[PATCH 4/5] iommu/vt-d: Fix recursive lock issue in iommu_flush_dev_iotlb()
Lucas De Marchi
lucas.demarchi at intel.com
Fri Aug 26 16:56:04 UTC 2022
From: Lu Baolu <baolu.lu at linux.intel.com>
The per domain spinlock is acquired in iommu_flush_dev_iotlb(), which
is possbile to be called in the interrupt context. For example, the
drm-intel's CI system got completely blocked with below error:
WARNING: inconsistent lock state
6.0.0-rc1-CI_DRM_11990-g6590d43d39b9+ #1 Not tainted
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
swapper/6/0 [HC0[0]:SC1[1]:HE1:SE0] takes:
ffff88810440d678 (&domain->lock){+.?.}-{2:2}, at: iommu_flush_dev_iotlb.part.61+0x23/0x80
{SOFTIRQ-ON-W} state was registered at:
lock_acquire+0xd3/0x310
_raw_spin_lock+0x2a/0x40
domain_update_iommu_cap+0x20b/0x2c0
intel_iommu_attach_device+0x5bd/0x860
__iommu_attach_device+0x18/0xe0
bus_iommu_probe+0x1f3/0x2d0
bus_set_iommu+0x82/0xd0
intel_iommu_init+0xe45/0x102a
pci_iommu_init+0x9/0x31
do_one_initcall+0x53/0x2f0
kernel_init_freeable+0x18f/0x1e1
kernel_init+0x11/0x120
ret_from_fork+0x1f/0x30
irq event stamp: 162354
hardirqs last enabled at (162354): [<ffffffff81b59274>] _raw_spin_unlock_irqrestore+0x54/0x70
hardirqs last disabled at (162353): [<ffffffff81b5901b>] _raw_spin_lock_irqsave+0x4b/0x50
softirqs last enabled at (162338): [<ffffffff81e00323>] __do_softirq+0x323/0x48e
softirqs last disabled at (162349): [<ffffffff810c1588>] irq_exit_rcu+0xb8/0xe0
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&domain->lock);
<Interrupt>
lock(&domain->lock);
*** DEADLOCK ***
1 lock held by swapper/6/0:
This coverts the spin_lock/unlock() into the irq save/restore varieties
to fix the recursive locking issues.
Fixes: ffd5869d93530 ("iommu/vt-d: Replace spin_lock_irqsave() with spin_lock()")
Signed-off-by: Lu Baolu <baolu.lu at linux.intel.com>
Acked-by: Lucas De Marchi <lucas.demarchi at intel.com>
Link: https://lore.kernel.org/r/20220817025650.3253959-1-baolu.lu@linux.intel.com
---
drivers/iommu/intel/iommu.c | 39 ++++++++++++++++++++++---------------
1 file changed, 23 insertions(+), 16 deletions(-)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 743ca1f7a752..1ab63a8ef4c6 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -513,8 +513,9 @@ static int domain_update_device_node(struct dmar_domain *domain)
{
struct device_domain_info *info;
int nid = NUMA_NO_NODE;
+ unsigned long flags;
- spin_lock(&domain->lock);
+ spin_lock_irqsave(&domain->lock, flags);
list_for_each_entry(info, &domain->devices, link) {
/*
* There could possibly be multiple device numa nodes as devices
@@ -526,7 +527,7 @@ static int domain_update_device_node(struct dmar_domain *domain)
if (nid != NUMA_NO_NODE)
break;
}
- spin_unlock(&domain->lock);
+ spin_unlock_irqrestore(&domain->lock, flags);
return nid;
}
@@ -1360,19 +1361,20 @@ iommu_support_dev_iotlb(struct dmar_domain *domain, struct intel_iommu *iommu,
u8 bus, u8 devfn)
{
struct device_domain_info *info;
+ unsigned long flags;
if (!iommu->qi)
return NULL;
- spin_lock(&domain->lock);
+ spin_lock_irqsave(&domain->lock, flags);
list_for_each_entry(info, &domain->devices, link) {
if (info->iommu == iommu && info->bus == bus &&
info->devfn == devfn) {
- spin_unlock(&domain->lock);
+ spin_unlock_irqrestore(&domain->lock, flags);
return info->ats_supported ? info : NULL;
}
}
- spin_unlock(&domain->lock);
+ spin_unlock_irqrestore(&domain->lock, flags);
return NULL;
}
@@ -1381,8 +1383,9 @@ static void domain_update_iotlb(struct dmar_domain *domain)
{
struct device_domain_info *info;
bool has_iotlb_device = false;
+ unsigned long flags;
- spin_lock(&domain->lock);
+ spin_lock_irqsave(&domain->lock, flags);
list_for_each_entry(info, &domain->devices, link) {
if (info->ats_enabled) {
has_iotlb_device = true;
@@ -1390,7 +1393,7 @@ static void domain_update_iotlb(struct dmar_domain *domain)
}
}
domain->has_iotlb_device = has_iotlb_device;
- spin_unlock(&domain->lock);
+ spin_unlock_irqrestore(&domain->lock, flags);
}
static void iommu_enable_dev_iotlb(struct device_domain_info *info)
@@ -1482,14 +1485,15 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
u64 addr, unsigned mask)
{
struct device_domain_info *info;
+ unsigned long flags;
if (!domain->has_iotlb_device)
return;
- spin_lock(&domain->lock);
+ spin_lock_irqsave(&domain->lock, flags);
list_for_each_entry(info, &domain->devices, link)
__iommu_flush_dev_iotlb(info, addr, mask);
- spin_unlock(&domain->lock);
+ spin_unlock_irqrestore(&domain->lock, flags);
}
static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
@@ -2451,6 +2455,7 @@ static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
{
struct device_domain_info *info = dev_iommu_priv_get(dev);
struct intel_iommu *iommu;
+ unsigned long flags;
u8 bus, devfn;
int ret;
@@ -2462,9 +2467,9 @@ static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
if (ret)
return ret;
info->domain = domain;
- spin_lock(&domain->lock);
+ spin_lock_irqsave(&domain->lock, flags);
list_add(&info->link, &domain->devices);
- spin_unlock(&domain->lock);
+ spin_unlock_irqrestore(&domain->lock, flags);
/* PASID table is mandatory for a PCI device in scalable mode. */
if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
@@ -4088,6 +4093,7 @@ static void dmar_remove_one_dev_info(struct device *dev)
struct device_domain_info *info = dev_iommu_priv_get(dev);
struct dmar_domain *domain = info->domain;
struct intel_iommu *iommu = info->iommu;
+ unsigned long flags;
if (!dev_is_real_dma_subdevice(info->dev)) {
if (dev_is_pci(info->dev) && sm_supported(iommu))
@@ -4099,9 +4105,9 @@ static void dmar_remove_one_dev_info(struct device *dev)
intel_pasid_free_table(info->dev);
}
- spin_lock(&domain->lock);
+ spin_lock_irqsave(&domain->lock, flags);
list_del(&info->link);
- spin_unlock(&domain->lock);
+ spin_unlock_irqrestore(&domain->lock, flags);
domain_detach_iommu(domain, iommu);
info->domain = NULL;
@@ -4420,19 +4426,20 @@ static void domain_set_force_snooping(struct dmar_domain *domain)
static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
{
struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+ unsigned long flags;
if (dmar_domain->force_snooping)
return true;
- spin_lock(&dmar_domain->lock);
+ spin_lock_irqsave(&dmar_domain->lock, flags);
if (!domain_support_force_snooping(dmar_domain)) {
- spin_unlock(&dmar_domain->lock);
+ spin_unlock_irqrestore(&dmar_domain->lock, flags);
return false;
}
domain_set_force_snooping(dmar_domain);
dmar_domain->force_snooping = true;
- spin_unlock(&dmar_domain->lock);
+ spin_unlock_irqrestore(&dmar_domain->lock, flags);
return true;
}
--
2.37.2
More information about the Intel-gfx-trybot
mailing list