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, 660 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
new file mode 100644
index 000000000..129746713
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -0,0 +1,660 @@
+/*
+ * Copyright © 2012-2014 Intel Corporation
+ *
+ * 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 (including the next
+ * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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:
+ *    Eugeni Dodonov <eugeni.dodonov@intel.com>
+ *    Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ */
+
+#include <linux/pm_runtime.h>
+
+#include <drm/drm_print.h>
+
+#include "i915_drv.h"
+#include "i915_trace.h"
+
+/**
+ * DOC: runtime pm
+ *
+ * The i915 driver supports dynamic enabling and disabling of entire hardware
+ * blocks at runtime. This is especially important on the display side where
+ * software is supposed to control many power gates manually on recent hardware,
+ * since on the GT side a lot of the power management is done by the hardware.
+ * But even there some manual control at the device level is required.
+ *
+ * Since i915 supports a diverse set of platforms with a unified codebase and
+ * hardware engineers just love to shuffle functionality around between power
+ * domains there's a sizeable amount of indirection required. This file provides
+ * generic functions to the driver for grabbing and releasing references for
+ * abstract power domains. It then maps those to the actual power wells
+ * present for a given platform.
+ */
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+
+#include <linux/sort.h>
+
+#define STACKDEPTH 8
+
+static noinline depot_stack_handle_t __save_depot_stack(void)
+{
+	unsigned long entries[STACKDEPTH];
+	unsigned int n;
+
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
+}
+
+static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
+{
+	spin_lock_init(&rpm->debug.lock);
+	stack_depot_init();
+}
+
+static noinline depot_stack_handle_t
+track_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
+{
+	depot_stack_handle_t stack, *stacks;
+	unsigned long flags;
+
+	if (rpm->no_wakeref_tracking)
+		return -1;
+
+	stack = __save_depot_stack();
+	if (!stack)
+		return -1;
+
+	spin_lock_irqsave(&rpm->debug.lock, flags);
+
+	if (!rpm->debug.count)
+		rpm->debug.last_acquire = stack;
+
+	stacks = krealloc(rpm->debug.owners,
+			  (rpm->debug.count + 1) * sizeof(*stacks),
+			  GFP_NOWAIT | __GFP_NOWARN);
+	if (stacks) {
+		stacks[rpm->debug.count++] = stack;
+		rpm->debug.owners = stacks;
+	} else {
+		stack = -1;
+	}
+
+	spin_unlock_irqrestore(&rpm->debug.lock, flags);
+
+	return stack;
+}
+
+static void untrack_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm,
+					     depot_stack_handle_t stack)
+{
+	struct drm_i915_private *i915 = container_of(rpm,
+						     struct drm_i915_private,
+						     runtime_pm);
+	unsigned long flags, n;
+	bool found = false;
+
+	if (unlikely(stack == -1))
+		return;
+
+	spin_lock_irqsave(&rpm->debug.lock, flags);
+	for (n = rpm->debug.count; n--; ) {
+		if (rpm->debug.owners[n] == stack) {
+			memmove(rpm->debug.owners + n,
+				rpm->debug.owners + n + 1,
+				(--rpm->debug.count - n) * sizeof(stack));
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&rpm->debug.lock, flags);
+
+	if (drm_WARN(&i915->drm, !found,
+		     "Unmatched wakeref (tracking %lu), count %u\n",
+		     rpm->debug.count, atomic_read(&rpm->wakeref_count))) {
+		char *buf;
+
+		buf = kmalloc(PAGE_SIZE, GFP_NOWAIT | __GFP_NOWARN);
+		if (!buf)
+			return;
+
+		stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
+		DRM_DEBUG_DRIVER("wakeref %x from\n%s", stack, buf);
+
+		stack = READ_ONCE(rpm->debug.last_release);
+		if (stack) {
+			stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
+			DRM_DEBUG_DRIVER("wakeref last released at\n%s", buf);
+		}
+
+		kfree(buf);
+	}
+}
+
+static int cmphandle(const void *_a, const void *_b)
+{
+	const depot_stack_handle_t * const a = _a, * const b = _b;
+
+	if (*a < *b)
+		return -1;
+	else if (*a > *b)
+		return 1;
+	else
+		return 0;
+}
+
+static void
+__print_intel_runtime_pm_wakeref(struct drm_printer *p,
+				 const struct intel_runtime_pm_debug *dbg)
+{
+	unsigned long i;
+	char *buf;
+
+	buf = kmalloc(PAGE_SIZE, GFP_NOWAIT | __GFP_NOWARN);
+	if (!buf)
+		return;
+
+	if (dbg->last_acquire) {
+		stack_depot_snprint(dbg->last_acquire, buf, PAGE_SIZE, 2);
+		drm_printf(p, "Wakeref last acquired:\n%s", buf);
+	}
+
+	if (dbg->last_release) {
+		stack_depot_snprint(dbg->last_release, buf, PAGE_SIZE, 2);
+		drm_printf(p, "Wakeref last released:\n%s", buf);
+	}
+
+	drm_printf(p, "Wakeref count: %lu\n", dbg->count);
+
+	sort(dbg->owners, dbg->count, sizeof(*dbg->owners), cmphandle, NULL);
+
+	for (i = 0; i < dbg->count; i++) {
+		depot_stack_handle_t stack = dbg->owners[i];
+		unsigned long rep;
+
+		rep = 1;
+		while (i + 1 < dbg->count && dbg->owners[i + 1] == stack)
+			rep++, i++;
+		stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
+		drm_printf(p, "Wakeref x%lu taken at:\n%s", rep, buf);
+	}
+
+	kfree(buf);
+}
+
+static noinline void
+__untrack_all_wakerefs(struct intel_runtime_pm_debug *debug,
+		       struct intel_runtime_pm_debug *saved)
+{
+	*saved = *debug;
+
+	debug->owners = NULL;
+	debug->count = 0;
+	debug->last_release = __save_depot_stack();
+}
+
+static void
+dump_and_free_wakeref_tracking(struct intel_runtime_pm_debug *debug)
+{
+	if (debug->count) {
+		struct drm_printer p = drm_debug_printer("i915");
+
+		__print_intel_runtime_pm_wakeref(&p, debug);
+	}
+
+	kfree(debug->owners);
+}
+
+static noinline void
+__intel_wakeref_dec_and_check_tracking(struct intel_runtime_pm *rpm)
+{
+	struct intel_runtime_pm_debug dbg = {};
+	unsigned long flags;
+
+	if (!atomic_dec_and_lock_irqsave(&rpm->wakeref_count,
+					 &rpm->debug.lock,
+					 flags))
+		return;
+
+	__untrack_all_wakerefs(&rpm->debug, &dbg);
+	spin_unlock_irqrestore(&rpm->debug.lock, flags);
+
+	dump_and_free_wakeref_tracking(&dbg);
+}
+
+static noinline void
+untrack_all_intel_runtime_pm_wakerefs(struct intel_runtime_pm *rpm)
+{
+	struct intel_runtime_pm_debug dbg = {};
+	unsigned long flags;
+
+	spin_lock_irqsave(&rpm->debug.lock, flags);
+	__untrack_all_wakerefs(&rpm->debug, &dbg);
+	spin_unlock_irqrestore(&rpm->debug.lock, flags);
+
+	dump_and_free_wakeref_tracking(&dbg);
+}
+
+void print_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm,
+				    struct drm_printer *p)
+{
+	struct intel_runtime_pm_debug dbg = {};
+
+	do {
+		unsigned long alloc = dbg.count;
+		depot_stack_handle_t *s;
+
+		spin_lock_irq(&rpm->debug.lock);
+		dbg.count = rpm->debug.count;
+		if (dbg.count <= alloc) {
+			memcpy(dbg.owners,
+			       rpm->debug.owners,
+			       dbg.count * sizeof(*s));
+		}
+		dbg.last_acquire = rpm->debug.last_acquire;
+		dbg.last_release = rpm->debug.last_release;
+		spin_unlock_irq(&rpm->debug.lock);
+		if (dbg.count <= alloc)
+			break;
+
+		s = krealloc(dbg.owners,
+			     dbg.count * sizeof(*s),
+			     GFP_NOWAIT | __GFP_NOWARN);
+		if (!s)
+			goto out;
+
+		dbg.owners = s;
+	} while (1);
+
+	__print_intel_runtime_pm_wakeref(p, &dbg);
+
+out:
+	kfree(dbg.owners);
+}
+
+#else
+
+static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
+{
+}
+
+static depot_stack_handle_t
+track_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
+{
+	return -1;
+}
+
+static void untrack_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm,
+					     intel_wakeref_t wref)
+{
+}
+
+static void
+__intel_wakeref_dec_and_check_tracking(struct intel_runtime_pm *rpm)
+{
+	atomic_dec(&rpm->wakeref_count);
+}
+
+static void
+untrack_all_intel_runtime_pm_wakerefs(struct intel_runtime_pm *rpm)
+{
+}
+
+#endif
+
+static void
+intel_runtime_pm_acquire(struct intel_runtime_pm *rpm, bool wakelock)
+{
+	if (wakelock) {
+		atomic_add(1 + INTEL_RPM_WAKELOCK_BIAS, &rpm->wakeref_count);
+		assert_rpm_wakelock_held(rpm);
+	} else {
+		atomic_inc(&rpm->wakeref_count);
+		assert_rpm_raw_wakeref_held(rpm);
+	}
+}
+
+static void
+intel_runtime_pm_release(struct intel_runtime_pm *rpm, int wakelock)
+{
+	if (wakelock) {
+		assert_rpm_wakelock_held(rpm);
+		atomic_sub(INTEL_RPM_WAKELOCK_BIAS, &rpm->wakeref_count);
+	} else {
+		assert_rpm_raw_wakeref_held(rpm);
+	}
+
+	__intel_wakeref_dec_and_check_tracking(rpm);
+}
+
+static intel_wakeref_t __intel_runtime_pm_get(struct intel_runtime_pm *rpm,
+					      bool wakelock)
+{
+	struct drm_i915_private *i915 = container_of(rpm,
+						     struct drm_i915_private,
+						     runtime_pm);
+	int ret;
+
+	ret = pm_runtime_get_sync(rpm->kdev);
+	drm_WARN_ONCE(&i915->drm, ret < 0,
+		      "pm_runtime_get_sync() failed: %d\n", ret);
+
+	intel_runtime_pm_acquire(rpm, wakelock);
+
+	return track_intel_runtime_pm_wakeref(rpm);
+}
+
+/**
+ * intel_runtime_pm_get_raw - grab a raw runtime pm reference
+ * @rpm: the intel_runtime_pm structure
+ *
+ * This is the unlocked version of intel_display_power_is_enabled() and should
+ * only be used from error capture and recovery code where deadlocks are
+ * possible.
+ * This function grabs a device-level runtime pm reference (mostly used for
+ * asynchronous PM management from display code) and ensures that it is powered
+ * up. Raw references are not considered during wakelock assert checks.
+ *
+ * Any runtime pm reference obtained by this function must have a symmetric
+ * call to intel_runtime_pm_put_raw() to release the reference again.
+ *
+ * Returns: the wakeref cookie to pass to intel_runtime_pm_put_raw(), evaluates
+ * as True if the wakeref was acquired, or False otherwise.
+ */
+intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm)
+{
+	return __intel_runtime_pm_get(rpm, false);
+}
+
+/**
+ * intel_runtime_pm_get - grab a runtime pm reference
+ * @rpm: the intel_runtime_pm structure
+ *
+ * This function grabs a device-level runtime pm reference (mostly used for GEM
+ * code to ensure the GTT or GT is on) and ensures that it is powered up.
+ *
+ * Any runtime pm reference obtained by this function must have a symmetric
+ * call to intel_runtime_pm_put() to release the reference again.
+ *
+ * Returns: the wakeref cookie to pass to intel_runtime_pm_put()
+ */
+intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm)
+{
+	return __intel_runtime_pm_get(rpm, true);
+}
+
+/**
+ * __intel_runtime_pm_get_if_active - grab a runtime pm reference if device is active
+ * @rpm: the intel_runtime_pm structure
+ * @ignore_usecount: get a ref even if dev->power.usage_count is 0
+ *
+ * This function grabs a device-level runtime pm reference if the device is
+ * already active and ensures that it is powered up. It is illegal to try
+ * and access the HW should intel_runtime_pm_get_if_active() report failure.
+ *
+ * If @ignore_usecount is true, a reference will be acquired even if there is no
+ * user requiring the device to be powered up (dev->power.usage_count == 0).
+ * If the function returns false in this case then it's guaranteed that the
+ * device's runtime suspend hook has been called already or that it will be
+ * called (and hence it's also guaranteed that the device's runtime resume
+ * hook will be called eventually).
+ *
+ * Any runtime pm reference obtained by this function must have a symmetric
+ * call to intel_runtime_pm_put() to release the reference again.
+ *
+ * Returns: the wakeref cookie to pass to intel_runtime_pm_put(), evaluates
+ * as True if the wakeref was acquired, or False otherwise.
+ */
+static intel_wakeref_t __intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm,
+							bool ignore_usecount)
+{
+	if (IS_ENABLED(CONFIG_PM)) {
+		/*
+		 * In cases runtime PM is disabled by the RPM core and we get
+		 * an -EINVAL return value we are not supposed to call this
+		 * function, since the power state is undefined. This applies
+		 * atm to the late/early system suspend/resume handlers.
+		 */
+		if (pm_runtime_get_if_active(rpm->kdev, ignore_usecount) <= 0)
+			return 0;
+	}
+
+	intel_runtime_pm_acquire(rpm, true);
+
+	return track_intel_runtime_pm_wakeref(rpm);
+}
+
+intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm)
+{
+	return __intel_runtime_pm_get_if_active(rpm, false);
+}
+
+intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm)
+{
+	return __intel_runtime_pm_get_if_active(rpm, true);
+}
+
+/**
+ * intel_runtime_pm_get_noresume - grab a runtime pm reference
+ * @rpm: the intel_runtime_pm structure
+ *
+ * This function grabs a device-level runtime pm reference (mostly used for GEM
+ * code to ensure the GTT or GT is on).
+ *
+ * It will _not_ power up the device but instead only check that it's powered
+ * on.  Therefore it is only valid to call this functions from contexts where
+ * the device is known to be powered up and where trying to power it up would
+ * result in hilarity and deadlocks. That pretty much means only the system
+ * suspend/resume code where this is used to grab runtime pm references for
+ * delayed setup down in work items.
+ *
+ * Any runtime pm reference obtained by this function must have a symmetric
+ * call to intel_runtime_pm_put() to release the reference again.
+ *
+ * Returns: the wakeref cookie to pass to intel_runtime_pm_put()
+ */
+intel_wakeref_t intel_runtime_pm_get_noresume(struct intel_runtime_pm *rpm)
+{
+	assert_rpm_wakelock_held(rpm);
+	pm_runtime_get_noresume(rpm->kdev);
+
+	intel_runtime_pm_acquire(rpm, true);
+
+	return track_intel_runtime_pm_wakeref(rpm);
+}
+
+static void __intel_runtime_pm_put(struct intel_runtime_pm *rpm,
+				   intel_wakeref_t wref,
+				   bool wakelock)
+{
+	struct device *kdev = rpm->kdev;
+
+	untrack_intel_runtime_pm_wakeref(rpm, wref);
+
+	intel_runtime_pm_release(rpm, wakelock);
+
+	pm_runtime_mark_last_busy(kdev);
+	pm_runtime_put_autosuspend(kdev);
+}
+
+/**
+ * intel_runtime_pm_put_raw - release a raw runtime pm reference
+ * @rpm: the intel_runtime_pm structure
+ * @wref: wakeref acquired for the reference that is being released
+ *
+ * This function drops the device-level runtime pm reference obtained by
+ * intel_runtime_pm_get_raw() and might power down the corresponding
+ * hardware block right away if this is the last reference.
+ */
+void
+intel_runtime_pm_put_raw(struct intel_runtime_pm *rpm, intel_wakeref_t wref)
+{
+	__intel_runtime_pm_put(rpm, wref, false);
+}
+
+/**
+ * intel_runtime_pm_put_unchecked - release an unchecked runtime pm reference
+ * @rpm: the intel_runtime_pm structure
+ *
+ * This function drops the device-level runtime pm reference obtained by
+ * intel_runtime_pm_get() and might power down the corresponding
+ * hardware block right away if this is the last reference.
+ *
+ * This function exists only for historical reasons and should be avoided in
+ * new code, as the correctness of its use cannot be checked. Always use
+ * intel_runtime_pm_put() instead.
+ */
+void intel_runtime_pm_put_unchecked(struct intel_runtime_pm *rpm)
+{
+	__intel_runtime_pm_put(rpm, -1, true);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+/**
+ * intel_runtime_pm_put - release a runtime pm reference
+ * @rpm: the intel_runtime_pm structure
+ * @wref: wakeref acquired for the reference that is being released
+ *
+ * This function drops the device-level runtime pm reference obtained by
+ * intel_runtime_pm_get() and might power down the corresponding
+ * hardware block right away if this is the last reference.
+ */
+void intel_runtime_pm_put(struct intel_runtime_pm *rpm, intel_wakeref_t wref)
+{
+	__intel_runtime_pm_put(rpm, wref, true);
+}
+#endif
+
+/**
+ * intel_runtime_pm_enable - enable runtime pm
+ * @rpm: the intel_runtime_pm structure
+ *
+ * This function enables runtime pm at the end of the driver load sequence.
+ *
+ * Note that this function does currently not enable runtime pm for the
+ * subordinate display power domains. That is done by
+ * intel_power_domains_enable().
+ */
+void intel_runtime_pm_enable(struct intel_runtime_pm *rpm)
+{
+	struct drm_i915_private *i915 = container_of(rpm,
+						     struct drm_i915_private,
+						     runtime_pm);
+	struct device *kdev = rpm->kdev;
+
+	/*
+	 * Disable the system suspend direct complete optimization, which can
+	 * leave the device suspended skipping the driver's suspend handlers
+	 * if the device was already runtime suspended. This is needed due to
+	 * the difference in our runtime and system suspend sequence and
+	 * becaue the HDA driver may require us to enable the audio power
+	 * domain during system suspend.
+	 */
+	dev_pm_set_driver_flags(kdev, DPM_FLAG_NO_DIRECT_COMPLETE);
+
+	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
+	pm_runtime_mark_last_busy(kdev);
+
+	/*
+	 * Take a permanent reference to disable the RPM functionality and drop
+	 * it only when unloading the driver. Use the low level get/put helpers,
+	 * so the driver's own RPM reference tracking asserts also work on
+	 * platforms without RPM support.
+	 */
+	if (!rpm->available) {
+		int ret;
+
+		pm_runtime_dont_use_autosuspend(kdev);
+		ret = pm_runtime_get_sync(kdev);
+		drm_WARN(&i915->drm, ret < 0,
+			 "pm_runtime_get_sync() failed: %d\n", ret);
+	} else {
+		pm_runtime_use_autosuspend(kdev);
+	}
+
+	/*
+	 *  FIXME: Temp hammer to keep autosupend disable on lmem supported platforms.
+	 *  As per PCIe specs 5.3.1.4.1, all iomem read write request over a PCIe
+	 *  function will be unsupported in case PCIe endpoint function is in D3.
+	 *  Let's keep i915 autosuspend control 'on' till we fix all known issue
+	 *  with lmem access in D3.
+	 */
+	if (!IS_DGFX(i915))
+		pm_runtime_allow(kdev);
+
+	/*
+	 * The core calls the driver load handler with an RPM reference held.
+	 * We drop that here and will reacquire it during unloading in
+	 * intel_power_domains_fini().
+	 */
+	pm_runtime_put_autosuspend(kdev);
+}
+
+void intel_runtime_pm_disable(struct intel_runtime_pm *rpm)
+{
+	struct drm_i915_private *i915 = container_of(rpm,
+						     struct drm_i915_private,
+						     runtime_pm);
+	struct device *kdev = rpm->kdev;
+
+	/* Transfer rpm ownership back to core */
+	drm_WARN(&i915->drm, pm_runtime_get_sync(kdev) < 0,
+		 "Failed to pass rpm ownership back to core\n");
+
+	pm_runtime_dont_use_autosuspend(kdev);
+
+	if (!rpm->available)
+		pm_runtime_put(kdev);
+}
+
+void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm)
+{
+	struct drm_i915_private *i915 = container_of(rpm,
+						     struct drm_i915_private,
+						     runtime_pm);
+	int count = atomic_read(&rpm->wakeref_count);
+
+	intel_wakeref_auto_fini(&rpm->userfault_wakeref);
+
+	drm_WARN(&i915->drm, count,
+		 "i915 raw-wakerefs=%d wakelocks=%d on cleanup\n",
+		 intel_rpm_raw_wakeref_count(count),
+		 intel_rpm_wakelock_count(count));
+
+	untrack_all_intel_runtime_pm_wakerefs(rpm);
+}
+
+void intel_runtime_pm_init_early(struct intel_runtime_pm *rpm)
+{
+	struct drm_i915_private *i915 =
+			container_of(rpm, struct drm_i915_private, runtime_pm);
+	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+	struct device *kdev = &pdev->dev;
+
+	rpm->kdev = kdev;
+	rpm->available = HAS_RUNTIME_PM(i915);
+
+	init_intel_runtime_pm_wakeref(rpm);
+	INIT_LIST_HEAD(&rpm->lmem_userfault_list);
+	spin_lock_init(&rpm->lmem_userfault_lock);
+	intel_wakeref_auto_init(&rpm->userfault_wakeref, rpm);
+}