summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c17
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c76
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c27
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c126
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c7
17 files changed, 195 insertions, 93 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 1e651b959141..694c3726e0f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3166,6 +3166,12 @@ static void amdgpu_device_detect_sriov_bios(struct amdgpu_device *adev)
bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
{
switch (asic_type) {
+#ifdef CONFIG_DRM_AMDGPU_SI
+ case CHIP_HAINAN:
+#endif
+ case CHIP_TOPAZ:
+ /* chips with no display hardware */
+ return false;
#if defined(CONFIG_DRM_AMD_DC)
case CHIP_TAHITI:
case CHIP_PITCAIRN:
@@ -4461,7 +4467,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
struct amdgpu_reset_context *reset_context)
{
- int i, j, r = 0;
+ int i, r = 0;
struct amdgpu_job *job = NULL;
bool need_full_reset =
test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
@@ -4483,15 +4489,8 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
/*clear job fence from fence drv to avoid force_completion
*leave NULL and vm flush fence in fence drv */
- for (j = 0; j <= ring->fence_drv.num_fences_mask; j++) {
- struct dma_fence *old, **ptr;
+ amdgpu_fence_driver_clear_job_fences(ring);
- ptr = &ring->fence_drv.fences[j];
- old = rcu_dereference_protected(*ptr, 1);
- if (old && test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &old->flags)) {
- RCU_INIT_POINTER(*ptr, NULL);
- }
- }
/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
amdgpu_fence_driver_force_completion(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index ea00090b3fb3..bcc9343353b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -526,10 +526,15 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
}
}
+union gc_info {
+ struct gc_info_v1_0 v1;
+ struct gc_info_v2_0 v2;
+};
+
int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
{
struct binary_header *bhdr;
- struct gc_info_v1_0 *gc_info;
+ union gc_info *gc_info;
if (!adev->mman.discovery_bin) {
DRM_ERROR("ip discovery uninitialized\n");
@@ -537,28 +542,55 @@ int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
}
bhdr = (struct binary_header *)adev->mman.discovery_bin;
- gc_info = (struct gc_info_v1_0 *)(adev->mman.discovery_bin +
+ gc_info = (union gc_info *)(adev->mman.discovery_bin +
le16_to_cpu(bhdr->table_list[GC].offset));
-
- adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se);
- adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->gc_num_wgp0_per_sa) +
- le32_to_cpu(gc_info->gc_num_wgp1_per_sa));
- adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->gc_num_sa_per_se);
- adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->gc_num_rb_per_se);
- adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->gc_num_gl2c);
- adev->gfx.config.max_gprs = le32_to_cpu(gc_info->gc_num_gprs);
- adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->gc_num_max_gs_thds);
- adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->gc_gs_table_depth);
- adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->gc_gsprim_buff_depth);
- adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->gc_double_offchip_lds_buffer);
- adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->gc_wave_size);
- adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->gc_max_waves_per_simd);
- adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->gc_max_scratch_slots_per_cu);
- adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->gc_lds_size);
- adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->gc_num_sc_per_se) /
- le32_to_cpu(gc_info->gc_num_sa_per_se);
- adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->gc_num_packer_per_sc);
-
+ switch (gc_info->v1.header.version_major) {
+ case 1:
+ adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v1.gc_num_se);
+ adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->v1.gc_num_wgp0_per_sa) +
+ le32_to_cpu(gc_info->v1.gc_num_wgp1_per_sa));
+ adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+ adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v1.gc_num_rb_per_se);
+ adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v1.gc_num_gl2c);
+ adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v1.gc_num_gprs);
+ adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v1.gc_num_max_gs_thds);
+ adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v1.gc_gs_table_depth);
+ adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v1.gc_gsprim_buff_depth);
+ adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v1.gc_double_offchip_lds_buffer);
+ adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v1.gc_wave_size);
+ adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v1.gc_max_waves_per_simd);
+ adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v1.gc_max_scratch_slots_per_cu);
+ adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v1.gc_lds_size);
+ adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v1.gc_num_sc_per_se) /
+ le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+ adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v1.gc_num_packer_per_sc);
+ break;
+ case 2:
+ adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v2.gc_num_se);
+ adev->gfx.config.max_cu_per_sh = le32_to_cpu(gc_info->v2.gc_num_cu_per_sh);
+ adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+ adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v2.gc_num_rb_per_se);
+ adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v2.gc_num_tccs);
+ adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v2.gc_num_gprs);
+ adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v2.gc_num_max_gs_thds);
+ adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v2.gc_gs_table_depth);
+ adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v2.gc_gsprim_buff_depth);
+ adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v2.gc_double_offchip_lds_buffer);
+ adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v2.gc_wave_size);
+ adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v2.gc_max_waves_per_simd);
+ adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v2.gc_max_scratch_slots_per_cu);
+ adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v2.gc_lds_size);
+ adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) /
+ le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+ adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc);
+ break;
+ default:
+ dev_err(adev->dev,
+ "Unhandled GC info table %d.%d\n",
+ gc_info->v1.header.version_major,
+ gc_info->v1.header.version_minor);
+ return -EINVAL;
+ }
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index ae6ab93c868b..7444484a12bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -384,7 +384,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach)
struct amdgpu_vm_bo_base *bo_base;
int r;
- if (bo->tbo.resource->mem_type == TTM_PL_SYSTEM)
+ if (!bo->tbo.resource || bo->tbo.resource->mem_type == TTM_PL_SYSTEM)
return;
r = ttm_bo_validate(&bo->tbo, &placement, &ctx);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index ad95de6399af..86ca80da9eea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -328,10 +328,11 @@ module_param_named(aspm, amdgpu_aspm, int, 0444);
/**
* DOC: runpm (int)
- * Override for runtime power management control for dGPUs in PX/HG laptops. The amdgpu driver can dynamically power down
- * the dGPU on PX/HG laptops when it is idle. The default is -1 (auto enable). Setting the value to 0 disables this functionality.
+ * Override for runtime power management control for dGPUs. The amdgpu driver can dynamically power down
+ * the dGPUs when they are idle if supported. The default is -1 (auto enable).
+ * Setting the value to 0 disables this functionality.
*/
-MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = PX only default)");
+MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = auto)");
module_param_named(runpm, amdgpu_runtime_pm, int, 0444);
/**
@@ -2153,7 +2154,10 @@ static int amdgpu_pmops_suspend(struct device *dev)
adev->in_s3 = true;
r = amdgpu_device_suspend(drm_dev, true);
adev->in_s3 = false;
-
+ if (r)
+ return r;
+ if (!adev->in_s0ix)
+ r = amdgpu_asic_reset(adev);
return r;
}
@@ -2234,12 +2238,27 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
if (amdgpu_device_supports_px(drm_dev))
drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+ /*
+ * By setting mp1_state as PP_MP1_STATE_UNLOAD, MP1 will do some
+ * proper cleanups and put itself into a state ready for PNP. That
+ * can address some random resuming failure observed on BOCO capable
+ * platforms.
+ * TODO: this may be also needed for PX capable platform.
+ */
+ if (amdgpu_device_supports_boco(drm_dev))
+ adev->mp1_state = PP_MP1_STATE_UNLOAD;
+
ret = amdgpu_device_suspend(drm_dev, false);
if (ret) {
adev->in_runpm = false;
+ if (amdgpu_device_supports_boco(drm_dev))
+ adev->mp1_state = PP_MP1_STATE_NONE;
return ret;
}
+ if (amdgpu_device_supports_boco(drm_dev))
+ adev->mp1_state = PP_MP1_STATE_NONE;
+
if (amdgpu_device_supports_px(drm_dev)) {
/* Only need to handle PCI state in the driver for ATPX
* PCI core handles it for _PR3.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 3b7e86ea7167..9afd11ca2709 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -77,11 +77,13 @@ void amdgpu_fence_slab_fini(void)
* Cast helper
*/
static const struct dma_fence_ops amdgpu_fence_ops;
+static const struct dma_fence_ops amdgpu_job_fence_ops;
static inline struct amdgpu_fence *to_amdgpu_fence(struct dma_fence *f)
{
struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base);
- if (__f->base.ops == &amdgpu_fence_ops)
+ if (__f->base.ops == &amdgpu_fence_ops ||
+ __f->base.ops == &amdgpu_job_fence_ops)
return __f;
return NULL;
@@ -158,19 +160,18 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
}
seq = ++ring->fence_drv.sync_seq;
- if (job != NULL && job->job_run_counter) {
+ if (job && job->job_run_counter) {
/* reinit seq for resubmitted jobs */
fence->seqno = seq;
} else {
- dma_fence_init(fence, &amdgpu_fence_ops,
- &ring->fence_drv.lock,
- adev->fence_context + ring->idx,
- seq);
- }
-
- if (job != NULL) {
- /* mark this fence has a parent job */
- set_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &fence->flags);
+ if (job)
+ dma_fence_init(fence, &amdgpu_job_fence_ops,
+ &ring->fence_drv.lock,
+ adev->fence_context + ring->idx, seq);
+ else
+ dma_fence_init(fence, &amdgpu_fence_ops,
+ &ring->fence_drv.lock,
+ adev->fence_context + ring->idx, seq);
}
amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
@@ -621,6 +622,25 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
}
/**
+ * amdgpu_fence_driver_clear_job_fences - clear job embedded fences of ring
+ *
+ * @ring: fence of the ring to be cleared
+ *
+ */
+void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
+{
+ int i;
+ struct dma_fence *old, **ptr;
+
+ for (i = 0; i <= ring->fence_drv.num_fences_mask; i++) {
+ ptr = &ring->fence_drv.fences[i];
+ old = rcu_dereference_protected(*ptr, 1);
+ if (old && old->ops == &amdgpu_job_fence_ops)
+ RCU_INIT_POINTER(*ptr, NULL);
+ }
+}
+
+/**
* amdgpu_fence_driver_force_completion - force signal latest fence of ring
*
* @ring: fence of the ring to signal
@@ -643,16 +663,14 @@ static const char *amdgpu_fence_get_driver_name(struct dma_fence *fence)
static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
{
- struct amdgpu_ring *ring;
+ return (const char *)to_amdgpu_fence(f)->ring->name;
+}
- if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
- struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f)
+{
+ struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
- ring = to_amdgpu_ring(job->base.sched);
- } else {
- ring = to_amdgpu_fence(f)->ring;
- }
- return (const char *)ring->name;
+ return (const char *)to_amdgpu_ring(job->base.sched)->name;
}
/**
@@ -665,18 +683,25 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
*/
static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
{
- struct amdgpu_ring *ring;
+ if (!timer_pending(&to_amdgpu_fence(f)->ring->fence_drv.fallback_timer))
+ amdgpu_fence_schedule_fallback(to_amdgpu_fence(f)->ring);
- if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
- struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+ return true;
+}
- ring = to_amdgpu_ring(job->base.sched);
- } else {
- ring = to_amdgpu_fence(f)->ring;
- }
+/**
+ * amdgpu_job_fence_enable_signaling - enable signalling on job fence
+ * @f: fence
+ *
+ * This is the simliar function with amdgpu_fence_enable_signaling above, it
+ * only handles the job embedded fence.
+ */
+static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f)
+{
+ struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
- if (!timer_pending(&ring->fence_drv.fallback_timer))
- amdgpu_fence_schedule_fallback(ring);
+ if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer))
+ amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched));
return true;
}
@@ -692,19 +717,23 @@ static void amdgpu_fence_free(struct rcu_head *rcu)
{
struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
- if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
- /* free job if fence has a parent job */
- struct amdgpu_job *job;
-
- job = container_of(f, struct amdgpu_job, hw_fence);
- kfree(job);
- } else {
/* free fence_slab if it's separated fence*/
- struct amdgpu_fence *fence;
+ kmem_cache_free(amdgpu_fence_slab, to_amdgpu_fence(f));
+}
- fence = to_amdgpu_fence(f);
- kmem_cache_free(amdgpu_fence_slab, fence);
- }
+/**
+ * amdgpu_job_fence_free - free up the job with embedded fence
+ *
+ * @rcu: RCU callback head
+ *
+ * Free up the job with embedded fence after the RCU grace period.
+ */
+static void amdgpu_job_fence_free(struct rcu_head *rcu)
+{
+ struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
+
+ /* free job if fence has a parent job */
+ kfree(container_of(f, struct amdgpu_job, hw_fence));
}
/**
@@ -720,6 +749,19 @@ static void amdgpu_fence_release(struct dma_fence *f)
call_rcu(&f->rcu, amdgpu_fence_free);
}
+/**
+ * amdgpu_job_fence_release - callback that job embedded fence can be freed
+ *
+ * @f: fence
+ *
+ * This is the simliar function with amdgpu_fence_release above, it
+ * only handles the job embedded fence.
+ */
+static void amdgpu_job_fence_release(struct dma_fence *f)
+{
+ call_rcu(&f->rcu, amdgpu_job_fence_free);
+}
+
static const struct dma_fence_ops amdgpu_fence_ops = {
.get_driver_name = amdgpu_fence_get_driver_name,
.get_timeline_name = amdgpu_fence_get_timeline_name,
@@ -727,6 +769,12 @@ static const struct dma_fence_ops amdgpu_fence_ops = {
.release = amdgpu_fence_release,
};
+static const struct dma_fence_ops amdgpu_job_fence_ops = {
+ .get_driver_name = amdgpu_fence_get_driver_name,
+ .get_timeline_name = amdgpu_job_fence_get_timeline_name,
+ .enable_signaling = amdgpu_job_fence_enable_signaling,
+ .release = amdgpu_job_fence_release,
+};
/*
* Fence debugfs
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 4d380e79752c..fae7d185ad0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -53,9 +53,6 @@ enum amdgpu_ring_priority_level {
#define AMDGPU_FENCE_FLAG_INT (1 << 1)
#define AMDGPU_FENCE_FLAG_TC_WB_ONLY (1 << 2)
-/* fence flag bit to indicate the face is embedded in job*/
-#define AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT (DMA_FENCE_FLAG_USER_BITS + 1)
-
#define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
#define AMDGPU_IB_POOL_SIZE (1024 * 1024)
@@ -114,6 +111,7 @@ struct amdgpu_fence_driver {
struct dma_fence **fences;
};
+void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index b305fd39874f..edb3e3b08eed 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3070,8 +3070,8 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
AMD_PG_SUPPORT_CP |
AMD_PG_SUPPORT_GDS |
AMD_PG_SUPPORT_RLC_SMU_HS)) {
- WREG32(mmRLC_JUMP_TABLE_RESTORE,
- adev->gfx.rlc.cp_table_gpu_addr >> 8);
+ WREG32_SOC15(GC, 0, mmRLC_JUMP_TABLE_RESTORE,
+ adev->gfx.rlc.cp_table_gpu_addr >> 8);
gfx_v9_0_init_gfx_power_gating(adev);
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 480e41847d7c..ec4d5e15b766 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -162,7 +162,6 @@ static void gfxhub_v1_0_init_tlb_regs(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 14c1c1a297dd..6e0ace2fbfab 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -196,7 +196,6 @@ static void gfxhub_v2_0_init_tlb_regs(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index e80d1dc43079..b4eddf6e98a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -197,7 +197,6 @@ static void gfxhub_v2_1_init_tlb_regs(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index cb82404df534..d84523cf5f75 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1808,6 +1808,14 @@ static int gmc_v9_0_hw_fini(void *handle)
return 0;
}
+ /*
+ * Pair the operations did in gmc_v9_0_hw_init and thus maintain
+ * a correct cached state for GMC. Otherwise, the "gate" again
+ * operation on S3 resuming will fail due to wrong cached state.
+ */
+ if (adev->mmhub.funcs->update_power_gating)
+ adev->mmhub.funcs->update_power_gating(adev, false);
+
amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index a99953833820..1da2ec692057 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -145,7 +145,6 @@ static void mmhub_v1_0_init_tlb_regs(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
@@ -302,10 +301,10 @@ static void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
if (amdgpu_sriov_vf(adev))
return;
- if (enable && adev->pg_flags & AMD_PG_SUPPORT_MMHUB) {
- amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
-
- }
+ if (adev->pg_flags & AMD_PG_SUPPORT_MMHUB)
+ amdgpu_dpm_set_powergating_by_smu(adev,
+ AMD_IP_BLOCK_TYPE_GMC,
+ enable);
}
static int mmhub_v1_0_gart_enable(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
index f80a14a1b82d..f5f7181f9af5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
@@ -165,7 +165,6 @@ static void mmhub_v1_7_init_tlb_regs(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 25f8e93e5ec3..3718ff610ab2 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -267,7 +267,6 @@ static void mmhub_v2_0_init_tlb_regs(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index a11d60ec6321..9e16da28505a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
@@ -194,7 +194,6 @@ static void mmhub_v2_3_init_tlb_regs(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index c4ef822bbe8c..ff49eeaf7882 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -190,8 +190,6 @@ static void mmhub_v9_4_init_tlb_regs(struct amdgpu_device *adev, int hubid)
tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
- ECO_BITS, 0);
- tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
ATC_EN, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index d54d720b3cf6..3799226defc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -246,6 +246,13 @@ static int vcn_v1_0_suspend(void *handle)
{
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ bool idle_work_unexecuted;
+
+ idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.idle_work);
+ if (idle_work_unexecuted) {
+ if (adev->pm.dpm_enabled)
+ amdgpu_dpm_enable_uvd(adev, false);
+ }
r = vcn_v1_0_hw_fini(adev);
if (r)
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-20 14:29:09 +0300