summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c39
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c12
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c35
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c55
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_object.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c25
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c61
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c18
-rw-r--r--drivers/gpu/drm/amd/amdgpu/navi10_ih.c34
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nv.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc15.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c24
29 files changed, 283 insertions, 112 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 751557af09bb..a15a4787c7ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -297,7 +297,7 @@ void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd);
void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
struct amdgpu_vm *vm);
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo);
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo);
void amdgpu_amdkfd_reserve_system_mem(uint64_t size);
#else
static inline
@@ -312,7 +312,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
}
static inline
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo)
{
}
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 0e9cfe99ae9e..6348559608ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -207,7 +207,7 @@ static void unreserve_mem_limit(struct amdgpu_device *adev,
spin_unlock(&kfd_mem_limit.mem_limit_lock);
}
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
u32 domain = bo->preferred_domains;
@@ -219,6 +219,8 @@ void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
}
unreserve_mem_limit(adev, amdgpu_bo_size(bo), domain, sg);
+
+ kfree(bo->kfd_bo);
}
@@ -644,12 +646,6 @@ kfd_mem_attach_dmabuf(struct amdgpu_device *adev, struct kgd_mem *mem,
if (IS_ERR(gobj))
return PTR_ERR(gobj);
- /* Import takes an extra reference on the dmabuf. Drop it now to
- * avoid leaking it. We only need the one reference in
- * kgd_mem->dmabuf.
- */
- dma_buf_put(mem->dmabuf);
-
*bo = gem_to_amdgpu_bo(gobj);
(*bo)->flags |= AMDGPU_GEM_CREATE_PREEMPTIBLE;
(*bo)->parent = amdgpu_bo_ref(mem->bo);
@@ -734,14 +730,19 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
}
/* Add BO to VM internal data structures */
+ ret = amdgpu_bo_reserve(bo[i], false);
+ if (ret) {
+ pr_debug("Unable to reserve BO during memory attach");
+ goto unwind;
+ }
attachment[i]->bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]);
+ amdgpu_bo_unreserve(bo[i]);
if (unlikely(!attachment[i]->bo_va)) {
ret = -ENOMEM;
pr_err("Failed to add BO object to VM. ret == %d\n",
ret);
goto unwind;
}
-
attachment[i]->va = va;
attachment[i]->pte_flags = get_pte_flags(adev, mem);
attachment[i]->adev = adev;
@@ -757,7 +758,9 @@ unwind:
if (!attachment[i])
continue;
if (attachment[i]->bo_va) {
+ amdgpu_bo_reserve(bo[i], true);
amdgpu_vm_bo_rmv(adev, attachment[i]->bo_va);
+ amdgpu_bo_unreserve(bo[i]);
list_del(&attachment[i]->list);
}
if (bo[i])
@@ -1393,7 +1396,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
struct sg_table *sg = NULL;
uint64_t user_addr = 0;
struct amdgpu_bo *bo;
- struct drm_gem_object *gobj;
+ struct drm_gem_object *gobj = NULL;
u32 domain, alloc_domain;
u64 alloc_flags;
int ret;
@@ -1503,14 +1506,16 @@ allocate_init_user_pages_failed:
remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info);
drm_vma_node_revoke(&gobj->vma_node, drm_priv);
err_node_allow:
- drm_gem_object_put(gobj);
/* Don't unreserve system mem limit twice */
goto err_reserve_limit;
err_bo_create:
unreserve_mem_limit(adev, size, alloc_domain, !!sg);
err_reserve_limit:
mutex_destroy(&(*mem)->lock);
- kfree(*mem);
+ if (gobj)
+ drm_gem_object_put(gobj);
+ else
+ kfree(*mem);
err:
if (sg) {
sg_free_table(sg);
@@ -1568,12 +1573,12 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va,
mem->va + bo_size * (1 + mem->aql_queue));
- ret = unreserve_bo_and_vms(&ctx, false, false);
-
/* Remove from VM internal data structures */
list_for_each_entry_safe(entry, tmp, &mem->attachments, list)
kfd_mem_detach(entry);
+ ret = unreserve_bo_and_vms(&ctx, false, false);
+
/* Free the sync object */
amdgpu_sync_free(&mem->sync);
@@ -1600,9 +1605,13 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
drm_vma_node_revoke(&mem->bo->tbo.base.vma_node, drm_priv);
if (mem->dmabuf)
dma_buf_put(mem->dmabuf);
- drm_gem_object_put(&mem->bo->tbo.base);
mutex_destroy(&mem->lock);
- kfree(mem);
+
+ /* If this releases the last reference, it will end up calling
+ * amdgpu_amdkfd_release_notify and kfree the mem struct. That's why
+ * this needs to be the last call here.
+ */
+ drm_gem_object_put(&mem->bo->tbo.base);
return ret;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 96b7bb13a2dd..12a6b1c99c93 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -1569,6 +1569,18 @@ void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev,
WREG32(adev->bios_scratch_reg_offset + 3, tmp);
}
+void amdgpu_atombios_scratch_regs_set_backlight_level(struct amdgpu_device *adev,
+ u32 backlight_level)
+{
+ u32 tmp = RREG32(adev->bios_scratch_reg_offset + 2);
+
+ tmp &= ~ATOM_S2_CURRENT_BL_LEVEL_MASK;
+ tmp |= (backlight_level << ATOM_S2_CURRENT_BL_LEVEL_SHIFT) &
+ ATOM_S2_CURRENT_BL_LEVEL_MASK;
+
+ WREG32(adev->bios_scratch_reg_offset + 2, tmp);
+}
+
bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev)
{
u32 tmp = RREG32(adev->bios_scratch_reg_offset + 7);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
index 8cc0222dba19..27e74b1fc260 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
@@ -185,6 +185,8 @@ bool amdgpu_atombios_has_gpu_virtualization_table(struct amdgpu_device *adev);
void amdgpu_atombios_scratch_regs_lock(struct amdgpu_device *adev, bool lock);
void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev,
bool hung);
+void amdgpu_atombios_scratch_regs_set_backlight_level(struct amdgpu_device *adev,
+ u32 backlight_level);
bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev);
void amdgpu_atombios_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index b9c11c2b2885..0de66f59adb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -827,6 +827,7 @@ static int amdgpu_connector_vga_get_modes(struct drm_connector *connector)
amdgpu_connector_get_edid(connector);
ret = amdgpu_connector_ddc_get_modes(connector);
+ amdgpu_get_native_mode(connector);
return ret;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6e40cc1bc6dc..1e651b959141 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2398,10 +2398,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
if (!adev->gmc.xgmi.pending_reset)
amdgpu_amdkfd_device_init(adev);
- r = amdgpu_amdkfd_resume_iommu(adev);
- if (r)
- goto init_failed;
-
amdgpu_fru_get_product_info(adev);
init_failed:
@@ -3171,11 +3167,21 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
{
switch (asic_type) {
#if defined(CONFIG_DRM_AMD_DC)
-#if defined(CONFIG_DRM_AMD_DC_SI)
case CHIP_TAHITI:
case CHIP_PITCAIRN:
case CHIP_VERDE:
case CHIP_OLAND:
+ /*
+ * We have systems in the wild with these ASICs that require
+ * LVDS and VGA support which is not supported with DC.
+ *
+ * Fallback to the non-DC driver here by default so as not to
+ * cause regressions.
+ */
+#if defined(CONFIG_DRM_AMD_DC_SI)
+ return amdgpu_dc > 0;
+#else
+ return false;
#endif
case CHIP_BONAIRE:
case CHIP_KAVERI:
@@ -3503,6 +3509,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
adev->rmmio_size = pci_resource_len(adev->pdev, 2);
}
+ for (i = 0; i < AMD_IP_BLOCK_TYPE_NUM; i++)
+ atomic_set(&adev->pm.pwr_state[i], POWER_STATE_UNKNOWN);
+
adev->rmmio = ioremap(adev->rmmio_base, adev->rmmio_size);
if (adev->rmmio == NULL) {
return -ENOMEM;
@@ -3824,7 +3833,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
/* disable all interrupts */
amdgpu_irq_disable_all(adev);
if (adev->mode_info.mode_config_initialized){
- if (!amdgpu_device_has_dc_support(adev))
+ if (!drm_drv_uses_atomic_modeset(adev_to_drm(adev)))
drm_helper_force_disable_all(adev_to_drm(adev));
else
drm_atomic_helper_shutdown(adev_to_drm(adev));
@@ -4280,6 +4289,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
{
int r;
+ amdgpu_amdkfd_pre_reset(adev);
+
if (from_hypervisor)
r = amdgpu_virt_request_full_gpu(adev, true);
else
@@ -4287,8 +4298,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
if (r)
return r;
- amdgpu_amdkfd_pre_reset(adev);
-
/* Resume IP prior to SMC */
r = amdgpu_device_ip_reinit_early_sriov(adev);
if (r)
@@ -4850,6 +4859,9 @@ static void amdgpu_device_recheck_guilty_jobs(
/* clear job's guilty and depend the folowing step to decide the real one */
drm_sched_reset_karma(s_job);
+ /* for the real bad job, it will be resubmitted twice, adding a dma_fence_get
+ * to make sure fence is balanced */
+ dma_fence_get(s_job->s_fence->parent);
drm_sched_resubmit_jobs_ext(&ring->sched, 1);
ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout);
@@ -4885,6 +4897,7 @@ retry:
/* got the hw fence, signal finished fence */
atomic_dec(ring->sched.score);
+ dma_fence_put(s_job->s_fence->parent);
dma_fence_get(&s_job->s_fence->finished);
dma_fence_signal(&s_job->s_fence->finished);
dma_fence_put(&s_job->s_fence->finished);
@@ -5079,7 +5092,7 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */
tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter));
/* Actual ASIC resets if needed.*/
- /* TODO Implement XGMI hive reset logic for SRIOV */
+ /* Host driver will handle XGMI hive reset for SRIOV */
if (amdgpu_sriov_vf(adev)) {
r = amdgpu_device_reset_sriov(adev, job ? false : true);
if (r)
@@ -5120,7 +5133,7 @@ skip_hw_reset:
drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
}
- if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) {
+ if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) {
drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
}
@@ -5141,7 +5154,7 @@ skip_sched_resume:
list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
/* unlock kfd: SRIOV would do it separately */
if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
- amdgpu_amdkfd_post_reset(tmp_adev);
+ amdgpu_amdkfd_post_reset(tmp_adev);
/* kfd_post_reset will do nothing if kfd device is not initialized,
* need to bring up kfd here if it's not be initialized before
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index d7c8d9e3c203..ea00090b3fb3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -157,6 +157,8 @@ static int hw_id_map[MAX_HWIP] = {
[HDP_HWIP] = HDP_HWID,
[SDMA0_HWIP] = SDMA0_HWID,
[SDMA1_HWIP] = SDMA1_HWID,
+ [SDMA2_HWIP] = SDMA2_HWID,
+ [SDMA3_HWIP] = SDMA3_HWID,
[MMHUB_HWIP] = MMHUB_HWID,
[ATHUB_HWIP] = ATHUB_HWID,
[NBIO_HWIP] = NBIF_HWID,
@@ -248,8 +250,8 @@ get_from_vram:
offset = offsetof(struct binary_header, binary_checksum) +
sizeof(bhdr->binary_checksum);
- size = bhdr->binary_size - offset;
- checksum = bhdr->binary_checksum;
+ size = le16_to_cpu(bhdr->binary_size) - offset;
+ checksum = le16_to_cpu(bhdr->binary_checksum);
if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
size, checksum)) {
@@ -270,7 +272,7 @@ get_from_vram:
}
if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
- ihdr->size, checksum)) {
+ le16_to_cpu(ihdr->size), checksum)) {
DRM_ERROR("invalid ip discovery data table checksum\n");
r = -EINVAL;
goto out;
@@ -282,7 +284,7 @@ get_from_vram:
ghdr = (struct gpu_info_header *)(adev->mman.discovery_bin + offset);
if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
- ghdr->size, checksum)) {
+ le32_to_cpu(ghdr->size), checksum)) {
DRM_ERROR("invalid gc data table checksum\n");
r = -EINVAL;
goto out;
@@ -489,10 +491,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset));
for (i = 0; i < 32; i++) {
- if (le32_to_cpu(harvest_info->list[i].hw_id) == 0)
+ if (le16_to_cpu(harvest_info->list[i].hw_id) == 0)
break;
- switch (le32_to_cpu(harvest_info->list[i].hw_id)) {
+ switch (le16_to_cpu(harvest_info->list[i].hw_id)) {
case VCN_HWID:
vcn_harvest_count++;
if (harvest_info->list[i].number_instance == 0)
@@ -587,6 +589,9 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add common ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -619,6 +624,9 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add gmc ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -648,6 +656,9 @@ static int amdgpu_discovery_set_ih_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add ih ip block(OSSSYS_HWIP:0x%x)\n",
+ adev->ip_versions[OSSSYS_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -688,6 +699,9 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add psp ip block(MP0_HWIP:0x%x)\n",
+ adev->ip_versions[MP0_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -726,6 +740,9 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add smu ip block(MP1_HWIP:0x%x)\n",
+ adev->ip_versions[MP1_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -753,6 +770,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &dm_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add dm ip block(DCE_HWIP:0x%x)\n",
+ adev->ip_versions[DCE_HWIP][0]);
return -EINVAL;
}
} else if (adev->ip_versions[DCI_HWIP][0]) {
@@ -763,6 +783,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &dm_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add dm ip block(DCI_HWIP:0x%x)\n",
+ adev->ip_versions[DCI_HWIP][0]);
return -EINVAL;
}
#endif
@@ -796,6 +819,9 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add gfx ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -829,6 +855,9 @@ static int amdgpu_discovery_set_sdma_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add sdma ip block(SDMA0_HWIP:0x%x)\n",
+ adev->ip_versions[SDMA0_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -845,6 +874,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add uvd v7 ip block(UVD_HWIP:0x%x)\n",
+ adev->ip_versions[UVD_HWIP][0]);
return -EINVAL;
}
switch (adev->ip_versions[VCE_HWIP][0]) {
@@ -855,6 +887,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add VCE v4 ip block(VCE_HWIP:0x%x)\n",
+ adev->ip_versions[VCE_HWIP][0]);
return -EINVAL;
}
} else {
@@ -867,7 +902,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
case IP_VERSION(2, 0, 2):
case IP_VERSION(2, 2, 0):
amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
- amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
+ if (!amdgpu_sriov_vf(adev))
+ amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
break;
case IP_VERSION(2, 0, 3):
break;
@@ -881,8 +917,10 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
break;
case IP_VERSION(3, 0, 0):
case IP_VERSION(3, 0, 16):
+ case IP_VERSION(3, 0, 64):
case IP_VERSION(3, 1, 1):
case IP_VERSION(3, 0, 2):
+ case IP_VERSION(3, 0, 192):
amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
if (!amdgpu_sriov_vf(adev))
amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block);
@@ -891,6 +929,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add vcn/jpeg ip block(UVD_HWIP:0x%x)\n",
+ adev->ip_versions[UVD_HWIP][0]);
return -EINVAL;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index a573424a6e0b..a1e63ba4c54a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -60,9 +60,10 @@ static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf)
goto unlock;
}
- ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
- TTM_BO_VM_NUM_PREFAULT, 1);
- drm_dev_exit(idx);
+ ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+ TTM_BO_VM_NUM_PREFAULT);
+
+ drm_dev_exit(idx);
} else {
ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index f3d62e196901..0c7963dfacad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -223,7 +223,7 @@ int amdgpu_ih_wait_on_checkpoint_process(struct amdgpu_device *adev,
*/
int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih)
{
- unsigned int count = AMDGPU_IH_MAX_NUM_IVS;
+ unsigned int count;
u32 wptr;
if (!ih->enabled || adev->shutdown)
@@ -232,6 +232,7 @@ int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih)
wptr = amdgpu_ih_get_wptr(adev, ih);
restart_ih:
+ count = AMDGPU_IH_MAX_NUM_IVS;
DRM_DEBUG("%s: rptr %d, wptr %d\n", __func__, ih->rptr, wptr);
/* Order reading of wptr vs. reading of IH ring data */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index dfe667ea8b05..651c7abfde03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1423,6 +1423,8 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
struct drm_amdgpu_info_firmware fw_info;
struct drm_amdgpu_query_fw query_fw;
struct atom_context *ctx = adev->mode_info.atom_context;
+ uint8_t smu_minor, smu_debug;
+ uint16_t smu_major;
int ret, i;
static const char *ta_fw_name[TA_FW_TYPE_MAX_INDEX] = {
@@ -1568,8 +1570,11 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
if (ret)
return ret;
- seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x\n",
- fw_info.feature, fw_info.ver);
+ smu_major = (fw_info.ver >> 16) & 0xffff;
+ smu_minor = (fw_info.ver >> 8) & 0xff;
+ smu_debug = (fw_info.ver >> 0) & 0xff;
+ seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x (%d.%d.%d)\n",
+ fw_info.feature, fw_info.ver, smu_major, smu_minor, smu_debug);
/* SDMA */
query_fw.fw_type = AMDGPU_INFO_FW_SDMA;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index aeb92e5677ac..4fcfc2313b8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1274,7 +1274,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
abo = ttm_to_amdgpu_bo(bo);
if (abo->kfd_bo)
- amdgpu_amdkfd_unreserve_memory_limit(abo);
+ amdgpu_amdkfd_release_notify(abo);
/* We only remove the fence if the resv has individualized. */
WARN_ON_ONCE(bo->type == ttm_bo_type_kernel
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 2658414c503d..585961c2f5f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -134,6 +134,8 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
adev->vcn.indirect_sram = true;
break;
case IP_VERSION(3, 0, 0):
+ case IP_VERSION(3, 0, 64):
+ case IP_VERSION(3, 0, 192):
if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0))
fw_name = FIRMWARE_SIENNA_CICHLID;
else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index ce982afeff91..ac9a8cd21c4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -504,8 +504,8 @@ static int amdgpu_vkms_sw_fini(void *handle)
int i = 0;
for (i = 0; i < adev->mode_info.num_crtc; i++)
- if (adev->mode_info.crtcs[i])
- hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer);
+ if (adev->amdgpu_vkms_output[i].vblank_hrtimer.function)
+ hrtimer_cancel(&adev->amdgpu_vkms_output[i].vblank_hrtimer);
kfree(adev->mode_info.bios_hardcoded_edid);
kfree(adev->amdgpu_vkms_output);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 978ac927ac11..567df2db23ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -386,6 +386,7 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
"%s", "xgmi_hive_info");
if (ret) {
dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
+ kobject_put(&hive->kobj);
kfree(hive);
hive = NULL;
goto pro_end;
@@ -806,9 +807,9 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
pcs_clear_status(adev,
xgmi23_pcs_err_status_reg_aldebaran[i]);
- for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
+ for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++)
pcs_clear_status(adev,
- xgmi23_pcs_err_status_reg_aldebaran[i]);
+ xgmi3x16_pcs_err_status_reg_aldebaran[i]);
for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++)
pcs_clear_status(adev,
walf_pcs_err_status_reg_aldebaran[i]);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 90a834dc4008..dbe7442fb25c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7707,8 +7707,19 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(10, 3, 1):
case IP_VERSION(10, 3, 3):
- clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh) |
- ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
+ preempt_disable();
+ clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh);
+ clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh);
+ hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh);
+ /* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over
+ * roughly every 42 seconds.
+ */
+ if (hi_check != clock_hi) {
+ clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh);
+ clock_hi = hi_check;
+ }
+ preempt_enable();
+ clock = clock_lo | (clock_hi << 32ULL);
break;
default:
preempt_disable();
@@ -8249,6 +8260,9 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
{
u32 reg, data;
+
+ amdgpu_gfx_off_ctrl(adev, false);
+
/* not for *_SOC15 */
reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
if (amdgpu_sriov_is_pp_one_vf(adev))
@@ -8263,6 +8277,8 @@ static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
else
WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+ amdgpu_gfx_off_ctrl(adev, true);
}
static bool gfx_v10_0_check_rlcg_range(struct amdgpu_device *adev,
@@ -8316,11 +8332,8 @@ static void gfx_v10_cntl_power_gating(struct amdgpu_device *adev, bool enable)
if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(10, 3, 1):
- data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
- WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
- break;
case IP_VERSION(10, 3, 3):
- data = 0x1388 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
+ data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
break;
default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 37b4a3db6360..d17a6f399347 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3575,12 +3575,16 @@ static void gfx_v7_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
{
u32 data;
+ amdgpu_gfx_off_ctrl(adev, false);
+
data = RREG32(mmRLC_SPM_VMID);
data &= ~RLC_SPM_VMID__RLC_SPM_VMID_MASK;
data |= (vmid & RLC_SPM_VMID__RLC_SPM_VMID_MASK) << RLC_SPM_VMID__RLC_SPM_VMID__SHIFT;
WREG32(mmRLC_SPM_VMID, data);
+
+ amdgpu_gfx_off_ctrl(adev, true);
}
static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index e0302c23e9a7..5f112efda634 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5624,6 +5624,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
{
u32 data;
+ amdgpu_gfx_off_ctrl(adev, false);
+
if (amdgpu_sriov_is_pp_one_vf(adev))
data = RREG32_NO_KIQ(mmRLC_SPM_VMID);
else
@@ -5636,6 +5638,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
WREG32_NO_KIQ(mmRLC_SPM_VMID, data);
else
WREG32(mmRLC_SPM_VMID, data);
+
+ amdgpu_gfx_off_ctrl(adev, true);
}
static const struct amdgpu_rlc_funcs iceland_rlc_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 7f944bb11298..b305fd39874f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -140,6 +140,11 @@ MODULE_FIRMWARE("amdgpu/aldebaran_rlc.bin");
#define mmTCP_CHAN_STEER_5_ARCT 0x0b0c
#define mmTCP_CHAN_STEER_5_ARCT_BASE_IDX 0
+#define mmGOLDEN_TSC_COUNT_UPPER_Renoir 0x0025
+#define mmGOLDEN_TSC_COUNT_UPPER_Renoir_BASE_IDX 1
+#define mmGOLDEN_TSC_COUNT_LOWER_Renoir 0x0026
+#define mmGOLDEN_TSC_COUNT_LOWER_Renoir_BASE_IDX 1
+
enum ta_ras_gfx_subblock {
/*CPC*/
TA_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
@@ -2462,7 +2467,9 @@ static int gfx_v9_0_sw_fini(void *handle)
amdgpu_gfx_kiq_fini(adev);
gfx_v9_0_mec_fini(adev);
- amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj);
+ amdgpu_bo_free_kernel(&adev->gfx.rlc.clear_state_obj,
+ &adev->gfx.rlc.clear_state_gpu_addr,
+ (void **)&adev->gfx.rlc.cs_ptr);
if (adev->flags & AMD_IS_APU) {
amdgpu_bo_free_kernel(&adev->gfx.rlc.cp_table_obj,
&adev->gfx.rlc.cp_table_gpu_addr,
@@ -4053,9 +4060,10 @@ static int gfx_v9_0_hw_fini(void *handle)
gfx_v9_0_cp_enable(adev, false);
- /* Skip suspend with A+A reset */
- if (adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) {
- dev_dbg(adev->dev, "Device in reset. Skipping RLC halt\n");
+ /* Skip stopping RLC with A+A reset or when RLC controls GFX clock */
+ if ((adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) ||
+ (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2))) {
+ dev_dbg(adev->dev, "Skipping RLC halt\n");
return 0;
}
@@ -4236,19 +4244,38 @@ failed_kiq_read:
static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
{
- uint64_t clock;
+ uint64_t clock, clock_lo, clock_hi, hi_check;
- amdgpu_gfx_off_ctrl(adev, false);
- mutex_lock(&adev->gfx.gpu_clock_mutex);
- if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 0, 1) && amdgpu_sriov_runtime(adev)) {
- clock = gfx_v9_0_kiq_read_clock(adev);
- } else {
- WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
- clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
- ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+ switch (adev->ip_versions[GC_HWIP][0]) {
+ case IP_VERSION(9, 3, 0):
+ preempt_disable();
+ clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir);
+ clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir);
+ hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir);
+ /* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over
+ * roughly every 42 seconds.
+ */
+ if (hi_check != clock_hi) {
+ clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir);
+ clock_hi = hi_check;
+ }
+ preempt_enable();
+ clock = clock_lo | (clock_hi << 32ULL);
+ break;
+ default:
+ amdgpu_gfx_off_ctrl(adev, false);
+ mutex_lock(&adev->gfx.gpu_clock_mutex);
+ if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 0, 1) && amdgpu_sriov_runtime(adev)) {
+ clock = gfx_v9_0_kiq_read_clock(adev);
+ } else {
+ WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+ clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
+ ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+ }
+ mutex_unlock(&adev->gfx.gpu_clock_mutex);
+ amdgpu_gfx_off_ctrl(adev, true);
+ break;
}
- mutex_unlock(&adev->gfx.gpu_clock_mutex);
- amdgpu_gfx_off_ctrl(adev, true);
return clock;
}
@@ -5102,6 +5129,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
{
u32 reg, data;
+ amdgpu_gfx_off_ctrl(adev, false);
+
reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
if (amdgpu_sriov_is_pp_one_vf(adev))
data = RREG32_NO_KIQ(reg);
@@ -5115,6 +5144,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
else
WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+ amdgpu_gfx_off_ctrl(adev, true);
}
static bool gfx_v9_0_check_rlcg_range(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index bda1542ef1dd..480e41847d7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -348,6 +348,10 @@ static void gfxhub_v1_0_gart_disable(struct amdgpu_device *adev)
WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT0_CNTL,
i * hub->ctx_distance, 0);
+ if (amdgpu_sriov_vf(adev))
+ /* Avoid write to GMC registers */
+ return;
+
/* Setup TLB control */
tmp = RREG32_SOC15(GC, 0, mmMC_VM_MX_L1_TLB_CNTL);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
index 497b86c376c6..90f0aefbdb39 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@@ -54,15 +54,17 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
seg_size = REG_GET_FIELD(
RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE_ALDE),
MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+ max_region =
+ REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE, PF_MAX_REGION);
} else {
xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL);
seg_size = REG_GET_FIELD(
RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE),
MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+ max_region =
+ REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
}
- max_region =
- REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
switch (adev->asic_type) {
@@ -89,9 +91,15 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes)
return -EINVAL;
- adev->gmc.xgmi.physical_node_id =
- REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
- PF_LFB_REGION);
+ if (adev->asic_type == CHIP_ALDEBARAN) {
+ adev->gmc.xgmi.physical_node_id =
+ REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE,
+ PF_LFB_REGION);
+ } else {
+ adev->gmc.xgmi.physical_node_id =
+ REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
+ PF_LFB_REGION);
+ }
if (adev->gmc.xgmi.physical_node_id > max_physical_node_id)
return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 1d8414c3fadb..38241cf0e1f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -160,6 +160,7 @@ static int navi10_ih_toggle_ring_interrupts(struct amdgpu_device *adev,
tmp = RREG32(ih_regs->ih_rb_cntl);
tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_ENABLE, (enable ? 1 : 0));
+ tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_GPU_TS_ENABLE, 1);
/* enable_intr field is only valid in ring0 */
if (ih == &adev->irq.ih)
tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0));
@@ -275,10 +276,8 @@ static int navi10_ih_enable_ring(struct amdgpu_device *adev,
tmp = navi10_ih_rb_cntl(ih, tmp);
if (ih == &adev->irq.ih)
tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RPTR_REARM, !!adev->irq.msi_enabled);
- if (ih == &adev->irq.ih1) {
- tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0);
+ if (ih == &adev->irq.ih1)
tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1);
- }
if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) {
if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
@@ -319,7 +318,6 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
{
struct amdgpu_ih_ring *ih[] = {&adev->irq.ih, &adev->irq.ih1, &adev->irq.ih2};
u32 ih_chicken;
- u32 tmp;
int ret;
int i;
@@ -363,15 +361,6 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
adev->nbio.funcs->ih_doorbell_range(adev, ih[0]->use_doorbell,
ih[0]->doorbell_index);
- tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
- tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL,
- CLIENT18_IS_STORM_CLIENT, 1);
- WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp);
-
- tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL);
- tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1);
- WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp);
-
pci_set_master(adev->pdev);
/* enable interrupts */
@@ -420,12 +409,19 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
u32 wptr, tmp;
struct amdgpu_ih_regs *ih_regs;
- wptr = le32_to_cpu(*ih->wptr_cpu);
- ih_regs = &ih->ih_regs;
+ if (ih == &adev->irq.ih) {
+ /* Only ring0 supports writeback. On other rings fall back
+ * to register-based code with overflow checking below.
+ */
+ wptr = le32_to_cpu(*ih->wptr_cpu);
- if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
- goto out;
+ if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+ goto out;
+ }
+ ih_regs = &ih->ih_regs;
+
+ /* Double check that the overflow wasn't already cleared. */
wptr = RREG32_NO_KIQ(ih_regs->ih_rb_wptr);
if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
goto out;
@@ -513,15 +509,11 @@ static int navi10_ih_self_irq(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
{
- uint32_t wptr = cpu_to_le32(entry->src_data[0]);
-
switch (entry->ring_id) {
case 1:
- *adev->irq.ih1.wptr_cpu = wptr;
schedule_work(&adev->irq.ih1_work);
break;
case 2:
- *adev->irq.ih2.wptr_cpu = wptr;
schedule_work(&adev->irq.ih2_work);
break;
default: break;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index 4ecd2b5808ce..ee7cab37dfd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -359,6 +359,10 @@ static void nbio_v2_3_init_registers(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnPCIE_CONFIG_CNTL, data);
+
+ if (amdgpu_sriov_vf(adev))
+ adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+ mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
}
#define NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT 0x00000000 // off by default, no gains over L1
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 0d2d629e2d6a..4bbacf1be25a 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -276,6 +276,10 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE(smnPCIE_CI_CNTL, data);
+
+ if (amdgpu_sriov_vf(adev))
+ adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+ mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
}
static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index 3c00666a13e1..37a4039fdfc5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -273,7 +273,9 @@ const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = {
static void nbio_v7_0_init_registers(struct amdgpu_device *adev)
{
-
+ if (amdgpu_sriov_vf(adev))
+ adev->rmmio_remap.reg_offset =
+ SOC15_REG_OFFSET(NBIO, 0, mmHDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
}
const struct amdgpu_nbio_funcs nbio_v7_0_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
index 8f2a315e7c73..3444332ea110 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
@@ -371,6 +371,10 @@ static void nbio_v7_2_init_registers(struct amdgpu_device *adev)
if (def != data)
WREG32_PCIE_PORT(SOC15_REG_OFFSET(NBIO, 0, regPCIE_CONFIG_CNTL), data);
}
+
+ if (amdgpu_sriov_vf(adev))
+ adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+ regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
}
const struct amdgpu_nbio_funcs nbio_v7_2_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index b8bd03d16dba..dc5e93756fea 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -362,7 +362,9 @@ const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg_ald = {
static void nbio_v7_4_init_registers(struct amdgpu_device *adev)
{
-
+ if (amdgpu_sriov_vf(adev))
+ adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+ mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
}
static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev)
@@ -692,6 +694,9 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
{
uint32_t def, data;
+ if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4))
+ return;
+
def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK;
data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index febc903adf58..2ec1ffb36b1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -182,6 +182,8 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
{
switch (adev->ip_versions[UVD_HWIP][0]) {
case IP_VERSION(3, 0, 0):
+ case IP_VERSION(3, 0, 64):
+ case IP_VERSION(3, 0, 192):
if (amdgpu_sriov_vf(adev)) {
if (encode)
*codecs = &sriov_sc_video_codecs_encode;
@@ -730,8 +732,10 @@ static int nv_common_early_init(void *handle)
#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
- adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+ if (!amdgpu_sriov_vf(adev)) {
+ adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
+ adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+ }
adev->smc_rreg = NULL;
adev->smc_wreg = NULL;
adev->pcie_rreg = &nv_pcie_rreg;
@@ -1031,7 +1035,7 @@ static int nv_common_hw_init(void *handle)
* for the purpose of expose those registers
* to process space
*/
- if (adev->nbio.funcs->remap_hdp_registers)
+ if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
adev->nbio.funcs->remap_hdp_registers(adev);
/* enable the doorbell aperture */
nv_enable_doorbell_aperture(adev, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 0c316a2d42ed..de9b55383e9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -971,8 +971,10 @@ static int soc15_common_early_init(void *handle)
#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
- adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+ if (!amdgpu_sriov_vf(adev)) {
+ adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
+ adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+ }
adev->smc_rreg = NULL;
adev->smc_wreg = NULL;
adev->pcie_rreg = &soc15_pcie_rreg;
@@ -1285,7 +1287,7 @@ static int soc15_common_hw_init(void *handle)
* for the purpose of expose those registers
* to process space
*/
- if (adev->nbio.funcs->remap_hdp_registers)
+ if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
adev->nbio.funcs->remap_hdp_registers(adev);
/* enable the doorbell aperture */
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index d5d023a24269..2d558c2f417d 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -534,6 +534,19 @@ static int uvd_v6_0_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+ if (RREG32(mmUVD_STATUS) != 0)
+ uvd_v6_0_stop(adev);
+
+ return 0;
+}
+
+static int uvd_v6_0_suspend(void *handle)
+{
+ int r;
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
/*
* Proper cleanups before halting the HW engine:
* - cancel the delayed idle work
@@ -558,17 +571,6 @@ static int uvd_v6_0_hw_fini(void *handle)
AMD_CG_STATE_GATE);
}
- if (RREG32(mmUVD_STATUS) != 0)
- uvd_v6_0_stop(adev);
-
- return 0;
-}
-
-static int uvd_v6_0_suspend(void *handle)
-{
- int r;
- struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
r = uvd_v6_0_hw_fini(adev);
if (r)
return r;