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 = fence->sync_buf; get_dma_buf(fence_buf);

... tell the hw the memory location to wait ... custom_wait_on(fence_buf, fence->seqno_ofs, fence->seqno); } else { /* fall-back to sw sync * / fence_add_callback(fence, my_cb); }

On SoC platforms, if some other hw mechanism is provided for synchronizing between IP blocks, it could be supported as an alternate implementation with it's own fence ops in a similar way.

enable_signaling callback is used to provide sw signaling in case a cpu waiter is requested or no compatible hardware signaling could be used.

The intention is to provide a userspace interface (presumably via eventfd) later, to be used in conjunction with dma-buf's mmap support for sw access to buffers (or for userspace apps that would prefer to do their own synchronization).

v1: Original v2: After discussion w/ danvet and mlankhorst on #dri-devel, we decided that dma-fence didn't need to care about the sw->hw signaling path (it can be handled same as sw->sw case), and therefore the fence->ops can be simplified and more handled in the core. So remove the signal, add_callback, cancel_callback, and wait ops, and replace with a simple enable_signaling() op which can be used to inform a fence supporting hw->hw signaling that one or more devices which do not support hw signaling are waiting (and therefore it should enable an irq or do whatever is necessary in order that the CPU is notified when the fence is passed). v3: Fix locking fail in attach_fence() and get_fence() v4: Remove tie-in w/ dma-buf.. after discussion w/ danvet and mlankorst we decided that we need to be able to attach one fence to N dma-buf's, so using the list_head in dma-fence struct would be problematic. v5: [ Maarten Lankhorst ] Updated for dma-bikeshed-fence and dma-buf-manager. v6: [ Maarten Lankhorst ] I removed dma_fence_cancel_callback and some comments about checking if fence fired or not. This is broken by design. waitqueue_active during destruction is now fatal, since the signaller should be holding a reference in enable_signalling until it signalled the fence. Pass the original dma_fence_cb along, and call __remove_wait in the dma_fence_callback handler, so that no cleanup needs to be performed. v7: [ Maarten Lankhorst ] Set cb->func and only enable sw signaling if fence wasn't signaled yet, for example for hardware fences that may choose to signal blindly. v8: [ Maarten Lankhorst ] Tons of tiny fixes, moved __dma_fence_init to header and fixed include mess. dma-fence.h now includes dma-buf.h All members are now initialized, so kmalloc can be used for allocating a dma-fence. More documentation added. v9: Change compiler bitfields to flags, change return type of enable_signaling to bool. Rework dma_fence_wait. Added dma_fence_is_signaled and dma_fence_wait_timeout. s/dma// and change exports to non GPL. Added fence_is_signaled and fence_enable_sw_signaling calls, add ability to override default wait operation. v10: remove event_queue, use a custom list, export try_to_wake_up from scheduler. Remove fence lock and use a global spinlock instead, this should hopefully remove all the locking headaches I was having on trying to implement this. enable_signaling is called with this lock held. v11: Use atomic ops for flags, lifting the need for some spin_lock_irqsaves. However I kept the guarantee that after fence_signal returns, it is guaranteed that enable_signaling has either been called to completion, or will not be called any more.

Add contexts and seqno to base fence implementation. This allows you to wait for less fences, by testing for seqno + signaled, and then only wait on the later fence.

Add FENCE_TRACE, FENCE_WARN, and FENCE_ERR. This makes debugging easier. An CONFIG_DEBUG_FENCE will be added to turn off the FENCE_TRACE spam, and another runtime option can turn it off at runtime. v12: Add CONFIG_FENCE_TRACE. Add missing documentation for the fence->context and fence->seqno members. 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.

Signed-off-by: Maarten Lankhorst maarten.lankhorst@canonical.com --- Documentation/DocBook/device-drivers.tmpl | 2 drivers/base/Kconfig | 9 + drivers/base/Makefile | 2 drivers/base/fence.c | 415 +++++++++++++++++++++++++++++ include/linux/fence.h | 329 +++++++++++++++++++++++ include/trace/events/fence.h | 125 +++++++++ 6 files changed, 881 insertions(+), 1 deletion(-) create mode 100644 drivers/base/fence.c create mode 100644 include/linux/fence.h create mode 100644 include/trace/events/fence.h

diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index f5170082bdb3..7a0c9ddb4818 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -129,6 +129,8 @@ X!Edrivers/base/interface.c </sect1> <sect1><title>Device Drivers DMA Management</title> !Edrivers/base/dma-buf.c +!Edrivers/base/fence.c +!Iinclude/linux/fence.h !Edrivers/base/reservation.c !Iinclude/linux/reservation.h !Edrivers/base/dma-coherent.c diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index e373671652b0..f8a68aa8c06a 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -200,6 +200,15 @@ 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/base/Makefile b/drivers/base/Makefile index 94e8a80e87f8..253b836a7b68 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_DMA_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o -obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf.o reservation.o +obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf.o fence.o reservation.o obj-$(CONFIG_ISA) += isa.o obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o diff --git a/drivers/base/fence.c b/drivers/base/fence.c new file mode 100644 index 000000000000..ac5f68020436 --- /dev/null +++ b/drivers/base/fence.c @@ -0,0 +1,415 @@ +/* + * 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 robdclark@gmail.com + * Maarten Lankhorst maarten.lankhorst@canonical.com + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see http://www.gnu.org/licenses/. + */ + +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/atomic.h> +#include <linux/fence.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/fence.h> + +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); + +int __fence_signal(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_clear_bit(); + } + + 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); + +/** + * 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_clear_bit(); + } + + 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. + */ +long +fence_wait_timeout(struct fence *fence, bool intr, signed long timeout) +{ + unsigned 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 release_fence(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 + kfree(fence); +} +EXPORT_SYMBOL(release_fence); + +/** + * fence_enable_sw_signaling - enable signaling on fence + * @fence: [in] the fence to enable + * + * this will request for sw signaling to be enabled, to make the fence + * complete as soon as possible + */ +void fence_enable_sw_signaling(struct fence *fence) +{ + unsigned long flags; + + if (!test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags) && + !test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + trace_fence_enable_signal(fence); + + spin_lock_irqsave(fence->lock, flags); + + if (!fence->ops->enable_signaling(fence)) + __fence_signal(fence); + + spin_unlock_irqrestore(fence->lock, flags); + } +} +EXPORT_SYMBOL(fence_enable_sw_signaling); + +/** + * fence_add_callback - add a callback to be called when the fence + * is signaled + * @fence: [in] the fence to wait on + * @cb: [in] the callback to register + * @func: [in] the function to call + * + * 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(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); + + try_to_wake_up(wait->task, TASK_NORMAL, 0); +} + +/** + * fence_default_wait - default sleep until the fence gets signaled + * or until timeout elapses + * @fence: [in] the fence to wait on + * @intr: [in] if true, do an interruptible wait + * @timeout: [in] timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the + * remaining timeout in jiffies on success. + */ +long +fence_default_wait(struct fence *fence, bool intr, signed long timeout) +{ + struct default_wait_cb cb; + unsigned long flags; + long ret = timeout; + bool was_set; + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return timeout; + + spin_lock_irqsave(fence->lock, flags); + + if (intr && signal_pending(current)) { + ret = -ERESTARTSYS; + goto out; + } + + was_set = test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + goto out; + + if (!was_set) { + trace_fence_enable_signal(fence); + + if (!fence->ops->enable_signaling(fence)) { + __fence_signal(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..a868eceb7cf5 --- /dev/null +++ b/include/linux/fence.h @@ -0,0 +1,329 @@ +/* + * Fence mechanism for dma-buf to allow for asynchronous dma access + * + * Copyright (C) 2012 Canonical Ltd + * Copyright (C) 2012 Texas Instruments + * + * Authors: + * Rob Clark robdclark@gmail.com + * Maarten Lankhorst maarten.lankhorst@canonical.com + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see http://www.gnu.org/licenses/. + */ + +#ifndef __LINUX_FENCE_H +#define __LINUX_FENCE_H + +#include <linux/err.h> +#include <linux/wait.h> +#include <linux/list.h> +#include <linux/bitops.h> +#include <linux/kref.h> +#include <linux/sched.h> +#include <linux/printk.h> + +struct fence; +struct fence_ops; +struct fence_cb; + +/** + * struct fence - software synchronization primitive + * @refcount: refcount for this fence + * @ops: fence_ops associated with this fence + * @cb_list: list of all callbacks to call + * @lock: spin_lock_irqsave used for locking + * @context: execution context this fence belongs to, returned by + * fence_context_alloc() + * @seqno: the sequence number of this fence inside the execution context, + * can be compared to decide which fence would be signaled later. + * @flags: A mask of FENCE_FLAG_* defined below + * @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); + 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); + +/** + * fence_get - increases refcount of the fence + * @fence: [in] fence to increase refcount of + */ +static inline void fence_get(struct fence *fence) +{ + if (WARN_ON(!fence)) + return; + kref_get(&fence->refcount); +} + +extern void release_fence(struct kref *kref); + +/** + * fence_put - decreases refcount of the fence + * @fence: [in] fence to reduce refcount of + */ +static inline void fence_put(struct fence *fence) +{ + if (WARN_ON(!fence)) + return; + kref_put(&fence->refcount, release_fence); +} + +int fence_signal(struct fence *fence); +int __fence_signal(struct fence *fence); +long fence_default_wait(struct fence *fence, bool intr, signed long timeout); +int fence_add_callback(struct fence *fence, struct fence_cb *cb, + fence_func_t func); +bool fence_remove_callback(struct fence *fence, struct fence_cb *cb); +void fence_enable_sw_signaling(struct fence *fence); + +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_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) +{ + BUG_ON(f1->context != f2->context); + + /* + * can't check just FENCE_FLAG_SIGNALED_BIT here, it may never have been + * set called if enable_signaling wasn't, and enabling that here is + * overkill. + */ + if (f2->seqno - f1->seqno <= INT_MAX) + return fence_is_signaled(f2) ? NULL : f2; + else + return fence_is_signaled(f1) ? NULL : f1; +} + +long fence_wait_timeout(struct fence *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 (buf-mgr between reservation and committing) + * holds a reference to the fence, otherwise the fence might be + * freed before return, resulting in undefined behavior. + */ +static inline long fence_wait(struct fence *fence, bool intr) +{ + long ret; + + /* Since fence_wait_timeout cannot timeout with + * MAX_SCHEDULE_TIMEOUT, only valid return values are + * -ERESTARTSYS and MAX_SCHEDULE_TIMEOUT. + */ + ret = fence_wait_timeout(fence, intr, MAX_SCHEDULE_TIMEOUT); + + return ret < 0 ? ret : 0; +} + +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..ce3d83230cff --- /dev/null +++ b/include/trace/events/fence.h @@ -0,0 +1,125 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM fence + +#if !defined(_TRACE_FENCE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_FENCE_H + +#include <linux/tracepoint.h> + +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 <trace/define_trace.h>

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 maarten.lankhorst@canonical.com --- drivers/base/dma-buf.c | 22 ++++++++++++++++++++-- drivers/gpu/drm/drm_prime.c | 8 +++++++- drivers/gpu/drm/exynos/exynos_drm_dmabuf.c | 2 +- drivers/gpu/drm/i915/i915_gem_dmabuf.c | 2 +- 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/ttm/ttm_object.c | 2 +- drivers/media/v4l2-core/videobuf2-dma-contig.c | 2 +- include/drm/drmP.h | 2 ++ include/linux/dma-buf.h | 9 ++++++--- 14 files changed, 59 insertions(+), 11 deletions(-)

diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 1e16cbd61da2..85e792c2c909 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -25,10 +25,12 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/dma-buf.h> +#include <linux/fence.h> #include <linux/anon_inodes.h> #include <linux/export.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/reservation.h>

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/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 56805c39c906..a13e90245adf 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -318,7 +318,13 @@ 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 59827cc5e770..b5e89f46326e 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 9bb533e0d762..ea66f40e95b3 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -233,7 +233,7 @@ static const struct dma_buf_ops i915_dmabuf_ops = { struct dma_buf *i915_gem_prime_export(struct drm_device *dev, struct drm_gem_object *gem_obj, int flags) { - 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 98a22e6e27a1..c7cff8163882 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -808,6 +808,7 @@ 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 db39ea36bf22..1ee9c9697be8 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -126,6 +126,7 @@ 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, @@ -549,6 +550,7 @@ 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/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c index 6fe7b92a82d1..411bbe4617d9 100644 --- a/drivers/gpu/drm/ttm/ttm_object.c +++ b/drivers/gpu/drm/ttm/ttm_object.c @@ -631,7 +631,7 @@ 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 33d3871d1e13..93bd2230ab0b 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/include/drm/drmP.h b/include/drm/drmP.h index 1d4a920ef7ff..1725225eb6ab 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -81,6 +81,7 @@ struct drm_device;

struct device_node; struct videomode; +struct reservation_object;

#include <drm/drm_os_linux.h> #include <drm/drm_hashtab.h> @@ -950,6 +951,7 @@ 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 *); 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 dfac5ed31120..34cfbac52c03 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, __FILE__) +#define dma_buf_export(priv, ops, size, flags, resv) \ + dma_buf_export_named(priv, ops, size, flags, __FILE__, resv)

int dma_buf_fd(struct dma_buf *dmabuf, int flags); struct dma_buf *dma_buf_get(int fd);

Signed-off-by: Maarten Lankhorst maarten.lankhorst@canonical.com --- include/linux/reservation.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 813dae960ebd..92c4851b5a39 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@linaro.org + * Rob Clark robdclark@gmail.com * Maarten Lankhorst maarten.lankhorst@canonical.com * Thomas Hellstrom <thellstrom-at-vmware-dot-com> * @@ -40,22 +40,38 @@ #define _LINUX_RESERVATION_H

#include <linux/ww_mutex.h> +#include <linux/fence.h>

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]); + ww_mutex_destroy(&obj->lock); }

On Mon, Jan 13, 2014 at 4:31 AM, Maarten Lankhorst maarten.lankhorst@canonical.com wrote:

The kernel fence implementation doesn't use event queues, but needs to perform the same wake up. The symbol is not exported, since the fence implementation is not built as a module.

Signed-off-by: Maarten Lankhorst maarten.lankhorst@canonical.com

include/linux/wait.h | 1 + kernel/sched/core.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/wait.h b/include/linux/wait.h index eaa00b10abaa..c54e3ef50134 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -12,6 +12,7 @@ typedef struct __wait_queue wait_queue_t; typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key); +int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags);

struct __wait_queue { unsigned int flags; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a88f4a485c5e..f41d317042dd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1578,7 +1578,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)

• Return: %true if @p was woken up, %false if it was already running.
• or @state didn't match @p's state.

*/ -static int +int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) { unsigned long flags;

wake_up_state is already available in linux/sched.h, can you use that?

Em Mon, 13 Jan 2014 13:32:16 +0100 Maarten Lankhorst maarten.lankhorst@canonical.com escreveu:

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 maarten.lankhorst@canonical.com

drivers/base/dma-buf.c | 22 ++++++++++++++++++++-- drivers/gpu/drm/drm_prime.c | 8 +++++++- drivers/gpu/drm/exynos/exynos_drm_dmabuf.c | 2 +- drivers/gpu/drm/i915/i915_gem_dmabuf.c | 2 +- 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/ttm/ttm_object.c | 2 +-

drivers/media/v4l2-core/videobuf2-dma-contig.c | 2 +-

With regards to this small change on VB2-dma-contig: Acked-by: Mauro Carvalho Chehab m.chehab@samsung.com

include/drm/drmP.h | 2 ++ include/linux/dma-buf.h | 9 ++++++--- 14 files changed, 59 insertions(+), 11 deletions(-)

diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 1e16cbd61da2..85e792c2c909 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -25,10 +25,12 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/dma-buf.h> +#include <linux/fence.h> #include <linux/anon_inodes.h> #include <linux/export.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/reservation.h> 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/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 56805c39c906..a13e90245adf 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -318,7 +318,13 @@ 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 59827cc5e770..b5e89f46326e 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 9bb533e0d762..ea66f40e95b3 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -233,7 +233,7 @@ static const struct dma_buf_ops i915_dmabuf_ops = { struct dma_buf *i915_gem_prime_export(struct drm_device *dev, struct drm_gem_object *gem_obj, int flags) {

• 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 98a22e6e27a1..c7cff8163882 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -808,6 +808,7 @@ 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 db39ea36bf22..1ee9c9697be8 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -126,6 +126,7 @@ 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, @@ -549,6 +550,7 @@ 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/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c index 6fe7b92a82d1..411bbe4617d9 100644 --- a/drivers/gpu/drm/ttm/ttm_object.c +++ b/drivers/gpu/drm/ttm/ttm_object.c @@ -631,7 +631,7 @@ 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 33d3871d1e13..93bd2230ab0b 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/include/drm/drmP.h b/include/drm/drmP.h index 1d4a920ef7ff..1725225eb6ab 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -81,6 +81,7 @@ struct drm_device; struct device_node; struct videomode; +struct reservation_object; #include <drm/drm_os_linux.h> #include <drm/drm_hashtab.h> @@ -950,6 +951,7 @@ 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 *); 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 dfac5ed31120..34cfbac52c03 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, __FILE__)

+#define dma_buf_export(priv, ops, size, flags, resv) \

• dma_buf_export_named(priv, ops, size, flags, __FILE__, resv)

int dma_buf_fd(struct dma_buf *dmabuf, int flags); struct dma_buf *dma_buf_get(int fd);

-- To unsubscribe from this list: send the line "unsubscribe linux-media" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html