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, 584 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
new file mode 100644
index 000000000..ef52e6b6e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -0,0 +1,584 @@
+/*
+ * Copyright 2016 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 "dcn10_dpp.h"
+#include "basics/conversion.h"
+
+#define NUM_PHASES    64
+#define HORZ_MAX_TAPS 8
+#define VERT_MAX_TAPS 8
+
+#define BLACK_OFFSET_RGB_Y 0x0
+#define BLACK_OFFSET_CBCR  0x8000
+
+#define REG(reg)\
+	dpp->tf_regs->reg
+
+#define CTX \
+	dpp->base.ctx
+
+#undef FN
+#define FN(reg_name, field_name) \
+	dpp->tf_shift->field_name, dpp->tf_mask->field_name
+
+enum pixel_format_description {
+	PIXEL_FORMAT_FIXED = 0,
+	PIXEL_FORMAT_FIXED16,
+	PIXEL_FORMAT_FLOAT
+
+};
+
+enum dcn10_coef_filter_type_sel {
+	SCL_COEF_LUMA_VERT_FILTER = 0,
+	SCL_COEF_LUMA_HORZ_FILTER = 1,
+	SCL_COEF_CHROMA_VERT_FILTER = 2,
+	SCL_COEF_CHROMA_HORZ_FILTER = 3,
+	SCL_COEF_ALPHA_VERT_FILTER = 4,
+	SCL_COEF_ALPHA_HORZ_FILTER = 5
+};
+
+enum dscl_autocal_mode {
+	AUTOCAL_MODE_OFF = 0,
+
+	/* Autocal calculate the scaling ratio and initial phase and the
+	 * DSCL_MODE_SEL must be set to 1
+	 */
+	AUTOCAL_MODE_AUTOSCALE = 1,
+	/* Autocal perform auto centering without replication and the
+	 * DSCL_MODE_SEL must be set to 0
+	 */
+	AUTOCAL_MODE_AUTOCENTER = 2,
+	/* Autocal perform auto centering and auto replication and the
+	 * DSCL_MODE_SEL must be set to 0
+	 */
+	AUTOCAL_MODE_AUTOREPLICATE = 3
+};
+
+enum dscl_mode_sel {
+	DSCL_MODE_SCALING_444_BYPASS = 0,
+	DSCL_MODE_SCALING_444_RGB_ENABLE = 1,
+	DSCL_MODE_SCALING_444_YCBCR_ENABLE = 2,
+	DSCL_MODE_SCALING_420_YCBCR_ENABLE = 3,
+	DSCL_MODE_SCALING_420_LUMA_BYPASS = 4,
+	DSCL_MODE_SCALING_420_CHROMA_BYPASS = 5,
+	DSCL_MODE_DSCL_BYPASS = 6
+};
+
+void dpp_read_state(struct dpp *dpp_base,
+		struct dcn_dpp_state *s)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	REG_GET(DPP_CONTROL,
+			DPP_CLOCK_ENABLE, &s->is_enabled);
+	REG_GET(CM_IGAM_CONTROL,
+			CM_IGAM_LUT_MODE, &s->igam_lut_mode);
+	REG_GET(CM_IGAM_CONTROL,
+			CM_IGAM_INPUT_FORMAT, &s->igam_input_format);
+	REG_GET(CM_DGAM_CONTROL,
+			CM_DGAM_LUT_MODE, &s->dgam_lut_mode);
+	REG_GET(CM_RGAM_CONTROL,
+			CM_RGAM_LUT_MODE, &s->rgam_lut_mode);
+	REG_GET(CM_GAMUT_REMAP_CONTROL,
+			CM_GAMUT_REMAP_MODE, &s->gamut_remap_mode);
+
+	if (s->gamut_remap_mode) {
+		s->gamut_remap_c11_c12 = REG_READ(CM_GAMUT_REMAP_C11_C12);
+		s->gamut_remap_c13_c14 = REG_READ(CM_GAMUT_REMAP_C13_C14);
+		s->gamut_remap_c21_c22 = REG_READ(CM_GAMUT_REMAP_C21_C22);
+		s->gamut_remap_c23_c24 = REG_READ(CM_GAMUT_REMAP_C23_C24);
+		s->gamut_remap_c31_c32 = REG_READ(CM_GAMUT_REMAP_C31_C32);
+		s->gamut_remap_c33_c34 = REG_READ(CM_GAMUT_REMAP_C33_C34);
+	}
+}
+
+#define IDENTITY_RATIO(ratio) (dc_fixpt_u2d19(ratio) == (1 << 19))
+
+bool dpp1_get_optimal_number_of_taps(
+		struct dpp *dpp,
+		struct scaler_data *scl_data,
+		const struct scaling_taps *in_taps)
+{
+	/* Some ASICs does not support  FP16 scaling, so we reject modes require this*/
+	if (scl_data->format == PIXEL_FORMAT_FP16 &&
+		dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
+		scl_data->ratios.horz.value != dc_fixpt_one.value &&
+		scl_data->ratios.vert.value != dc_fixpt_one.value)
+		return false;
+
+	if (scl_data->viewport.width > scl_data->h_active &&
+		dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
+		scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
+		return false;
+
+	/* TODO: add lb check */
+
+	/* No support for programming ratio of 4, drop to 3.99999.. */
+	if (scl_data->ratios.horz.value == (4ll << 32))
+		scl_data->ratios.horz.value--;
+	if (scl_data->ratios.vert.value == (4ll << 32))
+		scl_data->ratios.vert.value--;
+	if (scl_data->ratios.horz_c.value == (4ll << 32))
+		scl_data->ratios.horz_c.value--;
+	if (scl_data->ratios.vert_c.value == (4ll << 32))
+		scl_data->ratios.vert_c.value--;
+
+	/* Set default taps if none are provided */
+	if (in_taps->h_taps == 0)
+		scl_data->taps.h_taps = 4;
+	else
+		scl_data->taps.h_taps = in_taps->h_taps;
+	if (in_taps->v_taps == 0)
+		scl_data->taps.v_taps = 4;
+	else
+		scl_data->taps.v_taps = in_taps->v_taps;
+	if (in_taps->v_taps_c == 0)
+		scl_data->taps.v_taps_c = 2;
+	else
+		scl_data->taps.v_taps_c = in_taps->v_taps_c;
+	if (in_taps->h_taps_c == 0)
+		scl_data->taps.h_taps_c = 2;
+	/* Only 1 and even h_taps_c are supported by hw */
+	else if ((in_taps->h_taps_c % 2) != 0 && in_taps->h_taps_c != 1)
+		scl_data->taps.h_taps_c = in_taps->h_taps_c - 1;
+	else
+		scl_data->taps.h_taps_c = in_taps->h_taps_c;
+
+	if (!dpp->ctx->dc->debug.always_scale) {
+		if (IDENTITY_RATIO(scl_data->ratios.horz))
+			scl_data->taps.h_taps = 1;
+		if (IDENTITY_RATIO(scl_data->ratios.vert))
+			scl_data->taps.v_taps = 1;
+		if (IDENTITY_RATIO(scl_data->ratios.horz_c))
+			scl_data->taps.h_taps_c = 1;
+		if (IDENTITY_RATIO(scl_data->ratios.vert_c))
+			scl_data->taps.v_taps_c = 1;
+	}
+
+	return true;
+}
+
+void dpp_reset(struct dpp *dpp_base)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	dpp->filter_h_c = NULL;
+	dpp->filter_v_c = NULL;
+	dpp->filter_h = NULL;
+	dpp->filter_v = NULL;
+
+	memset(&dpp->scl_data, 0, sizeof(dpp->scl_data));
+	memset(&dpp->pwl_data, 0, sizeof(dpp->pwl_data));
+}
+
+
+
+static void dpp1_cm_set_regamma_pwl(
+	struct dpp *dpp_base, const struct pwl_params *params, enum opp_regamma mode)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+	uint32_t re_mode = 0;
+
+	switch (mode) {
+	case OPP_REGAMMA_BYPASS:
+		re_mode = 0;
+		break;
+	case OPP_REGAMMA_SRGB:
+		re_mode = 1;
+		break;
+	case OPP_REGAMMA_XVYCC:
+		re_mode = 2;
+		break;
+	case OPP_REGAMMA_USER:
+		re_mode = dpp->is_write_to_ram_a_safe ? 4 : 3;
+		if (memcmp(&dpp->pwl_data, params, sizeof(*params)) == 0)
+			break;
+
+		dpp1_cm_power_on_regamma_lut(dpp_base, true);
+		dpp1_cm_configure_regamma_lut(dpp_base, dpp->is_write_to_ram_a_safe);
+
+		if (dpp->is_write_to_ram_a_safe)
+			dpp1_cm_program_regamma_luta_settings(dpp_base, params);
+		else
+			dpp1_cm_program_regamma_lutb_settings(dpp_base, params);
+
+		dpp1_cm_program_regamma_lut(dpp_base, params->rgb_resulted,
+					    params->hw_points_num);
+		dpp->pwl_data = *params;
+
+		re_mode = dpp->is_write_to_ram_a_safe ? 3 : 4;
+		dpp->is_write_to_ram_a_safe = !dpp->is_write_to_ram_a_safe;
+		break;
+	default:
+		break;
+	}
+	REG_SET(CM_RGAM_CONTROL, 0, CM_RGAM_LUT_MODE, re_mode);
+}
+
+static void dpp1_setup_format_flags(enum surface_pixel_format input_format,\
+						enum pixel_format_description *fmt)
+{
+
+	if (input_format == SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F ||
+		input_format == SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F)
+		*fmt = PIXEL_FORMAT_FLOAT;
+	else if (input_format == SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ||
+		input_format == SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616)
+		*fmt = PIXEL_FORMAT_FIXED16;
+	else
+		*fmt = PIXEL_FORMAT_FIXED;
+}
+
+static void dpp1_set_degamma_format_float(
+		struct dpp *dpp_base,
+		bool is_float)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	if (is_float) {
+		REG_UPDATE(CM_IGAM_CONTROL, CM_IGAM_INPUT_FORMAT, 3);
+		REG_UPDATE(CM_IGAM_CONTROL, CM_IGAM_LUT_MODE, 1);
+	} else {
+		REG_UPDATE(CM_IGAM_CONTROL, CM_IGAM_INPUT_FORMAT, 2);
+		REG_UPDATE(CM_IGAM_CONTROL, CM_IGAM_LUT_MODE, 0);
+	}
+}
+
+void dpp1_cnv_setup (
+		struct dpp *dpp_base,
+		enum surface_pixel_format format,
+		enum expansion_mode mode,
+		struct dc_csc_transform input_csc_color_matrix,
+		enum dc_color_space input_color_space,
+		struct cnv_alpha_2bit_lut *alpha_2bit_lut)
+{
+	uint32_t pixel_format;
+	uint32_t alpha_en;
+	enum pixel_format_description fmt ;
+	enum dc_color_space color_space;
+	enum dcn10_input_csc_select select;
+	bool is_float;
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+	bool force_disable_cursor = false;
+	struct out_csc_color_matrix tbl_entry;
+	int i = 0;
+
+	dpp1_setup_format_flags(format, &fmt);
+	alpha_en = 1;
+	pixel_format = 0;
+	color_space = COLOR_SPACE_SRGB;
+	select = INPUT_CSC_SELECT_BYPASS;
+	is_float = false;
+
+	switch (fmt) {
+	case PIXEL_FORMAT_FIXED:
+	case PIXEL_FORMAT_FIXED16:
+	/*when output is float then FORMAT_CONTROL__OUTPUT_FP=1*/
+		REG_SET_3(FORMAT_CONTROL, 0,
+			CNVC_BYPASS, 0,
+			FORMAT_EXPANSION_MODE, mode,
+			OUTPUT_FP, 0);
+		break;
+	case PIXEL_FORMAT_FLOAT:
+		REG_SET_3(FORMAT_CONTROL, 0,
+			CNVC_BYPASS, 0,
+			FORMAT_EXPANSION_MODE, mode,
+			OUTPUT_FP, 1);
+		is_float = true;
+		break;
+	default:
+
+		break;
+	}
+
+	dpp1_set_degamma_format_float(dpp_base, is_float);
+
+	switch (format) {
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555:
+		pixel_format = 1;
+		break;
+	case SURFACE_PIXEL_FORMAT_GRPH_RGB565:
+		pixel_format = 3;
+		alpha_en = 0;
+		break;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB8888:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR8888:
+		pixel_format = 8;
+		break;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB2101010:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010:
+		pixel_format = 10;
+		break;
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr:
+		force_disable_cursor = false;
+		pixel_format = 65;
+		color_space = COLOR_SPACE_YCBCR709;
+		select = INPUT_CSC_SELECT_ICSC;
+		break;
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb:
+		force_disable_cursor = true;
+		pixel_format = 64;
+		color_space = COLOR_SPACE_YCBCR709;
+		select = INPUT_CSC_SELECT_ICSC;
+		break;
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr:
+		force_disable_cursor = true;
+		pixel_format = 67;
+		color_space = COLOR_SPACE_YCBCR709;
+		select = INPUT_CSC_SELECT_ICSC;
+		break;
+	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb:
+		force_disable_cursor = true;
+		pixel_format = 66;
+		color_space = COLOR_SPACE_YCBCR709;
+		select = INPUT_CSC_SELECT_ICSC;
+		break;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
+		pixel_format = 26; /* ARGB16161616_UNORM */
+		break;
+	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
+		pixel_format = 24;
+		break;
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
+		pixel_format = 25;
+		break;
+	default:
+		break;
+	}
+
+	/* Set default color space based on format if none is given. */
+	color_space = input_color_space ? input_color_space : color_space;
+
+	REG_SET(CNVC_SURFACE_PIXEL_FORMAT, 0,
+			CNVC_SURFACE_PIXEL_FORMAT, pixel_format);
+	REG_UPDATE(FORMAT_CONTROL, FORMAT_CONTROL__ALPHA_EN, alpha_en);
+
+	// if input adjustments exist, program icsc with those values
+
+	if (input_csc_color_matrix.enable_adjustment
+				== true) {
+		for (i = 0; i < 12; i++)
+			tbl_entry.regval[i] = input_csc_color_matrix.matrix[i];
+
+		tbl_entry.color_space = color_space;
+
+		if (color_space >= COLOR_SPACE_YCBCR601)
+			select = INPUT_CSC_SELECT_ICSC;
+		else
+			select = INPUT_CSC_SELECT_BYPASS;
+
+		dpp1_program_input_csc(dpp_base, color_space, select, &tbl_entry);
+	} else
+		dpp1_program_input_csc(dpp_base, color_space, select, NULL);
+
+	if (force_disable_cursor) {
+		REG_UPDATE(CURSOR_CONTROL,
+				CURSOR_ENABLE, 0);
+		REG_UPDATE(CURSOR0_CONTROL,
+				CUR0_ENABLE, 0);
+	}
+}
+
+void dpp1_set_cursor_attributes(
+		struct dpp *dpp_base,
+		struct dc_cursor_attributes *cursor_attributes)
+{
+	enum dc_cursor_color_format color_format = cursor_attributes->color_format;
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	REG_UPDATE_2(CURSOR0_CONTROL,
+			CUR0_MODE, color_format,
+			CUR0_EXPANSION_MODE, 0);
+
+	if (color_format == CURSOR_MODE_MONO) {
+		/* todo: clarify what to program these to */
+		REG_UPDATE(CURSOR0_COLOR0,
+				CUR0_COLOR0, 0x00000000);
+		REG_UPDATE(CURSOR0_COLOR1,
+				CUR0_COLOR1, 0xFFFFFFFF);
+	}
+}
+
+
+void dpp1_set_cursor_position(
+		struct dpp *dpp_base,
+		const struct dc_cursor_position *pos,
+		const struct dc_cursor_mi_param *param,
+		uint32_t width,
+		uint32_t height)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+	int x_pos = pos->x - param->viewport.x;
+	int y_pos = pos->y - param->viewport.y;
+	int x_hotspot = pos->x_hotspot;
+	int y_hotspot = pos->y_hotspot;
+	int src_x_offset = x_pos - pos->x_hotspot;
+	int src_y_offset = y_pos - pos->y_hotspot;
+	int cursor_height = (int)height;
+	int cursor_width = (int)width;
+	uint32_t cur_en = pos->enable ? 1 : 0;
+
+	// Transform cursor width / height and hotspots for offset calculations
+	if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) {
+		swap(cursor_height, cursor_width);
+		swap(x_hotspot, y_hotspot);
+
+		if (param->rotation == ROTATION_ANGLE_90) {
+			// hotspot = (-y, x)
+			src_x_offset = x_pos - (cursor_width - x_hotspot);
+			src_y_offset = y_pos - y_hotspot;
+		} else if (param->rotation == ROTATION_ANGLE_270) {
+			// hotspot = (y, -x)
+			src_x_offset = x_pos - x_hotspot;
+			src_y_offset = y_pos - (cursor_height - y_hotspot);
+		}
+	} else if (param->rotation == ROTATION_ANGLE_180) {
+		// hotspot = (-x, -y)
+		if (!param->mirror)
+			src_x_offset = x_pos - (cursor_width - x_hotspot);
+
+		src_y_offset = y_pos - (cursor_height - y_hotspot);
+	}
+
+	if (src_x_offset >= (int)param->viewport.width)
+		cur_en = 0;  /* not visible beyond right edge*/
+
+	if (src_x_offset + cursor_width <= 0)
+		cur_en = 0;  /* not visible beyond left edge*/
+
+	if (src_y_offset >= (int)param->viewport.height)
+		cur_en = 0;  /* not visible beyond bottom edge*/
+
+	if (src_y_offset + cursor_height <= 0)
+		cur_en = 0;  /* not visible beyond top edge*/
+
+	REG_UPDATE(CURSOR0_CONTROL,
+			CUR0_ENABLE, cur_en);
+
+	dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+}
+
+void dpp1_cnv_set_optional_cursor_attributes(
+		struct dpp *dpp_base,
+		struct dpp_cursor_attributes *attr)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	if (attr) {
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_BIAS,  attr->bias);
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_SCALE, attr->scale);
+	}
+}
+
+void dpp1_dppclk_control(
+		struct dpp *dpp_base,
+		bool dppclk_div,
+		bool enable)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	if (enable) {
+		if (dpp->tf_mask->DPPCLK_RATE_CONTROL)
+			REG_UPDATE_2(DPP_CONTROL,
+				DPPCLK_RATE_CONTROL, dppclk_div,
+				DPP_CLOCK_ENABLE, 1);
+		else
+			REG_UPDATE(DPP_CONTROL, DPP_CLOCK_ENABLE, 1);
+	} else
+		REG_UPDATE(DPP_CONTROL, DPP_CLOCK_ENABLE, 0);
+}
+
+static const struct dpp_funcs dcn10_dpp_funcs = {
+		.dpp_read_state = dpp_read_state,
+		.dpp_reset = dpp_reset,
+		.dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale,
+		.dpp_get_optimal_number_of_taps = dpp1_get_optimal_number_of_taps,
+		.dpp_set_gamut_remap = dpp1_cm_set_gamut_remap,
+		.dpp_set_csc_adjustment = dpp1_cm_set_output_csc_adjustment,
+		.dpp_set_csc_default = dpp1_cm_set_output_csc_default,
+		.dpp_power_on_regamma_lut = dpp1_cm_power_on_regamma_lut,
+		.dpp_program_regamma_lut = dpp1_cm_program_regamma_lut,
+		.dpp_configure_regamma_lut = dpp1_cm_configure_regamma_lut,
+		.dpp_program_regamma_lutb_settings = dpp1_cm_program_regamma_lutb_settings,
+		.dpp_program_regamma_luta_settings = dpp1_cm_program_regamma_luta_settings,
+		.dpp_program_regamma_pwl = dpp1_cm_set_regamma_pwl,
+		.dpp_program_bias_and_scale = dpp1_program_bias_and_scale,
+		.dpp_set_degamma = dpp1_set_degamma,
+		.dpp_program_input_lut		= dpp1_program_input_lut,
+		.dpp_program_degamma_pwl	= dpp1_set_degamma_pwl,
+		.dpp_setup			= dpp1_cnv_setup,
+		.dpp_full_bypass		= dpp1_full_bypass,
+		.set_cursor_attributes = dpp1_set_cursor_attributes,
+		.set_cursor_position = dpp1_set_cursor_position,
+		.set_optional_cursor_attributes = dpp1_cnv_set_optional_cursor_attributes,
+		.dpp_dppclk_control = dpp1_dppclk_control,
+		.dpp_set_hdr_multiplier = dpp1_set_hdr_multiplier,
+		.dpp_program_blnd_lut = NULL,
+		.dpp_program_shaper_lut = NULL,
+		.dpp_program_3dlut = NULL
+};
+
+static struct dpp_caps dcn10_dpp_cap = {
+	.dscl_data_proc_format = DSCL_DATA_PRCESSING_FIXED_FORMAT,
+	.dscl_calc_lb_num_partitions = dpp1_dscl_calc_lb_num_partitions,
+};
+
+/*****************************************/
+/* Constructor, Destructor               */
+/*****************************************/
+
+void dpp1_construct(
+	struct dcn10_dpp *dpp,
+	struct dc_context *ctx,
+	uint32_t inst,
+	const struct dcn_dpp_registers *tf_regs,
+	const struct dcn_dpp_shift *tf_shift,
+	const struct dcn_dpp_mask *tf_mask)
+{
+	dpp->base.ctx = ctx;
+
+	dpp->base.inst = inst;
+	dpp->base.funcs = &dcn10_dpp_funcs;
+	dpp->base.caps = &dcn10_dpp_cap;
+
+	dpp->tf_regs = tf_regs;
+	dpp->tf_shift = tf_shift;
+	dpp->tf_mask = tf_mask;
+
+	dpp->lb_pixel_depth_supported =
+		LB_PIXEL_DEPTH_18BPP |
+		LB_PIXEL_DEPTH_24BPP |
+		LB_PIXEL_DEPTH_30BPP |
+		LB_PIXEL_DEPTH_36BPP;
+
+	dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
+	dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/
+}