[PATCH v3 7/7] arm64: ftrace: add arch-specific stack tracer

From: AKASHI Takahiro
Date: Thu Oct 08 2015 - 06:04:08 EST

Stack tracer on arm64, check_stack(), is uniqeue in the following
points:
* analyze a function prologue of a traced function to estimate a more
accurate stack pointer value, replacing naive '<child's fp> + 0x10.'
* use walk_stackframe(), instead of slurping stack contents as orignal
check_stack() does, to identify a stack frame and a stack index (height)
for every callsite.

Regarding a function prologue analyzer, there is no guarantee that we can
handle all the possible patterns of function prologue as gcc does not use
any fixed templates to generate them. 'Instruction scheduling' is another
issue here.
Nevertheless, the current version will surely cover almost all the cases
in the kernel image and give us useful information on stack pointers.

So this patch utilizes a function prologue only for stack tracer, and
does not affect the behaviors of existing stacktrace functions.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@xxxxxxxxxx>
---
arch/arm64/include/asm/stacktrace.h | 1 +
arch/arm64/kernel/ftrace.c | 66 +++++++++++++
arch/arm64/kernel/stacktrace.c | 186 ++++++++++++++++++++++++++++++++++-
3 files changed, 250 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 7318f6d..bfaa22a 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -25,5 +25,6 @@ struct stackframe {
extern int unwind_frame(struct stackframe *frame);
extern void walk_stackframe(struct stackframe *frame,
int (*fn)(struct stackframe *, void *), void *data);
+extern void save_stack_trace_sp(struct stack_trace *trace, unsigned long *sp);

#endif /* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 314f82d..fa37875 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -9,6 +9,7 @@
* published by the Free Software Foundation.
*/

+#include <linux/bug.h>
#include <linux/ftrace.h>
#include <linux/swab.h>
#include <linux/uaccess.h>
@@ -16,6 +17,7 @@
#include <asm/cacheflush.h>
#include <asm/ftrace.h>
#include <asm/insn.h>
+#include <asm/stacktrace.h>

#ifdef CONFIG_DYNAMIC_FTRACE
/*
@@ -173,3 +175,67 @@ int ftrace_disable_ftrace_graph_caller(void)
}
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_STACK_TRACER
+static unsigned long stack_dump_sp[STACK_TRACE_ENTRIES];
+static unsigned long raw_max_stack_size;
+
+void check_stack(unsigned long ip, unsigned long *stack)
+{
+ unsigned long this_size, flags;
+ unsigned long top;
+ int i, j;
+
+ this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
+ this_size = THREAD_SIZE - this_size;
+
+ if (this_size <= raw_max_stack_size)
+ return;
+
+ /* we do not handle an interrupt stack yet */
+ if (!object_is_on_stack(stack))
+ return;
+
+ local_irq_save(flags);
+ arch_spin_lock(&max_stack_lock);
+
+ /* check again */
+ if (this_size <= raw_max_stack_size)
+ goto out;
+
+ /* find out stack frames */
+ max_stack_trace.nr_entries = 0;
+ max_stack_trace.skip = 0;
+ save_stack_trace_sp(&max_stack_trace, stack_dump_sp);
+ max_stack_trace.nr_entries--; /* for the last entry ('-1') */
+
+ /* calculate a stack index for each function */
+ top = ((unsigned long)stack & ~(THREAD_SIZE-1)) + THREAD_SIZE;
+ for (i = 0; i < max_stack_trace.nr_entries; i++)
+ stack_dump_index[i] = top - stack_dump_sp[i];
+ raw_max_stack_size = this_size;
+
+ /* Skip over the overhead of the stack tracer itself */
+ for (i = 0; i < max_stack_trace.nr_entries; i++) {
+ if ((max_stack_trace.entries[i] + FTRACE_STACK_FRAME_OFFSET)
+ == ip)
+ break;
+ }
+
+ max_stack_trace.nr_entries -= i;
+ for (j = 0; j < max_stack_trace.nr_entries; j++) {
+ stack_dump_index[j] = stack_dump_index[j + i];
+ max_stack_trace.entries[j] = max_stack_trace.entries[j + i];
+ }
+ max_stack_size = stack_dump_index[0];
+
+ if (task_stack_end_corrupted(current)) {
+ WARN(1, "task stack is corrupted.\n");
+ print_max_stack();
+ }
+
+ out:
+ arch_spin_unlock(&max_stack_lock);
+ local_irq_restore(flags);
+}
+#endif /* CONFIG_STACK_TRACER */
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 1555a8b..1b293fe 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -17,12 +17,151 @@
*/
#include <linux/kernel.h>
#include <linux/export.h>
+#include <linux/ftrace.h>
#include <linux/sched.h>
#include <linux/stacktrace.h>

#include <asm/insn.h>
#include <asm/stacktrace.h>

+#ifdef CONFIG_STACK_TRACER
+/*
+ * This function parses a function prologue of a traced function and
+ * determines its stack size.
+ * A return value indicates a location of @pc in a function prologue.
+ * @return value:
+ * <case 1> <case 1'>
+ * 1:
+ * sub sp, sp, #XX sub sp, sp, #XX
+ * 2:
+ * stp x29, x30, [sp, #YY] stp x29, x30, [sp, #--ZZ]!
+ * 3:
+ * add x29, sp, #YY mov x29, sp
+ * 0:
+ *
+ * <case 2>
+ * 1:
+ * stp x29, x30, [sp, #-XX]!
+ * 3:
+ * mov x29, sp
+ * 0:
+ *
+ * @size: sp offset from calller's sp (XX or XX + ZZ)
+ * @size2: fp offset from new sp (YY or 0)
+ */
+static int analyze_function_prologue(unsigned long pc,
+ unsigned long *size, unsigned long *size2)
+{
+ unsigned long offset;
+ u32 *addr, insn;
+ int pos = -1;
+ enum aarch64_insn_register src, dst, reg1, reg2, base;
+ int imm;
+ enum aarch64_insn_variant variant;
+ enum aarch64_insn_adsb_type adsb_type;
+ enum aarch64_insn_ldst_type ldst_type;
+
+ *size = *size2 = 0;
+
+ if (!pc)
+ goto out;
+
+ if (unlikely(!kallsyms_lookup_size_offset(pc, NULL, &offset)))
+ goto out;
+
+ addr = (u32 *)(pc - offset);
+#ifdef CONFIG_DYNAMIC_FTRACE
+ if (addr == (u32 *)ftrace_call)
+ addr = (u32 *)ftrace_caller;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ else if (addr == (u32 *)ftrace_graph_caller)
+#ifdef CONFIG_DYNAMIC_FTRACE
+ addr = (u32 *)ftrace_caller;
+#else
+ addr = (u32 *)_mcount;
+#endif
+#endif
+#endif
+
+ insn = *addr;
+ pos = 1;
+
+ /* analyze a function prologue */
+ while ((unsigned long)addr < pc) {
+ if (aarch64_insn_is_branch_imm(insn) ||
+ aarch64_insn_is_br(insn) ||
+ aarch64_insn_is_blr(insn) ||
+ aarch64_insn_is_ret(insn) ||
+ aarch64_insn_is_eret(insn))
+ /* exiting a basic block */
+ goto out;
+
+ if (aarch64_insn_decode_add_sub_imm(insn, &dst, &src,
+ &imm, &variant, &adsb_type)) {
+ if ((adsb_type == AARCH64_INSN_ADSB_SUB) &&
+ (dst == AARCH64_INSN_REG_SP) &&
+ (src == AARCH64_INSN_REG_SP)) {
+ /*
+ * Starting the following sequence:
+ * sub sp, sp, #xx
+ * stp x29, x30, [sp, #yy]
+ * add x29, sp, #yy
+ */
+ WARN_ON(pos != 1);
+ pos = 2;
+ *size += imm;
+ } else if ((adsb_type == AARCH64_INSN_ADSB_ADD) &&
+ (dst == AARCH64_INSN_REG_29) &&
+ (src == AARCH64_INSN_REG_SP)) {
+ /*
+ * add x29, sp, #yy
+ * or
+ * mov x29, sp
+ */
+ WARN_ON(pos != 3);
+ pos = 0;
+ *size2 = imm;
+
+ break;
+ }
+ } else if (aarch64_insn_decode_load_store_pair(insn,
+ &reg1, &reg2, &base, &imm,
+ &variant, &ldst_type)) {
+ if ((ldst_type ==
+ AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX) &&
+ (reg1 == AARCH64_INSN_REG_29) &&
+ (reg2 == AARCH64_INSN_REG_30) &&
+ (base == AARCH64_INSN_REG_SP)) {
+ /*
+ * Starting the following sequence:
+ * stp x29, x30, [sp, #-xx]!
+ * mov x29, sp
+ */
+ WARN_ON(!((pos == 1) || (pos == 2)));
+ pos = 3;
+ *size += -imm;
+ } else if ((ldst_type ==
+ AARCH64_INSN_LDST_STORE_PAIR) &&
+ (reg1 == AARCH64_INSN_REG_29) &&
+ (reg2 == AARCH64_INSN_REG_30) &&
+ (base == AARCH64_INSN_REG_SP)) {
+ /*
+ * stp x29, x30, [sp, #yy]
+ */
+ WARN_ON(pos != 2);
+ pos = 3;
+ }
+ }
+
+ addr++;
+ insn = *addr;
+ }
+
+out:
+ return pos;
+}
+#endif
+
/*
* AArch64 PCS assigns the frame pointer to x29.
*
@@ -81,6 +220,9 @@ struct stack_trace_data {
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned int ret_stack_index;
#endif
+#ifdef CONFIG_STACK_TRACER
+ unsigned long *sp;
+#endif
};

static int save_trace(struct stackframe *frame, void *d)
@@ -110,12 +252,33 @@ static int save_trace(struct stackframe *frame, void *d)
return 0;
}

+#ifdef CONFIG_STACK_TRACER
+ if (data->sp) {
+ if (trace->nr_entries) {
+ unsigned long child_pc, sp_off, fp_off;
+ int pos;
+
+ child_pc = trace->entries[trace->nr_entries - 1];
+ pos = analyze_function_prologue(child_pc,
+ &sp_off, &fp_off);
+ /*
+ * frame->sp - 0x10 is actually a child's fp.
+ * See above.
+ */
+ data->sp[trace->nr_entries] = (pos < 0 ? frame->sp :
+ (frame->sp - 0x10) + sp_off - fp_off);
+ } else {
+ data->sp[0] = frame->sp;
+ }
+ }
+#endif
trace->entries[trace->nr_entries++] = addr;

return trace->nr_entries >= trace->max_entries;
}

-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+static void __save_stack_trace_tsk(struct task_struct *tsk,
+ struct stack_trace *trace, unsigned long *stack_dump_sp)
{
struct stack_trace_data data;
struct stackframe frame;
@@ -125,6 +288,9 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
data.ret_stack_index = current->curr_ret_stack;
#endif
+#ifdef CONFIG_STACK_TRACER
+ data.sp = stack_dump_sp;
+#endif

if (tsk != current) {
data.no_sched_functions = 1;
@@ -135,7 +301,8 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
data.no_sched_functions = 0;
frame.fp = (unsigned long)__builtin_frame_address(0);
frame.sp = current_stack_pointer;
- frame.pc = (unsigned long)save_stack_trace_tsk;
+ asm("1:");
+ asm("ldr %0, =1b" : "=r" (frame.pc));
}

walk_stackframe(&frame, save_trace, &data);
@@ -143,9 +310,22 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}

+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+ __save_stack_trace_tsk(tsk, trace, NULL);
+}
+
void save_stack_trace(struct stack_trace *trace)
{
- save_stack_trace_tsk(current, trace);
+ __save_stack_trace_tsk(current, trace, NULL);
}
EXPORT_SYMBOL_GPL(save_stack_trace);
+
+#ifdef CONFIG_STACK_TRACER
+void save_stack_trace_sp(struct stack_trace *trace,
+ unsigned long *stack_dump_sp)
+{
+ __save_stack_trace_tsk(current, trace, stack_dump_sp);
+}
+#endif /* CONFIG_STACK_TRACER */
#endif
--
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/