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, 1056 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
new file mode 100644
index 000000000..6ccf477d1
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -0,0 +1,1056 @@
+/*
+ * Copyright 2019 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 "dc.h"
+#include "dc_dmub_srv.h"
+#include "../dmub/dmub_srv.h"
+#include "dm_helpers.h"
+#include "dc_hw_types.h"
+#include "core_types.h"
+#include "../basics/conversion.h"
+#include "cursor_reg_cache.h"
+
+#define CTX dc_dmub_srv->ctx
+#define DC_LOGGER CTX->logger
+
+static void dc_dmub_srv_construct(struct dc_dmub_srv *dc_srv, struct dc *dc,
+				  struct dmub_srv *dmub)
+{
+	dc_srv->dmub = dmub;
+	dc_srv->ctx = dc->ctx;
+}
+
+struct dc_dmub_srv *dc_dmub_srv_create(struct dc *dc, struct dmub_srv *dmub)
+{
+	struct dc_dmub_srv *dc_srv =
+		kzalloc(sizeof(struct dc_dmub_srv), GFP_KERNEL);
+
+	if (dc_srv == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dc_dmub_srv_construct(dc_srv, dc, dmub);
+
+	return dc_srv;
+}
+
+void dc_dmub_srv_destroy(struct dc_dmub_srv **dmub_srv)
+{
+	if (*dmub_srv) {
+		kfree(*dmub_srv);
+		*dmub_srv = NULL;
+	}
+}
+
+void dc_dmub_srv_cmd_queue(struct dc_dmub_srv *dc_dmub_srv,
+			   union dmub_rb_cmd *cmd)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_cmd_queue(dmub, cmd);
+	if (status == DMUB_STATUS_OK)
+		return;
+
+	if (status != DMUB_STATUS_QUEUE_FULL)
+		goto error;
+
+	/* Execute and wait for queue to become empty again. */
+	dc_dmub_srv_cmd_execute(dc_dmub_srv);
+	dc_dmub_srv_wait_idle(dc_dmub_srv);
+
+	/* Requeue the command. */
+	status = dmub_srv_cmd_queue(dmub, cmd);
+	if (status == DMUB_STATUS_OK)
+		return;
+
+error:
+	DC_ERROR("Error queuing DMUB command: status=%d\n", status);
+	dc_dmub_srv_log_diagnostic_data(dc_dmub_srv);
+}
+
+void dc_dmub_srv_cmd_execute(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_cmd_execute(dmub);
+	if (status != DMUB_STATUS_OK) {
+		DC_ERROR("Error starting DMUB execution: status=%d\n", status);
+		dc_dmub_srv_log_diagnostic_data(dc_dmub_srv);
+	}
+}
+
+void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_wait_for_idle(dmub, 100000);
+	if (status != DMUB_STATUS_OK) {
+		DC_ERROR("Error waiting for DMUB idle: status=%d\n", status);
+		dc_dmub_srv_log_diagnostic_data(dc_dmub_srv);
+	}
+}
+
+void dc_dmub_srv_clear_inbox0_ack(struct dc_dmub_srv *dmub_srv)
+{
+	struct dmub_srv *dmub = dmub_srv->dmub;
+	struct dc_context *dc_ctx = dmub_srv->ctx;
+	enum dmub_status status = DMUB_STATUS_OK;
+
+	status = dmub_srv_clear_inbox0_ack(dmub);
+	if (status != DMUB_STATUS_OK) {
+		DC_ERROR("Error clearing INBOX0 ack: status=%d\n", status);
+		dc_dmub_srv_log_diagnostic_data(dmub_srv);
+	}
+}
+
+void dc_dmub_srv_wait_for_inbox0_ack(struct dc_dmub_srv *dmub_srv)
+{
+	struct dmub_srv *dmub = dmub_srv->dmub;
+	struct dc_context *dc_ctx = dmub_srv->ctx;
+	enum dmub_status status = DMUB_STATUS_OK;
+
+	status = dmub_srv_wait_for_inbox0_ack(dmub, 100000);
+	if (status != DMUB_STATUS_OK) {
+		DC_ERROR("Error waiting for INBOX0 HW Lock Ack\n");
+		dc_dmub_srv_log_diagnostic_data(dmub_srv);
+	}
+}
+
+void dc_dmub_srv_send_inbox0_cmd(struct dc_dmub_srv *dmub_srv,
+		union dmub_inbox0_data_register data)
+{
+	struct dmub_srv *dmub = dmub_srv->dmub;
+	struct dc_context *dc_ctx = dmub_srv->ctx;
+	enum dmub_status status = DMUB_STATUS_OK;
+
+	status = dmub_srv_send_inbox0_cmd(dmub, data);
+	if (status != DMUB_STATUS_OK) {
+		DC_ERROR("Error sending INBOX0 cmd\n");
+		dc_dmub_srv_log_diagnostic_data(dmub_srv);
+	}
+}
+
+bool dc_dmub_srv_cmd_with_reply_data(struct dc_dmub_srv *dc_dmub_srv, union dmub_rb_cmd *cmd)
+{
+	struct dmub_srv *dmub;
+	enum dmub_status status;
+
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
+		return false;
+
+	dmub = dc_dmub_srv->dmub;
+
+	status = dmub_srv_cmd_with_reply_data(dmub, cmd);
+	if (status != DMUB_STATUS_OK) {
+		DC_LOG_DEBUG("No reply for DMUB command: status=%d\n", status);
+		return false;
+	}
+
+	return true;
+}
+
+void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	for (;;) {
+		/* Wait up to a second for PHY init. */
+		status = dmub_srv_wait_for_phy_init(dmub, 1000000);
+		if (status == DMUB_STATUS_OK)
+			/* Initialization OK */
+			break;
+
+		DC_ERROR("DMCUB PHY init failed: status=%d\n", status);
+		ASSERT(0);
+
+		if (status != DMUB_STATUS_TIMEOUT)
+			/*
+			 * Server likely initialized or we don't have
+			 * DMCUB HW support - this won't end.
+			 */
+			break;
+
+		/* Continue spinning so we don't hang the ASIC. */
+	}
+}
+
+bool dc_dmub_srv_notify_stream_mask(struct dc_dmub_srv *dc_dmub_srv,
+				    unsigned int stream_mask)
+{
+	struct dmub_srv *dmub;
+	const uint32_t timeout = 30;
+
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
+		return false;
+
+	dmub = dc_dmub_srv->dmub;
+
+	return dmub_srv_send_gpint_command(
+		       dmub, DMUB_GPINT__IDLE_OPT_NOTIFY_STREAM_MASK,
+		       stream_mask, timeout) == DMUB_STATUS_OK;
+}
+
+bool dc_dmub_srv_is_restore_required(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub;
+	struct dc_context *dc_ctx;
+	union dmub_fw_boot_status boot_status;
+	enum dmub_status status;
+
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
+		return false;
+
+	dmub = dc_dmub_srv->dmub;
+	dc_ctx = dc_dmub_srv->ctx;
+
+	status = dmub_srv_get_fw_boot_status(dmub, &boot_status);
+	if (status != DMUB_STATUS_OK) {
+		DC_ERROR("Error querying DMUB boot status: error=%d\n", status);
+		return false;
+	}
+
+	return boot_status.bits.restore_required;
+}
+
+bool dc_dmub_srv_get_dmub_outbox0_msg(const struct dc *dc, struct dmcub_trace_buf_entry *entry)
+{
+	struct dmub_srv *dmub = dc->ctx->dmub_srv->dmub;
+	return dmub_srv_get_outbox0_msg(dmub, entry);
+}
+
+void dc_dmub_trace_event_control(struct dc *dc, bool enable)
+{
+	dm_helpers_dmub_outbox_interrupt_control(dc->ctx, enable);
+}
+
+void dc_dmub_srv_drr_update_cmd(struct dc *dc, uint32_t tg_inst, uint32_t vtotal_min, uint32_t vtotal_max)
+{
+	union dmub_rb_cmd cmd = { 0 };
+
+	cmd.drr_update.header.type = DMUB_CMD__FW_ASSISTED_MCLK_SWITCH;
+	cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_DRR_UPDATE;
+	cmd.drr_update.dmub_optc_state_req.v_total_max = vtotal_max;
+	cmd.drr_update.dmub_optc_state_req.v_total_min = vtotal_min;
+	cmd.drr_update.dmub_optc_state_req.tg_inst = tg_inst;
+
+	cmd.drr_update.header.payload_bytes = sizeof(cmd.drr_update) - sizeof(cmd.drr_update.header);
+
+	// Send the command to the DMCUB.
+	dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
+	dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->ctx->dmub_srv);
+}
+
+void dc_dmub_srv_set_drr_manual_trigger_cmd(struct dc *dc, uint32_t tg_inst)
+{
+	union dmub_rb_cmd cmd = { 0 };
+
+	cmd.drr_update.header.type = DMUB_CMD__FW_ASSISTED_MCLK_SWITCH;
+	cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_SET_MANUAL_TRIGGER;
+	cmd.drr_update.dmub_optc_state_req.tg_inst = tg_inst;
+
+	cmd.drr_update.header.payload_bytes = sizeof(cmd.drr_update) - sizeof(cmd.drr_update.header);
+
+	// Send the command to the DMCUB.
+	dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
+	dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->ctx->dmub_srv);
+}
+
+static uint8_t dc_dmub_srv_get_pipes_for_stream(struct dc *dc, struct dc_stream_state *stream)
+{
+	uint8_t pipes = 0;
+	int i = 0;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (pipe->stream == stream && pipe->stream_res.tg)
+			pipes = i;
+	}
+	return pipes;
+}
+
+static int dc_dmub_srv_get_timing_generator_offset(struct dc *dc, struct dc_stream_state *stream)
+{
+	int  tg_inst = 0;
+	int i = 0;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (pipe->stream == stream && pipe->stream_res.tg) {
+			tg_inst = pipe->stream_res.tg->inst;
+			break;
+		}
+	}
+	return tg_inst;
+}
+
+bool dc_dmub_srv_p_state_delegate(struct dc *dc, bool should_manage_pstate, struct dc_state *context)
+{
+	union dmub_rb_cmd cmd = { 0 };
+	struct dmub_cmd_fw_assisted_mclk_switch_config *config_data = &cmd.fw_assisted_mclk_switch.config_data;
+	int i = 0;
+	int ramp_up_num_steps = 1; // TODO: Ramp is currently disabled. Reenable it.
+	uint8_t visual_confirm_enabled;
+
+	if (dc == NULL)
+		return false;
+
+	visual_confirm_enabled = dc->debug.visual_confirm == VISUAL_CONFIRM_FAMS;
+
+	// Format command.
+	cmd.fw_assisted_mclk_switch.header.type = DMUB_CMD__FW_ASSISTED_MCLK_SWITCH;
+	cmd.fw_assisted_mclk_switch.header.sub_type = DMUB_CMD__FAMS_SETUP_FW_CTRL;
+	cmd.fw_assisted_mclk_switch.config_data.fams_enabled = should_manage_pstate;
+	cmd.fw_assisted_mclk_switch.config_data.visual_confirm_enabled = visual_confirm_enabled;
+
+	for (i = 0; context && i < context->stream_count; i++) {
+		struct dc_stream_state *stream = context->streams[i];
+		uint8_t min_refresh_in_hz = (stream->timing.min_refresh_in_uhz + 999999) / 1000000;
+		int  tg_inst = dc_dmub_srv_get_timing_generator_offset(dc, stream);
+
+		config_data->pipe_data[tg_inst].pix_clk_100hz = stream->timing.pix_clk_100hz;
+		config_data->pipe_data[tg_inst].min_refresh_in_hz = min_refresh_in_hz;
+		config_data->pipe_data[tg_inst].max_ramp_step = ramp_up_num_steps;
+		config_data->pipe_data[tg_inst].pipes = dc_dmub_srv_get_pipes_for_stream(dc, stream);
+	}
+
+	cmd.fw_assisted_mclk_switch.header.payload_bytes =
+		sizeof(cmd.fw_assisted_mclk_switch) - sizeof(cmd.fw_assisted_mclk_switch.header);
+
+	// Send the command to the DMCUB.
+	dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
+	dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->ctx->dmub_srv);
+
+	return true;
+}
+
+void dc_dmub_srv_query_caps_cmd(struct dmub_srv *dmub)
+{
+	union dmub_rb_cmd cmd = { 0 };
+	enum dmub_status status;
+
+	if (!dmub) {
+		return;
+	}
+
+	memset(&cmd, 0, sizeof(cmd));
+
+	/* Prepare fw command */
+	cmd.query_feature_caps.header.type = DMUB_CMD__QUERY_FEATURE_CAPS;
+	cmd.query_feature_caps.header.sub_type = 0;
+	cmd.query_feature_caps.header.ret_status = 1;
+	cmd.query_feature_caps.header.payload_bytes = sizeof(struct dmub_cmd_query_feature_caps_data);
+
+	/* Send command to fw */
+	status = dmub_srv_cmd_with_reply_data(dmub, &cmd);
+
+	ASSERT(status == DMUB_STATUS_OK);
+
+	/* If command was processed, copy feature caps to dmub srv */
+	if (status == DMUB_STATUS_OK &&
+	    cmd.query_feature_caps.header.ret_status == 0) {
+		memcpy(&dmub->feature_caps,
+		       &cmd.query_feature_caps.query_feature_caps_data,
+		       sizeof(struct dmub_feature_caps));
+	}
+}
+
+void dc_dmub_srv_get_visual_confirm_color_cmd(struct dc *dc, struct pipe_ctx *pipe_ctx)
+{
+	union dmub_rb_cmd cmd = { 0 };
+	enum dmub_status status;
+	unsigned int panel_inst = 0;
+
+	dc_get_edp_link_panel_inst(dc, pipe_ctx->stream->link, &panel_inst);
+
+	memset(&cmd, 0, sizeof(cmd));
+
+	// Prepare fw command
+	cmd.visual_confirm_color.header.type = DMUB_CMD__GET_VISUAL_CONFIRM_COLOR;
+	cmd.visual_confirm_color.header.sub_type = 0;
+	cmd.visual_confirm_color.header.ret_status = 1;
+	cmd.visual_confirm_color.header.payload_bytes = sizeof(struct dmub_cmd_visual_confirm_color_data);
+	cmd.visual_confirm_color.visual_confirm_color_data.visual_confirm_color.panel_inst = panel_inst;
+
+	// Send command to fw
+	status = dmub_srv_cmd_with_reply_data(dc->ctx->dmub_srv->dmub, &cmd);
+
+	ASSERT(status == DMUB_STATUS_OK);
+
+	// If command was processed, copy feature caps to dmub srv
+	if (status == DMUB_STATUS_OK &&
+		cmd.visual_confirm_color.header.ret_status == 0) {
+		memcpy(&dc->ctx->dmub_srv->dmub->visual_confirm_color,
+			&cmd.visual_confirm_color.visual_confirm_color_data,
+			sizeof(struct dmub_visual_confirm_color));
+	}
+}
+
+#ifdef CONFIG_DRM_AMD_DC_DCN
+/**
+ * populate_subvp_cmd_drr_info - Helper to populate DRR pipe info for the DMCUB subvp command
+ *
+ * @dc: [in] current dc state
+ * @subvp_pipe: [in] pipe_ctx for the SubVP pipe
+ * @vblank_pipe: [in] pipe_ctx for the DRR pipe
+ * @pipe_data: [in] Pipe data which stores the VBLANK/DRR info
+ *
+ * Populate the DMCUB SubVP command with DRR pipe info. All the information
+ * required for calculating the SubVP + DRR microschedule is populated here.
+ *
+ * High level algorithm:
+ * 1. Get timing for SubVP pipe, phantom pipe, and DRR pipe
+ * 2. Calculate the min and max vtotal which supports SubVP + DRR microschedule
+ * 3. Populate the drr_info with the min and max supported vtotal values
+ */
+static void populate_subvp_cmd_drr_info(struct dc *dc,
+		struct pipe_ctx *subvp_pipe,
+		struct pipe_ctx *vblank_pipe,
+		struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data)
+{
+	struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing;
+	struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing;
+	struct dc_crtc_timing *drr_timing = &vblank_pipe->stream->timing;
+	uint16_t drr_frame_us = 0;
+	uint16_t min_drr_supported_us = 0;
+	uint16_t max_drr_supported_us = 0;
+	uint16_t max_drr_vblank_us = 0;
+	uint16_t max_drr_mallregion_us = 0;
+	uint16_t mall_region_us = 0;
+	uint16_t prefetch_us = 0;
+	uint16_t subvp_active_us = 0;
+	uint16_t drr_active_us = 0;
+	uint16_t min_vtotal_supported = 0;
+	uint16_t max_vtotal_supported = 0;
+
+	pipe_data->pipe_config.vblank_data.drr_info.drr_in_use = true;
+	pipe_data->pipe_config.vblank_data.drr_info.use_ramping = false; // for now don't use ramping
+	pipe_data->pipe_config.vblank_data.drr_info.drr_window_size_ms = 4; // hardcode 4ms DRR window for now
+
+	drr_frame_us = div64_u64(((uint64_t)drr_timing->v_total * drr_timing->h_total * 1000000),
+			(((uint64_t)drr_timing->pix_clk_100hz * 100)));
+	// P-State allow width and FW delays already included phantom_timing->v_addressable
+	mall_region_us = div64_u64(((uint64_t)phantom_timing->v_addressable * phantom_timing->h_total * 1000000),
+			(((uint64_t)phantom_timing->pix_clk_100hz * 100)));
+	min_drr_supported_us = drr_frame_us + mall_region_us + SUBVP_DRR_MARGIN_US;
+	min_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * min_drr_supported_us),
+			(((uint64_t)drr_timing->h_total * 1000000)));
+
+	prefetch_us = div64_u64(((uint64_t)(phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total * 1000000),
+			(((uint64_t)phantom_timing->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
+	subvp_active_us = div64_u64(((uint64_t)main_timing->v_addressable * main_timing->h_total * 1000000),
+			(((uint64_t)main_timing->pix_clk_100hz * 100)));
+	drr_active_us = div64_u64(((uint64_t)drr_timing->v_addressable * drr_timing->h_total * 1000000),
+			(((uint64_t)drr_timing->pix_clk_100hz * 100)));
+	max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us -
+			dc->caps.subvp_fw_processing_delay_us - drr_active_us), 2) + drr_active_us;
+	max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us - dc->caps.subvp_fw_processing_delay_us;
+	max_drr_supported_us = max_drr_vblank_us > max_drr_mallregion_us ? max_drr_vblank_us : max_drr_mallregion_us;
+	max_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * max_drr_supported_us),
+			(((uint64_t)drr_timing->h_total * 1000000)));
+
+	/* When calculating the max vtotal supported for SubVP + DRR cases, add
+	 * margin due to possible rounding errors (being off by 1 line in the
+	 * FW calculation can incorrectly push the P-State switch to wait 1 frame
+	 * longer).
+	 */
+	max_vtotal_supported = max_vtotal_supported - dc->caps.subvp_drr_max_vblank_margin_us;
+
+	pipe_data->pipe_config.vblank_data.drr_info.min_vtotal_supported = min_vtotal_supported;
+	pipe_data->pipe_config.vblank_data.drr_info.max_vtotal_supported = max_vtotal_supported;
+	pipe_data->pipe_config.vblank_data.drr_info.drr_vblank_start_margin = dc->caps.subvp_drr_vblank_start_margin_us;
+}
+
+/**
+ * populate_subvp_cmd_vblank_pipe_info - Helper to populate VBLANK pipe info for the DMUB subvp command
+ *
+ * @dc: [in] current dc state
+ * @context: [in] new dc state
+ * @cmd: [in] DMUB cmd to be populated with SubVP info
+ * @vblank_pipe: [in] pipe_ctx for the VBLANK pipe
+ * @cmd_pipe_index: [in] index for the pipe array in DMCUB SubVP cmd
+ *
+ * Populate the DMCUB SubVP command with VBLANK pipe info. All the information
+ * required to calculate the microschedule for SubVP + VBLANK case is stored in
+ * the pipe_data (subvp_data and vblank_data).  Also check if the VBLANK pipe
+ * is a DRR display -- if it is make a call to populate drr_info.
+ */
+static void populate_subvp_cmd_vblank_pipe_info(struct dc *dc,
+		struct dc_state *context,
+		union dmub_rb_cmd *cmd,
+		struct pipe_ctx *vblank_pipe,
+		uint8_t cmd_pipe_index)
+{
+	uint32_t i;
+	struct pipe_ctx *pipe = NULL;
+	struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data =
+			&cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[cmd_pipe_index];
+
+	// Find the SubVP pipe
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+
+		// We check for master pipe, but it shouldn't matter since we only need
+		// the pipe for timing info (stream should be same for any pipe splits)
+		if (!pipe->stream || !pipe->plane_state || pipe->top_pipe || pipe->prev_odm_pipe)
+			continue;
+
+		// Find the SubVP pipe
+		if (pipe->stream->mall_stream_config.type == SUBVP_MAIN)
+			break;
+	}
+
+	pipe_data->mode = VBLANK;
+	pipe_data->pipe_config.vblank_data.pix_clk_100hz = vblank_pipe->stream->timing.pix_clk_100hz;
+	pipe_data->pipe_config.vblank_data.vblank_start = vblank_pipe->stream->timing.v_total -
+							vblank_pipe->stream->timing.v_front_porch;
+	pipe_data->pipe_config.vblank_data.vtotal = vblank_pipe->stream->timing.v_total;
+	pipe_data->pipe_config.vblank_data.htotal = vblank_pipe->stream->timing.h_total;
+	pipe_data->pipe_config.vblank_data.vblank_pipe_index = vblank_pipe->pipe_idx;
+	pipe_data->pipe_config.vblank_data.vstartup_start = vblank_pipe->pipe_dlg_param.vstartup_start;
+	pipe_data->pipe_config.vblank_data.vblank_end =
+			vblank_pipe->stream->timing.v_total - vblank_pipe->stream->timing.v_front_porch - vblank_pipe->stream->timing.v_addressable;
+
+	if (vblank_pipe->stream->ignore_msa_timing_param)
+		populate_subvp_cmd_drr_info(dc, pipe, vblank_pipe, pipe_data);
+}
+
+/**
+ * update_subvp_prefetch_end_to_mall_start - Helper for SubVP + SubVP case
+ *
+ * @dc: [in] current dc state
+ * @context: [in] new dc state
+ * @cmd: [in] DMUB cmd to be populated with SubVP info
+ * @subvp_pipes: [in] Array of SubVP pipes (should always be length 2)
+ *
+ * For SubVP + SubVP, we use a single vertical interrupt to start the
+ * microschedule for both SubVP pipes. In order for this to work correctly, the
+ * MALL REGION of both SubVP pipes must start at the same time. This function
+ * lengthens the prefetch end to mall start delay of the SubVP pipe that has
+ * the shorter prefetch so that both MALL REGION's will start at the same time.
+ */
+static void update_subvp_prefetch_end_to_mall_start(struct dc *dc,
+		struct dc_state *context,
+		union dmub_rb_cmd *cmd,
+		struct pipe_ctx *subvp_pipes[])
+{
+	uint32_t subvp0_prefetch_us = 0;
+	uint32_t subvp1_prefetch_us = 0;
+	uint32_t prefetch_delta_us = 0;
+	struct dc_crtc_timing *phantom_timing0 = &subvp_pipes[0]->stream->mall_stream_config.paired_stream->timing;
+	struct dc_crtc_timing *phantom_timing1 = &subvp_pipes[1]->stream->mall_stream_config.paired_stream->timing;
+	struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data = NULL;
+
+	subvp0_prefetch_us = div64_u64(((uint64_t)(phantom_timing0->v_total - phantom_timing0->v_front_porch) *
+			(uint64_t)phantom_timing0->h_total * 1000000),
+			(((uint64_t)phantom_timing0->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
+	subvp1_prefetch_us = div64_u64(((uint64_t)(phantom_timing1->v_total - phantom_timing1->v_front_porch) *
+			(uint64_t)phantom_timing1->h_total * 1000000),
+			(((uint64_t)phantom_timing1->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
+
+	// Whichever SubVP PIPE has the smaller prefetch (including the prefetch end to mall start time)
+	// should increase it's prefetch time to match the other
+	if (subvp0_prefetch_us > subvp1_prefetch_us) {
+		pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[1];
+		prefetch_delta_us = subvp0_prefetch_us - subvp1_prefetch_us;
+		pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
+				div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) *
+					((uint64_t)phantom_timing1->pix_clk_100hz * 100) + ((uint64_t)phantom_timing1->h_total * 1000000 - 1)),
+					((uint64_t)phantom_timing1->h_total * 1000000));
+
+	} else if (subvp1_prefetch_us >  subvp0_prefetch_us) {
+		pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[0];
+		prefetch_delta_us = subvp1_prefetch_us - subvp0_prefetch_us;
+		pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
+				div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) *
+					((uint64_t)phantom_timing0->pix_clk_100hz * 100) + ((uint64_t)phantom_timing0->h_total * 1000000 - 1)),
+					((uint64_t)phantom_timing0->h_total * 1000000));
+	}
+}
+
+/**
+ * populate_subvp_cmd_pipe_info - Helper to populate the SubVP pipe info for the DMUB subvp command
+ *
+ * @dc: [in] current dc state
+ * @context: [in] new dc state
+ * @cmd: [in] DMUB cmd to be populated with SubVP info
+ * @subvp_pipe: [in] pipe_ctx for the SubVP pipe
+ * @cmd_pipe_index: [in] index for the pipe array in DMCUB SubVP cmd
+ *
+ * Populate the DMCUB SubVP command with SubVP pipe info. All the information
+ * required to calculate the microschedule for the SubVP pipe is stored in the
+ * pipe_data of the DMCUB SubVP command.
+ */
+static void populate_subvp_cmd_pipe_info(struct dc *dc,
+		struct dc_state *context,
+		union dmub_rb_cmd *cmd,
+		struct pipe_ctx *subvp_pipe,
+		uint8_t cmd_pipe_index)
+{
+	uint32_t j;
+	struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data =
+			&cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[cmd_pipe_index];
+	struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing;
+	struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing;
+	uint32_t out_num_stream, out_den_stream, out_num_plane, out_den_plane, out_num, out_den;
+
+	pipe_data->mode = SUBVP;
+	pipe_data->pipe_config.subvp_data.pix_clk_100hz = subvp_pipe->stream->timing.pix_clk_100hz;
+	pipe_data->pipe_config.subvp_data.htotal = subvp_pipe->stream->timing.h_total;
+	pipe_data->pipe_config.subvp_data.vtotal = subvp_pipe->stream->timing.v_total;
+	pipe_data->pipe_config.subvp_data.main_vblank_start =
+			main_timing->v_total - main_timing->v_front_porch;
+	pipe_data->pipe_config.subvp_data.main_vblank_end =
+			main_timing->v_total - main_timing->v_front_porch - main_timing->v_addressable;
+	pipe_data->pipe_config.subvp_data.mall_region_lines = phantom_timing->v_addressable;
+	pipe_data->pipe_config.subvp_data.main_pipe_index = subvp_pipe->pipe_idx;
+	pipe_data->pipe_config.subvp_data.is_drr = subvp_pipe->stream->ignore_msa_timing_param;
+
+	/* Calculate the scaling factor from the src and dst height.
+	 * e.g. If 3840x2160 being downscaled to 1920x1080, the scaling factor is 1/2.
+	 * Reduce the fraction 1080/2160 = 1/2 for the "scaling factor"
+	 *
+	 * Make sure to combine stream and plane scaling together.
+	 */
+	reduce_fraction(subvp_pipe->stream->src.height, subvp_pipe->stream->dst.height,
+			&out_num_stream, &out_den_stream);
+	reduce_fraction(subvp_pipe->plane_state->src_rect.height, subvp_pipe->plane_state->dst_rect.height,
+			&out_num_plane, &out_den_plane);
+	reduce_fraction(out_num_stream * out_num_plane, out_den_stream * out_den_plane, &out_num, &out_den);
+	pipe_data->pipe_config.subvp_data.scale_factor_numerator = out_num;
+	pipe_data->pipe_config.subvp_data.scale_factor_denominator = out_den;
+
+	// Prefetch lines is equal to VACTIVE + BP + VSYNC
+	pipe_data->pipe_config.subvp_data.prefetch_lines =
+			phantom_timing->v_total - phantom_timing->v_front_porch;
+
+	// Round up
+	pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
+			div64_u64(((uint64_t)dc->caps.subvp_prefetch_end_to_mall_start_us * ((uint64_t)phantom_timing->pix_clk_100hz * 100) +
+					((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000));
+	pipe_data->pipe_config.subvp_data.processing_delay_lines =
+			div64_u64(((uint64_t)(dc->caps.subvp_fw_processing_delay_us) * ((uint64_t)phantom_timing->pix_clk_100hz * 100) +
+					((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000));
+
+	if (subvp_pipe->bottom_pipe) {
+		pipe_data->pipe_config.subvp_data.main_split_pipe_index = subvp_pipe->bottom_pipe->pipe_idx;
+	} else if (subvp_pipe->next_odm_pipe) {
+		pipe_data->pipe_config.subvp_data.main_split_pipe_index = subvp_pipe->next_odm_pipe->pipe_idx;
+	} else {
+		pipe_data->pipe_config.subvp_data.main_split_pipe_index = 0;
+	}
+
+	// Find phantom pipe index based on phantom stream
+	for (j = 0; j < dc->res_pool->pipe_count; j++) {
+		struct pipe_ctx *phantom_pipe = &context->res_ctx.pipe_ctx[j];
+
+		if (phantom_pipe->stream == subvp_pipe->stream->mall_stream_config.paired_stream) {
+			pipe_data->pipe_config.subvp_data.phantom_pipe_index = phantom_pipe->pipe_idx;
+			if (phantom_pipe->bottom_pipe) {
+				pipe_data->pipe_config.subvp_data.phantom_split_pipe_index = phantom_pipe->bottom_pipe->pipe_idx;
+			} else if (phantom_pipe->next_odm_pipe) {
+				pipe_data->pipe_config.subvp_data.phantom_split_pipe_index = phantom_pipe->next_odm_pipe->pipe_idx;
+			} else {
+				pipe_data->pipe_config.subvp_data.phantom_split_pipe_index = 0;
+			}
+			break;
+		}
+	}
+}
+
+/**
+ * dc_dmub_setup_subvp_dmub_command - Populate the DMCUB SubVP command
+ *
+ * @dc: [in] current dc state
+ * @context: [in] new dc state
+ * @cmd: [in] DMUB cmd to be populated with SubVP info
+ *
+ * This function loops through each pipe and populates the DMUB SubVP CMD info
+ * based on the pipe (e.g. SubVP, VBLANK).
+ */
+void dc_dmub_setup_subvp_dmub_command(struct dc *dc,
+		struct dc_state *context,
+		bool enable)
+{
+	uint8_t cmd_pipe_index = 0;
+	uint32_t i, pipe_idx;
+	uint8_t subvp_count = 0;
+	union dmub_rb_cmd cmd;
+	struct pipe_ctx *subvp_pipes[2];
+	uint32_t wm_val_refclk = 0;
+
+	memset(&cmd, 0, sizeof(cmd));
+	// FW command for SUBVP
+	cmd.fw_assisted_mclk_switch_v2.header.type = DMUB_CMD__FW_ASSISTED_MCLK_SWITCH;
+	cmd.fw_assisted_mclk_switch_v2.header.sub_type = DMUB_CMD__HANDLE_SUBVP_CMD;
+	cmd.fw_assisted_mclk_switch_v2.header.payload_bytes =
+			sizeof(cmd.fw_assisted_mclk_switch_v2) - sizeof(cmd.fw_assisted_mclk_switch_v2.header);
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe->stream)
+			continue;
+
+		/* For SubVP pipe count, only count the top most (ODM / MPC) pipe
+		 */
+		if (pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe &&
+				pipe->stream->mall_stream_config.type == SUBVP_MAIN)
+			subvp_pipes[subvp_count++] = pipe;
+	}
+
+	if (enable) {
+		// For each pipe that is a "main" SUBVP pipe, fill in pipe data for DMUB SUBVP cmd
+		for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+			if (!pipe->stream)
+				continue;
+
+			/* When populating subvp cmd info, only pass in the top most (ODM / MPC) pipe.
+			 * Any ODM or MPC splits being used in SubVP will be handled internally in
+			 * populate_subvp_cmd_pipe_info
+			 */
+			if (pipe->plane_state && pipe->stream->mall_stream_config.paired_stream &&
+					!pipe->top_pipe && !pipe->prev_odm_pipe &&
+					pipe->stream->mall_stream_config.type == SUBVP_MAIN) {
+				populate_subvp_cmd_pipe_info(dc, context, &cmd, pipe, cmd_pipe_index++);
+			} else if (pipe->plane_state && pipe->stream->mall_stream_config.type == SUBVP_NONE) {
+				// Don't need to check for ActiveDRAMClockChangeMargin < 0, not valid in cases where
+				// we run through DML without calculating "natural" P-state support
+				populate_subvp_cmd_vblank_pipe_info(dc, context, &cmd, pipe, cmd_pipe_index++);
+
+			}
+			pipe_idx++;
+		}
+		if (subvp_count == 2) {
+			update_subvp_prefetch_end_to_mall_start(dc, context, &cmd, subvp_pipes);
+		}
+		cmd.fw_assisted_mclk_switch_v2.config_data.pstate_allow_width_us = dc->caps.subvp_pstate_allow_width_us;
+		cmd.fw_assisted_mclk_switch_v2.config_data.vertical_int_margin_us = dc->caps.subvp_vertical_int_margin_us;
+
+		// Store the original watermark value for this SubVP config so we can lower it when the
+		// MCLK switch starts
+		wm_val_refclk = context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns *
+				(dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000) / 1000;
+
+		cmd.fw_assisted_mclk_switch_v2.config_data.watermark_a_cache = wm_val_refclk < 0xFFFF ? wm_val_refclk : 0xFFFF;
+	}
+	dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
+	dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->ctx->dmub_srv);
+}
+#endif
+
+bool dc_dmub_srv_get_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv, struct dmub_diagnostic_data *diag_data)
+{
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub || !diag_data)
+		return false;
+	return dmub_srv_get_diagnostic_data(dc_dmub_srv->dmub, diag_data);
+}
+
+void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_diagnostic_data diag_data = {0};
+
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub) {
+		DC_LOG_ERROR("%s: invalid parameters.", __func__);
+		return;
+	}
+
+	if (!dc_dmub_srv_get_diagnostic_data(dc_dmub_srv, &diag_data)) {
+		DC_LOG_ERROR("%s: dc_dmub_srv_get_diagnostic_data failed.", __func__);
+		return;
+	}
+
+	DC_LOG_DEBUG(
+		"DMCUB STATE\n"
+		"    dmcub_version      : %08x\n"
+		"    scratch  [0]       : %08x\n"
+		"    scratch  [1]       : %08x\n"
+		"    scratch  [2]       : %08x\n"
+		"    scratch  [3]       : %08x\n"
+		"    scratch  [4]       : %08x\n"
+		"    scratch  [5]       : %08x\n"
+		"    scratch  [6]       : %08x\n"
+		"    scratch  [7]       : %08x\n"
+		"    scratch  [8]       : %08x\n"
+		"    scratch  [9]       : %08x\n"
+		"    scratch [10]       : %08x\n"
+		"    scratch [11]       : %08x\n"
+		"    scratch [12]       : %08x\n"
+		"    scratch [13]       : %08x\n"
+		"    scratch [14]       : %08x\n"
+		"    scratch [15]       : %08x\n"
+		"    pc                 : %08x\n"
+		"    unk_fault_addr     : %08x\n"
+		"    inst_fault_addr    : %08x\n"
+		"    data_fault_addr    : %08x\n"
+		"    inbox1_rptr        : %08x\n"
+		"    inbox1_wptr        : %08x\n"
+		"    inbox1_size        : %08x\n"
+		"    inbox0_rptr        : %08x\n"
+		"    inbox0_wptr        : %08x\n"
+		"    inbox0_size        : %08x\n"
+		"    is_enabled         : %d\n"
+		"    is_soft_reset      : %d\n"
+		"    is_secure_reset    : %d\n"
+		"    is_traceport_en    : %d\n"
+		"    is_cw0_en          : %d\n"
+		"    is_cw6_en          : %d\n",
+		diag_data.dmcub_version,
+		diag_data.scratch[0],
+		diag_data.scratch[1],
+		diag_data.scratch[2],
+		diag_data.scratch[3],
+		diag_data.scratch[4],
+		diag_data.scratch[5],
+		diag_data.scratch[6],
+		diag_data.scratch[7],
+		diag_data.scratch[8],
+		diag_data.scratch[9],
+		diag_data.scratch[10],
+		diag_data.scratch[11],
+		diag_data.scratch[12],
+		diag_data.scratch[13],
+		diag_data.scratch[14],
+		diag_data.scratch[15],
+		diag_data.pc,
+		diag_data.undefined_address_fault_addr,
+		diag_data.inst_fetch_fault_addr,
+		diag_data.data_write_fault_addr,
+		diag_data.inbox1_rptr,
+		diag_data.inbox1_wptr,
+		diag_data.inbox1_size,
+		diag_data.inbox0_rptr,
+		diag_data.inbox0_wptr,
+		diag_data.inbox0_size,
+		diag_data.is_dmcub_enabled,
+		diag_data.is_dmcub_soft_reset,
+		diag_data.is_dmcub_secure_reset,
+		diag_data.is_traceport_en,
+		diag_data.is_cw0_enabled,
+		diag_data.is_cw6_enabled);
+}
+
+static bool dc_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx)
+{
+	struct pipe_ctx *test_pipe, *split_pipe;
+	const struct scaler_data *scl_data = &pipe_ctx->plane_res.scl_data;
+	struct rect r1 = scl_data->recout, r2, r2_half;
+	int r1_r = r1.x + r1.width, r1_b = r1.y + r1.height, r2_r, r2_b;
+	int cur_layer = pipe_ctx->plane_state->layer_index;
+
+	/**
+	 * Disable the cursor if there's another pipe above this with a
+	 * plane that contains this pipe's viewport to prevent double cursor
+	 * and incorrect scaling artifacts.
+	 */
+	for (test_pipe = pipe_ctx->top_pipe; test_pipe;
+	     test_pipe = test_pipe->top_pipe) {
+		// Skip invisible layer and pipe-split plane on same layer
+		if (!test_pipe->plane_state->visible || test_pipe->plane_state->layer_index == cur_layer)
+			continue;
+
+		r2 = test_pipe->plane_res.scl_data.recout;
+		r2_r = r2.x + r2.width;
+		r2_b = r2.y + r2.height;
+		split_pipe = test_pipe;
+
+		/**
+		 * There is another half plane on same layer because of
+		 * pipe-split, merge together per same height.
+		 */
+		for (split_pipe = pipe_ctx->top_pipe; split_pipe;
+		     split_pipe = split_pipe->top_pipe)
+			if (split_pipe->plane_state->layer_index == test_pipe->plane_state->layer_index) {
+				r2_half = split_pipe->plane_res.scl_data.recout;
+				r2.x = (r2_half.x < r2.x) ? r2_half.x : r2.x;
+				r2.width = r2.width + r2_half.width;
+				r2_r = r2.x + r2.width;
+				break;
+			}
+
+		if (r1.x >= r2.x && r1.y >= r2.y && r1_r <= r2_r && r1_b <= r2_b)
+			return true;
+	}
+
+	return false;
+}
+
+static bool dc_dmub_should_update_cursor_data(struct pipe_ctx *pipe_ctx)
+{
+	if (pipe_ctx->plane_state != NULL) {
+		if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE)
+			return false;
+
+		if (dc_can_pipe_disable_cursor(pipe_ctx))
+			return false;
+	}
+
+	if ((pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 ||
+		pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) &&
+		pipe_ctx->stream->ctx->dce_version >= DCN_VERSION_3_1)
+		return true;
+
+	return false;
+}
+
+static void dc_build_cursor_update_payload0(
+		struct pipe_ctx *pipe_ctx, uint8_t p_idx,
+		struct dmub_cmd_update_cursor_payload0 *payload)
+{
+	struct hubp *hubp = pipe_ctx->plane_res.hubp;
+	unsigned int panel_inst = 0;
+
+	if (!dc_get_edp_link_panel_inst(hubp->ctx->dc,
+		pipe_ctx->stream->link, &panel_inst))
+		return;
+
+	/* Payload: Cursor Rect is built from position & attribute
+	 * x & y are obtained from postion
+	 */
+	payload->cursor_rect.x = hubp->cur_rect.x;
+	payload->cursor_rect.y = hubp->cur_rect.y;
+	/* w & h are obtained from attribute */
+	payload->cursor_rect.width  = hubp->cur_rect.w;
+	payload->cursor_rect.height = hubp->cur_rect.h;
+
+	payload->enable      = hubp->pos.cur_ctl.bits.cur_enable;
+	payload->pipe_idx    = p_idx;
+	payload->cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1;
+	payload->panel_inst  = panel_inst;
+}
+
+static void dc_send_cmd_to_dmu(struct dc_dmub_srv *dmub_srv,
+		union dmub_rb_cmd *cmd)
+{
+	dc_dmub_srv_cmd_queue(dmub_srv, cmd);
+	dc_dmub_srv_cmd_execute(dmub_srv);
+	dc_dmub_srv_wait_idle(dmub_srv);
+}
+
+static void dc_build_cursor_position_update_payload0(
+		struct dmub_cmd_update_cursor_payload0 *pl, const uint8_t p_idx,
+		const struct hubp *hubp, const struct dpp *dpp)
+{
+	/* Hubp */
+	pl->position_cfg.pHubp.cur_ctl.raw  = hubp->pos.cur_ctl.raw;
+	pl->position_cfg.pHubp.position.raw = hubp->pos.position.raw;
+	pl->position_cfg.pHubp.hot_spot.raw = hubp->pos.hot_spot.raw;
+	pl->position_cfg.pHubp.dst_offset.raw = hubp->pos.dst_offset.raw;
+
+	/* dpp */
+	pl->position_cfg.pDpp.cur0_ctl.raw = dpp->pos.cur0_ctl.raw;
+	pl->position_cfg.pipe_idx = p_idx;
+}
+
+static void dc_build_cursor_attribute_update_payload1(
+		struct dmub_cursor_attributes_cfg *pl_A, const uint8_t p_idx,
+		const struct hubp *hubp, const struct dpp *dpp)
+{
+	/* Hubp */
+	pl_A->aHubp.SURFACE_ADDR_HIGH = hubp->att.SURFACE_ADDR_HIGH;
+	pl_A->aHubp.SURFACE_ADDR = hubp->att.SURFACE_ADDR;
+	pl_A->aHubp.cur_ctl.raw  = hubp->att.cur_ctl.raw;
+	pl_A->aHubp.size.raw     = hubp->att.size.raw;
+	pl_A->aHubp.settings.raw = hubp->att.settings.raw;
+
+	/* dpp */
+	pl_A->aDpp.cur0_ctl.raw = dpp->att.cur0_ctl.raw;
+}
+
+/**
+ * dc_send_update_cursor_info_to_dmu - Populate the DMCUB Cursor update info command
+ *
+ * @pCtx: [in] pipe context
+ * @pipe_idx: [in] pipe index
+ *
+ * This function would store the cursor related information and pass it into
+ * dmub
+ */
+void dc_send_update_cursor_info_to_dmu(
+		struct pipe_ctx *pCtx, uint8_t pipe_idx)
+{
+	union dmub_rb_cmd cmd = { 0 };
+	union dmub_cmd_update_cursor_info_data *update_cursor_info =
+					&cmd.update_cursor_info.update_cursor_info_data;
+
+	if (!dc_dmub_should_update_cursor_data(pCtx))
+		return;
+	/*
+	 * Since we use multi_cmd_pending for dmub command, the 2nd command is
+	 * only assigned to store cursor attributes info.
+	 * 1st command can view as 2 parts, 1st is for PSR/Replay data, the other
+	 * is to store cursor position info.
+	 *
+	 * Command heaer type must be the same type if using  multi_cmd_pending.
+	 * Besides, while process 2nd command in DMU, the sub type is useless.
+	 * So it's meanless to pass the sub type header with different type.
+	 */
+
+	{
+		/* Build Payload#0 Header */
+		cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO;
+		cmd.update_cursor_info.header.payload_bytes =
+				sizeof(cmd.update_cursor_info.update_cursor_info_data);
+		cmd.update_cursor_info.header.multi_cmd_pending = 1; /* To combine multi dmu cmd, 1st cmd */
+
+		/* Prepare Payload */
+		dc_build_cursor_update_payload0(pCtx, pipe_idx, &update_cursor_info->payload0);
+
+		dc_build_cursor_position_update_payload0(&update_cursor_info->payload0, pipe_idx,
+				pCtx->plane_res.hubp, pCtx->plane_res.dpp);
+		/* Send update_curosr_info to queue */
+		dc_dmub_srv_cmd_queue(pCtx->stream->ctx->dmub_srv, &cmd);
+	}
+	{
+		/* Build Payload#1 Header */
+		memset(update_cursor_info, 0, sizeof(union dmub_cmd_update_cursor_info_data));
+		cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO;
+		cmd.update_cursor_info.header.payload_bytes = sizeof(struct cursor_attributes_cfg);
+		cmd.update_cursor_info.header.multi_cmd_pending = 0; /* Indicate it's the last command. */
+
+		dc_build_cursor_attribute_update_payload1(
+				&cmd.update_cursor_info.update_cursor_info_data.payload1.attribute_cfg,
+				pipe_idx, pCtx->plane_res.hubp, pCtx->plane_res.dpp);
+
+		/* Combine 2nd cmds update_curosr_info to DMU */
+		dc_send_cmd_to_dmu(pCtx->stream->ctx->dmub_srv, &cmd);
+	}
+}