diff options
-rw-r--r-- | drivers/accel/ivpu/ivpu_hw_37xx.c | 44 | ||||
-rw-r--r-- | drivers/accel/ivpu/ivpu_pm.c | 39 | ||||
-rw-r--r-- | drivers/gpu/drm/drm_buddy.c | 6 | ||||
-rw-r--r-- | drivers/gpu/drm/drm_crtc.c | 1 | ||||
-rw-r--r-- | drivers/gpu/drm/drm_prime.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_abi16.c | 20 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_abi16.h | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_drm.c | 7 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_drv.h | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_exec.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_sched.c | 38 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_sched.h | 6 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_svm.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_uvmm.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 4 | ||||
-rw-r--r-- | drivers/gpu/drm/tests/drm_buddy_test.c | 89 |
16 files changed, 216 insertions, 50 deletions
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 77accd029c4a..89af1006df55 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -510,16 +510,6 @@ 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); @@ -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_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); diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index f57e6d74fb0e..c1a99bf4dffd 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -539,6 +539,12 @@ static int __alloc_range(struct drm_buddy *mm, } while (1); list_splice_tail(&allocated, blocks); + + if (total_allocated < size) { + err = -ENOSPC; + goto err_free; + } + return 0; err_undo: diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index cb90e70d85e8..65f9f66933bb 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -904,6 +904,7 @@ out: connector_set = NULL; fb = NULL; mode = NULL; + num_connectors = 0; DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 834a5e28abbe..7352bde299d5 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -820,7 +820,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, if (max_segment == 0) max_segment = UINT_MAX; err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, + (unsigned long)nr_pages << PAGE_SHIFT, max_segment, GFP_KERNEL); if (err) { kfree(sg); diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index a04156ca8390..d1bb8151a1df 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -128,12 +128,14 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16, struct nouveau_abi16_ntfy *ntfy, *temp; /* Cancel all jobs from the entity's queue. */ - drm_sched_entity_fini(&chan->sched.entity); + if (chan->sched) + drm_sched_entity_fini(&chan->sched->entity); if (chan->chan) nouveau_channel_idle(chan->chan); - nouveau_sched_fini(&chan->sched); + if (chan->sched) + nouveau_sched_destroy(&chan->sched); /* cleanup notifier state */ list_for_each_entry_safe(ntfy, temp, &chan->notifiers, head) { @@ -337,10 +339,16 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) if (ret) goto done; - ret = nouveau_sched_init(&chan->sched, drm, drm->sched_wq, - chan->chan->dma.ib_max); - if (ret) - goto done; + /* If we're not using the VM_BIND uAPI, we don't need a scheduler. + * + * The client lock is already acquired by nouveau_abi16_get(). + */ + if (nouveau_cli_uvmm(cli)) { + ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq, + chan->chan->dma.ib_max); + if (ret) + goto done; + } init->channel = chan->chan->chid; diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h index 1f5e243c0c75..11c8c4a80079 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.h +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h @@ -26,7 +26,7 @@ struct nouveau_abi16_chan { struct nouveau_bo *ntfy; struct nouveau_vma *ntfy_vma; struct nvkm_mm heap; - struct nouveau_sched sched; + struct nouveau_sched *sched; }; struct nouveau_abi16 { diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 6f6c31a9937b..a947e1d5f309 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -201,7 +201,8 @@ nouveau_cli_fini(struct nouveau_cli *cli) WARN_ON(!list_empty(&cli->worker)); usif_client_fini(cli); - nouveau_sched_fini(&cli->sched); + if (cli->sched) + nouveau_sched_destroy(&cli->sched); if (uvmm) nouveau_uvmm_fini(uvmm); nouveau_vmm_fini(&cli->svm); @@ -311,7 +312,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, cli->mem = &mems[ret]; /* Don't pass in the (shared) sched_wq in order to let - * nouveau_sched_init() create a dedicated one for VM_BIND jobs. + * nouveau_sched_create() create a dedicated one for VM_BIND jobs. * * This is required to ensure that for VM_BIND jobs free_job() work and * run_job() work can always run concurrently and hence, free_job() work @@ -320,7 +321,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, * locks which indirectly or directly are held for allocations * elsewhere. */ - ret = nouveau_sched_init(&cli->sched, drm, NULL, 1); + ret = nouveau_sched_create(&cli->sched, drm, NULL, 1); if (ret) goto done; diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 8a6d94c8b163..e239c6bf4afa 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -98,7 +98,7 @@ struct nouveau_cli { bool disabled; } uvmm; - struct nouveau_sched sched; + struct nouveau_sched *sched; const struct nvif_mclass *mem; diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index bc5d71b79ab2..e65c0ef23bc7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -389,7 +389,7 @@ nouveau_exec_ioctl_exec(struct drm_device *dev, if (ret) goto out; - args.sched = &chan16->sched; + args.sched = chan16->sched; args.file_priv = file_priv; args.chan = chan; diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index dd98f6910f9c..32fa2e273965 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -398,7 +398,7 @@ static const struct drm_sched_backend_ops nouveau_sched_ops = { .free_job = nouveau_sched_free_job, }; -int +static int nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm, struct workqueue_struct *wq, u32 credit_limit) { @@ -453,7 +453,30 @@ fail_wq: return ret; } -void +int +nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, + struct workqueue_struct *wq, u32 credit_limit) +{ + struct nouveau_sched *sched; + int ret; + + sched = kzalloc(sizeof(*sched), GFP_KERNEL); + if (!sched) + return -ENOMEM; + + ret = nouveau_sched_init(sched, drm, wq, credit_limit); + if (ret) { + kfree(sched); + return ret; + } + + *psched = sched; + + return 0; +} + + +static void nouveau_sched_fini(struct nouveau_sched *sched) { struct drm_gpu_scheduler *drm_sched = &sched->base; @@ -471,3 +494,14 @@ nouveau_sched_fini(struct nouveau_sched *sched) if (sched->wq) destroy_workqueue(sched->wq); } + +void +nouveau_sched_destroy(struct nouveau_sched **psched) +{ + struct nouveau_sched *sched = *psched; + + nouveau_sched_fini(sched); + kfree(sched); + + *psched = NULL; +} diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h index a6528f5981e6..e1f01a23e6f6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.h +++ b/drivers/gpu/drm/nouveau/nouveau_sched.h @@ -111,8 +111,8 @@ struct nouveau_sched { } job; }; -int nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm, - struct workqueue_struct *wq, u32 credit_limit); -void nouveau_sched_fini(struct nouveau_sched *sched); +int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, + struct workqueue_struct *wq, u32 credit_limit); +void nouveau_sched_destroy(struct nouveau_sched **psched); #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index cc03e0c22ff3..5e4565c5011a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -1011,7 +1011,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id) if (ret) return ret; - buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL); + buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL); if (!buffer->fault) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index 4f223c972c6a..0a0a11dc9ec0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1740,7 +1740,7 @@ nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev, if (ret) return ret; - args.sched = &cli->sched; + args.sched = cli->sched; args.file_priv = file_priv; ret = nouveau_uvmm_vm_bind(&args); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 85b3b4871a1d..fdd768bbd487 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -1985,8 +1985,10 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc, clock = vop2_set_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags); } - if (!clock) + if (!clock) { + vop2_unlock(vop2); return; + } if (vcstate->output_mode == ROCKCHIP_OUT_MODE_AAAA && !(vp_data->feature & VOP2_VP_FEATURE_OUTPUT_10BIT)) diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index ea2af6bd9abe..fee6bec757d1 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -8,6 +8,7 @@ #include <linux/prime_numbers.h> #include <linux/sched/signal.h> +#include <linux/sizes.h> #include <drm/drm_buddy.h> @@ -18,6 +19,93 @@ static inline u64 get_size(int order, u64 chunk_size) return (1 << order) * chunk_size; } +static void drm_test_buddy_alloc_contiguous(struct kunit *test) +{ + u64 mm_size, ps = SZ_4K, i, n_pages, total; + struct drm_buddy_block *block; + struct drm_buddy mm; + LIST_HEAD(left); + LIST_HEAD(middle); + LIST_HEAD(right); + LIST_HEAD(allocated); + + mm_size = 16 * 3 * SZ_4K; + + KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps)); + + /* + * Idea is to fragment the address space by alternating block + * allocations between three different lists; one for left, middle and + * right. We can then free a list to simulate fragmentation. In + * particular we want to exercise the DRM_BUDDY_CONTIGUOUS_ALLOCATION, + * including the try_harder path. + */ + + i = 0; + n_pages = mm_size / ps; + do { + struct list_head *list; + int slot = i % 3; + + if (slot == 0) + list = &left; + else if (slot == 1) + list = &middle; + else + list = &right; + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, 0, mm_size, + ps, ps, list, 0), + "buddy_alloc hit an error size=%d\n", + ps); + } while (++i < n_pages); + + KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, + 3 * ps, ps, &allocated, + DRM_BUDDY_CONTIGUOUS_ALLOCATION), + "buddy_alloc didn't error size=%d\n", 3 * ps); + + drm_buddy_free_list(&mm, &middle); + KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, + 3 * ps, ps, &allocated, + DRM_BUDDY_CONTIGUOUS_ALLOCATION), + "buddy_alloc didn't error size=%llu\n", 3 * ps); + KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, + 2 * ps, ps, &allocated, + DRM_BUDDY_CONTIGUOUS_ALLOCATION), + "buddy_alloc didn't error size=%llu\n", 2 * ps); + + drm_buddy_free_list(&mm, &right); + KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, + 3 * ps, ps, &allocated, + DRM_BUDDY_CONTIGUOUS_ALLOCATION), + "buddy_alloc didn't error size=%llu\n", 3 * ps); + /* + * At this point we should have enough contiguous space for 2 blocks, + * however they are never buddies (since we freed middle and right) so + * will require the try_harder logic to find them. + */ + KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, + 2 * ps, ps, &allocated, + DRM_BUDDY_CONTIGUOUS_ALLOCATION), + "buddy_alloc hit an error size=%d\n", 2 * ps); + + drm_buddy_free_list(&mm, &left); + KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, + 3 * ps, ps, &allocated, + DRM_BUDDY_CONTIGUOUS_ALLOCATION), + "buddy_alloc hit an error size=%d\n", 3 * ps); + + total = 0; + list_for_each_entry(block, &allocated, link) + total += drm_buddy_block_size(&mm, block); + + KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3); + + drm_buddy_free_list(&mm, &allocated); + drm_buddy_fini(&mm); +} + static void drm_test_buddy_alloc_pathological(struct kunit *test) { u64 mm_size, size, start = 0; @@ -280,6 +368,7 @@ static struct kunit_case drm_buddy_tests[] = { KUNIT_CASE(drm_test_buddy_alloc_optimistic), KUNIT_CASE(drm_test_buddy_alloc_pessimistic), KUNIT_CASE(drm_test_buddy_alloc_pathological), + KUNIT_CASE(drm_test_buddy_alloc_contiguous), {} }; |