103 lines
3.5 KiB
Diff
103 lines
3.5 KiB
Diff
From 43363c3aab4d701b57875b36a51a7adbc01f8d19 Mon Sep 17 00:00:00 2001
|
|
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
|
|
Date: Mon, 11 May 2015 17:52:07 +0200
|
|
Subject: [PATCH 02/14] mm, uaccess: trigger might_sleep() in might_fault()
|
|
with disabled pagefaults
|
|
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.0/patches-4.0.4-rt1.tar.xz
|
|
|
|
Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with
|
|
pagefault_disable()") removed might_sleep() checks for all user access
|
|
code (that uses might_fault()).
|
|
|
|
The reason was to disable wrong "sleep in atomic" warnings in the
|
|
following scenario:
|
|
pagefault_disable()
|
|
rc = copy_to_user(...)
|
|
pagefault_enable()
|
|
|
|
Which is valid, as pagefault_disable() increments the preempt counter
|
|
and therefore disables the pagefault handler. copy_to_user() will not
|
|
sleep and return an error code if a page is not available.
|
|
|
|
However, as all might_sleep() checks are removed,
|
|
CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario:
|
|
spin_lock(&lock);
|
|
rc = copy_to_user(...)
|
|
spin_unlock(&lock)
|
|
|
|
If the kernel is compiled with preemption turned on, preempt_disable()
|
|
will make in_atomic() detect disabled preemption. The fault handler would
|
|
correctly never sleep on user access.
|
|
However, with preemption turned off, preempt_disable() is usually a NOP
|
|
(with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to
|
|
detect disabled preemption nor disabled pagefaults. The fault handler
|
|
could sleep.
|
|
We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access
|
|
functions again, otherwise we can end up with horrible deadlocks.
|
|
|
|
Root of all evil is that pagefault_disable() acts almost as
|
|
preempt_disable(), depending on preemption being turned on/off.
|
|
|
|
As we now have pagefault_disabled(), we can use it to distinguish
|
|
whether user acces functions might sleep.
|
|
|
|
Convert might_fault() into a makro that calls __might_fault(), to
|
|
allow proper file + line messages in case of a might_sleep() warning.
|
|
|
|
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
|
|
---
|
|
include/linux/kernel.h | 3 ++-
|
|
mm/memory.c | 18 ++++++------------
|
|
2 files changed, 8 insertions(+), 13 deletions(-)
|
|
|
|
--- a/include/linux/kernel.h
|
|
+++ b/include/linux/kernel.h
|
|
@@ -232,7 +232,8 @@ static inline u32 reciprocal_scale(u32 v
|
|
|
|
#if defined(CONFIG_MMU) && \
|
|
(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
|
|
-void might_fault(void);
|
|
+#define might_fault() __might_fault(__FILE__, __LINE__)
|
|
+void __might_fault(const char *file, int line);
|
|
#else
|
|
static inline void might_fault(void) { }
|
|
#endif
|
|
--- a/mm/memory.c
|
|
+++ b/mm/memory.c
|
|
@@ -3642,7 +3642,7 @@ void print_vma_addr(char *prefix, unsign
|
|
}
|
|
|
|
#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
|
|
-void might_fault(void)
|
|
+void __might_fault(const char *file, int line)
|
|
{
|
|
/*
|
|
* Some code (nfs/sunrpc) uses socket ops on kernel memory while
|
|
@@ -3652,21 +3652,15 @@ void might_fault(void)
|
|
*/
|
|
if (segment_eq(get_fs(), KERNEL_DS))
|
|
return;
|
|
-
|
|
- /*
|
|
- * it would be nicer only to annotate paths which are not under
|
|
- * pagefault_disable, however that requires a larger audit and
|
|
- * providing helpers like get_user_atomic.
|
|
- */
|
|
- if (in_atomic())
|
|
+ if (pagefault_disabled())
|
|
return;
|
|
-
|
|
- __might_sleep(__FILE__, __LINE__, 0);
|
|
-
|
|
+ __might_sleep(file, line, 0);
|
|
+#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
|
|
if (current->mm)
|
|
might_lock_read(¤t->mm->mmap_sem);
|
|
+#endif
|
|
}
|
|
-EXPORT_SYMBOL(might_fault);
|
|
+EXPORT_SYMBOL(__might_fault);
|
|
#endif
|
|
|
|
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
|