From c9d53c0f2d23c792e4b9cf1551b63de4516f839e Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Wed, 11 Jun 2014 14:00:05 +0900 Subject: devres: remove devm_request_and_ioremap() devm_request_and_ioremap() was obsoleted by the commit 7509657 ("lib: devres: Introduce devm_ioremap_resource()") and has been deprecated for a long time. So, let's remove this function. In addition, all usages of devm_request_and_ioremap() are also removed. Signed-off-by: Jingoo Han Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index af424acd393d..921fa0a74df6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -631,8 +631,6 @@ extern unsigned long devm_get_free_pages(struct device *dev, extern void devm_free_pages(struct device *dev, unsigned long addr); void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res); -void __iomem *devm_request_and_ioremap(struct device *dev, - struct resource *res); /* allows to add/remove a custom action to devres stack */ int devm_add_action(struct device *dev, void (*action)(void *), void *data); -- cgit v1.2.3-59-g8ed1b From 6955b58254c2bcee8a7b55ce06468a645dc98ec5 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 19 Apr 2014 11:18:01 +0100 Subject: component: add support for component match array Add support for generating a set of component matches at master probe time, and submitting them to the component layer. This allows the component layer to perform the matches internally without needing to call into the master driver, and allows for further restructuring of the component helper. Acked-by: Laurent Pinchart Signed-off-by: Russell King --- drivers/base/component.c | 120 ++++++++++++++++++++++++++++++++++++++++++++-- include/linux/component.h | 7 +++ 2 files changed, 124 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/component.c b/drivers/base/component.c index 55813e91bf0d..b4236daed4fa 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -18,6 +18,15 @@ #include #include +struct component_match { + size_t alloc; + size_t num; + struct { + void *data; + int (*fn)(struct device *, void *); + } compare[0]; +}; + struct master { struct list_head node; struct list_head components; @@ -25,6 +34,7 @@ struct master { const struct component_master_ops *ops; struct device *dev; + struct component_match *match; }; struct component { @@ -96,6 +106,34 @@ int component_master_add_child(struct master *master, } EXPORT_SYMBOL_GPL(component_master_add_child); +static int find_components(struct master *master) +{ + struct component_match *match = master->match; + size_t i; + int ret = 0; + + if (!match) { + /* + * Search the list of components, looking for components that + * belong to this master, and attach them to the master. + */ + return master->ops->add_components(master->dev, master); + } + + /* + * Scan the array of match functions and attach + * any components which are found to this master. + */ + for (i = 0; i < match->num; i++) { + ret = component_master_add_child(master, + match->compare[i].fn, + match->compare[i].data); + if (ret) + break; + } + return ret; +} + /* Detach all attached components from this master */ static void master_remove_components(struct master *master) { @@ -128,7 +166,7 @@ static int try_to_bring_up_master(struct master *master, * Search the list of components, looking for components that * belong to this master, and attach them to the master. */ - if (master->ops->add_components(master->dev, master)) { + if (find_components(master)) { /* Failed to find all components */ ret = 0; goto out; @@ -186,18 +224,87 @@ static void take_down_master(struct master *master) master_remove_components(master); } -int component_master_add(struct device *dev, - const struct component_master_ops *ops) +static size_t component_match_size(size_t num) +{ + return offsetof(struct component_match, compare[num]); +} + +static struct component_match *component_match_realloc(struct device *dev, + struct component_match *match, size_t num) +{ + struct component_match *new; + + if (match && match->alloc == num) + return match; + + new = devm_kmalloc(dev, component_match_size(num), GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + if (match) { + memcpy(new, match, component_match_size(min(match->num, num))); + devm_kfree(dev, match); + } else { + new->num = 0; + } + + new->alloc = num; + + return new; +} + +/* + * Add a component to be matched. + * + * The match array is first created or extended if necessary. + */ +void component_match_add(struct device *dev, struct component_match **matchptr, + int (*compare)(struct device *, void *), void *compare_data) +{ + struct component_match *match = *matchptr; + + if (IS_ERR(match)) + return; + + if (!match || match->num == match->alloc) { + size_t new_size = match ? match->alloc + 16 : 15; + + match = component_match_realloc(dev, match, new_size); + + *matchptr = match; + + if (IS_ERR(match)) + return; + } + + match->compare[match->num].fn = compare; + match->compare[match->num].data = compare_data; + match->num++; +} +EXPORT_SYMBOL(component_match_add); + +int component_master_add_with_match(struct device *dev, + const struct component_master_ops *ops, + struct component_match *match) { struct master *master; int ret; + if (ops->add_components && match) + return -EINVAL; + + /* Reallocate the match array for its true size */ + match = component_match_realloc(dev, match, match->num); + if (IS_ERR(match)) + return PTR_ERR(match); + master = kzalloc(sizeof(*master), GFP_KERNEL); if (!master) return -ENOMEM; master->dev = dev; master->ops = ops; + master->match = match; INIT_LIST_HEAD(&master->components); /* Add to the list of available masters. */ @@ -215,6 +322,13 @@ int component_master_add(struct device *dev, return ret < 0 ? ret : 0; } +EXPORT_SYMBOL_GPL(component_master_add_with_match); + +int component_master_add(struct device *dev, + const struct component_master_ops *ops) +{ + return component_master_add_with_match(dev, ops, NULL); +} EXPORT_SYMBOL_GPL(component_master_add); void component_master_del(struct device *dev, diff --git a/include/linux/component.h b/include/linux/component.h index 68870182ca1e..c00dcc302611 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -29,4 +29,11 @@ void component_master_del(struct device *, int component_master_add_child(struct master *master, int (*compare)(struct device *, void *), void *compare_data); +struct component_match; + +int component_master_add_with_match(struct device *, + const struct component_master_ops *, struct component_match *); +void component_match_add(struct device *, struct component_match **, + int (*compare)(struct device *, void *), void *compare_data); + #endif -- cgit v1.2.3-59-g8ed1b 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/linux') 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 v1.2.3-59-g8ed1b From 606b23ad609c71cfb37eeb972ea4c901034edd3c Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 1 Jul 2014 12:57:20 +0200 Subject: seqno-fence: Hardware dma-buf implementation of fencing (v6) This type of fence can be used with hardware synchronization for simple hardware that can block execution until the condition (dma_buf[offset] - value) >= 0 has been met when WAIT_GEQUAL is used, or (dma_buf[offset] != 0) has been met when WAIT_NONZERO is set. A software fallback still has to be provided in case the fence is used with a device that doesn't support this mechanism. It is useful to expose this for graphics cards that have an op to support this. Some cards like i915 can export those, but don't have an option to wait, so they need the software fallback. I extended the original patch by Rob Clark. v1: Original v2: Renamed from bikeshed to seqno, moved into dma-fence.c since not much was left of the file. Lots of documentation added. v3: Use fence_ops instead of custom callbacks. Moved to own file to avoid circular dependency between dma-buf.h and fence.h v4: Add spinlock pointer to seqno_fence_init v5: Add condition member to allow wait for != 0. Fix small style errors pointed out by checkpatch. v6: Move to a separate file. Fix up api changes in fences. Signed-off-by: Maarten Lankhorst Acked-by: Sumit Semwal Acked-by: Daniel Vetter Reviewed-by: Rob Clark #v4 Signed-off-by: Greg Kroah-Hartman --- Documentation/DocBook/device-drivers.tmpl | 2 + MAINTAINERS | 2 +- drivers/dma-buf/Makefile | 2 +- drivers/dma-buf/seqno-fence.c | 73 +++++++++++++++++++ include/linux/seqno-fence.h | 116 ++++++++++++++++++++++++++++++ 5 files changed, 193 insertions(+), 2 deletions(-) create mode 100644 drivers/dma-buf/seqno-fence.c create mode 100644 include/linux/seqno-fence.h (limited to 'include/linux') diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index e634657efb52..ed0ef00cd7bc 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -130,7 +130,9 @@ X!Edrivers/base/interface.c Device Drivers DMA Management !Edrivers/dma-buf/dma-buf.c !Edrivers/dma-buf/fence.c +!Edrivers/dma-buf/seqno-fence.c !Iinclude/linux/fence.h +!Iinclude/linux/seqno-fence.h !Iinclude/linux/reservation.h !Edrivers/base/dma-coherent.c !Edrivers/base/dma-mapping.c diff --git a/MAINTAINERS b/MAINTAINERS index 65c8f534b22f..7c97777dd1b3 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 include/linux/fence.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/dma-buf/Makefile b/drivers/dma-buf/Makefile index d7825bfe630e..57a675f90cd0 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1 +1 @@ -obj-y := dma-buf.o fence.o reservation.o +obj-y := dma-buf.o fence.o reservation.o seqno-fence.o diff --git a/drivers/dma-buf/seqno-fence.c b/drivers/dma-buf/seqno-fence.c new file mode 100644 index 000000000000..7d12a39a4b57 --- /dev/null +++ b/drivers/dma-buf/seqno-fence.c @@ -0,0 +1,73 @@ +/* + * seqno-fence, using a dma-buf to synchronize fencing + * + * Copyright (C) 2012 Texas Instruments + * Copyright (C) 2012-2014 Canonical Ltd + * 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 + +static const char *seqno_fence_get_driver_name(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->get_driver_name(fence); +} + +static const char *seqno_fence_get_timeline_name(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->get_timeline_name(fence); +} + +static bool seqno_enable_signaling(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->enable_signaling(fence); +} + +static bool seqno_signaled(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->signaled && seqno_fence->ops->signaled(fence); +} + +static void seqno_release(struct fence *fence) +{ + struct seqno_fence *f = to_seqno_fence(fence); + + dma_buf_put(f->sync_buf); + if (f->ops->release) + f->ops->release(fence); + else + fence_free(&f->base); +} + +static signed long seqno_wait(struct fence *fence, bool intr, signed long timeout) +{ + struct seqno_fence *f = to_seqno_fence(fence); + return f->ops->wait(fence, intr, timeout); +} + +const struct fence_ops seqno_fence_ops = { + .get_driver_name = seqno_fence_get_driver_name, + .get_timeline_name = seqno_fence_get_timeline_name, + .enable_signaling = seqno_enable_signaling, + .signaled = seqno_signaled, + .wait = seqno_wait, + .release = seqno_release, +}; +EXPORT_SYMBOL(seqno_fence_ops); diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h new file mode 100644 index 000000000000..3d6003de4b0d --- /dev/null +++ b/include/linux/seqno-fence.h @@ -0,0 +1,116 @@ +/* + * seqno-fence, using a dma-buf to synchronize fencing + * + * Copyright (C) 2012 Texas Instruments + * Copyright (C) 2012 Canonical Ltd + * 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_SEQNO_FENCE_H +#define __LINUX_SEQNO_FENCE_H + +#include +#include + +enum seqno_fence_condition { + SEQNO_FENCE_WAIT_GEQUAL, + SEQNO_FENCE_WAIT_NONZERO +}; + +struct seqno_fence { + struct fence base; + + const struct fence_ops *ops; + struct dma_buf *sync_buf; + uint32_t seqno_ofs; + enum seqno_fence_condition condition; +}; + +extern const struct fence_ops seqno_fence_ops; + +/** + * to_seqno_fence - cast a fence to a seqno_fence + * @fence: fence to cast to a seqno_fence + * + * Returns NULL if the fence is not a seqno_fence, + * or the seqno_fence otherwise. + */ +static inline struct seqno_fence * +to_seqno_fence(struct fence *fence) +{ + if (fence->ops != &seqno_fence_ops) + return NULL; + return container_of(fence, struct seqno_fence, base); +} + +/** + * seqno_fence_init - initialize a seqno fence + * @fence: seqno_fence to initialize + * @lock: pointer to spinlock to use for fence + * @sync_buf: buffer containing the memory location to signal on + * @context: the execution context this fence is a part of + * @seqno_ofs: the offset within @sync_buf + * @seqno: the sequence # to signal on + * @ops: the fence_ops for operations on this seqno fence + * + * This function initializes a struct seqno_fence with passed parameters, + * and takes a reference on sync_buf which is released on fence destruction. + * + * A seqno_fence is a dma_fence which can complete in software when + * enable_signaling is called, but it also completes when + * (s32)((sync_buf)[seqno_ofs] - seqno) >= 0 is true + * + * The seqno_fence will take a refcount on the sync_buf until it's + * destroyed, but actual lifetime of sync_buf may be longer if one of the + * callers take a reference to it. + * + * Certain hardware have instructions to insert this type of wait condition + * in the command stream, so no intervention from software would be needed. + * This type of fence can be destroyed before completed, however a reference + * on the sync_buf dma-buf can be taken. It is encouraged to re-use the same + * dma-buf for sync_buf, since mapping or unmapping the sync_buf to the + * device's vm can be expensive. + * + * It is recommended for creators of seqno_fence to call fence_signal + * before destruction. This will prevent possible issues from wraparound at + * time of issue vs time of check, since users can check fence_is_signaled + * before submitting instructions for the hardware to wait on the fence. + * However, when ops.enable_signaling is not called, it doesn't have to be + * done as soon as possible, just before there's any real danger of seqno + * wraparound. + */ +static inline void +seqno_fence_init(struct seqno_fence *fence, spinlock_t *lock, + struct dma_buf *sync_buf, uint32_t context, + uint32_t seqno_ofs, uint32_t seqno, + enum seqno_fence_condition cond, + const struct fence_ops *ops) +{ + BUG_ON(!fence || !sync_buf || !ops); + BUG_ON(!ops->wait || !ops->enable_signaling || + !ops->get_driver_name || !ops->get_timeline_name); + + /* + * ops is used in fence_init for get_driver_name, so needs to be + * initialized first + */ + fence->ops = ops; + fence_init(&fence->base, &seqno_fence_ops, lock, context, seqno); + get_dma_buf(sync_buf); + fence->sync_buf = sync_buf; + fence->seqno_ofs = seqno_ofs; + fence->condition = cond; +} + +#endif /* __LINUX_SEQNO_FENCE_H */ -- cgit v1.2.3-59-g8ed1b From 3aac4502fd3f80dcf7e65dbf6edd8676893c1f46 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 1 Jul 2014 12:57:26 +0200 Subject: dma-buf: use reservation objects MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows reservation objects to be used in dma-buf. it's required for implementing polling support on the fences that belong to a dma-buf. Signed-off-by: Maarten Lankhorst Acked-by: Mauro Carvalho Chehab #drivers/media/v4l2-core/ Acked-by: Thomas Hellstrom #drivers/gpu/drm/ttm Acked-by: Sumit Semwal Acked-by: Daniel Vetter Signed-off-by: Vincent Stehlé #drivers/gpu/drm/armada/ Signed-off-by: Greg Kroah-Hartman --- drivers/dma-buf/dma-buf.c | 22 ++++++++++++++++++++-- drivers/gpu/drm/armada/armada_gem.c | 2 +- drivers/gpu/drm/drm_prime.c | 8 +++++++- drivers/gpu/drm/exynos/exynos_drm_dmabuf.c | 2 +- drivers/gpu/drm/i915/i915_gem_dmabuf.c | 3 ++- drivers/gpu/drm/nouveau/nouveau_drm.c | 1 + drivers/gpu/drm/nouveau/nouveau_gem.h | 1 + drivers/gpu/drm/nouveau/nouveau_prime.c | 7 +++++++ drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c | 2 +- drivers/gpu/drm/radeon/radeon_drv.c | 2 ++ drivers/gpu/drm/radeon/radeon_prime.c | 8 ++++++++ drivers/gpu/drm/tegra/gem.c | 2 +- drivers/gpu/drm/ttm/ttm_object.c | 2 +- drivers/media/v4l2-core/videobuf2-dma-contig.c | 2 +- drivers/staging/android/ion/ion.c | 3 ++- include/drm/drmP.h | 3 +++ include/linux/dma-buf.h | 9 ++++++--- 17 files changed, 65 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 840c7fa80983..cd40ca22911f 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -25,10 +25,12 @@ #include #include #include +#include #include #include #include #include +#include static inline int is_dma_buf_file(struct file *); @@ -56,6 +58,9 @@ static int dma_buf_release(struct inode *inode, struct file *file) list_del(&dmabuf->list_node); mutex_unlock(&db_list.lock); + if (dmabuf->resv == (struct reservation_object *)&dmabuf[1]) + reservation_object_fini(dmabuf->resv); + kfree(dmabuf); return 0; } @@ -128,6 +133,7 @@ static inline int is_dma_buf_file(struct file *file) * @size: [in] Size of the buffer * @flags: [in] mode flags for the file. * @exp_name: [in] name of the exporting module - useful for debugging. + * @resv: [in] reservation-object, NULL to allocate default one. * * Returns, on success, a newly created dma_buf object, which wraps the * supplied private data and operations for dma_buf_ops. On either missing @@ -135,10 +141,17 @@ static inline int is_dma_buf_file(struct file *file) * */ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, - size_t size, int flags, const char *exp_name) + size_t size, int flags, const char *exp_name, + struct reservation_object *resv) { struct dma_buf *dmabuf; struct file *file; + size_t alloc_size = sizeof(struct dma_buf); + if (!resv) + alloc_size += sizeof(struct reservation_object); + else + /* prevent &dma_buf[1] == dma_buf->resv */ + alloc_size += 1; if (WARN_ON(!priv || !ops || !ops->map_dma_buf @@ -150,7 +163,7 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, return ERR_PTR(-EINVAL); } - dmabuf = kzalloc(sizeof(struct dma_buf), GFP_KERNEL); + dmabuf = kzalloc(alloc_size, GFP_KERNEL); if (dmabuf == NULL) return ERR_PTR(-ENOMEM); @@ -158,6 +171,11 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, dmabuf->ops = ops; dmabuf->size = size; dmabuf->exp_name = exp_name; + if (!resv) { + resv = (struct reservation_object *)&dmabuf[1]; + reservation_object_init(resv); + } + dmabuf->resv = resv; file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, flags); if (IS_ERR(file)) { diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index bb9b642d8485..7496f55611a5 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -539,7 +539,7 @@ armada_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { return dma_buf_export(obj, &armada_gem_prime_dmabuf_ops, obj->size, - O_RDWR); + O_RDWR, NULL); } struct drm_gem_object * diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 304ca8cacbc4..99d578bad17e 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -336,7 +336,13 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { struct dma_buf *drm_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - return dma_buf_export(obj, &drm_gem_prime_dmabuf_ops, obj->size, flags); + struct reservation_object *robj = NULL; + + if (dev->driver->gem_prime_res_obj) + robj = dev->driver->gem_prime_res_obj(obj); + + return dma_buf_export(obj, &drm_gem_prime_dmabuf_ops, obj->size, + flags, robj); } EXPORT_SYMBOL(drm_gem_prime_export); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c index 2a3ad24276f8..60192ed544f0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c @@ -187,7 +187,7 @@ struct dma_buf *exynos_dmabuf_prime_export(struct drm_device *drm_dev, struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj); return dma_buf_export(obj, &exynos_dmabuf_ops, - exynos_gem_obj->base.size, flags); + exynos_gem_obj->base.size, flags, NULL); } struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev, diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index 580aa42443ed..82a1f4b57778 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -237,7 +237,8 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev, return ERR_PTR(ret); } - return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags); + return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags, + NULL); } static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index ddd83756b9a2..e8ae68a9aaf1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -844,6 +844,7 @@ driver = { .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, .gem_prime_pin = nouveau_gem_prime_pin, + .gem_prime_res_obj = nouveau_gem_prime_res_obj, .gem_prime_unpin = nouveau_gem_prime_unpin, .gem_prime_get_sg_table = nouveau_gem_prime_get_sg_table, .gem_prime_import_sg_table = nouveau_gem_prime_import_sg_table, diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.h b/drivers/gpu/drm/nouveau/nouveau_gem.h index 7caca057bc38..ddab762d81fe 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.h +++ b/drivers/gpu/drm/nouveau/nouveau_gem.h @@ -35,6 +35,7 @@ extern int nouveau_gem_ioctl_info(struct drm_device *, void *, struct drm_file *); extern int nouveau_gem_prime_pin(struct drm_gem_object *); +struct reservation_object *nouveau_gem_prime_res_obj(struct drm_gem_object *); extern void nouveau_gem_prime_unpin(struct drm_gem_object *); extern struct sg_table *nouveau_gem_prime_get_sg_table(struct drm_gem_object *); extern struct drm_gem_object *nouveau_gem_prime_import_sg_table( diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 51a2cb102b44..1f51008e4d26 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -102,3 +102,10 @@ void nouveau_gem_prime_unpin(struct drm_gem_object *obj) nouveau_bo_unpin(nvbo); } + +struct reservation_object *nouveau_gem_prime_res_obj(struct drm_gem_object *obj) +{ + struct nouveau_bo *nvbo = nouveau_gem_object(obj); + + return nvbo->bo.resv; +} diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index 4fcca8d42796..a2dbfb1737b4 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -171,7 +171,7 @@ static struct dma_buf_ops omap_dmabuf_ops = { struct dma_buf *omap_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - return dma_buf_export(obj, &omap_dmabuf_ops, obj->size, flags); + return dma_buf_export(obj, &omap_dmabuf_ops, obj->size, flags, NULL); } struct drm_gem_object *omap_gem_prime_import(struct drm_device *dev, diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index cb1421369e3a..5fa62a113db6 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -132,6 +132,7 @@ struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev, struct sg_table *sg); int radeon_gem_prime_pin(struct drm_gem_object *obj); void radeon_gem_prime_unpin(struct drm_gem_object *obj); +struct reservation_object *radeon_gem_prime_res_obj(struct drm_gem_object *); void *radeon_gem_prime_vmap(struct drm_gem_object *obj); void radeon_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); extern long radeon_kms_compat_ioctl(struct file *filp, unsigned int cmd, @@ -566,6 +567,7 @@ static struct drm_driver kms_driver = { .gem_prime_import = drm_gem_prime_import, .gem_prime_pin = radeon_gem_prime_pin, .gem_prime_unpin = radeon_gem_prime_unpin, + .gem_prime_res_obj = radeon_gem_prime_res_obj, .gem_prime_get_sg_table = radeon_gem_prime_get_sg_table, .gem_prime_import_sg_table = radeon_gem_prime_import_sg_table, .gem_prime_vmap = radeon_gem_prime_vmap, diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index 20074560fc25..28d71070c389 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -103,3 +103,11 @@ void radeon_gem_prime_unpin(struct drm_gem_object *obj) radeon_bo_unpin(bo); radeon_bo_unreserve(bo); } + + +struct reservation_object *radeon_gem_prime_res_obj(struct drm_gem_object *obj) +{ + struct radeon_bo *bo = gem_to_radeon_bo(obj); + + return bo->tbo.resv; +} diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index aa85b7b26f10..78cc8143760a 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -420,7 +420,7 @@ struct dma_buf *tegra_gem_prime_export(struct drm_device *drm, int flags) { return dma_buf_export(gem, &tegra_gem_prime_dmabuf_ops, gem->size, - flags); + flags, NULL); } struct drm_gem_object *tegra_gem_prime_import(struct drm_device *drm, diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c index d2a053352789..12c87110db3a 100644 --- a/drivers/gpu/drm/ttm/ttm_object.c +++ b/drivers/gpu/drm/ttm/ttm_object.c @@ -695,7 +695,7 @@ int ttm_prime_handle_to_fd(struct ttm_object_file *tfile, } dma_buf = dma_buf_export(prime, &tdev->ops, - prime->size, flags); + prime->size, flags, NULL); if (IS_ERR(dma_buf)) { ret = PTR_ERR(dma_buf); ttm_mem_global_free(tdev->mem_glob, diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c index 880be0782dd9..c4e4dfa8123a 100644 --- a/drivers/media/v4l2-core/videobuf2-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c @@ -404,7 +404,7 @@ static struct dma_buf *vb2_dc_get_dmabuf(void *buf_priv, unsigned long flags) if (WARN_ON(!buf->sgt_base)) return NULL; - dbuf = dma_buf_export(buf, &vb2_dc_dmabuf_ops, buf->size, flags); + dbuf = dma_buf_export(buf, &vb2_dc_dmabuf_ops, buf->size, flags, NULL); if (IS_ERR(dbuf)) return NULL; diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index 389b8f67a2ec..270360912b2c 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -1120,7 +1120,8 @@ struct dma_buf *ion_share_dma_buf(struct ion_client *client, ion_buffer_get(buffer); mutex_unlock(&client->lock); - dmabuf = dma_buf_export(buffer, &dma_buf_ops, buffer->size, O_RDWR); + dmabuf = dma_buf_export(buffer, &dma_buf_ops, buffer->size, O_RDWR, + NULL); if (IS_ERR(dmabuf)) { ion_buffer_put(buffer); return dmabuf; diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 8af71a8e2c00..e41f17ea1f13 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -83,6 +83,7 @@ struct drm_device; struct device_node; struct videomode; +struct reservation_object; #include #include @@ -923,6 +924,8 @@ struct drm_driver { /* low-level interface used by drm_gem_prime_{import,export} */ int (*gem_prime_pin)(struct drm_gem_object *obj); void (*gem_prime_unpin)(struct drm_gem_object *obj); + struct reservation_object * (*gem_prime_res_obj)( + struct drm_gem_object *obj); struct sg_table *(*gem_prime_get_sg_table)(struct drm_gem_object *obj); struct drm_gem_object *(*gem_prime_import_sg_table)( struct drm_device *dev, size_t size, diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index f886985a28b2..fd7def2e0ae2 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -115,6 +115,7 @@ struct dma_buf_ops { * @exp_name: name of the exporter; useful for debugging. * @list_node: node for dma_buf accounting and debugging. * @priv: exporter specific private data for this buffer object. + * @resv: reservation object linked to this dma-buf */ struct dma_buf { size_t size; @@ -128,6 +129,7 @@ struct dma_buf { const char *exp_name; struct list_head list_node; void *priv; + struct reservation_object *resv; }; /** @@ -168,10 +170,11 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *dmabuf_attach); struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, - size_t size, int flags, const char *); + size_t size, int flags, const char *, + struct reservation_object *); -#define dma_buf_export(priv, ops, size, flags) \ - dma_buf_export_named(priv, ops, size, flags, KBUILD_MODNAME) +#define dma_buf_export(priv, ops, size, flags, resv) \ + dma_buf_export_named(priv, ops, size, flags, KBUILD_MODNAME, resv) int dma_buf_fd(struct dma_buf *dmabuf, int flags); struct dma_buf *dma_buf_get(int fd); -- cgit v1.2.3-59-g8ed1b From 0ba6b8fb91fc051535c7612f6241c8197d92323b Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 1 Jul 2014 12:57:37 +0200 Subject: reservation: add support for fences to enable cross-device synchronisation Signed-off-by: Maarten Lankhorst Acked-by: Sumit Semwal Acked-by: Daniel Vetter Reviewed-by: Rob Clark Signed-off-by: Greg Kroah-Hartman --- include/linux/reservation.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 813dae960ebd..f3f57460a205 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -6,7 +6,7 @@ * Copyright (C) 2012 Texas Instruments * * Authors: - * Rob Clark + * Rob Clark * Maarten Lankhorst * Thomas Hellstrom * @@ -40,22 +40,40 @@ #define _LINUX_RESERVATION_H #include +#include +#include extern struct ww_class reservation_ww_class; struct reservation_object { struct ww_mutex lock; + + struct fence *fence_excl; + struct fence **fence_shared; + u32 fence_shared_count, fence_shared_max; }; static inline void reservation_object_init(struct reservation_object *obj) { ww_mutex_init(&obj->lock, &reservation_ww_class); + + obj->fence_shared_count = obj->fence_shared_max = 0; + obj->fence_shared = NULL; + obj->fence_excl = NULL; } static inline void reservation_object_fini(struct reservation_object *obj) { + int i; + + if (obj->fence_excl) + fence_put(obj->fence_excl); + for (i = 0; i < obj->fence_shared_count; ++i) + fence_put(obj->fence_shared[i]); + kfree(obj->fence_shared); + ww_mutex_destroy(&obj->lock); } -- cgit v1.2.3-59-g8ed1b From 9b495a5887994a6d74d5c261d012083a92b94738 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 1 Jul 2014 12:57:43 +0200 Subject: dma-buf: add poll support, v3 Thanks to Fengguang Wu for spotting a missing static cast. v2: - Kill unused variable need_shared. v3: - Clarify the BUG() in dma_buf_release some more. (Rob Clark) Signed-off-by: Maarten Lankhorst Acked-by: Sumit Semwal Acked-by: Daniel Vetter Signed-off-by: Greg Kroah-Hartman --- drivers/dma-buf/dma-buf.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/dma-buf.h | 12 ++++++ 2 files changed, 120 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index cd40ca22911f..25e8c4165936 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -30,6 +30,7 @@ #include #include #include +#include #include static inline int is_dma_buf_file(struct file *); @@ -52,6 +53,16 @@ static int dma_buf_release(struct inode *inode, struct file *file) BUG_ON(dmabuf->vmapping_counter); + /* + * Any fences that a dma-buf poll can wait on should be signaled + * before releasing dma-buf. This is the responsibility of each + * driver that uses the reservation objects. + * + * If you hit this BUG() it means someone dropped their ref to the + * dma-buf while still having pending operation to the buffer. + */ + BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active); + dmabuf->ops->release(dmabuf); mutex_lock(&db_list.lock); @@ -108,10 +119,103 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) return base + offset; } +static void dma_buf_poll_cb(struct fence *fence, struct fence_cb *cb) +{ + struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb; + unsigned long flags; + + spin_lock_irqsave(&dcb->poll->lock, flags); + wake_up_locked_poll(dcb->poll, dcb->active); + dcb->active = 0; + spin_unlock_irqrestore(&dcb->poll->lock, flags); +} + +static unsigned int dma_buf_poll(struct file *file, poll_table *poll) +{ + struct dma_buf *dmabuf; + struct reservation_object *resv; + unsigned long events; + + dmabuf = file->private_data; + if (!dmabuf || !dmabuf->resv) + return POLLERR; + + resv = dmabuf->resv; + + poll_wait(file, &dmabuf->poll, poll); + + events = poll_requested_events(poll) & (POLLIN | POLLOUT); + if (!events) + return 0; + + ww_mutex_lock(&resv->lock, NULL); + + if (resv->fence_excl && (!(events & POLLOUT) || + resv->fence_shared_count == 0)) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; + unsigned long pevents = POLLIN; + + if (resv->fence_shared_count == 0) + pevents |= POLLOUT; + + spin_lock_irq(&dmabuf->poll.lock); + if (dcb->active) { + dcb->active |= pevents; + events &= ~pevents; + } else + dcb->active = pevents; + spin_unlock_irq(&dmabuf->poll.lock); + + if (events & pevents) { + if (!fence_add_callback(resv->fence_excl, + &dcb->cb, dma_buf_poll_cb)) + events &= ~pevents; + else + /* + * No callback queued, wake up any additional + * waiters. + */ + dma_buf_poll_cb(NULL, &dcb->cb); + } + } + + if ((events & POLLOUT) && resv->fence_shared_count > 0) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; + int i; + + /* Only queue a new callback if no event has fired yet */ + spin_lock_irq(&dmabuf->poll.lock); + if (dcb->active) + events &= ~POLLOUT; + else + dcb->active = POLLOUT; + spin_unlock_irq(&dmabuf->poll.lock); + + if (!(events & POLLOUT)) + goto out; + + for (i = 0; i < resv->fence_shared_count; ++i) + if (!fence_add_callback(resv->fence_shared[i], + &dcb->cb, dma_buf_poll_cb)) { + events &= ~POLLOUT; + break; + } + + /* No callback queued, wake up any additional waiters. */ + if (i == resv->fence_shared_count) + dma_buf_poll_cb(NULL, &dcb->cb); + } + +out: + ww_mutex_unlock(&resv->lock); + return events; +} + static const struct file_operations dma_buf_fops = { .release = dma_buf_release, .mmap = dma_buf_mmap_internal, .llseek = dma_buf_llseek, + .poll = dma_buf_poll, }; /* @@ -171,6 +275,10 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, dmabuf->ops = ops; dmabuf->size = size; dmabuf->exp_name = exp_name; + init_waitqueue_head(&dmabuf->poll); + dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; + dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; + if (!resv) { resv = (struct reservation_object *)&dmabuf[1]; reservation_object_init(resv); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index fd7def2e0ae2..694e1fe1c4b4 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -30,6 +30,8 @@ #include #include #include +#include +#include struct device; struct dma_buf; @@ -130,6 +132,16 @@ struct dma_buf { struct list_head list_node; void *priv; struct reservation_object *resv; + + /* poll support */ + wait_queue_head_t poll; + + struct dma_buf_poll_cb_t { + struct fence_cb cb; + wait_queue_head_t *poll; + + unsigned long active; + } cb_excl, cb_shared; }; /** -- cgit v1.2.3-59-g8ed1b From 04a5faa8cbe5a8eaf152cb88959ba6360c26e702 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 1 Jul 2014 12:57:54 +0200 Subject: reservation: update api and add some helpers Move the list of shared fences to a struct, and return it in reservation_object_get_list(). Add reservation_object_get_excl to get the exclusive fence. Add reservation_object_reserve_shared(), which reserves space in the reservation_object for 1 more shared fence. reservation_object_add_shared_fence() and reservation_object_add_excl_fence() are used to assign a new fence to a reservation_object pointer, to complete a reservation. Changes since v1: - Add reservation_object_get_excl, reorder code a bit. Signed-off-by: Maarten Lankhorst Acked-by: Sumit Semwal Acked-by: Daniel Vetter Signed-off-by: Greg Kroah-Hartman --- Documentation/DocBook/device-drivers.tmpl | 1 + drivers/dma-buf/dma-buf.c | 35 ++++--- drivers/dma-buf/reservation.c | 156 +++++++++++++++++++++++++++++- include/linux/reservation.h | 56 +++++++++-- 4 files changed, 229 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index ed0ef00cd7bc..dd3f278faa8a 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -133,6 +133,7 @@ X!Edrivers/base/interface.c !Edrivers/dma-buf/seqno-fence.c !Iinclude/linux/fence.h !Iinclude/linux/seqno-fence.h +!Edrivers/dma-buf/reservation.c !Iinclude/linux/reservation.h !Edrivers/base/dma-coherent.c !Edrivers/base/dma-mapping.c diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 25e8c4165936..cb8379dfeed5 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -134,7 +134,10 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) { struct dma_buf *dmabuf; struct reservation_object *resv; + struct reservation_object_list *fobj; + struct fence *fence_excl; unsigned long events; + unsigned shared_count; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) @@ -150,12 +153,18 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) ww_mutex_lock(&resv->lock, NULL); - if (resv->fence_excl && (!(events & POLLOUT) || - resv->fence_shared_count == 0)) { + fobj = resv->fence; + if (!fobj) + goto out; + + shared_count = fobj->shared_count; + fence_excl = resv->fence_excl; + + if (fence_excl && (!(events & POLLOUT) || shared_count == 0)) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; unsigned long pevents = POLLIN; - if (resv->fence_shared_count == 0) + if (shared_count == 0) pevents |= POLLOUT; spin_lock_irq(&dmabuf->poll.lock); @@ -167,19 +176,20 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) spin_unlock_irq(&dmabuf->poll.lock); if (events & pevents) { - if (!fence_add_callback(resv->fence_excl, - &dcb->cb, dma_buf_poll_cb)) + if (!fence_add_callback(fence_excl, &dcb->cb, + dma_buf_poll_cb)) { events &= ~pevents; - else + } else { /* * No callback queued, wake up any additional * waiters. */ dma_buf_poll_cb(NULL, &dcb->cb); + } } } - if ((events & POLLOUT) && resv->fence_shared_count > 0) { + if ((events & POLLOUT) && shared_count > 0) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; int i; @@ -194,15 +204,18 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) if (!(events & POLLOUT)) goto out; - for (i = 0; i < resv->fence_shared_count; ++i) - if (!fence_add_callback(resv->fence_shared[i], - &dcb->cb, dma_buf_poll_cb)) { + for (i = 0; i < shared_count; ++i) { + struct fence *fence = fobj->shared[i]; + + if (!fence_add_callback(fence, &dcb->cb, + dma_buf_poll_cb)) { events &= ~POLLOUT; break; } + } /* No callback queued, wake up any additional waiters. */ - if (i == resv->fence_shared_count) + if (i == shared_count) dma_buf_poll_cb(NULL, &dcb->cb); } diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index a73fbf3b8e56..e6166723a9ae 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2012-2013 Canonical Ltd + * Copyright (C) 2012-2014 Canonical Ltd (Maarten Lankhorst) * * Based on bo.c which bears the following copyright notice, * but is dual licensed: @@ -37,3 +37,157 @@ DEFINE_WW_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); + +/* + * Reserve space to add a shared fence to a reservation_object, + * must be called with obj->lock held. + */ +int reservation_object_reserve_shared(struct reservation_object *obj) +{ + struct reservation_object_list *fobj, *old; + u32 max; + + old = reservation_object_get_list(obj); + + if (old && old->shared_max) { + if (old->shared_count < old->shared_max) { + /* perform an in-place update */ + kfree(obj->staged); + obj->staged = NULL; + return 0; + } else + max = old->shared_max * 2; + } else + max = 4; + + /* + * resize obj->staged or allocate if it doesn't exist, + * noop if already correct size + */ + fobj = krealloc(obj->staged, offsetof(typeof(*fobj), shared[max]), + GFP_KERNEL); + if (!fobj) + return -ENOMEM; + + obj->staged = fobj; + fobj->shared_max = max; + return 0; +} +EXPORT_SYMBOL(reservation_object_reserve_shared); + +static void +reservation_object_add_shared_inplace(struct reservation_object *obj, + struct reservation_object_list *fobj, + struct fence *fence) +{ + u32 i; + + for (i = 0; i < fobj->shared_count; ++i) { + if (fobj->shared[i]->context == fence->context) { + struct fence *old_fence = fobj->shared[i]; + + fence_get(fence); + + fobj->shared[i] = fence; + + fence_put(old_fence); + return; + } + } + + fence_get(fence); + fobj->shared[fobj->shared_count] = fence; + /* + * make the new fence visible before incrementing + * fobj->shared_count + */ + smp_wmb(); + fobj->shared_count++; +} + +static void +reservation_object_add_shared_replace(struct reservation_object *obj, + struct reservation_object_list *old, + struct reservation_object_list *fobj, + struct fence *fence) +{ + unsigned i; + + fence_get(fence); + + if (!old) { + fobj->shared[0] = fence; + fobj->shared_count = 1; + goto done; + } + + /* + * no need to bump fence refcounts, rcu_read access + * requires the use of kref_get_unless_zero, and the + * references from the old struct are carried over to + * the new. + */ + fobj->shared_count = old->shared_count; + + for (i = 0; i < old->shared_count; ++i) { + if (fence && old->shared[i]->context == fence->context) { + fence_put(old->shared[i]); + fobj->shared[i] = fence; + fence = NULL; + } else + fobj->shared[i] = old->shared[i]; + } + if (fence) + fobj->shared[fobj->shared_count++] = fence; + +done: + obj->fence = fobj; + kfree(old); +} + +/* + * Add a fence to a shared slot, obj->lock must be held, and + * reservation_object_reserve_shared_fence has been called. + */ +void reservation_object_add_shared_fence(struct reservation_object *obj, + struct fence *fence) +{ + struct reservation_object_list *old, *fobj = obj->staged; + + old = reservation_object_get_list(obj); + obj->staged = NULL; + + if (!fobj) { + BUG_ON(old->shared_count == old->shared_max); + reservation_object_add_shared_inplace(obj, old, fence); + } else + reservation_object_add_shared_replace(obj, old, fobj, fence); +} +EXPORT_SYMBOL(reservation_object_add_shared_fence); + +void reservation_object_add_excl_fence(struct reservation_object *obj, + struct fence *fence) +{ + struct fence *old_fence = obj->fence_excl; + struct reservation_object_list *old; + u32 i = 0; + + old = reservation_object_get_list(obj); + if (old) { + i = old->shared_count; + old->shared_count = 0; + } + + if (fence) + fence_get(fence); + + obj->fence_excl = fence; + + /* inplace update, no shared fences */ + while (i--) + fence_put(old->shared[i]); + + if (old_fence) + fence_put(old_fence); +} +EXPORT_SYMBOL(reservation_object_add_excl_fence); diff --git a/include/linux/reservation.h b/include/linux/reservation.h index f3f57460a205..2affe67dea6e 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -45,36 +45,78 @@ extern struct ww_class reservation_ww_class; +struct reservation_object_list { + u32 shared_count, shared_max; + struct fence *shared[]; +}; + struct reservation_object { struct ww_mutex lock; struct fence *fence_excl; - struct fence **fence_shared; - u32 fence_shared_count, fence_shared_max; + struct reservation_object_list *fence; + struct reservation_object_list *staged; }; +#define reservation_object_assert_held(obj) \ + lockdep_assert_held(&(obj)->lock.base) + static inline void reservation_object_init(struct reservation_object *obj) { ww_mutex_init(&obj->lock, &reservation_ww_class); - obj->fence_shared_count = obj->fence_shared_max = 0; - obj->fence_shared = NULL; obj->fence_excl = NULL; + obj->fence = NULL; + obj->staged = NULL; } static inline void reservation_object_fini(struct reservation_object *obj) { int i; + struct reservation_object_list *fobj; + /* + * This object should be dead and all references must have + * been released to it. + */ if (obj->fence_excl) fence_put(obj->fence_excl); - for (i = 0; i < obj->fence_shared_count; ++i) - fence_put(obj->fence_shared[i]); - kfree(obj->fence_shared); + + fobj = obj->fence; + if (fobj) { + for (i = 0; i < fobj->shared_count; ++i) + fence_put(fobj->shared[i]); + + kfree(fobj); + } + kfree(obj->staged); ww_mutex_destroy(&obj->lock); } +static inline struct reservation_object_list * +reservation_object_get_list(struct reservation_object *obj) +{ + reservation_object_assert_held(obj); + + return obj->fence; +} + +static inline struct fence * +reservation_object_get_excl(struct reservation_object *obj) +{ + reservation_object_assert_held(obj); + + return obj->fence_excl; +} + +int reservation_object_reserve_shared(struct reservation_object *obj); +void reservation_object_add_shared_fence(struct reservation_object *obj, + struct fence *fence); + +void reservation_object_add_excl_fence(struct reservation_object *obj, + struct fence *fence); + #endif /* _LINUX_RESERVATION_H */ -- cgit v1.2.3-59-g8ed1b From 3c3b177a9369b26890ced004867fb32708e8ef5b Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Tue, 1 Jul 2014 12:58:00 +0200 Subject: reservation: add suppport for read-only access using rcu This adds some extra functions to deal with rcu. reservation_object_get_fences_rcu() will obtain the list of shared and exclusive fences without obtaining the ww_mutex. reservation_object_wait_timeout_rcu() will wait on all fences of the reservation_object, without obtaining the ww_mutex. reservation_object_test_signaled_rcu() will test if all fences of the reservation_object are signaled without using the ww_mutex. reservation_object_get_excl and reservation_object_get_list require the reservation object to be held, updating requires write_seqcount_begin/end. If only the exclusive fence is needed, rcu_dereference followed by fence_get_rcu can be used, if the shared fences are needed it's recommended to use the supplied functions. Signed-off-by: Maarten Lankhorst Acked-by: Sumit Semwal Acked-by: Daniel Vetter Reviewed-By: Thomas Hellstrom Signed-off-by: Greg Kroah-Hartman --- drivers/dma-buf/dma-buf.c | 47 ++++-- drivers/dma-buf/fence.c | 2 +- drivers/dma-buf/reservation.c | 336 ++++++++++++++++++++++++++++++++++++++---- include/linux/fence.h | 17 +++ include/linux/reservation.h | 52 +++++-- 5 files changed, 400 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index cb8379dfeed5..f3014c448e1e 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -137,7 +137,7 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) struct reservation_object_list *fobj; struct fence *fence_excl; unsigned long events; - unsigned shared_count; + unsigned shared_count, seq; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) @@ -151,14 +151,20 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) if (!events) return 0; - ww_mutex_lock(&resv->lock, NULL); +retry: + seq = read_seqcount_begin(&resv->seq); + rcu_read_lock(); - fobj = resv->fence; - if (!fobj) - goto out; - - shared_count = fobj->shared_count; - fence_excl = resv->fence_excl; + fobj = rcu_dereference(resv->fence); + if (fobj) + shared_count = fobj->shared_count; + else + shared_count = 0; + fence_excl = rcu_dereference(resv->fence_excl); + if (read_seqcount_retry(&resv->seq, seq)) { + rcu_read_unlock(); + goto retry; + } if (fence_excl && (!(events & POLLOUT) || shared_count == 0)) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; @@ -176,14 +182,20 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) spin_unlock_irq(&dmabuf->poll.lock); if (events & pevents) { - if (!fence_add_callback(fence_excl, &dcb->cb, + if (!fence_get_rcu(fence_excl)) { + /* force a recheck */ + events &= ~pevents; + dma_buf_poll_cb(NULL, &dcb->cb); + } else if (!fence_add_callback(fence_excl, &dcb->cb, dma_buf_poll_cb)) { events &= ~pevents; + fence_put(fence_excl); } else { /* * No callback queued, wake up any additional * waiters. */ + fence_put(fence_excl); dma_buf_poll_cb(NULL, &dcb->cb); } } @@ -205,13 +217,26 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) goto out; for (i = 0; i < shared_count; ++i) { - struct fence *fence = fobj->shared[i]; + struct fence *fence = rcu_dereference(fobj->shared[i]); + if (!fence_get_rcu(fence)) { + /* + * fence refcount dropped to zero, this means + * that fobj has been freed + * + * call dma_buf_poll_cb and force a recheck! + */ + events &= ~POLLOUT; + dma_buf_poll_cb(NULL, &dcb->cb); + break; + } if (!fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb)) { + fence_put(fence); events &= ~POLLOUT; break; } + fence_put(fence); } /* No callback queued, wake up any additional waiters. */ @@ -220,7 +245,7 @@ static unsigned int dma_buf_poll(struct file *file, poll_table *poll) } out: - ww_mutex_unlock(&resv->lock); + rcu_read_unlock(); return events; } diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c index 948bf00d955e..4222cb2aa96a 100644 --- a/drivers/dma-buf/fence.c +++ b/drivers/dma-buf/fence.c @@ -184,7 +184,7 @@ EXPORT_SYMBOL(fence_release); void fence_free(struct fence *fence) { - kfree(fence); + kfree_rcu(fence, rcu); } EXPORT_SYMBOL(fence_free); diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index e6166723a9ae..3c97c8fa8d02 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -38,6 +38,11 @@ DEFINE_WW_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); +struct lock_class_key reservation_seqcount_class; +EXPORT_SYMBOL(reservation_seqcount_class); + +const char reservation_seqcount_string[] = "reservation_seqcount"; +EXPORT_SYMBOL(reservation_seqcount_string); /* * Reserve space to add a shared fence to a reservation_object, * must be called with obj->lock held. @@ -82,27 +87,37 @@ reservation_object_add_shared_inplace(struct reservation_object *obj, { u32 i; + fence_get(fence); + + preempt_disable(); + write_seqcount_begin(&obj->seq); + for (i = 0; i < fobj->shared_count; ++i) { - if (fobj->shared[i]->context == fence->context) { - struct fence *old_fence = fobj->shared[i]; + struct fence *old_fence; - fence_get(fence); + old_fence = rcu_dereference_protected(fobj->shared[i], + reservation_object_held(obj)); - fobj->shared[i] = fence; + if (old_fence->context == fence->context) { + /* memory barrier is added by write_seqcount_begin */ + RCU_INIT_POINTER(fobj->shared[i], fence); + write_seqcount_end(&obj->seq); + preempt_enable(); fence_put(old_fence); return; } } - fence_get(fence); - fobj->shared[fobj->shared_count] = fence; /* - * make the new fence visible before incrementing - * fobj->shared_count + * memory barrier is added by write_seqcount_begin, + * fobj->shared_count is protected by this lock too */ - smp_wmb(); + RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence); fobj->shared_count++; + + write_seqcount_end(&obj->seq); + preempt_enable(); } static void @@ -112,11 +127,12 @@ reservation_object_add_shared_replace(struct reservation_object *obj, struct fence *fence) { unsigned i; + struct fence *old_fence = NULL; fence_get(fence); if (!old) { - fobj->shared[0] = fence; + RCU_INIT_POINTER(fobj->shared[0], fence); fobj->shared_count = 1; goto done; } @@ -130,19 +146,38 @@ reservation_object_add_shared_replace(struct reservation_object *obj, fobj->shared_count = old->shared_count; for (i = 0; i < old->shared_count; ++i) { - if (fence && old->shared[i]->context == fence->context) { - fence_put(old->shared[i]); - fobj->shared[i] = fence; - fence = NULL; + struct fence *check; + + check = rcu_dereference_protected(old->shared[i], + reservation_object_held(obj)); + + if (!old_fence && check->context == fence->context) { + old_fence = check; + RCU_INIT_POINTER(fobj->shared[i], fence); } else - fobj->shared[i] = old->shared[i]; + RCU_INIT_POINTER(fobj->shared[i], check); + } + if (!old_fence) { + RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence); + fobj->shared_count++; } - if (fence) - fobj->shared[fobj->shared_count++] = fence; done: - obj->fence = fobj; - kfree(old); + preempt_disable(); + write_seqcount_begin(&obj->seq); + /* + * RCU_INIT_POINTER can be used here, + * seqcount provides the necessary barriers + */ + RCU_INIT_POINTER(obj->fence, fobj); + write_seqcount_end(&obj->seq); + preempt_enable(); + + if (old) + kfree_rcu(old, rcu); + + if (old_fence) + fence_put(old_fence); } /* @@ -158,7 +193,7 @@ void reservation_object_add_shared_fence(struct reservation_object *obj, obj->staged = NULL; if (!fobj) { - BUG_ON(old->shared_count == old->shared_max); + BUG_ON(old->shared_count >= old->shared_max); reservation_object_add_shared_inplace(obj, old, fence); } else reservation_object_add_shared_replace(obj, old, fobj, fence); @@ -168,26 +203,275 @@ EXPORT_SYMBOL(reservation_object_add_shared_fence); void reservation_object_add_excl_fence(struct reservation_object *obj, struct fence *fence) { - struct fence *old_fence = obj->fence_excl; + struct fence *old_fence = reservation_object_get_excl(obj); struct reservation_object_list *old; u32 i = 0; old = reservation_object_get_list(obj); - if (old) { + if (old) i = old->shared_count; - old->shared_count = 0; - } if (fence) fence_get(fence); - obj->fence_excl = fence; + preempt_disable(); + write_seqcount_begin(&obj->seq); + /* write_seqcount_begin provides the necessary memory barrier */ + RCU_INIT_POINTER(obj->fence_excl, fence); + if (old) + old->shared_count = 0; + write_seqcount_end(&obj->seq); + preempt_enable(); /* inplace update, no shared fences */ while (i--) - fence_put(old->shared[i]); + fence_put(rcu_dereference_protected(old->shared[i], + reservation_object_held(obj))); if (old_fence) fence_put(old_fence); } EXPORT_SYMBOL(reservation_object_add_excl_fence); + +int reservation_object_get_fences_rcu(struct reservation_object *obj, + struct fence **pfence_excl, + unsigned *pshared_count, + struct fence ***pshared) +{ + unsigned shared_count = 0; + unsigned retry = 1; + struct fence **shared = NULL, *fence_excl = NULL; + int ret = 0; + + while (retry) { + struct reservation_object_list *fobj; + unsigned seq; + + seq = read_seqcount_begin(&obj->seq); + + rcu_read_lock(); + + fobj = rcu_dereference(obj->fence); + if (fobj) { + struct fence **nshared; + size_t sz = sizeof(*shared) * fobj->shared_max; + + nshared = krealloc(shared, sz, + GFP_NOWAIT | __GFP_NOWARN); + if (!nshared) { + rcu_read_unlock(); + nshared = krealloc(shared, sz, GFP_KERNEL); + if (nshared) { + shared = nshared; + continue; + } + + ret = -ENOMEM; + shared_count = 0; + break; + } + shared = nshared; + memcpy(shared, fobj->shared, sz); + shared_count = fobj->shared_count; + } else + shared_count = 0; + fence_excl = rcu_dereference(obj->fence_excl); + + retry = read_seqcount_retry(&obj->seq, seq); + if (retry) + goto unlock; + + if (!fence_excl || fence_get_rcu(fence_excl)) { + unsigned i; + + for (i = 0; i < shared_count; ++i) { + if (fence_get_rcu(shared[i])) + continue; + + /* uh oh, refcount failed, abort and retry */ + while (i--) + fence_put(shared[i]); + + if (fence_excl) { + fence_put(fence_excl); + fence_excl = NULL; + } + + retry = 1; + break; + } + } else + retry = 1; + +unlock: + rcu_read_unlock(); + } + *pshared_count = shared_count; + if (shared_count) + *pshared = shared; + else { + *pshared = NULL; + kfree(shared); + } + *pfence_excl = fence_excl; + + return ret; +} +EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu); + +long reservation_object_wait_timeout_rcu(struct reservation_object *obj, + bool wait_all, bool intr, + unsigned long timeout) +{ + struct fence *fence; + unsigned seq, shared_count, i = 0; + long ret = timeout; + +retry: + fence = NULL; + shared_count = 0; + seq = read_seqcount_begin(&obj->seq); + rcu_read_lock(); + + if (wait_all) { + struct reservation_object_list *fobj = rcu_dereference(obj->fence); + + if (fobj) + shared_count = fobj->shared_count; + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + for (i = 0; i < shared_count; ++i) { + struct fence *lfence = rcu_dereference(fobj->shared[i]); + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) + continue; + + if (!fence_get_rcu(lfence)) + goto unlock_retry; + + if (fence_is_signaled(lfence)) { + fence_put(lfence); + continue; + } + + fence = lfence; + break; + } + } + + if (!shared_count) { + struct fence *fence_excl = rcu_dereference(obj->fence_excl); + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + if (fence_excl && + !test_bit(FENCE_FLAG_SIGNALED_BIT, &fence_excl->flags)) { + if (!fence_get_rcu(fence_excl)) + goto unlock_retry; + + if (fence_is_signaled(fence_excl)) + fence_put(fence_excl); + else + fence = fence_excl; + } + } + + rcu_read_unlock(); + if (fence) { + ret = fence_wait_timeout(fence, intr, ret); + fence_put(fence); + if (ret > 0 && wait_all && (i + 1 < shared_count)) + goto retry; + } + return ret; + +unlock_retry: + rcu_read_unlock(); + goto retry; +} +EXPORT_SYMBOL_GPL(reservation_object_wait_timeout_rcu); + + +static inline int +reservation_object_test_signaled_single(struct fence *passed_fence) +{ + struct fence *fence, *lfence = passed_fence; + int ret = 1; + + if (!test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) { + int ret; + + fence = fence_get_rcu(lfence); + if (!fence) + return -1; + + ret = !!fence_is_signaled(fence); + fence_put(fence); + } + return ret; +} + +bool reservation_object_test_signaled_rcu(struct reservation_object *obj, + bool test_all) +{ + unsigned seq, shared_count; + int ret = true; + +retry: + shared_count = 0; + seq = read_seqcount_begin(&obj->seq); + rcu_read_lock(); + + if (test_all) { + unsigned i; + + struct reservation_object_list *fobj = rcu_dereference(obj->fence); + + if (fobj) + shared_count = fobj->shared_count; + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + for (i = 0; i < shared_count; ++i) { + struct fence *fence = rcu_dereference(fobj->shared[i]); + + ret = reservation_object_test_signaled_single(fence); + if (ret < 0) + goto unlock_retry; + else if (!ret) + break; + } + + /* + * There could be a read_seqcount_retry here, but nothing cares + * about whether it's the old or newer fence pointers that are + * signaled. That race could still have happened after checking + * read_seqcount_retry. If you care, use ww_mutex_lock. + */ + } + + if (!shared_count) { + struct fence *fence_excl = rcu_dereference(obj->fence_excl); + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + if (fence_excl) { + ret = reservation_object_test_signaled_single(fence_excl); + if (ret < 0) + goto unlock_retry; + } + } + + rcu_read_unlock(); + return ret; + +unlock_retry: + rcu_read_unlock(); + goto retry; +} +EXPORT_SYMBOL_GPL(reservation_object_test_signaled_rcu); diff --git a/include/linux/fence.h b/include/linux/fence.h index b935cc650123..d174585b874b 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -28,6 +28,7 @@ #include #include #include +#include struct fence; struct fence_ops; @@ -37,6 +38,7 @@ struct fence_cb; * struct fence - software synchronization primitive * @refcount: refcount for this fence * @ops: fence_ops associated with this fence + * @rcu: used for releasing fence with kfree_rcu * @cb_list: list of all callbacks to call * @lock: spin_lock_irqsave used for locking * @context: execution context this fence belongs to, returned by @@ -70,6 +72,7 @@ struct fence_cb; struct fence { struct kref refcount; const struct fence_ops *ops; + struct rcu_head rcu; struct list_head cb_list; spinlock_t *lock; unsigned context, seqno; @@ -191,6 +194,20 @@ static inline struct fence *fence_get(struct fence *fence) return fence; } +/** + * fence_get_rcu - get a fence from a reservation_object_list with rcu read lock + * @fence: [in] fence to increase refcount of + * + * Function returns NULL if no refcount could be obtained, or the fence. + */ +static inline struct fence *fence_get_rcu(struct fence *fence) +{ + if (kref_get_unless_zero(&fence->refcount)) + return fence; + else + return NULL; +} + /** * fence_put - decreases refcount of the fence * @fence: [in] fence to reduce refcount of diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 2affe67dea6e..5a0b64cf68b4 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -42,22 +42,29 @@ #include #include #include +#include +#include extern struct ww_class reservation_ww_class; +extern struct lock_class_key reservation_seqcount_class; +extern const char reservation_seqcount_string[]; struct reservation_object_list { + struct rcu_head rcu; u32 shared_count, shared_max; - struct fence *shared[]; + struct fence __rcu *shared[]; }; struct reservation_object { struct ww_mutex lock; + seqcount_t seq; - struct fence *fence_excl; - struct reservation_object_list *fence; + struct fence __rcu *fence_excl; + struct reservation_object_list __rcu *fence; struct reservation_object_list *staged; }; +#define reservation_object_held(obj) lockdep_is_held(&(obj)->lock.base) #define reservation_object_assert_held(obj) \ lockdep_assert_held(&(obj)->lock.base) @@ -66,8 +73,9 @@ reservation_object_init(struct reservation_object *obj) { ww_mutex_init(&obj->lock, &reservation_ww_class); - obj->fence_excl = NULL; - obj->fence = NULL; + __seqcount_init(&obj->seq, reservation_seqcount_string, &reservation_seqcount_class); + RCU_INIT_POINTER(obj->fence, NULL); + RCU_INIT_POINTER(obj->fence_excl, NULL); obj->staged = NULL; } @@ -76,18 +84,20 @@ reservation_object_fini(struct reservation_object *obj) { int i; struct reservation_object_list *fobj; + struct fence *excl; /* * This object should be dead and all references must have - * been released to it. + * been released to it, so no need to be protected with rcu. */ - if (obj->fence_excl) - fence_put(obj->fence_excl); + excl = rcu_dereference_protected(obj->fence_excl, 1); + if (excl) + fence_put(excl); - fobj = obj->fence; + fobj = rcu_dereference_protected(obj->fence, 1); if (fobj) { for (i = 0; i < fobj->shared_count; ++i) - fence_put(fobj->shared[i]); + fence_put(rcu_dereference_protected(fobj->shared[i], 1)); kfree(fobj); } @@ -99,17 +109,15 @@ reservation_object_fini(struct reservation_object *obj) static inline struct reservation_object_list * reservation_object_get_list(struct reservation_object *obj) { - reservation_object_assert_held(obj); - - return obj->fence; + return rcu_dereference_protected(obj->fence, + reservation_object_held(obj)); } static inline struct fence * reservation_object_get_excl(struct reservation_object *obj) { - reservation_object_assert_held(obj); - - return obj->fence_excl; + return rcu_dereference_protected(obj->fence_excl, + reservation_object_held(obj)); } int reservation_object_reserve_shared(struct reservation_object *obj); @@ -119,4 +127,16 @@ void reservation_object_add_shared_fence(struct reservation_object *obj, void reservation_object_add_excl_fence(struct reservation_object *obj, struct fence *fence); +int reservation_object_get_fences_rcu(struct reservation_object *obj, + struct fence **pfence_excl, + unsigned *pshared_count, + struct fence ***pshared); + +long reservation_object_wait_timeout_rcu(struct reservation_object *obj, + bool wait_all, bool intr, + unsigned long timeout); + +bool reservation_object_test_signaled_rcu(struct reservation_object *obj, + bool test_all); + #endif /* _LINUX_RESERVATION_H */ -- cgit v1.2.3-59-g8ed1b From 5a1379e8748a5cfa3eb068f812d61bde849ef76c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 4 Jun 2014 17:48:15 +0200 Subject: firmware loader: allow disabling of udev as firmware loader [The patch was originally proposed by Tom Gundersen, and rewritten afterwards by me; most of changelogs below borrowed from Tom's original patch -- tiwai] Currently (at least) the dell-rbu driver selects FW_LOADER_USER_HELPER, which means that distros can't really stop loading firmware through udev without breaking other users (though some have). Ideally we would remove/disable the udev firmware helper in both the kernel and in udev, but if we were to disable it in udev and not the kernel, the result would be (seemingly) hung kernels as no one would be around to cancel firmware requests. This patch allows udev firmware loading to be disabled while still allowing non-udev firmware loading, as done by the dell-rbu driver, to continue working. This is achieved by only using the fallback mechanism when the uevent is suppressed. The patch renames the user-selectable Kconfig from FW_LOADER_USER_HELPER to FW_LOADER_USER_HELPER_FALLBACK, and the former is reverse-selected by the latter or the drivers that need userhelper like dell-rbu. Also, the "default y" is removed together with this change, since it's been deprecated in udev upstream, thus rather better to disable it nowadays. Tested with FW_LOADER_USER_HELPER=n LATTICE_ECP3_CONFIG=y DELL_RBU=y and udev without the firmware loading support, but I don't have the hardware to test the lattice/dell drivers, so additional testing would be appreciated. Reviewed-by: Tom Gundersen Cc: Ming Lei Cc: Abhay Salunke Cc: Stefan Roese Cc: Arnd Bergmann Cc: Kay Sievers Tested-by: Balaji Singh Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- drivers/base/Kconfig | 10 ++++++++-- drivers/base/firmware_class.c | 15 ++++++++++----- include/linux/firmware.h | 2 +- 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 00e13ce5cbbd..88500fed3c7a 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -149,15 +149,21 @@ config EXTRA_FIRMWARE_DIR some other directory containing the firmware files. config FW_LOADER_USER_HELPER + bool + +config FW_LOADER_USER_HELPER_FALLBACK bool "Fallback user-helper invocation for firmware loading" depends on FW_LOADER - default y + select FW_LOADER_USER_HELPER help This option enables / disables the invocation of user-helper (e.g. udev) for loading firmware files as a fallback after the direct file loading in kernel fails. The user-mode helper is no longer required unless you have a special firmware file that - resides in a non-standard path. + resides in a non-standard path. Moreover, the udev support has + been deprecated upstream. + + If you are unsure about this, say N here. config DEBUG_DRIVER bool "Driver Core verbose debug messages" diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index d276e33880be..46ea5f4c3bb5 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -100,9 +100,14 @@ static inline long firmware_loading_timeout(void) #define FW_OPT_UEVENT (1U << 0) #define FW_OPT_NOWAIT (1U << 1) #ifdef CONFIG_FW_LOADER_USER_HELPER -#define FW_OPT_FALLBACK (1U << 2) +#define FW_OPT_USERHELPER (1U << 2) #else -#define FW_OPT_FALLBACK 0 +#define FW_OPT_USERHELPER 0 +#endif +#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK +#define FW_OPT_FALLBACK FW_OPT_USERHELPER +#else +#define FW_OPT_FALLBACK 0 #endif struct firmware_cache { @@ -1111,7 +1116,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name, ret = fw_get_filesystem_firmware(device, fw->priv); if (ret) { - if (opt_flags & FW_OPT_FALLBACK) { + if (opt_flags & FW_OPT_USERHELPER) { dev_warn(device, "Direct firmware load failed with error %d\n", ret); @@ -1171,7 +1176,7 @@ request_firmware(const struct firmware **firmware_p, const char *name, } EXPORT_SYMBOL(request_firmware); -#ifdef CONFIG_FW_LOADER_USER_HELPER +#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK /** * request_firmware: - load firmware directly without usermode helper * @firmware_p: pointer to firmware image @@ -1277,7 +1282,7 @@ request_firmware_nowait( fw_work->context = context; fw_work->cont = cont; fw_work->opt_flags = FW_OPT_NOWAIT | FW_OPT_FALLBACK | - (uevent ? FW_OPT_UEVENT : 0); + (uevent ? FW_OPT_UEVENT : FW_OPT_USERHELPER); if (!try_module_get(module)) { kfree(fw_work); diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 59529330efd6..67e5b801af0c 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -68,7 +68,7 @@ static inline void release_firmware(const struct firmware *fw) #endif -#ifdef CONFIG_FW_LOADER_USER_HELPER +#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK int request_firmware_direct(const struct firmware **fw, const char *name, struct device *device); #else -- cgit v1.2.3-59-g8ed1b From c868edf42b4db89907b467c92b7f035c8c1cb0e5 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 2 Jul 2014 09:55:05 -0700 Subject: firmware loader: inform direct failure when udev loader is disabled Now that the udev firmware loader is optional request_firmware() will not provide any information on the kernel ring buffer if direct firmware loading failed and udev firmware loading is disabled. If no information is needed request_firmware_direct() should be used for optional firmware, at which point drivers can take on the onus over informing of any failures, if udev firmware loading is disabled though we should at the very least provide some sort of information as when the udev loader was enabled by default back in the days. With this change with a simple firmware load test module [0]: Example output without FW_LOADER_USER_HELPER_FALLBACK platform fake-dev.0: Direct firmware load for fake.bin failed with error -2 Example with FW_LOADER_USER_HELPER_FALLBACK platform fake-dev.0: Direct firmware load for fake.bin failed with error -2 platform fake-dev.0: Falling back to user helper Without this change without FW_LOADER_USER_HELPER_FALLBACK we get no output logged upon failure. Cc: Tom Gundersen Cc: Ming Lei Cc: Abhay Salunke Cc: Stefan Roese Cc: Arnd Bergmann Cc: Kay Sievers Signed-off-by: Luis R. Rodriguez Reviewed-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_class.c | 13 +++++++------ include/linux/firmware.h | 15 ++++++++------- 2 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 28bc6db9fbf4..124d50ceb116 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -109,6 +109,7 @@ static inline long firmware_loading_timeout(void) #else #define FW_OPT_FALLBACK 0 #endif +#define FW_OPT_NO_WARN (1U << 3) struct firmware_cache { /* firmware_buf instance will be added into the below list */ @@ -1105,10 +1106,11 @@ _request_firmware(const struct firmware **firmware_p, const char *name, ret = fw_get_filesystem_firmware(device, fw->priv); if (ret) { - if (opt_flags & FW_OPT_USERHELPER) { + if (!(opt_flags & FW_OPT_NO_WARN)) dev_warn(device, - "Direct firmware load failed with error %d\n", - ret); + "Direct firmware load for %s failed with error %d\n", + name, ret); + if (opt_flags & FW_OPT_USERHELPER) { dev_warn(device, "Falling back to user helper\n"); ret = fw_load_from_user_helper(fw, name, device, opt_flags, timeout); @@ -1165,7 +1167,6 @@ request_firmware(const struct firmware **firmware_p, const char *name, } EXPORT_SYMBOL(request_firmware); -#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK /** * request_firmware: - load firmware directly without usermode helper * @firmware_p: pointer to firmware image @@ -1182,12 +1183,12 @@ int request_firmware_direct(const struct firmware **firmware_p, { int ret; __module_get(THIS_MODULE); - ret = _request_firmware(firmware_p, name, device, FW_OPT_UEVENT); + ret = _request_firmware(firmware_p, name, device, + FW_OPT_UEVENT | FW_OPT_NO_WARN); module_put(THIS_MODULE); return ret; } EXPORT_SYMBOL_GPL(request_firmware_direct); -#endif /** * release_firmware: - release the resource associated with a firmware image diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 67e5b801af0c..5c41c5e75b5c 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -45,6 +45,8 @@ int request_firmware_nowait( struct module *module, bool uevent, const char *name, struct device *device, gfp_t gfp, void *context, void (*cont)(const struct firmware *fw, void *context)); +int request_firmware_direct(const struct firmware **fw, const char *name, + struct device *device); void release_firmware(const struct firmware *fw); #else @@ -66,13 +68,12 @@ static inline void release_firmware(const struct firmware *fw) { } -#endif +static inline int request_firmware_direct(const struct firmware **fw, + const char *name, + struct device *device) +{ + return -EINVAL; +} -#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK -int request_firmware_direct(const struct firmware **fw, const char *name, - struct device *device); -#else -#define request_firmware_direct request_firmware #endif - #endif -- cgit v1.2.3-59-g8ed1b From 3d713e0e382e6fcfb4bba1501645b66c129ad60b Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Mon, 2 Jun 2014 19:42:58 -0500 Subject: driver core: platform: add device binding path 'driver_override' Needed by platform device drivers, such as the upcoming vfio-platform driver, in order to bypass the existing OF, ACPI, id_table and name string matches, and successfully be able to be bound to any device, like so: echo vfio-platform > /sys/bus/platform/devices/fff51000.ethernet/driver_override echo fff51000.ethernet > /sys/bus/platform/devices/fff51000.ethernet/driver/unbind echo fff51000.ethernet > /sys/bus/platform/drivers_probe This mimics "PCI: Introduce new device binding path using pci_dev.driver_override", which is an interface enhancement for more deterministic PCI device binding, e.g., when in the presence of hotplug. Reviewed-by: Alex Williamson Reviewed-by: Alexander Graf Reviewed-by: Stuart Yoder Signed-off-by: Kim Phillips Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-bus-platform | 20 ++++++++++++ drivers/base/platform.c | 47 ++++++++++++++++++++++++++++ include/linux/platform_device.h | 1 + 3 files changed, 68 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-bus-platform (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-platform b/Documentation/ABI/testing/sysfs-bus-platform new file mode 100644 index 000000000000..5172a6124b27 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-platform @@ -0,0 +1,20 @@ +What: /sys/bus/platform/devices/.../driver_override +Date: April 2014 +Contact: Kim Phillips +Description: + This file allows the driver for a device to be specified which + will override standard OF, ACPI, ID table, and name matching. + When specified, only a driver with a name matching the value + written to driver_override will have an opportunity to bind + to the device. The override is specified by writing a string + to the driver_override file (echo vfio-platform > \ + driver_override) and may be cleared with an empty string + (echo > driver_override). This returns the device to standard + matching rules binding. Writing to driver_override does not + automatically unbind the device from its current driver or make + any attempt to automatically load the specified driver. If no + driver with a matching name is currently loaded in the kernel, + the device will not bind to any driver. This also allows + devices to opt-out of driver binding using a driver_override + name such as "none". Only a single driver may be specified in + the override, there is no support for parsing delimiters. diff --git a/drivers/base/platform.c b/drivers/base/platform.c index c48c4acb9b87..148f66a1d49a 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "base.h" #include "power/power.h" @@ -191,6 +192,7 @@ static void platform_device_release(struct device *dev) kfree(pa->pdev.dev.platform_data); kfree(pa->pdev.mfd_cell); kfree(pa->pdev.resource); + kfree(pa->pdev.driver_override); kfree(pa); } @@ -698,8 +700,49 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a, } static DEVICE_ATTR_RO(modalias); +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct platform_device *pdev = to_platform_device(dev); + char *driver_override, *old = pdev->driver_override, *cp; + + if (count > PATH_MAX) + return -EINVAL; + + driver_override = kstrndup(buf, count, GFP_KERNEL); + if (!driver_override) + return -ENOMEM; + + cp = strchr(driver_override, '\n'); + if (cp) + *cp = '\0'; + + if (strlen(driver_override)) { + pdev->driver_override = driver_override; + } else { + kfree(driver_override); + pdev->driver_override = NULL; + } + + kfree(old); + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct platform_device *pdev = to_platform_device(dev); + + return sprintf(buf, "%s\n", pdev->driver_override); +} +static DEVICE_ATTR_RW(driver_override); + + static struct attribute *platform_dev_attrs[] = { &dev_attr_modalias.attr, + &dev_attr_driver_override.attr, NULL, }; ATTRIBUTE_GROUPS(platform_dev); @@ -755,6 +798,10 @@ static int platform_match(struct device *dev, struct device_driver *drv) struct platform_device *pdev = to_platform_device(dev); struct platform_driver *pdrv = to_platform_driver(drv); + /* When driver_override is set, only bind to the matching driver */ + if (pdev->driver_override) + return !strcmp(pdev->driver_override, drv->name); + /* Attempt an OF style match first */ if (of_driver_match_device(dev, drv)) return 1; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 16f6654082dd..153d303af7eb 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -28,6 +28,7 @@ struct platform_device { struct resource *resource; const struct platform_device_id *id_entry; + char *driver_override; /* Driver name to force a match */ /* MFD cell pointer */ struct mfd_cell *mfd_cell; -- cgit v1.2.3-59-g8ed1b