net-rps: fixes for rps flow limit
Caught by sparse:
- __rcu: missing annotation to sd->flow_limit
- __user: direct access in cpumask_scnprintf
Also
- add endline character when printing bitmap if room in buffer
- avoid bucket overflow by reducing FLOW_LIMIT_HISTORY
The last item warrants some explanation. The hashtable buckets are
subject to overflow if FLOW_LIMIT_HISTORY is larger than or equal
to bucket size, since all packets may end up in a single bucket. The
current (rather arbitrary) history value of 256 happens to match the
buffer size (u8).
As a result, with a single flow, the first 128 packets are accepted
(correct), the second 128 packets dropped (correct) and then the
history[] array has filled, so that each subsequent new packet
causes an increment in the bucket for new_flow plus a decrement
for old_flow: a steady state.
This is fine if packets are dropped, as the steady state goes away
as soon as a mix of traffic reappears. But, because the 256th packet
overflowed the bucket to 0: no packets are dropped.
Instead of explicitly adding an overflow check, this patch changes
FLOW_LIMIT_HISTORY to never be able to overflow a single bucket.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
(first item)
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e5d6557..8c9fcc4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1840,7 +1840,7 @@
}
#ifdef CONFIG_NET_FLOW_LIMIT
-#define FLOW_LIMIT_HISTORY (1 << 8) /* must be ^2 */
+#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */
struct sd_flow_limit {
u64 count;
unsigned int num_buckets;
@@ -1883,7 +1883,7 @@
struct napi_struct backlog;
#ifdef CONFIG_NET_FLOW_LIMIT
- struct sd_flow_limit *flow_limit;
+ struct sd_flow_limit __rcu *flow_limit;
#endif
};
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 637a42e..78c746e 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -132,6 +132,8 @@
write_unlock:
mutex_unlock(&flow_limit_update_mutex);
} else {
+ char kbuf[128];
+
if (*ppos || !*lenp) {
*lenp = 0;
goto done;
@@ -146,9 +148,20 @@
}
rcu_read_unlock();
- len = cpumask_scnprintf(buffer, *lenp, mask);
- *lenp = len + 1;
- *ppos += len + 1;
+ len = min(sizeof(kbuf) - 1, *lenp);
+ len = cpumask_scnprintf(kbuf, len, mask);
+ if (!len) {
+ *lenp = 0;
+ goto done;
+ }
+ if (len < *lenp)
+ kbuf[len++] = '\n';
+ if (copy_to_user(buffer, kbuf, len)) {
+ ret = -EFAULT;
+ goto done;
+ }
+ *lenp = len;
+ *ppos += len;
}
done:
