drm/i915: Make sure we have enough memory bandwidth on ICL

ICL has so many planes that it can easily exceed the maximum
effective memory bandwidth of the system. We must therefore check
that we don't exceed that limit.

The algorithm is very magic number heavy and lacks sufficient
explanation for now. We also have no sane way to query the
memory clock and timings, so we must rely on a combination of
raw readout from the memory controller and hardcoded assumptions.
The memory controller values obviously change as the system
jumps between the different SAGV points, so we try to stabilize
it first by disabling SAGV for the duration of the readout.

The utilized bandwidth is tracked via a device wide atomic
private object. That is actually not robust because we can't
afford to enforce strict global ordering between the pipes.
Thus I think I'll need to change this to simply chop up the
available bandwidth between all the active pipes. Each pipe
can then do whatever it wants as long as it doesn't exceed
its budget. That scheme will also require that we assume that
any number of planes could be active at any time.

TODO: make it robust and deal with all the open questions

v2: Sleep longer after disabling SAGV
v3: Poll for the dclk to get raised (seen it take 250ms!)
    If the system has 2133MT/s memory then we pointlessly
    wait one full second :(
v4: Use the new pcode interface to get the qgv points rather
    that using hardcoded numbers
v5: Move the pcode stuff into intel_bw.c (Matt)
    s/intel_sagv_info/intel_qgv_info/
    Do the NV12/P010 as per spec for now (Matt)
    s/IS_ICELAKE/IS_GEN11/
v6: Ignore bandwidth limits if the pcode query fails

Signed-off-by: Ville Syrjälä <[email protected]>
Reviewed-by: Matt Roper <[email protected]>
Acked-by: Clint Taylor <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: vsyrjala

drivers/gpu/drm/i915/Makefile

@@ -138,6 +138,7 @@ i915-y += intel_audio.o \
 	  intel_atomic.o \
 	  intel_atomic_plane.o \
 	  intel_bios.o \
+	  intel_bw.o \
 	  intel_cdclk.o \
 	  intel_color.o \
 	  intel_combo_phy.o \

drivers/gpu/drm/i915/i915_drv.c

@@ -60,6 +60,7 @@
 #include "i915_vgpu.h"
 #include "intel_acpi.h"
 #include "intel_audio.h"
+#include "intel_bw.h"
 #include "intel_cdclk.h"
 #include "intel_csr.h"
 #include "intel_dp.h"
@@ -1657,6 +1658,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 	 */
 	intel_get_dram_info(dev_priv);
 
+	intel_bw_init_hw(dev_priv);
 
 	return 0;
 

drivers/gpu/drm/i915/i915_drv.h

@@ -54,6 +54,7 @@
 #include <drm/drm_cache.h>
 #include <drm/drm_util.h>
 #include <drm/drm_dsc.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_connector.h>
 #include <drm/i915_mei_hdcp_interface.h>
 
@@ -1841,6 +1842,13 @@ struct drm_i915_private {
 		} type;
 	} dram_info;
 
+	struct intel_bw_info {
+		int num_planes;
+		int deratedbw[3];
+	} max_bw[6];
+
+	struct drm_private_obj bw_obj;
+
 	struct i915_runtime_pm runtime_pm;
 
 	struct {

drivers/gpu/drm/i915/i915_reg.h

@@ -8780,6 +8780,9 @@ enum {
 #define   GEN6_PCODE_WRITE_MIN_FREQ_TABLE	0x8
 #define   GEN6_PCODE_READ_MIN_FREQ_TABLE	0x9
 #define   GEN6_READ_OC_PARAMS			0xc
+#define   ICL_PCODE_MEM_SUBSYSYSTEM_INFO	0xd
+#define     ICL_PCODE_MEM_SS_READ_GLOBAL_INFO	(0x0 << 8)
+#define     ICL_PCODE_MEM_SS_READ_QGV_POINT_INFO(point)	(((point) << 16) | (0x1 << 8))
 #define   GEN6_PCODE_READ_D_COMP		0x10
 #define   GEN6_PCODE_WRITE_D_COMP		0x11
 #define   HSW_PCODE_DE_WRITE_FREQ_REQ		0x17

drivers/gpu/drm/i915/intel_atomic_plane.c

@@ -114,6 +114,29 @@ intel_plane_destroy_state(struct drm_plane *plane,
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
 
+unsigned int intel_plane_data_rate(const struct intel_crtc_state *crtc_state,
+				   const struct intel_plane_state *plane_state)
+{
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	unsigned int cpp;
+
+	if (!plane_state->base.visible)
+		return 0;
+
+	cpp = fb->format->cpp[0];
+
+	/*
+	 * Based on HSD#:1408715493
+	 * NV12 cpp == 4, P010 cpp == 8
+	 *
+	 * FIXME what is the logic behind this?
+	 */
+	if (fb->format->is_yuv && fb->format->num_planes > 1)
+		cpp *= 4;
+
+	return cpp * crtc_state->pixel_rate;
+}
+
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *new_crtc_state,
 					const struct intel_plane_state *old_plane_state,
@@ -125,6 +148,7 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 	new_crtc_state->active_planes &= ~BIT(plane->id);
 	new_crtc_state->nv12_planes &= ~BIT(plane->id);
 	new_crtc_state->c8_planes &= ~BIT(plane->id);
+	new_crtc_state->data_rate[plane->id] = 0;
 	new_plane_state->base.visible = false;
 
 	if (!new_plane_state->base.crtc && !old_plane_state->base.crtc)
@@ -149,6 +173,9 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 	if (new_plane_state->base.visible || old_plane_state->base.visible)
 		new_crtc_state->update_planes |= BIT(plane->id);
 
+	new_crtc_state->data_rate[plane->id] =
+		intel_plane_data_rate(new_crtc_state, new_plane_state);
+
 	return intel_plane_atomic_calc_changes(old_crtc_state,
 					       &new_crtc_state->base,
 					       old_plane_state,

drivers/gpu/drm/i915/intel_atomic_plane.h

@@ -15,6 +15,8 @@ struct intel_plane_state;
 
 extern const struct drm_plane_helper_funcs intel_plane_helper_funcs;
 
+unsigned int intel_plane_data_rate(const struct intel_crtc_state *crtc_state,
+				   const struct intel_plane_state *plane_state);
 void intel_update_plane(struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);