From f4333203ec933f9272c90c7add01774ec2cf94d3 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 16 Jun 2014 18:13:02 +0200 Subject: ASoC: Move name and id from CODEC/platform to component The component struct already has a name and id field which are initialized to the same values as the same fields in the CODEC and platform structs. So remove them from the CODEC and platform structs and used the ones from the component struct instead. Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- include/trace/events/asoc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h index c75c795a377b..0194a641e4e2 100644 --- a/include/trace/events/asoc.h +++ b/include/trace/events/asoc.h @@ -296,17 +296,17 @@ TRACE_EVENT(snd_soc_cache_sync, TP_ARGS(codec, type, status), TP_STRUCT__entry( - __string( name, codec->name ) + __string( name, codec->component.name) __string( status, status ) __string( type, type ) __field( int, id ) ), TP_fast_assign( - __assign_str(name, codec->name); + __assign_str(name, codec->component.name); __assign_str(status, status); __assign_str(type, type); - __entry->id = codec->id; + __entry->id = codec->component.id; ), TP_printk("codec=%s.%d type=%s status=%s", __get_str(name), -- cgit v1.2.3 From e941759c74a44d6ac2eed21bb0a38b21fe4559e2 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 1 Jul 2014 12:57:14 +0200 Subject: fence: dma-buf cross-device synchronization (v18) 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() When emitting a fence, call: + trace_fence_emit() To annotate that a fence is blocking on another fence, call: + trace_fence_annotate_wait_on(fence, on_fence) 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 = seqno_fence->sync_buf; get_dma_buf(fence_buf); ... tell the hw the memory location to wait ... custom_wait_on(fence_buf, seqno_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. v13: Fixup CONFIG_FENCE_TRACE kconfig description. Move fence_context_alloc to fence. Simplify fence_later. Kill priv member to fence_cb. v14: Remove priv argument from fence_add_callback, oops! v15: Remove priv from documentation. Explicitly include linux/atomic.h. v16: Add trace events. Import changes required by android syncpoints. v17: Use wake_up_state instead of try_to_wake_up. (Colin Cross) Fix up commit description for seqno_fence. (Rob Clark) v18: Rename release_fence to fence_release. Move to drivers/dma-buf/. Rename __fence_is_signaled and __fence_signal to *_locked. Rename __fence_init to fence_init. Make fence_default_wait return a signed long, and fix wait ops too. Signed-off-by: Maarten Lankhorst Signed-off-by: Thierry Reding #use smp_mb__before_atomic() Acked-by: Sumit Semwal Acked-by: Daniel Vetter Reviewed-by: Rob Clark Signed-off-by: Greg Kroah-Hartman --- Documentation/DocBook/device-drivers.tmpl | 2 + MAINTAINERS | 2 +- drivers/base/Kconfig | 9 + drivers/dma-buf/Makefile | 2 +- drivers/dma-buf/fence.c | 431 ++++++++++++++++++++++++++++++ include/linux/fence.h | 343 ++++++++++++++++++++++++ include/trace/events/fence.h | 128 +++++++++ 7 files changed, 915 insertions(+), 2 deletions(-) create mode 100644 drivers/dma-buf/fence.c create mode 100644 include/linux/fence.h create mode 100644 include/trace/events/fence.h (limited to 'include/trace') diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index ac61ebd92875..e634657efb52 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -129,6 +129,8 @@ X!Edrivers/base/interface.c Device Drivers DMA Management !Edrivers/dma-buf/dma-buf.c +!Edrivers/dma-buf/fence.c +!Iinclude/linux/fence.h !Iinclude/linux/reservation.h !Edrivers/base/dma-coherent.c !Edrivers/base/dma-mapping.c diff --git a/MAINTAINERS b/MAINTAINERS index 2eefee768d46..65c8f534b22f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2901,7 +2901,7 @@ L: linux-media@vger.kernel.org L: dri-devel@lists.freedesktop.org L: linaro-mm-sig@lists.linaro.org F: drivers/dma-buf/ -F: include/linux/dma-buf* include/linux/reservation.h +F: include/linux/dma-buf* include/linux/reservation.h include/linux/fence.h F: Documentation/dma-buf-sharing.txt T: git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 23b8726962af..00e13ce5cbbd 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -208,6 +208,15 @@ 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" + depends on DMA_SHARED_BUFFER + help + Enable the FENCE_TRACE printks. This will add extra + spam to the console log, but will make it easier to diagnose + lockup related problems for dma-buffers shared across multiple + devices. + config DMA_CMA bool "DMA Contiguous Memory Allocator" depends on HAVE_DMA_CONTIGUOUS && CMA diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 4a4f4c9bacd0..d7825bfe630e 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1 +1 @@ -obj-y := dma-buf.o reservation.o +obj-y := dma-buf.o fence.o reservation.o diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c new file mode 100644 index 000000000000..948bf00d955e --- /dev/null +++ b/drivers/dma-buf/fence.c @@ -0,0 +1,431 @@ +/* + * 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 + * Maarten Lankhorst + * + * 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. + */ + +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL(fence_annotate_wait_on); +EXPORT_TRACEPOINT_SYMBOL(fence_emit); + +/** + * 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. + */ +static atomic_t fence_context_counter = ATOMIC_INIT(0); + +/** + * fence_context_alloc - allocate an array of fence contexts + * @num: [in] amount of contexts to allocate + * + * This function will return the first index of the number of fences allocated. + * The fence context is used for setting fence->context to a unique number. + */ +unsigned fence_context_alloc(unsigned num) +{ + BUG_ON(!num); + return atomic_add_return(num, &fence_context_counter) - num; +} +EXPORT_SYMBOL(fence_context_alloc); + +/** + * fence_signal_locked - 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. + * + * Unlike fence_signal, this function must be called with fence->lock held. + */ +int fence_signal_locked(struct fence *fence) +{ + struct fence_cb *cur, *tmp; + int ret = 0; + + if (WARN_ON(!fence)) + return -EINVAL; + + if (!ktime_to_ns(fence->timestamp)) { + fence->timestamp = ktime_get(); + smp_mb__before_atomic(); + } + + 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 + */ + } else + trace_fence_signaled(fence); + + list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { + list_del_init(&cur->node); + cur->func(fence, cur); + } + return ret; +} +EXPORT_SYMBOL(fence_signal_locked); + +/** + * 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) + return -EINVAL; + + if (!ktime_to_ns(fence->timestamp)) { + fence->timestamp = ktime_get(); + smp_mb__before_atomic(); + } + + if (test_and_set_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return -EINVAL; + + trace_fence_signaled(fence); + + 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); + } + spin_unlock_irqrestore(fence->lock, flags); + } + return 0; +} +EXPORT_SYMBOL(fence_signal); + +/** + * 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. + */ +signed long +fence_wait_timeout(struct fence *fence, bool intr, signed long timeout) +{ + signed long ret; + + if (WARN_ON(timeout < 0)) + return -EINVAL; + + trace_fence_wait_start(fence); + ret = fence->ops->wait(fence, intr, timeout); + trace_fence_wait_end(fence); + return ret; +} +EXPORT_SYMBOL(fence_wait_timeout); + +void fence_release(struct kref *kref) +{ + struct fence *fence = + container_of(kref, struct fence, refcount); + + trace_fence_destroy(fence); + + BUG_ON(!list_empty(&fence->cb_list)); + + if (fence->ops->release) + fence->ops->release(fence); + else + fence_free(fence); +} +EXPORT_SYMBOL(fence_release); + +void fence_free(struct fence *fence) +{ + kfree(fence); +} +EXPORT_SYMBOL(fence_free); + +/** + * 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)) { + trace_fence_enable_signal(fence); + + spin_lock_irqsave(fence->lock, flags); + + if (!fence->ops->enable_signaling(fence)) + fence_signal_locked(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 + * + * 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) +{ + 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)) { + INIT_LIST_HEAD(&cb->node); + 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) { + trace_fence_enable_signal(fence); + + if (!fence->ops->enable_signaling(fence)) { + fence_signal_locked(fence); + ret = -ENOENT; + } + } + + if (!ret) { + cb->func = func; + list_add_tail(&cb->node, &fence->cb_list); + } else + INIT_LIST_HEAD(&cb->node); + 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 if 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); + +struct default_wait_cb { + struct fence_cb base; + struct task_struct *task; +}; + +static void +fence_default_wait_cb(struct fence *fence, struct fence_cb *cb) +{ + struct default_wait_cb *wait = + container_of(cb, struct default_wait_cb, base); + + wake_up_state(wait->task, TASK_NORMAL); +} + +/** + * 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. + */ +signed long +fence_default_wait(struct fence *fence, bool intr, signed long timeout) +{ + struct default_wait_cb cb; + unsigned long flags; + signed 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) { + trace_fence_enable_signal(fence); + + if (!fence->ops->enable_signaling(fence)) { + fence_signal_locked(fence); + goto out; + } + } + + cb.base.func = fence_default_wait_cb; + cb.task = current; + list_add(&cb.base.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.base.node)) + list_del(&cb.base.node); + __set_current_state(TASK_RUNNING); + +out: + spin_unlock_irqrestore(fence->lock, flags); + return ret; +} +EXPORT_SYMBOL(fence_default_wait); + +/** + * 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. + */ +void +fence_init(struct fence *fence, const struct fence_ops *ops, + spinlock_t *lock, unsigned context, unsigned seqno) +{ + BUG_ON(!lock); + BUG_ON(!ops || !ops->wait || !ops->enable_signaling || + !ops->get_driver_name || !ops->get_timeline_name); + + 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; + + trace_fence_init(fence); +} +EXPORT_SYMBOL(fence_init); diff --git a/include/linux/fence.h b/include/linux/fence.h new file mode 100644 index 000000000000..b935cc650123 --- /dev/null +++ b/include/linux/fence.h @@ -0,0 +1,343 @@ +/* + * Fence mechanism for dma-buf to allow for asynchronous dma access + * + * Copyright (C) 2012 Canonical Ltd + * Copyright (C) 2012 Texas Instruments + * + * Authors: + * Rob Clark + * Maarten Lankhorst + * + * 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. + */ + +#ifndef __LINUX_FENCE_H +#define __LINUX_FENCE_H + +#include +#include +#include +#include +#include +#include +#include + +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 + * @timestamp: Timestamp when the fence was signaled. + * @status: Optional, only valid if < 0, must be set before calling + * fence_signal, indicates that the fence has completed with an error. + * + * 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; + ktime_t timestamp; + int status; +}; + +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); + +/** + * 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 + * + * 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; +}; + +/** + * struct fence_ops - operations implemented for fence + * @get_driver_name: returns the driver name. + * @get_timeline_name: return the name of the context this fence belongs to. + * @enable_signaling: enable software signaling of fence. + * @signaled: [optional] peek whether the fence is signaled, can be null. + * @wait: custom wait implementation, or fence_default_wait. + * @release: [optional] called on destruction of fence, can be null + * @fill_driver_data: [optional] callback to fill in free-form debug info + * Returns amount of bytes filled, or -errno. + * @fence_value_str: [optional] fills in the value of the fence as a string + * @timeline_value_str: [optional] fills in the current value of the timeline + * as a string + * + * 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. + * + * fence->status may be set in enable_signaling, but only when false is + * returned. + * + * 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 signaled: + * May set fence->status if returning true. + * + * 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 { + const char * (*get_driver_name)(struct fence *fence); + const char * (*get_timeline_name)(struct fence *fence); + bool (*enable_signaling)(struct fence *fence); + bool (*signaled)(struct fence *fence); + signed long (*wait)(struct fence *fence, bool intr, signed long timeout); + void (*release)(struct fence *fence); + + int (*fill_driver_data)(struct fence *fence, void *data, int size); + void (*fence_value_str)(struct fence *fence, char *str, int size); + void (*timeline_value_str)(struct fence *fence, char *str, int size); +}; + +void fence_init(struct fence *fence, const struct fence_ops *ops, + spinlock_t *lock, unsigned context, unsigned seqno); + +void fence_release(struct kref *kref); +void fence_free(struct fence *fence); + +/** + * fence_get - increases refcount of the fence + * @fence: [in] fence to increase refcount of + * + * Returns the same fence, with refcount increased by 1. + */ +static inline struct fence *fence_get(struct fence *fence) +{ + if (fence) + kref_get(&fence->refcount); + return fence; +} + +/** + * fence_put - decreases refcount of the fence + * @fence: [in] fence to reduce refcount of + */ +static inline void fence_put(struct fence *fence) +{ + if (fence) + kref_put(&fence->refcount, fence_release); +} + +int fence_signal(struct fence *fence); +int fence_signal_locked(struct fence *fence); +signed 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); +bool fence_remove_callback(struct fence *fence, struct fence_cb *cb); +void fence_enable_sw_signaling(struct fence *fence); + +/** + * fence_is_signaled_locked - 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. + * + * This function requires fence->lock to be held. + */ +static inline bool +fence_is_signaled_locked(struct fence *fence) +{ + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return true; + + if (fence->ops->signaled && fence->ops->signaled(fence)) { + fence_signal_locked(fence); + return true; + } + + return false; +} + +/** + * 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) +{ + if (WARN_ON(f1->context != f2->context)) + return NULL; + + /* + * can't check just FENCE_FLAG_SIGNALED_BIT here, it may never have been + * set if enable_signaling wasn't called, and enabling that here is + * overkill. + */ + if (f2->seqno - f1->seqno <= INT_MAX) + return fence_is_signaled(f2) ? NULL : f2; + else + return fence_is_signaled(f1) ? NULL : f1; +} + +signed long fence_wait_timeout(struct fence *, bool intr, signed long 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 holds a reference to the fence, otherwise the + * fence might be freed before return, resulting in undefined behavior. + */ +static inline signed long fence_wait(struct fence *fence, bool intr) +{ + signed 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; +} + +unsigned fence_context_alloc(unsigned 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 */ diff --git a/include/trace/events/fence.h b/include/trace/events/fence.h new file mode 100644 index 000000000000..98feb1b82896 --- /dev/null +++ b/include/trace/events/fence.h @@ -0,0 +1,128 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM fence + +#if !defined(_TRACE_FENCE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_FENCE_H + +#include + +struct fence; + +TRACE_EVENT(fence_annotate_wait_on, + + /* fence: the fence waiting on f1, f1: the fence to be waited on. */ + TP_PROTO(struct fence *fence, struct fence *f1), + + TP_ARGS(fence, f1), + + TP_STRUCT__entry( + __string(driver, fence->ops->get_driver_name(fence)) + __string(timeline, fence->ops->get_driver_name(fence)) + __field(unsigned int, context) + __field(unsigned int, seqno) + + __string(waiting_driver, f1->ops->get_driver_name(f1)) + __string(waiting_timeline, f1->ops->get_timeline_name(f1)) + __field(unsigned int, waiting_context) + __field(unsigned int, waiting_seqno) + ), + + TP_fast_assign( + __assign_str(driver, fence->ops->get_driver_name(fence)) + __assign_str(timeline, fence->ops->get_timeline_name(fence)) + __entry->context = fence->context; + __entry->seqno = fence->seqno; + + __assign_str(waiting_driver, f1->ops->get_driver_name(f1)) + __assign_str(waiting_timeline, f1->ops->get_timeline_name(f1)) + __entry->waiting_context = f1->context; + __entry->waiting_seqno = f1->seqno; + + ), + + TP_printk("driver=%s timeline=%s context=%u seqno=%u " \ + "waits on driver=%s timeline=%s context=%u seqno=%u", + __get_str(driver), __get_str(timeline), __entry->context, + __entry->seqno, + __get_str(waiting_driver), __get_str(waiting_timeline), + __entry->waiting_context, __entry->waiting_seqno) +); + +DECLARE_EVENT_CLASS(fence, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence), + + TP_STRUCT__entry( + __string(driver, fence->ops->get_driver_name(fence)) + __string(timeline, fence->ops->get_timeline_name(fence)) + __field(unsigned int, context) + __field(unsigned int, seqno) + ), + + TP_fast_assign( + __assign_str(driver, fence->ops->get_driver_name(fence)) + __assign_str(timeline, fence->ops->get_timeline_name(fence)) + __entry->context = fence->context; + __entry->seqno = fence->seqno; + ), + + TP_printk("driver=%s timeline=%s context=%u seqno=%u", + __get_str(driver), __get_str(timeline), __entry->context, + __entry->seqno) +); + +DEFINE_EVENT(fence, fence_emit, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence) +); + +DEFINE_EVENT(fence, fence_init, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence) +); + +DEFINE_EVENT(fence, fence_destroy, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence) +); + +DEFINE_EVENT(fence, fence_enable_signal, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence) +); + +DEFINE_EVENT(fence, fence_signaled, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence) +); + +DEFINE_EVENT(fence, fence_wait_start, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence) +); + +DEFINE_EVENT(fence, fence_wait_end, + + TP_PROTO(struct fence *fence), + + TP_ARGS(fence) +); + +#endif /* _TRACE_FENCE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 24a9ee0fa3d40415765d2d9f6064930d72ad8b5a Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 25 Jul 2014 17:46:10 -0700 Subject: f2fs: add tracepoint for f2fs_issue_flush This patch adds a tracepoint for f2fs_issue_flush. Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.c | 3 +++ include/trace/events/f2fs.h | 24 ++++++++++++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/trace') diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index e016b97be2ac..5a53a0ac6e4f 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -239,6 +239,9 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info; struct flush_cmd cmd; + trace_f2fs_issue_flush(sbi->sb, test_opt(sbi, NOBARRIER), + test_opt(sbi, FLUSH_MERGE)); + if (test_opt(sbi, NOBARRIER)) return 0; diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index b983990b4a9f..7d2e70e75f16 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -926,6 +926,30 @@ TRACE_EVENT(f2fs_issue_discard, (unsigned long long)__entry->blkstart, (unsigned long long)__entry->blklen) ); + +TRACE_EVENT(f2fs_issue_flush, + + TP_PROTO(struct super_block *sb, bool nobarrier, bool flush_merge), + + TP_ARGS(sb, nobarrier, flush_merge), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(bool, nobarrier) + __field(bool, flush_merge) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->nobarrier = nobarrier; + __entry->flush_merge = flush_merge; + ), + + TP_printk("dev = (%d,%d), %s %s", + show_dev(__entry), + __entry->nobarrier ? "skip (nobarrier)" : "issue", + __entry->flush_merge ? " with flush_merge" : "") +); #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 70407fad85f2ec87a0cf56057c3267cd3aa22768 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 31 Jul 2014 21:11:22 +0800 Subject: f2fs: add tracepoint for f2fs_direct_IO This patch adds a tracepoint for f2fs_direct_IO. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 5 ++++ include/trace/events/f2fs.h | 63 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) (limited to 'include/trace') diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ec3c8860539e..03313099c51c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1086,9 +1086,14 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, /* clear fsync mark to recover these blocks */ fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino); + trace_f2fs_direct_IO_enter(inode, offset, count, rw); + err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block); if (err < 0 && (rw & WRITE)) f2fs_write_failed(mapping, offset + count); + + trace_f2fs_direct_IO_exit(inode, offset, count, rw, err); + return err; } diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 7d2e70e75f16..d06d44363fea 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -587,6 +587,69 @@ TRACE_EVENT(f2fs_fallocate, __entry->ret) ); +TRACE_EVENT(f2fs_direct_IO_enter, + + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw), + + TP_ARGS(inode, offset, len, rw), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, pos) + __field(unsigned long, len) + __field(int, rw) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = offset; + __entry->len = len; + __entry->rw = rw; + ), + + TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu rw = %d", + show_dev_ino(__entry), + __entry->pos, + __entry->len, + __entry->rw) +); + +TRACE_EVENT(f2fs_direct_IO_exit, + + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, + int rw, int ret), + + TP_ARGS(inode, offset, len, rw, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, pos) + __field(unsigned long, len) + __field(int, rw) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = offset; + __entry->len = len; + __entry->rw = rw; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu " + "rw = %d ret = %d", + show_dev_ino(__entry), + __entry->pos, + __entry->len, + __entry->rw, + __entry->ret) +); + TRACE_EVENT(f2fs_reserve_new_block, TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node), -- cgit v1.2.3 From 60ae81eee86dd7a520db8c1e3d702b49fc0418b5 Mon Sep 17 00:00:00 2001 From: Slava Pestov Date: Thu, 22 May 2014 12:14:24 -0700 Subject: bcache: bcache_write tracepoint was crashing Signed-off-by: Kent Overstreet --- drivers/md/bcache/request.c | 3 ++- include/trace/events/bcache.h | 15 +++++++++------ 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/trace') diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 15fff4f68a7c..62e6e98186b5 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -311,7 +311,8 @@ void bch_data_insert(struct closure *cl) { struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); - trace_bcache_write(op->bio, op->writeback, op->bypass); + trace_bcache_write(op->c, op->inode, op->bio, + op->writeback, op->bypass); bch_keylist_init(&op->insert_keys); bio_get(op->bio); diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index c9c3c044b32f..6778e4135a8e 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -148,11 +148,13 @@ TRACE_EVENT(bcache_read, ); TRACE_EVENT(bcache_write, - TP_PROTO(struct bio *bio, bool writeback, bool bypass), - TP_ARGS(bio, writeback, bypass), + TP_PROTO(struct cache_set *c, u64 inode, struct bio *bio, + bool writeback, bool bypass), + TP_ARGS(c, inode, bio, writeback, bypass), TP_STRUCT__entry( - __field(dev_t, dev ) + __array(char, uuid, 16 ) + __field(u64, inode ) __field(sector_t, sector ) __field(unsigned int, nr_sector ) __array(char, rwbs, 6 ) @@ -161,7 +163,8 @@ TRACE_EVENT(bcache_write, ), TP_fast_assign( - __entry->dev = bio->bi_bdev->bd_dev; + memcpy(__entry->uuid, c->sb.set_uuid, 16); + __entry->inode = inode; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); @@ -169,8 +172,8 @@ TRACE_EVENT(bcache_write, __entry->bypass = bypass; ), - TP_printk("%d,%d %s %llu + %u hit %u bypass %u", - MAJOR(__entry->dev), MINOR(__entry->dev), + TP_printk("%pU inode %llu %s %llu + %u hit %u bypass %u", + __entry->uuid, __entry->inode, __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, __entry->writeback, __entry->bypass) ); -- cgit v1.2.3 From 913dc33fb2720fb5f979011664294137ddd8b13b Mon Sep 17 00:00:00 2001 From: Slava Pestov Date: Fri, 23 May 2014 11:18:35 -0700 Subject: bcache: fix crash in bcache_btree_node_alloc_fail tracepoint 'b' was NULL. Change-Id: Icac0fd04afa2d23f213d96d51afd53374e6dd0c0 --- drivers/md/bcache/btree.c | 2 +- include/trace/events/bcache.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 39c7f5b73724..f8237856a61b 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1096,7 +1096,7 @@ err_free: err: mutex_unlock(&c->bucket_lock); - trace_bcache_btree_node_alloc_fail(b); + trace_bcache_btree_node_alloc_fail(c); return b; } diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index 6778e4135a8e..981acf74b14f 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -261,9 +261,9 @@ DEFINE_EVENT(btree_node, bcache_btree_node_alloc, TP_ARGS(b) ); -DEFINE_EVENT(btree_node, bcache_btree_node_alloc_fail, - TP_PROTO(struct btree *b), - TP_ARGS(b) +DEFINE_EVENT(cache_set, bcache_btree_node_alloc_fail, + TP_PROTO(struct cache_set *c), + TP_ARGS(c) ); DEFINE_EVENT(btree_node, bcache_btree_node_free, -- cgit v1.2.3 From c77dcacb397519b6ade8f08201a4a90a7f4f751e Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 6 Aug 2014 14:24:45 +0200 Subject: KVM: Move more code under CONFIG_HAVE_KVM_IRQFD Commits e4d57e1ee1ab (KVM: Move irq notifier implementation into eventfd.c, 2014-06-30) included the irq notifier code unconditionally in eventfd.c, while it was under CONFIG_HAVE_KVM_IRQCHIP before. Similarly, commit 297e21053a52 (KVM: Give IRQFD its own separate enabling Kconfig option, 2014-06-30) moved code from CONFIG_HAVE_IRQ_ROUTING to CONFIG_HAVE_KVM_IRQFD but forgot to move the pieces that used to be under CONFIG_HAVE_KVM_IRQCHIP. Together, this broke compilation without CONFIG_KVM_XICS. Fix by adding or changing the #ifdefs so that they point at CONFIG_HAVE_KVM_IRQFD. Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 + include/trace/events/kvm.h | 8 +-- virt/kvm/eventfd.c | 122 ++++++++++++++++++++++----------------------- virt/kvm/kvm_main.c | 2 + 4 files changed, 69 insertions(+), 65 deletions(-) (limited to 'include/trace') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8593d2e61cbf..a4c33b34fe3f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -388,6 +388,8 @@ struct kvm { */ struct kvm_irq_routing_table __rcu *irq_routing; struct hlist_head mask_notifier_list; +#endif +#ifdef CONFIG_HAVE_KVM_IRQFD struct hlist_head irq_ack_notifier_list; #endif diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 131a0bda7aec..908925ace776 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -37,7 +37,7 @@ TRACE_EVENT(kvm_userspace_exit, __entry->errno < 0 ? -__entry->errno : __entry->reason) ); -#if defined(CONFIG_HAVE_KVM_IRQCHIP) +#if defined(CONFIG_HAVE_KVM_IRQFD) TRACE_EVENT(kvm_set_irq, TP_PROTO(unsigned int gsi, int level, int irq_source_id), TP_ARGS(gsi, level, irq_source_id), @@ -57,7 +57,7 @@ TRACE_EVENT(kvm_set_irq, TP_printk("gsi %u level %d source %d", __entry->gsi, __entry->level, __entry->irq_source_id) ); -#endif +#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */ #if defined(__KVM_HAVE_IOAPIC) #define kvm_deliver_mode \ @@ -124,7 +124,7 @@ TRACE_EVENT(kvm_msi_set_irq, #endif /* defined(__KVM_HAVE_IOAPIC) */ -#if defined(CONFIG_HAVE_KVM_IRQCHIP) +#if defined(CONFIG_HAVE_KVM_IRQFD) TRACE_EVENT(kvm_ack_irq, TP_PROTO(unsigned int irqchip, unsigned int pin), @@ -149,7 +149,7 @@ TRACE_EVENT(kvm_ack_irq, #endif ); -#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ +#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */ diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index f5f61548f60d..3c5981c87c3f 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -445,6 +445,67 @@ out: kfree(irqfd); return ret; } + +bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + struct kvm_irq_ack_notifier *kian; + int gsi, idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) + hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, + link) + if (kian->gsi == gsi) { + srcu_read_unlock(&kvm->irq_srcu, idx); + return true; + } + + srcu_read_unlock(&kvm->irq_srcu, idx); + + return false; +} +EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); + +void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + struct kvm_irq_ack_notifier *kian; + int gsi, idx; + + trace_kvm_ack_irq(irqchip, pin); + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) + hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, + link) + if (kian->gsi == gsi) + kian->irq_acked(kian); + srcu_read_unlock(&kvm->irq_srcu, idx); +} + +void kvm_register_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian) +{ + mutex_lock(&kvm->irq_lock); + hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); + mutex_unlock(&kvm->irq_lock); +#ifdef __KVM_HAVE_IOAPIC + kvm_vcpu_request_scan_ioapic(kvm); +#endif +} + +void kvm_unregister_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian) +{ + mutex_lock(&kvm->irq_lock); + hlist_del_init_rcu(&kian->link); + mutex_unlock(&kvm->irq_lock); + synchronize_srcu(&kvm->irq_srcu); +#ifdef __KVM_HAVE_IOAPIC + kvm_vcpu_request_scan_ioapic(kvm); +#endif +} #endif void @@ -867,64 +928,3 @@ kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) return kvm_assign_ioeventfd(kvm, args); } - -bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) -{ - struct kvm_irq_ack_notifier *kian; - int gsi, idx; - - idx = srcu_read_lock(&kvm->irq_srcu); - gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); - if (gsi != -1) - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) { - srcu_read_unlock(&kvm->irq_srcu, idx); - return true; - } - - srcu_read_unlock(&kvm->irq_srcu, idx); - - return false; -} -EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); - -void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) -{ - struct kvm_irq_ack_notifier *kian; - int gsi, idx; - - trace_kvm_ack_irq(irqchip, pin); - - idx = srcu_read_lock(&kvm->irq_srcu); - gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); - if (gsi != -1) - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) - kian->irq_acked(kian); - srcu_read_unlock(&kvm->irq_srcu, idx); -} - -void kvm_register_irq_ack_notifier(struct kvm *kvm, - struct kvm_irq_ack_notifier *kian) -{ - mutex_lock(&kvm->irq_lock); - hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); - mutex_unlock(&kvm->irq_lock); -#ifdef __KVM_HAVE_IOAPIC - kvm_vcpu_request_scan_ioapic(kvm); -#endif -} - -void kvm_unregister_irq_ack_notifier(struct kvm *kvm, - struct kvm_irq_ack_notifier *kian) -{ - mutex_lock(&kvm->irq_lock); - hlist_del_init_rcu(&kian->link); - mutex_unlock(&kvm->irq_lock); - synchronize_srcu(&kvm->irq_srcu); -#ifdef __KVM_HAVE_IOAPIC - kvm_vcpu_request_scan_ioapic(kvm); -#endif -} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a69a623938b8..33712fb26eb1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -465,6 +465,8 @@ static struct kvm *kvm_create_vm(unsigned long type) #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); +#endif +#ifdef CONFIG_HAVE_KVM_IRQFD INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif -- cgit v1.2.3 From 4a262d265878477a46c842e47d1c2b5ce6f66477 Mon Sep 17 00:00:00 2001 From: Max Asbock Date: Wed, 6 Aug 2014 16:06:21 -0700 Subject: mm tracing: tell mm_migrate_pages event about numa_misplaced The mm_migrate_pages trace event reports a reason for the migration, typically as a symbolic string. The exception is the reason MR_NUMA_MISPLACED for which it just displays the numeric value: mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=0x5 This patch makes the output consistent by introducing a string value for MR_NUMA_MISPLACED. The event is then reported as: mm_migrate_pages: nr_succeeded=1 nr_failed=0 mode=MIGRATE_ASYNC reason=numa_misplaced Signed-off-by: Max Asbock Acked-by: Steven Rostedt Cc: Ingo Molnar Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/migrate.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 4e4f2f8b1ac2..dd2b5467d905 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -17,6 +17,7 @@ {MR_MEMORY_HOTPLUG, "memory_hotplug"}, \ {MR_SYSCALL, "syscall_or_cpuset"}, \ {MR_MEMPOLICY_MBIND, "mempolicy_mbind"}, \ + {MR_NUMA_MISPLACED, "numa_misplaced"}, \ {MR_CMA, "cma"} TRACE_EVENT(mm_migrate_pages, -- cgit v1.2.3 From 24b7e5819ad5cbef2b7c7376510862aa8319d240 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 6 Aug 2014 16:07:11 -0700 Subject: mm: pagemap: avoid unnecessary overhead when tracepoints are deactivated This was formerly the series "Improve sequential read throughput" which noted some major differences in performance of tiobench since 3.0. While there are a number of factors, two that dominated were the introduction of the fair zone allocation policy and changes to CFQ. The behaviour of fair zone allocation policy makes more sense than tiobench as a benchmark and CFQ defaults were not changed due to insufficient benchmarking. This series is what's left. It's one functional fix to the fair zone allocation policy when used on NUMA machines and a reduction of overhead in general. tiobench was used for the comparison despite its flaws as an IO benchmark as in this case we are primarily interested in the overhead of page allocator and page reclaim activity. On UMA, it makes little difference to overhead 3.16.0-rc3 3.16.0-rc3 vanilla lowercost-v5 User 383.61 386.77 System 403.83 401.74 Elapsed 5411.50 5413.11 On a 4-socket NUMA machine it's a bit more noticable 3.16.0-rc3 3.16.0-rc3 vanilla lowercost-v5 User 746.94 802.00 System 65336.22 40852.33 Elapsed 27553.52 27368.46 This patch (of 6): The LRU insertion and activate tracepoints take PFN as a parameter forcing the overhead to the caller. Move the overhead to the tracepoint fast-assign method to ensure the cost is only incurred when the tracepoint is active. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/pagemap.h | 16 +++++++--------- mm/swap.c | 4 ++-- 2 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index 1c9fabde69e4..ce0803b8d05f 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -28,12 +28,10 @@ TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, - unsigned long pfn, - int lru, - unsigned long flags + int lru ), - TP_ARGS(page, pfn, lru, flags), + TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) @@ -44,9 +42,9 @@ TRACE_EVENT(mm_lru_insertion, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); __entry->lru = lru; - __entry->flags = flags; + __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ @@ -64,9 +62,9 @@ TRACE_EVENT(mm_lru_insertion, TRACE_EVENT(mm_lru_activate, - TP_PROTO(struct page *page, unsigned long pfn), + TP_PROTO(struct page *page), - TP_ARGS(page, pfn), + TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) @@ -75,7 +73,7 @@ TRACE_EVENT(mm_lru_activate, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ diff --git a/mm/swap.c b/mm/swap.c index d8eb4d09ffa2..c789d01c9ec3 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -501,7 +501,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec, SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); - trace_mm_lru_activate(page, page_to_pfn(page)); + trace_mm_lru_activate(page); __count_vm_event(PGACTIVATE); update_page_reclaim_stat(lruvec, file, 1); @@ -988,7 +988,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, SetPageLRU(page); add_page_to_lru_list(page, lruvec, lru); update_page_reclaim_stat(lruvec, file, active); - trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page)); + trace_mm_lru_insertion(page, lru); } /* -- cgit v1.2.3 From f6d9804d145b9c42dbbabefdda208a6a492b2236 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Fri, 25 Jul 2014 16:05:30 -0400 Subject: tracepoint: add generic tracepoint definitions for IPI tracing The Inter Processor Interrupt is used to make another processor do a specific action such as rescheduling tasks, signal a timer event or execute something in another CPU's context. IRQs are already traceable but IPIs were not. Tracing them is useful for monitoring IPI latency, or to verify when they are the source of CPU wake-ups with power management implications. Three trace hooks are defined: ipi_raise, ipi_entry and ipi_exit. To make them portable, a string is used to identify them and correlate related events. Additionally, ipi_raise records a bitmask representing targeted CPUs. Link: http://lkml.kernel.org/p/1406318733-26754-3-git-send-email-nicolas.pitre@linaro.org Acked-by: Daniel Lezcano Signed-off-by: Nicolas Pitre Signed-off-by: Steven Rostedt --- include/trace/events/ipi.h | 89 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 include/trace/events/ipi.h (limited to 'include/trace') diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h new file mode 100644 index 000000000000..834a7362a610 --- /dev/null +++ b/include/trace/events/ipi.h @@ -0,0 +1,89 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ipi + +#if !defined(_TRACE_IPI_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IPI_H + +#include + +/** + * ipi_raise - called when a smp cross call is made + * + * @mask: mask of recipient CPUs for the IPI + * @reason: string identifying the IPI purpose + * + * It is necessary for @reason to be a static string declared with + * __tracepoint_string. + */ +TRACE_EVENT(ipi_raise, + + TP_PROTO(const struct cpumask *mask, const char *reason), + + TP_ARGS(mask, reason), + + TP_STRUCT__entry( + __bitmask(target_cpus, nr_cpumask_bits) + __field(const char *, reason) + ), + + TP_fast_assign( + __assign_bitmask(target_cpus, cpumask_bits(mask), nr_cpumask_bits); + __entry->reason = reason; + ), + + TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) +); + +DECLARE_EVENT_CLASS(ipi_handler, + + TP_PROTO(const char *reason), + + TP_ARGS(reason), + + TP_STRUCT__entry( + __field(const char *, reason) + ), + + TP_fast_assign( + __entry->reason = reason; + ), + + TP_printk("(%s)", __entry->reason) +); + +/** + * ipi_entry - called immediately before the IPI handler + * + * @reason: string identifying the IPI purpose + * + * It is necessary for @reason to be a static string declared with + * __tracepoint_string, ideally the same as used with trace_ipi_raise + * for that IPI. + */ +DEFINE_EVENT(ipi_handler, ipi_entry, + + TP_PROTO(const char *reason), + + TP_ARGS(reason) +); + +/** + * ipi_exit - called immediately after the IPI handler returns + * + * @reason: string identifying the IPI purpose + * + * It is necessary for @reason to be a static string declared with + * __tracepoint_string, ideally the same as used with trace_ipi_raise for + * that IPI. + */ +DEFINE_EVENT(ipi_handler, ipi_exit, + + TP_PROTO(const char *reason), + + TP_ARGS(reason) +); + +#endif /* _TRACE_IPI_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 9e813308a5c18c58f9ccae1ec72ed4e14eaf9025 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 13 Aug 2014 12:32:04 +0530 Subject: powerpc/thp: Add tracepoints to track hugepage invalidate Add tracepoint to track hugepage invalidate. This help us in debugging difficult to track bugs. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/pgtable_64.c | 6 +++ arch/powerpc/mm/tlb_hash64.c | 4 ++ include/trace/events/thp.h | 88 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 98 insertions(+) create mode 100644 include/trace/events/thp.h (limited to 'include/trace') diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 948a81e02ddb..c8d709ab489d 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -54,6 +54,9 @@ #include "mmu_decl.h" +#define CREATE_TRACE_POINTS +#include + /* Some sanity checking */ #if TASK_SIZE_USER64 > PGTABLE_RANGE #error TASK_SIZE_USER64 exceeds pagetable range @@ -537,6 +540,7 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, old = pmd_val(*pmdp); *pmdp = __pmd((old & ~clr) | set); #endif + trace_hugepage_update(addr, old, clr, set); if (old & _PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp, old); return old; @@ -642,6 +646,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, * If we didn't had the splitting flag set, go and flush the * HPTE entries. */ + trace_hugepage_splitting(address, old); if (!(old & _PAGE_SPLITTING)) { /* We need to flush the hpte */ if (old & _PAGE_HASHPTE) @@ -709,6 +714,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, assert_spin_locked(&mm->page_table_lock); WARN_ON(!pmd_trans_huge(pmd)); #endif + trace_hugepage_set_pmd(addr, pmd); return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 9adda5790463..d2a94b85dbc2 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -30,6 +30,8 @@ #include #include +#include + DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); /* @@ -213,6 +215,8 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, if (ptep == NULL) continue; pte = pte_val(*ptep); + if (hugepage_shift) + trace_hugepage_invalidate(start, pte_val(pte)); if (!(pte & _PAGE_HASHPTE)) continue; if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte))) diff --git a/include/trace/events/thp.h b/include/trace/events/thp.h new file mode 100644 index 000000000000..b59b065e9e5d --- /dev/null +++ b/include/trace/events/thp.h @@ -0,0 +1,88 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM thp + +#if !defined(_TRACE_THP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_THP_H + +#include +#include + +TRACE_EVENT(hugepage_invalidate, + + TP_PROTO(unsigned long addr, unsigned long pte), + TP_ARGS(addr, pte), + TP_STRUCT__entry( + __field(unsigned long, addr) + __field(unsigned long, pte) + ), + + TP_fast_assign( + __entry->addr = addr; + __entry->pte = pte; + ), + + TP_printk("hugepage invalidate at addr 0x%lx and pte = 0x%lx", + __entry->addr, __entry->pte) +); + +TRACE_EVENT(hugepage_set_pmd, + + TP_PROTO(unsigned long addr, unsigned long pmd), + TP_ARGS(addr, pmd), + TP_STRUCT__entry( + __field(unsigned long, addr) + __field(unsigned long, pmd) + ), + + TP_fast_assign( + __entry->addr = addr; + __entry->pmd = pmd; + ), + + TP_printk("Set pmd with 0x%lx with 0x%lx", __entry->addr, __entry->pmd) +); + + +TRACE_EVENT(hugepage_update, + + TP_PROTO(unsigned long addr, unsigned long pte, unsigned long clr, unsigned long set), + TP_ARGS(addr, pte, clr, set), + TP_STRUCT__entry( + __field(unsigned long, addr) + __field(unsigned long, pte) + __field(unsigned long, clr) + __field(unsigned long, set) + ), + + TP_fast_assign( + __entry->addr = addr; + __entry->pte = pte; + __entry->clr = clr; + __entry->set = set; + + ), + + TP_printk("hugepage update at addr 0x%lx and pte = 0x%lx clr = 0x%lx, set = 0x%lx", __entry->addr, __entry->pte, __entry->clr, __entry->set) +); +TRACE_EVENT(hugepage_splitting, + + TP_PROTO(unsigned long addr, unsigned long pte), + TP_ARGS(addr, pte), + TP_STRUCT__entry( + __field(unsigned long, addr) + __field(unsigned long, pte) + ), + + TP_fast_assign( + __entry->addr = addr; + __entry->pte = pte; + ), + + TP_printk("hugepage splitting at addr 0x%lx and pte = 0x%lx", + __entry->addr, __entry->pte) +); + +#endif /* _TRACE_THP_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3