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, 607 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
new file mode 100644
index 000000000..3f07b1a2c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -0,0 +1,607 @@
+/*
+ * 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.
+ *
+ */
+#include "amdgpu_ids.h"
+
+#include <linux/idr.h>
+#include <linux/dma-fence-array.h>
+
+
+#include "amdgpu.h"
+#include "amdgpu_trace.h"
+
+/*
+ * PASID manager
+ *
+ * PASIDs are global address space identifiers that can be shared
+ * between the GPU, an IOMMU and the driver. VMs on different devices
+ * may use the same PASID if they share the same address
+ * space. Therefore PASIDs are allocated using a global IDA. VMs are
+ * looked up from the PASID per amdgpu_device.
+ */
+static DEFINE_IDA(amdgpu_pasid_ida);
+
+/* Helper to free pasid from a fence callback */
+struct amdgpu_pasid_cb {
+	struct dma_fence_cb cb;
+	u32 pasid;
+};
+
+/**
+ * amdgpu_pasid_alloc - Allocate a PASID
+ * @bits: Maximum width of the PASID in bits, must be at least 1
+ *
+ * Allocates a PASID of the given width while keeping smaller PASIDs
+ * available if possible.
+ *
+ * Returns a positive integer on success. Returns %-EINVAL if bits==0.
+ * Returns %-ENOSPC if no PASID was available. Returns %-ENOMEM on
+ * memory allocation failure.
+ */
+int amdgpu_pasid_alloc(unsigned int bits)
+{
+	int pasid = -EINVAL;
+
+	for (bits = min(bits, 31U); bits > 0; bits--) {
+		pasid = ida_simple_get(&amdgpu_pasid_ida,
+				       1U << (bits - 1), 1U << bits,
+				       GFP_KERNEL);
+		if (pasid != -ENOSPC)
+			break;
+	}
+
+	if (pasid >= 0)
+		trace_amdgpu_pasid_allocated(pasid);
+
+	return pasid;
+}
+
+/**
+ * amdgpu_pasid_free - Free a PASID
+ * @pasid: PASID to free
+ */
+void amdgpu_pasid_free(u32 pasid)
+{
+	trace_amdgpu_pasid_freed(pasid);
+	ida_simple_remove(&amdgpu_pasid_ida, pasid);
+}
+
+static void amdgpu_pasid_free_cb(struct dma_fence *fence,
+				 struct dma_fence_cb *_cb)
+{
+	struct amdgpu_pasid_cb *cb =
+		container_of(_cb, struct amdgpu_pasid_cb, cb);
+
+	amdgpu_pasid_free(cb->pasid);
+	dma_fence_put(fence);
+	kfree(cb);
+}
+
+/**
+ * amdgpu_pasid_free_delayed - free pasid when fences signal
+ *
+ * @resv: reservation object with the fences to wait for
+ * @pasid: pasid to free
+ *
+ * Free the pasid only after all the fences in resv are signaled.
+ */
+void amdgpu_pasid_free_delayed(struct dma_resv *resv,
+			       u32 pasid)
+{
+	struct amdgpu_pasid_cb *cb;
+	struct dma_fence *fence;
+	int r;
+
+	r = dma_resv_get_singleton(resv, DMA_RESV_USAGE_BOOKKEEP, &fence);
+	if (r)
+		goto fallback;
+
+	if (!fence) {
+		amdgpu_pasid_free(pasid);
+		return;
+	}
+
+	cb = kmalloc(sizeof(*cb), GFP_KERNEL);
+	if (!cb) {
+		/* Last resort when we are OOM */
+		dma_fence_wait(fence, false);
+		dma_fence_put(fence);
+		amdgpu_pasid_free(pasid);
+	} else {
+		cb->pasid = pasid;
+		if (dma_fence_add_callback(fence, &cb->cb,
+					   amdgpu_pasid_free_cb))
+			amdgpu_pasid_free_cb(fence, &cb->cb);
+	}
+
+	return;
+
+fallback:
+	/* Not enough memory for the delayed delete, as last resort
+	 * block for all the fences to complete.
+	 */
+	dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP,
+			      false, MAX_SCHEDULE_TIMEOUT);
+	amdgpu_pasid_free(pasid);
+}
+
+/*
+ * VMID manager
+ *
+ * VMIDs are a per VMHUB identifier for page tables handling.
+ */
+
+/**
+ * amdgpu_vmid_had_gpu_reset - check if reset occured since last use
+ *
+ * @adev: amdgpu_device pointer
+ * @id: VMID structure
+ *
+ * Check if GPU reset occured since last use of the VMID.
+ */
+bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
+			       struct amdgpu_vmid *id)
+{
+	return id->current_gpu_reset_count !=
+		atomic_read(&adev->gpu_reset_counter);
+}
+
+/* Check if we need to switch to another set of resources */
+static bool amdgpu_vmid_gds_switch_needed(struct amdgpu_vmid *id,
+					  struct amdgpu_job *job)
+{
+	return id->gds_base != job->gds_base ||
+		id->gds_size != job->gds_size ||
+		id->gws_base != job->gws_base ||
+		id->gws_size != job->gws_size ||
+		id->oa_base != job->oa_base ||
+		id->oa_size != job->oa_size;
+}
+
+/* Check if the id is compatible with the job */
+static bool amdgpu_vmid_compatible(struct amdgpu_vmid *id,
+				   struct amdgpu_job *job)
+{
+	return  id->pd_gpu_addr == job->vm_pd_addr &&
+		!amdgpu_vmid_gds_switch_needed(id, job);
+}
+
+/**
+ * amdgpu_vmid_grab_idle - grab idle VMID
+ *
+ * @vm: vm to allocate id for
+ * @ring: ring we want to submit job to
+ * @idle: resulting idle VMID
+ * @fence: fence to wait for if no id could be grabbed
+ *
+ * Try to find an idle VMID, if none is idle add a fence to wait to the sync
+ * object. Returns -ENOMEM when we are out of memory.
+ */
+static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm,
+				 struct amdgpu_ring *ring,
+				 struct amdgpu_vmid **idle,
+				 struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmhub = ring->funcs->vmhub;
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct dma_fence **fences;
+	unsigned i;
+
+	if (!dma_fence_is_signaled(ring->vmid_wait)) {
+		*fence = dma_fence_get(ring->vmid_wait);
+		return 0;
+	}
+
+	fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_KERNEL);
+	if (!fences)
+		return -ENOMEM;
+
+	/* Check if we have an idle VMID */
+	i = 0;
+	list_for_each_entry((*idle), &id_mgr->ids_lru, list) {
+		/* Don't use per engine and per process VMID at the same time */
+		struct amdgpu_ring *r = adev->vm_manager.concurrent_flush ?
+			NULL : ring;
+
+		fences[i] = amdgpu_sync_peek_fence(&(*idle)->active, r);
+		if (!fences[i])
+			break;
+		++i;
+	}
+
+	/* If we can't find a idle VMID to use, wait till one becomes available */
+	if (&(*idle)->list == &id_mgr->ids_lru) {
+		u64 fence_context = adev->vm_manager.fence_context + ring->idx;
+		unsigned seqno = ++adev->vm_manager.seqno[ring->idx];
+		struct dma_fence_array *array;
+		unsigned j;
+
+		*idle = NULL;
+		for (j = 0; j < i; ++j)
+			dma_fence_get(fences[j]);
+
+		array = dma_fence_array_create(i, fences, fence_context,
+					       seqno, true);
+		if (!array) {
+			for (j = 0; j < i; ++j)
+				dma_fence_put(fences[j]);
+			kfree(fences);
+			return -ENOMEM;
+		}
+
+		*fence = dma_fence_get(&array->base);
+		dma_fence_put(ring->vmid_wait);
+		ring->vmid_wait = &array->base;
+		return 0;
+	}
+	kfree(fences);
+
+	return 0;
+}
+
+/**
+ * amdgpu_vmid_grab_reserved - try to assign reserved VMID
+ *
+ * @vm: vm to allocate id for
+ * @ring: ring we want to submit job to
+ * @job: job who wants to use the VMID
+ * @id: resulting VMID
+ * @fence: fence to wait for if no id could be grabbed
+ *
+ * Try to assign a reserved VMID.
+ */
+static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
+				     struct amdgpu_ring *ring,
+				     struct amdgpu_job *job,
+				     struct amdgpu_vmid **id,
+				     struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmhub = ring->funcs->vmhub;
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	uint64_t fence_context = adev->fence_context + ring->idx;
+	bool needs_flush = vm->use_cpu_for_update;
+	uint64_t updates = amdgpu_vm_tlb_seq(vm);
+	int r;
+
+	*id = id_mgr->reserved;
+	if ((*id)->owner != vm->immediate.fence_context ||
+	    !amdgpu_vmid_compatible(*id, job) ||
+	    (*id)->flushed_updates < updates ||
+	    !(*id)->last_flush ||
+	    ((*id)->last_flush->context != fence_context &&
+	     !dma_fence_is_signaled((*id)->last_flush))) {
+		struct dma_fence *tmp;
+
+		/* Don't use per engine and per process VMID at the same time */
+		if (adev->vm_manager.concurrent_flush)
+			ring = NULL;
+
+		/* to prevent one context starved by another context */
+		(*id)->pd_gpu_addr = 0;
+		tmp = amdgpu_sync_peek_fence(&(*id)->active, ring);
+		if (tmp) {
+			*id = NULL;
+			*fence = dma_fence_get(tmp);
+			return 0;
+		}
+		needs_flush = true;
+	}
+
+	/* Good we can use this VMID. Remember this submission as
+	* user of the VMID.
+	*/
+	r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished);
+	if (r)
+		return r;
+
+	job->vm_needs_flush = needs_flush;
+	job->spm_update_needed = true;
+	return 0;
+}
+
+/**
+ * amdgpu_vmid_grab_used - try to reuse a VMID
+ *
+ * @vm: vm to allocate id for
+ * @ring: ring we want to submit job to
+ * @job: job who wants to use the VMID
+ * @id: resulting VMID
+ * @fence: fence to wait for if no id could be grabbed
+ *
+ * Try to reuse a VMID for this submission.
+ */
+static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm,
+				 struct amdgpu_ring *ring,
+				 struct amdgpu_job *job,
+				 struct amdgpu_vmid **id,
+				 struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmhub = ring->funcs->vmhub;
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	uint64_t fence_context = adev->fence_context + ring->idx;
+	uint64_t updates = amdgpu_vm_tlb_seq(vm);
+	int r;
+
+	job->vm_needs_flush = vm->use_cpu_for_update;
+
+	/* Check if we can use a VMID already assigned to this VM */
+	list_for_each_entry_reverse((*id), &id_mgr->ids_lru, list) {
+		bool needs_flush = vm->use_cpu_for_update;
+
+		/* Check all the prerequisites to using this VMID */
+		if ((*id)->owner != vm->immediate.fence_context)
+			continue;
+
+		if (!amdgpu_vmid_compatible(*id, job))
+			continue;
+
+		if (!(*id)->last_flush ||
+		    ((*id)->last_flush->context != fence_context &&
+		     !dma_fence_is_signaled((*id)->last_flush)))
+			needs_flush = true;
+
+		if ((*id)->flushed_updates < updates)
+			needs_flush = true;
+
+		if (needs_flush && !adev->vm_manager.concurrent_flush)
+			continue;
+
+		/* Good, we can use this VMID. Remember this submission as
+		 * user of the VMID.
+		 */
+		r = amdgpu_sync_fence(&(*id)->active,
+				      &job->base.s_fence->finished);
+		if (r)
+			return r;
+
+		job->vm_needs_flush |= needs_flush;
+		return 0;
+	}
+
+	*id = NULL;
+	return 0;
+}
+
+/**
+ * amdgpu_vmid_grab - allocate the next free VMID
+ *
+ * @vm: vm to allocate id for
+ * @ring: ring we want to submit job to
+ * @job: job who wants to use the VMID
+ * @fence: fence to wait for if no id could be grabbed
+ *
+ * Allocate an id for the vm, adding fences to the sync obj as necessary.
+ */
+int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+		     struct amdgpu_job *job, struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmhub = ring->funcs->vmhub;
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct amdgpu_vmid *idle = NULL;
+	struct amdgpu_vmid *id = NULL;
+	int r = 0;
+
+	mutex_lock(&id_mgr->lock);
+	r = amdgpu_vmid_grab_idle(vm, ring, &idle, fence);
+	if (r || !idle)
+		goto error;
+
+	if (vm->reserved_vmid[vmhub]) {
+		r = amdgpu_vmid_grab_reserved(vm, ring, job, &id, fence);
+		if (r || !id)
+			goto error;
+	} else {
+		r = amdgpu_vmid_grab_used(vm, ring, job, &id, fence);
+		if (r)
+			goto error;
+
+		if (!id) {
+			/* Still no ID to use? Then use the idle one found earlier */
+			id = idle;
+
+			/* Remember this submission as user of the VMID */
+			r = amdgpu_sync_fence(&id->active,
+					      &job->base.s_fence->finished);
+			if (r)
+				goto error;
+
+			job->vm_needs_flush = true;
+		}
+
+		list_move_tail(&id->list, &id_mgr->ids_lru);
+	}
+
+	job->gds_switch_needed = amdgpu_vmid_gds_switch_needed(id, job);
+	if (job->vm_needs_flush) {
+		id->flushed_updates = amdgpu_vm_tlb_seq(vm);
+		dma_fence_put(id->last_flush);
+		id->last_flush = NULL;
+	}
+	job->vmid = id - id_mgr->ids;
+	job->pasid = vm->pasid;
+
+	id->gds_base = job->gds_base;
+	id->gds_size = job->gds_size;
+	id->gws_base = job->gws_base;
+	id->gws_size = job->gws_size;
+	id->oa_base = job->oa_base;
+	id->oa_size = job->oa_size;
+	id->pd_gpu_addr = job->vm_pd_addr;
+	id->owner = vm->immediate.fence_context;
+
+	trace_amdgpu_vm_grab_id(vm, ring, job);
+
+error:
+	mutex_unlock(&id_mgr->lock);
+	return r;
+}
+
+int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
+			       struct amdgpu_vm *vm,
+			       unsigned vmhub)
+{
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+
+	mutex_lock(&id_mgr->lock);
+	if (vm->reserved_vmid[vmhub])
+		goto unlock;
+
+	++id_mgr->reserved_use_count;
+	if (!id_mgr->reserved) {
+		struct amdgpu_vmid *id;
+
+		id = list_first_entry(&id_mgr->ids_lru, struct amdgpu_vmid,
+				      list);
+		/* Remove from normal round robin handling */
+		list_del_init(&id->list);
+		id_mgr->reserved = id;
+	}
+	vm->reserved_vmid[vmhub] = true;
+
+unlock:
+	mutex_unlock(&id_mgr->lock);
+	return 0;
+}
+
+void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
+			       struct amdgpu_vm *vm,
+			       unsigned vmhub)
+{
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+
+	mutex_lock(&id_mgr->lock);
+	if (vm->reserved_vmid[vmhub] &&
+	    !--id_mgr->reserved_use_count) {
+		/* give the reserved ID back to normal round robin */
+		list_add(&id_mgr->reserved->list, &id_mgr->ids_lru);
+		id_mgr->reserved = NULL;
+	}
+	vm->reserved_vmid[vmhub] = false;
+	mutex_unlock(&id_mgr->lock);
+}
+
+/**
+ * amdgpu_vmid_reset - reset VMID to zero
+ *
+ * @adev: amdgpu device structure
+ * @vmhub: vmhub type
+ * @vmid: vmid number to use
+ *
+ * Reset saved GDW, GWS and OA to force switch on next flush.
+ */
+void amdgpu_vmid_reset(struct amdgpu_device *adev, unsigned vmhub,
+		       unsigned vmid)
+{
+	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct amdgpu_vmid *id = &id_mgr->ids[vmid];
+
+	mutex_lock(&id_mgr->lock);
+	id->owner = 0;
+	id->gds_base = 0;
+	id->gds_size = 0;
+	id->gws_base = 0;
+	id->gws_size = 0;
+	id->oa_base = 0;
+	id->oa_size = 0;
+	mutex_unlock(&id_mgr->lock);
+}
+
+/**
+ * amdgpu_vmid_reset_all - reset VMID to zero
+ *
+ * @adev: amdgpu device structure
+ *
+ * Reset VMID to force flush on next use
+ */
+void amdgpu_vmid_reset_all(struct amdgpu_device *adev)
+{
+	unsigned i, j;
+
+	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+		struct amdgpu_vmid_mgr *id_mgr =
+			&adev->vm_manager.id_mgr[i];
+
+		for (j = 1; j < id_mgr->num_ids; ++j)
+			amdgpu_vmid_reset(adev, i, j);
+	}
+}
+
+/**
+ * amdgpu_vmid_mgr_init - init the VMID manager
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Initialize the VM manager structures
+ */
+void amdgpu_vmid_mgr_init(struct amdgpu_device *adev)
+{
+	unsigned i, j;
+
+	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+		struct amdgpu_vmid_mgr *id_mgr =
+			&adev->vm_manager.id_mgr[i];
+
+		mutex_init(&id_mgr->lock);
+		INIT_LIST_HEAD(&id_mgr->ids_lru);
+		id_mgr->reserved_use_count = 0;
+
+		/* manage only VMIDs not used by KFD */
+		id_mgr->num_ids = adev->vm_manager.first_kfd_vmid;
+
+		/* skip over VMID 0, since it is the system VM */
+		for (j = 1; j < id_mgr->num_ids; ++j) {
+			amdgpu_vmid_reset(adev, i, j);
+			amdgpu_sync_create(&id_mgr->ids[j].active);
+			list_add_tail(&id_mgr->ids[j].list, &id_mgr->ids_lru);
+		}
+	}
+}
+
+/**
+ * amdgpu_vmid_mgr_fini - cleanup VM manager
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Cleanup the VM manager and free resources.
+ */
+void amdgpu_vmid_mgr_fini(struct amdgpu_device *adev)
+{
+	unsigned i, j;
+
+	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+		struct amdgpu_vmid_mgr *id_mgr =
+			&adev->vm_manager.id_mgr[i];
+
+		mutex_destroy(&id_mgr->lock);
+		for (j = 0; j < AMDGPU_NUM_VMID; ++j) {
+			struct amdgpu_vmid *id = &id_mgr->ids[j];
+
+			amdgpu_sync_free(&id->active);
+			dma_fence_put(id->last_flush);
+			dma_fence_put(id->pasid_mapping);
+		}
+	}
+}