nvmet: pci-epf: Avoid RCU stalls under heavy workload

The delayed work item function nvmet_pci_epf_poll_sqs_work() polls all
submission queues and keeps running in a loop as long as commands are
being submitted by the host. Depending on the preemption configuration
of the kernel, under heavy command workload, this function can thus run
for more than RCU_CPU_STALL_TIMEOUT seconds, leading to a RCU stall:

 rcu: INFO: rcu_sched self-detected stall on CPU
 rcu:   5-....: (20998 ticks this GP) idle=4244/1/0x4000000000000000 softirq=301/301 fqs=5132
 rcu:   (t=21000 jiffies g=-443 q=12 ncpus=8)
 CPU: 5 UID: 0 PID: 82 Comm: kworker/5:1 Not tainted 6.14.0-rc2 #1
 Hardware name: Radxa ROCK 5B (DT)
 Workqueue: events nvmet_pci_epf_poll_sqs_work [nvmet_pci_epf]
 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : dw_edma_device_tx_status+0xb8/0x130
 lr : dw_edma_device_tx_status+0x9c/0x130
 sp : ffff800080b5bbb0
 x29: ffff800080b5bbb0 x28: ffff0331c5c78400 x27: ffff0331c1cd1960
 x26: ffff0331c0e39010 x25: ffff0331c20e4000 x24: ffff0331c20e4a90
 x23: 0000000000000000 x22: 0000000000000001 x21: 00000000005aca33
 x20: ffff800080b5bc30 x19: ffff0331c123e370 x18: 000000000ab29e62
 x17: ffffb2a878c9c118 x16: ffff0335bde82040 x15: 0000000000000000
 x14: 000000000000017b x13: 00000000ee601780 x12: 0000000000000018
 x11: 0000000000000000 x10: 0000000000000001 x9 : 0000000000000040
 x8 : 00000000ee601780 x7 : 0000000105c785c0 x6 : ffff0331c1027d80
 x5 : 0000000001ee7ad6 x4 : ffff0335bdea16c0 x3 : ffff0331c123e438
 x2 : 00000000005aca33 x1 : 0000000000000000 x0 : ffff0331c123e410
 Call trace:
  dw_edma_device_tx_status+0xb8/0x130 (P)
  dma_sync_wait+0x60/0xbc
  nvmet_pci_epf_dma_transfer+0x128/0x264 [nvmet_pci_epf]
  nvmet_pci_epf_poll_sqs_work+0x2a0/0x2e0 [nvmet_pci_epf]
  process_one_work+0x144/0x390
  worker_thread+0x27c/0x458
  kthread+0xe8/0x19c
  ret_from_fork+0x10/0x20

The solution for this is simply to explicitly allow rescheduling using
cond_resched(). However, since doing so for every loop of
nvmet_pci_epf_poll_sqs_work() significantly degrades performance
(for 4K random reads using 4 I/O queues, the maximum IOPS goes down from
137 KIOPS to 110 KIOPS), call cond_resched() every second to avoid the
RCU stalls.

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index b646a8f468ea9e4938fbf3f228c4e120efc56390..565d2bd36dcde44fb00725fc0a8ed8ea130638e7 100644 (file)
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1694,6 +1694,7 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work)
        struct nvmet_pci_epf_ctrl *ctrl =
                container_of(work, struct nvmet_pci_epf_ctrl, poll_sqs.work);
        struct nvmet_pci_epf_queue *sq;
+       unsigned long limit = jiffies;
        unsigned long last = 0;
        int i, nr_sqs;
 
@@ -1708,6 +1709,16 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work)
                                nr_sqs++;
                }
 
+               /*
+                * If we have been running for a while, reschedule to let other
+                * tasks run and to avoid RCU stalls.
+                */
+               if (time_is_before_jiffies(limit + secs_to_jiffies(1))) {
+                       cond_resched();
+                       limit = jiffies;
+                       continue;
+               }
+
                if (nr_sqs) {
                        last = jiffies;
                        continue;