On Wed, Jul 13, 2016 at 03:10:45PM +0100, Chris Wilson wrote:
> I plan to usurp the short name of struct fence for a core kernel struct,
> and so I need to rename the specialised fence/timeline for DMA
> operations to make room.
>
> As an indication of the scale of the flag day:
>
> 91 files changed, 904 insertions(+), 880 deletions(-)
>
> with the greatest victim being amdgpu.
>
> Just the highlights shown below.
+1 on dma_fence, for more consistency with dma_buf and everything else
dma_*. I think if we land this right before/after 4.8-rc1 through the drm
tree it should be minimally invasive. Worst case we'll have a fun merge
between drm.git and drm-intel.git (since drm-intel-next-queued doesn't get
closed while the merge window is open).
Adding lots more people to gather their opinion.
-Daniel
> -Chris
>
> ---
> drivers/base/Kconfig | 6 +-
> drivers/dma-buf/Makefile | 2 +-
> drivers/dma-buf/dma-buf.c | 28 +-
> drivers/dma-buf/dma-fence.c | 535 ++++++++++++++++++++++++
> drivers/dma-buf/fence.c | 532 -----------------------
> drivers/dma-buf/reservation.c | 90 ++--
> drivers/dma-buf/seqno-fence.c | 18 +-
> drivers/dma-buf/sw_sync.c | 44 +-
> drivers/dma-buf/sync_debug.c | 9 +-
> drivers/dma-buf/sync_debug.h | 13 +-
> drivers/dma-buf/sync_file.c | 30 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu.h | 56 +--
> drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c | 8 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 18 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 22 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 16 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 50 +--
> drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 10 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 18 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 4 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c | 24 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 56 +--
> drivers/gpu/drm/amd/amdgpu/amdgpu_test.c | 12 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h | 4 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 18 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h | 4 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 22 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h | 4 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 56 +--
> drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 8 +-
> drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 8 +-
> drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 16 +-
> drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 8 +-
> drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 8 +-
> drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c | 6 +-
> drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c | 6 +-
> drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 6 +-
> drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h | 4 +-
> drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 42 +-
> drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 24 +-
> drivers/gpu/drm/amd/scheduler/sched_fence.c | 22 +-
> drivers/gpu/drm/drm_atomic_helper.c | 6 +-
> drivers/gpu/drm/etnaviv/etnaviv_gem.c | 6 +-
> drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 46 +-
> drivers/gpu/drm/etnaviv/etnaviv_gpu.h | 4 +-
> drivers/gpu/drm/imx/ipuv3-crtc.c | 12 +-
> drivers/gpu/drm/msm/msm_drv.h | 2 +-
> drivers/gpu/drm/msm/msm_fence.c | 30 +-
> drivers/gpu/drm/msm/msm_fence.h | 2 +-
> drivers/gpu/drm/msm/msm_gem.c | 14 +-
> drivers/gpu/drm/msm/msm_gem.h | 2 +-
> drivers/gpu/drm/msm/msm_gem_submit.c | 2 +-
> drivers/gpu/drm/msm/msm_gpu.c | 2 +-
> drivers/gpu/drm/nouveau/nouveau_bo.c | 6 +-
> drivers/gpu/drm/nouveau/nouveau_fence.c | 68 +--
> drivers/gpu/drm/nouveau/nouveau_fence.h | 6 +-
> drivers/gpu/drm/nouveau/nouveau_gem.c | 2 +-
> drivers/gpu/drm/nouveau/nv04_fence.c | 2 +-
> drivers/gpu/drm/nouveau/nv10_fence.c | 2 +-
> drivers/gpu/drm/nouveau/nv17_fence.c | 2 +-
> drivers/gpu/drm/nouveau/nv50_fence.c | 2 +-
> drivers/gpu/drm/nouveau/nv84_fence.c | 2 +-
> drivers/gpu/drm/qxl/qxl_drv.h | 4 +-
> drivers/gpu/drm/qxl/qxl_release.c | 27 +-
> drivers/gpu/drm/radeon/radeon.h | 10 +-
> drivers/gpu/drm/radeon/radeon_device.c | 2 +-
> drivers/gpu/drm/radeon/radeon_display.c | 8 +-
> drivers/gpu/drm/radeon/radeon_fence.c | 50 +--
> drivers/gpu/drm/radeon/radeon_sync.c | 6 +-
> drivers/gpu/drm/radeon/radeon_uvd.c | 2 +-
> drivers/gpu/drm/ttm/ttm_bo.c | 24 +-
> drivers/gpu/drm/ttm/ttm_bo_util.c | 2 +-
> drivers/gpu/drm/ttm/ttm_execbuf_util.c | 3 +-
> drivers/gpu/drm/virtio/virtgpu_display.c | 2 +-
> drivers/gpu/drm/virtio/virtgpu_drv.h | 2 +-
> drivers/gpu/drm/virtio/virtgpu_fence.c | 22 +-
> drivers/gpu/drm/virtio/virtgpu_ioctl.c | 12 +-
> drivers/gpu/drm/vmwgfx/vmwgfx_fence.c | 40 +-
> drivers/gpu/drm/vmwgfx/vmwgfx_fence.h | 8 +-
> drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 2 +-
> include/drm/drm_crtc.h | 4 +-
> include/drm/ttm/ttm_bo_driver.h | 2 +-
> include/drm/ttm/ttm_execbuf_util.h | 2 +-
> include/linux/dma-buf.h | 4 +-
> include/linux/dma-fence.h | 392 +++++++++++++++++
> include/linux/fence.h | 379 -----------------
> include/linux/reservation.h | 28 +-
> include/linux/seqno-fence.h | 16 +-
> include/linux/sync_file.h | 8 +-
> include/trace/events/dma-fence.h | 128 ++++++
> include/trace/events/fence.h | 128 ------
> 94 files changed, 1719 insertions(+), 1695 deletions(-)
> create mode 100644 drivers/dma-buf/dma-fence.c
> delete mode 100644 drivers/dma-buf/fence.c
> create mode 100644 include/linux/dma-fence.h
> delete mode 100644 include/linux/fence.h
> create mode 100644 include/trace/events/dma-fence.h
> delete mode 100644 include/trace/events/fence.h
>
> diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
> index 98504ec99c7d..2f716c374616 100644
> --- a/drivers/base/Kconfig
> +++ b/drivers/base/Kconfig
> @@ -238,11 +238,11 @@ 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"
> +config DMA_FENCE_TRACE
> + bool "Enable verbose DMA_FENCE_TRACE messages"
> depends on DMA_SHARED_BUFFER
> help
> - Enable the FENCE_TRACE printks. This will add extra
> + Enable the DMA_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.
> diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
> index d1559cd04e3d..8a5a6dc917f6 100644
> --- a/include/drm/drm_crtc.h
> +++ b/include/drm/drm_crtc.h
> @@ -43,7 +43,7 @@ struct drm_object_properties;
> struct drm_file;
> struct drm_clip_rect;
> struct device_node;
> -struct fence;
> +struct dma_fence;
>
> struct drm_mode_object {
> uint32_t id;
> @@ -1270,7 +1270,7 @@ struct drm_plane_state {
>
> struct drm_crtc *crtc; /* do not write directly, use drm_atomic_set_crtc_for_plane() */
> struct drm_framebuffer *fb; /* do not write directly, use drm_atomic_set_fb_for_plane() */
> - struct fence *fence;
> + struct dma_fence *fence;
>
> /* Signed dest location allows it to be partially off screen */
> int32_t crtc_x, crtc_y;
> diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
> index 513f7f96b80a..325776a00907 100644
> --- a/include/drm/ttm/ttm_bo_driver.h
> +++ b/include/drm/ttm/ttm_bo_driver.h
> @@ -1023,7 +1023,7 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
> */
>
> extern int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
> - struct fence *fence,
> + struct dma_fence *fence,
> bool evict, bool no_wait_gpu,
> struct ttm_mem_reg *new_mem);
> /**
> diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
> index b620c317c772..47f35b8e6d09 100644
> --- a/include/drm/ttm/ttm_execbuf_util.h
> +++ b/include/drm/ttm/ttm_execbuf_util.h
> @@ -114,6 +114,6 @@ extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
>
> extern void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
> struct list_head *list,
> - struct fence *fence);
> + struct dma_fence *fence);
>
> #endif
> diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
> index 4551c6f2a6c4..a22550795ac7 100644
> --- a/include/linux/dma-buf.h
> +++ b/include/linux/dma-buf.h
> @@ -30,7 +30,7 @@
> #include <linux/list.h>
> #include <linux/dma-mapping.h>
> #include <linux/fs.h>
> -#include <linux/fence.h>
> +#include <linux/dma-fence.h>
> #include <linux/wait.h>
>
> struct device;
> @@ -143,7 +143,7 @@ struct dma_buf {
> wait_queue_head_t poll;
>
> struct dma_buf_poll_cb_t {
> - struct fence_cb cb;
> + struct dma_fence_cb cb;
> wait_queue_head_t *poll;
>
> unsigned long active;
> diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
> new file mode 100644
> index 000000000000..a543a87fd0ed
> --- /dev/null
> +++ b/include/linux/dma-fence.h
> @@ -0,0 +1,392 @@
> +/*
> + * 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@xxxxxxxxx>
> + * Maarten Lankhorst <maarten.lankhorst@xxxxxxxxxxxxx>
> + *
> + * 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_DMA_FENCE_H
> +#define __LINUX_DMA_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>
> +#include <linux/rcupdate.h>
> +
> +struct dma_fence;
> +struct dma_fence_ops;
> +struct dma_fence_cb;
> +
> +/**
> + * struct dma_fence - software synchronization primitive
> + * @refcount: refcount for this fence
> + * @ops: dma_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
> + * dma_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 DMA_FENCE_FLAG_* defined below
> + * @timestamp: Timestamp when the fence was signaled.
> + * @status: Optional, only valid if < 0, must be set before calling
> + * dma_fence_signal, indicates that the fence has completed with an error.
> + * @child_list: list of children fences
> + * @active_list: list of active fences
> + *
> + * 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.
> + *
> + * DMA_FENCE_FLAG_SIGNALED_BIT - fence is already signaled
> + * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called
> + * DMA_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 dma_fence_signal was called right
> + * before this bit was set, it would have been able to set the
> + * DMA_FENCE_FLAG_SIGNALED_BIT, before enable_signaling was called.
> + * Adding a check for DMA_FENCE_FLAG_SIGNALED_BIT after setting
> + * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT closes this race, and makes sure that
> + * after dma_fence_signal was called, any enable_signaling call will have either
> + * been completed, or never called at all.
> + */
> +struct dma_fence {
> + struct kref refcount;
> + const struct dma_fence_ops *ops;
> + struct rcu_head rcu;
> + struct list_head cb_list;
> + spinlock_t *lock;
> + unsigned context, seqno;
> + unsigned long flags;
> + ktime_t timestamp;
> + int status;
> +};
> +
> +enum dma_fence_flag_bits {
> + DMA_FENCE_FLAG_SIGNALED_BIT,
> + DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
> + DMA_FENCE_FLAG_USER_BITS, /* must always be last member */
> +};
> +
> +typedef void (*dma_fence_func_t)(struct dma_fence *fence,
> + struct dma_fence_cb *cb);
> +
> +/**
> + * struct dma_fence_cb - callback for dma_fence_add_callback
> + * @node: used by dma_fence_add_callback to append this struct to fence::cb_list
> + * @func: dma_fence_func_t to call
> + *
> + * This struct will be initialized by dma_fence_add_callback, additional
> + * data can be passed along by embedding dma_fence_cb in another struct.
> + */
> +struct dma_fence_cb {
> + struct list_head node;
> + dma_fence_func_t func;
> +};
> +
> +/**
> + * struct dma_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 dma_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 occurred that made it impossible to enable
> + * signaling. True indicates successful enabling.
> + *
> + * fence->status may be set in enable_signaling, but only when false is
> + * returned.
> + *
> + * Calling dma_fence_signal before enable_signaling is called allows
> + * for a tiny race window in which enable_signaling is called during,
> + * before, or after dma_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 dma_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 dma_fence_default_wait for default implementation.
> + * the dma_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 dma_fence_ops {
> + const char * (*get_driver_name)(struct dma_fence *fence);
> + const char * (*get_timeline_name)(struct dma_fence *fence);
> + bool (*enable_signaling)(struct dma_fence *fence);
> + bool (*signaled)(struct dma_fence *fence);
> + signed long (*wait)(struct dma_fence *fence,
> + bool intr, signed long timeout);
> + void (*release)(struct dma_fence *fence);
> +
> + int (*fill_driver_data)(struct dma_fence *fence, void *data, int size);
> + void (*fence_value_str)(struct dma_fence *fence, char *str, int size);
> + void (*timeline_value_str)(struct dma_fence *fence,
> + char *str, int size);
> +};
> +
> +void dma_fence_init(struct dma_fence *fence,
> + const struct dma_fence_ops *ops,
> + spinlock_t *lock, unsigned context, unsigned seqno);
> +
> +void dma_fence_release(struct kref *kref);
> +void dma_fence_free(struct dma_fence *fence);
> +
> +/**
> + * dma_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 dma_fence *dma_fence_get(struct dma_fence *fence)
> +{
> + if (fence)
> + kref_get(&fence->refcount);
> + return fence;
> +}
> +
> +/**
> + * dma_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 dma_fence *dma_fence_get_rcu(struct dma_fence *fence)
> +{
> + if (kref_get_unless_zero(&fence->refcount))
> + return fence;
> + else
> + return NULL;
> +}
> +
> +/**
> + * dma_fence_put - decreases refcount of the fence
> + * @fence: [in] fence to reduce refcount of
> + */
> +static inline void dma_fence_put(struct dma_fence *fence)
> +{
> + if (fence)
> + kref_put(&fence->refcount, dma_fence_release);
> +}
> +
> +int dma_fence_signal(struct dma_fence *fence);
> +int dma_fence_signal_locked(struct dma_fence *fence);
> +signed long dma_fence_default_wait(struct dma_fence *fence,
> + bool intr, signed long timeout);
> +int dma_fence_add_callback(struct dma_fence *fence,
> + struct dma_fence_cb *cb,
> + dma_fence_func_t func);
> +bool dma_fence_remove_callback(struct dma_fence *fence,
> + struct dma_fence_cb *cb);
> +void dma_fence_enable_sw_signaling(struct dma_fence *fence);
> +
> +/**
> + * dma_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 dma_fence_add_callback, dma_fence_wait or
> + * dma_fence_enable_sw_signaling haven't been called before.
> + *
> + * This function requires fence->lock to be held.
> + */
> +static inline bool
> +dma_fence_is_signaled_locked(struct dma_fence *fence)
> +{
> + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
> + return true;
> +
> + if (fence->ops->signaled && fence->ops->signaled(fence)) {
> + dma_fence_signal_locked(fence);
> + return true;
> + }
> +
> + return false;
> +}
> +
> +/**
> + * dma_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 dma_fence_add_callback, dma_fence_wait or
> + * dma_fence_enable_sw_signaling haven't been called before.
> + *
> + * It's recommended for seqno fences to call dma_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
> +dma_fence_is_signaled(struct dma_fence *fence)
> +{
> + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
> + return true;
> +
> + if (fence->ops->signaled && fence->ops->signaled(fence)) {
> + dma_fence_signal(fence);
> + return true;
> + }
> +
> + return false;
> +}
> +
> +/**
> + * dma_fence_is_later - return if f1 is chronologically later than f2
> + * @f1: [in] the first fence from the same context
> + * @f2: [in] the second fence from the same context
> + *
> + * Returns true if f1 is chronologically later than f2. Both fences must be
> + * from the same context, since a seqno is not re-used across contexts.
> + */
> +static inline bool dma_fence_is_later(struct dma_fence *f1,
> + struct dma_fence *f2)
> +{
> + if (WARN_ON(f1->context != f2->context))
> + return false;
> +
> + return (int)(f1->seqno - f2->seqno) > 0;
> +}
> +
> +/**
> + * dma_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 dma_fence *dma_fence_later(struct dma_fence *f1,
> + struct dma_fence *f2)
> +{
> + if (WARN_ON(f1->context != f2->context))
> + return NULL;
> +
> + /*
> + * Can't check just DMA_FENCE_FLAG_SIGNALED_BIT here, it may never
> + * have been set if enable_signaling wasn't called, and enabling that
> + * here is overkill.
> + */
> + if (dma_fence_is_later(f1, f2))
> + return dma_fence_is_signaled(f1) ? NULL : f1;
> + else
> + return dma_fence_is_signaled(f2) ? NULL : f2;
> +}
> +
> +signed long dma_fence_wait_timeout(struct dma_fence *,
> + bool intr, signed long timeout);
> +signed long dma_fence_wait_any_timeout(struct dma_fence **fences,
> + uint32_t count,
> + bool intr, signed long timeout);
> +
> +/**
> + * dma_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 dma_fence_wait(struct dma_fence *fence, bool intr)
> +{
> + signed long ret;
> +
> + /* Since dma_fence_wait_timeout cannot timeout with
> + * MAX_SCHEDULE_TIMEOUT, only valid return values are
> + * -ERESTARTSYS and MAX_SCHEDULE_TIMEOUT.
> + */
> + ret = dma_fence_wait_timeout(fence, intr, MAX_SCHEDULE_TIMEOUT);
> +
> + return ret < 0 ? ret : 0;
> +}
> +
> +unsigned dma_fence_context_alloc(unsigned num);
> +
> +#define DMA_FENCE_TRACE(f, fmt, args...) \
> + do { \
> + struct dma_fence *__ff = (f); \
> + if (config_enabled(CONFIG_DMA_FENCE_TRACE)) \
> + pr_info("f %u#%u: " fmt, \
> + __ff->context, __ff->seqno, ##args); \
> + } while (0)
> +
> +#define DMA_FENCE_WARN(f, fmt, args...) \
> + do { \
> + struct dma_fence *__ff = (f); \
> + pr_warn("f %u#%u: " fmt, __ff->context, __ff->seqno, \
> + ##args); \
> + } while (0)
> +
> +#define DMA_FENCE_ERR(f, fmt, args...) \
> + do { \
> + struct dma_fence *__ff = (f); \
> + pr_err("f %u#%u: " fmt, __ff->context, __ff->seqno, \
> + ##args); \
> + } while (0)
> +
> +#endif /* __LINUX_DMA_FENCE_H */
> diff --git a/include/linux/reservation.h b/include/linux/reservation.h
> index b0f305e77b7f..2e313cca08f0 100644
> --- a/include/linux/reservation.h
> +++ b/include/linux/reservation.h
> @@ -40,7 +40,7 @@
> #define _LINUX_RESERVATION_H
>
> #include <linux/ww_mutex.h>
> -#include <linux/fence.h>
> +#include <linux/dma-fence.h>
> #include <linux/slab.h>
> #include <linux/seqlock.h>
> #include <linux/rcupdate.h>
> @@ -59,7 +59,7 @@ extern const char reservation_seqcount_string[];
> struct reservation_object_list {
> struct rcu_head rcu;
> u32 shared_count, shared_max;
> - struct fence __rcu *shared[];
> + struct dma_fence __rcu *shared[];
> };
>
> /**
> @@ -74,7 +74,7 @@ struct reservation_object {
> struct ww_mutex lock;
> seqcount_t seq;
>
> - struct fence __rcu *fence_excl;
> + struct dma_fence __rcu *fence_excl;
> struct reservation_object_list __rcu *fence;
> struct reservation_object_list *staged;
> };
> @@ -107,7 +107,7 @@ reservation_object_fini(struct reservation_object *obj)
> {
> int i;
> struct reservation_object_list *fobj;
> - struct fence *excl;
> + struct dma_fence *excl;
>
> /*
> * This object should be dead and all references must have
> @@ -115,12 +115,12 @@ reservation_object_fini(struct reservation_object *obj)
> */
> excl = rcu_dereference_protected(obj->fence_excl, 1);
> if (excl)
> - fence_put(excl);
> + dma_fence_put(excl);
>
> fobj = rcu_dereference_protected(obj->fence, 1);
> if (fobj) {
> for (i = 0; i < fobj->shared_count; ++i)
> - fence_put(rcu_dereference_protected(fobj->shared[i], 1));
> + dma_fence_put(rcu_dereference_protected(fobj->shared[i], 1));
>
> kfree(fobj);
> }
> @@ -155,7 +155,7 @@ reservation_object_get_list(struct reservation_object *obj)
> * RETURNS
> * The exclusive fence or NULL
> */
> -static inline struct fence *
> +static inline struct dma_fence *
> reservation_object_get_excl(struct reservation_object *obj)
> {
> return rcu_dereference_protected(obj->fence_excl,
> @@ -173,10 +173,10 @@ reservation_object_get_excl(struct reservation_object *obj)
> * RETURNS
> * The exclusive fence or NULL if none
> */
> -static inline struct fence *
> +static inline struct dma_fence *
> reservation_object_get_excl_rcu(struct reservation_object *obj)
> {
> - struct fence *fence;
> + struct dma_fence *fence;
> unsigned seq;
> retry:
> seq = read_seqcount_begin(&obj->seq);
> @@ -186,22 +186,22 @@ retry:
> rcu_read_unlock();
> goto retry;
> }
> - fence = fence_get(fence);
> + fence = dma_fence_get(fence);
> rcu_read_unlock();
> return fence;
> }
>
> int reservation_object_reserve_shared(struct reservation_object *obj);
> void reservation_object_add_shared_fence(struct reservation_object *obj,
> - struct fence *fence);
> + struct dma_fence *fence);
>
> void reservation_object_add_excl_fence(struct reservation_object *obj,
> - struct fence *fence);
> + struct dma_fence *fence);
>
> int reservation_object_get_fences_rcu(struct reservation_object *obj,
> - struct fence **pfence_excl,
> + struct dma_fence **pfence_excl,
> unsigned *pshared_count,
> - struct fence ***pshared);
> + struct dma_fence ***pshared);
>
> long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
> bool wait_all, bool intr,
> diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h
> index a1ba6a5ccdd6..a1f2dbeb1ba6 100644
> --- a/include/linux/seqno-fence.h
> +++ b/include/linux/seqno-fence.h
> @@ -20,7 +20,7 @@
> #ifndef __LINUX_SEQNO_FENCE_H
> #define __LINUX_SEQNO_FENCE_H
>
> -#include <linux/fence.h>
> +#include <linux/dma-fence.h>
> #include <linux/dma-buf.h>
>
> enum seqno_fence_condition {
> @@ -29,15 +29,15 @@ enum seqno_fence_condition {
> };
>
> struct seqno_fence {
> - struct fence base;
> + struct dma_fence base;
>
> - const struct fence_ops *ops;
> + const struct dma_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;
> +extern const struct dma_fence_ops seqno_fence_ops;
>
> /**
> * to_seqno_fence - cast a fence to a seqno_fence
> @@ -47,7 +47,7 @@ extern const struct fence_ops seqno_fence_ops;
> * or the seqno_fence otherwise.
> */
> static inline struct seqno_fence *
> -to_seqno_fence(struct fence *fence)
> +to_seqno_fence(struct dma_fence *fence)
> {
> if (fence->ops != &seqno_fence_ops)
> return NULL;
> @@ -96,18 +96,18 @@ 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)
> + const struct dma_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
> + * ops is used in dma_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);
> + dma_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;
> diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h
> index c6ffe8b0725c..6aae242b26de 100644
> --- a/include/linux/sync_file.h
> +++ b/include/linux/sync_file.h
> @@ -18,11 +18,11 @@
> #include <linux/ktime.h>
> #include <linux/list.h>
> #include <linux/spinlock.h>
> -#include <linux/fence.h>
> +#include <linux/dma-fence.h>
>
> struct sync_file_cb {
> - struct fence_cb cb;
> - struct fence *fence;
> + struct dma_fence_cb cb;
> + struct dma_fence *fence;
> struct sync_file *sync_file;
> };
>
> @@ -52,6 +52,6 @@ struct sync_file {
> struct sync_file_cb cbs[];
> };
>
> -struct sync_file *sync_file_create(struct fence *fence);
> +struct sync_file *sync_file_create(struct dma_fence *fence);
>
> #endif /* _LINUX_SYNC_H */
> diff --git a/include/trace/events/dma-fence.h b/include/trace/events/dma-fence.h
> new file mode 100644
> index 000000000000..9d6e9434e53c
> --- /dev/null
> +++ b/include/trace/events/dma-fence.h
> @@ -0,0 +1,128 @@
> +#undef TRACE_SYSTEM
> +#define TRACE_SYSTEM dma-fence
> +
> +#if !defined(_TRACE_FENCE_H) || defined(TRACE_HEADER_MULTI_READ)
> +#define _TRACE_DMA_FENCE_H
> +
> +#include <linux/tracepoint.h>
> +
> +struct dma_fence;
> +
> +TRACE_EVENT(dma_fence_annotate_wait_on,
> +
> + /* fence: the fence waiting on f1, f1: the fence to be waited on. */
> + TP_PROTO(struct dma_fence *fence, struct dma_fence *f1),
> +
> + TP_ARGS(fence, f1),
> +
> + 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)
> +
> + __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(dma_fence,
> +
> + TP_PROTO(struct dma_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(dma_fence, dma_fence_emit,
> +
> + TP_PROTO(struct dma_fence *fence),
> +
> + TP_ARGS(fence)
> +);
> +
> +DEFINE_EVENT(dma_fence, dma_fence_init,
> +
> + TP_PROTO(struct dma_fence *fence),
> +
> + TP_ARGS(fence)
> +);
> +
> +DEFINE_EVENT(dma_fence, dma_fence_destroy,
> +
> + TP_PROTO(struct dma_fence *fence),
> +
> + TP_ARGS(fence)
> +);
> +
> +DEFINE_EVENT(dma_fence, dma_fence_enable_signal,
> +
> + TP_PROTO(struct dma_fence *fence),
> +
> + TP_ARGS(fence)
> +);
> +
> +DEFINE_EVENT(dma_fence, dma_fence_signaled,
> +
> + TP_PROTO(struct dma_fence *fence),
> +
> + TP_ARGS(fence)
> +);
> +
> +DEFINE_EVENT(dma_fence, dma_fence_wait_start,
> +
> + TP_PROTO(struct dma_fence *fence),
> +
> + TP_ARGS(fence)
> +);
> +
> +DEFINE_EVENT(dma_fence, dma_fence_wait_end,
> +
> + TP_PROTO(struct dma_fence *fence),
> +
> + TP_ARGS(fence)
> +);
> +
> +#endif /* _TRACE_DMA_FENCE_H */
> +
> +/* This part must be outside protection */
> +#include <trace/define_trace.h>
> --
> 2.8.1
>
> _______________________________________________
> dri-devel mailing list
> dri-devel@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/dri-devel
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
dri-devel mailing list
dri-devel@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/dri-devel
