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, 357 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
new file mode 100644
index 000000000..e2bcd205a
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
@@ -0,0 +1,357 @@
+/*
+ * Copyright 2021 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 "resource.h"
+#include "clk_mgr.h"
+#include "dcn20/dcn20_resource.h"
+#include "dcn302/dcn302_resource.h"
+
+#include "dml/dcn20/dcn20_fpu.h"
+#include "dcn302_fpu.h"
+
+struct _vcs_dpi_ip_params_st dcn3_02_ip = {
+		.use_min_dcfclk = 0,
+		.clamp_min_dcfclk = 0,
+		.odm_capable = 1,
+		.gpuvm_enable = 1,
+		.hostvm_enable = 0,
+		.gpuvm_max_page_table_levels = 4,
+		.hostvm_max_page_table_levels = 4,
+		.hostvm_cached_page_table_levels = 0,
+		.pte_group_size_bytes = 2048,
+		.num_dsc = 5,
+		.rob_buffer_size_kbytes = 184,
+		.det_buffer_size_kbytes = 184,
+		.dpte_buffer_size_in_pte_reqs_luma = 64,
+		.dpte_buffer_size_in_pte_reqs_chroma = 34,
+		.pde_proc_buffer_size_64k_reqs = 48,
+		.dpp_output_buffer_pixels = 2560,
+		.opp_output_buffer_lines = 1,
+		.pixel_chunk_size_kbytes = 8,
+		.pte_enable = 1,
+		.max_page_table_levels = 2,
+		.pte_chunk_size_kbytes = 2,  // ?
+		.meta_chunk_size_kbytes = 2,
+		.writeback_chunk_size_kbytes = 8,
+		.line_buffer_size_bits = 789504,
+		.is_line_buffer_bpp_fixed = 0,  // ?
+		.line_buffer_fixed_bpp = 0,     // ?
+		.dcc_supported = true,
+		.writeback_interface_buffer_size_kbytes = 90,
+		.writeback_line_buffer_buffer_size = 0,
+		.max_line_buffer_lines = 12,
+		.writeback_luma_buffer_size_kbytes = 12,  // writeback_line_buffer_buffer_size = 656640
+		.writeback_chroma_buffer_size_kbytes = 8,
+		.writeback_chroma_line_buffer_width_pixels = 4,
+		.writeback_max_hscl_ratio = 1,
+		.writeback_max_vscl_ratio = 1,
+		.writeback_min_hscl_ratio = 1,
+		.writeback_min_vscl_ratio = 1,
+		.writeback_max_hscl_taps = 1,
+		.writeback_max_vscl_taps = 1,
+		.writeback_line_buffer_luma_buffer_size = 0,
+		.writeback_line_buffer_chroma_buffer_size = 14643,
+		.cursor_buffer_size = 8,
+		.cursor_chunk_size = 2,
+		.max_num_otg = 5,
+		.max_num_dpp = 5,
+		.max_num_wb = 1,
+		.max_dchub_pscl_bw_pix_per_clk = 4,
+		.max_pscl_lb_bw_pix_per_clk = 2,
+		.max_lb_vscl_bw_pix_per_clk = 4,
+		.max_vscl_hscl_bw_pix_per_clk = 4,
+		.max_hscl_ratio = 6,
+		.max_vscl_ratio = 6,
+		.hscl_mults = 4,
+		.vscl_mults = 4,
+		.max_hscl_taps = 8,
+		.max_vscl_taps = 8,
+		.dispclk_ramp_margin_percent = 1,
+		.underscan_factor = 1.11,
+		.min_vblank_lines = 32,
+		.dppclk_delay_subtotal = 46,
+		.dynamic_metadata_vm_enabled = true,
+		.dppclk_delay_scl_lb_only = 16,
+		.dppclk_delay_scl = 50,
+		.dppclk_delay_cnvc_formatter = 27,
+		.dppclk_delay_cnvc_cursor = 6,
+		.dispclk_delay_subtotal = 119,
+		.dcfclk_cstate_latency = 5.2, // SRExitTime
+		.max_inter_dcn_tile_repeaters = 8,
+		.max_num_hdmi_frl_outputs = 1,
+		.odm_combine_4to1_supported = true,
+
+		.xfc_supported = false,
+		.xfc_fill_bw_overhead_percent = 10.0,
+		.xfc_fill_constant_bytes = 0,
+		.gfx7_compat_tiling_supported = 0,
+		.number_of_cursors = 1,
+};
+
+struct _vcs_dpi_soc_bounding_box_st dcn3_02_soc = {
+		.clock_limits = {
+				{
+						.state = 0,
+						.dispclk_mhz = 562.0,
+						.dppclk_mhz = 300.0,
+						.phyclk_mhz = 300.0,
+						.phyclk_d18_mhz = 667.0,
+						.dscclk_mhz = 405.6,
+				},
+		},
+
+		.min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */
+		.num_states = 1,
+		.sr_exit_time_us = 26.5,
+		.sr_enter_plus_exit_time_us = 31,
+		.urgent_latency_us = 4.0,
+		.urgent_latency_pixel_data_only_us = 4.0,
+		.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
+		.urgent_latency_vm_data_only_us = 4.0,
+		.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
+		.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
+		.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
+		.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 80.0,
+		.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 60.0,
+		.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0,
+		.max_avg_sdp_bw_use_normal_percent = 60.0,
+		.max_avg_dram_bw_use_normal_percent = 40.0,
+		.writeback_latency_us = 12.0,
+		.max_request_size_bytes = 256,
+		.fabric_datapath_to_dcn_data_return_bytes = 64,
+		.dcn_downspread_percent = 0.5,
+		.downspread_percent = 0.38,
+		.dram_page_open_time_ns = 50.0,
+		.dram_rw_turnaround_time_ns = 17.5,
+		.dram_return_buffer_per_channel_bytes = 8192,
+		.round_trip_ping_latency_dcfclk_cycles = 156,
+		.urgent_out_of_order_return_per_channel_bytes = 4096,
+		.channel_interleave_bytes = 256,
+		.num_banks = 8,
+		.gpuvm_min_page_size_bytes = 4096,
+		.hostvm_min_page_size_bytes = 4096,
+		.dram_clock_change_latency_us = 404,
+		.dummy_pstate_latency_us = 5,
+		.writeback_dram_clock_change_latency_us = 23.0,
+		.return_bus_width_bytes = 64,
+		.dispclk_dppclk_vco_speed_mhz = 3650,
+		.xfc_bus_transport_time_us = 20,      // ?
+		.xfc_xbuf_latency_tolerance_us = 4,  // ?
+		.use_urgent_burst_bw = 1,            // ?
+		.do_urgent_latency_adjustment = true,
+		.urgent_latency_adjustment_fabric_clock_component_us = 1.0,
+		.urgent_latency_adjustment_fabric_clock_reference_mhz = 1000,
+};
+
+static void dcn302_get_optimal_dcfclk_fclk_for_uclk(unsigned int uclk_mts,
+	unsigned int *optimal_dcfclk,
+	unsigned int *optimal_fclk)
+{
+
+			double bw_from_dram, bw_from_dram1, bw_from_dram2;
+
+			bw_from_dram1 = uclk_mts * dcn3_02_soc.num_chans *
+				dcn3_02_soc.dram_channel_width_bytes *
+				(dcn3_02_soc.max_avg_dram_bw_use_normal_percent / 100);
+			bw_from_dram2 = uclk_mts * dcn3_02_soc.num_chans *
+				dcn3_02_soc.dram_channel_width_bytes *
+				(dcn3_02_soc.max_avg_sdp_bw_use_normal_percent / 100);
+
+			bw_from_dram = (bw_from_dram1 < bw_from_dram2) ? bw_from_dram1 : bw_from_dram2;
+
+			if (optimal_fclk)
+				*optimal_fclk = bw_from_dram /
+				(dcn3_02_soc.fabric_datapath_to_dcn_data_return_bytes *
+				 (dcn3_02_soc.max_avg_sdp_bw_use_normal_percent / 100));
+
+			if (optimal_dcfclk)
+				*optimal_dcfclk =  bw_from_dram /
+				(dcn3_02_soc.return_bus_width_bytes *
+				 (dcn3_02_soc.max_avg_sdp_bw_use_normal_percent / 100));
+}
+
+void dcn302_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
+{
+	unsigned int i, j;
+	unsigned int num_states = 0;
+
+	unsigned int dcfclk_mhz[DC__VOLTAGE_STATES] = {0};
+	unsigned int dram_speed_mts[DC__VOLTAGE_STATES] = {0};
+	unsigned int optimal_uclk_for_dcfclk_sta_targets[DC__VOLTAGE_STATES] = {0};
+	unsigned int optimal_dcfclk_for_uclk[DC__VOLTAGE_STATES] = {0};
+
+	unsigned int dcfclk_sta_targets[DC__VOLTAGE_STATES] = {694, 875, 1000, 1200};
+	unsigned int num_dcfclk_sta_targets = 4;
+	unsigned int num_uclk_states;
+
+	dc_assert_fp_enabled();
+
+	if (dc->ctx->dc_bios->vram_info.num_chans)
+		dcn3_02_soc.num_chans = dc->ctx->dc_bios->vram_info.num_chans;
+
+	if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes)
+		dcn3_02_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes;
+
+	dcn3_02_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
+	dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
+
+	if (bw_params->clk_table.entries[0].memclk_mhz) {
+		int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, max_phyclk_mhz = 0;
+
+		for (i = 0; i < MAX_NUM_DPM_LVL; i++) {
+			if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz)
+				max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz;
+			if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz)
+				max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz;
+			if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz)
+				max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz;
+			if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz)
+				max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz;
+		}
+		if (!max_dcfclk_mhz)
+			max_dcfclk_mhz = dcn3_02_soc.clock_limits[0].dcfclk_mhz;
+		if (!max_dispclk_mhz)
+			max_dispclk_mhz = dcn3_02_soc.clock_limits[0].dispclk_mhz;
+		if (!max_dppclk_mhz)
+			max_dppclk_mhz = dcn3_02_soc.clock_limits[0].dppclk_mhz;
+		if (!max_phyclk_mhz)
+			max_phyclk_mhz = dcn3_02_soc.clock_limits[0].phyclk_mhz;
+
+		if (max_dcfclk_mhz > dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
+			/* If max DCFCLK is greater than the max DCFCLK STA target, insert into the DCFCLK STA target array */
+			dcfclk_sta_targets[num_dcfclk_sta_targets] = max_dcfclk_mhz;
+			num_dcfclk_sta_targets++;
+		} else if (max_dcfclk_mhz < dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
+			/* If max DCFCLK is less than the max DCFCLK STA target, cap values and remove duplicates */
+			for (i = 0; i < num_dcfclk_sta_targets; i++) {
+				if (dcfclk_sta_targets[i] > max_dcfclk_mhz) {
+					dcfclk_sta_targets[i] = max_dcfclk_mhz;
+					break;
+				}
+			}
+			/* Update size of array since we "removed" duplicates */
+			num_dcfclk_sta_targets = i + 1;
+		}
+
+		num_uclk_states = bw_params->clk_table.num_entries;
+
+		/* Calculate optimal dcfclk for each uclk */
+		for (i = 0; i < num_uclk_states; i++) {
+			dcn302_get_optimal_dcfclk_fclk_for_uclk(bw_params->clk_table.entries[i].memclk_mhz * 16,
+					&optimal_dcfclk_for_uclk[i], NULL);
+			if (optimal_dcfclk_for_uclk[i] < bw_params->clk_table.entries[0].dcfclk_mhz)
+				optimal_dcfclk_for_uclk[i] = bw_params->clk_table.entries[0].dcfclk_mhz;
+		}
+
+		/* Calculate optimal uclk for each dcfclk sta target */
+		for (i = 0; i < num_dcfclk_sta_targets; i++) {
+			for (j = 0; j < num_uclk_states; j++) {
+				if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) {
+					optimal_uclk_for_dcfclk_sta_targets[i] =
+							bw_params->clk_table.entries[j].memclk_mhz * 16;
+					break;
+				}
+			}
+		}
+
+		i = 0;
+		j = 0;
+		/* create the final dcfclk and uclk table */
+		while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) {
+			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) {
+				dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
+				dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
+			} else {
+				if (j < num_uclk_states && optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) {
+					dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j];
+					dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
+				} else {
+					j = num_uclk_states;
+				}
+			}
+		}
+
+		while (i < num_dcfclk_sta_targets && num_states < DC__VOLTAGE_STATES) {
+			dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
+			dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
+		}
+
+		while (j < num_uclk_states && num_states < DC__VOLTAGE_STATES &&
+				optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) {
+			dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j];
+			dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
+		}
+
+		dcn3_02_soc.num_states = num_states;
+		for (i = 0; i < dcn3_02_soc.num_states; i++) {
+			dcn3_02_soc.clock_limits[i].state = i;
+			dcn3_02_soc.clock_limits[i].dcfclk_mhz = dcfclk_mhz[i];
+			dcn3_02_soc.clock_limits[i].fabricclk_mhz = dcfclk_mhz[i];
+			dcn3_02_soc.clock_limits[i].dram_speed_mts = dram_speed_mts[i];
+
+			/* Fill all states with max values of all other clocks */
+			dcn3_02_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
+			dcn3_02_soc.clock_limits[i].dppclk_mhz  = max_dppclk_mhz;
+			dcn3_02_soc.clock_limits[i].phyclk_mhz  = max_phyclk_mhz;
+			/* Populate from bw_params for DTBCLK, SOCCLK */
+			if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0)
+				dcn3_02_soc.clock_limits[i].dtbclk_mhz  = dcn3_02_soc.clock_limits[i-1].dtbclk_mhz;
+			else
+				dcn3_02_soc.clock_limits[i].dtbclk_mhz  = bw_params->clk_table.entries[i].dtbclk_mhz;
+			if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0)
+				dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[i-1].socclk_mhz;
+			else
+				dcn3_02_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz;
+			/* These clocks cannot come from bw_params, always fill from dcn3_02_soc[1] */
+			/* FCLK, PHYCLK_D18, DSCCLK */
+			dcn3_02_soc.clock_limits[i].phyclk_d18_mhz = dcn3_02_soc.clock_limits[0].phyclk_d18_mhz;
+			dcn3_02_soc.clock_limits[i].dscclk_mhz = dcn3_02_soc.clock_limits[0].dscclk_mhz;
+		}
+		/* re-init DML with updated bb */
+		dml_init_instance(&dc->dml, &dcn3_02_soc, &dcn3_02_ip, DML_PROJECT_DCN30);
+		if (dc->current_state)
+			dml_init_instance(&dc->current_state->bw_ctx.dml, &dcn3_02_soc, &dcn3_02_ip, DML_PROJECT_DCN30);
+	}
+}
+
+void dcn302_fpu_init_soc_bounding_box(struct bp_soc_bb_info bb_info)
+{
+
+			dc_assert_fp_enabled();
+
+			if (bb_info.dram_clock_change_latency_100ns > 0)
+				dcn3_02_soc.dram_clock_change_latency_us =
+					bb_info.dram_clock_change_latency_100ns * 10;
+
+			if (bb_info.dram_sr_enter_exit_latency_100ns > 0)
+				dcn3_02_soc.sr_enter_plus_exit_time_us =
+					bb_info.dram_sr_enter_exit_latency_100ns * 10;
+
+			if (bb_info.dram_sr_exit_latency_100ns > 0)
+				dcn3_02_soc.sr_exit_time_us =
+					bb_info.dram_sr_exit_latency_100ns * 10;
+}
+
+