From a189b2ee938f6b15ad9f95bdef63f95a3a092418 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 17 Nov 2022 12:47:29 +0100 Subject: fbdev: Make fb_modesetting_disabled() static inline Make fb_modesetting_disabled() a static-inline function when it is defined in the header file. Avoid the linker error shown below. ld: drivers/video/fbdev/core/fbmon.o: in function `fb_modesetting_disabled': fbmon.c:(.text+0x1e4): multiple definition of `fb_modesetting_disabled'; drivers/video/fbdev/core/fbmem.o:fbmem.c:(.text+0x1bac): first defined here A bug report is at [1]. Reported-by: Stephen Rothwell Reported-by: kernel test robot Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Fixes: 0ba2fa8cbd29 ("fbdev: Add support for the nomodeset kernel parameter") Cc: Javier Martinez Canillas Cc: Daniel Vetter Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Link: https://lore.kernel.org/dri-devel/20221117183214.2473e745@canb.auug.org.au/T/#u # 1 Link: https://patchwork.freedesktop.org/patch/msgid/20221117114729.7570-1-tzimmermann@suse.de --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 8dc9635f5bc1..a2a52f730989 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -807,7 +807,7 @@ extern int fb_find_mode(struct fb_var_screeninfo *var, #if defined(CONFIG_VIDEO_NOMODESET) bool fb_modesetting_disabled(const char *drvname); #else -bool fb_modesetting_disabled(const char *drvname) +static inline bool fb_modesetting_disabled(const char *drvname) { return false; } -- cgit v1.3.1 From 8b83e1a455382dc667898a525a93f4eb6716cc41 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 18 Nov 2022 14:35:34 +0100 Subject: Revert "drm/fb-helper: Schedule deferred-I/O worker after writing to framebuffer" This reverts commit 7f5cc4a3e5e4c5a38e5748defc952e45278f7a70. Needed to restore the fbdev damage worker. There have been bug reports about locking order [1] and incorrectly takens branches. [2] Restore the damage worker until these problems have been resovled. Signed-off-by: Thomas Zimmermann Acked-by: Daniel Vetter Link: https://intel-gfx-ci.01.org/tree/drm-tip/fi-kbl-8809g.html # 1 Link: https://lore.kernel.org/dri-devel/20221115115819.23088-6-tzimmermann@suse.de/T/#m06eedc0a468940e4cbbd14ca026733b639bc445a # 2 Link: https://patchwork.freedesktop.org/patch/msgid/20221118133535.9739-3-tzimmermann@suse.de --- drivers/gpu/drm/drm_fb_helper.c | 9 +-------- drivers/video/fbdev/core/fb_defio.c | 16 ---------------- include/linux/fb.h | 1 - 3 files changed, 1 insertion(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index c0e9a977a3b3..cdbf03e941b2 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -599,16 +599,9 @@ static void drm_fb_helper_add_damage_clip(struct drm_fb_helper *helper, u32 x, u static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, u32 width, u32 height) { - struct fb_info *info = helper->info; - drm_fb_helper_add_damage_clip(helper, x, y, width, height); - /* - * The current fbdev emulation only flushes buffers if a damage - * update is necessary. And we can assume that deferred I/O has - * been enabled as damage updates require deferred I/O for mmap. - */ - fb_deferred_io_schedule_flush(info); + schedule_work(&helper->damage_work); } /* diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index dec678f72a42..c730253ab85c 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -332,19 +332,3 @@ void fb_deferred_io_cleanup(struct fb_info *info) mutex_destroy(&fbdefio->lock); } EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup); - -void fb_deferred_io_schedule_flush(struct fb_info *info) -{ - struct fb_deferred_io *fbdefio = info->fbdefio; - - if (WARN_ON_ONCE(!fbdefio)) - return; /* bug in driver logic */ - - /* - * There's no requirement from callers to schedule the - * flush immediately. Rather schedule the worker with a - * delay and let a few more writes pile up. - */ - schedule_delayed_work(&info->deferred_work, fbdefio->delay); -} -EXPORT_SYMBOL_GPL(fb_deferred_io_schedule_flush); diff --git a/include/linux/fb.h b/include/linux/fb.h index a2a52f730989..64889a2b783f 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -663,7 +663,6 @@ extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); extern void fb_deferred_io_cleanup(struct fb_info *info); -extern void fb_deferred_io_schedule_flush(struct fb_info *info); extern int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasync); -- cgit v1.3.1 From b56ffa583350f605446d78cb4163114e4d1ac60c Mon Sep 17 00:00:00 2001 From: "T.J. Mercier" Date: Wed, 23 Nov 2022 19:35:18 +0000 Subject: dma-buf: A collection of typo and documentation fixes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I've been collecting these typo fixes for a while and it feels like time to send them in. Signed-off-by: T.J. Mercier Reviewed-by: Randy Dunlap Acked-by: Christian König Reviewed-by: Tommaso Merciai Link: https://patchwork.freedesktop.org/patch/msgid/20221123193519.3948105-1-tjmercier@google.com Signed-off-by: Christian König --- drivers/dma-buf/dma-buf.c | 14 +++++++------- include/linux/dma-buf.h | 4 ++-- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index b809513b03fe..6277ba3525de 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1252,7 +1252,7 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment_unlocked, DMA_BUF); * * @dmabuf: [in] buffer which is moving * - * Informs all attachmenst that they need to destroy and recreated all their + * Informs all attachments that they need to destroy and recreate all their * mappings. */ void dma_buf_move_notify(struct dma_buf *dmabuf) @@ -1270,11 +1270,11 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, DMA_BUF); /** * DOC: cpu access * - * There are mutliple reasons for supporting CPU access to a dma buffer object: + * There are multiple reasons for supporting CPU access to a dma buffer object: * * - Fallback operations in the kernel, for example when a device is connected * over USB and the kernel needs to shuffle the data around first before - * sending it away. Cache coherency is handled by braketing any transactions + * sending it away. Cache coherency is handled by bracketing any transactions * with calls to dma_buf_begin_cpu_access() and dma_buf_end_cpu_access() * access. * @@ -1301,7 +1301,7 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_move_notify, DMA_BUF); * replace ION buffers mmap support was needed. * * There is no special interfaces, userspace simply calls mmap on the dma-buf - * fd. But like for CPU access there's a need to braket the actual access, + * fd. But like for CPU access there's a need to bracket the actual access, * which is handled by the ioctl (DMA_BUF_IOCTL_SYNC). Note that * DMA_BUF_IOCTL_SYNC can fail with -EAGAIN or -EINTR, in which case it must * be restarted. @@ -1375,10 +1375,10 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, * preparations. Coherency is only guaranteed in the specified range for the * specified access direction. * @dmabuf: [in] buffer to prepare cpu access for. - * @direction: [in] length of range for cpu access. + * @direction: [in] direction of access. * * After the cpu access is complete the caller should call - * dma_buf_end_cpu_access(). Only when cpu access is braketed by both calls is + * dma_buf_end_cpu_access(). Only when cpu access is bracketed by both calls is * it guaranteed to be coherent with other DMA access. * * This function will also wait for any DMA transactions tracked through @@ -1418,7 +1418,7 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_begin_cpu_access, DMA_BUF); * actions. Coherency is only guaranteed in the specified range for the * specified access direction. * @dmabuf: [in] buffer to complete cpu access for. - * @direction: [in] length of range for cpu access. + * @direction: [in] direction of access. * * This terminates CPU access started with dma_buf_begin_cpu_access(). * diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 6fa8d4e29719..3f31baa3293f 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -356,7 +356,7 @@ struct dma_buf { */ const char *name; - /** @name_lock: Spinlock to protect name acces for read access. */ + /** @name_lock: Spinlock to protect name access for read access. */ spinlock_t name_lock; /** @@ -393,7 +393,7 @@ struct dma_buf { * anything the userspace API considers write access. * * - Drivers may just always add a write fence, since that only - * causes unecessarily synchronization, but no correctness issues. + * causes unnecessary synchronization, but no correctness issues. * * - Some drivers only expose a synchronous userspace API with no * pipelining across drivers. These do not set any fences for their -- cgit v1.3.1 From 5b6373de4351debd9fa87f1c46442b2c28d8b18e Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 19 Dec 2022 17:05:16 +0100 Subject: drm/fbdev: Remove aperture handling and FBINFO_MISC_FIRMWARE There are no users left of struct fb_info.apertures and the flag FBINFO_MISC_FIRMWARE. Remove both and the aperture-ownership code in the fbdev core. All code for aperture ownership is now located in the fbdev drivers. Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20221219160516.23436-19-tzimmermann@suse.de --- drivers/video/fbdev/core/fbmem.c | 33 --------------------------------- drivers/video/fbdev/core/fbsysfs.c | 1 - include/linux/fb.h | 22 ---------------------- 3 files changed, 56 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 3a6c8458eb8d..02217c33d152 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -13,7 +13,6 @@ #include -#include #include #include #include @@ -1653,32 +1652,6 @@ static void do_unregister_framebuffer(struct fb_info *fb_info) put_fb_info(fb_info); } -static int fb_aperture_acquire_for_platform_device(struct fb_info *fb_info) -{ - struct apertures_struct *ap = fb_info->apertures; - struct device *dev = fb_info->device; - struct platform_device *pdev; - unsigned int i; - int ret; - - if (!ap) - return 0; - - if (!dev_is_platform(dev)) - return 0; - - pdev = to_platform_device(dev); - - for (ret = 0, i = 0; i < ap->count; ++i) { - ret = devm_aperture_acquire_for_platform_device(pdev, ap->ranges[i].base, - ap->ranges[i].size); - if (ret) - break; - } - - return ret; -} - /** * register_framebuffer - registers a frame buffer device * @fb_info: frame buffer info structure @@ -1693,12 +1666,6 @@ register_framebuffer(struct fb_info *fb_info) { int ret; - if (fb_info->flags & FBINFO_MISC_FIRMWARE) { - ret = fb_aperture_acquire_for_platform_device(fb_info); - if (ret) - return ret; - } - mutex_lock(®istration_lock); ret = do_register_framebuffer(fb_info); mutex_unlock(®istration_lock); diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index 4d7f63892dcc..0c33c4adcd79 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -88,7 +88,6 @@ void framebuffer_release(struct fb_info *info) mutex_destroy(&info->bl_curve_mutex); #endif - kfree(info->apertures); kfree(info); } EXPORT_SYMBOL(framebuffer_release); diff --git a/include/linux/fb.h b/include/linux/fb.h index 96b96323e9cb..30183fd259ae 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -423,8 +423,6 @@ struct fb_tile_ops { */ #define FBINFO_MISC_ALWAYS_SETPAR 0x40000 -/* where the fb is a firmware driver, and can be replaced with a proper one */ -#define FBINFO_MISC_FIRMWARE 0x80000 /* * Host and GPU endianness differ. */ @@ -499,30 +497,10 @@ struct fb_info { void *fbcon_par; /* fbcon use-only private area */ /* From here on everything is device dependent */ void *par; - /* we need the PCI or similar aperture base/size not - smem_start/size as smem_start may just be an object - allocated inside the aperture so may not actually overlap */ - struct apertures_struct { - unsigned int count; - struct aperture { - resource_size_t base; - resource_size_t size; - } ranges[0]; - } *apertures; bool skip_vt_switch; /* no VT switch on suspend/resume required */ }; -static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { - struct apertures_struct *a; - - a = kzalloc(struct_size(a, ranges, max_num), GFP_KERNEL); - if (!a) - return NULL; - a->count = max_num; - return a; -} - #define FBINFO_FLAG_DEFAULT FBINFO_DEFAULT /* This will go away -- cgit v1.3.1 From 8681e3663411ee6b64dd0714b23f5c86f64f7533 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 20 Jan 2023 18:31:02 +0100 Subject: drm/simpledrm: Support the XB24/AB24 format Add XB24 and AB24 to the list of supported formats. The format helpers support conversion to these formats and they are documented in the simple-framebuffer device tree bindings. Reviewed-by: Thomas Zimmermann Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20230120173103.4002342-8-thierry.reding@gmail.com --- include/linux/platform_data/simplefb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h index 27ea99af6e1d..4f94d52ac99f 100644 --- a/include/linux/platform_data/simplefb.h +++ b/include/linux/platform_data/simplefb.h @@ -22,6 +22,7 @@ { "r8g8b8", 24, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_RGB888 }, \ { "x8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_XRGB8888 }, \ { "a8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {24, 8}, DRM_FORMAT_ARGB8888 }, \ + { "x8b8g8r8", 32, {0, 8}, {8, 8}, {16, 8}, {0, 0}, DRM_FORMAT_XBGR8888 }, \ { "a8b8g8r8", 32, {0, 8}, {8, 8}, {16, 8}, {24, 8}, DRM_FORMAT_ABGR8888 }, \ { "x2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {0, 0}, DRM_FORMAT_XRGB2101010 }, \ { "a2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {30, 2}, DRM_FORMAT_ARGB2101010 }, \ -- cgit v1.3.1 From 998101f2a78cf506022f2094461105cb3d00e19f Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Sat, 21 Jan 2023 20:24:16 +0100 Subject: fbdev: Remove unused struct fb_deferred_io .first_io field This optional callback was added in the commit 1f45f9dbb392 ("fb_defio: add first_io callback") but it was never used by a driver. Let's remove it since it's unlikely that will be used after a decade that was added. Signed-off-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230121192418.2814955-2-javierm@redhat.com --- drivers/video/fbdev/core/fb_defio.c | 4 ---- include/linux/fb.h | 1 - 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index c730253ab85c..1b680742b7f3 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -157,10 +157,6 @@ static vm_fault_t fb_deferred_io_track_page(struct fb_info *info, unsigned long /* protect against the workqueue changing the page list */ mutex_lock(&fbdefio->lock); - /* first write in this cycle, notify the driver */ - if (fbdefio->first_io && list_empty(&fbdefio->pagereflist)) - fbdefio->first_io(info); - pageref = fb_deferred_io_pageref_get(info, offset, page); if (WARN_ON_ONCE(!pageref)) { ret = VM_FAULT_OOM; diff --git a/include/linux/fb.h b/include/linux/fb.h index 30183fd259ae..daf336385613 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -215,7 +215,6 @@ struct fb_deferred_io { struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ - void (*first_io)(struct fb_info *info); void (*deferred_io)(struct fb_info *info, struct list_head *pagelist); }; #endif -- cgit v1.3.1 From c24973ed795fec5c12d8a822a0de99a4b7bab394 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 19 Jan 2023 15:09:19 +0200 Subject: gpu: host1x: Implement job tracking using DMA fences In anticipation of removal of the intr API, implement job tracking using DMA fences instead. The main two things about this are making cdma_update schedule the work since fence completion can now be called from interrupt context, and some complication in ensuring the callback is not running when we free the fence. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/host1x/cdma.c | 14 ++++++++--- drivers/gpu/host1x/cdma.h | 2 ++ drivers/gpu/host1x/hw/channel_hw.c | 48 +++++++++++++++++++++----------------- drivers/gpu/host1x/job.c | 12 +++++++--- include/linux/host1x.h | 6 +++-- 5 files changed, 53 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c index 103fda055394..bc821b0ed908 100644 --- a/drivers/gpu/host1x/cdma.c +++ b/drivers/gpu/host1x/cdma.c @@ -490,6 +490,15 @@ resume: host1x_hw_cdma_resume(host1x, cdma, restart_addr); } +static void cdma_update_work(struct work_struct *work) +{ + struct host1x_cdma *cdma = container_of(work, struct host1x_cdma, update_work); + + mutex_lock(&cdma->lock); + update_cdma_locked(cdma); + mutex_unlock(&cdma->lock); +} + /* * Create a cdma */ @@ -499,6 +508,7 @@ int host1x_cdma_init(struct host1x_cdma *cdma) mutex_init(&cdma->lock); init_completion(&cdma->complete); + INIT_WORK(&cdma->update_work, cdma_update_work); INIT_LIST_HEAD(&cdma->sync_queue); @@ -679,7 +689,5 @@ void host1x_cdma_end(struct host1x_cdma *cdma, */ void host1x_cdma_update(struct host1x_cdma *cdma) { - mutex_lock(&cdma->lock); - update_cdma_locked(cdma); - mutex_unlock(&cdma->lock); + schedule_work(&cdma->update_work); } diff --git a/drivers/gpu/host1x/cdma.h b/drivers/gpu/host1x/cdma.h index 12c4327c4df0..7fd8168af4f9 100644 --- a/drivers/gpu/host1x/cdma.h +++ b/drivers/gpu/host1x/cdma.h @@ -11,6 +11,7 @@ #include #include #include +#include struct host1x_syncpt; struct host1x_userctx_timeout; @@ -69,6 +70,7 @@ struct host1x_cdma { struct buffer_timeout timeout; /* channel's timeout state/wq */ bool running; bool torndown; + struct work_struct update_work; }; #define cdma_to_channel(cdma) container_of(cdma, struct host1x_channel, cdma) diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 732abe0750ff..8a3119fc5a77 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -278,6 +278,14 @@ static void channel_program_cdma(struct host1x_job *job) #endif } +static void job_complete_callback(struct dma_fence *fence, struct dma_fence_cb *cb) +{ + struct host1x_job *job = container_of(cb, struct host1x_job, fence_cb); + + /* Schedules CDMA update. */ + host1x_cdma_update(&job->channel->cdma); +} + static int channel_submit(struct host1x_job *job) { struct host1x_channel *ch = job->channel; @@ -285,7 +293,6 @@ static int channel_submit(struct host1x_job *job) u32 prev_max = 0; u32 syncval; int err; - struct host1x_waitlist *completed_waiter = NULL; struct host1x *host = dev_get_drvdata(ch->dev->parent); trace_host1x_channel_submit(dev_name(ch->dev), @@ -298,14 +305,7 @@ static int channel_submit(struct host1x_job *job) /* get submit lock */ err = mutex_lock_interruptible(&ch->submitlock); if (err) - goto error; - - completed_waiter = kzalloc(sizeof(*completed_waiter), GFP_KERNEL); - if (!completed_waiter) { - mutex_unlock(&ch->submitlock); - err = -ENOMEM; - goto error; - } + return err; host1x_channel_set_streamid(ch); host1x_enable_gather_filter(ch); @@ -315,31 +315,37 @@ static int channel_submit(struct host1x_job *job) err = host1x_cdma_begin(&ch->cdma, job); if (err) { mutex_unlock(&ch->submitlock); - goto error; + return err; } channel_program_cdma(job); syncval = host1x_syncpt_read_max(sp); + /* + * Create fence before submitting job to HW to avoid job completing + * before the fence is set up. + */ + job->fence = host1x_fence_create(sp, syncval); + if (WARN(IS_ERR(job->fence), "Failed to create submit complete fence")) { + job->fence = NULL; + } else { + err = dma_fence_add_callback(job->fence, &job->fence_cb, + job_complete_callback); + } + /* end CDMA submit & stash pinned hMems into sync queue */ host1x_cdma_end(&ch->cdma, job); trace_host1x_channel_submitted(dev_name(ch->dev), prev_max, syncval); - /* schedule a submit complete interrupt */ - err = host1x_intr_add_action(host, sp, syncval, - HOST1X_INTR_ACTION_SUBMIT_COMPLETE, ch, - completed_waiter, &job->waiter); - completed_waiter = NULL; - WARN(err, "Failed to set submit complete interrupt"); - mutex_unlock(&ch->submitlock); - return 0; + if (err == -ENOENT) + host1x_cdma_update(&ch->cdma); + else + WARN(err, "Failed to set submit complete interrupt"); -error: - kfree(completed_waiter); - return err; + return 0; } static int host1x_channel_init(struct host1x_channel *ch, struct host1x *dev, diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index b2761aa03b95..3ed49e1fd933 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -88,9 +88,15 @@ static void job_free(struct kref *ref) if (job->release) job->release(job); - if (job->waiter) - host1x_intr_put_ref(job->syncpt->host, job->syncpt->id, - job->waiter, false); + if (job->fence) { + /* + * remove_callback is atomic w.r.t. fence signaling, so + * after the call returns, we know that the callback is not + * in execution, and the fence can be safely freed. + */ + dma_fence_remove_callback(job->fence, &job->fence_cb); + dma_fence_put(job->fence); + } if (job->syncpt) host1x_syncpt_put(job->syncpt); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index dc55d9d3b94f..db6cf6f34361 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -8,6 +8,7 @@ #include #include +#include #include #include @@ -288,8 +289,9 @@ struct host1x_job { u32 syncpt_incrs; u32 syncpt_end; - /* Completion waiter ref */ - void *waiter; + /* Completion fence for job tracking */ + struct dma_fence *fence; + struct dma_fence_cb fence_cb; /* Maximum time to wait for this job */ unsigned int timeout; -- cgit v1.3.1 From d5179020f5ce44fd449790a9c12ef6c1a90a2ca7 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 19 Jan 2023 15:09:21 +0200 Subject: gpu: host1x: External timeout/cancellation for fences Currently all fences have a 30 second timeout to ensure they are cleaned up if the fence never completes otherwise. However, this one size fits all solution doesn't actually fit in every case, such as syncpoint waiting where we want to be able to have timeouts longer than 30 seconds. As such, we want to be able to give control over fence cancellation to the caller (and maybe eventually get rid of the internal timeout altogether). Here we add this cancellation mechanism by essentially adding a function for entering the timeout path by function call, and changing the syncpoint wait function to use it. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/submit.c | 2 +- drivers/gpu/host1x/fence.c | 40 +++++++++++++++++++++++++------------- drivers/gpu/host1x/fence.h | 1 + drivers/gpu/host1x/hw/channel_hw.c | 2 +- drivers/gpu/host1x/syncpt.c | 4 +++- include/linux/host1x.h | 4 +++- 6 files changed, 36 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c index 066f88564169..f4688fcafe93 100644 --- a/drivers/gpu/drm/tegra/submit.c +++ b/drivers/gpu/drm/tegra/submit.c @@ -654,7 +654,7 @@ int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data, args->syncpt.value = job->syncpt_end; if (syncobj) { - struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end); + struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end, true); if (IS_ERR(fence)) { err = PTR_ERR(fence); SUBMIT_ERR(context, "failed to create postfence: %d", err); diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c index df5b56692d2c..139ad1afd935 100644 --- a/drivers/gpu/host1x/fence.c +++ b/drivers/gpu/host1x/fence.c @@ -37,8 +37,7 @@ static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f) if (host1x_syncpt_is_expired(sf->sp, sf->threshold)) return false; - /* One reference for interrupt path, one for timeout path. */ - dma_fence_get(f); + /* Reference for interrupt path. */ dma_fence_get(f); /* @@ -46,11 +45,15 @@ static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f) * reference to any fences for which 'enable_signaling' has been * called (and that have not been signalled). * - * We cannot (for now) normally guarantee that all fences get signalled. - * As such, setup a timeout, so that long-lasting fences will get - * reaped eventually. + * We cannot currently always guarantee that all fences get signalled + * or cancelled. As such, for such situations, set up a timeout, so + * that long-lasting fences will get reaped eventually. */ - schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000)); + if (sf->timeout) { + /* Reference for timeout path. */ + dma_fence_get(f); + schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000)); + } host1x_intr_add_fence_locked(sf->sp->host, sf); @@ -80,7 +83,7 @@ void host1x_fence_signal(struct host1x_syncpt_fence *f) return; } - if (cancel_delayed_work(&f->timeout_work)) { + if (f->timeout && cancel_delayed_work(&f->timeout_work)) { /* * We know that the timeout path will not be entered. * Safe to drop the timeout path's reference now. @@ -99,8 +102,9 @@ static void do_fence_timeout(struct work_struct *work) container_of(dwork, struct host1x_syncpt_fence, timeout_work); if (atomic_xchg(&f->signaling, 1)) { - /* Already on interrupt path, drop timeout path reference. */ - dma_fence_put(&f->base); + /* Already on interrupt path, drop timeout path reference if any. */ + if (f->timeout) + dma_fence_put(&f->base); return; } @@ -114,12 +118,12 @@ static void do_fence_timeout(struct work_struct *work) dma_fence_set_error(&f->base, -ETIMEDOUT); dma_fence_signal(&f->base); - - /* Drop timeout path reference. */ - dma_fence_put(&f->base); + if (f->timeout) + dma_fence_put(&f->base); } -struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) +struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold, + bool timeout) { struct host1x_syncpt_fence *fence; @@ -129,6 +133,7 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) fence->sp = sp; fence->threshold = threshold; + fence->timeout = timeout; dma_fence_init(&fence->base, &host1x_syncpt_fence_ops, &sp->fences.lock, dma_fence_context_alloc(1), 0); @@ -138,3 +143,12 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) return &fence->base; } EXPORT_SYMBOL(host1x_fence_create); + +void host1x_fence_cancel(struct dma_fence *f) +{ + struct host1x_syncpt_fence *sf = to_host1x_fence(f); + + schedule_delayed_work(&sf->timeout_work, 0); + flush_delayed_work(&sf->timeout_work); +} +EXPORT_SYMBOL(host1x_fence_cancel); diff --git a/drivers/gpu/host1x/fence.h b/drivers/gpu/host1x/fence.h index 4352d046f92c..f3c644c73cad 100644 --- a/drivers/gpu/host1x/fence.h +++ b/drivers/gpu/host1x/fence.h @@ -13,6 +13,7 @@ struct host1x_syncpt_fence { struct host1x_syncpt *sp; u32 threshold; + bool timeout; struct delayed_work timeout_work; diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 8a3119fc5a77..0a528573a792 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -325,7 +325,7 @@ static int channel_submit(struct host1x_job *job) * Create fence before submitting job to HW to avoid job completing * before the fence is set up. */ - job->fence = host1x_fence_create(sp, syncval); + job->fence = host1x_fence_create(sp, syncval, true); if (WARN(IS_ERR(job->fence), "Failed to create submit complete fence")) { job->fence = NULL; } else { diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c index 75f58ec2ae23..2d2007760eac 100644 --- a/drivers/gpu/host1x/syncpt.c +++ b/drivers/gpu/host1x/syncpt.c @@ -236,11 +236,13 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout, else if (timeout == 0) return -EAGAIN; - fence = host1x_fence_create(sp, thresh); + fence = host1x_fence_create(sp, thresh, false); if (IS_ERR(fence)) return PTR_ERR(fence); wait_err = dma_fence_wait_timeout(fence, true, timeout); + if (wait_err == 0) + host1x_fence_cancel(fence); dma_fence_put(fence); if (value) diff --git a/include/linux/host1x.h b/include/linux/host1x.h index db6cf6f34361..9a9de4b97a25 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -222,7 +222,9 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); void host1x_syncpt_release_vblank_reservation(struct host1x_client *client, u32 syncpt_id); -struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold); +struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold, + bool timeout); +void host1x_fence_cancel(struct dma_fence *fence); /* * host1x channel -- cgit v1.3.1 From dbd7a2a941b8cbf9e5f79a777ed9fe0090eebb61 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 23 Jan 2023 07:37:45 -0800 Subject: PM / devfreq: Fix build issues with devfreq disabled The existing no-op shims for when PM_DEVFREQ (or an individual governor) only do half the job. The governor specific config/tuning structs need to be available to avoid compile errors in drivers using devfreq. Fixes: 6563f60f14cb ("drm/msm/gpu: Add devfreq tuning debugfs") Signed-off-by: Rob Clark Acked-by: MyungJoo Ham Acked-by: Chanwoo Choi Patchwork: https://patchwork.freedesktop.org/patch/519801/ Link: https://lore.kernel.org/r/20230123153745.3185032-1-robdclark@gmail.com --- include/linux/devfreq.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 4dc7cda4fd46..7fd704bb8f3d 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -273,8 +273,8 @@ void devm_devfreq_unregister_notifier(struct device *dev, struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node); struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, const char *phandle_name, int index); +#endif /* CONFIG_PM_DEVFREQ */ -#if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - ``void *data`` fed to struct devfreq * and devfreq_add_device @@ -292,9 +292,7 @@ struct devfreq_simple_ondemand_data { unsigned int upthreshold; unsigned int downdifferential; }; -#endif -#if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE) enum devfreq_parent_dev_type { DEVFREQ_PARENT_DEV, CPUFREQ_PARENT_DEV, @@ -337,9 +335,8 @@ struct devfreq_passive_data { struct notifier_block nb; struct list_head cpu_data_list; }; -#endif -#else /* !CONFIG_PM_DEVFREQ */ +#if !defined(CONFIG_PM_DEVFREQ) static inline struct devfreq *devfreq_add_device(struct device *dev, struct devfreq_dev_profile *profile, const char *governor_name, -- cgit v1.3.1