drm/nouveau: Introduce CRC support for gf119+
Subsystems (4)
Lyude Paul
maintainerv7 cover drm/nouveau: Introduce CRC support for gf119+
Nvidia released some documentation on how CRC support works on their GPUs, hooray!
So: this patch series implements said CRC support in nouveau, along with adding some special debugfs interfaces for some relevant igt-gpu-tools tests (already on the ML).
First - we add some new functionality to kthread_work in the kernel, and then use this to add a new feature to DRM that Ville Syrjälä came up
with: vblank workers. Basically, this is just a generic DRM interface that allows for scheduling high-priority workers that start on a given vblank interrupt. Note that while we're currently only using this in nouveau, Intel has plans to use this for i915 as well (hence why they came up with it!).
And finally: in order to implement the last feature, we expose some new functions in the kernel's kthread_worker infrastructure so that we can de-complicate our implementation of this.
Anyway-welcome to the future! :)
Major changes since v6:
* Move vblank_work related functions into their own files
* Write documentation
* Simplify work flushing and cancellation by getting rid of seqcounts and ->pending
Major changes since v4:
* Remove the interfaces we tried adding to kthread_worker and use a wait queue + seqcount in order to implement flushing vblank workers.
* Rebase
Major changes since v3:
* Style fixes on nouveau patches from checkpatch, no functional changes
* Don't integrate so tightly with kthread_work (and use our own lock), instead introduce some new functions for doing simple async flushing and cancelling. I think this interface looks a lot more acceptable then what I was previously trying.
* Apply some changes requested by danvet
Major changes since v2:
* Use kthread_worker instead of kthreadd for vblank workers
* Don't check debugfs return values
Lyude Paul (11):
drm/vblank: Register drmm cleanup action once per drm_vblank_crtc drm/vblank: Use spin_(un)lock_irq() in drm_crtc_vblank_off() drm/vblank: Add vblank works
drm/nouveau/kms/nv50-: Unroll error cleanup in nv50_head_create() drm/nouveau/kms/nv140-: Don't modify depth in state during atomic
commit
drm/nouveau/kms/nv50-: Fix disabling dithering drm/nouveau/kms/nv50-: s/harm/armh/g drm/nouveau/kms/nv140-: Track wndw mappings in nv50_head_atom drm/nouveau/kms/nv50-: Expose nv50_outp_atom in disp.h drm/nouveau/kms/nv50-: Move hard-coded object handles into header drm/nouveau/kms/nvd9-: Add CRC support
Documentation/gpu/drm-kms.rst | 15 + drivers/gpu/drm/Makefile | 2 +- drivers/gpu/drm/drm_vblank.c | 83 ++- drivers/gpu/drm/drm_vblank_internal.h | 19 + drivers/gpu/drm/drm_vblank_work.c | 259 +++++++ drivers/gpu/drm/drm_vblank_work_internal.h | 24 + drivers/gpu/drm/nouveau/dispnv04/crtc.c | 25 +- drivers/gpu/drm/nouveau/dispnv50/Kbuild | 4 + drivers/gpu/drm/nouveau/dispnv50/atom.h | 21 + drivers/gpu/drm/nouveau/dispnv50/core.h | 4 + drivers/gpu/drm/nouveau/dispnv50/core907d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/core917d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/corec37d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/corec57d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/crc.c | 714 ++++++++++++++++++++ drivers/gpu/drm/nouveau/dispnv50/crc.h | 125 ++++ drivers/gpu/drm/nouveau/dispnv50/crc907d.c | 139 ++++ drivers/gpu/drm/nouveau/dispnv50/crcc37d.c | 153 +++++ drivers/gpu/drm/nouveau/dispnv50/disp.c | 58 +- drivers/gpu/drm/nouveau/dispnv50/disp.h | 24 + drivers/gpu/drm/nouveau/dispnv50/handles.h | 16 + drivers/gpu/drm/nouveau/dispnv50/head.c | 134 +++- drivers/gpu/drm/nouveau/dispnv50/head.h | 12 +- drivers/gpu/drm/nouveau/dispnv50/head907d.c | 14 +- drivers/gpu/drm/nouveau/dispnv50/headc37d.c | 27 +- drivers/gpu/drm/nouveau/dispnv50/headc57d.c | 20 +- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 15 +- drivers/gpu/drm/nouveau/nouveau_display.c | 60 +- include/drm/drm_vblank.h | 20 + include/drm/drm_vblank_work.h | 71 ++ 30 files changed, 1910 insertions(+), 160 deletions(-) create mode 100644 drivers/gpu/drm/drm_vblank_internal.h create mode 100644 drivers/gpu/drm/drm_vblank_work.c create mode 100644 drivers/gpu/drm/drm_vblank_work_internal.h create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crc.c create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crc.h create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crc907d.c create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crcc37d.c create mode 100644 drivers/gpu/drm/nouveau/dispnv50/handles.h create mode 100644 include/drm/drm_vblank_work.h
Signature · 6 lines
2.26.2 _______________________________________________ Nouveau mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/nouveau
Lyude Paul
maintainerRFC v7 1/11 drm/vblank: Register drmm cleanup action once per drm_vblank_crtc
Since we'll be allocating resources for kthread_create_worker() in the next commit (which could fail and require us to clean up the mess), let's simplify the cleanup process a bit by registering a drm_vblank_init_release() action for each drm_vblank_crtc so they're still cleaned up if we fail to initialize one of them.
Changes since v3:
* Use drmm_add_action_or_reset() - Daniel Vetter
--- drivers/gpu/drm/drm_vblank.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-)
drivers/gpu/drm/drm_vblank.c +10 -13
@@ -492,16 +492,12 @@ static void vblank_disable_fn(struct timer_list *t)static void drm_vblank_init_release (struct drm_device *dev,void *ptr) { -unsigned int pipe; - -for (pipe =0 ; pipe < dev->num_crtcs; pipe++) { -struct drm_vblank_crtc *vblank = &dev->vblank[pipe]; +struct drm_vblank_crtc *vblank = ptr; -drm_WARN_ON (dev,READ_ONCE (vblank->enabled) && -drm_core_check_feature (dev,DRIVER_MODESET )); +drm_WARN_ON (dev,READ_ONCE (vblank->enabled) && +drm_core_check_feature (dev,DRIVER_MODESET )); -del_timer_sync (&vblank->disable_timer); - } +del_timer_sync (&vblank->disable_timer); }/**
@@ -511,7 +507,7 @@ static void drm_vblank_init_release(struct drm_device *dev, void *ptr)* * This function initializes vblank support for @num_crtcs display pipelines. * Cleanup is handled automatically through a cleanup function added with -* drmm_add_action(). +* drmm_add_action_or_reset(). * * Returns: * Zero on success or a negative error code on failure.
@@ -530,10 +526,6 @@ int drm_vblank_init(struct drm_device *dev, unsigned int num_crtcs) dev->num_crtcs = num_crtcs; - ret =drmm_add_action (dev, drm_vblank_init_release,NULL ); -if (ret) -return ret; -for (i =0 ; i < num_crtcs; i++) {struct drm_vblank_crtc *vblank = &dev->vblank[i];
@@ -542,6 +534,11 @@ int drm_vblank_init(struct drm_device *dev, unsigned int num_crtcs)init_waitqueue_head (&vblank->queue);timer_setup (&vblank->disable_timer, vblank_disable_fn,0 );seqlock_init (&vblank->seqlock); + + ret =drmm_add_action_or_reset (dev, drm_vblank_init_release, + vblank); +if (ret) +return ret; }return 0 ;
Signature · 6 lines
2.26.2 _______________________________________________ Nouveau mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/nouveau
Lyude Paul
maintainerRFC v7 2/11 drm/vblank: Use spin_(un)lock_irq() in drm_crtc_vblank_off()
In reply to Lyude PaulThis got me confused for a bit while looking over this code: I had been planning on adding some blocking function calls into this function, but seeing the irqsave/irqrestore variants of spin_(un)lock() didn't make it very clear whether or not that would actually be safe.
So I went ahead and reviewed every single driver in the kernel that uses this function, and they all fall into three categories:
* Driver probe code
* ->atomic_disable() callbacks
* Legacy modesetting callbacks
All of these will be guaranteed to have IRQs enabled, which means it's perfectly safe to block here. Just to make things a little less confusing to others in the future, let's switch over to spin_lock_irq()/spin_unlock_irq() to make that fact a little more obvious.
--- drivers/gpu/drm/drm_vblank.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/gpu/drm/drm_vblank.c +2 -3
@@ -1283,13 +1283,12 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc)struct drm_pending_vblank_event *e, *t;ktime_t now; -unsigned long irqflags;u64 seq;if (drm_WARN_ON (dev, pipe >= dev->num_crtcs))return ; -spin_lock_irqsave (&dev->event_lock, irqflags); +spin_lock_irq (&dev->event_lock);spin_lock (&dev->vbl_lock); drm_dbg_vbl(dev, "crtc %d, vblank enabled %d, inmodeset %d\n",
@@ -1325,7 +1324,7 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc)drm_vblank_put (dev, pipe);send_vblank_event (dev, e, seq, now); } -spin_unlock_irqrestore (&dev->event_lock, irqflags); +spin_unlock_irq (&dev->event_lock);/* Will be reset by the modeset helpers when re-enabling the crtc by * calling drm_calc_timestamping_constants(). */
Signature · 1 line
2.26.2
Re: [RFC v7 02/11] drm/vblank: Use spin_(un)lock_irq() in drm_crtc_vblank_off()
Quoted 18 lines · Lyude Paul
This got me confused for a bit while looking over this code: I had been planning on adding some blocking function calls into this function, but seeing the irqsave/irqrestore variants of spin_(un)lock() didn't make it very clear whether or not that would actually be safe.
So I went ahead and reviewed every single driver in the kernel that uses this function, and they all fall into three categories:
* Driver probe code
* ->atomic_disable() callbacks
* Legacy modesetting callbacksAll of these will be guaranteed to have IRQs enabled, which means it's perfectly safe to block here. Just to make things a little less confusing to others in the future, let's switch over to spin_lock_irq()/spin_unlock_irq() to make that fact a little more obvious.
Quoted 3 lines
Signed-off-by Lyude Paul <[email protected]>Cc Daniel Vetter <[email protected]>Cc Ville Syrjälä <[email protected]>
I think the patch is correct, but now we're having a bit a inconsistency, since all other functions where the same applies still use _irqsave. I looked through the file and I think drm_vblank_get, drm_crtc_vblank_reset, drm_crtc_vblank_on and drm_legacy_vblank_post_modeset, drm_queue_vblank_event and drm_crtc_queue_sequence_ioctl are all candiates for the same cleanup.
Maybe follow up patches for less confusion?
On this:
Quoted 35 lines
--- drivers/gpu/drm/drm_vblank.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)drivers/gpu/drm/drm_vblank.c +2
-3@@ -1283,13 +1283,12 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc)struct drm_pending_vblank_event *e, *t;ktime_t now; -unsigned long irqflags;u64 seq;if (drm_WARN_ON (dev, pipe >= dev->num_crtcs))return ; -spin_lock_irqsave (&dev->event_lock, irqflags); +spin_lock_irq (&dev->event_lock);spin_lock (&dev->vbl_lock); drm_dbg_vbl(dev, "crtc %d, vblank enabled %d, inmodeset %d\n",@@ -1325,7 +1324,7 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc)drm_vblank_put (dev, pipe);send_vblank_event (dev, e, seq, now); } -spin_unlock_irqrestore (&dev->event_lock, irqflags); +spin_unlock_irq (&dev->event_lock);/* Will be reset by the modeset helpers when re-enabling the crtc by * calling drm_calc_timestamping_constants(). */ Signature · 1 line
2.26.2
Signature · 3 lines
Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch
Lyude Paul
maintainerRFC v7 3/11 drm/vblank: Add vblank works
In reply to Lyude PaulAdd some kind of vblank workers. The interface is similar to regular delayed works, and is mostly based off kthread_work. It allows for scheduling delayed works that execute once a particular vblank sequence has passed. It also allows for accurate flushing of scheduled vblank works - in that flushing waits for both the vblank sequence and job execution to complete, or for the work to get cancelled - whichever comes first.
Whatever hardware programming we do in the work must be fast (must at least complete during the vblank or scanout period, sometimes during the first few scanlines of the vblank). As such we use a high-priority per-CRTC thread to accomplish this.
Changes since v6:
* Get rid of ->pending and seqcounts, and implement flushing through simpler means - danvet
* Get rid of work_lock, just use drm_device->event_lock
* Move drm_vblank_work item cleanup into drm_crtc_vblank_off() so that we ensure that all vblank work has finished before disabling vblanks
* Add checks into drm_crtc_vblank_reset() so we yell if it gets called while there's vblank workers active
* Grab event_lock in both drm_crtc_vblank_on()/drm_crtc_vblank_off(), the main reason for this is so that other threads calling drm_vblank_work_schedule() are blocked from attempting to schedule while we're in the middle of enabling/disabling vblanks.
* Move drm_handle_vblank_works() call below drm_handle_vblank_events()
* Simplify drm_vblank_work_cancel_sync()
* Fix drm_vblank_work_cancel_sync() documentation
* Move wake_up_all() calls out of spinlock where we can. The only one I left was the call to wake_up_all() in drm_vblank_handle_works() as this seemed like it made more sense just living in that function (which is all technically under lock)
* Move drm_vblank_work related functions into their own source files
* Add drm_vblank_internal.h so we can export some functions we don't want drivers using, but that we do need to use in drm_vblank_work.c
* Add a bunch of documentation
Changes since v4:
* Get rid of kthread interfaces we tried adding and move all of the locking into drm_vblank.c. For implementing drm_vblank_work_flush(), we now use a wait_queue and sequence counters in order to differentiate between multiple work item executions.
* Get rid of drm_vblank_work_cancel() - this would have been pretty difficult to actually reimplement and it occurred to me that neither nouveau or i915 are even planning to use this function. Since there's also no async cancel function for most of the work interfaces in the kernel, it seems a bit unnecessary anyway.
* Get rid of to_drm_vblank_work() since we now are also able to just pass the struct drm_vblank_work to work item callbacks anyway
Changes since v3:
* Use our own spinlocks, don't integrate so tightly with kthread_works Changes since v2:
* Use kthread_workers instead of reinventing the wheel.
--- Documentation/gpu/drm-kms.rst | 15 ++ drivers/gpu/drm/Makefile | 2 +- drivers/gpu/drm/drm_vblank.c | 55 +++-- drivers/gpu/drm/drm_vblank_internal.h | 19 ++ drivers/gpu/drm/drm_vblank_work.c | 259 +++++++++++++++++++++ drivers/gpu/drm/drm_vblank_work_internal.h | 24 ++ include/drm/drm_vblank.h | 20 ++ include/drm/drm_vblank_work.h | 71 ++++++ 8 files changed, 447 insertions(+), 18 deletions(-) create mode 100644 drivers/gpu/drm/drm_vblank_internal.h create mode 100644 drivers/gpu/drm/drm_vblank_work.c create mode 100644 drivers/gpu/drm/drm_vblank_work_internal.h create mode 100644 include/drm/drm_vblank_work.h
Documentation/gpu/drm-kms.rst +15 -0
@@ -543,3 +543,18 @@ Vertical Blanking and Interrupt Handling Functions Reference .. kernel-doc:: drivers/gpu/drm/drm_vblank.c :export: + +Vertical Blank Work +=================== + +.. kernel-doc:: drivers/gpu/drm/drm_vblank_work.c + :doc: vblank works + +Vertical Blank Work Functions Reference +--------------------------------------- + +.. kernel-doc:: include/drm/drm_vblank_work.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/drm_vblank_work.c + :export:
drivers/gpu/drm/Makefile +1 -1
@@ -18,7 +18,7 @@ drm-y := drm_auth.o drm_cache.o \ drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \ drm_syncobj.o drm_lease.o drm_writeback.o drm_client.o \ drm_client_modeset.o drm_atomic_uapi.o drm_hdcp.o \ - drm_managed.o + drm_managed.o drm_vblank_work.o drm-$(CONFIG_DRM_LEGACY) += drm_legacy_misc.o drm_bufs.o drm_context.o drm_dma.o drm_scatter.o drm_lock.o drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
drivers/gpu/drm/drm_vblank.c +38 -17
189 lines not on this page · raw message
drivers/gpu/drm/drm_vblank_internal.h new file +19 -0
@@ -0,0 +1,19 @@ +// SPDX-License-Identifier: MIT + +#ifndef DRM_VBLANK_INTERNAL_H +#define DRM_VBLANK_INTERNAL_H + +#include <linux/types.h> + +#include <drm/drm_device.h> + +static inline bool drm_vblank_passed (u64 seq,u64 ref) +{ +return (seq - ref) <= (1 <<23 ); +} + +int drm_vblank_get (struct drm_device *dev,unsigned int pipe); +void drm_vblank_put (struct drm_device *dev,unsigned int pipe); +u64 drm_vblank_count (struct drm_device *dev,unsigned int pipe); + +#endif /* !DRM_VBLANK_INTERNAL_H */
drivers/gpu/drm/drm_vblank_work.c new file +259 -0
259 lines not on this page · raw message
drivers/gpu/drm/drm_vblank_work_internal.h new file +24 -0
@@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT + +#ifndef _DRM_VBLANK_WORK_INTERNAL_H_ +#define _DRM_VBLANK_WORK_INTERNAL_H_ + +#include <drm/drm_vblank.h> + +int drm_vblank_worker_init (struct drm_vblank_crtc *vblank); +void drm_vblank_cancel_pending_works (struct drm_vblank_crtc *vblank); +void drm_handle_vblank_works (struct drm_vblank_crtc *vblank); + +static inline void drm_vblank_flush_worker (struct drm_vblank_crtc *vblank) +{ +if (vblank->worker) +kthread_flush_worker (vblank->worker); +} + +static inline void drm_vblank_destroy_worker (struct drm_vblank_crtc *vblank) +{ +if (vblank->worker) +kthread_destroy_worker (vblank->worker); +} + +#endif /* !_DRM_VBLANK_WORK_INTERNAL_H_ */
include/drm/drm_vblank.h +20 -0
@@ -27,12 +27,14 @@#include <linux/seqlock.h> #include <linux/idr.h> #include <linux/poll.h> +#include <linux/kthread.h> #include <drm/drm_file.h> #include <drm/drm_modes.h> struct drm_device ;struct drm_crtc ; +struct drm_vblank_work ;/** * struct drm_pending_vblank_event - pending vblank event tracking
@@ -203,6 +205,24 @@ struct drm_vblank_crtc {* disabling functions multiple times. */ bool enabled; + +/** +* @worker: The &kthread_worker used for executing vblank works. +*/ +struct kthread_worker *worker; + +/** +* @pending_work: A list of scheduled &drm_vblank_work items that are +* waiting for a future vblank. +*/ +struct list_head pending_work; + +/** +* @work_wait_queue: The wait queue used for signaling that a +* &drm_vblank_work item has either finished executing, or was +* cancelled. +*/ +wait_queue_head_t work_wait_queue; };int drm_vblank_init (struct drm_device *dev,unsigned int num_crtcs);
include/drm/drm_vblank_work.h new file +71 -0
71 lines not on this page · raw message
Signature · 1 line
2.26.2
Re: [RFC v7 03/11] drm/vblank: Add vblank works
Quoted 53 lines · Lyude Paul
Add some kind of vblank workers. The interface is similar to regular delayed works, and is mostly based off
kthread_work. It allows for scheduling delayed works that execute once a particular vblank sequence has passed. It also allows for accurate flushing of scheduled vblank works - in that flushing waits for both the vblank sequence and job execution to complete, or for the work to get cancelled - whichever comes first.Whatever hardware programming we do in the work must be fast (must at least complete during the vblank or scanout period, sometimes during the first few scanlines of the vblank). As such we use a high-priority per-CRTC thread to accomplish this.
Changes since v6:
* Get rid of ->pending and seqcounts, and implement flushing through simpler means - danvet
* Get rid ofwork_lock, just usedrm_device->event_lock
* Movedrm_vblank_workitem cleanup intodrm_crtc_vblank_off()so that we ensure that all vblank work has finished before disabling vblanks
* Add checks intodrm_crtc_vblank_reset()so we yell if it gets called while there's vblank workers active
* Grabevent_lockin both drm_crtc_vblank_on()/drm_crtc_vblank_off(), the main reason for this is so that other threads callingdrm_vblank_work_schedule()are blocked from attempting to schedule while we're in the middle of enabling/disabling vblanks.
* Movedrm_handle_vblank_works()call belowdrm_handle_vblank_events()
* Simplifydrm_vblank_work_cancel_sync()
* Fixdrm_vblank_work_cancel_sync()documentation
* Movewake_up_all()calls out of spinlock where we can. The only one I left was the call towake_up_all()indrm_vblank_handle_works()as this seemed like it made more sense just living in that function (which is all technically under lock)
* Movedrm_vblank_workrelated functions into their own source files
* Adddrm_vblank_internal.hso we can export some functions we don't want drivers using, but that we do need to use indrm_vblank_work.c
* Add a bunch of documentation
Changes since v4:
* Get rid of kthread interfaces we tried adding and move all of the locking intodrm_vblank.c. For implementingdrm_vblank_work_flush(), we now use await_queueand sequence counters in order to differentiate between multiple work item executions.
* Get rid ofdrm_vblank_work_cancel()- this would have been pretty difficult to actually reimplement and it occurred to me that neither nouveau or i915 are even planning to use this function. Since there's also no async cancel function for most of the work interfaces in the kernel, it seems a bit unnecessary anyway.
* Get rid ofto_drm_vblank_work()since we now are also able to just pass the structdrm_vblank_workto work item callbacks anyway
Changes since v3:
* Use our own spinlocks, don't integrate so tightly withkthread_worksChanges since v2:
* Usekthread_workersinstead of reinventing the wheel.
Quoted 6 lines
Cc Daniel Vetter <[email protected]>Cc Tejun Heo <[email protected]>Co-developed-by Ville Syrjälä <[email protected]>Signed-off-by Lyude Paul <[email protected]>
I found a bunch of tiny details below, but overall looks great and thanks for polishing the kerneldoc.
With the details addressed one way or another:
But feel free to resend and poke me again if you want me to recheck the details that needed changing.
Cheers, Daniel
Quoted 64 lines
--- Documentation/gpu/drm-kms.rst | 15 ++ drivers/gpu/drm/Makefile | 2 +- drivers/gpu/drm/drm_vblank.c | 55 +++-- drivers/gpu/drm/drm_vblank_internal.h | 19 ++ drivers/gpu/drm/drm_vblank_work.c | 259 +++++++++++++++++++++ drivers/gpu/drm/drm_vblank_work_internal.h | 24 ++ include/drm/drm_vblank.h | 20 ++ include/drm/drm_vblank_work.h | 71 ++++++ 8 files changed, 447 insertions(+), 18 deletions(-) create mode 100644 drivers/gpu/drm/drm_vblank_internal.h create mode 100644 drivers/gpu/drm/drm_vblank_work.c create mode 100644 drivers/gpu/drm/drm_vblank_work_internal.h create mode 100644 include/drm/drm_vblank_work.hDocumentation/gpu/drm-kms.rst +15
-0@@ -543,3 +543,18 @@ Vertical Blanking and Interrupt Handling Functions Reference .. kernel-doc:: drivers/gpu/drm/drm_vblank.c :export: + +Vertical Blank Work +=================== + +.. kernel-doc:: drivers/gpu/drm/drm_vblank_work.c + :doc: vblank works + +Vertical Blank Work Functions Reference +--------------------------------------- + +.. kernel-doc:: include/drm/drm_vblank_work.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/drm_vblank_work.c + :export:drivers/gpu/drm/Makefile +1
-1@@ -18,7 +18,7 @@ drm-y := drm_auth.o drm_cache.o \ drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \ drm_syncobj.o drm_lease.o drm_writeback.o drm_client.o \ drm_client_modeset.o drm_atomic_uapi.o drm_hdcp.o \ - drm_managed.o + drm_managed.o drm_vblank_work.o drm-$(CONFIG_DRM_LEGACY) += drm_legacy_misc.o drm_bufs.o drm_context.o drm_dma.o drm_scatter.o drm_lock.o drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.odrivers/gpu/drm/drm_vblank.c +1
-0@@ -25,6 +25,7 @@*/ #include <linux/export.h> +#include <linux/kthread.h> #include <linux/moduleparam.h> #include <drm/drm_crtc.h>
drivers/gpu/drm/drm_vblank.c line 42
Quoted 5 lines
drivers/gpu/drm/drm_vblank.c +2
-0@@ -37,6 +38,8 @@#include "drm_internal.h" #include "drm_trace.h" +#include "drm_vblank_internal.h" +#include "drm_vblank_work_internal.h"
Feels mild overkill to have these files with 1-2 functions each, I'd stuff them all into drm_internal.h. We do have other vblank stuff in there already.
Quoted 95 lines
drivers/gpu/drm/drm_vblank.c +20
-4/** * DOC: vblank handling @@ -363,7 +366,7 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,store_vblank (dev, pipe, diff, t_vblank, cur_vblank); } -static u64 drm_vblank_count (struct drm_device *dev,unsigned int pipe) +u64 drm_vblank_count (struct drm_device *dev,unsigned int pipe) {struct drm_vblank_crtc *vblank = &dev->vblank[pipe];u64 count;@@ -497,6 +500,7 @@ static void drm_vblank_init_release(struct drm_device *dev, void *ptr)drm_WARN_ON (dev,READ_ONCE (vblank->enabled) &&drm_core_check_feature (dev,DRIVER_MODESET )); +drm_vblank_destroy_worker (vblank);del_timer_sync (&vblank->disable_timer); }@@ -539,6 +543,10 @@ int drm_vblank_init(struct drm_device *dev, unsigned int num_crtcs) vblank);if (ret)return ret; + + ret =drm_vblank_worker_init (vblank); +if (ret) +return ret; }return 0 ;@@ -1135,7 +1143,7 @@ static int drm_vblank_enable(struct drm_device *dev, unsigned int pipe)return ret; } -static int drm_vblank_get (struct drm_device *dev,unsigned int pipe) +int drm_vblank_get (struct drm_device *dev,unsigned int pipe) {struct drm_vblank_crtc *vblank = &dev->vblank[pipe];unsigned long irqflags;@@ -1178,7 +1186,7 @@ int drm_crtc_vblank_get(struct drm_crtc *crtc) }EXPORT_SYMBOL (drm_crtc_vblank_get); -static void drm_vblank_put (struct drm_device *dev,unsigned int pipe) +void drm_vblank_put (struct drm_device *dev,unsigned int pipe) {struct drm_vblank_crtc *vblank = &dev->vblank[pipe];@@ -1281,13 +1289,16 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc)unsigned int pipe =drm_crtc_index (crtc);struct drm_vblank_crtc *vblank = &dev->vblank[pipe];struct drm_pending_vblank_event *e, *t; -ktime_t now;u64 seq;if (drm_WARN_ON (dev, pipe >= dev->num_crtcs))return ; +/* +* Grab event_lock early to prevent vblank work from being scheduled +* while we're in the middle of shutting down vblank interrupts +*/ spin_lock_irq (&dev->event_lock);spin_lock (&dev->vbl_lock);@@ -1324,11 +1335,18 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc)drm_vblank_put (dev, pipe);send_vblank_event (dev, e, seq, now); } + +/* Cancel any leftover pending vblank work */ +drm_vblank_cancel_pending_works (vblank); +spin_unlock_irq (&dev->event_lock);/* Will be reset by the modeset helpers when re-enabling the crtc by * calling drm_calc_timestamping_constants(). */ vblank->hwmode.crtc_clock =0 ; + +/* Wait for any vblank work that's still executing to finish */ +drm_vblank_flush_worker (vblank); }EXPORT_SYMBOL (drm_crtc_vblank_off);@@ -1363,6 +1381,7 @@ void drm_crtc_vblank_reset(struct drm_crtc *crtc)spin_unlock_irqrestore (&dev->vbl_lock, irqflags);drm_WARN_ON (dev, !list_empty (&dev->vblank_event_list)); +drm_WARN_ON (dev, !list_empty (&vblank->pending_work)); }EXPORT_SYMBOL (drm_crtc_vblank_reset);
drivers/gpu/drm/drm_vblank.c void drm_crtc_vblank_on(struct drm_crtc *crtc) · line 1440
Quoted 6 lines
drivers/gpu/drm/drm_vblank.c +2
-1@@ -1417,7 +1436,10 @@ void drm_crtc_vblank_on(struct drm_crtc *crtc)if (drm_WARN_ON (dev, pipe >= dev->num_crtcs))return ; -spin_lock_irqsave (&dev->vbl_lock, irqflags); +/* So vblank works can't be scheduled until we've finished */ +spin_lock_irqsave (&dev->event_lock, irqflags);
This smells fishy, why do we need this? drm_enable_vblank takes the ->vblank_time_lock spinlock, which is the first thing drm_handle_vblank takes, so there's absolute no way for a vblank event or worker to get ahead of this here.
Except if I'm missing something this isn't needed.
Quoted 217 lines
drivers/gpu/drm/drm_vblank.c +13
-12+ +spin_lock (&dev->vbl_lock);drm_dbg_vbl (dev,"crtc %d, vblank enabled %d, inmodeset %d\n" , pipe, vblank->enabled, vblank->inmodeset);@@ -1435,7 +1457,9 @@ void drm_crtc_vblank_on(struct drm_crtc *crtc)*/ if (atomic_read (&vblank->refcount) !=0 || drm_vblank_offdelay ==0 )drm_WARN_ON (dev,drm_vblank_enable (dev, pipe)); -spin_unlock_irqrestore (&dev->vbl_lock, irqflags); + +spin_unlock (&dev->vbl_lock); +spin_unlock_irqrestore (&dev->event_lock, irqflags); }EXPORT_SYMBOL (drm_crtc_vblank_on);@@ -1589,11 +1613,6 @@ int drm_legacy_modeset_ctl_ioctl(struct drm_device *dev, void *data,return 0 ; } -static inline bool vblank_passed (u64 seq,u64 ref) -{ -return (seq - ref) <= (1 <<23 ); -} - static int drm_queue_vblank_event(struct drm_device *dev, unsigned int pipe, u64 req_seq, union drm_wait_vblank *vblwait,@@ -1650,7 +1669,7 @@ static int drm_queue_vblank_event(struct drm_device *dev, unsigned int pipe,trace_drm_vblank_event_queued (file_priv, pipe, req_seq); e->sequence = req_seq; -if (vblank_passed (seq, req_seq)) { +if (drm_vblank_passed (seq, req_seq)) {drm_vblank_put (dev, pipe);send_vblank_event (dev, e, seq, now); vblwait->reply.sequence = seq;@@ -1805,7 +1824,7 @@ int drm_wait_vblank_ioctl(struct drm_device *dev, void *data, }if ((flags & _DRM_VBLANK_NEXTONMISS) && -vblank_passed (seq, req_seq)) { +drm_vblank_passed (seq, req_seq)) { req_seq = seq +1 ; vblwait->request.type &= ~_DRM_VBLANK_NEXTONMISS; vblwait->request.sequence = req_seq;@@ -1824,7 +1843,7 @@ int drm_wait_vblank_ioctl(struct drm_device *dev, void *data,drm_dbg_core (dev,"waiting on vblank count %llu, crtc %u\n" , req_seq, pipe); wait =wait_event_interruptible_timeout (vblank->queue, -vblank_passed (drm_vblank_count (dev, pipe), req_seq) || +drm_vblank_passed (drm_vblank_count (dev, pipe), req_seq) || !READ_ONCE (vblank->enabled),msecs_to_jiffies (3000 ));@@ -1873,7 +1892,7 @@ static void drm_handle_vblank_events(struct drm_device *dev, unsigned int pipe)list_for_each_entry_safe (e, t, &dev->vblank_event_list, base.link) {if (e->pipe != pipe)continue ; -if (!vblank_passed (seq, e->sequence)) +if (!drm_vblank_passed (seq, e->sequence))continue ; drm_dbg_core(dev, "vblank event on %llu, current %llu\n",@@ -1943,6 +1962,7 @@ bool drm_handle_vblank(struct drm_device *dev, unsigned int pipe) !atomic_read(&vblank->refcount));drm_handle_vblank_events (dev, pipe); +drm_handle_vblank_works (vblank);spin_unlock_irqrestore (&dev->event_lock, irqflags);@@ -2096,7 +2116,7 @@ int drm_crtc_queue_sequence_ioctl(struct drm_device *dev, void *data,if (flags &DRM_CRTC_SEQUENCE_RELATIVE ) req_seq += seq; -if ((flags &DRM_CRTC_SEQUENCE_NEXT_ON_MISS ) &&vblank_passed (seq, req_seq)) +if ((flags &DRM_CRTC_SEQUENCE_NEXT_ON_MISS ) &&drm_vblank_passed (seq, req_seq)) req_seq = seq +1 ; e->pipe = pipe;@@ -2125,7 +2145,7 @@ int drm_crtc_queue_sequence_ioctl(struct drm_device *dev, void *data, e->sequence = req_seq; -if (vblank_passed (seq, req_seq)) { +if (drm_vblank_passed (seq, req_seq)) {drm_crtc_vblank_put (crtc);send_vblank_event (dev, e, seq, now); queue_seq->sequence = seq;@@ -2145,3 +2165,4 @@ int drm_crtc_queue_sequence_ioctl(struct drm_device *dev, void *data,kfree (e);return ret; } +drivers/gpu/drm/drm_vblank_internal.h new file +19
-0@@ -0,0 +1,19 @@ +// SPDX-License-Identifier: MIT + +#ifndef DRM_VBLANK_INTERNAL_H +#define DRM_VBLANK_INTERNAL_H + +#include <linux/types.h> + +#include <drm/drm_device.h> + +static inline bool drm_vblank_passed (u64 seq,u64 ref) +{ +return (seq - ref) <= (1 <<23 ); +} + +int drm_vblank_get (struct drm_device *dev,unsigned int pipe); +void drm_vblank_put (struct drm_device *dev,unsigned int pipe); +u64 drm_vblank_count (struct drm_device *dev,unsigned int pipe); + +#endif /* !DRM_VBLANK_INTERNAL_H */ drivers/gpu/drm/drm_vblank_work.c new file +91
-0@@ -0,0 +1,259 @@ +// SPDX-License-Identifier: MIT + +#include <uapi/linux/sched/types.h> + +#include <drm/drm_print.h> +#include <drm/drm_vblank.h> +#include <drm/drm_vblank_work.h> +#include <drm/drm_crtc.h> + +#include "drm_vblank_internal.h" +#include "drm_vblank_work_internal.h" + +/** +* DOC: vblank works +* +* Many DRM drivers need to program hardware in a time-sensitive manner, many +* times with a deadline of starting and finishing within a certain region of +* the scanout. Most of the time the safest way to accomplish this is to +* simply do said time-sensitive programming in the driver's IRQ handler, +* which allows drivers to avoid being preempted during these critical +* regions. Or even better, the hardware may even handle applying such +* time-critical programming independently of the CPU. +* +* While there's a decent amount of hardware that's designed so that the CPU +* doesn't need to be concerned with extremely time-sensitive programming, +* there's a few situations where it can't be helped. Some unforgiving +* hardware may require that certain time-sensitive programming be handled +* completely by the CPU, and said programming may even take too long to +* handle in an IRQ handler. Another such situation would be where the driver +* needs to perform a task that needs to complete within a specific scanout +* period, but might possibly block and thus cannot be handled in an IRQ +* context. Both of these situations can't be solved perfectly in Linux since +* we're not a realtime kernel, and thus the scheduler may cause us to miss +* our deadline if it decides to preempt us. But for some drivers, it's good +* enough if we can lower our chance of being preempted to an absolute +* minimum. +* +* This is where &drm_vblank_work comes in. &drm_vblank_work provides a simple +* generic delayed work implementation which delays work execution until a +* particular vblank has passed, and then executes the work at realtime +* priority. This provides the best possible chance at performing +* time-sensitive hardware programming on time, even when the system is under +* heavy load. &drm_vblank_work also supports rescheduling, so that self +* re-arming work items can be easily implemented. +*/ + +void drm_handle_vblank_works (struct drm_vblank_crtc *vblank) +{ +struct drm_vblank_work *work, *next; +u64 count =atomic64_read (&vblank->count); +bool wake = false; + +assert_spin_locked (&vblank->dev->event_lock); + +list_for_each_entry_safe (work, next, &vblank->pending_work, node) { +if (!drm_vblank_passed (count, work->count)) +continue ; + +list_del_init (&work->node); +drm_vblank_put (vblank->dev, vblank->pipe); +kthread_queue_work (vblank->worker, &work->base); + wake = true; + } +if (wake) +wake_up_all (&vblank->work_wait_queue); +} + +/* Handle cancelling any pending vblank work items and drop respective vblank +* references in response to vblank interrupts being disabled. +*/ +void drm_vblank_cancel_pending_works (struct drm_vblank_crtc *vblank) +{ +struct drm_vblank_work *work, *next; + +assert_spin_locked (&vblank->dev->event_lock); + +list_for_each_entry_safe (work, next, &vblank->pending_work, node) { +list_del_init (&work->node); +drm_vblank_put (vblank->dev, vblank->pipe); + } + +wake_up_all (&vblank->work_wait_queue); +} + +/** +* drm_vblank_work_schedule - schedule a vblank work +* @work: vblank work to schedule +* @count: target vblank count +* @nextonmiss: defer until the next vblank if target vblank was missed +* +* Schedule @work for execution once the crtc vblank count reaches @count.
drivers/gpu/drm/drm_vblank_work.c line 101
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work.c new file +10
-0+* +* If the crtc vblank count has already reached @count and @nextonmiss is +* %false the work starts to execute immediately. +* +* If the crtc vblank count has already reached @count and @nextonmiss is +* %true the work is deferred until the next vblank (as if @count has been +* specified as crtc vblank count + 1). +* +* If @work is already scheduled, this function will reschedule said work +* using the new @count.
Maybe clarify here that "This can be use for self-rearming work items." or something like that.
Quoted 6 lines
drivers/gpu/drm/drm_vblank_work.c new file +6
-0+* +* Returns: +* 0 on success, error code on failure. +*/ +int drm_vblank_work_schedule (struct drm_vblank_work *work, +u64 count,bool nextonmiss)
drivers/gpu/drm/drm_vblank_work.c line 117
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work.c new file +10
-0+{ +struct drm_vblank_crtc *vblank = work->vblank; +struct drm_device *dev = vblank->dev; +u64 cur_vbl; +unsigned long irqflags; +bool passed, rescheduling = false, wake = false; +int ret =0 ; + +spin_lock_irqsave (&dev->event_lock, irqflags); +if (!vblank->worker || vblank->inmodeset || work->cancelling)
Oh nice catch with ->inmodeset, I totally missed to check re-arming vs drm_crtc_vblank_off races. Only problem I'm seeing is that we're holding the wrong spinlock, this needs to be check under ->vbl_lock. But ->cancelling needs the event_lock, so I think you need to split this check into two, and grab the ->vbl_lock around the ->inmodeset check.
The ->worker check otoh looks fishy, that should never happen. If you feel like some defensive programming then I think that should be an
if (WARN_ON(!vblank->worker)) return;
drivers/gpu/drm/drm_vblank_work.c line 121
Quoted 4 lines
drivers/gpu/drm/drm_vblank_work.c new file +4
-0+ goto out; + +if (list_empty (&work->node)) { + ret =drm_vblank_get (dev, vblank->pipe);
Ok that kills the idea of converting the _irqsave to _irq in drm_vblank_get. I do wonder whether it wouldn't be nicer to have the vblank_get outside of the spinlock, and unconditional - would allow you to drop the ->inmodeset check. But the end result in code flow cleanliness is not any better, so not a good idea I think.
Quoted 6 lines
drivers/gpu/drm/drm_vblank_work.c new file +6
-0+if (ret <0 ) + goto out; + }else if (work->count == count) { +/* Already scheduled w/ same vbl count */ + goto out; + }else {
drivers/gpu/drm/drm_vblank_work.c line 137
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work.c new file +10
-0+ rescheduling = true; + } + + work->count = count; + cur_vbl =drm_vblank_count (dev, vblank->pipe); + passed =drm_vblank_passed (cur_vbl, count); +if (passed) +DRM_DEV_ERROR (dev->dev, +"crtc %d vblank %llu already passed (current %llu)\n" , + vblank->pipe, count, cur_vbl);
This is a bit loud, I think that should be debug out most. You can't really prevent races. I do wonder though whether we should do something like 1 indicates that the work item has been scheduled, and 0 that it hasn't been scheduled (aside from failure, which is negative).
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work.c new file +10
-0+ +if (!nextonmiss && passed) { +drm_vblank_put (dev, vblank->pipe); +kthread_queue_work (vblank->worker, &work->base); + +if (rescheduling) { +list_del_init (&work->node); + wake = true; + } + }else if (!rescheduling) {
drivers/gpu/drm/drm_vblank_work.c line 157
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work.c new file +10
-0+list_add_tail (&work->node, &vblank->pending_work); + } + +out: +spin_unlock_irqrestore (&dev->event_lock, irqflags); +if (wake) +wake_up_all (&vblank->work_wait_queue); +return ret; +} +EXPORT_SYMBOL (drm_vblank_work_schedule);
I think the above control flow is all correct, but this is the kind of stuff that's prime material for some selftests. But we don't have enough ready-made mocking I think, so not going to ask for that. Just an idea.
Quoted 30 lines
drivers/gpu/drm/drm_vblank_work.c new file +30
-0+ +/** +* drm_vblank_work_cancel_sync - cancel a vblank work and wait for it to +* finish executing +* @work: vblank work to cancel +* +* Cancel an already scheduled vblank work and wait for its +* execution to finish. +* +* On return, @work is guaranteed to no longer be scheduled or running, even +* if it's self-arming. +* +* Returns: +* %True if the work was cancelled before it started to execute, %false +* otherwise. +*/ +bool drm_vblank_work_cancel_sync (struct drm_vblank_work *work) +{ +struct drm_vblank_crtc *vblank = work->vblank; +struct drm_device *dev = vblank->dev; +bool ret = false; + +spin_lock_irq (&dev->event_lock); +if (!list_empty (&work->node)) { +list_del_init (&work->node); +drm_vblank_put (vblank->dev, vblank->pipe); + ret = true; + } + + work->cancelling++;
drivers/gpu/drm/drm_vblank_work.c line 197
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work.c new file +10
-0+spin_unlock_irq (&dev->event_lock); + +wake_up_all (&vblank->work_wait_queue); + +if (kthread_cancel_work_sync (&work->base)) + ret = true; + +spin_lock_irq (&dev->event_lock); + work->cancelling--; +spin_unlock_irq (&dev->event_lock);
lgtm, everything looks ordered correctly to avoid a self-arming work escaping.
Quoted 13 lines
drivers/gpu/drm/drm_vblank_work.c new file +13
-0+ +return ret; +} +EXPORT_SYMBOL (drm_vblank_work_cancel_sync); + +/** +* drm_vblank_work_flush - wait for a scheduled vblank work to finish +* executing +* @work: vblank work to flush +* +* Wait until @work has finished executing once. +*/ +void drm_vblank_work_flush (struct drm_vblank_work *work)
drivers/gpu/drm/drm_vblank_work.c line 220
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work.c new file +10
-0+{ +struct drm_vblank_crtc *vblank = work->vblank; +struct drm_device *dev = vblank->dev; + +spin_lock_irq (&dev->event_lock); +wait_event_lock_irq (vblank->work_wait_queue,list_empty (&work->node), + dev->event_lock); +spin_unlock_irq (&dev->event_lock); + +kthread_flush_work (&work->base);
So much less magic here, I like.
Quoted 49 lines
drivers/gpu/drm/drm_vblank_work.c new file +39
-0+} +EXPORT_SYMBOL (drm_vblank_work_flush); + +/** +* drm_vblank_work_init - initialize a vblank work item +* @work: vblank work item +* @crtc: CRTC whose vblank will trigger the work execution +* @func: work function to be executed +* +* Initialize a vblank work item for a specific crtc. +*/ +void drm_vblank_work_init (struct drm_vblank_work *work,struct drm_crtc *crtc, +void (*func)(struct kthread_work *work)) +{ +kthread_init_work (&work->base, func); +INIT_LIST_HEAD (&work->node); + work->vblank = &crtc->dev->vblank[drm_crtc_index (crtc)]; +} +EXPORT_SYMBOL (drm_vblank_work_init); + +int drm_vblank_worker_init (struct drm_vblank_crtc *vblank) +{ +struct sched_param param = { + .sched_priority =MAX_RT_PRIO -1 , + }; +struct kthread_worker *worker; + +INIT_LIST_HEAD (&vblank->pending_work); +init_waitqueue_head (&vblank->work_wait_queue); + worker =kthread_create_worker (0 ,"card%d-crtc%d" , + vblank->dev->primary->index, + vblank->pipe); +if (IS_ERR (worker)) +return PTR_ERR (worker); + + vblank->worker = worker; + +return sched_setscheduler (vblank->worker->task,SCHED_FIFO , ¶m); +}drivers/gpu/drm/drm_vblank_work_internal.h new file +4
-0@@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT + +#ifndef _DRM_VBLANK_WORK_INTERNAL_H_ +#define _DRM_VBLANK_WORK_INTERNAL_H_
drivers/gpu/drm/drm_vblank_work_internal.h line 14
Quoted 10 lines
drivers/gpu/drm/drm_vblank_work_internal.h new file +10
-0+ +#include <drm/drm_vblank.h> + +int drm_vblank_worker_init (struct drm_vblank_crtc *vblank); +void drm_vblank_cancel_pending_works (struct drm_vblank_crtc *vblank); +void drm_handle_vblank_works (struct drm_vblank_crtc *vblank); + +static inline void drm_vblank_flush_worker (struct drm_vblank_crtc *vblank) +{ +if (vblank->worker)
Is this check really required? We should always have a worker I thought?
drivers/gpu/drm/drm_vblank_work_internal.h line 20
Quoted 6 lines
drivers/gpu/drm/drm_vblank_work_internal.h new file +6
-0+kthread_flush_worker (vblank->worker); +} + +static inline void drm_vblank_destroy_worker (struct drm_vblank_crtc *vblank) +{ +if (vblank->worker)
Same here.
Quoted 128 lines
drivers/gpu/drm/drm_vblank_work_internal.h new file +4
-0+ kthread_destroy_worker(vblank->worker); +} + +#endif /* !_DRM_VBLANK_WORK_INTERNAL_H_ */ include/drm/drm_vblank.h +20
-0@@ -27,12 +27,14 @@#include <linux/seqlock.h> #include <linux/idr.h> #include <linux/poll.h> +#include <linux/kthread.h> #include <drm/drm_file.h> #include <drm/drm_modes.h> struct drm_device ;struct drm_crtc ; +struct drm_vblank_work ;/** * struct drm_pending_vblank_event - pending vblank event tracking @@ -203,6 +205,24 @@ struct drm_vblank_crtc {* disabling functions multiple times. */ bool enabled; + +/** +* @worker: The &kthread_worker used for executing vblank works. +*/ +struct kthread_worker *worker; + +/** +* @pending_work: A list of scheduled &drm_vblank_work items that are +* waiting for a future vblank. +*/ +struct list_head pending_work; + +/** +* @work_wait_queue: The wait queue used for signaling that a +* &drm_vblank_work item has either finished executing, or was +* cancelled. +*/ +wait_queue_head_t work_wait_queue; };int drm_vblank_init (struct drm_device *dev,unsigned int num_crtcs);include/drm/drm_vblank_work.h new file +71
-0@@ -0,0 +1,71 @@ +// SPDX-License-Identifier: MIT + +#ifndef _DRM_VBLANK_WORK_H_ +#define _DRM_VBLANK_WORK_H_ + +#include <linux/kthread.h> + +struct drm_crtc ; + +/** +* struct drm_vblank_work - A delayed work item which delays until a target +* vblank passes, and then executes at realtime priority outside of IRQ +* context. +* +* See also: +* drm_vblank_work_schedule() +* drm_vblank_work_init() +* drm_vblank_work_cancel_sync() +* drm_vblank_work_flush() +*/ +struct drm_vblank_work { +/** +* @base: The base &kthread_work item which will be executed by +* &drm_vblank_crtc.worker. Drivers should not interact with this +* directly, and instead rely on drm_vblank_work_init() to initialize +* this. +*/ +struct kthread_work base; + +/** +* @vblank: A pointer to &drm_vblank_crtc this work item belongs to. +*/ +struct drm_vblank_crtc *vblank; + +/** +* @count: The target vblank this work will execute on. Drivers should +* not modify this value directly, and instead use +* drm_vblank_work_schedule() +*/ +u64 count; + +/** +* @cancelling: The number of drm_vblank_work_cancel_sync() calls that +* are currently running. A work item cannot be rescheduled until all +* calls have finished. +*/ +int cancelling; + +/** +* @node: The position of this work item in +* &drm_vblank_crtc.pending_work. +*/ +struct list_head node; +}; + +/** +* to_drm_vblank_work - Retrieve the respective &drm_vblank_work item from a +* &kthread_work +* @_work: The &kthread_work embedded inside a &drm_vblank_work +*/ +#define to_drm_vblank_work (_work) \ + container_of((_work), struct drm_vblank_work, base) + +int drm_vblank_work_schedule (struct drm_vblank_work *work, +u64 count,bool nextonmiss); +void drm_vblank_work_init (struct drm_vblank_work *work,struct drm_crtc *crtc, +void (*func)(struct kthread_work *work)); +bool drm_vblank_work_cancel_sync (struct drm_vblank_work *work); +void drm_vblank_work_flush (struct drm_vblank_work *work); + +#endif /* !_DRM_VBLANK_WORK_H_ */ Signature · 1 line
2.26.2
Signature · 3 lines
Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch
Lyude Paul
maintainerRFC v7 4/11 drm/nouveau/kms/nv50-: Unroll error cleanup in nv50_head_create()
In reply to Lyude PaulWe'll be rolling back more things in this function, and the way it's structured is a bit confusing. So, let's clean this up a bit and just unroll in the event of failure.
--- drivers/gpu/drm/nouveau/dispnv50/head.c | 33 +++++++++++++++++-------- 1 file changed, 23 insertions(+), 10 deletions(-)
drivers/gpu/drm/nouveau/dispnv50/head.c +23 -10
@@ -507,20 +507,28 @@ nv50_head_create(struct drm_device *dev, int index)if (disp->disp->object.oclass <GV100_DISP ) { ret =nv50_base_new (drm, head->base.index, &base); +if (ret) + goto fail_free; + ret =nv50_ovly_new (drm, head->base.index, &ovly); +if (ret) + goto fail_free; }else { ret =nv50_wndw_new (drm,DRM_PLANE_TYPE_PRIMARY , head->base.index *2 +0 , &base); +if (ret) + goto fail_free; + ret =nv50_wndw_new (drm,DRM_PLANE_TYPE_OVERLAY , head->base.index *2 +1 , &ovly); - } -if (ret ==0 ) - ret =nv50_curs_new (drm, head->base.index, &curs); -if (ret) { -kfree (head); -return ERR_PTR (ret); +if (ret) + goto fail_free; } + ret =nv50_curs_new (drm, head->base.index, &curs); +if (ret) + goto fail_free; + crtc = &head->base.base;drm_crtc_init_with_planes (dev, crtc, &base->plane, &curs->plane, &nv50_head_func,"head-%d" , head->base.index);
@@ -533,11 +541,16 @@ nv50_head_create(struct drm_device *dev, int index)if (head->func->olut_set) { ret =nv50_lut_init (disp, &drm->client.mmu, &head->olut); -if (ret) { -nv50_head_destroy (crtc); -return ERR_PTR (ret); - } +if (ret) + goto fail_crtc_cleanup; }return head; + +fail_crtc_cleanup: +drm_crtc_cleanup (crtc); +fail_free: +kfree (head); + +return ERR_PTR (ret); }
Signature · 1 line
2.26.2
Lyude Paul
maintainerRFC v7 5/11 drm/nouveau/kms/nv140-: Don't modify depth in state during atomic commit
In reply to Lyude PaulCurrently, we modify the depth value stored in the atomic state when performing a commit in order to workaround the fact we haven't implemented support for depths higher then 10 yet. This isn't idempotent though, as it will happen every atomic commit where we modify the OR state even if the head's depth in the atomic state hasn't been modified.
Normally this wouldn't matter, since we don't modify OR state outside of modesets, but since the CRC capture region is implemented as part of the OR state in hardware we'll want to make sure all commits modifying OR state are idempotent so as to avoid changing the depth unexpectedly.
So, fix this by simply not writing the reduced depth value we come up with to the atomic state.
--- drivers/gpu/drm/nouveau/dispnv50/headc37d.c | 11 +++++++---- drivers/gpu/drm/nouveau/dispnv50/headc57d.c | 11 +++++++---- 2 files changed, 14 insertions(+), 8 deletions(-)
drivers/gpu/drm/nouveau/dispnv50/headc37d.c +7 -4
@@ -27,17 +27,20 @@ static void headc37d_or(struct nv50_head *head, struct nv50_head_atom *asyh) { struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan; +u8 depth;u32 *push; +if ((push =evo_wait (core,2 ))) {/*XXX: This is a dirty hack until OR depth handling is * improved later for deep colour etc. */ switch (asyh->or.depth) { -case 6 : asyh->or.depth =5 ;break ; -case 5 : asyh->or.depth =4 ;break ; -case 2 : asyh->or.depth =1 ;break ; -case 0 : asyh->or.depth =4 ;break ; +case 6 : depth =5 ;break ; +case 5 : depth =4 ;break ; +case 2 : depth =1 ;break ; +case 0 : depth =4 ;break ;default : + depth = asyh->or.depth;WARN_ON (1 );break ; }
drivers/gpu/drm/nouveau/dispnv50/headc57d.c +7 -4
@@ -27,17 +27,20 @@ static void headc57d_or(struct nv50_head *head, struct nv50_head_atom *asyh) { struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->core->chan; +u8 depth;u32 *push; +if ((push =evo_wait (core,2 ))) {/*XXX: This is a dirty hack until OR depth handling is * improved later for deep colour etc. */ switch (asyh->or.depth) { -case 6 : asyh->or.depth =5 ;break ; -case 5 : asyh->or.depth =4 ;break ; -case 2 : asyh->or.depth =1 ;break ; -case 0 : asyh->or.depth =4 ;break ; +case 6 : depth =5 ;break ; +case 5 : depth =4 ;break ; +case 2 : depth =1 ;break ; +case 0 : depth =4 ;break ;default : + depth = asyh->or.depth;WARN_ON (1 );break ; }
Signature · 1 line
2.26.2
Lyude Paul
maintainerRFC v7 6/11 drm/nouveau/kms/nv50-: Fix disabling dithering
In reply to Lyude PaulWhile we expose the ability to turn off hardware dithering for nouveau, we actually make the mistake of turning it on anyway, due to dithering_depth containing a non-zero value if our dithering depth isn't also set to 6 bpc.
So, fix it by never enabling dithering when it's disabled.
--- drivers/gpu/drm/nouveau/dispnv50/head.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-)
drivers/gpu/drm/nouveau/dispnv50/head.c +13 -11
@@ -84,18 +84,20 @@ nv50_head_atomic_check_dither(struct nv50_head_atom *armh, {u32 mode =0x00 ; -if (asyc->dither.mode ==DITHERING_MODE_AUTO ) { -if (asyh->base.depth > asyh->or.bpc *3 ) - mode =DITHERING_MODE_DYNAMIC2X2 ; - }else { - mode = asyc->dither.mode; - } +if (asyc->dither.mode) { +if (asyc->dither.mode ==DITHERING_MODE_AUTO ) { +if (asyh->base.depth > asyh->or.bpc *3 ) + mode =DITHERING_MODE_DYNAMIC2X2 ; + }else { + mode = asyc->dither.mode; + } -if (asyc->dither.depth ==DITHERING_DEPTH_AUTO ) { -if (asyh->or.bpc >=8 ) - mode |=DITHERING_DEPTH_8BPC ; - }else { - mode |= asyc->dither.depth; +if (asyc->dither.depth ==DITHERING_DEPTH_AUTO ) { +if (asyh->or.bpc >=8 ) + mode |=DITHERING_DEPTH_8BPC ; + }else { + mode |= asyc->dither.depth; + } } asyh->dither.enable = mode;
Signature · 1 line
2.26.2
Lyude Paul
maintainerRFC v7 7/11 drm/nouveau/kms/nv50-: s/harm/armh/g
In reply to Lyude PaulWe refer to the armed hardware assembly as armh elsewhere in nouveau, so fix the naming here to make it consistent.
This patch contains no functional changes.
--- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)
drivers/gpu/drm/nouveau/dispnv50/wndw.c +6 -6
@@ -408,7 +408,7 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)struct nv50_wndw *wndw =nv50_wndw (plane);struct nv50_wndw_atom *armw =nv50_wndw_atom (wndw->plane.state);struct nv50_wndw_atom *asyw =nv50_wndw_atom (state); -struct nv50_head_atom *harm =NULL , *asyh =NULL ; +struct nv50_head_atom *armh =NULL , *asyh =NULL ;bool modeset = false;int ret;
@@ -429,9 +429,9 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)/* Fetch assembly state for the head the window used to belong to. */ if (armw->state.crtc) { - harm =nv50_head_atom_get (asyw->state.state, armw->state.crtc); -if (IS_ERR (harm)) -return PTR_ERR (harm); + armh =nv50_head_atom_get (asyw->state.state, armw->state.crtc); +if (IS_ERR (armh)) +return PTR_ERR (armh); }/* LUT configuration can potentially cause the window to be disabled. */
@@ -455,8 +455,8 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state) asyh->wndw.mask |=BIT (wndw->id); }else if (armw->visible) { -nv50_wndw_atomic_check_release (wndw, asyw, harm); - harm->wndw.mask &= ~BIT (wndw->id); +nv50_wndw_atomic_check_release (wndw, asyw, armh); + armh->wndw.mask &= ~BIT (wndw->id); }else {return 0 ; }
Signature · 1 line
2.26.2
Lyude Paul
maintainerRFC v7 8/11 drm/nouveau/kms/nv140-: Track wndw mappings in nv50_head_atom
In reply to Lyude PaulWhile we're not quite ready yet to add support for flexible wndw mappings, we are going to need to at least keep track of the static wndw mappings we're currently using in each head's atomic state. We'll likely use this in the future to implement real flexible window mapping, but the primary reason we'll need this is for CRC support.
See: on nvidia hardware, each CRC entry in the CRC notifier dma context has a "tag". This tag corresponds to the nth update on a specific EVO/NvDisplay channel, which itself is referred to as the "controlling channel". For gf119+ this can be the core channel, ovly channel, or base channel. Since we don't expose CRC entry tags to userspace, we simply ignore this feature and always use the core channel as the controlling channel. Simple.
Things get a little bit more complicated on gv100+ though. GV100+ only lets us set the controlling channel to a specific wndw channel, and that wndw must be owned by the head that we're grabbing CRCs when we enable CRC generation. Thus, we always need to make sure that each atomic head state has at least one wndw that is mapped to the head, which will be used as the controlling channel.
Note that since we don't have flexible wndw mappings yet, we don't expect to run into any scenarios yet where we'd have a head with no mapped wndws. When we do add support for flexible wndw mappings however, we'll need to make sure that we handle reprogramming CRC capture if our controlling wndw is moved to another head (and potentially reject the new head state entirely if we can't find another available wndw to replace it).
With that being said, nouveau currently tracks wndw visibility on heads. It does not keep track of the actual ownership mappings, which are (currently) statically programmed. To fix this, we introduce another bitmask into nv50_head_atom.wndw to keep track of ownership separately from visibility. We then introduce a nv50_head callback to handle populating the wndw ownership map, and call it during the atomic check phase when core->assign_windows is set to true.
--- drivers/gpu/drm/nouveau/dispnv50/atom.h | 1 + drivers/gpu/drm/nouveau/dispnv50/disp.c | 16 ++++++++++++++++ drivers/gpu/drm/nouveau/dispnv50/head.h | 2 ++ drivers/gpu/drm/nouveau/dispnv50/headc37d.c | 10 ++++++++++ drivers/gpu/drm/nouveau/dispnv50/headc57d.c | 2 ++ 5 files changed, 31 insertions(+)
drivers/gpu/drm/nouveau/dispnv50/atom.h +1 -0
@@ -18,6 +18,7 @@ struct nv50_head_atom {struct {u32 mask; +u32 owned;u32 olut; } wndw;
drivers/gpu/drm/nouveau/dispnv50/disp.c +16 -0
@@ -2287,12 +2287,28 @@ static int nv50_disp_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { struct nv50_atom *atom = nv50_atom(state); +struct nv50_core *core =nv50_disp (dev)->core;struct drm_connector_state *old_connector_state, *new_connector_state;struct drm_connector *connector;struct drm_crtc_state *new_crtc_state;struct drm_crtc *crtc; +struct nv50_head *head; +struct nv50_head_atom *asyh;int ret, i; +if (core->assign_windows && core->func->head->static_wndw_map) { +drm_for_each_crtc (crtc, dev) { + new_crtc_state =drm_atomic_get_crtc_state (state, + crtc); +if (IS_ERR (new_crtc_state)) +return PTR_ERR (new_crtc_state); + + head =nv50_head (crtc); + asyh =nv50_head_atom (new_crtc_state); + core->func->head->static_wndw_map (head, asyh); + } + } +/* We need to handle colour management on a per-plane basis. */ for_each_new_crtc_in_state (state, crtc, new_crtc_state, i) {if (new_crtc_state->color_mgmt_changed) {
drivers/gpu/drm/nouveau/dispnv50/head.h +2 -0
@@ -40,6 +40,7 @@ struct nv50_head_func {void (*dither)(struct nv50_head *,struct nv50_head_atom *);void (*procamp)(struct nv50_head *,struct nv50_head_atom *);void (*or)(struct nv50_head *,struct nv50_head_atom *); +void (*static_wndw_map)(struct nv50_head *,struct nv50_head_atom *); };extern const struct nv50_head_func head507d;
@@ -86,6 +87,7 @@ int headc37d_curs_format(struct nv50_head *, struct nv50_wndw_atom *,void headc37d_curs_set (struct nv50_head *,struct nv50_head_atom *);void headc37d_curs_clr (struct nv50_head *);void headc37d_dither (struct nv50_head *,struct nv50_head_atom *); +void headc37d_static_wndw_map (struct nv50_head *,struct nv50_head_atom *);extern const struct nv50_head_func headc57d;#endif
drivers/gpu/drm/nouveau/dispnv50/headc37d.c +10 -0
@@ -204,6 +204,15 @@ headc37d_view(struct nv50_head *head, struct nv50_head_atom *asyh) } } +void +headc37d_static_wndw_map (struct nv50_head *head,struct nv50_head_atom *asyh) +{ +int i, end; + +for (i = head->base.index *2 , end = i +2 ; i < end; i++) + asyh->wndw.owned |=BIT (i); +} +const struct nv50_head_func headc37d = { .view = headc37d_view,
@@ -219,4 +228,5 @@ headc37d = { .dither = headc37d_dither, .procamp = headc37d_procamp, .or = headc37d_or, + .static_wndw_map = headc37d_static_wndw_map, };
drivers/gpu/drm/nouveau/dispnv50/headc57d.c +2 -0
@@ -211,4 +211,6 @@ headc57d = { .dither = headc37d_dither, .procamp = headc57d_procamp, .or = headc57d_or, + /* TODO: flexible window mappings */ + .static_wndw_map = headc37d_static_wndw_map, };
Signature · 1 line
2.26.2
Lyude Paul
maintainerRFC v7 9/11 drm/nouveau/kms/nv50-: Expose nv50_outp_atom in disp.h
In reply to Lyude PaulIn order to make sure that we flush disable updates at the right time when disabling CRCs, we'll need to be able to look at the outp state to see if we're changing it at the same time that we're disabling CRCs.
So, expose the struct in disp.h.
--- drivers/gpu/drm/nouveau/dispnv50/disp.c | 18 ------------------ drivers/gpu/drm/nouveau/dispnv50/disp.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 18 deletions(-)
drivers/gpu/drm/nouveau/dispnv50/disp.c +0 -18
@@ -57,24 +57,6 @@#include <subdev/bios/dp.h> -/****************************************************************************** -* Atomic state -*****************************************************************************/ - -struct nv50_outp_atom { -struct list_head head; - -struct drm_encoder *encoder; -bool flush_disable; - -union nv50_outp_atom_mask { -struct { -bool ctrl:1 ; - }; -u8 mask; - } set, clr; -}; -/****************************************************************************** * EVO channel *****************************************************************************/
drivers/gpu/drm/nouveau/dispnv50/disp.h +14 -0
@@ -71,6 +71,20 @@ struct nv50_dmac {struct mutex lock; }; +struct nv50_outp_atom { +struct list_head head; + +struct drm_encoder *encoder; +bool flush_disable; + +union nv50_outp_atom_mask { +struct { +bool ctrl:1 ; + }; +u8 mask; + } set, clr; +}; +int nv50_dmac_create (struct nvif_device *device,struct nvif_object *disp,const s32 *oclass,u8 head,void *data,u32 size,u64 syncbuf,struct nv50_dmac *dmac);
Signature · 1 line
2.26.2
Lyude Paul
maintainerRFC v7 10/11 drm/nouveau/kms/nv50-: Move hard-coded object handles into header
In reply to Lyude PaulWhile most of the functionality on Nvidia GPUs doesn't require using an explicit handle instead of the main VRAM handle + offset, there are a couple of places that do require explicit handles, such as CRC functionality. Since this means we're about to add another nouveau-chosen handle, let's just go ahead and move any hard-coded handles into a single header. This is just to keep things slightly organized, and to make it a little bit easier if we need to add more handles in the future.
This patch should contain no functional changes.
Changes since v3:
* Correct SPDX license identifier (checkpatch)
--- drivers/gpu/drm/nouveau/dispnv50/disp.c | 7 +++++-- drivers/gpu/drm/nouveau/dispnv50/handles.h | 15 +++++++++++++++ drivers/gpu/drm/nouveau/dispnv50/wndw.c | 3 ++- 3 files changed, 22 insertions(+), 3 deletions(-) create mode 100644 drivers/gpu/drm/nouveau/dispnv50/handles.h
drivers/gpu/drm/nouveau/dispnv50/disp.c +5 -2
@@ -26,6 +26,7 @@#include "core.h" #include "head.h" #include "wndw.h" +#include "handles.h" #include <linux/dma-mapping.h> #include <linux/hdmi.h>
@@ -154,7 +155,8 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,if (!syncbuf)return 0 ; - ret = nvif_object_init(&dmac->base.user, 0xf0000000, NV_DMA_IN_MEMORY, + ret = nvif_object_init(&dmac->base.user, NV50_DISP_HANDLE_SYNCBUF, + NV_DMA_IN_MEMORY, &(struct nv_dma_v0) { .target = NV_DMA_V0_TARGET_VRAM, .access = NV_DMA_V0_ACCESS_RDWR,
@@ -165,7 +167,8 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,if (ret)return ret; - ret = nvif_object_init(&dmac->base.user, 0xf0000001, NV_DMA_IN_MEMORY, + ret = nvif_object_init(&dmac->base.user, NV50_DISP_HANDLE_VRAM, + NV_DMA_IN_MEMORY, &(struct nv_dma_v0) { .target = NV_DMA_V0_TARGET_VRAM, .access = NV_DMA_V0_ACCESS_RDWR,
drivers/gpu/drm/nouveau/dispnv50/handles.h new file +15 -0
@@ -0,0 +1,15 @@ +// SPDX-License-Identifier: MIT +#ifndef __NV50_KMS_HANDLES_H__ +#define __NV50_KMS_HANDLES_H__ + +/* +* Various hard-coded object handles that nouveau uses. These are made-up by +* nouveau developers, not Nvidia. The only significance of the handles chosen +* is that they must all be unique. +*/ +#define NV50_DISP_HANDLE_SYNCBUF 0xf0000000 +#define NV50_DISP_HANDLE_VRAM 0xf0000001 + +#define NV50_DISP_HANDLE_WNDW_CTX (kind) (0xfb000000 | kind) + +#endif /* !__NV50_KMS_HANDLES_H__ */
drivers/gpu/drm/nouveau/dispnv50/wndw.c +2 -1
@@ -21,6 +21,7 @@*/ #include "wndw.h" #include "wimm.h" +#include "handles.h" #include <nvif/class.h> #include <nvif/cl0002.h>
@@ -59,7 +60,7 @@ nv50_wndw_ctxdma_new(struct nv50_wndw *wndw, struct drm_framebuffer *fb)int ret;nouveau_framebuffer_get_layout (fb, &unused, &kind); - handle =0xfb000000 | kind; + handle =NV50_DISP_HANDLE_WNDW_CTX (kind);list_for_each_entry (ctxdma, &wndw->ctxdma.list, head) {if (ctxdma->object.handle == handle)
Signature · 1 line
2.26.2
Lyude Paul
maintainerRFC v7 11/11 drm/nouveau/kms/nvd9-: Add CRC support
In reply to Lyude PaulThis introduces support for CRC readback on gf119+, using the documentation generously provided to us by Nvidia:
https://github.com/NVIDIA/open-gpu-doc/blob/master/Display-CRC/display-crc.txt
We expose all available CRC sources. SF, SOR, PIOR, and DAC are exposed through a single set of "outp" sources: outp-active/auto for a CRC of the scanout region, outp-complete for a CRC of both the scanout and blanking/sync region combined, and outp-inactive for a CRC of only the blanking/sync region. For each source, nouveau selects the appropriate tap point based on the output path in use. We also expose an "rg" source, which allows for capturing CRCs of the scanout raster before it's encoded into a video signal in the output path. This tap point is referred to as the raster generator.
Note that while there's some other neat features that can be used with CRC capture on nvidia hardware, like capturing from two CRC sources simultaneously, I couldn't see any usecase for them and did not implement them.
Nvidia only allows for accessing CRCs through a shared DMA region that we program through the core EVO/NvDisplay channel which is referred to as the notifier context. The notifier context is limited to either 255 (for Fermi-Pascal) or 2047 (Volta+) entries to store CRCs in, and unfortunately the hardware simply drops CRCs and reports an overflow once all available entries in the notifier context are filled.
Since the DRM CRC API and igt-gpu-tools don't expect there to be a limit on how many CRCs can be captured, we work around this in nouveau by allocating two separate notifier contexts for each head instead of one. We schedule a vblank worker ahead of time so that once we start getting close to filling up all of the available entries in the notifier context, we can swap the currently used notifier context out with another pre-prepared notifier context in a manner similar to page flipping.
Unfortunately, the hardware only allows us to this by flushing two separate updates on the core channel: one to release the current notifier context handle, and one to program the next notifier context's handle. When the hardware processes the first update, the CRC for the current frame is lost. However, the second update can be flushed immediately without waiting for the first to complete so that CRC generation resumes on the next frame. According to Nvidia's hardware engineers, there isn't any cleaner way of flipping notifier contexts that would avoid this.
Since using vblank workers to swap out the notifier context will ensure we can usually flush both updates to hardware within the timespan of a single frame, we can also ensure that there will only be exactly one frame lost between the first and second update being executed by the hardware. This gives us the guarantee that we're always correctly matching each CRC entry with it's respective frame even after a context flip. And since IGT will retrieve the CRC entry for a frame by waiting until it receives a CRC for any subsequent frames, this doesn't cause an issue with any tests and is much simpler than trying to change the current DRM API to accommodate.
In order to facilitate testing of correct handling of this limitation, we also expose a debugfs interface to manually control the threshold for when we start trying to flip the notifier context. We will use this in igt to trigger a context flip for testing purposes without needing to wait for the notifier to completely fill up. This threshold is reset to the default value set by nouveau after each capture, and is exposed in a separate folder within each CRTC's debugfs directory labelled "nv_crc".
Changes since v1:
* Forgot to finish saving crc.h before saving, whoops. This just adds some corrections to the empty function declarations that we use if CONFIG_DEBUG_FS isn't enabled.
Changes since v2:
* Don't check return code from debugfs_create_dir() or debugfs_create_file() - Greg K-H
Changes since v3:
(no functional changes)
* Fix SPDX license identifiers (checkpatch)
* s/uint32_t/u32/ (checkpatch)
* Fix indenting in switch cases (checkpatch)
Changes since v4:
* Remove unneeded param changes with nv50_head_flush_clr/set
* Rebase
Changes since v5:
* Remove set but unused variable (outp) in nv50_crc_atomic_check() - Kbuild bot
--- drivers/gpu/drm/nouveau/dispnv04/crtc.c | 25 +- drivers/gpu/drm/nouveau/dispnv50/Kbuild | 4 + drivers/gpu/drm/nouveau/dispnv50/atom.h | 20 + drivers/gpu/drm/nouveau/dispnv50/core.h | 4 + drivers/gpu/drm/nouveau/dispnv50/core907d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/core917d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/corec37d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/corec57d.c | 3 + drivers/gpu/drm/nouveau/dispnv50/crc.c | 714 ++++++++++++++++++++ drivers/gpu/drm/nouveau/dispnv50/crc.h | 125 ++++ drivers/gpu/drm/nouveau/dispnv50/crc907d.c | 139 ++++ drivers/gpu/drm/nouveau/dispnv50/crcc37d.c | 153 +++++ drivers/gpu/drm/nouveau/dispnv50/disp.c | 17 + drivers/gpu/drm/nouveau/dispnv50/disp.h | 10 + drivers/gpu/drm/nouveau/dispnv50/handles.h | 1 + drivers/gpu/drm/nouveau/dispnv50/head.c | 77 ++- drivers/gpu/drm/nouveau/dispnv50/head.h | 10 +- drivers/gpu/drm/nouveau/dispnv50/head907d.c | 14 +- drivers/gpu/drm/nouveau/dispnv50/headc37d.c | 6 +- drivers/gpu/drm/nouveau/dispnv50/headc57d.c | 7 +- drivers/gpu/drm/nouveau/nouveau_display.c | 60 +- 21 files changed, 1328 insertions(+), 70 deletions(-) create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crc.c create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crc.h create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crc907d.c create mode 100644 drivers/gpu/drm/nouveau/dispnv50/crcc37d.c
drivers/gpu/drm/nouveau/dispnv04/crtc.c +24 -1
@@ -44,6 +44,9 @@#include <subdev/bios/pll.h> #include <subdev/clk.h> +#include <nvif/event.h> +#include <nvif/cl0046.h> +static int nv04_crtc_mode_set_base (struct drm_crtc *crtc,int x,int y,struct drm_framebuffer *old_fb);
@@ -756,6 +759,7 @@ static void nv_crtc_destroy(struct drm_crtc *crtc)nouveau_bo_unmap (nv_crtc->cursor.nvbo);nouveau_bo_unpin (nv_crtc->cursor.nvbo);nouveau_bo_ref (NULL , &nv_crtc->cursor.nvbo); +nvif_notify_fini (&nv_crtc->vblank);kfree (nv_crtc); }
@@ -1297,9 +1301,19 @@ create_primary_plane(struct drm_device *dev)return primary; } +static int nv04_crtc_vblank_handler (struct nvif_notify *notify) +{ +struct nouveau_crtc *nv_crtc = + container_of(notify, struct nouveau_crtc, vblank); + +drm_crtc_handle_vblank (&nv_crtc->base); +return NVIF_NOTIFY_KEEP ; +} +int nv04_crtc_create (struct drm_device *dev,int crtc_num) { +struct nouveau_display *disp =nouveau_display (dev);struct nouveau_crtc *nv_crtc;int ret;
@@ -1337,5 +1351,14 @@ nv04_crtc_create(struct drm_device *dev, int crtc_num)nv04_cursor_init (nv_crtc); -return 0 ; + ret =nvif_notify_init (&disp->disp.object, nv04_crtc_vblank_handler, + false,NV04_DISP_NTFY_VBLANK , + &(struct nvif_notify_head_req_v0 ) { + .head = nv_crtc->index, + }, +sizeof (struct nvif_notify_head_req_v0 ), +sizeof (struct nvif_notify_head_rep_v0 ), + &nv_crtc->vblank); + +return ret; }
drivers/gpu/drm/nouveau/dispnv50/Kbuild +4 -0
@@ -10,6 +10,10 @@ nouveau-y += dispnv50/core917d.o nouveau-y += dispnv50/corec37d.o nouveau-y += dispnv50/corec57d.o +nouveau-$(CONFIG_DEBUG_FS) += dispnv50/crc.o +nouveau-$(CONFIG_DEBUG_FS) += dispnv50/crc907d.o +nouveau-$(CONFIG_DEBUG_FS) += dispnv50/crcc37d.o + nouveau-y += dispnv50/dac507d.o nouveau-y += dispnv50/dac907d.o
drivers/gpu/drm/nouveau/dispnv50/atom.h +20 -0
@@ -2,6 +2,9 @@#define __NV50_KMS_ATOM_H__#define nv50_atom (p) container_of((p), struct nv50_atom, state)#include <drm/drm_atomic.h> +#include "crc.h" + +struct nouveau_encoder ;struct nv50_atom {struct drm_atomic_state state;
@@ -115,9 +118,12 @@ struct nv50_head_atom { u8 nhsync:1; u8 nvsync:1; u8 depth:4; + u8 crc_raster:2;u8 bpc; } or; +struct nv50_crc_atom crc; +/* Currently only used for MST */ struct {int pbn;
@@ -135,6 +141,7 @@ struct nv50_head_atom { bool ovly:1; bool dither:1; bool procamp:1; + bool crc:1; bool or:1; };u16 mask;
@@ -150,6 +157,19 @@ nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc)return nv50_head_atom (statec); } +static inline struct drm_encoder * +nv50_head_atom_get_encoder (struct nv50_head_atom *atom) +{ +struct drm_encoder *encoder =NULL ; + +/* We only ever have a single encoder */ +drm_for_each_encoder_mask (encoder, atom->state.crtc->dev, + atom->state.encoder_mask) +break ; + +return encoder; +} +#define nv50_wndw_atom (p) container_of((p), struct nv50_wndw_atom, state)struct nv50_wndw_atom {
drivers/gpu/drm/nouveau/dispnv50/core.h +4 -0
@@ -2,6 +2,7 @@#define __NV50_KMS_CORE_H__#include "disp.h" #include "atom.h" +#include "crc.h" #include <nouveau_encoder.h> struct nv50_core {
@@ -26,6 +27,9 @@ struct nv50_core_func { } wndw;const struct nv50_head_func *head; +#if IS_ENABLED (CONFIG_DEBUG_FS ) +const struct nv50_crc_func *crc; +#endif const struct nv50_outp_func { void (*ctrl)(struct nv50_core *, int or, u32 ctrl, struct nv50_head_atom *);
drivers/gpu/drm/nouveau/dispnv50/core907d.c +3 -0
@@ -30,6 +30,9 @@ core907d = { .ntfy_wait_done = core507d_ntfy_wait_done, .update = core507d_update, .head = &head907d, +#if IS_ENABLED(CONFIG_DEBUG_FS) + .crc = &crc907d, +#endif .dac = &dac907d, .sor = &sor907d, };
drivers/gpu/drm/nouveau/dispnv50/core917d.c +3 -0
@@ -30,6 +30,9 @@ core917d = { .ntfy_wait_done = core507d_ntfy_wait_done, .update = core507d_update, .head = &head917d, +#if IS_ENABLED(CONFIG_DEBUG_FS) + .crc = &crc907d, +#endif .dac = &dac907d, .sor = &sor907d, };
drivers/gpu/drm/nouveau/dispnv50/corec37d.c +3 -0
@@ -142,6 +142,9 @@ corec37d = { .wndw.owner = corec37d_wndw_owner, .head = &headc37d, .sor = &sorc37d, +#if IS_ENABLED (CONFIG_DEBUG_FS ) + .crc = &crcc37d, +#endif };int
drivers/gpu/drm/nouveau/dispnv50/corec57d.c +3 -0
@@ -52,6 +52,9 @@ corec57d = { .wndw.owner = corec37d_wndw_owner, .head = &headc57d, .sor = &sorc37d, +#if IS_ENABLED (CONFIG_DEBUG_FS ) + .crc = &crcc37d, +#endif };int
drivers/gpu/drm/nouveau/dispnv50/crc.c new file +714 -0
714 lines not on this page · raw message
drivers/gpu/drm/nouveau/dispnv50/crc.h new file +125 -0
125 lines not on this page · raw message
drivers/gpu/drm/nouveau/dispnv50/crc907d.c new file +139 -0
139 lines not on this page · raw message
drivers/gpu/drm/nouveau/dispnv50/crcc37d.c new file +153 -0
153 lines not on this page · raw message
drivers/gpu/drm/nouveau/dispnv50/disp.c +17 -0
@@ -783,6 +783,19 @@ struct nv50_msto {bool disabled; }; +struct nouveau_encoder *nv50_real_outp (struct drm_encoder *encoder) +{ +struct nv50_msto *msto; + +if (encoder->encoder_type !=DRM_MODE_ENCODER_DPMST ) +return nouveau_encoder (encoder); + + msto =nv50_msto (encoder); +if (!msto->mstc) +return NULL ; +return msto->mstc->mstm->outp; +} +static struct drm_dp_payload *nv50_msto_payload (struct nv50_msto *msto) {
@@ -1932,6 +1945,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)int i;NV_ATOMIC (drm,"commit %d %d\n" , atom->lock_core, atom->flush_disable); +nv50_crc_atomic_stop_reporting (state);drm_atomic_helper_wait_for_fences (dev, state, false);drm_atomic_helper_wait_for_dependencies (state);drm_atomic_helper_update_legacy_modeset_state (dev, state);
@@ -2002,6 +2016,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) } } +nv50_crc_atomic_prepare_notifier_contexts (state); +/* Update output path(s). */ list_for_each_entry_safe (outp, outt, &atom->outp, head) {const struct drm_encoder_helper_funcs *help;
@@ -2115,6 +2131,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) } } +nv50_crc_atomic_start_reporting (state);drm_atomic_helper_commit_hw_done (state);drm_atomic_helper_cleanup_planes (dev, state);drm_atomic_helper_commit_cleanup_done (state);
drivers/gpu/drm/nouveau/dispnv50/disp.h +10 -0
@@ -1,10 +1,12 @@ #ifndef __NV50_KMS_H__ #define __NV50_KMS_H__ +#include <linux/workqueue.h> #include <nvif/mem.h> #include "nouveau_display.h" struct nv50_msto; +struct nouveau_encoder; struct nv50_disp { struct nvif_disp *disp;
@@ -90,6 +92,14 @@ int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp, u64 syncbuf, struct nv50_dmac *dmac);void nv50_dmac_destroy (struct nv50_dmac *); +/* +* For normal encoders this just returns the encoder. For active MST encoders, +* this returns the real outp that's driving displays on the topology. +* Inactive MST encoders return NULL, since they would have no real outp to +* return anyway. +*/ +struct nouveau_encoder *nv50_real_outp (struct drm_encoder *encoder); +u32 *evo_wait (struct nv50_dmac *,int nr);void evo_kick (u32 *,struct nv50_dmac *);
drivers/gpu/drm/nouveau/dispnv50/handles.h +1 -0
@@ -11,5 +11,6 @@#define NV50_DISP_HANDLE_VRAM 0xf0000001#define NV50_DISP_HANDLE_WNDW_CTX (kind) (0xfb000000 | kind) +#define NV50_DISP_HANDLE_CRC_CTX (head, i) (0xfc000000 | head->base.index << 1 | i)#endif /* !__NV50_KMS_HANDLES_H__ */
drivers/gpu/drm/nouveau/dispnv50/head.c +74 -3
166 lines not on this page · raw message
drivers/gpu/drm/nouveau/dispnv50/head.h +8 -2
@@ -1,22 +1,28 @@ #ifndef __NV50_KMS_HEAD_H__ #define __NV50_KMS_HEAD_H__ #define nv50_head(c) container_of((c), struct nv50_head, base.base) +#include <linux/workqueue.h> + #include "disp.h" #include "atom.h" +#include "crc.h" #include "lut.h" #include "nouveau_crtc.h" +#include "nouveau_encoder.h" struct nv50_head { const struct nv50_head_func *func; struct nouveau_crtc base; + struct nv50_crc crc; struct nv50_lut olut; struct nv50_msto *msto; }; struct nv50_head *nv50_head_create(struct drm_device *, int index); -void nv50_head_flush_set(struct nv50_head *, struct nv50_head_atom *); -void nv50_head_flush_clr(struct nv50_head *, struct nv50_head_atom *, bool y); +void nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh); +void nv50_head_flush_clr(struct nv50_head *head, + struct nv50_head_atom *asyh, bool flush); struct nv50_head_func { void (*view)(struct nv50_head *, struct nv50_head_atom *);
drivers/gpu/drm/nouveau/dispnv50/head907d.c +11 -3
@@ -19,8 +19,15 @@* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. */ +#include <drm/drm_connector.h> +#include <drm/drm_mode_config.h> +#include <drm/drm_vblank.h> +#include "nouveau_drv.h" +#include "nouveau_bios.h" +#include "nouveau_connector.h" #include "head.h" #include "core.h" +#include "crc.h" void head907d_or (struct nv50_head *head,struct nv50_head_atom *asyh)
@@ -29,9 +36,10 @@ head907d_or(struct nv50_head *head, struct nv50_head_atom *asyh)u32 *push;if ((push =evo_wait (core,3 ))) {evo_mthd (push,0x0404 + (head->base.index *0x300 ),2 ); -evo_data (push,0x00000001 | asyh->or.depth <<6 | - asyh->or.nvsync <<4 | - asyh->or.nhsync <<3 ); +evo_data (push, asyh->or.depth <<6 | + asyh->or.nvsync <<4 | + asyh->or.nhsync <<3 | + asyh->or.crc_raster);evo_data (push,0x31ec6000 | head->base.index <<25 | asyh->mode.interlace);evo_kick (push, core);
drivers/gpu/drm/nouveau/dispnv50/headc37d.c +3 -3
@@ -46,10 +46,10 @@ headc37d_or(struct nv50_head *head, struct nv50_head_atom *asyh) }evo_mthd (push,0x2004 + (head->base.index *0x400 ),1 ); -evo_data (push,0x00000001 | - asyh->or.depth <<4 | +evo_data (push, depth <<4 | asyh->or.nvsync <<3 | - asyh->or.nhsync <<2 ); + asyh->or.nhsync <<2 | + asyh->or.crc_raster);evo_kick (push, core); } }
drivers/gpu/drm/nouveau/dispnv50/headc57d.c +4 -3
@@ -46,10 +46,11 @@ headc57d_or(struct nv50_head *head, struct nv50_head_atom *asyh) }evo_mthd (push,0x2004 + (head->base.index *0x400 ),1 ); -evo_data (push,0xfc000001 | - asyh->or.depth <<4 | +evo_data (push,0xfc000000 | + depth <<4 | asyh->or.nvsync <<3 | - asyh->or.nhsync <<2 ); + asyh->or.nhsync <<2 | + asyh->or.crc_raster);evo_kick (push, core); } }
drivers/gpu/drm/nouveau/nouveau_display.c +5 -55
86 lines not on this page · raw message
Signature · 1 line
2.26.2