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, 563 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
new file mode 100644
index 000000000..677ad2016
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -0,0 +1,563 @@
+/*
+ * Copyright 2017 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.
+ *
+ */
+
+#if !defined(_AMDGPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _AMDGPU_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM amdgpu
+#define TRACE_INCLUDE_FILE amdgpu_trace
+
+#define AMDGPU_JOB_GET_TIMELINE_NAME(job) \
+	 job->base.s_fence->finished.ops->get_timeline_name(&job->base.s_fence->finished)
+
+TRACE_EVENT(amdgpu_device_rreg,
+	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
+	    TP_ARGS(did, reg, value),
+	    TP_STRUCT__entry(
+				__field(unsigned, did)
+				__field(uint32_t, reg)
+				__field(uint32_t, value)
+			    ),
+	    TP_fast_assign(
+			   __entry->did = did;
+			   __entry->reg = reg;
+			   __entry->value = value;
+			   ),
+	    TP_printk("0x%04lx, 0x%08lx, 0x%08lx",
+		      (unsigned long)__entry->did,
+		      (unsigned long)__entry->reg,
+		      (unsigned long)__entry->value)
+);
+
+TRACE_EVENT(amdgpu_device_wreg,
+	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
+	    TP_ARGS(did, reg, value),
+	    TP_STRUCT__entry(
+				__field(unsigned, did)
+				__field(uint32_t, reg)
+				__field(uint32_t, value)
+			    ),
+	    TP_fast_assign(
+			   __entry->did = did;
+			   __entry->reg = reg;
+			   __entry->value = value;
+			   ),
+	    TP_printk("0x%04lx, 0x%08lx, 0x%08lx",
+		      (unsigned long)__entry->did,
+		      (unsigned long)__entry->reg,
+		      (unsigned long)__entry->value)
+);
+
+TRACE_EVENT(amdgpu_iv,
+	    TP_PROTO(unsigned ih, struct amdgpu_iv_entry *iv),
+	    TP_ARGS(ih, iv),
+	    TP_STRUCT__entry(
+			     __field(unsigned, ih)
+			     __field(unsigned, client_id)
+			     __field(unsigned, src_id)
+			     __field(unsigned, ring_id)
+			     __field(unsigned, vmid)
+			     __field(unsigned, vmid_src)
+			     __field(uint64_t, timestamp)
+			     __field(unsigned, timestamp_src)
+			     __field(unsigned, pasid)
+			     __array(unsigned, src_data, 4)
+			    ),
+	    TP_fast_assign(
+			   __entry->ih = ih;
+			   __entry->client_id = iv->client_id;
+			   __entry->src_id = iv->src_id;
+			   __entry->ring_id = iv->ring_id;
+			   __entry->vmid = iv->vmid;
+			   __entry->vmid_src = iv->vmid_src;
+			   __entry->timestamp = iv->timestamp;
+			   __entry->timestamp_src = iv->timestamp_src;
+			   __entry->pasid = iv->pasid;
+			   __entry->src_data[0] = iv->src_data[0];
+			   __entry->src_data[1] = iv->src_data[1];
+			   __entry->src_data[2] = iv->src_data[2];
+			   __entry->src_data[3] = iv->src_data[3];
+			   ),
+	    TP_printk("ih:%u client_id:%u src_id:%u ring:%u vmid:%u "
+		      "timestamp: %llu pasid:%u src_data: %08x %08x %08x %08x",
+		      __entry->ih, __entry->client_id, __entry->src_id,
+		      __entry->ring_id, __entry->vmid,
+		      __entry->timestamp, __entry->pasid,
+		      __entry->src_data[0], __entry->src_data[1],
+		      __entry->src_data[2], __entry->src_data[3])
+);
+
+
+TRACE_EVENT(amdgpu_bo_create,
+	    TP_PROTO(struct amdgpu_bo *bo),
+	    TP_ARGS(bo),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo *, bo)
+			     __field(u32, pages)
+			     __field(u32, type)
+			     __field(u32, prefer)
+			     __field(u32, allow)
+			     __field(u32, visible)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->bo = bo;
+			   __entry->pages = PFN_UP(bo->tbo.resource->size);
+			   __entry->type = bo->tbo.resource->mem_type;
+			   __entry->prefer = bo->preferred_domains;
+			   __entry->allow = bo->allowed_domains;
+			   __entry->visible = bo->flags;
+			   ),
+
+	    TP_printk("bo=%p, pages=%u, type=%d, preferred=%d, allowed=%d, visible=%d",
+		       __entry->bo, __entry->pages, __entry->type,
+		       __entry->prefer, __entry->allow, __entry->visible)
+);
+
+TRACE_EVENT(amdgpu_cs,
+	    TP_PROTO(struct amdgpu_cs_parser *p,
+		     struct amdgpu_job *job,
+		     struct amdgpu_ib *ib),
+	    TP_ARGS(p, job, ib),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo_list *, bo_list)
+			     __field(u32, ring)
+			     __field(u32, dw)
+			     __field(u32, fences)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->bo_list = p->bo_list;
+			   __entry->ring = to_amdgpu_ring(job->base.sched)->idx;
+			   __entry->dw = ib->length_dw;
+			   __entry->fences = amdgpu_fence_count_emitted(
+				to_amdgpu_ring(job->base.sched));
+			   ),
+	    TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u",
+		      __entry->bo_list, __entry->ring, __entry->dw,
+		      __entry->fences)
+);
+
+TRACE_EVENT(amdgpu_cs_ioctl,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(uint64_t, sched_job_id)
+			     __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			     __field(unsigned int, context)
+			     __field(unsigned int, seqno)
+			     __field(struct dma_fence *, fence)
+			     __string(ring, to_amdgpu_ring(job->base.sched)->name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->sched_job_id = job->base.id;
+			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job));
+			   __entry->context = job->base.s_fence->finished.context;
+			   __entry->seqno = job->base.s_fence->finished.seqno;
+			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name);
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
+		      __entry->sched_job_id, __get_str(timeline), __entry->context,
+		      __entry->seqno, __get_str(ring), __entry->num_ibs)
+);
+
+TRACE_EVENT(amdgpu_sched_run_job,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(uint64_t, sched_job_id)
+			     __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			     __field(unsigned int, context)
+			     __field(unsigned int, seqno)
+			     __string(ring, to_amdgpu_ring(job->base.sched)->name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->sched_job_id = job->base.id;
+			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job));
+			   __entry->context = job->base.s_fence->finished.context;
+			   __entry->seqno = job->base.s_fence->finished.seqno;
+			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name);
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
+		      __entry->sched_job_id, __get_str(timeline), __entry->context,
+		      __entry->seqno, __get_str(ring), __entry->num_ibs)
+);
+
+
+TRACE_EVENT(amdgpu_vm_grab_id,
+	    TP_PROTO(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+		     struct amdgpu_job *job),
+	    TP_ARGS(vm, ring, job),
+	    TP_STRUCT__entry(
+			     __field(u32, pasid)
+			     __string(ring, ring->name)
+			     __field(u32, ring)
+			     __field(u32, vmid)
+			     __field(u32, vm_hub)
+			     __field(u64, pd_addr)
+			     __field(u32, needs_flush)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pasid = vm->pasid;
+			   __assign_str(ring, ring->name);
+			   __entry->vmid = job->vmid;
+			   __entry->vm_hub = ring->funcs->vmhub,
+			   __entry->pd_addr = job->vm_pd_addr;
+			   __entry->needs_flush = job->vm_needs_flush;
+			   ),
+	    TP_printk("pasid=%d, ring=%s, id=%u, hub=%u, pd_addr=%010Lx needs_flush=%u",
+		      __entry->pasid, __get_str(ring), __entry->vmid,
+		      __entry->vm_hub, __entry->pd_addr, __entry->needs_flush)
+);
+
+TRACE_EVENT(amdgpu_vm_bo_map,
+	    TP_PROTO(struct amdgpu_bo_va *bo_va,
+		     struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(bo_va, mapping),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo *, bo)
+			     __field(long, start)
+			     __field(long, last)
+			     __field(u64, offset)
+			     __field(u64, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->bo = bo_va ? bo_va->base.bo : NULL;
+			   __entry->start = mapping->start;
+			   __entry->last = mapping->last;
+			   __entry->offset = mapping->offset;
+			   __entry->flags = mapping->flags;
+			   ),
+	    TP_printk("bo=%p, start=%lx, last=%lx, offset=%010llx, flags=%llx",
+		      __entry->bo, __entry->start, __entry->last,
+		      __entry->offset, __entry->flags)
+);
+
+TRACE_EVENT(amdgpu_vm_bo_unmap,
+	    TP_PROTO(struct amdgpu_bo_va *bo_va,
+		     struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(bo_va, mapping),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo *, bo)
+			     __field(long, start)
+			     __field(long, last)
+			     __field(u64, offset)
+			     __field(u64, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->bo = bo_va ? bo_va->base.bo : NULL;
+			   __entry->start = mapping->start;
+			   __entry->last = mapping->last;
+			   __entry->offset = mapping->offset;
+			   __entry->flags = mapping->flags;
+			   ),
+	    TP_printk("bo=%p, start=%lx, last=%lx, offset=%010llx, flags=%llx",
+		      __entry->bo, __entry->start, __entry->last,
+		      __entry->offset, __entry->flags)
+);
+
+DECLARE_EVENT_CLASS(amdgpu_vm_mapping,
+	    TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(mapping),
+	    TP_STRUCT__entry(
+			     __field(u64, soffset)
+			     __field(u64, eoffset)
+			     __field(u64, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->soffset = mapping->start;
+			   __entry->eoffset = mapping->last + 1;
+			   __entry->flags = mapping->flags;
+			   ),
+	    TP_printk("soffs=%010llx, eoffs=%010llx, flags=%llx",
+		      __entry->soffset, __entry->eoffset, __entry->flags)
+);
+
+DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_update,
+	    TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(mapping)
+);
+
+DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_mapping,
+	    TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(mapping)
+);
+
+DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_cs,
+	    TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(mapping)
+);
+
+TRACE_EVENT(amdgpu_vm_update_ptes,
+	    TP_PROTO(struct amdgpu_vm_update_params *p,
+		     uint64_t start, uint64_t end,
+		     unsigned int nptes, uint64_t dst,
+		     uint64_t incr, uint64_t flags,
+		     pid_t pid, uint64_t vm_ctx),
+	TP_ARGS(p, start, end, nptes, dst, incr, flags, pid, vm_ctx),
+	TP_STRUCT__entry(
+			 __field(u64, start)
+			 __field(u64, end)
+			 __field(u64, flags)
+			 __field(unsigned int, nptes)
+			 __field(u64, incr)
+			 __field(pid_t, pid)
+			 __field(u64, vm_ctx)
+			 __dynamic_array(u64, dst, nptes)
+	),
+
+	TP_fast_assign(
+			unsigned int i;
+
+			__entry->start = start;
+			__entry->end = end;
+			__entry->flags = flags;
+			__entry->incr = incr;
+			__entry->nptes = nptes;
+			__entry->pid = pid;
+			__entry->vm_ctx = vm_ctx;
+			for (i = 0; i < nptes; ++i) {
+				u64 addr = p->pages_addr ? amdgpu_vm_map_gart(
+					p->pages_addr, dst) : dst;
+
+				((u64 *)__get_dynamic_array(dst))[i] = addr;
+				dst += incr;
+			}
+	),
+	TP_printk("pid:%u vm_ctx:0x%llx start:0x%010llx end:0x%010llx,"
+		  " flags:0x%llx, incr:%llu, dst:\n%s", __entry->pid,
+		  __entry->vm_ctx, __entry->start, __entry->end,
+		  __entry->flags, __entry->incr,  __print_array(
+		  __get_dynamic_array(dst), __entry->nptes, 8))
+);
+
+TRACE_EVENT(amdgpu_vm_set_ptes,
+	    TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
+		     uint32_t incr, uint64_t flags, bool immediate),
+	    TP_ARGS(pe, addr, count, incr, flags, immediate),
+	    TP_STRUCT__entry(
+			     __field(u64, pe)
+			     __field(u64, addr)
+			     __field(u32, count)
+			     __field(u32, incr)
+			     __field(u64, flags)
+			     __field(bool, immediate)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pe = pe;
+			   __entry->addr = addr;
+			   __entry->count = count;
+			   __entry->incr = incr;
+			   __entry->flags = flags;
+			   __entry->immediate = immediate;
+			   ),
+	    TP_printk("pe=%010Lx, addr=%010Lx, incr=%u, flags=%llx, count=%u, "
+		      "immediate=%d", __entry->pe, __entry->addr, __entry->incr,
+		      __entry->flags, __entry->count, __entry->immediate)
+);
+
+TRACE_EVENT(amdgpu_vm_copy_ptes,
+	    TP_PROTO(uint64_t pe, uint64_t src, unsigned count, bool immediate),
+	    TP_ARGS(pe, src, count, immediate),
+	    TP_STRUCT__entry(
+			     __field(u64, pe)
+			     __field(u64, src)
+			     __field(u32, count)
+			     __field(bool, immediate)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pe = pe;
+			   __entry->src = src;
+			   __entry->count = count;
+			   __entry->immediate = immediate;
+			   ),
+	    TP_printk("pe=%010Lx, src=%010Lx, count=%u, immediate=%d",
+		      __entry->pe, __entry->src, __entry->count,
+		      __entry->immediate)
+);
+
+TRACE_EVENT(amdgpu_vm_flush,
+	    TP_PROTO(struct amdgpu_ring *ring, unsigned vmid,
+		     uint64_t pd_addr),
+	    TP_ARGS(ring, vmid, pd_addr),
+	    TP_STRUCT__entry(
+			     __string(ring, ring->name)
+			     __field(u32, vmid)
+			     __field(u32, vm_hub)
+			     __field(u64, pd_addr)
+			     ),
+
+	    TP_fast_assign(
+			   __assign_str(ring, ring->name);
+			   __entry->vmid = vmid;
+			   __entry->vm_hub = ring->funcs->vmhub;
+			   __entry->pd_addr = pd_addr;
+			   ),
+	    TP_printk("ring=%s, id=%u, hub=%u, pd_addr=%010Lx",
+		      __get_str(ring), __entry->vmid,
+		      __entry->vm_hub,__entry->pd_addr)
+);
+
+DECLARE_EVENT_CLASS(amdgpu_pasid,
+	    TP_PROTO(unsigned pasid),
+	    TP_ARGS(pasid),
+	    TP_STRUCT__entry(
+			     __field(unsigned, pasid)
+			     ),
+	    TP_fast_assign(
+			   __entry->pasid = pasid;
+			   ),
+	    TP_printk("pasid=%u", __entry->pasid)
+);
+
+DEFINE_EVENT(amdgpu_pasid, amdgpu_pasid_allocated,
+	    TP_PROTO(unsigned pasid),
+	    TP_ARGS(pasid)
+);
+
+DEFINE_EVENT(amdgpu_pasid, amdgpu_pasid_freed,
+	    TP_PROTO(unsigned pasid),
+	    TP_ARGS(pasid)
+);
+
+TRACE_EVENT(amdgpu_bo_list_set,
+	    TP_PROTO(struct amdgpu_bo_list *list, struct amdgpu_bo *bo),
+	    TP_ARGS(list, bo),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_bo_list *, list)
+			     __field(struct amdgpu_bo *, bo)
+			     __field(u64, bo_size)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->list = list;
+			   __entry->bo = bo;
+			   __entry->bo_size = amdgpu_bo_size(bo);
+			   ),
+	    TP_printk("list=%p, bo=%p, bo_size=%Ld",
+		      __entry->list,
+		      __entry->bo,
+		      __entry->bo_size)
+);
+
+TRACE_EVENT(amdgpu_cs_bo_status,
+	    TP_PROTO(uint64_t total_bo, uint64_t total_size),
+	    TP_ARGS(total_bo, total_size),
+	    TP_STRUCT__entry(
+			__field(u64, total_bo)
+			__field(u64, total_size)
+			),
+
+	    TP_fast_assign(
+			__entry->total_bo = total_bo;
+			__entry->total_size = total_size;
+			),
+	    TP_printk("total_bo_size=%Ld, total_bo_count=%Ld",
+			__entry->total_bo, __entry->total_size)
+);
+
+TRACE_EVENT(amdgpu_bo_move,
+	    TP_PROTO(struct amdgpu_bo* bo, uint32_t new_placement, uint32_t old_placement),
+	    TP_ARGS(bo, new_placement, old_placement),
+	    TP_STRUCT__entry(
+			__field(struct amdgpu_bo *, bo)
+			__field(u64, bo_size)
+			__field(u32, new_placement)
+			__field(u32, old_placement)
+			),
+
+	    TP_fast_assign(
+			__entry->bo      = bo;
+			__entry->bo_size = amdgpu_bo_size(bo);
+			__entry->new_placement = new_placement;
+			__entry->old_placement = old_placement;
+			),
+	    TP_printk("bo=%p, from=%d, to=%d, size=%Ld",
+			__entry->bo, __entry->old_placement,
+			__entry->new_placement, __entry->bo_size)
+);
+
+TRACE_EVENT(amdgpu_ib_pipe_sync,
+	    TP_PROTO(struct amdgpu_job *sched_job, struct dma_fence *fence),
+	    TP_ARGS(sched_job, fence),
+	    TP_STRUCT__entry(
+			     __string(ring, sched_job->base.sched->name)
+			     __field(uint64_t, id)
+			     __field(struct dma_fence *, fence)
+			     __field(uint64_t, ctx)
+			     __field(unsigned, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __assign_str(ring, sched_job->base.sched->name);
+			   __entry->id = sched_job->base.id;
+			   __entry->fence = fence;
+			   __entry->ctx = fence->context;
+			   __entry->seqno = fence->seqno;
+			   ),
+	    TP_printk("job ring=%s, id=%llu, need pipe sync to fence=%p, context=%llu, seq=%u",
+		      __get_str(ring), __entry->id,
+		      __entry->fence, __entry->ctx,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(amdgpu_reset_reg_dumps,
+	    TP_PROTO(uint32_t address, uint32_t value),
+	    TP_ARGS(address, value),
+	    TP_STRUCT__entry(
+			     __field(uint32_t, address)
+			     __field(uint32_t, value)
+			     ),
+	    TP_fast_assign(
+			   __entry->address = address;
+			   __entry->value = value;
+			   ),
+	    TP_printk("amdgpu register dump 0x%x: 0x%x",
+		      __entry->address,
+		      __entry->value)
+);
+
+#undef AMDGPU_JOB_GET_TIMELINE_NAME
+#endif
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/amd/amdgpu
+#include <trace/define_trace.h>