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, 468 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
new file mode 100644
index 000000000..bcccc348d
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -0,0 +1,468 @@
+/*
+ * Copyright 2008 Advanced Micro Devices, Inc.
+ * Copyright 2008 Red Hat Inc.
+ * Copyright 2009 Jerome Glisse.
+ *
+ * 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.
+ *
+ * Authors: Dave Airlie
+ *          Alex Deucher
+ *          Jerome Glisse
+ *          Christian König
+ */
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+
+#include <drm/amdgpu_drm.h>
+
+#include "amdgpu.h"
+#include "atom.h"
+#include "amdgpu_trace.h"
+
+#define AMDGPU_IB_TEST_TIMEOUT	msecs_to_jiffies(1000)
+#define AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT	msecs_to_jiffies(2000)
+
+/*
+ * IB
+ * IBs (Indirect Buffers) and areas of GPU accessible memory where
+ * commands are stored.  You can put a pointer to the IB in the
+ * command ring and the hw will fetch the commands from the IB
+ * and execute them.  Generally userspace acceleration drivers
+ * produce command buffers which are send to the kernel and
+ * put in IBs for execution by the requested ring.
+ */
+
+/**
+ * amdgpu_ib_get - request an IB (Indirect Buffer)
+ *
+ * @adev: amdgpu_device pointer
+ * @vm: amdgpu_vm pointer
+ * @size: requested IB size
+ * @pool_type: IB pool type (delayed, immediate, direct)
+ * @ib: IB object returned
+ *
+ * Request an IB (all asics).  IBs are allocated using the
+ * suballocator.
+ * Returns 0 on success, error on failure.
+ */
+int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+		  unsigned size, enum amdgpu_ib_pool_type pool_type,
+		  struct amdgpu_ib *ib)
+{
+	int r;
+
+	if (size) {
+		r = amdgpu_sa_bo_new(&adev->ib_pools[pool_type],
+				      &ib->sa_bo, size, 256);
+		if (r) {
+			dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
+			return r;
+		}
+
+		ib->ptr = amdgpu_sa_bo_cpu_addr(ib->sa_bo);
+		/* flush the cache before commit the IB */
+		ib->flags = AMDGPU_IB_FLAG_EMIT_MEM_SYNC;
+
+		if (!vm)
+			ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
+	}
+
+	return 0;
+}
+
+/**
+ * amdgpu_ib_free - free an IB (Indirect Buffer)
+ *
+ * @adev: amdgpu_device pointer
+ * @ib: IB object to free
+ * @f: the fence SA bo need wait on for the ib alloation
+ *
+ * Free an IB (all asics).
+ */
+void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
+		    struct dma_fence *f)
+{
+	amdgpu_sa_bo_free(adev, &ib->sa_bo, f);
+}
+
+/**
+ * amdgpu_ib_schedule - schedule an IB (Indirect Buffer) on the ring
+ *
+ * @ring: ring index the IB is associated with
+ * @num_ibs: number of IBs to schedule
+ * @ibs: IB objects to schedule
+ * @job: job to schedule
+ * @f: fence created during this submission
+ *
+ * Schedule an IB on the associated ring (all asics).
+ * Returns 0 on success, error on failure.
+ *
+ * On SI, there are two parallel engines fed from the primary ring,
+ * the CE (Constant Engine) and the DE (Drawing Engine).  Since
+ * resource descriptors have moved to memory, the CE allows you to
+ * prime the caches while the DE is updating register state so that
+ * the resource descriptors will be already in cache when the draw is
+ * processed.  To accomplish this, the userspace driver submits two
+ * IBs, one for the CE and one for the DE.  If there is a CE IB (called
+ * a CONST_IB), it will be put on the ring prior to the DE IB.  Prior
+ * to SI there was just a DE IB.
+ */
+int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
+		       struct amdgpu_ib *ibs, struct amdgpu_job *job,
+		       struct dma_fence **f)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_ib *ib = &ibs[0];
+	struct dma_fence *tmp = NULL;
+	bool need_ctx_switch;
+	unsigned patch_offset = ~0;
+	struct amdgpu_vm *vm;
+	uint64_t fence_ctx;
+	uint32_t status = 0, alloc_size;
+	unsigned fence_flags = 0;
+	bool secure;
+
+	unsigned i;
+	int r = 0;
+	bool need_pipe_sync = false;
+
+	if (num_ibs == 0)
+		return -EINVAL;
+
+	/* ring tests don't use a job */
+	if (job) {
+		vm = job->vm;
+		fence_ctx = job->base.s_fence ?
+			job->base.s_fence->scheduled.context : 0;
+	} else {
+		vm = NULL;
+		fence_ctx = 0;
+	}
+
+	if (!ring->sched.ready && !ring->is_mes_queue) {
+		dev_err(adev->dev, "couldn't schedule ib on ring <%s>\n", ring->name);
+		return -EINVAL;
+	}
+
+	if (vm && !job->vmid && !ring->is_mes_queue) {
+		dev_err(adev->dev, "VM IB without ID\n");
+		return -EINVAL;
+	}
+
+	if ((ib->flags & AMDGPU_IB_FLAGS_SECURE) &&
+	    (!ring->funcs->secure_submission_supported)) {
+		dev_err(adev->dev, "secure submissions not supported on ring <%s>\n", ring->name);
+		return -EINVAL;
+	}
+
+	alloc_size = ring->funcs->emit_frame_size + num_ibs *
+		ring->funcs->emit_ib_size;
+
+	r = amdgpu_ring_alloc(ring, alloc_size);
+	if (r) {
+		dev_err(adev->dev, "scheduling IB failed (%d).\n", r);
+		return r;
+	}
+
+	need_ctx_switch = ring->current_ctx != fence_ctx;
+	if (ring->funcs->emit_pipeline_sync && job &&
+	    ((tmp = amdgpu_sync_get_fence(&job->explicit_sync)) ||
+	     (amdgpu_sriov_vf(adev) && need_ctx_switch) ||
+	     amdgpu_vm_need_pipeline_sync(ring, job))) {
+		need_pipe_sync = true;
+
+		if (tmp)
+			trace_amdgpu_ib_pipe_sync(job, tmp);
+
+		dma_fence_put(tmp);
+	}
+
+	if ((ib->flags & AMDGPU_IB_FLAG_EMIT_MEM_SYNC) && ring->funcs->emit_mem_sync)
+		ring->funcs->emit_mem_sync(ring);
+
+	if (ring->funcs->emit_wave_limit &&
+	    ring->hw_prio == AMDGPU_GFX_PIPE_PRIO_HIGH)
+		ring->funcs->emit_wave_limit(ring, true);
+
+	if (ring->funcs->insert_start)
+		ring->funcs->insert_start(ring);
+
+	if (job) {
+		r = amdgpu_vm_flush(ring, job, need_pipe_sync);
+		if (r) {
+			amdgpu_ring_undo(ring);
+			return r;
+		}
+	}
+
+	amdgpu_ring_ib_begin(ring);
+	if (job && ring->funcs->init_cond_exec)
+		patch_offset = amdgpu_ring_init_cond_exec(ring);
+
+	amdgpu_device_flush_hdp(adev, ring);
+
+	if (need_ctx_switch)
+		status |= AMDGPU_HAVE_CTX_SWITCH;
+
+	if (job && ring->funcs->emit_cntxcntl) {
+		status |= job->preamble_status;
+		status |= job->preemption_status;
+		amdgpu_ring_emit_cntxcntl(ring, status);
+	}
+
+	/* Setup initial TMZiness and send it off.
+	 */
+	secure = false;
+	if (job && ring->funcs->emit_frame_cntl) {
+		secure = ib->flags & AMDGPU_IB_FLAGS_SECURE;
+		amdgpu_ring_emit_frame_cntl(ring, true, secure);
+	}
+
+	for (i = 0; i < num_ibs; ++i) {
+		ib = &ibs[i];
+
+		if (job && ring->funcs->emit_frame_cntl) {
+			if (secure != !!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) {
+				amdgpu_ring_emit_frame_cntl(ring, false, secure);
+				secure = !secure;
+				amdgpu_ring_emit_frame_cntl(ring, true, secure);
+			}
+		}
+
+		amdgpu_ring_emit_ib(ring, job, ib, status);
+		status &= ~AMDGPU_HAVE_CTX_SWITCH;
+	}
+
+	if (job && ring->funcs->emit_frame_cntl)
+		amdgpu_ring_emit_frame_cntl(ring, false, secure);
+
+	amdgpu_device_invalidate_hdp(adev, ring);
+
+	if (ib->flags & AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE)
+		fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
+
+	/* wrap the last IB with fence */
+	if (job && job->uf_addr) {
+		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
+				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
+	}
+
+	r = amdgpu_fence_emit(ring, f, job, fence_flags);
+	if (r) {
+		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
+		if (job && job->vmid)
+			amdgpu_vmid_reset(adev, ring->funcs->vmhub, job->vmid);
+		amdgpu_ring_undo(ring);
+		return r;
+	}
+
+	if (ring->funcs->insert_end)
+		ring->funcs->insert_end(ring);
+
+	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
+		amdgpu_ring_patch_cond_exec(ring, patch_offset);
+
+	ring->current_ctx = fence_ctx;
+	if (vm && ring->funcs->emit_switch_buffer)
+		amdgpu_ring_emit_switch_buffer(ring);
+
+	if (ring->funcs->emit_wave_limit &&
+	    ring->hw_prio == AMDGPU_GFX_PIPE_PRIO_HIGH)
+		ring->funcs->emit_wave_limit(ring, false);
+
+	amdgpu_ring_ib_end(ring);
+	amdgpu_ring_commit(ring);
+	return 0;
+}
+
+/**
+ * amdgpu_ib_pool_init - Init the IB (Indirect Buffer) pool
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Initialize the suballocator to manage a pool of memory
+ * for use as IBs (all asics).
+ * Returns 0 on success, error on failure.
+ */
+int amdgpu_ib_pool_init(struct amdgpu_device *adev)
+{
+	int r, i;
+
+	if (adev->ib_pool_ready)
+		return 0;
+
+	for (i = 0; i < AMDGPU_IB_POOL_MAX; i++) {
+		r = amdgpu_sa_bo_manager_init(adev, &adev->ib_pools[i],
+					      AMDGPU_IB_POOL_SIZE,
+					      AMDGPU_GPU_PAGE_SIZE,
+					      AMDGPU_GEM_DOMAIN_GTT);
+		if (r)
+			goto error;
+	}
+	adev->ib_pool_ready = true;
+
+	return 0;
+
+error:
+	while (i--)
+		amdgpu_sa_bo_manager_fini(adev, &adev->ib_pools[i]);
+	return r;
+}
+
+/**
+ * amdgpu_ib_pool_fini - Free the IB (Indirect Buffer) pool
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Tear down the suballocator managing the pool of memory
+ * for use as IBs (all asics).
+ */
+void amdgpu_ib_pool_fini(struct amdgpu_device *adev)
+{
+	int i;
+
+	if (!adev->ib_pool_ready)
+		return;
+
+	for (i = 0; i < AMDGPU_IB_POOL_MAX; i++)
+		amdgpu_sa_bo_manager_fini(adev, &adev->ib_pools[i]);
+	adev->ib_pool_ready = false;
+}
+
+/**
+ * amdgpu_ib_ring_tests - test IBs on the rings
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Test an IB (Indirect Buffer) on each ring.
+ * If the test fails, disable the ring.
+ * Returns 0 on success, error if the primary GFX ring
+ * IB test fails.
+ */
+int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
+{
+	long tmo_gfx, tmo_mm;
+	int r, ret = 0;
+	unsigned i;
+
+	tmo_mm = tmo_gfx = AMDGPU_IB_TEST_TIMEOUT;
+	if (amdgpu_sriov_vf(adev)) {
+		/* for MM engines in hypervisor side they are not scheduled together
+		 * with CP and SDMA engines, so even in exclusive mode MM engine could
+		 * still running on other VF thus the IB TEST TIMEOUT for MM engines
+		 * under SR-IOV should be set to a long time. 8 sec should be enough
+		 * for the MM comes back to this VF.
+		 */
+		tmo_mm = 8 * AMDGPU_IB_TEST_TIMEOUT;
+	}
+
+	if (amdgpu_sriov_runtime(adev)) {
+		/* for CP & SDMA engines since they are scheduled together so
+		 * need to make the timeout width enough to cover the time
+		 * cost waiting for it coming back under RUNTIME only
+		*/
+		tmo_gfx = 8 * AMDGPU_IB_TEST_TIMEOUT;
+	} else if (adev->gmc.xgmi.hive_id) {
+		tmo_gfx = AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT;
+	}
+
+	for (i = 0; i < adev->num_rings; ++i) {
+		struct amdgpu_ring *ring = adev->rings[i];
+		long tmo;
+
+		/* KIQ rings don't have an IB test because we never submit IBs
+		 * to them and they have no interrupt support.
+		 */
+		if (!ring->sched.ready || !ring->funcs->test_ib)
+			continue;
+
+		if (adev->enable_mes &&
+		    ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+			continue;
+
+		/* MM engine need more time */
+		if (ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
+			ring->funcs->type == AMDGPU_RING_TYPE_VCE ||
+			ring->funcs->type == AMDGPU_RING_TYPE_UVD_ENC ||
+			ring->funcs->type == AMDGPU_RING_TYPE_VCN_DEC ||
+			ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC ||
+			ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
+			tmo = tmo_mm;
+		else
+			tmo = tmo_gfx;
+
+		r = amdgpu_ring_test_ib(ring, tmo);
+		if (!r) {
+			DRM_DEV_DEBUG(adev->dev, "ib test on %s succeeded\n",
+				      ring->name);
+			continue;
+		}
+
+		ring->sched.ready = false;
+		DRM_DEV_ERROR(adev->dev, "IB test failed on %s (%d).\n",
+			  ring->name, r);
+
+		if (ring == &adev->gfx.gfx_ring[0]) {
+			/* oh, oh, that's really bad */
+			adev->accel_working = false;
+			return r;
+
+		} else {
+			ret = r;
+		}
+	}
+	return ret;
+}
+
+/*
+ * Debugfs info
+ */
+#if defined(CONFIG_DEBUG_FS)
+
+static int amdgpu_debugfs_sa_info_show(struct seq_file *m, void *unused)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)m->private;
+
+	seq_printf(m, "--------------------- DELAYED --------------------- \n");
+	amdgpu_sa_bo_dump_debug_info(&adev->ib_pools[AMDGPU_IB_POOL_DELAYED],
+				     m);
+	seq_printf(m, "-------------------- IMMEDIATE -------------------- \n");
+	amdgpu_sa_bo_dump_debug_info(&adev->ib_pools[AMDGPU_IB_POOL_IMMEDIATE],
+				     m);
+	seq_printf(m, "--------------------- DIRECT ---------------------- \n");
+	amdgpu_sa_bo_dump_debug_info(&adev->ib_pools[AMDGPU_IB_POOL_DIRECT], m);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_sa_info);
+
+#endif
+
+void amdgpu_debugfs_sa_init(struct amdgpu_device *adev)
+{
+#if defined(CONFIG_DEBUG_FS)
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
+	struct dentry *root = minor->debugfs_root;
+
+	debugfs_create_file("amdgpu_sa_info", 0444, root, adev,
+			    &amdgpu_debugfs_sa_info_fops);
+
+#endif
+}