[PATCH v3 3/3] sched, x86: Check that we're on the right stack in schedule and __might_sleep

From: Andy Lutomirski
Date: Tue Nov 18 2014 - 18:15:41 EST


On x86, sleeping while on an IST or irq stack has a surprisingly
good chance of working, but it can also fail dramatically. Add an
arch hook to allow schedule and __might_sleep to catch sleeping on
the wrong stack.

This will also catch do_exit from a funny stack, which could leave
an IST stack shifted or an NMI nesting count incremented.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
---
arch/x86/Kconfig | 1 +
arch/x86/include/asm/thread_info.h | 17 +++++++++++++++++
arch/x86/kernel/irq_32.c | 13 +++----------
include/linux/thread_info.h | 7 +++++++
kernel/Kconfig.locks | 3 +++
kernel/sched/core.c | 14 ++++++++++----
6 files changed, 41 insertions(+), 14 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ded8a6774ac9..a811286636d2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -137,6 +137,7 @@ config X86
select HAVE_ACPI_APEI_NMI if ACPI
select ACPI_LEGACY_TABLES_LOOKUP if ACPI
select X86_FEATURE_NAMES if PROC_FS
+ select HAVE_ARCH_SCHEDULE_ALLOWED

config INSTRUCTION_DECODER
def_bool y
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 547e344a6dc6..05701f132473 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -170,6 +170,23 @@ static inline struct thread_info *current_thread_info(void)
return ti;
}

+static inline unsigned long current_stack_pointer(void)
+{
+ unsigned long sp;
+#ifdef CONFIG_X86_64
+ asm("mov %%rsp,%0" : "=g" (sp));
+#else
+ asm("mov %%esp,%0" : "=g" (sp));
+#endif
+ return sp;
+}
+
+static inline bool arch_schedule_allowed(void)
+{
+ return ((current_stack_pointer() ^ this_cpu_read_stable(kernel_stack))
+ & ~(THREAD_SIZE - 1)) == 0;
+}
+
#else /* !__ASSEMBLY__ */

/* how to get the thread information struct from ASM */
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 63ce838e5a54..28d28f5eb8f4 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -69,16 +69,9 @@ static void call_on_stack(void *func, void *stack)
: "memory", "cc", "edx", "ecx", "eax");
}

-/* how to get the current stack pointer from C */
-#define current_stack_pointer ({ \
- unsigned long sp; \
- asm("mov %%esp,%0" : "=g" (sp)); \
- sp; \
-})
-
static inline void *current_stack(void)
{
- return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+ return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
}

static inline int
@@ -103,7 +96,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)

/* Save the next esp at the bottom of the stack */
prev_esp = (u32 *)irqstk;
- *prev_esp = current_stack_pointer;
+ *prev_esp = current_stack_pointer();

if (unlikely(overflow))
call_on_stack(print_stack_overflow, isp);
@@ -156,7 +149,7 @@ void do_softirq_own_stack(void)

/* Push the previous esp onto the stack */
prev_esp = (u32 *)irqstk;
- *prev_esp = current_stack_pointer;
+ *prev_esp = current_stack_pointer();

call_on_stack(__do_softirq, isp);
}
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index ff307b548ed3..6deaf7e97009 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -145,6 +145,13 @@ static inline bool test_and_clear_restore_sigmask(void)
#error "no set_restore_sigmask() provided and default one won't work"
#endif

+#ifndef CONFIG_HAVE_ARCH_SCHEDULE_ALLOWED
+static inline bool arch_schedule_allowed(void)
+{
+ return true;
+}
+#endif
+
#endif /* __KERNEL__ */

#endif /* _LINUX_THREAD_INFO_H */
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 76768ee812b2..2714dc34695a 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -237,3 +237,6 @@ config ARCH_USE_QUEUE_RWLOCK
config QUEUE_RWLOCK
def_bool y if ARCH_USE_QUEUE_RWLOCK
depends on SMP
+
+config HAVE_ARCH_SCHEDULE_ALLOWED
+ bool
\ No newline at end of file
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 240157c13ddc..e51ab65a9750 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2705,8 +2705,12 @@ static inline void schedule_debug(struct task_struct *prev)
* Test if we are atomic. Since do_exit() needs to call into
* schedule() atomically, we ignore that path. Otherwise whine
* if we are scheduling when we should not.
+ *
+ * If architectural conditions for scheduling are not met,
+ * complain even if we are in do_exit.
*/
- if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
+ if (unlikely((in_atomic_preempt_off() && prev->state != TASK_DEAD) ||
+ !arch_schedule_allowed()))
__schedule_bug(prev);
rcu_sleep_check();

@@ -7200,10 +7204,12 @@ static inline int preempt_count_equals(int preempt_offset)
void __might_sleep(const char *file, int line, int preempt_offset)
{
static unsigned long prev_jiffy; /* ratelimiting */
+ bool arch_ok;

rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
+ arch_ok = arch_schedule_allowed();
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
- !is_idle_task(current)) ||
+ !is_idle_task(current) && arch_ok) ||
system_state != SYSTEM_RUNNING || oops_in_progress)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
@@ -7214,8 +7220,8 @@ void __might_sleep(const char *file, int line, int preempt_offset)
"BUG: sleeping function called from invalid context at %s:%d\n",
file, line);
printk(KERN_ERR
- "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
- in_atomic(), irqs_disabled(),
+ "in_atomic(): %d, irqs_disabled(): %d, arch_schedule_allowed: %d, pid: %d, name: %s\n",
+ in_atomic(), irqs_disabled(), (int)arch_ok,
current->pid, current->comm);

debug_show_held_locks(current);
--
1.9.3

--
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/