summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm')
-rw-r--r--drivers/gpu/drm/Kconfig5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu.h5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c18
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c12
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c15
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc15.c31
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc21.c4
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c4
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c9
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_priv.h1
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c4
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_topology.c10
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c99
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c6
-rw-r--r--drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c16
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c15
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc_state.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c7
-rw-r--r--drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c5
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c18
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/Makefile6
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c17
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c9
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c5
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h4
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h4
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c63
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c76
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h2
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h1
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h7
-rw-r--r--drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h2
-rw-r--r--drivers/gpu/drm/amd/display/dc/inc/resource.h20
-rw-r--r--drivers/gpu/drm/amd/display/dc/link/link_factory.c26
-rw-r--r--drivers/gpu/drm/amd/display/dc/link/link_validation.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c5
-rw-r--r--drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c16
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c5
-rw-r--r--drivers/gpu/drm/amd/pm/amdgpu_pm.c12
-rw-r--r--drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c29
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c9
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c9
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c9
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c9
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c9
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c2
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c5
-rw-r--r--drivers/gpu/drm/bridge/aux-hpd-bridge.c70
-rw-r--r--drivers/gpu/drm/drm_buddy.c22
-rw-r--r--drivers/gpu/drm/drm_crtc.c1
-rw-r--r--drivers/gpu/drm/drm_prime.c2
-rw-r--r--drivers/gpu/drm/drm_probe_helper.c8
-rw-r--r--drivers/gpu/drm/drm_syncobj.c19
-rw-r--r--drivers/gpu/drm/i915/Kconfig2
-rw-r--r--drivers/gpu/drm/i915/display/intel_display_power_well.c17
-rw-r--r--drivers/gpu/drm/i915/display/intel_display_types.h7
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp.c19
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp.h2
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp_hdcp.c47
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp_mst.c1
-rw-r--r--drivers/gpu/drm/i915/display/intel_modeset_setup.c13
-rw-r--r--drivers/gpu/drm/i915/display/intel_psr.c3
-rw-r--r--drivers/gpu/drm/i915/display/intel_sdvo.c10
-rw-r--r--drivers/gpu/drm/i915/display/intel_tv.c10
-rw-r--r--drivers/gpu/drm/i915/display/intel_vdsc_regs.h4
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_userptr.c3
-rw-r--r--drivers/gpu/drm/i915/gvt/handlers.c3
-rw-r--r--drivers/gpu/drm/i915/intel_gvt.c2
-rw-r--r--drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c6
-rw-r--r--drivers/gpu/drm/meson/meson_encoder_cvbs.c1
-rw-r--r--drivers/gpu/drm/meson/meson_encoder_dsi.c1
-rw-r--r--drivers/gpu/drm/meson/meson_encoder_hdmi.c1
-rw-r--r--drivers/gpu/drm/msm/adreno/a6xx_gpu.c2
-rw-r--r--drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c8
-rw-r--r--drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c3
-rw-r--r--drivers/gpu/drm/msm/dp/dp_ctrl.c5
-rw-r--r--drivers/gpu/drm/msm/dp/dp_display.c20
-rw-r--r--drivers/gpu/drm/msm/dp/dp_link.c22
-rw-r--r--drivers/gpu/drm/msm/dp/dp_reg.h3
-rw-r--r--drivers/gpu/drm/msm/msm_gem_prime.c4
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.c11
-rw-r--r--drivers/gpu/drm/msm/msm_iommu.c32
-rw-r--r--drivers/gpu/drm/msm/msm_mdss.c1
-rw-r--r--drivers/gpu/drm/msm/msm_ringbuffer.c7
-rw-r--r--drivers/gpu/drm/nouveau/Kconfig8
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/client.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_abi16.c29
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_abi16.h2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_drm.c7
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_drv.h2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_exec.c2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_gem.c2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_sched.c38
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_sched.h6
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_svm.c2
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_uvmm.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/client.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/core/object.c26
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c5
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c8
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c83
-rw-r--r--drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c8
-rw-r--r--drivers/gpu/drm/rockchip/rockchip_drm_vop2.c4
-rw-r--r--drivers/gpu/drm/scheduler/sched_main.c15
-rw-r--r--drivers/gpu/drm/tegra/drm.c23
-rw-r--r--drivers/gpu/drm/tests/drm_buddy_test.c306
-rw-r--r--drivers/gpu/drm/ttm/ttm_pool.c2
-rw-r--r--drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h2
-rw-r--r--drivers/gpu/drm/xe/tests/xe_mocs_test.c1
-rw-r--r--drivers/gpu/drm/xe/xe_bo.c11
-rw-r--r--drivers/gpu/drm/xe/xe_bo.h1
-rw-r--r--drivers/gpu/drm/xe/xe_device.c39
-rw-r--r--drivers/gpu/drm/xe/xe_device.h4
-rw-r--r--drivers/gpu/drm/xe/xe_device_types.h8
-rw-r--r--drivers/gpu/drm/xe/xe_display.c6
-rw-r--r--drivers/gpu/drm/xe/xe_drm_client.c12
-rw-r--r--drivers/gpu/drm/xe/xe_exec_queue.c129
-rw-r--r--drivers/gpu/drm/xe/xe_exec_queue_types.h20
-rw-r--r--drivers/gpu/drm/xe/xe_execlist.c4
-rw-r--r--drivers/gpu/drm/xe/xe_gt.c5
-rw-r--r--drivers/gpu/drm/xe/xe_gt_idle.c4
-rw-r--r--drivers/gpu/drm/xe/xe_gt_pagefault.c2
-rw-r--r--drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c12
-rw-r--r--drivers/gpu/drm/xe/xe_guc_submit.c2
-rw-r--r--drivers/gpu/drm/xe/xe_lrc.c10
-rw-r--r--drivers/gpu/drm/xe/xe_migrate.c28
-rw-r--r--drivers/gpu/drm/xe/xe_mmio.c2
-rw-r--r--drivers/gpu/drm/xe/xe_pt.c50
-rw-r--r--drivers/gpu/drm/xe/xe_pt_walk.c2
-rw-r--r--drivers/gpu/drm/xe/xe_pt_walk.h19
-rw-r--r--drivers/gpu/drm/xe/xe_range_fence.c7
-rw-r--r--drivers/gpu/drm/xe/xe_sched_job.c1
-rw-r--r--drivers/gpu/drm/xe/xe_sync.c60
-rw-r--r--drivers/gpu/drm/xe/xe_sync.h4
-rw-r--r--drivers/gpu/drm/xe/xe_sync_types.h2
-rw-r--r--drivers/gpu/drm/xe/xe_tile.c5
-rw-r--r--drivers/gpu/drm/xe/xe_trace.h59
-rw-r--r--drivers/gpu/drm/xe/xe_vm.c167
-rw-r--r--drivers/gpu/drm/xe/xe_vm_types.h21
157 files changed, 1593 insertions, 807 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2520db0b776e..c7edba18a6f0 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -199,7 +199,7 @@ config DRM_TTM
config DRM_TTM_KUNIT_TEST
tristate "KUnit tests for TTM" if !KUNIT_ALL_TESTS
default n
- depends on DRM && KUNIT && MMU
+ depends on DRM && KUNIT && MMU && (UML || COMPILE_TEST)
select DRM_TTM
select DRM_EXPORT_FOR_TESTS if m
select DRM_KUNIT_TEST_HELPERS
@@ -207,7 +207,8 @@ config DRM_TTM_KUNIT_TEST
help
Enables unit tests for TTM, a GPU memory manager subsystem used
to manage memory buffers. This option is mostly useful for kernel
- developers.
+ developers. It depends on (UML || COMPILE_TEST) since no other driver
+ which uses TTM can be loaded while running the tests.
If in doubt, say "N".
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 3d8a48f46b01..79827a6dcd7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -200,6 +200,7 @@ extern uint amdgpu_dc_debug_mask;
extern uint amdgpu_dc_visual_confirm;
extern uint amdgpu_dm_abm_level;
extern int amdgpu_backlight;
+extern int amdgpu_damage_clips;
extern struct amdgpu_mgpu_info mgpu_info;
extern int amdgpu_ras_enable;
extern uint amdgpu_ras_mask;
@@ -1078,6 +1079,8 @@ struct amdgpu_device {
bool in_s3;
bool in_s4;
bool in_s0ix;
+ /* indicate amdgpu suspension status */
+ bool suspend_complete;
enum pp_mp1_state mp1_state;
struct amdgpu_doorbell_index doorbell_index;
@@ -1547,9 +1550,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev,
#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
#else
static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
+static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
#endif
#if defined(CONFIG_DRM_AMD_DC)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 2deebece810e..7099ff9cf8c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1519,4 +1519,22 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
#endif /* CONFIG_AMD_PMC */
}
+/**
+ * amdgpu_choose_low_power_state
+ *
+ * @adev: amdgpu_device_pointer
+ *
+ * Choose the target low power state for the GPU
+ */
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
+{
+ if (adev->in_runpm)
+ return;
+
+ if (amdgpu_acpi_is_s0ix_active(adev))
+ adev->in_s0ix = true;
+ else if (amdgpu_acpi_is_s3_active(adev))
+ adev->in_s3 = true;
+}
+
#endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fdde7488d0ed..94bdb5fa6ebc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4514,13 +4514,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
struct amdgpu_device *adev = drm_to_adev(dev);
int i, r;
+ amdgpu_choose_low_power_state(adev);
+
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
/* Evict the majority of BOs before starting suspend sequence */
r = amdgpu_device_evict_resources(adev);
if (r)
- return r;
+ goto unprepare;
for (i = 0; i < adev->num_ip_blocks; i++) {
if (!adev->ip_blocks[i].status.valid)
@@ -4529,10 +4531,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
continue;
r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev);
if (r)
- return r;
+ goto unprepare;
}
return 0;
+
+unprepare:
+ adev->in_s0ix = adev->in_s3 = false;
+
+ return r;
}
/**
@@ -4569,7 +4576,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
cancel_delayed_work_sync(&adev->delayed_init_work);
- flush_delayed_work(&adev->gfx.gfx_off_delay_work);
amdgpu_ras_suspend(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 971acf01bea6..586f4d03039d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -211,6 +211,7 @@ int amdgpu_seamless = -1; /* auto */
uint amdgpu_debug_mask;
int amdgpu_agp = -1; /* auto */
int amdgpu_wbrf = -1;
+int amdgpu_damage_clips = -1; /* auto */
static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
@@ -860,6 +861,18 @@ MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (defau
module_param_named(backlight, amdgpu_backlight, bint, 0444);
/**
+ * DOC: damageclips (int)
+ * Enable or disable damage clips support. If damage clips support is disabled,
+ * we will force full frame updates, irrespective of what user space sends to
+ * us.
+ *
+ * Defaults to -1 (where it is enabled unless a PSR-SU display is detected).
+ */
+MODULE_PARM_DESC(damageclips,
+ "Damage clips support (0 = disable, 1 = enable, -1 auto (default))");
+module_param_named(damageclips, amdgpu_damage_clips, int, 0444);
+
+/**
* DOC: tmz (int)
* Trusted Memory Zone (TMZ) is a method to protect data being written
* to or read from memory.
@@ -2476,6 +2489,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
struct drm_device *drm_dev = dev_get_drvdata(dev);
struct amdgpu_device *adev = drm_to_adev(drm_dev);
+ adev->suspend_complete = false;
if (amdgpu_acpi_is_s0ix_active(adev))
adev->in_s0ix = true;
else if (amdgpu_acpi_is_s3_active(adev))
@@ -2490,6 +2504,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
struct drm_device *drm_dev = dev_get_drvdata(dev);
struct amdgpu_device *adev = drm_to_adev(drm_dev);
+ adev->suspend_complete = true;
if (amdgpu_acpi_should_gpu_reset(adev))
return amdgpu_asic_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b9674c57c436..6ddc8e3360e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -723,8 +723,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
if (adev->gfx.gfx_off_req_count == 0 &&
!adev->gfx.gfx_off_state) {
- schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+ /* If going to s2idle, no need to wait */
+ if (adev->in_s0ix) {
+ if (!amdgpu_dpm_set_powergating_by_smu(adev,
+ AMD_IP_BLOCK_TYPE_GFX, true))
+ adev->gfx.gfx_off_state = true;
+ } else {
+ schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
delay);
+ }
}
} else {
if (adev->gfx.gfx_off_req_count == 0) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 468a67b302d4..ca5c86e5f7cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
}
}
- if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len))
+ if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
ret = -EFAULT;
err_free_shared_buf:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 69c500910746..3bc6943365a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev)
gfx_v9_0_cp_gfx_enable(adev, true);
+ /* Now only limit the quirk on the APU gfx9 series and already
+ * confirmed that the APU gfx10/gfx11 needn't such update.
+ */
+ if (adev->flags & AMD_IS_APU &&
+ adev->in_s3 && !adev->suspend_complete) {
+ DRM_INFO(" Will skip the CSB packet resubmit\n");
+ return 0;
+ }
r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
if (r) {
DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 40a00ea0009f..e67a62db9e12 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1947,14 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev)
static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
{
- static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
- u32 vram_info;
-
- /* Only for dGPU, vendor informaton is reliable */
- if (!amdgpu_sriov_vf(adev) && !(adev->flags & AMD_IS_APU)) {
- vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
- adev->gmc.vram_vendor = vram_info & 0xF;
- }
adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
adev->gmc.vram_width = 128 * 64;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index bc38b90f8cf8..88ea58d5c4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle,
return ret;
}
-static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev,
- struct amdgpu_irq_src *source,
- unsigned type,
- enum amdgpu_interrupt_state state)
-{
- return 0;
-}
-
static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
unsigned int type,
@@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
}
static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = {
- .set = jpeg_v4_0_set_interrupt_state,
.process = jpeg_v4_0_process_interrupt,
};
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6ede85b28cc8..78b74daf4eeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle)
RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
}
- amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0);
return 0;
}
@@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
return ret;
}
-static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev,
- struct amdgpu_irq_src *source,
- unsigned type,
- enum amdgpu_interrupt_state state)
-{
- return 0;
-}
-
static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
@@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
}
static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = {
- .set = jpeg_v4_0_5_set_interrupt_state,
.process = jpeg_v4_0_5_process_interrupt,
};
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index e90f33780803..b4723d68eab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
u32 inst_mask;
int i;
+ if (amdgpu_sriov_vf(adev))
+ adev->rmmio_remap.reg_offset =
+ SOC15_REG_OFFSET(
+ NBIO, 0,
+ regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL)
+ << 2;
WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE,
0xff & ~(adev->gfx.xcc_mask));
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15033efec2ba..1c614451dead 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -574,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
return AMD_RESET_METHOD_MODE1;
}
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+ u32 sol_reg;
+
+ sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+ /* Will reset for the following suspend abort cases.
+ * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+ * 2) S3 suspend abort and TOS already launched.
+ */
+ if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+ !adev->suspend_complete &&
+ sol_reg)
+ return true;
+
+ return false;
+}
+
static int soc15_asic_reset(struct amdgpu_device *adev)
{
/* original raven doesn't have full asic reset */
- if ((adev->apu_flags & AMD_APU_IS_RAVEN) ||
- (adev->apu_flags & AMD_APU_IS_RAVEN2))
+ /* On the latest Raven, the GPU reset can be performed
+ * successfully. So now, temporarily enable it for the
+ * S3 suspend abort case.
+ */
+ if (((adev->apu_flags & AMD_APU_IS_RAVEN) ||
+ (adev->apu_flags & AMD_APU_IS_RAVEN2)) &&
+ !soc15_need_reset_on_resume(adev))
return 0;
switch (soc15_asic_reset_method(adev)) {
@@ -1302,6 +1325,10 @@ static int soc15_common_resume(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ if (soc15_need_reset_on_resume(adev)) {
+ dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
+ soc15_asic_reset(adev);
+ }
return soc15_common_hw_init(adev);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 48c6efcdeac9..4d7188912edf 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
/* SOC21 */
static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
- {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
};
static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
- {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index d722cbd31783..826bc4f6c8a7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -55,8 +55,8 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
m = get_mqd(mqd);
if (has_wa_flag) {
- uint32_t wa_mask = minfo->update_flag == UPDATE_FLAG_DBG_WA_ENABLE ?
- 0xffff : 0xffffffff;
+ uint32_t wa_mask =
+ (minfo->update_flag & UPDATE_FLAG_DBG_WA_ENABLE) ? 0xffff : 0xffffffff;
m->compute_static_thread_mgmt_se0 = wa_mask;
m->compute_static_thread_mgmt_se1 = wa_mask;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 42d881809dc7..697b6d530d12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -303,6 +303,15 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
update_cu_mask(mm, mqd, minfo, 0);
set_priority(m, q);
+ if (minfo && KFD_GC_VERSION(mm->dev) >= IP_VERSION(9, 4, 2)) {
+ if (minfo->update_flag & UPDATE_FLAG_IS_GWS)
+ m->compute_resource_limits |=
+ COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+ else
+ m->compute_resource_limits &=
+ ~COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+ }
+
q->is_active = QUEUE_IS_ACTIVE(*q);
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 677281c0793e..80320b8603fc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -532,6 +532,7 @@ struct queue_properties {
enum mqd_update_flag {
UPDATE_FLAG_DBG_WA_ENABLE = 1,
UPDATE_FLAG_DBG_WA_DISABLE = 2,
+ UPDATE_FLAG_IS_GWS = 4, /* quirk for gfx9 IP */
};
struct mqd_update_info {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 43eff221eae5..4858112f9a53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -95,6 +95,7 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
void *gws)
{
+ struct mqd_update_info minfo = {0};
struct kfd_node *dev = NULL;
struct process_queue_node *pqn;
struct kfd_process_device *pdd;
@@ -146,9 +147,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
}
pdd->qpd.num_gws = gws ? dev->adev->gds.gws_size : 0;
+ minfo.update_flag = gws ? UPDATE_FLAG_IS_GWS : 0;
return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
- pqn->q, NULL);
+ pqn->q, &minfo);
}
void kfd_process_dequeue_from_all_devices(struct kfd_process *p)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e5f7c92eebcb..6ed2ec381aaa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1638,12 +1638,10 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
else
mode = UNKNOWN_MEMORY_PARTITION_MODE;
- if (pcache->cache_level == 2)
- pcache->cache_size = pcache_info[cache_type].cache_size * num_xcc;
- else if (mode)
- pcache->cache_size = pcache_info[cache_type].cache_size / mode;
- else
- pcache->cache_size = pcache_info[cache_type].cache_size;
+ pcache->cache_size = pcache_info[cache_type].cache_size;
+ /* Partition mode only affects L3 cache size */
+ if (mode && pcache->cache_level == 3)
+ pcache->cache_size /= mode;
if (pcache_info[cache_type].flags & CRAT_CACHE_FLAGS_DATA_CACHE)
pcache->cache_type |= HSA_CACHE_TYPE_DATA;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d292f290cd6e..1a9bbb04bd5e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1843,21 +1843,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
DRM_ERROR("amdgpu: fail to register dmub aux callback");
goto error;
}
- if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true)) {
- DRM_ERROR("amdgpu: fail to register dmub hpd callback");
- goto error;
- }
- if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) {
- DRM_ERROR("amdgpu: fail to register dmub hpd callback");
- goto error;
- }
- }
-
- /* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
- * It is expected that DMUB will resend any pending notifications at this point, for
- * example HPD from DPIA.
- */
- if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+ /* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
+ * It is expected that DMUB will resend any pending notifications at this point. Note
+ * that hpd and hpd_irq handler registration are deferred to register_hpd_handlers() to
+ * align legacy interface initialization sequence. Connection status will be proactivly
+ * detected once in the amdgpu_dm_initialize_drm_device.
+ */
dc_enable_dmub_outbox(adev->dm.dc);
/* DPIA trace goes to dmesg logs only if outbox is enabled */
@@ -1956,7 +1947,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
&adev->dm.dmub_bo_gpu_addr,
&adev->dm.dmub_bo_cpu_addr);
- if (adev->dm.hpd_rx_offload_wq) {
+ if (adev->dm.hpd_rx_offload_wq && adev->dm.dc) {
for (i = 0; i < adev->dm.dc->caps.max_links; i++) {
if (adev->dm.hpd_rx_offload_wq[i].wq) {
destroy_workqueue(adev->dm.hpd_rx_offload_wq[i].wq);
@@ -2287,6 +2278,7 @@ static int dm_sw_fini(void *handle)
if (adev->dm.dmub_srv) {
dmub_srv_destroy(adev->dm.dmub_srv);
+ kfree(adev->dm.dmub_srv);
adev->dm.dmub_srv = NULL;
}
@@ -3536,6 +3528,14 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
int_params.requested_polarity = INTERRUPT_POLARITY_DEFAULT;
int_params.current_polarity = INTERRUPT_POLARITY_DEFAULT;
+ if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+ if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true))
+ DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+
+ if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true))
+ DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+ }
+
list_for_each_entry(connector,
&dev->mode_config.connector_list, head) {
@@ -3564,10 +3564,6 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
handle_hpd_rx_irq,
(void *) aconnector);
}
-
- if (adev->dm.hpd_rx_offload_wq)
- adev->dm.hpd_rx_offload_wq[connector->index].aconnector =
- aconnector;
}
}
@@ -4561,6 +4557,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
goto fail;
}
+ if (dm->hpd_rx_offload_wq)
+ dm->hpd_rx_offload_wq[aconnector->base.index].aconnector =
+ aconnector;
+
if (!dc_link_detect_connection_type(link, &new_connection_type))
DRM_ERROR("KMS: Failed to detect connector\n");
@@ -5219,6 +5219,7 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
struct drm_plane_state *new_plane_state,
struct drm_crtc_state *crtc_state,
struct dc_flip_addrs *flip_addrs,
+ bool is_psr_su,
bool *dirty_regions_changed)
{
struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state);
@@ -5243,6 +5244,10 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
num_clips = drm_plane_get_damage_clips_count(new_plane_state);
clips = drm_plane_get_damage_clips(new_plane_state);
+ if (num_clips && (!amdgpu_damage_clips || (amdgpu_damage_clips < 0 &&
+ is_psr_su)))
+ goto ffu;
+
if (!dm_crtc_state->mpo_requested) {
if (!num_clips || num_clips > DC_MAX_DIRTY_RECTS)
goto ffu;
@@ -6194,7 +6199,9 @@ create_stream_for_sink(struct drm_connector *connector,
if (recalculate_timing) {
freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
drm_mode_copy(&saved_mode, &mode);
+ saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio;
drm_mode_copy(&mode, freesync_mode);
+ mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio;
} else {
decide_crtc_timing_for_drm_display_mode(
&mode, preferred_mode, scale);
@@ -6527,10 +6534,15 @@ amdgpu_dm_connector_late_register(struct drm_connector *connector)
static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
{
struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
- struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
struct dc_link *dc_link = aconnector->dc_link;
struct dc_sink *dc_em_sink = aconnector->dc_em_sink;
struct edid *edid;
+ struct i2c_adapter *ddc;
+
+ if (dc_link && dc_link->aux_mode)
+ ddc = &aconnector->dm_dp_aux.aux.ddc;
+ else
+ ddc = &aconnector->i2c->base;
/*
* Note: drm_get_edid gets edid in the following order:
@@ -6538,7 +6550,7 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
* 2) firmware EDID if set via edid_firmware module parameter
* 3) regular DDC read.
*/
- edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+ edid = drm_get_edid(connector, ddc);
if (!edid) {
DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
return;
@@ -6579,12 +6591,18 @@ static int get_modes(struct drm_connector *connector)
static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
{
struct drm_connector *connector = &aconnector->base;
- struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(&aconnector->base);
+ struct dc_link *dc_link = aconnector->dc_link;
struct dc_sink_init_data init_params = {
.link = aconnector->dc_link,
.sink_signal = SIGNAL_TYPE_VIRTUAL
};
struct edid *edid;
+ struct i2c_adapter *ddc;
+
+ if (dc_link->aux_mode)
+ ddc = &aconnector->dm_dp_aux.aux.ddc;
+ else
+ ddc = &aconnector->i2c->base;
/*
* Note: drm_get_edid gets edid in the following order:
@@ -6592,7 +6610,7 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
* 2) firmware EDID if set via edid_firmware module parameter
* 3) regular DDC read.
*/
- edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+ edid = drm_get_edid(connector, ddc);
if (!edid) {
DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
return;
@@ -8298,6 +8316,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
fill_dc_dirty_rects(plane, old_plane_state,
new_plane_state, new_crtc_state,
&bundle->flip_addrs[planes_count],
+ acrtc_state->stream->link->psr_settings.psr_version ==
+ DC_PSR_VERSION_SU_1,
&dirty_rects_changed);
/*
@@ -10731,11 +10751,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
goto fail;
}
- ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
- if (ret) {
- DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
- ret = -EINVAL;
- goto fail;
+ if (dc_resource_is_dsc_encoding_supported(dc)) {
+ ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+ if (ret) {
+ DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+ ret = -EINVAL;
+ goto fail;
+ }
}
ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
@@ -11147,14 +11169,23 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
if (range->flags != 1)
continue;
- amdgpu_dm_connector->min_vfreq = range->min_vfreq;
- amdgpu_dm_connector->max_vfreq = range->max_vfreq;
- amdgpu_dm_connector->pixel_clock_mhz =
- range->pixel_clock_mhz * 10;
-
connector->display_info.monitor_range.min_vfreq = range->min_vfreq;
connector->display_info.monitor_range.max_vfreq = range->max_vfreq;
+ if (edid->revision >= 4) {
+ if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ)
+ connector->display_info.monitor_range.min_vfreq += 255;
+ if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ)
+ connector->display_info.monitor_range.max_vfreq += 255;
+ }
+
+ amdgpu_dm_connector->min_vfreq =
+ connector->display_info.monitor_range.min_vfreq;
+ amdgpu_dm_connector->max_vfreq =
+ connector->display_info.monitor_range.max_vfreq;
+ amdgpu_dm_connector->pixel_clock_mhz =
+ range->pixel_clock_mhz * 10;
+
break;
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 85b7f58a7f35..c27063305a13 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -67,6 +67,8 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps)
/* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */
case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB):
case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B):
+ case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A):
+ case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1):
DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id);
edid_caps->panel_patch.remove_sink_ext_caps = true;
break;
@@ -120,6 +122,8 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
edid_caps->edid_hdmi = connector->display_info.is_hdmi;
+ apply_edid_quirks(edid_buf, edid_caps);
+
sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads);
if (sad_count <= 0)
return result;
@@ -146,8 +150,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
else
edid_caps->speaker_flags = DEFAULT_SPEAKER_LOCATION;
- apply_edid_quirks(edid_buf, edid_caps);
-
kfree(sads);
kfree(sadb);
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
index f2dfa96f9ef5..39530b2ea495 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
@@ -94,7 +94,7 @@ static void calculate_bandwidth(
const uint32_t s_high = 7;
const uint32_t dmif_chunk_buff_margin = 1;
- uint32_t max_chunks_fbc_mode;
+ uint32_t max_chunks_fbc_mode = 0;
int32_t num_cursor_lines;
int32_t i, j, k;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 960c4b4f6ddf..05f392501c0a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1850,19 +1850,21 @@ static enum bp_result get_firmware_info_v3_2(
/* Vega12 */
smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
DATA_TABLES(smu_info));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
if (!smu_info_v3_2)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
+
info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
} else if (revision.minor == 3) {
/* Vega20 */
smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
DATA_TABLES(smu_info));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
if (!smu_info_v3_3)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
+
info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
}
@@ -2422,10 +2424,11 @@ static enum bp_result get_integrated_info_v11(
info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11,
DATA_TABLES(integratedsysteminfo));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
if (info_v11 == NULL)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
+
info->gpu_cap_info =
le32_to_cpu(info_v11->gpucapinfo);
/*
@@ -2637,11 +2640,12 @@ static enum bp_result get_integrated_info_v2_1(
info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1,
DATA_TABLES(integratedsysteminfo));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
if (info_v2_1 == NULL)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
+
info->gpu_cap_info =
le32_to_cpu(info_v2_1->gpucapinfo);
/*
@@ -2799,11 +2803,11 @@ static enum bp_result get_integrated_info_v2_2(
info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2,
DATA_TABLES(integratedsysteminfo));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
-
if (info_v2_2 == NULL)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
+
info->gpu_cap_info =
le32_to_cpu(info_v2_2->gpucapinfo);
/*
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index a5489fe6875f..aa9fd1dc550a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -546,6 +546,8 @@ static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_ta
int i;
for (i = 0; i < VG_NUM_SOC_VOLTAGE_LEVELS; i++) {
+ if (i >= VG_NUM_DCFCLK_DPM_LEVELS)
+ break;
if (clock_table->SocVoltage[i] == voltage)
return clock_table->DcfClocks[i];
}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 14cec1c7b718..e64890259235 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -655,10 +655,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
+ uint32_t num_memps, num_fclk, num_dcfclk;
int i;
/* Determine min/max p-state values. */
- for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+ num_memps = (clock_table->NumMemPstatesEnabled > NUM_MEM_PSTATE_LEVELS) ? NUM_MEM_PSTATE_LEVELS :
+ clock_table->NumMemPstatesEnabled;
+ for (i = 0; i < num_memps; i++) {
uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
@@ -670,7 +673,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
min_dram_speed_mts = max_dram_speed_mts;
min_pstate = max_pstate;
- for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+ for (i = 0; i < num_memps; i++) {
uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
@@ -699,9 +702,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
- max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
+ num_fclk = (clock_table->NumFclkLevelsEnabled > NUM_FCLK_DPM_LEVELS) ? NUM_FCLK_DPM_LEVELS :
+ clock_table->NumFclkLevelsEnabled;
+ max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
- for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+ num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+ clock_table->NumDcfClkLevelsEnabled;
+ for (i = 0; i < num_dcfclk; i++) {
int j;
/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index aa7c02ba948e..2c424e435962 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3817,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc,
* programming has completed (we turn on phantom OTG in order
* to complete the plane disable for phantom pipes).
*/
- dc->hwss.apply_ctx_to_hw(dc, context);
+
+ if (dc->hwss.disable_phantom_streams)
+ dc->hwss.disable_phantom_streams(dc, context);
}
if (update_type != UPDATE_TYPE_FAST)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 88c6436b28b6..180ac47868c2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -291,11 +291,14 @@ void dc_state_destruct(struct dc_state *state)
dc_stream_release(state->phantom_streams[i]);
state->phantom_streams[i] = NULL;
}
+ state->phantom_stream_count = 0;
for (i = 0; i < state->phantom_plane_count; i++) {
dc_plane_state_release(state->phantom_planes[i]);
state->phantom_planes[i] = NULL;
}
+ state->phantom_plane_count = 0;
+
state->stream_mask = 0;
memset(&state->res_ctx, 0, sizeof(state->res_ctx));
memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg));
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 2b79a0e5638e..363d522603a2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -125,7 +125,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
unsigned int count,
union dmub_rb_cmd *cmd_list)
{
- struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+ struct dc_context *dc_ctx;
struct dmub_srv *dmub;
enum dmub_status status;
int i;
@@ -133,6 +133,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
if (!dc_dmub_srv || !dc_dmub_srv->dmub)
return false;
+ dc_ctx = dc_dmub_srv->ctx;
dmub = dc_dmub_srv->dmub;
for (i = 0 ; i < count; i++) {
@@ -1161,7 +1162,7 @@ void dc_dmub_srv_subvp_save_surf_addr(const struct dc_dmub_srv *dc_dmub_srv, con
bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
{
- struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+ struct dc_context *dc_ctx;
enum dmub_status status;
if (!dc_dmub_srv || !dc_dmub_srv->dmub)
@@ -1170,6 +1171,8 @@ bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
if (dc_dmub_srv->ctx->dc->debug.dmcub_emulation)
return true;
+ dc_ctx = dc_dmub_srv->ctx;
+
if (wait) {
if (dc_dmub_srv->ctx->dc->debug.disable_timeout) {
do {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index e8570060d007..5bca67407c5b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -290,4 +290,5 @@ void dce_panel_cntl_construct(
dce_panel_cntl->base.funcs = &dce_link_panel_cntl_funcs;
dce_panel_cntl->base.ctx = init_data->ctx;
dce_panel_cntl->base.inst = init_data->inst;
+ dce_panel_cntl->base.pwrseq_inst = 0;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
index e43f77c11c00..5f97a868ada3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
@@ -56,16 +56,13 @@ static void dpp3_enable_cm_block(
static enum dc_lut_mode dpp30_get_gamcor_current(struct dpp *dpp_base)
{
- enum dc_lut_mode mode;
+ enum dc_lut_mode mode = LUT_BYPASS;
uint32_t state_mode;
uint32_t lut_mode;
struct dcn3_dpp *dpp = TO_DCN30_DPP(dpp_base);
REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_MODE_CURRENT, &state_mode);
- if (state_mode == 0)
- mode = LUT_BYPASS;
-
if (state_mode == 2) {//Programmable RAM LUT
REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_SELECT_CURRENT, &lut_mode);
if (lut_mode == 0)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
index ad0df1a72a90..9e96a3ace207 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
@@ -215,4 +215,5 @@ void dcn301_panel_cntl_construct(
dcn301_panel_cntl->base.funcs = &dcn301_link_panel_cntl_funcs;
dcn301_panel_cntl->base.ctx = init_data->ctx;
dcn301_panel_cntl->base.inst = init_data->inst;
+ dcn301_panel_cntl->base.pwrseq_inst = 0;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
index 03248422d6ff..281be20b1a10 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
@@ -154,8 +154,24 @@ void dcn31_panel_cntl_construct(
struct dcn31_panel_cntl *dcn31_panel_cntl,
const struct panel_cntl_init_data *init_data)
{
+ uint8_t pwrseq_inst = 0xF;
+
dcn31_panel_cntl->base.funcs = &dcn31_link_panel_cntl_funcs;
dcn31_panel_cntl->base.ctx = init_data->ctx;
dcn31_panel_cntl->base.inst = init_data->inst;
- dcn31_panel_cntl->base.pwrseq_inst = init_data->pwrseq_inst;
+
+ switch (init_data->eng_id) {
+ case ENGINE_ID_DIGA:
+ pwrseq_inst = 0;
+ break;
+ case ENGINE_ID_DIGB:
+ pwrseq_inst = 1;
+ break;
+ default:
+ DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", init_data->eng_id);
+ ASSERT(false);
+ break;
+ }
+
+ dcn31_panel_cntl->base.pwrseq_inst = pwrseq_inst;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 6042a5a6a44f..59ade76ffb18 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index dd781a20692e..a0a65e099104 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1288,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex
return updated;
}
-static bool should_allow_odm_power_optimization(struct dc *dc,
+static bool should_apply_odm_power_optimization(struct dc *dc,
struct dc_state *context, struct vba_vars_st *v, int *split,
bool *merge)
{
@@ -1392,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate(
{
int i;
unsigned int new_vlevel;
+ unsigned int cur_policy[MAX_PIPES];
- for (i = 0; i < pipe_cnt; i++)
+ for (i = 0; i < pipe_cnt; i++) {
+ cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy;
pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+ }
new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
@@ -1403,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate(
memset(merge, 0, MAX_PIPES * sizeof(bool));
*vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge);
context->bw_ctx.dml.vba.VoltageLevel = *vlevel;
+ } else {
+ for (i = 0; i < pipe_cnt; i++)
+ pipes[i].pipe.dest.odm_combine_policy = cur_policy[i];
}
}
@@ -1580,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
}
}
- if (should_allow_odm_power_optimization(dc, context, vba, split, merge))
+ if (should_apply_odm_power_optimization(dc, context, vba, split, merge))
try_odm_power_optimization_and_revalidate(
dc, context, pipes, split, merge, vlevel, *pipe_cnt);
@@ -2209,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
int i;
pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
- dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
+ if (!dc->config.enable_windowed_mpo_odm)
+ dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
/* repopulate_pipes = 1 means the pipes were either split or merged. In this case
* we have to re-calculate the DET allocation and run through DML once more to
@@ -2753,7 +2760,7 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
struct _vcs_dpi_voltage_scaling_st entry = {0};
struct clk_limit_table_entry max_clk_data = {0};
- unsigned int min_dcfclk_mhz = 399, min_fclk_mhz = 599;
+ unsigned int min_dcfclk_mhz = 199, min_fclk_mhz = 299;
static const unsigned int num_dcfclk_stas = 5;
unsigned int dcfclk_sta_targets[DC__VOLTAGE_STATES] = {199, 615, 906, 1324, 1564};
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 23a608274096..1ba6933d2b36 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -398,7 +398,6 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
/* Copy clocks tables entries, if available */
if (dml2->config.bbox_overrides.clks_table.num_states) {
p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
-
for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels; i++) {
p->in_states->state_array[i].dcfclk_mhz = dml2->config.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz;
}
@@ -437,6 +436,14 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
}
dml2_policy_build_synthetic_soc_states(s, p);
+ if (dml2->v20.dml_core_ctx.project == dml_project_dcn35 ||
+ dml2->v20.dml_core_ctx.project == dml_project_dcn351) {
+ // Override last out_state with data from last in_state
+ // This will ensure that out_state contains max fclk
+ memcpy(&p->out_states->state_array[p->out_states->num_states - 1],
+ &p->in_states->state_array[p->in_states->num_states - 1],
+ sizeof(struct soc_state_bounding_box_st));
+ }
}
void dml2_translate_ip_params(const struct dc *in, struct ip_params_st *out)
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 26307e599614..2a58a7687bdb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -76,6 +76,11 @@ static void map_hw_resources(struct dml2_context *dml2,
in_out_display_cfg->hw.DLGRefClkFreqMHz = 50;
}
for (j = 0; j < mode_support_info->DPPPerSurface[i]; j++) {
+ if (i >= __DML2_WRAPPER_MAX_STREAMS_PLANES__) {
+ dml_print("DML::%s: Index out of bounds: i=%d, __DML2_WRAPPER_MAX_STREAMS_PLANES__=%d\n",
+ __func__, i, __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+ break;
+ }
dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_stream_id[i];
dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id_valid[num_pipes] = true;
dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[i];
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 2352428bcea3..01493c49bd7a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing(
return DC_OK;
}
-static enum dc_status apply_single_controller_ctx_to_hw(
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
struct pipe_ctx *pipe_ctx,
struct dc_state *context,
struct dc *dc)
@@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw(
if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
continue;
- status = apply_single_controller_ctx_to_hw(
+ status = dce110_apply_single_controller_ctx_to_hw(
pipe_ctx,
context,
dc);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 08028a1779ae..ed3cc3648e8e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw(
struct dc *dc,
struct dc_state *context);
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context,
+ struct dc *dc);
void dce110_enable_stream(struct pipe_ctx *pipe_ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 4853ecac53f9..931ac8ed7069 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -2561,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
tg->funcs->setup_vertical_interrupt2(tg, start_line);
}
-static void dcn20_reset_back_end_for_pipe(
+void dcn20_reset_back_end_for_pipe(
struct dc *dc,
struct pipe_ctx *pipe_ctx,
struct dc_state *context)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
index b94c85340abf..d950b3e54ec2 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
@@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing(
void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_reset_back_end_for_pipe(
+ struct dc *dc,
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context);
void dcn20_init_blank(
struct dc *dc,
struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 8e88dcaf88f5..7252f5f781f0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx)
void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
{
struct abm *abm = pipe_ctx->stream_res.abm;
- uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
+ struct timing_generator *tg = pipe_ctx->stream_res.tg;
struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
+ uint32_t otg_inst;
+
+ if (!abm || !tg || !panel_cntl)
+ return;
+
+ otg_inst = tg->inst;
if (dmcu) {
dce110_set_pipe(pipe_ctx);
return;
}
- if (abm && panel_cntl) {
- if (abm->funcs && abm->funcs->set_pipe_ex) {
- abm->funcs->set_pipe_ex(abm,
+ if (abm->funcs && abm->funcs->set_pipe_ex) {
+ abm->funcs->set_pipe_ex(abm,
otg_inst,
SET_ABM_PIPE_NORMAL,
panel_cntl->inst,
panel_cntl->pwrseq_inst);
- } else {
- dmub_abm_set_pipe(abm, otg_inst,
- SET_ABM_PIPE_NORMAL,
- panel_cntl->inst,
- panel_cntl->pwrseq_inst);
- }
+ } else {
+ dmub_abm_set_pipe(abm, otg_inst,
+ SET_ABM_PIPE_NORMAL,
+ panel_cntl->inst,
+ panel_cntl->pwrseq_inst);
}
}
@@ -237,34 +241,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
{
struct dc_context *dc = pipe_ctx->stream->ctx;
struct abm *abm = pipe_ctx->stream_res.abm;
+ struct timing_generator *tg = pipe_ctx->stream_res.tg;
struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
+ uint32_t otg_inst;
+
+ if (!abm || !tg || !panel_cntl)
+ return false;
+
+ otg_inst = tg->inst;
if (dc->dc->res_pool->dmcu) {
dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp);
return true;
}
- if (abm != NULL) {
- uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
-
- if (abm && panel_cntl) {
- if (abm->funcs && abm->funcs->set_pipe_ex) {
- abm->funcs->set_pipe_ex(abm,
- otg_inst,
- SET_ABM_PIPE_NORMAL,
- panel_cntl->inst,
- panel_cntl->pwrseq_inst);
- } else {
- dmub_abm_set_pipe(abm,
- otg_inst,
- SET_ABM_PIPE_NORMAL,
- panel_cntl->inst,
- panel_cntl->pwrseq_inst);
- }
- }
+ if (abm->funcs && abm->funcs->set_pipe_ex) {
+ abm->funcs->set_pipe_ex(abm,
+ otg_inst,
+ SET_ABM_PIPE_NORMAL,
+ panel_cntl->inst,
+ panel_cntl->pwrseq_inst);
+ } else {
+ dmub_abm_set_pipe(abm,
+ otg_inst,
+ SET_ABM_PIPE_NORMAL,
+ panel_cntl->inst,
+ panel_cntl->pwrseq_inst);
}
- if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm)
+ if (abm->funcs && abm->funcs->set_backlight_level_pwm)
abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16,
frame_ramp, 0, panel_cntl->inst);
else
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6c9299c7683d..aa36d7a56ca8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc,
}
}
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context)
+{
+ struct dce_hwseq *hws = dc->hwseq;
+ int i;
+
+ for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+ struct pipe_ctx *pipe_ctx_old =
+ &dc->current_state->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+ if (!pipe_ctx_old->stream)
+ continue;
+
+ if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM)
+ continue;
+
+ if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+ continue;
+
+ if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) ||
+ (pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) {
+ struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+ if (hws->funcs.reset_back_end_for_pipe)
+ hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+ if (hws->funcs.enable_stream_gating)
+ hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+ if (old_clk)
+ old_clk->funcs->cs_power_down(old_clk);
+ }
+ }
+}
+
void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
{
unsigned int i;
+ enum dc_status status = DC_OK;
+ struct dce_hwseq *hws = dc->hwseq;
for (i = 0; i < dc->res_pool->pipe_count; i++) {
struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
}
}
for (i = 0; i < dc->res_pool->pipe_count; i++) {
- struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-
- if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) {
- // If old context or new context has phantom pipes, apply
- // the phantom timings now. We can't change the phantom
- // pipe configuration safely without driver acquiring
- // the DMCUB lock first.
- dc->hwss.apply_ctx_to_hw(dc, context);
- break;
+ struct pipe_ctx *pipe_ctx_old =
+ &dc->current_state->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+ if (pipe_ctx->stream == NULL)
+ continue;
+
+ if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)
+ continue;
+
+ if (pipe_ctx->stream == pipe_ctx_old->stream &&
+ pipe_ctx->stream->link->link_state_valid) {
+ continue;
}
+
+ if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+ continue;
+
+ if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
+ continue;
+
+ if (hws->funcs.apply_single_controller_ctx_to_hw)
+ status = hws->funcs.apply_single_controller_ctx_to_hw(
+ pipe_ctx,
+ context,
+ dc);
+
+ ASSERT(status == DC_OK);
+
+#ifdef CONFIG_DRM_AMD_DC_FP
+ if (hws->funcs.resync_fifo_dccg_dio)
+ hws->funcs.resync_fifo_dccg_dio(hws, dc, context);
+#endif
}
}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
index cecf7f0f5671..069e20bc87c0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
@@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc,
void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context);
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context);
+
void dcn32_init_blank(
struct dc *dc,
struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index 427cfc8c24a4..e8ac94a005b8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
.get_dcc_en_bits = dcn10_get_dcc_en_bits,
.commit_subvp_config = dcn32_commit_subvp_config,
.enable_phantom_streams = dcn32_enable_phantom_streams,
+ .disable_phantom_streams = dcn32_disable_phantom_streams,
.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
.update_visual_confirm_color = dcn10_update_visual_confirm_color,
.subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast,
@@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = {
.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
.resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio,
.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+ .apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
+ .reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
};
void dcn32_hw_sequencer_init_functions(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index a54399383318..64ca7c66509b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -379,6 +379,7 @@ struct hw_sequencer_funcs {
struct dc_cursor_attributes *cursor_attr);
void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
+ void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context);
void (*subvp_pipe_control_lock)(struct dc *dc,
struct dc_state *context,
bool lock,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 6137cf09aa54..b3c62a82cb1c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -165,8 +165,15 @@ struct hwseq_private_funcs {
void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc,
struct dc_state *context);
+ enum dc_status (*apply_single_controller_ctx_to_hw)(
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context,
+ struct dc *dc);
bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx);
#endif
+ void (*reset_back_end_for_pipe)(struct dc *dc,
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context);
};
struct dce_hwseq {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
index 5dcbaa2db964..e97d964a1791 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
@@ -57,7 +57,7 @@ struct panel_cntl_funcs {
struct panel_cntl_init_data {
struct dc_context *ctx;
uint32_t inst;
- uint32_t pwrseq_inst;
+ uint32_t eng_id;
};
struct panel_cntl {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index c958ef37b78a..77a60aa9f27b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe);
int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe);
/*
- * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice
- * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for a plane with MPCC combine. otherwise
- * the number of MPC "cuts" for the plane.
+ * Get the number of MPC slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an MPC combine
+ * pipe topology.
*/
-int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head);
+int resource_get_mpc_slice_count(const struct pipe_ctx *pipe);
/*
- * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice
- * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for ODM combine. otherwise
- * the number of ODM "cuts" for the timing.
+ * Get the number of ODM slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an ODM combine
+ * pipe topology.
*/
-int resource_get_odm_slice_count(const struct pipe_ctx *otg_master);
+int resource_get_odm_slice_count(const struct pipe_ctx *pipe);
/* Get the ODM slice index counting from 0 from left most slice */
int resource_get_odm_slice_index(const struct pipe_ctx *opp_head);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
index 37d3027c32dc..cf22b8f28ba6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
@@ -370,30 +370,6 @@ static enum transmitter translate_encoder_to_transmitter(
}
}
-static uint8_t translate_dig_inst_to_pwrseq_inst(struct dc_link *link)
-{
- uint8_t pwrseq_inst = 0xF;
- struct dc_context *dc_ctx = link->dc->ctx;
-
- DC_LOGGER_INIT(dc_ctx->logger);
-
- switch (link->eng_id) {
- case ENGINE_ID_DIGA:
- pwrseq_inst = 0;
- break;
- case ENGINE_ID_DIGB:
- pwrseq_inst = 1;
- break;
- default:
- DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", link->eng_id);
- ASSERT(false);
- break;
- }
-
- return pwrseq_inst;
-}
-
-
static void link_destruct(struct dc_link *link)
{
int i;
@@ -657,7 +633,7 @@ static bool construct_phy(struct dc_link *link,
link->link_id.id == CONNECTOR_ID_LVDS)) {
panel_cntl_init_data.ctx = dc_ctx;
panel_cntl_init_data.inst = panel_cntl_init_data.ctx->dc_edp_id_count;
- panel_cntl_init_data.pwrseq_inst = translate_dig_inst_to_pwrseq_inst(link);
+ panel_cntl_init_data.eng_id = link->eng_id;
link->panel_cntl =
link->dc->res_pool->funcs->panel_cntl_create(
&panel_cntl_init_data);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index 8fe66c367850..5b0bc7f6a188 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -361,7 +361,7 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un
struct dc_link *dpia_link[MAX_DPIA_NUM] = {0};
int num_dpias = 0;
- for (uint8_t i = 0; i < num_streams; ++i) {
+ for (unsigned int i = 0; i < num_streams; ++i) {
if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) {
/* new dpia sst stream, check whether it exceeds max dpia */
if (num_dpias >= MAX_DPIA_NUM)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 5a0b04518956..16a62e018712 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -517,6 +517,7 @@ enum link_training_result dp_check_link_loss_status(
{
enum link_training_result status = LINK_TRAINING_SUCCESS;
union lane_status lane_status;
+ union lane_align_status_updated dpcd_lane_status_updated;
uint8_t dpcd_buf[6] = {0};
uint32_t lane;
@@ -532,10 +533,12 @@ enum link_training_result dp_check_link_loss_status(
* check lanes status
*/
lane_status.raw = dp_get_nibble_at_index(&dpcd_buf[2], lane);
+ dpcd_lane_status_updated.raw = dpcd_buf[4];
if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
!lane_status.bits.CR_DONE_0 ||
- !lane_status.bits.SYMBOL_LOCKED_0) {
+ !lane_status.bits.SYMBOL_LOCKED_0 ||
+ !dp_is_interlane_aligned(dpcd_lane_status_updated)) {
/* if one of the channel equalization, clock
* recovery or symbol lock is dropped
* consider it as (link has been
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
index e8dda44b23cb..5d36bab0029c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
@@ -619,7 +619,7 @@ static enum link_training_result dpia_training_eq_non_transparent(
uint32_t retries_eq = 0;
enum dc_status status;
enum dc_dp_training_pattern tr_pattern;
- uint32_t wait_time_microsec;
+ uint32_t wait_time_microsec = 0;
enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
union lane_align_status_updated dpcd_lane_status_updated = {0};
union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0};
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 511ff6b5b985..7538b548c572 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id
vpg = dcn301_vpg_create(ctx, vpg_inst);
afmt = dcn301_afmt_create(ctx, afmt_inst);
- if (!enc1 || !vpg || !afmt) {
+ if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) {
kfree(enc1);
kfree(vpg);
kfree(afmt);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index c4d71e7f18af..6f10052caeef 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context(
dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
DC_FP_END();
pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
- pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+ if (dc->config.enable_windowed_mpo_odm &&
+ dc->debug.enable_single_display_2to1_odm_policy) {
+ switch (resource_get_odm_slice_count(pipe)) {
+ case 2:
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+ break;
+ case 4:
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1;
+ break;
+ default:
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+ }
+ } else {
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+ }
pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet
pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 761ec9891875..5fdcda8f8602 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = {
.disable_z10 = false,
.ignore_pg = true,
.psp_disabled_wa = true,
- .ips2_eval_delay_us = 200,
- .ips2_entry_delay_us = 400,
+ .ips2_eval_delay_us = 2000,
+ .ips2_entry_delay_us = 800,
.static_screen_wait_frames = 2,
};
@@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct(
dc->dml2_options.dcn_pipe_count = pool->base.pipe_count;
dc->dml2_options.use_native_pstate_optimization = true;
dc->dml2_options.use_native_soc_bb_construction = true;
+ dc->dml2_options.minimize_dispclk_using_odm = false;
if (dc->config.EnableMinDispClkODM)
dc->dml2_options.minimize_dispclk_using_odm = true;
dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 087d57850304..39c5e1dfa275 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2558,6 +2558,7 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
{
struct amdgpu_device *adev = dev_get_drvdata(dev);
int err, ret;
+ u32 pwm_mode;
int value;
if (amdgpu_in_reset(adev))
@@ -2569,13 +2570,22 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
if (err)
return err;
+ if (value == 0)
+ pwm_mode = AMD_FAN_CTRL_NONE;
+ else if (value == 1)
+ pwm_mode = AMD_FAN_CTRL_MANUAL;
+ else if (value == 2)
+ pwm_mode = AMD_FAN_CTRL_AUTO;
+ else
+ return -EINVAL;
+
ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
if (ret < 0) {
pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
return ret;
}
- ret = amdgpu_dpm_set_fan_control_mode(adev, value);
+ ret = amdgpu_dpm_set_fan_control_mode(adev, pwm_mode);
pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index df4f20293c16..eb4da3666e05 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev)
return 0;
}
+static int si_set_temperature_range(struct amdgpu_device *adev)
+{
+ int ret;
+
+ ret = si_thermal_enable_alert(adev, false);
+ if (ret)
+ return ret;
+ ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX);
+ if (ret)
+ return ret;
+ ret = si_thermal_enable_alert(adev, true);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
static void si_dpm_disable(struct amdgpu_device *adev)
{
struct rv7xx_power_info *pi = rv770_get_pi(adev);
@@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev,
static int si_dpm_late_init(void *handle)
{
+ int ret;
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+ if (!adev->pm.dpm_enabled)
+ return 0;
+
+ ret = si_set_temperature_range(adev);
+ if (ret)
+ return ret;
+#if 0 //TODO ?
+ si_dpm_powergate_uvd(adev, true);
+#endif
return 0;
}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 4cd43bbec910..bcad42534da4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1303,13 +1303,12 @@ static int arcturus_get_power_limit(struct smu_context *smu,
if (default_power_limit)
*default_power_limit = power_limit;
- if (smu->od_enabled) {
+ if (smu->od_enabled)
od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
- od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
- } else {
+ else
od_percent_upper = 0;
- od_percent_lower = 100;
- }
+
+ od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 8d1d29ffb0f1..ed189a3878eb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2357,13 +2357,12 @@ static int navi10_get_power_limit(struct smu_context *smu,
*default_power_limit = power_limit;
if (smu->od_enabled &&
- navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) {
+ navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT))
od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
- od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
- } else {
+ else
od_percent_upper = 0;
- od_percent_lower = 100;
- }
+
+ od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 21fc033528fa..e2ad2b972ab0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -640,13 +640,12 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu,
if (default_power_limit)
*default_power_limit = power_limit;
- if (smu->od_enabled) {
+ if (smu->od_enabled)
od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
- od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
- } else {
+ else
od_percent_upper = 0;
- od_percent_lower = 100;
- }
+
+ od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index a9954ffc02c5..9b80f18ea6c3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2369,13 +2369,12 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
if (default_power_limit)
*default_power_limit = power_limit;
- if (smu->od_enabled) {
+ if (smu->od_enabled)
od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
- od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
- } else {
+ else
od_percent_upper = 0;
- od_percent_lower = 100;
- }
+
+ od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 0ffdb58af74e..3dc7b60cb075 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2333,13 +2333,12 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
if (default_power_limit)
*default_power_limit = power_limit;
- if (smu->od_enabled) {
+ if (smu->od_enabled)
od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
- od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
- } else {
+ else
od_percent_upper = 0;
- od_percent_lower = 100;
- }
+
+ od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 4894f7ee737b..6dae5ad74ff0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -229,8 +229,6 @@ int smu_v14_0_check_fw_version(struct smu_context *smu)
smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_2;
break;
case IP_VERSION(14, 0, 0):
- if ((smu->smc_fw_version < 0x5d3a00))
- dev_warn(smu->adev->dev, "The PMFW version(%x) is behind in this BIOS!\n", smu->smc_fw_version);
smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
break;
default:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 47fdbae4adfc..9310c4758e38 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -261,7 +261,10 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu,
*value = metrics->MpipuclkFrequency;
break;
case METRICS_AVERAGE_GFXACTIVITY:
- *value = metrics->GfxActivity / 100;
+ if ((smu->smc_fw_version > 0x5d4600))
+ *value = metrics->GfxActivity;
+ else
+ *value = metrics->GfxActivity / 100;
break;
case METRICS_AVERAGE_VCNACTIVITY:
*value = metrics->VcnActivity / 100;
diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
index bb55f697a181..6886db2d9e00 100644
--- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
@@ -25,20 +25,18 @@ static void drm_aux_hpd_bridge_release(struct device *dev)
ida_free(&drm_aux_hpd_bridge_ida, adev->id);
of_node_put(adev->dev.platform_data);
+ of_node_put(adev->dev.of_node);
kfree(adev);
}
-static void drm_aux_hpd_bridge_unregister_adev(void *_adev)
+static void drm_aux_hpd_bridge_free_adev(void *_adev)
{
- struct auxiliary_device *adev = _adev;
-
- auxiliary_device_delete(adev);
- auxiliary_device_uninit(adev);
+ auxiliary_device_uninit(_adev);
}
/**
- * drm_dp_hpd_bridge_register - Create a simple HPD DisplayPort bridge
+ * devm_drm_dp_hpd_bridge_alloc - allocate a HPD DisplayPort bridge
* @parent: device instance providing this bridge
* @np: device node pointer corresponding to this bridge instance
*
@@ -46,11 +44,9 @@ static void drm_aux_hpd_bridge_unregister_adev(void *_adev)
* DRM_MODE_CONNECTOR_DisplayPort, which terminates the bridge chain and is
* able to send the HPD events.
*
- * Return: device instance that will handle created bridge or an error code
- * encoded into the pointer.
+ * Return: bridge auxiliary device pointer or an error pointer
*/
-struct device *drm_dp_hpd_bridge_register(struct device *parent,
- struct device_node *np)
+struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np)
{
struct auxiliary_device *adev;
int ret;
@@ -74,18 +70,62 @@ struct device *drm_dp_hpd_bridge_register(struct device *parent,
ret = auxiliary_device_init(adev);
if (ret) {
+ of_node_put(adev->dev.platform_data);
+ of_node_put(adev->dev.of_node);
ida_free(&drm_aux_hpd_bridge_ida, adev->id);
kfree(adev);
return ERR_PTR(ret);
}
- ret = auxiliary_device_add(adev);
- if (ret) {
- auxiliary_device_uninit(adev);
+ ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_free_adev, adev);
+ if (ret)
return ERR_PTR(ret);
- }
- ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_unregister_adev, adev);
+ return adev;
+}
+EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_alloc);
+
+static void drm_aux_hpd_bridge_del_adev(void *_adev)
+{
+ auxiliary_device_delete(_adev);
+}
+
+/**
+ * devm_drm_dp_hpd_bridge_add - register a HDP DisplayPort bridge
+ * @dev: struct device to tie registration lifetime to
+ * @adev: bridge auxiliary device to be registered
+ *
+ * Returns: zero on success or a negative errno
+ */
+int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev)
+{
+ int ret;
+
+ ret = auxiliary_device_add(adev);
+ if (ret)
+ return ret;
+
+ return devm_add_action_or_reset(dev, drm_aux_hpd_bridge_del_adev, adev);
+}
+EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_add);
+
+/**
+ * drm_dp_hpd_bridge_register - allocate and register a HDP DisplayPort bridge
+ * @parent: device instance providing this bridge
+ * @np: device node pointer corresponding to this bridge instance
+ *
+ * Return: device instance that will handle created bridge or an error pointer
+ */
+struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np)
+{
+ struct auxiliary_device *adev;
+ int ret;
+
+ adev = devm_drm_dp_hpd_bridge_alloc(parent, np);
+ if (IS_ERR(adev))
+ return ERR_CAST(adev);
+
+ ret = devm_drm_dp_hpd_bridge_add(parent, adev);
if (ret)
return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index f57e6d74fb0e..5ebdd6f8f36e 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm,
u64 start, u64 end,
unsigned int order)
{
+ u64 req_size = mm->chunk_size << order;
struct drm_buddy_block *block;
struct drm_buddy_block *buddy;
LIST_HEAD(dfs);
@@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm,
if (drm_buddy_block_is_allocated(block))
continue;
+ if (block_start < start || block_end > end) {
+ u64 adjusted_start = max(block_start, start);
+ u64 adjusted_end = min(block_end, end);
+
+ if (round_down(adjusted_end + 1, req_size) <=
+ round_up(adjusted_start, req_size))
+ continue;
+ }
+
if (contains(start, end, block_start, block_end) &&
order == drm_buddy_block_order(block)) {
/*
@@ -538,7 +548,13 @@ static int __alloc_range(struct drm_buddy *mm,
list_add(&block->left->tmp_link, dfs);
} while (1);
+ if (total_allocated < size) {
+ err = -ENOSPC;
+ goto err_free;
+ }
+
list_splice_tail(&allocated, blocks);
+
return 0;
err_undo:
@@ -755,8 +771,12 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
return -EINVAL;
/* Actual range allocation */
- if (start + size == end)
+ if (start + size == end) {
+ if (!IS_ALIGNED(start | end, min_block_size))
+ return -EINVAL;
+
return __drm_buddy_alloc_range(mm, start, size, NULL, blocks);
+ }
original_size = size;
original_min_size = min_block_size;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index cb90e70d85e8..65f9f66933bb 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -904,6 +904,7 @@ out:
connector_set = NULL;
fb = NULL;
mode = NULL;
+ num_connectors = 0;
DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 834a5e28abbe..7352bde299d5 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -820,7 +820,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
if (max_segment == 0)
max_segment = UINT_MAX;
err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0,
- nr_pages << PAGE_SHIFT,
+ (unsigned long)nr_pages << PAGE_SHIFT,
max_segment, GFP_KERNEL);
if (err) {
kfree(sg);
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 3f479483d7d8..23b4e9a3361d 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -760,9 +760,11 @@ static void output_poll_execute(struct work_struct *work)
changed = dev->mode_config.delayed_event;
dev->mode_config.delayed_event = false;
- if (!drm_kms_helper_poll && dev->mode_config.poll_running) {
- drm_kms_helper_disable_hpd(dev);
- dev->mode_config.poll_running = false;
+ if (!drm_kms_helper_poll) {
+ if (dev->mode_config.poll_running) {
+ drm_kms_helper_disable_hpd(dev);
+ dev->mode_config.poll_running = false;
+ }
goto out;
}
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 84101baeecc6..a6c19de46292 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1040,7 +1040,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
uint64_t *points;
uint32_t signaled_count, i;
- if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT)
+ if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+ DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE))
lockdep_assert_none_held_once();
points = kmalloc_array(count, sizeof(*points), GFP_KERNEL);
@@ -1109,7 +1110,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
* fallthough and try a 0 timeout wait!
*/
- if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
+ if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+ DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) {
for (i = 0; i < count; ++i)
drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]);
}
@@ -1416,10 +1418,21 @@ syncobj_eventfd_entry_func(struct drm_syncobj *syncobj,
/* This happens inside the syncobj lock */
fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1));
+ if (!fence)
+ return;
+
ret = dma_fence_chain_find_seqno(&fence, entry->point);
- if (ret != 0 || !fence) {
+ if (ret != 0) {
+ /* The given seqno has not been submitted yet. */
dma_fence_put(fence);
return;
+ } else if (!fence) {
+ /* If dma_fence_chain_find_seqno returns 0 but sets the fence
+ * to NULL, it implies that the given seqno is signaled and a
+ * later seqno has already been submitted. Assign a stub fence
+ * so that the eventfd still gets signaled below.
+ */
+ fence = dma_fence_get_stub();
}
list_del_init(&entry->node);
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b5d6e3352071..3089029abba4 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT
Note that this driver only supports newer device from Broadwell on.
For further information and setup guide, you can visit:
- http://01.org/igvt-g.
+ https://github.com/intel/gvt-linux/wiki.
If in doubt, say "N".
diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index 47cd6bb04366..06900ff307b2 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -246,7 +246,14 @@ static enum phy icl_aux_pw_to_phy(struct drm_i915_private *i915,
enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well);
struct intel_digital_port *dig_port = aux_ch_to_digital_port(i915, aux_ch);
- return intel_port_to_phy(i915, dig_port->base.port);
+ /*
+ * FIXME should we care about the (VBT defined) dig_port->aux_ch
+ * relationship or should this be purely defined by the hardware layout?
+ * Currently if the port doesn't appear in the VBT, or if it's declared
+ * as HDMI-only and routed to a combo PHY, the encoder either won't be
+ * present at all or it will not have an aux_ch assigned.
+ */
+ return dig_port ? intel_port_to_phy(i915, dig_port->base.port) : PHY_NONE;
}
static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv,
@@ -414,7 +421,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
intel_de_rmw(dev_priv, regs->driver, 0, HSW_PWR_WELL_CTL_REQ(pw_idx));
- if (DISPLAY_VER(dev_priv) < 12)
+ /* FIXME this is a mess */
+ if (phy != PHY_NONE)
intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy),
0, ICL_LANE_ENABLE_AUX);
@@ -437,7 +445,10 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv));
- intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), ICL_LANE_ENABLE_AUX, 0);
+ /* FIXME this is a mess */
+ if (phy != PHY_NONE)
+ intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy),
+ ICL_LANE_ENABLE_AUX, 0);
intel_de_rmw(dev_priv, regs->driver, HSW_PWR_WELL_CTL_REQ(pw_idx), 0);
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 3fdd8a517983..ac7fe6281afe 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -609,6 +609,13 @@ struct intel_connector {
* and active (i.e. dpms ON state). */
bool (*get_hw_state)(struct intel_connector *);
+ /*
+ * Optional hook called during init/resume to sync any state
+ * stored in the connector (eg. DSC state) wrt. the HW state.
+ */
+ void (*sync_state)(struct intel_connector *connector,
+ const struct intel_crtc_state *crtc_state);
+
/* Panel info for eDP and LVDS */
struct intel_panel panel;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f5ef95da5534..94d2a15d8444 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2355,6 +2355,9 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
limits->min_rate = intel_dp_common_rate(intel_dp, 0);
limits->max_rate = intel_dp_max_link_rate(intel_dp);
+ /* FIXME 128b/132b SST support missing */
+ limits->max_rate = min(limits->max_rate, 810000);
+
limits->min_lane_count = 1;
limits->max_lane_count = intel_dp_max_lane_count(intel_dp);
@@ -5696,6 +5699,9 @@ intel_dp_detect(struct drm_connector *connector,
goto out;
}
+ if (!intel_dp_is_edp(intel_dp))
+ intel_psr_init_dpcd(intel_dp);
+
intel_dp_detect_dsc_caps(intel_dp, intel_connector);
intel_dp_configure_mst(intel_dp);
@@ -5856,6 +5862,19 @@ intel_dp_connector_unregister(struct drm_connector *connector)
intel_connector_unregister(connector);
}
+void intel_dp_connector_sync_state(struct intel_connector *connector,
+ const struct intel_crtc_state *crtc_state)
+{
+ struct drm_i915_private *i915 = to_i915(connector->base.dev);
+
+ if (crtc_state && crtc_state->dsc.compression_enable) {
+ drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux);
+ connector->dp.dsc_decompression_enabled = true;
+ } else {
+ connector->dp.dsc_decompression_enabled = false;
+ }
+}
+
void intel_dp_encoder_flush_work(struct drm_encoder *encoder)
{
struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder));
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 05db46b111f2..375d0677cd8c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -45,6 +45,8 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
int intel_dp_min_bpp(enum intel_output_format output_format);
bool intel_dp_init_connector(struct intel_digital_port *dig_port,
struct intel_connector *intel_connector);
+void intel_dp_connector_sync_state(struct intel_connector *connector,
+ const struct intel_crtc_state *crtc_state);
void intel_dp_set_link_params(struct intel_dp *intel_dp,
int link_rate, int lane_count);
int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
index 3a595cd433d4..8538d1ce2fcb 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@@ -330,23 +330,13 @@ static const struct hdcp2_dp_msg_data hdcp2_dp_msg_data[] = {
0, 0 },
};
-static struct drm_dp_aux *
-intel_dp_hdcp_get_aux(struct intel_connector *connector)
-{
- struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
-
- if (intel_encoder_is_mst(connector->encoder))
- return &connector->port->aux;
- else
- return &dig_port->dp.aux;
-}
-
static int
intel_dp_hdcp2_read_rx_status(struct intel_connector *connector,
u8 *rx_status)
{
struct drm_i915_private *i915 = to_i915(connector->base.dev);
- struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector);
+ struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+ struct drm_dp_aux *aux = &dig_port->dp.aux;
ssize_t ret;
ret = drm_dp_dpcd_read(aux,
@@ -399,7 +389,9 @@ intel_dp_hdcp2_wait_for_msg(struct intel_connector *connector,
const struct hdcp2_dp_msg_data *hdcp2_msg_data)
{
struct drm_i915_private *i915 = to_i915(connector->base.dev);
- struct intel_hdcp *hdcp = &connector->hdcp;
+ struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+ struct intel_dp *dp = &dig_port->dp;
+ struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
u8 msg_id = hdcp2_msg_data->msg_id;
int ret, timeout;
bool msg_ready = false;
@@ -454,8 +446,9 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector,
unsigned int offset;
u8 *byte = buf;
ssize_t ret, bytes_to_write, len;
+ struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+ struct drm_dp_aux *aux = &dig_port->dp.aux;
const struct hdcp2_dp_msg_data *hdcp2_msg_data;
- struct drm_dp_aux *aux;
hdcp2_msg_data = get_hdcp2_dp_msg_data(*byte);
if (!hdcp2_msg_data)
@@ -463,8 +456,6 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector,
offset = hdcp2_msg_data->offset;
- aux = intel_dp_hdcp_get_aux(connector);
-
/* No msg_id in DP HDCP2.2 msgs */
bytes_to_write = size - 1;
byte++;
@@ -490,7 +481,8 @@ static
ssize_t get_receiver_id_list_rx_info(struct intel_connector *connector,
u32 *dev_cnt, u8 *byte)
{
- struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector);
+ struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+ struct drm_dp_aux *aux = &dig_port->dp.aux;
ssize_t ret;
u8 *rx_info = byte;
@@ -515,8 +507,9 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
{
struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
- struct intel_hdcp *hdcp = &connector->hdcp;
- struct drm_dp_aux *aux;
+ struct drm_dp_aux *aux = &dig_port->dp.aux;
+ struct intel_dp *dp = &dig_port->dp;
+ struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
unsigned int offset;
u8 *byte = buf;
ssize_t ret, bytes_to_recv, len;
@@ -530,8 +523,6 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
return -EINVAL;
offset = hdcp2_msg_data->offset;
- aux = intel_dp_hdcp_get_aux(connector);
-
ret = intel_dp_hdcp2_wait_for_msg(connector, hdcp2_msg_data);
if (ret < 0)
return ret;
@@ -561,13 +552,8 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
/* Entire msg read timeout since initiate of msg read */
if (bytes_to_recv == size - 1 && hdcp2_msg_data->msg_read_timeout > 0) {
- if (intel_encoder_is_mst(connector->encoder))
- msg_end = ktime_add_ms(ktime_get_raw(),
- hdcp2_msg_data->msg_read_timeout *
- connector->port->parent->num_ports);
- else
- msg_end = ktime_add_ms(ktime_get_raw(),
- hdcp2_msg_data->msg_read_timeout);
+ msg_end = ktime_add_ms(ktime_get_raw(),
+ hdcp2_msg_data->msg_read_timeout);
}
ret = drm_dp_dpcd_read(aux, offset,
@@ -651,12 +637,11 @@ static
int intel_dp_hdcp2_capable(struct intel_connector *connector,
bool *capable)
{
- struct drm_dp_aux *aux;
+ struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+ struct drm_dp_aux *aux = &dig_port->dp.aux;
u8 rx_caps[3];
int ret;
- aux = intel_dp_hdcp_get_aux(connector);
-
*capable = false;
ret = drm_dp_dpcd_read(aux,
DP_HDCP_2_2_REG_RX_CAPS_OFFSET,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 8a9432335030..a01a59f57ae5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1534,6 +1534,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
return NULL;
intel_connector->get_hw_state = intel_dp_mst_get_hw_state;
+ intel_connector->sync_state = intel_dp_connector_sync_state;
intel_connector->mst_port = intel_dp;
intel_connector->port = port;
drm_dp_mst_get_port_malloc(port);
diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
index 94eece7f63be..caeca3a8442c 100644
--- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c
+++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
@@ -318,12 +318,6 @@ static void intel_modeset_update_connector_atomic_state(struct drm_i915_private
const struct intel_crtc_state *crtc_state =
to_intel_crtc_state(crtc->base.state);
- if (crtc_state->dsc.compression_enable) {
- drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux);
- connector->dp.dsc_decompression_enabled = true;
- } else {
- connector->dp.dsc_decompression_enabled = false;
- }
conn_state->max_bpc = (crtc_state->pipe_bpp ?: 24) / 3;
}
}
@@ -775,8 +769,9 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915)
drm_connector_list_iter_begin(&i915->drm, &conn_iter);
for_each_intel_connector_iter(connector, &conn_iter) {
+ struct intel_crtc_state *crtc_state = NULL;
+
if (connector->get_hw_state(connector)) {
- struct intel_crtc_state *crtc_state;
struct intel_crtc *crtc;
connector->base.dpms = DRM_MODE_DPMS_ON;
@@ -802,6 +797,10 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915)
connector->base.dpms = DRM_MODE_DPMS_OFF;
connector->base.encoder = NULL;
}
+
+ if (connector->sync_state)
+ connector->sync_state(connector, crtc_state);
+
drm_dbg_kms(&i915->drm,
"[CONNECTOR:%d:%s] hw state readout: %s\n",
connector->base.base.id, connector->base.name,
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 57bbf3e3af92..4faaf4b3fc53 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2776,9 +2776,6 @@ void intel_psr_init(struct intel_dp *intel_dp)
if (!(HAS_PSR(dev_priv) || HAS_DP20(dev_priv)))
return;
- if (!intel_dp_is_edp(intel_dp))
- intel_psr_init_dpcd(intel_dp);
-
/*
* HSW spec explicitly says PSR is tied to port A.
* BDW+ platforms have a instance of PSR registers per transcoder but
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index acc6b6804105..2915d7afe5cc 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1209,7 +1209,7 @@ static bool intel_sdvo_set_tv_format(struct intel_sdvo *intel_sdvo,
struct intel_sdvo_tv_format format;
u32 format_map;
- format_map = 1 << conn_state->tv.mode;
+ format_map = 1 << conn_state->tv.legacy_mode;
memset(&format, 0, sizeof(format));
memcpy(&format, &format_map, min(sizeof(format), sizeof(format_map)));
@@ -2298,7 +2298,7 @@ static int intel_sdvo_get_tv_modes(struct drm_connector *connector)
* Read the list of supported input resolutions for the selected TV
* format.
*/
- format_map = 1 << conn_state->tv.mode;
+ format_map = 1 << conn_state->tv.legacy_mode;
memcpy(&tv_res, &format_map,
min(sizeof(format_map), sizeof(struct intel_sdvo_sdtv_resolution_request)));
@@ -2363,7 +2363,7 @@ intel_sdvo_connector_atomic_get_property(struct drm_connector *connector,
int i;
for (i = 0; i < intel_sdvo_connector->format_supported_num; i++)
- if (state->tv.mode == intel_sdvo_connector->tv_format_supported[i]) {
+ if (state->tv.legacy_mode == intel_sdvo_connector->tv_format_supported[i]) {
*val = i;
return 0;
@@ -2419,7 +2419,7 @@ intel_sdvo_connector_atomic_set_property(struct drm_connector *connector,
struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state(state);
if (property == intel_sdvo_connector->tv_format) {
- state->tv.mode = intel_sdvo_connector->tv_format_supported[val];
+ state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[val];
if (state->crtc) {
struct drm_crtc_state *crtc_state =
@@ -3076,7 +3076,7 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo,
drm_property_add_enum(intel_sdvo_connector->tv_format, i,
tv_format_names[intel_sdvo_connector->tv_format_supported[i]]);
- intel_sdvo_connector->base.base.state->tv.mode = intel_sdvo_connector->tv_format_supported[0];
+ intel_sdvo_connector->base.base.state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[0];
drm_object_attach_property(&intel_sdvo_connector->base.base.base,
intel_sdvo_connector->tv_format, 0);
return true;
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index d4386cb3569e..992a725de751 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -949,7 +949,7 @@ intel_disable_tv(struct intel_atomic_state *state,
static const struct tv_mode *intel_tv_mode_find(const struct drm_connector_state *conn_state)
{
- int format = conn_state->tv.mode;
+ int format = conn_state->tv.legacy_mode;
return &tv_modes[format];
}
@@ -1704,7 +1704,7 @@ static void intel_tv_find_better_format(struct drm_connector *connector)
break;
}
- connector->state->tv.mode = i;
+ connector->state->tv.legacy_mode = i;
}
static int
@@ -1859,7 +1859,7 @@ static int intel_tv_atomic_check(struct drm_connector *connector,
old_state = drm_atomic_get_old_connector_state(state, connector);
new_crtc_state = drm_atomic_get_new_crtc_state(state, new_state->crtc);
- if (old_state->tv.mode != new_state->tv.mode ||
+ if (old_state->tv.legacy_mode != new_state->tv.legacy_mode ||
old_state->tv.margins.left != new_state->tv.margins.left ||
old_state->tv.margins.right != new_state->tv.margins.right ||
old_state->tv.margins.top != new_state->tv.margins.top ||
@@ -1896,7 +1896,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
conn_state->tv.margins.right = 46;
conn_state->tv.margins.bottom = 37;
- conn_state->tv.mode = 0;
+ conn_state->tv.legacy_mode = 0;
/* Create TV properties then attach current values */
for (i = 0; i < ARRAY_SIZE(tv_modes); i++) {
@@ -1910,7 +1910,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
drm_object_attach_property(&connector->base,
i915->drm.mode_config.legacy_tv_mode_property,
- conn_state->tv.mode);
+ conn_state->tv.legacy_mode);
drm_object_attach_property(&connector->base,
i915->drm.mode_config.tv_left_margin_property,
conn_state->tv.margins.left);
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 64f440fdc22b..8b21dc8e26d5 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
@@ -51,8 +51,8 @@
#define DSCC_PICTURE_PARAMETER_SET_0 _MMIO(0x6BA00)
#define _DSCA_PPS_0 0x6B200
#define _DSCC_PPS_0 0x6BA00
-#define DSCA_PPS(pps) _MMIO(_DSCA_PPS_0 + (pps) * 4)
-#define DSCC_PPS(pps) _MMIO(_DSCC_PPS_0 + (pps) * 4)
+#define DSCA_PPS(pps) _MMIO(_DSCA_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
+#define DSCC_PPS(pps) _MMIO(_DSCC_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB 0x78270
#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB 0x78370
#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC 0x78470
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 1d3ebdf4069b..c08b67593565 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -379,6 +379,9 @@ i915_gem_userptr_release(struct drm_i915_gem_object *obj)
{
GEM_WARN_ON(obj->userptr.page_ref);
+ if (!obj->userptr.notifier.mm)
+ return;
+
mmu_interval_notifier_remove(&obj->userptr.notifier);
obj->userptr.notifier.mm = NULL;
}
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f6c1ece57d..efcb00472be2 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
for (i = start; i < end; i += 4) {
p = intel_gvt_find_mmio_info(gvt, i);
if (p) {
- WARN(1, "dup mmio definition offset %x\n",
- info->offset);
+ WARN(1, "dup mmio definition offset %x\n", i);
/* We return -EEXIST here to make GVT-g load fail.
* So duplicated MMIO can be found as soon as
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index e98b6d69a91a..9b6d87c8b583 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -41,7 +41,7 @@
* To virtualize GPU resources GVT-g driver depends on hypervisor technology
* e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
* and be virtualized within GVT-g device module. More architectural design
- * doc is available on https://01.org/group/2230/documentation-list.
+ * doc is available on https://github.com/intel/gvt-linux/wiki.
*/
static LIST_HEAD(intel_gvt_devices);
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
index 2990dd4d4a0d..e14ac0ab1314 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
@@ -3,6 +3,8 @@
* Copyright © 2021 Intel Corporation
*/
+#include <linux/jiffies.h>
+
//#include "gt/intel_engine_user.h"
#include "gt/intel_gt.h"
#include "i915_drv.h"
@@ -12,7 +14,7 @@
#define REDUCED_TIMESLICE 5
#define REDUCED_PREEMPT 10
-#define WAIT_FOR_RESET_TIME 10000
+#define WAIT_FOR_RESET_TIME_MS 10000
struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt)
{
@@ -91,7 +93,7 @@ int intel_selftest_wait_for_rq(struct i915_request *rq)
{
long ret;
- ret = i915_request_wait(rq, 0, WAIT_FOR_RESET_TIME);
+ ret = i915_request_wait(rq, 0, msecs_to_jiffies(WAIT_FOR_RESET_TIME_MS));
if (ret < 0)
return ret;
diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c
index 3f73b211fa8e..3407450435e2 100644
--- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c
@@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv)
if (priv->encoders[MESON_ENC_CVBS]) {
meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS];
drm_bridge_remove(&meson_encoder_cvbs->bridge);
- drm_bridge_remove(meson_encoder_cvbs->next_bridge);
}
}
diff --git a/drivers/gpu/drm/meson/meson_encoder_dsi.c b/drivers/gpu/drm/meson/meson_encoder_dsi.c
index 3f93c70488ca..311b91630fbe 100644
--- a/drivers/gpu/drm/meson/meson_encoder_dsi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_dsi.c
@@ -168,6 +168,5 @@ void meson_encoder_dsi_remove(struct meson_drm *priv)
if (priv->encoders[MESON_ENC_DSI]) {
meson_encoder_dsi = priv->encoders[MESON_ENC_DSI];
drm_bridge_remove(&meson_encoder_dsi->bridge);
- drm_bridge_remove(meson_encoder_dsi->next_bridge);
}
}
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 25ea76558690..c4686568c9ca 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -474,6 +474,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv)
if (priv->encoders[MESON_ENC_HDMI]) {
meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI];
drm_bridge_remove(&meson_encoder_hdmi->bridge);
- drm_bridge_remove(meson_encoder_hdmi->next_bridge);
}
}
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c0bc924cd302..c9c55e2ea584 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1287,7 +1287,7 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
gpu->ubwc_config.highest_bank_bit = 15;
if (adreno_is_a610(gpu)) {
- gpu->ubwc_config.highest_bank_bit = 14;
+ gpu->ubwc_config.highest_bank_bit = 13;
gpu->ubwc_config.min_acc_len = 1;
gpu->ubwc_config.ubwc_mode = 1;
}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 83380bc92a00..6a4b489d44e5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -144,10 +144,6 @@ enum dpu_enc_rc_states {
* to track crtc in the disable() hook which is called
* _after_ encoder_mask is cleared.
* @connector: If a mode is set, cached pointer to the active connector
- * @crtc_kickoff_cb: Callback into CRTC that will flush & start
- * all CTL paths
- * @crtc_kickoff_cb_data: Opaque user data given to crtc_kickoff_cb
- * @debugfs_root: Debug file system root file node
* @enc_lock: Lock around physical encoder
* create/destroy/enable/disable
* @frame_busy_mask: Bitmask tracking which phys_enc we are still
@@ -2072,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
}
/* reset the merge 3D HW block */
- if (phys_enc->hw_pp->merge_3d) {
+ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
BLEND_3D_NONE);
if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2103,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
if (phys_enc->hw_wb)
intf_cfg.wb = phys_enc->hw_wb->idx;
- if (phys_enc->hw_pp->merge_3d)
+ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
if (ctl->ops.reset_intf_cfg)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index b58a9c2ae326..724537ab776d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
/**
* struct dpu_rm_requirements - Reservation requirements parameter bundle
* @topology: selected topology for the display
- * @hw_res: Hardware resources required as reported by the encoders
*/
struct dpu_rm_requirements {
struct msm_display_topology topology;
@@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
* _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary
* @rm: dpu resource manager handle
* @primary_idx: index of primary mixer in rm->mixer_blks[]
+ *
+ * Returns: lm peer mixed id on success or %-EINVAL on error
*/
static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx)
{
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366ed7..fb588fde298a 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
tbd = dp_link_get_test_bits_depth(ctrl->link,
ctrl->panel->dp_mode.bpp);
- if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
- pr_debug("BIT_DEPTH not set. Configure default\n");
- tbd = DP_TEST_BIT_DEPTH_8;
- }
-
config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index d37d599aec27..4c72124ffb5d 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -329,10 +329,26 @@ static const struct component_ops dp_display_comp_ops = {
.unbind = dp_display_unbind,
};
+static void dp_display_send_hpd_event(struct msm_dp *dp_display)
+{
+ struct dp_display_private *dp;
+ struct drm_connector *connector;
+
+ dp = container_of(dp_display, struct dp_display_private, dp_display);
+
+ connector = dp->dp_display.connector;
+ drm_helper_hpd_irq_event(connector->dev);
+}
+
static int dp_display_send_hpd_notification(struct dp_display_private *dp,
bool hpd)
{
- struct drm_bridge *bridge = dp->dp_display.bridge;
+ if ((hpd && dp->dp_display.link_ready) ||
+ (!hpd && !dp->dp_display.link_ready)) {
+ drm_dbg_dp(dp->drm_dev, "HPD already %s\n",
+ (hpd ? "on" : "off"));
+ return 0;
+ }
/* reset video pattern flag on disconnect */
if (!hpd) {
@@ -348,7 +364,7 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp,
drm_dbg_dp(dp->drm_dev, "type=%d hpd=%d\n",
dp->dp_display.connector_type, hpd);
- drm_bridge_hpd_notify(bridge, dp->dp_display.link_ready);
+ dp_display_send_hpd_event(&dp->dp_display);
return 0;
}
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 98427d45e9a7..49dfac1fd1ef 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
#include <drm/drm_print.h>
+#include "dp_reg.h"
#include "dp_link.h"
#include "dp_panel.h"
@@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
int dp_link_get_colorimetry_config(struct dp_link *dp_link)
{
- u32 cc;
+ u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
struct dp_link_private *link;
if (!dp_link) {
@@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
* Unless a video pattern CTS test is ongoing, use RGB_VESA
* Only RGB_VESA and RGB_CEA supported for now
*/
- if (dp_link_is_video_pattern_requested(link))
- cc = link->dp_link.test_video.test_dyn_range;
- else
- cc = DP_TEST_DYNAMIC_RANGE_VESA;
+ if (dp_link_is_video_pattern_requested(link)) {
+ if (link->dp_link.test_video.test_dyn_range &
+ DP_TEST_DYNAMIC_RANGE_CEA)
+ cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+ }
return cc;
}
@@ -1179,6 +1181,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
{
u32 tbd;
+ struct dp_link_private *link;
+
+ link = container_of(dp_link, struct dp_link_private, dp_link);
/*
* Few simplistic rules and assumptions made here:
@@ -1196,12 +1201,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
tbd = DP_TEST_BIT_DEPTH_10;
break;
default:
- tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+ drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+ bpp);
+ tbd = DP_TEST_BIT_DEPTH_8;
break;
}
- if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
- tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+ tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
return tbd;
}
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e72b..78785ed4b40c 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
#define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001)
#define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005)
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB (0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB (0x04)
+
#define REG_DP_VALID_BOUNDARY (0x00000030)
#define REG_DP_VALID_BOUNDARY_2 (0x00000034)
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 5f68e31a3e4e..0915f3b68752 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
{
void *vaddr;
- vaddr = msm_gem_get_vaddr(obj);
+ vaddr = msm_gem_get_vaddr_locked(obj);
if (IS_ERR(vaddr))
return PTR_ERR(vaddr);
iosys_map_set_vaddr(map, vaddr);
@@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
{
- msm_gem_put_vaddr(obj);
+ msm_gem_put_vaddr_locked(obj);
}
struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 095390774f22..655002b21b0d 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -751,12 +751,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
struct msm_ringbuffer *ring = submit->ring;
unsigned long flags;
- pm_runtime_get_sync(&gpu->pdev->dev);
+ WARN_ON(!mutex_is_locked(&gpu->lock));
- mutex_lock(&gpu->lock);
+ pm_runtime_get_sync(&gpu->pdev->dev);
msm_gpu_hw_init(gpu);
+ submit->seqno = submit->hw_fence->seqno;
+
update_sw_cntrs(gpu);
/*
@@ -781,11 +783,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
gpu->funcs->submit(gpu, submit);
gpu->cur_ctx_seqno = submit->queue->ctx->seqno;
- hangcheck_timer_reset(gpu);
-
- mutex_unlock(&gpu->lock);
-
pm_runtime_put(&gpu->pdev->dev);
+ hangcheck_timer_reset(gpu);
}
/*
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 5cc8d358cc97..d5512037c38b 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -21,6 +21,8 @@ struct msm_iommu_pagetable {
struct msm_mmu base;
struct msm_mmu *parent;
struct io_pgtable_ops *pgtbl_ops;
+ const struct iommu_flush_ops *tlb;
+ struct device *iommu_dev;
unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */
phys_addr_t ttbr;
u32 asid;
@@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = {
static void msm_iommu_tlb_flush_all(void *cookie)
{
+ struct msm_iommu_pagetable *pagetable = cookie;
+ struct adreno_smmu_priv *adreno_smmu;
+
+ if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+ return;
+
+ adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+ pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie);
+
+ pm_runtime_put_autosuspend(pagetable->iommu_dev);
}
static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
size_t granule, void *cookie)
{
+ struct msm_iommu_pagetable *pagetable = cookie;
+ struct adreno_smmu_priv *adreno_smmu;
+
+ if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+ return;
+
+ adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+ pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie);
+
+ pm_runtime_put_autosuspend(pagetable->iommu_dev);
}
static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
@@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
{
}
-static const struct iommu_flush_ops null_tlb_ops = {
+static const struct iommu_flush_ops tlb_ops = {
.tlb_flush_all = msm_iommu_tlb_flush_all,
.tlb_flush_walk = msm_iommu_tlb_flush_walk,
.tlb_add_page = msm_iommu_tlb_add_page,
@@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
/* The incoming cfg will have the TTBR1 quirk enabled */
ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
- ttbr0_cfg.tlb = &null_tlb_ops;
+ ttbr0_cfg.tlb = &tlb_ops;
pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
- &ttbr0_cfg, iommu->domain);
+ &ttbr0_cfg, pagetable);
if (!pagetable->pgtbl_ops) {
kfree(pagetable);
@@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
/* Needed later for TLB flush */
pagetable->parent = parent;
+ pagetable->tlb = ttbr1_cfg->tlb;
+ pagetable->iommu_dev = ttbr1_cfg->iommu_dev;
pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap;
pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 455b2e3a0cdd..35423d10aafa 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = {
.ubwc_enc_version = UBWC_2_0,
.ubwc_dec_version = UBWC_2_0,
.highest_bank_bit = 1,
+ .reg_bus_bw = 76800,
};
static const struct msm_mdss_data sdm845_data = {
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 4bc13f7d005a..9d6655f96f0c 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
msm_fence_init(submit->hw_fence, fctx);
- submit->seqno = submit->hw_fence->seqno;
-
mutex_lock(&priv->lru.lock);
for (i = 0; i < submit->nr_bos; i++) {
@@ -35,8 +33,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
mutex_unlock(&priv->lru.lock);
+ /* TODO move submit path over to using a per-ring lock.. */
+ mutex_lock(&gpu->lock);
+
msm_gpu_submit(gpu, submit);
+ mutex_unlock(&gpu->lock);
+
return dma_fence_get(submit->hw_fence);
}
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 1e6aaf95ff7c..ceef470c9fbf 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -100,3 +100,11 @@ config DRM_NOUVEAU_SVM
help
Say Y here if you want to enable experimental support for
Shared Virtual Memory (SVM).
+
+config DRM_NOUVEAU_GSP_DEFAULT
+ bool "Use GSP firmware for Turing/Ampere (needs firmware installed)"
+ depends on DRM_NOUVEAU
+ default n
+ help
+ Say Y here if you want to use the GSP codepaths by default on
+ Turing and Ampere GPUs.
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
index 0d9fc741a719..932c9fd0b2d8 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
@@ -11,6 +11,7 @@ struct nvkm_client {
u32 debug;
struct rb_root objroot;
+ spinlock_t obj_lock;
void *data;
int (*event)(u64 token, void *argv, u32 argc);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index d1437c08645f..6f5d376d8fcc 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -9,7 +9,7 @@
#define GSP_PAGE_SIZE BIT(GSP_PAGE_SHIFT)
struct nvkm_gsp_mem {
- u32 size;
+ size_t size;
void *data;
dma_addr_t addr;
};
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index a04156ca8390..80f74ee0fc78 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -128,12 +128,14 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
struct nouveau_abi16_ntfy *ntfy, *temp;
/* Cancel all jobs from the entity's queue. */
- drm_sched_entity_fini(&chan->sched.entity);
+ if (chan->sched)
+ drm_sched_entity_fini(&chan->sched->entity);
if (chan->chan)
nouveau_channel_idle(chan->chan);
- nouveau_sched_fini(&chan->sched);
+ if (chan->sched)
+ nouveau_sched_destroy(&chan->sched);
/* cleanup notifier state */
list_for_each_entry_safe(ntfy, temp, &chan->notifiers, head) {
@@ -197,6 +199,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
struct nouveau_cli *cli = nouveau_cli(file_priv);
struct nouveau_drm *drm = nouveau_drm(dev);
struct nvif_device *device = &drm->client.device;
+ struct nvkm_device *nvkm_device = nvxx_device(&drm->client.device);
struct nvkm_gr *gr = nvxx_gr(device);
struct drm_nouveau_getparam *getparam = data;
struct pci_dev *pdev = to_pci_dev(dev->dev);
@@ -261,6 +264,14 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
getparam->value = nouveau_exec_push_max_from_ib_max(ib_max);
break;
}
+ case NOUVEAU_GETPARAM_VRAM_BAR_SIZE:
+ getparam->value = nvkm_device->func->resource_size(nvkm_device, 1);
+ break;
+ case NOUVEAU_GETPARAM_VRAM_USED: {
+ struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
+ getparam->value = (u64)ttm_resource_manager_usage(vram_mgr);
+ break;
+ }
default:
NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param);
return -EINVAL;
@@ -337,10 +348,16 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
if (ret)
goto done;
- ret = nouveau_sched_init(&chan->sched, drm, drm->sched_wq,
- chan->chan->dma.ib_max);
- if (ret)
- goto done;
+ /* If we're not using the VM_BIND uAPI, we don't need a scheduler.
+ *
+ * The client lock is already acquired by nouveau_abi16_get().
+ */
+ if (nouveau_cli_uvmm(cli)) {
+ ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
+ chan->chan->dma.ib_max);
+ if (ret)
+ goto done;
+ }
init->channel = chan->chan->chid;
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
index 1f5e243c0c75..11c8c4a80079 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.h
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h
@@ -26,7 +26,7 @@ struct nouveau_abi16_chan {
struct nouveau_bo *ntfy;
struct nouveau_vma *ntfy_vma;
struct nvkm_mm heap;
- struct nouveau_sched sched;
+ struct nouveau_sched *sched;
};
struct nouveau_abi16 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 6f6c31a9937b..a947e1d5f309 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -201,7 +201,8 @@ nouveau_cli_fini(struct nouveau_cli *cli)
WARN_ON(!list_empty(&cli->worker));
usif_client_fini(cli);
- nouveau_sched_fini(&cli->sched);
+ if (cli->sched)
+ nouveau_sched_destroy(&cli->sched);
if (uvmm)
nouveau_uvmm_fini(uvmm);
nouveau_vmm_fini(&cli->svm);
@@ -311,7 +312,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
cli->mem = &mems[ret];
/* Don't pass in the (shared) sched_wq in order to let
- * nouveau_sched_init() create a dedicated one for VM_BIND jobs.
+ * nouveau_sched_create() create a dedicated one for VM_BIND jobs.
*
* This is required to ensure that for VM_BIND jobs free_job() work and
* run_job() work can always run concurrently and hence, free_job() work
@@ -320,7 +321,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
* locks which indirectly or directly are held for allocations
* elsewhere.
*/
- ret = nouveau_sched_init(&cli->sched, drm, NULL, 1);
+ ret = nouveau_sched_create(&cli->sched, drm, NULL, 1);
if (ret)
goto done;
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8a6d94c8b163..e239c6bf4afa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -98,7 +98,7 @@ struct nouveau_cli {
bool disabled;
} uvmm;
- struct nouveau_sched sched;
+ struct nouveau_sched *sched;
const struct nvif_mclass *mem;
diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
index bc5d71b79ab2..e65c0ef23bc7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -389,7 +389,7 @@ nouveau_exec_ioctl_exec(struct drm_device *dev,
if (ret)
goto out;
- args.sched = &chan16->sched;
+ args.sched = chan16->sched;
args.file_priv = file_priv;
args.chan = chan;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 49c2bcbef129..5a887d67dc0e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -764,7 +764,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
return -ENOMEM;
if (unlikely(nouveau_cli_uvmm(cli)))
- return -ENOSYS;
+ return nouveau_abi16_put(abi16, -ENOSYS);
list_for_each_entry(temp, &abi16->channels, head) {
if (temp->chan->chid == req->channel) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index dd98f6910f9c..32fa2e273965 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -398,7 +398,7 @@ static const struct drm_sched_backend_ops nouveau_sched_ops = {
.free_job = nouveau_sched_free_job,
};
-int
+static int
nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
struct workqueue_struct *wq, u32 credit_limit)
{
@@ -453,7 +453,30 @@ fail_wq:
return ret;
}
-void
+int
+nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+ struct workqueue_struct *wq, u32 credit_limit)
+{
+ struct nouveau_sched *sched;
+ int ret;
+
+ sched = kzalloc(sizeof(*sched), GFP_KERNEL);
+ if (!sched)
+ return -ENOMEM;
+
+ ret = nouveau_sched_init(sched, drm, wq, credit_limit);
+ if (ret) {
+ kfree(sched);
+ return ret;
+ }
+
+ *psched = sched;
+
+ return 0;
+}
+
+
+static void
nouveau_sched_fini(struct nouveau_sched *sched)
{
struct drm_gpu_scheduler *drm_sched = &sched->base;
@@ -471,3 +494,14 @@ nouveau_sched_fini(struct nouveau_sched *sched)
if (sched->wq)
destroy_workqueue(sched->wq);
}
+
+void
+nouveau_sched_destroy(struct nouveau_sched **psched)
+{
+ struct nouveau_sched *sched = *psched;
+
+ nouveau_sched_fini(sched);
+ kfree(sched);
+
+ *psched = NULL;
+}
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h
index a6528f5981e6..e1f01a23e6f6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.h
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.h
@@ -111,8 +111,8 @@ struct nouveau_sched {
} job;
};
-int nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
- struct workqueue_struct *wq, u32 credit_limit);
-void nouveau_sched_fini(struct nouveau_sched *sched);
+int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+ struct workqueue_struct *wq, u32 credit_limit);
+void nouveau_sched_destroy(struct nouveau_sched **psched);
#endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index cc03e0c22ff3..5e4565c5011a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -1011,7 +1011,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id)
if (ret)
return ret;
- buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL);
+ buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL);
if (!buffer->fault)
return -ENOMEM;
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 4f223c972c6a..0a0a11dc9ec0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1740,7 +1740,7 @@ nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev,
if (ret)
return ret;
- args.sched = &cli->sched;
+ args.sched = cli->sched;
args.file_priv = file_priv;
ret = nouveau_uvmm_vm_bind(&args);
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/client.c b/drivers/gpu/drm/nouveau/nvkm/core/client.c
index ebdeb8eb9e77..c55662937ab2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/client.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/client.c
@@ -180,6 +180,7 @@ nvkm_client_new(const char *name, u64 device, const char *cfg, const char *dbg,
client->device = device;
client->debug = nvkm_dbgopt(dbg, "CLIENT");
client->objroot = RB_ROOT;
+ spin_lock_init(&client->obj_lock);
client->event = event;
INIT_LIST_HEAD(&client->umem);
spin_lock_init(&client->lock);
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/object.c b/drivers/gpu/drm/nouveau/nvkm/core/object.c
index 7c554c14e884..aea3ba72027a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/object.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/object.c
@@ -30,8 +30,10 @@ nvkm_object_search(struct nvkm_client *client, u64 handle,
const struct nvkm_object_func *func)
{
struct nvkm_object *object;
+ unsigned long flags;
if (handle) {
+ spin_lock_irqsave(&client->obj_lock, flags);
struct rb_node *node = client->objroot.rb_node;
while (node) {
object = rb_entry(node, typeof(*object), node);
@@ -40,9 +42,12 @@ nvkm_object_search(struct nvkm_client *client, u64 handle,
else
if (handle > object->object)
node = node->rb_right;
- else
+ else {
+ spin_unlock_irqrestore(&client->obj_lock, flags);
goto done;
+ }
}
+ spin_unlock_irqrestore(&client->obj_lock, flags);
return ERR_PTR(-ENOENT);
} else {
object = &client->object;
@@ -57,30 +62,39 @@ done:
void
nvkm_object_remove(struct nvkm_object *object)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&object->client->obj_lock, flags);
if (!RB_EMPTY_NODE(&object->node))
rb_erase(&object->node, &object->client->objroot);
+ spin_unlock_irqrestore(&object->client->obj_lock, flags);
}
bool
nvkm_object_insert(struct nvkm_object *object)
{
- struct rb_node **ptr = &object->client->objroot.rb_node;
+ struct rb_node **ptr;
struct rb_node *parent = NULL;
+ unsigned long flags;
+ spin_lock_irqsave(&object->client->obj_lock, flags);
+ ptr = &object->client->objroot.rb_node;
while (*ptr) {
struct nvkm_object *this = rb_entry(*ptr, typeof(*this), node);
parent = *ptr;
- if (object->object < this->object)
+ if (object->object < this->object) {
ptr = &parent->rb_left;
- else
- if (object->object > this->object)
+ } else if (object->object > this->object) {
ptr = &parent->rb_right;
- else
+ } else {
+ spin_unlock_irqrestore(&object->client->obj_lock, flags);
return false;
+ }
}
rb_link_node(&object->node, parent, ptr);
rb_insert_color(&object->node, &object->client->objroot);
+ spin_unlock_irqrestore(&object->client->obj_lock, flags);
return true;
}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
index 4135690326f4..3a30bea30e36 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
@@ -168,12 +168,11 @@ r535_bar_new_(const struct nvkm_bar_func *hw, struct nvkm_device *device,
rm->flush = r535_bar_flush;
ret = gf100_bar_new_(rm, device, type, inst, &bar);
- *pbar = bar;
if (ret) {
- if (!bar)
- kfree(rm);
+ kfree(rm);
return ret;
}
+ *pbar = bar;
bar->flushBAR2PhysMode = ioremap(device->func->resource_addr(device, 3), PAGE_SIZE);
if (!bar->flushBAR2PhysMode)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index 19188683c8fc..8c2bf1c16f2a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -154,11 +154,17 @@ shadow_fw_init(struct nvkm_bios *bios, const char *name)
return (void *)fw;
}
+static void
+shadow_fw_release(void *fw)
+{
+ release_firmware(fw);
+}
+
static const struct nvbios_source
shadow_fw = {
.name = "firmware",
.init = shadow_fw_init,
- .fini = (void(*)(void *))release_firmware,
+ .fini = shadow_fw_release,
.read = shadow_fw_read,
.rw = false,
};
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 5e1fa176aac4..a73a5b589790 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
return 0;
}
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+ if (mem->data) {
+ /*
+ * Poison the buffer to catch any unexpected access from
+ * GSP-RM if the buffer was prematurely freed.
+ */
+ memset(mem->data, 0xFF, mem->size);
+
+ dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+ memset(mem, 0, sizeof(*mem));
+ }
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+ mem->size = size;
+ mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+ if (WARN_ON(!mem->data))
+ return -ENOMEM;
+
+ return 0;
+}
+
static int
r535_gsp_postinit(struct nvkm_gsp *gsp)
{
@@ -1024,6 +1050,11 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
nvkm_inth_allow(&gsp->subdev.inth);
nvkm_wr32(device, 0x110004, 0x00000040);
+
+ /* Release the DMA buffers that were needed only for boot and init */
+ nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+ nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+
return ret;
}
@@ -1532,27 +1563,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
return 0;
}
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
- if (mem->data) {
- dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
- mem->data = NULL;
- }
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
- mem->size = size;
- mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
- if (WARN_ON(!mem->data))
- return -ENOMEM;
-
- return 0;
-}
-
-
static int
r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
{
@@ -1938,20 +1948,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
* See kgspCreateRadix3_IMPL
*/
static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
struct nvkm_gsp_radix3 *rx3)
{
u64 addr;
for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
u64 *ptes;
- int idx;
+ size_t bufsize;
+ int ret, idx;
- rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
- rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
- &rx3->mem[i].addr, GFP_KERNEL);
- if (WARN_ON(!rx3->mem[i].data))
- return -ENOMEM;
+ bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+ ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+ if (ret)
+ return ret;
ptes = rx3->mem[i].data;
if (i == 2) {
@@ -1991,7 +2001,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
if (ret)
return ret;
- ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+ ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
if (ret)
return ret;
@@ -2150,6 +2160,13 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
mutex_destroy(&gsp->cmdq.mutex);
r535_gsp_dtor_fws(gsp);
+
+ nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+ nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+ nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+ nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+ nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+ nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
}
int
@@ -2194,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
memcpy(gsp->sig.data, data, size);
/* Build radix3 page table for ELF image. */
- ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+ ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
if (ret)
return ret;
@@ -2295,8 +2312,12 @@ r535_gsp_load(struct nvkm_gsp *gsp, int ver, const struct nvkm_gsp_fwif *fwif)
{
struct nvkm_subdev *subdev = &gsp->subdev;
int ret;
+ bool enable_gsp = fwif->enable;
- if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", fwif->enable))
+#if IS_ENABLED(CONFIG_DRM_NOUVEAU_GSP_DEFAULT)
+ enable_gsp = true;
+#endif
+ if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", enable_gsp))
return -EINVAL;
if ((ret = r535_gsp_load_fw(gsp, "gsp", fwif->ver, &gsp->fws.rm)) ||
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index c4c0f08e9202..4945a1e787eb 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -1768,11 +1768,11 @@ static const struct panel_desc starry_qfh032011_53g_desc = {
};
static const struct drm_display_mode starry_himax83102_j02_default_mode = {
- .clock = 162850,
+ .clock = 162680,
.hdisplay = 1200,
- .hsync_start = 1200 + 50,
- .hsync_end = 1200 + 50 + 20,
- .htotal = 1200 + 50 + 20 + 50,
+ .hsync_start = 1200 + 60,
+ .hsync_end = 1200 + 60 + 20,
+ .htotal = 1200 + 60 + 20 + 40,
.vdisplay = 1920,
.vsync_start = 1920 + 116,
.vsync_end = 1920 + 116 + 8,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 85b3b4871a1d..fdd768bbd487 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -1985,8 +1985,10 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
clock = vop2_set_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags);
}
- if (!clock)
+ if (!clock) {
+ vop2_unlock(vop2);
return;
+ }
if (vcstate->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
!(vp_data->feature & VOP2_VP_FEATURE_OUTPUT_10BIT))
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 85f082396d42..d442b893275b 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1178,21 +1178,24 @@ static void drm_sched_run_job_work(struct work_struct *w)
struct drm_sched_entity *entity;
struct dma_fence *fence;
struct drm_sched_fence *s_fence;
- struct drm_sched_job *sched_job = NULL;
+ struct drm_sched_job *sched_job;
int r;
if (READ_ONCE(sched->pause_submit))
return;
/* Find entity with a ready job */
- while (!sched_job && (entity = drm_sched_select_entity(sched))) {
- sched_job = drm_sched_entity_pop_job(entity);
- if (!sched_job)
- complete_all(&entity->entity_idle);
- }
+ entity = drm_sched_select_entity(sched);
if (!entity)
return; /* No more work */
+ sched_job = drm_sched_entity_pop_job(entity);
+ if (!sched_job) {
+ complete_all(&entity->entity_idle);
+ drm_sched_run_job_queue(sched);
+ return;
+ }
+
s_fence = sched_job->s_fence;
atomic_add(sched_job->credits, &sched->credit_count);
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index a73cff7a3070..03d1c76aec2d 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -1243,9 +1243,26 @@ static int host1x_drm_probe(struct host1x_device *dev)
drm_mode_config_reset(drm);
- err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
- if (err < 0)
- goto hub;
+ /*
+ * Only take over from a potential firmware framebuffer if any CRTCs
+ * have been registered. This must not be a fatal error because there
+ * are other accelerators that are exposed via this driver.
+ *
+ * Another case where this happens is on Tegra234 where the display
+ * hardware is no longer part of the host1x complex, so this driver
+ * will not expose any modesetting features.
+ */
+ if (drm->mode_config.num_crtc > 0) {
+ err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
+ if (err < 0)
+ goto hub;
+ } else {
+ /*
+ * Indicate to userspace that this doesn't expose any display
+ * capabilities.
+ */
+ drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC);
+ }
err = drm_dev_register(drm, 0);
if (err < 0)
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index ea2af6bd9abe..484360c7e1f6 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -8,16 +8,308 @@
#include <linux/prime_numbers.h>
#include <linux/sched/signal.h>
+#include <linux/sizes.h>
#include <drm/drm_buddy.h>
#include "../lib/drm_random.h"
+static unsigned int random_seed;
+
static inline u64 get_size(int order, u64 chunk_size)
{
return (1 << order) * chunk_size;
}
+static void drm_test_buddy_alloc_range_bias(struct kunit *test)
+{
+ u32 mm_size, ps, bias_size, bias_start, bias_end, bias_rem;
+ DRM_RND_STATE(prng, random_seed);
+ unsigned int i, count, *order;
+ struct drm_buddy mm;
+ LIST_HEAD(allocated);
+
+ bias_size = SZ_1M;
+ ps = roundup_pow_of_two(prandom_u32_state(&prng) % bias_size);
+ ps = max(SZ_4K, ps);
+ mm_size = (SZ_8M-1) & ~(ps-1); /* Multiple roots */
+
+ kunit_info(test, "mm_size=%u, ps=%u\n", mm_size, ps);
+
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+ "buddy_init failed\n");
+
+ count = mm_size / bias_size;
+ order = drm_random_order(count, &prng);
+ KUNIT_EXPECT_TRUE(test, order);
+
+ /*
+ * Idea is to split the address space into uniform bias ranges, and then
+ * in some random order allocate within each bias, using various
+ * patterns within. This should detect if allocations leak out from a
+ * given bias, for example.
+ */
+
+ for (i = 0; i < count; i++) {
+ LIST_HEAD(tmp);
+ u32 size;
+
+ bias_start = order[i] * bias_size;
+ bias_end = bias_start + bias_size;
+ bias_rem = bias_size;
+
+ /* internal round_up too big */
+ KUNIT_ASSERT_TRUE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, bias_size + ps, bias_size,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, bias_size, bias_size);
+
+ /* size too big */
+ KUNIT_ASSERT_TRUE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, bias_size + ps, ps,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, bias_size + ps, ps);
+
+ /* bias range too small for size */
+ KUNIT_ASSERT_TRUE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start + ps,
+ bias_end, bias_size, ps,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start + ps, bias_end, bias_size, ps);
+
+ /* bias misaligned */
+ KUNIT_ASSERT_TRUE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start + ps,
+ bias_end - ps,
+ bias_size >> 1, bias_size >> 1,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc h didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start + ps, bias_end - ps, bias_size >> 1, bias_size >> 1);
+
+ /* single big page */
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, bias_size, bias_size,
+ &tmp,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc i failed with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, bias_size, bias_size);
+ drm_buddy_free_list(&mm, &tmp);
+
+ /* single page with internal round_up */
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, ps, bias_size,
+ &tmp,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, ps, bias_size);
+ drm_buddy_free_list(&mm, &tmp);
+
+ /* random size within */
+ size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+ if (size)
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, size, ps,
+ &tmp,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, size, ps);
+
+ bias_rem -= size;
+ /* too big for current avail */
+ KUNIT_ASSERT_TRUE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, bias_rem + ps, ps,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, bias_rem + ps, ps);
+
+ if (bias_rem) {
+ /* random fill of the remainder */
+ size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+ size = max(size, ps);
+
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, size, ps,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, size, ps);
+ /*
+ * Intentionally allow some space to be left
+ * unallocated, and ideally not always on the bias
+ * boundaries.
+ */
+ drm_buddy_free_list(&mm, &tmp);
+ } else {
+ list_splice_tail(&tmp, &allocated);
+ }
+ }
+
+ kfree(order);
+ drm_buddy_free_list(&mm, &allocated);
+ drm_buddy_fini(&mm);
+
+ /*
+ * Something more free-form. Idea is to pick a random starting bias
+ * range within the address space and then start filling it up. Also
+ * randomly grow the bias range in both directions as we go along. This
+ * should give us bias start/end which is not always uniform like above,
+ * and in some cases will require the allocator to jump over already
+ * allocated nodes in the middle of the address space.
+ */
+
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+ "buddy_init failed\n");
+
+ bias_start = round_up(prandom_u32_state(&prng) % (mm_size - ps), ps);
+ bias_end = round_up(bias_start + prandom_u32_state(&prng) % (mm_size - bias_start), ps);
+ bias_end = max(bias_end, bias_start + ps);
+ bias_rem = bias_end - bias_start;
+
+ do {
+ u32 size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start,
+ bias_end, size, ps,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+ bias_start, bias_end, size, ps);
+ bias_rem -= size;
+
+ /*
+ * Try to randomly grow the bias range in both directions, or
+ * only one, or perhaps don't grow at all.
+ */
+ do {
+ u32 old_bias_start = bias_start;
+ u32 old_bias_end = bias_end;
+
+ if (bias_start)
+ bias_start -= round_up(prandom_u32_state(&prng) % bias_start, ps);
+ if (bias_end != mm_size)
+ bias_end += round_up(prandom_u32_state(&prng) % (mm_size - bias_end), ps);
+
+ bias_rem += old_bias_start - bias_start;
+ bias_rem += bias_end - old_bias_end;
+ } while (!bias_rem && (bias_start || bias_end != mm_size));
+ } while (bias_rem);
+
+ KUNIT_ASSERT_EQ(test, bias_start, 0);
+ KUNIT_ASSERT_EQ(test, bias_end, mm_size);
+ KUNIT_ASSERT_TRUE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, bias_start, bias_end,
+ ps, ps,
+ &allocated,
+ DRM_BUDDY_RANGE_ALLOCATION),
+ "buddy_alloc passed with bias(%x-%x), size=%u\n",
+ bias_start, bias_end, ps);
+
+ drm_buddy_free_list(&mm, &allocated);
+ drm_buddy_fini(&mm);
+}
+
+static void drm_test_buddy_alloc_contiguous(struct kunit *test)
+{
+ const unsigned long ps = SZ_4K, mm_size = 16 * 3 * SZ_4K;
+ unsigned long i, n_pages, total;
+ struct drm_buddy_block *block;
+ struct drm_buddy mm;
+ LIST_HEAD(left);
+ LIST_HEAD(middle);
+ LIST_HEAD(right);
+ LIST_HEAD(allocated);
+
+ KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+
+ /*
+ * Idea is to fragment the address space by alternating block
+ * allocations between three different lists; one for left, middle and
+ * right. We can then free a list to simulate fragmentation. In
+ * particular we want to exercise the DRM_BUDDY_CONTIGUOUS_ALLOCATION,
+ * including the try_harder path.
+ */
+
+ i = 0;
+ n_pages = mm_size / ps;
+ do {
+ struct list_head *list;
+ int slot = i % 3;
+
+ if (slot == 0)
+ list = &left;
+ else if (slot == 1)
+ list = &middle;
+ else
+ list = &right;
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ ps, ps, list, 0),
+ "buddy_alloc hit an error size=%u\n",
+ ps);
+ } while (++i < n_pages);
+
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%u\n", 3 * ps);
+
+ drm_buddy_free_list(&mm, &middle);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%u\n", 3 * ps);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 2 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%u\n", 2 * ps);
+
+ drm_buddy_free_list(&mm, &right);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%u\n", 3 * ps);
+ /*
+ * At this point we should have enough contiguous space for 2 blocks,
+ * however they are never buddies (since we freed middle and right) so
+ * will require the try_harder logic to find them.
+ */
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 2 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc hit an error size=%u\n", 2 * ps);
+
+ drm_buddy_free_list(&mm, &left);
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc hit an error size=%u\n", 3 * ps);
+
+ total = 0;
+ list_for_each_entry(block, &allocated, link)
+ total += drm_buddy_block_size(&mm, block);
+
+ KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3);
+
+ drm_buddy_free_list(&mm, &allocated);
+ drm_buddy_fini(&mm);
+}
+
static void drm_test_buddy_alloc_pathological(struct kunit *test)
{
u64 mm_size, size, start = 0;
@@ -275,16 +567,30 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
drm_buddy_fini(&mm);
}
+static int drm_buddy_suite_init(struct kunit_suite *suite)
+{
+ while (!random_seed)
+ random_seed = get_random_u32();
+
+ kunit_info(suite, "Testing DRM buddy manager, with random_seed=0x%x\n",
+ random_seed);
+
+ return 0;
+}
+
static struct kunit_case drm_buddy_tests[] = {
KUNIT_CASE(drm_test_buddy_alloc_limit),
KUNIT_CASE(drm_test_buddy_alloc_optimistic),
KUNIT_CASE(drm_test_buddy_alloc_pessimistic),
KUNIT_CASE(drm_test_buddy_alloc_pathological),
+ KUNIT_CASE(drm_test_buddy_alloc_contiguous),
+ KUNIT_CASE(drm_test_buddy_alloc_range_bias),
{}
};
static struct kunit_suite drm_buddy_test_suite = {
.name = "drm_buddy",
+ .suite_init = drm_buddy_suite_init,
.test_cases = drm_buddy_tests,
};
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index b62f420a9f96..112438d965ff 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -387,7 +387,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt,
enum ttm_caching caching,
pgoff_t start_page, pgoff_t end_page)
{
- struct page **pages = tt->pages;
+ struct page **pages = &tt->pages[start_page];
unsigned int order;
pgoff_t i, nr;
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
index 68d9f6116bdf..777c20ceabab 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
@@ -10,7 +10,7 @@
#include "xe_bo.h"
-#define i915_gem_object_is_shmem(obj) ((obj)->flags & XE_BO_CREATE_SYSTEM_BIT)
+#define i915_gem_object_is_shmem(obj) (0) /* We don't use shmem */
static inline dma_addr_t i915_gem_object_get_dma_address(const struct xe_bo *bo, pgoff_t n)
{
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs_test.c b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
index ef56bd517b28..421b819fd4ba 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
@@ -21,4 +21,5 @@ kunit_test_suite(xe_mocs_test_suite);
MODULE_AUTHOR("Intel Corporation");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("xe_mocs kunit test");
MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING);
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 0b0e262e2166..4d3b80ec906d 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -28,6 +28,14 @@
#include "xe_ttm_stolen_mgr.h"
#include "xe_vm.h"
+const char *const xe_mem_type_to_name[TTM_NUM_MEM_TYPES] = {
+ [XE_PL_SYSTEM] = "system",
+ [XE_PL_TT] = "gtt",
+ [XE_PL_VRAM0] = "vram0",
+ [XE_PL_VRAM1] = "vram1",
+ [XE_PL_STOLEN] = "stolen"
+};
+
static const struct ttm_place sys_placement_flags = {
.fpfn = 0,
.lpfn = 0,
@@ -713,8 +721,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
migrate = xe->tiles[0].migrate;
xe_assert(xe, migrate);
-
- trace_xe_bo_move(bo);
+ trace_xe_bo_move(bo, new_mem->mem_type, old_mem_type, move_lacks_source);
xe_device_mem_access_get(xe);
if (xe_bo_is_pinned(bo) && !xe_bo_is_user(bo)) {
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 9b1279aca127..8be42ac6cd07 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -243,6 +243,7 @@ int xe_bo_evict_pinned(struct xe_bo *bo);
int xe_bo_restore_pinned(struct xe_bo *bo);
extern struct ttm_device_funcs xe_ttm_funcs;
+extern const char *const xe_mem_type_to_name[];
int xe_gem_create_ioctl(struct drm_device *dev, void *data,
struct drm_file *file);
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 1f0b4b9ce84f..5176c27e4b6a 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -83,9 +83,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
return 0;
}
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
- struct xe_file *xef);
-
static void xe_file_close(struct drm_device *dev, struct drm_file *file)
{
struct xe_device *xe = to_xe_device(dev);
@@ -102,8 +99,6 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
mutex_unlock(&xef->exec_queue.lock);
xa_destroy(&xef->exec_queue.xa);
mutex_destroy(&xef->exec_queue.lock);
- device_kill_persistent_exec_queues(xe, xef);
-
mutex_lock(&xef->vm.lock);
xa_for_each(&xef->vm.xa, idx, vm)
xe_vm_close_and_put(vm);
@@ -255,9 +250,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
xa_erase(&xe->usm.asid_to_vm, asid);
}
- drmm_mutex_init(&xe->drm, &xe->persistent_engines.lock);
- INIT_LIST_HEAD(&xe->persistent_engines.list);
-
spin_lock_init(&xe->pinned.lock);
INIT_LIST_HEAD(&xe->pinned.kernel_bo_present);
INIT_LIST_HEAD(&xe->pinned.external_vram);
@@ -570,37 +562,6 @@ void xe_device_shutdown(struct xe_device *xe)
{
}
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q)
-{
- mutex_lock(&xe->persistent_engines.lock);
- list_add_tail(&q->persistent.link, &xe->persistent_engines.list);
- mutex_unlock(&xe->persistent_engines.lock);
-}
-
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
- struct xe_exec_queue *q)
-{
- mutex_lock(&xe->persistent_engines.lock);
- if (!list_empty(&q->persistent.link))
- list_del(&q->persistent.link);
- mutex_unlock(&xe->persistent_engines.lock);
-}
-
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
- struct xe_file *xef)
-{
- struct xe_exec_queue *q, *next;
-
- mutex_lock(&xe->persistent_engines.lock);
- list_for_each_entry_safe(q, next, &xe->persistent_engines.list,
- persistent.link)
- if (q->persistent.xef == xef) {
- xe_exec_queue_kill(q);
- list_del_init(&q->persistent.link);
- }
- mutex_unlock(&xe->persistent_engines.lock);
-}
-
void xe_device_wmb(struct xe_device *xe)
{
struct xe_gt *gt = xe_root_mmio_gt(xe);
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 3da83b233206..08d8b72c7731 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -42,10 +42,6 @@ int xe_device_probe(struct xe_device *xe);
void xe_device_remove(struct xe_device *xe);
void xe_device_shutdown(struct xe_device *xe);
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q);
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
- struct xe_exec_queue *q);
-
void xe_device_wmb(struct xe_device *xe);
static inline struct xe_file *to_xe_file(const struct drm_file *file)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 5dc9127a2029..e8491979a6f2 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -341,14 +341,6 @@ struct xe_device {
struct mutex lock;
} usm;
- /** @persistent_engines: engines that are closed but still running */
- struct {
- /** @lock: protects persistent engines */
- struct mutex lock;
- /** @list: list of persistent engines */
- struct list_head list;
- } persistent_engines;
-
/** @pinned: pinned BO state */
struct {
/** @lock: protected pinned BO list state */
diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae..e4db069f0db3 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
int xe_display_init_nommio(struct xe_device *xe)
{
- int err;
-
if (!xe->info.enable_display)
return 0;
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
/* This must be called before any calls to HAS_PCH_* */
intel_detect_pch(xe);
- err = intel_power_domains_init(xe);
- if (err)
- return err;
-
return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
}
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index 82d1305e831f..6040e4d22b28 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -131,14 +131,6 @@ static void bo_meminfo(struct xe_bo *bo,
static void show_meminfo(struct drm_printer *p, struct drm_file *file)
{
- static const char *const mem_type_to_name[TTM_NUM_MEM_TYPES] = {
- [XE_PL_SYSTEM] = "system",
- [XE_PL_TT] = "gtt",
- [XE_PL_VRAM0] = "vram0",
- [XE_PL_VRAM1] = "vram1",
- [4 ... 6] = NULL,
- [XE_PL_STOLEN] = "stolen"
- };
struct drm_memory_stats stats[TTM_NUM_MEM_TYPES] = {};
struct xe_file *xef = file->driver_priv;
struct ttm_device *bdev = &xef->xe->ttm;
@@ -171,7 +163,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
spin_unlock(&client->bos_lock);
for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) {
- if (!mem_type_to_name[mem_type])
+ if (!xe_mem_type_to_name[mem_type])
continue;
man = ttm_manager_type(bdev, mem_type);
@@ -182,7 +174,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
DRM_GEM_OBJECT_RESIDENT |
(mem_type != XE_PL_SYSTEM ? 0 :
DRM_GEM_OBJECT_PURGEABLE),
- mem_type_to_name[mem_type]);
+ xe_mem_type_to_name[mem_type]);
}
}
}
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index bcfc4127c7c5..49223026c89f 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -60,7 +60,6 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
q->fence_irq = &gt->fence_irq[hwe->class];
q->ring_ops = gt->ring_ops[hwe->class];
q->ops = gt->exec_queue_ops;
- INIT_LIST_HEAD(&q->persistent.link);
INIT_LIST_HEAD(&q->compute.link);
INIT_LIST_HEAD(&q->multi_gt_link);
@@ -310,102 +309,6 @@ static int exec_queue_set_timeslice(struct xe_device *xe, struct xe_exec_queue *
return q->ops->set_timeslice(q, value);
}
-static int exec_queue_set_preemption_timeout(struct xe_device *xe,
- struct xe_exec_queue *q, u64 value,
- bool create)
-{
- u32 min = 0, max = 0;
-
- xe_exec_queue_get_prop_minmax(q->hwe->eclass,
- XE_EXEC_QUEUE_PREEMPT_TIMEOUT, &min, &max);
-
- if (xe_exec_queue_enforce_schedule_limit() &&
- !xe_hw_engine_timeout_in_range(value, min, max))
- return -EINVAL;
-
- return q->ops->set_preempt_timeout(q, value);
-}
-
-static int exec_queue_set_persistence(struct xe_device *xe, struct xe_exec_queue *q,
- u64 value, bool create)
-{
- if (XE_IOCTL_DBG(xe, !create))
- return -EINVAL;
-
- if (XE_IOCTL_DBG(xe, xe_vm_in_preempt_fence_mode(q->vm)))
- return -EINVAL;
-
- if (value)
- q->flags |= EXEC_QUEUE_FLAG_PERSISTENT;
- else
- q->flags &= ~EXEC_QUEUE_FLAG_PERSISTENT;
-
- return 0;
-}
-
-static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q,
- u64 value, bool create)
-{
- u32 min = 0, max = 0;
-
- if (XE_IOCTL_DBG(xe, !create))
- return -EINVAL;
-
- xe_exec_queue_get_prop_minmax(q->hwe->eclass,
- XE_EXEC_QUEUE_JOB_TIMEOUT, &min, &max);
-
- if (xe_exec_queue_enforce_schedule_limit() &&
- !xe_hw_engine_timeout_in_range(value, min, max))
- return -EINVAL;
-
- return q->ops->set_job_timeout(q, value);
-}
-
-static int exec_queue_set_acc_trigger(struct xe_device *xe, struct xe_exec_queue *q,
- u64 value, bool create)
-{
- if (XE_IOCTL_DBG(xe, !create))
- return -EINVAL;
-
- if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
- return -EINVAL;
-
- q->usm.acc_trigger = value;
-
- return 0;
-}
-
-static int exec_queue_set_acc_notify(struct xe_device *xe, struct xe_exec_queue *q,
- u64 value, bool create)
-{
- if (XE_IOCTL_DBG(xe, !create))
- return -EINVAL;
-
- if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
- return -EINVAL;
-
- q->usm.acc_notify = value;
-
- return 0;
-}
-
-static int exec_queue_set_acc_granularity(struct xe_device *xe, struct xe_exec_queue *q,
- u64 value, bool create)
-{
- if (XE_IOCTL_DBG(xe, !create))
- return -EINVAL;
-
- if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
- return -EINVAL;
-
- if (value > DRM_XE_ACC_GRANULARITY_64M)
- return -EINVAL;
-
- q->usm.acc_granularity = value;
-
- return 0;
-}
-
typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe,
struct xe_exec_queue *q,
u64 value, bool create);
@@ -413,12 +316,6 @@ typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe,
static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = {
[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority,
[DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice,
- [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout,
- [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE] = exec_queue_set_persistence,
- [DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout,
- [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger,
- [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify,
- [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY] = exec_queue_set_acc_granularity,
};
static int exec_queue_user_ext_set_property(struct xe_device *xe,
@@ -437,10 +334,15 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe,
if (XE_IOCTL_DBG(xe, ext.property >=
ARRAY_SIZE(exec_queue_set_property_funcs)) ||
- XE_IOCTL_DBG(xe, ext.pad))
+ XE_IOCTL_DBG(xe, ext.pad) ||
+ XE_IOCTL_DBG(xe, ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY &&
+ ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE))
return -EINVAL;
idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs));
+ if (!exec_queue_set_property_funcs[idx])
+ return -EINVAL;
+
return exec_queue_set_property_funcs[idx](xe, q, ext.value, create);
}
@@ -704,9 +606,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
}
q = xe_exec_queue_create(xe, vm, logical_mask,
- args->width, hwe,
- xe_vm_in_lr_mode(vm) ? 0 :
- EXEC_QUEUE_FLAG_PERSISTENT);
+ args->width, hwe, 0);
up_read(&vm->lock);
xe_vm_put(vm);
if (IS_ERR(q))
@@ -728,8 +628,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
goto kill_exec_queue;
}
- q->persistent.xef = xef;
-
mutex_lock(&xef->exec_queue.lock);
err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL);
mutex_unlock(&xef->exec_queue.lock);
@@ -872,10 +770,7 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data,
if (XE_IOCTL_DBG(xe, !q))
return -ENOENT;
- if (!(q->flags & EXEC_QUEUE_FLAG_PERSISTENT))
- xe_exec_queue_kill(q);
- else
- xe_device_add_persistent_exec_queues(xe, q);
+ xe_exec_queue_kill(q);
trace_xe_exec_queue_close(q);
xe_exec_queue_put(q);
@@ -926,20 +821,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
* @q: The exec queue
* @vm: The VM the engine does a bind or exec for
*
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
*
* Returns: last fence if not signaled, dma fence stub if signaled
*/
struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
struct xe_vm *vm)
{
+ struct dma_fence *fence;
+
xe_exec_queue_last_fence_lockdep_assert(q, vm);
if (q->last_fence &&
test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
xe_exec_queue_last_fence_put(q, vm);
- return q->last_fence ? q->last_fence : dma_fence_get_stub();
+ fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+ dma_fence_get(fence);
+ return fence;
}
/**
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 8d4b7feb8c30..36f4901d8d7e 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -105,16 +105,6 @@ struct xe_exec_queue {
struct xe_guc_exec_queue *guc;
};
- /**
- * @persistent: persistent exec queue state
- */
- struct {
- /** @xef: file which this exec queue belongs to */
- struct xe_file *xef;
- /** @link: link in list of persistent exec queues */
- struct list_head link;
- } persistent;
-
union {
/**
* @parallel: parallel submission state
@@ -160,16 +150,6 @@ struct xe_exec_queue {
spinlock_t lock;
} compute;
- /** @usm: unified shared memory state */
- struct {
- /** @acc_trigger: access counter trigger */
- u32 acc_trigger;
- /** @acc_notify: access counter notify */
- u32 acc_notify;
- /** @acc_granularity: access counter granularity */
- u32 acc_granularity;
- } usm;
-
/** @ops: submission backend exec queue operations */
const struct xe_exec_queue_ops *ops;
diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index 96b5224eb478..acb4d9f38fd7 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -212,7 +212,7 @@ static void xe_execlist_port_wake_locked(struct xe_execlist_port *port,
static void xe_execlist_make_active(struct xe_execlist_exec_queue *exl)
{
struct xe_execlist_port *port = exl->port;
- enum xe_exec_queue_priority priority = exl->active_priority;
+ enum xe_exec_queue_priority priority = exl->q->sched_props.priority;
XE_WARN_ON(priority == XE_EXEC_QUEUE_PRIORITY_UNSET);
XE_WARN_ON(priority < 0);
@@ -378,8 +378,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w)
list_del(&exl->active_link);
spin_unlock_irqrestore(&exl->port->lock, flags);
- if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
- xe_device_remove_persistent_exec_queues(xe, q);
drm_sched_entity_fini(&exl->entity);
drm_sched_fini(&exl->sched);
kfree(exl);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec1295..35474ddbaf97 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
* USM has its only SA pool to non-block behind user operations
*/
if (gt_to_xe(gt)->info.has_usm) {
- gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+ struct xe_device *xe = gt_to_xe(gt);
+
+ gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+ IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
if (IS_ERR(gt->usm.bb_pool)) {
err = PTR_ERR(gt->usm.bb_pool);
goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
index 9358f7336889..9fcae65b6469 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.c
+++ b/drivers/gpu/drm/xe/xe_gt_idle.c
@@ -145,10 +145,10 @@ void xe_gt_idle_sysfs_init(struct xe_gt_idle *gtidle)
}
if (xe_gt_is_media_type(gt)) {
- sprintf(gtidle->name, "gt%d-mc\n", gt->info.id);
+ sprintf(gtidle->name, "gt%d-mc", gt->info.id);
gtidle->idle_residency = xe_guc_pc_mc6_residency;
} else {
- sprintf(gtidle->name, "gt%d-rc\n", gt->info.id);
+ sprintf(gtidle->name, "gt%d-rc", gt->info.id);
gtidle->idle_residency = xe_guc_pc_rc6_residency;
}
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 9c2fe1697d6e..73f08f1924df 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -335,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
return -EPROTO;
asid = FIELD_GET(PFD_ASID, msg[1]);
- pf_queue = &gt->usm.pf_queue[asid % NUM_PF_QUEUE];
+ pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
spin_lock_irqsave(&pf_queue->lock, flags);
full = pf_queue_full(pf_queue);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 7eef23a00d77..f4c485289dbe 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -247,6 +247,14 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
xe_gt_assert(gt, vma);
+ /* Execlists not supported */
+ if (gt_to_xe(gt)->info.force_execlist) {
+ if (fence)
+ __invalidation_fence_signal(fence);
+
+ return 0;
+ }
+
action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
if (!xe->info.has_range_tlb_invalidation) {
@@ -317,6 +325,10 @@ int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno)
struct drm_printer p = drm_err_printer(__func__);
int ret;
+ /* Execlists not supported */
+ if (gt_to_xe(gt)->info.force_execlist)
+ return 0;
+
/*
* XXX: See above, this algorithm only works if seqno are always in
* order
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 54ffcfcdd41f..f22ae717b0b2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1028,8 +1028,6 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
if (xe_exec_queue_is_lr(q))
cancel_work_sync(&ge->lr_tdr);
- if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
- xe_device_remove_persistent_exec_queues(gt_to_xe(q->gt), q);
release_guc_id(guc, q);
xe_sched_entity_fini(&ge->entity);
xe_sched_fini(&ge->sched);
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 0ec5ad2539f1..b38319d2801e 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -682,8 +682,6 @@ static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
#define PVC_CTX_ASID (0x2e + 1)
#define PVC_CTX_ACC_CTR_THOLD (0x2a + 1)
-#define ACC_GRANULARITY_S 20
-#define ACC_NOTIFY_S 16
int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
struct xe_exec_queue *q, struct xe_vm *vm, u32 ring_size)
@@ -754,13 +752,7 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
xe_lrc_write_ctx_reg(lrc, CTX_RING_CTL,
RING_CTL_SIZE(lrc->ring.size) | RING_VALID);
if (xe->info.has_asid && vm)
- xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID,
- (q->usm.acc_granularity <<
- ACC_GRANULARITY_S) | vm->usm.asid);
- if (xe->info.has_usm && vm)
- xe_lrc_write_ctx_reg(lrc, PVC_CTX_ACC_CTR_THOLD,
- (q->usm.acc_notify << ACC_NOTIFY_S) |
- q->usm.acc_trigger);
+ xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid);
lrc->desc = LRC_VALID;
lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 5c6c54624252..70480c305602 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
if (!IS_DGFX(xe)) {
/* Write out batch too */
m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
- if (xe->info.has_usm) {
- batch = tile->primary_gt->usm.bb_pool->bo;
- m->usm_batch_base_ofs = m->batch_base_ofs;
- }
-
for (i = 0; i < batch->size;
i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
entry);
level++;
}
+ if (xe->info.has_usm) {
+ xe_tile_assert(tile, batch->size == SZ_1M);
+
+ batch = tile->primary_gt->usm.bb_pool->bo;
+ m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+ xe_tile_assert(tile, batch->size == SZ_512K);
+
+ for (i = 0; i < batch->size;
+ i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+ XE_PAGE_SIZE) {
+ entry = vm->pt_ops->pte_encode_bo(batch, i,
+ pat_index, 0);
+
+ xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+ entry);
+ level++;
+ }
+ }
} else {
u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
@@ -1204,8 +1217,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
}
if (q) {
fence = xe_exec_queue_last_fence_get(q, vm);
- if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+ if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+ dma_fence_put(fence);
return false;
+ }
+ dma_fence_put(fence);
}
return true;
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index 5f6b53ea5528..02f7808f28ca 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -105,7 +105,7 @@ static void xe_resize_vram_bar(struct xe_device *xe)
pci_bus_for_each_resource(root, root_res, i) {
if (root_res && root_res->flags & (IORESOURCE_MEM | IORESOURCE_MEM_64) &&
- root_res->start > 0x100000000ull)
+ (u64)root_res->start > 0x100000000ul)
break;
}
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index e45b37c3f0c2..6653c045f3c9 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -20,8 +20,8 @@
struct xe_pt_dir {
struct xe_pt pt;
- /** @dir: Directory structure for the xe_pt_walk functionality */
- struct xe_ptw_dir dir;
+ /** @children: Array of page-table child nodes */
+ struct xe_ptw *children[XE_PDES];
};
#if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -44,7 +44,7 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
{
- return container_of(pt_dir->dir.entries[index], struct xe_pt, base);
+ return container_of(pt_dir->children[index], struct xe_pt, base);
}
static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -65,6 +65,14 @@ static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
XE_PTE_NULL;
}
+static void xe_pt_free(struct xe_pt *pt)
+{
+ if (pt->level)
+ kfree(as_xe_pt_dir(pt));
+ else
+ kfree(pt);
+}
+
/**
* xe_pt_create() - Create a page-table.
* @vm: The vm to create for.
@@ -85,15 +93,19 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
{
struct xe_pt *pt;
struct xe_bo *bo;
- size_t size;
int err;
- size = !level ? sizeof(struct xe_pt) : sizeof(struct xe_pt_dir) +
- XE_PDES * sizeof(struct xe_ptw *);
- pt = kzalloc(size, GFP_KERNEL);
+ if (level) {
+ struct xe_pt_dir *dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+
+ pt = (dir) ? &dir->pt : NULL;
+ } else {
+ pt = kzalloc(sizeof(*pt), GFP_KERNEL);
+ }
if (!pt)
return ERR_PTR(-ENOMEM);
+ pt->level = level;
bo = xe_bo_create_pin_map(vm->xe, tile, vm, SZ_4K,
ttm_bo_type_kernel,
XE_BO_CREATE_VRAM_IF_DGFX(tile) |
@@ -106,8 +118,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
goto err_kfree;
}
pt->bo = bo;
- pt->level = level;
- pt->base.dir = level ? &as_xe_pt_dir(pt)->dir : NULL;
+ pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
if (vm->xef)
xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -116,7 +127,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
return pt;
err_kfree:
- kfree(pt);
+ xe_pt_free(pt);
return ERR_PTR(err);
}
@@ -193,7 +204,7 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
deferred);
}
}
- kfree(pt);
+ xe_pt_free(pt);
}
/**
@@ -358,7 +369,7 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
struct iosys_map *map = &parent->bo->vmap;
if (unlikely(xe_child))
- parent->base.dir->entries[offset] = &xe_child->base;
+ parent->base.children[offset] = &xe_child->base;
xe_pt_write(xe_walk->vm->xe, map, offset, pte);
parent->num_live++;
@@ -488,10 +499,12 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
* this device *requires* 64K PTE size for VRAM, fail.
*/
if (level == 0 && !xe_parent->is_compact) {
- if (xe_pt_is_pte_ps64K(addr, next, xe_walk))
+ if (xe_pt_is_pte_ps64K(addr, next, xe_walk)) {
+ xe_walk->vma->gpuva.flags |= XE_VMA_PTE_64K;
pte |= XE_PTE_PS64;
- else if (XE_WARN_ON(xe_walk->needs_64K))
+ } else if (XE_WARN_ON(xe_walk->needs_64K)) {
return -EINVAL;
+ }
}
ret = xe_pt_insert_entry(xe_walk, xe_parent, offset, NULL, pte);
@@ -534,13 +547,16 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
*child = &xe_child->base;
/*
- * Prefer the compact pagetable layout for L0 if possible.
+ * Prefer the compact pagetable layout for L0 if possible. Only
+ * possible if VMA covers entire 2MB region as compact 64k and
+ * 4k pages cannot be mixed within a 2MB region.
* TODO: Suballocate the pt bo to avoid wasting a lot of
* memory.
*/
if (GRAPHICS_VERx100(tile_to_xe(xe_walk->tile)) >= 1250 && level == 1 &&
covers && xe_pt_scan_64K(addr, next, xe_walk)) {
walk->shifts = xe_compact_pt_shifts;
+ xe_walk->vma->gpuva.flags |= XE_VMA_PTE_COMPACT;
flags |= XE_PDE_64K;
xe_child->is_compact = true;
}
@@ -853,7 +869,7 @@ static void xe_pt_commit_bind(struct xe_vma *vma,
xe_pt_destroy(xe_pt_entry(pt_dir, j_),
xe_vma_vm(vma)->flags, deferred);
- pt_dir->dir.entries[j_] = &newpte->base;
+ pt_dir->children[j_] = &newpte->base;
}
kfree(entries[i].pt_entries);
}
@@ -1507,7 +1523,7 @@ xe_pt_commit_unbind(struct xe_vma *vma,
xe_pt_destroy(xe_pt_entry(pt_dir, i),
xe_vma_vm(vma)->flags, deferred);
- pt_dir->dir.entries[i] = NULL;
+ pt_dir->children[i] = NULL;
}
}
}
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index 8f6c8d063f39..b8b3d2aea492 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,7 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
u64 addr, u64 end, struct xe_pt_walk *walk)
{
pgoff_t offset = xe_pt_offset(addr, level, walk);
- struct xe_ptw **entries = parent->dir ? parent->dir->entries : NULL;
+ struct xe_ptw **entries = parent->children ? parent->children : NULL;
const struct xe_pt_walk_ops *ops = walk->ops;
enum page_walk_action action;
struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index ec3d1e9efa6d..5ecc4d2f0f65 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -8,28 +8,15 @@
#include <linux/pagewalk.h>
#include <linux/types.h>
-struct xe_ptw_dir;
-
/**
* struct xe_ptw - base class for driver pagetable subclassing.
- * @dir: Pointer to an array of children if any.
+ * @children: Pointer to an array of children if any.
*
* Drivers could subclass this, and if it's a page-directory, typically
- * embed the xe_ptw_dir::entries array in the same allocation.
+ * embed an array of xe_ptw pointers.
*/
struct xe_ptw {
- struct xe_ptw_dir *dir;
-};
-
-/**
- * struct xe_ptw_dir - page directory structure
- * @entries: Array holding page directory children.
- *
- * It is the responsibility of the user to ensure @entries is
- * correctly sized.
- */
-struct xe_ptw_dir {
- struct xe_ptw *entries[0];
+ struct xe_ptw **children;
};
/**
diff --git a/drivers/gpu/drm/xe/xe_range_fence.c b/drivers/gpu/drm/xe/xe_range_fence.c
index d35d9ec58e86..372378e89e98 100644
--- a/drivers/gpu/drm/xe/xe_range_fence.c
+++ b/drivers/gpu/drm/xe/xe_range_fence.c
@@ -151,6 +151,11 @@ xe_range_fence_tree_next(struct xe_range_fence *rfence, u64 start, u64 last)
return xe_range_fence_tree_iter_next(rfence, start, last);
}
+static void xe_range_fence_free(struct xe_range_fence *rfence)
+{
+ kfree(rfence);
+}
+
const struct xe_range_fence_ops xe_range_fence_kfree_ops = {
- .free = (void (*)(struct xe_range_fence *rfence)) kfree,
+ .free = xe_range_fence_free,
};
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad..4e2ccad0e52f 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
struct dma_fence *fence;
fence = xe_exec_queue_last_fence_get(job->q, vm);
- dma_fence_get(fence);
return drm_sched_job_add_dependency(&job->drm, fence);
}
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115..02c9577fe418 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -19,7 +19,7 @@
#include "xe_macros.h"
#include "xe_sched_job_types.h"
-struct user_fence {
+struct xe_user_fence {
struct xe_device *xe;
struct kref refcount;
struct dma_fence_cb cb;
@@ -27,31 +27,32 @@ struct user_fence {
struct mm_struct *mm;
u64 __user *addr;
u64 value;
+ int signalled;
};
static void user_fence_destroy(struct kref *kref)
{
- struct user_fence *ufence = container_of(kref, struct user_fence,
+ struct xe_user_fence *ufence = container_of(kref, struct xe_user_fence,
refcount);
mmdrop(ufence->mm);
kfree(ufence);
}
-static void user_fence_get(struct user_fence *ufence)
+static void user_fence_get(struct xe_user_fence *ufence)
{
kref_get(&ufence->refcount);
}
-static void user_fence_put(struct user_fence *ufence)
+static void user_fence_put(struct xe_user_fence *ufence)
{
kref_put(&ufence->refcount, user_fence_destroy);
}
-static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr,
- u64 value)
+static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
+ u64 value)
{
- struct user_fence *ufence;
+ struct xe_user_fence *ufence;
ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
if (!ufence)
@@ -69,7 +70,7 @@ static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr,
static void user_fence_worker(struct work_struct *w)
{
- struct user_fence *ufence = container_of(w, struct user_fence, worker);
+ struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker);
if (mmget_not_zero(ufence->mm)) {
kthread_use_mm(ufence->mm);
@@ -80,10 +81,11 @@ static void user_fence_worker(struct work_struct *w)
}
wake_up_all(&ufence->xe->ufence_wq);
+ WRITE_ONCE(ufence->signalled, 1);
user_fence_put(ufence);
}
-static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence)
+static void kick_ufence(struct xe_user_fence *ufence, struct dma_fence *fence)
{
INIT_WORK(&ufence->worker, user_fence_worker);
queue_work(ufence->xe->ordered_wq, &ufence->worker);
@@ -92,7 +94,7 @@ static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence)
static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
{
- struct user_fence *ufence = container_of(cb, struct user_fence, cb);
+ struct xe_user_fence *ufence = container_of(cb, struct xe_user_fence, cb);
kick_ufence(ufence, fence);
}
@@ -307,7 +309,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
/* Easy case... */
if (!num_in_fence) {
fence = xe_exec_queue_last_fence_get(q, vm);
- dma_fence_get(fence);
return fence;
}
@@ -322,7 +323,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
}
}
fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
- dma_fence_get(fences[current_fence - 1]);
cf = dma_fence_array_create(num_in_fence, fences,
vm->composite_fence_ctx,
vm->composite_fence_seqno++,
@@ -342,3 +342,39 @@ err_out:
return ERR_PTR(-ENOMEM);
}
+
+/**
+ * xe_sync_ufence_get() - Get user fence from sync
+ * @sync: input sync
+ *
+ * Get a user fence reference from sync.
+ *
+ * Return: xe_user_fence pointer with reference
+ */
+struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync)
+{
+ user_fence_get(sync->ufence);
+
+ return sync->ufence;
+}
+
+/**
+ * xe_sync_ufence_put() - Put user fence reference
+ * @ufence: user fence reference
+ *
+ */
+void xe_sync_ufence_put(struct xe_user_fence *ufence)
+{
+ user_fence_put(ufence);
+}
+
+/**
+ * xe_sync_ufence_get_status() - Get user fence status
+ * @ufence: user fence
+ *
+ * Return: 1 if signalled, 0 not signalled, <0 on error
+ */
+int xe_sync_ufence_get_status(struct xe_user_fence *ufence)
+{
+ return READ_ONCE(ufence->signalled);
+}
diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h
index f43cdcaca6c5..0fd0d51208e6 100644
--- a/drivers/gpu/drm/xe/xe_sync.h
+++ b/drivers/gpu/drm/xe/xe_sync.h
@@ -38,4 +38,8 @@ static inline bool xe_sync_is_ufence(struct xe_sync_entry *sync)
return !!sync->ufence;
}
+struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync);
+void xe_sync_ufence_put(struct xe_user_fence *ufence);
+int xe_sync_ufence_get_status(struct xe_user_fence *ufence);
+
#endif
diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h
index 852db5e7884f..30ac3f51993b 100644
--- a/drivers/gpu/drm/xe/xe_sync_types.h
+++ b/drivers/gpu/drm/xe/xe_sync_types.h
@@ -18,7 +18,7 @@ struct xe_sync_entry {
struct drm_syncobj *syncobj;
struct dma_fence *fence;
struct dma_fence_chain *chain_fence;
- struct user_fence *ufence;
+ struct xe_user_fence *ufence;
u64 addr;
u64 timeline_value;
u32 type;
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 044c20881de7..0650b2fa75ef 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -167,9 +167,10 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
goto err_mem_access;
tile->mem.kernel_bb_pool = xe_sa_bo_manager_init(tile, SZ_1M, 16);
- if (IS_ERR(tile->mem.kernel_bb_pool))
+ if (IS_ERR(tile->mem.kernel_bb_pool)) {
err = PTR_ERR(tile->mem.kernel_bb_pool);
-
+ goto err_mem_access;
+ }
xe_wa_apply_tile_workarounds(tile);
xe_tile_sysfs_init(tile);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 95163c303f3e..4ddc55527f9a 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -12,6 +12,7 @@
#include <linux/tracepoint.h>
#include <linux/types.h>
+#include "xe_bo.h"
#include "xe_bo_types.h"
#include "xe_exec_queue_types.h"
#include "xe_gpu_scheduler_types.h"
@@ -26,16 +27,16 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence,
TP_ARGS(fence),
TP_STRUCT__entry(
- __field(u64, fence)
+ __field(struct xe_gt_tlb_invalidation_fence *, fence)
__field(int, seqno)
),
TP_fast_assign(
- __entry->fence = (u64)fence;
+ __entry->fence = fence;
__entry->seqno = fence->seqno;
),
- TP_printk("fence=0x%016llx, seqno=%d",
+ TP_printk("fence=%p, seqno=%d",
__entry->fence, __entry->seqno)
);
@@ -82,16 +83,16 @@ DECLARE_EVENT_CLASS(xe_bo,
TP_STRUCT__entry(
__field(size_t, size)
__field(u32, flags)
- __field(u64, vm)
+ __field(struct xe_vm *, vm)
),
TP_fast_assign(
__entry->size = bo->size;
__entry->flags = bo->flags;
- __entry->vm = (unsigned long)bo->vm;
+ __entry->vm = bo->vm;
),
- TP_printk("size=%zu, flags=0x%02x, vm=0x%016llx",
+ TP_printk("size=%zu, flags=0x%02x, vm=%p",
__entry->size, __entry->flags, __entry->vm)
);
@@ -100,9 +101,31 @@ DEFINE_EVENT(xe_bo, xe_bo_cpu_fault,
TP_ARGS(bo)
);
-DEFINE_EVENT(xe_bo, xe_bo_move,
- TP_PROTO(struct xe_bo *bo),
- TP_ARGS(bo)
+TRACE_EVENT(xe_bo_move,
+ TP_PROTO(struct xe_bo *bo, uint32_t new_placement, uint32_t old_placement,
+ bool move_lacks_source),
+ TP_ARGS(bo, new_placement, old_placement, move_lacks_source),
+ TP_STRUCT__entry(
+ __field(struct xe_bo *, bo)
+ __field(size_t, size)
+ __field(u32, new_placement)
+ __field(u32, old_placement)
+ __array(char, device_id, 12)
+ __field(bool, move_lacks_source)
+ ),
+
+ TP_fast_assign(
+ __entry->bo = bo;
+ __entry->size = bo->size;
+ __entry->new_placement = new_placement;
+ __entry->old_placement = old_placement;
+ strscpy(__entry->device_id, dev_name(xe_bo_device(__entry->bo)->drm.dev), 12);
+ __entry->move_lacks_source = move_lacks_source;
+ ),
+ TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s",
+ __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size,
+ xe_mem_type_to_name[__entry->old_placement],
+ xe_mem_type_to_name[__entry->new_placement], __entry->device_id)
);
DECLARE_EVENT_CLASS(xe_exec_queue,
@@ -327,16 +350,16 @@ DECLARE_EVENT_CLASS(xe_hw_fence,
TP_STRUCT__entry(
__field(u64, ctx)
__field(u32, seqno)
- __field(u64, fence)
+ __field(struct xe_hw_fence *, fence)
),
TP_fast_assign(
__entry->ctx = fence->dma.context;
__entry->seqno = fence->dma.seqno;
- __entry->fence = (unsigned long)fence;
+ __entry->fence = fence;
),
- TP_printk("ctx=0x%016llx, fence=0x%016llx, seqno=%u",
+ TP_printk("ctx=0x%016llx, fence=%p, seqno=%u",
__entry->ctx, __entry->fence, __entry->seqno)
);
@@ -365,7 +388,7 @@ DECLARE_EVENT_CLASS(xe_vma,
TP_ARGS(vma),
TP_STRUCT__entry(
- __field(u64, vma)
+ __field(struct xe_vma *, vma)
__field(u32, asid)
__field(u64, start)
__field(u64, end)
@@ -373,14 +396,14 @@ DECLARE_EVENT_CLASS(xe_vma,
),
TP_fast_assign(
- __entry->vma = (unsigned long)vma;
+ __entry->vma = vma;
__entry->asid = xe_vma_vm(vma)->usm.asid;
__entry->start = xe_vma_start(vma);
__entry->end = xe_vma_end(vma) - 1;
__entry->ptr = xe_vma_userptr(vma);
),
- TP_printk("vma=0x%016llx, asid=0x%05x, start=0x%012llx, end=0x%012llx, ptr=0x%012llx,",
+ TP_printk("vma=%p, asid=0x%05x, start=0x%012llx, end=0x%012llx, userptr=0x%012llx,",
__entry->vma, __entry->asid, __entry->start,
__entry->end, __entry->ptr)
)
@@ -465,16 +488,16 @@ DECLARE_EVENT_CLASS(xe_vm,
TP_ARGS(vm),
TP_STRUCT__entry(
- __field(u64, vm)
+ __field(struct xe_vm *, vm)
__field(u32, asid)
),
TP_fast_assign(
- __entry->vm = (unsigned long)vm;
+ __entry->vm = vm;
__entry->asid = vm->usm.asid;
),
- TP_printk("vm=0x%016llx, asid=0x%05x", __entry->vm,
+ TP_printk("vm=%p, asid=0x%05x", __entry->vm,
__entry->asid)
);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 30db264d34a3..3b21afe5b488 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
#include "generated/xe_wa_oob.h"
#include "xe_wa.h"
-#define TEST_VM_ASYNC_OPS_ERROR
-
static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
{
return vm->gpuvm.r_obj;
@@ -114,11 +112,8 @@ retry:
num_pages - pinned,
read_only ? 0 : FOLL_WRITE,
&pages[pinned]);
- if (ret < 0) {
- if (in_kthread)
- ret = 0;
+ if (ret < 0)
break;
- }
pinned += ret;
ret = 0;
@@ -902,6 +897,11 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
struct xe_device *xe = vm->xe;
bool read_only = xe_vma_read_only(vma);
+ if (vma->ufence) {
+ xe_sync_ufence_put(vma->ufence);
+ vma->ufence = NULL;
+ }
+
if (xe_vma_is_userptr(vma)) {
struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
@@ -1000,9 +1000,16 @@ int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
int err;
XE_WARN_ON(!vm);
- err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
- if (!err && bo && !bo->vm)
- err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+ if (num_shared)
+ err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
+ else
+ err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
+ if (!err && bo && !bo->vm) {
+ if (num_shared)
+ err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+ else
+ err = drm_exec_lock_obj(exec, &bo->ttm.base);
+ }
return err;
}
@@ -1606,6 +1613,16 @@ xe_vm_unbind_vma(struct xe_vma *vma, struct xe_exec_queue *q,
trace_xe_vma_unbind(vma);
+ if (vma->ufence) {
+ struct xe_user_fence * const f = vma->ufence;
+
+ if (!xe_sync_ufence_get_status(f))
+ return ERR_PTR(-EBUSY);
+
+ vma->ufence = NULL;
+ xe_sync_ufence_put(f);
+ }
+
if (number_tiles > 1) {
fences = kmalloc_array(number_tiles, sizeof(*fences),
GFP_KERNEL);
@@ -1739,6 +1756,21 @@ err_fences:
return ERR_PTR(err);
}
+static struct xe_user_fence *
+find_ufence_get(struct xe_sync_entry *syncs, u32 num_syncs)
+{
+ unsigned int i;
+
+ for (i = 0; i < num_syncs; i++) {
+ struct xe_sync_entry *e = &syncs[i];
+
+ if (xe_sync_is_ufence(e))
+ return xe_sync_ufence_get(e);
+ }
+
+ return NULL;
+}
+
static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma,
struct xe_exec_queue *q, struct xe_sync_entry *syncs,
u32 num_syncs, bool immediate, bool first_op,
@@ -1746,9 +1778,16 @@ static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma,
{
struct dma_fence *fence;
struct xe_exec_queue *wait_exec_queue = to_wait_exec_queue(vm, q);
+ struct xe_user_fence *ufence;
xe_vm_assert_held(vm);
+ ufence = find_ufence_get(syncs, num_syncs);
+ if (vma->ufence && ufence)
+ xe_sync_ufence_put(vma->ufence);
+
+ vma->ufence = ufence ?: vma->ufence;
+
if (immediate) {
fence = xe_vm_bind_vma(vma, q, syncs, num_syncs, first_op,
last_op);
@@ -1984,6 +2023,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
xe_exec_queue_last_fence_get(wait_exec_queue, vm);
xe_sync_entry_signal(&syncs[i], NULL, fence);
+ dma_fence_put(fence);
}
}
@@ -2064,7 +2104,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
struct drm_gpuva_ops *ops;
struct drm_gpuva_op *__op;
- struct xe_vma_op *op;
struct drm_gpuvm_bo *vm_bo;
int err;
@@ -2111,23 +2150,10 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
if (IS_ERR(ops))
return ops;
-#ifdef TEST_VM_ASYNC_OPS_ERROR
- if (operation & FORCE_ASYNC_OP_ERROR) {
- op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
- base.entry);
- if (op)
- op->inject_error = true;
- }
-#endif
-
drm_gpuva_for_each_op(__op, ops) {
struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
if (__op->op == DRM_GPUVA_OP_MAP) {
- op->map.immediate =
- flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE;
- op->map.read_only =
- flags & DRM_XE_VM_BIND_FLAG_READONLY;
op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL;
op->map.pat_index = pat_index;
} else if (__op->op == DRM_GPUVA_OP_PREFETCH) {
@@ -2197,13 +2223,17 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
{
if (vma->gpuva.flags & XE_VMA_PTE_1G)
return SZ_1G;
- else if (vma->gpuva.flags & XE_VMA_PTE_2M)
+ else if (vma->gpuva.flags & (XE_VMA_PTE_2M | XE_VMA_PTE_COMPACT))
return SZ_2M;
+ else if (vma->gpuva.flags & XE_VMA_PTE_64K)
+ return SZ_64K;
+ else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+ return SZ_4K;
- return SZ_4K;
+ return SZ_1G; /* Uninitialized, used max size */
}
-static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
+static void xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
{
switch (size) {
case SZ_1G:
@@ -2212,9 +2242,13 @@ static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
case SZ_2M:
vma->gpuva.flags |= XE_VMA_PTE_2M;
break;
+ case SZ_64K:
+ vma->gpuva.flags |= XE_VMA_PTE_64K;
+ break;
+ case SZ_4K:
+ vma->gpuva.flags |= XE_VMA_PTE_4K;
+ break;
}
-
- return SZ_4K;
}
static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
@@ -2312,8 +2346,6 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
switch (op->base.op) {
case DRM_GPUVA_OP_MAP:
{
- flags |= op->map.read_only ?
- VMA_CREATE_FLAG_READ_ONLY : 0;
flags |= op->map.is_null ?
VMA_CREATE_FLAG_IS_NULL : 0;
@@ -2444,7 +2476,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm,
case DRM_GPUVA_OP_MAP:
err = xe_vm_bind(vm, vma, op->q, xe_vma_bo(vma),
op->syncs, op->num_syncs,
- op->map.immediate || !xe_vm_in_fault_mode(vm),
+ !xe_vm_in_fault_mode(vm),
op->flags & XE_VMA_OP_FIRST,
op->flags & XE_VMA_OP_LAST);
break;
@@ -2530,13 +2562,25 @@ retry_userptr:
}
drm_exec_fini(&exec);
- if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+ if (err == -EAGAIN) {
lockdep_assert_held_write(&vm->lock);
- err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
- if (!err)
- goto retry_userptr;
- trace_xe_vma_fail(vma);
+ if (op->base.op == DRM_GPUVA_OP_REMAP) {
+ if (!op->remap.unmap_done)
+ vma = gpuva_to_vma(op->base.remap.unmap->va);
+ else if (op->remap.prev)
+ vma = op->remap.prev;
+ else
+ vma = op->remap.next;
+ }
+
+ if (xe_vma_is_userptr(vma)) {
+ err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+ if (!err)
+ goto retry_userptr;
+
+ trace_xe_vma_fail(vma);
+ }
}
return err;
@@ -2548,13 +2592,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
lockdep_assert_held_write(&vm->lock);
-#ifdef TEST_VM_ASYNC_OPS_ERROR
- if (op->inject_error) {
- op->inject_error = false;
- return -ENOMEM;
- }
-#endif
-
switch (op->base.op) {
case DRM_GPUVA_OP_MAP:
ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2669,7 +2706,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
{
int i;
- for (i = num_ops_list - 1; i; ++i) {
+ for (i = num_ops_list - 1; i >= 0; --i) {
struct drm_gpuva_ops *__ops = ops[i];
struct drm_gpuva_op *__op;
@@ -2714,21 +2751,11 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
return 0;
}
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS \
- (FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
- DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
-#define SUPPORTED_FLAGS \
- (DRM_XE_VM_BIND_FLAG_READONLY | \
- DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
- 0xffff)
-#endif
+#define SUPPORTED_FLAGS (DRM_XE_VM_BIND_FLAG_NULL | \
+ DRM_XE_VM_BIND_FLAG_DUMPABLE)
#define XE_64K_PAGE_MASK 0xffffull
#define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
-#define MAX_BINDS 512 /* FIXME: Picking random upper limit */
-
static int vm_bind_ioctl_check_args(struct xe_device *xe,
struct drm_xe_vm_bind *args,
struct drm_xe_vm_bind_op **bind_ops)
@@ -2740,16 +2767,16 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe,
XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]))
return -EINVAL;
- if (XE_IOCTL_DBG(xe, args->extensions) ||
- XE_IOCTL_DBG(xe, args->num_binds > MAX_BINDS))
+ if (XE_IOCTL_DBG(xe, args->extensions))
return -EINVAL;
if (args->num_binds > 1) {
u64 __user *bind_user =
u64_to_user_ptr(args->vector_of_binds);
- *bind_ops = kmalloc(sizeof(struct drm_xe_vm_bind_op) *
- args->num_binds, GFP_KERNEL);
+ *bind_ops = kvmalloc_array(args->num_binds,
+ sizeof(struct drm_xe_vm_bind_op),
+ GFP_KERNEL | __GFP_ACCOUNT);
if (!*bind_ops)
return -ENOMEM;
@@ -2839,7 +2866,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe,
free_bind_ops:
if (args->num_binds > 1)
- kfree(*bind_ops);
+ kvfree(*bind_ops);
return err;
}
@@ -2927,13 +2954,15 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
}
if (args->num_binds) {
- bos = kcalloc(args->num_binds, sizeof(*bos), GFP_KERNEL);
+ bos = kvcalloc(args->num_binds, sizeof(*bos),
+ GFP_KERNEL | __GFP_ACCOUNT);
if (!bos) {
err = -ENOMEM;
goto release_vm_lock;
}
- ops = kcalloc(args->num_binds, sizeof(*ops), GFP_KERNEL);
+ ops = kvcalloc(args->num_binds, sizeof(*ops),
+ GFP_KERNEL | __GFP_ACCOUNT);
if (!ops) {
err = -ENOMEM;
goto release_vm_lock;
@@ -3074,10 +3103,10 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
for (i = 0; bos && i < args->num_binds; ++i)
xe_bo_put(bos[i]);
- kfree(bos);
- kfree(ops);
+ kvfree(bos);
+ kvfree(ops);
if (args->num_binds > 1)
- kfree(bind_ops);
+ kvfree(bind_ops);
return err;
@@ -3101,10 +3130,10 @@ put_exec_queue:
if (q)
xe_exec_queue_put(q);
free_objs:
- kfree(bos);
- kfree(ops);
+ kvfree(bos);
+ kvfree(ops);
if (args->num_binds > 1)
- kfree(bind_ops);
+ kvfree(bind_ops);
return err;
}
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 1fec66ae2eb2..7300eea5394b 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -19,11 +19,9 @@
struct xe_bo;
struct xe_sync_entry;
+struct xe_user_fence;
struct xe_vm;
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR BIT(31)
-
#define XE_VMA_READ_ONLY DRM_GPUVA_USERBITS
#define XE_VMA_DESTROYED (DRM_GPUVA_USERBITS << 1)
#define XE_VMA_ATOMIC_PTE_BIT (DRM_GPUVA_USERBITS << 2)
@@ -32,6 +30,8 @@ struct xe_vm;
#define XE_VMA_PTE_4K (DRM_GPUVA_USERBITS << 5)
#define XE_VMA_PTE_2M (DRM_GPUVA_USERBITS << 6)
#define XE_VMA_PTE_1G (DRM_GPUVA_USERBITS << 7)
+#define XE_VMA_PTE_64K (DRM_GPUVA_USERBITS << 8)
+#define XE_VMA_PTE_COMPACT (DRM_GPUVA_USERBITS << 9)
/** struct xe_userptr - User pointer */
struct xe_userptr {
@@ -105,6 +105,12 @@ struct xe_vma {
* @pat_index: The pat index to use when encoding the PTEs for this vma.
*/
u16 pat_index;
+
+ /**
+ * @ufence: The user fence that was provided with MAP.
+ * Needs to be signalled before UNMAP can be processed.
+ */
+ struct xe_user_fence *ufence;
};
/**
@@ -289,10 +295,6 @@ struct xe_vm {
struct xe_vma_op_map {
/** @vma: VMA to map */
struct xe_vma *vma;
- /** @immediate: Immediate bind */
- bool immediate;
- /** @read_only: Read only */
- bool read_only;
/** @is_null: is NULL binding */
bool is_null;
/** @pat_index: The pat index to use for this operation. */
@@ -360,11 +362,6 @@ struct xe_vma_op {
/** @flags: operation flags */
enum xe_vma_op_flags flags;
-#ifdef TEST_VM_ASYNC_OPS_ERROR
- /** @inject_error: inject error to test async op error handling */
- bool inject_error;
-#endif
-
union {
/** @map: VMA map operation specific data */
struct xe_vma_op_map map;