Merge tag 'drm-misc-fixes-2026-06-05' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-fixes

Short summary of fixes pull:

dumb-buffer:
- remove strict limits on buffer geometry

ethosu:
- reject unsupported NPU_OP_RESIZE
- fix index of IFM region
- fix weight index
- fix overflows in DMA-size calculations
- reject DMA commands with uninitialized length
- fix OOB write in ethosu_gem_cmdstream_copy_and_validate

imx:
- fix kernel-doc warnings

ivpu:
- add overflow checks in firmware handling and get_info_ioctl

v3d:
- wait for pending L2T flush before cleaning caches
- fix leak of vaddr
- skip CSD when it has zeroed workgroups
- fix ref counting in performance monitoring

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patch.msgid.link/20260605072602.GA268798@linux.fritz.box

9 files changed, 98 insertions, 24 deletions

diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c
index 7994e7073903..3401883e207f 100644
--- a/drivers/accel/ethosu/ethosu_gem.c
+++ b/drivers/accel/ethosu/ethosu_gem.c
@@ -2,6 +2,7 @@
 /* Copyright 2025 Arm, Ltd. */
 
 #include <linux/err.h>
+#include <linux/overflow.h>
 #include <linux/slab.h>
 
 #include <drm/ethosu_accel.h>
@@ -163,17 +164,30 @@ static u64 dma_length(struct ethosu_validated_cmdstream_info *info,
 	s8 mode = dma_st->mode;
 	u64 len = dma->len;
 
+	if (len == U64_MAX)
+		return U64_MAX;
+
 	if (mode >= 1) {
+		if (dma->stride[0] < 0 && (u64)(-dma->stride[0]) > len)
+			return U64_MAX;
 		len += dma->stride[0];
-		len *= dma_st->size0;
+		if (check_mul_overflow(len, (u64)dma_st->size0, &len))
+			return U64_MAX;
 	}
 	if (mode == 2) {
+		if (dma->stride[1] < 0 && (u64)(-dma->stride[1]) > len)
+			return U64_MAX;
 		len += dma->stride[1];
-		len *= dma_st->size1;
+		if (check_mul_overflow(len, (u64)dma_st->size1, &len))
+			return U64_MAX;
+	}
+	if (dma->region >= 0) {
+		u64 end;
+
+		if (check_add_overflow(len, dma->offset, &end))
+			return U64_MAX;
+		info->region_size[dma->region] = max(info->region_size[dma->region], end);
 	}
-	if (dma->region >= 0)
-		info->region_size[dma->region] = max(info->region_size[dma->region],
-						     len + dma->offset);
 
 	return len;
 }
@@ -387,6 +401,8 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev,
 				return -EFAULT;
 
 			i++;
+			if (i >= size / 4)
+				return -EINVAL;
 			bocmds[i] = cmds[1];
 			addr = cmd_to_addr(cmds);
 		}
@@ -395,6 +411,8 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev,
 		case NPU_OP_DMA_START:
 			srclen = dma_length(info, &st.dma, &st.dma.src);
 			dstlen = dma_length(info, &st.dma, &st.dma.dst);
+			if (srclen == U64_MAX || dstlen == U64_MAX)
+				return -EINVAL;
 
 			if (st.dma.dst.region >= 0)
 				info->output_region[st.dma.dst.region] = true;
@@ -431,8 +449,7 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev,
 				return ret;
 			break;
 		case NPU_OP_RESIZE: // U85 only
-			WARN_ON(1); // TODO
-			break;
+			return -EINVAL;
 		case NPU_SET_KERNEL_WIDTH_M1:
 			st.ifm.width = param;
 			break;
@@ -464,7 +481,7 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev,
 			st.ifm.broadcast = param;
 			break;
 		case NPU_SET_IFM_REGION:
-			st.ifm.region = param & 0x7f;
+			st.ifm.region = param & 0x7;
 			break;
 		case NPU_SET_IFM_WIDTH0_M1:
 			st.ifm.width0 = param;
@@ -599,7 +616,7 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev,
 			if (ethosu_is_u65(edev))
 				st.scale[1].length = cmds[1];
 			else
-				st.weight[1].length = cmds[1];
+				st.weight[2].length = cmds[1];
 			break;
 		case NPU_SET_WEIGHT3_BASE:
 			st.weight[3].base = addr;
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 107f8ad31050..33c50779c06b 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -259,6 +259,22 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 		return -EINVAL;
 	}
 
+	if (!PAGE_ALIGNED(runtime_addr)) {
+		ivpu_err(vdev, "Runtime address 0x%llx not page aligned\n", runtime_addr);
+		return -EINVAL;
+	}
+
+	if (!PAGE_ALIGNED(runtime_size)) {
+		ivpu_err(vdev, "Runtime size %llu not page aligned\n", runtime_size);
+		return -EINVAL;
+	}
+
+	if (runtime_size < image_size) {
+		ivpu_err(vdev, "Runtime size too small: %llu, image size: %llu\n",
+			 runtime_size, image_size);
+		return -EINVAL;
+	}
+
 	if (!ivpu_is_within_range(image_load_addr, image_size, &vdev->hw->ranges.runtime)) {
 		ivpu_err(vdev, "Invalid firmware load address: 0x%llx and size %llu\n",
 			 image_load_addr, image_size);
diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c
index 337c906b0210..275baf844b56 100644
--- a/drivers/accel/ivpu/ivpu_fw_log.c
+++ b/drivers/accel/ivpu/ivpu_fw_log.c
@@ -98,6 +98,11 @@ static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const cha
 	u32 log_start = only_new_msgs ? READ_ONCE(log->read_index) : 0;
 	u32 log_end = READ_ONCE(log->write_index);
 
+	if (log_start >= data_size)
+		log_start = 0;
+	if (log_end > data_size)
+		log_end = data_size;
+
 	if (log->wrap_count == log->read_wrap_count) {
 		if (log_end <= log_start) {
 			drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name);
diff --git a/drivers/accel/ivpu/ivpu_ms.c b/drivers/accel/ivpu/ivpu_ms.c
index be43851f5f32..cd176e77b9a0 100644
--- a/drivers/accel/ivpu/ivpu_ms.c
+++ b/drivers/accel/ivpu/ivpu_ms.c
@@ -291,6 +291,13 @@ int ivpu_ms_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *
 	if (ret)
 		goto unlock;
 
+	if (info_size > ivpu_bo_size(bo)) {
+		ivpu_warn_ratelimited(vdev, "MS info overflow: %#llx > %#zx\n",
+				      info_size, ivpu_bo_size(bo));
+		ret = -EOVERFLOW;
+		goto unlock;
+	}
+
 	if (args->buffer_size < info_size) {
 		ret = -ENOSPC;
 		goto unlock;
diff --git a/drivers/gpu/drm/drm_dumb_buffers.c b/drivers/gpu/drm/drm_dumb_buffers.c
index cc99681a9ed0..2156dbe601c9 100644
--- a/drivers/gpu/drm/drm_dumb_buffers.c
+++ b/drivers/gpu/drm/drm_dumb_buffers.c
@@ -202,13 +202,6 @@ int drm_mode_create_dumb(struct drm_device *dev,
 	if (!args->width || !args->height || !args->bpp)
 		return -EINVAL;
 
-	/* Reject unreasonable inputs early.  Dumb buffers are for software
-	 * rendering; nothing legitimate needs more than 8192x8192 at 32bpp.
-	 * This prevents overflows in downstream alignment helpers.
-	 */
-	if (args->width >= 8192 || args->height >= 8192 || args->bpp > 32)
-		return -EINVAL;
-
 	/* overflow checks for 32bit size calculations */
 	if (args->bpp > U32_MAX - 8)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/imx/dcss/dcss-scaler.c b/drivers/gpu/drm/imx/dcss/dcss-scaler.c
index 32c3f46b21da..5c7f8d952ec1 100644
--- a/drivers/gpu/drm/imx/dcss/dcss-scaler.c
+++ b/drivers/gpu/drm/imx/dcss/dcss-scaler.c
@@ -166,6 +166,7 @@ static int exp_approx_q(int x)
  * dcss_scaler_gaussian_filter() - Generate gaussian prototype filter.
  * @fc_q: fixed-point cutoff frequency normalized to range [0, 1]
  * @use_5_taps: indicates whether to use 5 taps or 7 taps
+ * @phase0_identity: whether to override phase 0 coefficients with identity filter
  * @coef: output filter coefficients
  */
 static void dcss_scaler_gaussian_filter(int fc_q, bool use_5_taps,
@@ -262,7 +263,9 @@ static void dcss_scaler_nearest_neighbor_filter(bool use_5_taps,
  * @src_length: length of input
  * @dst_length: length of output
  * @use_5_taps: 0 for 7 taps per phase, 1 for 5 taps
+ * @phase0_identity: whether to override phase 0 coefficients with identity filter
  * @coef: output coefficients
+ * @nn_interpolation: whether to use nearest neighbor instead of gaussian filter
  */
 static void dcss_scaler_filter_design(int src_length, int dst_length,
 				      bool use_5_taps, bool phase0_identity,
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 75d9eccd7966..dd7da419702f 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -213,6 +213,14 @@ v3d_clean_caches(struct v3d_dev *v3d)
 
 	trace_v3d_cache_clean_begin(dev);
 
+	/* GFXH-1897: Ensure pending flushes complete before writing L2TCACTL */
+	if (v3d->ver < V3D_GEN_71) {
+		if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+			       V3D_L2TCACTL_L2TFLS), 100)) {
+			drm_err(dev, "Timeout waiting for L2T clean\n");
+		}
+	}
+
 	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL, V3D_L2TCACTL_TMUWCF);
 	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
 		       V3D_L2TCACTL_TMUWCF), 100)) {
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
index 8e0249580bba..ecfd446ff75f 100644
--- a/drivers/gpu/drm/v3d/v3d_perfmon.c
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -309,8 +309,11 @@ static void v3d_perfmon_delete(struct v3d_file_priv *v3d_priv,
 	if (perfmon == v3d->active_perfmon)
 		v3d_perfmon_stop(v3d, perfmon, false);
 
-	/* If the global perfmon is being destroyed, set it to NULL */
-	cmpxchg(&v3d->global_perfmon, perfmon, NULL);
+	/* If the global perfmon is being destroyed, clean it and release
+	 * the reference stashed in v3d_perfmon_set_global_ioctl().
+	 */
+	if (cmpxchg(&v3d->global_perfmon, perfmon, NULL) == perfmon)
+		v3d_perfmon_put(perfmon);
 
 	v3d_perfmon_put(perfmon);
 }
@@ -461,16 +464,27 @@ int v3d_perfmon_set_global_ioctl(struct drm_device *dev, void *data,
 
 	/* If the request is to clear the global performance monitor */
 	if (req->flags & DRM_V3D_PERFMON_CLEAR_GLOBAL) {
-		if (!v3d->global_perfmon)
+		struct v3d_perfmon *old;
+
+		/* DRM_V3D_PERFMON_CLEAR_GLOBAL doesn't check if
+		 * v3d->global_perfmon == perfmon. Therefore, there
+		 * is no need to keep perfmon's reference.
+		 */
+		v3d_perfmon_put(perfmon);
+
+		old = xchg(&v3d->global_perfmon, NULL);
+		if (!old)
 			return -EINVAL;
 
-		xchg(&v3d->global_perfmon, NULL);
+		v3d_perfmon_put(old);
 
 		return 0;
 	}
 
-	if (cmpxchg(&v3d->global_perfmon, NULL, perfmon))
+	if (cmpxchg(&v3d->global_perfmon, NULL, perfmon)) {
+		v3d_perfmon_put(perfmon);
 		return -EBUSY;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 94bf628dc91c..8a635a9ec046 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -352,6 +352,16 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 		return NULL;
 	}
 
+	/* The HW interprets a workgroup size of 0 as 65536; however, the
+	 * user-space driver exposes a maximum of 65535. Therefore, a 0 in
+	 * any dimension means that we have no workgroups and the compute
+	 * shader should not be dispatched.
+	 */
+	if (!V3D_GET_FIELD(job->args.cfg[0], V3D_CSD_QUEUED_CFG0_NUM_WGS_X) ||
+	    !V3D_GET_FIELD(job->args.cfg[1], V3D_CSD_QUEUED_CFG1_NUM_WGS_Y) ||
+	    !V3D_GET_FIELD(job->args.cfg[2], V3D_CSD_QUEUED_CFG2_NUM_WGS_Z))
+		return NULL;
+
 	v3d->queue[V3D_CSD].active_job = &job->base;
 
 	v3d_invalidate_caches(v3d);
@@ -402,13 +412,13 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 
 	wg_counts = (uint32_t *)(bo->vaddr + indirect_csd->offset);
 
-	if (wg_counts[0] == 0 || wg_counts[1] == 0 || wg_counts[2] == 0)
-		return;
-
 	args->cfg[0] = wg_counts[0] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[1] = wg_counts[1] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[2] = wg_counts[2] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 
+	if (wg_counts[0] == 0 || wg_counts[1] == 0 || wg_counts[2] == 0)
+		goto unmap_bo;
+
 	num_batches = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
 		      (wg_counts[0] * wg_counts[1] * wg_counts[2]);
 
@@ -428,6 +438,7 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 		}
 	}
 
+unmap_bo:
 	v3d_put_bo_vaddr(indirect);
 	v3d_put_bo_vaddr(bo);
 }