On Wed, Sep 15, 2021 at 09:51:57AM +0800, 王贇 wrote:
> > +
> > + if (in_exception_stack_guard((void *)address))
> > + pr_emerg("PANIC: exception stack guard: 0x%lx\n", address);
> > #endif
> >
> > pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
> >
>
> The panic triggered as below after the stack size recovered, I found this info
> could be helpful, maybe we should keep it?
Could you please test this?
---
Subject: x86/dumpstack/64: Add guard pages to stack_info
From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Date: Wed Sep 15 17:12:59 CEST 2021
Explicitly add the exception stack guard pages to stack_info and
report on them from #DF.
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
arch/x86/include/asm/cpu_entry_area.h | 3 +++
arch/x86/include/asm/stacktrace.h | 3 ++-
arch/x86/kernel/dumpstack_64.c | 17 ++++++++++++++++-
arch/x86/kernel/traps.c | 17 ++++++++++++++++-
4 files changed, 37 insertions(+), 3 deletions(-)
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -61,6 +61,9 @@ enum exception_stack_ordering {
#define CEA_ESTACK_OFFS(st) \
offsetof(struct cea_exception_stacks, st## _stack)
+#define CEA_EGUARD_OFFS(st) \
+ offsetof(struct cea_exception_stacks, st## _stack_guard)
+
#define CEA_ESTACK_PAGES \
(sizeof(struct cea_exception_stacks) / PAGE_SIZE)
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -14,13 +14,14 @@
#include <asm/switch_to.h>
enum stack_type {
- STACK_TYPE_UNKNOWN,
+ STACK_TYPE_UNKNOWN = 0,
STACK_TYPE_TASK,
STACK_TYPE_IRQ,
STACK_TYPE_SOFTIRQ,
STACK_TYPE_ENTRY,
STACK_TYPE_EXCEPTION,
STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
+ STACK_TYPE_GUARD = 0x80,
};
struct stack_info {
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -32,9 +32,15 @@ const char *stack_type_name(enum stack_t
{
BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
+ if (type == STACK_TYPE_TASK)
+ return "TASK";
+
if (type == STACK_TYPE_IRQ)
return "IRQ";
+ if (type == STACK_TYPE_SOFTIRQ)
+ return "SOFTIRQ";
+
if (type == STACK_TYPE_ENTRY) {
/*
* On 64-bit, we have a generic entry stack that we
@@ -63,6 +69,11 @@ struct estack_pages {
};
#define EPAGERANGE(st) \
+ [PFN_DOWN(CEA_EGUARD_OFFS(st))] = { \
+ .offs = CEA_EGUARD_OFFS(st), \
+ .size = PAGE_SIZE, \
+ .type = STACK_TYPE_GUARD + \
+ STACK_TYPE_EXCEPTION + ESTACK_ ##st, }, \
[PFN_DOWN(CEA_ESTACK_OFFS(st)) ... \
PFN_DOWN(CEA_ESTACK_OFFS(st) + CEA_ESTACK_SIZE(st) - 1)] = { \
.offs = CEA_ESTACK_OFFS(st), \
@@ -111,10 +122,11 @@ static __always_inline bool in_exception
k = (stk - begin) >> PAGE_SHIFT;
/* Lookup the page descriptor */
ep = &estack_pages[k];
- /* Guard page? */
+ /* unknown entry */
if (!ep->size)
return false;
+
begin += (unsigned long)ep->offs;
end = begin + (unsigned long)ep->size;
regs = (struct pt_regs *)end - 1;
@@ -193,6 +205,9 @@ int get_stack_info(unsigned long *stack,
if (!get_stack_info_noinstr(stack, task, info))
goto unknown;
+ if (info->type & STACK_TYPE_GUARD)
+ goto unknown;
+
/*
* Make sure we don't iterate through any given stack more than once.
* If it comes up a second time then there's something wrong going on:
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -461,6 +461,19 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
}
#endif
+#ifdef CONFIG_X86_64
+ {
+ struct stack_info info;
+
+ if (get_stack_info_noinstr((void *)address, current, &info) &&
+ info.type & STACK_TYPE_GUARD) {
+ const char *name = stack_type_name(info.type & ~STACK_TYPE_GUARD);
+ pr_emerg("BUG: %s stack guard hit at %p (stack is %p..%p)\n",
+ name, (void *)address, info.begin, info.end);
+ }
+ }
+#endif
+
pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
die("double fault", regs, error_code);
panic("Machine halted.");
@@ -708,7 +721,9 @@ asmlinkage __visible noinstr struct pt_r
sp = regs->sp;
stack = (unsigned long *)sp;
- if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY ||
+ if (!get_stack_info_noinstr(stack, current, &info) ||
+ info.type & STACK_TYPE_GUARD ||
+ info.type == STACK_TYPE_ENTRY ||
info.type >= STACK_TYPE_EXCEPTION_LAST)
sp = __this_cpu_ist_top_va(VC2);
