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, 679 insertions, 0 deletions

diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
new file mode 100644
index 000000000..29dc253d0
--- /dev/null
+++ b/kernel/locking/test-ww_mutex.c
@@ -0,0 +1,679 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module-based API test facility for ww_mutexes
+ */
+
+#include <linux/kernel.h>
+
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/ww_mutex.h>
+
+static DEFINE_WD_CLASS(ww_class);
+struct workqueue_struct *wq;
+
+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
+#define ww_acquire_init_noinject(a, b) do { \
+		ww_acquire_init((a), (b)); \
+		(a)->deadlock_inject_countdown = ~0U; \
+	} while (0)
+#else
+#define ww_acquire_init_noinject(a, b) ww_acquire_init((a), (b))
+#endif
+
+struct test_mutex {
+	struct work_struct work;
+	struct ww_mutex mutex;
+	struct completion ready, go, done;
+	unsigned int flags;
+};
+
+#define TEST_MTX_SPIN BIT(0)
+#define TEST_MTX_TRY BIT(1)
+#define TEST_MTX_CTX BIT(2)
+#define __TEST_MTX_LAST BIT(3)
+
+static void test_mutex_work(struct work_struct *work)
+{
+	struct test_mutex *mtx = container_of(work, typeof(*mtx), work);
+
+	complete(&mtx->ready);
+	wait_for_completion(&mtx->go);
+
+	if (mtx->flags & TEST_MTX_TRY) {
+		while (!ww_mutex_trylock(&mtx->mutex, NULL))
+			cond_resched();
+	} else {
+		ww_mutex_lock(&mtx->mutex, NULL);
+	}
+	complete(&mtx->done);
+	ww_mutex_unlock(&mtx->mutex);
+}
+
+static int __test_mutex(unsigned int flags)
+{
+#define TIMEOUT (HZ / 16)
+	struct test_mutex mtx;
+	struct ww_acquire_ctx ctx;
+	int ret;
+
+	ww_mutex_init(&mtx.mutex, &ww_class);
+	ww_acquire_init(&ctx, &ww_class);
+
+	INIT_WORK_ONSTACK(&mtx.work, test_mutex_work);
+	init_completion(&mtx.ready);
+	init_completion(&mtx.go);
+	init_completion(&mtx.done);
+	mtx.flags = flags;
+
+	schedule_work(&mtx.work);
+
+	wait_for_completion(&mtx.ready);
+	ww_mutex_lock(&mtx.mutex, (flags & TEST_MTX_CTX) ? &ctx : NULL);
+	complete(&mtx.go);
+	if (flags & TEST_MTX_SPIN) {
+		unsigned long timeout = jiffies + TIMEOUT;
+
+		ret = 0;
+		do {
+			if (completion_done(&mtx.done)) {
+				ret = -EINVAL;
+				break;
+			}
+			cond_resched();
+		} while (time_before(jiffies, timeout));
+	} else {
+		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
+	}
+	ww_mutex_unlock(&mtx.mutex);
+	ww_acquire_fini(&ctx);
+
+	if (ret) {
+		pr_err("%s(flags=%x): mutual exclusion failure\n",
+		       __func__, flags);
+		ret = -EINVAL;
+	}
+
+	flush_work(&mtx.work);
+	destroy_work_on_stack(&mtx.work);
+	return ret;
+#undef TIMEOUT
+}
+
+static int test_mutex(void)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < __TEST_MTX_LAST; i++) {
+		ret = __test_mutex(i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int test_aa(bool trylock)
+{
+	struct ww_mutex mutex;
+	struct ww_acquire_ctx ctx;
+	int ret;
+	const char *from = trylock ? "trylock" : "lock";
+
+	ww_mutex_init(&mutex, &ww_class);
+	ww_acquire_init(&ctx, &ww_class);
+
+	if (!trylock) {
+		ret = ww_mutex_lock(&mutex, &ctx);
+		if (ret) {
+			pr_err("%s: initial lock failed!\n", __func__);
+			goto out;
+		}
+	} else {
+		ret = !ww_mutex_trylock(&mutex, &ctx);
+		if (ret) {
+			pr_err("%s: initial trylock failed!\n", __func__);
+			goto out;
+		}
+	}
+
+	if (ww_mutex_trylock(&mutex, NULL))  {
+		pr_err("%s: trylocked itself without context from %s!\n", __func__, from);
+		ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (ww_mutex_trylock(&mutex, &ctx))  {
+		pr_err("%s: trylocked itself with context from %s!\n", __func__, from);
+		ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = ww_mutex_lock(&mutex, &ctx);
+	if (ret != -EALREADY) {
+		pr_err("%s: missed deadlock for recursing, ret=%d from %s\n",
+		       __func__, ret, from);
+		if (!ret)
+			ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ww_mutex_unlock(&mutex);
+	ret = 0;
+out:
+	ww_acquire_fini(&ctx);
+	return ret;
+}
+
+struct test_abba {
+	struct work_struct work;
+	struct ww_mutex a_mutex;
+	struct ww_mutex b_mutex;
+	struct completion a_ready;
+	struct completion b_ready;
+	bool resolve, trylock;
+	int result;
+};
+
+static void test_abba_work(struct work_struct *work)
+{
+	struct test_abba *abba = container_of(work, typeof(*abba), work);
+	struct ww_acquire_ctx ctx;
+	int err;
+
+	ww_acquire_init_noinject(&ctx, &ww_class);
+	if (!abba->trylock)
+		ww_mutex_lock(&abba->b_mutex, &ctx);
+	else
+		WARN_ON(!ww_mutex_trylock(&abba->b_mutex, &ctx));
+
+	WARN_ON(READ_ONCE(abba->b_mutex.ctx) != &ctx);
+
+	complete(&abba->b_ready);
+	wait_for_completion(&abba->a_ready);
+
+	err = ww_mutex_lock(&abba->a_mutex, &ctx);
+	if (abba->resolve && err == -EDEADLK) {
+		ww_mutex_unlock(&abba->b_mutex);
+		ww_mutex_lock_slow(&abba->a_mutex, &ctx);
+		err = ww_mutex_lock(&abba->b_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(&abba->a_mutex);
+	ww_mutex_unlock(&abba->b_mutex);
+	ww_acquire_fini(&ctx);
+
+	abba->result = err;
+}
+
+static int test_abba(bool trylock, bool resolve)
+{
+	struct test_abba abba;
+	struct ww_acquire_ctx ctx;
+	int err, ret;
+
+	ww_mutex_init(&abba.a_mutex, &ww_class);
+	ww_mutex_init(&abba.b_mutex, &ww_class);
+	INIT_WORK_ONSTACK(&abba.work, test_abba_work);
+	init_completion(&abba.a_ready);
+	init_completion(&abba.b_ready);
+	abba.trylock = trylock;
+	abba.resolve = resolve;
+
+	schedule_work(&abba.work);
+
+	ww_acquire_init_noinject(&ctx, &ww_class);
+	if (!trylock)
+		ww_mutex_lock(&abba.a_mutex, &ctx);
+	else
+		WARN_ON(!ww_mutex_trylock(&abba.a_mutex, &ctx));
+
+	WARN_ON(READ_ONCE(abba.a_mutex.ctx) != &ctx);
+
+	complete(&abba.a_ready);
+	wait_for_completion(&abba.b_ready);
+
+	err = ww_mutex_lock(&abba.b_mutex, &ctx);
+	if (resolve && err == -EDEADLK) {
+		ww_mutex_unlock(&abba.a_mutex);
+		ww_mutex_lock_slow(&abba.b_mutex, &ctx);
+		err = ww_mutex_lock(&abba.a_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(&abba.b_mutex);
+	ww_mutex_unlock(&abba.a_mutex);
+	ww_acquire_fini(&ctx);
+
+	flush_work(&abba.work);
+	destroy_work_on_stack(&abba.work);
+
+	ret = 0;
+	if (resolve) {
+		if (err || abba.result) {
+			pr_err("%s: failed to resolve ABBA deadlock, A err=%d, B err=%d\n",
+			       __func__, err, abba.result);
+			ret = -EINVAL;
+		}
+	} else {
+		if (err != -EDEADLK && abba.result != -EDEADLK) {
+			pr_err("%s: missed ABBA deadlock, A err=%d, B err=%d\n",
+			       __func__, err, abba.result);
+			ret = -EINVAL;
+		}
+	}
+	return ret;
+}
+
+struct test_cycle {
+	struct work_struct work;
+	struct ww_mutex a_mutex;
+	struct ww_mutex *b_mutex;
+	struct completion *a_signal;
+	struct completion b_signal;
+	int result;
+};
+
+static void test_cycle_work(struct work_struct *work)
+{
+	struct test_cycle *cycle = container_of(work, typeof(*cycle), work);
+	struct ww_acquire_ctx ctx;
+	int err, erra = 0;
+
+	ww_acquire_init_noinject(&ctx, &ww_class);
+	ww_mutex_lock(&cycle->a_mutex, &ctx);
+
+	complete(cycle->a_signal);
+	wait_for_completion(&cycle->b_signal);
+
+	err = ww_mutex_lock(cycle->b_mutex, &ctx);
+	if (err == -EDEADLK) {
+		err = 0;
+		ww_mutex_unlock(&cycle->a_mutex);
+		ww_mutex_lock_slow(cycle->b_mutex, &ctx);
+		erra = ww_mutex_lock(&cycle->a_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(cycle->b_mutex);
+	if (!erra)
+		ww_mutex_unlock(&cycle->a_mutex);
+	ww_acquire_fini(&ctx);
+
+	cycle->result = err ?: erra;
+}
+
+static int __test_cycle(unsigned int nthreads)
+{
+	struct test_cycle *cycles;
+	unsigned int n, last = nthreads - 1;
+	int ret;
+
+	cycles = kmalloc_array(nthreads, sizeof(*cycles), GFP_KERNEL);
+	if (!cycles)
+		return -ENOMEM;
+
+	for (n = 0; n < nthreads; n++) {
+		struct test_cycle *cycle = &cycles[n];
+
+		ww_mutex_init(&cycle->a_mutex, &ww_class);
+		if (n == last)
+			cycle->b_mutex = &cycles[0].a_mutex;
+		else
+			cycle->b_mutex = &cycles[n + 1].a_mutex;
+
+		if (n == 0)
+			cycle->a_signal = &cycles[last].b_signal;
+		else
+			cycle->a_signal = &cycles[n - 1].b_signal;
+		init_completion(&cycle->b_signal);
+
+		INIT_WORK(&cycle->work, test_cycle_work);
+		cycle->result = 0;
+	}
+
+	for (n = 0; n < nthreads; n++)
+		queue_work(wq, &cycles[n].work);
+
+	flush_workqueue(wq);
+
+	ret = 0;
+	for (n = 0; n < nthreads; n++) {
+		struct test_cycle *cycle = &cycles[n];
+
+		if (!cycle->result)
+			continue;
+
+		pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n",
+		       n, nthreads, cycle->result);
+		ret = -EINVAL;
+		break;
+	}
+
+	for (n = 0; n < nthreads; n++)
+		ww_mutex_destroy(&cycles[n].a_mutex);
+	kfree(cycles);
+	return ret;
+}
+
+static int test_cycle(unsigned int ncpus)
+{
+	unsigned int n;
+	int ret;
+
+	for (n = 2; n <= ncpus + 1; n++) {
+		ret = __test_cycle(n);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+struct stress {
+	struct work_struct work;
+	struct ww_mutex *locks;
+	unsigned long timeout;
+	int nlocks;
+};
+
+static int *get_random_order(int count)
+{
+	int *order;
+	int n, r, tmp;
+
+	order = kmalloc_array(count, sizeof(*order), GFP_KERNEL);
+	if (!order)
+		return order;
+
+	for (n = 0; n < count; n++)
+		order[n] = n;
+
+	for (n = count - 1; n > 1; n--) {
+		r = get_random_u32_below(n + 1);
+		if (r != n) {
+			tmp = order[n];
+			order[n] = order[r];
+			order[r] = tmp;
+		}
+	}
+
+	return order;
+}
+
+static void dummy_load(struct stress *stress)
+{
+	usleep_range(1000, 2000);
+}
+
+static void stress_inorder_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	const int nlocks = stress->nlocks;
+	struct ww_mutex *locks = stress->locks;
+	struct ww_acquire_ctx ctx;
+	int *order;
+
+	order = get_random_order(nlocks);
+	if (!order)
+		return;
+
+	do {
+		int contended = -1;
+		int n, err;
+
+		ww_acquire_init(&ctx, &ww_class);
+retry:
+		err = 0;
+		for (n = 0; n < nlocks; n++) {
+			if (n == contended)
+				continue;
+
+			err = ww_mutex_lock(&locks[order[n]], &ctx);
+			if (err < 0)
+				break;
+		}
+		if (!err)
+			dummy_load(stress);
+
+		if (contended > n)
+			ww_mutex_unlock(&locks[order[contended]]);
+		contended = n;
+		while (n--)
+			ww_mutex_unlock(&locks[order[n]]);
+
+		if (err == -EDEADLK) {
+			ww_mutex_lock_slow(&locks[order[contended]], &ctx);
+			goto retry;
+		}
+
+		if (err) {
+			pr_err_once("stress (%s) failed with %d\n",
+				    __func__, err);
+			break;
+		}
+
+		ww_acquire_fini(&ctx);
+	} while (!time_after(jiffies, stress->timeout));
+
+	kfree(order);
+	kfree(stress);
+}
+
+struct reorder_lock {
+	struct list_head link;
+	struct ww_mutex *lock;
+};
+
+static void stress_reorder_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	LIST_HEAD(locks);
+	struct ww_acquire_ctx ctx;
+	struct reorder_lock *ll, *ln;
+	int *order;
+	int n, err;
+
+	order = get_random_order(stress->nlocks);
+	if (!order)
+		return;
+
+	for (n = 0; n < stress->nlocks; n++) {
+		ll = kmalloc(sizeof(*ll), GFP_KERNEL);
+		if (!ll)
+			goto out;
+
+		ll->lock = &stress->locks[order[n]];
+		list_add(&ll->link, &locks);
+	}
+	kfree(order);
+	order = NULL;
+
+	do {
+		ww_acquire_init(&ctx, &ww_class);
+
+		list_for_each_entry(ll, &locks, link) {
+			err = ww_mutex_lock(ll->lock, &ctx);
+			if (!err)
+				continue;
+
+			ln = ll;
+			list_for_each_entry_continue_reverse(ln, &locks, link)
+				ww_mutex_unlock(ln->lock);
+
+			if (err != -EDEADLK) {
+				pr_err_once("stress (%s) failed with %d\n",
+					    __func__, err);
+				break;
+			}
+
+			ww_mutex_lock_slow(ll->lock, &ctx);
+			list_move(&ll->link, &locks); /* restarts iteration */
+		}
+
+		dummy_load(stress);
+		list_for_each_entry(ll, &locks, link)
+			ww_mutex_unlock(ll->lock);
+
+		ww_acquire_fini(&ctx);
+	} while (!time_after(jiffies, stress->timeout));
+
+out:
+	list_for_each_entry_safe(ll, ln, &locks, link)
+		kfree(ll);
+	kfree(order);
+	kfree(stress);
+}
+
+static void stress_one_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	const int nlocks = stress->nlocks;
+	struct ww_mutex *lock = stress->locks + get_random_u32_below(nlocks);
+	int err;
+
+	do {
+		err = ww_mutex_lock(lock, NULL);
+		if (!err) {
+			dummy_load(stress);
+			ww_mutex_unlock(lock);
+		} else {
+			pr_err_once("stress (%s) failed with %d\n",
+				    __func__, err);
+			break;
+		}
+	} while (!time_after(jiffies, stress->timeout));
+
+	kfree(stress);
+}
+
+#define STRESS_INORDER BIT(0)
+#define STRESS_REORDER BIT(1)
+#define STRESS_ONE BIT(2)
+#define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE)
+
+static int stress(int nlocks, int nthreads, unsigned int flags)
+{
+	struct ww_mutex *locks;
+	int n;
+
+	locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL);
+	if (!locks)
+		return -ENOMEM;
+
+	for (n = 0; n < nlocks; n++)
+		ww_mutex_init(&locks[n], &ww_class);
+
+	for (n = 0; nthreads; n++) {
+		struct stress *stress;
+		void (*fn)(struct work_struct *work);
+
+		fn = NULL;
+		switch (n & 3) {
+		case 0:
+			if (flags & STRESS_INORDER)
+				fn = stress_inorder_work;
+			break;
+		case 1:
+			if (flags & STRESS_REORDER)
+				fn = stress_reorder_work;
+			break;
+		case 2:
+			if (flags & STRESS_ONE)
+				fn = stress_one_work;
+			break;
+		}
+
+		if (!fn)
+			continue;
+
+		stress = kmalloc(sizeof(*stress), GFP_KERNEL);
+		if (!stress)
+			break;
+
+		INIT_WORK(&stress->work, fn);
+		stress->locks = locks;
+		stress->nlocks = nlocks;
+		stress->timeout = jiffies + 2*HZ;
+
+		queue_work(wq, &stress->work);
+		nthreads--;
+	}
+
+	flush_workqueue(wq);
+
+	for (n = 0; n < nlocks; n++)
+		ww_mutex_destroy(&locks[n]);
+	kfree(locks);
+
+	return 0;
+}
+
+static int __init test_ww_mutex_init(void)
+{
+	int ncpus = num_online_cpus();
+	int ret, i;
+
+	printk(KERN_INFO "Beginning ww mutex selftests\n");
+
+	wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0);
+	if (!wq)
+		return -ENOMEM;
+
+	ret = test_mutex();
+	if (ret)
+		return ret;
+
+	ret = test_aa(false);
+	if (ret)
+		return ret;
+
+	ret = test_aa(true);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 4; i++) {
+		ret = test_abba(i & 1, i & 2);
+		if (ret)
+			return ret;
+	}
+
+	ret = test_cycle(ncpus);
+	if (ret)
+		return ret;
+
+	ret = stress(16, 2*ncpus, STRESS_INORDER);
+	if (ret)
+		return ret;
+
+	ret = stress(16, 2*ncpus, STRESS_REORDER);
+	if (ret)
+		return ret;
+
+	ret = stress(4095, hweight32(STRESS_ALL)*ncpus, STRESS_ALL);
+	if (ret)
+		return ret;
+
+	printk(KERN_INFO "All ww mutex selftests passed\n");
+	return 0;
+}
+
+static void __exit test_ww_mutex_exit(void)
+{
+	destroy_workqueue(wq);
+}
+
+module_init(test_ww_mutex_init);
+module_exit(test_ww_mutex_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Intel Corporation");