Merge tag 'drm-fixes-2020-06-19' of git://anongit.freedesktop.org/drm…

…/drm

Pull drm fixes from Dave Airlie:
 "Just i915 and amd here.

  i915 has some workaround movement so they get applied at the right
  times, and a timeslicing fix, along with some display fixes.

  AMD has a few display floating point fix and a devcgroup fix for
  amdkfd.

  i915:
   - Fix for timeslicing and virtual engines/unpremptable requests (+ 1
     dependency patch)
   - Fixes into TypeC register programming and interrupt storm detecting
   - Disable DIP on MST ports with the transcoder clock still on
   - Avoid missing GT workarounds at reset for HSW and older gens
   - Fix for unwinding multiple requests missing force restore
   - Fix encoder type check for DDI vswing sequence
   - Build warning fixes

  amdgpu:
   - Fix kvfree/kfree mixup
   - Fix hawaii device id in powertune configuration
   - Display FP fixes
   - Documentation fixes

  amdkfd:
   - devcgroup check fix"

* tag 'drm-fixes-2020-06-19' of git://anongit.freedesktop.org/drm/drm: (23 commits)
  drm/amdgpu: fix documentation around busy_percentage
  drm/amdgpu/pm: update comment to clarify Overdrive interfaces
  drm/amdkfd: Use correct major in devcgroup check
  drm/i915/display: Fix the encoder type check
  drm/i915/icl+: Fix hotplug interrupt disabling after storm detection
  drm/i915/gt: Move gen4 GT workarounds from init_clock_gating to workarounds
  drm/i915/gt: Move ilk GT workarounds from init_clock_gating to workarounds
  drm/i915/gt: Move snb GT workarounds from init_clock_gating to workarounds
  drm/i915/gt: Move vlv GT workarounds from init_clock_gating to workarounds
  drm/i915/gt: Move ivb GT workarounds from init_clock_gating to workarounds
  drm/i915/gt: Move hsw GT workarounds from init_clock_gating to workarounds
  drm/i915/icl: Disable DIP on MST ports with the transcoder clock still on
  drm/i915/gt: Incrementally check for rewinding
  drm/i915/tc: fix the reset of ln0
  drm/i915/gt: Prevent timeslicing into unpreemptable requests
  drm/i915/selftests: Restore to default heartbeat
  drm/i915: work around false-positive maybe-uninitialized warning
  drm/i915/pmu: avoid an maybe-uninitialized warning
  drm/i915/gt: Incorporate the virtual engine into timeslicing
  drm/amd/display: Rework dsc to isolate FPU operations
  ...

Documentation/gpu/amdgpu.rst

@@ -197,11 +197,14 @@ pp_power_profile_mode
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
    :doc: pp_power_profile_mode
 
-busy_percent
-~~~~~~~~~~~~
+*_busy_percent
+~~~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
-   :doc: busy_percent
+   :doc: gpu_busy_percent
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: mem_busy_percent
 
 GPU Product Information
 =======================

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

@@ -696,7 +696,7 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
  * default power levels, write "r" (reset) to the file to reset them.
  *
  *
- * < For Vega20 >
+ * < For Vega20 and newer ASICs >
  *
  * Reading the file will display:
  *
@@ -1668,7 +1668,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 }
 
 /**
- * DOC: busy_percent
+ * DOC: gpu_busy_percent
  *
  * The amdgpu driver provides a sysfs API for reading how busy the GPU
  * is as a percentage.  The file gpu_busy_percent is used for this.

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -40,6 +40,7 @@
 #include <drm/drm_file.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_device.h>
+#include <drm/drm_ioctl.h>
 #include <kgd_kfd_interface.h>
 #include <linux/swap.h>
 
@@ -1076,7 +1077,7 @@ static inline int kfd_devcgroup_check_permission(struct kfd_dev *kfd)
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
 	struct drm_device *ddev = kfd->ddev;
 
-	return devcgroup_check_permission(DEVCG_DEV_CHAR, ddev->driver->major,
+	return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR,
 					  ddev->render->index,
 					  DEVCG_ACC_WRITE | DEVCG_ACC_READ);
 #else

drivers/gpu/drm/amd/display/dc/dsc/Makefile

@@ -28,8 +28,6 @@ endif
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dsc/dc_dsc.o := $(dsc_ccflags)
 
 DSC = dc_dsc.o rc_calc.o rc_calc_dpi.o
 

drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c

@@ -22,10 +22,12 @@
  * Author: AMD
  */
 
+#include <drm/drm_dsc.h>
 #include "dc_hw_types.h"
 #include "dsc.h"
 #include <drm/drm_dp_helper.h>
 #include "dc.h"
+#include "rc_calc.h"
 
 /* This module's internal functions */
 
@@ -304,22 +306,6 @@ static inline uint32_t dsc_div_by_10_round_up(uint32_t value)
 	return (value + 9) / 10;
 }
 
-static inline uint32_t calc_dsc_bpp_x16(uint32_t stream_bandwidth_kbps, uint32_t pix_clk_100hz, uint32_t bpp_increment_div)
-{
-	uint32_t dsc_target_bpp_x16;
-	float f_dsc_target_bpp;
-	float f_stream_bandwidth_100bps = stream_bandwidth_kbps * 10.0f;
-	uint32_t precision = bpp_increment_div; // bpp_increment_div is actually precision
-
-	f_dsc_target_bpp = f_stream_bandwidth_100bps / pix_clk_100hz;
-
-	// Round down to the nearest precision stop to bring it into DSC spec range
-	dsc_target_bpp_x16 = (uint32_t)(f_dsc_target_bpp * precision);
-	dsc_target_bpp_x16 = (dsc_target_bpp_x16 * 16) / precision;
-
-	return dsc_target_bpp_x16;
-}
-
 /* Get DSC bandwidth range based on [min_bpp, max_bpp] target bitrate range, and timing's pixel clock
  * and uncompressed bandwidth.
  */

drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c

@@ -23,6 +23,7 @@
  * Authors: AMD
  *
  */
+#include <drm/drm_dsc.h>
 
 #include "os_types.h"
 #include "rc_calc.h"
@@ -40,7 +41,8 @@
 	break
 
 
-void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, enum max_min max_min, float bpp)
+static void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc,
+		       enum max_min max_min, float bpp)
 {
 	int mode = MODE_SELECT(444, 422, 420);
 	int sel = table_hash(mode, bpc, max_min);
@@ -85,7 +87,7 @@ void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, enum ma
 	memcpy(qps, table[index].qps, sizeof(qp_set));
 }
 
-double dsc_roundf(double num)
+static double dsc_roundf(double num)
 {
 	if (num < 0.0)
 		num = num - 0.5;
@@ -95,7 +97,7 @@ double dsc_roundf(double num)
 	return (int)(num);
 }
 
-double dsc_ceil(double num)
+static double dsc_ceil(double num)
 {
 	double retval = (int)num;
 
@@ -105,7 +107,7 @@ double dsc_ceil(double num)
 	return (int)retval;
 }
 
-void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
+static void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
 {
 	int   *p = ofs;
 
@@ -160,7 +162,7 @@ void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
 	}
 }
 
-int median3(int a, int b, int c)
+static int median3(int a, int b, int c)
 {
 	if (a > b)
 		swap(a, b);
@@ -172,13 +174,25 @@ int median3(int a, int b, int c)
 	return b;
 }
 
-void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_comp bpc, float bpp, int slice_width, int slice_height, int minor_version)
+static void _do_calc_rc_params(struct rc_params *rc, enum colour_mode cm,
+			       enum bits_per_comp bpc, u8 drm_bpp,
+			       bool is_navite_422_or_420,
+			       int slice_width, int slice_height,
+			       int minor_version)
 {
+	float bpp;
 	float bpp_group;
 	float initial_xmit_delay_factor;
 	int padding_pixels;
 	int i;
 
+	bpp = ((float)drm_bpp / 16.0);
+	/* in native_422 or native_420 modes, the bits_per_pixel is double the
+	 * target bpp (the latter is what calc_rc_params expects)
+	 */
+	if (is_navite_422_or_420)
+		bpp /= 2.0;
+
 	rc->rc_quant_incr_limit0 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 	rc->rc_quant_incr_limit1 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 
@@ -251,3 +265,128 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 	rc->rc_buf_thresh[13] = 8064;
 }
 
+static u32 _do_bytes_per_pixel_calc(int slice_width, u8 drm_bpp,
+				    bool is_navite_422_or_420)
+{
+	float bpp;
+	u32 bytes_per_pixel;
+	double d_bytes_per_pixel;
+
+	bpp = ((float)drm_bpp / 16.0);
+	d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width;
+	// TODO: Make sure the formula for calculating this is precise (ceiling
+	// vs. floor, and at what point they should be applied)
+	if (is_navite_422_or_420)
+		d_bytes_per_pixel /= 2;
+
+	bytes_per_pixel = (u32)dsc_ceil(d_bytes_per_pixel * 0x10000000);
+
+	return bytes_per_pixel;
+}
+
+static u32 _do_calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+				u32 bpp_increment_div)
+{
+	u32 dsc_target_bpp_x16;
+	float f_dsc_target_bpp;
+	float f_stream_bandwidth_100bps;
+	// bpp_increment_div is actually precision
+	u32 precision = bpp_increment_div;
+
+	f_stream_bandwidth_100bps = stream_bandwidth_kbps * 10.0f;
+	f_dsc_target_bpp = f_stream_bandwidth_100bps / pix_clk_100hz;
+
+	// Round down to the nearest precision stop to bring it into DSC spec
+	// range
+	dsc_target_bpp_x16 = (u32)(f_dsc_target_bpp * precision);
+	dsc_target_bpp_x16 = (dsc_target_bpp_x16 * 16) / precision;
+
+	return dsc_target_bpp_x16;
+}
+
+/**
+ * calc_rc_params - reads the user's cmdline mode
+ * @rc: DC internal DSC parameters
+ * @pps: DRM struct with all required DSC values
+ *
+ * This function expects a drm_dsc_config data struct with all the required DSC
+ * values previously filled out by our driver and based on this information it
+ * computes some of the DSC values.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ */
+void calc_rc_params(struct rc_params *rc, const struct drm_dsc_config *pps)
+{
+	enum colour_mode mode;
+	enum bits_per_comp bpc;
+	bool is_navite_422_or_420;
+	u8 drm_bpp = pps->bits_per_pixel;
+	int slice_width  = pps->slice_width;
+	int slice_height = pps->slice_height;
+
+	mode = pps->convert_rgb ? CM_RGB : (pps->simple_422  ? CM_444 :
+					   (pps->native_422  ? CM_422 :
+					    pps->native_420  ? CM_420 : CM_444));
+	bpc = (pps->bits_per_component == 8) ? BPC_8 : (pps->bits_per_component == 10)
+					     ? BPC_10 : BPC_12;
+
+	is_navite_422_or_420 = pps->native_422 || pps->native_420;
+
+	DC_FP_START();
+	_do_calc_rc_params(rc, mode, bpc, drm_bpp, is_navite_422_or_420,
+			   slice_width, slice_height,
+			   pps->dsc_version_minor);
+	DC_FP_END();
+}
+
+/**
+ * calc_dsc_bytes_per_pixel - calculate bytes per pixel
+ * @pps: DRM struct with all required DSC values
+ *
+ * Based on the information inside drm_dsc_config, this function calculates the
+ * total of bytes per pixel.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ *
+ * Return:
+ * Return the number of bytes per pixel
+ */
+u32 calc_dsc_bytes_per_pixel(const struct drm_dsc_config *pps)
+
+{
+	u32 ret;
+	u8 drm_bpp = pps->bits_per_pixel;
+	int slice_width  = pps->slice_width;
+	bool is_navite_422_or_420 = pps->native_422 || pps->native_420;
+
+	DC_FP_START();
+	ret = _do_bytes_per_pixel_calc(slice_width, drm_bpp,
+				       is_navite_422_or_420);
+	DC_FP_END();
+	return ret;
+}
+
+/**
+ * calc_dsc_bpp_x16 - retrieve the dsc bits per pixel
+ * @stream_bandwidth_kbps:
+ * @pix_clk_100hz:
+ * @bpp_increment_div:
+ *
+ * Calculate the total of bits per pixel for DSC configuration.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ */
+u32 calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+		     u32 bpp_increment_div)
+{
+	u32 dsc_bpp;
+
+	DC_FP_START();
+	dsc_bpp =  _do_calc_dsc_bpp_x16(stream_bandwidth_kbps, pix_clk_100hz,
+					bpp_increment_div);
+	DC_FP_END();
+	return dsc_bpp;
+}

drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h

@@ -77,7 +77,10 @@ struct qp_entry {
 
 typedef struct qp_entry qp_table[];
 
-void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_comp bpc, float bpp, int slice_width, int slice_height, int minor_version);
+void calc_rc_params(struct rc_params *rc, const struct drm_dsc_config *pps);
+u32 calc_dsc_bytes_per_pixel(const struct drm_dsc_config *pps);
+u32 calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+		     u32 bpp_increment_div);
 
 #endif
 

drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c

@@ -27,8 +27,6 @@
 #include "dscc_types.h"
 #include "rc_calc.h"
 
-double dsc_ceil(double num);
-
 static void copy_pps_fields(struct drm_dsc_config *to, const struct drm_dsc_config *from)
 {
 	to->line_buf_depth           = from->line_buf_depth;
@@ -100,34 +98,13 @@ static void copy_rc_to_cfg(struct drm_dsc_config *dsc_cfg, const struct rc_param
 
 int dscc_compute_dsc_parameters(const struct drm_dsc_config *pps, struct dsc_parameters *dsc_params)
 {
-	enum colour_mode  mode = pps->convert_rgb ? CM_RGB :
-							(pps->simple_422  ? CM_444 :
-							(pps->native_422  ? CM_422 :
-							pps->native_420  ? CM_420 : CM_444));
-	enum bits_per_comp bpc = (pps->bits_per_component == 8) ? BPC_8 :
-							(pps->bits_per_component == 10) ? BPC_10 : BPC_12;
-	float            bpp = ((float) pps->bits_per_pixel / 16.0);
-	int              slice_width  = pps->slice_width;
-	int              slice_height = pps->slice_height;
 	int              ret;
 	struct rc_params rc;
 	struct drm_dsc_config   dsc_cfg;
 
-	double d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width;
-
-	// TODO: Make sure the formula for calculating this is precise (ceiling vs. floor, and at what point they should be applied)
-	if (pps->native_422 || pps->native_420)
-		d_bytes_per_pixel /= 2;
-
-	dsc_params->bytes_per_pixel = (uint32_t)dsc_ceil(d_bytes_per_pixel * 0x10000000);
-
-	/* in native_422 or native_420 modes, the bits_per_pixel is double the target bpp
-	 * (the latter is what calc_rc_params expects)
-	 */
-	if (pps->native_422 || pps->native_420)
-		bpp /= 2.0;
+	dsc_params->bytes_per_pixel = calc_dsc_bytes_per_pixel(pps);
 
-	calc_rc_params(&rc, mode, bpc, bpp, slice_width, slice_height, pps->dsc_version_minor);
+	calc_rc_params(&rc, pps);
 	dsc_params->pps = *pps;
 	dsc_params->pps.initial_scale_value = 8 * rc.rc_model_size / (rc.rc_model_size - rc.initial_fullness_offset);
 

drivers/gpu/drm/amd/display/modules/color/color_gamma.c

@@ -843,7 +843,7 @@ static bool build_regamma(struct pwl_float_data_ex *rgb_regamma,
 	pow_buffer_ptr = -1; // reset back to no optimize
 	ret = true;
 release:
-	kfree(coeff);
+	kvfree(coeff);
 	return ret;
 }
 
@@ -1777,7 +1777,7 @@ bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf,
 
 	kfree(rgb_regamma);
 rgb_regamma_alloc_fail:
-	kvfree(rgb_user);
+	kfree(rgb_user);
 rgb_user_alloc_fail:
 	return ret;
 }

drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c

@@ -239,7 +239,7 @@ static void ci_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr)
 
 	switch (dev_id) {
 	case 0x67BA:
-	case 0x66B1:
+	case 0x67B1:
 		smu_data->power_tune_defaults = &defaults_hawaii_pro;
 		break;
 	case 0x67B8: