drm/amdgpu: introduce a new parameter to configure how many KCQ we want(v5)

what:
the MQD's save and restore of KCQ (kernel compute queue)
cost lots of clocks during world switch which impacts a lot
to multi-VF performance

how:
introduce a paramter to control the number of KCQ to avoid
performance drop if there is no kernel compute queue needed

notes:
this paramter only affects gfx 8/9/10

v2:
refine namings

v3:
choose queues for each ring to that try best to cross pipes evenly.

v4:
fix indentation
some cleanupsin the gfx_compute_queue_acquire()

v5:
further fix on indentations
more cleanupsin gfx_compute_queue_acquire()

TODO:
in the future we will let hypervisor driver to set this paramter
automatically thus no need for user to configure it through
modprobe in virtual machine
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -202,6 +202,7 @@ extern int amdgpu_si_support;
 #ifdef CONFIG_DRM_AMDGPU_CIK
 extern int amdgpu_cik_support;
 #endif
+extern int amdgpu_num_kcq;
 
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -1199,6 +1199,11 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	amdgpu_gmc_tmz_set(adev);
 
+	if (amdgpu_num_kcq > 8 || amdgpu_num_kcq < 0) {
+		amdgpu_num_kcq = 8;
+		dev_warn(adev->dev, "set kernel compute queue number to 8 due to invalid paramter provided by user\n");
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -150,6 +150,7 @@ int amdgpu_noretry;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = 0;
 int amdgpu_reset_method = -1; /* auto */
+int amdgpu_num_kcq = -1;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
@@ -776,6 +777,9 @@ module_param_named(reset_method, amdgpu_reset_method, int, 0444);
 MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
 module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
 
+MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
+module_param_named(num_kcq, amdgpu_num_kcq, 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},

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c

@@ -202,40 +202,29 @@ bool amdgpu_gfx_is_high_priority_compute_queue(struct amdgpu_device *adev,
 
 void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
 {
-	int i, queue, pipe, mec;
+	int i, queue, pipe;
 	bool multipipe_policy = amdgpu_gfx_is_multipipe_capable(adev);
-
-	/* policy for amdgpu compute queue ownership */
-	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
-		queue = i % adev->gfx.mec.num_queue_per_pipe;
-		pipe = (i / adev->gfx.mec.num_queue_per_pipe)
-			% adev->gfx.mec.num_pipe_per_mec;
-		mec = (i / adev->gfx.mec.num_queue_per_pipe)
-			/ adev->gfx.mec.num_pipe_per_mec;
-
-		/* we've run out of HW */
-		if (mec >= adev->gfx.mec.num_mec)
-			break;
-
-		if (multipipe_policy) {
-			/* policy: amdgpu owns the first two queues of the first MEC */
-			if (mec == 0 && queue < 2)
-				set_bit(i, adev->gfx.mec.queue_bitmap);
-		} else {
-			/* policy: amdgpu owns all queues in the first pipe */
-			if (mec == 0 && pipe == 0)
-				set_bit(i, adev->gfx.mec.queue_bitmap);
+	int max_queues_per_mec = min(adev->gfx.mec.num_pipe_per_mec *
+				     adev->gfx.mec.num_queue_per_pipe,
+				     adev->gfx.num_compute_rings);
+
+	if (multipipe_policy) {
+		/* policy: make queues evenly cross all pipes on MEC1 only */
+		for (i = 0; i < max_queues_per_mec; i++) {
+			pipe = i % adev->gfx.mec.num_pipe_per_mec;
+			queue = (i / adev->gfx.mec.num_pipe_per_mec) %
+				adev->gfx.mec.num_queue_per_pipe;
+
+			set_bit(pipe * adev->gfx.mec.num_queue_per_pipe + queue,
+					adev->gfx.mec.queue_bitmap);
 		}
+	} else {
+		/* policy: amdgpu owns all queues in the given pipe */
+		for (i = 0; i < max_queues_per_mec; ++i)
+			set_bit(i, adev->gfx.mec.queue_bitmap);
 	}
 
-	/* update the number of active compute rings */
-	adev->gfx.num_compute_rings =
-		bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
-
-	/* If you hit this case and edited the policy, you probably just
-	 * need to increase AMDGPU_MAX_COMPUTE_RINGS */
-	if (WARN_ON(adev->gfx.num_compute_rings > AMDGPU_MAX_COMPUTE_RINGS))
-		adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	dev_dbg(adev->dev, "mec queue bitmap weight=%d\n", bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES));
 }
 
 void amdgpu_gfx_graphics_queue_acquire(struct amdgpu_device *adev)

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -4022,21 +4022,23 @@ static int gfx_v10_0_mec_init(struct amdgpu_device *adev)
 	amdgpu_gfx_compute_queue_acquire(adev);
 	mec_hpd_size = adev->gfx.num_compute_rings * GFX10_MEC_HPD_SIZE;
 
-	r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_GTT,
-				      &adev->gfx.mec.hpd_eop_obj,
-				      &adev->gfx.mec.hpd_eop_gpu_addr,
-				      (void **)&hpd);
-	if (r) {
-		dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
-		gfx_v10_0_mec_fini(adev);
-		return r;
-	}
+	if (mec_hpd_size) {
+		r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_GTT,
+					      &adev->gfx.mec.hpd_eop_obj,
+					      &adev->gfx.mec.hpd_eop_gpu_addr,
+					      (void **)&hpd);
+		if (r) {
+			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
+			gfx_v10_0_mec_fini(adev);
+			return r;
+		}
 
-	memset(hpd, 0, mec_hpd_size);
+		memset(hpd, 0, mec_hpd_size);
 
-	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
-	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+	}
 
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
 		mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
@@ -7159,7 +7161,7 @@ static int gfx_v10_0_early_init(void *handle)
 		break;
 	}
 
-	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	adev->gfx.num_compute_rings = amdgpu_num_kcq;
 
 	gfx_v10_0_set_kiq_pm4_funcs(adev);
 	gfx_v10_0_set_ring_funcs(adev);

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -1343,21 +1343,22 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 	amdgpu_gfx_compute_queue_acquire(adev);
 
 	mec_hpd_size = adev->gfx.num_compute_rings * GFX8_MEC_HPD_SIZE;
+	if (mec_hpd_size) {
+		r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_VRAM,
+					      &adev->gfx.mec.hpd_eop_obj,
+					      &adev->gfx.mec.hpd_eop_gpu_addr,
+					      (void **)&hpd);
+		if (r) {
+			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
+			return r;
+		}
 
-	r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &adev->gfx.mec.hpd_eop_obj,
-				      &adev->gfx.mec.hpd_eop_gpu_addr,
-				      (void **)&hpd);
-	if (r) {
-		dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
-		return r;
-	}
-
-	memset(hpd, 0, mec_hpd_size);
+		memset(hpd, 0, mec_hpd_size);
 
-	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
-	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+	}
 
 	return 0;
 }
@@ -5294,7 +5295,7 @@ static int gfx_v8_0_early_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	adev->gfx.num_gfx_rings = GFX8_NUM_GFX_RINGS;
-	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	adev->gfx.num_compute_rings = amdgpu_num_kcq;
 	adev->gfx.funcs = &gfx_v8_0_gfx_funcs;
 	gfx_v8_0_set_ring_funcs(adev);
 	gfx_v8_0_set_irq_funcs(adev);

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -1938,22 +1938,23 @@ static int gfx_v9_0_mec_init(struct amdgpu_device *adev)
 	/* take ownership of the relevant compute queues */
 	amdgpu_gfx_compute_queue_acquire(adev);
 	mec_hpd_size = adev->gfx.num_compute_rings * GFX9_MEC_HPD_SIZE;
+	if (mec_hpd_size) {
+		r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_VRAM,
+					      &adev->gfx.mec.hpd_eop_obj,
+					      &adev->gfx.mec.hpd_eop_gpu_addr,
+					      (void **)&hpd);
+		if (r) {
+			dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
+			gfx_v9_0_mec_fini(adev);
+			return r;
+		}
 
-	r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &adev->gfx.mec.hpd_eop_obj,
-				      &adev->gfx.mec.hpd_eop_gpu_addr,
-				      (void **)&hpd);
-	if (r) {
-		dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
-		gfx_v9_0_mec_fini(adev);
-		return r;
-	}
-
-	memset(hpd, 0, mec_hpd_size);
+		memset(hpd, 0, mec_hpd_size);
 
-	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
-	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
+		amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+	}
 
 	mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
 
@@ -4625,7 +4626,7 @@ static int gfx_v9_0_early_init(void *handle)
 		adev->gfx.num_gfx_rings = 0;
 	else
 		adev->gfx.num_gfx_rings = GFX9_NUM_GFX_RINGS;
-	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	adev->gfx.num_compute_rings = amdgpu_num_kcq;
 	gfx_v9_0_set_kiq_pm4_funcs(adev);
 	gfx_v9_0_set_ring_funcs(adev);
 	gfx_v9_0_set_irq_funcs(adev);