Merge tag 'drm-next-2024-01-10' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This contains two major new drivers:

   - imagination is a first driver for Imagination Technologies devices,
     it only covers very specific devices, but there is hope to grow it

   - xe is a reboot of the i915 GPU (shares display) side using a more
     upstream focused development model, and trying to maximise code
     sharing. It's not enabled for any hw by default, and will hopefully
     get switched on for Intel's Lunarlake.

  This also drops a bunch of the old UMS ioctls. It's been dead long
  enough.

  amdgpu has a bunch of new color management code that is being used in
  the Steam Deck.

  amdgpu also has a new ACPI WBRF interaction to help avoid radio
  interference.

  Otherwise it's the usual lots of changes in lots of places.

  Detailed summary:

  new drivers:
   - imagination - new driver for Imagination Technologies GPU
   - xe - new driver for Intel GPUs using core drm concepts

  core:
   - add CLOSE_FB ioctl
   - remove old UMS ioctls
   - increase max objects to accomodate AMD color mgmt

  encoder:
   - create per-encoder debugfs directory

  edid:
   - split out drm_eld
   - SAD helpers
   - drop edid_firmware module parameter

  format-helper:
   - cache format conversion buffers

  sched:
   - move from kthread to workqueue
   - rename some internals
   - implement dynamic job-flow control

  gpuvm:
   - provide more features to handle GEM objects

  client:
   - don't acquire module reference

  displayport:
   - add mst path property documentation

  fdinfo:
   - alignment fix

  dma-buf:
   - add fence timestamp helper
   - add fence deadline support

  bridge:
   - transparent aux-bridge for DP/USB-C
   - lt8912b: add suspend/resume support and power regulator support

  panel:
   - edp: AUO B116XTN02, BOE NT116WHM-N21,836X2, NV116WHM-N49
   - chromebook panel support
   - elida-kd35t133: rework pm
   - powkiddy RK2023 panel
   - himax-hx8394: drop prepare/unprepare and shutdown logic
   - BOE BP101WX1-100, Powkiddy X55, Ampire AM8001280G
   - Evervision VGG644804, SDC ATNA45AF01
   - nv3052c: register docs, init sequence fixes, fascontek FS035VG158
   - st7701: Anbernic RG-ARC support
   - r63353 panel controller
   - Ilitek ILI9805 panel controller
   - AUO G156HAN04.0

  simplefb:
   - support memory regions
   - support power domains

  amdgpu:
   - add new 64-bit sequence number infrastructure
   - add AMD specific color management
   - ACPI WBRF support for RF interference handling
   - GPUVM updates
   - RAS updates
   - DCN 3.5 updates
   - Rework PCIe link speed handling
   - Document GPU reset types
   - DMUB fixes
   - eDP fixes
   - NBIO 7.9/7.11 updates
   - SubVP updates
   - XGMI PCIe state dumping for aqua vanjaram
   - GFX11 golden register updates
   - enable tunnelling on high pri compute

  amdkfd:
   - Migrate TLB flushing logic to amdgpu
   - Trap handler fixes
   - Fix restore workers handling on suspend/resume
   - Fix possible memory leak in pqm_uninit()
   - support import/export of dma-bufs using GEM handles

  radeon:
   - fix possible overflows in command buffer checking
   - check for errors in ring_lock

  i915:
   - reorg display code for reuse in xe driver
   - fdinfo memory stats printing
   - DP MST bandwidth mgmt improvements
   - DP panel replay enabling
   - MTL C20 phy state verification
   - MTL DP DSC fractional bpp support
   - Audio fastset support
   - use dma_fence interfaces instead of i915_sw_fence
   - Separate gem and display code
   - AUX register macro refactoring
   - Separate display module/device parameters
   - Move display capabilities debugfs under display
   - Makefile cleanups
   - Register cleanups
   - Move display lock inits under display/
   - VLV/CHV DPIO PHY register and interface refactoring
   - DSI VBT sequence refactoring
   - C10/C20 PHY PLL hardware readout
   - DPLL code cleanups
   - Cleanup PXP plane protection checks
   - Improve display debug msgs
   - PSR selective fetch fixes/improvements
   - DP MST fixes
   - Xe2LPD FBC restrictions removed
   - DGFX uses direct VBT pin mapping
   - more MTL WAs
   - fix MTL eDP bug
   - eliminate use of kmap_atomic

  habanalabs:
   - sysfs entry to identify a device minor id with debugfs path
   - sysfs entry to expose device module id
   - add signed device info retrieval through INFO ioctl
   - add Gaudi2C device support
   - pcie reset prepare/done hooks

  msm:
   - Add support for SDM670, SM8650
   - Handle the CFG interconnect to fix the obscure hangs / timeouts
   - Kconfig fix for QMP dependency
   - use managed allocators
   - DPU: SDM670, SM8650 support
   - DPU: Enable SmartDMA on SM8350 and SM8450
   - DP: enable runtime PM support
   - GPU: add metadata UAPI
   - GPU: move devcoredumps to GPU device
   - GPU: convert to drm_exec

  ivpu:
   - update FW API
   - new debugfs file
   - a new NOP job submission test mode
   - improve suspend/resume
   - PM improvements
   - MMU PT optimizations
   - firmware profile frequency support
   - support for uncached buffers
   - switch to gem shmem helpers
   - replace kthread with threaded irqs

  rockchip:
   - rk3066_hdmi: convert to atomic
   - vop2: support nv20 and nv30
   - rk3588 support

  mediatek:
   - use devm_platform_ioremap_resource
   - stop using iommu_present
   - MT8188 VDOSYS1 display support

  panfrost:
   - PM improvements
   - improve interrupt handling as poweroff

  qaic:
   - allow to run with single MSI
   - support host/device time sync
   - switch to persistent DRM devices

  exynos:
   - fix potential error pointer dereference
   - fix wrong error checking
   - add missing call to drm_atomic_helper_shutdown

  omapdrm:
   - dma-fence lockdep annotation fix

  tidss:
   - dma-fence lockdep annotation fix
   - support for AM62A7

  v3d:
   - BCM2712 - rpi5 support
   - fdinfo + gputop support
   - uapi for CPU job handling

  virtio-gpu:
   - add context debug name"

* tag 'drm-next-2024-01-10' of git://anongit.freedesktop.org/drm/drm: (2340 commits)
  drm/amd/display: Allow z8/z10 from driver
  drm/amd/display: fix bandwidth validation failure on DCN 2.1
  drm/amdgpu: apply the RV2 system aperture fix to RN/CZN as well
  drm/amd/display: Move fixpt_from_s3132 to amdgpu_dm
  drm/amd/display: Fix recent checkpatch errors in amdgpu_dm
  Revert "drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole"
  drm/amd/display: avoid stringop-overflow warnings for dp_decide_lane_settings()
  drm/amd/display: Fix power_helpers.c codestyle
  drm/amd/display: Fix hdcp_log.h codestyle
  drm/amd/display: Fix hdcp2_execution.c codestyle
  drm/amd/display: Fix hdcp_psp.h codestyle
  drm/amd/display: Fix freesync.c codestyle
  drm/amd/display: Fix hdcp_psp.c codestyle
  drm/amd/display: Fix hdcp1_execution.c codestyle
  drm/amd/pm/smu7: fix a memleak in smu7_hwmgr_backend_init
  drm/amdkfd: Fix iterator used outside loop in 'kfd_add_peer_prop()'
  drm/amdgpu: Drop 'fence' check in 'to_amdgpu_amdkfd_fence()'
  drm/amdkfd: Confirm list is non-empty before utilizing list_first_entry in kfd_topology.c
  drm/amdgpu: Fix '*fw' from request_firmware() not released in 'amdgpu_ucode_request()'
  drm/amdgpu: Fix variable 'mca_funcs' dereferenced before NULL check in 'amdgpu_mca_smu_get_mca_entry()'
  ...

2 files changed, 342 insertions, 53 deletions

diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index f3680f4e6970..d72b6f9a352c 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -2245,6 +2245,8 @@ static const struct dpcd_quirk dpcd_quirk_list[] = {
 	{ OUI(0x00, 0x00, 0x00), DEVICE_ID('C', 'H', '7', '5', '1', '1'), false, BIT(DP_DPCD_QUIRK_NO_SINK_COUNT) },
 	/* Synaptics DP1.4 MST hubs can support DSC without virtual DPCD */
 	{ OUI(0x90, 0xCC, 0x24), DEVICE_ID_ANY, true, BIT(DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) },
+	/* Synaptics DP1.4 MST hubs require DSC for some modes on which it applies HBLANK expansion. */
+	{ OUI(0x90, 0xCC, 0x24), DEVICE_ID_ANY, true, BIT(DP_DPCD_QUIRK_HBLANK_EXPANSION_REQUIRES_DSC) },
 	/* Apple MacBookPro 2017 15 inch eDP Retina panel reports too low DP_MAX_LINK_RATE */
 	{ OUI(0x00, 0x10, 0xfa), DEVICE_ID(101, 68, 21, 101, 98, 97), false, BIT(DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS) },
 };
@@ -2327,6 +2329,33 @@ int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc,
 EXPORT_SYMBOL(drm_dp_read_desc);
 
 /**
+ * drm_dp_dsc_sink_bpp_incr() - Get bits per pixel increment
+ * @dsc_dpcd: DSC capabilities from DPCD
+ *
+ * Returns the bpp precision supported by the DP sink.
+ */
+u8 drm_dp_dsc_sink_bpp_incr(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE])
+{
+	u8 bpp_increment_dpcd = dsc_dpcd[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT];
+
+	switch (bpp_increment_dpcd) {
+	case DP_DSC_BITS_PER_PIXEL_1_16:
+		return 16;
+	case DP_DSC_BITS_PER_PIXEL_1_8:
+		return 8;
+	case DP_DSC_BITS_PER_PIXEL_1_4:
+		return 4;
+	case DP_DSC_BITS_PER_PIXEL_1_2:
+		return 2;
+	case DP_DSC_BITS_PER_PIXEL_1_1:
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_dp_dsc_sink_bpp_incr);
+
+/**
  * drm_dp_dsc_sink_max_slice_count() - Get the max slice count
  * supported by the DSC sink.
  * @dsc_dpcd: DSC capabilities from DPCD
@@ -3898,3 +3927,135 @@ int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux)
 EXPORT_SYMBOL(drm_panel_dp_aux_backlight);
 
 #endif
+
+/* See DP Standard v2.1 2.6.4.4.1.1, 2.8.4.4, 2.8.7 */
+static int drm_dp_link_symbol_cycles(int lane_count, int pixels, int bpp_x16,
+				     int symbol_size, bool is_mst)
+{
+	int cycles = DIV_ROUND_UP(pixels * bpp_x16, 16 * symbol_size * lane_count);
+	int align = is_mst ? 4 / lane_count : 1;
+
+	return ALIGN(cycles, align);
+}
+
+static int drm_dp_link_dsc_symbol_cycles(int lane_count, int pixels, int slice_count,
+					 int bpp_x16, int symbol_size, bool is_mst)
+{
+	int slice_pixels = DIV_ROUND_UP(pixels, slice_count);
+	int slice_data_cycles = drm_dp_link_symbol_cycles(lane_count, slice_pixels,
+							  bpp_x16, symbol_size, is_mst);
+	int slice_eoc_cycles = is_mst ? 4 / lane_count : 1;
+
+	return slice_count * (slice_data_cycles + slice_eoc_cycles);
+}
+
+/**
+ * drm_dp_bw_overhead - Calculate the BW overhead of a DP link stream
+ * @lane_count: DP link lane count
+ * @hactive: pixel count of the active period in one scanline of the stream
+ * @dsc_slice_count: DSC slice count if @flags/DRM_DP_LINK_BW_OVERHEAD_DSC is set
+ * @bpp_x16: bits per pixel in .4 binary fixed point
+ * @flags: DRM_DP_OVERHEAD_x flags
+ *
+ * Calculate the BW allocation overhead of a DP link stream, depending
+ * on the link's
+ * - @lane_count
+ * - SST/MST mode (@flags / %DRM_DP_OVERHEAD_MST)
+ * - symbol size (@flags / %DRM_DP_OVERHEAD_UHBR)
+ * - FEC mode (@flags / %DRM_DP_OVERHEAD_FEC)
+ * - SSC/REF_CLK mode (@flags / %DRM_DP_OVERHEAD_SSC_REF_CLK)
+ * as well as the stream's
+ * - @hactive timing
+ * - @bpp_x16 color depth
+ * - compression mode (@flags / %DRM_DP_OVERHEAD_DSC).
+ * Note that this overhead doesn't account for the 8b/10b, 128b/132b
+ * channel coding efficiency, for that see
+ * @drm_dp_link_bw_channel_coding_efficiency().
+ *
+ * Returns the overhead as 100% + overhead% in 1ppm units.
+ */
+int drm_dp_bw_overhead(int lane_count, int hactive,
+		       int dsc_slice_count,
+		       int bpp_x16, unsigned long flags)
+{
+	int symbol_size = flags & DRM_DP_BW_OVERHEAD_UHBR ? 32 : 8;
+	bool is_mst = flags & DRM_DP_BW_OVERHEAD_MST;
+	u32 overhead = 1000000;
+	int symbol_cycles;
+
+	/*
+	 * DP Standard v2.1 2.6.4.1
+	 * SSC downspread and ref clock variation margin:
+	 *   5300ppm + 300ppm ~ 0.6%
+	 */
+	if (flags & DRM_DP_BW_OVERHEAD_SSC_REF_CLK)
+		overhead += 6000;
+
+	/*
+	 * DP Standard v2.1 2.6.4.1.1, 3.5.1.5.4:
+	 * FEC symbol insertions for 8b/10b channel coding:
+	 * After each 250 data symbols on 2-4 lanes:
+	 *   250 LL + 5 FEC_PARITY_PH + 1 CD_ADJ   (256 byte FEC block)
+	 * After each 2 x 250 data symbols on 1 lane:
+	 *   2 * 250 LL + 11 FEC_PARITY_PH + 1 CD_ADJ (512 byte FEC block)
+	 * After 256 (2-4 lanes) or 128 (1 lane) FEC blocks:
+	 *   256 * 256 bytes + 1 FEC_PM
+	 * or
+	 *   128 * 512 bytes + 1 FEC_PM
+	 * (256 * 6 + 1) / (256 * 250) = 2.4015625 %
+	 */
+	if (flags & DRM_DP_BW_OVERHEAD_FEC)
+		overhead += 24016;
+
+	/*
+	 * DP Standard v2.1 2.7.9, 5.9.7
+	 * The FEC overhead for UHBR is accounted for in its 96.71% channel
+	 * coding efficiency.
+	 */
+	WARN_ON((flags & DRM_DP_BW_OVERHEAD_UHBR) &&
+		(flags & DRM_DP_BW_OVERHEAD_FEC));
+
+	if (flags & DRM_DP_BW_OVERHEAD_DSC)
+		symbol_cycles = drm_dp_link_dsc_symbol_cycles(lane_count, hactive,
+							      dsc_slice_count,
+							      bpp_x16, symbol_size,
+							      is_mst);
+	else
+		symbol_cycles = drm_dp_link_symbol_cycles(lane_count, hactive,
+							  bpp_x16, symbol_size,
+							  is_mst);
+
+	return DIV_ROUND_UP_ULL(mul_u32_u32(symbol_cycles * symbol_size * lane_count,
+					    overhead * 16),
+				hactive * bpp_x16);
+}
+EXPORT_SYMBOL(drm_dp_bw_overhead);
+
+/**
+ * drm_dp_bw_channel_coding_efficiency - Get a DP link's channel coding efficiency
+ * @is_uhbr: Whether the link has a 128b/132b channel coding
+ *
+ * Return the channel coding efficiency of the given DP link type, which is
+ * either 8b/10b or 128b/132b (aka UHBR). The corresponding overhead includes
+ * the 8b -> 10b, 128b -> 132b pixel data to link symbol conversion overhead
+ * and for 128b/132b any link or PHY level control symbol insertion overhead
+ * (LLCP, FEC, PHY sync, see DP Standard v2.1 3.5.2.18). For 8b/10b the
+ * corresponding FEC overhead is BW allocation specific, included in the value
+ * returned by drm_dp_bw_overhead().
+ *
+ * Returns the efficiency in the 100%/coding-overhead% ratio in
+ * 1ppm units.
+ */
+int drm_dp_bw_channel_coding_efficiency(bool is_uhbr)
+{
+	if (is_uhbr)
+		return 967100;
+	else
+		/*
+		 * Note that on 8b/10b MST the efficiency is only
+		 * 78.75% due to the 1 out of 64 MTPH packet overhead,
+		 * not accounted for here.
+		 */
+		return 800000;
+}
+EXPORT_SYMBOL(drm_dp_bw_channel_coding_efficiency);
diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index 0e0d0e76de06..8ca01a6bf645 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -43,6 +43,7 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_fixed.h>
 #include <drm/drm_print.h>
 #include <drm/drm_probe_helper.h>
 
@@ -3578,16 +3579,26 @@ static int drm_dp_send_up_ack_reply(struct drm_dp_mst_topology_mgr *mgr,
  * value is in units of PBNs/(timeslots/1 MTP). This value can be used to
  * convert the number of PBNs required for a given stream to the number of
  * timeslots this stream requires in each MTP.
+ *
+ * Returns the BW / timeslot value in 20.12 fixed point format.
  */
-int drm_dp_get_vc_payload_bw(const struct drm_dp_mst_topology_mgr *mgr,
-			     int link_rate, int link_lane_count)
+fixed20_12 drm_dp_get_vc_payload_bw(const struct drm_dp_mst_topology_mgr *mgr,
+				    int link_rate, int link_lane_count)
 {
+	int ch_coding_efficiency =
+		drm_dp_bw_channel_coding_efficiency(drm_dp_is_uhbr_rate(link_rate));
+	fixed20_12 ret;
+
 	if (link_rate == 0 || link_lane_count == 0)
 		drm_dbg_kms(mgr->dev, "invalid link rate/lane count: (%d / %d)\n",
 			    link_rate, link_lane_count);
 
-	/* See DP v2.0 2.6.4.2, VCPayload_Bandwidth_for_OneTimeSlotPer_MTP_Allocation */
-	return link_rate * link_lane_count / 54000;
+	/* See DP v2.0 2.6.4.2, 2.7.6.3 VCPayload_Bandwidth_for_OneTimeSlotPer_MTP_Allocation */
+	ret.full = DIV_ROUND_DOWN_ULL(mul_u32_u32(link_rate * link_lane_count,
+						  ch_coding_efficiency),
+				      (1000000ULL * 8 * 5400) >> 12);
+
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_get_vc_payload_bw);
 
@@ -4335,7 +4346,7 @@ int drm_dp_atomic_find_time_slots(struct drm_atomic_state *state,
 		}
 	}
 
-	req_slots = DIV_ROUND_UP(pbn, topology_state->pbn_div);
+	req_slots = DIV_ROUND_UP(dfixed_const(pbn), topology_state->pbn_div.full);
 
 	drm_dbg_atomic(mgr->dev, "[CONNECTOR:%d:%s] [MST PORT:%p] TU %d -> %d\n",
 		       port->connector->base.id, port->connector->name,
@@ -4718,35 +4729,36 @@ EXPORT_SYMBOL(drm_dp_check_act_status);
 
 /**
  * drm_dp_calc_pbn_mode() - Calculate the PBN for a mode.
- * @clock: dot clock for the mode
- * @bpp: bpp for the mode.
- * @dsc: DSC mode. If true, bpp has units of 1/16 of a bit per pixel
+ * @clock: dot clock
+ * @bpp: bpp as .4 binary fixed point
  *
  * This uses the formula in the spec to calculate the PBN value for a mode.
  */
-int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc)
+int drm_dp_calc_pbn_mode(int clock, int bpp)
 {
 	/*
-	 * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006
 	 * The unit of 54/64Mbytes/sec is an arbitrary unit chosen based on
 	 * common multiplier to render an integer PBN for all link rate/lane
 	 * counts combinations
 	 * calculate
-	 * peak_kbps *= (1006/1000)
-	 * peak_kbps *= (64/54)
-	 * peak_kbps *= 8    convert to bytes
-	 *
-	 * If the bpp is in units of 1/16, further divide by 16. Put this
-	 * factor in the numerator rather than the denominator to avoid
-	 * integer overflow
+	 * peak_kbps = clock * bpp / 16
+	 * peak_kbps *= SSC overhead / 1000000
+	 * peak_kbps /= 8    convert to Kbytes
+	 * peak_kBps *= (64/54) / 1000    convert to PBN
 	 */
+	/*
+	 * TODO: Use the actual link and mode parameters to calculate
+	 * the overhead. For now it's assumed that these are
+	 * 4 link lanes, 4096 hactive pixels, which don't add any
+	 * significant data padding overhead and that there is no DSC
+	 * or FEC overhead.
+	 */
+	int overhead = drm_dp_bw_overhead(4, 4096, 0, bpp,
+					  DRM_DP_BW_OVERHEAD_MST |
+					  DRM_DP_BW_OVERHEAD_SSC_REF_CLK);
 
-	if (dsc)
-		return DIV_ROUND_UP_ULL(mul_u32_u32(clock * (bpp / 16), 64 * 1006),
-					8 * 54 * 1000 * 1000);
-
-	return DIV_ROUND_UP_ULL(mul_u32_u32(clock * bpp, 64 * 1006),
-				8 * 54 * 1000 * 1000);
+	return DIV64_U64_ROUND_UP(mul_u32_u32(clock * bpp, 64 * overhead >> 4),
+				  1000000ULL * 8 * 54 * 1000);
 }
 EXPORT_SYMBOL(drm_dp_calc_pbn_mode);
 
@@ -4871,7 +4883,8 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 	state = to_drm_dp_mst_topology_state(mgr->base.state);
 	seq_printf(m, "\n*** Atomic state info ***\n");
 	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);
+		   state->payload_mask, mgr->max_payloads, state->start_slot,
+		   dfixed_trunc(state->pbn_div));
 
 	seq_printf(m, "\n| idx | port | vcpi | slots | pbn | dsc | status |     sink name     |\n");
 	for (i = 0; i < mgr->max_payloads; i++) {
@@ -5136,13 +5149,67 @@ static bool drm_dp_mst_port_downstream_of_branch(struct drm_dp_mst_port *port,
 	return false;
 }
 
+static bool
+drm_dp_mst_port_downstream_of_parent_locked(struct drm_dp_mst_topology_mgr *mgr,
+					    struct drm_dp_mst_port *port,
+					    struct drm_dp_mst_port *parent)
+{
+	if (!mgr->mst_primary)
+		return false;
+
+	port = drm_dp_mst_topology_get_port_validated_locked(mgr->mst_primary,
+							     port);
+	if (!port)
+		return false;
+
+	if (!parent)
+		return true;
+
+	parent = drm_dp_mst_topology_get_port_validated_locked(mgr->mst_primary,
+							       parent);
+	if (!parent)
+		return false;
+
+	if (!parent->mstb)
+		return false;
+
+	return drm_dp_mst_port_downstream_of_branch(port, parent->mstb);
+}
+
+/**
+ * drm_dp_mst_port_downstream_of_parent - check if a port is downstream of a parent port
+ * @mgr: MST topology manager
+ * @port: the port being looked up
+ * @parent: the parent port
+ *
+ * The function returns %true if @port is downstream of @parent. If @parent is
+ * %NULL - denoting the root port - the function returns %true if @port is in
+ * @mgr's topology.
+ */
+bool
+drm_dp_mst_port_downstream_of_parent(struct drm_dp_mst_topology_mgr *mgr,
+				     struct drm_dp_mst_port *port,
+				     struct drm_dp_mst_port *parent)
+{
+	bool ret;
+
+	mutex_lock(&mgr->lock);
+	ret = drm_dp_mst_port_downstream_of_parent_locked(mgr, port, parent);
+	mutex_unlock(&mgr->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_dp_mst_port_downstream_of_parent);
+
 static int
 drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port,
-				      struct drm_dp_mst_topology_state *state);
+				      struct drm_dp_mst_topology_state *state,
+				      struct drm_dp_mst_port **failing_port);
 
 static int
 drm_dp_mst_atomic_check_mstb_bw_limit(struct drm_dp_mst_branch *mstb,
-				      struct drm_dp_mst_topology_state *state)
+				      struct drm_dp_mst_topology_state *state,
+				      struct drm_dp_mst_port **failing_port)
 {
 	struct drm_dp_mst_atomic_payload *payload;
 	struct drm_dp_mst_port *port;
@@ -5171,7 +5238,7 @@ drm_dp_mst_atomic_check_mstb_bw_limit(struct drm_dp_mst_branch *mstb,
 		drm_dbg_atomic(mstb->mgr->dev, "[MSTB:%p] Checking bandwidth limits\n", mstb);
 
 	list_for_each_entry(port, &mstb->ports, next) {
-		ret = drm_dp_mst_atomic_check_port_bw_limit(port, state);
+		ret = drm_dp_mst_atomic_check_port_bw_limit(port, state, failing_port);
 		if (ret < 0)
 			return ret;
 
@@ -5183,7 +5250,8 @@ drm_dp_mst_atomic_check_mstb_bw_limit(struct drm_dp_mst_branch *mstb,
 
 static int
 drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port,
-				      struct drm_dp_mst_topology_state *state)
+				      struct drm_dp_mst_topology_state *state,
+				      struct drm_dp_mst_port **failing_port)
 {
 	struct drm_dp_mst_atomic_payload *payload;
 	int pbn_used = 0;
@@ -5204,13 +5272,15 @@ drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port,
 			drm_dbg_atomic(port->mgr->dev,
 				       "[MSTB:%p] [MST PORT:%p] no BW available for the port\n",
 				       port->parent, port);
+			*failing_port = port;
 			return -EINVAL;
 		}
 
 		pbn_used = payload->pbn;
 	} else {
 		pbn_used = drm_dp_mst_atomic_check_mstb_bw_limit(port->mstb,
-								 state);
+								 state,
+								 failing_port);
 		if (pbn_used <= 0)
 			return pbn_used;
 	}
@@ -5219,6 +5289,7 @@ drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port,
 		drm_dbg_atomic(port->mgr->dev,
 			       "[MSTB:%p] [MST PORT:%p] required PBN of %d exceeds port limit of %d\n",
 			       port->parent, port, pbn_used, port->full_pbn);
+		*failing_port = port;
 		return -ENOSPC;
 	}
 
@@ -5271,10 +5342,10 @@ drm_dp_mst_atomic_check_payload_alloc_limits(struct drm_dp_mst_topology_mgr *mgr
 	}
 
 	if (!payload_count)
-		mst_state->pbn_div = 0;
+		mst_state->pbn_div.full = dfixed_const(0);
 
 	drm_dbg_atomic(mgr->dev, "[MST MGR:%p] mst state %p TU pbn_div=%d avail=%d used=%d\n",
-		       mgr, mst_state, mst_state->pbn_div, avail_slots,
+		       mgr, mst_state, dfixed_trunc(mst_state->pbn_div), avail_slots,
 		       mst_state->total_avail_slots - avail_slots);
 
 	return 0;
@@ -5397,19 +5468,81 @@ int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state,
 EXPORT_SYMBOL(drm_dp_mst_atomic_enable_dsc);
 
 /**
+ * drm_dp_mst_atomic_check_mgr - Check the atomic state of an MST topology manager
+ * @state: The global atomic state
+ * @mgr: Manager to check
+ * @mst_state: The MST atomic state for @mgr
+ * @failing_port: Returns the port with a BW limitation
+ *
+ * Checks the given MST manager's topology state for an atomic update to ensure
+ * that it's valid. This includes checking whether there's enough bandwidth to
+ * support the new timeslot allocations in the atomic update.
+ *
+ * Any atomic drivers supporting DP MST must make sure to call this or
+ * the drm_dp_mst_atomic_check() function after checking the rest of their state
+ * in their &drm_mode_config_funcs.atomic_check() callback.
+ *
+ * See also:
+ * drm_dp_mst_atomic_check()
+ * drm_dp_atomic_find_time_slots()
+ * drm_dp_atomic_release_time_slots()
+ *
+ * Returns:
+ *   - 0 if the new state is valid
+ *   - %-ENOSPC, if the new state is invalid, because of BW limitation
+ *         @failing_port is set to:
+ *         - The non-root port where a BW limit check failed
+ *           with all the ports downstream of @failing_port passing
+ *           the BW limit check.
+ *           The returned port pointer is valid until at least
+ *           one payload downstream of it exists.
+ *         - %NULL if the BW limit check failed at the root port
+ *           with all the ports downstream of the root port passing
+ *           the BW limit check.
+ *   - %-EINVAL, if the new state is invalid, because the root port has
+ *     too many payloads.
+ */
+int drm_dp_mst_atomic_check_mgr(struct drm_atomic_state *state,
+				struct drm_dp_mst_topology_mgr *mgr,
+				struct drm_dp_mst_topology_state *mst_state,
+				struct drm_dp_mst_port **failing_port)
+{
+	int ret;
+
+	*failing_port = NULL;
+
+	if (!mgr->mst_state)
+		return 0;
+
+	mutex_lock(&mgr->lock);
+	ret = drm_dp_mst_atomic_check_mstb_bw_limit(mgr->mst_primary,
+						    mst_state,
+						    failing_port);
+	mutex_unlock(&mgr->lock);
+
+	if (ret < 0)
+		return ret;
+
+	return drm_dp_mst_atomic_check_payload_alloc_limits(mgr, mst_state);
+}
+EXPORT_SYMBOL(drm_dp_mst_atomic_check_mgr);
+
+/**
  * drm_dp_mst_atomic_check - Check that the new state of an MST topology in an
  * atomic update is valid
  * @state: Pointer to the new &struct drm_dp_mst_topology_state
  *
  * Checks the given topology state for an atomic update to ensure that it's
- * valid. This includes checking whether there's enough bandwidth to support
- * the new timeslot allocations in the atomic update.
+ * valid, calling drm_dp_mst_atomic_check_mgr() for all MST manager in the
+ * atomic state. This includes checking whether there's enough bandwidth to
+ * support the new timeslot allocations in the atomic update.
  *
  * Any atomic drivers supporting DP MST must make sure to call this after
  * checking the rest of their state in their
  * &drm_mode_config_funcs.atomic_check() callback.
  *
  * See also:
+ * drm_dp_mst_atomic_check_mgr()
  * drm_dp_atomic_find_time_slots()
  * drm_dp_atomic_release_time_slots()
  *
@@ -5424,21 +5557,11 @@ int drm_dp_mst_atomic_check(struct drm_atomic_state *state)
 	int i, ret = 0;
 
 	for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) {
-		if (!mgr->mst_state)
-			continue;
+		struct drm_dp_mst_port *tmp_port;
 
-		ret = drm_dp_mst_atomic_check_payload_alloc_limits(mgr, mst_state);
+		ret = drm_dp_mst_atomic_check_mgr(state, mgr, mst_state, &tmp_port);
 		if (ret)
 			break;
-
-		mutex_lock(&mgr->lock);
-		ret = drm_dp_mst_atomic_check_mstb_bw_limit(mgr->mst_primary,
-							    mst_state);
-		mutex_unlock(&mgr->lock);
-		if (ret < 0)
-			break;
-		else
-			ret = 0;
 	}
 
 	return ret;
@@ -5894,6 +6017,7 @@ static bool drm_dp_mst_is_virtual_dpcd(struct drm_dp_mst_port *port)
 struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port)
 {
 	struct drm_dp_mst_port *immediate_upstream_port;
+	struct drm_dp_aux *immediate_upstream_aux;
 	struct drm_dp_mst_port *fec_port;
 	struct drm_dp_desc desc = {};
 	u8 endpoint_fec;
@@ -5958,21 +6082,25 @@ struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port)
 	 * - Port is on primary branch device
 	 * - Not a VGA adapter (DP_DWN_STRM_PORT_TYPE_ANALOG)
 	 */
-	if (drm_dp_read_desc(port->mgr->aux, &desc, true))
+	if (immediate_upstream_port)
+		immediate_upstream_aux = &immediate_upstream_port->aux;
+	else
+		immediate_upstream_aux = port->mgr->aux;
+
+	if (drm_dp_read_desc(immediate_upstream_aux, &desc, true))
 		return NULL;
 
-	if (drm_dp_has_quirk(&desc, DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) &&
-	    port->mgr->dpcd[DP_DPCD_REV] >= DP_DPCD_REV_14 &&
-	    port->parent == port->mgr->mst_primary) {
+	if (drm_dp_has_quirk(&desc, DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD)) {
 		u8 dpcd_ext[DP_RECEIVER_CAP_SIZE];
 
-		if (drm_dp_read_dpcd_caps(port->mgr->aux, dpcd_ext) < 0)
+		if (drm_dp_read_dpcd_caps(immediate_upstream_aux, dpcd_ext) < 0)
 			return NULL;
 
-		if ((dpcd_ext[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT) &&
+		if (dpcd_ext[DP_DPCD_REV] >= DP_DPCD_REV_14 &&
+		    ((dpcd_ext[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT) &&
 		    ((dpcd_ext[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK)
-		     != DP_DWN_STRM_PORT_TYPE_ANALOG))
-			return port->mgr->aux;
+		     != DP_DWN_STRM_PORT_TYPE_ANALOG)))
+			return immediate_upstream_aux;
 	}
 
 	/*