6.6-stable review patch. If anyone has any objections, please let me know. ------------------ From: Maíra Canal [ Upstream commit 25a1669907512e927fab9ad4d4fb74ff57f63cd9 ] The run_job() callbacks for BIN, RENDER, TFU and CSD assign the incoming job to queue->active_job before calling v3d_fence_create(). If v3d_fence_create() fails, the callback returns NULL without clearing active_job, leaving a dangling pointer. Create a failure path in all run_job() callbacks that clears the active job before returning NULL. The BIN path takes queue->queue_lock around the clear as it races against v3d_overflow_mem_work(); RENDER, TFU and CSD paths have no concurrent reader, so the clear is lock-free. Fixes: a783a09ee76d ("drm/v3d: Refactor job management.") Reviewed-by: Tvrtko Ursulin Link: https://patch.msgid.link/20260604-v3d-sched-misc-fixes-v4-2-c068f5bf5ccf@igalia.com Signed-off-by: Maíra Canal Signed-off-by: Sasha Levin --- drivers/gpu/drm/v3d/v3d_sched.c | 60 +++++++++++++++++++-------------- 1 file changed, 34 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 1708d7cd2627a..8048910113303 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -77,15 +77,11 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job) struct v3d_bin_job *job = to_bin_job(sched_job); struct v3d_dev *v3d = job->base.v3d; struct drm_device *dev = &v3d->drm; - struct dma_fence *fence; + struct dma_fence *fence = NULL; unsigned long irqflags; - if (unlikely(job->base.base.s_fence->finished.error)) { - spin_lock_irqsave(&v3d->job_lock, irqflags); - v3d->queue[V3D_BIN].active_job = NULL; - spin_unlock_irqrestore(&v3d->job_lock, irqflags); - return NULL; - } + if (unlikely(job->base.base.s_fence->finished.error)) + goto out_clean_job; /* Lock required around bin_job update vs * v3d_overflow_mem_work(). @@ -102,7 +98,7 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job) fence = v3d_fence_create(v3d, V3D_BIN); if (IS_ERR(fence)) - return NULL; + goto out_clean_job; if (job->base.irq_fence) dma_fence_put(job->base.irq_fence); @@ -129,6 +125,12 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job) V3D_CORE_WRITE(0, V3D_CLE_CT0QEA, job->end); return fence; + +out_clean_job: + spin_lock_irqsave(&v3d->job_lock, irqflags); + v3d->queue[V3D_BIN].active_job = NULL; + spin_unlock_irqrestore(&v3d->job_lock, irqflags); + return fence; } static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job) @@ -136,12 +138,10 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job) struct v3d_render_job *job = to_render_job(sched_job); struct v3d_dev *v3d = job->base.v3d; struct drm_device *dev = &v3d->drm; - struct dma_fence *fence; + struct dma_fence *fence = NULL; - if (unlikely(job->base.base.s_fence->finished.error)) { - v3d->queue[V3D_RENDER].active_job = NULL; - return NULL; - } + if (unlikely(job->base.base.s_fence->finished.error)) + goto out_clean_job; v3d->queue[V3D_RENDER].active_job = &job->base; @@ -155,7 +155,7 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job) fence = v3d_fence_create(v3d, V3D_RENDER); if (IS_ERR(fence)) - return NULL; + goto out_clean_job; if (job->base.irq_fence) dma_fence_put(job->base.irq_fence); @@ -175,6 +175,10 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job) V3D_CORE_WRITE(0, V3D_CLE_CT1QEA, job->end); return fence; + +out_clean_job: + v3d->queue[V3D_RENDER].active_job = NULL; + return fence; } static struct dma_fence * @@ -183,18 +187,16 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job) struct v3d_tfu_job *job = to_tfu_job(sched_job); struct v3d_dev *v3d = job->base.v3d; struct drm_device *dev = &v3d->drm; - struct dma_fence *fence; + struct dma_fence *fence = NULL; - if (unlikely(job->base.base.s_fence->finished.error)) { - v3d->queue[V3D_TFU].active_job = NULL; - return NULL; - } + if (unlikely(job->base.base.s_fence->finished.error)) + goto out_clean_job; v3d->queue[V3D_TFU].active_job = &job->base; fence = v3d_fence_create(v3d, V3D_TFU); if (IS_ERR(fence)) - return NULL; + goto out_clean_job; if (job->base.irq_fence) dma_fence_put(job->base.irq_fence); @@ -218,6 +220,10 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job) V3D_WRITE(V3D_TFU_ICFG, job->args.icfg | V3D_TFU_ICFG_IOC); return fence; + +out_clean_job: + v3d->queue[V3D_TFU].active_job = NULL; + return fence; } static struct dma_fence * @@ -226,13 +232,11 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) struct v3d_csd_job *job = to_csd_job(sched_job); struct v3d_dev *v3d = job->base.v3d; struct drm_device *dev = &v3d->drm; - struct dma_fence *fence; + struct dma_fence *fence = NULL; int i; - if (unlikely(job->base.base.s_fence->finished.error)) { - v3d->queue[V3D_CSD].active_job = NULL; - return NULL; - } + if (unlikely(job->base.base.s_fence->finished.error)) + goto out_clean_job; /* The HW interprets a workgroup size of 0 as 65536; however, the * user-space driver exposes a maximum of 65535. Therefore, a 0 in @@ -250,7 +254,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) fence = v3d_fence_create(v3d, V3D_CSD); if (IS_ERR(fence)) - return NULL; + goto out_clean_job; if (job->base.irq_fence) dma_fence_put(job->base.irq_fence); @@ -266,6 +270,10 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0, job->args.cfg[0]); return fence; + +out_clean_job: + v3d->queue[V3D_CSD].active_job = NULL; + return fence; } static struct dma_fence * -- 2.53.0