Skip to contentSkip to conversation

Patch "net: rfs: fix crash in get_rps_cpus()" has been added to the 4.0-stable tree

PATCH [email protected] 1 participant 1 message Apr 29, 2015

Subsystems (3)
Networking Stable branch Documentation
lore
Share & tools
lore

[email protected]

author maintainer Applied
#0 lore raw

This is a note to let you know that I've just added the patch titled

net: rfs: fix crash in get_rps_cpus()

to the 4.0-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
net-rfs-fix-crash-in-get_rps_cpus.patch
and it can be found in the queue-4.0 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

Quoted 1 line

From foo@baz Wed Apr 29 11:59:49 CEST 2015

From: Eric Dumazet <[email protected]>
Date: Sat, 25 Apr 2015 09:35:24 -0700
Subject: net: rfs: fix crash in get_rps_cpus()

From: Eric Dumazet <[email protected]>

[ Upstream commit a31196b07f8034eba6a3487a1ad1bb5ec5cd58a5 ]

Commit 567e4b79731c ("net: rfs: add hash collision detection") had one mistake :

RPS_NO_CPU is no longer the marker for invalid cpu in set_rps_cpu() and get_rps_cpu(), as @next_cpu was the result of an AND with rps_cpu_mask

This bug showed up on a host with 72 cpus :
next_cpu was 0x7f, and the code was trying to access percpu data of an non existent cpu.

In a follow up patch, we might get rid of compares against nr_cpu_ids, if we init the tables with 0. This is silly to test for a very unlikely condition that exists only shortly after table initialization, as we got rid of rps_reset_sock_flow() and similar functions that were writing this RPS_NO_CPU magic value at flow dismantle : When table is old enough, it never contains this value anymore.

Fixes 567e4b79731c ("net: rfs: add hash collision detection")
Signed-off-by Eric Dumazet <[email protected]>
Cc Tom Herbert <[email protected]>
Cc Ben Hutchings <[email protected]>
Signed-off-by David S. Miller <[email protected]>
Signed-off-by Greg Kroah-Hartman <[email protected]>
---
 Documentation/networking/scaling.txt |    2 +-
 net/core/dev.c                       |   12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)
Documentation/networking/scaling.txt +1 -1
@@ -282,7 +282,7 @@ following is true:
 
 - The current CPU's queue head counter >= the recorded tail counter
   value in rps_dev_flow[i]
-- The current CPU is unset (equal to RPS_NO_CPU)
+- The current CPU is unset (>= nr_cpu_ids)
 - The current CPU is offline
 
 After this check, the packet is sent to the (possibly updated) current
net/core/dev.c +6 -6
@@ -3041,7 +3041,7 @@ static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	    struct rps_dev_flow *rflow, u16 next_cpu)
 {
-	if (next_cpu != RPS_NO_CPU) {
+	if (next_cpu < nr_cpu_ids) {
 #ifdef CONFIG_RFS_ACCEL
 		struct netdev_rx_queue *rxqueue;
 		struct rps_dev_flow_table *flow_table;

@@ -3146,7 +3146,7 @@ static int get_rps_cpu(struct net_device
 		 * If the desired CPU (where last recvmsg was done) is
 		 * different from current CPU (one in the rx-queue flow
 		 * table entry), switch if one of the following holds:
-		 *   - Current CPU is unset (equal to RPS_NO_CPU).
+		 *   - Current CPU is unset (>= nr_cpu_ids).
 		 *   - Current CPU is offline.
 		 *   - The current CPU's queue tail has advanced beyond the
 		 *     last packet that was enqueued using this table entry.

@@ -3154,14 +3154,14 @@ static int get_rps_cpu(struct net_device
 		 *     have been dequeued, thus preserving in order delivery.
 		 */
 		if (unlikely(tcpu != next_cpu) &&
-		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
+		    (tcpu >= nr_cpu_ids || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
 		      rflow->last_qtail)) >= 0)) {
 			tcpu = next_cpu;
 			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
 		}
 
-		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
+		if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
 			*rflowp = rflow;
 			cpu = tcpu;
 			goto done;

@@ -3202,14 +3202,14 @@ bool rps_may_expire_flow(struct net_devi
 	struct rps_dev_flow_table *flow_table;
 	struct rps_dev_flow *rflow;
 	bool expire = true;
-	int cpu;
+	unsigned int cpu;
 
 	rcu_read_lock();
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	if (flow_table && flow_id <= flow_table->mask) {
 		rflow = &flow_table->flows[flow_id];
 		cpu = ACCESS_ONCE(rflow->cpu);
-		if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
+		if (rflow->filter == filter_id && cpu < nr_cpu_ids &&
 		    ((int)(per_cpu(softnet_data, cpu).input_queue_head -
 			   rflow->last_qtail) <
 		     (int)(10 * flow_table->mask)))

Patches currently in stable-queue which might be from [email protected] are

queue-4.0/net-rfs-fix-crash-in-get_rps_cpus.patch queue-4.0/net-fix-crash-in-build_skb.patch queue-4.0/tcp-avoid-looping-in-tcp_send_fin.patch queue-4.0/net-do-not-deplete-pfmemalloc-reserve.patch queue-4.0/tcp-fix-possible-deadlock-in-tcp_send_fin.patch