Linaro-mm-sig July 2013

linaro-mm-sig@lists.linaro.org

5 participants
6 discussions

[PATCH v3 0/2] Device Tree support for CMA (Contiguous Memory Allocator)

by Marek Szyprowski

Hello, This is a third version of my proposal for device tree integration for Contiguous Memory Allocator. Over 2 month has passed from the time I've posted the second version, but now some things about using /chosen device tree node has been clarified, so I expect to get this code merged soon this time. Just a few words for those who see this code for the first time: The proposed bindings allows to define contiguous memory regions of specified base address and size. Then, the defined regions can be assigned to the given device(s) by adding a property with a phanle to the defined contiguous memory region. From the device tree perspective that's all. Once the bindings are added, all the memory allocations from dma-mapping subsystem will be served from the defined contiguous memory regions. Contiguous Memory Allocator is a framework, which lets to provide a large contiguous memory buffers for (usually a multimedia) devices. The contiguous memory is reserved during early boot and then shared with kernel, which is allowed to allocate it for movable pages. Then, when device driver requests a contigouous buffer, the framework migrates movable pages out of contiguous region and gives it to the driver. When device driver frees the buffer, it is added to kernel memory pool again. For more information, please refer to commit c64be2bb1c6eb43c838b2c6d57 ("drivers: add Contiguous Memory Allocator") and d484864dd96e1830e76895 (CMA merge commit). Why we need device tree bindings for CMA at all? Older ARM kernels used so called board-based initialization. Those board files contained a definition of all hardware blocks available on the target system and particular kernel and driver software configuration selected by the board maintainer. In the new approach the board files will be removed completely and Device Tree approach is used to describe all hardware blocks available on the target system. By definition, the bindings should be software independent, so at least in theory it should be possible to use those bindings with other operating systems than Linux kernel. However we also need to pass somehow the information about kernel and device driver software-only configuration data, which were earlier encoded in the board file. For such data I decided to use /chosen node, where kernel command line has been already stored. Future bootloaders will allow to modify or replace particular nodes and one will be able to use custom /chosen node to configure his system. The proposed patches introduce /chosen/contiguous-memory node and related bindings, to avoid complicated encoding of CMA related configuration to kernel command line. Some rationale for using /chosen/ node for kernel configuration entities has been already suggested by Grant Likely in the following thread: http://thread.gmane.org/gmane.comp.boot-loaders.u-boot/155296/focus=34363 Best regards Marek Szyprowski Samsung R&D Institute Poland Changelog: v3: - fixed issues pointed by Laura and updated documentation v2: http://thread.gmane.org/gmane.linux.drivers.devicetree/34075 - moved contiguous-memory bindings from /memory to /chosen/contiguous-memory/ node to avoid spreading Linux specific parameters over the whole device tree definitions - added support for autoconfigured regions (use zero base) - fixes minor bugs v1: http://thread.gmane.org/gmane.linux.drivers.devicetree/30111/ - initial proposal Patch summary: Marek Szyprowski (2): drivers: dma-contiguous: clean source code and prepare for device tree drivers: dma-contiguous: add initialization from device tree .../devicetree/bindings/contiguous-memory.txt | 94 ++++++ arch/arm/boot/dts/skeleton.dtsi | 7 +- drivers/base/dma-contiguous.c | 325 +++++++++++++------- include/asm-generic/dma-contiguous.h | 2 - include/linux/dma-contiguous.h | 32 +- 5 files changed, 352 insertions(+), 108 deletions(-) create mode 100644 Documentation/devicetree/bindings/contiguous-memory.txt -- 1.7.9.5

11 years, 3 months

[RFC PATCH] fence: dma-buf cross-device synchronization (v12)

by Maarten Lankhorst

A fence can be attached to a buffer which is being filled or consumed by hw, to allow userspace to pass the buffer without waiting to another device. For example, userspace can call page_flip ioctl to display the next frame of graphics after kicking the GPU but while the GPU is still rendering. The display device sharing the buffer with the GPU would attach a callback to get notified when the GPU's rendering-complete IRQ fires, to update the scan-out address of the display, without having to wake up userspace. A driver must allocate a fence context for each execution ring that can run in parallel. The function for this takes an argument with how many contexts to allocate: + fence_context_alloc() A fence is transient, one-shot deal. It is allocated and attached to one or more dma-buf's. When the one that attached it is done, with the pending operation, it can signal the fence: + fence_signal() To have a rough approximation whether a fence is fired, call: + fence_is_signaled() The dma-buf-mgr handles tracking, and waiting on, the fences associated with a dma-buf. The one pending on the fence can add an async callback: + fence_add_callback() The callback can optionally be cancelled with: + fence_remove_callback() To wait synchronously, optionally with a timeout: + fence_wait() + fence_wait_timeout() A default software-only implementation is provided, which can be used by drivers attaching a fence to a buffer when they have no other means for hw sync. But a memory backed fence is also envisioned, because it is common that GPU's can write to, or poll on some memory location for synchronization. For example: fence = custom_get_fence(...); if ((seqno_fence = to_seqno_fence(fence)) != NULL) { dma_buf *fence_buf = fence->sync_buf; get_dma_buf(fence_buf); ... tell the hw the memory location to wait ... custom_wait_on(fence_buf, fence->seqno_ofs, fence->seqno); } else { /* fall-back to sw sync * / fence_add_callback(fence, my_cb); } On SoC platforms, if some other hw mechanism is provided for synchronizing between IP blocks, it could be supported as an alternate implementation with it's own fence ops in a similar way. enable_signaling callback is used to provide sw signaling in case a cpu waiter is requested or no compatible hardware signaling could be used. The intention is to provide a userspace interface (presumably via eventfd) later, to be used in conjunction with dma-buf's mmap support for sw access to buffers (or for userspace apps that would prefer to do their own synchronization). v1: Original v2: After discussion w/ danvet and mlankhorst on #dri-devel, we decided that dma-fence didn't need to care about the sw->hw signaling path (it can be handled same as sw->sw case), and therefore the fence->ops can be simplified and more handled in the core. So remove the signal, add_callback, cancel_callback, and wait ops, and replace with a simple enable_signaling() op which can be used to inform a fence supporting hw->hw signaling that one or more devices which do not support hw signaling are waiting (and therefore it should enable an irq or do whatever is necessary in order that the CPU is notified when the fence is passed). v3: Fix locking fail in attach_fence() and get_fence() v4: Remove tie-in w/ dma-buf.. after discussion w/ danvet and mlankorst we decided that we need to be able to attach one fence to N dma-buf's, so using the list_head in dma-fence struct would be problematic. v5: [ Maarten Lankhorst ] Updated for dma-bikeshed-fence and dma-buf-manager. v6: [ Maarten Lankhorst ] I removed dma_fence_cancel_callback and some comments about checking if fence fired or not. This is broken by design. waitqueue_active during destruction is now fatal, since the signaller should be holding a reference in enable_signalling until it signalled the fence. Pass the original dma_fence_cb along, and call __remove_wait in the dma_fence_callback handler, so that no cleanup needs to be performed. v7: [ Maarten Lankhorst ] Set cb->func and only enable sw signaling if fence wasn't signaled yet, for example for hardware fences that may choose to signal blindly. v8: [ Maarten Lankhorst ] Tons of tiny fixes, moved __dma_fence_init to header and fixed include mess. dma-fence.h now includes dma-buf.h All members are now initialized, so kmalloc can be used for allocating a dma-fence. More documentation added. v9: Change compiler bitfields to flags, change return type of enable_signaling to bool. Rework dma_fence_wait. Added dma_fence_is_signaled and dma_fence_wait_timeout. s/dma// and change exports to non GPL. Added fence_is_signaled and fence_enable_sw_signaling calls, add ability to override default wait operation. v10: remove event_queue, use a custom list, export try_to_wake_up from scheduler. Remove fence lock and use a global spinlock instead, this should hopefully remove all the locking headaches I was having on trying to implement this. enable_signaling is called with this lock held. v11: Use atomic ops for flags, lifting the need for some spin_lock_irqsaves. However I kept the guarantee that after fence_signal returns, it is guaranteed that enable_signaling has either been called to completion, or will not be called any more. Add contexts and seqno to base fence implementation. This allows you to wait for less fences, by testing for seqno + signaled, and then only wait on the later fence. Add FENCE_TRACE, FENCE_WARN, and FENCE_ERR. This makes debugging easier. An CONFIG_DEBUG_FENCE will be added to turn off the FENCE_TRACE spam, and another runtime option can turn it off at runtime. v12: Add CONFIG_FENCE_TRACE. Add missing documentation for the fence->context and fence->seqno members. Signed-off-by: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> --- Documentation/DocBook/device-drivers.tmpl | 2 drivers/base/Kconfig | 10 + drivers/base/Makefile | 2 drivers/base/fence.c | 286 +++++++++++++++++++++++ include/linux/fence.h | 365 +++++++++++++++++++++++++++++ 5 files changed, 664 insertions(+), 1 deletion(-) create mode 100644 drivers/base/fence.c create mode 100644 include/linux/fence.h diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index cbfdf54..241f4c5 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -126,6 +126,8 @@ X!Edrivers/base/interface.c </sect1> <sect1><title>Device Drivers DMA Management</title> !Edrivers/base/dma-buf.c +!Edrivers/base/fence.c +!Iinclude/linux/fence.h !Edrivers/base/reservation.c !Iinclude/linux/reservation.h !Edrivers/base/dma-coherent.c diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 5daa259..0ad35df 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -200,6 +200,16 @@ config DMA_SHARED_BUFFER APIs extension; the file's descriptor can then be passed on to other driver. +config FENCE_TRACE + bool "Enable verbose FENCE_TRACE messages" + default n + depends on DMA_SHARED_BUFFER + help + Enable the FENCE_TRACE printks. This will add extra + spam to the config log, but will make it easier to diagnose + lockup related problems for dma-buffers shared across multiple + devices. + config CMA bool "Contiguous Memory Allocator" depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 48029aa..8a55cb9 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o -obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf.o reservation.o +obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf.o fence.o reservation.o obj-$(CONFIG_ISA) += isa.o obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o diff --git a/drivers/base/fence.c b/drivers/base/fence.c new file mode 100644 index 0000000..28e5ffd --- /dev/null +++ b/drivers/base/fence.c @@ -0,0 +1,286 @@ +/* + * Fence mechanism for dma-buf and to allow for asynchronous dma access + * + * Copyright (C) 2012 Canonical Ltd + * Copyright (C) 2012 Texas Instruments + * + * Authors: + * Rob Clark <rob.clark(a)linaro.org> + * Maarten Lankhorst <maarten.lankhorst(a)canonical.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/fence.h> + +atomic_t fence_context_counter = ATOMIC_INIT(0); +EXPORT_SYMBOL(fence_context_counter); + +int __fence_signal(struct fence *fence) +{ + struct fence_cb *cur, *tmp; + int ret = 0; + + if (WARN_ON(!fence)) + return -EINVAL; + + if (test_and_set_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + ret = -EINVAL; + + /* + * we might have raced with the unlocked fence_signal, + * still run through all callbacks + */ + } + + list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { + list_del_init(&cur->node); + cur->func(fence, cur, cur->priv); + } + return ret; +} +EXPORT_SYMBOL(__fence_signal); + +/** + * fence_signal - signal completion of a fence + * @fence: the fence to signal + * + * Signal completion for software callbacks on a fence, this will unblock + * fence_wait() calls and run all the callbacks added with + * fence_add_callback(). Can be called multiple times, but since a fence + * can only go from unsignaled to signaled state, it will only be effective + * the first time. + */ +int fence_signal(struct fence *fence) +{ + unsigned long flags; + + if (!fence || test_and_set_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return -EINVAL; + + if (test_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) { + struct fence_cb *cur, *tmp; + + spin_lock_irqsave(fence->lock, flags); + list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { + list_del_init(&cur->node); + cur->func(fence, cur, cur->priv); + } + spin_unlock_irqrestore(fence->lock, flags); + } + return 0; +} +EXPORT_SYMBOL(fence_signal); + +void release_fence(struct kref *kref) +{ + struct fence *fence = + container_of(kref, struct fence, refcount); + + BUG_ON(!list_empty(&fence->cb_list)); + + if (fence->ops->release) + fence->ops->release(fence); + else + kfree(fence); +} +EXPORT_SYMBOL(release_fence); + +/** + * fence_enable_sw_signaling - enable signaling on fence + * @fence: [in] the fence to enable + * + * this will request for sw signaling to be enabled, to make the fence + * complete as soon as possible + */ +void fence_enable_sw_signaling(struct fence *fence) +{ + unsigned long flags; + + if (!test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags) && + !test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + spin_lock_irqsave(fence->lock, flags); + + if (!fence->ops->enable_signaling(fence)) + __fence_signal(fence); + + spin_unlock_irqrestore(fence->lock, flags); + } +} +EXPORT_SYMBOL(fence_enable_sw_signaling); + +/** + * fence_add_callback - add a callback to be called when the fence + * is signaled + * @fence: [in] the fence to wait on + * @cb: [in] the callback to register + * @func: [in] the function to call + * @priv: [in] the argument to pass to function + * + * cb will be initialized by fence_add_callback, no initialization + * by the caller is required. Any number of callbacks can be registered + * to a fence, but a callback can only be registered to one fence at a time. + * + * Note that the callback can be called from an atomic context. If + * fence is already signaled, this function will return -ENOENT (and + * *not* call the callback) + * + * Add a software callback to the fence. Same restrictions apply to + * refcount as it does to fence_wait, however the caller doesn't need to + * keep a refcount to fence afterwards: when software access is enabled, + * the creator of the fence is required to keep the fence alive until + * after it signals with fence_signal. The callback itself can be called + * from irq context. + * + */ +int fence_add_callback(struct fence *fence, struct fence_cb *cb, + fence_func_t func, void *priv) +{ + unsigned long flags; + int ret = 0; + bool was_set; + + if (WARN_ON(!fence || !func)) + return -EINVAL; + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return -ENOENT; + + spin_lock_irqsave(fence->lock, flags); + + was_set = test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + ret = -ENOENT; + else if (!was_set && !fence->ops->enable_signaling(fence)) { + __fence_signal(fence); + ret = -ENOENT; + } + + if (!ret) { + cb->func = func; + cb->priv = priv; + list_add_tail(&cb->node, &fence->cb_list); + } + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(fence_add_callback); + +/** + * fence_remove_callback - remove a callback from the signaling list + * @fence: [in] the fence to wait on + * @cb: [in] the callback to remove + * + * Remove a previously queued callback from the fence. This function returns + * true is the callback is succesfully removed, or false if the fence has + * already been signaled. + * + * *WARNING*: + * Cancelling a callback should only be done if you really know what you're + * doing, since deadlocks and race conditions could occur all too easily. For + * this reason, it should only ever be done on hardware lockup recovery, + * with a reference held to the fence. + */ +bool +fence_remove_callback(struct fence *fence, struct fence_cb *cb) +{ + unsigned long flags; + bool ret; + + spin_lock_irqsave(fence->lock, flags); + + ret = !list_empty(&cb->node); + if (ret) + list_del_init(&cb->node); + + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(fence_remove_callback); + +static void +fence_default_wait_cb(struct fence *fence, struct fence_cb *cb, void *priv) +{ + try_to_wake_up(priv, TASK_NORMAL, 0); +} + +/** + * fence_default_wait - default sleep until the fence gets signaled + * or until timeout elapses + * @fence: [in] the fence to wait on + * @intr: [in] if true, do an interruptible wait + * @timeout: [in] timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the + * remaining timeout in jiffies on success. + */ +long +fence_default_wait(struct fence *fence, bool intr, signed long timeout) +{ + struct fence_cb cb; + unsigned long flags; + long ret = timeout; + bool was_set; + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return timeout; + + spin_lock_irqsave(fence->lock, flags); + + if (intr && signal_pending(current)) { + ret = -ERESTARTSYS; + goto out; + } + + was_set = test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + goto out; + + if (!was_set && !fence->ops->enable_signaling(fence)) { + __fence_signal(fence); + goto out; + } + + cb.func = fence_default_wait_cb; + cb.priv = current; + list_add(&cb.node, &fence->cb_list); + + while (!test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags) && ret > 0) { + if (intr) + __set_current_state(TASK_INTERRUPTIBLE); + else + __set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock_irqrestore(fence->lock, flags); + + ret = schedule_timeout(ret); + + spin_lock_irqsave(fence->lock, flags); + if (ret > 0 && intr && signal_pending(current)) + ret = -ERESTARTSYS; + } + + if (!list_empty(&cb.node)) + list_del(&cb.node); + __set_current_state(TASK_RUNNING); + +out: + spin_unlock_irqrestore(fence->lock, flags); + return ret; +} +EXPORT_SYMBOL(fence_default_wait); diff --git a/include/linux/fence.h b/include/linux/fence.h new file mode 100644 index 0000000..8c7a126 --- /dev/null +++ b/include/linux/fence.h @@ -0,0 +1,365 @@ +/* + * Fence mechanism for dma-buf to allow for asynchronous dma access + * + * Copyright (C) 2012 Canonical Ltd + * Copyright (C) 2012 Texas Instruments + * + * Authors: + * Rob Clark <rob.clark(a)linaro.org> + * Maarten Lankhorst <maarten.lankhorst(a)canonical.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __LINUX_FENCE_H +#define __LINUX_FENCE_H + +#include <linux/err.h> +#include <linux/wait.h> +#include <linux/list.h> +#include <linux/bitops.h> +#include <linux/kref.h> +#include <linux/sched.h> +#include <linux/printk.h> + +struct fence; +struct fence_ops; +struct fence_cb; + +/** + * struct fence - software synchronization primitive + * @refcount: refcount for this fence + * @ops: fence_ops associated with this fence + * @cb_list: list of all callbacks to call + * @lock: spin_lock_irqsave used for locking + * @context: execution context this fence belongs to, returned by + * fence_context_alloc() + * @seqno: the sequence number of this fence inside the execution context, + * can be compared to decide which fence would be signaled later. + * @flags: A mask of FENCE_FLAG_* defined below + * + * the flags member must be manipulated and read using the appropriate + * atomic ops (bit_*), so taking the spinlock will not be needed most + * of the time. + * + * FENCE_FLAG_SIGNALED_BIT - fence is already signaled + * FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called* + * FENCE_FLAG_USER_BITS - start of the unused bits, can be used by the + * implementer of the fence for its own purposes. Can be used in different + * ways by different fence implementers, so do not rely on this. + * + * *) Since atomic bitops are used, this is not guaranteed to be the case. + * Particularly, if the bit was set, but fence_signal was called right + * before this bit was set, it would have been able to set the + * FENCE_FLAG_SIGNALED_BIT, before enable_signaling was called. + * Adding a check for FENCE_FLAG_SIGNALED_BIT after setting + * FENCE_FLAG_ENABLE_SIGNAL_BIT closes this race, and makes sure that + * after fence_signal was called, any enable_signaling call will have either + * been completed, or never called at all. + */ +struct fence { + struct kref refcount; + const struct fence_ops *ops; + struct list_head cb_list; + spinlock_t *lock; + unsigned context, seqno; + unsigned long flags; +}; + +enum fence_flag_bits { + FENCE_FLAG_SIGNALED_BIT, + FENCE_FLAG_ENABLE_SIGNAL_BIT, + FENCE_FLAG_USER_BITS, /* must always be last member */ +}; + +typedef void (*fence_func_t)(struct fence *fence, struct fence_cb *cb, void *priv); + +/** + * struct fence_cb - callback for fence_add_callback + * @node: used by fence_add_callback to append this struct to fence::cb_list + * @func: fence_func_t to call + * @priv: value of priv to pass to function + * + * This struct will be initialized by fence_add_callback, additional + * data can be passed along by embedding fence_cb in another struct. + */ +struct fence_cb { + struct list_head node; + fence_func_t func; + void *priv; +}; + +/** + * struct fence_ops - operations implemented for fence + * @enable_signaling: enable software signaling of fence + * @signaled: [optional] peek whether the fence is signaled, can be null + * @wait: custom wait implementation + * @release: [optional] called on destruction of fence, can be null + * + * Notes on enable_signaling: + * For fence implementations that have the capability for hw->hw + * signaling, they can implement this op to enable the necessary + * irqs, or insert commands into cmdstream, etc. This is called + * in the first wait() or add_callback() path to let the fence + * implementation know that there is another driver waiting on + * the signal (ie. hw->sw case). + * + * This function can be called called from atomic context, but not + * from irq context, so normal spinlocks can be used. + * + * A return value of false indicates the fence already passed, + * or some failure occured that made it impossible to enable + * signaling. True indicates succesful enabling. + * + * Calling fence_signal before enable_signaling is called allows + * for a tiny race window in which enable_signaling is called during, + * before, or after fence_signal. To fight this, it is recommended + * that before enable_signaling returns true an extra reference is + * taken on the fence, to be released when the fence is signaled. + * This will mean fence_signal will still be called twice, but + * the second time will be a noop since it was already signaled. + * + * Notes on wait: + * Must not be NULL, set to fence_default_wait for default implementation. + * the fence_default_wait implementation should work for any fence, as long + * as enable_signaling works correctly. + * + * Must return -ERESTARTSYS if the wait is intr = true and the wait was + * interrupted, and remaining jiffies if fence has signaled, or 0 if wait + * timed out. Can also return other error values on custom implementations, + * which should be treated as if the fence is signaled. For example a hardware + * lockup could be reported like that. + * + * Notes on release: + * Can be NULL, this function allows additional commands to run on + * destruction of the fence. Can be called from irq context. + * If pointer is set to NULL, kfree will get called instead. + */ + +struct fence_ops { + bool (*enable_signaling)(struct fence *fence); + bool (*signaled)(struct fence *fence); + long (*wait)(struct fence *fence, bool intr, signed long timeout); + void (*release)(struct fence *fence); +}; + +/** + * __fence_init - Initialize a custom fence. + * @fence: [in] the fence to initialize + * @ops: [in] the fence_ops for operations on this fence + * @lock: [in] the irqsafe spinlock to use for locking this fence + * @context: [in] the execution context this fence is run on + * @seqno: [in] a linear increasing sequence number for this context + * + * Initializes an allocated fence, the caller doesn't have to keep its + * refcount after committing with this fence, but it will need to hold a + * refcount again if fence_ops.enable_signaling gets called. This can + * be used for other implementing other types of fence. + * + * context and seqno are used for easy comparison between fences, allowing + * to check which fence is later by simply using fence_later. + */ +static inline void +__fence_init(struct fence *fence, const struct fence_ops *ops, + spinlock_t *lock, unsigned context, unsigned seqno) +{ + BUG_ON(!ops || !lock || !ops->enable_signaling || !ops->wait); + + kref_init(&fence->refcount); + fence->ops = ops; + INIT_LIST_HEAD(&fence->cb_list); + fence->lock = lock; + fence->context = context; + fence->seqno = seqno; + fence->flags = 0UL; +} + +/** + * fence_get - increases refcount of the fence + * @fence: [in] fence to increase refcount of + */ +static inline void fence_get(struct fence *fence) +{ + if (WARN_ON(!fence)) + return; + kref_get(&fence->refcount); +} + +extern void release_fence(struct kref *kref); + +/** + * fence_put - decreases refcount of the fence + * @fence: [in] fence to reduce refcount of + */ +static inline void fence_put(struct fence *fence) +{ + if (WARN_ON(!fence)) + return; + kref_put(&fence->refcount, release_fence); +} + +int fence_signal(struct fence *fence); +int __fence_signal(struct fence *fence); +long fence_default_wait(struct fence *fence, bool intr, signed long timeout); +int fence_add_callback(struct fence *fence, struct fence_cb *cb, + fence_func_t func, void *priv); +bool fence_remove_callback(struct fence *fence, struct fence_cb *cb); +void fence_enable_sw_signaling(struct fence *fence); + +/** + * fence_is_signaled - Return an indication if the fence is signaled yet. + * @fence: [in] the fence to check + * + * Returns true if the fence was already signaled, false if not. Since this + * function doesn't enable signaling, it is not guaranteed to ever return true + * If fence_add_callback, fence_wait or fence_enable_sw_signaling + * haven't been called before. + * + * It's recommended for seqno fences to call fence_signal when the + * operation is complete, it makes it possible to prevent issues from + * wraparound between time of issue and time of use by checking the return + * value of this function before calling hardware-specific wait instructions. + */ +static inline bool +fence_is_signaled(struct fence *fence) +{ + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return true; + + if (fence->ops->signaled && fence->ops->signaled(fence)) { + fence_signal(fence); + return true; + } + + return false; +} + +/** + * fence_later - return the chronologically later fence + * @f1: [in] the first fence from the same context + * @f2: [in] the second fence from the same context + * + * Returns NULL if both fences are signaled, otherwise the fence that would be + * signaled last. Both fences must be from the same context, since a seqno is + * not re-used across contexts. + */ +static inline struct fence *fence_later(struct fence *f1, struct fence *f2) +{ + bool sig1, sig2; + + /* + * can't check just FENCE_FLAG_SIGNALED_BIT here, it may never have been + * set called if enable_signaling wasn't, and enabling that here is + * overkill. + */ + sig1 = fence_is_signaled(f1); + sig2 = fence_is_signaled(f2); + + if (sig1 && sig2) + return NULL; + + BUG_ON(f1->context != f2->context); + + if (sig1 || f2->seqno - f1->seqno <= INT_MAX) + return f2; + else + return f1; +} + +/** + * fence_wait_timeout - sleep until the fence gets signaled + * or until timeout elapses + * @fence: [in] the fence to wait on + * @intr: [in] if true, do an interruptible wait + * @timeout: [in] timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the + * remaining timeout in jiffies on success. Other error values may be + * returned on custom implementations. + * + * Performs a synchronous wait on this fence. It is assumed the caller + * directly or indirectly (buf-mgr between reservation and committing) + * holds a reference to the fence, otherwise the fence might be + * freed before return, resulting in undefined behavior. + */ +static inline long +fence_wait_timeout(struct fence *fence, bool intr, signed long timeout) +{ + if (WARN_ON(timeout < 0)) + return -EINVAL; + + return fence->ops->wait(fence, intr, timeout); +} + +/** + * fence_wait - sleep until the fence gets signaled + * @fence: [in] the fence to wait on + * @intr: [in] if true, do an interruptible wait + * + * This function will return -ERESTARTSYS if interrupted by a signal, + * or 0 if the fence was signaled. Other error values may be + * returned on custom implementations. + * + * Performs a synchronous wait on this fence. It is assumed the caller + * directly or indirectly (buf-mgr between reservation and committing) + * holds a reference to the fence, otherwise the fence might be + * freed before return, resulting in undefined behavior. + */ +static inline long fence_wait(struct fence *fence, bool intr) +{ + long ret; + + /* Since fence_wait_timeout cannot timeout with + * MAX_SCHEDULE_TIMEOUT, only valid return values are + * -ERESTARTSYS and MAX_SCHEDULE_TIMEOUT. + */ + ret = fence_wait_timeout(fence, intr, MAX_SCHEDULE_TIMEOUT); + + return ret < 0 ? ret : 0; +} + +/** + * fence context counter: each execution context should have its own + * fence context, this allows checking if fences belong to the same + * context or not. One device can have multiple separate contexts, + * and they're used if some engine can run independently of another. + */ +extern atomic_t fence_context_counter; + +static inline unsigned fence_context_alloc(unsigned num) +{ + BUG_ON(!num); + return atomic_add_return(num, &fence_context_counter) - num; +} + +#define FENCE_TRACE(f, fmt, args...) \ + do { \ + struct fence *__ff = (f); \ + if (config_enabled(CONFIG_FENCE_TRACE)) \ + pr_info("f %u#%u: " fmt, \ + __ff->context, __ff->seqno, ##args); \ + } while (0) + +#define FENCE_WARN(f, fmt, args...) \ + do { \ + struct fence *__ff = (f); \ + pr_warn("f %u#%u: " fmt, __ff->context, __ff->seqno, ##args); \ + } while (0) + +#define FENCE_ERR(f, fmt, args...) \ + do { \ + struct fence *__ff = (f); \ + pr_err("f %u#%u: " fmt, __ff->context, __ff->seqno, ##args); \ + } while (0) + +#endif /* __LINUX_FENCE_H */

11 years, 4 months

[PATCH v4 0/4] Device Tree support for CMA (Contiguous Memory Allocator)

by Marek Szyprowski

Hello, This is a fourth version of my proposal for device tree integration for reserved memory and Contiguous Memory Allocator. After the comments from Grant Likely I moved back memory region definitions back to /memory node (as it was in the first version of this proposal). I've also extended the code and made it more generic, added support for so called reserved dma memory (special dma memory regions created by dma_alloc_coherent() function, for exclusive usage for dma allocation for the given device). Just a few words for those who see this code for the first time: The proposed bindings allows to define contiguous memory regions of specified base address and size. Then, the defined regions can be assigned to the given device(s) by adding a property with a phanle to the defined contiguous memory region. From the device tree perspective that's all. Once the bindings are added, all the memory allocations from dma-mapping subsystem will be served from the defined contiguous memory regions. Contiguous Memory Allocator is a framework, which lets to provide a large contiguous memory buffers for (usually a multimedia) devices. The contiguous memory is reserved during early boot and then shared with kernel, which is allowed to allocate it for movable pages. Then, when device driver requests a contigouous buffer, the framework migrates movable pages out of contiguous region and gives it to the driver. When device driver frees the buffer, it is added to kernel memory pool again. For more information, please refer to commit c64be2bb1c6eb43c838b2c6d57 ("drivers: add Contiguous Memory Allocator") and d484864dd96e1830e76895 (CMA merge commit). Why we need device tree bindings for CMA at all? Older ARM kernels used so called board-based initialization. Those board files contained a definition of all hardware blocks available on the target system and particular kernel and driver software configuration selected by the board maintainer. In the new approach the board files will be removed completely and Device Tree approach is used to describe all hardware blocks available on the target system. By definition, the bindings should be software independent, so at least in theory it should be possible to use those bindings with other operating systems than Linux kernel. Reserved memory configuration belongs to the grey area. It might depend on hardware restriction of the board or modules and low-level configuration done by bootloader. Putting reserved and contiguous memory regions to /memory node and having phandles to those regions in the device nodes however matches well with the device-tree typical style of linking devices with other resources like clocks, interrupts, regulators, power domains, etc. This is the main reason to use such approach instead of putting everything to /chosen node as it has been proposed in v2 and v3. Best regards Marek Szyprowski Samsung R&D Institute Poland Changelog: v4: - moved back contiguous-memory bindings from /chosen/contiguous-memory to /memory nodes as suggested by Grant (see http://article.gmane.org/gmane.linux.drivers.devicetree/41030 for more details) - added support for DMA reserved memory with dma_declare_coherent() - moved code to drivers/of/of_reserved_mem.c - added generic code to scan specific path in flat device tree v3: http://thread.gmane.org/gmane.linux.drivers.devicetree/40013/ - fixed issues pointed by Laura and updated documentation v2: http://thread.gmane.org/gmane.linux.drivers.devicetree/34075 - moved contiguous-memory bindings from /memory to /chosen/contiguous-memory/ node to avoid spreading Linux specific parameters over the whole device tree definitions - added support for autoconfigured regions (use zero base) - fixes minor bugs v1: http://thread.gmane.org/gmane.linux.drivers.devicetree/30111/ - initial proposal Patch summary: Marek Szyprowski (4): drivers: dma-contiguous: clean source code and prepare for device tree drivers: of: add function to scan fdt nodes given by path drivers: of: add initialization code for dma reserved memory ARM: init: add support for reserved memory defined by device tree Documentation/devicetree/bindings/memory.txt | 152 ++++++++++++++++++++++ arch/arm/mm/init.c | 3 + drivers/base/dma-contiguous.c | 147 +++++++++++----------- drivers/of/Kconfig | 6 + drivers/of/Makefile | 1 + drivers/of/fdt.c | 76 +++++++++++ drivers/of/of_reserved_mem.c | 175 ++++++++++++++++++++++++++ include/asm-generic/dma-coherent.h | 6 + include/asm-generic/dma-contiguous.h | 2 - include/linux/dma-contiguous.h | 49 +++++++- include/linux/of_fdt.h | 3 + 11 files changed, 541 insertions(+), 79 deletions(-) create mode 100644 Documentation/devicetree/bindings/memory.txt create mode 100644 drivers/of/of_reserved_mem.c -- 1.7.9.5

11 years, 4 months

[PATCH 08/14] backports: backport ww_mutex support

by Luis R. Rodriguez

From: "Luis R. Rodriguez" <mcgrof(a)do-not-panic.com> This backports the kernel's wound/wait style locks 040a0a371, using the linux-stable v3.11-rc2 as a base for development. Given the complexity to support debugging mutexes this backport implementation is simplified by only making this feature availabe if you to have DEBUG_MUTEXES and DEBUG_LOCK_ALLOC disabled. Given that ww mutex is required for DRM this also means we must update the kconfig for DRM and require you to also not be able to build DRM if you have either of these options enabled. Support for DEBUG_MUTEXES and DEBUG_LOCK_ALLOC can be added later by anyone daring. This uses the new dependencies file kconfig language extension to specify the backport feature build restrictions for DRM. Part of the ww mutex addition to the kernel required modifying the fast path mutex locking scheme by requiring you to deal with the slow path alternatives on your own (refer to a41b56ef). The reason for this change was that the mutex fastpath implementation assumed your slowpath alternative can only be passed one argument and the addition of ww mutexes requires dealing with the slow path with a context passed. It'd be painful to backport all asm for an optimized fastpath implementation so we penalize the backport ww mutex fast path by using the generic atomic_dec_return(). To backport a clean our own mutex_lock_common() with the least amount of changes against upstream commits 2bd2c92c and 41fcb9f2 also needed to be backported. Commit 2bd2c92c dealt with adding support for queue mutex spinners with an MCS lock, since this cannot be backported for older kernels we provide empty inlines. Commit 41fcb9f2 just removed SCHED_FEAT_OWNER_SPIN as it was an early hack, the only thing required to backport this commit was to provide an alternative declaration for mutex_spin_on_owner() as it was declared non-inline for older kernels. Finally c5491ea7 required backporting schedule_preempt_disabled() as well but that just consisted of carrying over the original implementation. Since its not exported we need to reimplement it to make it available to our internal core ww mutex port. mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains 040a0a371 v3.11-rc1~147^2~5 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains a41b56ef v3.11-rc1~147^2~6 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains 2bd2c92c v3.10-rc1~200^2~3 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains 41fcb9f2 v3.10-rc1~200^2~5 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains c5491ea7 v3.4-rc1~3^2~27 commit 040a0a37100563754bb1fee6ff6427420bcfa609 Author: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Date: Mon Jun 24 10:30:04 2013 +0200 mutex: Add support for wound/wait style locks Wound/wait mutexes are used when other multiple lock acquisitions of a similar type can be done in an arbitrary order. The deadlock handling used here is called wait/wound in the RDBMS literature: 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. For full documentation please read Documentation/ww-mutex-design.txt. References: https://lwn.net/Articles/548909/ Signed-off-by: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Acked-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Acked-by: Rob Clark <robdclark(a)gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: rostedt(a)goodmis.org Cc: daniel(a)ffwll.ch Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/51C8038C.9000106@canonical.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> commit a41b56efa70e060f650aeb54740aaf52044a1ead Author: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Date: Thu Jun 20 13:31:05 2013 +0200 arch: Make __mutex_fastpath_lock_retval return whether fastpath succeeded or not This will allow me to call functions that have multiple arguments if fastpath fails. This is required to support ticket mutexes, because they need to be able to pass an extra argument to the fail function. Originally I duplicated the functions, by adding __mutex_fastpath_lock_retval_arg. This ended up being just a duplication of the existing function, so a way to test if fastpath was called ended up being better. This also cleaned up the reservation mutex patch some by being able to call an atomic_set instead of atomic_xchg, and making it easier to detect if the wrong unlock function was previously used. Signed-off-by: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Acked-by: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: robclark(a)gmail.com Cc: rostedt(a)goodmis.org Cc: daniel(a)ffwll.ch Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/20130620113105.4001.83929.stgit@patser Signed-off-by: Ingo Molnar <mingo(a)kernel.org> commit 2bd2c92cf07cc4a373bf316c75b78ac465fefd35 Author: Waiman Long <Waiman.Long(a)hp.com> Date: Wed Apr 17 15:23:13 2013 -0400 mutex: Queue mutex spinners with MCS lock to reduce cacheline contention <-- snip --> commit 41fcb9f230bf773656d1768b73000ef720bf00c3 Author: Waiman Long <Waiman.Long(a)hp.com> Date: Wed Apr 17 15:23:11 2013 -0400 mutex: Move mutex spinning code from sched/core.c back to mutex.c <-- snip --> commit c5491ea779793f977d282754db478157cc409d82 Author: Thomas Gleixner <tglx(a)linutronix.de> Date: Mon Mar 21 12:09:35 2011 +0100 sched/rt: Add schedule_preempt_disabled() <-- snip --> Cc: maarten.lankhorst(a)canonical.com Cc: Daniel Vetter <daniel.vetter(a)ffwll.ch> Cc: Rob Clark <robdclark(a)gmail.com> Cc: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: rostedt(a)goodmis.org Cc: daniel(a)ffwll.ch Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: Luis R. Rodriguez <mcgrof(a)do-not-panic.com> --- backport/backport-include/linux/ww_mutex.h | 333 ++++++++++++++ backport/compat/Kconfig | 11 + backport/compat/Makefile | 1 + backport/compat/kernel/ww_mutex.c | 667 ++++++++++++++++++++++++++++ dependencies | 6 + 5 files changed, 1018 insertions(+) create mode 100644 backport/backport-include/linux/ww_mutex.h create mode 100644 backport/compat/kernel/ww_mutex.c diff --git a/backport/backport-include/linux/ww_mutex.h b/backport/backport-include/linux/ww_mutex.h new file mode 100644 index 0000000..0953939 --- /dev/null +++ b/backport/backport-include/linux/ww_mutex.h @@ -0,0 +1,333 @@ +#ifndef __BACKPORT_LINUX_WW_MUTEX_H +#define __BACKPORT_LINUX_WW_MUTEX_H + +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0) +#include_next <linux/ww_mutex.h> +#else +#ifdef CPTCFG_BACKPORT_BUILD_WW_MUTEX +/* + * Wound/Wait Mutexes: blocking mutual exclusion locks with deadlock avoidance + * + * Original mutex implementation started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo(a)redhat.com> + * + * Wound/wait implementation: + * Copyright (C) 2013 Canonical Ltd. + * + * This file contains the main data structure and API definitions. + */ + +#include <linux/mutex.h> + +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; +}; + +struct ww_mutex { + struct mutex base; + struct ww_acquire_ctx *ctx; +}; + +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) + +#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_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) + +/** + * 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. + */ +#define ww_mutex_init LINUX_BACKPORT(ww_mutex_init) +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; +} + +/** + * 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. + */ +#define ww_acquire_init LINUX_BACKPORT(ww_acquire_init) +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; +} + +/** + * 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. + */ +#define ww_acquire_done LINUX_BACKPORT(ww_acquire_done) +static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) +{ +} + +/** + * 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. + */ +#define ww_acquire_fini LINUX_BACKPORT(ww_acquire_fini) +static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) +{ +} + +#define __ww_mutex_lock LINUX_BACKPORT(__ww_mutex_lock) +extern int __must_check __ww_mutex_lock(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); +#define __ww_mutex_lock_interruptible LINUX_BACKPORT(__ww_mutex_lock_interruptible) +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. + */ +#define ww_mutex_lock LINUX_BACKPORT(ww_mutex_lock) +static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + if (ctx) + return __ww_mutex_lock(lock, ctx); + + 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. + */ +#define ww_mutex_lock_interruptible LINUX_BACKPORT(ww_mutex_lock_interruptible) +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. + */ +#define ww_mutex_lock_slow LINUX_BACKPORT(ww_mutex_lock_slow) +static inline void +ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + 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. + */ +#define ww_mutex_lock_slow_interruptible LINUX_BACKPORT(ww_mutex_lock_slow_interruptible) +static inline int __must_check +ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + return ww_mutex_lock_interruptible(lock, ctx); +} + +#define ww_mutex_unlock LINUX_BACKPORT(ww_mutex_unlock) +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. + */ +#define ww_mutex_trylock LINUX_BACKPORT(ww_mutex_trylock) +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. + */ +#define ww_mutex_destroy LINUX_BACKPORT(ww_mutex_destroy) +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. + */ +#define ww_mutex_is_locked LINUX_BACKPORT(ww_mutex_is_locked) +static inline bool ww_mutex_is_locked(struct ww_mutex *lock) +{ + return mutex_is_locked(&lock->base); +} + +#endif /* CPTCFG_BACKPORT_BUILD_WW_MUTEX */ +#endif /* LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0) */ +#endif /* __BACKPORT_LINUX_WW_MUTEX_H */ diff --git a/backport/compat/Kconfig b/backport/compat/Kconfig index e2f0cdd..f3c1ab3 100644 --- a/backport/compat/Kconfig +++ b/backport/compat/Kconfig @@ -185,6 +185,17 @@ config BACKPORT_LEDS_CLASS config BACKPORT_LEDS_TRIGGERS bool +config BACKPORT_BUILD_WW_MUTEX + bool + # Build only if on kernels < 3.11 + # For now only DRM drivers use ww mutexes. + depends on DRM && BACKPORT_KERNEL_3_11 + default y if BACKPORT_USERSEL_BUILD_ALL + # probably a bad idea if you have these options given we + # ripped those options out. + depends on !DEBUG_MUTEXES + depends on !DEBUG_LOCK_ALLOC + config BACKPORT_BUILD_RADIX_HELPERS bool # You have selected to build backported DRM drivers diff --git a/backport/compat/Makefile b/backport/compat/Makefile index 252290e..fec01c4 100644 --- a/backport/compat/Makefile +++ b/backport/compat/Makefile @@ -41,3 +41,4 @@ compat-$(CPTCFG_BACKPORT_BUILD_KFIFO) += kfifo.o compat-$(CPTCFG_BACKPORT_BUILD_GENERIC_ATOMIC64) += compat_atomic.o compat-$(CPTCFG_BACKPORT_BUILD_DMA_SHARED_HELPERS) += dma-shared-helpers.o compat-$(CPTCFG_BACKPORT_BUILD_RADIX_HELPERS) += lib-radix-tree-helpers.o +compat-$(CPTCFG_BACKPORT_BUILD_WW_MUTEX) += kernel/ww_mutex.o diff --git a/backport/compat/kernel/ww_mutex.c b/backport/compat/kernel/ww_mutex.c new file mode 100644 index 0000000..257c2a4 --- /dev/null +++ b/backport/compat/kernel/ww_mutex.c @@ -0,0 +1,667 @@ +/* + * Copyright (c) 2013 Luis R. Rodriguez <mcgrof(a)do-not-panic.com> + * + * Backport ww mutex for older kernels. This is not supported when + * DEBUG_MUTEXES or DEBUG_LOCK_ALLOC is enabled. + * + * Taken from: kernel/mutex.c - via linux-stable v3.11-rc2 + * + * Mutexes: blocking mutual exclusion locks + * + * Started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo(a)redhat.com> + * + * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and + * David Howells for suggestions and improvements. + * + * - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline + * from the -rt tree, where it was originally implemented for rtmutexes + * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale + * and Sven Dietrich. + * + * Also see Documentation/mutex-design.txt. + */ + +#include <linux/mutex.h> +#include <linux/ww_mutex.h> +#include <asm/mutex.h> +#include <linux/sched.h> +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,9,0) +#include <linux/sched/rt.h> +#endif +#include <linux/export.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/debug_locks.h> +#include <linux/version.h> + +/* + * A negative mutex count indicates that waiters are sleeping waiting for the + * mutex. + */ +#define MUTEX_SHOW_NO_WAITER(mutex) (atomic_read(&(mutex)->count) >= 0) + +#define spin_lock_mutex(lock, flags) \ + do { spin_lock(lock); (void)(flags); } while (0) +#define spin_unlock_mutex(lock, flags) \ + do { spin_unlock(lock); (void)(flags); } while (0) +#define mutex_remove_waiter(lock, waiter, ti) \ + __list_del((waiter)->list.prev, (waiter)->list.next) + +#ifdef CONFIG_SMP +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current; +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} +#else +static inline void mutex_set_owner(struct mutex *lock) +{ +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ +} +#endif + + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0) /* 2bd2c92c and 41fcb9f2 */ +/* + * In order to avoid a stampede of mutex spinners from acquiring the mutex + * more or less simultaneously, the spinners need to acquire a MCS lock + * first before spinning on the owner field. + * + * We don't inline mspin_lock() so that perf can correctly account for the + * time spent in this lock function. + */ +struct mspin_node { + struct mspin_node *next ; + int locked; /* 1 if lock acquired */ +}; +#define MLOCK(mutex) ((struct mspin_node **)&((mutex)->spin_mlock)) + +static noinline +void mspin_lock(struct mspin_node **lock, struct mspin_node *node) +{ + struct mspin_node *prev; + + /* Init node */ + node->locked = 0; + node->next = NULL; + + prev = xchg(lock, node); + if (likely(prev == NULL)) { + /* Lock acquired */ + node->locked = 1; + return; + } + ACCESS_ONCE(prev->next) = node; + smp_wmb(); + /* Wait until the lock holder passes the lock down */ + while (!ACCESS_ONCE(node->locked)) + arch_mutex_cpu_relax(); +} + +static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node) +{ + struct mspin_node *next = ACCESS_ONCE(node->next); + + if (likely(!next)) { + /* + * Release the lock by setting it to NULL + */ + if (cmpxchg(lock, node, NULL) == node) + return; + /* Wait until the next pointer is set */ + while (!(next = ACCESS_ONCE(node->next))) + arch_mutex_cpu_relax(); + } + ACCESS_ONCE(next->locked) = 1; + smp_wmb(); +} + +/* + * Mutex spinning code migrated from kernel/sched/core.c + */ + +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ + if (lock->owner != owner) + return false; + + /* + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * lock->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. + */ + barrier(); + + return owner->on_cpu; +} + +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0) +static noinline +#endif +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ + rcu_read_lock(); + while (owner_running(lock, owner)) { + if (need_resched()) + break; + + arch_mutex_cpu_relax(); + } + rcu_read_unlock(); + + /* + * We break out the loop above on need_resched() and when the + * owner changed, which is a sign for heavy contention. Return + * success only when lock->owner is NULL. + */ + return lock->owner == NULL; +} + +/* + * Initial check for entering the mutex spinning loop + */ +static inline int mutex_can_spin_on_owner(struct mutex *lock) +{ + int retval = 1; + + rcu_read_lock(); + if (lock->owner) + retval = lock->owner->on_cpu; + rcu_read_unlock(); + /* + * if lock->owner is not set, the mutex owner may have just acquired + * it and not set the owner yet or the mutex has been released. + */ + return retval; +} +#else /* Backport 2bd2c92c: help keep backport_mutex_lock_common() clean */ + +struct mspin_node { +}; +#define MLOCK(mutex) NULL + +static noinline +void mspin_lock(struct mspin_node **lock, struct mspin_node *node) +{ +} + +static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node) +{ +} + +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ +} + +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ +} + +static inline int mutex_can_spin_on_owner(struct mutex *lock) +{ + return 1; +} +#endif /* LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0) */ +#endif /* CONFIG_MUTEX_SPIN_ON_OWNER */ + +/* + * Release the lock, slowpath: + */ +static inline void +__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + unsigned long flags; + + spin_lock_mutex(&lock->wait_lock, flags); + mutex_release(&lock->dep_map, nested, _RET_IP_); + /* debug_mutex_unlock(lock); */ + + /* + * some architectures leave the lock unlocked in the fastpath failure + * case, others need to leave it locked. In the later case we have to + * unlock it here + */ + if (__mutex_slowpath_needs_to_unlock()) + atomic_set(&lock->count, 1); + + if (!list_empty(&lock->wait_list)) { + /* get the first entry from the wait-list: */ + struct mutex_waiter *waiter = + list_entry(lock->wait_list.next, + struct mutex_waiter, list); + + /* debug_mutex_wake_waiter(lock, waiter); */ + + wake_up_process(waiter->task); + } + + spin_unlock_mutex(&lock->wait_lock, flags); +} + +/* + * Release the lock, slowpath: + */ +static __used noinline void +__mutex_unlock_slowpath(atomic_t *lock_count) +{ + __mutex_unlock_common_slowpath(lock_count, 1); +} + +/** + * 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) { + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + + __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath); +} +EXPORT_SYMBOL_GPL(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)) { + return -EDEADLK; + } + + return 0; +} + +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ + 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); +} + +/** + * backport_schedule_preempt_disabled - called with preemption disabled + * + * Backports c5491ea7. This is not exported so we leave it + * here as this is the only current core user on backports. + * Although available on >= 3.4 its only for in-kernel code so + * we provide our own. + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +static void __sched backport_schedule_preempt_disabled(void) +{ + preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + +/* + * Lock a mutex (possibly interruptible), slowpath: + */ +static __always_inline int __sched +__backport_mutex_lock_common(struct mutex *lock, long state, + unsigned int subclass, + 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); + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + /* + * Optimistic spinning. + * + * We try to spin for acquisition when we find that there are no + * pending waiters and the lock owner is currently running on a + * (different) CPU. + * + * The rationale is that if the lock owner is running, it is likely to + * release the lock soon. + * + * Since this needs the lock owner, and this mutex implementation + * doesn't track the owner atomically in the lock field, we need to + * track it non-atomically. + * + * We can't do this for DEBUG_MUTEXES because that relies on wait_lock + * to serialize everything. + * + * The mutex spinners are queued up using MCS lock so that only one + * spinner can compete for the mutex. However, if mutex spinning isn't + * going to happen, there is no point in going through the lock/unlock + * overhead. + */ + if (!mutex_can_spin_on_owner(lock)) + goto slowpath; + + for (;;) { + 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. + */ + mspin_lock(MLOCK(lock), &node); + owner = ACCESS_ONCE(lock->owner); + if (owner && !mutex_spin_on_owner(lock, owner)) { + mspin_unlock(MLOCK(lock), &node); + break; + } + + 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(); + return 0; + } + mspin_unlock(MLOCK(lock), &node); + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(task))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + arch_mutex_cpu_relax(); + } +slowpath: +#endif + spin_lock_mutex(&lock->wait_lock, flags); + + /* We don't support DEBUG_MUTEXES on the backport */ + /* debug_mutex_lock_common(lock, &waiter); */ + /* debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); */ + + /* add waiting tasks to the end of the waitqueue (FIFO): */ + list_add_tail(&waiter.list, &lock->wait_list); + waiter.task = task; + + if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, -1) == 1)) + goto done; + + lock_contended(&lock->dep_map, ip); + + for (;;) { + /* + * Lets try to take the lock again - this is needed even if + * we get here for the first time (shortly after failing to + * acquire the lock), to make sure that we get a wakeup once + * it's unlocked. Later on, if we sleep, this is the + * operation that gives us the lock. We xchg it to -1, so + * that when we release the lock, we properly wake up the + * other waiters: + */ + if (MUTEX_SHOW_NO_WAITER(lock) && + (atomic_xchg(&lock->count, -1) == 1)) + break; + + /* + * got a signal? (This code gets eliminated in the + * TASK_UNINTERRUPTIBLE case.) + */ + if (unlikely(signal_pending_state(state, task))) { + ret = -EINTR; + goto err; + } + + 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: */ + spin_unlock_mutex(&lock->wait_lock, flags); + backport_schedule_preempt_disabled(); + spin_lock_mutex(&lock->wait_lock, flags); + } + +done: + lock_acquired(&lock->dep_map, ip); + /* got the lock - rejoice! */ + 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); + + spin_unlock_mutex(&lock->wait_lock, flags); + + /* debug_mutex_free_waiter(&waiter); */ + 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; +} + +static noinline int __sched +__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + return __backport_mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx); +} + +static noinline int __sched +__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + return __backport_mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx); +} + +/** + * __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 + * + * For backporting purposes we can't use the older kernel's + * __mutex_fastpath_lock_retval() since upon failure of a fastpath + * lock we want to call our a failure routine with more than one argument, in + * this case the context for ww mutexes. Refer to commit a41b56ef the + * argument increase. It'd be painful to backport all asm code for the + * supported architectures so instead lets penalize the backport ww mutex + * fastpath lock with the not so efficient generic atomic_dec_return() + * implementation. + * + * 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 +__backport_mutex_fastpath_lock_retval(atomic_t *count) +{ + if (unlikely(atomic_dec_return(count) < 0)) + return -1; + return 0; +} + +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __backport_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_GPL(__ww_mutex_lock); + +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __backport_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_GPL(__ww_mutex_lock_interruptible); diff --git a/dependencies b/dependencies index 6841613..5c50571 100644 --- a/dependencies +++ b/dependencies @@ -48,6 +48,12 @@ MWIFIEX 2.6.27 # DRM stuff HDMI 3.2 DRM 3.2 +# As of 3.11 DRM depends on the new ww_mutex which is +# backported via BACKPORT_BUILD_WW_MUTEX. This backported +# feature however has does not yet have support for +# DEBUG_MUTEXES and DEBUG_LOCK_ALLOC. +DRM kconfig: !BACKPORT_KERNEL_3_11 || !DEBUG_MUTEXES +DRM kconfig: !BACKPORT_KERNEL_3_11 || !DEBUG_LOCK_ALLOC DRM_TTM 3.2 # See e2bdb933, this was added on v3.3, in order to # support DRM_QXL on 3.2 you'd have to backport 78c1d7848 -- 1.7.10.4

11 years, 4 months

[RFC 7/9] backports: backport ww_mutex support

by Luis R. Rodriguez

From: "Luis R. Rodriguez" <mcgrof(a)do-not-panic.com> This backports the kernel's wound/wait style locks 040a0a371, using the linux-stable v3.11-rc2 as a base for development. Given the complexity to support debugging mutexes this backport implementation is simplified by only making this feature availabe if you to have DEBUG_MUTEXES and DEBUG_LOCK_ALLOC disabled. Given that ww mutex is required for DRM this also means we must update the kconfig for DRM and require you to also not be able to build DRM if you have either of these options enabled. Support for DEBUG_MUTEXES and DEBUG_LOCK_ALLOC can be added later by anyone daring. Part of the ww mutex addition to the kernel required modifying the fast path mutex locking scheme by requiring you to deal with the slow path alternatives on your own (refer to a41b56ef). The reason for this change was that the mutex fastpath implementation assumed your slowpath alternative can only be passed one argument and the addition of ww mutexes requires dealing with the slow path with a context passed. It'd be painful to backport all asm for an optimized fastpath implementation so we penalize the backport ww mutex fast path by using the generic atomic_dec_return(). To backport a clean our own mutex_lock_common() with the least amount of changes against upstream commits 2bd2c92c and 41fcb9f2 also needed to be backported. Commit 2bd2c92c dealt with adding support for queue mutex spinners with an MCS lock, since this cannot be backported for older kernels we provide empty inlines. Commit 41fcb9f2 just removed SCHED_FEAT_OWNER_SPIN as it was an early hack, the only thing required to backport this commit was to provide an alternative declaration for mutex_spin_on_owner() as it was declared non-inline for older kernels. Finally c5491ea7 required backporting schedule_preempt_disabled() as well but that just consisted of carrying over the original implementation. Since its not exported we need to reimplement it to make it available to our internal core ww mutex port. mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains 040a0a371 v3.11-rc1~147^2~5 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains a41b56ef v3.11-rc1~147^2~6 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains 2bd2c92c v3.10-rc1~200^2~3 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains 41fcb9f2 v3.10-rc1~200^2~5 mcgrof@frijol ~/linux-stable (git::master)$ git describe --contains c5491ea7 v3.4-rc1~3^2~27 commit 040a0a37100563754bb1fee6ff6427420bcfa609 Author: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Date: Mon Jun 24 10:30:04 2013 +0200 mutex: Add support for wound/wait style locks Wound/wait mutexes are used when other multiple lock acquisitions of a similar type can be done in an arbitrary order. The deadlock handling used here is called wait/wound in the RDBMS literature: 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. For full documentation please read Documentation/ww-mutex-design.txt. References: https://lwn.net/Articles/548909/ Signed-off-by: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Acked-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Acked-by: Rob Clark <robdclark(a)gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: rostedt(a)goodmis.org Cc: daniel(a)ffwll.ch Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/51C8038C.9000106@canonical.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> commit a41b56efa70e060f650aeb54740aaf52044a1ead Author: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Date: Thu Jun 20 13:31:05 2013 +0200 arch: Make __mutex_fastpath_lock_retval return whether fastpath succeeded or not This will allow me to call functions that have multiple arguments if fastpath fails. This is required to support ticket mutexes, because they need to be able to pass an extra argument to the fail function. Originally I duplicated the functions, by adding __mutex_fastpath_lock_retval_arg. This ended up being just a duplication of the existing function, so a way to test if fastpath was called ended up being better. This also cleaned up the reservation mutex patch some by being able to call an atomic_set instead of atomic_xchg, and making it easier to detect if the wrong unlock function was previously used. Signed-off-by: Maarten Lankhorst <maarten.lankhorst(a)canonical.com> Acked-by: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: robclark(a)gmail.com Cc: rostedt(a)goodmis.org Cc: daniel(a)ffwll.ch Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/20130620113105.4001.83929.stgit@patser Signed-off-by: Ingo Molnar <mingo(a)kernel.org> commit 2bd2c92cf07cc4a373bf316c75b78ac465fefd35 Author: Waiman Long <Waiman.Long(a)hp.com> Date: Wed Apr 17 15:23:13 2013 -0400 mutex: Queue mutex spinners with MCS lock to reduce cacheline contention <-- snip --> commit 41fcb9f230bf773656d1768b73000ef720bf00c3 Author: Waiman Long <Waiman.Long(a)hp.com> Date: Wed Apr 17 15:23:11 2013 -0400 mutex: Move mutex spinning code from sched/core.c back to mutex.c <-- snip --> commit c5491ea779793f977d282754db478157cc409d82 Author: Thomas Gleixner <tglx(a)linutronix.de> Date: Mon Mar 21 12:09:35 2011 +0100 sched/rt: Add schedule_preempt_disabled() <-- snip --> Cc: maarten.lankhorst(a)canonical.com Cc: Daniel Vetter <daniel.vetter(a)ffwll.ch> Cc: Rob Clark <robdclark(a)gmail.com> Cc: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: rostedt(a)goodmis.org Cc: daniel(a)ffwll.ch Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: Luis R. Rodriguez <mcgrof(a)do-not-panic.com> --- backport/backport-include/linux/ww_mutex.h | 333 ++++++++++++++ backport/compat/Kconfig | 11 + backport/compat/Makefile | 1 + backport/compat/kernel/ww_mutex.c | 667 ++++++++++++++++++++++++++++ 4 files changed, 1012 insertions(+) create mode 100644 backport/backport-include/linux/ww_mutex.h create mode 100644 backport/compat/kernel/ww_mutex.c diff --git a/backport/backport-include/linux/ww_mutex.h b/backport/backport-include/linux/ww_mutex.h new file mode 100644 index 0000000..0953939 --- /dev/null +++ b/backport/backport-include/linux/ww_mutex.h @@ -0,0 +1,333 @@ +#ifndef __BACKPORT_LINUX_WW_MUTEX_H +#define __BACKPORT_LINUX_WW_MUTEX_H + +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0) +#include_next <linux/ww_mutex.h> +#else +#ifdef CPTCFG_BACKPORT_BUILD_WW_MUTEX +/* + * Wound/Wait Mutexes: blocking mutual exclusion locks with deadlock avoidance + * + * Original mutex implementation started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo(a)redhat.com> + * + * Wound/wait implementation: + * Copyright (C) 2013 Canonical Ltd. + * + * This file contains the main data structure and API definitions. + */ + +#include <linux/mutex.h> + +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; +}; + +struct ww_mutex { + struct mutex base; + struct ww_acquire_ctx *ctx; +}; + +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) + +#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_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) + +/** + * 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. + */ +#define ww_mutex_init LINUX_BACKPORT(ww_mutex_init) +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; +} + +/** + * 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. + */ +#define ww_acquire_init LINUX_BACKPORT(ww_acquire_init) +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; +} + +/** + * 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. + */ +#define ww_acquire_done LINUX_BACKPORT(ww_acquire_done) +static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) +{ +} + +/** + * 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. + */ +#define ww_acquire_fini LINUX_BACKPORT(ww_acquire_fini) +static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) +{ +} + +#define __ww_mutex_lock LINUX_BACKPORT(__ww_mutex_lock) +extern int __must_check __ww_mutex_lock(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); +#define __ww_mutex_lock_interruptible LINUX_BACKPORT(__ww_mutex_lock_interruptible) +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. + */ +#define ww_mutex_lock LINUX_BACKPORT(ww_mutex_lock) +static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + if (ctx) + return __ww_mutex_lock(lock, ctx); + + 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. + */ +#define ww_mutex_lock_interruptible LINUX_BACKPORT(ww_mutex_lock_interruptible) +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. + */ +#define ww_mutex_lock_slow LINUX_BACKPORT(ww_mutex_lock_slow) +static inline void +ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + 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. + */ +#define ww_mutex_lock_slow_interruptible LINUX_BACKPORT(ww_mutex_lock_slow_interruptible) +static inline int __must_check +ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + return ww_mutex_lock_interruptible(lock, ctx); +} + +#define ww_mutex_unlock LINUX_BACKPORT(ww_mutex_unlock) +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. + */ +#define ww_mutex_trylock LINUX_BACKPORT(ww_mutex_trylock) +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. + */ +#define ww_mutex_destroy LINUX_BACKPORT(ww_mutex_destroy) +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. + */ +#define ww_mutex_is_locked LINUX_BACKPORT(ww_mutex_is_locked) +static inline bool ww_mutex_is_locked(struct ww_mutex *lock) +{ + return mutex_is_locked(&lock->base); +} + +#endif /* CPTCFG_BACKPORT_BUILD_WW_MUTEX */ +#endif /* LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0) */ +#endif /* __BACKPORT_LINUX_WW_MUTEX_H */ diff --git a/backport/compat/Kconfig b/backport/compat/Kconfig index e2f0cdd..f3c1ab3 100644 --- a/backport/compat/Kconfig +++ b/backport/compat/Kconfig @@ -185,6 +185,17 @@ config BACKPORT_LEDS_CLASS config BACKPORT_LEDS_TRIGGERS bool +config BACKPORT_BUILD_WW_MUTEX + bool + # Build only if on kernels < 3.11 + # For now only DRM drivers use ww mutexes. + depends on DRM && BACKPORT_KERNEL_3_11 + default y if BACKPORT_USERSEL_BUILD_ALL + # probably a bad idea if you have these options given we + # ripped those options out. + depends on !DEBUG_MUTEXES + depends on !DEBUG_LOCK_ALLOC + config BACKPORT_BUILD_RADIX_HELPERS bool # You have selected to build backported DRM drivers diff --git a/backport/compat/Makefile b/backport/compat/Makefile index 252290e..fec01c4 100644 --- a/backport/compat/Makefile +++ b/backport/compat/Makefile @@ -41,3 +41,4 @@ compat-$(CPTCFG_BACKPORT_BUILD_KFIFO) += kfifo.o compat-$(CPTCFG_BACKPORT_BUILD_GENERIC_ATOMIC64) += compat_atomic.o compat-$(CPTCFG_BACKPORT_BUILD_DMA_SHARED_HELPERS) += dma-shared-helpers.o compat-$(CPTCFG_BACKPORT_BUILD_RADIX_HELPERS) += lib-radix-tree-helpers.o +compat-$(CPTCFG_BACKPORT_BUILD_WW_MUTEX) += kernel/ww_mutex.o diff --git a/backport/compat/kernel/ww_mutex.c b/backport/compat/kernel/ww_mutex.c new file mode 100644 index 0000000..257c2a4 --- /dev/null +++ b/backport/compat/kernel/ww_mutex.c @@ -0,0 +1,667 @@ +/* + * Copyright (c) 2013 Luis R. Rodriguez <mcgrof(a)do-not-panic.com> + * + * Backport ww mutex for older kernels. This is not supported when + * DEBUG_MUTEXES or DEBUG_LOCK_ALLOC is enabled. + * + * Taken from: kernel/mutex.c - via linux-stable v3.11-rc2 + * + * Mutexes: blocking mutual exclusion locks + * + * Started by Ingo Molnar: + * + * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo(a)redhat.com> + * + * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and + * David Howells for suggestions and improvements. + * + * - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline + * from the -rt tree, where it was originally implemented for rtmutexes + * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale + * and Sven Dietrich. + * + * Also see Documentation/mutex-design.txt. + */ + +#include <linux/mutex.h> +#include <linux/ww_mutex.h> +#include <asm/mutex.h> +#include <linux/sched.h> +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,9,0) +#include <linux/sched/rt.h> +#endif +#include <linux/export.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/debug_locks.h> +#include <linux/version.h> + +/* + * A negative mutex count indicates that waiters are sleeping waiting for the + * mutex. + */ +#define MUTEX_SHOW_NO_WAITER(mutex) (atomic_read(&(mutex)->count) >= 0) + +#define spin_lock_mutex(lock, flags) \ + do { spin_lock(lock); (void)(flags); } while (0) +#define spin_unlock_mutex(lock, flags) \ + do { spin_unlock(lock); (void)(flags); } while (0) +#define mutex_remove_waiter(lock, waiter, ti) \ + __list_del((waiter)->list.prev, (waiter)->list.next) + +#ifdef CONFIG_SMP +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current; +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} +#else +static inline void mutex_set_owner(struct mutex *lock) +{ +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ +} +#endif + + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0) /* 2bd2c92c and 41fcb9f2 */ +/* + * In order to avoid a stampede of mutex spinners from acquiring the mutex + * more or less simultaneously, the spinners need to acquire a MCS lock + * first before spinning on the owner field. + * + * We don't inline mspin_lock() so that perf can correctly account for the + * time spent in this lock function. + */ +struct mspin_node { + struct mspin_node *next ; + int locked; /* 1 if lock acquired */ +}; +#define MLOCK(mutex) ((struct mspin_node **)&((mutex)->spin_mlock)) + +static noinline +void mspin_lock(struct mspin_node **lock, struct mspin_node *node) +{ + struct mspin_node *prev; + + /* Init node */ + node->locked = 0; + node->next = NULL; + + prev = xchg(lock, node); + if (likely(prev == NULL)) { + /* Lock acquired */ + node->locked = 1; + return; + } + ACCESS_ONCE(prev->next) = node; + smp_wmb(); + /* Wait until the lock holder passes the lock down */ + while (!ACCESS_ONCE(node->locked)) + arch_mutex_cpu_relax(); +} + +static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node) +{ + struct mspin_node *next = ACCESS_ONCE(node->next); + + if (likely(!next)) { + /* + * Release the lock by setting it to NULL + */ + if (cmpxchg(lock, node, NULL) == node) + return; + /* Wait until the next pointer is set */ + while (!(next = ACCESS_ONCE(node->next))) + arch_mutex_cpu_relax(); + } + ACCESS_ONCE(next->locked) = 1; + smp_wmb(); +} + +/* + * Mutex spinning code migrated from kernel/sched/core.c + */ + +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ + if (lock->owner != owner) + return false; + + /* + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * lock->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. + */ + barrier(); + + return owner->on_cpu; +} + +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0) +static noinline +#endif +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ + rcu_read_lock(); + while (owner_running(lock, owner)) { + if (need_resched()) + break; + + arch_mutex_cpu_relax(); + } + rcu_read_unlock(); + + /* + * We break out the loop above on need_resched() and when the + * owner changed, which is a sign for heavy contention. Return + * success only when lock->owner is NULL. + */ + return lock->owner == NULL; +} + +/* + * Initial check for entering the mutex spinning loop + */ +static inline int mutex_can_spin_on_owner(struct mutex *lock) +{ + int retval = 1; + + rcu_read_lock(); + if (lock->owner) + retval = lock->owner->on_cpu; + rcu_read_unlock(); + /* + * if lock->owner is not set, the mutex owner may have just acquired + * it and not set the owner yet or the mutex has been released. + */ + return retval; +} +#else /* Backport 2bd2c92c: help keep backport_mutex_lock_common() clean */ + +struct mspin_node { +}; +#define MLOCK(mutex) NULL + +static noinline +void mspin_lock(struct mspin_node **lock, struct mspin_node *node) +{ +} + +static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node) +{ +} + +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ +} + +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ +} + +static inline int mutex_can_spin_on_owner(struct mutex *lock) +{ + return 1; +} +#endif /* LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0) */ +#endif /* CONFIG_MUTEX_SPIN_ON_OWNER */ + +/* + * Release the lock, slowpath: + */ +static inline void +__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) +{ + struct mutex *lock = container_of(lock_count, struct mutex, count); + unsigned long flags; + + spin_lock_mutex(&lock->wait_lock, flags); + mutex_release(&lock->dep_map, nested, _RET_IP_); + /* debug_mutex_unlock(lock); */ + + /* + * some architectures leave the lock unlocked in the fastpath failure + * case, others need to leave it locked. In the later case we have to + * unlock it here + */ + if (__mutex_slowpath_needs_to_unlock()) + atomic_set(&lock->count, 1); + + if (!list_empty(&lock->wait_list)) { + /* get the first entry from the wait-list: */ + struct mutex_waiter *waiter = + list_entry(lock->wait_list.next, + struct mutex_waiter, list); + + /* debug_mutex_wake_waiter(lock, waiter); */ + + wake_up_process(waiter->task); + } + + spin_unlock_mutex(&lock->wait_lock, flags); +} + +/* + * Release the lock, slowpath: + */ +static __used noinline void +__mutex_unlock_slowpath(atomic_t *lock_count) +{ + __mutex_unlock_common_slowpath(lock_count, 1); +} + +/** + * 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) { + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + + __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath); +} +EXPORT_SYMBOL_GPL(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)) { + return -EDEADLK; + } + + return 0; +} + +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ + 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); +} + +/** + * backport_schedule_preempt_disabled - called with preemption disabled + * + * Backports c5491ea7. This is not exported so we leave it + * here as this is the only current core user on backports. + * Although available on >= 3.4 its only for in-kernel code so + * we provide our own. + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +static void __sched backport_schedule_preempt_disabled(void) +{ + preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + +/* + * Lock a mutex (possibly interruptible), slowpath: + */ +static __always_inline int __sched +__backport_mutex_lock_common(struct mutex *lock, long state, + unsigned int subclass, + 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); + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + /* + * Optimistic spinning. + * + * We try to spin for acquisition when we find that there are no + * pending waiters and the lock owner is currently running on a + * (different) CPU. + * + * The rationale is that if the lock owner is running, it is likely to + * release the lock soon. + * + * Since this needs the lock owner, and this mutex implementation + * doesn't track the owner atomically in the lock field, we need to + * track it non-atomically. + * + * We can't do this for DEBUG_MUTEXES because that relies on wait_lock + * to serialize everything. + * + * The mutex spinners are queued up using MCS lock so that only one + * spinner can compete for the mutex. However, if mutex spinning isn't + * going to happen, there is no point in going through the lock/unlock + * overhead. + */ + if (!mutex_can_spin_on_owner(lock)) + goto slowpath; + + for (;;) { + 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. + */ + mspin_lock(MLOCK(lock), &node); + owner = ACCESS_ONCE(lock->owner); + if (owner && !mutex_spin_on_owner(lock, owner)) { + mspin_unlock(MLOCK(lock), &node); + break; + } + + 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(); + return 0; + } + mspin_unlock(MLOCK(lock), &node); + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(task))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + arch_mutex_cpu_relax(); + } +slowpath: +#endif + spin_lock_mutex(&lock->wait_lock, flags); + + /* We don't support DEBUG_MUTEXES on the backport */ + /* debug_mutex_lock_common(lock, &waiter); */ + /* debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); */ + + /* add waiting tasks to the end of the waitqueue (FIFO): */ + list_add_tail(&waiter.list, &lock->wait_list); + waiter.task = task; + + if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, -1) == 1)) + goto done; + + lock_contended(&lock->dep_map, ip); + + for (;;) { + /* + * Lets try to take the lock again - this is needed even if + * we get here for the first time (shortly after failing to + * acquire the lock), to make sure that we get a wakeup once + * it's unlocked. Later on, if we sleep, this is the + * operation that gives us the lock. We xchg it to -1, so + * that when we release the lock, we properly wake up the + * other waiters: + */ + if (MUTEX_SHOW_NO_WAITER(lock) && + (atomic_xchg(&lock->count, -1) == 1)) + break; + + /* + * got a signal? (This code gets eliminated in the + * TASK_UNINTERRUPTIBLE case.) + */ + if (unlikely(signal_pending_state(state, task))) { + ret = -EINTR; + goto err; + } + + 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: */ + spin_unlock_mutex(&lock->wait_lock, flags); + backport_schedule_preempt_disabled(); + spin_lock_mutex(&lock->wait_lock, flags); + } + +done: + lock_acquired(&lock->dep_map, ip); + /* got the lock - rejoice! */ + 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); + + spin_unlock_mutex(&lock->wait_lock, flags); + + /* debug_mutex_free_waiter(&waiter); */ + 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; +} + +static noinline int __sched +__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + return __backport_mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx); +} + +static noinline int __sched +__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + return __backport_mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, + NULL, _RET_IP_, ctx); +} + +/** + * __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 + * + * For backporting purposes we can't use the older kernel's + * __mutex_fastpath_lock_retval() since upon failure of a fastpath + * lock we want to call our a failure routine with more than one argument, in + * this case the context for ww mutexes. Refer to commit a41b56ef the + * argument increase. It'd be painful to backport all asm code for the + * supported architectures so instead lets penalize the backport ww mutex + * fastpath lock with the not so efficient generic atomic_dec_return() + * implementation. + * + * 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 +__backport_mutex_fastpath_lock_retval(atomic_t *count) +{ + if (unlikely(atomic_dec_return(count) < 0)) + return -1; + return 0; +} + +int __sched +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __backport_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_GPL(__ww_mutex_lock); + +int __sched +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + ret = __backport_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_GPL(__ww_mutex_lock_interruptible); -- 1.7.10.4

11 years, 4 months

[PATCH 1/1] dma-buf: Replace PTR_RET with PTR_ERR_OR_ZERO

by Sachin Kamat

PTR_RET is now deprecated. Use PTR_ERR_OR_ZERO instead. Signed-off-by: Sachin Kamat <sachin.kamat(a)linaro.org> --- Compile tested and based on the following tree: git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux.git (PTR_RET) Dependent on [1] [1] http://lkml.indiana.edu/hypermail/linux/kernel/1306.2/00010.html --- drivers/base/dma-buf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 6687ba7..1219ab7 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -680,7 +680,7 @@ int dma_buf_debugfs_create_file(const char *name, d = debugfs_create_file(name, S_IRUGO, dma_buf_debugfs_dir, write, &dma_buf_debug_fops); - return PTR_RET(d); + return PTR_ERR_OR_ZERO(d); } #else static inline int dma_buf_init_debugfs(void) -- 1.7.9.5

11 years, 5 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig July 2013