[PATCH v2 1/4] lockdep: Apply crossrelease to PG_locked locks
Although lock_page() and its family can cause deadlock, lockdep have not worked with them, becasue unlock_page() might be called in a different context from the acquire context, which violated lockdep's assumption. Now CONFIG_LOCKDEP_CROSSRELEASE has been introduced, lockdep can work with page locks. Signed-off-by: Byungchul Park--- include/linux/mm_types.h | 8 include/linux/pagemap.h | 101 --- lib/Kconfig.debug| 7 mm/filemap.c | 4 +- mm/page_alloc.c | 3 ++ 5 files changed, 115 insertions(+), 8 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c85f11d..263b861 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -17,6 +17,10 @@ #include +#ifdef CONFIG_LOCKDEP_PAGELOCK +#include +#endif + #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH 0 #endif @@ -218,6 +222,10 @@ 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 e08b533..35b4f67 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -15,6 +15,9 @@ #include #include /* for in_interrupt() */ #include +#ifdef CONFIG_LOCKDEP_PAGELOCK +#include +#endif /* * Bits in mapping->flags. @@ -457,26 +460,91 @@ 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 *)>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 *)>map); + lock_release((struct lockdep_map *)>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, >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(_gen_id) +* ~ +* acquire B +*Y = atomic_read_acquire(_gen_id) +* lock B +* +* so that 'lock A and then lock B' can be seen globally, +* if X <= Y. +*/ + lock_page_acquire(page, 0); } /* @@ -486,9 +554,20 @@ 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
[PATCH v2 1/4] lockdep: Apply crossrelease to PG_locked locks
Although lock_page() and its family can cause deadlock, lockdep have not worked with them, becasue unlock_page() might be called in a different context from the acquire context, which violated lockdep's assumption. Now CONFIG_LOCKDEP_CROSSRELEASE has been introduced, lockdep can work with page locks. Signed-off-by: Byungchul Park --- include/linux/mm_types.h | 8 include/linux/pagemap.h | 101 --- lib/Kconfig.debug| 7 mm/filemap.c | 4 +- mm/page_alloc.c | 3 ++ 5 files changed, 115 insertions(+), 8 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c85f11d..263b861 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -17,6 +17,10 @@ #include +#ifdef CONFIG_LOCKDEP_PAGELOCK +#include +#endif + #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH 0 #endif @@ -218,6 +222,10 @@ 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 e08b533..35b4f67 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -15,6 +15,9 @@ #include #include /* for in_interrupt() */ #include +#ifdef CONFIG_LOCKDEP_PAGELOCK +#include +#endif /* * Bits in mapping->flags. @@ -457,26 +460,91 @@ 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 *)>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 *)>map); + lock_release((struct lockdep_map *)>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, >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(_gen_id) +* ~ +* acquire B +*Y = atomic_read_acquire(_gen_id) +* lock B +* +* so that 'lock A and then lock B' can be seen globally, +* if X <= Y. +*/ + lock_page_acquire(page, 0); } /* @@ -486,9 +554,20 @@ 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