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, 520 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
new file mode 100644
index 000000000..a4b4d9b7d
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -0,0 +1,520 @@
+/*
+ * Copyright © 2008-2010 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Eric Anholt <eric@anholt.net>
+ *    Chris Wilson <chris@chris-wilson.co.uuk>
+ *
+ */
+
+#include "gem/i915_gem_context.h"
+#include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
+
+#include "i915_drv.h"
+#include "i915_gem_evict.h"
+#include "i915_trace.h"
+
+I915_SELFTEST_DECLARE(static struct igt_evict_ctl {
+	bool fail_if_busy:1;
+} igt_evict_ctl;)
+
+static bool dying_vma(struct i915_vma *vma)
+{
+	return !kref_read(&vma->obj->base.refcount);
+}
+
+static int ggtt_flush(struct intel_gt *gt)
+{
+	/*
+	 * Not everything in the GGTT is tracked via vma (otherwise we
+	 * could evict as required with minimal stalling) so we are forced
+	 * to idle the GPU and explicitly retire outstanding requests in
+	 * the hopes that we can then remove contexts and the like only
+	 * bound by their active reference.
+	 */
+	return intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT);
+}
+
+static bool grab_vma(struct i915_vma *vma, struct i915_gem_ww_ctx *ww)
+{
+	/*
+	 * We add the extra refcount so the object doesn't drop to zero until
+	 * after ungrab_vma(), this way trylock is always paired with unlock.
+	 */
+	if (i915_gem_object_get_rcu(vma->obj)) {
+		if (!i915_gem_object_trylock(vma->obj, ww)) {
+			i915_gem_object_put(vma->obj);
+			return false;
+		}
+	} else {
+		/* Dead objects don't need pins */
+		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
+	}
+
+	return true;
+}
+
+static void ungrab_vma(struct i915_vma *vma)
+{
+	if (dying_vma(vma))
+		return;
+
+	i915_gem_object_unlock(vma->obj);
+	i915_gem_object_put(vma->obj);
+}
+
+static bool
+mark_free(struct drm_mm_scan *scan,
+	  struct i915_gem_ww_ctx *ww,
+	  struct i915_vma *vma,
+	  unsigned int flags,
+	  struct list_head *unwind)
+{
+	if (i915_vma_is_pinned(vma))
+		return false;
+
+	if (!grab_vma(vma, ww))
+		return false;
+
+	list_add(&vma->evict_link, unwind);
+	return drm_mm_scan_add_block(scan, &vma->node);
+}
+
+static bool defer_evict(struct i915_vma *vma)
+{
+	if (i915_vma_is_active(vma))
+		return true;
+
+	if (i915_vma_is_scanout(vma))
+		return true;
+
+	return false;
+}
+
+/**
+ * i915_gem_evict_something - Evict vmas to make room for binding a new one
+ * @vm: address space to evict from
+ * @ww: An optional struct i915_gem_ww_ctx.
+ * @min_size: size of the desired free space
+ * @alignment: alignment constraint of the desired free space
+ * @color: color for the desired space
+ * @start: start (inclusive) of the range from which to evict objects
+ * @end: end (exclusive) of the range from which to evict objects
+ * @flags: additional flags to control the eviction algorithm
+ *
+ * This function will try to evict vmas until a free space satisfying the
+ * requirements is found. Callers must check first whether any such hole exists
+ * already before calling this function.
+ *
+ * This function is used by the object/vma binding code.
+ *
+ * Since this function is only used to free up virtual address space it only
+ * ignores pinned vmas, and not object where the backing storage itself is
+ * pinned. Hence obj->pages_pin_count does not protect against eviction.
+ *
+ * To clarify: This is for freeing up virtual address space, not for freeing
+ * memory in e.g. the shrinker.
+ */
+int
+i915_gem_evict_something(struct i915_address_space *vm,
+			 struct i915_gem_ww_ctx *ww,
+			 u64 min_size, u64 alignment,
+			 unsigned long color,
+			 u64 start, u64 end,
+			 unsigned flags)
+{
+	struct drm_mm_scan scan;
+	struct list_head eviction_list;
+	struct i915_vma *vma, *next;
+	struct drm_mm_node *node;
+	enum drm_mm_insert_mode mode;
+	struct i915_vma *active;
+	int ret;
+
+	lockdep_assert_held(&vm->mutex);
+	trace_i915_gem_evict(vm, min_size, alignment, flags);
+
+	/*
+	 * The goal is to evict objects and amalgamate space in rough LRU order.
+	 * Since both active and inactive objects reside on the same list,
+	 * in a mix of creation and last scanned order, as we process the list
+	 * we sort it into inactive/active, which keeps the active portion
+	 * in a rough MRU order.
+	 *
+	 * The retirement sequence is thus:
+	 *   1. Inactive objects (already retired, random order)
+	 *   2. Active objects (will stall on unbinding, oldest scanned first)
+	 */
+	mode = DRM_MM_INSERT_BEST;
+	if (flags & PIN_HIGH)
+		mode = DRM_MM_INSERT_HIGH;
+	if (flags & PIN_MAPPABLE)
+		mode = DRM_MM_INSERT_LOW;
+	drm_mm_scan_init_with_range(&scan, &vm->mm,
+				    min_size, alignment, color,
+				    start, end, mode);
+
+	intel_gt_retire_requests(vm->gt);
+
+search_again:
+	active = NULL;
+	INIT_LIST_HEAD(&eviction_list);
+	list_for_each_entry_safe(vma, next, &vm->bound_list, vm_link) {
+		if (vma == active) { /* now seen this vma twice */
+			if (flags & PIN_NONBLOCK)
+				break;
+
+			active = ERR_PTR(-EAGAIN);
+		}
+
+		/*
+		 * We keep this list in a rough least-recently scanned order
+		 * of active elements (inactive elements are cheap to reap).
+		 * New entries are added to the end, and we move anything we
+		 * scan to the end. The assumption is that the working set
+		 * of applications is either steady state (and thanks to the
+		 * userspace bo cache it almost always is) or volatile and
+		 * frequently replaced after a frame, which are self-evicting!
+		 * Given that assumption, the MRU order of the scan list is
+		 * fairly static, and keeping it in least-recently scan order
+		 * is suitable.
+		 *
+		 * To notice when we complete one full cycle, we record the
+		 * first active element seen, before moving it to the tail.
+		 */
+		if (active != ERR_PTR(-EAGAIN) && defer_evict(vma)) {
+			if (!active)
+				active = vma;
+
+			list_move_tail(&vma->vm_link, &vm->bound_list);
+			continue;
+		}
+
+		if (mark_free(&scan, ww, vma, flags, &eviction_list))
+			goto found;
+	}
+
+	/* Nothing found, clean up and bail out! */
+	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
+		ret = drm_mm_scan_remove_block(&scan, &vma->node);
+		BUG_ON(ret);
+		ungrab_vma(vma);
+	}
+
+	/*
+	 * Can we unpin some objects such as idle hw contents,
+	 * or pending flips? But since only the GGTT has global entries
+	 * such as scanouts, rinbuffers and contexts, we can skip the
+	 * purge when inspecting per-process local address spaces.
+	 */
+	if (!i915_is_ggtt(vm) || flags & PIN_NONBLOCK)
+		return -ENOSPC;
+
+	/*
+	 * Not everything in the GGTT is tracked via VMA using
+	 * i915_vma_move_to_active(), otherwise we could evict as required
+	 * with minimal stalling. Instead we are forced to idle the GPU and
+	 * explicitly retire outstanding requests which will then remove
+	 * the pinning for active objects such as contexts and ring,
+	 * enabling us to evict them on the next iteration.
+	 *
+	 * To ensure that all user contexts are evictable, we perform
+	 * a switch to the perma-pinned kernel context. This all also gives
+	 * us a termination condition, when the last retired context is
+	 * the kernel's there is no more we can evict.
+	 */
+	if (I915_SELFTEST_ONLY(igt_evict_ctl.fail_if_busy))
+		return -EBUSY;
+
+	ret = ggtt_flush(vm->gt);
+	if (ret)
+		return ret;
+
+	cond_resched();
+
+	flags |= PIN_NONBLOCK;
+	goto search_again;
+
+found:
+	/* drm_mm doesn't allow any other other operations while
+	 * scanning, therefore store to-be-evicted objects on a
+	 * temporary list and take a reference for all before
+	 * calling unbind (which may remove the active reference
+	 * of any of our objects, thus corrupting the list).
+	 */
+	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
+		if (drm_mm_scan_remove_block(&scan, &vma->node)) {
+			__i915_vma_pin(vma);
+		} else {
+			list_del(&vma->evict_link);
+			ungrab_vma(vma);
+		}
+	}
+
+	/* Unbinding will emit any required flushes */
+	ret = 0;
+	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
+		__i915_vma_unpin(vma);
+		if (ret == 0)
+			ret = __i915_vma_unbind(vma);
+		ungrab_vma(vma);
+	}
+
+	while (ret == 0 && (node = drm_mm_scan_color_evict(&scan))) {
+		vma = container_of(node, struct i915_vma, node);
+
+		/* If we find any non-objects (!vma), we cannot evict them */
+		if (vma->node.color != I915_COLOR_UNEVICTABLE &&
+		    grab_vma(vma, ww)) {
+			ret = __i915_vma_unbind(vma);
+			ungrab_vma(vma);
+		} else {
+			ret = -ENOSPC;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * i915_gem_evict_for_node - Evict vmas to make room for binding a new one
+ * @vm: address space to evict from
+ * @ww: An optional struct i915_gem_ww_ctx.
+ * @target: range (and color) to evict for
+ * @flags: additional flags to control the eviction algorithm
+ *
+ * This function will try to evict vmas that overlap the target node.
+ *
+ * To clarify: This is for freeing up virtual address space, not for freeing
+ * memory in e.g. the shrinker.
+ */
+int i915_gem_evict_for_node(struct i915_address_space *vm,
+			    struct i915_gem_ww_ctx *ww,
+			    struct drm_mm_node *target,
+			    unsigned int flags)
+{
+	LIST_HEAD(eviction_list);
+	struct drm_mm_node *node;
+	u64 start = target->start;
+	u64 end = start + target->size;
+	struct i915_vma *vma, *next;
+	int ret = 0;
+
+	lockdep_assert_held(&vm->mutex);
+	GEM_BUG_ON(!IS_ALIGNED(start, I915_GTT_PAGE_SIZE));
+	GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
+
+	trace_i915_gem_evict_node(vm, target, flags);
+
+	/*
+	 * Retire before we search the active list. Although we have
+	 * reasonable accuracy in our retirement lists, we may have
+	 * a stray pin (preventing eviction) that can only be resolved by
+	 * retiring.
+	 */
+	intel_gt_retire_requests(vm->gt);
+
+	if (i915_vm_has_cache_coloring(vm)) {
+		/* Expand search to cover neighbouring guard pages (or lack!) */
+		if (start)
+			start -= I915_GTT_PAGE_SIZE;
+
+		/* Always look at the page afterwards to avoid the end-of-GTT */
+		end += I915_GTT_PAGE_SIZE;
+	}
+	GEM_BUG_ON(start >= end);
+
+	drm_mm_for_each_node_in_range(node, &vm->mm, start, end) {
+		/* If we find any non-objects (!vma), we cannot evict them */
+		if (node->color == I915_COLOR_UNEVICTABLE) {
+			ret = -ENOSPC;
+			break;
+		}
+
+		GEM_BUG_ON(!drm_mm_node_allocated(node));
+		vma = container_of(node, typeof(*vma), node);
+
+		/*
+		 * If we are using coloring to insert guard pages between
+		 * different cache domains within the address space, we have
+		 * to check whether the objects on either side of our range
+		 * abutt and conflict. If they are in conflict, then we evict
+		 * those as well to make room for our guard pages.
+		 */
+		if (i915_vm_has_cache_coloring(vm)) {
+			if (node->start + node->size == target->start) {
+				if (node->color == target->color)
+					continue;
+			}
+			if (node->start == target->start + target->size) {
+				if (node->color == target->color)
+					continue;
+			}
+		}
+
+		if (i915_vma_is_pinned(vma)) {
+			ret = -ENOSPC;
+			break;
+		}
+
+		if (flags & PIN_NONBLOCK && i915_vma_is_active(vma)) {
+			ret = -ENOSPC;
+			break;
+		}
+
+		if (!grab_vma(vma, ww)) {
+			ret = -ENOSPC;
+			break;
+		}
+
+		/*
+		 * Never show fear in the face of dragons!
+		 *
+		 * We cannot directly remove this node from within this
+		 * iterator and as with i915_gem_evict_something() we employ
+		 * the vma pin_count in order to prevent the action of
+		 * unbinding one vma from freeing (by dropping its active
+		 * reference) another in our eviction list.
+		 */
+		__i915_vma_pin(vma);
+		list_add(&vma->evict_link, &eviction_list);
+	}
+
+	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
+		__i915_vma_unpin(vma);
+		if (ret == 0)
+			ret = __i915_vma_unbind(vma);
+
+		ungrab_vma(vma);
+	}
+
+	return ret;
+}
+
+/**
+ * i915_gem_evict_vm - Evict all idle vmas from a vm
+ * @vm: Address space to cleanse
+ * @ww: An optional struct i915_gem_ww_ctx. If not NULL, i915_gem_evict_vm
+ * will be able to evict vma's locked by the ww as well.
+ * @busy_bo: Optional pointer to struct drm_i915_gem_object. If not NULL, then
+ * in the event i915_gem_evict_vm() is unable to trylock an object for eviction,
+ * then @busy_bo will point to it. -EBUSY is also returned. The caller must drop
+ * the vm->mutex, before trying again to acquire the contended lock. The caller
+ * also owns a reference to the object.
+ *
+ * This function evicts all vmas from a vm.
+ *
+ * This is used by the execbuf code as a last-ditch effort to defragment the
+ * address space.
+ *
+ * To clarify: This is for freeing up virtual address space, not for freeing
+ * memory in e.g. the shrinker.
+ */
+int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww,
+		      struct drm_i915_gem_object **busy_bo)
+{
+	int ret = 0;
+
+	lockdep_assert_held(&vm->mutex);
+	trace_i915_gem_evict_vm(vm);
+
+	/* Switch back to the default context in order to unpin
+	 * the existing context objects. However, such objects only
+	 * pin themselves inside the global GTT and performing the
+	 * switch otherwise is ineffective.
+	 */
+	if (i915_is_ggtt(vm)) {
+		ret = ggtt_flush(vm->gt);
+		if (ret)
+			return ret;
+	}
+
+	do {
+		struct i915_vma *vma, *vn;
+		LIST_HEAD(eviction_list);
+		LIST_HEAD(locked_eviction_list);
+
+		list_for_each_entry(vma, &vm->bound_list, vm_link) {
+			if (i915_vma_is_pinned(vma))
+				continue;
+
+			/*
+			 * If we already own the lock, trylock fails. In case
+			 * the resv is shared among multiple objects, we still
+			 * need the object ref.
+			 */
+			if (!i915_gem_object_get_rcu(vma->obj) ||
+			    (ww && (dma_resv_locking_ctx(vma->obj->base.resv) == &ww->ctx))) {
+				__i915_vma_pin(vma);
+				list_add(&vma->evict_link, &locked_eviction_list);
+				continue;
+			}
+
+			if (!i915_gem_object_trylock(vma->obj, ww)) {
+				if (busy_bo) {
+					*busy_bo = vma->obj; /* holds ref */
+					ret = -EBUSY;
+					break;
+				}
+				i915_gem_object_put(vma->obj);
+				continue;
+			}
+
+			__i915_vma_pin(vma);
+			list_add(&vma->evict_link, &eviction_list);
+		}
+		if (list_empty(&eviction_list) && list_empty(&locked_eviction_list))
+			break;
+
+		/* Unbind locked objects first, before unlocking the eviction_list */
+		list_for_each_entry_safe(vma, vn, &locked_eviction_list, evict_link) {
+			__i915_vma_unpin(vma);
+
+			if (ret == 0) {
+				ret = __i915_vma_unbind(vma);
+				if (ret != -EINTR) /* "Get me out of here!" */
+					ret = 0;
+			}
+			if (!dying_vma(vma))
+				i915_gem_object_put(vma->obj);
+		}
+
+		list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) {
+			__i915_vma_unpin(vma);
+			if (ret == 0) {
+				ret = __i915_vma_unbind(vma);
+				if (ret != -EINTR) /* "Get me out of here!" */
+					ret = 0;
+			}
+
+			i915_gem_object_unlock(vma->obj);
+			i915_gem_object_put(vma->obj);
+		}
+	} while (ret == 0);
+
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/i915_gem_evict.c"
+#endif