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, 569 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
new file mode 100644
index 000000000..37068542a
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -0,0 +1,569 @@
+/*
+ * Copyright © 2016 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.
+ *
+ */
+
+#include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_pm.h"
+#include "gem/selftests/igt_gem_utils.h"
+#include "gem/selftests/mock_context.h"
+#include "gt/intel_gt.h"
+
+#include "i915_selftest.h"
+
+#include "igt_flush_test.h"
+#include "lib_sw_fence.h"
+#include "mock_drm.h"
+#include "mock_gem_device.h"
+
+static void quirk_add(struct drm_i915_gem_object *obj,
+		      struct list_head *objects)
+{
+	/* quirk is only for live tiled objects, use it to declare ownership */
+	GEM_BUG_ON(i915_gem_object_has_tiling_quirk(obj));
+	i915_gem_object_set_tiling_quirk(obj);
+	list_add(&obj->st_link, objects);
+}
+
+static int populate_ggtt(struct i915_ggtt *ggtt, struct list_head *objects)
+{
+	struct drm_i915_gem_object *obj;
+	unsigned long count;
+
+	count = 0;
+	do {
+		struct i915_vma *vma;
+
+		obj = i915_gem_object_create_internal(ggtt->vm.i915,
+						      I915_GTT_PAGE_SIZE);
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
+		if (IS_ERR(vma)) {
+			i915_gem_object_put(obj);
+			if (vma == ERR_PTR(-ENOSPC))
+				break;
+
+			return PTR_ERR(vma);
+		}
+
+		quirk_add(obj, objects);
+		count++;
+	} while (1);
+	pr_debug("Filled GGTT with %lu pages [%llu total]\n",
+		 count, ggtt->vm.total / PAGE_SIZE);
+
+	if (list_empty(&ggtt->vm.bound_list)) {
+		pr_err("No objects on the GGTT inactive list!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void unpin_ggtt(struct i915_ggtt *ggtt)
+{
+	struct i915_vma *vma;
+
+	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link)
+		if (i915_gem_object_has_tiling_quirk(vma->obj))
+			i915_vma_unpin(vma);
+}
+
+static void cleanup_objects(struct i915_ggtt *ggtt, struct list_head *list)
+{
+	struct drm_i915_gem_object *obj, *on;
+
+	list_for_each_entry_safe(obj, on, list, st_link) {
+		GEM_BUG_ON(!i915_gem_object_has_tiling_quirk(obj));
+		i915_gem_object_set_tiling_quirk(obj);
+		i915_gem_object_put(obj);
+	}
+
+	i915_gem_drain_freed_objects(ggtt->vm.i915);
+}
+
+static int igt_evict_something(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
+	LIST_HEAD(objects);
+	int err;
+
+	/* Fill the GGTT with pinned objects and try to evict one. */
+
+	err = populate_ggtt(ggtt, &objects);
+	if (err)
+		goto cleanup;
+
+	/* Everything is pinned, nothing should happen */
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_evict_something(&ggtt->vm, NULL,
+				       I915_GTT_PAGE_SIZE, 0, 0,
+				       0, U64_MAX,
+				       0);
+	mutex_unlock(&ggtt->vm.mutex);
+	if (err != -ENOSPC) {
+		pr_err("i915_gem_evict_something failed on a full GGTT with err=%d\n",
+		       err);
+		goto cleanup;
+	}
+
+	unpin_ggtt(ggtt);
+
+	/* Everything is unpinned, we should be able to evict something */
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_evict_something(&ggtt->vm, NULL,
+				       I915_GTT_PAGE_SIZE, 0, 0,
+				       0, U64_MAX,
+				       0);
+	mutex_unlock(&ggtt->vm.mutex);
+	if (err) {
+		pr_err("i915_gem_evict_something failed on a full GGTT with err=%d\n",
+		       err);
+		goto cleanup;
+	}
+
+cleanup:
+	cleanup_objects(ggtt, &objects);
+	return err;
+}
+
+static int igt_overcommit(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	LIST_HEAD(objects);
+	int err;
+
+	/* Fill the GGTT with pinned objects and then try to pin one more.
+	 * We expect it to fail.
+	 */
+
+	err = populate_ggtt(ggtt, &objects);
+	if (err)
+		goto cleanup;
+
+	obj = i915_gem_object_create_internal(gt->i915, I915_GTT_PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto cleanup;
+	}
+
+	quirk_add(obj, &objects);
+
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
+	if (vma != ERR_PTR(-ENOSPC)) {
+		pr_err("Failed to evict+insert, i915_gem_object_ggtt_pin returned err=%d\n", (int)PTR_ERR_OR_ZERO(vma));
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+cleanup:
+	cleanup_objects(ggtt, &objects);
+	return err;
+}
+
+static int igt_evict_for_vma(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
+	struct drm_mm_node target = {
+		.start = 0,
+		.size = 4096,
+	};
+	LIST_HEAD(objects);
+	int err;
+
+	/* Fill the GGTT with pinned objects and try to evict a range. */
+
+	err = populate_ggtt(ggtt, &objects);
+	if (err)
+		goto cleanup;
+
+	/* Everything is pinned, nothing should happen */
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_evict_for_node(&ggtt->vm, NULL, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
+	if (err != -ENOSPC) {
+		pr_err("i915_gem_evict_for_node on a full GGTT returned err=%d\n",
+		       err);
+		goto cleanup;
+	}
+
+	unpin_ggtt(ggtt);
+
+	/* Everything is unpinned, we should be able to evict the node */
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_evict_for_node(&ggtt->vm, NULL, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
+	if (err) {
+		pr_err("i915_gem_evict_for_node returned err=%d\n",
+		       err);
+		goto cleanup;
+	}
+
+cleanup:
+	cleanup_objects(ggtt, &objects);
+	return err;
+}
+
+static void mock_color_adjust(const struct drm_mm_node *node,
+			      unsigned long color,
+			      u64 *start,
+			      u64 *end)
+{
+}
+
+static int igt_evict_for_cache_color(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
+	const unsigned long flags = PIN_OFFSET_FIXED;
+	struct drm_mm_node target = {
+		.start = I915_GTT_PAGE_SIZE * 2,
+		.size = I915_GTT_PAGE_SIZE,
+		.color = I915_CACHE_LLC,
+	};
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	LIST_HEAD(objects);
+	int err;
+
+	/*
+	 * Currently the use of color_adjust for the GGTT is limited to cache
+	 * coloring and guard pages, and so the presence of mm.color_adjust for
+	 * the GGTT is assumed to be i915_ggtt_color_adjust, hence using a mock
+	 * color adjust will work just fine for our purposes.
+	 */
+	ggtt->vm.mm.color_adjust = mock_color_adjust;
+	GEM_BUG_ON(!i915_vm_has_cache_coloring(&ggtt->vm));
+
+	obj = i915_gem_object_create_internal(gt->i915, I915_GTT_PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto cleanup;
+	}
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
+	quirk_add(obj, &objects);
+
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+				       I915_GTT_PAGE_SIZE | flags);
+	if (IS_ERR(vma)) {
+		pr_err("[0]i915_gem_object_ggtt_pin failed\n");
+		err = PTR_ERR(vma);
+		goto cleanup;
+	}
+
+	obj = i915_gem_object_create_internal(gt->i915, I915_GTT_PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto cleanup;
+	}
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
+	quirk_add(obj, &objects);
+
+	/* Neighbouring; same colour - should fit */
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+				       (I915_GTT_PAGE_SIZE * 2) | flags);
+	if (IS_ERR(vma)) {
+		pr_err("[1]i915_gem_object_ggtt_pin failed\n");
+		err = PTR_ERR(vma);
+		goto cleanup;
+	}
+
+	i915_vma_unpin(vma);
+
+	/* Remove just the second vma */
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_evict_for_node(&ggtt->vm, NULL, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
+	if (err) {
+		pr_err("[0]i915_gem_evict_for_node returned err=%d\n", err);
+		goto cleanup;
+	}
+
+	/* Attempt to remove the first *pinned* vma, by removing the (empty)
+	 * neighbour -- this should fail.
+	 */
+	target.color = I915_CACHE_L3_LLC;
+
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_evict_for_node(&ggtt->vm, NULL, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
+	if (!err) {
+		pr_err("[1]i915_gem_evict_for_node returned err=%d\n", err);
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	err = 0;
+
+cleanup:
+	unpin_ggtt(ggtt);
+	cleanup_objects(ggtt, &objects);
+	ggtt->vm.mm.color_adjust = NULL;
+	return err;
+}
+
+static int igt_evict_vm(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
+	struct i915_gem_ww_ctx ww;
+	LIST_HEAD(objects);
+	int err;
+
+	/* Fill the GGTT with pinned objects and try to evict everything. */
+
+	err = populate_ggtt(ggtt, &objects);
+	if (err)
+		goto cleanup;
+
+	/* Everything is pinned, nothing should happen */
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_evict_vm(&ggtt->vm, NULL, NULL);
+	mutex_unlock(&ggtt->vm.mutex);
+	if (err) {
+		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
+		       err);
+		goto cleanup;
+	}
+
+	unpin_ggtt(ggtt);
+
+	for_i915_gem_ww(&ww, err, false) {
+		mutex_lock(&ggtt->vm.mutex);
+		err = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
+		mutex_unlock(&ggtt->vm.mutex);
+	}
+
+	if (err) {
+		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
+		       err);
+		goto cleanup;
+	}
+
+cleanup:
+	cleanup_objects(ggtt, &objects);
+	return err;
+}
+
+static int igt_evict_contexts(void *arg)
+{
+	const u64 PRETEND_GGTT_SIZE = 16ull << 20;
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct reserved {
+		struct drm_mm_node node;
+		struct reserved *next;
+	} *reserved = NULL;
+	intel_wakeref_t wakeref;
+	struct drm_mm_node hole;
+	unsigned long count;
+	int err;
+
+	/*
+	 * The purpose of this test is to verify that we will trigger an
+	 * eviction in the GGTT when constructing a request that requires
+	 * additional space in the GGTT for pinning the context. This space
+	 * is not directly tied to the request so reclaiming it requires
+	 * extra work.
+	 *
+	 * As such this test is only meaningful for full-ppgtt environments
+	 * where the GTT space of the request is separate from the GGTT
+	 * allocation required to build the request.
+	 */
+	if (!HAS_FULL_PPGTT(i915))
+		return 0;
+
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+
+	/* Reserve a block so that we know we have enough to fit a few rq */
+	memset(&hole, 0, sizeof(hole));
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_gtt_insert(&ggtt->vm, NULL, &hole,
+				  PRETEND_GGTT_SIZE, 0, I915_COLOR_UNEVICTABLE,
+				  0, ggtt->vm.total,
+				  PIN_NOEVICT);
+	if (err)
+		goto out_locked;
+
+	/* Make the GGTT appear small by filling it with unevictable nodes */
+	count = 0;
+	do {
+		struct reserved *r;
+
+		mutex_unlock(&ggtt->vm.mutex);
+		r = kcalloc(1, sizeof(*r), GFP_KERNEL);
+		mutex_lock(&ggtt->vm.mutex);
+		if (!r) {
+			err = -ENOMEM;
+			goto out_locked;
+		}
+
+		if (i915_gem_gtt_insert(&ggtt->vm, NULL, &r->node,
+					1ul << 20, 0, I915_COLOR_UNEVICTABLE,
+					0, ggtt->vm.total,
+					PIN_NOEVICT)) {
+			kfree(r);
+			break;
+		}
+
+		r->next = reserved;
+		reserved = r;
+
+		count++;
+	} while (1);
+	drm_mm_remove_node(&hole);
+	mutex_unlock(&ggtt->vm.mutex);
+	pr_info("Filled GGTT with %lu 1MiB nodes\n", count);
+
+	/* Overfill the GGTT with context objects and so try to evict one. */
+	for_each_engine(engine, gt, id) {
+		struct i915_sw_fence fence;
+		struct i915_request *last = NULL;
+
+		count = 0;
+		onstack_fence_init(&fence);
+		do {
+			struct intel_context *ce;
+			struct i915_request *rq;
+
+			ce = intel_context_create(engine);
+			if (IS_ERR(ce))
+				break;
+
+			/* We will need some GGTT space for the rq's context */
+			igt_evict_ctl.fail_if_busy = true;
+			rq = intel_context_create_request(ce);
+			igt_evict_ctl.fail_if_busy = false;
+			intel_context_put(ce);
+
+			if (IS_ERR(rq)) {
+				/* When full, fail_if_busy will trigger EBUSY */
+				if (PTR_ERR(rq) != -EBUSY) {
+					pr_err("Unexpected error from request alloc (on %s): %d\n",
+					       engine->name,
+					       (int)PTR_ERR(rq));
+					err = PTR_ERR(rq);
+				}
+				break;
+			}
+
+			/* Keep every request/ctx pinned until we are full */
+			err = i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+							       &fence,
+							       GFP_KERNEL);
+			if (err < 0)
+				break;
+
+			i915_request_add(rq);
+			count++;
+			if (last)
+				i915_request_put(last);
+			last = i915_request_get(rq);
+			err = 0;
+		} while(1);
+		onstack_fence_fini(&fence);
+		pr_info("Submitted %lu contexts/requests on %s\n",
+			count, engine->name);
+		if (err)
+			break;
+		if (last) {
+			if (i915_request_wait(last, 0, HZ) < 0) {
+				err = -EIO;
+				i915_request_put(last);
+				pr_err("Failed waiting for last request (on %s)",
+				       engine->name);
+				break;
+			}
+			i915_request_put(last);
+		}
+		err = intel_gt_wait_for_idle(engine->gt, HZ * 3);
+		if (err) {
+			pr_err("Failed to idle GT (on %s)", engine->name);
+			break;
+		}
+	}
+
+	mutex_lock(&ggtt->vm.mutex);
+out_locked:
+	if (igt_flush_test(i915))
+		err = -EIO;
+	while (reserved) {
+		struct reserved *next = reserved->next;
+
+		drm_mm_remove_node(&reserved->node);
+		kfree(reserved);
+
+		reserved = next;
+	}
+	if (drm_mm_node_allocated(&hole))
+		drm_mm_remove_node(&hole);
+	mutex_unlock(&ggtt->vm.mutex);
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+
+	return err;
+}
+
+int i915_gem_evict_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_evict_something),
+		SUBTEST(igt_evict_for_vma),
+		SUBTEST(igt_evict_for_cache_color),
+		SUBTEST(igt_evict_vm),
+		SUBTEST(igt_overcommit),
+	};
+	struct drm_i915_private *i915;
+	intel_wakeref_t wakeref;
+	int err = 0;
+
+	i915 = mock_gem_device();
+	if (!i915)
+		return -ENOMEM;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		err = i915_subtests(tests, to_gt(i915));
+
+	mock_destroy_device(i915);
+	return err;
+}
+
+int i915_gem_evict_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_evict_contexts),
+	};
+
+	if (intel_gt_is_wedged(to_gt(i915)))
+		return 0;
+
+	return intel_gt_live_subtests(tests, to_gt(i915));
+}