Netdev List
 help / color / mirror / Atom feed
From: Nikolay Aleksandrov <razor@blackwall.org>
To: David Laight <david.laight.linux@gmail.com>
Cc: Hangbin Liu <hangbin.liu@linux.dev>,
	Jay Vosburgh <jv@jvosburgh.net>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Simon Horman <horms@kernel.org>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	Hangbin Liu <liuhangbin@kylinos.cn>
Subject: Re: [PATCH net v5 2/2] bonding: fix u32 overflow in compute_gap()
Date: Fri, 28 Aug 2026 12:19:47 +0300	[thread overview]
Message-ID: <31228099-41a8-4976-acc3-9b320a5012ea@blackwall.org> (raw)
In-Reply-To: <20260827215611.1cb9f252@pumpkin>

On 27/08/2026 23:56, David Laight wrote:
> On Thu, 27 Aug 2026 22:09:04 +0300
> Nikolay Aleksandrov <razor@blackwall.org> wrote:
> 
>> On 27/08/2026 21:20, David Laight wrote:
>>> On Tue, 25 Aug 2026 09:01:30 +0800
>>> Hangbin Liu <hangbin.liu@linux.dev> wrote:
>>>    
>>>> From: Hangbin Liu <liuhangbin@kylinos.cn>
>>>>
>>>> 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.
>>>
>>> How about changing the rebalance interval to either 8 or 16 seconds
>>> to avoid the expensive divide?
>>> Alternatively multiply the other side of the comparisons by the interval,
>>> replacing the expensive divide with a cheap multiply.
>>>
>>> David
>>>    
>>
>> How is that relevant to these patches?
>> And how does that help at all if today that is done at about 10 second interval?
> 
> The 10 seconds is almost certainly completely arbitrary.
> It is relevant because the 64bit divide is significantly expensive on 32bit.
> 
> David
> 

Yeah, that is clear. But currently that recalculation is done once every 10
seconds, such optimizations will be noise. Regardless of that, these changes
are unrelated to the problem he is fixing with the set.

>>
>>>>
>>>> Rework compute_gap() to use s64 arithmetic throughout. Return LLONG_MIN
>>>> when the speed is unknown.
>>>>
>>>> Detected by AI code review.
>>>>
>>>> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
>>>> Signed-off-by: Hangbin Liu <liuhangbin@kylinos.cn>
>>>> ---
>>>>    drivers/net/bonding/bond_alb.c | 52 ++++++++++++++++++++++++++++++------------
>>>>    include/net/bond_alb.h         | 11 +++++----
>>>>    2 files changed, 44 insertions(+), 19 deletions(-)
>>>>
>>>> diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
>>>> index 0afed2c39231..9a43a1f47893 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;
>>>>    
>>>> @@ -170,8 +171,14 @@ static void tlb_deinitialize(struct bonding *bond)
>>>>    
>>>>    static long long 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 */
>>>> +	u32 raw_speed = READ_ONCE(slave->speed);
>>>> +
>>>> +	/* It's meaningless to compare gap on unknown speed NIC */
>>>> +	if (raw_speed == (u32)SPEED_UNKNOWN)
>>>> +		return LLONG_MIN;
>>>> +
>>>> +	return ((s64)raw_speed << 20) - /* Convert to bits per sec */
>>>> +	       ((s64)SLAVE_TLB_INFO(slave).load << 3); /* Bytes to bits */
>>>>    }
>>>>    
>>>>    static struct slave *tlb_get_least_loaded_slave(struct bonding *bond)
>>>> @@ -188,7 +195,7 @@ static struct slave *tlb_get_least_loaded_slave(struct bonding *bond)
>>>>    		if (bond_slave_can_tx(slave)) {
>>>>    			long long gap = compute_gap(slave);
>>>>    
>>>> -			if (max_gap < gap) {
>>>> +			if (!least_loaded || max_gap < gap) {
>>>>    				least_loaded = slave;
>>>>    				max_gap = gap;
>>>>    			}
>>>> @@ -1354,8 +1361,14 @@ 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 +1552,27 @@ 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 +1616,13 @@ 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 -------- */
>>>>   
>>>    
>>
> 


      reply	other threads:[~2026-08-28  9:19 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-25  1:01 [PATCH net v5 0/2] bonding: fix TLB load-tracking overflow on high-speed NICs Hangbin Liu
2026-08-25  1:01 ` [PATCH net v5 1/2] bonding: convert unbalanced_load to per-cpu state Hangbin Liu
2026-08-26  7:34   ` Nikolay Aleksandrov
2026-08-25  1:01 ` [PATCH net v5 2/2] bonding: fix u32 overflow in compute_gap() Hangbin Liu
2026-08-26  7:34   ` Nikolay Aleksandrov
2026-08-27 13:42   ` Paolo Abeni
2026-08-28  1:28     ` Hangbin Liu
2026-08-27 18:20   ` David Laight
2026-08-27 19:09     ` Nikolay Aleksandrov
2026-08-27 20:56       ` David Laight
2026-08-28  9:19         ` Nikolay Aleksandrov [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=31228099-41a8-4976-acc3-9b320a5012ea@blackwall.org \
    --to=razor@blackwall.org \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=david.laight.linux@gmail.com \
    --cc=edumazet@google.com \
    --cc=hangbin.liu@linux.dev \
    --cc=horms@kernel.org \
    --cc=jv@jvosburgh.net \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=liuhangbin@kylinos.cn \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox