Re: [PATCH net v4 2/2] bonding: fix u32 overflow in compute_gap()
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: 2026-08-21 10:16:26
Also in:
lkml
On 20/08/2026 08:55, Hangbin Liu wrote:
quoted hunk ↗ jump to hunk
From: Hangbin Liu <redacted> The TLB load-tracking fields tx_bytes, load_history, load, and unbalanced_load are all u32. At sustained throughput above ~3.2 Gbit/s over the 10-second rebalance interval the byte counters wrap, causing compute_gap() to produce incorrect gap values and mis-select slaves. Such speeds are common on modern NICs under heavy traffic. Widen these fields to u64. Use u64_stats_sync to protect the per-cpu unbalanced_load_stats against tearing on 32-bit architectures, and div_u64() for the 64-bit divisions. The tx_bytes and load_history are protected in spin_lock. Also protect the slave load writing in bond_alb_monitor() with spin_lock in case of tear on 32-bit. Rework compute_gap() to use u64 arithmetic throughout. Return 0 when the speed is unknown or the slave is already overloaded. Detected by AI code review. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Hangbin Liu <redacted> --- drivers/net/bonding/bond_alb.c | 65 ++++++++++++++++++++++++++++++------------ include/net/bond_alb.h | 11 +++---- 2 files changed, 53 insertions(+), 23 deletions(-)diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 0afed2c39231..372db54803d3 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c@@ -6,6 +6,7 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/ethtool.h> #include <linux/pkt_sched.h> #include <linux/spinlock.h> #include <linux/slab.h>@@ -74,8 +75,8 @@ static inline u8 _simple_hash(const u8 *hash_start, int hash_size) static inline void tlb_init_table_entry(struct tlb_client_info *entry, int save_load) { if (save_load) { - entry->load_history = 1 + entry->tx_bytes / - BOND_TLB_REBALANCE_INTERVAL; + entry->load_history = 1 + div_u64(entry->tx_bytes, + BOND_TLB_REBALANCE_INTERVAL); entry->tx_bytes = 0; }@@ -133,7 +134,7 @@ static int tlb_initialize(struct bonding *bond) if (!new_hashtbl) return -ENOMEM; - bond_info->unbalanced_load = alloc_percpu(struct unbalanced_load_stats); + bond_info->unbalanced_load = netdev_alloc_pcpu_stats(struct unbalanced_load_stats); if (!bond_info->unbalanced_load) goto out;@@ -168,27 +169,38 @@ static void tlb_deinitialize(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); } -static long long compute_gap(struct slave *slave) +static u64 compute_gap(struct slave *slave) { - return (s64) (slave->speed << 20) - /* Convert to Megabit per sec */ - (s64) (SLAVE_TLB_INFO(slave).load << 3); /* Bytes to bits */ + u64 slave_load = SLAVE_TLB_INFO(slave).load << 3; /* Bytes to bits */ + u32 raw_speed = READ_ONCE(slave->speed); + u64 speed = (u64)raw_speed << 20; /* Convert to bits per sec */ + + /* It's meaningless to compare gap on unknown speed NIC */ + if (raw_speed == (u32)SPEED_UNKNOWN) + return 0; + + /* Skip slave which is over loaded */ + if (speed <= slave_load) + return 0; + + return speed - slave_load; } static struct slave *tlb_get_least_loaded_slave(struct bonding *bond) { struct slave *slave, *least_loaded; struct list_head *iter; - long long max_gap; + u64 max_gap = 0; least_loaded = NULL; - max_gap = LLONG_MIN; /* Find the slave with the largest gap */ bond_for_each_slave_rcu(bond, slave, iter) { if (bond_slave_can_tx(slave)) { - long long gap = compute_gap(slave); + u64 gap = compute_gap(slave); - if (max_gap < gap) { + /* Make sure we have one available slave */ + if (max_gap <= gap) { least_loaded = slave; max_gap = gap;
I think Sashiko's review has a point here: "Does clamping the gap to 0 completely break load balancing when all interfaces are overloaded? When all slaves are overloaded, compute_gap() returns 0 for all of them. Since max_gap is initialized to 0, max_gap <= gap will evaluate to 0 <= 0, which is true. This means tlb_get_least_loaded_slave() will continually update least_loaded to the current slave, ultimately routing all traffic to the last slave in the list instead of distributing it across the least overloaded interfaces." That is, compute_gap makes multiple different scenarios look the same: if speed is unknown = 0 if exactly equal capacity = 0 if overloaded by *any* amount = 0 So Sashiko's comment seems correct, it doesn't matter if a slave is overloaded with 1 gbps or 100, they will look the same.
quoted hunk ↗ jump to hunk
}@@ -1354,8 +1366,14 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, if (!tx_slave) { /* unbalanced or unassigned, send through primary */ tx_slave = rcu_dereference(bond->curr_active_slave); - if (bond->params.tlb_dynamic_lb) - this_cpu_add(bond_info->unbalanced_load->tx_bytes, skb->len); + if (bond->params.tlb_dynamic_lb) { + struct unbalanced_load_stats *pcpu_load; + + pcpu_load = this_cpu_ptr(bond_info->unbalanced_load); + u64_stats_update_begin(&pcpu_load->syncp); + u64_stats_add(&pcpu_load->tx_bytes, skb->len); + u64_stats_update_end(&pcpu_load->syncp); + } } if (tx_slave && bond_slave_can_tx(tx_slave)) {@@ -1539,21 +1557,27 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) return bond_do_alb_xmit(skb, bond, tx_slave); } -static u32 reset_unbalanced_load(struct alb_bond_info *bond_info) +static u64 reset_unbalanced_load(struct alb_bond_info *bond_info) { + u64 delta, tx_bytes, total_bytes = 0; struct unbalanced_load_stats *p; - u32 delta, total_bytes = 0; + unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(bond_info->unbalanced_load, i); - total_bytes += READ_ONCE(p->tx_bytes); + do { + start = u64_stats_fetch_begin(&p->syncp); + tx_bytes = u64_stats_read(&p->tx_bytes); + } while (u64_stats_fetch_retry(&p->syncp, start)); + + total_bytes += tx_bytes; } delta = total_bytes - bond_info->prev_total_unbalanced; bond_info->prev_total_unbalanced = total_bytes; - return delta / BOND_TLB_REBALANCE_INTERVAL; + return div_u64(delta, BOND_TLB_REBALANCE_INTERVAL); } void bond_alb_monitor(struct work_struct *work)@@ -1597,8 +1621,13 @@ void bond_alb_monitor(struct work_struct *work) if (atomic_read(&bond_info->tx_rebalance_counter) >= BOND_TLB_REBALANCE_TICKS) { bond_for_each_slave_rcu(bond, slave, iter) { tlb_clear_slave(bond, slave, 1); - if (slave == rcu_access_pointer(bond->curr_active_slave)) - SLAVE_TLB_INFO(slave).load = reset_unbalanced_load(bond_info); + if (slave == rcu_access_pointer(bond->curr_active_slave)) { + u64 new_load = reset_unbalanced_load(bond_info); + + spin_lock_bh(&bond->mode_lock); + SLAVE_TLB_INFO(slave).load = new_load; + spin_unlock_bh(&bond->mode_lock); + } } atomic_set(&bond_info->tx_rebalance_counter, 0); }diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 6fb09b4fc7e2..32f1981033e4 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h@@ -57,12 +57,12 @@ struct tlb_client_info { * packets to a Client that the Hash function * gave this entry index. */ - u32 tx_bytes; /* Each Client accumulates the BytesTx that + u64 tx_bytes; /* Each Client accumulates the BytesTx that * were transmitted to it, and after each * CallBack the LoadHistory is divided * by the balance interval */ - u32 load_history; /* This field contains the amount of Bytes + u64 load_history; /* This field contains the amount of Bytes * that were transmitted to this client by * the server on the previous balance * interval in Bps.@@ -118,19 +118,20 @@ struct tlb_slave_info { * are the entries that were assigned to use this * slave for transmit. */ - u32 load; /* Each slave sums the loadHistory of all clients + u64 load; /* Each slave sums the loadHistory of all clients * assigned to it */ }; struct unbalanced_load_stats { - u32 tx_bytes; + u64_stats_t tx_bytes; + struct u64_stats_sync syncp; }; struct alb_bond_info { struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */ struct unbalanced_load_stats __percpu *unbalanced_load; - u32 prev_total_unbalanced; + u64 prev_total_unbalanced; atomic_t tx_rebalance_counter; int lp_counter; /* -------- rlb parameters -------- */