| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 7 Aug 2017 16:12:58 +0900
From: Byungchul Park <byungchul.park@....com>
To: peterz@...radead.org, mingo@...nel.org
Cc: tglx@...utronix.de, walken@...gle.com, boqun.feng@...il.com,
kirill@...temov.name, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, akpm@...ux-foundation.org, willy@...radead.org,
npiggin@...il.com, kernel-team@....com
Subject: [PATCH v8 11/14] lockdep: Apply crossrelease to PG_locked locks
Although lock_page() and its family can cause deadlock, the lock
correctness validator could not be applied to them until now, becasue
things like unlock_page() might be called in a different context from
the acquisition context, which violates lockdep's assumption.
Thanks to CONFIG_LOCKDEP_CROSSRELEASE, we can now apply the lockdep
detector to page locks. Applied it.
Signed-off-by: Byungchul Park <byungchul.park@....com>
---
include/linux/mm_types.h | 8 ++++
include/linux/pagemap.h | 101 ++++++++++++++++++++++++++++++++++++++++++++---
lib/Kconfig.debug | 8 ++++
mm/filemap.c | 4 +-
mm/page_alloc.c | 3 ++
5 files changed, 116 insertions(+), 8 deletions(-)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ff15181..f1e3dba 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -16,6 +16,10 @@
#include <asm/mmu.h>
+#ifdef CONFIG_LOCKDEP_PAGELOCK
+#include <linux/lockdep.h>
+#endif
+
#ifndef AT_VECTOR_SIZE_ARCH
#define AT_VECTOR_SIZE_ARCH 0
#endif
@@ -216,6 +220,10 @@ struct page {
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
int _last_cpupid;
#endif
+
+#ifdef CONFIG_LOCKDEP_PAGELOCK
+ struct lockdep_map_cross map;
+#endif
}
/*
* The struct page can be forced to be double word aligned so that atomic ops
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 9717ca8..9f448c6 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -14,6 +14,9 @@
#include <linux/bitops.h>
#include <linux/hardirq.h> /* for in_interrupt() */
#include <linux/hugetlb_inline.h>
+#ifdef CONFIG_LOCKDEP_PAGELOCK
+#include <linux/lockdep.h>
+#endif
/*
* Bits in mapping->flags.
@@ -450,26 +453,91 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
return pgoff;
}
+#ifdef CONFIG_LOCKDEP_PAGELOCK
+#define lock_page_init(p) \
+do { \
+ static struct lock_class_key __key; \
+ lockdep_init_map_crosslock((struct lockdep_map *)&(p)->map, \
+ "(PG_locked)" #p, &__key, 0); \
+} while (0)
+
+static inline void lock_page_acquire(struct page *page, int try)
+{
+ page = compound_head(page);
+ lock_acquire_exclusive((struct lockdep_map *)&page->map, 0,
+ try, NULL, _RET_IP_);
+}
+
+static inline void lock_page_release(struct page *page)
+{
+ page = compound_head(page);
+ /*
+ * lock_commit_crosslock() is necessary for crosslocks.
+ */
+ lock_commit_crosslock((struct lockdep_map *)&page->map);
+ lock_release((struct lockdep_map *)&page->map, 0, _RET_IP_);
+}
+#else
+static inline void lock_page_init(struct page *page) {}
+static inline void lock_page_free(struct page *page) {}
+static inline void lock_page_acquire(struct page *page, int try) {}
+static inline void lock_page_release(struct page *page) {}
+#endif
+
extern void __lock_page(struct page *page);
extern int __lock_page_killable(struct page *page);
extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags);
-extern void unlock_page(struct page *page);
+extern void do_raw_unlock_page(struct page *page);
-static inline int trylock_page(struct page *page)
+static inline void unlock_page(struct page *page)
+{
+ lock_page_release(page);
+ do_raw_unlock_page(page);
+}
+
+static inline int do_raw_trylock_page(struct page *page)
{
page = compound_head(page);
return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
}
+static inline int trylock_page(struct page *page)
+{
+ if (do_raw_trylock_page(page)) {
+ lock_page_acquire(page, 1);
+ return 1;
+ }
+ return 0;
+}
+
/*
* lock_page may only be called if we have the page's inode pinned.
*/
static inline void lock_page(struct page *page)
{
might_sleep();
- if (!trylock_page(page))
+
+ if (!do_raw_trylock_page(page))
__lock_page(page);
+ /*
+ * acquire() must be after actual lock operation for crosslocks.
+ * This way a crosslock and current lock can be ordered like:
+ *
+ * CONTEXT 1 CONTEXT 2
+ * --------- ---------
+ * lock A (cross)
+ * acquire A
+ * X = atomic_inc_return(&cross_gen_id)
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * acquire B
+ * Y = atomic_read_acquire(&cross_gen_id)
+ * lock B
+ *
+ * so that 'lock A and then lock B' can be seen globally,
+ * if X <= Y.
+ */
+ lock_page_acquire(page, 0);
}
/*
@@ -479,9 +547,20 @@ static inline void lock_page(struct page *page)
*/
static inline int lock_page_killable(struct page *page)
{
+ int ret;
+
might_sleep();
- if (!trylock_page(page))
- return __lock_page_killable(page);
+
+ if (!do_raw_trylock_page(page)) {
+ ret = __lock_page_killable(page);
+ if (ret)
+ return ret;
+ }
+ /*
+ * acquire() must be after actual lock operation for crosslocks.
+ * This way a crosslock and other locks can be ordered.
+ */
+ lock_page_acquire(page, 0);
return 0;
}
@@ -496,7 +575,17 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
might_sleep();
- return trylock_page(page) || __lock_page_or_retry(page, mm, flags);
+
+ if (do_raw_trylock_page(page) || __lock_page_or_retry(page, mm, flags)) {
+ /*
+ * acquire() must be after actual lock operation for crosslocks.
+ * This way a crosslock and other locks can be ordered.
+ */
+ lock_page_acquire(page, 0);
+ return 1;
+ }
+
+ return 0;
}
/*
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4ba8adc..99b5f76 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1093,6 +1093,14 @@ config LOCKDEP_COMPLETE
A deadlock caused by wait_for_completion() and complete() can be
detected by lockdep using crossrelease feature.
+config LOCKDEP_PAGELOCK
+ bool "Lock debugging: allow PG_locked lock to use deadlock detector"
+ select LOCKDEP_CROSSRELEASE
+ default n
+ help
+ PG_locked lock is a kind of crosslock. Using crossrelease feature,
+ PG_locked lock can work with runtime deadlock detector.
+
config PROVE_LOCKING
bool "Lock debugging: prove locking correctness"
depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
diff --git a/mm/filemap.c b/mm/filemap.c
index a497024..0d83bf0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1083,7 +1083,7 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem
* portably (architectures that do LL/SC can test any bit, while x86 can
* test the sign bit).
*/
-void unlock_page(struct page *page)
+void do_raw_unlock_page(struct page *page)
{
BUILD_BUG_ON(PG_waiters != 7);
page = compound_head(page);
@@ -1091,7 +1091,7 @@ void unlock_page(struct page *page)
if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
wake_up_page_bit(page, PG_locked);
}
-EXPORT_SYMBOL(unlock_page);
+EXPORT_SYMBOL(do_raw_unlock_page);
/**
* end_page_writeback - end writeback against a page
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6d30e91..2cbf412 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5406,6 +5406,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
} else {
__init_single_pfn(pfn, zone, nid);
}
+#ifdef CONFIG_LOCKDEP_PAGELOCK
+ lock_page_init(pfn_to_page(pfn));
+#endif
}
}
--
1.9.1
Powered by blists - more mailing lists