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, 460 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
new file mode 100644
index 000000000..ed02b6d8b
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -0,0 +1,460 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright 2014-2022 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include "kfd_device_queue_manager.h"
+#include "kfd_kernel_queue.h"
+#include "kfd_priv.h"
+
+static inline void inc_wptr(unsigned int *wptr, unsigned int increment_bytes,
+				unsigned int buffer_size_bytes)
+{
+	unsigned int temp = *wptr + increment_bytes / sizeof(uint32_t);
+
+	WARN((temp * sizeof(uint32_t)) > buffer_size_bytes,
+	     "Runlist IB overflow");
+	*wptr = temp;
+}
+
+static void pm_calc_rlib_size(struct packet_manager *pm,
+				unsigned int *rlib_size,
+				bool *over_subscription)
+{
+	unsigned int process_count, queue_count, compute_queue_count, gws_queue_count;
+	unsigned int map_queue_size;
+	unsigned int max_proc_per_quantum = 1;
+	struct kfd_dev *dev = pm->dqm->dev;
+
+	process_count = pm->dqm->processes_count;
+	queue_count = pm->dqm->active_queue_count;
+	compute_queue_count = pm->dqm->active_cp_queue_count;
+	gws_queue_count = pm->dqm->gws_queue_count;
+
+	/* check if there is over subscription
+	 * Note: the arbitration between the number of VMIDs and
+	 * hws_max_conc_proc has been done in
+	 * kgd2kfd_device_init().
+	 */
+	*over_subscription = false;
+
+	if (dev->max_proc_per_quantum > 1)
+		max_proc_per_quantum = dev->max_proc_per_quantum;
+
+	if ((process_count > max_proc_per_quantum) ||
+	    compute_queue_count > get_cp_queues_num(pm->dqm) ||
+	    gws_queue_count > 1) {
+		*over_subscription = true;
+		pr_debug("Over subscribed runlist\n");
+	}
+
+	map_queue_size = pm->pmf->map_queues_size;
+	/* calculate run list ib allocation size */
+	*rlib_size = process_count * pm->pmf->map_process_size +
+		     queue_count * map_queue_size;
+
+	/*
+	 * Increase the allocation size in case we need a chained run list
+	 * when over subscription
+	 */
+	if (*over_subscription)
+		*rlib_size += pm->pmf->runlist_size;
+
+	pr_debug("runlist ib size %d\n", *rlib_size);
+}
+
+static int pm_allocate_runlist_ib(struct packet_manager *pm,
+				unsigned int **rl_buffer,
+				uint64_t *rl_gpu_buffer,
+				unsigned int *rl_buffer_size,
+				bool *is_over_subscription)
+{
+	int retval;
+
+	if (WARN_ON(pm->allocated))
+		return -EINVAL;
+
+	pm_calc_rlib_size(pm, rl_buffer_size, is_over_subscription);
+
+	mutex_lock(&pm->lock);
+
+	retval = kfd_gtt_sa_allocate(pm->dqm->dev, *rl_buffer_size,
+					&pm->ib_buffer_obj);
+
+	if (retval) {
+		pr_err("Failed to allocate runlist IB\n");
+		goto out;
+	}
+
+	*(void **)rl_buffer = pm->ib_buffer_obj->cpu_ptr;
+	*rl_gpu_buffer = pm->ib_buffer_obj->gpu_addr;
+
+	memset(*rl_buffer, 0, *rl_buffer_size);
+	pm->allocated = true;
+
+out:
+	mutex_unlock(&pm->lock);
+	return retval;
+}
+
+static int pm_create_runlist_ib(struct packet_manager *pm,
+				struct list_head *queues,
+				uint64_t *rl_gpu_addr,
+				size_t *rl_size_bytes)
+{
+	unsigned int alloc_size_bytes;
+	unsigned int *rl_buffer, rl_wptr, i;
+	int retval, processes_mapped;
+	struct device_process_node *cur;
+	struct qcm_process_device *qpd;
+	struct queue *q;
+	struct kernel_queue *kq;
+	bool is_over_subscription;
+
+	rl_wptr = retval = processes_mapped = 0;
+
+	retval = pm_allocate_runlist_ib(pm, &rl_buffer, rl_gpu_addr,
+				&alloc_size_bytes, &is_over_subscription);
+	if (retval)
+		return retval;
+
+	*rl_size_bytes = alloc_size_bytes;
+	pm->ib_size_bytes = alloc_size_bytes;
+
+	pr_debug("Building runlist ib process count: %d queues count %d\n",
+		pm->dqm->processes_count, pm->dqm->active_queue_count);
+
+	/* build the run list ib packet */
+	list_for_each_entry(cur, queues, list) {
+		qpd = cur->qpd;
+		/* build map process packet */
+		if (processes_mapped >= pm->dqm->processes_count) {
+			pr_debug("Not enough space left in runlist IB\n");
+			pm_release_ib(pm);
+			return -ENOMEM;
+		}
+
+		retval = pm->pmf->map_process(pm, &rl_buffer[rl_wptr], qpd);
+		if (retval)
+			return retval;
+
+		processes_mapped++;
+		inc_wptr(&rl_wptr, pm->pmf->map_process_size,
+				alloc_size_bytes);
+
+		list_for_each_entry(kq, &qpd->priv_queue_list, list) {
+			if (!kq->queue->properties.is_active)
+				continue;
+
+			pr_debug("static_queue, mapping kernel q %d, is debug status %d\n",
+				kq->queue->queue, qpd->is_debug);
+
+			retval = pm->pmf->map_queues(pm,
+						&rl_buffer[rl_wptr],
+						kq->queue,
+						qpd->is_debug);
+			if (retval)
+				return retval;
+
+			inc_wptr(&rl_wptr,
+				pm->pmf->map_queues_size,
+				alloc_size_bytes);
+		}
+
+		list_for_each_entry(q, &qpd->queues_list, list) {
+			if (!q->properties.is_active)
+				continue;
+
+			pr_debug("static_queue, mapping user queue %d, is debug status %d\n",
+				q->queue, qpd->is_debug);
+
+			retval = pm->pmf->map_queues(pm,
+						&rl_buffer[rl_wptr],
+						q,
+						qpd->is_debug);
+
+			if (retval)
+				return retval;
+
+			inc_wptr(&rl_wptr,
+				pm->pmf->map_queues_size,
+				alloc_size_bytes);
+		}
+	}
+
+	pr_debug("Finished map process and queues to runlist\n");
+
+	if (is_over_subscription) {
+		if (!pm->is_over_subscription)
+			pr_warn("Runlist is getting oversubscribed. Expect reduced ROCm performance.\n");
+		retval = pm->pmf->runlist(pm, &rl_buffer[rl_wptr],
+					*rl_gpu_addr,
+					alloc_size_bytes / sizeof(uint32_t),
+					true);
+	}
+	pm->is_over_subscription = is_over_subscription;
+
+	for (i = 0; i < alloc_size_bytes / sizeof(uint32_t); i++)
+		pr_debug("0x%2X ", rl_buffer[i]);
+	pr_debug("\n");
+
+	return retval;
+}
+
+int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
+{
+	switch (dqm->dev->adev->asic_type) {
+	case CHIP_KAVERI:
+	case CHIP_HAWAII:
+		/* PM4 packet structures on CIK are the same as on VI */
+	case CHIP_CARRIZO:
+	case CHIP_TONGA:
+	case CHIP_FIJI:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
+		pm->pmf = &kfd_vi_pm_funcs;
+		break;
+	default:
+		if (KFD_GC_VERSION(dqm->dev) == IP_VERSION(9, 4, 2))
+			pm->pmf = &kfd_aldebaran_pm_funcs;
+		else if (KFD_GC_VERSION(dqm->dev) >= IP_VERSION(9, 0, 1))
+			pm->pmf = &kfd_v9_pm_funcs;
+		else {
+			WARN(1, "Unexpected ASIC family %u",
+			     dqm->dev->adev->asic_type);
+			return -EINVAL;
+		}
+	}
+
+	pm->dqm = dqm;
+	mutex_init(&pm->lock);
+	pm->priv_queue = kernel_queue_init(dqm->dev, KFD_QUEUE_TYPE_HIQ);
+	if (!pm->priv_queue) {
+		mutex_destroy(&pm->lock);
+		return -ENOMEM;
+	}
+	pm->allocated = false;
+
+	return 0;
+}
+
+void pm_uninit(struct packet_manager *pm, bool hanging)
+{
+	mutex_destroy(&pm->lock);
+	kernel_queue_uninit(pm->priv_queue, hanging);
+	pm->priv_queue = NULL;
+}
+
+int pm_send_set_resources(struct packet_manager *pm,
+				struct scheduling_resources *res)
+{
+	uint32_t *buffer, size;
+	int retval = 0;
+
+	size = pm->pmf->set_resources_size;
+	mutex_lock(&pm->lock);
+	kq_acquire_packet_buffer(pm->priv_queue,
+					size / sizeof(uint32_t),
+					(unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		retval = -ENOMEM;
+		goto out;
+	}
+
+	retval = pm->pmf->set_resources(pm, buffer, res);
+	if (!retval)
+		kq_submit_packet(pm->priv_queue);
+	else
+		kq_rollback_packet(pm->priv_queue);
+
+out:
+	mutex_unlock(&pm->lock);
+
+	return retval;
+}
+
+int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
+{
+	uint64_t rl_gpu_ib_addr;
+	uint32_t *rl_buffer;
+	size_t rl_ib_size, packet_size_dwords;
+	int retval;
+
+	retval = pm_create_runlist_ib(pm, dqm_queues, &rl_gpu_ib_addr,
+					&rl_ib_size);
+	if (retval)
+		goto fail_create_runlist_ib;
+
+	pr_debug("runlist IB address: 0x%llX\n", rl_gpu_ib_addr);
+
+	packet_size_dwords = pm->pmf->runlist_size / sizeof(uint32_t);
+	mutex_lock(&pm->lock);
+
+	retval = kq_acquire_packet_buffer(pm->priv_queue,
+					packet_size_dwords, &rl_buffer);
+	if (retval)
+		goto fail_acquire_packet_buffer;
+
+	retval = pm->pmf->runlist(pm, rl_buffer, rl_gpu_ib_addr,
+					rl_ib_size / sizeof(uint32_t), false);
+	if (retval)
+		goto fail_create_runlist;
+
+	kq_submit_packet(pm->priv_queue);
+
+	mutex_unlock(&pm->lock);
+
+	return retval;
+
+fail_create_runlist:
+	kq_rollback_packet(pm->priv_queue);
+fail_acquire_packet_buffer:
+	mutex_unlock(&pm->lock);
+fail_create_runlist_ib:
+	pm_release_ib(pm);
+	return retval;
+}
+
+int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
+			uint64_t fence_value)
+{
+	uint32_t *buffer, size;
+	int retval = 0;
+
+	if (WARN_ON(!fence_address))
+		return -EFAULT;
+
+	size = pm->pmf->query_status_size;
+	mutex_lock(&pm->lock);
+	kq_acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		retval = -ENOMEM;
+		goto out;
+	}
+
+	retval = pm->pmf->query_status(pm, buffer, fence_address, fence_value);
+	if (!retval)
+		kq_submit_packet(pm->priv_queue);
+	else
+		kq_rollback_packet(pm->priv_queue);
+
+out:
+	mutex_unlock(&pm->lock);
+	return retval;
+}
+
+int pm_send_unmap_queue(struct packet_manager *pm,
+			enum kfd_unmap_queues_filter filter,
+			uint32_t filter_param, bool reset)
+{
+	uint32_t *buffer, size;
+	int retval = 0;
+
+	size = pm->pmf->unmap_queues_size;
+	mutex_lock(&pm->lock);
+	kq_acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		retval = -ENOMEM;
+		goto out;
+	}
+
+	retval = pm->pmf->unmap_queues(pm, buffer, filter, filter_param, reset);
+	if (!retval)
+		kq_submit_packet(pm->priv_queue);
+	else
+		kq_rollback_packet(pm->priv_queue);
+
+out:
+	mutex_unlock(&pm->lock);
+	return retval;
+}
+
+void pm_release_ib(struct packet_manager *pm)
+{
+	mutex_lock(&pm->lock);
+	if (pm->allocated) {
+		kfd_gtt_sa_free(pm->dqm->dev, pm->ib_buffer_obj);
+		pm->allocated = false;
+	}
+	mutex_unlock(&pm->lock);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+
+int pm_debugfs_runlist(struct seq_file *m, void *data)
+{
+	struct packet_manager *pm = data;
+
+	mutex_lock(&pm->lock);
+
+	if (!pm->allocated) {
+		seq_puts(m, "  No active runlist\n");
+		goto out;
+	}
+
+	seq_hex_dump(m, "  ", DUMP_PREFIX_OFFSET, 32, 4,
+		     pm->ib_buffer_obj->cpu_ptr, pm->ib_size_bytes, false);
+
+out:
+	mutex_unlock(&pm->lock);
+	return 0;
+}
+
+int pm_debugfs_hang_hws(struct packet_manager *pm)
+{
+	uint32_t *buffer, size;
+	int r = 0;
+
+	if (!pm->priv_queue)
+		return -EAGAIN;
+
+	size = pm->pmf->query_status_size;
+	mutex_lock(&pm->lock);
+	kq_acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		r = -ENOMEM;
+		goto out;
+	}
+	memset(buffer, 0x55, size);
+	kq_submit_packet(pm->priv_queue);
+
+	pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
+		buffer[0], buffer[1], buffer[2], buffer[3],
+		buffer[4], buffer[5], buffer[6]);
+out:
+	mutex_unlock(&pm->lock);
+	return r;
+}
+
+
+#endif