summaryrefslogtreecommitdiffstats
path: root/drivers/gpu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c21
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c36
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_job.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c36
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_object.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c38
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c20
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c35
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c54
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c13
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c15
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc15.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c31
-rw-r--r--drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c33
-rw-r--r--drivers/gpu/drm/amd/display/dc/calcs/Makefile19
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c24
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc_resource.c6
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c22
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn20/Makefile19
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c7
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn21/Makefile19
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/Makefile19
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dsc/Makefile19
-rw-r--r--drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c4
-rw-r--r--drivers/gpu/drm/amd/powerplay/navi10_ppt.c2
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c2
-rw-r--r--drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c2
-rw-r--r--drivers/gpu/drm/amd/powerplay/vega20_ppt.c2
-rw-r--r--drivers/gpu/drm/arm/display/komeda/komeda_kms.c3
-rw-r--r--drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c4
-rw-r--r--drivers/gpu/drm/bridge/tc358767.c7
-rw-r--r--drivers/gpu/drm/drm_atomic_helper.c15
-rw-r--r--drivers/gpu/drm/drm_edid.c3
-rw-r--r--drivers/gpu/drm/drm_self_refresh_helper.c18
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_dump.c4
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c6
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_mmu.c17
-rw-r--r--drivers/gpu/drm/i915/display/intel_bios.c22
-rw-r--r--drivers/gpu/drm/i915/display/intel_crt.c7
-rw-r--r--drivers/gpu/drm/i915/display/intel_display.c26
-rw-r--r--drivers/gpu/drm/i915/display/intel_display_power.c3
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp.c12
-rw-r--r--drivers/gpu/drm/i915/display/intel_dpll_mgr.c15
-rw-r--r--drivers/gpu/drm/i915/display/intel_dpll_mgr.h4
-rw-r--r--drivers/gpu/drm/i915/display/intel_hdmi.c6
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_context.c5
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_context_types.h7
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c111
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_mman.c19
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_object.h6
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_object_types.h3
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_pm.c3
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_userptr.c1
-rw-r--r--drivers/gpu/drm/i915/gt/intel_engine.h14
-rw-r--r--drivers/gpu/drm/i915/gt/intel_engine_cs.c16
-rw-r--r--drivers/gpu/drm/i915/gt/intel_engine_types.h13
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt_pm.c8
-rw-r--r--drivers/gpu/drm/i915/gt/intel_lrc.c164
-rw-r--r--drivers/gpu/drm/i915/gt/intel_mocs.c10
-rw-r--r--drivers/gpu/drm/i915/gt/intel_reset.c12
-rw-r--r--drivers/gpu/drm/i915/gt/intel_reset.h2
-rw-r--r--drivers/gpu/drm/i915/gt/intel_ringbuffer.c2
-rw-r--r--drivers/gpu/drm/i915/gt/intel_workarounds.c3
-rw-r--r--drivers/gpu/drm/i915/gvt/dmabuf.c4
-rw-r--r--drivers/gpu/drm/i915/i915_cmd_parser.c435
-rw-r--r--drivers/gpu/drm/i915/i915_drv.c12
-rw-r--r--drivers/gpu/drm/i915/i915_drv.h33
-rw-r--r--drivers/gpu/drm/i915/i915_gem.c19
-rw-r--r--drivers/gpu/drm/i915/i915_gem.h6
-rw-r--r--drivers/gpu/drm/i915/i915_getparam.c2
-rw-r--r--drivers/gpu/drm/i915/i915_reg.h10
-rw-r--r--drivers/gpu/drm/i915/i915_request.c69
-rw-r--r--drivers/gpu/drm/i915/i915_request.h2
-rw-r--r--drivers/gpu/drm/i915/intel_pch.c1
-rw-r--r--drivers/gpu/drm/i915/intel_pch.h1
-rw-r--r--drivers/gpu/drm/i915/intel_pm.c122
-rw-r--r--drivers/gpu/drm/i915/intel_pm.h3
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem.c6
-rw-r--r--drivers/gpu/drm/msm/dsi/dsi_host.c6
-rw-r--r--drivers/gpu/drm/panel/panel-lg-lb035q02.c9
-rw-r--r--drivers/gpu/drm/panel/panel-nec-nl8048hl11.c9
-rw-r--r--drivers/gpu/drm/panel/panel-sony-acx565akm.c9
-rw-r--r--drivers/gpu/drm/panel/panel-tpo-td028ttec1.c3
-rw-r--r--drivers/gpu/drm/panel/panel-tpo-td043mtea1.c9
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_drv.c2
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_gpu.c3
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_job.c16
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_mmu.c15
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_perfcnt.c1
-rw-r--r--drivers/gpu/drm/radeon/radeon_drv.c12
-rw-r--r--drivers/gpu/drm/radeon/si_dpm.c1
-rw-r--r--drivers/gpu/drm/scheduler/sched_main.c19
-rw-r--r--drivers/gpu/drm/sun4i/sun4i_tcon.c2
-rw-r--r--drivers/gpu/drm/tiny/Kconfig1
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo.c9
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo_vm.c16
-rw-r--r--drivers/gpu/drm/v3d/v3d_gem.c5
-rw-r--r--drivers/gpu/drm/xen/xen_drm_front.c12
110 files changed, 1464 insertions, 567 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 7bcf86c61999..85b0515c0fdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -140,7 +140,12 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
return 0;
error_free:
- while (i--) {
+ for (i = 0; i < last_entry; ++i) {
+ struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
+
+ amdgpu_bo_unref(&bo);
+ }
+ for (i = first_userptr; i < num_entries; ++i) {
struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
amdgpu_bo_unref(&bo);
@@ -270,7 +275,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
r = amdgpu_bo_create_list_entry_array(&args->in, &info);
if (r)
- goto error_free;
+ return r;
switch (args->in.operation) {
case AMDGPU_BO_LIST_OP_CREATE:
@@ -283,8 +288,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
mutex_unlock(&fpriv->bo_list_lock);
if (r < 0) {
- amdgpu_bo_list_put(list);
- return r;
+ goto error_put_list;
}
handle = r;
@@ -306,9 +310,8 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
mutex_unlock(&fpriv->bo_list_lock);
if (IS_ERR(old)) {
- amdgpu_bo_list_put(list);
r = PTR_ERR(old);
- goto error_free;
+ goto error_put_list;
}
amdgpu_bo_list_put(old);
@@ -325,8 +328,10 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
return 0;
+error_put_list:
+ amdgpu_bo_list_put(list);
+
error_free:
- if (info)
- kvfree(info);
+ kvfree(info);
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 2e53feed40e2..82823d9a8ba8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -536,7 +536,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
list_for_each_entry(lobj, validated, tv.head) {
struct amdgpu_bo *bo = ttm_to_amdgpu_bo(lobj->tv.bo);
- bool binding_userptr = false;
struct mm_struct *usermm;
usermm = amdgpu_ttm_tt_get_usermm(bo->tbo.ttm);
@@ -553,7 +552,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
lobj->user_pages);
- binding_userptr = true;
}
if (p->evictable == lobj)
@@ -563,10 +561,8 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
if (r)
return r;
- if (binding_userptr) {
- kvfree(lobj->user_pages);
- lobj->user_pages = NULL;
- }
+ kvfree(lobj->user_pages);
+ lobj->user_pages = NULL;
}
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 6614d8a6f4c8..2cdaf3b2a721 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -604,8 +604,11 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
continue;
}
- for (i = 0; i < num_entities; i++)
+ for (i = 0; i < num_entities; i++) {
+ mutex_lock(&ctx->adev->lock_reset);
drm_sched_entity_fini(&ctx->entities[0][i].entity);
+ mutex_unlock(&ctx->adev->lock_reset);
+ }
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5a1939dbd4e3..7a6c837c0a85 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2885,6 +2885,13 @@ fence_driver_init:
DRM_INFO("amdgpu: acceleration disabled, skipping benchmarks\n");
}
+ /*
+ * Register gpu instance before amdgpu_device_enable_mgpu_fan_boost.
+ * Otherwise the mgpu fan boost feature will be skipped due to the
+ * gpu instance is counted less.
+ */
+ amdgpu_register_gpu_instance(adev);
+
/* enable clockgating, etc. after ib tests, etc. since some blocks require
* explicit gating rather than handling it automatically.
*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 6f8aaf655a9f..e1c15721611a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1016,6 +1016,7 @@ static const struct pci_device_id pciidlist[] = {
{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+ {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
/* Renoir */
{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
@@ -1048,6 +1049,41 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
return -ENODEV;
}
+#ifdef CONFIG_DRM_AMDGPU_SI
+ if (!amdgpu_si_support) {
+ switch (flags & AMD_ASIC_MASK) {
+ case CHIP_TAHITI:
+ case CHIP_PITCAIRN:
+ case CHIP_VERDE:
+ case CHIP_OLAND:
+ case CHIP_HAINAN:
+ dev_info(&pdev->dev,
+ "SI support provided by radeon.\n");
+ dev_info(&pdev->dev,
+ "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
+ );
+ return -ENODEV;
+ }
+ }
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+ if (!amdgpu_cik_support) {
+ switch (flags & AMD_ASIC_MASK) {
+ case CHIP_KAVERI:
+ case CHIP_BONAIRE:
+ case CHIP_HAWAII:
+ case CHIP_KABINI:
+ case CHIP_MULLINS:
+ dev_info(&pdev->dev,
+ "CIK support provided by radeon.\n");
+ dev_info(&pdev->dev,
+ "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
+ );
+ return -ENODEV;
+ }
+ }
+#endif
+
/* Get rid of things like offb */
ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "amdgpudrmfb");
if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 6ee4021910e2..6d19183b478b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -289,6 +289,7 @@ struct amdgpu_gfx {
uint32_t mec2_feature_version;
bool mec_fw_write_wait;
bool me_fw_write_wait;
+ bool cp_fw_write_wait;
struct amdgpu_ring gfx_ring[AMDGPU_MAX_GFX_RINGS];
unsigned num_gfx_rings;
struct amdgpu_ring compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9d76e0923a5a..96b2a31ccfed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -218,7 +218,7 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
struct dma_fence *fence = NULL, *finished;
struct amdgpu_job *job;
- int r;
+ int r = 0;
job = to_amdgpu_job(sched_job);
finished = &job->base.s_fence->finished;
@@ -243,6 +243,8 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
job->fence = dma_fence_get(fence);
amdgpu_job_free_resources(job);
+
+ fence = r ? ERR_PTR(r) : fence;
return fence;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index f2c097983f48..a042ef471fbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -144,41 +144,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
struct amdgpu_device *adev;
int r, acpi_status;
-#ifdef CONFIG_DRM_AMDGPU_SI
- if (!amdgpu_si_support) {
- switch (flags & AMD_ASIC_MASK) {
- case CHIP_TAHITI:
- case CHIP_PITCAIRN:
- case CHIP_VERDE:
- case CHIP_OLAND:
- case CHIP_HAINAN:
- dev_info(dev->dev,
- "SI support provided by radeon.\n");
- dev_info(dev->dev,
- "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
- );
- return -ENODEV;
- }
- }
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
- if (!amdgpu_cik_support) {
- switch (flags & AMD_ASIC_MASK) {
- case CHIP_KAVERI:
- case CHIP_BONAIRE:
- case CHIP_HAWAII:
- case CHIP_KABINI:
- case CHIP_MULLINS:
- dev_info(dev->dev,
- "CIK support provided by radeon.\n");
- dev_info(dev->dev,
- "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
- );
- return -ENODEV;
- }
- }
-#endif
-
adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL);
if (adev == NULL) {
return -ENOMEM;
@@ -225,7 +190,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
pm_runtime_put_autosuspend(dev->dev);
}
- amdgpu_register_gpu_instance(adev);
out:
if (r) {
/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 1fead0e8b890..7289e1b4fb60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -453,7 +453,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
.interruptible = (bp->type != ttm_bo_type_kernel),
.no_wait_gpu = false,
.resv = bp->resv,
- .flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
+ .flags = bp->type != ttm_bo_type_kernel ?
+ TTM_OPT_FLAG_ALLOW_RES_EVICT : 0
};
struct amdgpu_bo *bo;
unsigned long page_align, size = bp->size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 4d71537a960d..a46090071034 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -950,21 +950,7 @@ static void psp_print_fw_hdr(struct psp_context *psp,
struct amdgpu_firmware_info *ucode)
{
struct amdgpu_device *adev = psp->adev;
- const struct sdma_firmware_header_v1_0 *sdma_hdr =
- (const struct sdma_firmware_header_v1_0 *)
- adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
- const struct gfx_firmware_header_v1_0 *ce_hdr =
- (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
- const struct gfx_firmware_header_v1_0 *pfp_hdr =
- (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
- const struct gfx_firmware_header_v1_0 *me_hdr =
- (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
- const struct gfx_firmware_header_v1_0 *mec_hdr =
- (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
- const struct rlc_firmware_header_v2_0 *rlc_hdr =
- (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
- const struct smc_firmware_header_v1_0 *smc_hdr =
- (const struct smc_firmware_header_v1_0 *)adev->pm.fw->data;
+ struct common_firmware_header *hdr;
switch (ucode->ucode_id) {
case AMDGPU_UCODE_ID_SDMA0:
@@ -975,25 +961,33 @@ static void psp_print_fw_hdr(struct psp_context *psp,
case AMDGPU_UCODE_ID_SDMA5:
case AMDGPU_UCODE_ID_SDMA6:
case AMDGPU_UCODE_ID_SDMA7:
- amdgpu_ucode_print_sdma_hdr(&sdma_hdr->header);
+ hdr = (struct common_firmware_header *)
+ adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
+ amdgpu_ucode_print_sdma_hdr(hdr);
break;
case AMDGPU_UCODE_ID_CP_CE:
- amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
+ hdr = (struct common_firmware_header *)adev->gfx.ce_fw->data;
+ amdgpu_ucode_print_gfx_hdr(hdr);
break;
case AMDGPU_UCODE_ID_CP_PFP:
- amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
+ hdr = (struct common_firmware_header *)adev->gfx.pfp_fw->data;
+ amdgpu_ucode_print_gfx_hdr(hdr);
break;
case AMDGPU_UCODE_ID_CP_ME:
- amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
+ hdr = (struct common_firmware_header *)adev->gfx.me_fw->data;
+ amdgpu_ucode_print_gfx_hdr(hdr);
break;
case AMDGPU_UCODE_ID_CP_MEC1:
- amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
+ hdr = (struct common_firmware_header *)adev->gfx.mec_fw->data;
+ amdgpu_ucode_print_gfx_hdr(hdr);
break;
case AMDGPU_UCODE_ID_RLC_G:
- amdgpu_ucode_print_rlc_hdr(&rlc_hdr->header);
+ hdr = (struct common_firmware_header *)adev->gfx.rlc_fw->data;
+ amdgpu_ucode_print_rlc_hdr(hdr);
break;
case AMDGPU_UCODE_ID_SMC:
- amdgpu_ucode_print_smc_hdr(&smc_hdr->header);
+ hdr = (struct common_firmware_header *)adev->pm.fw->data;
+ amdgpu_ucode_print_smc_hdr(hdr);
break;
default:
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index b70b3c45bb29..65044b1b3d4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -429,13 +429,14 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
* Open up a stream for HW test
*/
int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+ struct amdgpu_bo *bo,
struct dma_fence **fence)
{
const unsigned ib_size_dw = 1024;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -444,7 +445,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
/* stitch together an VCE create msg */
ib->length_dw = 0;
@@ -476,8 +477,8 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
ib->ptr[ib->length_dw++] = 0x00000014; /* len */
ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x00000001;
for (i = ib->length_dw; i < ib_size_dw; ++i)
@@ -1110,13 +1111,20 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring)
int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
{
struct dma_fence *fence = NULL;
+ struct amdgpu_bo *bo = NULL;
long r;
/* skip vce ring1/2 ib test for now, since it's not reliable */
if (ring != &ring->adev->vce.ring[0])
return 0;
- r = amdgpu_vce_get_create_msg(ring, 1, NULL);
+ r = amdgpu_bo_create_reserved(ring->adev, 512, PAGE_SIZE,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ &bo, NULL, NULL);
+ if (r)
+ return r;
+
+ r = amdgpu_vce_get_create_msg(ring, 1, bo, NULL);
if (r)
goto error;
@@ -1132,5 +1140,7 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
error:
dma_fence_put(fence);
+ amdgpu_bo_unreserve(bo);
+ amdgpu_bo_unref(&bo);
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index 30ea54dd9117..e802f7d9db0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -59,6 +59,7 @@ int amdgpu_vce_entity_init(struct amdgpu_device *adev);
int amdgpu_vce_suspend(struct amdgpu_device *adev);
int amdgpu_vce_resume(struct amdgpu_device *adev);
int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+ struct amdgpu_bo *bo,
struct dma_fence **fence);
int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
bool direct, struct dma_fence **fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 7a6beb2e7c4e..3199e4a5ff12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -569,13 +569,14 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring)
}
static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
- struct dma_fence **fence)
+ struct amdgpu_bo *bo,
+ struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -583,14 +584,14 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
ib->ptr[ib->length_dw++] = handle;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x0000000b;
ib->ptr[ib->length_dw++] = 0x00000014;
@@ -621,13 +622,14 @@ err:
}
static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
- struct dma_fence **fence)
+ struct amdgpu_bo *bo,
+ struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -635,14 +637,14 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001;
ib->ptr[ib->length_dw++] = handle;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x0000000b;
ib->ptr[ib->length_dw++] = 0x00000014;
@@ -675,13 +677,20 @@ err:
int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
{
struct dma_fence *fence = NULL;
+ struct amdgpu_bo *bo = NULL;
long r;
- r = amdgpu_vcn_enc_get_create_msg(ring, 1, NULL);
+ r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ &bo, NULL, NULL);
+ if (r)
+ return r;
+
+ r = amdgpu_vcn_enc_get_create_msg(ring, 1, bo, NULL);
if (r)
goto error;
- r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, &fence);
+ r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, bo, &fence);
if (r)
goto error;
@@ -693,6 +702,8 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
error:
dma_fence_put(fence);
+ amdgpu_bo_unreserve(bo);
+ amdgpu_bo_unref(&bo);
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 957811b73672..53090eae0082 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -93,7 +93,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
{
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_CPF_CLK_CTRL, 0xfcff8fff, 0xf8000100),
- SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0x60000ff0, 0x60000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000000, 0x40000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -140,7 +140,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x003c0014),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
- SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xf8ff0fff, 0x60000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000ff0, 0x40000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -179,7 +179,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x003e001f, 0x003c0014),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
- SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0xc0000100),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0x0d000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xffffcfff, 0x60000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0xffff0fff, 0x40000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -564,6 +564,32 @@ static void gfx_v10_0_free_microcode(struct amdgpu_device *adev)
kfree(adev->gfx.rlc.register_list_format);
}
+static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev)
+{
+ adev->gfx.cp_fw_write_wait = false;
+
+ switch (adev->asic_type) {
+ case CHIP_NAVI10:
+ case CHIP_NAVI12:
+ case CHIP_NAVI14:
+ if ((adev->gfx.me_fw_version >= 0x00000046) &&
+ (adev->gfx.me_feature_version >= 27) &&
+ (adev->gfx.pfp_fw_version >= 0x00000068) &&
+ (adev->gfx.pfp_feature_version >= 27) &&
+ (adev->gfx.mec_fw_version >= 0x0000005b) &&
+ (adev->gfx.mec_feature_version >= 27))
+ adev->gfx.cp_fw_write_wait = true;
+ break;
+ default:
+ break;
+ }
+
+ if (adev->gfx.cp_fw_write_wait == false)
+ DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
+ GRBM requires 1-cycle delay in cp firmware\n");
+}
+
+
static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
{
const struct rlc_firmware_header_v2_1 *rlc_hdr;
@@ -832,6 +858,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
}
}
+ gfx_v10_0_check_fw_write_wait(adev);
out:
if (err) {
dev_err(adev->dev,
@@ -4765,6 +4792,24 @@ static void gfx_v10_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
gfx_v10_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20);
}
+static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+ uint32_t reg0, uint32_t reg1,
+ uint32_t ref, uint32_t mask)
+{
+ int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
+ struct amdgpu_device *adev = ring->adev;
+ bool fw_version_ok = false;
+
+ fw_version_ok = adev->gfx.cp_fw_write_wait;
+
+ if (fw_version_ok)
+ gfx_v10_0_wait_reg_mem(ring, usepfp, 0, 1, reg0, reg1,
+ ref, mask, 0x20);
+ else
+ amdgpu_ring_emit_reg_write_reg_wait_helper(ring, reg0, reg1,
+ ref, mask);
+}
+
static void
gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
uint32_t me, uint32_t pipe,
@@ -5155,6 +5200,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
.emit_tmz = gfx_v10_0_ring_emit_tmz,
.emit_wreg = gfx_v10_0_ring_emit_wreg,
.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+ .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
};
static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
@@ -5188,6 +5234,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
.pad_ib = amdgpu_ring_generic_pad_ib,
.emit_wreg = gfx_v10_0_ring_emit_wreg,
.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+ .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
};
static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
@@ -5218,6 +5265,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
.emit_rreg = gfx_v10_0_ring_emit_rreg,
.emit_wreg = gfx_v10_0_ring_emit_wreg,
.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+ .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
};
static void gfx_v10_0_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index dcadc73bffd2..dfca83a2de47 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -973,6 +973,13 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
adev->gfx.me_fw_write_wait = false;
adev->gfx.mec_fw_write_wait = false;
+ if ((adev->gfx.mec_fw_version < 0x000001a5) ||
+ (adev->gfx.mec_feature_version < 46) ||
+ (adev->gfx.pfp_fw_version < 0x000000b7) ||
+ (adev->gfx.pfp_feature_version < 46))
+ DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
+ GRBM requires 1-cycle delay in cp firmware\n");
+
switch (adev->asic_type) {
case CHIP_VEGA10:
if ((adev->gfx.me_fw_version >= 0x0000009c) &&
@@ -1044,6 +1051,12 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
AMD_PG_SUPPORT_CP |
AMD_PG_SUPPORT_RLC_SMU_HS;
break;
+ case CHIP_RENOIR:
+ if (adev->pm.pp_feature & PP_GFXOFF_MASK)
+ adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+ AMD_PG_SUPPORT_CP |
+ AMD_PG_SUPPORT_RLC_SMU_HS;
+ break;
default:
break;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 8b789f750b72..db10640a3b2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -151,6 +151,15 @@ static void gfxhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL2, tmp);
tmp = mmGCVM_L2_CNTL3_DEFAULT;
+ if (adev->gmc.translate_further) {
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 12);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+ } else {
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 9);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+ }
WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL3, tmp);
tmp = mmGCVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 241a4e57cf4a..5c7d5f73f54f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -309,6 +309,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
job->vm_pd_addr = amdgpu_gmc_pd_addr(adev->gart.bo);
job->vm_needs_flush = true;
+ job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop;
amdgpu_ring_pad_ib(ring, &job->ibs[0]);
r = amdgpu_job_submit(job, &adev->mman.entity,
AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
@@ -343,11 +344,9 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
upper_32_bits(pd_addr));
- amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req);
-
- /* wait for the invalidate to complete */
- amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_ack + eng,
- 1 << vmid, 1 << vmid);
+ amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng,
+ hub->vm_inv_eng0_ack + eng,
+ req, 1 << vmid);
return pd_addr;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 3542c203c3c8..b39bea6f54e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -137,6 +137,15 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL2, tmp);
tmp = mmMMVM_L2_CNTL3_DEFAULT;
+ if (adev->gmc.translate_further) {
+ tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 12);
+ tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+ } else {
+ tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 9);
+ tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+ }
WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL3, tmp);
tmp = mmMMVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 0cf7ef44b4b5..9ed178fa241c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -219,6 +219,15 @@ static void mmhub_v9_4_init_cache_regs(struct amdgpu_device *adev, int hubid)
hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
tmp = mmVML2PF0_VM_L2_CNTL3_DEFAULT;
+ if (adev->gmc.translate_further) {
+ tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 12);
+ tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+ } else {
+ tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 9);
+ tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+ }
WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2PF0_VM_L2_CNTL3,
hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 78452cf0115d..4554e72c8378 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -254,6 +254,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+ SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
};
static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index fa2f70ce2e2b..8493bfbbc148 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1129,7 +1129,7 @@ static void sdma_v5_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, addr & 0xfffffffc);
amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
amdgpu_ring_write(ring, seq); /* reference */
- amdgpu_ring_write(ring, 0xfffffff); /* mask */
+ amdgpu_ring_write(ring, 0xffffffff); /* mask */
amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */
}
@@ -1173,6 +1173,16 @@ static void sdma_v5_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10));
}
+static void sdma_v5_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+ uint32_t reg0, uint32_t reg1,
+ uint32_t ref, uint32_t mask)
+{
+ amdgpu_ring_emit_wreg(ring, reg0, ref);
+ /* wait for a cycle to reset vm_inv_eng*_ack */
+ amdgpu_ring_emit_reg_wait(ring, reg0, 0, 0);
+ amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask);
+}
+
static int sdma_v5_0_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1588,7 +1598,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
6 + /* sdma_v5_0_ring_emit_pipeline_sync */
/* sdma_v5_0_ring_emit_vm_flush */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
- SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 * 2 +
10 + 10 + 10, /* sdma_v5_0_ring_emit_fence x3 for user fence, vm fence */
.emit_ib_size = 7 + 6, /* sdma_v5_0_ring_emit_ib */
.emit_ib = sdma_v5_0_ring_emit_ib,
@@ -1602,6 +1612,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
.pad_ib = sdma_v5_0_ring_pad_ib,
.emit_wreg = sdma_v5_0_ring_emit_wreg,
.emit_reg_wait = sdma_v5_0_ring_emit_reg_wait,
+ .emit_reg_write_reg_wait = sdma_v5_0_ring_emit_reg_write_reg_wait,
.init_cond_exec = sdma_v5_0_ring_init_cond_exec,
.patch_cond_exec = sdma_v5_0_ring_patch_cond_exec,
.preempt_ib = sdma_v5_0_ring_preempt_ib,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index f8ab80c8801b..4ccfcdf8f16a 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1186,11 +1186,6 @@ static int soc15_common_early_init(void *handle)
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_VCN_DPG;
adev->external_rev_id = adev->rev_id + 0x91;
-
- if (adev->pm.pp_feature & PP_GFXOFF_MASK)
- adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
- AMD_PG_SUPPORT_CP |
- AMD_PG_SUPPORT_RLC_SMU_HS;
break;
default:
/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 670784a78512..217084d56ab8 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -206,13 +206,14 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring)
* Open up a stream for HW test
*/
static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+ struct amdgpu_bo *bo,
struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -220,15 +221,15 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
ib->ptr[ib->length_dw++] = handle;
ib->ptr[ib->length_dw++] = 0x00010000;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x00000014;
ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -268,13 +269,14 @@ err:
*/
static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
uint32_t handle,
+ struct amdgpu_bo *bo,
struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -282,15 +284,15 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
ib->ptr[ib->length_dw++] = handle;
ib->ptr[ib->length_dw++] = 0x00010000;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x00000014;
ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -327,13 +329,20 @@ err:
static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
{
struct dma_fence *fence = NULL;
+ struct amdgpu_bo *bo = NULL;
long r;
- r = uvd_v6_0_enc_get_create_msg(ring, 1, NULL);
+ r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ &bo, NULL, NULL);
+ if (r)
+ return r;
+
+ r = uvd_v6_0_enc_get_create_msg(ring, 1, bo, NULL);
if (r)
goto error;
- r = uvd_v6_0_enc_get_destroy_msg(ring, 1, &fence);
+ r = uvd_v6_0_enc_get_destroy_msg(ring, 1, bo, &fence);
if (r)
goto error;
@@ -345,6 +354,8 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
error:
dma_fence_put(fence);
+ amdgpu_bo_unreserve(bo);
+ amdgpu_bo_unref(&bo);
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 01f658fa72c6..0995378d8263 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -214,13 +214,14 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
* Open up a stream for HW test
*/
static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+ struct amdgpu_bo *bo,
struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -228,15 +229,15 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
ib->ptr[ib->length_dw++] = handle;
ib->ptr[ib->length_dw++] = 0x00000000;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x00000014;
ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -275,13 +276,14 @@ err:
* Close up a stream for HW test or if userspace failed to do so
*/
static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
- struct dma_fence **fence)
+ struct amdgpu_bo *bo,
+ struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -289,15 +291,15 @@ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handl
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001;
ib->ptr[ib->length_dw++] = handle;
ib->ptr[ib->length_dw++] = 0x00000000;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x00000014;
ib->ptr[ib->length_dw++] = 0x00000002;
@@ -334,13 +336,20 @@ err:
static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
{
struct dma_fence *fence = NULL;
+ struct amdgpu_bo *bo = NULL;
long r;
- r = uvd_v7_0_enc_get_create_msg(ring, 1, NULL);
+ r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ &bo, NULL, NULL);
+ if (r)
+ return r;
+
+ r = uvd_v7_0_enc_get_create_msg(ring, 1, bo, NULL);
if (r)
goto error;
- r = uvd_v7_0_enc_get_destroy_msg(ring, 1, &fence);
+ r = uvd_v7_0_enc_get_destroy_msg(ring, 1, bo, &fence);
if (r)
goto error;
@@ -352,6 +361,8 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
error:
dma_fence_put(fence);
+ amdgpu_bo_unreserve(bo);
+ amdgpu_bo_unref(&bo);
return r;
}
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 985633c08a26..26c6d735cdc7 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -24,15 +24,20 @@
# It calculates Bandwidth and Watermarks values for HW programming
#
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
- cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
- cc_stack_align := -mstack-alignment=16
-endif
+calcs_ccflags := -mhard-float -msse
-calcs_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+calcs_ccflags += -mpreferred-stack-boundary=4
+else
calcs_ccflags += -msse2
endif
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 5d1adeda4d90..4b8819c27fcd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -580,6 +580,10 @@ static bool construct(struct dc *dc,
#ifdef CONFIG_DRM_AMD_DC_DCN2_0
// Allocate memory for the vm_helper
dc->vm_helper = kzalloc(sizeof(struct vm_helper), GFP_KERNEL);
+ if (!dc->vm_helper) {
+ dm_error("%s: failed to create dc->vm_helper\n", __func__);
+ goto fail;
+ }
#endif
memcpy(&dc->bb_overrides, &init_params->bb_overrides, sizeof(dc->bb_overrides));
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 505967b48e14..51991bf26a93 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -374,6 +374,7 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
enum display_dongle_type *dongle = &sink_cap->dongle_type;
uint8_t type2_dongle_buf[DP_ADAPTOR_TYPE2_SIZE];
bool is_type2_dongle = false;
+ int retry_count = 2;
struct dp_hdmi_dongle_signature_data *dongle_signature;
/* Assume we have no valid DP passive dongle connected */
@@ -386,13 +387,24 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
DP_HDMI_DONGLE_ADDRESS,
type2_dongle_buf,
sizeof(type2_dongle_buf))) {
- *dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
- sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
+ /* Passive HDMI dongles can sometimes fail here without retrying*/
+ while (retry_count > 0) {
+ if (i2c_read(ddc,
+ DP_HDMI_DONGLE_ADDRESS,
+ type2_dongle_buf,
+ sizeof(type2_dongle_buf)))
+ break;
+ retry_count--;
+ }
+ if (retry_count == 0) {
+ *dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
+ sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
- CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
- "DP-DVI passive dongle %dMhz: ",
- DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
- return;
+ CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
+ "DP-DVI passive dongle %dMhz: ",
+ DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
+ return;
+ }
}
/* Check if Type 2 dongle.*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 8f70295179ff..f25ac17f47fa 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -404,6 +404,9 @@ bool resource_are_streams_timing_synchronizable(
if (stream1->view_format != stream2->view_format)
return false;
+ if (stream1->ignore_msa_timing_param || stream2->ignore_msa_timing_param)
+ return false;
+
return true;
}
static bool is_dp_and_hdmi_sharable(
@@ -1540,6 +1543,9 @@ bool dc_is_stream_unchanged(
if (!are_stream_backends_same(old_stream, stream))
return false;
+ if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param)
+ return false;
+
return true;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 01c7e30b9ce1..bbd6e01b3eca 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -393,6 +393,10 @@ bool cm_helper_translate_curve_to_hw_format(
rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+ rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+ rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+ rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
// All 3 color channels have same x
corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
dc_fixpt_from_int(region_start));
@@ -464,13 +468,6 @@ bool cm_helper_translate_curve_to_hw_format(
i = 1;
while (i != hw_points + 1) {
- if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
- rgb_plus_1->red = rgb->red;
- if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
- rgb_plus_1->green = rgb->green;
- if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
- rgb_plus_1->blue = rgb->blue;
-
rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red);
rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
rgb->delta_blue = dc_fixpt_sub(rgb_plus_1->blue, rgb->blue);
@@ -562,6 +559,10 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+ rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+ rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+ rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
dc_fixpt_from_int(region_start));
corner_points[0].green.x = corner_points[0].red.x;
@@ -624,13 +625,6 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
i = 1;
while (i != hw_points + 1) {
- if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
- rgb_plus_1->red = rgb->red;
- if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
- rgb_plus_1->green = rgb->green;
- if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
- rgb_plus_1->blue = rgb->blue;
-
rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red);
rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
rgb->delta_blue = dc_fixpt_sub(rgb_plus_1->blue, rgb->blue);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index ddb8d5649e79..63f3bddba7da 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -10,15 +10,20 @@ ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
DCN20 += dcn20_dsc.o
endif
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
- cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
- cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse
-CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
+else
CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2
endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 5a2763daff4d..6b2f2f1a1c9c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -814,7 +814,7 @@ static const struct resource_caps res_cap_nv14 = {
.num_audio = 6,
.num_stream_encoder = 5,
.num_pll = 5,
- .num_dwb = 0,
+ .num_dwb = 1,
.num_ddc = 5,
};
@@ -1107,6 +1107,11 @@ struct stream_encoder *dcn20_stream_encoder_create(
if (!enc1)
return NULL;
+ if (ASICREV_IS_NAVI14_M(ctx->asic_id.hw_internal_rev)) {
+ if (eng_id >= ENGINE_ID_DIGD)
+ eng_id++;
+ }
+
dcn20_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id,
&stream_enc_regs[eng_id],
&se_shift, &se_mask);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index ef673bffc241..ff50ae71fe27 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -3,15 +3,20 @@
DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
- cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
- cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
+else
CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 5b2a65b42403..8df251626e22 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -24,15 +24,20 @@
# It provides the general basic services required by other DAL
# subcomponents.
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
- cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
- cc_stack_align := -mstack-alignment=16
-endif
+dml_ccflags := -mhard-float -msse
-dml_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dml_ccflags += -mpreferred-stack-boundary=4
+else
dml_ccflags += -msse2
endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 649883777f62..6c6c486b774a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
mode_lib->vba.MinActiveDRAMClockChangeMargin
+ mode_lib->vba.DRAMClockChangeLatency;
- if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+ if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+ mode_lib->vba.DRAMClockChangeWatermark += 25;
mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
} else {
if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) {
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index b456cd23c6fa..970737217e53 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -1,15 +1,20 @@
#
# Makefile for the 'dsc' sub-component of DAL.
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
- cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
- cc_stack_align := -mstack-alignment=16
-endif
+dsc_ccflags := -mhard-float -msse
-dsc_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dsc_ccflags += -mpreferred-stack-boundary=4
+else
dsc_ccflags += -msse2
endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index d08493b67b67..beacfffbdc3e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -5098,9 +5098,7 @@ static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr,
if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
- for (i = 0; i < podn_vdd_dep->count - 1; i++)
- od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
- if (od_vddc_lookup_table->entries[i].us_vdd < podn_vdd_dep->entries[i].vddc)
+ for (i = 0; i < podn_vdd_dep->count; i++)
od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
} else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) {
podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 0b461404af6b..3ec5a10a7c4d 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -205,7 +205,7 @@ static struct smu_11_0_cmn2aisc_mapping navi10_workload_map[PP_SMC_POWER_PROFILE
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT),
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT),
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT),
- WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT),
+ WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT),
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT),
};
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index dc754447f0dd..23c12018dbc1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -655,7 +655,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
count = SMU_MAX_SMIO_LEVELS;
for (level = 0; level < count; level++) {
table->SmioTable2.Pattern[level].Voltage =
- PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+ PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
table->SmioTable2.Pattern[level].Smio =
(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 7c960b07746f..ae18fbcb26fb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -456,7 +456,7 @@ static int vegam_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
count = SMU_MAX_SMIO_LEVELS;
for (level = 0; level < count; level++) {
table->SmioTable2.Pattern[level].Voltage = PP_HOST_TO_SMC_US(
- data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+ data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
table->SmioTable2.Pattern[level].Smio =
(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index bbd8ebd58434..92c393f613d3 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -219,7 +219,7 @@ static struct smu_11_0_cmn2aisc_mapping vega20_workload_map[PP_SMC_POWER_PROFILE
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT),
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT),
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT),
- WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT),
+ WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT),
WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT),
};
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index 8820ce15ce37..ae274902ff92 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -82,7 +82,8 @@ static void komeda_kms_commit_tail(struct drm_atomic_state *old_state)
drm_atomic_helper_commit_modeset_disables(dev, old_state);
- drm_atomic_helper_commit_planes(dev, old_state, 0);
+ drm_atomic_helper_commit_planes(dev, old_state,
+ DRM_PLANE_COMMIT_ACTIVE_ONLY);
drm_atomic_helper_commit_modeset_enables(dev, old_state);
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index ea26bc9c2d00..b848270e0a1f 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -564,8 +564,8 @@ komeda_splitter_validate(struct komeda_splitter *splitter,
}
if (!in_range(&splitter->vsize, dflow->in_h)) {
- DRM_DEBUG_ATOMIC("split in_in: %d exceed the acceptable range.\n",
- dflow->in_w);
+ DRM_DEBUG_ATOMIC("split in_h: %d exceeds the acceptable range.\n",
+ dflow->in_h);
return -EINVAL;
}
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index cebc8e620820..8a8d605021f0 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -728,6 +728,8 @@ static int tc_set_video_mode(struct tc_data *tc,
int lower_margin = mode->vsync_start - mode->vdisplay;
int vsync_len = mode->vsync_end - mode->vsync_start;
u32 dp0_syncval;
+ u32 bits_per_pixel = 24;
+ u32 in_bw, out_bw;
/*
* Recommended maximum number of symbols transferred in a transfer unit:
@@ -735,7 +737,10 @@ static int tc_set_video_mode(struct tc_data *tc,
* (output active video bandwidth in bytes))
* Must be less than tu_size.
*/
- max_tu_symbol = TU_SIZE_RECOMMENDED - 1;
+
+ in_bw = mode->clock * bits_per_pixel / 8;
+ out_bw = tc->link.base.num_lanes * tc->link.base.rate;
+ max_tu_symbol = DIV_ROUND_UP(in_bw * TU_SIZE_RECOMMENDED, out_bw);
dev_dbg(tc->dev, "set mode %dx%d\n",
mode->hdisplay, mode->vdisplay);
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 3ef2ac52ce94..2dd2cd87cdbb 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1581,8 +1581,11 @@ static void commit_tail(struct drm_atomic_state *old_state)
{
struct drm_device *dev = old_state->dev;
const struct drm_mode_config_helper_funcs *funcs;
+ struct drm_crtc_state *new_crtc_state;
+ struct drm_crtc *crtc;
ktime_t start;
s64 commit_time_ms;
+ unsigned int i, new_self_refresh_mask = 0;
funcs = dev->mode_config.helper_private;
@@ -1602,6 +1605,15 @@ static void commit_tail(struct drm_atomic_state *old_state)
drm_atomic_helper_wait_for_dependencies(old_state);
+ /*
+ * We cannot safely access new_crtc_state after
+ * drm_atomic_helper_commit_hw_done() so figure out which crtc's have
+ * self-refresh active beforehand:
+ */
+ for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i)
+ if (new_crtc_state->self_refresh_active)
+ new_self_refresh_mask |= BIT(i);
+
if (funcs && funcs->atomic_commit_tail)
funcs->atomic_commit_tail(old_state);
else
@@ -1610,7 +1622,8 @@ static void commit_tail(struct drm_atomic_state *old_state)
commit_time_ms = ktime_ms_delta(ktime_get(), start);
if (commit_time_ms > 0)
drm_self_refresh_helper_update_avg_times(old_state,
- (unsigned long)commit_time_ms);
+ (unsigned long)commit_time_ms,
+ new_self_refresh_mask);
drm_atomic_helper_commit_cleanup_done(old_state);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 82a4ceed3fcf..6b0177112e18 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -159,6 +159,9 @@ static const struct edid_quirk {
/* Medion MD 30217 PG */
{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
+ /* Lenovo G50 */
+ { "SDC", 18514, EDID_QUIRK_FORCE_6BPC },
+
/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
diff --git a/drivers/gpu/drm/drm_self_refresh_helper.c b/drivers/gpu/drm/drm_self_refresh_helper.c
index 68f4765a5896..dd33fec5aabd 100644
--- a/drivers/gpu/drm/drm_self_refresh_helper.c
+++ b/drivers/gpu/drm/drm_self_refresh_helper.c
@@ -133,29 +133,33 @@ out_drop_locks:
* drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages
* @state: the state which has just been applied to hardware
* @commit_time_ms: the amount of time in ms that this commit took to complete
+ * @new_self_refresh_mask: bitmask of crtc's that have self_refresh_active in
+ * new state
*
* Called after &drm_mode_config_funcs.atomic_commit_tail, this function will
* update the average entry/exit self refresh times on self refresh transitions.
* These averages will be used when calculating how long to delay before
* entering self refresh mode after activity.
*/
-void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
- unsigned int commit_time_ms)
+void
+drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
+ unsigned int commit_time_ms,
+ unsigned int new_self_refresh_mask)
{
struct drm_crtc *crtc;
- struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+ struct drm_crtc_state *old_crtc_state;
int i;
- for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
- new_crtc_state, i) {
+ for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
+ bool new_self_refresh_active = new_self_refresh_mask & BIT(i);
struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;
struct ewma_psr_time *time;
if (old_crtc_state->self_refresh_active ==
- new_crtc_state->self_refresh_active)
+ new_self_refresh_active)
continue;
- if (new_crtc_state->self_refresh_active)
+ if (new_self_refresh_active)
time = &sr_data->entry_avg_ms;
else
time = &sr_data->exit_avg_ms;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
index 698db540972c..648cf0207309 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
@@ -180,6 +180,8 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
etnaviv_cmdbuf_get_va(&submit->cmdbuf,
&gpu->mmu_context->cmdbuf_mapping));
+ mutex_unlock(&gpu->mmu_context->lock);
+
/* Reserve space for the bomap */
if (n_bomap_pages) {
bomap_start = bomap = iter.data;
@@ -221,8 +223,6 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
obj->base.size);
}
- mutex_unlock(&gpu->mmu_context->lock);
-
etnaviv_core_dump_header(&iter, ETDUMP_BUF_END, iter.data);
dev_coredumpv(gpu->dev, iter.start, iter.data - iter.start, GFP_KERNEL);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index 043111a1d60c..f8bf488e9d71 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -155,9 +155,11 @@ static void etnaviv_iommuv2_dump(struct etnaviv_iommu_context *context, void *bu
memcpy(buf, v2_context->mtlb_cpu, SZ_4K);
buf += SZ_4K;
- for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++, buf += SZ_4K)
- if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT)
+ for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++)
+ if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT) {
memcpy(buf, v2_context->stlb_cpu[i], SZ_4K);
+ buf += SZ_4K;
+ }
}
static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 35ebae6a1be7..3607d348c298 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -328,12 +328,23 @@ etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
ret = etnaviv_cmdbuf_suballoc_map(suballoc, ctx, &ctx->cmdbuf_mapping,
global->memory_base);
- if (ret) {
- global->ops->free(ctx);
- return NULL;
+ if (ret)
+ goto out_free;
+
+ if (global->version == ETNAVIV_IOMMU_V1 &&
+ ctx->cmdbuf_mapping.iova > 0x80000000) {
+ dev_err(global->dev,
+ "command buffer outside valid memory window\n");
+ goto out_unmap;
}
return ctx;
+
+out_unmap:
+ etnaviv_cmdbuf_suballoc_unmap(ctx, &ctx->cmdbuf_mapping);
+out_free:
+ global->ops->free(ctx);
+ return NULL;
}
void etnaviv_iommu_restore(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index efb39f350b19..3250c1b8dcca 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1270,7 +1270,7 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
"disabling port %c DVI/HDMI support\n",
port_name(port), info->alternate_ddc_pin,
- port_name(p), port_name(port));
+ port_name(p), port_name(p));
/*
* If we have multiple ports supposedly sharing the
@@ -1278,9 +1278,14 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
* port. Otherwise they share the same ddc bin and
* system couldn't communicate with them separately.
*
- * Give child device order the priority, first come first
- * served.
+ * Give inverse child device order the priority,
+ * last one wins. Yes, there are real machines
+ * (eg. Asrock B250M-HDV) where VBT has both
+ * port A and port E with the same AUX ch and
+ * we must pick port E :(
*/
+ info = &dev_priv->vbt.ddi_port_info[p];
+
info->supports_dvi = false;
info->supports_hdmi = false;
info->alternate_ddc_pin = 0;
@@ -1316,7 +1321,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
"disabling port %c DP support\n",
port_name(port), info->alternate_aux_channel,
- port_name(p), port_name(port));
+ port_name(p), port_name(p));
/*
* If we have multiple ports supposedlt sharing the
@@ -1324,9 +1329,14 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
* port. Otherwise they share the same aux channel
* and system couldn't communicate with them separately.
*
- * Give child device order the priority, first come first
- * served.
+ * Give inverse child device order the priority,
+ * last one wins. Yes, there are real machines
+ * (eg. Asrock B250M-HDV) where VBT has both
+ * port A and port E with the same AUX ch and
+ * we must pick port E :(
*/
+ info = &dev_priv->vbt.ddi_port_info[p];
+
info->supports_dp = false;
info->alternate_aux_channel = 0;
}
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index e6e8d4a82044..0a08354a6183 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -864,6 +864,13 @@ load_detect:
out:
intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref);
+
+ /*
+ * Make sure the refs for power wells enabled during detect are
+ * dropped to avoid a new detect cycle triggered by HPD polling.
+ */
+ intel_display_power_flush_work(dev_priv);
+
return status;
}
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index ce05e805b08f..dfff6f4357b8 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3280,7 +3280,20 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb,
switch (fb->modifier) {
case DRM_FORMAT_MOD_LINEAR:
case I915_FORMAT_MOD_X_TILED:
- return 4096;
+ /*
+ * Validated limit is 4k, but has 5k should
+ * work apart from the following features:
+ * - Ytile (already limited to 4k)
+ * - FP16 (already limited to 4k)
+ * - render compression (already limited to 4k)
+ * - KVMR sprite and cursor (don't care)
+ * - horizontal panning (TODO verify this)
+ * - pipe and plane scaling (TODO verify this)
+ */
+ if (cpp == 8)
+ return 4096;
+ else
+ return 5120;
case I915_FORMAT_MOD_Y_TILED_CCS:
case I915_FORMAT_MOD_Yf_TILED_CCS:
/* FIXME AUX plane? */
@@ -9302,7 +9315,6 @@ static bool wrpll_uses_pch_ssc(struct drm_i915_private *dev_priv,
static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
{
struct intel_encoder *encoder;
- bool pch_ssc_in_use = false;
bool has_fdi = false;
for_each_intel_encoder(&dev_priv->drm, encoder) {
@@ -9330,22 +9342,24 @@ static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
* clock hierarchy. That would also allow us to do
* clock bending finally.
*/
+ dev_priv->pch_ssc_use = 0;
+
if (spll_uses_pch_ssc(dev_priv)) {
DRM_DEBUG_KMS("SPLL using PCH SSC\n");
- pch_ssc_in_use = true;
+ dev_priv->pch_ssc_use |= BIT(DPLL_ID_SPLL);
}
if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL1)) {
DRM_DEBUG_KMS("WRPLL1 using PCH SSC\n");
- pch_ssc_in_use = true;
+ dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL1);
}
if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL2)) {
DRM_DEBUG_KMS("WRPLL2 using PCH SSC\n");
- pch_ssc_in_use = true;
+ dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL2);
}
- if (pch_ssc_in_use)
+ if (dev_priv->pch_ssc_use)
return;
if (has_fdi) {
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 12099760d99e..c002f234ff31 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -4896,6 +4896,9 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume)
power_domains->initializing = true;
+ /* Must happen before power domain init on VLV/CHV */
+ intel_update_rawclk(i915);
+
if (INTEL_GEN(i915) >= 11) {
icl_display_core_init(i915, resume);
} else if (IS_CANNONLAKE(i915)) {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 57e9f0ba331b..9b15ac4f2fb6 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1256,6 +1256,9 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
u32 unused)
{
struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+ struct drm_i915_private *i915 =
+ to_i915(intel_dig_port->base.base.dev);
+ enum phy phy = intel_port_to_phy(i915, intel_dig_port->base.port);
u32 ret;
ret = DP_AUX_CH_CTL_SEND_BUSY |
@@ -1268,7 +1271,8 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) |
DP_AUX_CH_CTL_SYNC_PULSE_SKL(32);
- if (intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
+ if (intel_phy_is_tc(i915, phy) &&
+ intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
ret |= DP_AUX_CH_CTL_TBT_IO;
return ret;
@@ -5436,6 +5440,12 @@ out:
if (status != connector_status_connected && !intel_dp->is_mst)
intel_dp_unset_edid(intel_dp);
+ /*
+ * Make sure the refs for power wells enabled during detect are
+ * dropped to avoid a new detect cycle triggered by HPD polling.
+ */
+ intel_display_power_flush_work(dev_priv);
+
return status;
}
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index b8148f838354..d5a298c3c83b 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -525,16 +525,31 @@ static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv,
val = I915_READ(WRPLL_CTL(id));
I915_WRITE(WRPLL_CTL(id), val & ~WRPLL_PLL_ENABLE);
POSTING_READ(WRPLL_CTL(id));
+
+ /*
+ * Try to set up the PCH reference clock once all DPLLs
+ * that depend on it have been shut down.
+ */
+ if (dev_priv->pch_ssc_use & BIT(id))
+ intel_init_pch_refclk(dev_priv);
}
static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv,
struct intel_shared_dpll *pll)
{
+ enum intel_dpll_id id = pll->info->id;
u32 val;
val = I915_READ(SPLL_CTL);
I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
POSTING_READ(SPLL_CTL);
+
+ /*
+ * Try to set up the PCH reference clock once all DPLLs
+ * that depend on it have been shut down.
+ */
+ if (dev_priv->pch_ssc_use & BIT(id))
+ intel_init_pch_refclk(dev_priv);
}
static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
index e7588799fce5..104cf6d42333 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
@@ -147,11 +147,11 @@ enum intel_dpll_id {
*/
DPLL_ID_ICL_MGPLL4 = 6,
/**
- * @DPLL_ID_TGL_TCPLL5: TGL TC PLL port 5 (TC5)
+ * @DPLL_ID_TGL_MGPLL5: TGL TC PLL port 5 (TC5)
*/
DPLL_ID_TGL_MGPLL5 = 7,
/**
- * @DPLL_ID_TGL_TCPLL6: TGL TC PLL port 6 (TC6)
+ * @DPLL_ID_TGL_MGPLL6: TGL TC PLL port 6 (TC6)
*/
DPLL_ID_TGL_MGPLL6 = 8,
};
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index e02f0faecf02..b030f7ae3302 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2565,6 +2565,12 @@ out:
if (status != connector_status_connected)
cec_notifier_phys_addr_invalidate(intel_hdmi->cec_notifier);
+ /*
+ * Make sure the refs for power wells enabled during detect are
+ * dropped to avoid a new detect cycle triggered by HPD polling.
+ */
+ intel_display_power_flush_work(dev_priv);
+
return status;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 1cdfe05514c3..e41fd94ae5a9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -319,6 +319,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
free_engines(rcu_access_pointer(ctx->engines));
mutex_destroy(&ctx->engines_mutex);
+ kfree(ctx->jump_whitelist);
+
if (ctx->timeline)
intel_timeline_put(ctx->timeline);
@@ -441,6 +443,9 @@ __create_context(struct drm_i915_private *i915)
for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
+ ctx->jump_whitelist = NULL;
+ ctx->jump_whitelist_cmds = 0;
+
return ctx;
err_free:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 260d59cc3de8..00537b9d7006 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -192,6 +192,13 @@ struct i915_gem_context {
* per vm, which may be one per context or shared with the global GTT)
*/
struct radix_tree_root handles_vma;
+
+ /** jump_whitelist: Bit array for tracking cmds during cmdparsing
+ * Guarded by struct_mutex
+ */
+ unsigned long *jump_whitelist;
+ /** jump_whitelist_cmds: No of cmd slots available */
+ u32 jump_whitelist_cmds;
};
#endif /* __I915_GEM_CONTEXT_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index b5f6937369ea..e635e1e5f4d3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -296,7 +296,9 @@ static inline u64 gen8_noncanonical_addr(u64 address)
static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
{
- return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len;
+ return intel_engine_requires_cmd_parser(eb->engine) ||
+ (intel_engine_using_cmd_parser(eb->engine) &&
+ eb->args->batch_len);
}
static int eb_create(struct i915_execbuffer *eb)
@@ -1955,40 +1957,94 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
return 0;
}
-static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master)
+static struct i915_vma *
+shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj)
+{
+ struct drm_i915_private *dev_priv = eb->i915;
+ struct i915_vma * const vma = *eb->vma;
+ struct i915_address_space *vm;
+ u64 flags;
+
+ /*
+ * PPGTT backed shadow buffers must be mapped RO, to prevent
+ * post-scan tampering
+ */
+ if (CMDPARSER_USES_GGTT(dev_priv)) {
+ flags = PIN_GLOBAL;
+ vm = &dev_priv->ggtt.vm;
+ } else if (vma->vm->has_read_only) {
+ flags = PIN_USER;
+ vm = vma->vm;
+ i915_gem_object_set_readonly(obj);
+ } else {
+ DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags);
+}
+
+static struct i915_vma *eb_parse(struct i915_execbuffer *eb)
{
struct intel_engine_pool_node *pool;
struct i915_vma *vma;
+ u64 batch_start;
+ u64 shadow_batch_start;
int err;
pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len);
if (IS_ERR(pool))
return ERR_CAST(pool);
- err = intel_engine_cmd_parser(eb->engine,
+ vma = shadow_batch_pin(eb, pool->obj);
+ if (IS_ERR(vma))
+ goto err;
+
+ batch_start = gen8_canonical_addr(eb->batch->node.start) +
+ eb->batch_start_offset;
+
+ shadow_batch_start = gen8_canonical_addr(vma->node.start);
+
+ err = intel_engine_cmd_parser(eb->gem_context,
+ eb->engine,
eb->batch->obj,
- pool->obj,
+ batch_start,
eb->batch_start_offset,
eb->batch_len,
- is_master);
+ pool->obj,
+ shadow_batch_start);
+
if (err) {
- if (err == -EACCES) /* unhandled chained batch */
+ i915_vma_unpin(vma);
+
+ /*
+ * Unsafe GGTT-backed buffers can still be submitted safely
+ * as non-secure.
+ * For PPGTT backing however, we have no choice but to forcibly
+ * reject unsafe buffers
+ */
+ if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES))
+ /* Execute original buffer non-secure */
vma = NULL;
else
vma = ERR_PTR(err);
goto err;
}
- vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0);
- if (IS_ERR(vma))
- goto err;
-
eb->vma[eb->buffer_count] = i915_vma_get(vma);
eb->flags[eb->buffer_count] =
__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
vma->exec_flags = &eb->flags[eb->buffer_count];
eb->buffer_count++;
+ eb->batch_start_offset = 0;
+ eb->batch = vma;
+
+ if (CMDPARSER_USES_GGTT(eb->i915))
+ eb->batch_flags |= I915_DISPATCH_SECURE;
+
+ /* eb->batch_len unchanged */
+
vma->private = pool;
return vma;
@@ -2421,6 +2477,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
struct drm_i915_gem_exec_object2 *exec,
struct drm_syncobj **fences)
{
+ struct drm_i915_private *i915 = to_i915(dev);
struct i915_execbuffer eb;
struct dma_fence *in_fence = NULL;
struct dma_fence *exec_fence = NULL;
@@ -2432,7 +2489,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS &
~__EXEC_OBJECT_UNKNOWN_FLAGS);
- eb.i915 = to_i915(dev);
+ eb.i915 = i915;
eb.file = file;
eb.args = args;
if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
@@ -2452,8 +2509,15 @@ i915_gem_do_execbuffer(struct drm_device *dev,
eb.batch_flags = 0;
if (args->flags & I915_EXEC_SECURE) {
+ if (INTEL_GEN(i915) >= 11)
+ return -ENODEV;
+
+ /* Return -EPERM to trigger fallback code on old binaries. */
+ if (!HAS_SECURE_BATCHES(i915))
+ return -EPERM;
+
if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN))
- return -EPERM;
+ return -EPERM;
eb.batch_flags |= I915_DISPATCH_SECURE;
}
@@ -2530,34 +2594,19 @@ i915_gem_do_execbuffer(struct drm_device *dev,
goto err_vma;
}
+ if (eb.batch_len == 0)
+ eb.batch_len = eb.batch->size - eb.batch_start_offset;
+
if (eb_use_cmdparser(&eb)) {
struct i915_vma *vma;
- vma = eb_parse(&eb, drm_is_current_master(file));
+ vma = eb_parse(&eb);
if (IS_ERR(vma)) {
err = PTR_ERR(vma);
goto err_vma;
}
-
- if (vma) {
- /*
- * Batch parsed and accepted:
- *
- * Set the DISPATCH_SECURE bit to remove the NON_SECURE
- * bit from MI_BATCH_BUFFER_START commands issued in
- * the dispatch_execbuffer implementations. We
- * specifically don't want that set on batches the
- * command parser has accepted.
- */
- eb.batch_flags |= I915_DISPATCH_SECURE;
- eb.batch_start_offset = 0;
- eb.batch = vma;
- }
}
- if (eb.batch_len == 0)
- eb.batch_len = eb.batch->size - eb.batch_start_offset;
-
/*
* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
* batch" bit. Hence we need to pin secure batches into the global gtt.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 261c9bd83f51..05289edbafe3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -245,11 +245,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
wakeref = intel_runtime_pm_get(rpm);
- srcu = intel_gt_reset_trylock(ggtt->vm.gt);
- if (srcu < 0) {
- ret = srcu;
+ ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+ if (ret)
goto err_rpm;
- }
ret = i915_mutex_lock_interruptible(dev);
if (ret)
@@ -318,7 +316,11 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
- i915_vma_set_ggtt_write(vma);
+ if (write) {
+ GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+ i915_vma_set_ggtt_write(vma);
+ obj->mm.dirty = true;
+ }
err_fence:
i915_vma_unpin_fence(vma);
@@ -362,6 +364,7 @@ err:
return VM_FAULT_OOM;
case -ENOSPC:
case -EFAULT:
+ case -ENODEV: /* bad object, how did you get here! */
return VM_FAULT_SIGBUS;
default:
WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
@@ -473,10 +476,16 @@ i915_gem_mmap_gtt(struct drm_file *file,
if (!obj)
return -ENOENT;
+ if (i915_gem_object_never_bind_ggtt(obj)) {
+ ret = -ENODEV;
+ goto out;
+ }
+
ret = create_mmap_offset(obj);
if (ret == 0)
*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
+out:
i915_gem_object_put(obj);
return ret;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 5efb9936e05b..ddf3605bea8e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -153,6 +153,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
}
static inline bool
+i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj)
+{
+ return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT;
+}
+
+static inline bool
i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
{
return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index ede0eb4218a8..646859fea224 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops {
#define I915_GEM_OBJECT_HAS_STRUCT_PAGE BIT(0)
#define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1)
#define I915_GEM_OBJECT_IS_PROXY BIT(2)
-#define I915_GEM_OBJECT_ASYNC_CANCEL BIT(3)
+#define I915_GEM_OBJECT_NO_GGTT BIT(3)
+#define I915_GEM_OBJECT_ASYNC_CANCEL BIT(4)
/* Interface between the GEM object and its backing storage.
* get_pages() is called once prior to the use of the associated set
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 92e53c25424c..ad2a63dbcac2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -241,9 +241,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
mutex_lock(&i915->drm.struct_mutex);
intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
- i915_gem_restore_gtt_mappings(i915);
- i915_gem_restore_fences(i915);
-
if (i915_gem_init_hw(i915))
goto err_wedged;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 11b231c187c5..6b3b50f0f6d9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -702,6 +702,7 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
I915_GEM_OBJECT_IS_SHRINKABLE |
+ I915_GEM_OBJECT_NO_GGTT |
I915_GEM_OBJECT_ASYNC_CANCEL,
.get_pages = i915_gem_userptr_get_pages,
.put_pages = i915_gem_userptr_put_pages,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index d3c6993f4f46..22aab8593abf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -136,6 +136,20 @@ execlists_active(const struct intel_engine_execlists *execlists)
return READ_ONCE(*execlists->active);
}
+static inline void
+execlists_active_lock_bh(struct intel_engine_execlists *execlists)
+{
+ local_bh_disable(); /* prevent local softirq and lock recursion */
+ tasklet_lock(&execlists->tasklet);
+}
+
+static inline void
+execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
+{
+ tasklet_unlock(&execlists->tasklet);
+ local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
+}
+
struct i915_request *
execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 82630db0394b..4ce8626b140e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1197,9 +1197,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
struct drm_printer *m)
{
struct drm_i915_private *dev_priv = engine->i915;
- const struct intel_engine_execlists * const execlists =
- &engine->execlists;
- unsigned long flags;
+ struct intel_engine_execlists * const execlists = &engine->execlists;
u64 addr;
if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
@@ -1281,7 +1279,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
idx, hws[idx * 2], hws[idx * 2 + 1]);
}
- spin_lock_irqsave(&engine->active.lock, flags);
+ execlists_active_lock_bh(execlists);
for (port = execlists->active; (rq = *port); port++) {
char hdr[80];
int len;
@@ -1309,7 +1307,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
hwsp_seqno(rq));
print_request(m, rq, hdr);
}
- spin_unlock_irqrestore(&engine->active.lock, flags);
+ execlists_active_unlock_bh(execlists);
} else if (INTEL_GEN(dev_priv) > 6) {
drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
ENGINE_READ(engine, RING_PP_DIR_BASE));
@@ -1440,8 +1438,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
if (!intel_engine_supports_stats(engine))
return -ENODEV;
- spin_lock_irqsave(&engine->active.lock, flags);
- write_seqlock(&engine->stats.lock);
+ execlists_active_lock_bh(execlists);
+ write_seqlock_irqsave(&engine->stats.lock, flags);
if (unlikely(engine->stats.enabled == ~0)) {
err = -EBUSY;
@@ -1469,8 +1467,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
}
unlock:
- write_sequnlock(&engine->stats.lock);
- spin_unlock_irqrestore(&engine->active.lock, flags);
+ write_sequnlock_irqrestore(&engine->stats.lock, flags);
+ execlists_active_unlock_bh(execlists);
return err;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index a82cea95c2f2..9dd8c299cb2d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -475,12 +475,13 @@ struct intel_engine_cs {
struct intel_engine_hangcheck hangcheck;
-#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0)
+#define I915_ENGINE_USING_CMD_PARSER BIT(0)
#define I915_ENGINE_SUPPORTS_STATS BIT(1)
#define I915_ENGINE_HAS_PREEMPTION BIT(2)
#define I915_ENGINE_HAS_SEMAPHORES BIT(3)
#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
#define I915_ENGINE_IS_VIRTUAL BIT(5)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
unsigned int flags;
/*
@@ -541,9 +542,15 @@ struct intel_engine_cs {
};
static inline bool
-intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine)
+intel_engine_using_cmd_parser(const struct intel_engine_cs *engine)
{
- return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER;
+ return engine->flags & I915_ENGINE_USING_CMD_PARSER;
+}
+
+static inline bool
+intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine)
+{
+ return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER;
}
static inline bool
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 1363e069ec83..fac75afed35b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -38,6 +38,9 @@ static int __gt_unpark(struct intel_wakeref *wf)
gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
GEM_BUG_ON(!gt->awake);
+ if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+ intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
+
intel_enable_gt_powersave(i915);
i915_update_gfx_val(i915);
@@ -67,6 +70,11 @@ static int __gt_park(struct intel_wakeref *wf)
if (INTEL_GEN(i915) >= 6)
gen6_rps_idle(i915);
+ if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
+ i915_rc6_ctx_wa_check(i915);
+ intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
+ }
+
/* Everything switched off, flush any residual interrupt just in case */
intel_synchronize_irq(i915);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d42584439f51..06a506c29463 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -234,6 +234,13 @@ static void execlists_init_reg_state(u32 *reg_state,
struct intel_engine_cs *engine,
struct intel_ring *ring);
+static void mark_eio(struct i915_request *rq)
+{
+ if (!i915_request_signaled(rq))
+ dma_fence_set_error(&rq->fence, -EIO);
+ i915_request_mark_complete(rq);
+}
+
static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
{
return (i915_ggtt_offset(engine->status_page.vma) +
@@ -631,7 +638,6 @@ execlists_schedule_out(struct i915_request *rq)
struct intel_engine_cs *cur, *old;
trace_i915_request_out(rq);
- GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
old = READ_ONCE(ce->inflight);
do
@@ -797,6 +803,17 @@ static bool can_merge_rq(const struct i915_request *prev,
GEM_BUG_ON(prev == next);
GEM_BUG_ON(!assert_priority_queue(prev, next));
+ /*
+ * We do not submit known completed requests. Therefore if the next
+ * request is already completed, we can pretend to merge it in
+ * with the previous context (and we will skip updating the ELSP
+ * and tracking). Thus hopefully keeping the ELSP full with active
+ * contexts, despite the best efforts of preempt-to-busy to confuse
+ * us.
+ */
+ if (i915_request_completed(next))
+ return true;
+
if (!can_merge_ctx(prev->hw_context, next->hw_context))
return false;
@@ -893,7 +910,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
static struct i915_request *
last_active(const struct intel_engine_execlists *execlists)
{
- struct i915_request * const *last = execlists->active;
+ struct i915_request * const *last = READ_ONCE(execlists->active);
while (*last && i915_request_completed(*last))
last++;
@@ -1172,21 +1189,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
continue;
}
- if (i915_request_completed(rq)) {
- ve->request = NULL;
- ve->base.execlists.queue_priority_hint = INT_MIN;
- rb_erase_cached(rb, &execlists->virtual);
- RB_CLEAR_NODE(rb);
-
- rq->engine = engine;
- __i915_request_submit(rq);
-
- spin_unlock(&ve->base.active.lock);
-
- rb = rb_first_cached(&execlists->virtual);
- continue;
- }
-
if (last && !can_merge_rq(last, rq)) {
spin_unlock(&ve->base.active.lock);
return; /* leave this for another */
@@ -1237,11 +1239,24 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
GEM_BUG_ON(ve->siblings[0] != engine);
}
- __i915_request_submit(rq);
- if (!i915_request_completed(rq)) {
+ if (__i915_request_submit(rq)) {
submit = true;
last = rq;
}
+ i915_request_put(rq);
+
+ /*
+ * Hmm, we have a bunch of virtual engine requests,
+ * but the first one was already completed (thanks
+ * preempt-to-busy!). Keep looking at the veng queue
+ * until we have no more relevant requests (i.e.
+ * the normal submit queue has higher priority).
+ */
+ if (!submit) {
+ spin_unlock(&ve->base.active.lock);
+ rb = rb_first_cached(&execlists->virtual);
+ continue;
+ }
}
spin_unlock(&ve->base.active.lock);
@@ -1254,8 +1269,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
int i;
priolist_for_each_request_consume(rq, rn, p, i) {
- if (i915_request_completed(rq))
- goto skip;
+ bool merge = true;
/*
* Can we combine this request with the current port?
@@ -1296,14 +1310,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
ctx_single_port_submission(rq->hw_context))
goto done;
- *port = execlists_schedule_in(last, port - execlists->pending);
- port++;
+ merge = false;
}
- last = rq;
- submit = true;
-skip:
- __i915_request_submit(rq);
+ if (__i915_request_submit(rq)) {
+ if (!merge) {
+ *port = execlists_schedule_in(last, port - execlists->pending);
+ port++;
+ last = NULL;
+ }
+
+ GEM_BUG_ON(last &&
+ !can_merge_ctx(last->hw_context,
+ rq->hw_context));
+
+ submit = true;
+ last = rq;
+ }
}
rb_erase_cached(&p->node, &execlists->queue);
@@ -1593,8 +1616,11 @@ static void process_csb(struct intel_engine_cs *engine)
static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
{
lockdep_assert_held(&engine->active.lock);
- if (!engine->execlists.pending[0])
+ if (!engine->execlists.pending[0]) {
+ rcu_read_lock(); /* protect peeking at execlists->active */
execlists_dequeue(engine);
+ rcu_read_unlock();
+ }
}
/*
@@ -2399,10 +2425,14 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
static struct i915_request *active_request(struct i915_request *rq)
{
- const struct list_head * const list = &rq->timeline->requests;
const struct intel_context * const ce = rq->hw_context;
struct i915_request *active = NULL;
+ struct list_head *list;
+ if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
+ return rq;
+
+ list = &rq->timeline->requests;
list_for_each_entry_from_reverse(rq, list, link) {
if (i915_request_completed(rq))
break;
@@ -2552,12 +2582,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
__execlists_reset(engine, true);
/* Mark all executing requests as skipped. */
- list_for_each_entry(rq, &engine->active.requests, sched.link) {
- if (!i915_request_signaled(rq))
- dma_fence_set_error(&rq->fence, -EIO);
-
- i915_request_mark_complete(rq);
- }
+ list_for_each_entry(rq, &engine->active.requests, sched.link)
+ mark_eio(rq);
/* Flush the queued requests to the timeline list (for retiring). */
while ((rb = rb_first_cached(&execlists->queue))) {
@@ -2565,10 +2591,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
int i;
priolist_for_each_request_consume(rq, rn, p, i) {
- list_del_init(&rq->sched.link);
+ mark_eio(rq);
__i915_request_submit(rq);
- dma_fence_set_error(&rq->fence, -EIO);
- i915_request_mark_complete(rq);
}
rb_erase_cached(&p->node, &execlists->queue);
@@ -2584,13 +2608,15 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
RB_CLEAR_NODE(rb);
spin_lock(&ve->base.active.lock);
- if (ve->request) {
- ve->request->engine = engine;
- __i915_request_submit(ve->request);
- dma_fence_set_error(&ve->request->fence, -EIO);
- i915_request_mark_complete(ve->request);
+ rq = fetch_and_zero(&ve->request);
+ if (rq) {
+ mark_eio(rq);
+
+ rq->engine = engine;
+ __i915_request_submit(rq);
+ i915_request_put(rq);
+
ve->base.execlists.queue_priority_hint = INT_MIN;
- ve->request = NULL;
}
spin_unlock(&ve->base.active.lock);
}
@@ -3594,6 +3620,8 @@ submit_engine:
static void virtual_submit_request(struct i915_request *rq)
{
struct virtual_engine *ve = to_virtual_engine(rq->engine);
+ struct i915_request *old;
+ unsigned long flags;
GEM_TRACE("%s: rq=%llx:%lld\n",
ve->base.name,
@@ -3602,15 +3630,31 @@ static void virtual_submit_request(struct i915_request *rq)
GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
- GEM_BUG_ON(ve->request);
- GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+ spin_lock_irqsave(&ve->base.active.lock, flags);
+
+ old = ve->request;
+ if (old) { /* background completion event from preempt-to-busy */
+ GEM_BUG_ON(!i915_request_completed(old));
+ __i915_request_submit(old);
+ i915_request_put(old);
+ }
+
+ if (i915_request_completed(rq)) {
+ __i915_request_submit(rq);
+
+ ve->base.execlists.queue_priority_hint = INT_MIN;
+ ve->request = NULL;
+ } else {
+ ve->base.execlists.queue_priority_hint = rq_prio(rq);
+ ve->request = i915_request_get(rq);
- ve->base.execlists.queue_priority_hint = rq_prio(rq);
- WRITE_ONCE(ve->request, rq);
+ GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+ list_move_tail(&rq->sched.link, virtual_queue(ve));
- list_move_tail(&rq->sched.link, virtual_queue(ve));
+ tasklet_schedule(&ve->base.execlists.tasklet);
+ }
- tasklet_schedule(&ve->base.execlists.tasklet);
+ spin_unlock_irqrestore(&ve->base.active.lock, flags);
}
static struct ve_bond *
@@ -3631,18 +3675,22 @@ static void
virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
{
struct virtual_engine *ve = to_virtual_engine(rq->engine);
+ intel_engine_mask_t allowed, exec;
struct ve_bond *bond;
+ allowed = ~to_request(signal)->engine->mask;
+
bond = virtual_find_bond(ve, to_request(signal)->engine);
- if (bond) {
- intel_engine_mask_t old, new, cmp;
+ if (bond)
+ allowed &= bond->sibling_mask;
- cmp = READ_ONCE(rq->execution_mask);
- do {
- old = cmp;
- new = cmp & bond->sibling_mask;
- } while ((cmp = cmpxchg(&rq->execution_mask, old, new)) != old);
- }
+ /* Restrict the bonded request to run on only the available engines */
+ exec = READ_ONCE(rq->execution_mask);
+ while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed))
+ ;
+
+ /* Prevent the master from being re-run on the bonded engines */
+ to_request(signal)->execution_mask &= ~allowed;
}
struct intel_context *
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 728704bbbe18..cea184a7dde9 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -199,14 +199,6 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
MOCS_ENTRY(15, \
LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \
L3_3_WB), \
- /* Bypass LLC - Uncached (EHL+) */ \
- MOCS_ENTRY(16, \
- LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \
- L3_1_UC), \
- /* Bypass LLC - L3 (Read-Only) (EHL+) */ \
- MOCS_ENTRY(17, \
- LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \
- L3_3_WB), \
/* Self-Snoop - L3 + LLC */ \
MOCS_ENTRY(18, \
LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \
@@ -270,7 +262,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = {
L3_1_UC),
/* HW Special Case (Displayable) */
MOCS_ENTRY(61,
- LE_1_UC | LE_TC_1_LLC | LE_SCF(1),
+ LE_1_UC | LE_TC_1_LLC,
L3_3_WB),
};
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b9d84d52e986..8cea42379dd7 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -42,11 +42,10 @@ static void engine_skip_context(struct i915_request *rq)
struct intel_engine_cs *engine = rq->engine;
struct i915_gem_context *hung_ctx = rq->gem_context;
- lockdep_assert_held(&engine->active.lock);
-
if (!i915_request_is_active(rq))
return;
+ lockdep_assert_held(&engine->active.lock);
list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
if (rq->gem_context == hung_ctx)
i915_request_skip(rq, -EIO);
@@ -123,7 +122,6 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
rq->fence.seqno,
yesno(guilty));
- lockdep_assert_held(&rq->engine->active.lock);
GEM_BUG_ON(i915_request_completed(rq));
if (guilty) {
@@ -1214,10 +1212,8 @@ out:
intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
}
-int intel_gt_reset_trylock(struct intel_gt *gt)
+int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
{
- int srcu;
-
might_lock(&gt->reset.backoff_srcu);
might_sleep();
@@ -1232,10 +1228,10 @@ int intel_gt_reset_trylock(struct intel_gt *gt)
rcu_read_lock();
}
- srcu = srcu_read_lock(&gt->reset.backoff_srcu);
+ *srcu = srcu_read_lock(&gt->reset.backoff_srcu);
rcu_read_unlock();
- return srcu;
+ return 0;
}
void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 37a987b17108..52c00199e069 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -38,7 +38,7 @@ int intel_engine_reset(struct intel_engine_cs *engine,
void __i915_request_reset(struct i915_request *rq, bool guilty);
-int __must_check intel_gt_reset_trylock(struct intel_gt *gt);
+int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu);
void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
void intel_gt_set_wedged(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 601c16239fdf..bacaa7bb8c9a 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1573,7 +1573,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
struct intel_engine_cs *engine = rq->engine;
enum intel_engine_id id;
const int num_engines =
- IS_HSW_GT1(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
+ IS_HASWELL(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
bool force_restore = false;
int len;
u32 *cs;
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 45481eb1fa3c..5f6ec2fd29a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1063,6 +1063,9 @@ static void gen9_whitelist_build(struct i915_wa_list *w)
/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
whitelist_reg(w, GEN8_HDC_CHICKEN1);
+
+ /* WaSendPushConstantsFromMMIO:skl,bxt */
+ whitelist_reg(w, COMMON_SLICE_CHICKEN2);
}
static void skl_whitelist_build(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 13044c027f27..4bfaefdf548d 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -498,8 +498,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
goto out_free_gem;
}
- i915_gem_object_put(obj);
-
ret = dma_buf_fd(dmabuf, DRM_CLOEXEC | DRM_RDWR);
if (ret < 0) {
gvt_vgpu_err("create dma-buf fd failed ret:%d\n", ret);
@@ -524,6 +522,8 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
file_count(dmabuf->file),
kref_read(&obj->base.refcount));
+ i915_gem_object_put(obj);
+
return dmabuf_fd;
out_free_dmabuf:
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 24555102e198..f24096e27bef 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -53,13 +53,11 @@
* granting userspace undue privileges. There are three categories of privilege.
*
* First, commands which are explicitly defined as privileged or which should
- * only be used by the kernel driver. The parser generally rejects such
- * commands, though it may allow some from the drm master process.
+ * only be used by the kernel driver. The parser rejects such commands
*
* Second, commands which access registers. To support correct/enhanced
* userspace functionality, particularly certain OpenGL extensions, the parser
- * provides a whitelist of registers which userspace may safely access (for both
- * normal and drm master processes).
+ * provides a whitelist of registers which userspace may safely access
*
* Third, commands which access privileged memory (i.e. GGTT, HWS page, etc).
* The parser always rejects such commands.
@@ -84,9 +82,9 @@
* in the per-engine command tables.
*
* Other command table entries map fairly directly to high level categories
- * mentioned above: rejected, master-only, register whitelist. The parser
- * implements a number of checks, including the privileged memory checks, via a
- * general bitmasking mechanism.
+ * mentioned above: rejected, register whitelist. The parser implements a number
+ * of checks, including the privileged memory checks, via a general bitmasking
+ * mechanism.
*/
/*
@@ -104,8 +102,6 @@ struct drm_i915_cmd_descriptor {
* CMD_DESC_REJECT: The command is never allowed
* CMD_DESC_REGISTER: The command should be checked against the
* register whitelist for the appropriate ring
- * CMD_DESC_MASTER: The command is allowed if the submitting process
- * is the DRM master
*/
u32 flags;
#define CMD_DESC_FIXED (1<<0)
@@ -113,7 +109,6 @@ struct drm_i915_cmd_descriptor {
#define CMD_DESC_REJECT (1<<2)
#define CMD_DESC_REGISTER (1<<3)
#define CMD_DESC_BITMASK (1<<4)
-#define CMD_DESC_MASTER (1<<5)
/*
* The command's unique identification bits and the bitmask to get them.
@@ -194,7 +189,7 @@ struct drm_i915_cmd_table {
#define CMD(op, opm, f, lm, fl, ...) \
{ \
.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \
- .cmd = { (op), ~0u << (opm) }, \
+ .cmd = { (op & ~0u << (opm)), ~0u << (opm) }, \
.length = { (lm) }, \
__VA_ARGS__ \
}
@@ -209,14 +204,13 @@ struct drm_i915_cmd_table {
#define R CMD_DESC_REJECT
#define W CMD_DESC_REGISTER
#define B CMD_DESC_BITMASK
-#define M CMD_DESC_MASTER
/* Command Mask Fixed Len Action
---------------------------------------------------------- */
-static const struct drm_i915_cmd_descriptor common_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
CMD( MI_NOOP, SMI, F, 1, S ),
CMD( MI_USER_INTERRUPT, SMI, F, 1, R ),
- CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ),
+ CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, R ),
CMD( MI_ARB_CHECK, SMI, F, 1, S ),
CMD( MI_REPORT_HEAD, SMI, F, 1, S ),
CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ),
@@ -246,7 +240,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {
CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ),
};
-static const struct drm_i915_cmd_descriptor render_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = {
CMD( MI_FLUSH, SMI, F, 1, S ),
CMD( MI_ARB_ON_OFF, SMI, F, 1, R ),
CMD( MI_PREDICATE, SMI, F, 1, S ),
@@ -313,7 +307,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
CMD( MI_URB_ATOMIC_ALLOC, SMI, F, 1, S ),
CMD( MI_SET_APPID, SMI, F, 1, S ),
CMD( MI_RS_CONTEXT, SMI, F, 1, S ),
- CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ),
+ CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ),
CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ),
CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W,
.reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ),
@@ -330,7 +324,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS, S3D, !F, 0x1FF, S ),
};
-static const struct drm_i915_cmd_descriptor video_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = {
CMD( MI_ARB_ON_OFF, SMI, F, 1, R ),
CMD( MI_SET_APPID, SMI, F, 1, S ),
CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B,
@@ -374,7 +368,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = {
CMD( MFX_WAIT, SMFX, F, 1, S ),
};
-static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = {
CMD( MI_ARB_ON_OFF, SMI, F, 1, R ),
CMD( MI_SET_APPID, SMI, F, 1, S ),
CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B,
@@ -412,7 +406,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
}}, ),
};
-static const struct drm_i915_cmd_descriptor blt_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = {
CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ),
CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B,
.bits = {{
@@ -446,10 +440,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = {
};
static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
- CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ),
+ CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ),
CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ),
};
+/*
+ * For Gen9 we can still rely on the h/w to enforce cmd security, and only
+ * need to re-enforce the register access checks. We therefore only need to
+ * teach the cmdparser how to find the end of each command, and identify
+ * register accesses. The table doesn't need to reject any commands, and so
+ * the only commands listed here are:
+ * 1) Those that touch registers
+ * 2) Those that do not have the default 8-bit length
+ *
+ * Note that the default MI length mask chosen for this table is 0xFF, not
+ * the 0x3F used on older devices. This is because the vast majority of MI
+ * cmds on Gen9 use a standard 8-bit Length field.
+ * All the Gen9 blitter instructions are standard 0xFF length mask, and
+ * none allow access to non-general registers, so in fact no BLT cmds are
+ * included in the table at all.
+ *
+ */
+static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = {
+ CMD( MI_NOOP, SMI, F, 1, S ),
+ CMD( MI_USER_INTERRUPT, SMI, F, 1, S ),
+ CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, S ),
+ CMD( MI_FLUSH, SMI, F, 1, S ),
+ CMD( MI_ARB_CHECK, SMI, F, 1, S ),
+ CMD( MI_REPORT_HEAD, SMI, F, 1, S ),
+ CMD( MI_ARB_ON_OFF, SMI, F, 1, S ),
+ CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ),
+ CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, S ),
+ CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, S ),
+ CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, S ),
+ CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W,
+ .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ),
+ CMD( MI_UPDATE_GTT, SMI, !F, 0x3FF, S ),
+ CMD( MI_STORE_REGISTER_MEM_GEN8, SMI, F, 4, W,
+ .reg = { .offset = 1, .mask = 0x007FFFFC } ),
+ CMD( MI_FLUSH_DW, SMI, !F, 0x3F, S ),
+ CMD( MI_LOAD_REGISTER_MEM_GEN8, SMI, F, 4, W,
+ .reg = { .offset = 1, .mask = 0x007FFFFC } ),
+ CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W,
+ .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ),
+
+ /*
+ * We allow BB_START but apply further checks. We just sanitize the
+ * basic fields here.
+ */
+#define MI_BB_START_OPERAND_MASK GENMASK(SMI-1, 0)
+#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1)
+ CMD( MI_BATCH_BUFFER_START_GEN8, SMI, !F, 0xFF, B,
+ .bits = {{
+ .offset = 0,
+ .mask = MI_BB_START_OPERAND_MASK,
+ .expected = MI_BB_START_OPERAND_EXPECT,
+ }}, ),
+};
+
static const struct drm_i915_cmd_descriptor noop_desc =
CMD(MI_NOOP, SMI, F, 1, S);
@@ -463,40 +511,44 @@ static const struct drm_i915_cmd_descriptor noop_desc =
#undef R
#undef W
#undef B
-#undef M
-static const struct drm_i915_cmd_table gen7_render_cmds[] = {
- { common_cmds, ARRAY_SIZE(common_cmds) },
- { render_cmds, ARRAY_SIZE(render_cmds) },
+static const struct drm_i915_cmd_table gen7_render_cmd_table[] = {
+ { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+ { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
};
-static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = {
- { common_cmds, ARRAY_SIZE(common_cmds) },
- { render_cmds, ARRAY_SIZE(render_cmds) },
+static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = {
+ { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+ { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
{ hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) },
};
-static const struct drm_i915_cmd_table gen7_video_cmds[] = {
- { common_cmds, ARRAY_SIZE(common_cmds) },
- { video_cmds, ARRAY_SIZE(video_cmds) },
+static const struct drm_i915_cmd_table gen7_video_cmd_table[] = {
+ { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+ { gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) },
};
-static const struct drm_i915_cmd_table hsw_vebox_cmds[] = {
- { common_cmds, ARRAY_SIZE(common_cmds) },
- { vecs_cmds, ARRAY_SIZE(vecs_cmds) },
+static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = {
+ { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+ { gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) },
};
-static const struct drm_i915_cmd_table gen7_blt_cmds[] = {
- { common_cmds, ARRAY_SIZE(common_cmds) },
- { blt_cmds, ARRAY_SIZE(blt_cmds) },
+static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = {
+ { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+ { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
};
-static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = {
- { common_cmds, ARRAY_SIZE(common_cmds) },
- { blt_cmds, ARRAY_SIZE(blt_cmds) },
+static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = {
+ { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+ { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
};
+static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = {
+ { gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) },
+};
+
+
/*
* Register whitelists, sorted by increasing register offset.
*/
@@ -612,17 +664,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = {
REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
};
-static const struct drm_i915_reg_descriptor ivb_master_regs[] = {
- REG32(FORCEWAKE_MT),
- REG32(DERRMR),
- REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)),
- REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)),
- REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)),
-};
-
-static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
- REG32(FORCEWAKE_MT),
- REG32(DERRMR),
+static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
+ REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
+ REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
+ REG32(BCS_SWCTRL),
+ REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
+ REG64_IDX(BCS_GPR, 0),
+ REG64_IDX(BCS_GPR, 1),
+ REG64_IDX(BCS_GPR, 2),
+ REG64_IDX(BCS_GPR, 3),
+ REG64_IDX(BCS_GPR, 4),
+ REG64_IDX(BCS_GPR, 5),
+ REG64_IDX(BCS_GPR, 6),
+ REG64_IDX(BCS_GPR, 7),
+ REG64_IDX(BCS_GPR, 8),
+ REG64_IDX(BCS_GPR, 9),
+ REG64_IDX(BCS_GPR, 10),
+ REG64_IDX(BCS_GPR, 11),
+ REG64_IDX(BCS_GPR, 12),
+ REG64_IDX(BCS_GPR, 13),
+ REG64_IDX(BCS_GPR, 14),
+ REG64_IDX(BCS_GPR, 15),
};
#undef REG64
@@ -631,28 +693,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
struct drm_i915_reg_table {
const struct drm_i915_reg_descriptor *regs;
int num_regs;
- bool master;
};
static const struct drm_i915_reg_table ivb_render_reg_tables[] = {
- { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
- { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
+ { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
};
static const struct drm_i915_reg_table ivb_blt_reg_tables[] = {
- { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
- { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
+ { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
};
static const struct drm_i915_reg_table hsw_render_reg_tables[] = {
- { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
- { hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false },
- { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
+ { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
+ { hsw_render_regs, ARRAY_SIZE(hsw_render_regs) },
};
static const struct drm_i915_reg_table hsw_blt_reg_tables[] = {
- { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
- { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
+ { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
+};
+
+static const struct drm_i915_reg_table gen9_blt_reg_tables[] = {
+ { gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) },
};
static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
@@ -710,6 +771,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
return 0;
}
+static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
+{
+ u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
+
+ if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
+ return 0xFF;
+
+ DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+ return 0;
+}
+
static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
const struct drm_i915_cmd_table *cmd_tables,
int cmd_table_count)
@@ -867,18 +939,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
int cmd_table_count;
int ret;
- if (!IS_GEN(engine->i915, 7))
+ if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
+ engine->class == COPY_ENGINE_CLASS))
return;
switch (engine->class) {
case RENDER_CLASS:
if (IS_HASWELL(engine->i915)) {
- cmd_tables = hsw_render_ring_cmds;
+ cmd_tables = hsw_render_ring_cmd_table;
cmd_table_count =
- ARRAY_SIZE(hsw_render_ring_cmds);
+ ARRAY_SIZE(hsw_render_ring_cmd_table);
} else {
- cmd_tables = gen7_render_cmds;
- cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
+ cmd_tables = gen7_render_cmd_table;
+ cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table);
}
if (IS_HASWELL(engine->i915)) {
@@ -888,36 +961,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
engine->reg_tables = ivb_render_reg_tables;
engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables);
}
-
engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
break;
case VIDEO_DECODE_CLASS:
- cmd_tables = gen7_video_cmds;
- cmd_table_count = ARRAY_SIZE(gen7_video_cmds);
+ cmd_tables = gen7_video_cmd_table;
+ cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table);
engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
break;
case COPY_ENGINE_CLASS:
- if (IS_HASWELL(engine->i915)) {
- cmd_tables = hsw_blt_ring_cmds;
- cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
+ engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
+ if (IS_GEN(engine->i915, 9)) {
+ cmd_tables = gen9_blt_cmd_table;
+ cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table);
+ engine->get_cmd_length_mask =
+ gen9_blt_get_cmd_length_mask;
+
+ /* BCS Engine unsafe without parser */
+ engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER;
+ } else if (IS_HASWELL(engine->i915)) {
+ cmd_tables = hsw_blt_ring_cmd_table;
+ cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table);
} else {
- cmd_tables = gen7_blt_cmds;
- cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
+ cmd_tables = gen7_blt_cmd_table;
+ cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table);
}
- if (IS_HASWELL(engine->i915)) {
+ if (IS_GEN(engine->i915, 9)) {
+ engine->reg_tables = gen9_blt_reg_tables;
+ engine->reg_table_count =
+ ARRAY_SIZE(gen9_blt_reg_tables);
+ } else if (IS_HASWELL(engine->i915)) {
engine->reg_tables = hsw_blt_reg_tables;
engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
} else {
engine->reg_tables = ivb_blt_reg_tables;
engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables);
}
-
- engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
break;
case VIDEO_ENHANCEMENT_CLASS:
- cmd_tables = hsw_vebox_cmds;
- cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds);
+ cmd_tables = hsw_vebox_cmd_table;
+ cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table);
/* VECS can use the same length_mask function as VCS */
engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
break;
@@ -943,7 +1026,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
return;
}
- engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER;
+ engine->flags |= I915_ENGINE_USING_CMD_PARSER;
}
/**
@@ -955,7 +1038,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
*/
void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
{
- if (!intel_engine_needs_cmd_parser(engine))
+ if (!intel_engine_using_cmd_parser(engine))
return;
fini_hash_table(engine);
@@ -1029,22 +1112,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr)
}
static const struct drm_i915_reg_descriptor *
-find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr)
+find_reg(const struct intel_engine_cs *engine, u32 addr)
{
const struct drm_i915_reg_table *table = engine->reg_tables;
+ const struct drm_i915_reg_descriptor *reg = NULL;
int count = engine->reg_table_count;
- for (; count > 0; ++table, --count) {
- if (!table->master || is_master) {
- const struct drm_i915_reg_descriptor *reg;
+ for (; !reg && (count > 0); ++table, --count)
+ reg = __find_reg(table->regs, table->num_regs, addr);
- reg = __find_reg(table->regs, table->num_regs, addr);
- if (reg != NULL)
- return reg;
- }
- }
-
- return NULL;
+ return reg;
}
/* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
@@ -1128,8 +1205,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
static bool check_cmd(const struct intel_engine_cs *engine,
const struct drm_i915_cmd_descriptor *desc,
- const u32 *cmd, u32 length,
- const bool is_master)
+ const u32 *cmd, u32 length)
{
if (desc->flags & CMD_DESC_SKIP)
return true;
@@ -1139,12 +1215,6 @@ static bool check_cmd(const struct intel_engine_cs *engine,
return false;
}
- if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
- DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
- *cmd);
- return false;
- }
-
if (desc->flags & CMD_DESC_REGISTER) {
/*
* Get the distance between individual register offset
@@ -1158,7 +1228,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
offset += step) {
const u32 reg_addr = cmd[offset] & desc->reg.mask;
const struct drm_i915_reg_descriptor *reg =
- find_reg(engine, is_master, reg_addr);
+ find_reg(engine, reg_addr);
if (!reg) {
DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
@@ -1236,16 +1306,112 @@ static bool check_cmd(const struct intel_engine_cs *engine,
return true;
}
+static int check_bbstart(const struct i915_gem_context *ctx,
+ u32 *cmd, u32 offset, u32 length,
+ u32 batch_len,
+ u64 batch_start,
+ u64 shadow_batch_start)
+{
+ u64 jump_offset, jump_target;
+ u32 target_cmd_offset, target_cmd_index;
+
+ /* For igt compatibility on older platforms */
+ if (CMDPARSER_USES_GGTT(ctx->i915)) {
+ DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
+ return -EACCES;
+ }
+
+ if (length != 3) {
+ DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n",
+ length);
+ return -EINVAL;
+ }
+
+ jump_target = *(u64*)(cmd+1);
+ jump_offset = jump_target - batch_start;
+
+ /*
+ * Any underflow of jump_target is guaranteed to be outside the range
+ * of a u32, so >= test catches both too large and too small
+ */
+ if (jump_offset >= batch_len) {
+ DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
+ jump_target);
+ return -EINVAL;
+ }
+
+ /*
+ * This cannot overflow a u32 because we already checked jump_offset
+ * is within the BB, and the batch_len is a u32
+ */
+ target_cmd_offset = lower_32_bits(jump_offset);
+ target_cmd_index = target_cmd_offset / sizeof(u32);
+
+ *(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset;
+
+ if (target_cmd_index == offset)
+ return 0;
+
+ if (ctx->jump_whitelist_cmds <= target_cmd_index) {
+ DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
+ return -EINVAL;
+ } else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
+ DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
+ jump_target);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
+{
+ const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
+ const u32 exact_size = BITS_TO_LONGS(batch_cmds);
+ u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
+ unsigned long *next_whitelist;
+
+ if (CMDPARSER_USES_GGTT(ctx->i915))
+ return;
+
+ if (batch_cmds <= ctx->jump_whitelist_cmds) {
+ bitmap_zero(ctx->jump_whitelist, batch_cmds);
+ return;
+ }
+
+again:
+ next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
+ if (next_whitelist) {
+ kfree(ctx->jump_whitelist);
+ ctx->jump_whitelist = next_whitelist;
+ ctx->jump_whitelist_cmds =
+ next_size * BITS_PER_BYTE * sizeof(long);
+ return;
+ }
+
+ if (next_size > exact_size) {
+ next_size = exact_size;
+ goto again;
+ }
+
+ DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
+ bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
+
+ return;
+}
+
#define LENGTH_BIAS 2
/**
* i915_parse_cmds() - parse a submitted batch buffer for privilege violations
+ * @ctx: the context in which the batch is to execute
* @engine: the engine on which the batch is to execute
* @batch_obj: the batch buffer in question
- * @shadow_batch_obj: copy of the batch buffer in question
+ * @batch_start: Canonical base address of batch
* @batch_start_offset: byte offset in the batch at which execution starts
* @batch_len: length of the commands in batch_obj
- * @is_master: is the submitting process the drm master?
+ * @shadow_batch_obj: copy of the batch buffer in question
+ * @shadow_batch_start: Canonical base address of shadow_batch_obj
*
* Parses the specified batch buffer looking for privilege violations as
* described in the overview.
@@ -1253,14 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine,
* Return: non-zero if the parser finds violations or otherwise fails; -EACCES
* if the batch appears legal but should use hardware parsing
*/
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+
+int intel_engine_cmd_parser(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
struct drm_i915_gem_object *batch_obj,
- struct drm_i915_gem_object *shadow_batch_obj,
+ u64 batch_start,
u32 batch_start_offset,
u32 batch_len,
- bool is_master)
+ struct drm_i915_gem_object *shadow_batch_obj,
+ u64 shadow_batch_start)
{
- u32 *cmd, *batch_end;
+ u32 *cmd, *batch_end, offset = 0;
struct drm_i915_cmd_descriptor default_desc = noop_desc;
const struct drm_i915_cmd_descriptor *desc = &default_desc;
bool needs_clflush_after = false;
@@ -1274,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
return PTR_ERR(cmd);
}
+ init_whitelist(ctx, batch_len);
+
/*
* We use the batch length as size because the shadow object is as
* large or larger and copy_batch() will write MI_NOPs to the extra
@@ -1283,31 +1454,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
do {
u32 length;
- if (*cmd == MI_BATCH_BUFFER_END) {
- if (needs_clflush_after) {
- void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
- drm_clflush_virt_range(ptr,
- (void *)(cmd + 1) - ptr);
- }
+ if (*cmd == MI_BATCH_BUFFER_END)
break;
- }
desc = find_cmd(engine, *cmd, desc, &default_desc);
if (!desc) {
DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
*cmd);
ret = -EINVAL;
- break;
- }
-
- /*
- * If the batch buffer contains a chained batch, return an
- * error that tells the caller to abort and dispatch the
- * workload as a non-secure batch.
- */
- if (desc->cmd.value == MI_BATCH_BUFFER_START) {
- ret = -EACCES;
- break;
+ goto err;
}
if (desc->flags & CMD_DESC_FIXED)
@@ -1321,22 +1476,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
length,
batch_end - cmd);
ret = -EINVAL;
- break;
+ goto err;
}
- if (!check_cmd(engine, desc, cmd, length, is_master)) {
+ if (!check_cmd(engine, desc, cmd, length)) {
ret = -EACCES;
+ goto err;
+ }
+
+ if (desc->cmd.value == MI_BATCH_BUFFER_START) {
+ ret = check_bbstart(ctx, cmd, offset, length,
+ batch_len, batch_start,
+ shadow_batch_start);
+
+ if (ret)
+ goto err;
break;
}
+ if (ctx->jump_whitelist_cmds > offset)
+ set_bit(offset, ctx->jump_whitelist);
+
cmd += length;
+ offset += length;
if (cmd >= batch_end) {
DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
ret = -EINVAL;
- break;
+ goto err;
}
} while (1);
+ if (needs_clflush_after) {
+ void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
+
+ drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
+ }
+
+err:
i915_gem_object_unpin_map(shadow_batch_obj);
return ret;
}
@@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
/* If the command parser is not enabled, report 0 - unsupported */
for_each_uabi_engine(engine, dev_priv) {
- if (intel_engine_needs_cmd_parser(engine)) {
+ if (intel_engine_using_cmd_parser(engine)) {
active = true;
break;
}
@@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
* the parser enabled.
* 9. Don't whitelist or handle oacontrol specially, as ownership
* for oacontrol state is moving to i915-perf.
+ * 10. Support for Gen9 BCS Parsing
*/
- return 9;
+ return 10;
}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 020696726f9e..3d717e282908 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -364,9 +364,6 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
if (ret)
goto cleanup_vga_client;
- /* must happen before intel_power_domains_init_hw() on VLV/CHV */
- intel_update_rawclk(dev_priv);
-
intel_power_domains_init_hw(dev_priv, false);
intel_csr_ucode_init(dev_priv);
@@ -1850,6 +1847,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
i915_gem_suspend_late(dev_priv);
+ i915_rc6_ctx_wa_suspend(dev_priv);
+
intel_uncore_suspend(&dev_priv->uncore);
intel_power_domains_suspend(dev_priv,
@@ -1924,6 +1923,11 @@ static int i915_drm_resume(struct drm_device *dev)
if (ret)
DRM_ERROR("failed to re-enable GGTT\n");
+ mutex_lock(&dev_priv->drm.struct_mutex);
+ i915_gem_restore_gtt_mappings(dev_priv);
+ i915_gem_restore_fences(dev_priv);
+ mutex_unlock(&dev_priv->drm.struct_mutex);
+
intel_csr_ucode_resume(dev_priv);
i915_restore_state(dev_priv);
@@ -2048,6 +2052,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
intel_power_domains_resume(dev_priv);
+ i915_rc6_ctx_wa_resume(dev_priv);
+
intel_gt_sanitize(&dev_priv->gt, true);
enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 772154e4073e..89b6112bd66b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -593,6 +593,8 @@ struct intel_rps {
struct intel_rc6 {
bool enabled;
+ bool ctx_corrupted;
+ intel_wakeref_t ctx_corrupted_wakeref;
u64 prev_hw_residency[4];
u64 cur_residency[4];
};
@@ -1723,6 +1725,8 @@ struct drm_i915_private {
struct work_struct idle_work;
} gem;
+ u8 pch_ssc_use;
+
/* For i945gm vblank irq vs. C3 workaround */
struct {
struct work_struct work;
@@ -2073,9 +2077,16 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
#define VEBOX_MASK(dev_priv) \
ENGINE_INSTANCES_MASK(dev_priv, VECS0, I915_MAX_VECS)
+/*
+ * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution
+ * All later gens can run the final buffer from the ppgtt
+ */
+#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7)
+
#define HAS_LLC(dev_priv) (INTEL_INFO(dev_priv)->has_llc)
#define HAS_SNOOP(dev_priv) (INTEL_INFO(dev_priv)->has_snoop)
#define HAS_EDRAM(dev_priv) ((dev_priv)->edram_size_mb)
+#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6)
#define HAS_WT(dev_priv) ((IS_HASWELL(dev_priv) || \
IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv))
@@ -2108,10 +2119,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
/* Early gen2 have a totally busted CS tlb and require pinned batches. */
#define HAS_BROKEN_CS_TLB(dev_priv) (IS_I830(dev_priv) || IS_I845G(dev_priv))
+#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv) \
+ (IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
+
/* WaRsDisableCoarsePowerGating:skl,cnl */
#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
- (IS_CANNONLAKE(dev_priv) || \
- IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
+ (IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
#define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
@@ -2282,6 +2295,14 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
unsigned long flags);
#define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
+struct i915_vma * __must_check
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm,
+ const struct i915_ggtt_view *view,
+ u64 size,
+ u64 alignment,
+ u64 flags);
+
void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
static inline int __must_check
@@ -2391,12 +2412,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+int intel_engine_cmd_parser(struct i915_gem_context *cxt,
+ struct intel_engine_cs *engine,
struct drm_i915_gem_object *batch_obj,
- struct drm_i915_gem_object *shadow_batch_obj,
+ u64 user_batch_start,
u32 batch_start_offset,
u32 batch_len,
- bool is_master);
+ struct drm_i915_gem_object *shadow_batch_obj,
+ u64 shadow_batch_start);
/* intel_device_info.c */
static inline struct intel_device_info *
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 95e7c52cf8ed..98305d987ac1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -964,11 +964,28 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
{
struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
struct i915_address_space *vm = &dev_priv->ggtt.vm;
+
+ return i915_gem_object_pin(obj, vm, view, size, alignment,
+ flags | PIN_GLOBAL);
+}
+
+struct i915_vma *
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm,
+ const struct i915_ggtt_view *view,
+ u64 size,
+ u64 alignment,
+ u64 flags)
+{
+ struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
struct i915_vma *vma;
int ret;
lockdep_assert_held(&obj->base.dev->struct_mutex);
+ if (i915_gem_object_never_bind_ggtt(obj))
+ return ERR_PTR(-ENODEV);
+
if (flags & PIN_MAPPABLE &&
(!view || view->type == I915_GGTT_VIEW_NORMAL)) {
/* If the required space is larger than the available
@@ -1035,7 +1052,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
return ERR_PTR(ret);
}
- ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
+ ret = i915_vma_pin(vma, size, alignment, flags);
if (ret)
return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 167a7b56ed5b..6795f1daa3d5 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -77,6 +77,12 @@ struct drm_i915_private;
#define I915_GEM_IDLE_TIMEOUT (HZ / 5)
+static inline void tasklet_lock(struct tasklet_struct *t)
+{
+ while (!tasklet_trylock(t))
+ cpu_relax();
+}
+
static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
{
if (!atomic_fetch_inc(&t->count))
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 5d9101376a3d..9f1517af5b7f 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -62,7 +62,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
value = !!(i915->caps.scheduler & I915_SCHEDULER_CAP_SEMAPHORES);
break;
case I915_PARAM_HAS_SECURE_BATCHES:
- value = capable(CAP_SYS_ADMIN);
+ value = HAS_SECURE_BATCHES(i915) && capable(CAP_SYS_ADMIN);
break;
case I915_PARAM_CMD_PARSER_VERSION:
value = i915_cmd_parser_get_version(i915);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2abd199093c5..f8ee9aba3955 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -471,6 +471,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
#define ECOCHK_PPGTT_WT_HSW (0x2 << 3)
#define ECOCHK_PPGTT_WB_HSW (0x3 << 3)
+#define GEN8_RC6_CTX_INFO _MMIO(0x8504)
+
#define GAC_ECO_BITS _MMIO(0x14090)
#define ECOBITS_SNB_BIT (1 << 13)
#define ECOBITS_PPGTT_CACHE64B (3 << 8)
@@ -555,6 +557,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
*/
#define BCS_SWCTRL _MMIO(0x22200)
+/* There are 16 GPR registers */
+#define BCS_GPR(n) _MMIO(0x22600 + (n) * 8)
+#define BCS_GPR_UDW(n) _MMIO(0x22600 + (n) * 8 + 4)
+
#define GPGPU_THREADS_DISPATCHED _MMIO(0x2290)
#define GPGPU_THREADS_DISPATCHED_UDW _MMIO(0x2290 + 4)
#define HS_INVOCATION_COUNT _MMIO(0x2300)
@@ -7211,6 +7217,10 @@ enum {
#define TGL_DMC_DEBUG_DC5_COUNT _MMIO(0x101084)
#define TGL_DMC_DEBUG_DC6_COUNT _MMIO(0x101088)
+/* Display Internal Timeout Register */
+#define RM_TIMEOUT _MMIO(0x42060)
+#define MMIO_TIMEOUT_US(us) ((us) << 0)
+
/* interrupts */
#define DE_MASTER_IRQ_CONTROL (1 << 31)
#define DE_SPRITEB_FLIP_DONE (1 << 29)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a53777dd371c..1c5506822dc7 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -194,6 +194,27 @@ static void free_capture_list(struct i915_request *request)
}
}
+static void remove_from_engine(struct i915_request *rq)
+{
+ struct intel_engine_cs *engine, *locked;
+
+ /*
+ * Virtual engines complicate acquiring the engine timeline lock,
+ * as their rq->engine pointer is not stable until under that
+ * engine lock. The simple ploy we use is to take the lock then
+ * check that the rq still belongs to the newly locked engine.
+ */
+ locked = READ_ONCE(rq->engine);
+ spin_lock(&locked->active.lock);
+ while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+ spin_unlock(&locked->active.lock);
+ spin_lock(&engine->active.lock);
+ locked = engine;
+ }
+ list_del(&rq->sched.link);
+ spin_unlock(&locked->active.lock);
+}
+
static bool i915_request_retire(struct i915_request *rq)
{
struct i915_active_request *active, *next;
@@ -259,9 +280,7 @@ static bool i915_request_retire(struct i915_request *rq)
* request that we have removed from the HW and put back on a run
* queue.
*/
- spin_lock(&rq->engine->active.lock);
- list_del(&rq->sched.link);
- spin_unlock(&rq->engine->active.lock);
+ remove_from_engine(rq);
spin_lock(&rq->lock);
i915_request_mark_complete(rq);
@@ -358,9 +377,10 @@ __i915_request_await_execution(struct i915_request *rq,
return 0;
}
-void __i915_request_submit(struct i915_request *request)
+bool __i915_request_submit(struct i915_request *request)
{
struct intel_engine_cs *engine = request->engine;
+ bool result = false;
GEM_TRACE("%s fence %llx:%lld, current %d\n",
engine->name,
@@ -370,6 +390,25 @@ void __i915_request_submit(struct i915_request *request)
GEM_BUG_ON(!irqs_disabled());
lockdep_assert_held(&engine->active.lock);
+ /*
+ * With the advent of preempt-to-busy, we frequently encounter
+ * requests that we have unsubmitted from HW, but left running
+ * until the next ack and so have completed in the meantime. On
+ * resubmission of that completed request, we can skip
+ * updating the payload, and execlists can even skip submitting
+ * the request.
+ *
+ * We must remove the request from the caller's priority queue,
+ * and the caller must only call us when the request is in their
+ * priority queue, under the active.lock. This ensures that the
+ * request has *not* yet been retired and we can safely move
+ * the request into the engine->active.list where it will be
+ * dropped upon retiring. (Otherwise if resubmit a *retired*
+ * request, this would be a horrible use-after-free.)
+ */
+ if (i915_request_completed(request))
+ goto xfer;
+
if (i915_gem_context_is_banned(request->gem_context))
i915_request_skip(request, -EIO);
@@ -393,13 +432,18 @@ void __i915_request_submit(struct i915_request *request)
i915_sw_fence_signaled(&request->semaphore))
engine->saturated |= request->sched.semaphores;
- /* We may be recursing from the signal callback of another i915 fence */
- spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
+ engine->emit_fini_breadcrumb(request,
+ request->ring->vaddr + request->postfix);
- list_move_tail(&request->sched.link, &engine->active.requests);
+ trace_i915_request_execute(request);
+ engine->serial++;
+ result = true;
+
+xfer: /* We may be recursing from the signal callback of another i915 fence */
+ spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
- GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
- set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
+ if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags))
+ list_move_tail(&request->sched.link, &engine->active.requests);
if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
@@ -410,12 +454,7 @@ void __i915_request_submit(struct i915_request *request)
spin_unlock(&request->lock);
- engine->emit_fini_breadcrumb(request,
- request->ring->vaddr + request->postfix);
-
- engine->serial++;
-
- trace_i915_request_execute(request);
+ return result;
}
void i915_request_submit(struct i915_request *request)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 8ac6e1226a56..e4dd013761e8 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -292,7 +292,7 @@ int i915_request_await_execution(struct i915_request *rq,
void i915_request_add(struct i915_request *rq);
-void __i915_request_submit(struct i915_request *request);
+bool __i915_request_submit(struct i915_request *request);
void i915_request_submit(struct i915_request *request);
void i915_request_skip(struct i915_request *request, int error);
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index fa864d8f2b73..15f8bff141f9 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -69,6 +69,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
return PCH_CNP;
case INTEL_PCH_CMP_DEVICE_ID_TYPE:
+ case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
WARN_ON(!IS_COFFEELAKE(dev_priv));
/* CometPoint is CNP Compatible */
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index e6a2d65f19c6..c29c81ec7971 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -41,6 +41,7 @@ enum intel_pch {
#define INTEL_PCH_CNP_DEVICE_ID_TYPE 0xA300
#define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE 0x9D80
#define INTEL_PCH_CMP_DEVICE_ID_TYPE 0x0280
+#define INTEL_PCH_CMP2_DEVICE_ID_TYPE 0x0680
#define INTEL_PCH_ICP_DEVICE_ID_TYPE 0x3480
#define INTEL_PCH_MCC_DEVICE_ID_TYPE 0x4B00
#define INTEL_PCH_MCC2_DEVICE_ID_TYPE 0x3880
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75ee027abb80..2efe1d12d5a9 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -126,6 +126,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
*/
I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
PWM1_GATING_DIS | PWM2_GATING_DIS);
+
+ /*
+ * Lower the display internal timeout.
+ * This is needed to avoid any hard hangs when DSI port PLL
+ * is off and a MMIO access is attempted by any privilege
+ * application, using batch buffers or any other means.
+ */
+ I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950));
}
static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -8544,6 +8552,100 @@ static void intel_init_emon(struct drm_i915_private *dev_priv)
dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
}
+static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv)
+{
+ return !I915_READ(GEN8_RC6_CTX_INFO);
+}
+
+static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915)
+{
+ if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+ return;
+
+ if (i915_rc6_ctx_corrupted(i915)) {
+ DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
+ i915->gt_pm.rc6.ctx_corrupted = true;
+ i915->gt_pm.rc6.ctx_corrupted_wakeref =
+ intel_runtime_pm_get(&i915->runtime_pm);
+ }
+}
+
+static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915)
+{
+ if (i915->gt_pm.rc6.ctx_corrupted) {
+ intel_runtime_pm_put(&i915->runtime_pm,
+ i915->gt_pm.rc6.ctx_corrupted_wakeref);
+ i915->gt_pm.rc6.ctx_corrupted = false;
+ }
+}
+
+/**
+ * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to clean up the RC6 CTX WA before system suspend.
+ */
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915)
+{
+ if (i915->gt_pm.rc6.ctx_corrupted)
+ intel_runtime_pm_put(&i915->runtime_pm,
+ i915->gt_pm.rc6.ctx_corrupted_wakeref);
+}
+
+/**
+ * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to re-init the RC6 CTX WA after system resume.
+ */
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915)
+{
+ if (!i915->gt_pm.rc6.ctx_corrupted)
+ return;
+
+ if (i915_rc6_ctx_corrupted(i915)) {
+ i915->gt_pm.rc6.ctx_corrupted_wakeref =
+ intel_runtime_pm_get(&i915->runtime_pm);
+ return;
+ }
+
+ DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
+ i915->gt_pm.rc6.ctx_corrupted = false;
+}
+
+static void intel_disable_rc6(struct drm_i915_private *dev_priv);
+
+/**
+ * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption
+ * @i915: i915 device
+ *
+ * Check if an RC6 CTX corruption has happened since the last check and if so
+ * disable RC6 and runtime power management.
+ *
+ * Return false if no context corruption has happened since the last call of
+ * this function, true otherwise.
+*/
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915)
+{
+ if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+ return false;
+
+ if (i915->gt_pm.rc6.ctx_corrupted)
+ return false;
+
+ if (!i915_rc6_ctx_corrupted(i915))
+ return false;
+
+ DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
+
+ intel_disable_rc6(i915);
+ i915->gt_pm.rc6.ctx_corrupted = true;
+ i915->gt_pm.rc6.ctx_corrupted_wakeref =
+ intel_runtime_pm_get_noresume(&i915->runtime_pm);
+
+ return true;
+}
+
void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
{
struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -8557,6 +8659,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
pm_runtime_get(&dev_priv->drm.pdev->dev);
}
+ i915_rc6_ctx_wa_init(dev_priv);
+
/* Initialize RPS limits (for userspace) */
if (IS_CHERRYVIEW(dev_priv))
cherryview_init_gt_powersave(dev_priv);
@@ -8595,6 +8699,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
if (IS_VALLEYVIEW(dev_priv))
valleyview_cleanup_gt_powersave(dev_priv);
+ i915_rc6_ctx_wa_cleanup(dev_priv);
+
if (!HAS_RC6(dev_priv))
pm_runtime_put(&dev_priv->drm.pdev->dev);
}
@@ -8623,7 +8729,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
i915->gt_pm.llc_pstate.enabled = false;
}
-static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+static void __intel_disable_rc6(struct drm_i915_private *dev_priv)
{
lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@@ -8642,6 +8748,15 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv)
dev_priv->gt_pm.rc6.enabled = false;
}
+static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+{
+ struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
+ mutex_lock(&rps->lock);
+ __intel_disable_rc6(dev_priv);
+ mutex_unlock(&rps->lock);
+}
+
static void intel_disable_rps(struct drm_i915_private *dev_priv)
{
lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@@ -8667,7 +8782,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
{
mutex_lock(&dev_priv->gt_pm.rps.lock);
- intel_disable_rc6(dev_priv);
+ __intel_disable_rc6(dev_priv);
intel_disable_rps(dev_priv);
if (HAS_LLC(dev_priv))
intel_disable_llc_pstate(dev_priv);
@@ -8694,6 +8809,9 @@ static void intel_enable_rc6(struct drm_i915_private *dev_priv)
if (dev_priv->gt_pm.rc6.enabled)
return;
+ if (dev_priv->gt_pm.rc6.ctx_corrupted)
+ return;
+
if (IS_CHERRYVIEW(dev_priv))
cherryview_enable_rc6(dev_priv);
else if (IS_VALLEYVIEW(dev_priv))
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index e3573e1e16e3..0f7390c850ec 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -36,6 +36,9 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv);
void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915);
void gen6_rps_busy(struct drm_i915_private *dev_priv);
void gen6_rps_idle(struct drm_i915_private *dev_priv);
void gen6_rps_boost(struct i915_request *rq);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index bb6dd54a6ff3..37593831b539 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -118,6 +118,12 @@ static void pm_resume(struct drm_i915_private *i915)
with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
intel_gt_sanitize(&i915->gt, false);
i915_gem_sanitize(i915);
+
+ mutex_lock(&i915->drm.struct_mutex);
+ i915_gem_restore_gtt_mappings(i915);
+ i915_gem_restore_fences(i915);
+ mutex_unlock(&i915->drm.struct_mutex);
+
i915_gem_resume(i915);
}
}
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 663ff9f4fac9..1e7b1be25bb0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -26,6 +26,8 @@
#include "dsi_cfg.h"
#include "msm_kms.h"
+#define DSI_RESET_TOGGLE_DELAY_MS 20
+
static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
{
u32 ver;
@@ -986,7 +988,7 @@ static void dsi_sw_reset(struct msm_dsi_host *msm_host)
wmb(); /* clocks need to be enabled before reset */
dsi_write(msm_host, REG_DSI_RESET, 1);
- wmb(); /* make sure reset happen */
+ msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
dsi_write(msm_host, REG_DSI_RESET, 0);
}
@@ -1396,7 +1398,7 @@ static void dsi_sw_reset_restore(struct msm_dsi_host *msm_host)
/* dsi controller can only be reset while clocks are running */
dsi_write(msm_host, REG_DSI_RESET, 1);
- wmb(); /* make sure reset happen */
+ msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
dsi_write(msm_host, REG_DSI_RESET, 0);
wmb(); /* controller out of reset */
dsi_write(msm_host, REG_DSI_CTRL, data0);
diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
index fc82a525b071..ee4379729a5b 100644
--- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c
+++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
@@ -220,9 +220,17 @@ static const struct of_device_id lb035q02_of_match[] = {
MODULE_DEVICE_TABLE(of, lb035q02_of_match);
+static const struct spi_device_id lb035q02_ids[] = {
+ { "lb035q02", 0 },
+ { /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, lb035q02_ids);
+
static struct spi_driver lb035q02_driver = {
.probe = lb035q02_probe,
.remove = lb035q02_remove,
+ .id_table = lb035q02_ids,
.driver = {
.name = "panel-lg-lb035q02",
.of_match_table = lb035q02_of_match,
@@ -231,7 +239,6 @@ static struct spi_driver lb035q02_driver = {
module_spi_driver(lb035q02_driver);
-MODULE_ALIAS("spi:lgphilips,lb035q02");
MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>");
MODULE_DESCRIPTION("LG.Philips LB035Q02 LCD Panel driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
index 299b217c83e1..20f17e46e65d 100644
--- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
@@ -230,9 +230,17 @@ static const struct of_device_id nl8048_of_match[] = {
MODULE_DEVICE_TABLE(of, nl8048_of_match);
+static const struct spi_device_id nl8048_ids[] = {
+ { "nl8048hl11", 0 },
+ { /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, nl8048_ids);
+
static struct spi_driver nl8048_driver = {
.probe = nl8048_probe,
.remove = nl8048_remove,
+ .id_table = nl8048_ids,
.driver = {
.name = "panel-nec-nl8048hl11",
.pm = &nl8048_pm_ops,
@@ -242,7 +250,6 @@ static struct spi_driver nl8048_driver = {
module_spi_driver(nl8048_driver);
-MODULE_ALIAS("spi:nec,nl8048hl11");
MODULE_AUTHOR("Erik Gilling <konkers@android.com>");
MODULE_DESCRIPTION("NEC-NL8048HL11 Driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
index 305259b58767..3d5b9c4f68d9 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
@@ -684,9 +684,17 @@ static const struct of_device_id acx565akm_of_match[] = {
MODULE_DEVICE_TABLE(of, acx565akm_of_match);
+static const struct spi_device_id acx565akm_ids[] = {
+ { "acx565akm", 0 },
+ { /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, acx565akm_ids);
+
static struct spi_driver acx565akm_driver = {
.probe = acx565akm_probe,
.remove = acx565akm_remove,
+ .id_table = acx565akm_ids,
.driver = {
.name = "panel-sony-acx565akm",
.of_match_table = acx565akm_of_match,
@@ -695,7 +703,6 @@ static struct spi_driver acx565akm_driver = {
module_spi_driver(acx565akm_driver);
-MODULE_ALIAS("spi:sony,acx565akm");
MODULE_AUTHOR("Nokia Corporation");
MODULE_DESCRIPTION("Sony ACX565AKM LCD Panel Driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
index d7b2e34626ef..f2baff827f50 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
@@ -375,8 +375,7 @@ static const struct of_device_id td028ttec1_of_match[] = {
MODULE_DEVICE_TABLE(of, td028ttec1_of_match);
static const struct spi_device_id td028ttec1_ids[] = {
- { "tpo,td028ttec1", 0},
- { "toppoly,td028ttec1", 0 },
+ { "td028ttec1", 0 },
{ /* sentinel */ }
};
diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
index 84370562910f..ba163c779084 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
@@ -491,9 +491,17 @@ static const struct of_device_id td043mtea1_of_match[] = {
MODULE_DEVICE_TABLE(of, td043mtea1_of_match);
+static const struct spi_device_id td043mtea1_ids[] = {
+ { "td043mtea1", 0 },
+ { /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, td043mtea1_ids);
+
static struct spi_driver td043mtea1_driver = {
.probe = td043mtea1_probe,
.remove = td043mtea1_remove,
+ .id_table = td043mtea1_ids,
.driver = {
.name = "panel-tpo-td043mtea1",
.pm = &td043mtea1_pm_ops,
@@ -503,7 +511,6 @@ static struct spi_driver td043mtea1_driver = {
module_spi_driver(td043mtea1_driver);
-MODULE_ALIAS("spi:tpo,td043mtea1");
MODULE_AUTHOR("GraÅžvydas Ignotas <notasas@gmail.com>");
MODULE_DESCRIPTION("TPO TD043MTEA1 Panel Driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index bc2ddeb55f5d..f21bc8a7ee3a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -556,11 +556,11 @@ static int panfrost_probe(struct platform_device *pdev)
return 0;
err_out2:
+ pm_runtime_disable(pfdev->dev);
panfrost_devfreq_fini(pfdev);
err_out1:
panfrost_device_fini(pfdev);
err_out0:
- pm_runtime_disable(pfdev->dev);
drm_dev_put(ddev);
return err;
}
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index f67ed925c0ef..8822ec13a0d6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -208,6 +208,9 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev)
pfdev->features.mem_features = gpu_read(pfdev, GPU_MEM_FEATURES);
pfdev->features.mmu_features = gpu_read(pfdev, GPU_MMU_FEATURES);
pfdev->features.thread_features = gpu_read(pfdev, GPU_THREAD_FEATURES);
+ pfdev->features.max_threads = gpu_read(pfdev, GPU_THREAD_MAX_THREADS);
+ pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE);
+ pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE);
pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES);
for (i = 0; i < 4; i++)
pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i));
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a58551668d9a..21f34d44aac2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
job_read(pfdev, JS_TAIL_LO(js)),
sched_job);
- mutex_lock(&pfdev->reset_lock);
+ if (!mutex_trylock(&pfdev->reset_lock))
+ return;
- for (i = 0; i < NUM_JOB_SLOTS; i++)
- drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
+ for (i = 0; i < NUM_JOB_SLOTS; i++) {
+ struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
+
+ drm_sched_stop(sched, sched_job);
+ if (js != i)
+ /* Ensure any timeouts on other slots have finished */
+ cancel_delayed_work_sync(&sched->work_tdr);
+ }
- if (sched_job)
- drm_sched_increase_karma(sched_job);
+ drm_sched_increase_karma(sched_job);
spin_lock_irqsave(&pfdev->js->job_lock, flags);
for (i = 0; i < NUM_JOB_SLOTS; i++) {
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index bdd990568476..a3ed64a1f15e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -224,9 +224,9 @@ static size_t get_pgsize(u64 addr, size_t size)
return SZ_2M;
}
-void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
- struct panfrost_mmu *mmu,
- u64 iova, size_t size)
+static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
+ struct panfrost_mmu *mmu,
+ u64 iova, size_t size)
{
if (mmu->as < 0)
return;
@@ -406,11 +406,11 @@ addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
spin_lock(&pfdev->as_lock);
list_for_each_entry(mmu, &pfdev->as_lru_list, list) {
if (as == mmu->as)
- break;
+ goto found_mmu;
}
- if (as != mmu->as)
- goto out;
+ goto out;
+found_mmu:
priv = container_of(mmu, struct panfrost_file_priv, mmu);
spin_lock(&priv->mm_lock);
@@ -432,7 +432,8 @@ out:
#define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE)
-int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
+static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
+ u64 addr)
{
int ret, i;
struct panfrost_gem_object *bo;
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 83c57d325ca8..2dba192bf198 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -16,6 +16,7 @@
#include "panfrost_issues.h"
#include "panfrost_job.h"
#include "panfrost_mmu.h"
+#include "panfrost_perfcnt.h"
#include "panfrost_regs.h"
#define COUNTERS_PER_BLOCK 64
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index d0bc91ed7c90..4528f4dc0b2d 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -379,7 +379,9 @@ radeon_pci_remove(struct pci_dev *pdev)
static void
radeon_pci_shutdown(struct pci_dev *pdev)
{
+#ifdef CONFIG_PPC64
struct drm_device *ddev = pci_get_drvdata(pdev);
+#endif
/* if we are running in a VM, make sure the device
* torn down properly on reboot/shutdown
@@ -387,11 +389,15 @@ radeon_pci_shutdown(struct pci_dev *pdev)
if (radeon_device_is_virtual())
radeon_pci_remove(pdev);
+#ifdef CONFIG_PPC64
/* Some adapters need to be suspended before a
- * shutdown occurs in order to prevent an error
- * during kexec.
- */
+ * shutdown occurs in order to prevent an error
+ * during kexec.
+ * Make this power specific becauase it breaks
+ * some non-power boards.
+ */
radeon_suspend_kms(ddev, true, true, false);
+#endif
}
static int radeon_pmops_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 460fd98e40a7..a0b382a637a6 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -1958,6 +1958,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
case 0x682C:
si_pi->cac_weights = cac_weights_cape_verde_pro;
si_pi->dte_data = dte_data_sun_xt;
+ update_dte_from_pl2 = true;
break;
case 0x6825:
case 0x6827:
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74d82dc..f39b97ed4ade 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
struct drm_sched_job *s_job, *tmp;
uint64_t guilty_context;
bool found_guilty = false;
+ struct dma_fence *fence;
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
dma_fence_set_error(&s_fence->finished, -ECANCELED);
dma_fence_put(s_job->s_fence->parent);
- s_job->s_fence->parent = sched->ops->run_job(s_job);
+ fence = sched->ops->run_job(s_job);
+
+ if (IS_ERR_OR_NULL(fence)) {
+ s_job->s_fence->parent = NULL;
+ dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+ } else {
+ s_job->s_fence->parent = fence;
+ }
+
+
}
}
EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@@ -720,7 +730,7 @@ static int drm_sched_main(void *param)
fence = sched->ops->run_job(sched_job);
drm_sched_fence_scheduled(s_fence);
- if (fence) {
+ if (!IS_ERR_OR_NULL(fence)) {
s_fence->parent = dma_fence_get(fence);
r = dma_fence_add_callback(fence, &sched_job->cb,
drm_sched_process_job);
@@ -730,8 +740,11 @@ static int drm_sched_main(void *param)
DRM_ERROR("fence add callback failed (%d)\n",
r);
dma_fence_put(fence);
- } else
+ } else {
+
+ dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
drm_sched_process_job(NULL, &sched_job->cb);
+ }
wake_up(&sched->job_scheduled);
}
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 04c721d0d3b9..b89439ed210d 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -488,7 +488,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
WARN_ON(!tcon->quirks->has_channel_0);
- tcon->dclk_min_div = 6;
+ tcon->dclk_min_div = 1;
tcon->dclk_max_div = 127;
sun4i_tcon0_mode_set_common(tcon, mode);
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 504763423d46..a46ac284dd5e 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -63,7 +63,6 @@ config TINYDRM_REPAPER
depends on DRM && SPI
select DRM_KMS_HELPER
select DRM_KMS_CMA_HELPER
- depends on THERMAL || !THERMAL
help
DRM driver for the following Pervasive Displays panels:
1.44" TFT EPD Panel (E1144CS021)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 20ff56f27aa4..98819462f025 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -185,8 +185,9 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
list_add_tail(&bo->lru, &man->lru[bo->priority]);
kref_get(&bo->list_kref);
- if (bo->ttm && !(bo->ttm->page_flags &
- (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) {
+ if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
+ !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
+ TTM_PAGE_FLAG_SWAPPED))) {
list_add_tail(&bo->swap, &bdev->glob->swap_lru[bo->priority]);
kref_get(&bo->list_kref);
}
@@ -878,11 +879,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
if (!bo) {
if (busy_bo)
- ttm_bo_get(busy_bo);
+ kref_get(&busy_bo->list_kref);
spin_unlock(&glob->lru_lock);
ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
if (busy_bo)
- ttm_bo_put(busy_bo);
+ kref_put(&busy_bo->list_kref, ttm_bo_release_list);
return ret;
}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 76eedb963693..46dc3de7e81b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -278,15 +278,13 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
else
ret = vmf_insert_pfn(&cvma, address, pfn);
- /*
- * Somebody beat us to this PTE or prefaulting to
- * an already populated PTE, or prefaulting error.
- */
-
- if (unlikely((ret == VM_FAULT_NOPAGE && i > 0)))
- break;
- else if (unlikely(ret & VM_FAULT_ERROR))
- goto out_io_unlock;
+ /* Never error on prefaulted PTEs */
+ if (unlikely((ret & VM_FAULT_ERROR))) {
+ if (i == 0)
+ goto out_io_unlock;
+ else
+ break;
+ }
address += PAGE_SIZE;
if (unlikely(++page_offset >= page_last))
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 5d80507b539b..19c092d75266 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -557,13 +557,16 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
if (args->bcl_start != args->bcl_end) {
bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
- if (!bin)
+ if (!bin) {
+ v3d_job_put(&render->base);
return -ENOMEM;
+ }
ret = v3d_job_init(v3d, file_priv, &bin->base,
v3d_job_free, args->in_sync_bcl);
if (ret) {
v3d_job_put(&render->base);
+ kfree(bin);
return ret;
}
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index ba1828acd8c9..4be49c1aef51 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -718,17 +718,9 @@ static int xen_drv_probe(struct xenbus_device *xb_dev,
struct device *dev = &xb_dev->dev;
int ret;
- /*
- * The device is not spawn from a device tree, so arch_setup_dma_ops
- * is not called, thus leaving the device with dummy DMA ops.
- * This makes the device return error on PRIME buffer import, which
- * is not correct: to fix this call of_dma_configure() with a NULL
- * node to set default DMA ops.
- */
- dev->coherent_dma_mask = DMA_BIT_MASK(32);
- ret = of_dma_configure(dev, NULL, true);
+ ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
if (ret < 0) {
- DRM_ERROR("Cannot setup DMA ops, ret %d", ret);
+ DRM_ERROR("Cannot setup DMA mask, ret %d", ret);
return ret;
}