Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 646 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
new file mode 100644
index 000000000..e0df9b006
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
@@ -0,0 +1,646 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+#include "core_types.h"
+#include "reg_helper.h"
+#include "dcn30_dpp.h"
+#include "basics/conversion.h"
+#include "dcn30_cm_common.h"
+#include "custom_float.h"
+
+#define REG(reg) reg
+
+#define CTX \
+	ctx //dpp->base.ctx
+
+#undef FN
+#define FN(reg_name, field_name) \
+	reg->shifts.field_name, reg->masks.field_name
+
+void cm_helper_program_gamcor_xfer_func(
+		struct dc_context *ctx,
+		const struct pwl_params *params,
+		const struct dcn3_xfer_func_reg *reg)
+{
+	uint32_t reg_region_cur;
+	unsigned int i = 0;
+
+	REG_SET_2(reg->start_cntl_b, 0,
+		exp_region_start, params->corner_points[0].blue.custom_float_x,
+		exp_resion_start_segment, 0);
+	REG_SET_2(reg->start_cntl_g, 0,
+		exp_region_start, params->corner_points[0].green.custom_float_x,
+		exp_resion_start_segment, 0);
+	REG_SET_2(reg->start_cntl_r, 0,
+		exp_region_start, params->corner_points[0].red.custom_float_x,
+		exp_resion_start_segment, 0);
+
+	REG_SET(reg->start_slope_cntl_b, 0, //linear slope at start of curve
+		field_region_linear_slope, params->corner_points[0].blue.custom_float_slope);
+	REG_SET(reg->start_slope_cntl_g, 0,
+		field_region_linear_slope, params->corner_points[0].green.custom_float_slope);
+	REG_SET(reg->start_slope_cntl_r, 0,
+		field_region_linear_slope, params->corner_points[0].red.custom_float_slope);
+
+	REG_SET(reg->start_end_cntl1_b, 0,
+		field_region_end_base, params->corner_points[1].blue.custom_float_y);
+	REG_SET(reg->start_end_cntl1_g, 0,
+		field_region_end_base, params->corner_points[1].green.custom_float_y);
+	REG_SET(reg->start_end_cntl1_r, 0,
+		field_region_end_base, params->corner_points[1].red.custom_float_y);
+
+	REG_SET_2(reg->start_end_cntl2_b, 0,
+		field_region_end_slope, params->corner_points[1].blue.custom_float_slope,
+		field_region_end, params->corner_points[1].blue.custom_float_x);
+	REG_SET_2(reg->start_end_cntl2_g, 0,
+		field_region_end_slope, params->corner_points[1].green.custom_float_slope,
+		field_region_end, params->corner_points[1].green.custom_float_x);
+	REG_SET_2(reg->start_end_cntl2_r, 0,
+		field_region_end_slope, params->corner_points[1].red.custom_float_slope,
+		field_region_end, params->corner_points[1].red.custom_float_x);
+
+	for (reg_region_cur = reg->region_start;
+		reg_region_cur <= reg->region_end;
+		reg_region_cur++) {
+
+		const struct gamma_curve *curve0 = &(params->arr_curve_points[2 * i]);
+		const struct gamma_curve *curve1 = &(params->arr_curve_points[(2 * i) + 1]);
+
+		REG_SET_4(reg_region_cur, 0,
+			exp_region0_lut_offset, curve0->offset,
+			exp_region0_num_segments, curve0->segments_num,
+			exp_region1_lut_offset, curve1->offset,
+			exp_region1_num_segments, curve1->segments_num);
+
+		i++;
+	}
+}
+
+/* driver uses 32 regions or less, but DCN HW has 34, extra 2 are set to 0 */
+#define MAX_REGIONS_NUMBER 34
+#define MAX_LOW_POINT      25
+#define NUMBER_REGIONS     32
+#define NUMBER_SW_SEGMENTS 16
+
+bool cm3_helper_translate_curve_to_hw_format(
+				const struct dc_transfer_func *output_tf,
+				struct pwl_params *lut_params, bool fixpoint)
+{
+	struct curve_points3 *corner_points;
+	struct pwl_result_data *rgb_resulted;
+	struct pwl_result_data *rgb;
+	struct pwl_result_data *rgb_plus_1;
+	struct pwl_result_data *rgb_minus_1;
+	struct fixed31_32 end_value;
+
+	int32_t region_start, region_end;
+	int32_t i;
+	uint32_t j, k, seg_distr[MAX_REGIONS_NUMBER], increment, start_index, hw_points;
+
+	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
+		return false;
+
+	corner_points = lut_params->corner_points;
+	rgb_resulted = lut_params->rgb_resulted;
+	hw_points = 0;
+
+	memset(lut_params, 0, sizeof(struct pwl_params));
+	memset(seg_distr, 0, sizeof(seg_distr));
+
+	if (output_tf->tf == TRANSFER_FUNCTION_PQ || output_tf->tf == TRANSFER_FUNCTION_GAMMA22 ||
+		output_tf->tf == TRANSFER_FUNCTION_HLG) {
+		/* 32 segments
+		 * segments are from 2^-25 to 2^7
+		 */
+		for (i = 0; i < NUMBER_REGIONS ; i++)
+			seg_distr[i] = 3;
+
+		region_start = -MAX_LOW_POINT;
+		region_end   = NUMBER_REGIONS - MAX_LOW_POINT;
+	} else {
+		/* 11 segments
+		 * segment is from 2^-10 to 2^0
+		 * There are less than 256 points, for optimization
+		 */
+		seg_distr[0] = 3;
+		seg_distr[1] = 4;
+		seg_distr[2] = 4;
+		seg_distr[3] = 4;
+		seg_distr[4] = 4;
+		seg_distr[5] = 4;
+		seg_distr[6] = 4;
+		seg_distr[7] = 4;
+		seg_distr[8] = 4;
+		seg_distr[9] = 4;
+		seg_distr[10] = 1;
+
+		region_start = -10;
+		region_end = 1;
+	}
+
+	for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++)
+		seg_distr[i] = -1;
+
+	for (k = 0; k < MAX_REGIONS_NUMBER; k++) {
+		if (seg_distr[k] != -1)
+			hw_points += (1 << seg_distr[k]);
+	}
+
+	j = 0;
+	for (k = 0; k < (region_end - region_start); k++) {
+		increment = NUMBER_SW_SEGMENTS / (1 << seg_distr[k]);
+		start_index = (region_start + k + MAX_LOW_POINT) *
+				NUMBER_SW_SEGMENTS;
+		for (i = start_index; i < start_index + NUMBER_SW_SEGMENTS;
+				i += increment) {
+			if (j == hw_points - 1)
+				break;
+			rgb_resulted[j].red = output_tf->tf_pts.red[i];
+			rgb_resulted[j].green = output_tf->tf_pts.green[i];
+			rgb_resulted[j].blue = output_tf->tf_pts.blue[i];
+			j++;
+		}
+	}
+
+	/* last point */
+	start_index = (region_end + MAX_LOW_POINT) * NUMBER_SW_SEGMENTS;
+	rgb_resulted[hw_points - 1].red = output_tf->tf_pts.red[start_index];
+	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
+	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
+	// All 3 color channels have same x
+	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_start));
+	corner_points[0].green.x = corner_points[0].red.x;
+	corner_points[0].blue.x = corner_points[0].red.x;
+
+	corner_points[1].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_end));
+	corner_points[1].green.x = corner_points[1].red.x;
+	corner_points[1].blue.x = corner_points[1].red.x;
+
+	corner_points[0].red.y = rgb_resulted[0].red;
+	corner_points[0].green.y = rgb_resulted[0].green;
+	corner_points[0].blue.y = rgb_resulted[0].blue;
+
+	corner_points[0].red.slope = dc_fixpt_div(corner_points[0].red.y,
+			corner_points[0].red.x);
+	corner_points[0].green.slope = dc_fixpt_div(corner_points[0].green.y,
+			corner_points[0].green.x);
+	corner_points[0].blue.slope = dc_fixpt_div(corner_points[0].blue.y,
+			corner_points[0].blue.x);
+
+	/* see comment above, m_arrPoints[1].y should be the Y value for the
+	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
+	 */
+	corner_points[1].red.y = rgb_resulted[hw_points - 1].red;
+	corner_points[1].green.y = rgb_resulted[hw_points - 1].green;
+	corner_points[1].blue.y = rgb_resulted[hw_points - 1].blue;
+	corner_points[1].red.slope = dc_fixpt_zero;
+	corner_points[1].green.slope = dc_fixpt_zero;
+	corner_points[1].blue.slope = dc_fixpt_zero;
+
+	if (output_tf->tf == TRANSFER_FUNCTION_PQ || output_tf->tf == TRANSFER_FUNCTION_HLG) {
+		/* for PQ/HLG, we want to have a straight line from last HW X point,
+		 * and the slope to be such that we hit 1.0 at 10000/1000 nits.
+		 */
+
+		if (output_tf->tf == TRANSFER_FUNCTION_PQ)
+			end_value = dc_fixpt_from_int(125);
+		else
+			end_value = dc_fixpt_from_fraction(125, 10);
+
+		corner_points[1].red.slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, corner_points[1].red.y),
+			dc_fixpt_sub(end_value, corner_points[1].red.x));
+		corner_points[1].green.slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, corner_points[1].green.y),
+			dc_fixpt_sub(end_value, corner_points[1].green.x));
+		corner_points[1].blue.slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, corner_points[1].blue.y),
+			dc_fixpt_sub(end_value, corner_points[1].blue.x));
+	}
+	lut_params->hw_points_num = hw_points;
+
+	k = 0;
+	for (i = 1; i < MAX_REGIONS_NUMBER; i++) {
+		if (seg_distr[k] != -1) {
+			lut_params->arr_curve_points[k].segments_num =
+					seg_distr[k];
+			lut_params->arr_curve_points[i].offset =
+					lut_params->arr_curve_points[k].offset + (1 << seg_distr[k]);
+		}
+		k++;
+	}
+
+	if (seg_distr[k] != -1)
+		lut_params->arr_curve_points[k].segments_num = seg_distr[k];
+
+	rgb = rgb_resulted;
+	rgb_plus_1 = rgb_resulted + 1;
+	rgb_minus_1 = rgb;
+
+	i = 1;
+	while (i != hw_points + 1) {
+		if (i >= hw_points - 1) {
+			if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
+				rgb_plus_1->red = dc_fixpt_add(rgb->red, rgb_minus_1->delta_red);
+			if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
+				rgb_plus_1->green = dc_fixpt_add(rgb->green, rgb_minus_1->delta_green);
+			if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
+				rgb_plus_1->blue = dc_fixpt_add(rgb->blue, rgb_minus_1->delta_blue);
+		}
+
+		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
+		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
+
+		if (fixpoint == true) {
+			rgb->delta_red_reg   = dc_fixpt_clamp_u0d10(rgb->delta_red);
+			rgb->delta_green_reg = dc_fixpt_clamp_u0d10(rgb->delta_green);
+			rgb->delta_blue_reg  = dc_fixpt_clamp_u0d10(rgb->delta_blue);
+			rgb->red_reg         = dc_fixpt_clamp_u0d14(rgb->red);
+			rgb->green_reg       = dc_fixpt_clamp_u0d14(rgb->green);
+			rgb->blue_reg        = dc_fixpt_clamp_u0d14(rgb->blue);
+		}
+
+		++rgb_plus_1;
+		rgb_minus_1 = rgb;
+		++rgb;
+		++i;
+	}
+	cm3_helper_convert_to_custom_float(rgb_resulted,
+						lut_params->corner_points,
+						hw_points, fixpoint);
+
+	return true;
+}
+
+#define NUM_DEGAMMA_REGIONS    12
+
+
+bool cm3_helper_translate_curve_to_degamma_hw_format(
+				const struct dc_transfer_func *output_tf,
+				struct pwl_params *lut_params)
+{
+	struct curve_points3 *corner_points;
+	struct pwl_result_data *rgb_resulted;
+	struct pwl_result_data *rgb;
+	struct pwl_result_data *rgb_plus_1;
+
+	int32_t region_start, region_end;
+	int32_t i;
+	uint32_t j, k, seg_distr[MAX_REGIONS_NUMBER], increment, start_index, hw_points;
+
+	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
+		return false;
+
+	corner_points = lut_params->corner_points;
+	rgb_resulted = lut_params->rgb_resulted;
+	hw_points = 0;
+
+	memset(lut_params, 0, sizeof(struct pwl_params));
+	memset(seg_distr, 0, sizeof(seg_distr));
+
+	region_start = -NUM_DEGAMMA_REGIONS;
+	region_end   = 0;
+
+
+	for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++)
+		seg_distr[i] = -1;
+	/* 12 segments
+	 * segments are from 2^-12 to 0
+	 */
+	for (i = 0; i < NUM_DEGAMMA_REGIONS ; i++)
+		seg_distr[i] = 4;
+
+	for (k = 0; k < MAX_REGIONS_NUMBER; k++) {
+		if (seg_distr[k] != -1)
+			hw_points += (1 << seg_distr[k]);
+	}
+
+	j = 0;
+	for (k = 0; k < (region_end - region_start); k++) {
+		increment = NUMBER_SW_SEGMENTS / (1 << seg_distr[k]);
+		start_index = (region_start + k + MAX_LOW_POINT) *
+				NUMBER_SW_SEGMENTS;
+		for (i = start_index; i < start_index + NUMBER_SW_SEGMENTS;
+				i += increment) {
+			if (j == hw_points - 1)
+				break;
+			rgb_resulted[j].red = output_tf->tf_pts.red[i];
+			rgb_resulted[j].green = output_tf->tf_pts.green[i];
+			rgb_resulted[j].blue = output_tf->tf_pts.blue[i];
+			j++;
+		}
+	}
+
+	/* last point */
+	start_index = (region_end + MAX_LOW_POINT) * NUMBER_SW_SEGMENTS;
+	rgb_resulted[hw_points - 1].red = output_tf->tf_pts.red[start_index];
+	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
+	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+
+	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_start));
+	corner_points[0].green.x = corner_points[0].red.x;
+	corner_points[0].blue.x = corner_points[0].red.x;
+	corner_points[1].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
+					     dc_fixpt_from_int(region_end));
+	corner_points[1].green.x = corner_points[1].red.x;
+	corner_points[1].blue.x = corner_points[1].red.x;
+
+	corner_points[0].red.y = rgb_resulted[0].red;
+	corner_points[0].green.y = rgb_resulted[0].green;
+	corner_points[0].blue.y = rgb_resulted[0].blue;
+
+	/* see comment above, m_arrPoints[1].y should be the Y value for the
+	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
+	 */
+	corner_points[1].red.y = rgb_resulted[hw_points - 1].red;
+	corner_points[1].green.y = rgb_resulted[hw_points - 1].green;
+	corner_points[1].blue.y = rgb_resulted[hw_points - 1].blue;
+	corner_points[1].red.slope = dc_fixpt_zero;
+	corner_points[1].green.slope = dc_fixpt_zero;
+	corner_points[1].blue.slope = dc_fixpt_zero;
+
+	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
+		/* for PQ, we want to have a straight line from last HW X point,
+		 * and the slope to be such that we hit 1.0 at 10000 nits.
+		 */
+		const struct fixed31_32 end_value =
+				dc_fixpt_from_int(125);
+
+		corner_points[1].red.slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, corner_points[1].red.y),
+			dc_fixpt_sub(end_value, corner_points[1].red.x));
+		corner_points[1].green.slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, corner_points[1].green.y),
+			dc_fixpt_sub(end_value, corner_points[1].green.x));
+		corner_points[1].blue.slope = dc_fixpt_div(
+			dc_fixpt_sub(dc_fixpt_one, corner_points[1].blue.y),
+			dc_fixpt_sub(end_value, corner_points[1].blue.x));
+	}
+
+	lut_params->hw_points_num = hw_points;
+
+	k = 0;
+	for (i = 1; i < MAX_REGIONS_NUMBER; i++) {
+		if (seg_distr[k] != -1) {
+			lut_params->arr_curve_points[k].segments_num =
+					seg_distr[k];
+			lut_params->arr_curve_points[i].offset =
+					lut_params->arr_curve_points[k].offset + (1 << seg_distr[k]);
+		}
+		k++;
+	}
+
+	if (seg_distr[k] != -1)
+		lut_params->arr_curve_points[k].segments_num = seg_distr[k];
+
+	rgb = rgb_resulted;
+	rgb_plus_1 = rgb_resulted + 1;
+
+	i = 1;
+	while (i != hw_points + 1) {
+		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
+			rgb_plus_1->red = rgb->red;
+		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
+			rgb_plus_1->green = rgb->green;
+		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
+			rgb_plus_1->blue = rgb->blue;
+
+		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
+		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
+
+		++rgb_plus_1;
+		++rgb;
+		++i;
+	}
+	cm3_helper_convert_to_custom_float(rgb_resulted,
+						lut_params->corner_points,
+						hw_points, false);
+
+	return true;
+}
+
+bool cm3_helper_convert_to_custom_float(
+		struct pwl_result_data *rgb_resulted,
+		struct curve_points3 *corner_points,
+		uint32_t hw_points_num,
+		bool fixpoint)
+{
+	struct custom_float_format fmt;
+
+	struct pwl_result_data *rgb = rgb_resulted;
+
+	uint32_t i = 0;
+
+	fmt.exponenta_bits = 6;
+	fmt.mantissa_bits = 12;
+	fmt.sign = false;
+
+	/* corner_points[0] - beginning base, slope offset for R,G,B
+	 * corner_points[1] - end base, slope offset for R,G,B
+	 */
+	if (!convert_to_custom_float_format(corner_points[0].red.x, &fmt,
+				&corner_points[0].red.custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[0].green.x, &fmt,
+				&corner_points[0].green.custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[0].blue.x, &fmt,
+				&corner_points[0].blue.custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (!convert_to_custom_float_format(corner_points[0].red.offset, &fmt,
+				&corner_points[0].red.custom_float_offset)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[0].green.offset, &fmt,
+				&corner_points[0].green.custom_float_offset)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[0].blue.offset, &fmt,
+				&corner_points[0].blue.custom_float_offset)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (!convert_to_custom_float_format(corner_points[0].red.slope, &fmt,
+				&corner_points[0].red.custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[0].green.slope, &fmt,
+				&corner_points[0].green.custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[0].blue.slope, &fmt,
+				&corner_points[0].blue.custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (fixpoint == true) {
+		corner_points[1].red.custom_float_y =
+				dc_fixpt_clamp_u0d14(corner_points[1].red.y);
+		corner_points[1].green.custom_float_y =
+				dc_fixpt_clamp_u0d14(corner_points[1].green.y);
+		corner_points[1].blue.custom_float_y =
+				dc_fixpt_clamp_u0d14(corner_points[1].blue.y);
+	} else {
+		if (!convert_to_custom_float_format(corner_points[1].red.y,
+				&fmt, &corner_points[1].red.custom_float_y)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+		if (!convert_to_custom_float_format(corner_points[1].green.y,
+				&fmt, &corner_points[1].green.custom_float_y)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+		if (!convert_to_custom_float_format(corner_points[1].blue.y,
+				&fmt, &corner_points[1].blue.custom_float_y)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+	}
+
+	fmt.mantissa_bits = 10;
+	fmt.sign = false;
+
+	if (!convert_to_custom_float_format(corner_points[1].red.x, &fmt,
+				&corner_points[1].red.custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[1].green.x, &fmt,
+				&corner_points[1].green.custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[1].blue.x, &fmt,
+				&corner_points[1].blue.custom_float_x)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (!convert_to_custom_float_format(corner_points[1].red.slope, &fmt,
+				&corner_points[1].red.custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[1].green.slope, &fmt,
+				&corner_points[1].green.custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+	if (!convert_to_custom_float_format(corner_points[1].blue.slope, &fmt,
+				&corner_points[1].blue.custom_float_slope)) {
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	if (hw_points_num == 0 || rgb_resulted == NULL || fixpoint == true)
+		return true;
+
+	fmt.mantissa_bits = 12;
+
+	while (i != hw_points_num) {
+		if (!convert_to_custom_float_format(rgb->red, &fmt,
+						    &rgb->red_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->green, &fmt,
+						    &rgb->green_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->blue, &fmt,
+						    &rgb->blue_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->delta_red, &fmt,
+						    &rgb->delta_red_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->delta_green, &fmt,
+						    &rgb->delta_green_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		if (!convert_to_custom_float_format(rgb->delta_blue, &fmt,
+						    &rgb->delta_blue_reg)) {
+			BREAK_TO_DEBUGGER();
+			return false;
+		}
+
+		++rgb;
+		++i;
+	}
+
+	return true;
+}
+
+bool is_rgb_equal(const struct pwl_result_data *rgb, uint32_t num)
+{
+	uint32_t i;
+	bool ret = true;
+
+	for (i = 0 ; i < num; i++) {
+		if (rgb[i].red_reg != rgb[i].green_reg ||
+		rgb[i].blue_reg != rgb[i].red_reg  ||
+		rgb[i].blue_reg != rgb[i].green_reg) {
+			ret = false;
+			break;
+		}
+	}
+	return ret;
+}
+