diff options
31 files changed, 1861 insertions, 129 deletions
diff --git a/Documentation/ww-mutex-design.txt b/Documentation/ww-mutex-design.txt new file mode 100644 index 000000000000..8a112dc304c3 --- /dev/null +++ b/Documentation/ww-mutex-design.txt @@ -0,0 +1,344 @@ +Wait/Wound Deadlock-Proof Mutex Design +====================================== + +Please read mutex-design.txt first, as it applies to wait/wound mutexes too. + +Motivation for WW-Mutexes +------------------------- + +GPU's do operations that commonly involve many buffers. Those buffers +can be shared across contexts/processes, exist in different memory +domains (for example VRAM vs system memory), and so on. And with +PRIME / dmabuf, they can even be shared across devices. So there are +a handful of situations where the driver needs to wait for buffers to +become ready. If you think about this in terms of waiting on a buffer +mutex for it to become available, this presents a problem because +there is no way to guarantee that buffers appear in a execbuf/batch in +the same order in all contexts. That is directly under control of +userspace, and a result of the sequence of GL calls that an application +makes. Which results in the potential for deadlock. The problem gets +more complex when you consider that the kernel may need to migrate the +buffer(s) into VRAM before the GPU operates on the buffer(s), which +may in turn require evicting some other buffers (and you don't want to +evict other buffers which are already queued up to the GPU), but for a +simplified understanding of the problem you can ignore this. + +The algorithm that the TTM graphics subsystem came up with for dealing with +this problem is quite simple. For each group of buffers (execbuf) that need +to be locked, the caller would be assigned a unique reservation id/ticket, +from a global counter. In case of deadlock while locking all the buffers +associated with a execbuf, the one with the lowest reservation ticket (i.e. +the oldest task) wins, and the one with the higher reservation id (i.e. the +younger task) unlocks all of the buffers that it has already locked, and then +tries again. + +In the RDBMS literature this deadlock handling approach is called wait/wound: +The older tasks waits until it can acquire the contended lock. The younger tasks +needs to back off and drop all the locks it is currently holding, i.e. the +younger task is wounded. + +Concepts +-------- + +Compared to normal mutexes two additional concepts/objects show up in the lock +interface for w/w mutexes: + +Acquire context: To ensure eventual forward progress it is important the a task +trying to acquire locks doesn't grab a new reservation id, but keeps the one it +acquired when starting the lock acquisition. This ticket is stored in the +acquire context. Furthermore the acquire context keeps track of debugging state +to catch w/w mutex interface abuse. + +W/w class: In contrast to normal mutexes the lock class needs to be explicit for +w/w mutexes, since it is required to initialize the acquire context. + +Furthermore there are three different class of w/w lock acquire functions: + +* Normal lock acquisition with a context, using ww_mutex_lock. + +* Slowpath lock acquisition on the contending lock, used by the wounded task + after having dropped all already acquired locks. These functions have the + _slow postfix. + + From a simple semantics point-of-view the _slow functions are not strictly + required, since simply calling the normal ww_mutex_lock functions on the + contending lock (after having dropped all other already acquired locks) will + work correctly. After all if no other ww mutex has been acquired yet there's + no deadlock potential and hence the ww_mutex_lock call will block and not + prematurely return -EDEADLK. The advantage of the _slow functions is in + interface safety: + - ww_mutex_lock has a __must_check int return type, whereas ww_mutex_lock_slow + has a void return type. Note that since ww mutex code needs loops/retries + anyway the __must_check doesn't result in spurious warnings, even though the + very first lock operation can never fail. + - When full debugging is enabled ww_mutex_lock_slow checks that all acquired + ww mutex have been released (preventing deadlocks) and makes sure that we + block on the contending lock (preventing spinning through the -EDEADLK + slowpath until the contended lock can be acquired). + +* Functions to only acquire a single w/w mutex, which results in the exact same + semantics as a normal mutex. This is done by calling ww_mutex_lock with a NULL + context. + + Again this is not strictly required. But often you only want to acquire a + single lock in which case it's pointless to set up an acquire context (and so + better to avoid grabbing a deadlock avoidance ticket). + +Of course, all the usual variants for handling wake-ups due to signals are also +provided. + +Usage +----- + +Three different ways to acquire locks within the same w/w class. Common +definitions for methods #1 and #2: + +static DEFINE_WW_CLASS(ww_class); + +struct obj { + struct ww_mutex lock; + /* obj data */ +}; + +struct obj_entry { + struct list_head head; + struct obj *obj; +}; + +Method 1, using a list in execbuf->buffers that's not allowed to be reordered. +This is useful if a list of required objects is already tracked somewhere. +Furthermore the lock helper can use propagate the -EALREADY return code back to +the caller as a signal that an object is twice on the list. This is useful if +the list is constructed from userspace input and the ABI requires userspace to +not have duplicate entries (e.g. for a gpu commandbuffer submission ioctl). + +int lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx) +{ + struct obj *res_obj = NULL; + struct obj_entry *contended_entry = NULL; + struct obj_entry *entry; + + ww_acquire_init(ctx, &ww_class); + +retry: + list_for_each_entry (entry, list, head) { + if (entry->obj == res_obj) { + res_obj = NULL; + continue; + } + ret = ww_mutex_lock(&entry->obj->lock, ctx); + if (ret < 0) { + contended_entry = entry; + goto err; + } + } + + ww_acquire_done(ctx); + return 0; + +err: + list_for_each_entry_continue_reverse (entry, list, head) + ww_mutex_unlock(&entry->obj->lock); + + if (res_obj) + ww_mutex_unlock(&res_obj->lock); + + if (ret == -EDEADLK) { + /* we lost out in a seqno race, lock and retry.. */ + ww_mutex_lock_slow(&contended_entry->obj->lock, ctx); + res_obj = contended_entry->obj; + goto retry; + } + ww_acquire_fini(ctx); + + return ret; +} + +Method 2, using a list in execbuf->buffers that can be reordered. Same semantics +of duplicate entry detection using -EALREADY as method 1 above. But the +list-reordering allows for a bit more idiomatic code. + +int lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx) +{ + struct obj_entry *entry, *entry2; + + ww_acquire_init(ctx, &ww_class); + + list_for_each_entry (entry, list, head) { + ret = ww_mutex_lock(&entry->obj->lock, ctx); + if (ret < 0) { + entry2 = entry; + + list_for_each_entry_continue_reverse (entry2, list, head) + ww_mutex_unlock(&entry2->obj->lock); + + if (ret != -EDEADLK) { + ww_acquire_fini(ctx); + return ret; + } + + /* we lost out in a seqno race, lock and retry.. */ + ww_mutex_lock_slow(&entry->obj->lock, ctx); + + /* + * Move buf to head of the list, this will point + * buf->next to the first unlocked entry, + * restarting the for loop. + */ + list_del(&entry->head); + list_add(&entry->head, list); + } + } + + ww_acquire_done(ctx); + return 0; +} + +Unlocking works the same way for both methods #1 and #2: + +void unlock_objs(struct list_head *list, struct ww_acquire_ctx *ctx) +{ + struct obj_entry *entry; + + list_for_each_entry (entry, list, head) + ww_mutex_unlock(&entry->obj->lock); + + ww_acquire_fini(ctx); +} + +Method 3 is useful if the list of objects is constructed ad-hoc and not upfront, +e.g. when adjusting edges in a graph where each node has its own ww_mutex lock, +and edges can only be changed when holding the locks of all involved nodes. w/w +mutexes are a natural fit for such a case for two reasons: +- They can handle lock-acquisition in any order which allows us to start walking + a graph from a starting point and then iteratively discovering new edges and + locking down the nodes those edges connect to. +- Due to the -EALREADY return code signalling that a given objects is already + held there's no need for additional book-keeping to break cycles in the graph + or keep track off which looks are already held (when using more than one node + as a starting point). + +Note that this approach differs in two important ways from the above methods: +- Since the list of objects is dynamically constructed (and might very well be + different when retrying due to hitting the -EDEADLK wound condition) there's + no need to keep any object on a persistent list when it's not locked. We can + therefore move the list_head into the object itself. +- On the other hand the dynamic object list construction also means that the -EALREADY return + code can't be propagated. + +Note also that methods #1 and #2 and method #3 can be combined, e.g. to first lock a +list of starting nodes (passed in from userspace) using one of the above +methods. And then lock any additional objects affected by the operations using +method #3 below. The backoff/retry procedure will be a bit more involved, since +when the dynamic locking step hits -EDEADLK we also need to unlock all the +objects acquired with the fixed list. But the w/w mutex debug checks will catch +any interface misuse for these cases. + +Also, method 3 can't fail the lock acquisition step since it doesn't return +-EALREADY. Of course this would be different when using the _interruptible +variants, but that's outside of the scope of these examples here. + +struct obj { + struct ww_mutex ww_mutex; + struct list_head locked_list; +}; + +static DEFINE_WW_CLASS(ww_class); + +void __unlock_objs(struct list_head *list) +{ + struct obj *entry, *temp; + + list_for_each_entry_safe (entry, temp, list, locked_list) { + /* need to do that before unlocking, since only the current lock holder is + allowed to use object */ + list_del(&entry->locked_list); + ww_mutex_unlock(entry->ww_mutex) + } +} + +void lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx) +{ + struct obj *obj; + + ww_acquire_init(ctx, &ww_class); + +retry: + /* re-init loop start state */ + loop { + /* magic code which walks over a graph and decides which objects + * to lock */ + + ret = ww_mutex_lock(obj->ww_mutex, ctx); + if (ret == -EALREADY) { + /* we have that one already, get to the next object */ + continue; + } + if (ret == -EDEADLK) { + __unlock_objs(list); + + ww_mutex_lock_slow(obj, ctx); + list_add(&entry->locked_list, list); + goto retry; + } + + /* locked a new object, add it to the list */ + list_add_tail(&entry->locked_list, list); + } + + ww_acquire_done(ctx); + return 0; +} + +void unlock_objs(struct list_head *list, struct ww_acquire_ctx *ctx) +{ + __unlock_objs(list); + ww_acquire_fini(ctx); +} + +Method 4: Only lock one single objects. In that case deadlock detection and +prevention is obviously overkill, since with grabbing just one lock you can't +produce a deadlock within just one class. To simplify this case the w/w mutex +api can be used with a NULL context. + +Implementation Details +---------------------- + +Design: + ww_mutex currently encapsulates a struct mutex, this means no extra overhead for + normal mutex locks, which are far more common. As such there is only a small + increase in code size if wait/wound mutexes are not used. + + In general, not much contention is expected. The locks are typically used to + serialize access to resources for devices. The only way to make wakeups + smarter would be at the cost of adding a field to struct mutex_waiter. This + would add overhead to all cases where normal mutexes are used, and + ww_mutexes are generally less performance sensitive. + +Lockdep: + Special care has been taken to warn for as many cases of api abuse + as possible. Some common api abuses will be caught with + CONFIG_DEBUG_MUTEXES, but CONFIG_PROVE_LOCKING is recommended. + + Some of the errors which will be warned about: + - Forgetting to call ww_acquire_fini or ww_acquire_init. + - Attempting to lock more mutexes after ww_acquire_done. + - Attempting to lock the wrong mutex after -EDEADLK and + unlocking all mutexes. + - Attempting to lock the right mutex after -EDEADLK, + before unlocking all mutexes. + + - Calling ww_mutex_lock_slow before -EDEADLK was returned. + + - Unlocking mutexes with the wrong unlock function. + - Calling one of the ww_acquire_* twice on the same context. + - Using a different ww_class for the mutex than for the ww_acquire_ctx. + - Normal lockdep errors that can result in deadlocks. + + Some of the lockdep errors that can result in deadlocks: + - Calling ww_acquire_init to initialize a second ww_acquire_ctx before + having called ww_acquire_fini on the first. + - 'normal' deadlocks that can occur. + +FIXME: Update this section once we have the TASK_DEADLOCK task state flag magic +implemented. diff --git a/arch/ia64/include/asm/mutex.h b/arch/ia64/include/asm/mutex.h index bed73a643a56..f41e66d65e31 100644 --- a/arch/ia64/include/asm/mutex.h +++ b/arch/ia64/include/asm/mutex.h @@ -29,17 +29,15 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if - * it wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns. + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ static inline int -__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) +__mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(ia64_fetchadd4_acq(count, -1) != 1)) - return fail_fn(count); + return -1; return 0; } diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h index 5399f7e18102..127ab23e1f6c 100644 --- a/arch/powerpc/include/asm/mutex.h +++ b/arch/powerpc/include/asm/mutex.h @@ -82,17 +82,15 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if - * it wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns. + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ static inline int -__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) +__mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(__mutex_dec_return_lock(count) < 0)) - return fail_fn(count); + return -1; return 0; } diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 028ac1f71b51..46ac1ddea683 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -97,22 +97,14 @@ static int fsl_indirect_read_config(struct pci_bus *bus, unsigned int devfn, return indirect_read_config(bus, devfn, offset, len, val); } -static struct pci_ops fsl_indirect_pci_ops = +#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx) + +static struct pci_ops fsl_indirect_pcie_ops = { .read = fsl_indirect_read_config, .write = indirect_write_config, }; -static void __init fsl_setup_indirect_pci(struct pci_controller* hose, - resource_size_t cfg_addr, - resource_size_t cfg_data, u32 flags) -{ - setup_indirect_pci(hose, cfg_addr, cfg_data, flags); - hose->ops = &fsl_indirect_pci_ops; -} - -#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx) - #define MAX_PHYS_ADDR_BITS 40 static u64 pci64_dma_offset = 1ull << MAX_PHYS_ADDR_BITS; @@ -504,13 +496,15 @@ int __init fsl_add_bridge(struct platform_device *pdev, int is_primary) if (!hose->private_data) goto no_bridge; - fsl_setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4, - PPC_INDIRECT_TYPE_BIG_ENDIAN); + setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4, + PPC_INDIRECT_TYPE_BIG_ENDIAN); if (in_be32(&pci->block_rev1) < PCIE_IP_REV_3_0) hose->indirect_type |= PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK; if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) { + /* use fsl_indirect_read_config for PCIe */ + hose->ops = &fsl_indirect_pcie_ops; /* For PCIE read HEADER_TYPE to identify controler mode */ early_read_config_byte(hose, 0, 0, PCI_HEADER_TYPE, &hdr_type); if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE) @@ -814,8 +808,8 @@ int __init mpc83xx_add_bridge(struct device_node *dev) if (ret) goto err0; } else { - fsl_setup_indirect_pci(hose, rsrc_cfg.start, - rsrc_cfg.start + 4, 0); + setup_indirect_pci(hose, rsrc_cfg.start, + rsrc_cfg.start + 4, 0); } printk(KERN_INFO "Found FSL PCI host bridge at 0x%016llx. " diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h index 886ac7d4937a..2f8c1abeb086 100644 --- a/arch/s390/include/asm/dma-mapping.h +++ b/arch/s390/include/asm/dma-mapping.h @@ -50,9 +50,10 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { struct dma_map_ops *dma_ops = get_dma_ops(dev); + debug_dma_mapping_error(dev, dma_addr); if (dma_ops->mapping_error) return dma_ops->mapping_error(dev, dma_addr); - return (dma_addr == 0UL); + return (dma_addr == DMA_ERROR_CODE); } static inline void *dma_alloc_coherent(struct device *dev, size_t size, diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index d8a6a385d048..feb719d3c851 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -754,9 +754,9 @@ static struct bin_attribute sys_reipl_fcp_scp_data_attr = { .write = reipl_fcp_scpdata_write, }; -DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n", reipl_block_fcp->ipl_info.fcp.wwpn); -DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n", reipl_block_fcp->ipl_info.fcp.lun); DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n", reipl_block_fcp->ipl_info.fcp.bootprog); @@ -1323,9 +1323,9 @@ static struct shutdown_action __refdata reipl_action = { /* FCP dump device attributes */ -DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n", dump_block_fcp->ipl_info.fcp.wwpn); -DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n", dump_block_fcp->ipl_info.fcp.lun); DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n", dump_block_fcp->ipl_info.fcp.bootprog); diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 408e866ae548..dd3c1994b8bd 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -312,6 +312,7 @@ void measurement_alert_subclass_unregister(void) } EXPORT_SYMBOL(measurement_alert_subclass_unregister); +#ifdef CONFIG_SMP void synchronize_irq(unsigned int irq) { /* @@ -320,6 +321,7 @@ void synchronize_irq(unsigned int irq) */ } EXPORT_SYMBOL_GPL(synchronize_irq); +#endif #ifndef CONFIG_PCI diff --git a/arch/s390/mm/mem_detect.c b/arch/s390/mm/mem_detect.c index 3cbd3b8bf311..cca388253a39 100644 --- a/arch/s390/mm/mem_detect.c +++ b/arch/s390/mm/mem_detect.c @@ -123,7 +123,8 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr, continue; } else if ((addr <= chunk->addr) && (addr + size >= chunk->addr + chunk->size)) { - memset(chunk, 0 , sizeof(*chunk)); + memmove(chunk, chunk + 1, (MEMORY_CHUNKS-i-1) * sizeof(*chunk)); + memset(&mem_chunk[MEMORY_CHUNKS-1], 0, sizeof(*chunk)); } else if (addr + size < chunk->addr + chunk->size) { chunk->size = chunk->addr + chunk->size - addr - size; chunk->addr = addr + size; diff --git a/arch/sh/include/asm/mutex-llsc.h b/arch/sh/include/asm/mutex-llsc.h index 090358a7e1bb..dad29b687bd3 100644 --- a/arch/sh/include/asm/mutex-llsc.h +++ b/arch/sh/include/asm/mutex-llsc.h @@ -37,7 +37,7 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) } static inline int -__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) +__mutex_fastpath_lock_retval(atomic_t *count) { int __done, __res; @@ -51,7 +51,7 @@ __mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) : "t"); if (unlikely(!__done || __res != 0)) - __res = fail_fn(count); + __res = -1; return __res; } diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h index 03f90c8a5a7c..0208c3c2cbc6 100644 --- a/arch/x86/include/asm/mutex_32.h +++ b/arch/x86/include/asm/mutex_32.h @@ -42,17 +42,14 @@ do { \ * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if it - * wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count, - int (*fail_fn)(atomic_t *)) +static inline int __mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(atomic_dec_return(count) < 0)) - return fail_fn(count); + return -1; else return 0; } diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h index 68a87b0f8e29..2c543fff241b 100644 --- a/arch/x86/include/asm/mutex_64.h +++ b/arch/x86/include/asm/mutex_64.h @@ -37,17 +37,14 @@ do { \ * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if - * it wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count, - int (*fail_fn)(atomic_t *)) +static inline int __mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(atomic_dec_return(count) < 0)) - return fail_fn(count); + return -1; else return 0; } diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index d6cbfe9df218..fa061d46527f 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -137,7 +137,7 @@ static const struct xpad_device { { 0x0738, 0x4540, "Mad Catz Beat Pad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX }, { 0x0738, 0x4556, "Mad Catz Lynx Wireless Controller", 0, XTYPE_XBOX }, { 0x0738, 0x4716, "Mad Catz Wired Xbox 360 Controller", 0, XTYPE_XBOX360 }, - { 0x0738, 0x4728, "Mad Catz Street Fighter IV FightPad", XTYPE_XBOX360 }, + { 0x0738, 0x4728, "Mad Catz Street Fighter IV FightPad", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0738, 0x4738, "Mad Catz Wired Xbox 360 Controller (SFIV)", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0738, 0x6040, "Mad Catz Beat Pad Pro", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX }, { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 }, diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 62a2c0e4cc99..7ac9c9818d55 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -431,6 +431,7 @@ config KEYBOARD_TEGRA config KEYBOARD_OPENCORES tristate "OpenCores Keyboard Controller" + depends on HAS_IOMEM help Say Y here if you want to use the OpenCores Keyboard Controller http://www.opencores.org/project,keyboardcontroller diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig index aebfe3ecb945..1bda828f4b55 100644 --- a/drivers/input/serio/Kconfig +++ b/drivers/input/serio/Kconfig @@ -205,6 +205,7 @@ config SERIO_XILINX_XPS_PS2 config SERIO_ALTERA_PS2 tristate "Altera UP PS/2 controller" + depends on HAS_IOMEM help Say Y here if you have Altera University Program PS/2 ports. diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index 518282da6d85..384fbcd0cee0 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -363,6 +363,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) case 0x140802: /* Intuos4/5 13HD/24HD Classic Pen */ case 0x160802: /* Cintiq 13HD Pro Pen */ case 0x180802: /* DTH2242 Pen */ + case 0x100802: /* Intuos4/5 13HD/24HD General Pen */ wacom->tool[idx] = BTN_TOOL_PEN; break; @@ -401,6 +402,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) case 0x10080c: /* Intuos4/5 13HD/24HD Art Pen Eraser */ case 0x16080a: /* Cintiq 13HD Pro Pen Eraser */ case 0x18080a: /* DTH2242 Eraser */ + case 0x10080a: /* Intuos4/5 13HD/24HD General Pen Eraser */ wacom->tool[idx] = BTN_TOOL_RUBBER; break; diff --git a/drivers/input/touchscreen/cyttsp_core.c b/drivers/input/touchscreen/cyttsp_core.c index 8e60437ac85b..ae89d2609ab0 100644 --- a/drivers/input/touchscreen/cyttsp_core.c +++ b/drivers/input/touchscreen/cyttsp_core.c @@ -116,6 +116,15 @@ static int ttsp_send_command(struct cyttsp *ts, u8 cmd) return ttsp_write_block_data(ts, CY_REG_BASE, sizeof(cmd), &cmd); } +static int cyttsp_handshake(struct cyttsp *ts) +{ + if (ts->pdata->use_hndshk) + return ttsp_send_command(ts, + ts->xy_data.hst_mode ^ CY_HNDSHK_BIT); + + return 0; +} + static int cyttsp_load_bl_regs(struct cyttsp *ts) { memset(&ts->bl_data, 0, sizeof(ts->bl_data)); @@ -133,7 +142,7 @@ static int cyttsp_exit_bl_mode(struct cyttsp *ts) memcpy(bl_cmd, bl_command, sizeof(bl_command)); if (ts->pdata->bl_keys) memcpy(&bl_cmd[sizeof(bl_command) - CY_NUM_BL_KEYS], - ts->pdata->bl_keys, sizeof(bl_command)); + ts->pdata->bl_keys, CY_NUM_BL_KEYS); error = ttsp_write_block_data(ts, CY_REG_BASE, sizeof(bl_cmd), bl_cmd); @@ -167,6 +176,10 @@ static int cyttsp_set_operational_mode(struct cyttsp *ts) if (error) return error; + error = cyttsp_handshake(ts); + if (error) + return error; + return ts->xy_data.act_dist == CY_ACT_DIST_DFLT ? -EIO : 0; } @@ -188,6 +201,10 @@ static int cyttsp_set_sysinfo_mode(struct cyttsp *ts) if (error) return error; + error = cyttsp_handshake(ts); + if (error) + return error; + if (!ts->sysinfo_data.tts_verh && !ts->sysinfo_data.tts_verl) return -EIO; @@ -344,12 +361,9 @@ static irqreturn_t cyttsp_irq(int irq, void *handle) goto out; /* provide flow control handshake */ - if (ts->pdata->use_hndshk) { - error = ttsp_send_command(ts, - ts->xy_data.hst_mode ^ CY_HNDSHK_BIT); - if (error) - goto out; - } + error = cyttsp_handshake(ts); + if (error) + goto out; if (unlikely(ts->state == CY_IDLE_STATE)) goto out; diff --git a/drivers/input/touchscreen/cyttsp_core.h b/drivers/input/touchscreen/cyttsp_core.h index 1aa3c6967e70..f1ebde369f86 100644 --- a/drivers/input/touchscreen/cyttsp_core.h +++ b/drivers/input/touchscreen/cyttsp_core.h @@ -67,8 +67,8 @@ struct cyttsp_xydata { /* TTSP System Information interface definition */ struct cyttsp_sysinfo_data { u8 hst_mode; - u8 mfg_cmd; u8 mfg_stat; + u8 mfg_cmd; u8 cid[3]; u8 tt_undef1; u8 uid[8]; diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c index c735c5a008a2..6427600b5bbe 100644 --- a/drivers/spi/spi-pxa2xx-dma.c +++ b/drivers/spi/spi-pxa2xx-dma.c @@ -59,7 +59,7 @@ static int pxa2xx_spi_map_dma_buffer(struct driver_data *drv_data, int ret; sg_free_table(sgt); - ret = sg_alloc_table(sgt, nents, GFP_KERNEL); + ret = sg_alloc_table(sgt, nents, GFP_ATOMIC); if (ret) return ret; } diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index f5d84d6f8222..48b396fced0a 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1075,7 +1075,7 @@ pxa2xx_spi_acpi_get_pdata(struct platform_device *pdev) acpi_bus_get_device(ACPI_HANDLE(&pdev->dev), &adev)) return NULL; - pdata = devm_kzalloc(&pdev->dev, sizeof(*ssp), GFP_KERNEL); + pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); if (!pdata) { dev_err(&pdev->dev, "failed to allocate memory for platform data\n"); diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 5000586cb98d..71cc3e6ef47c 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -444,7 +444,7 @@ static int s3c64xx_spi_prepare_transfer(struct spi_master *spi) } ret = pm_runtime_get_sync(&sdd->pdev->dev); - if (ret != 0) { + if (ret < 0) { dev_err(dev, "Failed to enable device: %d\n", ret); goto out_tx; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index e570081f9f76..35f281033142 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2470,13 +2470,16 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, .mode = mode }; int err; + bool lock_inode = !(mode & FALLOC_FL_KEEP_SIZE) || + (mode & FALLOC_FL_PUNCH_HOLE); if (fc->no_fallocate) return -EOPNOTSUPP; - if (mode & FALLOC_FL_PUNCH_HOLE) { + if (lock_inode) { mutex_lock(&inode->i_mutex); - fuse_set_nowrite(inode); + if (mode & FALLOC_FL_PUNCH_HOLE) + fuse_set_nowrite(inode); } req = fuse_get_req_nopages(fc); @@ -2511,8 +2514,9 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, fuse_invalidate_attr(inode); out: - if (mode & FALLOC_FL_PUNCH_HOLE) { - fuse_release_nowrite(inode); + if (lock_inode) { + if (mode & FALLOC_FL_PUNCH_HOLE) + fuse_release_nowrite(inode); mutex_unlock(&inode->i_mutex); } diff --git a/fs/splice.c b/fs/splice.c index 9eca476227d5..d37431dd60a1 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1283,6 +1283,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, * @in: file to splice from * @ppos: input file offset * @out: file to splice to + * @opos: output file offset * @len: number of bytes to splice * @flags: splice modifier flags * diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h index f104af7cf437..d4f9fb4e53df 100644 --- a/include/asm-generic/mutex-dec.h +++ b/include/asm-generic/mutex-dec.h @@ -28,17 +28,15 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if - * it wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns. + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ static inline int -__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) +__mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(atomic_dec_return(count) < 0)) - return fail_fn(count); + return -1; return 0; } diff --git a/include/asm-generic/mutex-null.h b/include/asm-generic/mutex-null.h index e1bbbc72b6a2..61069ed334e2 100644 --- a/include/asm-generic/mutex-null.h +++ b/include/asm-generic/mutex-null.h @@ -11,7 +11,7 @@ #define _ASM_GENERIC_MUTEX_NULL_H #define __mutex_fastpath_lock(count, fail_fn) fail_fn(count) -#define __mutex_fastpath_lock_retval(count, fail_fn) fail_fn(count) +#define __mutex_fastpath_lock_retval(count) (-1) #define __mutex_fastpath_unlock(count, fail_fn) fail_fn(count) #define __mutex_fastpath_trylock(count, fail_fn) fail_fn(count) #define __mutex_slowpath_needs_to_unlock() 1 diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h index c04e0db8a2d6..f169ec064785 100644 --- a/include/asm-generic/mutex-xchg.h +++ b/include/asm-generic/mutex-xchg.h @@ -39,18 +39,16 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if it - * wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ static inline int -__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) +__mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(atomic_xchg(count, 0) != 1)) if (likely(atomic_xchg(count, -1) != 1)) - return fail_fn(count); + return -1; return 0; } diff --git a/include/linux/mutex-debug.h b/include/linux/mutex-debug.h index 731d77d6e155..4ac8b1977b73 100644 --- a/include/linux/mutex-debug.h +++ b/include/linux/mutex-debug.h @@ -3,6 +3,7 @@ #include <linux/linkage.h> #include <linux/lockdep.h> +#include <linux/debug_locks.h> /* * Mutexes - debugging helpers: diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 433da8a1a426..3793ed7feeeb 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -10,6 +10,7 @@ #ifndef __LINUX_MUTEX_H #define __LINUX_MUTEX_H +#include <asm/current.h> #include <linux/list.h> #include <linux/spinlock_types.h> #include <linux/linkage.h> @@ -77,6 +78,40 @@ struct mutex_waiter { #endif }; +struct ww_class { + atomic_long_t stamp; + struct lock_class_key acquire_key; + struct lock_class_key mutex_key; + const char *acquire_name; + const char *mutex_name; +}; + +struct ww_acquire_ctx { + struct task_struct *task; + unsigned long stamp; + unsigned acquired; +#ifdef CONFIG_DEBUG_MUTEXES + unsigned done_acquire; + struct ww_class *ww_class; + struct ww_mutex *contending_lock; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + unsigned deadlock_inject_interval; + unsigned deadlock_inject_countdown; +#endif +}; + +struct ww_mutex { + struct mutex base; + struct ww_acquire_ctx *ctx; +#ifdef CONFIG_DEBUG_MUTEXES + struct ww_class *ww_class; +#endif +}; + #ifdef CONFIG_DEBUG_MUTEXES # include <linux/mutex-debug.h> #else @@ -101,8 +136,11 @@ static inline void mutex_destroy(struct mutex *lock) {} #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ , .dep_map = { .name = #lockname } +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) \ + , .ww_class = &ww_class #else # define __DEP_MAP_MUTEX_INITIALIZER(lockname) +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) #endif #define __MUTEX_INITIALIZER(lockname) \ @@ -112,13 +150,49 @@ static inline void mutex_destroy(struct mutex *lock) {} __DEBUG_MUTEX_INITIALIZER(lockname) \ __DEP_MAP_MUTEX_INITIALIZER(lockname) } +#define __WW_CLASS_INITIALIZER(ww_class) \ + { .stamp = ATOMIC_LONG_INIT(0) \ + , .acquire_name = #ww_class "_acquire" \ + , .mutex_name = #ww_class "_mutex" } + +#define __WW_MUTEX_INITIALIZER(lockname, class) \ + { .base = { \__MUTEX_INITIALIZER(lockname) } \ + __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } + #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) +#define DEFINE_WW_CLASS(classname) \ + struct ww_class classname = __WW_CLASS_INITIALIZER(classname) + +#define DEFINE_WW_MUTEX(mutexname, ww_class) \ + struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class) + + extern void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); /** + * ww_mutex_init - initialize the w/w mutex + * @lock: the mutex to be initialized + * @ww_class: the w/w class the mutex should belong to + * + * Initialize the w/w mutex to unlocked state and associate it with the given + * class. + * + * It is not allowed to initialize an already locked mutex. + */ +static inline void ww_mutex_init(struct ww_mutex *lock, + struct ww_class *ww_class) +{ + __mutex_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key); + lock->ctx = NULL; +#ifdef CONFIG_DEBUG_MUTEXES + lock->ww_class = ww_class; +#endif +} + +/** * mutex_is_locked - is the mutex locked * @lock: the mutex to be queried * @@ -136,6 +210,7 @@ static inline int mutex_is_locked(struct mutex *lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass); extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); + extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); extern int __must_check mutex_lock_killable_nested(struct mutex *lock, @@ -147,7 +222,7 @@ extern int __must_check mutex_lock_killable_nested(struct mutex *lock, #define mutex_lock_nest_lock(lock, nest_lock) \ do { \ - typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) @@ -170,6 +245,292 @@ extern int __must_check mutex_lock_killable(struct mutex *lock); */ extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); + +/** + * ww_acquire_init - initialize a w/w acquire context + * @ctx: w/w acquire context to initialize + * @ww_class: w/w class of the context + * + * Initializes an context to acquire multiple mutexes of the given w/w class. + * + * Context-based w/w mutex acquiring can be done in any order whatsoever within + * a given lock class. Deadlocks will be detected and handled with the + * wait/wound logic. + * + * Mixing of context-based w/w mutex acquiring and single w/w mutex locking can + * result in undetected deadlocks and is so forbidden. Mixing different contexts + * for the same w/w class when acquiring mutexes can also result in undetected + * deadlocks, and is hence also forbidden. Both types of abuse will be caught by + * enabling CONFIG_PROVE_LOCKING. + * + * Nesting of acquire contexts for _different_ w/w classes is possible, subject + * to the usual locking rules between different lock classes. + * + * An acquire context must be released with ww_acquire_fini by the same task + * before the memory is freed. It is recommended to allocate the context itself + * on the stack. + */ +static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, + struct ww_class *ww_class) +{ + ctx->task = current; + ctx->stamp = atomic_long_inc_return(&ww_class->stamp); + ctx->acquired = 0; +#ifdef CONFIG_DEBUG_MUTEXES + ctx->ww_class = ww_class; + ctx->done_acquire = 0; + ctx->contending_lock = NULL; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + debug_check_no_locks_freed((void *)ctx, sizeof(*ctx)); + lockdep_init_map(&ctx->dep_map, ww_class->acquire_name, + &ww_class->acquire_key, 0); + mutex_acquire(&ctx->dep_map, 0, 0, _RET_IP_); +#endif +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + ctx->deadlock_inject_interval = 1; + ctx->deadlock_inject_countdown = ctx->stamp & 0xf; +#endif +} + +/** + * ww_acquire_done - marks the end of the acquire phase + * @ctx: the acquire context + * + * Marks the end of the acquire phase, any further w/w mutex lock calls using + * this context are forbidden. + * + * Calling this function is optional, it is just useful to document w/w mutex + * code and clearly designated the acquire phase from actually using the locked + * data structures. + */ +static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + lockdep_assert_held(ctx); + + DEBUG_LOCKS_WARN_ON(ctx->done_acquire); + ctx->done_acquire = 1; +#endif +} + +/** + * ww_acquire_fini - releases a w/w acquire context + * @ctx: the acquire context to free + * + * Releases a w/w acquire context. This must be called _after_ all acquired w/w + * mutexes have been released with ww_mutex_unlock. + */ +static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + mutex_release(&ctx->dep_map, 0, _THIS_IP_); + + DEBUG_LOCKS_WARN_ON(ctx->acquired); + if (!config_enabled(CONFIG_PROVE_LOCKING)) + /* + * lockdep will normally handle this, + * but fail without anyway + */ + ctx->done_acquire = 1; + + if (!config_enabled(CONFIG_DEBUG_LOCK_ALLOC)) + /* ensure ww_acquire_fini will still fail if called twice */ + ctx->acquired = ~0U; +#endif +} + +extern int __must_check __ww_mutex_lock(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); +extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); + +/** + * ww_mutex_lock - acquire the w/w mutex + * @lock: the mutex to be acquired + * @ctx: w/w acquire context, or NULL to acquire only a single lock. + * + * Lock the w/w mutex exclusively for this task. + * + * Deadlocks within a given w/w class of locks are detected and handled with the + * wait/wound algorithm. If the lock isn't immediately avaiable this function + * will either sleep until it is (wait case). Or it selects the current context + * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * same lock with the same context twice is also detected and signalled by + * returning -EALREADY. Returns 0 if the mutex was successfully acquired. + * + * In the wound case the caller must release all currently held w/w mutexes for + * the given context and then wait for this contending lock to be available by + * calling ww_mutex_lock_slow. Alternatively callers can opt to not acquire this + * lock and proceed with trying to acquire further w/w mutexes (e.g. when + * scanning through lru lists trying to free resources). + * + * The mutex must later on be released by the same task that + * acquired it. The task may not exit without first unlocking the mutex. Also, + * kernel memory where the mutex resides must not be freed with the mutex still + * locked. The mutex must first be initialized (or statically defined) before it + * can be locked. memset()-ing the mutex to 0 is not allowed. The mutex must be + * of the same w/w lock class as was used to initialize the acquire context. + * + * A mutex acquired with this function must be released with ww_mutex_unlock. + */ +static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + if (ctx) + return __ww_mutex_lock(lock, ctx); + else { + mutex_lock(&lock->base); + return 0; + } +} + +/** + * ww_mutex_lock_interruptible - acquire the w/w mutex, interruptible + * @lock: the mutex to be acquired + * @ctx: w/w acquire context + * + * Lock the w/w mutex exclusively for this task. + * + * Deadlocks within a given w/w class of locks are detected and handled with the + * wait/wound algorithm. If the lock isn't immediately avaiable this function + * will either sleep until it is (wait case). Or it selects the current context + * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * same lock with the same context twice is also detected and signalled by + * returning -EALREADY. Returns 0 if the mutex was successfully acquired. If a + * signal arrives while waiting for the lock then this function returns -EINTR. + * + * In the wound case the caller must release all currently held w/w mutexes for + * the given context and then wait for this contending lock to be available by + * calling ww_mutex_lock_slow_interruptible. Alternatively callers can opt to + * not acquire this lock and proceed with trying to acquire further w/w mutexes + * (e.g. when scanning through lru lists trying to free resources). + * + * The mutex must later on be released by the same task that + * acquired it. The task may not exit without first unlocking the mutex. Also, + * kernel memory where the mutex resides must not be freed with the mutex still + * locked. The mutex must first be initialized (or statically defined) before it + * can be locked. memset()-ing the mutex to 0 is not allowed. The mutex must be + * of the same w/w lock class as was used to initialize the acquire context. + * + * A mutex acquired with this function must be released with ww_mutex_unlock. + */ +static inline int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + if (ctx) + return __ww_mutex_lock_interruptible(lock, ctx); + else + return mutex_lock_interruptible(&lock->base); +} + +/** + * ww_mutex_lock_slow - slowpath acquiring of the w/w mutex + * @lock: the mutex to be acquired + * @ctx: w/w acquire context + * + * Acquires a w/w mutex with the given context after a wound case. This function + * will sleep until the lock becomes available. + * + * The caller must have released all w/w mutexes already acquired with the + * context and then call this function on the contended lock. + * + * Afterwards the caller may continue to (re)acquire the other w/w mutexes it + * needs with ww_mutex_lock. Note that the -EALREADY return code from + * ww_mutex_lock can be used to avoid locking this contended mutex twice. + * + * It is forbidden to call this function with any other w/w mutexes associated + * with the context held. It is forbidden to call this on anything else than the + * contending mutex. + * + * Note that the slowpath lock acquiring can also be done by calling + * ww_mutex_lock directly. This function here is simply to help w/w mutex + * locking code readability by clearly denoting the slowpath. + */ +static inline void +ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!ctx->contending_lock); +#endif + ret = ww_mutex_lock(lock, ctx); + (void)ret; +} + +/** + * ww_mutex_lock_slow_interruptible - slowpath acquiring of the w/w mutex, + * interruptible + * @lock: the mutex to be acquired + * @ctx: w/w acquire context + * + * Acquires a w/w mutex with the given context after a wound case. This function + * will sleep until the lock becomes available and returns 0 when the lock has + * been acquired. If a signal arrives while waiting for the lock then this + * function returns -EINTR. + * + * The caller must have released all w/w mutexes already acquired with the + * context and then call this function on the contended lock. + * + * Afterwards the caller may continue to (re)acquire the other w/w mutexes it + * needs with ww_mutex_lock. Note that the -EALREADY return code from + * ww_mutex_lock can be used to avoid locking this contended mutex twice. + * + * It is forbidden to call this function with any other w/w mutexes associated + * with the given context held. It is forbidden to call this on anything else + * than the contending mutex. + * + * Note that the slowpath lock acquiring can also be done by calling + * ww_mutex_lock_interruptible directly. This function here is simply to help + * w/w mutex locking code readability by clearly denoting the slowpath. + */ +static inline int __must_check +ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!ctx->contending_lock); +#endif + return ww_mutex_lock_interruptible(lock, ctx); +} + +extern void ww_mutex_unlock(struct ww_mutex *lock); + +/** + * ww_mutex_trylock - tries to acquire the w/w mutex without acquire context + * @lock: mutex to lock + * + * Trylocks a mutex without acquire context, so no deadlock detection is + * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. + */ +static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) +{ + return mutex_trylock(&lock->base); +} + +/*** + * ww_mutex_destroy - mark a w/w mutex unusable + * @lock: the mutex to be destroyed + * + * This function marks the mutex uninitialized, and any subsequent + * use of the mutex is forbidden. The mutex must not be locked when + * this function is called. + */ +static inline void ww_mutex_destroy(struct ww_mutex *lock) +{ + mutex_destroy(&lock->base); +} + +/** + * ww_mutex_is_locked - is the w/w mutex locked + * @lock: the mutex to be queried + * + * Returns 1 if the mutex is locked, 0 if unlocked. + */ +static inline bool ww_mutex_is_locked(struct ww_mutex *lock) +{ + return mutex_is_locked(&lock->base); +} + extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); #ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX diff --git a/kernel/mutex.c b/kernel/mutex.c index ad53a664f113..e581ada5faf4 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -254,16 +254,165 @@ void __sched mutex_unlock(struct mutex *lock) EXPORT_SYMBOL(mutex_unlock); +/** + * ww_mutex_unlock - release the w/w mutex + * @lock: the mutex to be released + * + * Unlock a mutex that has been locked by this task previously with any of the + * ww_mutex_lock* functions (with or without an acquire context). It is + * forbidden to release the locks after releasing the acquire context. + * + * This function must not be used in interrupt context. Unlocking + * of a unlocked mutex is not allowed. + */ +void __sched ww_mutex_unlock(struct ww_mutex *lock) +{ + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + if (lock->ctx) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); +#endif + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + +#ifndef CONFIG_DEBUG_MUTEXES + /* + * When debugging is enabled we must not clear the owner before time, + * the slow path will always be taken, and that clears the owner field + * after verifying that it was indeed current. + */ + mutex_clear_owner(&lock->base); +#endif + __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath); +} +EXPORT_SYMBOL(ww_mutex_unlock); + +static inline int __sched +__mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); + + if (!hold_ctx) + return 0; + + if (unlikely(ctx == hold_ctx)) + return -EALREADY; + + if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && + (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} + +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); + + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } + + /* + * Naughty, using a different class will lead to undefined behavior! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +/* + * after acquiring lock with fastpath or when we lost out in contested + * slowpath, set ctx and wake up any waiters so they can recheck. + * + * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, + * as the fastpath and opportunistic spinning are disabled in that case. + */ +static __always_inline void +ww_mutex_set_context_fastpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + unsigned long flags; + struct mutex_waiter *cur; + + ww_mutex_lock_acquired(lock, ctx); + + lock->ctx = ctx; + + /* + * The lock->ctx update should be visible on all cores before + * the atomic read is done, otherwise contended waiters might be + * missed. The contended waiters will either see ww_ctx == NULL + * and keep spinning, or it will acquire wait_lock, add itself + * to waiter list and sleep. + */ + smp_mb(); /* ^^^ */ + + /* + * Check if lock is contended, if not there is nobody to wake up + */ + if (likely(atomic_read(&lock->base.count) == 0)) + return; + + /* + * Uh oh, we raced in fastpath, wake up everyone in this case, + * so they can see the new lock->ctx. + */ + spin_lock_mutex(&lock->base.wait_lock, flags); + list_for_each_entry(cur, &lock->base.wait_list, list) { + debug_mutex_wake_waiter(&lock->base, cur); + wake_up_process(cur->task); + } + spin_unlock_mutex(&lock->base.wait_lock, flags); +} + /* * Lock a mutex (possibly interruptible), slowpath: */ -static inline int __sched +static __always_inline int __sched __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, - struct lockdep_map *nest_lock, unsigned long ip) + struct lockdep_map *nest_lock, unsigned long ip, + struct ww_acquire_ctx *ww_ctx) { struct task_struct *task = current; struct mutex_waiter waiter; unsigned long flags; + int ret; preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); @@ -298,6 +447,22 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, struct task_struct *owner; struct mspin_node node; + if (!__builtin_constant_p(ww_ctx == NULL) && ww_ctx->acquired > 0) { + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + /* + * If ww->ctx is set the contents are undefined, only + * by acquiring wait_lock there is a guarantee that + * they are not invalid when reading. + * + * As such, when deadlock detection needs to be + * performed the optimistic spinning cannot be done. + */ + if (ACCESS_ONCE(ww->ctx)) + break; + } + /* * If there's an owner, wait for it to either * release the lock or go to sleep. @@ -312,6 +477,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if ((atomic_read(&lock->count) == 1) && (atomic_cmpxchg(&lock->count, 1, 0) == 1)) { lock_acquired(&lock->dep_map, ip); + if (!__builtin_constant_p(ww_ctx == NULL)) { + struct ww_mutex *ww; + ww = container_of(lock, struct ww_mutex, base); + + ww_mutex_set_context_fastpath(ww, ww_ctx); + } + mutex_set_owner(lock); mspin_unlock(MLOCK(lock), &node); preempt_enable(); @@ -371,15 +543,16 @@ slowpath: * TASK_UNINTERRUPTIBLE case.) */ if (unlikely(signal_pending_state(state, task))) { - mutex_remove_waiter(lock, &waiter, - task_thread_info(task)); - mutex_release(&lock->dep_map, 1, ip); - spin_unlock_mutex(&lock->wait_lock, flags); + ret = -EINTR; + goto err; + } - debug_mutex_free_waiter(&waiter); - preempt_enable(); - return -EINTR; + if (!__builtin_constant_p(ww_ctx == NULL) && ww_ctx->acquired > 0) { + ret = __mutex_lock_check_stamp(lock, ww_ctx); + if (ret) + goto err; } + __set_task_state(task, state); /* didn't get the lock, go to sleep: */ @@ -394,6 +567,30 @@ done: mutex_remove_waiter(lock, &waiter, current_thread_info()); mutex_set_owner(lock); + if (!__builtin_constant_p(ww_ctx == NULL)) { + struct ww_mutex *ww = container_of(lock, + struct ww_mutex, + base); + struct mutex_waiter *cur; + + /* + * This branch gets optimized out for the common case, + * and is only important for ww_mutex_lock. + */ + + ww_mutex_lock_acquired(ww, ww_ctx); + ww->ctx = ww_ctx; + + /* + * Give any possible sleeping processes the chance to wake up, + * so they can recheck if they have to back off. + */ + list_for_each_entry(cur, &lock->wait_list, list) { + debug_mutex_wake_waiter(lock, cur); + wake_up_process(cur->task); + } + } + /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); @@ -404,6 +601,14 @@ done: preempt_enable(); return 0; + +err: + mutex_remove_waiter(lock, &waiter, task_thread_info(task)); + spin_unlock_mutex(&lock->wait_lock, flags); + debug_mutex_free_waiter(&waiter); + mutex_release(&lock->dep_map, 1, ip); + preempt_enable(); + return ret; } #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -411,7 +616,8 @@ void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, + subclass, NULL, _RET_IP_, NULL); } EXPORT_SYMBOL_GPL(mutex_lock_nested); @@ -420,7 +626,8 @@ void __sched _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) { might_sleep(); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, + 0, nest, _RET_IP_, NULL); } EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); @@ -429,7 +636,8 @@ int __sched mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); - return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); + return __mutex_lock_common(lock, TASK_KILLABLE, + subclass, NULL, _RET_IP_, NULL); } EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); @@ -438,10 +646,68 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, - subclass, NULL, _RET_IP_); + subclass, NULL, _RET_IP_, NULL); } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); + +static inline int +ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + unsigned tmp; + + if (ctx->deadlock_inject_countdown-- == 0) { + tmp = ctx->deadlock_inject_interval; + if (tmp > UINT_MAX/4) + tmp = UINT_MAX; + else + tmp = tmp*2 + tmp + tmp/2; + + ctx->deadlock_inject_interval = tmp; + ctx->deadlock_inject_countdown = tmp; + ctx->contending_lock = lock; + + ww_mutex_unlock(lock); + + return -EDEADLK; + } +#endif + + return 0; +} + +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, + 0, &ctx->dep_map, _RET_IP_, ctx); + if (!ret && ctx->acquired > 0) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock); + +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, + 0, &ctx->dep_map, _RET_IP_, ctx); + + if (!ret && ctx->acquired > 0) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); + #endif /* @@ -494,10 +760,10 @@ __mutex_unlock_slowpath(atomic_t *lock_count) * mutex_lock_interruptible() and mutex_trylock(). */ static noinline int __sched -__mutex_lock_killable_slowpath(atomic_t *lock_count); +__mutex_lock_killable_slowpath(struct mutex *lock); static noinline int __sched -__mutex_lock_interruptible_slowpath(atomic_t *lock_count); +__mutex_lock_interruptible_slowpath(struct mutex *lock); /** * mutex_lock_interruptible - acquire the mutex, interruptible @@ -515,12 +781,12 @@ int __sched mutex_lock_interruptible(struct mutex *lock) int ret; might_sleep(); - ret = __mutex_fastpath_lock_retval - (&lock->count, __mutex_lock_interruptible_slowpath); - if (!ret) + ret = __mutex_fastpath_lock_retval(&lock->count); + if (likely(!ret)) { mutex_set_owner(lock); - - return ret; + return 0; + } else + return __mutex_lock_interruptible_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_interruptible); @@ -530,12 +796,12 @@ int __sched mutex_lock_killable(struct mutex *lock) int ret; might_sleep(); - ret = __mutex_fastpath_lock_retval - (&lock->count, __mutex_lock_killable_slowpath); - if (!ret) + ret = __mutex_fastpath_lock_retval(&lock->count); + if (likely(!ret)) { mutex_set_owner(lock); - - return ret; + return 0; + } else + return __mutex_lock_killable_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_killable); @@ -544,24 +810,39 @@ __mutex_lock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, + NULL, _RET_IP_, NULL); } static noinline int __sched -__mutex_lock_killable_slowpath(atomic_t *lock_count) +__mutex_lock_killable_slowpath(struct mutex *lock) { - struct mutex *lock = container_of(lock_count, struct mutex, count); + return __mutex_lock_common(lock, TASK_KILLABLE, 0, + NULL, _RET_IP_, NULL); +} - return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_); +static noinline int __sched +__mutex_lock_interruptible_slowpath(struct mutex *lock) +{ + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, + NULL, _RET_IP_, NULL); } static noinline int __sched -__mutex_lock_interruptible_slowpath(atomic_t *lock_count) +__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - struct mutex *lock = container_of(lock_count, struct mutex, count); + return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx); +} - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); +static noinline int __sched +__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx); } + #endif /* @@ -617,6 +898,45 @@ int __sched mutex_trylock(struct mutex *lock) } EXPORT_SYMBOL(mutex_trylock); +#ifndef CONFIG_DEBUG_LOCK_ALLOC +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __mutex_fastpath_lock_retval(&lock->base.count); + + if (likely(!ret)) { + ww_mutex_set_context_fastpath(lock, ctx); + mutex_set_owner(&lock->base); + } else + ret = __ww_mutex_lock_slowpath(lock, ctx); + return ret; +} +EXPORT_SYMBOL(__ww_mutex_lock); + +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __mutex_fastpath_lock_retval(&lock->base.count); + + if (likely(!ret)) { + ww_mutex_set_context_fastpath(lock, ctx); + mutex_set_owner(&lock->base); + } else + ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx); + return ret; +} +EXPORT_SYMBOL(__ww_mutex_lock_interruptible); + +#endif + /** * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 * @cnt: the atomic which we are to dec diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 566cf2bc08ea..7154f799541a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -547,6 +547,19 @@ config DEBUG_MUTEXES This feature allows mutex semantics violations to be detected and reported. +config DEBUG_WW_MUTEX_SLOWPATH + bool "Wait/wound mutex debugging: Slowpath testing" + depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT + select DEBUG_LOCK_ALLOC + select DEBUG_SPINLOCK + select DEBUG_MUTEXES + help + This feature enables slowpath testing for w/w mutex users by + injecting additional -EDEADLK wound/backoff cases. Together with + the full mutex checks enabled with (CONFIG_PROVE_LOCKING) this + will test all possible w/w mutex interface abuse with the + exception of simply not acquiring all the required locks. + config DEBUG_LOCK_ALLOC bool "Lock debugging: detect incorrect freeing of live locks" depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT diff --git a/lib/debug_locks.c b/lib/debug_locks.c index f2fa60c59343..96c4c633d95e 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -30,6 +30,7 @@ EXPORT_SYMBOL_GPL(debug_locks); * a locking bug is detected. */ int debug_locks_silent; +EXPORT_SYMBOL_GPL(debug_locks_silent); /* * Generic 'turn off all lock debugging' function: @@ -44,3 +45,4 @@ int debug_locks_off(void) } return 0; } +EXPORT_SYMBOL_GPL(debug_locks_off); diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index c3eb261a7df3..aad024dde3c4 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -26,6 +26,8 @@ */ static unsigned int debug_locks_verbose; +static DEFINE_WW_CLASS(ww_lockdep); + static int __init setup_debug_locks_verbose(char *str) { get_option(&str, &debug_locks_verbose); @@ -42,6 +44,10 @@ __setup("debug_locks_verbose=", setup_debug_locks_verbose); #define LOCKTYPE_RWLOCK 0x2 #define LOCKTYPE_MUTEX 0x4 #define LOCKTYPE_RWSEM 0x8 +#define LOCKTYPE_WW 0x10 + +static struct ww_acquire_ctx t, t2; +static struct ww_mutex o, o2, o3; /* * Normal standalone locks, for the circular and irq-context @@ -193,6 +199,20 @@ static void init_shared_classes(void) #define RSU(x) up_read(&rwsem_##x) #define RWSI(x) init_rwsem(&rwsem_##x) +#ifndef CONFIG_DEBUG_WW_MUTEX_SLOWPATH +#define WWAI(x) ww_acquire_init(x, &ww_lockdep) +#else +#define WWAI(x) do { ww_acquire_init(x, &ww_lockdep); (x)->deadlock_inject_countdown = ~0U; } while (0) +#endif +#define WWAD(x) ww_acquire_done(x) +#define WWAF(x) ww_acquire_fini(x) + +#define WWL(x, c) ww_mutex_lock(x, c) +#define WWT(x) ww_mutex_trylock(x) +#define WWL1(x) ww_mutex_lock(x, NULL) +#define WWU(x) ww_mutex_unlock(x) + + #define LOCK_UNLOCK_2(x,y) LOCK(x); LOCK(y); UNLOCK(y); UNLOCK(x) /* @@ -894,11 +914,13 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft) # define I_RWLOCK(x) lockdep_reset_lock(&rwlock_##x.dep_map) # define I_MUTEX(x) lockdep_reset_lock(&mutex_##x.dep_map) # define I_RWSEM(x) lockdep_reset_lock(&rwsem_##x.dep_map) +# define I_WW(x) lockdep_reset_lock(&x.dep_map) #else # define I_SPINLOCK(x) # define I_RWLOCK(x) # define I_MUTEX(x) # define I_RWSEM(x) +# define I_WW(x) #endif #define I1(x) \ @@ -920,11 +942,20 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft) static void reset_locks(void) { local_irq_disable(); + lockdep_free_key_range(&ww_lockdep.acquire_key, 1); + lockdep_free_key_range(&ww_lockdep.mutex_key, 1); + I1(A); I1(B); I1(C); I1(D); I1(X1); I1(X2); I1(Y1); I1(Y2); I1(Z1); I1(Z2); + I_WW(t); I_WW(t2); I_WW(o.base); I_WW(o2.base); I_WW(o3.base); lockdep_reset(); I2(A); I2(B); I2(C); I2(D); init_shared_classes(); + + ww_mutex_init(&o, &ww_lockdep); ww_mutex_init(&o2, &ww_lockdep); ww_mutex_init(&o3, &ww_lockdep); + memset(&t, 0, sizeof(t)); memset(&t2, 0, sizeof(t2)); + memset(&ww_lockdep.acquire_key, 0, sizeof(ww_lockdep.acquire_key)); + memset(&ww_lockdep.mutex_key, 0, sizeof(ww_lockdep.mutex_key)); local_irq_enable(); } @@ -938,7 +969,6 @@ static int unexpected_testcase_failures; static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask) { unsigned long saved_preempt_count = preempt_count(); - int expected_failure = 0; WARN_ON(irqs_disabled()); @@ -947,25 +977,17 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask) * Filter out expected failures: */ #ifndef CONFIG_PROVE_LOCKING - if ((lockclass_mask & LOCKTYPE_SPIN) && debug_locks != expected) - expected_failure = 1; - if ((lockclass_mask & LOCKTYPE_RWLOCK) && debug_locks != expected) - expected_failure = 1; - if ((lockclass_mask & LOCKTYPE_MUTEX) && debug_locks != expected) - expected_failure = 1; - if ((lockclass_mask & LOCKTYPE_RWSEM) && debug_locks != expected) - expected_failure = 1; + if (expected == FAILURE && debug_locks) { + expected_testcase_failures++; + printk("failed|"); + } + else #endif if (debug_locks != expected) { - if (expected_failure) { - expected_testcase_failures++; - printk("failed|"); - } else { - unexpected_testcase_failures++; - - printk("FAILED|"); - dump_stack(); - } + unexpected_testcase_failures++; + printk("FAILED|"); + + dump_stack(); } else { testcase_successes++; printk(" ok |"); @@ -1108,6 +1130,666 @@ static inline void print_testname(const char *testname) DO_TESTCASE_6IRW(desc, name, 312); \ DO_TESTCASE_6IRW(desc, name, 321); +static void ww_test_fail_acquire(void) +{ + int ret; + + WWAI(&t); + t.stamp++; + + ret = WWL(&o, &t); + + if (WARN_ON(!o.ctx) || + WARN_ON(ret)) + return; + + /* No lockdep test, pure API */ + ret = WWL(&o, &t); + WARN_ON(ret != -EALREADY); + + ret = WWT(&o); + WARN_ON(ret); + + t2 = t; + t2.stamp++; + ret = WWL(&o, &t2); + WARN_ON(ret != -EDEADLK); + WWU(&o); + + if (WWT(&o)) + WWU(&o); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + else + DEBUG_LOCKS_WARN_ON(1); +#endif +} + +static void ww_test_normal(void) +{ + int ret; + + WWAI(&t); + + /* + * None of the ww_mutex codepaths should be taken in the 'normal' + * mutex calls. The easiest way to verify this is by using the + * normal mutex calls, and making sure o.ctx is unmodified. + */ + + /* mutex_lock (and indirectly, mutex_lock_nested) */ + o.ctx = (void *)~0UL; + mutex_lock(&o.base); + mutex_unlock(&o.base); + WARN_ON(o.ctx != (void *)~0UL); + + /* mutex_lock_interruptible (and *_nested) */ + o.ctx = (void *)~0UL; + ret = mutex_lock_interruptible(&o.base); + if (!ret) + mutex_unlock(&o.base); + else + WARN_ON(1); + WARN_ON(o.ctx != (void *)~0UL); + + /* mutex_lock_killable (and *_nested) */ + o.ctx = (void *)~0UL; + ret = mutex_lock_killable(&o.base); + if (!ret) + mutex_unlock(&o.base); + else + WARN_ON(1); + WARN_ON(o.ctx != (void *)~0UL); + + /* trylock, succeeding */ + o.ctx = (void *)~0UL; + ret = mutex_trylock(&o.base); + WARN_ON(!ret); + if (ret) + mutex_unlock(&o.base); + else + WARN_ON(1); + WARN_ON(o.ctx != (void *)~0UL); + + /* trylock, failing */ + o.ctx = (void *)~0UL; + mutex_lock(&o.base); + ret = mutex_trylock(&o.base); + WARN_ON(ret); + mutex_unlock(&o.base); + WARN_ON(o.ctx != (void *)~0UL); + + /* nest_lock */ + o.ctx = (void *)~0UL; + mutex_lock_nest_lock(&o.base, &t); + mutex_unlock(&o.base); + WARN_ON(o.ctx != (void *)~0UL); +} + +static void ww_test_two_contexts(void) +{ + WWAI(&t); + WWAI(&t2); +} + +static void ww_test_diff_class(void) +{ + WWAI(&t); +#ifdef CONFIG_DEBUG_MUTEXES + t.ww_class = NULL; +#endif + WWL(&o, &t); +} + +static void ww_test_context_done_twice(void) +{ + WWAI(&t); + WWAD(&t); + WWAD(&t); + WWAF(&t); +} + +static void ww_test_context_unlock_twice(void) +{ + WWAI(&t); + WWAD(&t); + WWAF(&t); + WWAF(&t); +} + +static void ww_test_context_fini_early(void) +{ + WWAI(&t); + WWL(&o, &t); + WWAD(&t); + WWAF(&t); +} + +static void ww_test_context_lock_after_done(void) +{ + WWAI(&t); + WWAD(&t); + WWL(&o, &t); +} + +static void ww_test_object_unlock_twice(void) +{ + WWL1(&o); + WWU(&o); + WWU(&o); +} + +static void ww_test_object_lock_unbalanced(void) +{ + WWAI(&t); + WWL(&o, &t); + t.acquired = 0; + WWU(&o); + WWAF(&t); +} + +static void ww_test_object_lock_stale_context(void) +{ + WWAI(&t); + o.ctx = &t2; + WWL(&o, &t); +} + +static void ww_test_edeadlk_normal(void) +{ + int ret; + + mutex_lock(&o2.base); + o2.ctx = &t2; + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + o2.ctx = NULL; + mutex_acquire(&o2.base.dep_map, 0, 1, _THIS_IP_); + mutex_unlock(&o2.base); + WWU(&o); + + WWL(&o2, &t); +} + +static void ww_test_edeadlk_normal_slow(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + o2.ctx = NULL; + mutex_acquire(&o2.base.dep_map, 0, 1, _THIS_IP_); + mutex_unlock(&o2.base); + WWU(&o); + + ww_mutex_lock_slow(&o2, &t); +} + +static void ww_test_edeadlk_no_unlock(void) +{ + int ret; + + mutex_lock(&o2.base); + o2.ctx = &t2; + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + o2.ctx = NULL; + mutex_acquire(&o2.base.dep_map, 0, 1, _THIS_IP_); + mutex_unlock(&o2.base); + + WWL(&o2, &t); +} + +static void ww_test_edeadlk_no_unlock_slow(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + o2.ctx = NULL; + mutex_acquire(&o2.base.dep_map, 0, 1, _THIS_IP_); + mutex_unlock(&o2.base); + + ww_mutex_lock_slow(&o2, &t); +} + +static void ww_test_edeadlk_acquire_more(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + ret = WWL(&o3, &t); +} + +static void ww_test_edeadlk_acquire_more_slow(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + ww_mutex_lock_slow(&o3, &t); +} + +static void ww_test_edeadlk_acquire_more_edeadlk(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + mutex_lock(&o3.base); + mutex_release(&o3.base.dep_map, 1, _THIS_IP_); + o3.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + ret = WWL(&o3, &t); + WARN_ON(ret != -EDEADLK); +} + +static void ww_test_edeadlk_acquire_more_edeadlk_slow(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + mutex_lock(&o3.base); + mutex_release(&o3.base.dep_map, 1, _THIS_IP_); + o3.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + + ww_mutex_lock_slow(&o3, &t); +} + +static void ww_test_edeadlk_acquire_wrong(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + if (!ret) + WWU(&o2); + + WWU(&o); + + ret = WWL(&o3, &t); +} + +static void ww_test_edeadlk_acquire_wrong_slow(void) +{ + int ret; + + mutex_lock(&o2.base); + mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + o2.ctx = &t2; + + WWAI(&t); + t2 = t; + t2.stamp--; + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret != -EDEADLK); + if (!ret) + WWU(&o2); + + WWU(&o); + + ww_mutex_lock_slow(&o3, &t); +} + +static void ww_test_spin_nest_unlocked(void) +{ + raw_spin_lock_nest_lock(&lock_A, &o.base); + U(A); +} + +static void ww_test_unneeded_slow(void) +{ + WWAI(&t); + + ww_mutex_lock_slow(&o, &t); +} + +static void ww_test_context_block(void) +{ + int ret; + + WWAI(&t); + + ret = WWL(&o, &t); + WARN_ON(ret); + WWL1(&o2); +} + +static void ww_test_context_try(void) +{ + int ret; + + WWAI(&t); + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWT(&o2); + WARN_ON(!ret); + WWU(&o2); + WWU(&o); +} + +static void ww_test_context_context(void) +{ + int ret; + + WWAI(&t); + + ret = WWL(&o, &t); + WARN_ON(ret); + + ret = WWL(&o2, &t); + WARN_ON(ret); + + WWU(&o2); + WWU(&o); +} + +static void ww_test_try_block(void) +{ + bool ret; + + ret = WWT(&o); + WARN_ON(!ret); + + WWL1(&o2); + WWU(&o2); + WWU(&o); +} + +static void ww_test_try_try(void) +{ + bool ret; + + ret = WWT(&o); + WARN_ON(!ret); + ret = WWT(&o2); + WARN_ON(!ret); + WWU(&o2); + WWU(&o); +} + +static void ww_test_try_context(void) +{ + int ret; + + ret = WWT(&o); + WARN_ON(!ret); + + WWAI(&t); + + ret = WWL(&o2, &t); + WARN_ON(ret); +} + +static void ww_test_block_block(void) +{ + WWL1(&o); + WWL1(&o2); +} + +static void ww_test_block_try(void) +{ + bool ret; + + WWL1(&o); + ret = WWT(&o2); + WARN_ON(!ret); +} + +static void ww_test_block_context(void) +{ + int ret; + + WWL1(&o); + WWAI(&t); + + ret = WWL(&o2, &t); + WARN_ON(ret); +} + +static void ww_test_spin_block(void) +{ + L(A); + U(A); + + WWL1(&o); + L(A); + U(A); + WWU(&o); + + L(A); + WWL1(&o); + WWU(&o); + U(A); +} + +static void ww_test_spin_try(void) +{ + bool ret; + + L(A); + U(A); + + ret = WWT(&o); + WARN_ON(!ret); + L(A); + U(A); + WWU(&o); + + L(A); + ret = WWT(&o); + WARN_ON(!ret); + WWU(&o); + U(A); +} + +static void ww_test_spin_context(void) +{ + int ret; + + L(A); + U(A); + + WWAI(&t); + + ret = WWL(&o, &t); + WARN_ON(ret); + L(A); + U(A); + WWU(&o); + + L(A); + ret = WWL(&o, &t); + WARN_ON(ret); + WWU(&o); + U(A); +} + +static void ww_tests(void) +{ + printk(" --------------------------------------------------------------------------\n"); + printk(" | Wound/wait tests |\n"); + printk(" ---------------------\n"); + + print_testname("ww api failures"); + dotest(ww_test_fail_acquire, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_normal, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_unneeded_slow, FAILURE, LOCKTYPE_WW); + printk("\n"); + + print_testname("ww contexts mixing"); + dotest(ww_test_two_contexts, FAILURE, LOCKTYPE_WW); + dotest(ww_test_diff_class, FAILURE, LOCKTYPE_WW); + printk("\n"); + + print_testname("finishing ww context"); + dotest(ww_test_context_done_twice, FAILURE, LOCKTYPE_WW); + dotest(ww_test_context_unlock_twice, FAILURE, LOCKTYPE_WW); + dotest(ww_test_context_fini_early, FAILURE, LOCKTYPE_WW); + dotest(ww_test_context_lock_after_done, FAILURE, LOCKTYPE_WW); + printk("\n"); + + print_testname("locking mismatches"); + dotest(ww_test_object_unlock_twice, FAILURE, LOCKTYPE_WW); + dotest(ww_test_object_lock_unbalanced, FAILURE, LOCKTYPE_WW); + dotest(ww_test_object_lock_stale_context, FAILURE, LOCKTYPE_WW); + printk("\n"); + + print_testname("EDEADLK handling"); + dotest(ww_test_edeadlk_normal, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_edeadlk_normal_slow, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_edeadlk_no_unlock, FAILURE, LOCKTYPE_WW); + dotest(ww_test_edeadlk_no_unlock_slow, FAILURE, LOCKTYPE_WW); + dotest(ww_test_edeadlk_acquire_more, FAILURE, LOCKTYPE_WW); + dotest(ww_test_edeadlk_acquire_more_slow, FAILURE, LOCKTYPE_WW); + dotest(ww_test_edeadlk_acquire_more_edeadlk, FAILURE, LOCKTYPE_WW); + dotest(ww_test_edeadlk_acquire_more_edeadlk_slow, FAILURE, LOCKTYPE_WW); + dotest(ww_test_edeadlk_acquire_wrong, FAILURE, LOCKTYPE_WW); + dotest(ww_test_edeadlk_acquire_wrong_slow, FAILURE, LOCKTYPE_WW); + printk("\n"); + + print_testname("spinlock nest unlocked"); + dotest(ww_test_spin_nest_unlocked, FAILURE, LOCKTYPE_WW); + printk("\n"); + + printk(" -----------------------------------------------------\n"); + printk(" |block | try |context|\n"); + printk(" -----------------------------------------------------\n"); + + print_testname("context"); + dotest(ww_test_context_block, FAILURE, LOCKTYPE_WW); + dotest(ww_test_context_try, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_context_context, SUCCESS, LOCKTYPE_WW); + printk("\n"); + + print_testname("try"); + dotest(ww_test_try_block, FAILURE, LOCKTYPE_WW); + dotest(ww_test_try_try, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_try_context, FAILURE, LOCKTYPE_WW); + printk("\n"); + + print_testname("block"); + dotest(ww_test_block_block, FAILURE, LOCKTYPE_WW); + dotest(ww_test_block_try, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_block_context, FAILURE, LOCKTYPE_WW); + printk("\n"); + + print_testname("spinlock"); + dotest(ww_test_spin_block, FAILURE, LOCKTYPE_WW); + dotest(ww_test_spin_try, SUCCESS, LOCKTYPE_WW); + dotest(ww_test_spin_context, FAILURE, LOCKTYPE_WW); + printk("\n"); +} void locking_selftest(void) { @@ -1188,6 +1870,8 @@ void locking_selftest(void) DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); + ww_tests(); + if (unexpected_testcase_failures) { printk("-----------------------------------------------------------------\n"); debug_locks = 0; |