From: Wander Lairson Costa wander@redhat.com
[ Upstream commit f1e197a665c2148ebc25fe09c53689e60afea195 ]
trace_drop_common() is called with preemption disabled, and it acquires a spin_lock. This is problematic for RT kernels because spin_locks are sleeping locks in this configuration, which causes the following splat:
BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 449, name: rcuc/47 preempt_count: 1, expected: 0 RCU nest depth: 2, expected: 2 5 locks held by rcuc/47/449: #0: ff1100086ec30a60 ((softirq_ctrl.lock)){+.+.}-{2:2}, at: __local_bh_disable_ip+0x105/0x210 #1: ffffffffb394a280 (rcu_read_lock){....}-{1:2}, at: rt_spin_lock+0xbf/0x130 #2: ffffffffb394a280 (rcu_read_lock){....}-{1:2}, at: __local_bh_disable_ip+0x11c/0x210 #3: ffffffffb394a160 (rcu_callback){....}-{0:0}, at: rcu_do_batch+0x360/0xc70 #4: ff1100086ee07520 (&data->lock){+.+.}-{2:2}, at: trace_drop_common.constprop.0+0xb5/0x290 irq event stamp: 139909 hardirqs last enabled at (139908): [<ffffffffb1df2b33>] _raw_spin_unlock_irqrestore+0x63/0x80 hardirqs last disabled at (139909): [<ffffffffb19bd03d>] trace_drop_common.constprop.0+0x26d/0x290 softirqs last enabled at (139892): [<ffffffffb07a1083>] __local_bh_enable_ip+0x103/0x170 softirqs last disabled at (139898): [<ffffffffb0909b33>] rcu_cpu_kthread+0x93/0x1f0 Preemption disabled at: [<ffffffffb1de786b>] rt_mutex_slowunlock+0xab/0x2e0 CPU: 47 PID: 449 Comm: rcuc/47 Not tainted 6.9.0-rc2-rt1+ #7 Hardware name: Dell Inc. PowerEdge R650/0Y2G81, BIOS 1.6.5 04/15/2022 Call Trace: <TASK> dump_stack_lvl+0x8c/0xd0 dump_stack+0x14/0x20 __might_resched+0x21e/0x2f0 rt_spin_lock+0x5e/0x130 ? trace_drop_common.constprop.0+0xb5/0x290 ? skb_queue_purge_reason.part.0+0x1bf/0x230 trace_drop_common.constprop.0+0xb5/0x290 ? preempt_count_sub+0x1c/0xd0 ? _raw_spin_unlock_irqrestore+0x4a/0x80 ? __pfx_trace_drop_common.constprop.0+0x10/0x10 ? rt_mutex_slowunlock+0x26a/0x2e0 ? skb_queue_purge_reason.part.0+0x1bf/0x230 ? __pfx_rt_mutex_slowunlock+0x10/0x10 ? skb_queue_purge_reason.part.0+0x1bf/0x230 trace_kfree_skb_hit+0x15/0x20 trace_kfree_skb+0xe9/0x150 kfree_skb_reason+0x7b/0x110 skb_queue_purge_reason.part.0+0x1bf/0x230 ? __pfx_skb_queue_purge_reason.part.0+0x10/0x10 ? mark_lock.part.0+0x8a/0x520 ...
trace_drop_common() also disables interrupts, but this is a minor issue because we could easily replace it with a local_lock.
Replace the spin_lock with raw_spin_lock to avoid sleeping in atomic context.
Signed-off-by: Wander Lairson Costa wander@redhat.com Reported-by: Hu Chunyu chuhu@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/drop_monitor.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 8e0a90b45df22..522657b597d9f 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -72,7 +72,7 @@ struct net_dm_hw_entries { };
struct per_cpu_dm_data { - spinlock_t lock; /* Protects 'skb', 'hw_entries' and + raw_spinlock_t lock; /* Protects 'skb', 'hw_entries' and * 'send_timer' */ union { @@ -166,9 +166,9 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) err: mod_timer(&data->send_timer, jiffies + HZ / 10); out: - spin_lock_irqsave(&data->lock, flags); + raw_spin_lock_irqsave(&data->lock, flags); swap(data->skb, skb); - spin_unlock_irqrestore(&data->lock, flags); + raw_spin_unlock_irqrestore(&data->lock, flags);
if (skb) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; @@ -223,7 +223,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
local_irq_save(flags); data = this_cpu_ptr(&dm_cpu_data); - spin_lock(&data->lock); + raw_spin_lock(&data->lock); dskb = data->skb;
if (!dskb) @@ -257,7 +257,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location) }
out: - spin_unlock_irqrestore(&data->lock, flags); + raw_spin_unlock_irqrestore(&data->lock, flags); }
static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, @@ -312,9 +312,9 @@ net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data) mod_timer(&hw_data->send_timer, jiffies + HZ / 10); }
- spin_lock_irqsave(&hw_data->lock, flags); + raw_spin_lock_irqsave(&hw_data->lock, flags); swap(hw_data->hw_entries, hw_entries); - spin_unlock_irqrestore(&hw_data->lock, flags); + raw_spin_unlock_irqrestore(&hw_data->lock, flags);
return hw_entries; } @@ -446,7 +446,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, return;
hw_data = this_cpu_ptr(&dm_hw_cpu_data); - spin_lock_irqsave(&hw_data->lock, flags); + raw_spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries;
if (!hw_entries) @@ -475,7 +475,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, }
out: - spin_unlock_irqrestore(&hw_data->lock, flags); + raw_spin_unlock_irqrestore(&hw_data->lock, flags); }
static const struct net_dm_alert_ops net_dm_alert_summary_ops = { @@ -1658,7 +1658,7 @@ static struct notifier_block dropmon_net_notifier = {
static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data) { - spin_lock_init(&data->lock); + raw_spin_lock_init(&data->lock); skb_queue_head_init(&data->drop_queue); u64_stats_init(&data->stats.syncp); }