Merge tag 'drm-misc-fixes-2024-02-08' of git://anongit.freedesktop.org/drm/drm-misc into drm-fixes

A null pointer dereference fix for v3d, a TTM pool initialization fix,
several fixes for nouveau around register size, DMA buffer leaks and API
consistency, a multiple fixes for ivpu around MMU setup, initialization
and firmware interactions.
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maxime Ripard <mripard@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/4wsi2i6kgkqdu7nzp4g7hxasbswnrmc5cakgf5zzvnix53u7lr@4rmp7hwblow3

drivers/accel/ivpu/ivpu_drv.c

@@ -480,8 +480,7 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
 	/* Clear any pending errors */
 	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
 
-	/* VPU 37XX does not require 10m D3hot delay */
-	if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
+	/* NPU does not require 10m D3hot delay */
 	pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);

drivers/accel/ivpu/ivpu_fw.c

@@ -222,7 +222,6 @@ ivpu_fw_init_wa(struct ivpu_device *vdev)
 	const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
 
 	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
-	    (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
 	    (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
 		vdev->wa.disable_d0i3_msg = true;
 

drivers/accel/ivpu/ivpu_hw_37xx.c

@@ -525,7 +525,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+	val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);

drivers/accel/ivpu/ivpu_hw_40xx.c

@@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
 	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
@@ -704,7 +704,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 {
 	struct ivpu_hw_info *hw = vdev->hw;
 	u32 tile_disable;
-	u32 tile_enable;
 	u32 fuse;
 
 	fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE);
@@ -725,10 +724,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 	else
 		ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM);
 
-	tile_enable = (~tile_disable) & TILE_MAX_MASK;
-
-	hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku);
-	hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku);
 	hw->tile_fuse = tile_disable;
 	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
 

drivers/accel/ivpu/ivpu_job.c

@@ -294,7 +294,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 		return -ENOENT;
 
 	if (job->file_priv->has_mmu_faults)
-		job_status = VPU_JSM_STATUS_ABORTED;
+		job_status = DRM_IVPU_JOB_STATUS_ABORTED;
 
 	job->bos[CMD_BUF_IDX]->job_status = job_status;
 	dma_fence_signal(job->done_fence);
@@ -315,7 +315,7 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	unsigned long id;
 
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
-		ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED);
+		ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
 }
 
 static int ivpu_job_submit(struct ivpu_job *job)

drivers/accel/ivpu/ivpu_mmu.c

@@ -72,10 +72,10 @@
 
 #define IVPU_MMU_Q_COUNT_LOG2		4 /* 16 entries */
 #define IVPU_MMU_Q_COUNT		((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
-#define IVPU_MMU_Q_WRAP_BIT		(IVPU_MMU_Q_COUNT << 1)
-#define IVPU_MMU_Q_WRAP_MASK		(IVPU_MMU_Q_WRAP_BIT - 1)
+#define IVPU_MMU_Q_WRAP_MASK            GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0)
 #define IVPU_MMU_Q_IDX_MASK             (IVPU_MMU_Q_COUNT - 1)
 #define IVPU_MMU_Q_IDX(val)		((val) & IVPU_MMU_Q_IDX_MASK)
+#define IVPU_MMU_Q_WRP(val)             ((val) & IVPU_MMU_Q_COUNT)
 
 #define IVPU_MMU_CMDQ_CMD_SIZE		16
 #define IVPU_MMU_CMDQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
@@ -475,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
 	return 0;
 }
 
+static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons)));
+}
+
+static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons)));
+}
+
 static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
 {
-	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
-	u64 *queue_buffer = q->base;
-	int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+	u64 *queue_buffer = cmdq->base;
+	int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
 
-	if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+	if (ivpu_mmu_queue_is_full(cmdq)) {
 		ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
 		return -EBUSY;
 	}
 
 	queue_buffer[idx] = data0;
 	queue_buffer[idx + 1] = data1;
-	q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+	cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
 
 	ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
 
@@ -560,7 +572,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	mmu->cmdq.cons = 0;
 
 	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
-	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
@@ -874,14 +885,10 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
 
 	evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
-	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
+	if (ivpu_mmu_queue_is_empty(evtq))
 		return NULL;
 
-	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
-	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
-
 	return evt;
 }
 
@@ -902,6 +909,7 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		}
 
 		ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+		REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
 	}
 }
 

drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h

@@ -9,7 +9,7 @@
 #define GSP_PAGE_SIZE  BIT(GSP_PAGE_SHIFT)
 
 struct nvkm_gsp_mem {
-	u32 size;
+	size_t size;
 	void *data;
 	dma_addr_t addr;
 };

drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c

@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
 	return 0;
 }
 
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+	if (mem->data) {
+		/*
+		 * Poison the buffer to catch any unexpected access from
+		 * GSP-RM if the buffer was prematurely freed.
+		 */
+		memset(mem->data, 0xFF, mem->size);
+
+		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+		memset(mem, 0, sizeof(*mem));
+	}
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+	mem->size = size;
+	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+	if (WARN_ON(!mem->data))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int
 r535_gsp_postinit(struct nvkm_gsp *gsp)
 {
@@ -1024,6 +1050,13 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
 
 	nvkm_inth_allow(&gsp->subdev.inth);
 	nvkm_wr32(device, 0x110004, 0x00000040);
+
+	/* Release the DMA buffers that were needed only for boot and init */
+	nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+	nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+	nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+	nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+
 	return ret;
 }
 
@@ -1532,27 +1565,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
-	if (mem->data) {
-		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
-		mem->data = NULL;
-	}
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
-	mem->size = size;
-	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
-	if (WARN_ON(!mem->data))
-		return -ENOMEM;
-
-	return 0;
-}
-
-
 static int
 r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
 {
@@ -1938,20 +1950,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
  * See kgspCreateRadix3_IMPL
  */
 static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
 	u64 addr;
 
 	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
 		u64 *ptes;
-		int idx;
+		size_t bufsize;
+		int ret, idx;
 
-		rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
-						      &rx3->mem[i].addr, GFP_KERNEL);
-		if (WARN_ON(!rx3->mem[i].data))
-			return -ENOMEM;
+		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+		if (ret)
+			return ret;
 
 		ptes = rx3->mem[i].data;
 		if (i == 2) {
@@ -1991,7 +2003,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		if (ret)
 			return ret;
 
-		ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+		ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
 		if (ret)
 			return ret;
 
@@ -2150,6 +2162,11 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
 	mutex_destroy(&gsp->cmdq.mutex);
 
 	r535_gsp_dtor_fws(gsp);
+
+	nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+	nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
 }
 
 int
@@ -2194,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	memcpy(gsp->sig.data, data, size);
 
 	/* Build radix3 page table for ELF image. */
-	ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+	ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
 	if (ret)
 		return ret;
 

include/uapi/drm/ivpu_accel.h

@@ -305,6 +305,7 @@ struct drm_ivpu_submit {
 
 /* drm_ivpu_bo_wait job status codes */
 #define DRM_IVPU_JOB_STATUS_SUCCESS 0
+#define DRM_IVPU_JOB_STATUS_ABORTED 256
 
 /**
  * struct drm_ivpu_bo_wait - Wait for BO to become inactive