Commit 5f121b9a authored Jun 13, 2013 by Willem de Bruijn Committed by David S. Miller Jun 13, 2013

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>

parent 85f16525

include/linux/netdevice.h

+2 −2

Original line number	Diff line number	Diff line
		@@ -1840,7 +1840,7 @@ static inline int unregister_gifconf(unsigned int family)
		}

		#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 softnet_data {
		struct napi_struct backlog;

		#ifdef CONFIG_NET_FLOW_LIMIT
		struct sd_flow_limit *flow_limit;
		struct sd_flow_limit __rcu *flow_limit;
		#endif
		};

net/core/sysctl_net_core.c

+16 −3

Original line number	Diff line number	Diff line
		@@ -132,6 +132,8 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
		write_unlock:
		mutex_unlock(&flow_limit_update_mutex);
		} else {
		char kbuf[128];

		if (ppos \|\| !lenp) {
		*lenp = 0;
		goto done;
		@@ -146,9 +148,20 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
		}
		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: