x86/PCI: VMD: Use lock save/restore in interrupt enable path

Enabling interrupts may result in an interrupt raised and serviced while
VMD holds a lock, resulting in contention with the spin lock held while
enabling interrupts.

The solution is to disable preemption and save/restore the state during
interrupt enable and disable.

Fixes lockdep:

  ======================================================
  [ INFO: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected ]
  4.6.0-2016-06-16-lockdep+ #47 Tainted: G            E
  ------------------------------------------------------
  kworker/0:1/447 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
   (list_lock){+.+...}, at: [<ffffffffa04eb8fc>] vmd_irq_enable+0x3c/0x70 [vmd]

  and this task is already holding:
   (&irq_desc_lock_class){-.-...}, at: [<ffffffff810e1ff6>] __setup_irq+0xa6/0x610
  which would create a new lock dependency:
   (&irq_desc_lock_class){-.-...} -> (list_lock){+.+...}

  but this new dependency connects a HARDIRQ-irq-safe lock:
   (&irq_desc_lock_class){-.-...}
  ... which became HARDIRQ-irq-safe at:
    [<ffffffff810c9f21>] __lock_acquire+0x981/0xe00
    [<ffffffff810cb039>] lock_acquire+0x119/0x220
    [<ffffffff8167294d>] _raw_spin_lock+0x3d/0x80
    [<ffffffff810e36d4>] handle_level_irq+0x24/0x110
    [<ffffffff8101f20a>] handle_irq+0x1a/0x30
    [<ffffffff81675fc1>] do_IRQ+0x61/0x120
    [<ffffffff8167404c>] ret_from_intr+0x0/0x20
    [<ffffffff81672e30>] _raw_spin_unlock_irqrestore+0x40/0x60
    [<ffffffff810e21ee>] __setup_irq+0x29e/0x610
    [<ffffffff810e25a1>] setup_irq+0x41/0x90
    [<ffffffff81f5777f>] setup_default_timer_irq+0x1e/0x20
    [<ffffffff81f57798>] hpet_time_init+0x17/0x19
    [<ffffffff81f5775a>] x86_late_time_init+0xa/0x11
    [<ffffffff81f51e9b>] start_kernel+0x382/0x436
    [<ffffffff81f51308>] x86_64_start_reservations+0x2a/0x2c
    [<ffffffff81f51445>] x86_64_start_kernel+0x13b/0x14a

  to a HARDIRQ-irq-unsafe lock:
   (list_lock){+.+...}
  ... which became HARDIRQ-irq-unsafe at:
  ...  [<ffffffff810c9d8e>] __lock_acquire+0x7ee/0xe00
    [<ffffffff810cb039>] lock_acquire+0x119/0x220
    [<ffffffff8167294d>] _raw_spin_lock+0x3d/0x80
    [<ffffffffa04eba42>] vmd_msi_init+0x72/0x150 [vmd]
    [<ffffffff810e8597>] msi_domain_alloc+0xb7/0x140
    [<ffffffff810e6b10>] irq_domain_alloc_irqs_recursive+0x40/0xa0
    [<ffffffff810e6cea>] __irq_domain_alloc_irqs+0x14a/0x330
    [<ffffffff810e8a8c>] msi_domain_alloc_irqs+0x8c/0x1d0
    [<ffffffff813ca4e3>] pci_msi_setup_msi_irqs+0x43/0x70
    [<ffffffff813cada1>] pci_enable_msi_range+0x131/0x280
    [<ffffffff813bf5e0>] pcie_port_device_register+0x320/0x4e0
    [<ffffffff813bf9a4>] pcie_portdrv_probe+0x34/0x60
    [<ffffffff813b0e85>] local_pci_probe+0x45/0xa0
    [<ffffffff813b226b>] pci_device_probe+0xdb/0x130
    [<ffffffff8149e3cc>] driver_probe_device+0x22c/0x440
    [<ffffffff8149e774>] __device_attach_driver+0x94/0x110
    [<ffffffff8149bfad>] bus_for_each_drv+0x5d/0x90
    [<ffffffff8149e030>] __device_attach+0xc0/0x140
    [<ffffffff8149e0c0>] device_attach+0x10/0x20
    [<ffffffff813a77f7>] pci_bus_add_device+0x47/0x90
    [<ffffffff813a7879>] pci_bus_add_devices+0x39/0x70
    [<ffffffff813aaba7>] pci_rescan_bus+0x27/0x30
    [<ffffffffa04ec1af>] vmd_probe+0x68f/0x76c [vmd]
    [<ffffffff813b0e85>] local_pci_probe+0x45/0xa0
    [<ffffffff81088064>] work_for_cpu_fn+0x14/0x20
    [<ffffffff8108c244>] process_one_work+0x1f4/0x740
    [<ffffffff8108c9c6>] worker_thread+0x236/0x4f0
    [<ffffffff810935c2>] kthread+0xf2/0x110
    [<ffffffff816738f2>] ret_from_fork+0x22/0x50

  other info that might help us debug this:

   Possible interrupt unsafe locking scenario:

	 CPU0                    CPU1
	 ----                    ----
    lock(list_lock);
				 local_irq_disable();
				 lock(&irq_desc_lock_class);
				 lock(list_lock);
    <Interrupt>
      lock(&irq_desc_lock_class);

   *** DEADLOCK ***

Signed-off-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Keith Busch <keith.busch@intel.com>

diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c
index 3519a1578752ac7f04bd57435dba0c1ad9cad5bd..7aa80dc214453ea14476e947bc1c4677f65aec1f 100644 (file)
--- a/arch/x86/pci/vmd.c
+++ b/arch/x86/pci/vmd.c
@@ -119,10 +119,11 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 static void vmd_irq_enable(struct irq_data *data)
 {
        struct vmd_irq *vmdirq = data->chip_data;
+       unsigned long flags;
 
-       raw_spin_lock(&list_lock);
+       raw_spin_lock_irqsave(&list_lock, flags);
        list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
-       raw_spin_unlock(&list_lock);
+       raw_spin_unlock_irqrestore(&list_lock, flags);
 
        data->chip->irq_unmask(data);
 }
@@ -130,13 +131,14 @@ static void vmd_irq_enable(struct irq_data *data)
 static void vmd_irq_disable(struct irq_data *data)
 {
        struct vmd_irq *vmdirq = data->chip_data;
+       unsigned long flags;
 
        data->chip->irq_mask(data);
 
-       raw_spin_lock(&list_lock);
+       raw_spin_lock_irqsave(&list_lock, flags);
        list_del_rcu(&vmdirq->node);
        INIT_LIST_HEAD_RCU(&vmdirq->node);
-       raw_spin_unlock(&list_lock);
+       raw_spin_unlock_irqrestore(&list_lock, flags);
 }
 
 /*
@@ -170,13 +172,14 @@ static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info,
 static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd)
 {
        int i, best = 0;
+       unsigned long flags;
 
-       raw_spin_lock(&list_lock);
+       raw_spin_lock_irqsave(&list_lock, flags);
        for (i = 1; i < vmd->msix_count; i++)
                if (vmd->irqs[i].count < vmd->irqs[best].count)
                        best = i;
        vmd->irqs[best].count++;
-       raw_spin_unlock(&list_lock);
+       raw_spin_unlock_irqrestore(&list_lock, flags);
 
        return &vmd->irqs[best];
 }
@@ -204,11 +207,12 @@ static void vmd_msi_free(struct irq_domain *domain,
                        struct msi_domain_info *info, unsigned int virq)
 {
        struct vmd_irq *vmdirq = irq_get_chip_data(virq);
+       unsigned long flags;
 
        /* XXX: Potential optimization to rebalance */
-       raw_spin_lock(&list_lock);
+       raw_spin_lock_irqsave(&list_lock, flags);
        vmdirq->irq->count--;
-       raw_spin_unlock(&list_lock);
+       raw_spin_unlock_irqrestore(&list_lock, flags);
 
        kfree_rcu(vmdirq, rcu);
 }