-)

diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index d0fa2037460a..af87040b0353 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -9,6 +9,8 @@
 #include <asm/stacktrace.h>
 #include <asm/traps.h>
 
+#include "reboot.h"
+
 #if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
 /*
  * Unwind the current stack frame and store the new register values in the
@@ -39,29 +41,53 @@
  * Note that with framepointer enabled, even the leaf functions have the same
  * prologue and epilogue, therefore we can ignore the LR value in this case.
  */
-int notrace unwind_frame(struct stackframe *frame)
+
+extern unsigned long call_with_stack_end;
+
+static int frame_pointer_check(struct stackframe *frame)
 {
 	unsigned long high, low;
 	unsigned long fp = frame->fp;
+	unsigned long pc = frame->pc;
+
+	/*
+	 * call_with_stack() is the only place we allow SP to jump from one
+	 * stack to another, with FP and SP pointing to different stacks,
+	 * skipping the FP boundary check at this point.
+	 */
+	if (pc >= (unsigned long)&call_with_stack &&
+			pc < (unsigned long)&call_with_stack_end)
+		return 0;
 
 	/* only go to a higher address on the stack */
 	low = frame->sp;
 	high = ALIGN(low, THREAD_SIZE);
 
-#ifdef CONFIG_CC_IS_CLANG
 	/* check current frame pointer is within bounds */
+#ifdef CONFIG_CC_IS_CLANG
 	if (fp < low + 4 || fp > high - 4)
 		return -EINVAL;
-
-	frame->sp = frame->fp;
-	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
-	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 4));
 #else
-	/* check current frame pointer is within bounds */
 	if (fp < low + 12 || fp > high - 4)
 		return -EINVAL;
+#endif
+
+	return 0;
+}
+
+int notrace unwind_frame(struct stackframe *frame)
+{
+	unsigned long fp = frame->fp;
+
+	if (frame_pointer_check(frame))
+		return -EINVAL;
 
 	/* restore the registers from the stack frame */
+#ifdef CONFIG_CC_IS_CLANG
+	frame->sp = frame->fp;
+	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
+	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 4));
+#else
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 12));
 	frame->sp = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 8));
 	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 4));
diff --git a/arch/arm/lib/call_with_stack.S b/arch/arm/lib/call_with_stack.S
index 0a268a6c513c..5030d4e8d126 100644
--- a/arch/arm/lib/call_with_stack.S
+++ b/arch/arm/lib/call_with_stack.S
@@ -46,4 +46,6 @@ UNWIND( .setfp	fpreg, sp	)
 	pop	{fpreg, pc}
 UNWIND( .fnend			)
 #endif
+	.globl call_with_stack_end
+call_with_stack_end:
 ENDPROC(call_with_stack)
-- 
2.17.1

[PATCH v2 2/5] ARM: stacktrace: Avoid duplicate saving of exception PC value

[Li Huafei]

Because an exception stack frame is not created in the exception entry,
save_trace() does special handling for the exception PC, but this is
only needed when CONFIG_FRAME_POINTER_UNWIND=y. When
CONFIG_ARM_UNWIND=y, unwind annotations have been added to the exception
entry and save_trace() will repeatedly save the exception PC:

    [0x7f000090] hrtimer_hander+0x8/0x10 [hrtimer]
    [0x8019ec50] __hrtimer_run_queues+0x18c/0x394
    [0x8019f760] hrtimer_run_queues+0xbc/0xd0
    [0x8019def0] update_process_times+0x34/0x80
    [0x801ad2a4] tick_periodic+0x48/0xd0
    [0x801ad3dc] tick_handle_periodic+0x1c/0x7c
    [0x8010f2e0] twd_handler+0x30/0x40
    [0x80177620] handle_percpu_devid_irq+0xa0/0x23c
    [0x801718d0] generic_handle_domain_irq+0x24/0x34
    [0x80502d28] gic_handle_irq+0x74/0x88
    [0x8085817c] generic_handle_arch_irq+0x58/0x78
    [0x80100ba8] __irq_svc+0x88/0xc8
    [0x80108114] arch_cpu_idle+0x38/0x3c
    [0x80108114] arch_cpu_idle+0x38/0x3c    <==== duplicate saved exception PC
    [0x80861bf8] default_idle_call+0x38/0x130
    [0x8015d5cc] do_idle+0x150/0x214
    [0x8015d978] cpu_startup_entry+0x18/0x1c
    [0x808589c0] rest_init+0xd8/0xdc
    [0x80c00a44] arch_post_acpi_subsys_init+0x0/0x8

We can move the special handling of the exception PC in save_trace() to
the unwind_frame() of the frame pointer unwinder.

Signed-off-by: Li Huafei <lihuafei1@huawei.com>
---
 arch/arm/include/asm/stacktrace.h |  6 +++++
 arch/arm/kernel/return_address.c  |  1 +
 arch/arm/kernel/stacktrace.c      | 38 +++++++++++++++++++------------
 3 files changed, 31 insertions(+), 14 deletions(-)

diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
index 3e78f921b8b2..25282ff645fb 100644
--- a/arch/arm/include/asm/stacktrace.h
+++ b/arch/arm/include/asm/stacktrace.h
@@ -21,6 +21,9 @@ struct stackframe {
 	struct llist_node *kr_cur;
 	struct task_struct *tsk;
 #endif
+#ifdef CONFIG_UNWINDER_FRAME_POINTER
+	bool ex_frame;
+#endif
 };
 
 static __always_inline
@@ -34,6 +37,9 @@ void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
 		frame->kr_cur = NULL;
 		frame->tsk = current;
 #endif
+#ifdef CONFIG_UNWINDER_FRAME_POINTER
+		frame->ex_frame = in_entry_text(frame->pc) ? true : false;
+#endif
 }
 
 extern int unwind_frame(struct stackframe *frame);
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index 8aac1e10b117..38f1ea9c724d 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -47,6 +47,7 @@ void *return_address(unsigned int level)
 	frame.kr_cur = NULL;
 	frame.tsk = current;
 #endif
+	frame.ex_frame = false;
 
 	walk_stackframe(&frame, save_return_addr, &data);
 
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index af87040b0353..3acf51ee46bb 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -82,6 +82,21 @@ int notrace unwind_frame(struct stackframe *frame)
 	if (frame_pointer_check(frame))
 		return -EINVAL;
 
+	/*
+	 * When we unwind through an exception stack, include the saved PC
+	 * value into the stack trace.
+	 */
+	if (frame->ex_frame) {
+		struct pt_regs *regs = (struct pt_regs *)frame->sp;
+
+		if ((unsigned long)&regs[1] > ALIGN(frame->sp, THREAD_SIZE))
+			return -EINVAL;
+
+		frame->pc = regs->ARM_pc;
+		frame->ex_frame = false;
+		return 0;
+	}
+
 	/* restore the registers from the stack frame */
 #ifdef CONFIG_CC_IS_CLANG
 	frame->sp = frame->fp;
@@ -98,6 +113,9 @@ int notrace unwind_frame(struct stackframe *frame)
 					(void *)frame->fp, &frame->kr_cur);
 #endif
 
+	if (in_entry_text(frame->pc))
+		frame->ex_frame = true;
+
 	return 0;
 }
 #endif
@@ -128,7 +146,6 @@ static int save_trace(struct stackframe *frame, void *d)
 {
 	struct stack_trace_data *data = d;
 	struct stack_trace *trace = data->trace;
-	struct pt_regs *regs;
 	unsigned long addr = frame->pc;
 
 	if (data->no_sched_functions && in_sched_functions(addr))
@@ -139,19 +156,6 @@ static int save_trace(struct stackframe *frame, void *d)
 	}
 
 	trace->entries[trace->nr_entries++] = addr;
-
-	if (trace->nr_entries >= trace->max_entries)
-		return 1;
-
-	if (!in_entry_text(frame->pc))
-		return 0;
-
-	regs = (struct pt_regs *)frame->sp;
-	if ((unsigned long)&regs[1] > ALIGN(frame->sp, THREAD_SIZE))
-		return 0;
-
-	trace->entries[trace->nr_entries++] = regs->ARM_pc;
-
 	return trace->nr_entries >= trace->max_entries;
 }
 
@@ -193,6 +197,9 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 	frame.kr_cur = NULL;
 	frame.tsk = tsk;
 #endif
+#ifdef CONFIG_UNWINDER_FRAME_POINTER
+	frame.ex_frame = false;
+#endif
 
 	walk_stackframe(&frame, save_trace, &data);
 }
@@ -214,6 +221,9 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 	frame.kr_cur = NULL;
 	frame.tsk = current;
 #endif
+#ifdef CONFIG_UNWINDER_FRAME_POINTER
+	frame.ex_frame = in_entry_text(frame.pc) ? true : false;
+#endif
 
 	walk_stackframe(&frame, save_trace, &data);
 }
-- 
2.17.1

[PATCH v2 3/5] ARM: stacktrace: Allow stack trace saving for non-current tasks

[Li Huafei]

The current ARM implementation of save_stack_trace_tsk() does not allow
saving stack trace for non-current tasks, which may limit the scenarios
in which stack_trace_save_tsk() can be used. Like other architectures,
or like ARM's unwind_backtrace(), we can leave it up to the caller to
ensure that the task that needs to be unwound is not running.

Signed-off-by: Li Huafei <lihuafei1@huawei.com>
---
 arch/arm/kernel/stacktrace.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 3acf51ee46bb..836420c00938 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -171,19 +171,11 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 	data.no_sched_functions = nosched;
 
 	if (tsk != current) {
-#ifdef CONFIG_SMP
-		/*
-		 * What guarantees do we have here that 'tsk' is not
-		 * running on another CPU?  For now, ignore it as we
-		 * can't guarantee we won't explode.
-		 */
-		return;
-#else
+		/* task blocked in __switch_to */
 		frame.fp = thread_saved_fp(tsk);
 		frame.sp = thread_saved_sp(tsk);
 		frame.lr = 0;		/* recovered from the stack */
 		frame.pc = thread_saved_pc(tsk);
-#endif
 	} else {
 		/* We don't want this function nor the caller */
 		data.skip += 2;
-- 
2.17.1

[PATCH v2 4/5] ARM: stacktrace: Make stack walk callback consistent with generic code

[Li Huafei]

As with the generic arch_stack_walk() code the ARM stack walk code takes
a callback that is called per stack frame. Currently the ARM code always
passes a struct stackframe to the callback and the generic code just
passes the pc, however none of the users ever reference anything in the
struct other than the pc value. The ARM code also uses a return type of
int while the generic code uses a return type of bool though in both
cases the return value is a boolean value and the sense is inverted
between the two.

In order to reduce code duplication when ARM is converted to use
arch_stack_walk() change the signature and return sense of the ARM
specific callback to match that of the generic code.

Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/include/asm/stacktrace.h |  2 +-
 arch/arm/kernel/perf_callchain.c  |  9 ++++-----
 arch/arm/kernel/return_address.c  |  8 ++++----
 arch/arm/kernel/stacktrace.c      | 13 ++++++-------
 4 files changed, 15 insertions(+), 17 deletions(-)

diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
index 25282ff645fb..ce85d3ad5d05 100644
--- a/arch/arm/include/asm/stacktrace.h
+++ b/arch/arm/include/asm/stacktrace.h
@@ -44,7 +44,7 @@ void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
 
 extern int unwind_frame(struct stackframe *frame);
 extern void walk_stackframe(struct stackframe *frame,
-			    int (*fn)(struct stackframe *, void *), void *data);
+			    bool (*fn)(void *, unsigned long), void *data);
 extern void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 		     unsigned long top);
 
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index bc6b246ab55e..7147edbe56c6 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -81,13 +81,12 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
  * whist unwinding the stackframe and is like a subroutine return so we use
  * the PC.
  */
-static int
-callchain_trace(struct stackframe *fr,
-		void *data)
+static bool
+callchain_trace(void *data, unsigned long pc)
 {
 	struct perf_callchain_entry_ctx *entry = data;
-	perf_callchain_store(entry, fr->pc);
-	return 0;
+	perf_callchain_store(entry, pc);
+	return true;
 }
 
 void
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index 38f1ea9c724d..ac15db66df4c 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -16,17 +16,17 @@ struct return_address_data {
 	void *addr;
 };
 
-static int save_return_addr(struct stackframe *frame, void *d)
+static bool save_return_addr(void *d, unsigned long pc)
 {
 	struct return_address_data *data = d;
 
 	if (!data->level) {
-		data->addr = (void *)frame->pc;
+		data->addr = (void *)pc;
 
-		return 1;
+		return false;
 	} else {
 		--data->level;
-		return 0;
+		return true;
 	}
 }
 
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 836420c00938..ec0ca3192775 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -121,12 +121,12 @@ int notrace unwind_frame(struct stackframe *frame)
 #endif
 
 void notrace walk_stackframe(struct stackframe *frame,
-		     int (*fn)(struct stackframe *, void *), void *data)
+		     bool (*fn)(void *, unsigned long), void *data)
 {
 	while (1) {
 		int ret;
 
-		if (fn(frame, data))
+		if (!fn(data, frame->pc))
 			break;
 		ret = unwind_frame(frame);
 		if (ret < 0)
@@ -142,21 +142,20 @@ struct stack_trace_data {
 	unsigned int skip;
 };
 
-static int save_trace(struct stackframe *frame, void *d)
+static bool save_trace(void *d, unsigned long addr)
 {
 	struct stack_trace_data *data = d;
 	struct stack_trace *trace = data->trace;
-	unsigned long addr = frame->pc;
 
 	if (data->no_sched_functions && in_sched_functions(addr))
-		return 0;
+		return true;
 	if (data->skip) {
 		data->skip--;
-		return 0;
+		return true;
 	}
 
 	trace->entries[trace->nr_entries++] = addr;
-	return trace->nr_entries >= trace->max_entries;
+	return trace->nr_entries < trace->max_entries;
 }
 
 /* This must be noinline to so that our skip calculation works correctly */
-- 
2.17.1

[PATCH v2 5/5] ARM: stacktrace: Convert stacktrace to generic ARCH_STACKWALK

[Li Huafei]

Historically architectures have had duplicated code in their stack trace
implementations for filtering what gets traced. In order to avoid this
duplication some generic code has been provided using a new interface
arch_stack_walk(), enabled by selecting ARCH_STACKWALK in Kconfig, which
factors all this out into the generic stack trace code. Convert ARM to
use this common infrastructure.

When initializing the stack frame of the current task, arm64 uses
__builtin_frame_address(1) to initialize the frame pointer, skipping
arch_stack_walk(), see the commit c607ab4f916d ("arm64: stacktrace:
don't trace arch_ stack_walk()"). Since __builtin_frame_address(1) does
not work on ARM, unwind_frame() is used to unwind the stack one layer
forward before calling walk_stackframe().

Signed-off-by: Li Huafei <lihuafei1@huawei.com>
---
 arch/arm/Kconfig             |   1 +
 arch/arm/kernel/stacktrace.c | 114 ++++++++++-------------------------
 2 files changed, 33 insertions(+), 82 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 7630ba9cb6cc..8da192853562 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -18,6 +18,7 @@ config ARM
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_STACKWALK
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if SWIOTLB || !MMU
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index ec0ca3192775..1b9c91e14d2e 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -136,98 +136,48 @@ void notrace walk_stackframe(struct stackframe *frame,
 EXPORT_SYMBOL(walk_stackframe);
 
 #ifdef CONFIG_STACKTRACE
-struct stack_trace_data {
-	struct stack_trace *trace;
-	unsigned int no_sched_functions;
-	unsigned int skip;
-};
-
-static bool save_trace(void *d, unsigned long addr)
-{
-	struct stack_trace_data *data = d;
-	struct stack_trace *trace = data->trace;
-
-	if (data->no_sched_functions && in_sched_functions(addr))
-		return true;
-	if (data->skip) {
-		data->skip--;
-		return true;
-	}
-
-	trace->entries[trace->nr_entries++] = addr;
-	return trace->nr_entries < trace->max_entries;
-}
-
-/* This must be noinline to so that our skip calculation works correctly */
-static noinline void __save_stack_trace(struct task_struct *tsk,
-	struct stack_trace *trace, unsigned int nosched)
+static void start_stack_trace(struct stackframe *frame, struct task_struct *task,
+			      unsigned long fp, unsigned long sp,
+			      unsigned long lr, unsigned long pc)
 {
-	struct stack_trace_data data;
-	struct stackframe frame;
-
-	data.trace = trace;
-	data.skip = trace->skip;
-	data.no_sched_functions = nosched;
-
-	if (tsk != current) {
-		/* task blocked in __switch_to */
-		frame.fp = thread_saved_fp(tsk);
-		frame.sp = thread_saved_sp(tsk);
-		frame.lr = 0;		/* recovered from the stack */
-		frame.pc = thread_saved_pc(tsk);
-	} else {
-		/* We don't want this function nor the caller */
-		data.skip += 2;
-		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.sp = current_stack_pointer;
-		frame.lr = (unsigned long)__builtin_return_address(0);
-here:
-		frame.pc = (unsigned long)&&here;
-	}
+	frame->fp = fp;
+	frame->sp = sp;
+	frame->lr = lr;
+	frame->pc = pc;
 #ifdef CONFIG_KRETPROBES
-	frame.kr_cur = NULL;
-	frame.tsk = tsk;
+	frame->kr_cur = NULL;
+	frame->tsk = task;
 #endif
 #ifdef CONFIG_UNWINDER_FRAME_POINTER
-	frame.ex_frame = false;
+	frame->ex_frame = in_entry_text(frame->pc) ? true : false;
 #endif
-
-	walk_stackframe(&frame, save_trace, &data);
 }
 
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs)
 {
-	struct stack_trace_data data;
 	struct stackframe frame;
 
-	data.trace = trace;
-	data.skip = trace->skip;
-	data.no_sched_functions = 0;
-
-	frame.fp = regs->ARM_fp;
-	frame.sp = regs->ARM_sp;
-	frame.lr = regs->ARM_lr;
-	frame.pc = regs->ARM_pc;
-#ifdef CONFIG_KRETPROBES
-	frame.kr_cur = NULL;
-	frame.tsk = current;
-#endif
-#ifdef CONFIG_UNWINDER_FRAME_POINTER
-	frame.ex_frame = in_entry_text(frame.pc) ? true : false;
-#endif
-
-	walk_stackframe(&frame, save_trace, &data);
-}
-
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
-	__save_stack_trace(tsk, trace, 1);
-}
-EXPORT_SYMBOL(save_stack_trace_tsk);
+	if (regs) {
+		start_stack_trace(&frame, NULL, regs->ARM_fp, regs->ARM_sp,
+				  regs->ARM_lr, regs->ARM_pc);
+	} else if (task != current) {
+		/* task blocked in __switch_to */
+		start_stack_trace(&frame, task, thread_saved_fp(task),
+				  thread_saved_sp(task), 0,
+				  thread_saved_pc(task));
+	} else {
+here:
+		start_stack_trace(&frame, task,
+				  (unsigned long)__builtin_frame_address(0),
+				  current_stack_pointer,
+				  (unsigned long)__builtin_return_address(0),
+				  (unsigned long)&&here);
+		/* skip this function */
+		if (unwind_frame(&frame))
+			return;
+	}
 
-void save_stack_trace(struct stack_trace *trace)
-{
-	__save_stack_trace(current, trace, 0);
+	walk_stackframe(&frame, consume_entry, cookie);
 }
-EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
-- 
2.17.1

Re: [PATCH v2 0/5] ARM: Convert to ARCH_STACKWALK

[Linus Walleij]

On Wed, Jul 13, 2022 at 1:02 PM Li Huafei <lihuafei1@huawei.com> wrote:

> This series mainly updates the ARM stack trace code to use the newer and
> simpler arch_stack_walk() interface. Two issues were fixed before that
> (see patch 1 and 2), as well as allowing stack_trace_save_tsk() to
> trace non-current tasks (see patch 3).
>
> v2:
>  - As suggested by Mark, the commit logs for patch 4 and 5 were
>    refined for easy review.

I see I reviewed v1 when v2 was already out but think the
comments still stand.

I think you can already add patches 1 & 2 to Russells patch tracker,
they are straight-forward fixes.

Patches 3-5 may need some elaboration but I trust that you have
done some serious testing since you found the snags in
patches 1 & 2.

Yours,
Linus Walleij