On Thu, Aug 06, 2020 at 01:32PM +0200, pet...@infradead.org wrote:
> On Thu, Aug 06, 2020 at 09:47:23AM +0200, Marco Elver wrote:
> > Testing my hypothesis that raw then nested non-raw
> > local_irq_save/restore() breaks IRQ state tracking -- see the reproducer
> > below. This is at least 1 case I can think of that we're bound to hit.
...
>
> /me goes ponder things...
>
> How's something like this then?
>
> ---
> include/linux/sched.h | 3 ---
> kernel/kcsan/core.c | 62
> ++++++++++++++++++++++++++++++++++++---------------
> 2 files changed, 44 insertions(+), 21 deletions(-)
Thank you! That approach seems to pass syzbot (also with
CONFIG_PARAVIRT) and kcsan-test tests.
I had to modify it some, so that report.c's use of the restore logic
works and not mess up the IRQ trace printed on KCSAN reports (with
CONFIG_KCSAN_VERBOSE).
I still need to fully convince myself all is well now and we don't end
up with more fixes. :-) If it passes further testing, I'll send it as a
real patch (I want to add you as Co-developed-by, but would need your
Signed-off-by for the code you pasted, I think.)
Thanks,
-- Marco
------ >8 ------
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 9147ff6a12e5..b1d5dca10aa5 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -4,6 +4,7 @@
#include <linux/bug.h>
#include <linux/delay.h>
#include <linux/export.h>
+#include <linux/ftrace.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
@@ -291,13 +292,28 @@ static inline unsigned int get_delay(void)
0);
}
-void kcsan_save_irqtrace(struct task_struct *task)
-{
+/*
+ * KCSAN instrumentation is everywhere, which means we must treat the hooks
+ * NMI-like for interrupt tracing. In order to present a 'normal' as possible
+ * context to the code called by KCSAN when reporting errors we need to update
+ * the IRQ-tracing state.
+ *
+ * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's
+ * runtime is entered for every memory access, and potentially useful
+ * information is lost if dirtied by KCSAN.
+ */
+
+struct kcsan_irq_state {
+ unsigned long flags;
#ifdef CONFIG_TRACE_IRQFLAGS
- task->kcsan_save_irqtrace = task->irqtrace;
+ int hardirqs;
#endif
-}
+};
+/*
+ * This is also called by the reporting task for the other task, to generate
the
+ * right report with CONFIG_KCSAN_VERBOSE. No harm in restoring more than once.
+ */
void kcsan_restore_irqtrace(struct task_struct *task)
{
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -305,6 +321,34 @@ void kcsan_restore_irqtrace(struct task_struct *task)
#endif
}
+static void kcsan_irq_save(struct kcsan_irq_state *irq_state) {
+#ifdef CONFIG_TRACE_IRQFLAGS
+ current->kcsan_save_irqtrace = current->irqtrace;
+ irq_state->hardirqs = lockdep_hardirqs_enabled();
+#endif
+ if (!kcsan_interrupt_watcher) {
+ raw_local_irq_save(irq_state->flags);
+ kcsan_disable_current(); /* Lockdep might WARN. */
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ kcsan_enable_current();
+ }
+}
+
+static void kcsan_irq_restore(struct kcsan_irq_state *irq_state) {
+ if (!kcsan_interrupt_watcher) {
+#ifdef CONFIG_TRACE_IRQFLAGS
+ if (irq_state->hardirqs) {
+ kcsan_disable_current(); /* Lockdep might WARN. */
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ lockdep_hardirqs_on(CALLER_ADDR0);
+ kcsan_enable_current();
+ }
+#endif
+ raw_local_irq_restore(irq_state->flags);
+ }
+ kcsan_restore_irqtrace(current);
+}
+
/*
* Pull everything together: check_access() below contains the performance
* critical operations; the fast-path (including check_access) functions should
@@ -350,11 +394,13 @@ static noinline void kcsan_found_watchpoint(const
volatile void *ptr,
flags = user_access_save();
if (consumed) {
- kcsan_save_irqtrace(current);
+ struct kcsan_irq_state irqstate;
+
+ kcsan_irq_save(&irqstate);
kcsan_report(ptr, size, type, KCSAN_VALUE_CHANGE_MAYBE,
KCSAN_REPORT_CONSUMED_WATCHPOINT,
watchpoint - watchpoints);
- kcsan_restore_irqtrace(current);
+ kcsan_irq_restore(&irqstate);
} else {
/*
* The other thread may not print any diagnostics, as it has
@@ -387,7 +433,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t
size, int type)
unsigned long access_mask;
enum kcsan_value_change value_change = KCSAN_VALUE_CHANGE_MAYBE;
unsigned long ua_flags = user_access_save();
- unsigned long irq_flags = 0;
+ struct kcsan_irq_state irqstate;
/*
* Always reset kcsan_skip counter in slow-path to avoid underflow; see
@@ -412,14 +458,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t
size, int type)
goto out;
}
- /*
- * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's
- * runtime is entered for every memory access, and potentially useful
- * information is lost if dirtied by KCSAN.
- */
- kcsan_save_irqtrace(current);
- if (!kcsan_interrupt_watcher)
- local_irq_save(irq_flags);
+ kcsan_irq_save(&irqstate);
watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write);
if (watchpoint == NULL) {
@@ -559,9 +598,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t
size, int type)
remove_watchpoint(watchpoint);
kcsan_counter_dec(KCSAN_COUNTER_USED_WATCHPOINTS);
out_unlock:
- if (!kcsan_interrupt_watcher)
- local_irq_restore(irq_flags);
- kcsan_restore_irqtrace(current);
+ kcsan_irq_restore(&irqstate);
out:
user_access_restore(ua_flags);
}
diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h
index 29480010dc30..6eb35a9514d8 100644
--- a/kernel/kcsan/kcsan.h
+++ b/kernel/kcsan/kcsan.h
@@ -24,9 +24,8 @@ extern unsigned int kcsan_udelay_interrupt;
extern bool kcsan_enabled;
/*
- * Save/restore IRQ flags state trace dirtied by KCSAN.
+ * Restore IRQ flags state trace dirtied by KCSAN.
*/
-void kcsan_save_irqtrace(struct task_struct *task);
void kcsan_restore_irqtrace(struct task_struct *task);
/*
