Re: [net-next, v6, 6/7] net-sysfs: Add interface for Rx queue(s) map per Tx queue

["Nambiar, Amritha" <amritha.nambiar@intel.com>]

On 7/4/2018 12:20 AM, Andrei Vagin wrote:
> Hello Amritha,
> 
> I see a following warning on 4.18.0-rc3-next-20180703.
> It looks like a problem is in this series.
> 
> [    1.084722] ============================================
> [    1.084797] WARNING: possible recursive locking detected
> [    1.084872] 4.18.0-rc3-next-20180703+ #1 Not tainted
> [    1.084949] --------------------------------------------
> [    1.085024] swapper/0/1 is trying to acquire lock:
> [    1.085100] 00000000cf973d46 (cpu_hotplug_lock.rw_sem){++++}, at: static_key_slow_inc+0xe/0x20
> [    1.085189] 
> [    1.085189] but task is already holding lock:
> [    1.085271] 00000000cf973d46 (cpu_hotplug_lock.rw_sem){++++}, at: init_vqs+0x513/0x5a0
> [    1.085357] 
> [    1.085357] other info that might help us debug this:
> [    1.085450]  Possible unsafe locking scenario:
> [    1.085450] 
> [    1.085531]        CPU0
> [    1.085605]        ----
> [    1.085679]   lock(cpu_hotplug_lock.rw_sem);
> [    1.085753]   lock(cpu_hotplug_lock.rw_sem);
> [    1.085828] 
> [    1.085828]  *** DEADLOCK ***
> [    1.085828] 
> [    1.085916]  May be due to missing lock nesting notation
> [    1.085916] 
> [    1.085998] 3 locks held by swapper/0/1:
> [    1.086074]  #0: 00000000244bc7da (&dev->mutex){....}, at: __driver_attach+0x5a/0x110
> [    1.086164]  #1: 00000000cf973d46 (cpu_hotplug_lock.rw_sem){++++}, at: init_vqs+0x513/0x5a0
> [    1.086248]  #2: 000000005cd8463f (xps_map_mutex){+.+.}, at: __netif_set_xps_queue+0x8d/0xc60
> [    1.086336] 
> [    1.086336] stack backtrace:
> [    1.086419] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.18.0-rc3-next-20180703+ #1
> [    1.086504] Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
> [    1.086587] Call Trace:
> [    1.086667]  dump_stack+0x85/0xcb
> [    1.086744]  __lock_acquire+0x68a/0x1330
> [    1.086821]  ? lock_acquire+0x9f/0x200
> [    1.086900]  ? find_held_lock+0x2d/0x90
> [    1.086976]  ? lock_acquire+0x9f/0x200
> [    1.087051]  lock_acquire+0x9f/0x200
> [    1.087126]  ? static_key_slow_inc+0xe/0x20
> [    1.087205]  cpus_read_lock+0x3e/0x80
> [    1.087280]  ? static_key_slow_inc+0xe/0x20
> [    1.087355]  static_key_slow_inc+0xe/0x20
> [    1.087435]  __netif_set_xps_queue+0x216/0xc60
> [    1.087512]  virtnet_set_affinity+0xf0/0x130
> [    1.087589]  init_vqs+0x51b/0x5a0
> [    1.087665]  virtnet_probe+0x39f/0x870
> [    1.087742]  virtio_dev_probe+0x170/0x220
> [    1.087819]  driver_probe_device+0x30b/0x480
> [    1.087897]  ? set_debug_rodata+0x11/0x11
> [    1.087972]  __driver_attach+0xe0/0x110
> [    1.088064]  ? driver_probe_device+0x480/0x480
> [    1.088141]  bus_for_each_dev+0x79/0xc0
> [    1.088221]  bus_add_driver+0x164/0x260
> [    1.088302]  ? veth_init+0x11/0x11
> [    1.088379]  driver_register+0x5b/0xe0
> [    1.088402]  ? veth_init+0x11/0x11
> [    1.088402]  virtio_net_driver_init+0x6d/0x90
> [    1.088402]  do_one_initcall+0x5d/0x34c
> [    1.088402]  ? set_debug_rodata+0x11/0x11
> [    1.088402]  ? rcu_read_lock_sched_held+0x6b/0x80
> [    1.088402]  kernel_init_freeable+0x1ea/0x27b
> [    1.088402]  ? rest_init+0xd0/0xd0
> [    1.088402]  kernel_init+0xa/0x110
> [    1.088402]  ret_from_fork+0x3a/0x50
> [    1.094190] i8042: PNP: PS/2 Controller [PNP0303:KBD,PNP0f13:MOU] at 0x60,0x64 irq 1,12
> 
> 
> https://travis-ci.org/avagin/linux/jobs/399867744
> 

With this patch series, I introduced static_key for XPS maps
(xps_needed), so static_key_slow_inc() is used to switch branches. The
definition of static_key_slow_inc() has cpus_read_lock in place. In the
virtio_net driver, XPS queues are initialized after setting the
queue:cpu affinity in virtnet_set_affinity() which is already protected
within cpus_read_lock. Hence, the warning here trying to acquire
cpus_read_lock when it is already held.

A quick fix for this would be to just extract netif_set_xps_queue() out
of the lock by simply wrapping it with another put/get_online_cpus
(unlock right before and hold lock right after). But this may not a
clean solution. It'd help if I can get suggestions on what would be a
clean option to fix this without extensively changing the code in
virtio_net. Is it mandatory to protect the affinitization with
read_lock? I don't see similar lock in other drivers while setting the
affinity. I understand this warning should go away, but isn't it safe to
have multiple readers.

> On Fri, Jun 29, 2018 at 09:27:07PM -0700, Amritha Nambiar wrote:
>> Extend transmit queue sysfs attribute to configure Rx queue(s) map
>> per Tx queue. By default no receive queues are configured for the
>> Tx queue.
>>
>> - /sys/class/net/eth0/queues/tx-*/xps_rxqs
>>
>> Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
>> ---
>>  net/core/net-sysfs.c |   83 ++++++++++++++++++++++++++++++++++++++++++++++++++
>>  1 file changed, 83 insertions(+)
>>
>> diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
>> index b39987c..f25ac5f 100644
>> --- a/net/core/net-sysfs.c
>> +++ b/net/core/net-sysfs.c
>> @@ -1283,6 +1283,88 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
>>  
>>  static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
>>  	= __ATTR_RW(xps_cpus);
>> +
>> +static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
>> +{
>> +	struct net_device *dev = queue->dev;
>> +	struct xps_dev_maps *dev_maps;
>> +	unsigned long *mask, index;
>> +	int j, len, num_tc = 1, tc = 0;
>> +
>> +	index = get_netdev_queue_index(queue);
>> +
>> +	if (dev->num_tc) {
>> +		num_tc = dev->num_tc;
>> +		tc = netdev_txq_to_tc(dev, index);
>> +		if (tc < 0)
>> +			return -EINVAL;
>> +	}
>> +	mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long),
>> +		       GFP_KERNEL);
>> +	if (!mask)
>> +		return -ENOMEM;
>> +
>> +	rcu_read_lock();
>> +	dev_maps = rcu_dereference(dev->xps_rxqs_map);
>> +	if (!dev_maps)
>> +		goto out_no_maps;
>> +
>> +	for (j = -1; j = netif_attrmask_next(j, NULL, dev->num_rx_queues),
>> +	     j < dev->num_rx_queues;) {
>> +		int i, tci = j * num_tc + tc;
>> +		struct xps_map *map;
>> +
>> +		map = rcu_dereference(dev_maps->attr_map[tci]);
>> +		if (!map)
>> +			continue;
>> +
>> +		for (i = map->len; i--;) {
>> +			if (map->queues[i] == index) {
>> +				set_bit(j, mask);
>> +				break;
>> +			}
>> +		}
>> +	}
>> +out_no_maps:
>> +	rcu_read_unlock();
>> +
>> +	len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues);
>> +	kfree(mask);
>> +
>> +	return len < PAGE_SIZE ? len : -EINVAL;
>> +}
>> +
>> +static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
>> +			      size_t len)
>> +{
>> +	struct net_device *dev = queue->dev;
>> +	struct net *net = dev_net(dev);
>> +	unsigned long *mask, index;
>> +	int err;
>> +
>> +	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
>> +		return -EPERM;
>> +
>> +	mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long),
>> +		       GFP_KERNEL);
>> +	if (!mask)
>> +		return -ENOMEM;
>> +
>> +	index = get_netdev_queue_index(queue);
>> +
>> +	err = bitmap_parse(buf, len, mask, dev->num_rx_queues);
>> +	if (err) {
>> +		kfree(mask);
>> +		return err;
>> +	}
>> +
>> +	err = __netif_set_xps_queue(dev, mask, index, true);
>> +	kfree(mask);
>> +	return err ? : len;
>> +}
>> +
>> +static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init
>> +	= __ATTR_RW(xps_rxqs);
>>  #endif /* CONFIG_XPS */
>>  
>>  static struct attribute *netdev_queue_default_attrs[] __ro_after_init = {
>> @@ -1290,6 +1372,7 @@ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = {
>>  	&queue_traffic_class.attr,
>>  #ifdef CONFIG_XPS
>>  	&xps_cpus_attribute.attr,
>> +	&xps_rxqs_attribute.attr,
>>  	&queue_tx_maxrate.attr,
>>  #endif
>>  	NULL