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, 481 insertions, 0 deletions

diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
new file mode 100644
index 000000000..3dfc0af87
--- /dev/null
+++ b/include/uapi/drm/v3d_drm.h
@@ -0,0 +1,481 @@
+/*
+ * Copyright © 2014-2018 Broadcom
+ *
+ * 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.
+ */
+
+#ifndef _V3D_DRM_H_
+#define _V3D_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_V3D_SUBMIT_CL                         0x00
+#define DRM_V3D_WAIT_BO                           0x01
+#define DRM_V3D_CREATE_BO                         0x02
+#define DRM_V3D_MMAP_BO                           0x03
+#define DRM_V3D_GET_PARAM                         0x04
+#define DRM_V3D_GET_BO_OFFSET                     0x05
+#define DRM_V3D_SUBMIT_TFU                        0x06
+#define DRM_V3D_SUBMIT_CSD                        0x07
+#define DRM_V3D_PERFMON_CREATE                    0x08
+#define DRM_V3D_PERFMON_DESTROY                   0x09
+#define DRM_V3D_PERFMON_GET_VALUES                0x0a
+
+#define DRM_IOCTL_V3D_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl)
+#define DRM_IOCTL_V3D_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo)
+#define DRM_IOCTL_V3D_CREATE_BO           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_CREATE_BO, struct drm_v3d_create_bo)
+#define DRM_IOCTL_V3D_MMAP_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_MMAP_BO, struct drm_v3d_mmap_bo)
+#define DRM_IOCTL_V3D_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_PARAM, struct drm_v3d_get_param)
+#define DRM_IOCTL_V3D_GET_BO_OFFSET       DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_BO_OFFSET, struct drm_v3d_get_bo_offset)
+#define DRM_IOCTL_V3D_SUBMIT_TFU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_TFU, struct drm_v3d_submit_tfu)
+#define DRM_IOCTL_V3D_SUBMIT_CSD          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CSD, struct drm_v3d_submit_csd)
+#define DRM_IOCTL_V3D_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_CREATE, \
+						   struct drm_v3d_perfmon_create)
+#define DRM_IOCTL_V3D_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_DESTROY, \
+						   struct drm_v3d_perfmon_destroy)
+#define DRM_IOCTL_V3D_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_VALUES, \
+						   struct drm_v3d_perfmon_get_values)
+
+#define DRM_V3D_SUBMIT_CL_FLUSH_CACHE             0x01
+#define DRM_V3D_SUBMIT_EXTENSION		  0x02
+
+/* struct drm_v3d_extension - ioctl extensions
+ *
+ * Linked-list of generic extensions where the id identify which struct is
+ * pointed by ext_data. Therefore, DRM_V3D_EXT_ID_* is used on id to identify
+ * the extension type.
+ */
+struct drm_v3d_extension {
+	__u64 next;
+	__u32 id;
+#define DRM_V3D_EXT_ID_MULTI_SYNC		0x01
+	__u32 flags; /* mbz */
+};
+
+/* struct drm_v3d_sem - wait/signal semaphore
+ *
+ * If binary semaphore, it only takes syncobj handle and ignores flags and
+ * point fields. Point is defined for timeline syncobj feature.
+ */
+struct drm_v3d_sem {
+	__u32 handle; /* syncobj */
+	/* rsv below, for future uses */
+	__u32 flags;
+	__u64 point;  /* for timeline sem support */
+	__u64 mbz[2]; /* must be zero, rsv */
+};
+
+/* Enum for each of the V3D queues. */
+enum v3d_queue {
+	V3D_BIN,
+	V3D_RENDER,
+	V3D_TFU,
+	V3D_CSD,
+	V3D_CACHE_CLEAN,
+};
+
+/**
+ * struct drm_v3d_multi_sync - ioctl extension to add support multiples
+ * syncobjs for commands submission.
+ *
+ * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to
+ * this extension to define wait and signal dependencies, instead of single
+ * in/out sync entries on submitting commands. The field flags is used to
+ * determine the stage to set wait dependencies.
+ */
+struct drm_v3d_multi_sync {
+	struct drm_v3d_extension base;
+	/* Array of wait and signal semaphores */
+	__u64 in_syncs;
+	__u64 out_syncs;
+
+	/* Number of entries */
+	__u32 in_sync_count;
+	__u32 out_sync_count;
+
+	/* set the stage (v3d_queue) to sync */
+	__u32 wait_stage;
+
+	__u32 pad; /* mbz */
+};
+
+/**
+ * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D
+ * engine.
+ *
+ * This asks the kernel to have the GPU execute an optional binner
+ * command list, and a render command list.
+ *
+ * The L1T, slice, L2C, L2T, and GCA caches will be flushed before
+ * each CL executes.  The VCD cache should be flushed (if necessary)
+ * by the submitted CLs.  The TLB writes are guaranteed to have been
+ * flushed by the time the render done IRQ happens, which is the
+ * trigger for out_sync.  Any dirtying of cachelines by the job (only
+ * possible using TMU writes) must be flushed by the caller using the
+ * DRM_V3D_SUBMIT_CL_FLUSH_CACHE_FLAG flag.
+ */
+struct drm_v3d_submit_cl {
+	/* Pointer to the binner command list.
+	 *
+	 * This is the first set of commands executed, which runs the
+	 * coordinate shader to determine where primitives land on the screen,
+	 * then writes out the state updates and draw calls necessary per tile
+	 * to the tile allocation BO.
+	 *
+	 * This BCL will block on any previous BCL submitted on the
+	 * same FD, but not on any RCL or BCLs submitted by other
+	 * clients -- that is left up to the submitter to control
+	 * using in_sync_bcl if necessary.
+	 */
+	__u32 bcl_start;
+
+	/** End address of the BCL (first byte after the BCL) */
+	__u32 bcl_end;
+
+	/* Offset of the render command list.
+	 *
+	 * This is the second set of commands executed, which will either
+	 * execute the tiles that have been set up by the BCL, or a fixed set
+	 * of tiles (in the case of RCL-only blits).
+	 *
+	 * This RCL will block on this submit's BCL, and any previous
+	 * RCL submitted on the same FD, but not on any RCL or BCLs
+	 * submitted by other clients -- that is left up to the
+	 * submitter to control using in_sync_rcl if necessary.
+	 */
+	__u32 rcl_start;
+
+	/** End address of the RCL (first byte after the RCL) */
+	__u32 rcl_end;
+
+	/** An optional sync object to wait on before starting the BCL. */
+	__u32 in_sync_bcl;
+	/** An optional sync object to wait on before starting the RCL. */
+	__u32 in_sync_rcl;
+	/** An optional sync object to place the completion fence in. */
+	__u32 out_sync;
+
+	/* Offset of the tile alloc memory
+	 *
+	 * This is optional on V3D 3.3 (where the CL can set the value) but
+	 * required on V3D 4.1.
+	 */
+	__u32 qma;
+
+	/** Size of the tile alloc memory. */
+	__u32 qms;
+
+	/** Offset of the tile state data array. */
+	__u32 qts;
+
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	/* DRM_V3D_SUBMIT_* properties */
+	__u32 flags;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+
+	__u32 pad;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+};
+
+/**
+ * struct drm_v3d_wait_bo - ioctl argument for waiting for
+ * completion of the last DRM_V3D_SUBMIT_CL on a BO.
+ *
+ * This is useful for cases where multiple processes might be
+ * rendering to a BO and you want to wait for all rendering to be
+ * completed.
+ */
+struct drm_v3d_wait_bo {
+	__u32 handle;
+	__u32 pad;
+	__u64 timeout_ns;
+};
+
+/**
+ * struct drm_v3d_create_bo - ioctl argument for creating V3D BOs.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_v3d_create_bo {
+	__u32 size;
+	__u32 flags;
+	/** Returned GEM handle for the BO. */
+	__u32 handle;
+	/**
+	 * Returned offset for the BO in the V3D address space.  This offset
+	 * is private to the DRM fd and is valid for the lifetime of the GEM
+	 * handle.
+	 *
+	 * This offset value will always be nonzero, since various HW
+	 * units treat 0 specially.
+	 */
+	__u32 offset;
+};
+
+/**
+ * struct drm_v3d_mmap_bo - ioctl argument for mapping V3D BOs.
+ *
+ * This doesn't actually perform an mmap.  Instead, it returns the
+ * offset you need to use in an mmap on the DRM device node.  This
+ * means that tools like valgrind end up knowing about the mapped
+ * memory.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_v3d_mmap_bo {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 flags;
+	/** offset into the drm node to use for subsequent mmap call. */
+	__u64 offset;
+};
+
+enum drm_v3d_param {
+	DRM_V3D_PARAM_V3D_UIFCFG,
+	DRM_V3D_PARAM_V3D_HUB_IDENT1,
+	DRM_V3D_PARAM_V3D_HUB_IDENT2,
+	DRM_V3D_PARAM_V3D_HUB_IDENT3,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT0,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT1,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT2,
+	DRM_V3D_PARAM_SUPPORTS_TFU,
+	DRM_V3D_PARAM_SUPPORTS_CSD,
+	DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH,
+	DRM_V3D_PARAM_SUPPORTS_PERFMON,
+	DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT,
+};
+
+struct drm_v3d_get_param {
+	__u32 param;
+	__u32 pad;
+	__u64 value;
+};
+
+/**
+ * Returns the offset for the BO in the V3D address space for this DRM fd.
+ * This is the same value returned by drm_v3d_create_bo, if that was called
+ * from this DRM fd.
+ */
+struct drm_v3d_get_bo_offset {
+	__u32 handle;
+	__u32 offset;
+};
+
+struct drm_v3d_submit_tfu {
+	__u32 icfg;
+	__u32 iia;
+	__u32 iis;
+	__u32 ica;
+	__u32 iua;
+	__u32 ioa;
+	__u32 ios;
+	__u32 coef[4];
+	/* First handle is the output BO, following are other inputs.
+	 * 0 for unused.
+	 */
+	__u32 bo_handles[4];
+	/* sync object to block on before running the TFU job.  Each TFU
+	 * job will execute in the order submitted to its FD.  Synchronization
+	 * against rendering jobs requires using sync objects.
+	 */
+	__u32 in_sync;
+	/* Sync object to signal when the TFU job is done. */
+	__u32 out_sync;
+
+	__u32 flags;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+};
+
+/* Submits a compute shader for dispatch.  This job will block on any
+ * previous compute shaders submitted on this fd, and any other
+ * synchronization must be performed with in_sync/out_sync.
+ */
+struct drm_v3d_submit_csd {
+	__u32 cfg[7];
+	__u32 coef[4];
+
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	/* sync object to block on before running the CSD job.  Each
+	 * CSD job will execute in the order submitted to its FD.
+	 * Synchronization against rendering/TFU jobs or CSD from
+	 * other fds requires using sync objects.
+	 */
+	__u32 in_sync;
+	/* Sync object to signal when the CSD job is done. */
+	__u32 out_sync;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+
+	__u32 flags;
+
+	__u32 pad;
+};
+
+enum {
+	V3D_PERFCNT_FEP_VALID_PRIMTS_NO_PIXELS,
+	V3D_PERFCNT_FEP_VALID_PRIMS,
+	V3D_PERFCNT_FEP_EZ_NFCLIP_QUADS,
+	V3D_PERFCNT_FEP_VALID_QUADS,
+	V3D_PERFCNT_TLB_QUADS_STENCIL_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_PASS,
+	V3D_PERFCNT_TLB_QUADS_ZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_NONZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_WRITTEN,
+	V3D_PERFCNT_PTB_PRIM_VIEWPOINT_DISCARD,
+	V3D_PERFCNT_PTB_PRIM_CLIP,
+	V3D_PERFCNT_PTB_PRIM_REV,
+	V3D_PERFCNT_QPU_IDLE_CYCLES,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_FRAG,
+	V3D_PERFCNT_QPU_CYCLES_VALID_INSTR,
+	V3D_PERFCNT_QPU_CYCLES_TMU_STALL,
+	V3D_PERFCNT_QPU_CYCLES_SCOREBOARD_STALL,
+	V3D_PERFCNT_QPU_CYCLES_VARYINGS_STALL,
+	V3D_PERFCNT_QPU_IC_HIT,
+	V3D_PERFCNT_QPU_IC_MISS,
+	V3D_PERFCNT_QPU_UC_HIT,
+	V3D_PERFCNT_QPU_UC_MISS,
+	V3D_PERFCNT_TMU_TCACHE_ACCESS,
+	V3D_PERFCNT_TMU_TCACHE_MISS,
+	V3D_PERFCNT_VPM_VDW_STALL,
+	V3D_PERFCNT_VPM_VCD_STALL,
+	V3D_PERFCNT_BIN_ACTIVE,
+	V3D_PERFCNT_RDR_ACTIVE,
+	V3D_PERFCNT_L2T_HITS,
+	V3D_PERFCNT_L2T_MISSES,
+	V3D_PERFCNT_CYCLE_COUNT,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_FRAGMENT,
+	V3D_PERFCNT_PTB_PRIMS_BINNED,
+	V3D_PERFCNT_AXI_WRITES_WATCH_0,
+	V3D_PERFCNT_AXI_READS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_WRITES_WATCH_1,
+	V3D_PERFCNT_AXI_READS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_1,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_1,
+	V3D_PERFCNT_TLB_PARTIAL_QUADS,
+	V3D_PERFCNT_TMU_CONFIG_ACCESSES,
+	V3D_PERFCNT_L2T_NO_ID_STALL,
+	V3D_PERFCNT_L2T_COM_QUE_STALL,
+	V3D_PERFCNT_L2T_TMU_WRITES,
+	V3D_PERFCNT_TMU_ACTIVE_CYCLES,
+	V3D_PERFCNT_TMU_STALLED_CYCLES,
+	V3D_PERFCNT_CLE_ACTIVE,
+	V3D_PERFCNT_L2T_TMU_READS,
+	V3D_PERFCNT_L2T_CLE_READS,
+	V3D_PERFCNT_L2T_VCD_READS,
+	V3D_PERFCNT_L2T_TMUCFG_READS,
+	V3D_PERFCNT_L2T_SLC0_READS,
+	V3D_PERFCNT_L2T_SLC1_READS,
+	V3D_PERFCNT_L2T_SLC2_READS,
+	V3D_PERFCNT_L2T_TMU_W_MISSES,
+	V3D_PERFCNT_L2T_TMU_R_MISSES,
+	V3D_PERFCNT_L2T_CLE_MISSES,
+	V3D_PERFCNT_L2T_VCD_MISSES,
+	V3D_PERFCNT_L2T_TMUCFG_MISSES,
+	V3D_PERFCNT_L2T_SLC0_MISSES,
+	V3D_PERFCNT_L2T_SLC1_MISSES,
+	V3D_PERFCNT_L2T_SLC2_MISSES,
+	V3D_PERFCNT_CORE_MEM_WRITES,
+	V3D_PERFCNT_L2T_MEM_WRITES,
+	V3D_PERFCNT_PTB_MEM_WRITES,
+	V3D_PERFCNT_TLB_MEM_WRITES,
+	V3D_PERFCNT_CORE_MEM_READS,
+	V3D_PERFCNT_L2T_MEM_READS,
+	V3D_PERFCNT_PTB_MEM_READS,
+	V3D_PERFCNT_PSE_MEM_READS,
+	V3D_PERFCNT_TLB_MEM_READS,
+	V3D_PERFCNT_GMP_MEM_READS,
+	V3D_PERFCNT_PTB_W_MEM_WORDS,
+	V3D_PERFCNT_TLB_W_MEM_WORDS,
+	V3D_PERFCNT_PSE_R_MEM_WORDS,
+	V3D_PERFCNT_TLB_R_MEM_WORDS,
+	V3D_PERFCNT_TMU_MRU_HITS,
+	V3D_PERFCNT_COMPUTE_ACTIVE,
+	V3D_PERFCNT_NUM,
+};
+
+#define DRM_V3D_MAX_PERF_COUNTERS                 32
+
+struct drm_v3d_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u8 counters[DRM_V3D_MAX_PERF_COUNTERS];
+};
+
+struct drm_v3d_perfmon_destroy {
+	__u32 id;
+};
+
+/*
+ * Returns the values of the performance counters tracked by this
+ * perfmon (as an array of ncounters u64 values).
+ *
+ * No implicit synchronization is performed, so the user has to
+ * guarantee that any jobs using this perfmon have already been
+ * completed  (probably by blocking on the seqno returned by the
+ * last exec that used the perfmon).
+ */
+struct drm_v3d_perfmon_get_values {
+	__u32 id;
+	__u32 pad;
+	__u64 values_ptr;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _V3D_DRM_H_ */