Merge tag 'amd-drm-next-5.8-2020-04-30' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-next-5.8-2020-04-30:

amdgpu:
- SR-IOV fixes
- SDMA fix for Navi
- VCN 2.5 DPG fixes
- Display fixes
- Display stuttering fixes for pageflip and cursor
- Add support for handling encrypted GPU memory
- Add UAPI for encrypted GPU memory
- Rework IB pool handling

amdkfd:
- Expose asic revision in topology
- Add UAPI for GWS (Global Wave Sync) resource management

UAPI:
- Add amdgpu UAPI for encrypted GPU memory
  Used by: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401
- Add amdkfd UAPI for GWS (Global Wave Sync) resource management
  Thunk usage of KFD ioctl: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/blob/roc-2.8.0/src/queues.c#L840
  ROCr usage of Thunk API: https://github.com/RadeonOpenCompute/ROCR-Runtime/blob/roc-3.1.0/src/core/runtime/amd_gpu_agent.cpp#L597
  HCC code using ROCr API: https://github.com/RadeonOpenCompute/hcc/blob/98ee9f34945d3b5f572d7a4c15cbffa506487734/lib/hsa/mcwamp_hsa.cpp#L2161
  HIP code using HCC API: https://github.com/ROCm-Developer-Tools/HIP/blob/cf8589b8c8a40ddcc55fa3a51e23390a49824130/src/hip_module.cpp#L567

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200430212951.3902-1-alexander.deucher@amd.com

52 files changed, 739 insertions, 354 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 56da8920195d..99e5f474505d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -189,6 +189,8 @@ extern int sched_policy;
 static const int sched_policy = KFD_SCHED_POLICY_HWS;
 #endif
 
+extern int amdgpu_tmz;
+
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;
 #endif
@@ -202,8 +204,6 @@ extern int amdgpu_cik_support;
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
 #define AMDGPU_FENCE_JIFFIES_TIMEOUT		(HZ / 2)
-/* AMDGPU_IB_POOL_SIZE must be a power of 2 */
-#define AMDGPU_IB_POOL_SIZE			16
 #define AMDGPU_DEBUGFS_MAX_COMPONENTS		32
 #define AMDGPUFB_CONN_LIMIT			4
 #define AMDGPU_BIOS_NUM_SCRATCH			16
@@ -400,13 +400,6 @@ struct amdgpu_sa_bo {
 int amdgpu_fence_slab_init(void);
 void amdgpu_fence_slab_fini(void);
 
-enum amdgpu_ib_pool_type {
-	AMDGPU_IB_POOL_NORMAL = 0,
-	AMDGPU_IB_POOL_VM,
-	AMDGPU_IB_POOL_DIRECT,
-
-	AMDGPU_IB_POOL_MAX
-};
 /*
  * IRQS.
  */
@@ -864,7 +857,7 @@ struct amdgpu_device {
 	unsigned			num_rings;
 	struct amdgpu_ring		*rings[AMDGPU_MAX_RINGS];
 	bool				ib_pool_ready;
-	struct amdgpu_sa_manager	ring_tmp_bo[AMDGPU_IB_POOL_MAX];
+	struct amdgpu_sa_manager	ib_pools[AMDGPU_IB_POOL_MAX];
 	struct amdgpu_sched		gpu_sched[AMDGPU_HW_IP_NUM][AMDGPU_RING_PRIO_MAX];
 
 	/* interrupts */
@@ -945,7 +938,7 @@ struct amdgpu_device {
 	atomic64_t gart_pin_size;
 
 	/* soc15 register offset based on ip, instance and  segment */
-	uint32_t 		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
+	uint32_t		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
 
 	/* delayed work_func for deferring clockgating during resume */
 	struct delayed_work     delayed_init_work;
@@ -1263,5 +1256,9 @@ _name##_show(struct device *dev,					\
 									\
 static struct device_attribute pmu_attr_##_name = __ATTR_RO(_name)
 
-#endif
+static inline bool amdgpu_is_tmz(struct amdgpu_device *adev)
+{
+       return adev->gmc.tmz_enabled;
+}
 
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index abfbe89e805e..ad59ac4423b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -564,6 +564,13 @@ uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd)
 	return adev->gds.gws_size;
 }
 
+uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	return adev->rev_id;
+}
+
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 13feb313e9b3..d065c50582eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -175,6 +175,7 @@ uint64_t amdgpu_amdkfd_get_hive_id(struct kgd_dev *kgd);
 uint64_t amdgpu_amdkfd_get_unique_id(struct kgd_dev *kgd);
 uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
+uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);
 uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);
 
 /* Read user wptr from a specified user address space with page fault
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index d1495e1c9289..d9b35df33806 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -40,7 +40,7 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
 	for (i = 0; i < n; i++) {
 		struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 		r = amdgpu_copy_buffer(ring, saddr, daddr, size, NULL, &fence,
-				       false, false);
+				       false, false, false);
 		if (r)
 			goto exit_do_move;
 		r = dma_fence_wait(fence, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 3eee5c7d83e0..7653f62b1b2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -924,7 +924,8 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 
 		ring = to_amdgpu_ring(entity->rq->sched);
 		r =  amdgpu_ib_get(adev, vm, ring->funcs->parse_cs ?
-				   chunk_ib->ib_bytes : 0, AMDGPU_IB_POOL_NORMAL, ib);
+				   chunk_ib->ib_bytes : 0,
+				   AMDGPU_IB_POOL_DELAYED, ib);
 		if (r) {
 			DRM_ERROR("Failed to get ib !\n");
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f9b315e7e004..b038ddbb2ece 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1140,6 +1140,8 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
+	amdgpu_gmc_tmz_set(adev);
+
 	return 0;
 }
 
@@ -2998,7 +3000,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	INIT_WORK(&adev->xgmi_reset_work, amdgpu_device_xgmi_reset_func);
 
 	adev->gfx.gfx_off_req_count = 1;
-	adev->pm.ac_power = power_supply_is_system_supplied() > 0 ? true : false;
+	adev->pm.ac_power = power_supply_is_system_supplied() > 0;
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
@@ -3432,15 +3434,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		}
 	}
 
-	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
-	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
-
-	amdgpu_amdkfd_suspend(adev, !fbcon);
-
 	amdgpu_ras_suspend(adev);
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
 
+	amdgpu_amdkfd_suspend(adev, !fbcon);
+
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 8ea86ffdea0d..719a963c31a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -85,9 +85,10 @@
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
  * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
  * - 3.36.0 - Allow reading more status registers on si/cik
+ * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	36
+#define KMS_DRIVER_MINOR	37
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -144,6 +145,7 @@ int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
 int amdgpu_noretry;
 int amdgpu_force_asic_type = -1;
+int amdgpu_tmz = 0;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
@@ -687,13 +689,12 @@ MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (defau
 
 /**
  * DOC: hws_gws_support(bool)
- * Whether HWS support gws barriers. Default value: false (not supported)
- * This will be replaced with a MEC firmware version check once firmware
- * is ready
+ * Assume that HWS supports GWS barriers regardless of what firmware version
+ * check says. Default value: false (rely on MEC2 firmware version check).
  */
 bool hws_gws_support;
 module_param(hws_gws_support, bool, 0444);
-MODULE_PARM_DESC(hws_gws_support, "MEC FW support gws barriers (false = not supported (Default), true = supported)");
+MODULE_PARM_DESC(hws_gws_support, "Assume MEC2 FW supports GWS barriers (false = rely on FW version check (Default), true = force supported)");
 
 /**
   * DOC: queue_preemption_timeout_ms (int)
@@ -728,6 +729,16 @@ uint amdgpu_dm_abm_level = 0;
 MODULE_PARM_DESC(abmlevel, "ABM level (0 = off (default), 1-4 = backlight reduction level) ");
 module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444);
 
+/**
+ * DOC: tmz (int)
+ * Trusted Memory Zone (TMZ) is a method to protect data being written
+ * to or read from memory.
+ *
+ * The default value: 0 (off).  TODO: change to auto till it is completed.
+ */
+MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto, 0 = off (default), 1 = on)");
+module_param_named(tmz, amdgpu_tmz, int, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 7531527067df..d878fe7fee51 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -192,14 +192,22 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
  * Used For polling fence.
  * Returns 0 on success, -ENOMEM on failure.
  */
-int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s)
+int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,
+			      uint32_t timeout)
 {
 	uint32_t seq;
+	signed long r;
 
 	if (!s)
 		return -EINVAL;
 
 	seq = ++ring->fence_drv.sync_seq;
+	r = amdgpu_fence_wait_polling(ring,
+				      seq - ring->fence_drv.num_fences_mask,
+				      timeout);
+	if (r < 1)
+		return -ETIMEDOUT;
+
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, 0);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 245aec521388..4ed9958af94e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -234,7 +234,8 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 		      AMDGPU_GEM_CREATE_CPU_GTT_USWC |
 		      AMDGPU_GEM_CREATE_VRAM_CLEARED |
 		      AMDGPU_GEM_CREATE_VM_ALWAYS_VALID |
-		      AMDGPU_GEM_CREATE_EXPLICIT_SYNC))
+		      AMDGPU_GEM_CREATE_EXPLICIT_SYNC |
+		      AMDGPU_GEM_CREATE_ENCRYPTED))
 
 		return -EINVAL;
 
@@ -242,6 +243,11 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	if (args->in.domains & ~AMDGPU_GEM_DOMAIN_MASK)
 		return -EINVAL;
 
+	if (!amdgpu_is_tmz(adev) && (flags & AMDGPU_GEM_CREATE_ENCRYPTED)) {
+		DRM_NOTE_ONCE("Cannot allocate secure buffer since TMZ is disabled\n");
+		return -EINVAL;
+	}
+
 	/* create a gem object to contain this object in */
 	if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
 	    AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index a721b0e0ff69..0103acc57474 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -675,13 +675,15 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 	if (amdgpu_device_wb_get(adev, &reg_val_offs)) {
-		spin_unlock_irqrestore(&kiq->ring_lock, flags);
 		pr_err("critical bug! too many kiq readers\n");
-		goto failed_kiq_read;
+		goto failed_unlock;
 	}
 	amdgpu_ring_alloc(ring, 32);
 	amdgpu_ring_emit_rreg(ring, reg, reg_val_offs);
-	amdgpu_fence_emit_polling(ring, &seq);
+	r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+	if (r)
+		goto failed_undo;
+
 	amdgpu_ring_commit(ring);
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
@@ -712,7 +714,13 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 	amdgpu_device_wb_free(adev, reg_val_offs);
 	return value;
 
+failed_undo:
+	amdgpu_ring_undo(ring);
+failed_unlock:
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq_read:
+	if (reg_val_offs)
+		amdgpu_device_wb_free(adev, reg_val_offs);
 	pr_err("failed to read reg:%x\n", reg);
 	return ~0;
 }
@@ -730,7 +738,10 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 	amdgpu_ring_alloc(ring, 32);
 	amdgpu_ring_emit_wreg(ring, reg, v);
-	amdgpu_fence_emit_polling(ring, &seq);
+	r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+	if (r)
+		goto failed_undo;
+
 	amdgpu_ring_commit(ring);
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
@@ -759,6 +770,9 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 
 	return;
 
+failed_undo:
+	amdgpu_ring_undo(ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq_write:
 	pr_err("failed to write reg:%x\n", reg);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index a8ca808f453b..acabb57aa8af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -373,3 +373,38 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 
 	return 0;
 }
+
+/**
+ * amdgpu_tmz_set -- check and set if a device supports TMZ
+ * @adev: amdgpu_device pointer
+ *
+ * Check and set if an the device @adev supports Trusted Memory
+ * Zones (TMZ).
+ */
+void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_RAVEN:
+	case CHIP_RENOIR:
+	case CHIP_NAVI10:
+	case CHIP_NAVI14:
+	case CHIP_NAVI12:
+		/* Don't enable it by default yet.
+		 */
+		if (amdgpu_tmz < 1) {
+			adev->gmc.tmz_enabled = false;
+			dev_info(adev->dev,
+				 "Trusted Memory Zone (TMZ) feature disabled as experimental (default)\n");
+		} else {
+			adev->gmc.tmz_enabled = true;
+			dev_info(adev->dev,
+				 "Trusted Memory Zone (TMZ) feature enabled as experimental (cmd line)\n");
+		}
+		break;
+	default:
+		adev->gmc.tmz_enabled = false;
+		dev_warn(adev->dev,
+			 "Trusted Memory Zone (TMZ) feature not supported\n");
+		break;
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 7546da0cc70c..2bd9423c1dab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -213,6 +213,8 @@ struct amdgpu_gmc {
 	} fault_hash[AMDGPU_GMC_FAULT_HASH_SIZE];
 	uint64_t		last_fault:AMDGPU_GMC_FAULT_RING_ORDER;
 
+	bool tmz_enabled;
+
 	const struct amdgpu_gmc_funcs	*gmc_funcs;
 
 	struct amdgpu_xgmi xgmi;
@@ -276,4 +278,6 @@ int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev);
 void amdgpu_gmc_ras_fini(struct amdgpu_device *adev);
 int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev);
 
+extern void amdgpu_gmc_tmz_set(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 1adaac972190..c24366aacf3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -61,14 +61,13 @@
  * Returns 0 on success, error on failure.
  */
 int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		unsigned size,
-		enum amdgpu_ib_pool_type pool_type,
-		struct amdgpu_ib *ib)
+		  unsigned size, enum amdgpu_ib_pool_type pool_type,
+		  struct amdgpu_ib *ib)
 {
 	int r;
 
 	if (size) {
-		r = amdgpu_sa_bo_new(&adev->ring_tmp_bo[pool_type],
+		r = amdgpu_sa_bo_new(&adev->ib_pools[pool_type],
 				      &ib->sa_bo, size, 256);
 		if (r) {
 			dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
@@ -133,6 +132,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	uint64_t fence_ctx;
 	uint32_t status = 0, alloc_size;
 	unsigned fence_flags = 0;
+	bool secure;
 
 	unsigned i;
 	int r = 0;
@@ -161,6 +161,12 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		return -EINVAL;
 	}
 
+	if ((ib->flags & AMDGPU_IB_FLAGS_SECURE) &&
+	    (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)) {
+		dev_err(adev->dev, "secure submissions not supported on compute rings\n");
+		return -EINVAL;
+	}
+
 	alloc_size = ring->funcs->emit_frame_size + num_ibs *
 		ring->funcs->emit_ib_size;
 
@@ -217,6 +223,14 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		amdgpu_ring_emit_cntxcntl(ring, status);
 	}
 
+	/* Setup initial TMZiness and send it off.
+	 */
+	secure = false;
+	if (job && ring->funcs->emit_frame_cntl) {
+		secure = ib->flags & AMDGPU_IB_FLAGS_SECURE;
+		amdgpu_ring_emit_frame_cntl(ring, true, secure);
+	}
+
 	for (i = 0; i < num_ibs; ++i) {
 		ib = &ibs[i];
 
@@ -228,12 +242,20 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		    !amdgpu_sriov_vf(adev)) /* for SRIOV preemption, Preamble CE ib must be inserted anyway */
 			continue;
 
+		if (job && ring->funcs->emit_frame_cntl) {
+			if (secure != !!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) {
+				amdgpu_ring_emit_frame_cntl(ring, false, secure);
+				secure = !secure;
+				amdgpu_ring_emit_frame_cntl(ring, true, secure);
+			}
+		}
+
 		amdgpu_ring_emit_ib(ring, job, ib, status);
 		status &= ~AMDGPU_HAVE_CTX_SWITCH;
 	}
 
-	if (ring->funcs->emit_tmz)
-		amdgpu_ring_emit_tmz(ring, false);
+	if (job && ring->funcs->emit_frame_cntl)
+		amdgpu_ring_emit_frame_cntl(ring, false, secure);
 
 #ifdef CONFIG_X86_64
 	if (!(adev->flags & AMD_IS_APU))
@@ -282,30 +304,32 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
  */
 int amdgpu_ib_pool_init(struct amdgpu_device *adev)
 {
-	int r, i;
 	unsigned size;
+	int r, i;
 
-	if (adev->ib_pool_ready) {
+	if (adev->ib_pool_ready)
 		return 0;
-	}
+
 	for (i = 0; i < AMDGPU_IB_POOL_MAX; i++) {
 		if (i == AMDGPU_IB_POOL_DIRECT)
 			size = PAGE_SIZE * 2;
 		else
-			size = AMDGPU_IB_POOL_SIZE*64*1024;
-		r = amdgpu_sa_bo_manager_init(adev, &adev->ring_tmp_bo[i],
-				size,
-				AMDGPU_GPU_PAGE_SIZE,
-				AMDGPU_GEM_DOMAIN_GTT);
-		if (r) {
-			for (i--; i >= 0; i--)
-				amdgpu_sa_bo_manager_fini(adev, &adev->ring_tmp_bo[i]);
-			return r;
-		}
+			size = AMDGPU_IB_POOL_SIZE;
+
+		r = amdgpu_sa_bo_manager_init(adev, &adev->ib_pools[i],
+					      size, AMDGPU_GPU_PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_GTT);
+		if (r)
+			goto error;
 	}
 	adev->ib_pool_ready = true;
 
 	return 0;
+
+error:
+	while (i--)
+		amdgpu_sa_bo_manager_fini(adev, &adev->ib_pools[i]);
+	return r;
 }
 
 /**
@@ -320,11 +344,12 @@ void amdgpu_ib_pool_fini(struct amdgpu_device *adev)
 {
 	int i;
 
-	if (adev->ib_pool_ready) {
-		for (i = 0; i < AMDGPU_IB_POOL_MAX; i++)
-			amdgpu_sa_bo_manager_fini(adev, &adev->ring_tmp_bo[i]);
-		adev->ib_pool_ready = false;
-	}
+	if (!adev->ib_pool_ready)
+		return;
+
+	for (i = 0; i < AMDGPU_IB_POOL_MAX; i++)
+		amdgpu_sa_bo_manager_fini(adev, &adev-&g