Merge tag 'drm-intel-next-2024-02-27-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

drm/i915 feature pull #2 for v6.9:

Features and functionality:
- DP tunneling and bandwidth allocation support (Imre)
- Add more ADL-N PCI IDs (Gustavo)
- Enable fastboot also on older platforms (Ville)
- Bigjoiner force enable debugfs option for testing (Stan)

Refactoring and cleanups:
- Remove unused structs and struct members (Jiri Slaby)
- Use per-device debug logging (Ville)
- State check improvements (Ville)
- Hardcoded cd2x divider cleanups (Ville)
- CDCLK documentation updates (Ville, Rodrigo)

Fixes:
- HDCP MST Type1 fixes (Suraj)
- Fix MTL C20 PHY PLL values (Ravi)
- More hardware access prevention during init (Imre)
- Always enable decompression with tile4 on Xe2 (Juha-Pekka)
- Improve LNL package C residency (Suraj)

drm core changes:
- DP tunneling and bandwidth allocation helpers (Imre)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/87sf1devbj.fsf@intel.com

68 files changed, 4106 insertions, 670 deletions

diff --git a/drivers/gpu/drm/display/Kconfig b/drivers/gpu/drm/display/Kconfig
index 09712b88a5b8..c0f56888c328 100644
--- a/drivers/gpu/drm/display/Kconfig
+++ b/drivers/gpu/drm/display/Kconfig
@@ -17,6 +17,27 @@ config DRM_DISPLAY_DP_HELPER
 	help
 	  DRM display helpers for DisplayPort.
 
+config DRM_DISPLAY_DP_TUNNEL
+	bool
+	select DRM_DISPLAY_DP_HELPER
+	help
+	  Enable support for DisplayPort tunnels. This allows drivers to use
+	  DP tunnel features like the Bandwidth Allocation mode to maximize the
+	  BW utilization for display streams on Thunderbolt links.
+
+config DRM_DISPLAY_DEBUG_DP_TUNNEL_STATE
+	bool "Enable debugging the DP tunnel state"
+	depends on REF_TRACKER
+	depends on DRM_DISPLAY_DP_TUNNEL
+	depends on DEBUG_KERNEL
+	depends on EXPERT
+	help
+	  Enables debugging the DP tunnel manager's state, including the
+	  consistency of all managed tunnels' reference counting and the state of
+	  streams contained in tunnels.
+
+	  If in doubt, say "N".
+
 config DRM_DISPLAY_HDCP_HELPER
 	bool
 	depends on DRM_DISPLAY_HELPER
diff --git a/drivers/gpu/drm/display/Makefile b/drivers/gpu/drm/display/Makefile
index 17ac4a1006a8..7ca61333c669 100644
--- a/drivers/gpu/drm/display/Makefile
+++ b/drivers/gpu/drm/display/Makefile
@@ -8,6 +8,8 @@ drm_display_helper-$(CONFIG_DRM_DISPLAY_DP_HELPER) += \
 	drm_dp_helper.o \
 	drm_dp_mst_topology.o \
 	drm_dsc_helper.o
+drm_display_helper-$(CONFIG_DRM_DISPLAY_DP_TUNNEL) += \
+	drm_dp_tunnel.o
 drm_display_helper-$(CONFIG_DRM_DISPLAY_HDCP_HELPER) += drm_hdcp_helper.o
 drm_display_helper-$(CONFIG_DRM_DISPLAY_HDMI_HELPER) += \
 	drm_hdmi_helper.o \
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index 8d6ce46471ae..d046dfa79504 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -4055,3 +4055,33 @@ int drm_dp_bw_channel_coding_efficiency(bool is_uhbr)
 		return 800000;
 }
 EXPORT_SYMBOL(drm_dp_bw_channel_coding_efficiency);
+
+/**
+ * drm_dp_max_dprx_data_rate - Get the max data bandwidth of a DPRX sink
+ * @max_link_rate: max DPRX link rate in 10kbps units
+ * @max_lanes: max DPRX lane count
+ *
+ * Given a link rate and lanes, get the data bandwidth.
+ *
+ * Data bandwidth is the actual payload rate, which depends on the data
+ * bandwidth efficiency and the link rate.
+ *
+ * Note that protocol layers above the DPRX link level considered here can
+ * further limit the maximum data rate. Such layers are the MST topology (with
+ * limits on the link between the source and first branch device as well as on
+ * the whole MST path until the DPRX link) and (Thunderbolt) DP tunnels -
+ * which in turn can encapsulate an MST link with its own limit - with each
+ * SST or MST encapsulated tunnel sharing the BW of a tunnel group.
+ *
+ * Returns the maximum data rate in kBps units.
+ */
+int drm_dp_max_dprx_data_rate(int max_link_rate, int max_lanes)
+{
+	int ch_coding_efficiency =
+		drm_dp_bw_channel_coding_efficiency(drm_dp_is_uhbr_rate(max_link_rate));
+
+	return DIV_ROUND_DOWN_ULL(mul_u32_u32(max_link_rate * 10 * max_lanes,
+					      ch_coding_efficiency),
+				  1000000 * 8);
+}
+EXPORT_SYMBOL(drm_dp_max_dprx_data_rate);
diff --git a/drivers/gpu/drm/display/drm_dp_tunnel.c b/drivers/gpu/drm/display/drm_dp_tunnel.c
new file mode 100644
index 000000000000..120e0de674c1
--- /dev/null
+++ b/drivers/gpu/drm/display/drm_dp_tunnel.c
@@ -0,0 +1,1949 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2023 Intel Corporation
+ */
+
+#include <linux/ref_tracker.h>
+#include <linux/types.h>
+
+#include <drm/drm_atomic_state_helper.h>
+
+#include <drm/drm_atomic.h>
+#include <drm/drm_print.h>
+#include <drm/display/drm_dp.h>
+#include <drm/display/drm_dp_helper.h>
+#include <drm/display/drm_dp_tunnel.h>
+
+#define to_group(__private_obj) \
+	container_of(__private_obj, struct drm_dp_tunnel_group, base)
+
+#define to_group_state(__private_state) \
+	container_of(__private_state, struct drm_dp_tunnel_group_state, base)
+
+#define is_dp_tunnel_private_obj(__obj) \
+	((__obj)->funcs == &tunnel_group_funcs)
+
+#define for_each_new_group_in_state(__state, __new_group_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->num_private_objs; \
+	     (__i)++) \
+		for_each_if ((__state)->private_objs[__i].ptr && \
+			     is_dp_tunnel_private_obj((__state)->private_objs[__i].ptr) && \
+			     ((__new_group_state) = \
+				to_group_state((__state)->private_objs[__i].new_state), 1))
+
+#define for_each_old_group_in_state(__state, __old_group_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->num_private_objs; \
+	     (__i)++) \
+		for_each_if ((__state)->private_objs[__i].ptr && \
+			     is_dp_tunnel_private_obj((__state)->private_objs[__i].ptr) && \
+			     ((__old_group_state) = \
+				to_group_state((__state)->private_objs[__i].old_state), 1))
+
+#define for_each_tunnel_in_group(__group, __tunnel) \
+	list_for_each_entry(__tunnel, &(__group)->tunnels, node)
+
+#define for_each_tunnel_state(__group_state, __tunnel_state) \
+	list_for_each_entry(__tunnel_state, &(__group_state)->tunnel_states, node)
+
+#define for_each_tunnel_state_safe(__group_state, __tunnel_state, __tunnel_state_tmp) \
+	list_for_each_entry_safe(__tunnel_state, __tunnel_state_tmp, \
+				 &(__group_state)->tunnel_states, node)
+
+#define kbytes_to_mbits(__kbytes) \
+	DIV_ROUND_UP((__kbytes) * 8, 1000)
+
+#define DPTUN_BW_ARG(__bw) ((__bw) < 0 ? (__bw) : kbytes_to_mbits(__bw))
+
+#define __tun_prn(__tunnel, __level, __type, __fmt, ...) \
+	drm_##__level##__type((__tunnel)->group->mgr->dev, \
+			      "[DPTUN %s][%s] " __fmt, \
+			      drm_dp_tunnel_name(__tunnel), \
+			      (__tunnel)->aux->name, ## \
+			      __VA_ARGS__)
+
+#define tun_dbg(__tunnel, __fmt, ...) \
+	__tun_prn(__tunnel, dbg, _kms, __fmt, ## __VA_ARGS__)
+
+#define tun_dbg_stat(__tunnel, __err, __fmt, ...) do { \
+	if (__err) \
+		__tun_prn(__tunnel, dbg, _kms, __fmt " (Failed, err: %pe)\n", \
+			  ## __VA_ARGS__, ERR_PTR(__err)); \
+	else \
+		__tun_prn(__tunnel, dbg, _kms, __fmt " (Ok)\n", \
+			  ## __VA_ARGS__); \
+} while (0)
+
+#define tun_dbg_atomic(__tunnel, __fmt, ...) \
+	__tun_prn(__tunnel, dbg, _atomic, __fmt, ## __VA_ARGS__)
+
+#define tun_grp_dbg(__group, __fmt, ...) \
+	drm_dbg_kms((__group)->mgr->dev, \
+		    "[DPTUN %s] " __fmt, \
+		    drm_dp_tunnel_group_name(__group), ## \
+		    __VA_ARGS__)
+
+#define DP_TUNNELING_BASE DP_TUNNELING_OUI
+
+#define __DPTUN_REG_RANGE(__start, __size) \
+	GENMASK_ULL((__start) + (__size) - 1, (__start))
+
+#define DPTUN_REG_RANGE(__addr, __size) \
+	__DPTUN_REG_RANGE((__addr) - DP_TUNNELING_BASE, (__size))
+
+#define DPTUN_REG(__addr) DPTUN_REG_RANGE(__addr, 1)
+
+#define DPTUN_INFO_REG_MASK ( \
+	DPTUN_REG_RANGE(DP_TUNNELING_OUI, DP_TUNNELING_OUI_BYTES) | \
+	DPTUN_REG_RANGE(DP_TUNNELING_DEV_ID, DP_TUNNELING_DEV_ID_BYTES) | \
+	DPTUN_REG(DP_TUNNELING_HW_REV) | \
+	DPTUN_REG(DP_TUNNELING_SW_REV_MAJOR) | \
+	DPTUN_REG(DP_TUNNELING_SW_REV_MINOR) | \
+	DPTUN_REG(DP_TUNNELING_CAPABILITIES) | \
+	DPTUN_REG(DP_IN_ADAPTER_INFO) | \
+	DPTUN_REG(DP_USB4_DRIVER_ID) | \
+	DPTUN_REG(DP_USB4_DRIVER_BW_CAPABILITY) | \
+	DPTUN_REG(DP_IN_ADAPTER_TUNNEL_INFORMATION) | \
+	DPTUN_REG(DP_BW_GRANULARITY) | \
+	DPTUN_REG(DP_ESTIMATED_BW) | \
+	DPTUN_REG(DP_ALLOCATED_BW) | \
+	DPTUN_REG(DP_TUNNELING_MAX_LINK_RATE) | \
+	DPTUN_REG(DP_TUNNELING_MAX_LANE_COUNT) | \
+	DPTUN_REG(DP_DPTX_BW_ALLOCATION_MODE_CONTROL))
+
+static const DECLARE_BITMAP(dptun_info_regs, 64) = {
+	DPTUN_INFO_REG_MASK & -1UL,
+#if BITS_PER_LONG == 32
+	DPTUN_INFO_REG_MASK >> 32,
+#endif
+};
+
+struct drm_dp_tunnel_regs {
+	u8 buf[HWEIGHT64(DPTUN_INFO_REG_MASK)];
+};
+
+struct drm_dp_tunnel_group;
+
+struct drm_dp_tunnel {
+	struct drm_dp_tunnel_group *group;
+
+	struct list_head node;
+
+	struct kref kref;
+	struct ref_tracker *tracker;
+	struct drm_dp_aux *aux;
+	char name[8];
+
+	int bw_granularity;
+	int estimated_bw;
+	int allocated_bw;
+
+	int max_dprx_rate;
+	u8 max_dprx_lane_count;
+
+	u8 adapter_id;
+
+	bool bw_alloc_supported:1;
+	bool bw_alloc_enabled:1;
+	bool has_io_error:1;
+	bool destroyed:1;
+};
+
+struct drm_dp_tunnel_group_state;
+
+struct drm_dp_tunnel_state {
+	struct drm_dp_tunnel_group_state *group_state;
+
+	struct drm_dp_tunnel_ref tunnel_ref;
+
+	struct list_head node;
+
+	u32 stream_mask;
+	int *stream_bw;
+};
+
+struct drm_dp_tunnel_group_state {
+	struct drm_private_state base;
+
+	struct list_head tunnel_states;
+};
+
+struct drm_dp_tunnel_group {
+	struct drm_private_obj base;
+	struct drm_dp_tunnel_mgr *mgr;
+
+	struct list_head tunnels;
+
+	/* available BW including the allocated_bw of all tunnels in the group */
+	int available_bw;
+
+	u8 drv_group_id;
+	char name[8];
+
+	bool active:1;
+};
+
+struct drm_dp_tunnel_mgr {
+	struct drm_device *dev;
+
+	int group_count;
+	struct drm_dp_tunnel_group *groups;
+	wait_queue_head_t bw_req_queue;
+
+#ifdef CONFIG_DRM_DISPLAY_DEBUG_DP_TUNNEL_STATE
+	struct ref_tracker_dir ref_tracker;
+#endif
+};
+
+/*
+ * The following helpers provide a way to read out the tunneling DPCD
+ * registers with a minimal amount of AUX transfers (1 transfer per contiguous
+ * range, as permitted by the 16 byte per transfer AUX limit), not accessing
+ * other registers to avoid any read side-effects.
+ */
+static int next_reg_area(int *offset)
+{
+	*offset = find_next_bit(dptun_info_regs, 64, *offset);
+
+	return find_next_zero_bit(dptun_info_regs, 64, *offset + 1) - *offset;
+}
+
+#define tunnel_reg_ptr(__regs, __address) ({ \
+	WARN_ON(!test_bit((__address) - DP_TUNNELING_BASE, dptun_info_regs)); \
+	&(__regs)->buf[bitmap_weight(dptun_info_regs, (__address) - DP_TUNNELING_BASE)]; \
+})
+
+static int read_tunnel_regs(struct drm_dp_aux *aux, struct drm_dp_tunnel_regs *regs)
+{
+	int offset = 0;
+	int len;
+
+	while ((len = next_reg_area(&offset))) {
+		int address = DP_TUNNELING_BASE + offset;
+
+		if (drm_dp_dpcd_read(aux, address, tunnel_reg_ptr(regs, address), len) < 0)
+			return -EIO;
+
+		offset += len;
+	}
+
+	return 0;
+}
+
+static u8 tunnel_reg(const struct drm_dp_tunnel_regs *regs, int address)
+{
+	return *tunnel_reg_ptr(regs, address);
+}
+
+static u8 tunnel_reg_drv_group_id(const struct drm_dp_tunnel_regs *regs)
+{
+	u8 drv_id = tunnel_reg(regs, DP_USB4_DRIVER_ID) & DP_USB4_DRIVER_ID_MASK;
+	u8 group_id = tunnel_reg(regs, DP_IN_ADAPTER_TUNNEL_INFORMATION) & DP_GROUP_ID_MASK;
+
+	if (!group_id)
+		return 0;
+
+	return (drv_id << DP_GROUP_ID_BITS) | group_id;
+}
+
+/* Return granularity in kB/s units */
+static int tunnel_reg_bw_granularity(const struct drm_dp_tunnel_regs *regs)
+{
+	int gr = tunnel_reg(regs, DP_BW_GRANULARITY) & DP_BW_GRANULARITY_MASK;
+
+	if (gr > 2)
+		return -1;
+
+	return (250000 << gr) / 8;
+}
+
+static int tunnel_reg_max_dprx_rate(const struct drm_dp_tunnel_regs *regs)
+{
+	u8 bw_code = tunnel_reg(regs, DP_TUNNELING_MAX_LINK_RATE);
+
+	return drm_dp_bw_code_to_link_rate(bw_code);
+}
+
+static int tunnel_reg_max_dprx_lane_count(const struct drm_dp_tunnel_regs *regs)
+{
+	return tunnel_reg(regs, DP_TUNNELING_MAX_LANE_COUNT) &
+	       DP_TUNNELING_MAX_LANE_COUNT_MASK;
+}
+
+static bool tunnel_reg_bw_alloc_supported(const struct drm_dp_tunnel_regs *regs)
+{
+	u8 cap_mask = DP_TUNNELING_SUPPORT | DP_IN_BW_ALLOCATION_MODE_SUPPORT;
+
+	if ((tunnel_reg(regs, DP_TUNNELING_CAPABILITIES) & cap_mask) != cap_mask)
+		return false;
+
+	return tunnel_reg(regs, DP_USB4_DRIVER_BW_CAPABILITY) &
+	       DP_USB4_DRIVER_BW_ALLOCATION_MODE_SUPPORT;
+}
+
+static bool tunnel_reg_bw_alloc_enabled(const struct drm_dp_tunnel_regs *regs)
+{
+	return tunnel_reg(regs, DP_DPTX_BW_ALLOCATION_MODE_CONTROL) &
+	       DP_DISPLAY_DRIVER_BW_ALLOCATION_MODE_ENABLE;
+}
+
+static u8 tunnel_group_drv_id(u8 drv_group_id)
+{
+	return drv_group_id >> DP_GROUP_ID_BITS;
+}
+
+static u8 tunnel_group_id(u8 drv_group_id)
+{
+	return drv_group_id & DP_GROUP_ID_MASK;
+}
+
+const char *drm_dp_tunnel_name(const struct drm_dp_tunnel *tunnel)
+{
+	return tunnel->name;
+}
+EXPORT_SYMBOL(drm_dp_tunnel_name);
+
+static const char *drm_dp_tunnel_group_name(const struct drm_dp_tunnel_group *group)
+{
+	return group->name;
+}
+
+static struct drm_dp_tunnel_group *
+lookup_or_alloc_group(struct drm_dp_tunnel_mgr *mgr, u8 drv_group_id)
+{
+	struct drm_dp_tunnel_group *group = NULL;
+	int i;
+
+	for (i = 0; i < mgr->group_count; i++) {
+		/*
+		 * A tunnel group with 0 group ID shouldn't have more than one
+		 * tunnels.
+		 */
+		if (tunnel_group_id(drv_group_id) &&
+		    mgr->groups[i].drv_group_id == drv_group_id)
+			return &mgr->groups[i];
+
+		if (!group && !mgr->groups[i].active)
+			group = &mgr->groups[i];
+	}
+
+	if (!group) {
+		drm_dbg_kms(mgr->dev,
+			    "DPTUN: Can't allocate more tunnel groups\n");
+		return NULL;
+	}
+
+	group->drv_group_id = drv_group_id;
+	group->active = true;
+
+	/*
+	 * The group name format here and elsewhere: Driver-ID:Group-ID:*
+	 * (* standing for all DP-Adapters/tunnels in the group).
+	 */
+	snprintf(group->name, sizeof(group->name), "%d:%d:*",
+		 tunnel_group_drv_id(drv_group_id) & ((1 << DP_GROUP_ID_BITS) - 1),
+		 tunnel_group_id(drv_group_id) & ((1 << DP_USB4_DRIVER_ID_BITS) - 1));
+
+	return group;
+}
+
+static void free_group(struct drm_dp_tunnel_group *group)
+{
+	struct drm_dp_tunnel_mgr *mgr = group->mgr;
+
+	if (drm_WARN_ON(mgr->dev, !list_empty(&group->tunnels)))
+		return;
+
+	group->drv_group_id = 0;
+	group->available_bw = -1;
+	group->active = false;
+}
+
+static struct drm_dp_tunnel *
+tunnel_get(struct drm_dp_tunnel *tunnel)
+{
+	kref_get(&tunnel->kref);
+
+	return tunnel;
+}
+
+static void free_tunnel(struct kref *kref)
+{
+	struct drm_dp_tunnel *tunnel = container_of(kref, typeof(*tunnel), kref);
+	struct drm_dp_tunnel_group *group = tunnel->group;
+
+	list_del(&tunnel->node);
+	if (list_empty(&group->tunnels))
+		free_group(group);
+
+	kfree(tunnel);
+}
+
+static void tunnel_put(struct drm_dp_tunnel *tunnel)
+{
+	kref_put(&tunnel->kref, free_tunnel);
+}
+
+#ifdef CONFIG_DRM_DISPLAY_DEBUG_DP_TUNNEL_STATE
+static void track_tunnel_ref(struct drm_dp_tunnel *tunnel,
+			     struct ref_tracker **tracker)
+{
+	ref_tracker_alloc(&tunnel->group->mgr->ref_tracker,
+			  tracker, GFP_KERNEL);
+}
+
+static void untrack_tunnel_ref(struct drm_dp_tunnel *tunnel,
+			       struct ref_tracker **tracker)
+{
+	ref_tracker_free(&tunnel->group->mgr->ref_tracker,
+			 tracker);
+}
+#else
+static void track_tunnel_ref(struct drm_dp_tunnel *tunnel,
+			     struct ref_tracker **tracker)
+{