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, 604 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
new file mode 100644
index 000000000..00871ef99
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -0,0 +1,604 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include <linux/nospec.h>
+
+#include "i915_drv.h"
+#include "i915_perf.h"
+#include "i915_query.h"
+#include "gt/intel_engine_user.h"
+#include <uapi/drm/i915_drm.h>
+
+static int copy_query_item(void *query_hdr, size_t query_sz,
+			   u32 total_length,
+			   struct drm_i915_query_item *query_item)
+{
+	if (query_item->length == 0)
+		return total_length;
+
+	if (query_item->length < total_length)
+		return -EINVAL;
+
+	if (copy_from_user(query_hdr, u64_to_user_ptr(query_item->data_ptr),
+			   query_sz))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int fill_topology_info(const struct sseu_dev_info *sseu,
+			      struct drm_i915_query_item *query_item,
+			      intel_sseu_ss_mask_t subslice_mask)
+{
+	struct drm_i915_query_topology_info topo;
+	u32 slice_length, subslice_length, eu_length, total_length;
+	int ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
+	int eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+	int ret;
+
+	BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
+
+	if (sseu->max_slices == 0)
+		return -ENODEV;
+
+	slice_length = sizeof(sseu->slice_mask);
+	subslice_length = sseu->max_slices * ss_stride;
+	eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
+	total_length = sizeof(topo) + slice_length + subslice_length +
+		       eu_length;
+
+	ret = copy_query_item(&topo, sizeof(topo), total_length, query_item);
+
+	if (ret != 0)
+		return ret;
+
+	memset(&topo, 0, sizeof(topo));
+	topo.max_slices = sseu->max_slices;
+	topo.max_subslices = sseu->max_subslices;
+	topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
+
+	topo.subslice_offset = slice_length;
+	topo.subslice_stride = ss_stride;
+	topo.eu_offset = slice_length + subslice_length;
+	topo.eu_stride = eu_stride;
+
+	if (copy_to_user(u64_to_user_ptr(query_item->data_ptr),
+			 &topo, sizeof(topo)))
+		return -EFAULT;
+
+	if (copy_to_user(u64_to_user_ptr(query_item->data_ptr + sizeof(topo)),
+			 &sseu->slice_mask, slice_length))
+		return -EFAULT;
+
+	if (intel_sseu_copy_ssmask_to_user(u64_to_user_ptr(query_item->data_ptr +
+							   sizeof(topo) + slice_length),
+					   sseu))
+		return -EFAULT;
+
+	if (intel_sseu_copy_eumask_to_user(u64_to_user_ptr(query_item->data_ptr +
+							   sizeof(topo) +
+							   slice_length + subslice_length),
+					   sseu))
+		return -EFAULT;
+
+	return total_length;
+}
+
+static int query_topology_info(struct drm_i915_private *dev_priv,
+			       struct drm_i915_query_item *query_item)
+{
+	const struct sseu_dev_info *sseu = &to_gt(dev_priv)->info.sseu;
+
+	if (query_item->flags != 0)
+		return -EINVAL;
+
+	return fill_topology_info(sseu, query_item, sseu->subslice_mask);
+}
+
+static int query_geometry_subslices(struct drm_i915_private *i915,
+				    struct drm_i915_query_item *query_item)
+{
+	const struct sseu_dev_info *sseu;
+	struct intel_engine_cs *engine;
+	struct i915_engine_class_instance classinstance;
+
+	if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
+		return -ENODEV;
+
+	classinstance = *((struct i915_engine_class_instance *)&query_item->flags);
+
+	engine = intel_engine_lookup_user(i915, (u8)classinstance.engine_class,
+					  (u8)classinstance.engine_instance);
+
+	if (!engine)
+		return -EINVAL;
+
+	if (engine->class != RENDER_CLASS)
+		return -EINVAL;
+
+	sseu = &engine->gt->info.sseu;
+
+	return fill_topology_info(sseu, query_item, sseu->geometry_subslice_mask);
+}
+
+static int
+query_engine_info(struct drm_i915_private *i915,
+		  struct drm_i915_query_item *query_item)
+{
+	struct drm_i915_query_engine_info __user *query_ptr =
+				u64_to_user_ptr(query_item->data_ptr);
+	struct drm_i915_engine_info __user *info_ptr;
+	struct drm_i915_query_engine_info query;
+	struct drm_i915_engine_info info = { };
+	unsigned int num_uabi_engines = 0;
+	struct intel_engine_cs *engine;
+	int len, ret;
+
+	if (query_item->flags)
+		return -EINVAL;
+
+	for_each_uabi_engine(engine, i915)
+		num_uabi_engines++;
+
+	len = struct_size(query_ptr, engines, num_uabi_engines);
+
+	ret = copy_query_item(&query, sizeof(query), len, query_item);
+	if (ret != 0)
+		return ret;
+
+	if (query.num_engines || query.rsvd[0] || query.rsvd[1] ||
+	    query.rsvd[2])
+		return -EINVAL;
+
+	info_ptr = &query_ptr->engines[0];
+
+	for_each_uabi_engine(engine, i915) {
+		info.engine.engine_class = engine->uabi_class;
+		info.engine.engine_instance = engine->uabi_instance;
+		info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE;
+		info.capabilities = engine->uabi_capabilities;
+		info.logical_instance = ilog2(engine->logical_mask);
+
+		if (copy_to_user(info_ptr, &info, sizeof(info)))
+			return -EFAULT;
+
+		query.num_engines++;
+		info_ptr++;
+	}
+
+	if (copy_to_user(query_ptr, &query, sizeof(query)))
+		return -EFAULT;
+
+	return len;
+}
+
+static int can_copy_perf_config_registers_or_number(u32 user_n_regs,
+						    u64 user_regs_ptr,
+						    u32 kernel_n_regs)
+{
+	/*
+	 * We'll just put the number of registers, and won't copy the
+	 * register.
+	 */
+	if (user_n_regs == 0)
+		return 0;
+
+	if (user_n_regs < kernel_n_regs)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int copy_perf_config_registers_or_number(const struct i915_oa_reg *kernel_regs,
+						u32 kernel_n_regs,
+						u64 user_regs_ptr,
+						u32 *user_n_regs)
+{
+	u32 __user *p = u64_to_user_ptr(user_regs_ptr);
+	u32 r;
+
+	if (*user_n_regs == 0) {
+		*user_n_regs = kernel_n_regs;
+		return 0;
+	}
+
+	*user_n_regs = kernel_n_regs;
+
+	if (!user_write_access_begin(p, 2 * sizeof(u32) * kernel_n_regs))
+		return -EFAULT;
+
+	for (r = 0; r < kernel_n_regs; r++, p += 2) {
+		unsafe_put_user(i915_mmio_reg_offset(kernel_regs[r].addr),
+				p, Efault);
+		unsafe_put_user(kernel_regs[r].value, p + 1, Efault);
+	}
+	user_write_access_end();
+	return 0;
+Efault:
+	user_write_access_end();
+	return -EFAULT;
+}
+
+static int query_perf_config_data(struct drm_i915_private *i915,
+				  struct drm_i915_query_item *query_item,
+				  bool use_uuid)
+{
+	struct drm_i915_query_perf_config __user *user_query_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct drm_i915_perf_oa_config __user *user_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr +
+				sizeof(struct drm_i915_query_perf_config));
+	struct drm_i915_perf_oa_config user_config;
+	struct i915_perf *perf = &i915->perf;
+	struct i915_oa_config *oa_config;
+	char uuid[UUID_STRING_LEN + 1];
+	u64 config_id;
+	u32 flags, total_size;
+	int ret;
+
+	if (!perf->i915)
+		return -ENODEV;
+
+	total_size =
+		sizeof(struct drm_i915_query_perf_config) +
+		sizeof(struct drm_i915_perf_oa_config);
+
+	if (query_item->length == 0)
+		return total_size;
+
+	if (query_item->length < total_size) {
+		drm_dbg(&i915->drm,
+			"Invalid query config data item size=%u expected=%u\n",
+			query_item->length, total_size);
+		return -EINVAL;
+	}
+
+	if (get_user(flags, &user_query_config_ptr->flags))
+		return -EFAULT;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	if (use_uuid) {
+		struct i915_oa_config *tmp;
+		int id;
+
+		BUILD_BUG_ON(sizeof(user_query_config_ptr->uuid) >= sizeof(uuid));
+
+		memset(&uuid, 0, sizeof(uuid));
+		if (copy_from_user(uuid, user_query_config_ptr->uuid,
+				     sizeof(user_query_config_ptr->uuid)))
+			return -EFAULT;
+
+		oa_config = NULL;
+		rcu_read_lock();
+		idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+			if (!strcmp(tmp->uuid, uuid)) {
+				oa_config = i915_oa_config_get(tmp);
+				break;
+			}
+		}
+		rcu_read_unlock();
+	} else {
+		if (get_user(config_id, &user_query_config_ptr->config))
+			return -EFAULT;
+
+		oa_config = i915_perf_get_oa_config(perf, config_id);
+	}
+	if (!oa_config)
+		return -ENOENT;
+
+	if (copy_from_user(&user_config, user_config_ptr, sizeof(user_config))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_boolean_regs,
+						       user_config.boolean_regs_ptr,
+						       oa_config->b_counter_regs_len);
+	if (ret)
+		goto out;
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_flex_regs,
+						       user_config.flex_regs_ptr,
+						       oa_config->flex_regs_len);
+	if (ret)
+		goto out;
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_mux_regs,
+						       user_config.mux_regs_ptr,
+						       oa_config->mux_regs_len);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->b_counter_regs,
+						   oa_config->b_counter_regs_len,
+						   user_config.boolean_regs_ptr,
+						   &user_config.n_boolean_regs);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->flex_regs,
+						   oa_config->flex_regs_len,
+						   user_config.flex_regs_ptr,
+						   &user_config.n_flex_regs);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->mux_regs,
+						   oa_config->mux_regs_len,
+						   user_config.mux_regs_ptr,
+						   &user_config.n_mux_regs);
+	if (ret)
+		goto out;
+
+	memcpy(user_config.uuid, oa_config->uuid, sizeof(user_config.uuid));
+
+	if (copy_to_user(user_config_ptr, &user_config, sizeof(user_config))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = total_size;
+
+out:
+	i915_oa_config_put(oa_config);
+	return ret;
+}
+
+static size_t sizeof_perf_config_list(size_t count)
+{
+	return sizeof(struct drm_i915_query_perf_config) + sizeof(u64) * count;
+}
+
+static size_t sizeof_perf_metrics(struct i915_perf *perf)
+{
+	struct i915_oa_config *tmp;
+	size_t i;
+	int id;
+
+	i = 1;
+	rcu_read_lock();
+	idr_for_each_entry(&perf->metrics_idr, tmp, id)
+		i++;
+	rcu_read_unlock();
+
+	return sizeof_perf_config_list(i);
+}
+
+static int query_perf_config_list(struct drm_i915_private *i915,
+				  struct drm_i915_query_item *query_item)
+{
+	struct drm_i915_query_perf_config __user *user_query_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct i915_perf *perf = &i915->perf;
+	u64 *oa_config_ids = NULL;
+	int alloc, n_configs;
+	u32 flags;
+	int ret;
+
+	if (!perf->i915)
+		return -ENODEV;
+
+	if (query_item->length == 0)
+		return sizeof_perf_metrics(perf);
+
+	if (get_user(flags, &user_query_config_ptr->flags))
+		return -EFAULT;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	n_configs = 1;
+	do {
+		struct i915_oa_config *tmp;
+		u64 *ids;
+		int id;
+
+		ids = krealloc(oa_config_ids,
+			       n_configs * sizeof(*oa_config_ids),
+			       GFP_KERNEL);
+		if (!ids)
+			return -ENOMEM;
+
+		alloc = fetch_and_zero(&n_configs);
+
+		ids[n_configs++] = 1ull; /* reserved for test_config */
+		rcu_read_lock();
+		idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+			if (n_configs < alloc)
+				ids[n_configs] = id;
+			n_configs++;
+		}
+		rcu_read_unlock();
+
+		oa_config_ids = ids;
+	} while (n_configs > alloc);
+
+	if (query_item->length < sizeof_perf_config_list(n_configs)) {
+		drm_dbg(&i915->drm,
+			"Invalid query config list item size=%u expected=%zu\n",
+			query_item->length,
+			sizeof_perf_config_list(n_configs));
+		kfree(oa_config_ids);
+		return -EINVAL;
+	}
+
+	if (put_user(n_configs, &user_query_config_ptr->config)) {
+		kfree(oa_config_ids);
+		return -EFAULT;
+	}
+
+	ret = copy_to_user(user_query_config_ptr + 1,
+			   oa_config_ids,
+			   n_configs * sizeof(*oa_config_ids));
+	kfree(oa_config_ids);
+	if (ret)
+		return -EFAULT;
+
+	return sizeof_perf_config_list(n_configs);
+}
+
+static int query_perf_config(struct drm_i915_private *i915,
+			     struct drm_i915_query_item *query_item)
+{
+	switch (query_item->flags) {
+	case DRM_I915_QUERY_PERF_CONFIG_LIST:
+		return query_perf_config_list(i915, query_item);
+	case DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID:
+		return query_perf_config_data(i915, query_item, true);
+	case DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID:
+		return query_perf_config_data(i915, query_item, false);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int query_memregion_info(struct drm_i915_private *i915,
+				struct drm_i915_query_item *query_item)
+{
+	struct drm_i915_query_memory_regions __user *query_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct drm_i915_memory_region_info __user *info_ptr =
+		&query_ptr->regions[0];
+	struct drm_i915_memory_region_info info = { };
+	struct drm_i915_query_memory_regions query;
+	struct intel_memory_region *mr;
+	u32 total_length;
+	int ret, id, i;
+
+	if (query_item->flags != 0)
+		return -EINVAL;
+
+	total_length = sizeof(query);
+	for_each_memory_region(mr, i915, id) {
+		if (mr->private)
+			continue;
+
+		total_length += sizeof(info);
+	}
+
+	ret = copy_query_item(&query, sizeof(query), total_length, query_item);
+	if (ret != 0)
+		return ret;
+
+	if (query.num_regions)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(query.rsvd); i++) {
+		if (query.rsvd[i])
+			return -EINVAL;
+	}
+
+	for_each_memory_region(mr, i915, id) {
+		if (mr->private)
+			continue;
+
+		info.region.memory_class = mr->type;
+		info.region.memory_instance = mr->instance;
+		info.probed_size = mr->total;
+
+		if (mr->type == INTEL_MEMORY_LOCAL)
+			info.probed_cpu_visible_size = mr->io_size;
+		else
+			info.probed_cpu_visible_size = mr->total;
+
+		if (perfmon_capable()) {
+			intel_memory_region_avail(mr,
+						  &info.unallocated_size,
+						  &info.unallocated_cpu_visible_size);
+		} else {
+			info.unallocated_size = info.probed_size;
+			info.unallocated_cpu_visible_size =
+				info.probed_cpu_visible_size;
+		}
+
+		if (__copy_to_user(info_ptr, &info, sizeof(info)))
+			return -EFAULT;
+
+		query.num_regions++;
+		info_ptr++;
+	}
+
+	if (__copy_to_user(query_ptr, &query, sizeof(query)))
+		return -EFAULT;
+
+	return total_length;
+}
+
+static int query_hwconfig_blob(struct drm_i915_private *i915,
+			       struct drm_i915_query_item *query_item)
+{
+	struct intel_gt *gt = to_gt(i915);
+	struct intel_hwconfig *hwconfig = &gt->info.hwconfig;
+
+	if (!hwconfig->size || !hwconfig->ptr)
+		return -ENODEV;
+
+	if (query_item->length == 0)
+		return hwconfig->size;
+
+	if (query_item->length < hwconfig->size)
+		return -EINVAL;
+
+	if (copy_to_user(u64_to_user_ptr(query_item->data_ptr),
+			 hwconfig->ptr, hwconfig->size))
+		return -EFAULT;
+
+	return hwconfig->size;
+}
+
+static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
+					struct drm_i915_query_item *query_item) = {
+	query_topology_info,
+	query_engine_info,
+	query_perf_config,
+	query_memregion_info,
+	query_hwconfig_blob,
+	query_geometry_subslices,
+};
+
+int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_query *args = data;
+	struct drm_i915_query_item __user *user_item_ptr =
+		u64_to_user_ptr(args->items_ptr);
+	u32 i;
+
+	if (args->flags != 0)
+		return -EINVAL;
+
+	for (i = 0; i < args->num_items; i++, user_item_ptr++) {
+		struct drm_i915_query_item item;
+		unsigned long func_idx;
+		int ret;
+
+		if (copy_from_user(&item, user_item_ptr, sizeof(item)))
+			return -EFAULT;
+
+		if (item.query_id == 0)
+			return -EINVAL;
+
+		if (overflows_type(item.query_id - 1, unsigned long))
+			return -EINVAL;
+
+		func_idx = item.query_id - 1;
+
+		ret = -EINVAL;
+		if (func_idx < ARRAY_SIZE(i915_query_funcs)) {
+			func_idx = array_index_nospec(func_idx,
+						      ARRAY_SIZE(i915_query_funcs));
+			ret = i915_query_funcs[func_idx](dev_priv, &item);
+		}
+
+		/* Only write the length back to userspace if they differ. */
+		if (ret != item.length && put_user(ret, &user_item_ptr->length))
+			return -EFAULT;
+	}
+
+	return 0;
+}