mlx5e_channel_stats_alloc() publishes a new entry to
priv->channel_stats[] and then increments priv->stats_nch as a
publication token, but neither store carries any memory barrier:
priv->channel_stats[ix] = kvzalloc_node(...);
if (!priv->channel_stats[ix])
return -ENOMEM;
priv->stats_nch++;
Concurrent readers compute the loop bound from priv->stats_nch and
then dereference priv->channel_stats[i] using plain accesses, e.g.
for (i = 0; i < priv->stats_nch; i++) {
struct mlx5e_channel_stats *cs = priv->channel_stats[i];
... cs->rq.packets ...
}
On weakly-ordered architectures (ARM, PowerPC, RISC-V) the writes to
channel_stats[ix] and stats_nch may become visible to other CPUs out
of program order. A reader can observe stats_nch == N while still
seeing channel_stats[N-1] == NULL, leading to a NULL pointer
dereference in the channel_stats loop.
This has been observed in production on BlueField-3 DPUs (arm64),
where ovs-vswitchd queries netdev statistics over netlink during NIC
bringup, racing mlx5e_open_channel() -> mlx5e_channel_stats_alloc()
on another CPU:
Unable to handle kernel NULL pointer dereference at virtual address 0x840
Hardware name: BlueField-3 DPU
pc : mlx5e_fold_sw_stats64+0x30/0x180 [mlx5_core]
Call trace:
mlx5e_fold_sw_stats64+0x30/0x180 [mlx5_core]
dev_get_stats+0x50/0xc0
ovs_vport_get_stats+0x38/0xac [openvswitch]
ovs_vport_cmd_fill_info+0x194/0x290 [openvswitch]
ovs_vport_cmd_get+0xbc/0x10c [openvswitch]
genl_family_rcv_msg_doit+0xd0/0x160
genl_rcv_msg+0xec/0x1f0
netlink_rcv_skb+0x64/0x130
genl_rcv+0x40/0x60
netlink_unicast+0x2fc/0x370
netlink_sendmsg+0x1dc/0x454
...
__arm64_sys_sendmsg+0x2c/0x40
Add mlx5e_stats_nch_write() and mlx5e_stats_nch_read() helpers in en.h
that wrap the smp_store_release()/smp_load_acquire() pair on stats_nch.
The release/acquire pair establishes the contract:
stats_nch == N => channel_stats[0..N-1] are visible and non-NULL.
Publish the stats_nch increment via mlx5e_stats_nch_write() in the
writer (mlx5e_channel_stats_alloc()), and read stats_nch via
mlx5e_stats_nch_read() in all readers: mlx5e RX/TX queue stats,
mlx5e_get_base_stats(), ethtool channels stats, IPoIB stats, the
sw_stats fold and the HV VHCA stats agent.
Fixes: fa691d0c9c08 ("net/mlx5e: Allocate per-channel stats dynamically at first usage")
Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Eran Ben Elisha <eranbe@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260630115151.729219-4-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
struct ethtool_fec_hist_range *fec_ranges;
};
+static inline u16 mlx5e_stats_nch_read(const struct mlx5e_priv *priv)
+{
+ /* Pairs with smp_store_release in mlx5e_stats_nch_write(). */
+ return smp_load_acquire(&priv->stats_nch);
+}
+
+static inline void mlx5e_stats_nch_write(struct mlx5e_priv *priv, u16 n)
+{
+ /* Pairs with smp_load_acquire in mlx5e_stats_nch_read(). */
+ smp_store_release(&priv->stats_nch, n);
+}
+
struct mlx5e_dev {
struct net_device *netdev;
struct devlink_port dl_port;
static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data,
int buf_len)
{
+ u16 nch = mlx5e_stats_nch_read(priv);
int ch, i = 0;
- for (ch = 0; ch < priv->stats_nch; ch++) {
+ for (ch = 0; ch < nch; ch++) {
void *buf = data + i;
if (WARN_ON_ONCE(buf +
static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv)
{
- return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) *
- priv->stats_nch);
+ u16 nch = mlx5e_stats_nch_read(priv);
+
+ return sizeof(struct mlx5e_hv_vhca_per_ring_stats) * nch;
}
static int mlx5e_hv_vhca_stats_buf_max_size(struct mlx5e_priv *priv)
sagent = &priv->stats_agent;
block->version = MLX5_HV_VHCA_STATS_VERSION;
- block->rings = priv->stats_nch;
+ block->rings = mlx5e_stats_nch_read(priv);
if (!block->command) {
cancel_delayed_work_sync(&priv->stats_agent.work);
GFP_KERNEL, cpu_to_node(cpu));
if (!priv->channel_stats[ix])
return -ENOMEM;
- priv->stats_nch++;
+ mlx5e_stats_nch_write(priv, priv->stats_nch + 1);
return 0;
}
void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
{
+ u16 nch = mlx5e_stats_nch_read(priv);
int i;
- for (i = 0; i < priv->stats_nch; i++) {
+ for (i = 0; i < nch; i++) {
struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
struct mlx5e_rq_stats *xskrq_stats;
struct mlx5e_rq_stats *rq_stats;
- if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch)
+ if (mlx5e_is_uplink_rep(priv) || !mlx5e_stats_nch_read(priv))
return;
channel_stats = priv->channel_stats[i];
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5e_sq_stats *sq_stats;
- if (!priv->stats_nch)
+ if (!mlx5e_stats_nch_read(priv))
return;
/* no special case needed for ptp htb etc since txq2sq_stats is kept up
struct netdev_queue_stats_tx *tx)
{
struct mlx5e_priv *priv = netdev_priv(dev);
+ u16 nch = mlx5e_stats_nch_read(priv);
struct mlx5e_ptp *ptp_channel;
int i, tc;
rx->hw_gro_wire_packets = 0;
rx->hw_gro_wire_bytes = 0;
- for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) {
+ for (i = priv->channels.params.num_channels; i < nch; i++) {
struct netdev_queue_stats_rx rx_i = {0};
mlx5e_get_queue_stats_rx(dev, i, &rx_i);
tx->stop = 0;
tx->wake = 0;
- for (i = 0; i < priv->stats_nch; i++) {
+ for (i = 0; i < nch; i++) {
struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
/* handle two cases:
static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
{
struct mlx5e_sw_stats *s = &priv->stats.sw;
+ u16 nch = mlx5e_stats_nch_read(priv);
int i;
memset(s, 0, sizeof(*s));
for (i = 0; i < priv->channels.num; i++) /* for active channels only */
mlx5e_stats_update_stats_rq_page_pool(priv->channels.c[i]);
- for (i = 0; i < priv->stats_nch; i++) {
+ for (i = 0; i < nch; i++) {
struct mlx5e_channel_stats *channel_stats =
priv->channel_stats[i];
static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels)
{
- int max_nch = priv->stats_nch;
+ int max_nch = mlx5e_stats_nch_read(priv);
return (NUM_RQ_STATS * max_nch) +
(NUM_CH_STATS * max_nch) +
static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels)
{
+ int max_nch = mlx5e_stats_nch_read(priv);
bool is_xsk = priv->xsk.ever_used;
- int max_nch = priv->stats_nch;
int i, j, tc;
for (i = 0; i < max_nch; i++)
static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
{
+ int max_nch = mlx5e_stats_nch_read(priv);
bool is_xsk = priv->xsk.ever_used;
- int max_nch = priv->stats_nch;
int i, j, tc;
for (i = 0; i < max_nch; i++)
static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv)
{
+ u16 nch = mlx5e_stats_nch_read(priv);
struct rtnl_link_stats64 s = {};
int i, j;
- for (i = 0; i < priv->stats_nch; i++) {
+ for (i = 0; i < nch; i++) {
struct mlx5e_channel_stats *channel_stats;
struct mlx5e_rq_stats *rq_stats;