[PATCH] Debug: Gather more information about AMD iommu device

[Jiang Liu]

Hi Boris,
	From the log file, we got to know that the NULL pointer dereference
was caused by AMD IOMMU device. For normal MSI-enabled PCI devices, we get
valid irq numbers such as:
[   74.661170] ahci 0000:04:00.0: irqdomain: freeze msi 1 irq28
[   74.661297] radeon 0000:01:00.0: irqdomain: freeze msi 1 irq47
	But for AMD IOMMU device, we got an invalid irq number(0) after
enabling MSI as:
[   74.662488] pci 0000:00:00.2: irqdomain: freeze msi 1 irq0
which then caused NULL pointer deference when __pci_restore_msi_state()
gets called by system resume code.
	So we need to figure out why we got irq number 0 after enabling
MSI for AMD IOMMU device. The only hint I got is that iommu driver just
grabbing the PCI device without providing a PCI device driver for IOMMU
PCI device, we have solved a similar case for eata driver. So could you
please help to apply this debug patch to gather more info and send me
/proc/interrupts?
Thanks!
Gerry

Signed-off-by: Jiang Liu <jiang.liu@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/apic/msi.c     |    6 +++++-
 drivers/iommu/amd_iommu_init.c |    8 ++++++++
 drivers/pci/msi.c              |    4 ++++
 kernel/irq/msi.c               |    1 +
 4 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 5f1feb6854af..050dcf25577c 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -71,6 +71,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	struct irq_domain *domain;
 	struct irq_alloc_info info;
+	int ret;
 
 	init_irq_alloc_info(&info, NULL);
 	info.type = X86_IRQ_ALLOC_TYPE_MSI;
@@ -82,7 +83,10 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (domain == NULL)
 		return -ENOSYS;
 
-	return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+	ret = pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+	dev_warn(&dev->dev, "irqdomain: domain %p, def_domain %p ret%d\n",
+		 domain, msi_default_domain, ret);
+	return ret;
 }
 
 void native_teardown_msi_irq(unsigned int irq)
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 5ef347a13cb5..23cd4d861dba 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1416,7 +1416,11 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 {
 	int r;
 
+	dev_warn(&iommu->dev->dev, "irqdomain: before enabling MSI for msi%d, irq%d\n",
+		 iommu->dev->msi_enabled, iommu->dev->irq);
 	r = pci_enable_msi(iommu->dev);
+	dev_warn(&iommu->dev->dev, "irqdomain: after enabling MSI for msi%d, irq%d\n",
+		 iommu->dev->msi_enabled, iommu->dev->irq);
 	if (r)
 		return r;
 
@@ -1428,6 +1432,8 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 
 	if (r) {
 		pci_disable_msi(iommu->dev);
+		dev_warn(&iommu->dev->dev, "irqdomain: failed to enable MSI for msi%d, irq%d\n",
+			 iommu->dev->msi_enabled, iommu->dev->irq);
 		return r;
 	}
 
@@ -1440,6 +1446,8 @@ static int iommu_init_msi(struct amd_iommu *iommu)
 {
 	int ret;
 
+	dev_warn(&iommu->dev->dev, "irqdomain: init msi for iommu %p int_enabled%d\n",
+		 iommu, iommu->int_enabled);
 	if (iommu->int_enabled)
 		goto enable_faults;
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index d4497141d083..0301a18663b0 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -602,6 +602,8 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 	int ret;
 	unsigned mask;
 
+	dev_warn(&dev->dev, "irqdomain: enable msi cap msi_enabled%d irq%d\n",
+		 dev->msi_enabled, dev->irq);
 	pci_msi_set_enable(dev, 0);	/* Disable MSI during set up */
 
 	entry = msi_setup_entry(dev, nvec);
@@ -643,6 +645,8 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 
 	pcibios_free_irq(dev);
 	dev->irq = entry->irq;
+	dev_warn(&dev->dev, "irqdomain: succeed to enable msi cap msi_enabled%d irq%d\n",
+		 dev->msi_enabled, dev->irq);
 	return 0;
 }
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 7e6512b9dc1f..535cf59bc5a7 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -298,6 +298,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			return ret;
 		}
 
+		dev_warn(dev, "irqdomain: allocated virq%d\n", virq);
 		for (i = 0; i < desc->nvec_used; i++)
 			irq_set_msi_desc_off(virq, i, desc);
 	}
-- 
1.7.10.4


--------------020904080203070301050609--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/