Merge tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:
   - AMD adds some more upcoming HW platforms
   - Intel made Meteorlake stable and started adding Lunarlake
   - nouveau has a bunch of display rework in prepartion for the NVIDIA
     GSP firmware support
   - msm adds a7xx support
   - habanalabs has finished migration to accel subsystem

  Detail summary:

  kernel:
   - add initial vmemdup-user-array

  core:
   - fix platform remove() to return void
   - drm_file owner updated to reflect owner
   - move size calcs to drm buddy allocator
   - let GPUVM build as a module
   - allow variable number of run-queues in scheduler

  edid:
   - handle bad h/v sync_end in EDIDs

  panfrost:
   - add Boris as maintainer

  fbdev:
   - use fb_ops helpers more
   - only allow logo use from fbcon
   - rename fb_pgproto to pgprot_framebuffer
   - add HPD state to drm_connector_oob_hotplug_event
   - convert to fbdev i/o mem helpers

  i915:
   - Enable meteorlake by default
   - Early Xe2 LPD/Lunarlake display enablement
   - Rework subplatforms into IP version checks
   - GuC based TLB invalidation for Meteorlake
   - Display rework for future Xe driver integration
   - LNL FBC features
   - LNL display feature capability reads
   - update recommended fw versions for DG2+
   - drop fastboot module parameter
   - added deviceid for Arrowlake-S
   - drop preproduction workarounds
   - don't disable preemption for resets
   - cleanup inlines in headers
   - PXP firmware loading fix
   - Fix sg list lengths
   - DSC PPS state readout/verification
   - Add more RPL P/U PCI IDs
   - Add new DG2-G12 stepping
   - DP enhanced framing support to state checker
   - Improve shared link bandwidth management
   - stop using GEM macros in display code
   - refactor related code into display code
   - locally enable W=1 warnings
   - remove PSR watchdog timers on LNL

  amdgpu:
   - RAS/FRU EEPROM updatse
   - IP discovery updatses
   - GC 11.5 support
   - DCN 3.5 support
   - VPE 6.1 support
   - NBIO 7.11 support
   - DML2 support
   - lots of IP updates
   - use flexible arrays for bo list handling
   - W=1 fixes
   - Enable seamless boot in more cases
   - Enable context type property for HDMI
   - Rework GPUVM TLB flushing
   - VCN IB start/size alignment fixes

  amdkfd:
   - GC 10/11 fixes
   - GC 11.5 support
   - use partial migration in GPU faults

  radeon:
   - W=1 Fixes
   - fix some possible buffer overflow/NULL derefs

  nouveau:
   - update uapi for NO_PREFETCH
   - scheduler/fence fixes
   - rework suspend/resume for GSP-RM
   - rework display in preparation for GSP-RM

  habanalabs:
   - uapi: expose tsc clock
   - uapi: block access to eventfd through control device
   - uapi: force dma-buf export to PAGE_SIZE alignments
   - complete move to accel subsystem
   - move firmware interface include files
   - perform hard reset on PCIe AXI drain event
   - optimise user interrupt handling

  msm:
   - DP: use existing helpers for DPCD
   - DPU: interrupts reworked
   - gpu: a7xx (a730/a740) support
   - decouple msm_drv from kms for headless devices

  mediatek:
   - MT8188 dsi/dp/edp support
   - DDP GAMMA - 12 bit LUT support
   - connector dynamic selection capability

  rockchip:
   - rv1126 mipi-dsi/vop support
   - add planar formats

  ast:
   - rename constants

  panels:
   - Mitsubishi AA084XE01
   - JDI LPM102A188A
   - LTK050H3148W-CTA6

  ivpu:
   - power management fixes

  qaic:
   - add detach slice bo api

  komeda:
   - add NV12 writeback

  tegra:
   - support NVSYNC/NHSYNC
   - host1x suspend fixes

  ili9882t:
   - separate into own driver"

* tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm: (1803 commits)
  drm/amdgpu: Remove unused variables from amdgpu_show_fdinfo
  drm/amdgpu: Remove duplicate fdinfo fields
  drm/amd/amdgpu: avoid to disable gfxhub interrupt when driver is unloaded
  drm/amdgpu: Add EXT_COHERENT support for APU and NUMA systems
  drm/amdgpu: Retrieve CE count from ce_count_lo_chip in EccInfo table
  drm/amdgpu: Identify data parity error corrected in replay mode
  drm/amdgpu: Fix typo in IP discovery parsing
  drm/amd/display: fix S/G display enablement
  drm/amdxcp: fix amdxcp unloads incompletely
  drm/amd/amdgpu: fix the GPU power print error in pm info
  drm/amdgpu: Use pcie domain of xcc acpi objects
  drm/amd: check num of link levels when update pcie param
  drm/amdgpu: Add a read to GFX v9.4.3 ring test
  drm/amd/pm: call smu_cmn_get_smc_version in is_mode1_reset_supported.
  drm/amdgpu: get RAS poison status from DF v4_6_2
  drm/amdgpu: Use discovery table's subrevision
  drm/amd/display: 3.2.256
  drm/amd/display: add interface to query SubVP status
  drm/amd/display: Read before writing Backlight Mode Set Register
  drm/amd/display: Disable SYMCLK32_SE RCO on DCN314
  ...

3 files changed, 147 insertions, 87 deletions

diff --git a/drivers/gpu/drm/display/drm_dp_cec.c b/drivers/gpu/drm/display/drm_dp_cec.c
index ae39dc794190..007ceb281d00 100644
--- a/drivers/gpu/drm/display/drm_dp_cec.c
+++ b/drivers/gpu/drm/display/drm_dp_cec.c
@@ -14,6 +14,7 @@
 #include <drm/display/drm_dp_helper.h>
 #include <drm/drm_connector.h>
 #include <drm/drm_device.h>
+#include <drm/drm_edid.h>
 
 /*
  * Unfortunately it turns out that we have a chicken-and-egg situation
@@ -297,7 +298,7 @@ static void drm_dp_cec_unregister_work(struct work_struct *work)
  * were unchanged and just update the CEC physical address. Otherwise
  * unregister the old CEC adapter and create a new one.
  */
-void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid)
+void drm_dp_cec_attach(struct drm_dp_aux *aux, u16 source_physical_address)
 {
 	struct drm_connector *connector = aux->cec.connector;
 	u32 cec_caps = CEC_CAP_DEFAULTS | CEC_CAP_NEEDS_HPD |
@@ -339,7 +340,7 @@ void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid)
 		if (aux->cec.adap->capabilities == cec_caps &&
 		    aux->cec.adap->available_log_addrs == num_las) {
 			/* Unchanged, so just set the phys addr */
-			cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+			cec_s_phys_addr(aux->cec.adap, source_physical_address, false);
 			goto unlock;
 		}
 		/*
@@ -370,11 +371,27 @@ void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid)
 		 * from drm_dp_cec_register_connector() edid == NULL, so in
 		 * that case the phys addr is just invalidated.
 		 */
-		cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+		cec_s_phys_addr(aux->cec.adap, source_physical_address, false);
 	}
 unlock:
 	mutex_unlock(&aux->cec.lock);
 }
+EXPORT_SYMBOL(drm_dp_cec_attach);
+
+/*
+ * Note: Prefer calling drm_dp_cec_attach() with
+ * connector->display_info.source_physical_address if possible.
+ */
+void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid)
+{
+	u16 pa = CEC_PHYS_ADDR_INVALID;
+
+	if (edid && edid->extensions)
+		pa = cec_get_edid_phys_addr((const u8 *)edid,
+					    EDID_LENGTH * (edid->extensions + 1), NULL);
+
+	drm_dp_cec_attach(aux, pa);
+}
 EXPORT_SYMBOL(drm_dp_cec_set_edid);
 
 /*
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index e6a78fd32380..f3680f4e6970 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -746,8 +746,11 @@ int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux,
 }
 EXPORT_SYMBOL(drm_dp_dpcd_read_phy_link_status);
 
-static bool is_edid_digital_input_dp(const struct edid *edid)
+static bool is_edid_digital_input_dp(const struct drm_edid *drm_edid)
 {
+	/* FIXME: get rid of drm_edid_raw() */
+	const struct edid *edid = drm_edid_raw(drm_edid);
+
 	return edid && edid->revision >= 4 &&
 		edid->input & DRM_EDID_INPUT_DIGITAL &&
 		(edid->input & DRM_EDID_DIGITAL_TYPE_MASK) == DRM_EDID_DIGITAL_TYPE_DP;
@@ -779,13 +782,13 @@ EXPORT_SYMBOL(drm_dp_downstream_is_type);
  * drm_dp_downstream_is_tmds() - is the downstream facing port TMDS?
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
- * @edid: EDID
+ * @drm_edid: EDID
  *
  * Returns: whether the downstream facing port is TMDS (HDMI/DVI).
  */
 bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			       const u8 port_cap[4],
-			       const struct edid *edid)
+			       const struct drm_edid *drm_edid)
 {
 	if (dpcd[DP_DPCD_REV] < 0x11) {
 		switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) {
@@ -798,7 +801,7 @@ bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 
 	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
 	case DP_DS_PORT_TYPE_DP_DUALMODE:
-		if (is_edid_digital_input_dp(edid))
+		if (is_edid_digital_input_dp(drm_edid))
 			return false;
 		fallthrough;
 	case DP_DS_PORT_TYPE_DVI:
@@ -1036,14 +1039,14 @@ EXPORT_SYMBOL(drm_dp_downstream_max_dotclock);
  * drm_dp_downstream_max_tmds_clock() - extract downstream facing port max TMDS clock
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
- * @edid: EDID
+ * @drm_edid: EDID
  *
  * Returns: HDMI/DVI downstream facing port max TMDS clock in kHz on success,
  * or 0 if max TMDS clock not defined
  */
 int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				     const u8 port_cap[4],
-				     const struct edid *edid)
+				     const struct drm_edid *drm_edid)
 {
 	if (!drm_dp_is_branch(dpcd))
 		return 0;
@@ -1059,7 +1062,7 @@ int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 
 	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
 	case DP_DS_PORT_TYPE_DP_DUALMODE:
-		if (is_edid_digital_input_dp(edid))
+		if (is_edid_digital_input_dp(drm_edid))
 			return 0;
 		/*
 		 * It's left up to the driver to check the
@@ -1101,14 +1104,14 @@ EXPORT_SYMBOL(drm_dp_downstream_max_tmds_clock);
  * drm_dp_downstream_min_tmds_clock() - extract downstream facing port min TMDS clock
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
- * @edid: EDID
+ * @drm_edid: EDID
  *
  * Returns: HDMI/DVI downstream facing port min TMDS clock in kHz on success,
  * or 0 if max TMDS clock not defined
  */
 int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				     const u8 port_cap[4],
-				     const struct edid *edid)
+				     const struct drm_edid *drm_edid)
 {
 	if (!drm_dp_is_branch(dpcd))
 		return 0;
@@ -1124,7 +1127,7 @@ int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 
 	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
 	case DP_DS_PORT_TYPE_DP_DUALMODE:
-		if (is_edid_digital_input_dp(edid))
+		if (is_edid_digital_input_dp(drm_edid))
 			return 0;
 		fallthrough;
 	case DP_DS_PORT_TYPE_DVI:
@@ -1145,13 +1148,13 @@ EXPORT_SYMBOL(drm_dp_downstream_min_tmds_clock);
  *                               bits per component
  * @dpcd: DisplayPort configuration data
  * @port_cap: downstream facing port capabilities
- * @edid: EDID
+ * @drm_edid: EDID
  *
  * Returns: Max bpc on success or 0 if max bpc not defined
  */
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			      const u8 port_cap[4],
-			      const struct edid *edid)
+			      const struct drm_edid *drm_edid)
 {
 	if (!drm_dp_is_branch(dpcd))
 		return 0;
@@ -1169,7 +1172,7 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 	case DP_DS_PORT_TYPE_DP:
 		return 0;
 	case DP_DS_PORT_TYPE_DP_DUALMODE:
-		if (is_edid_digital_input_dp(edid))
+		if (is_edid_digital_input_dp(drm_edid))
 			return 0;
 		fallthrough;
 	case DP_DS_PORT_TYPE_HDMI:
@@ -1362,14 +1365,14 @@ EXPORT_SYMBOL(drm_dp_downstream_id);
  * @m: pointer for debugfs file
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
- * @edid: EDID
+ * @drm_edid: EDID
  * @aux: DisplayPort AUX channel
  *
  */
 void drm_dp_downstream_debug(struct seq_file *m,
 			     const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			     const u8 port_cap[4],
-			     const struct edid *edid,
+			     const struct drm_edid *drm_edid,
 			     struct drm_dp_aux *aux)
 {
 	bool detailed_cap_info = dpcd[DP_DOWNSTREAMPORT_PRESENT] &
@@ -1432,15 +1435,15 @@ void drm_dp_downstream_debug(struct seq_file *m,
 		if (clk > 0)
 			seq_printf(m, "\t\tMax dot clock: %d kHz\n", clk);
 
-		clk = drm_dp_downstream_max_tmds_clock(dpcd, port_cap, edid);
+		clk = drm_dp_downstream_max_tmds_clock(dpcd, port_cap, drm_edid);
 		if (clk > 0)
 			seq_printf(m, "\t\tMax TMDS clock: %d kHz\n", clk);
 
-		clk = drm_dp_downstream_min_tmds_clock(dpcd, port_cap, edid);
+		clk = drm_dp_downstream_min_tmds_clock(dpcd, port_cap, drm_edid);
 		if (clk > 0)
 			seq_printf(m, "\t\tMin TMDS clock: %d kHz\n", clk);
 
-		bpc = drm_dp_downstream_max_bpc(dpcd, port_cap, edid);
+		bpc = drm_dp_downstream_max_bpc(dpcd, port_cap, drm_edid);
 
 		if (bpc > 0)
 			seq_printf(m, "\t\tMax bpc: %d\n", bpc);
@@ -2449,12 +2452,16 @@ int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_S
 	int num_bpc = 0;
 	u8 color_depth = dsc_dpcd[DP_DSC_DEC_COLOR_DEPTH_CAP - DP_DSC_SUPPORT];
 
+	if (!drm_dp_sink_supports_dsc(dsc_dpcd))
+		return 0;
+
 	if (color_depth & DP_DSC_12_BPC)
 		dsc_bpc[num_bpc++] = 12;
 	if (color_depth & DP_DSC_10_BPC)
 		dsc_bpc[num_bpc++] = 10;
-	if (color_depth & DP_DSC_8_BPC)
-		dsc_bpc[num_bpc++] = 8;
+
+	/* A DP DSC Sink device shall support 8 bpc. */
+	dsc_bpc[num_bpc++] = 8;
 
 	return num_bpc;
 }
diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index 8c929ef72c72..0e0d0e76de06 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -3255,15 +3255,15 @@ out_get_port:
 }
 EXPORT_SYMBOL(drm_dp_send_query_stream_enc_status);
 
-static int drm_dp_create_payload_step1(struct drm_dp_mst_topology_mgr *mgr,
-				       struct drm_dp_mst_atomic_payload *payload)
+static int drm_dp_create_payload_at_dfp(struct drm_dp_mst_topology_mgr *mgr,
+					struct drm_dp_mst_atomic_payload *payload)
 {
 	return drm_dp_dpcd_write_payload(mgr, payload->vcpi, payload->vc_start_slot,
 					 payload->time_slots);
 }
 
-static int drm_dp_create_payload_step2(struct drm_dp_mst_topology_mgr *mgr,
-				       struct drm_dp_mst_atomic_payload *payload)
+static int drm_dp_create_payload_to_remote(struct drm_dp_mst_topology_mgr *mgr,
+					   struct drm_dp_mst_atomic_payload *payload)
 {
 	int ret;
 	struct drm_dp_mst_port *port = drm_dp_mst_topology_get_port_validated(mgr, payload->port);
@@ -3276,17 +3276,20 @@ static int drm_dp_create_payload_step2(struct drm_dp_mst_topology_mgr *mgr,
 	return ret;
 }
 
-static int drm_dp_destroy_payload_step1(struct drm_dp_mst_topology_mgr *mgr,
-					struct drm_dp_mst_topology_state *mst_state,
-					struct drm_dp_mst_atomic_payload *payload)
+static void drm_dp_destroy_payload_at_remote_and_dfp(struct drm_dp_mst_topology_mgr *mgr,
+						     struct drm_dp_mst_topology_state *mst_state,
+						     struct drm_dp_mst_atomic_payload *payload)
 {
 	drm_dbg_kms(mgr->dev, "\n");
 
 	/* it's okay for these to fail */
-	drm_dp_payload_send_msg(mgr, payload->port, payload->vcpi, 0);
-	drm_dp_dpcd_write_payload(mgr, payload->vcpi, payload->vc_start_slot, 0);
+	if (payload->payload_allocation_status == DRM_DP_MST_PAYLOAD_ALLOCATION_REMOTE) {
+		drm_dp_payload_send_msg(mgr, payload->port, payload->vcpi, 0);
+		payload->payload_allocation_status = DRM_DP_MST_PAYLOAD_ALLOCATION_DFP;
+	}
 
-	return 0;
+	if (payload->payload_allocation_status == DRM_DP_MST_PAYLOAD_ALLOCATION_DFP)
+		drm_dp_dpcd_write_payload(mgr, payload->vcpi, payload->vc_start_slot, 0);
 }
 
 /**
@@ -3296,10 +3299,9 @@ static int drm_dp_destroy_payload_step1(struct drm_dp_mst_topology_mgr *mgr,
  * @payload: The payload to write
  *
  * Determines the starting time slot for the given payload, and programs the VCPI for this payload
- * into hardware. After calling this, the driver should generate ACT and payload packets.
+ * into the DPCD of DPRX. After calling this, the driver should generate ACT and payload packets.
  *
- * Returns: 0 on success, error code on failure. In the event that this fails,
- * @payload.vc_start_slot will also be set to -1.
+ * Returns: 0 on success, error code on failure.
  */
 int drm_dp_add_payload_part1(struct drm_dp_mst_topology_mgr *mgr,
 			     struct drm_dp_mst_topology_state *mst_state,
@@ -3308,69 +3310,93 @@ int drm_dp_add_payload_part1(struct drm_dp_mst_topology_mgr *mgr,
 	struct drm_dp_mst_port *port;
 	int ret;
 
+	/* Update mst mgr info */
+	if (mgr->payload_count == 0)
+		mgr->next_start_slot = mst_state->start_slot;
+
+	payload->vc_start_slot = mgr->next_start_slot;
+
+	mgr->payload_count++;
+	mgr->next_start_slot += payload->time_slots;
+
+	payload->payload_allocation_status = DRM_DP_MST_PAYLOAD_ALLOCATION_LOCAL;
+
+	/* Allocate payload to immediate downstream facing port */
 	port = drm_dp_mst_topology_get_port_validated(mgr, payload->port);
 	if (!port) {
 		drm_dbg_kms(mgr->dev,
-			    "VCPI %d for port %p not in topology, not creating a payload\n",
+			    "VCPI %d for port %p not in topology, not creating a payload to remote\n",
 			    payload->vcpi, payload->port);
-		payload->vc_start_slot = -1;
-		return 0;
+		return -EIO;
 	}
 
-	if (mgr->payload_count == 0)
-		mgr->next_start_slot = mst_state->start_slot;
-
-	payload->vc_start_slot = mgr->next_start_slot;
-
-	ret = drm_dp_create_payload_step1(mgr, payload);
-	drm_dp_mst_topology_put_port(port);
+	ret = drm_dp_create_payload_at_dfp(mgr, payload);
 	if (ret < 0) {
-		drm_warn(mgr->dev, "Failed to create MST payload for port %p: %d\n",
-			 payload->port, ret);
-		payload->vc_start_slot = -1;
-		return ret;
+		drm_dbg_kms(mgr->dev, "Failed to create MST payload for port %p: %d\n",
+			    payload->port, ret);
+		goto put_port;
 	}
 
-	mgr->payload_count++;
-	mgr->next_start_slot += payload->time_slots;
+	payload->payload_allocation_status = DRM_DP_MST_PAYLOAD_ALLOCATION_DFP;
 
-	return 0;
+put_port:
+	drm_dp_mst_topology_put_port(port);
+
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_add_payload_part1);
 
 /**
- * drm_dp_remove_payload() - Remove an MST payload
+ * drm_dp_remove_payload_part1() - Remove an MST payload along the virtual channel
  * @mgr: Manager to use.
  * @mst_state: The MST atomic state
- * @old_payload: The payload with its old state
- * @new_payload: The payload to write
+ * @payload: The payload to remove
  *
- * Removes a payload from an MST topology if it was successfully assigned a start slot. Also updates
- * the starting time slots of all other payloads which would have been shifted towards the start of
- * the VC table as a result. After calling this, the driver should generate ACT and payload packets.
+ * Removes a payload along the virtual channel if it was successfully allocated.
+ * After calling this, the driver should set HW to generate ACT and then switch to new
+ * payload allocation state.
  */
-void drm_dp_remove_payload(struct drm_dp_mst_topology_mgr *mgr,
-			   struct drm_dp_mst_topology_state *mst_state,
-			   const struct drm_dp_mst_atomic_payload *old_payload,
-			   struct drm_dp_mst_atomic_payload *new_payload)
+void drm_dp_remove_payload_part1(struct drm_dp_mst_topology_mgr *mgr,
+				 struct drm_dp_mst_topology_state *mst_state,
+				 struct drm_dp_mst_atomic_payload *payload)
 {
-	struct drm_dp_mst_atomic_payload *pos;
+	/* Remove remote payload allocation */
 	bool send_remove = false;
 
-	/* We failed to make the payload, so nothing to do */
-	if (new_payload->vc_start_slot == -1)
-		return;
-
 	mutex_lock(&mgr->lock);
-	send_remove = drm_dp_mst_port_downstream_of_branch(new_payload->port, mgr->mst_primary);
+	send_remove = drm_dp_mst_port_downstream_of_branch(payload->port, mgr->mst_primary);
 	mutex_unlock(&mgr->lock);
 
 	if (send_remove)
-		drm_dp_destroy_payload_step1(mgr, mst_state, new_payload);
+		drm_dp_destroy_payload_at_remote_and_dfp(mgr, mst_state, payload);
 	else
 		drm_dbg_kms(mgr->dev, "Payload for VCPI %d not in topology, not sending remove\n",
-			    new_payload->vcpi);
+			    payload->vcpi);
 
+	payload->payload_allocation_status = DRM_DP_MST_PAYLOAD_ALLOCATION_LOCAL;
+}
+EXPORT_SYMBOL(drm_dp_remove_payload_part1);
+
+/**
+ * drm_dp_remove_payload_part2() - Remove an MST payload locally
+ * @mgr: Manager to use.
+ * @mst_state: The MST atomic state
+ * @old_payload: The payload with its old state
+ * @new_payload: The payload with its latest state
+ *
+ * Updates the starting time slots of all other payloads which would have been shifted towards
+ * the start of the payload ID table as a result of removing a payload. Driver should call this
+ * function whenever it removes a payload in its HW. It's independent to the result of payload
+ * allocation/deallocation at branch devices along the virtual channel.
+ */
+void drm_dp_remove_payload_part2(struct drm_dp_mst_topology_mgr *mgr,
+				 struct drm_dp_mst_topology_state *mst_state,
+				 const struct drm_dp_mst_atomic_payload *old_payload,
+				 struct drm_dp_mst_atomic_payload *new_payload)
+{
+	struct drm_dp_mst_atomic_payload *pos;
+
+	/* Remove local payload allocation */
 	list_for_each_entry(pos, &mst_state->payloads, next) {
 		if (pos != new_payload && pos->vc_start_slot > new_payload->vc_start_slot)
 			pos->vc_start_slot -= old_payload->time_slots;
@@ -3382,9 +3408,10 @@ void drm_dp_remove_payload(struct drm_dp_mst_topology_mgr *mgr,
 
 	if (new_payload->delete)
 		drm_dp_mst_put_port_malloc(new_payload->port);
-}
-EXPORT_SYMBOL(drm_dp_remove_payload);
 
+	new_payload->payload_allocation_status = DRM_DP_MST_PAYLOAD_ALLOCATION_NONE;
+}
+EXPORT_SYMBOL(drm_dp_remove_payload_part2);
 /**
  * drm_dp_add_payload_part2() - Execute payload update part 2
  * @mgr: Manager to use.
@@ -3403,21 +3430,19 @@ int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr,
 	int ret = 0;
 
 	/* Skip failed payloads */
-	if (payload->vc_start_slot == -1) {
-		drm_dbg_kms(mgr->dev, "Part 1 of payload creation for %s failed, skipping part 2\n",
+	if (payload->payload_allocation_status != DRM_DP_MST_PAYLOAD_ALLOCATION_DFP) {
+		drm_dbg_kms(state->dev, "Part 1 of payload creation for %s failed, skipping part 2\n",
 			    payload->port->connector->name);
 		return -EIO;
 	}
 
-	ret = drm_dp_create_payload_step2(mgr, payload);
-	if (ret < 0) {
-		if (!payload->delete)
-			drm_err(mgr->dev, "Step 2 of creating MST payload for %p failed: %d\n",
-				payload->port, ret);
-		else
-			drm_dbg_kms(mgr->dev, "Step 2 of removing MST payload for %p failed: %d\n",
-				    payload->port, ret);
-	}
+	/* Allocate payload to remote end */
+	ret = drm_dp_create_payload_to_remote(mgr, payload);
+	if (ret < 0)
+		drm_err(mgr->dev, "Step 2 of creating MST payload for %p failed: %d\n",
+			payload->port, ret);
+	else
+		payload->payload_allocation_status = DRM_DP_MST_PAYLOAD_ALLOCATION_REMOTE;
 
 	return ret;
 }
@@ -4328,6 +4353,7 @@ int drm_dp_atomic_find_time_slots(struct drm_atomic_state *state,
 		drm_dp_mst_get_port_malloc(port);
 		payload->port = port;
 		payload->vc_start_slot = -1;
+		payload->payload_allocation_status = DRM_DP_MST_PAYLOAD_ALLOCATION_NONE;
 		list_add(&payload->next, &topology_state->payloads);
 	}
 	payload->time_slots = req_slots;
@@ -4497,7 +4523,7 @@ void drm_dp_mst_atomic_wait_for_dependencies(struct drm_atomic_state *state)
 		}
 
 		/* Now that previous state is committed, it's safe to copy over the start slot
-		 * assignments
+		 * and allocation status assignments
 		 */
 		list_for_each_entry(old_payload, &old_mst_state->payloads, next) {
 			if (old_payload->delete)
@@ -4506,6 +4532,8 @@ void drm_dp_mst_atomic_wait_for_dependencies(struct drm_atomic_state *state)
 			new_payload = drm_atomic_get_mst_payload_state(new_mst_state,
 								       old_payload->port);
 			new_payload->vc_start_slot = old_payload->vc_start_slot;
+			new_payload->payload_allocation_status =
+							old_payload->payload_allocation_status;
 		}
 	}
 }
@@ -4822,6 +4850,13 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 	struct drm_dp_mst_atomic_payload *payload;
 	int i, ret;
 
+	static const char *const status[] = {
+		"None",
+		"Local",
+		"DFP",
+		"Remote",
+	};
+
 	mutex_lock(&mgr->lock);
 	if (mgr->mst_primary)
 		drm_dp_mst_dump_mstb(m, mgr->mst_primary);
@@ -4838,7 +4873,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 	seq_printf(m, "payload_mask: %x, max_payloads: %d, start_slot: %u, pbn_div: %d\n",
 		   state->payload_mask, mgr->max_payloads, state->start_slot, state->pbn_div);
 
-	seq_printf(m, "\n| idx | port | vcpi | slots | pbn | dsc |     sink name     |\n");
+	seq_printf(m, "\n| idx | port | vcpi | slots | pbn | dsc | status |     sink name     |\n");
 	for (i = 0; i < mgr->max_payloads; i++) {
 		list_for_each_entry(payload, &state->payloads, next) {
 			char name[14];
@@ -4847,7 +4882,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 				continue;
 
 			fetch_monitor_name(mgr, payload->port, name, sizeof(name));
-			seq_printf(m, " %5d %6d %6d %02d - %02d %5d %5s %19s\n",
+			seq_printf(m, " %5d %6d %6d %02d - %02d %5d %5s %8s %19s\n",
 				   i,
 				   payload->port->port_num,
 				   payload->vcpi,
@@ -4855,6 +4890,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 				   payload->vc_start_slot + payload->time_slots - 1,
 				   payload->pbn,
 				   payload->dsc_enabled ? "Y" : "N",
+				   status[payload->payload_allocation_status],
 				   (*name != 0) ? name : "Unknown");
 		}
 	}