summaryrefslogtreecommitdiff
path: root/drivers/net
diff options
context:
space:
mode:
authorAndrew Gallatin <gallatin@myri.com>2007-10-31 17:40:06 -0400
committerJeff Garzik <jeff@garzik.org>2007-11-01 16:04:45 -0400
commitc956a24018819bd903fad0cd275a63c089cdba53 (patch)
tree4a7e534f589e600c11384ee3892c98f8af3d0b58 /drivers/net
parent48d58459fe991e48bf7e6638a0ded0f8cbd2fa3b (diff)
Fix myri10ge NAPI oops & warnings
When testing the myri10ge driver with 2.6.24-rc1, I found that the machine crashed under heavy load: Unable to handle kernel paging request at 0000000000100108 RIP: [<ffffffff803cc8dd>] net_rx_action+0x11b/0x184 The address corresponds to the list_move_tail() in netif_rx_complete(): if (unlikely(work == weight)) list_move_tail(&n->poll_list, list); Eventually, I traced the crashes to calling netif_rx_complete() with work_done == budget. From looking at other drivers, it appears that one should only call netif_rx_complete() when work_done < budget. To fix it, I changed the test in myri10ge_poll() so that it refers to to work_done rather than looking at the rx ring status. If work_done is < budget, then that implies we have no more packets to process. Any races will be resolved by the NIC when the write to irq_claim is made. In myri10ge_clean_rx_done(), if we ever exceeded our budget, it would report a work_done one larger than was acutally done. This is because the increment was done in the conditional, so work_done would be incremented regardless of whether or not the test passed or failed. This would lead to the WARN_ON_ONCE(work > weight); warning in net_rx_action triggering. I've moved the increment of work_done inside the loop. Note that this would only be a problem when we had exceeded our budget. Signed off by: Andrew Gallatin <gallatin@myri.com> Andrew Gallatin Myricom Inc Signed-off-by: Jeff Garzik <jeff@garzik.org>
Diffstat (limited to 'drivers/net')
-rw-r--r--drivers/net/myri10ge/myri10ge.c6
1 files changed, 3 insertions, 3 deletions
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index 366e62a2b1e5..0f306ddb5630 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -1151,7 +1151,7 @@ static inline int myri10ge_clean_rx_done(struct myri10ge_priv *mgp, int budget)
u16 length;
__wsum checksum;
- while (rx_done->entry[idx].length != 0 && work_done++ < budget) {
+ while (rx_done->entry[idx].length != 0 && work_done < budget) {
length = ntohs(rx_done->entry[idx].length);
rx_done->entry[idx].length = 0;
checksum = csum_unfold(rx_done->entry[idx].checksum);
@@ -1167,6 +1167,7 @@ static inline int myri10ge_clean_rx_done(struct myri10ge_priv *mgp, int budget)
rx_bytes += rx_ok * (unsigned long)length;
cnt++;
idx = cnt & (myri10ge_max_intr_slots - 1);
+ work_done++;
}
rx_done->idx = idx;
rx_done->cnt = cnt;
@@ -1233,13 +1234,12 @@ static int myri10ge_poll(struct napi_struct *napi, int budget)
struct myri10ge_priv *mgp =
container_of(napi, struct myri10ge_priv, napi);
struct net_device *netdev = mgp->dev;
- struct myri10ge_rx_done *rx_done = &mgp->rx_done;
int work_done;
/* process as many rx events as NAPI will allow */
work_done = myri10ge_clean_rx_done(mgp, budget);
- if (rx_done->entry[rx_done->idx].length == 0 || !netif_running(netdev)) {
+ if (work_done < budget || !netif_running(netdev)) {
netif_rx_complete(netdev, napi);
put_be32(htonl(3), mgp->irq_claim);
}