summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_ethtool.c
diff options
context:
space:
mode:
authorJacob Keller <jacob.e.keller@intel.com>2018-08-09 16:28:54 +0300
committerJeff Kirsher <jeffrey.t.kirsher@intel.com>2018-08-23 19:49:16 +0300
commitf8ba7db850350319348b6d3c276f8ba19bc098ef (patch)
treec716336f2c95ea24de2368fdafff260a89cba744 /drivers/net/ethernet/intel/ice/ice_ethtool.c
parent5ab522443bd1dafa9e32d6f4b029128efda072de (diff)
downloadlinux-f8ba7db850350319348b6d3c276f8ba19bc098ef.tar.xz
ice: Report stats for allocated queues via ethtool stats
It is not safe to have the string table for statistics change order or size over the lifetime of a given netdevice. This is because of the nature of the 3-step process for obtaining stats. First, user space performs a request for the size of the strings table. Second it performs a separate request for the strings themselves, after allocating space for the table. Third, it requests the stats themselves, also allocating space for the table. If the size decreased, there is potential to see garbage data or stats values. In the worst case, we could potentially see stats values become mis-aligned with their strings, so that it looks like a statistic is being reported differently than it actually is. Even worse, if the size increased, there is potential that the strings table or stats table was not allocated large enough and the stats code could access and write to memory it should not, potentially resulting in undefined behavior and system crashes. It isn't even safe if the size always changes under the RTNL lock. This is because the calls take place over multiple user space commands, so it is not possible to hold the RTNL lock for the entire duration of obtaining strings and stats. Further, not all consumers of the ethtool API are the user space ethtool program, and it is possible that one assumes the strings will not change (valid under the current contract), and thus only requests the stats values when requesting stats in a loop. Finally, it's not possible in the general case to detect when the size changes, because it is quite possible that one value which could impact the stat size increased, while another decreased. This would result in the same total number of stats, but reordering them so that stats no longer line up with the strings they belong to. Since only size changes aren't enough, we would need some sort of hash or token to determine when the strings no longer match. This would require extending the ethtool stats commands, but there is no more space in the relevant structures. The real solution to resolve this would be to add a completely new API for stats, probably over netlink. In the ice driver, the only thing impacting the stats that is not constant is the number of queues. Instead of reporting stats for each used queue, report stats for each allocated queue. We do not change the number of queues allocated for a given netdevice, as we pass this into the alloc_etherdev_mq() function to set the num_tx_queues and num_rx_queues. This resolves the potential bugs at the slight cost of displaying many queue statistics which will not be activated. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com> Tested-by: Tony Brelinski <tonyx.brelinski@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_ethtool.c')
-rw-r--r--drivers/net/ethernet/intel/ice/ice_ethtool.c52
1 files changed, 39 insertions, 13 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 1db304c01d10..c71a9b528d6d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -26,7 +26,7 @@ static int ice_q_stats_len(struct net_device *netdev)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
- return ((np->vsi->num_txq + np->vsi->num_rxq) *
+ return ((np->vsi->alloc_txq + np->vsi->alloc_rxq) *
(sizeof(struct ice_q_stats) / sizeof(u64)));
}
@@ -218,7 +218,7 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
p += ETH_GSTRING_LEN;
}
- ice_for_each_txq(vsi, i) {
+ ice_for_each_alloc_txq(vsi, i) {
snprintf(p, ETH_GSTRING_LEN,
"tx-queue-%u.tx_packets", i);
p += ETH_GSTRING_LEN;
@@ -226,7 +226,7 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
p += ETH_GSTRING_LEN;
}
- ice_for_each_rxq(vsi, i) {
+ ice_for_each_alloc_rxq(vsi, i) {
snprintf(p, ETH_GSTRING_LEN,
"rx-queue-%u.rx_packets", i);
p += ETH_GSTRING_LEN;
@@ -253,6 +253,24 @@ static int ice_get_sset_count(struct net_device *netdev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
+ /* The number (and order) of strings reported *must* remain
+ * constant for a given netdevice. This function must not
+ * report a different number based on run time parameters
+ * (such as the number of queues in use, or the setting of
+ * a private ethtool flag). This is due to the nature of the
+ * ethtool stats API.
+ *
+ * User space programs such as ethtool must make 3 separate
+ * ioctl requests, one for size, one for the strings, and
+ * finally one for the stats. Since these cross into
+ * user space, changes to the number or size could result in
+ * undefined memory access or incorrect string<->value
+ * correlations for statistics.
+ *
+ * Even if it appears to be safe, changes to the size or
+ * order of strings will suffer from race conditions and are
+ * not safe.
+ */
return ICE_ALL_STATS_LEN(netdev);
default:
return -EOPNOTSUPP;
@@ -280,18 +298,26 @@ ice_get_ethtool_stats(struct net_device *netdev,
/* populate per queue stats */
rcu_read_lock();
- ice_for_each_txq(vsi, j) {
+ ice_for_each_alloc_txq(vsi, j) {
ring = READ_ONCE(vsi->tx_rings[j]);
- if (!ring)
- continue;
- data[i++] = ring->stats.pkts;
- data[i++] = ring->stats.bytes;
+ if (ring) {
+ data[i++] = ring->stats.pkts;
+ data[i++] = ring->stats.bytes;
+ } else {
+ data[i++] = 0;
+ data[i++] = 0;
+ }
}
- ice_for_each_rxq(vsi, j) {
+ ice_for_each_alloc_rxq(vsi, j) {
ring = READ_ONCE(vsi->rx_rings[j]);
- data[i++] = ring->stats.pkts;
- data[i++] = ring->stats.bytes;
+ if (ring) {
+ data[i++] = ring->stats.pkts;
+ data[i++] = ring->stats.bytes;
+ } else {
+ data[i++] = 0;
+ data[i++] = 0;
+ }
}
rcu_read_unlock();
@@ -519,7 +545,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
goto done;
}
- for (i = 0; i < vsi->num_txq; i++) {
+ for (i = 0; i < vsi->alloc_txq; i++) {
/* clone ring and setup updated count */
tx_rings[i] = *vsi->tx_rings[i];
tx_rings[i].count = new_tx_cnt;
@@ -551,7 +577,7 @@ process_rx:
goto done;
}
- for (i = 0; i < vsi->num_rxq; i++) {
+ for (i = 0; i < vsi->alloc_rxq; i++) {
/* clone ring and setup updated count */
rx_rings[i] = *vsi->rx_rings[i];
rx_rings[i].count = new_rx_cnt;