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, 424 insertions, 0 deletions

diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
new file mode 100644
index 000000000..0981948bd
--- /dev/null
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -0,0 +1,424 @@
+/*
+ * Copyright 2011 Red Hat Inc.
+ * All Rights Reserved.
+ *
+ * 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, sub license, 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 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 NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ */
+/*
+ * Authors:
+ *    Jerome Glisse <glisse@freedesktop.org>
+ */
+/* Algorithm:
+ *
+ * We store the last allocated bo in "hole", we always try to allocate
+ * after the last allocated bo. Principle is that in a linear GPU ring
+ * progression was is after last is the oldest bo we allocated and thus
+ * the first one that should no longer be in use by the GPU.
+ *
+ * If it's not the case we skip over the bo after last to the closest
+ * done bo if such one exist. If none exist and we are not asked to
+ * block we report failure to allocate.
+ *
+ * If we are asked to block we wait on all the oldest fence of all
+ * rings. We just wait for any of those fence to complete.
+ */
+
+#include "radeon.h"
+
+static void radeon_sa_bo_remove_locked(struct radeon_sa_bo *sa_bo);
+static void radeon_sa_bo_try_free(struct radeon_sa_manager *sa_manager);
+
+int radeon_sa_bo_manager_init(struct radeon_device *rdev,
+			      struct radeon_sa_manager *sa_manager,
+			      unsigned size, u32 align, u32 domain, u32 flags)
+{
+	int i, r;
+
+	init_waitqueue_head(&sa_manager->wq);
+	sa_manager->bo = NULL;
+	sa_manager->size = size;
+	sa_manager->domain = domain;
+	sa_manager->align = align;
+	sa_manager->hole = &sa_manager->olist;
+	INIT_LIST_HEAD(&sa_manager->olist);
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		INIT_LIST_HEAD(&sa_manager->flist[i]);
+	}
+
+	r = radeon_bo_create(rdev, size, align, true,
+			     domain, flags, NULL, NULL, &sa_manager->bo);
+	if (r) {
+		dev_err(rdev->dev, "(%d) failed to allocate bo for manager\n", r);
+		return r;
+	}
+
+	return r;
+}
+
+void radeon_sa_bo_manager_fini(struct radeon_device *rdev,
+			       struct radeon_sa_manager *sa_manager)
+{
+	struct radeon_sa_bo *sa_bo, *tmp;
+
+	if (!list_empty(&sa_manager->olist)) {
+		sa_manager->hole = &sa_manager->olist,
+		radeon_sa_bo_try_free(sa_manager);
+		if (!list_empty(&sa_manager->olist)) {
+			dev_err(rdev->dev, "sa_manager is not empty, clearing anyway\n");
+		}
+	}
+	list_for_each_entry_safe(sa_bo, tmp, &sa_manager->olist, olist) {
+		radeon_sa_bo_remove_locked(sa_bo);
+	}
+	radeon_bo_unref(&sa_manager->bo);
+	sa_manager->size = 0;
+}
+
+int radeon_sa_bo_manager_start(struct radeon_device *rdev,
+			       struct radeon_sa_manager *sa_manager)
+{
+	int r;
+
+	if (sa_manager->bo == NULL) {
+		dev_err(rdev->dev, "no bo for sa manager\n");
+		return -EINVAL;
+	}
+
+	/* map the buffer */
+	r = radeon_bo_reserve(sa_manager->bo, false);
+	if (r) {
+		dev_err(rdev->dev, "(%d) failed to reserve manager bo\n", r);
+		return r;
+	}
+	r = radeon_bo_pin(sa_manager->bo, sa_manager->domain, &sa_manager->gpu_addr);
+	if (r) {
+		radeon_bo_unreserve(sa_manager->bo);
+		dev_err(rdev->dev, "(%d) failed to pin manager bo\n", r);
+		return r;
+	}
+	r = radeon_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr);
+	radeon_bo_unreserve(sa_manager->bo);
+	return r;
+}
+
+int radeon_sa_bo_manager_suspend(struct radeon_device *rdev,
+				 struct radeon_sa_manager *sa_manager)
+{
+	int r;
+
+	if (sa_manager->bo == NULL) {
+		dev_err(rdev->dev, "no bo for sa manager\n");
+		return -EINVAL;
+	}
+
+	r = radeon_bo_reserve(sa_manager->bo, false);
+	if (!r) {
+		radeon_bo_kunmap(sa_manager->bo);
+		radeon_bo_unpin(sa_manager->bo);
+		radeon_bo_unreserve(sa_manager->bo);
+	}
+	return r;
+}
+
+static void radeon_sa_bo_remove_locked(struct radeon_sa_bo *sa_bo)
+{
+	struct radeon_sa_manager *sa_manager = sa_bo->manager;
+	if (sa_manager->hole == &sa_bo->olist) {
+		sa_manager->hole = sa_bo->olist.prev;
+	}
+	list_del_init(&sa_bo->olist);
+	list_del_init(&sa_bo->flist);
+	radeon_fence_unref(&sa_bo->fence);
+	kfree(sa_bo);
+}
+
+static void radeon_sa_bo_try_free(struct radeon_sa_manager *sa_manager)
+{
+	struct radeon_sa_bo *sa_bo, *tmp;
+
+	if (sa_manager->hole->next == &sa_manager->olist)
+		return;
+
+	sa_bo = list_entry(sa_manager->hole->next, struct radeon_sa_bo, olist);
+	list_for_each_entry_safe_from(sa_bo, tmp, &sa_manager->olist, olist) {
+		if (sa_bo->fence == NULL || !radeon_fence_signaled(sa_bo->fence)) {
+			return;
+		}
+		radeon_sa_bo_remove_locked(sa_bo);
+	}
+}
+
+static inline unsigned radeon_sa_bo_hole_soffset(struct radeon_sa_manager *sa_manager)
+{
+	struct list_head *hole = sa_manager->hole;
+
+	if (hole != &sa_manager->olist) {
+		return list_entry(hole, struct radeon_sa_bo, olist)->eoffset;
+	}
+	return 0;
+}
+
+static inline unsigned radeon_sa_bo_hole_eoffset(struct radeon_sa_manager *sa_manager)
+{
+	struct list_head *hole = sa_manager->hole;
+
+	if (hole->next != &sa_manager->olist) {
+		return list_entry(hole->next, struct radeon_sa_bo, olist)->soffset;
+	}
+	return sa_manager->size;
+}
+
+static bool radeon_sa_bo_try_alloc(struct radeon_sa_manager *sa_manager,
+				   struct radeon_sa_bo *sa_bo,
+				   unsigned size, unsigned align)
+{
+	unsigned soffset, eoffset, wasted;
+
+	soffset = radeon_sa_bo_hole_soffset(sa_manager);
+	eoffset = radeon_sa_bo_hole_eoffset(sa_manager);
+	wasted = (align - (soffset % align)) % align;
+
+	if ((eoffset - soffset) >= (size + wasted)) {
+		soffset += wasted;
+
+		sa_bo->manager = sa_manager;
+		sa_bo->soffset = soffset;
+		sa_bo->eoffset = soffset + size;
+		list_add(&sa_bo->olist, sa_manager->hole);
+		INIT_LIST_HEAD(&sa_bo->flist);
+		sa_manager->hole = &sa_bo->olist;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * radeon_sa_event - Check if we can stop waiting
+ *
+ * @sa_manager: pointer to the sa_manager
+ * @size: number of bytes we want to allocate
+ * @align: alignment we need to match
+ *
+ * Check if either there is a fence we can wait for or
+ * enough free memory to satisfy the allocation directly
+ */
+static bool radeon_sa_event(struct radeon_sa_manager *sa_manager,
+			    unsigned size, unsigned align)
+{
+	unsigned soffset, eoffset, wasted;
+	int i;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (!list_empty(&sa_manager->flist[i])) {
+			return true;
+		}
+	}
+
+	soffset = radeon_sa_bo_hole_soffset(sa_manager);
+	eoffset = radeon_sa_bo_hole_eoffset(sa_manager);
+	wasted = (align - (soffset % align)) % align;
+
+	if ((eoffset - soffset) >= (size + wasted)) {
+		return true;
+	}
+
+	return false;
+}
+
+static bool radeon_sa_bo_next_hole(struct radeon_sa_manager *sa_manager,
+				   struct radeon_fence **fences,
+				   unsigned *tries)
+{
+	struct radeon_sa_bo *best_bo = NULL;
+	unsigned i, soffset, best, tmp;
+
+	/* if hole points to the end of the buffer */
+	if (sa_manager->hole->next == &sa_manager->olist) {
+		/* try again with its beginning */
+		sa_manager->hole = &sa_manager->olist;
+		return true;
+	}
+
+	soffset = radeon_sa_bo_hole_soffset(sa_manager);
+	/* to handle wrap around we add sa_manager->size */
+	best = sa_manager->size * 2;
+	/* go over all fence list and try to find the closest sa_bo
+	 * of the current last
+	 */
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		struct radeon_sa_bo *sa_bo;
+
+		fences[i] = NULL;
+
+		if (list_empty(&sa_manager->flist[i])) {
+			continue;
+		}
+
+		sa_bo = list_first_entry(&sa_manager->flist[i],
+					 struct radeon_sa_bo, flist);
+
+		if (!radeon_fence_signaled(sa_bo->fence)) {
+			fences[i] = sa_bo->fence;
+			continue;
+		}
+
+		/* limit the number of tries each ring gets */
+		if (tries[i] > 2) {
+			continue;
+		}
+
+		tmp = sa_bo->soffset;
+		if (tmp < soffset) {
+			/* wrap around, pretend it's after */
+			tmp += sa_manager->size;
+		}
+		tmp -= soffset;
+		if (tmp < best) {
+			/* this sa bo is the closest one */
+			best = tmp;
+			best_bo = sa_bo;
+		}
+	}
+
+	if (best_bo) {
+		++tries[best_bo->fence->ring];
+		sa_manager->hole = best_bo->olist.prev;
+
+		/* we knew that this one is signaled,
+		   so it's save to remote it */
+		radeon_sa_bo_remove_locked(best_bo);
+		return true;
+	}
+	return false;
+}
+
+int radeon_sa_bo_new(struct radeon_device *rdev,
+		     struct radeon_sa_manager *sa_manager,
+		     struct radeon_sa_bo **sa_bo,
+		     unsigned size, unsigned align)
+{
+	struct radeon_fence *fences[RADEON_NUM_RINGS];
+	unsigned tries[RADEON_NUM_RINGS];
+	int i, r;
+
+	BUG_ON(align > sa_manager->align);
+	BUG_ON(size > sa_manager->size);
+
+	*sa_bo = kmalloc(sizeof(struct radeon_sa_bo), GFP_KERNEL);
+	if ((*sa_bo) == NULL) {
+		return -ENOMEM;
+	}
+	(*sa_bo)->manager = sa_manager;
+	(*sa_bo)->fence = NULL;
+	INIT_LIST_HEAD(&(*sa_bo)->olist);
+	INIT_LIST_HEAD(&(*sa_bo)->flist);
+
+	spin_lock(&sa_manager->wq.lock);
+	do {
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			tries[i] = 0;
+
+		do {
+			radeon_sa_bo_try_free(sa_manager);
+
+			if (radeon_sa_bo_try_alloc(sa_manager, *sa_bo,
+						   size, align)) {
+				spin_unlock(&sa_manager->wq.lock);
+				return 0;
+			}
+
+			/* see if we can skip over some allocations */
+		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
+
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_ref(fences[i]);
+
+		spin_unlock(&sa_manager->wq.lock);
+		r = radeon_fence_wait_any(rdev, fences, false);
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_unref(&fences[i]);
+		spin_lock(&sa_manager->wq.lock);
+		/* if we have nothing to wait for block */
+		if (r == -ENOENT) {
+			r = wait_event_interruptible_locked(
+				sa_manager->wq, 
+				radeon_sa_event(sa_manager, size, align)
+			);
+		}
+
+	} while (!r);
+
+	spin_unlock(&sa_manager->wq.lock);
+	kfree(*sa_bo);
+	*sa_bo = NULL;
+	return r;
+}
+
+void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo **sa_bo,
+		       struct radeon_fence *fence)
+{
+	struct radeon_sa_manager *sa_manager;
+
+	if (sa_bo == NULL || *sa_bo == NULL) {
+		return;
+	}
+
+	sa_manager = (*sa_bo)->manager;
+	spin_lock(&sa_manager->wq.lock);
+	if (fence && !radeon_fence_signaled(fence)) {
+		(*sa_bo)->fence = radeon_fence_ref(fence);
+		list_add_tail(&(*sa_bo)->flist,
+			      &sa_manager->flist[fence->ring]);
+	} else {
+		radeon_sa_bo_remove_locked(*sa_bo);
+	}
+	wake_up_all_locked(&sa_manager->wq);
+	spin_unlock(&sa_manager->wq.lock);
+	*sa_bo = NULL;
+}
+
+#if defined(CONFIG_DEBUG_FS)
+void radeon_sa_bo_dump_debug_info(struct radeon_sa_manager *sa_manager,
+				  struct seq_file *m)
+{
+	struct radeon_sa_bo *i;
+
+	spin_lock(&sa_manager->wq.lock);
+	list_for_each_entry(i, &sa_manager->olist, olist) {
+		uint64_t soffset = i->soffset + sa_manager->gpu_addr;
+		uint64_t eoffset = i->eoffset + sa_manager->gpu_addr;
+		if (&i->olist == sa_manager->hole) {
+			seq_printf(m, ">");
+		} else {
+			seq_printf(m, " ");
+		}
+		seq_printf(m, "[0x%010llx 0x%010llx] size %8lld",
+			   soffset, eoffset, eoffset - soffset);
+		if (i->fence) {
+			seq_printf(m, " protected by 0x%016llx on ring %d",
+				   i->fence->seq, i->fence->ring);
+		}
+		seq_printf(m, "\n");
+	}
+	spin_unlock(&sa_manager->wq.lock);
+}
+#endif