From be0e82b8e0c96649b8bc77a99ab0d185243b7659 Mon Sep 17 00:00:00 2001 From: Alexandre MINETTE Date: Wed, 10 Jun 2026 09:49:17 +0200 Subject: [PATCH] drm/msm/a3xx: Drain VBIF before GPU suspend A3xx hangs after every runtime suspend on the Samsung Galaxy S4 GT-I9505. Even simple GPU workloads, such as drawing a single triangle, hang reliably once the GPU has been suspended by runtime PM. The generic MSM GPU suspend path disables clocks/power, but A3xx also needs to ensure that pending VBIF transactions are drained before that happens. Add an A3xx-specific pm_suspend callback. Wait for the GPU to become idle, halt all VBIF XIN clients, wait for the corresponding acknowledgment, and only then enter the generic MSM GPU suspend path. This fixes reliable A3xx GPU hangs observed after runtime PM on the Samsung Galaxy S4 GT-I9505, codename jflte. The failure is reported as: mdp4 5100000.display-controller: [drm:hangcheck_handler] *ERROR* 3.2.0.2: hangcheck detected gpu lockup rb 0! mdp4 5100000.display-controller: [drm:hangcheck_handler] *ERROR* 3.2.0.2: completed fence: 4294967041 mdp4 5100000.display-controller: [drm:hangcheck_handler] *ERROR* 3.2.0.2: submitted fence: 4294967049 mdp4 5100000.display-controller: [drm:recover_worker] *ERROR* 3.2.0.2: hangcheck recover! Link: https://github.com/freedreno-zz/freedreno/issues/12 Signed-off-by: Alexandre MINETTE Patchwork: https://patchwork.freedesktop.org/patch/731919/ Message-ID: <20260610-mainline-fix-a3xx-gpu-hang-sending-v1-1-9282182840b5@alex-min.fr> Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/adreno/a3xx_gpu.c | 36 ++++++++++++++++++- drivers/gpu/drm/msm/registers/adreno/a3xx.xml | 2 ++ 2 files changed, 37 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index c17e9777beae..0259e60b8011 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -25,6 +25,8 @@ extern bool hang_debug; +#define A3XX_VBIF_XIN_HALT_CTRL0_MASK GENMASK(5, 0) + static void a3xx_dump(struct msm_gpu *gpu); static bool a3xx_idle(struct msm_gpu *gpu); @@ -496,6 +498,38 @@ static u64 a3xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate) return busy_cycles; } +static int a3xx_vbif_halt(struct msm_gpu *gpu) +{ + u32 ack; + int ret; + + gpu_write(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL0, + A3XX_VBIF_XIN_HALT_CTRL0_MASK); + ret = spin_until(((ack = gpu_read(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL1)) & + A3XX_VBIF_XIN_HALT_CTRL0_MASK) == + A3XX_VBIF_XIN_HALT_CTRL0_MASK); + gpu_write(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL0, 0); + + if (ret) + return -EBUSY; + + return 0; +} + +static int a3xx_pm_suspend(struct msm_gpu *gpu) +{ + int ret; + + if (!a3xx_idle(gpu)) + return -EBUSY; + + ret = a3xx_vbif_halt(gpu); + if (ret) + return ret; + + return msm_gpu_pm_suspend(gpu); +} + static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { ring->memptrs->rptr = gpu_read(gpu, REG_AXXX_CP_RB_RPTR); @@ -581,7 +615,7 @@ const struct adreno_gpu_funcs a3xx_gpu_funcs = { .get_param = adreno_get_param, .set_param = adreno_set_param, .hw_init = a3xx_hw_init, - .pm_suspend = msm_gpu_pm_suspend, + .pm_suspend = a3xx_pm_suspend, .pm_resume = msm_gpu_pm_resume, .recover = a3xx_recover, .submit = a3xx_submit, diff --git a/drivers/gpu/drm/msm/registers/adreno/a3xx.xml b/drivers/gpu/drm/msm/registers/adreno/a3xx.xml index 09c9606fc3e1..21b00a17ef3e 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a3xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a3xx.xml @@ -1495,6 +1495,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> + +