From 28083ff18d3f65ecd64857f4495623135dd1f132 Mon Sep 17 00:00:00 2001 From: Jacek Lawrynowicz Date: Wed, 7 Feb 2024 11:24:46 +0100 Subject: accel/ivpu: Fix DevTLB errors on suspend/resume and recovery Issue IP reset before shutdown in order to complete all upstream requests to the SOC. Without this DevTLB is complaining about incomplete transactions and NPU cannot resume from suspend. This problem is only happening on recent IFWI releases. IP reset in rare corner cases can mess up PCI configuration, so save it before the reset. After this happens it is also impossible to issue PLL requests and D0->D3->D0 cycle is needed to recover the NPU. Add WP 0 request on power up, so the PUNIT is always notified about NPU reset. Use D0/D3 cycle for recovery as it can recover from failed IP reset and FLR cannot. Fixes: 3f7c0634926d ("accel/ivpu/37xx: Fix hangs related to MMIO reset") Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20240207102446.3126981-1-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_pm.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) (limited to 'drivers/accel/ivpu/ivpu_pm.c') diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index f501f27ebafd..5f73854234ba 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); + + 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); - if (ret && ret != -EAGAIN) - ivpu_err(vdev, "Failed to reset VPU: %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); -- cgit v1.2.3