diff mbox series

[net-next,1/2] selftests: net-drv: exercise queue stats when the device is down

Message ID 20240729221042.2700882-1-sdf@fomichev.me (mailing list archive)
State New
Headers show
Series [net-next,1/2] selftests: net-drv: exercise queue stats when the device is down | expand

Commit Message

Stanislav Fomichev July 29, 2024, 10:10 p.m. UTC
Verify that total device stats don't decrease after it has been turned down.
Also make sure the device doesn't crash when we access per-queue stats
when it's down (in case it tries to access some pointers that are NULL).

KTAP version 1
1..5
ok 1 stats.check_pause
ok 2 stats.check_fec
ok 3 stats.pkt_byte_sum
ok 4 stats.qstat_by_ifindex
ok 5 stats.check_down
\# Totals: pass:5 fail:0 xfail:0 xpass:0 skip:0 error:0

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
--
Cc: Shuah Khan <shuah@kernel.org>
Cc: Joe Damato <jdamato@fastly.com>
Cc: Petr Machata <petrm@nvidia.com>
Cc: linux-kselftest@vger.kernel.org
---
 tools/testing/selftests/drivers/net/stats.py | 31 +++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

Comments

Jakub Kicinski July 30, 2024, 1:58 a.m. UTC | #1
On Mon, 29 Jul 2024 15:10:41 -0700 Stanislav Fomichev wrote:
> Verify that total device stats don't decrease after it has been turned down.
> Also make sure the device doesn't crash when we access per-queue stats
> when it's down (in case it tries to access some pointers that are NULL).
> 
> KTAP version 1
> 1..5
> ok 1 stats.check_pause
> ok 2 stats.check_fec
> ok 3 stats.pkt_byte_sum
> ok 4 stats.qstat_by_ifindex
> ok 5 stats.check_down
> \# Totals: pass:5 fail:0 xfail:0 xpass:0 skip:0 error:0

nit: may be personal preference but if you indent by 2 spaces
     that will neutralize the # as well

> +def check_down(cfg) -> None:
> +    try:
> +        qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)
> +    except NlError as e:
> +        if e.error == 95:
> +            raise KsftSkipEx("qstats not supported by the device")
> +        raise
> +
> +    ip(f"link set dev {cfg.dev['ifname']} down")
> +
> +    try:

The rest of this test predates defer() but I think it may be cleaner:

	ip(f"link set dev {cfg.dev['ifname']} down")
	defer(ip, f"link set dev {cfg.dev['ifname']} up")

then you don't need to try/finally.

> +        qstat = qstat[0]
> +        qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
> +        for k, v in qstat.items():
> +            if k not in qstat2:
> +                # skip the stats that are not globally preserved
> +                continue

I think we should fail if stats disappear. I can't think of a legit
reason for that to happen.

> +            if qstat2[k] < qstat[k]:
> +                raise Exception(f"{k} ({qstat2[k]}) should be preserved but has lower value ({qstat[k]}) when the device is down")

	ksft_ge(qstat2[k], qstat[k], comment=k)
?

> +
> +        # exercise per-queue API to make sure that "device down" state
> +        # is handled correctly and doesn't crash
> +        netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True)
> +    finally:
> +        ip(f"link set dev {cfg.dev['ifname']} up")
> +
> +
>  def main() -> None:
>      with NetDrvEnv(__file__) as cfg:
> -        ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex],
> +        ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex,
> +                  check_down],
>                   args=(cfg, ))
>      ksft_exit()
>
diff mbox series

Patch

diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
index 820b8e0a22c6..6f8bef379565 100755
--- a/tools/testing/selftests/drivers/net/stats.py
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -5,6 +5,7 @@  from lib.py import ksft_run, ksft_exit, ksft_pr
 from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx
 from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError
 from lib.py import NetDrvEnv
+from lib.py import ip
 
 ethnl = EthtoolFamily()
 netfam = NetdevFamily()
@@ -133,9 +134,37 @@  rtnl = RtnlFamily()
     ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex')
 
 
+def check_down(cfg) -> None:
+    try:
+        qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("qstats not supported by the device")
+        raise
+
+    ip(f"link set dev {cfg.dev['ifname']} down")
+
+    try:
+        qstat = qstat[0]
+        qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+        for k, v in qstat.items():
+            if k not in qstat2:
+                # skip the stats that are not globally preserved
+                continue
+            if qstat2[k] < qstat[k]:
+                raise Exception(f"{k} ({qstat2[k]}) should be preserved but has lower value ({qstat[k]}) when the device is down")
+
+        # exercise per-queue API to make sure that "device down" state
+        # is handled correctly and doesn't crash
+        netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True)
+    finally:
+        ip(f"link set dev {cfg.dev['ifname']} up")
+
+
 def main() -> None:
     with NetDrvEnv(__file__) as cfg:
-        ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex],
+        ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex,
+                  check_down],
                  args=(cfg, ))
     ksft_exit()