diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 77accd029c4a71399de1729323405d7a3c262cc2..89af1006df5587ba560415a7d669251648f3c3e8 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -510,16 +510,6 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
return ret;
}
-static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
-{
- ivpu_boot_dpu_active_drive(vdev, false);
- ivpu_boot_pwr_island_isolation_drive(vdev, true);
- ivpu_boot_pwr_island_trickle_drive(vdev, false);
- ivpu_boot_pwr_island_drive(vdev, false);
-
- return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
-}
-
static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
{
u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
@@ -616,12 +606,37 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
return 0;
}
+static int ivpu_hw_37xx_ip_reset(struct ivpu_device *vdev)
+{
+ int ret;
+ u32 val;
+
+ if (IVPU_WA(punit_disabled))
+ return 0;
+
+ ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+ if (ret) {
+ ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
+ return ret;
+ }
+
+ val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
+ val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
+ REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
+
+ ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+ if (ret)
+ ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+ return ret;
+}
+
static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
{
int ret = 0;
- if (ivpu_boot_pwr_domain_disable(vdev)) {
- ivpu_err(vdev, "Failed to disable power domain\n");
+ if (ivpu_hw_37xx_ip_reset(vdev)) {
+ ivpu_err(vdev, "Failed to reset NPU\n");
ret = -EIO;
}
@@ -661,6 +676,11 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
{
int ret;
+ /* PLL requests may fail when powering down, so issue WP 0 here */
+ ret = ivpu_pll_disable(vdev);
+ if (ret)
+ ivpu_warn(vdev, "Failed to disable PLL: %d\n", ret);
+
ret = ivpu_hw_37xx_d0i3_disable(vdev);
if (ret)
ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index f501f27ebafdf6687b5a46ca7e2387faa931af3e..5f73854234ba93da22b00113376c296df1ebd35a 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -58,11 +58,14 @@ static int ivpu_suspend(struct ivpu_device *vdev)
{
int ret;
+ /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+ pci_save_state(to_pci_dev(vdev->drm.dev));
+
ret = ivpu_shutdown(vdev);
- if (ret) {
+ if (ret)
ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
- return ret;
- }
+
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
return ret;
}
@@ -71,6 +74,9 @@ static int ivpu_resume(struct ivpu_device *vdev)
{
int ret;
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+ pci_restore_state(to_pci_dev(vdev->drm.dev));
+
retry:
ret = ivpu_hw_power_up(vdev);
if (ret) {
@@ -120,15 +126,20 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
ivpu_fw_log_dump(vdev);
-retry:
- ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
- if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
- cond_resched();
- goto retry;
- }
+ atomic_inc(&vdev->pm->reset_counter);
+ atomic_set(&vdev->pm->reset_pending, 1);
+ down_write(&vdev->pm->reset_lock);
+
+ ivpu_suspend(vdev);
+ ivpu_pm_prepare_cold_boot(vdev);
+ ivpu_jobs_abort_all(vdev);
+
+ ret = ivpu_resume(vdev);
+ if (ret)
+ ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
- if (ret && ret != -EAGAIN)
- ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
+ up_write(&vdev->pm->reset_lock);
+ atomic_set(&vdev->pm->reset_pending, 0);
kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
pm_runtime_mark_last_busy(vdev->drm.dev);
@@ -200,9 +211,6 @@ int ivpu_pm_suspend_cb(struct device *dev)
ivpu_suspend(vdev);
ivpu_pm_prepare_warm_boot(vdev);
- pci_save_state(to_pci_dev(dev));
- pci_set_power_state(to_pci_dev(dev), PCI_D3hot);
-
ivpu_dbg(vdev, PM, "Suspend done.\n");
return 0;
@@ -216,9 +224,6 @@ int ivpu_pm_resume_cb(struct device *dev)
ivpu_dbg(vdev, PM, "Resume..\n");
- pci_set_power_state(to_pci_dev(dev), PCI_D0);
- pci_restore_state(to_pci_dev(dev));
-
ret = ivpu_resume(vdev);
if (ret)
ivpu_err(vdev, "Failed to resume: %d\n", ret);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 6dce81a061ab1feff52c48f7b160c5e1c13b1322..79827a6dcd7f5cbbf30d61f6701ecee8ae6614fa 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;
@@ -1549,9 +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 2deebece810e78a7ce039772a839684f570bceca..cc21ed67a33075d4f197f2217b883faacc777f3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1519,4 +1519,19 @@ 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 (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 fdde7488d0ed9a8ff93f4a4cc58c123b904236c7..94bdb5fa6ebc6ac7715a64191b5050a9670bf673 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 211501ea91694d9f79b84752223f5e6ce60843c1..586f4d03039dfb5177a27fce81fbdbead88e0235 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);
@@ -859,6 +860,18 @@ int amdgpu_backlight = -1;
MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))");
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
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b9674c57c4365fb5ebdf9644fc4ac0a31b955da8..6ddc8e3360e220644618b26059d735e6bbda10e4 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/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 48c6efcdeac974ba109224510442b0488e1875d0..4d7188912edfee820dca2ac854b55314dc2f1b27 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 d722cbd317834a8a893a0ed5a847feb3a51d6961..826bc4f6c8a7043853d0b8e21bad73660c6a8a8c 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 42d881809dc70e230133674e4b12f6f68567837a..697b6d530d12ef30ed06a22d3cf5c15fa740b62a 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 677281c0793e23a694eb5a7bba9b5f9fd48f61d8..80320b8603fc6692cc5f10426d24f33b5ce0acfa 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 43eff221eae58ca008e2e2e92aec09eb749157d7..4858112f9a53b7e491186e0efa0e70dbb92ee47a 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 e5f7c92eebcbbfa6a1fda115ca2b599cab48e4e8..6ed2ec381aaa320ed1514038a1b6b10c44843019 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 59d2eee72a3297f4f9b7fbc70040391641f7c67f..cf875751971feea51531ffd8580ca54fdca5287d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1956,7 +1956,7 @@ 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);
@@ -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);
@@ -8298,6 +8305,8 @@ 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);
/*
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 f2dfa96f9ef5d9e4805fdbf592cac078efa391a5..39530b2ea4957cc0a6718f322158e101f15431d0 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 960c4b4f6ddf3670156abd99cc0a02aeb176c7dc..05f392501c0ae3572250061b31defef7cde51fb5 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 a5489fe6875f453149d622d59e9b6417b4db616c..aa9fd1dc550a5e8b2142cfb10db96f4779bdc788 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 14cec1c7b718c4ab48fbd9588f4b6465c13897cd..e648902592358ff08ca3a536d9f0abe56bfe5e34 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/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
index e43f77c11c00825aad64ada6ddfb4b0bdce23aff..5f97a868ada34734d99a6a35a329d9c3cd3c5ac2 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/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index ba76dd4a2ce29a68a75883b8e8538395195b4089..a0a65e0991041d90904c516c7279c5b8aa76967c 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
@@ -2760,7 +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/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 5c7f380a84f91ecb1a668e4798be6aaf9347a46f..7252f5f781f0d7869e147846bc1eb44f09e63593 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
@@ -211,7 +211,7 @@ void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
uint32_t otg_inst;
- if (!abm && !tg && !panel_cntl)
+ if (!abm || !tg || !panel_cntl)
return;
otg_inst = tg->inst;
@@ -245,7 +245,7 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
uint32_t otg_inst;
- if (!abm && !tg && !panel_cntl)
+ if (!abm || !tg || !panel_cntl)
return false;
otg_inst = tg->inst;
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 8fe66c3678508d9aee6779fa25cd6128e1f30832..5b0bc7f6a188ccd6b304a369be0bdfe43b91f76a 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 5a0b0451895690d184ec00c56873f0d1acad6864..16a62e01871224495cd771c4042f04d3be85e04d 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 e8dda44b23cb29aa3ec2686b6656bd044c194606..5d36bab0029ca54a03aaef4fc83ff99e59550e5a 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/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 1c3d89264ef72c56251e09549cde90f8d78ce91a..5fdcda8f86026d94697a069ed53a83752a0ebdee 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
@@ -780,7 +780,7 @@ static const struct dc_debug_options debug_defaults_drv = {
.disable_z10 = false,
.ignore_pg = true,
.psp_disabled_wa = true,
- .ips2_eval_delay_us = 1650,
+ .ips2_eval_delay_us = 2000,
.ips2_entry_delay_us = 800,
.static_screen_wait_frames = 2,
};
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index f57e6d74fb0e039a710b9bd8161a8e8e25d5888b..c1a99bf4dffd1d221d9ca9e57d303d415acef00f 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -539,6 +539,12 @@ static int __alloc_range(struct drm_buddy *mm,
} while (1);
list_splice_tail(&allocated, blocks);
+
+ if (total_allocated < size) {
+ err = -ENOSPC;
+ goto err_free;
+ }
+
return 0;
err_undo:
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index cb90e70d85e862a495f2e8691813161a93b7a030..65f9f66933bba2785fc3b64f7040e676c2afd352 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -904,6 +904,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
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 834a5e28abbe5959cc6da2933904c4feb4c7b00d..7352bde299d54767fecb34232cb5941a01d6ea88 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/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f5ef95da55346ff14cc6b102c27e78e8960cec65..ae647d03af25cd48a3151b362c5ed1e752bdba60 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);
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 64f440fdc22b2c832a77ca7ca73cf83ecc5ba625..8b21dc8e26d525f514f74f2a647ea703b2cd2d9a 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/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c0bc924cd3025dc21939e2e75548f273a90fd620..c9c55e2ea584927ce7b3f8ffc50e7ed807f6671a 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/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 5f68e31a3e4e1cbeed95bfde138711c0fc9c9759..0915f3b68752e34702ae8864249d049e3b277ee2 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 095390774f22b547668227ed492a6e9783b055f9..655002b21b0d5dc345283a7699d14b0e88b3e472 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 5cc8d358cc9759307a444cd62bce83c62b3dcdb7..d5512037c38bcd7ca807aaf281dceaebdd688a4e 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_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 4bc13f7d005ab7c643f78206d8d41d72cd779045..9d6655f96f0cebcc0c03e5b9bef6900c299f2f0d 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/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index a04156ca8390ba6fea6a21e07e9eb5bba3ec7605..d1bb8151a1df565c44db55432222f09641d7b109 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -128,12 +128,14 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
struct nouveau_abi16_ntfy *ntfy, *temp;
/* Cancel all jobs from the entity's queue. */
- drm_sched_entity_fini(&chan->sched.entity);
+ if (chan->sched)
+ drm_sched_entity_fini(&chan->sched->entity);
if (chan->chan)
nouveau_channel_idle(chan->chan);
- nouveau_sched_fini(&chan->sched);
+ if (chan->sched)
+ nouveau_sched_destroy(&chan->sched);
/* cleanup notifier state */
list_for_each_entry_safe(ntfy, temp, &chan->notifiers, head) {
@@ -337,10 +339,16 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
if (ret)
goto done;
- ret = nouveau_sched_init(&chan->sched, drm, drm->sched_wq,
- chan->chan->dma.ib_max);
- if (ret)
- goto done;
+ /* If we're not using the VM_BIND uAPI, we don't need a scheduler.
+ *
+ * The client lock is already acquired by nouveau_abi16_get().
+ */
+ if (nouveau_cli_uvmm(cli)) {
+ ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
+ chan->chan->dma.ib_max);
+ if (ret)
+ goto done;
+ }
init->channel = chan->chan->chid;
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
index 1f5e243c0c759ef759dbba7d4f89279c90bce5d4..11c8c4a80079bbb2b658816dd42d05f68a5eaab6 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 6f6c31a9937b2fe751c6cffe429cc21a6b47a385..a947e1d5f309ae525e8087d13899f1efd1e8e73b 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 8a6d94c8b1631fd7ab8bbc193f35b064057a0185..e239c6bf4afa4f75d4ca30c63583af82f2ab9621 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 bc5d71b79ab203ff7e874c612f3ea1e7c36323de..e65c0ef23bc73d59f3066ff02ae9360253b93e6d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -389,7 +389,7 @@ nouveau_exec_ioctl_exec(struct drm_device *dev,
if (ret)
goto out;
- args.sched = &chan16->sched;
+ args.sched = chan16->sched;
args.file_priv = file_priv;
args.chan = chan;
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index dd98f6910f9cab7b19117186339a138277e77b78..32fa2e273965bf140a4cb2e05262b638c312cd6e 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 @@ nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
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 a6528f5981e6a6e8182a44e0ec3c0336302e6154..e1f01a23e6f6e84cf2700bde86e4fb5e3e013df1 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 cc03e0c22ff3fec65cf6a40ae34db2af20bb349e..5e4565c5011a976d1c8057e9366d9e1da03de97a 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 4f223c972c6a8cb3bab7873dfa2a1c38756648b2..0a0a11dc9ec03eeba855f47ca57c1ad1c5669f54 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1740,7 +1740,7 @@ nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev,
if (ret)
return ret;
- args.sched = &cli->sched;
+ args.sched = cli->sched;
args.file_priv = file_priv;
ret = nouveau_uvmm_vm_bind(&args);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 85b3b4871a1d63bf5a8cb2315a25dfd5ef2b8b70..fdd768bbd487c24b545da7aba2d0d45f63784293 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -1985,8 +1985,10 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
clock = vop2_set_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags);
}
- if (!clock)
+ if (!clock) {
+ vop2_unlock(vop2);
return;
+ }
if (vcstate->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
!(vp_data->feature & VOP2_VP_FEATURE_OUTPUT_10BIT))
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index ea2af6bd9abebcf381cc6a1a245e8cc1f044a656..fee6bec757d1ac2e37918b5b16e97c4331cc0401 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -8,6 +8,7 @@
#include <linux/prime_numbers.h>
#include <linux/sched/signal.h>
+#include <linux/sizes.h>
#include <drm/drm_buddy.h>
@@ -18,6 +19,93 @@ static inline u64 get_size(int order, u64 chunk_size)
return (1 << order) * chunk_size;
}
+static void drm_test_buddy_alloc_contiguous(struct kunit *test)
+{
+ u64 mm_size, ps = SZ_4K, i, n_pages, total;
+ struct drm_buddy_block *block;
+ struct drm_buddy mm;
+ LIST_HEAD(left);
+ LIST_HEAD(middle);
+ LIST_HEAD(right);
+ LIST_HEAD(allocated);
+
+ mm_size = 16 * 3 * SZ_4K;
+
+ KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+
+ /*
+ * Idea is to fragment the address space by alternating block
+ * allocations between three different lists; one for left, middle and
+ * right. We can then free a list to simulate fragmentation. In
+ * particular we want to exercise the DRM_BUDDY_CONTIGUOUS_ALLOCATION,
+ * including the try_harder path.
+ */
+
+ i = 0;
+ n_pages = mm_size / ps;
+ do {
+ struct list_head *list;
+ int slot = i % 3;
+
+ if (slot == 0)
+ list = &left;
+ else if (slot == 1)
+ list = &middle;
+ else
+ list = &right;
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ ps, ps, list, 0),
+ "buddy_alloc hit an error size=%d\n",
+ ps);
+ } while (++i < n_pages);
+
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%d\n", 3 * ps);
+
+ drm_buddy_free_list(&mm, &middle);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%llu\n", 3 * ps);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 2 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%llu\n", 2 * ps);
+
+ drm_buddy_free_list(&mm, &right);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%llu\n", 3 * ps);
+ /*
+ * At this point we should have enough contiguous space for 2 blocks,
+ * however they are never buddies (since we freed middle and right) so
+ * will require the try_harder logic to find them.
+ */
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 2 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc hit an error size=%d\n", 2 * ps);
+
+ drm_buddy_free_list(&mm, &left);
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc hit an error size=%d\n", 3 * ps);
+
+ total = 0;
+ list_for_each_entry(block, &allocated, link)
+ total += drm_buddy_block_size(&mm, block);
+
+ KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3);
+
+ drm_buddy_free_list(&mm, &allocated);
+ drm_buddy_fini(&mm);
+}
+
static void drm_test_buddy_alloc_pathological(struct kunit *test)
{
u64 mm_size, size, start = 0;
@@ -280,6 +368,7 @@ static struct kunit_case drm_buddy_tests[] = {
KUNIT_CASE(drm_test_buddy_alloc_optimistic),
KUNIT_CASE(drm_test_buddy_alloc_pessimistic),
KUNIT_CASE(drm_test_buddy_alloc_pathological),
+ KUNIT_CASE(drm_test_buddy_alloc_contiguous),
{}
};
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 68d9f6116bdfc3522ee5d6d94ef2bb763ec81090..777c20ceabab12f04f3f2062df3524ef1c2c0923 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/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index e45b37c3f0c262744f960d769eeed29a07ef14e7..ac19bfa3f798c08e48511af0f18e093f29f88eab 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++;
@@ -853,7 +864,7 @@ 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 +1518,7 @@ 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 8f6c8d063f39f0293a6c4d966c009dfc24ca9045..b8b3d2aea4923d0ac087f6a2c972652aba8efc6f 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 ec3d1e9efa6d514ae21bb4b4a1b35a0bc2baf59c..5ecc4d2f0f6536b7ec79033f80f556ce1f00edc5 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 d35d9ec58e86f95c8244fc02e6a9709b63ccf93a..372378e89e989239833879e23d2e62a2fd573b54 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_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 865e10d0a06aa31bc13fc60802257b80ebdc9430..7b00faa672879c3b568c3ee3f3d9c20c54f527c9 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -995,9 +995,16 @@ 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;
}