Merge branch 'selftests-net-page_poll-allocation-error-injection'

Jakub Kicinski says:

====================
selftests: net: page_poll allocation error injection

Add a test for exercising driver memory allocation failure paths.
page pool is a bit tricky to inject errors into at the page allocator
level because of the bulk alloc and recycling, so add explicit error
injection support "in front" of the caches.

Add a test to exercise that using only the standard APIs.
This is the first useful test for the new tests with an endpoint.
There's no point testing netdevsim here, so this is also the first
HW-only test in Python.

I'm not super happy with the traffic generation using iperf3,
my initial approach was to use mausezahn. But it turned out to be
5x slower in terms of PPS. Hopefully this is good enough for now.

v1: https://lore.kernel.org/all/20240426232400.624864-1-kuba@kernel.org/
====================

Link: https://lore.kernel.org/r/20240429144426.743476-1-kuba@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

net/core/page_pool.c

@@ -5,6 +5,7 @@
  *	Copyright (C) 2016 Red Hat, Inc.
  */
 
+#include <linux/error-injection.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -550,6 +551,7 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
 	return page;
 }
 EXPORT_SYMBOL(page_pool_alloc_pages);
+ALLOW_ERROR_INJECTION(page_pool_alloc_pages, NULL);
 
 /* Calculate distance between two u32 values, valid if distance is below 2^(31)
  *  https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution

tools/testing/selftests/Makefile

@@ -119,7 +119,7 @@ TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
 # Networking tests want the net/lib target, include it automatically
-ifneq ($(filter net drivers/net,$(TARGETS)),)
+ifneq ($(filter net drivers/net drivers/net/hw,$(TARGETS)),)
 ifeq ($(filter net/lib,$(TARGETS)),)
 	INSTALL_DEP_TARGETS := net/lib
 endif

tools/testing/selftests/drivers/net/hw/Makefile

@@ -9,6 +9,7 @@ TEST_PROGS = \
 	hw_stats_l3.sh \
 	hw_stats_l3_gre.sh \
 	loopback.sh \
+	pp_alloc_fail.py \
 	#
 
 TEST_FILES := \
@@ -16,6 +17,7 @@ TEST_FILES := \
 	#
 
 TEST_INCLUDES := \
+	$(wildcard lib/py/*.py ../lib/py/*.py) \
 	../../../net/lib.sh \
 	../../../net/forwarding/lib.sh \
 	../../../net/forwarding/ipip_lib.sh \

tools/testing/selftests/drivers/net/hw/lib/py/__init__.py

+# SPDX-License-Identifier: GPL-2.0
+
+import sys
+from pathlib import Path
+
+KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve()
+
+try:
+    sys.path.append(KSFT_DIR.as_posix())
+    from net.lib.py import *
+    from drivers.net.lib.py import *
+except ModuleNotFoundError as e:
+    ksft_pr("Failed importing `net` library from kernel sources")
+    ksft_pr(str(e))
+    ktap_result(True, comment="SKIP")
+    sys.exit(4)

tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py

+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import time
+import os
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import NetdevFamily, NlError
+from lib.py import NetDrvEpEnv
+from lib.py import cmd, tool, GenerateTraffic
+
+
+def _write_fail_config(config):
+    for key, value in config.items():
+        with open("/sys/kernel/debug/fail_function/" + key, "w") as fp:
+            fp.write(str(value) + "\n")
+
+
+def _enable_pp_allocation_fail():
+    if not os.path.exists("/sys/kernel/debug/fail_function"):
+        raise KsftSkipEx("Kernel built without function error injection (or DebugFS)")
+
+    if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_pages"):
+        with open("/sys/kernel/debug/fail_function/inject", "w") as fp:
+            fp.write("page_pool_alloc_pages\n")
+
+    _write_fail_config({
+        "verbose": 0,
+        "interval": 511,
+        "probability": 100,
+        "times": -1,
+    })
+
+
+def _disable_pp_allocation_fail():
+    if not os.path.exists("/sys/kernel/debug/fail_function"):
+        return
+
+    if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_pages"):
+        with open("/sys/kernel/debug/fail_function/inject", "w") as fp:
+            fp.write("\n")
+
+    _write_fail_config({
+        "probability": 0,
+        "times": 0,
+    })
+
+
+def test_pp_alloc(cfg, netdevnl):
+    def get_stats():
+        return netdevnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+    def check_traffic_flowing():
+        stat1 = get_stats()
+        time.sleep(1)
+        stat2 = get_stats()
+        if stat2['rx-packets'] - stat1['rx-packets'] < 15000:
+            raise KsftFailEx("Traffic seems low:", stat2['rx-packets'] - stat1['rx-packets'])
+
+
+    try:
+        stats = get_stats()
+    except NlError as e:
+        if e.nl_msg.error == -95:
+            stats = {}
+        else:
+            raise
+    if 'rx-alloc-fail' not in stats:
+        raise KsftSkipEx("Driver does not report 'rx-alloc-fail' via qstats")
+
+    set_g = False
+    traffic = None
+    try:
+        traffic = GenerateTraffic(cfg)
+
+        check_traffic_flowing()
+
+        _enable_pp_allocation_fail()
+
+        s1 = get_stats()
+        time.sleep(3)
+        s2 = get_stats()
+
+        if s2['rx-alloc-fail'] - s1['rx-alloc-fail'] < 1:
+            raise KsftSkipEx("Allocation failures not increasing")
+        if s2['rx-alloc-fail'] - s1['rx-alloc-fail'] < 100:
+            raise KsftSkipEx("Allocation increasing too slowly", s2['rx-alloc-fail'] - s1['rx-alloc-fail'],
+                             "packets:", s2['rx-packets'] - s1['rx-packets'])
+
+        # Basic failures are fine, try to wobble some settings to catch extra failures
+        check_traffic_flowing()
+        g = tool("ethtool", "-g " + cfg.ifname, json=True)[0]
+        if 'rx' in g and g["rx"] * 2 <= g["rx-max"]:
+            new_g = g['rx'] * 2
+        elif 'rx' in g:
+            new_g = g['rx'] // 2
+        else:
+            new_g = None
+
+        if new_g:
+            set_g = cmd(f"ethtool -G {cfg.ifname} rx {new_g}", fail=False).ret == 0
+            if set_g:
+                ksft_pr("ethtool -G change retval: success")
+            else:
+                ksft_pr("ethtool -G change retval: did not succeed", new_g)
+        else:
+                ksft_pr("ethtool -G change retval: did not try")
+
+        time.sleep(0.1)
+        check_traffic_flowing()
+    finally:
+        _disable_pp_allocation_fail()
+        if traffic:
+            traffic.stop()
+        time.sleep(0.1)
+        if set_g:
+            cmd(f"ethtool -G {cfg.ifname} rx {g['rx']}")
+
+
+def main() -> None:
+    netdevnl = NetdevFamily()
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+
+        ksft_run([test_pp_alloc], args=(cfg, netdevnl, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

tools/testing/selftests/drivers/net/lib/py/__init__.py

@@ -15,4 +15,5 @@ except ModuleNotFoundError as e:
     sys.exit(4)
 
 from .env import *
+from .load import *
 from .remote import Remote

tools/testing/selftests/drivers/net/lib/py/env.py

@@ -2,7 +2,7 @@
 
 import os
 from pathlib import Path
-from lib.py import KsftSkipEx
+from lib.py import KsftSkipEx, KsftXfailEx
 from lib.py import cmd, ip
 from lib.py import NetNS, NetdevSimDev
 from .remote import Remote
@@ -76,7 +76,7 @@ class NetDrvEpEnv:
     nsim_v4_pfx = "192.0.2."
     nsim_v6_pfx = "2001:db8::"
 
-    def __init__(self, src_path):
+    def __init__(self, src_path, nsim_test=None):
 
         self.env = _load_env_file(src_path)
 
@@ -88,7 +88,10 @@ class NetDrvEpEnv:
         self._ns_peer = None
 
         if "NETIF" in self.env:
+            if nsim_test is True:
+                raise KsftXfailEx("Test only works on netdevsim")
             self._check_env()
+
             self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0]
 
             self.v4 = self.env.get("LOCAL_V4")
@@ -98,6 +101,9 @@ class NetDrvEpEnv:
             kind = self.env["REMOTE_TYPE"]
             args = self.env["REMOTE_ARGS"]
         else:
+            if nsim_test is False:
+                raise KsftXfailEx("Test does not work on netdevsim")
+
             self.create_local()
 
             self.dev = self._ns.nsims[0].dev

tools/testing/selftests/drivers/net/lib/py/load.py

+# SPDX-License-Identifier: GPL-2.0
+
+import time
+
+from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen
+
+class GenerateTraffic:
+    def __init__(self, env):
+        env.require_cmd("iperf3", remote=True)
+
+        self.env = env
+
+        port = rand_port()
+        self._iperf_server = cmd(f"iperf3 -s -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"]
+        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")
+
+    def stop(self, verbose=None):
+        self._iperf_client.process(terminate=True)
+        if verbose:
+            ksft_pr(">> Client:")
+            ksft_pr(self._iperf_client.stdout)
+            ksft_pr(self._iperf_client.stderr)
+        self._iperf_server.process(terminate=True)
+        if verbose:
+            ksft_pr(">> Server:")
+            ksft_pr(self._iperf_server.stdout)
+            ksft_pr(self._iperf_server.stderr)

tools/testing/selftests/net/lib/py/ksft.py

@@ -11,6 +11,10 @@ KSFT_RESULT = None
 KSFT_RESULT_ALL = True
 
 
+class KsftFailEx(Exception):
+    pass
+
+
 class KsftSkipEx(Exception):
     pass
 

tools/testing/selftests/net/lib/py/utils.py

@@ -56,10 +56,10 @@ class bkg(cmd):
         return self.process(terminate=self.terminate)
 
 
-def ip(args, json=None, ns=None, host=None):
-    cmd_str = "ip "
+def tool(name, args, json=None, ns=None, host=None):
+    cmd_str = name + ' '
     if json:
-        cmd_str += '-j '
+        cmd_str += '--json '
     cmd_str += args
     cmd_obj = cmd(cmd_str, ns=ns, host=host)
     if json:
@@ -67,11 +67,17 @@ def ip(args, json=None, ns=None, host=None):
     return cmd_obj
 
 
+def ip(args, json=None, ns=None, host=None):
+    if ns:
+        args = f'-netns {ns} ' + args
+    return tool('ip', args, json=json, host=host)
+
+
 def rand_port():
     """
     Get unprivileged port, for now just random, one day we may decide to check if used.
     """
-    return random.randint(1024, 65535)
+    return random.randint(10000, 65535)
 
 
 def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadline=5):