riscv: stacktrace: Make walk_stackframe cross pt_regs frame

The current walk_stackframe with FRAME_POINTER would stop unwinding at
ret_from_exception:
  BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1518
  in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 1, name: init
  CPU: 0 PID: 1 Comm: init Not tainted 5.10.113-00021-g15c15974895c-dirty #192
  Call Trace:
  [<ffffffe0002038c8>] walk_stackframe+0x0/0xee
  [<ffffffe000aecf48>] show_stack+0x32/0x4a
  [<ffffffe000af1618>] dump_stack_lvl+0x72/0x8e
  [<ffffffe000af1648>] dump_stack+0x14/0x1c
  [<ffffffe000239ad2>] ___might_sleep+0x12e/0x138
  [<ffffffe000239aec>] __might_sleep+0x10/0x18
  [<ffffffe000afe3fe>] down_read+0x22/0xa4
  [<ffffffe000207588>] do_page_fault+0xb0/0x2fe
  [<ffffffe000201b80>] ret_from_exception+0x0/0xc

The optimization would help walk_stackframe cross the pt_regs frame and
get more backtrace of debug info:
  BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1518
  in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 1, name: init
  CPU: 0 PID: 1 Comm: init Not tainted 5.10.113-00021-g15c15974895c-dirty #192
  Call Trace:
  [<ffffffe0002038c8>] walk_stackframe+0x0/0xee
  [<ffffffe000aecf48>] show_stack+0x32/0x4a
  [<ffffffe000af1618>] dump_stack_lvl+0x72/0x8e
  [<ffffffe000af1648>] dump_stack+0x14/0x1c
  [<ffffffe000239ad2>] ___might_sleep+0x12e/0x138
  [<ffffffe000239aec>] __might_sleep+0x10/0x18
  [<ffffffe000afe3fe>] down_read+0x22/0xa4
  [<ffffffe000207588>] do_page_fault+0xb0/0x2fe
  [<ffffffe000201b80>] ret_from_exception+0x0/0xc
  [<ffffffe000613c06>] riscv_intc_irq+0x1a/0x72
  [<ffffffe000201b80>] ret_from_exception+0x0/0xc
  [<ffffffe00033f44a>] vma_link+0x54/0x160
  [<ffffffe000341d7a>] mmap_region+0x2cc/0x4d0
  [<ffffffe000342256>] do_mmap+0x2d8/0x3ac
  [<ffffffe000326318>] vm_mmap_pgoff+0x70/0xb8
  [<ffffffe00032638a>] vm_mmap+0x2a/0x36
  [<ffffffe0003cfdde>] elf_map+0x72/0x84
  [<ffffffe0003d05f8>] load_elf_binary+0x69a/0xec8
  [<ffffffe000376240>] bprm_execve+0x246/0x53a
  [<ffffffe00037786c>] kernel_execve+0xe8/0x124
  [<ffffffe000aecdf2>] run_init_process+0xfa/0x10c
  [<ffffffe000aece16>] try_to_run_init_process+0x12/0x3c
  [<ffffffe000afa920>] kernel_init+0xb4/0xf8
  [<ffffffe000201b80>] ret_from_exception+0x0/0xc

Here is the error injection test code for the above output:
 drivers/irqchip/irq-riscv-intc.c:
 static asmlinkage void riscv_intc_irq(struct pt_regs *regs)
 {
        unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG;
+       u32 tmp; __get_user(tmp, (u32 *)0);

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20221109064937.3643993-3-guoren@kernel.org
[Palmer: use SYM_CODE_*]
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index b9eda3fcbd6d74e4e2b3aa6e10cc41f5d6359d60..da44fe2d0d821126d4ded9ea21fc97210ad741cf 100644 (file)
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -248,7 +248,7 @@ ret_from_syscall_rejected:
        andi t0, t0, _TIF_SYSCALL_WORK
        bnez t0, handle_syscall_trace_exit
 
-ret_from_exception:
+SYM_CODE_START_NOALIGN(ret_from_exception)
        REG_L s0, PT_STATUS(sp)
        csrc CSR_STATUS, SR_IE
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -262,6 +262,7 @@ ret_from_exception:
        andi s0, s0, SR_SPP
 #endif
        bnez s0, resume_kernel
+SYM_CODE_END(ret_from_exception)
 
 resume_userspace:
        /* Interrupts must be disabled here so flags are checked atomically */

diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index bcfe9eb55f80fbfa9b09f093a9339617d882e8aa..75c8dd64fc48e02ba56942d2d1a029ff88c061a4 100644 (file)
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -16,6 +16,8 @@
 
 #ifdef CONFIG_FRAME_POINTER
 
+extern asmlinkage void ret_from_exception(void);
+
 void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
                             bool (*fn)(void *, unsigned long), void *arg)
 {
@@ -59,6 +61,13 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
                        fp = frame->fp;
                        pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
                                                   &frame->ra);
+                       if (pc == (unsigned long)ret_from_exception) {
+                               if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc)))
+                                       break;
+
+                               pc = ((struct pt_regs *)sp)->epc;
+                               fp = ((struct pt_regs *)sp)->s0;
+                       }
                }
 
        }