riscv: stacktrace: fixed walk_stackframe()

If the load access fault occures in a leaf function (with CONFIG_FRAME_POINTER=y), when wrong stack trace will be displayed:

[<ffffffff804853c2>] regmap_mmio_read32le+0xe/0x1c
---[ end trace 0000000000000000 ]---

Registers dump:

    ra     0xffffffff80485758 <regmap_mmio_read+36>
    sp     0xffffffc80200b9a0
    fp     0xffffffc80200b9b0
    pc     0xffffffff804853ba <regmap_mmio_read32le+6>

Stack dump:

    0xffffffc80200b9a0:  0xffffffc80200b9e0  0xffffffc80200b9e0
    0xffffffc80200b9b0:  0xffffffff8116d7e8  0x0000000000000100
    0xffffffc80200b9c0:  0xffffffd8055b9400  0xffffffd8055b9400
    0xffffffc80200b9d0:  0xffffffc80200b9f0  0xffffffff8047c526
    0xffffffc80200b9e0:  0xffffffc80200ba30  0xffffffff8047fe9a

The assembler dump of the function preambula:

    add     sp,sp,-16
    sd      s0,8(sp)
    add     s0,sp,16

In the fist stack frame, where ra is not stored on the stack we can observe:

        0(sp)                  8(sp)
        .---------------------------------------------.
    sp->|       frame->fp      | frame->ra (saved fp) |
        |---------------------------------------------|
    fp->|         ....         |         ....         |
        |---------------------------------------------|
        |                      |                      |

and in the code check is performed:

	if (regs && (regs->epc == pc) && (frame->fp & 0x7))

I see no reason to check frame->fp value at all, because it is can be uninitialized value on the stack. A better way is to check frame->ra to be an address on the stack. After the stacktrace shows as expect:

[<ffffffff804853c2>] regmap_mmio_read32le+0xe/0x1c
[<ffffffff80485758>] regmap_mmio_read+0x24/0x52
[<ffffffff8047c526>] _regmap_bus_reg_read+0x1a/0x22
[<ffffffff8047fe9a>] _regmap_read+0x5c/0xea
[<ffffffff80480376>] _regmap_update_bits+0x76/0xc0
...
---[ end trace 0000000000000000 ]---

---
As pointed by Samuel Holland it is incorrect to remove check of the stackframe entirely.

Changes since v1 [1]:
- Instead of just dropping frame->fp check, replace it with validation of frame->ra, which should be a stack address.
- Move frame pointer validation into the separate function.

[1] https://lore.kernel.org/linux-riscv/[email protected]/

 arch/riscv/kernel/stacktrace.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

index 64a9c093aef9..80f6559b6654 100644
@@ -18,6 +18,16 @@
 
 extern asmlinkage void ret_from_exception(void);
 
+static inline int fp_is_valid(unsigned long fp, unsigned long sp)
+{
+	unsigned long low, high;
+
+	low = sp + sizeof(struct stackframe);
+	high = ALIGN(sp, THREAD_SIZE);
+
+	return !(fp < low || fp > high || fp & 0x07);
+}
+
 void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 			     bool (*fn)(void *, unsigned long), void *arg)
 {

@@ -41,21 +51,19 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 	}
 
 	for (;;) {
-		unsigned long low, high;
 		struct stackframe *frame;
 
 		if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc))))
 			break;
 
-		/* Validate frame pointer */
-		low = sp + sizeof(struct stackframe);
-		high = ALIGN(sp, THREAD_SIZE);
-		if (unlikely(fp < low || fp > high || fp & 0x7))
+		if (unlikely(!fp_is_valid(fp, sp)))
 			break;
+
 		/* Unwind stack frame */
 		frame = (struct stackframe *)fp - 1;
 		sp = fp;
-		if (regs && (regs->epc == pc) && (frame->fp & 0x7)) {
+		if (regs && (regs->epc == pc) && fp_is_valid(frame->ra, sp))
+			/* We hit function where ra is not saved on the stack */
 			fp = frame->ra;
 			pc = regs->ra;
 		} else {

2.43.0


_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv