Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextHEADmaster

Pull networking updates from Jakub Kicinski:
 "Not much excitement - a handful of large patchsets (devmem among them)
  did not make it in time.

  Core & protocols:

   - Use local_lock in addition to local_bh_disable() to protect per-CPU
     resources in networking, a step closer for local_bh_disable() not
     to act as a big lock on PREEMPT_RT

   - Use flex array for netdevice priv area, ensure its cache alignment

   - Add a sysctl knob to allow user to specify a default rto_min at
     socket init time. Bit of a big hammer but multiple companies were
     independently carrying such patch downstream so clearly it's useful

   - Support scheduling transmission of packets based on CLOCK_TAI

   - Un-pin TCP TIMEWAIT timer to avoid it firing on CPUs later cordoned
     off using cpusets

   - Support multiple L2TPv3 UDP tunnels using the same 5-tuple address

   - Allow configuration of multipath hash seed, to both allow
     synchronizing hashing of two routers, and preventing partial
     accidental sync

   - Improve TCP compliance with RFC 9293 for simultaneous connect()

   - Support sending NAT keepalives in IPsec ESP in UDP states.
     Userspace IKE daemon had to do this before, but the kernel can
     better keep track of it

   - Support sending supervision HSR frames with MAC addresses stored in
     ProxyNodeTable when RedBox (i.e. HSR-SAN) is enabled

   - Introduce IPPROTO_SMC for selecting SMC when socket is created

   - Allow UDP GSO transmit from devices with no checksum offload

   - openvswitch: add packet sampling via psample, separating the
     sampled traffic from "upcall" packets sent to user space for
     forwarding

   - nf_tables: shrink memory consumption for transaction objects

  Things we sprinkled into general kernel code:

   - Power Sequencing subsystem (used by Qualcomm Bluetooth driver for
     QCA6390)           [ Already merged separately - Linus ]

   - Add IRQ information in sysfs for auxiliary bus

   - Introduce guard definition for local_lock

   - Add aligned flavor of __cacheline_group_{begin, end}() markings for
     grouping fields in structures

  BPF:

   - Notify user space (via epoll) when a struct_ops object is getting
     detached/unregistered

   - Add new kfuncs for a generic, open-coded bits iterator

   - Enable BPF programs to declare arrays of kptr, bpf_rb_root, and
     bpf_list_head

   - Support resilient split BTF which cuts down on duplication and
     makes BTF as compact as possible WRT BTF from modules

   - Add support for dumping kfunc prototypes from BTF which enables
     both detecting as well as dumping compilable prototypes for kfuncs

   - riscv64 BPF JIT improvements in particular to add 12-argument
     support for BPF trampolines and to utilize bpf_prog_pack for the
     latter

   - Add the capability to offload the netfilter flowtable in XDP layer
     through kfuncs

  Driver API:

   - Allow users to configure IRQ tresholds between which automatic IRQ
     moderation can choose

   - Expand Power Sourcing (PoE) status with power, class and failure
     reason. Support setting power limits

   - Track additional RSS contexts in the core, make sure configuration
     changes don't break them

   - Support IPsec crypto offload for IPv6 ESP and IPv4 UDP-encapsulated
     ESP data paths

   - Support updating firmware on SFP modules

  Tests and tooling:

   - mptcp: use net/lib.sh to manage netns

   - TCP-AO and TCP-MD5: replace debug prints used by tests with
     tracepoints

   - openvswitch: make test self-contained (don't depend on OvS CLI
     tools)

  Drivers:

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - increase the max total outstanding PTP TX packets to 4
         - add timestamping statistics support
         - implement netdev_queue_mgmt_ops
         - support new RSS context API
      - Intel (100G, ice, idpf):
         - implement FEC statistics and dumping signal quality indicators
         - support E825C products (with 56Gbps PHYs)
      - nVidia/Mellanox:
         - support HW-GRO
         - mlx4/mlx5: support per-queue statistics via netlink
         - obey the max number of EQs setting in sub-functions
      - AMD/Solarflare:
         - support new RSS context API
      - AMD/Pensando:
         - ionic: rework fix for doorbell miss to lower overhead and
           skip it on new HW
      - Wangxun:
         - txgbe: support Flow Director perfect filters

   - Ethernet NICs consumer, embedded and virtual:
      - Add driver for Tehuti Networks TN40xx chips
      - Add driver for Meta's internal NIC chips
      - Add driver for Ethernet MAC on Airoha EN7581 SoCs
      - Add driver for Renesas Ethernet-TSN devices
      - Google cloud vNIC:
         - flow steering support
      - Microsoft vNIC:
         - support page sizes other than 4KB on ARM64
      - vmware vNIC:
         - support latency measurement (update to version 9)
      - VirtIO net:
         - support for Byte Queue Limits
         - support configuring thresholds for automatic IRQ moderation
         - support for AF_XDP Rx zero-copy
      - Synopsys (stmmac):
         - support for STM32MP13 SoC
         - let platforms select the right PCS implementation
      - TI:
         - icssg-prueth: add multicast filtering support
         - icssg-prueth: enable PTP timestamping and PPS
      - Renesas:
         - ravb: improve Rx performance 30-400% by using page pool,
           theaded NAPI and timer-based IRQ coalescing
         - ravb: add MII support for R-Car V4M
      - Cadence (macb):
         - macb: add ARP support to Wake-On-LAN
      - Cortina:
         - use phylib for RX and TX pause configuration

   - Ethernet switches:
      - nVidia/Mellanox:
         - support configuration of multipath hash seed
         - report more accurate max MTU
         - use page_pool to improve Rx performance
      - MediaTek:
         - mt7530: add support for bridge port isolation
      - Qualcomm:
         - qca8k: add support for bridge port isolation
      - Microchip:
         - lan9371/2: add 100BaseTX PHY support
      - NXP:
         - vsc73xx: implement VLAN operations

   - Ethernet PHYs:
      - aquantia: enable support for aqr115c
      - aquantia: add support for PHY LEDs
      - realtek: add support for rtl8224 2.5Gbps PHY
      - xpcs: add memory-mapped device support
      - add BroadR-Reach link mode and support in Broadcom's PHY driver

   - CAN:
      - add document for ISO 15765-2 protocol support
      - mcp251xfd: workaround for erratum DS80000789E, use timestamps to
        catch when device returns incorrect FIFO status

   - WiFi:
      - mac80211/cfg80211:
         - parse Transmit Power Envelope (TPE) data in mac80211 instead
           of in drivers
         - improvements for 6 GHz regulatory flexibility
         - multi-link improvements
         - support multiple radios per wiphy
         - remove DEAUTH_NEED_MGD_TX_PREP flag
      - Intel (iwlwifi):
         - bump FW API to 91 for BZ/SC devices
         - report 64-bit radiotap timestamp
         - enable P2P low latency by default
         - handle Transmit Power Envelope (TPE) advertised by AP
         - remove support for older FW for new devices
         - fast resume (keeping the device configured)
         - mvm: re-enable Multi-Link Operation (MLO)
         - aggregation (A-MSDU) optimizations
      - MediaTek (mt76):
         - mt7925 Multi-Link Operation (MLO) support
      - Qualcomm (ath10k):
         - LED support for various chipsets
      - Qualcomm (ath12k):
         - remove unsupported Tx monitor handling
         - support channel 2 in 6 GHz band
         - support Spatial Multiplexing Power Save (SMPS) in 6 GHz band
         - supprt multiple BSSID (MBSSID) and Enhanced Multi-BSSID
           Advertisements (EMA)
         - support dynamic VLAN
         - add panic handler for resetting the firmware state
         - DebugFS support for datapath statistics
         - WCN7850: support for Wake on WLAN
      - Microchip (wilc1000):
         - read MAC address during probe to make it visible to user space
         - suspend/resume improvements
      - TI (wl18xx):
         - support newer firmware versions
      - RealTek (rtw89):
         - preparation for RTL8852BE-VT support
         - Wake on WLAN support for WiFi 6 chips
         - 36-bit PCI DMA support
      - RealTek (rtlwifi):
         - RTL8192DU support
      - Broadcom (brcmfmac):
         - Management Frame Protection support (to enable WPA3)

   - Bluetooth:
      - qualcomm: use the power sequencer for QCA6390
      - btusb: mediatek: add ISO data transmission functions
      - hci_bcm4377: add BCM4388 support
      - btintel: add support for BlazarU core
      - btintel: add support for Whale Peak2
      - btnxpuart: add support for AW693 A1 chipset
      - btnxpuart: add support for IW615 chipset
      - btusb: add Realtek RTL8852BE support ID 0x13d3:0x3591"

* tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1589 commits)
  eth: fbnic: Fix spelling mistake "tiggerring" -> "triggering"
  tcp: Replace strncpy() with strscpy()
  wifi: ath12k: fix build vs old compiler
  tcp: Don't access uninit tcp_rsk(req)->ao_keyid in tcp_create_openreq_child().
  eth: fbnic: Write the TCAM tables used for RSS control and Rx to host
  eth: fbnic: Add L2 address programming
  eth: fbnic: Add basic Rx handling
  eth: fbnic: Add basic Tx handling
  eth: fbnic: Add link detection
  eth: fbnic: Add initial messaging to notify FW of our presence
  eth: fbnic: Implement Rx queue alloc/start/stop/free
  eth: fbnic: Implement Tx queue alloc/start/stop/free
  eth: fbnic: Allocate a netdevice and napi vectors with queues
  eth: fbnic: Add FW communication mechanism
  eth: fbnic: Add message parsing for FW messages
  eth: fbnic: Add register init to set PCIe/Ethernet device config
  eth: fbnic: Allocate core device specific structures and devlink interface
  eth: fbnic: Add scaffolding for Meta's NIC driver
  PCI: Add Meta Platforms vendor ID
  net/sched: cls_flower: propagate tca[TCA_OPTIONS] to NL_REQ_ATTR_CHECK
  ...

7 files changed, 649 insertions, 74 deletions

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 4933d045ab66..c9f2f48fc30f 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -11,6 +11,7 @@ TEST_PROGS = \
 	hw_stats_l3_gre.sh \
 	loopback.sh \
 	pp_alloc_fail.py \
+	rss_ctx.py \
 	#
 
 TEST_FILES := \
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
new file mode 100755
index 000000000000..931dbc36ca43
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -0,0 +1,522 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import datetime
+import random
+from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ge, ksft_lt
+from lib.py import NetDrvEpEnv
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import KsftSkipEx
+from lib.py import rand_port
+from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure
+
+
+def _rss_key_str(key):
+    return ":".join(["{:02x}".format(x) for x in key])
+
+
+def _rss_key_rand(length):
+    return [random.randint(0, 255) for _ in range(length)]
+
+
+def get_rss(cfg, context=0):
+    return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0]
+
+
+def get_drop_err_sum(cfg):
+    stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0]
+    cnt = 0
+    for key in ['errors', 'dropped', 'over_errors', 'fifo_errors',
+                'length_errors', 'crc_errors', 'missed_errors',
+                'frame_errors']:
+        cnt += stats["stats64"]["rx"][key]
+    return cnt, stats["stats64"]["tx"]["carrier_changes"]
+
+
+def ethtool_create(cfg, act, opts):
+    output = ethtool(f"{act} {cfg.ifname} {opts}").stdout
+    # Output will be something like: "New RSS context is 1" or
+    # "Added rule with ID 7", we want the integer from the end
+    return int(output.split()[-1])
+
+
+def require_ntuple(cfg):
+    features = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    if not features["ntuple-filters"]["active"]:
+        # ntuple is more of a capability than a config knob, don't bother
+        # trying to enable it (until some driver actually needs it).
+        raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"]))
+
+
+# Get Rx packet counts for all queues, as a simple list of integers
+# if @prev is specified the prev counts will be subtracted
+def _get_rx_cnts(cfg, prev=None):
+    cfg.wait_hw_stats_settle()
+    data = cfg.netdevnl.qstats_get({"ifindex": cfg.ifindex, "scope": ["queue"]}, dump=True)
+    data = [x for x in data if x['queue-type'] == "rx"]
+    max_q = max([x["queue-id"] for x in data])
+    queue_stats = [0] * (max_q + 1)
+    for q in data:
+        queue_stats[q["queue-id"]] = q["rx-packets"]
+        if prev and q["queue-id"] < len(prev):
+            queue_stats[q["queue-id"]] -= prev[q["queue-id"]]
+    return queue_stats
+
+
+def _send_traffic_check(cfg, port, name, params):
+    # params is a dict with 3 possible keys:
+    #  - "target": required, which queues we expect to get iperf traffic
+    #  - "empty": optional, which queues should see no traffic at all
+    #  - "noise": optional, which queues we expect to see low traffic;
+    #             used for queues of the main context, since some background
+    #             OS activity may use those queues while we're testing
+    # the value for each is a list, or some other iterable containing queue ids.
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    directed = sum(cnts[i] for i in params['target'])
+
+    ksft_ge(directed, 20000, f"traffic on {name}: " + str(cnts))
+    if params.get('noise'):
+        ksft_lt(sum(cnts[i] for i in params['noise']), directed / 2,
+                "traffic on other queues:" + str(cnts))
+    if params.get('empty'):
+        ksft_eq(sum(cnts[i] for i in params['empty']), 0,
+                "traffic on inactive queues: " + str(cnts))
+
+
+def test_rss_key_indir(cfg):
+    """Test basics like updating the main RSS key and indirection table."""
+
+    if len(_get_rx_cnts(cfg)) < 2:
+        KsftSkipEx("Device has only one queue (or doesn't support queue stats)")
+
+    data = get_rss(cfg)
+    want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table']
+    for k in want_keys:
+        if k not in data:
+            raise KsftFailEx("ethtool results missing key: " + k)
+        if not data[k]:
+            raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}")
+
+    key_len = len(data['rss-hash-key'])
+
+    # Set the key
+    key = _rss_key_rand(key_len)
+    ethtool(f"-X {cfg.ifname} hkey " + _rss_key_str(key))
+
+    data = get_rss(cfg)
+    ksft_eq(key, data['rss-hash-key'])
+
+    # Set the indirection table
+    ethtool(f"-X {cfg.ifname} equal 2")
+    reset_indir = defer(ethtool, f"-X {cfg.ifname} default")
+    data = get_rss(cfg)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(1, max(data['rss-indirection-table']))
+
+    # Check we only get traffic on the first 2 queues
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+    # 2 queues, 20k packets, must be at least 5k per queue
+    ksft_ge(cnts[0], 5000, "traffic on main context (1/2): " + str(cnts))
+    ksft_ge(cnts[1], 5000, "traffic on main context (2/2): " + str(cnts))
+    # The other queues should be unused
+    ksft_eq(sum(cnts[2:]), 0, "traffic on unused queues: " + str(cnts))
+
+    # Restore, and check traffic gets spread again
+    reset_indir.exec()
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+    # First two queues get less traffic than all the rest
+    ksft_lt(sum(cnts[:2]), sum(cnts[2:]), "traffic distributed: " + str(cnts))
+
+
+def test_rss_queue_reconfigure(cfg, main_ctx=True):
+    """Make sure queue changes can't override requested RSS config.
+
+    By default main RSS table should change to include all queues.
+    When user sets a specific RSS config the driver should preserve it,
+    even when queue count changes. Driver should refuse to deactivate
+    queues used in the user-set RSS config.
+    """
+
+    if not main_ctx:
+        require_ntuple(cfg)
+
+    # Start with 4 queues, an arbitrary known number.
+    try:
+        qcnt = len(_get_rx_cnts(cfg))
+        ethtool(f"-L {cfg.ifname} combined 4")
+        defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+    except:
+        raise KsftSkipEx("Not enough queues for the test or qstat not supported")
+
+    if main_ctx:
+        ctx_id = 0
+        ctx_ref = ""
+    else:
+        ctx_id = ethtool_create(cfg, "-X", "context new")
+        ctx_ref = f"context {ctx_id}"
+        defer(ethtool, f"-X {cfg.ifname} {ctx_ref} delete")
+
+    # Indirection table should be distributing to all queues.
+    data = get_rss(cfg, context=ctx_id)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(3, max(data['rss-indirection-table']))
+
+    # Increase queues, indirection table should be distributing to all queues.
+    # It's unclear whether tables of additional contexts should be reset, too.
+    if main_ctx:
+        ethtool(f"-L {cfg.ifname} combined 5")
+        data = get_rss(cfg)
+        ksft_eq(0, min(data['rss-indirection-table']))
+        ksft_eq(4, max(data['rss-indirection-table']))
+        ethtool(f"-L {cfg.ifname} combined 4")
+
+    # Configure the table explicitly
+    port = rand_port()
+    ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 0 1")
+    if main_ctx:
+        other_key = 'empty'
+        defer(ethtool, f"-X {cfg.ifname} default")
+    else:
+        other_key = 'noise'
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}"
+        ntuple = ethtool_create(cfg, "-N", flow)
+        defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
+
+    _send_traffic_check(cfg, port, ctx_ref, { 'target': (0, 3),
+                                              other_key: (1, 2) })
+
+    # We should be able to increase queues, but table should be left untouched
+    ethtool(f"-L {cfg.ifname} combined 5")
+    data = get_rss(cfg, context=ctx_id)
+    ksft_eq({0, 3}, set(data['rss-indirection-table']))
+
+    _send_traffic_check(cfg, port, ctx_ref, { 'target': (0, 3),
+                                              other_key: (1, 2, 4) })
+
+    # Setting queue count to 3 should fail, queue 3 is used
+    try:
+        ethtool(f"-L {cfg.ifname} combined 3")
+    except CmdExitFailure:
+        pass
+    else:
+        raise Exception(f"Driver didn't prevent us from deactivating a used queue (context {ctx_id})")
+
+
+def test_rss_resize(cfg):
+    """Test resizing of the RSS table.
+
+    Some devices dynamically increase and decrease the size of the RSS
+    indirection table based on the number of enabled queues.
+    When that happens driver must maintain the balance of entries
+    (preferably duplicating the smaller table).
+    """
+
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels['combined-max']
+    qcnt = channels['combined-count']
+
+    if ch_max < 2:
+        raise KsftSkipEx(f"Not enough queues for the test: {ch_max}")
+
+    ethtool(f"-L {cfg.ifname} combined 2")
+    defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+
+    ethtool(f"-X {cfg.ifname} weight 1 7")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    ethtool(f"-L {cfg.ifname} combined {ch_max}")
+    data = get_rss(cfg)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(1, max(data['rss-indirection-table']))
+
+    ksft_eq(7,
+            data['rss-indirection-table'].count(1) /
+            data['rss-indirection-table'].count(0),
+            f"Table imbalance after resize: {data['rss-indirection-table']}")
+
+
+def test_hitless_key_update(cfg):
+    """Test that flows may be rehashed without impacting traffic.
+
+    Some workloads may want to rehash the flows in response to an imbalance.
+    Most effective way to do that is changing the RSS key. Check that changing
+    the key does not cause link flaps or traffic disruption.
+
+    Disrupting traffic for key update is not a bug, but makes the key
+    update unusable for rehashing under load.
+    """
+    data = get_rss(cfg)
+    key_len = len(data['rss-hash-key'])
+
+    key = _rss_key_rand(key_len)
+
+    tgen = GenerateTraffic(cfg)
+    try:
+        errors0, carrier0 = get_drop_err_sum(cfg)
+        t0 = datetime.datetime.now()
+        ethtool(f"-X {cfg.ifname} hkey " + _rss_key_str(key))
+        t1 = datetime.datetime.now()
+        errors1, carrier1 = get_drop_err_sum(cfg)
+    finally:
+        tgen.wait_pkts_and_stop(5000)
+
+    ksft_lt((t1 - t0).total_seconds(), 0.2)
+    ksft_eq(errors1 - errors1, 0)
+    ksft_eq(carrier1 - carrier0, 0)
+
+
+def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
+    """
+    Test separating traffic into RSS contexts.
+    The queues will be allocated 2 for each context:
+     ctx0  ctx1  ctx2  ctx3
+    [0 1] [2 3] [4 5] [6 7] ...
+    """
+
+    require_ntuple(cfg)
+
+    requested_ctx_cnt = ctx_cnt
+
+    # Try to allocate more queues when necessary
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 2 + 2 * ctx_cnt:
+        try:
+            ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}")
+            ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}")
+            defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    ports = []
+
+    # Use queues 0 and 1 for normal traffic
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    for i in range(ctx_cnt):
+        want_cfg = f"start {2 + i * 2} equal 2"
+        create_cfg = want_cfg if create_with_cfg else ""
+
+        try:
+            ctx_id = ethtool_create(cfg, "-X", f"context new {create_cfg}")
+            defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+        except CmdExitFailure:
+            # try to carry on and skip at the end
+            if i == 0:
+                raise
+            ksft_pr(f"Failed to create context {i + 1}, trying to test what we got")
+            ctx_cnt = i
+            break
+
+        if not create_with_cfg:
+            ethtool(f"-X {cfg.ifname} context {ctx_id} {want_cfg}")
+
+        # Sanity check the context we just created
+        data = get_rss(cfg, ctx_id)
+        ksft_eq(min(data['rss-indirection-table']), 2 + i * 2, "Unexpected context cfg: " + str(data))
+        ksft_eq(max(data['rss-indirection-table']), 2 + i * 2 + 1, "Unexpected context cfg: " + str(data))
+
+        ports.append(rand_port())
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id}"
+        ntuple = ethtool_create(cfg, "-N", flow)
+        defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
+
+    for i in range(ctx_cnt):
+        _send_traffic_check(cfg, ports[i], f"context {i}",
+                            { 'target': (2+i*2, 3+i*2),
+                              'noise': (0, 1),
+                              'empty': list(range(2, 2+i*2)) + list(range(4+i*2, 2+2*ctx_cnt)) })
+
+    if requested_ctx_cnt != ctx_cnt:
+        raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}")
+
+
+def test_rss_context4(cfg):
+    test_rss_context(cfg, 4)
+
+
+def test_rss_context32(cfg):
+    test_rss_context(cfg, 32)
+
+
+def test_rss_context4_create_with_cfg(cfg):
+    test_rss_context(cfg, 4, create_with_cfg=True)
+
+
+def test_rss_context_queue_reconfigure(cfg):
+    test_rss_queue_reconfigure(cfg, main_ctx=False)
+
+
+def test_rss_context_out_of_order(cfg, ctx_cnt=4):
+    """
+    Test separating traffic into RSS contexts.
+    Contexts are removed in semi-random order, and steering re-tested
+    to make sure removal doesn't break steering to surviving contexts.
+    Test requires 3 contexts to work.
+    """
+
+    require_ntuple(cfg)
+
+    requested_ctx_cnt = ctx_cnt
+
+    # Try to allocate more queues when necessary
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 2 + 2 * ctx_cnt:
+        try:
+            ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}")
+            ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}")
+            defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    ntuple = []
+    ctx = []
+    ports = []
+
+    def remove_ctx(idx):
+        ntuple[idx].exec()
+        ntuple[idx] = None
+        ctx[idx].exec()
+        ctx[idx] = None
+
+    def check_traffic():
+        for i in range(ctx_cnt):
+            if ctx[i]:
+                expected = {
+                    'target': (2+i*2, 3+i*2),
+                    'noise': (0, 1),
+                    'empty': list(range(2, 2+i*2)) + list(range(4+i*2, 2+2*ctx_cnt))
+                }
+            else:
+                expected = {
+                    'target': (0, 1),
+                    'empty':  range(2, 2+2*ctx_cnt)
+                }
+
+            _send_traffic_check(cfg, ports[i], f"context {i}", expected)
+
+    # Use queues 0 and 1 for normal traffic
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    for i in range(ctx_cnt):
+        ctx_id = ethtool_create(cfg, "-X", f"context new start {2 + i * 2} equal 2")
+        ctx.append(defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete"))
+
+        ports.append(rand_port())
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id}"
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+        ntuple.append(defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}"))
+
+    check_traffic()
+
+    # Remove middle context
+    remove_ctx(ctx_cnt // 2)
+    check_traffic()
+
+    # Remove first context
+    remove_ctx(0)
+    check_traffic()
+
+    # Remove last context
+    remove_ctx(-1)
+    check_traffic()
+
+    if requested_ctx_cnt != ctx_cnt:
+        raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}")
+
+
+def test_rss_context_overlap(cfg, other_ctx=0):
+    """
+    Test contexts overlapping with each other.
+    Use 4 queues for the main context, but only queues 2 and 3 for context 1.
+    """
+
+    require_ntuple(cfg)
+
+    queue_cnt = len(_get_rx_cnts(cfg))
+    if queue_cnt < 4:
+        try:
+            ksft_pr(f"Increasing queue count {queue_cnt} -> 4")
+            ethtool(f"-L {cfg.ifname} combined 4")
+            defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    if other_ctx == 0:
+        ethtool(f"-X {cfg.ifname} equal 4")
+        defer(ethtool, f"-X {cfg.ifname} default")
+    else:
+        other_ctx = ethtool_create(cfg, "-X", "context new")
+        ethtool(f"-X {cfg.ifname} context {other_ctx} equal 4")
+        defer(ethtool, f"-X {cfg.ifname} context {other_ctx} delete")
+
+    ctx_id = ethtool_create(cfg, "-X", "context new")
+    ethtool(f"-X {cfg.ifname} context {ctx_id} start 2 equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    port = rand_port()
+    if other_ctx:
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {other_ctx}"
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+        ntuple = defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    # Test the main context
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    ksft_ge(sum(cnts[ :4]), 20000, "traffic on main context: " + str(cnts))
+    ksft_ge(sum(cnts[ :2]),  7000, "traffic on main context (1/2): " + str(cnts))
+    ksft_ge(sum(cnts[2:4]),  7000, "traffic on main context (2/2): " + str(cnts))
+    if other_ctx == 0:
+        ksft_eq(sum(cnts[4: ]),     0, "traffic on other queues: " + str(cnts))
+
+    # Now create a rule for context 1 and make sure traffic goes to a subset
+    if other_ctx:
+        ntuple.exec()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}"
+    ntuple_id = ethtool_create(cfg, "-N", flow)
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    directed = sum(cnts[2:4])
+    ksft_lt(sum(cnts[ :2]), directed / 2, "traffic on main context: " + str(cnts))
+    ksft_ge(directed, 20000, "traffic on extra context: " + str(cnts))
+    if other_ctx == 0:
+        ksft_eq(sum(cnts[4: ]),     0, "traffic on other queues: " + str(cnts))
+
+
+def test_rss_context_overlap2(cfg):
+    test_rss_context_overlap(cfg, True)
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netdevnl = NetdevFamily()
+
+        ksft_run([test_rss_key_indir, test_rss_queue_reconfigure,
+                  test_rss_resize, test_hitless_key_update,
+                  test_rss_context, test_rss_context4, test_rss_context32,
+                  test_rss_context_queue_reconfigure,
+                  test_rss_context_overlap, test_rss_context_overlap2,
+                  test_rss_context_out_of_order, test_rss_context4_create_with_cfg],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index edcedd7bffab..a5e800b8f103 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -1,9 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 
 import os
+import time
 from pathlib import Path
 from lib.py import KsftSkipEx, KsftXfailEx
-from lib.py import cmd, ip
+from lib.py import cmd, ethtool, ip
 from lib.py import NetNS, NetdevSimDev
 from .remote import Remote
 
@@ -82,6 +83,8 @@ class NetDrvEpEnv:
 
         self.env = _load_env_file(src_path)
 
+        self._stats_settle_time = None
+
         # Things we try to destroy
         self.remote = None
         # These are for local testing state
@@ -222,3 +225,17 @@ class NetDrvEpEnv:
         if remote:
             if not self._require_cmd(comm, "remote"):
                 raise KsftSkipEx("Test requires (remote) command: " + comm)
+
+    def wait_hw_stats_settle(self):
+        """
+        Wait for HW stats to become consistent, some devices DMA HW stats
+        periodically so events won't be reflected until next sync.
+        Good drivers will tell us via ethtool what their sync period is.
+        """
+        if self._stats_settle_time is None:
+            data = ethtool("-c " + self.ifname, json=True)[0]
+
+            self._stats_settle_time = 0.025 + \
+                data.get('stats-block-usecs', 0) / 1000 / 1000
+
+        time.sleep(self._stats_settle_time)
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
index abdb677bdb1c..d9c10613ae67 100644
--- a/tools/testing/selftests/drivers/net/lib/py/load.py
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -5,28 +5,45 @@ import time
 from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen
 
 class GenerateTraffic:
-    def __init__(self, env):
+    def __init__(self, env, port=None):
         env.require_cmd("iperf3", remote=True)
 
         self.env = env
 
-        port = rand_port()
-        self._iperf_server = cmd(f"iperf3 -s -p {port}", background=True)
+        if port is None:
+            port = rand_port()
+        self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True)
         wait_port_listen(port)
         time.sleep(0.1)
         self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400",
                                  background=True, host=env.remote)
 
         # Wait for traffic to ramp up
-        pkt = ip("-s link show dev " + env.ifname, json=True)[0]["stats64"]["rx"]["packets"]
+        if not self._wait_pkts(pps=1000):
+            self.stop(verbose=True)
+            raise Exception("iperf3 traffic did not ramp up")
+
+    def _wait_pkts(self, pkt_cnt=None, pps=None):
+        """
+        Wait until we've seen pkt_cnt or until traffic ramps up to pps.
+        Only one of pkt_cnt or pss can be specified.
+        """
+        pkt_start = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"]
         for _ in range(50):
             time.sleep(0.1)
-            now = ip("-s link show dev " + env.ifname, json=True)[0]["stats64"]["rx"]["packets"]
-            if now - pkt > 1000:
-                return
-            pkt = now
-        self.stop(verbose=True)
-        raise Exception("iperf3 traffic did not ramp up")
+            pkt_now = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"]
+            if pps:
+                if pkt_now - pkt_start > pps / 10:
+                    return True
+                pkt_start = pkt_now
+            elif pkt_cnt:
+                if pkt_now - pkt_start > pkt_cnt:
+                    return True
+        return False
+
+    def wait_pkts_and_stop(self, pkt_cnt):
+        failed = not self._wait_pkts(pkt_cnt=pkt_cnt)
+        self.stop(verbose=failed)
 
     def stop(self, verbose=None):
         self._iperf_client.process(terminate=True)
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
index 76f1ab4898d9..e1ad623146d7 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
@@ -15,6 +15,13 @@ source $lib_dir/mirror_lib.sh
 source $lib_dir/mirror_gre_lib.sh
 source $lib_dir/mirror_gre_topo_lib.sh
 
+ALL_TESTS="
+	test_keyful
+	test_soft
+	test_tos_fixed
+	test_ttl_inherit
+"
+
 setup_keyful()
 {
 	tunnel_create gt6-key ip6gretap 2001:db8:3::1 2001:db8:3::2 \
@@ -118,15 +125,15 @@ test_span_gre_ttl_inherit()
 	RET=0
 
 	ip link set dev $tundev type $type ttl inherit
-	mirror_install $swp1 ingress $tundev "matchall $tcflags"
-	fail_test_span_gre_dir $tundev ingress
+	mirror_install $swp1 ingress $tundev "matchall"
+	fail_test_span_gre_dir $tundev
 
 	ip link set dev $tundev type $type ttl 100
 
-	quick_test_span_gre_dir $tundev ingress
+	quick_test_span_gre_dir $tundev
 	mirror_uninstall $swp1 ingress
 
-	log_test "$what: no offload on TTL of inherit ($tcflags)"
+	log_test "$what: no offload on TTL of inherit"
 }
 
 test_span_gre_tos_fixed()
@@ -138,61 +145,49 @@ test_span_gre_tos_fixed()
 	RET=0
 
 	ip link set dev $tundev type $type tos 0x10
-	mirror_install $swp1 ingress $tundev "matchall $tcflags"
-	fail_test_span_gre_dir $tundev ingress
+	mirror_install $swp1 ingress $tundev "matchall"
+	fail_test_span_gre_dir $tundev
 
 	ip link set dev $tundev type $type tos inherit
-	quick_test_span_gre_dir $tundev ingress
+	quick_test_span_gre_dir $tundev
 	mirror_uninstall $swp1 ingress
 
-	log_test "$what: no offload on a fixed TOS ($tcflags)"
+	log_test "$what: no offload on a fixed TOS"
 }
 
 test_span_failable()
 {
-	local should_fail=$1; shift
 	local tundev=$1; shift
 	local what=$1; shift
 
 	RET=0
 
-	mirror_install $swp1 ingress $tundev "matchall $tcflags"
-	if ((should_fail)); then
-	    fail_test_span_gre_dir  $tundev ingress
-	else
-	    quick_test_span_gre_dir $tundev ingress
-	fi
+	mirror_install $swp1 ingress $tundev "matchall"
+	fail_test_span_gre_dir  $tundev
 	mirror_uninstall $swp1 ingress
 
-	log_test "$what: should_fail=$should_fail ($tcflags)"
+	log_test "fail $what"
 }
 
-test_failable()
+test_keyful()
 {
-	local should_fail=$1; shift
-
-	test_span_failable $should_fail gt6-key "mirror to keyful gretap"
-	test_span_failable $should_fail gt6-soft "mirror to gretap w/ soft underlay"
+	test_span_failable gt6-key "mirror to keyful gretap"
 }
 
-test_sw()
+test_soft()
 {
-	slow_path_trap_install $swp1 ingress
-	slow_path_trap_install $swp1 egress
-
-	test_failable 0
-
-	slow_path_trap_uninstall $swp1 egress
-	slow_path_trap_uninstall $swp1 ingress
+	test_span_failable gt6-soft "mirror to gretap w/ soft underlay"
 }
 
-test_hw()
+test_tos_fixed()
 {
-	test_failable 1
-
 	test_span_gre_tos_fixed gt4 gretap "mirror to gretap"
 	test_span_gre_tos_fixed gt6 ip6gretap "mirror to ip6gretap"
+}
+
 
+test_ttl_inherit()
+{
 	test_span_gre_ttl_inherit gt4 gretap "mirror to gretap"
 	test_span_gre_ttl_inherit gt6 ip6gretap "mirror to ip6gretap"
 }
@@ -202,16 +197,6 @@ trap cleanup EXIT
 setup_prepare
 setup_wait
 
-if ! tc_offload_check; then
-    check_err 1 "Could not test offloaded functionality"
-    log_test "mlxsw-specific tests for mirror to gretap"
-    exit
-fi
-
-tcflags="skip_hw"
-test_sw
-
-tcflags="skip_sw"
-test_hw
+tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
index e5589e2fca85..d43093310e23 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
@@ -79,7 +79,7 @@ mirror_gre_tunnels_create()
 		cat >> $MIRROR_GRE_BATCH_FILE <<-EOF
 			filter add dev $swp1 ingress pref 1000 \
 				protocol ipv6 \
-				flower $tcflags dst_ip $match_dip \
+				flower skip_sw dst_ip $match_dip \
 				action mirred egress mirror dev $tun
 		EOF
 	done
@@ -107,7 +107,7 @@ mirror_gre_tunnels_destroy()
 	done
 }
 
-__mirror_gre_test()
+mirror_gre_test()
 {
 	local count=$1; shift
 	local should_fail=$1; shift
@@ -131,20 +131,6 @@ __mirror_gre_test()
 	done
 }
 
-mirror_gre_test()
-{
-	local count=$1; shift
-	local should_fail=$1; shift
-
-	if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
-		check_err 1 "Could not test offloaded functionality"
-		return
-	fi
-
-	tcflags="skip_sw"
-	__mirror_gre_test $count $should_fail
-}
-
 mirror_gre_setup_prepare()
 {
 	h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index 31252bc8775e..4994bea5daf8 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -11,7 +11,7 @@ ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
 	delta_two_masks_one_key_test delta_simple_rehash_test \
 	bloom_simple_test bloom_complex_test bloom_delta_test \
-	max_erp_entries_test max_group_size_test"
+	max_erp_entries_test max_group_size_test collision_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
@@ -457,7 +457,7 @@ delta_two_masks_one_key_test()
 {
 	# If 2 keys are the same and only differ in mask in a way that
 	# they belong under the same ERP (second is delta of the first),
-	# there should be no C-TCAM spill.
+	# there should be C-TCAM spill.
 
 	RET=0
 
@@ -474,8 +474,8 @@ delta_two_masks_one_key_test()
 	tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \
 		   pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \
 		   action drop"
-	tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0
-	check_err $? "incorrect C-TCAM spill while inserting the second rule"
+	tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 1
+	check_err $? "C-TCAM spill did not happen while inserting the second rule"
 
 	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
 		-t ip -q
@@ -1087,6 +1087,53 @@ max_group_size_test()
 	log_test "max ACL group size test ($tcflags). max size $max_size"
 }
 
+collision_test()
+{
+	# Filters cannot share an eRP if in the common unmasked part (i.e.,
+	# without the delta bits) they have the same values. If the driver does
+	# not prevent such configuration (by spilling into the C-TCAM), then
+	# multiple entries will be present in the device with the same key,
+	# leading to collisions and a reduced scale.
+	#
+	# Create such a scenario and make sure all the filters are successfully
+	# added.
+
+	RET=0
+
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	# Add a single dst_ip/24 filter and multiple dst_ip/32 filters that all
+	# have the same values in the common unmasked part (dst_ip/24).
+
+	tc filter add dev $h2 ingress pref 1 proto ipv4 handle 101 \
+		flower $tcflags dst_ip 198.51.100.0/24 \
+		action drop
+
+	for i in {0..255}; do
+		tc filter add dev $h2 ingress pref 2 proto ipv4 \
+			handle $((102 + i)) \
+			flower $tcflags dst_ip 198.51.100.${i}/32 \
+			action drop
+		ret=$?
+		[[ $ret -ne 0 ]] && break
+	done
+
+	check_err $ret "failed to add all the filters"
+
+	for i in {255..0}; do
+		tc filter del dev $h2 ingress pref 2 proto ipv4 \
+			handle $((102 + i)) flower
+	done
+
+	tc filter del dev $h2 ingress pref 1 proto ipv4 handle 101 flower
+
+	log_test "collision test ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}