summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2021-09-15 18:12:59 +0300
committerPeter Zijlstra <peterz@infradead.org>2021-09-21 14:57:43 +0300
commit44b979fa302cab91bdd2cc982823e5c13202cd4e (patch)
tree95cda92efb3adb9b44d233dbd979e3ecfd9fa66e
parentb968e84b509da593c50dc3db679e1d33de701f78 (diff)
downloadlinux-44b979fa302cab91bdd2cc982823e5c13202cd4e.tar.xz
x86/mm/64: Improve stack overflow warnings
Current code has an explicit check for hitting the task stack guard; but overflowing any of the other stacks will get you a non-descript general #DF warning. Improve matters by using get_stack_info_noinstr() to detetrmine if and which stack guard page got hit, enabling a better stack warning. In specific, Michael Wang reported what turned out to be an NMI exception stack overflow, which is now clearly reported as such: [] BUG: NMI stack guard page was hit at 0000000085fd977b (stack is 000000003a55b09e..00000000d8cce1a5) Reported-by: Michael Wang <yun.wang@linux.alibaba.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Michael Wang <yun.wang@linux.alibaba.com> Link: https://lkml.kernel.org/r/YUTE/NuqnaWbST8n@hirez.programming.kicks-ass.net
-rw-r--r--arch/x86/include/asm/irq_stack.h37
-rw-r--r--arch/x86/include/asm/stacktrace.h10
-rw-r--r--arch/x86/include/asm/traps.h6
-rw-r--r--arch/x86/kernel/dumpstack_64.c6
-rw-r--r--arch/x86/kernel/traps.c25
-rw-r--r--arch/x86/mm/fault.c20
6 files changed, 67 insertions, 37 deletions
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 562854c60808..8d55bd11848c 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -77,11 +77,11 @@
* Function calls can clobber anything except the callee-saved
* registers. Tell the compiler.
*/
-#define call_on_irqstack(func, asm_call, argconstr...) \
+#define call_on_stack(stack, func, asm_call, argconstr...) \
{ \
register void *tos asm("r11"); \
\
- tos = ((void *)__this_cpu_read(hardirq_stack_ptr)); \
+ tos = ((void *)(stack)); \
\
asm_inline volatile( \
"movq %%rsp, (%[tos]) \n" \
@@ -98,6 +98,25 @@
); \
}
+#define ASM_CALL_ARG0 \
+ "call %P[__func] \n"
+
+#define ASM_CALL_ARG1 \
+ "movq %[arg1], %%rdi \n" \
+ ASM_CALL_ARG0
+
+#define ASM_CALL_ARG2 \
+ "movq %[arg2], %%rsi \n" \
+ ASM_CALL_ARG1
+
+#define ASM_CALL_ARG3 \
+ "movq %[arg3], %%rdx \n" \
+ ASM_CALL_ARG2
+
+#define call_on_irqstack(func, asm_call, argconstr...) \
+ call_on_stack(__this_cpu_read(hardirq_stack_ptr), \
+ func, asm_call, argconstr)
+
/* Macros to assert type correctness for run_*_on_irqstack macros */
#define assert_function_type(func, proto) \
static_assert(__builtin_types_compatible_p(typeof(&func), proto))
@@ -147,8 +166,7 @@
*/
#define ASM_CALL_SYSVEC \
"call irq_enter_rcu \n" \
- "movq %[arg1], %%rdi \n" \
- "call %P[__func] \n" \
+ ASM_CALL_ARG1 \
"call irq_exit_rcu \n"
#define SYSVEC_CONSTRAINTS , [arg1] "r" (regs)
@@ -168,12 +186,10 @@
*/
#define ASM_CALL_IRQ \
"call irq_enter_rcu \n" \
- "movq %[arg1], %%rdi \n" \
- "movl %[arg2], %%esi \n" \
- "call %P[__func] \n" \
+ ASM_CALL_ARG2 \
"call irq_exit_rcu \n"
-#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" (vector)
+#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" ((unsigned long)vector)
#define run_irq_on_irqstack_cond(func, regs, vector) \
{ \
@@ -185,9 +201,6 @@
IRQ_CONSTRAINTS, regs, vector); \
}
-#define ASM_CALL_SOFTIRQ \
- "call %P[__func] \n"
-
/*
* Macro to invoke __do_softirq on the irq stack. This is only called from
* task context when bottom halves are about to be reenabled and soft
@@ -197,7 +210,7 @@
#define do_softirq_own_stack() \
{ \
__this_cpu_write(hardirq_stack_inuse, true); \
- call_on_irqstack(__do_softirq, ASM_CALL_SOFTIRQ); \
+ call_on_irqstack(__do_softirq, ASM_CALL_ARG0); \
__this_cpu_write(hardirq_stack_inuse, false); \
}
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f248eb2ac2d4..3881b5333eb8 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -38,6 +38,16 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task,
struct stack_info *info);
+static __always_inline
+bool get_stack_guard_info(unsigned long *stack, struct stack_info *info)
+{
+ /* make sure it's not in the stack proper */
+ if (get_stack_info_noinstr(stack, current, info))
+ return false;
+ /* but if it is in the page below it, we hit a guard */
+ return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info);
+}
+
const char *stack_type_name(enum stack_type type);
static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 7f7200021bd1..6221be7cafc3 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -40,9 +40,9 @@ void math_emulate(struct math_emu_info *);
bool fault_in_kernel_space(unsigned long address);
#ifdef CONFIG_VMAP_STACK
-void __noreturn handle_stack_overflow(const char *message,
- struct pt_regs *regs,
- unsigned long fault_address);
+void __noreturn handle_stack_overflow(struct pt_regs *regs,
+ unsigned long fault_address,
+ struct stack_info *info);
#endif
#endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5601b95944fa..6c5defd6569a 100644
--- 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_type type)
{
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
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index f3f3034b06f3..cc6de3a01293 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -313,17 +313,19 @@ out:
}
#ifdef CONFIG_VMAP_STACK
-__visible void __noreturn handle_stack_overflow(const char *message,
- struct pt_regs *regs,
- unsigned long fault_address)
+__visible void __noreturn handle_stack_overflow(struct pt_regs *regs,
+ unsigned long fault_address,
+ struct stack_info *info)
{
- printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n",
- (void *)fault_address, current->stack,
- (char *)current->stack + THREAD_SIZE - 1);
- die(message, regs, 0);
+ const char *name = stack_type_name(info->type);
+
+ printk(KERN_EMERG "BUG: %s stack guard page was hit at %p (stack is %p..%p)\n",
+ name, (void *)fault_address, info->begin, info->end);
+
+ die("stack guard page", regs, 0);
/* Be absolutely certain we don't return. */
- panic("%s", message);
+ panic("%s stack guard hit", name);
}
#endif
@@ -353,6 +355,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
#ifdef CONFIG_VMAP_STACK
unsigned long address = read_cr2();
+ struct stack_info info;
#endif
#ifdef CONFIG_X86_ESPFIX64
@@ -455,10 +458,8 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
* stack even if the actual trigger for the double fault was
* something else.
*/
- if ((unsigned long)task_stack_page(tsk) - 1 - address < PAGE_SIZE) {
- handle_stack_overflow("kernel stack overflow (double-fault)",
- regs, address);
- }
+ if (get_stack_guard_info((void *)address, &info))
+ handle_stack_overflow(regs, address, &info);
#endif
pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b2eefdefc108..edb5152f0866 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -32,6 +32,7 @@
#include <asm/pgtable_areas.h> /* VMALLOC_START, ... */
#include <asm/kvm_para.h> /* kvm_handle_async_pf */
#include <asm/vdso.h> /* fixup_vdso_exception() */
+#include <asm/irq_stack.h>
#define CREATE_TRACE_POINTS
#include <asm/trace/exceptions.h>
@@ -631,6 +632,9 @@ static noinline void
page_fault_oops(struct pt_regs *regs, unsigned long error_code,
unsigned long address)
{
+#ifdef CONFIG_VMAP_STACK
+ struct stack_info info;
+#endif
unsigned long flags;
int sig;
@@ -649,9 +653,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code,
* that we're in vmalloc space to avoid this.
*/
if (is_vmalloc_addr((void *)address) &&
- (((unsigned long)current->stack - 1 - address < PAGE_SIZE) ||
- address - ((unsigned long)current->stack + THREAD_SIZE) < PAGE_SIZE)) {
- unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *);
+ get_stack_guard_info((void *)address, &info)) {
/*
* We're likely to be running with very little stack space
* left. It's plausible that we'd hit this condition but
@@ -662,13 +664,11 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code,
* and then double-fault, though, because we're likely to
* break the console driver and lose most of the stack dump.
*/
- asm volatile ("movq %[stack], %%rsp\n\t"
- "call handle_stack_overflow\n\t"
- "1: jmp 1b"
- : ASM_CALL_CONSTRAINT
- : "D" ("kernel stack overflow (page fault)"),
- "S" (regs), "d" (address),
- [stack] "rm" (stack));
+ call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*),
+ handle_stack_overflow,
+ ASM_CALL_ARG3,
+ , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info));
+
unreachable();
}
#endif