Merge v6.8-rc6 into drm-next

Thomas Zimmermann asked to backmerge -rc6 for drm-misc branches,
there's a few same-area-changed conflicts (xe and amdgpu mostly) that
are getting a bit too annoying.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

7 files changed, 83 insertions, 57 deletions

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 3f2439117582..39f6d1b98fd6 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -480,9 +480,8 @@ 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)
-		pdev->d3hot_delay = 0;
+	/* NPU does not require 10m D3hot delay */
+	pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);
 	if (ret) {
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index dfa91d48f901..1457300828bf 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -220,7 +220,6 @@ 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;
 
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index be91c6744b12..9a0c9498baba 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -510,22 +510,12 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
 	return ret;
 }
 
-static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
-{
-	ivpu_boot_dpu_active_drive(vdev, false);
-	ivpu_boot_pwr_island_isolation_drive(vdev, true);
-	ivpu_boot_pwr_island_trickle_drive(vdev, false);
-	ivpu_boot_pwr_island_drive(vdev, false);
-
-	return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
-}
-
 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);
@@ -616,12 +606,37 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
 	return 0;
 }
 
+static int ivpu_hw_37xx_ip_reset(struct ivpu_device *vdev)
+{
+	int ret;
+	u32 val;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
+	val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
+	REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+	return ret;
+}
+
 static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (ivpu_boot_pwr_domain_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable power domain\n");
+	if (ivpu_hw_37xx_ip_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset NPU\n");
 		ret = -EIO;
 	}
 
@@ -661,6 +676,11 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* PLL requests may fail when powering down, so issue WP 0 here */
+	ret = ivpu_pll_disable(vdev);
+	if (ret)
+		ivpu_warn(vdev, "Failed to disable PLL: %d\n", ret);
+
 	ret = ivpu_hw_37xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index d4663a42416b..e4eddbf5d11c 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -24,7 +24,7 @@
 #define SKU_HW_ID_SHIFT              16u
 #define SKU_HW_ID_MASK               0xffff0000u
 
-#define PLL_CONFIG_DEFAULT           0x1
+#define PLL_CONFIG_DEFAULT           0x0
 #define PLL_CDYN_DEFAULT             0x80
 #define PLL_EPP_DEFAULT              0x80
 #define PLL_REF_CLK_FREQ	     (50 * 1000000)
@@ -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;
 
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index a9f2fe1bddea..a49bc9105ed0 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -304,7 +304,7 @@ 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);
@@ -325,7 +325,7 @@ 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)
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 9a3122ffce03..91bd640655ab 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/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_IDX_MASK		(IVPU_MMU_Q_COUNT - 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);
 	}
 }
 
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 280fd3936f60..9973945dff5d 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -58,11 +58,14 @@ static int ivpu_suspend(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+	pci_save_state(to_pci_dev(vdev->drm.dev));
+
 	ret = ivpu_shutdown(vdev);
-	if (ret) {
+	if (ret)
 		ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
-		return ret;
-	}
+
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 
 	return ret;
 }
@@ -71,6 +74,9 @@ static int ivpu_resume(struct ivpu_device *vdev)
 {
 	int ret;
 
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+	pci_restore_state(to_pci_dev(vdev->drm.dev));
+
 retry:
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
@@ -120,15 +126,20 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
 
 	ivpu_fw_log_dump(vdev);
 
-retry:
-	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
-	if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
-		cond_resched();
-		goto retry;
-	}
+	atomic_inc(&vdev->pm->reset_counter);
+	atomic_set(&vdev->pm->reset_pending, 1);
+	down_write(&vdev->pm->reset_lock);
 
-	if (ret && ret != -EAGAIN)
-		ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
+	ivpu_suspend(vdev);
+	ivpu_pm_prepare_cold_boot(vdev);
+	ivpu_jobs_abort_all(vdev);
+
+	ret = ivpu_resume(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+
+	up_write(&vdev->pm->reset_lock);
+	atomic_set(&vdev->pm->reset_pending, 0);
 
 	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 	pm_runtime_mark_last_busy(vdev->drm.dev);
@@ -200,9 +211,6 @@ int ivpu_pm_suspend_cb(struct device *dev)
 	ivpu_suspend(vdev);
 	ivpu_pm_prepare_warm_boot(vdev);
 
-	pci_save_state(to_pci_dev(dev));
-	pci_set_power_state(to_pci_dev(dev), PCI_D3hot);
-
 	ivpu_dbg(vdev, PM, "Suspend done.\n");
 
 	return 0;
@@ -216,9 +224,6 @@ int ivpu_pm_resume_cb(struct device *dev)
 
 	ivpu_dbg(vdev, PM, "Resume..\n");
 
-	pci_set_power_state(to_pci_dev(dev), PCI_D0);
-	pci_restore_state(to_pci_dev(dev));
-
 	ret = ivpu_resume(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to resume: %d\n", ret);