diff mbox

[v4] aerdrv: Move cper_print_aer() call out of interrupt context

Message ID 20130530142512.3404.74494.stgit@grignak.americas.hpqcorp.net (mailing list archive)
State New, archived
Delegated to: Bjorn Helgaas
Headers show

Commit Message

Lance Ortiz May 30, 2013, 2:25 p.m. UTC
The following warning was seen on 3.9 when a corrected PCIe error was being
handled by the AER subsystem.

WARNING: at .../drivers/pci/search.c:214 pci_get_dev_by_id+0x8a/0x90()

This occurred because a call to pci_get_domain_bus_and_slot() was added to
cper_print_pcie() to setup for the call to cper_print_aer().  The warning
showed up because cper_print_pcie() is called in an interrupt context and
pci_get* functions are not supposed to be called in that context.

The solution is to move the cper_print_aer() call out of the interrupt
context and into aer_recover_work_func() to avoid any warnings when calling
pci_get* functions.

v2 - Re-worded header text.  Removed prefix arg from cper_print_aer().
     Added TODO message in cper_print_aer().
v3 - Changed type of u8* to struct aer_capability_regs* in the code
     to avoid too much casting based on comment from Bjorn Helgaas.
v4 - Removed TODO message.  Does not have to do with what this patch
     is trying to fix.

Signed-off-by: Lance Ortiz <lance.ortiz@hp.com>
Acked-by: Borislav Petkov <bp@suse.de>
---

 drivers/acpi/apei/cper.c               |   18 ------------------
 drivers/acpi/apei/ghes.c               |    4 +++-
 drivers/pci/pcie/aer/aerdrv_core.c     |    5 ++++-
 drivers/pci/pcie/aer/aerdrv_errprint.c |    4 ++--
 include/linux/aer.h                    |    5 +++--
 5 files changed, 12 insertions(+), 24 deletions(-)


--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Tony Luck May 30, 2013, 6:12 p.m. UTC | #1
Ok - grabbed this version. Will see if I can tempt Linus with a "please pull"
tomorrow (when the commit is suitably aged).

By the way ... this meta-commit description:

> v2 - Re-worded header text.  Removed prefix arg from cper_print_aer().
>      Added TODO message in cper_print_aer().
> v3 - Changed type of u8* to struct aer_capability_regs* in the code
>      to avoid too much casting based on comment from Bjorn Helgaas.
> v4 - Removed TODO message.  Does not have to do with what this patch
>      is trying to fix.

belongs *after* the "---" past the sign-off & Acks ... then "git am" will
drop it from the commit message automatically

-Tony
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
index 1e5d8a4..8713229 100644
--- a/drivers/acpi/apei/cper.c
+++ b/drivers/acpi/apei/cper.c
@@ -250,10 +250,6 @@  static const char *cper_pcie_port_type_strs[] = {
 static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 			    const struct acpi_hest_generic_data *gdata)
 {
-#ifdef CONFIG_ACPI_APEI_PCIEAER
-	struct pci_dev *dev;
-#endif
-
 	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
 		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
 		       pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ?
@@ -285,20 +281,6 @@  static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 		printk(
 	"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
-#ifdef CONFIG_ACPI_APEI_PCIEAER
-	dev = pci_get_domain_bus_and_slot(pcie->device_id.segment,
-			pcie->device_id.bus, pcie->device_id.function);
-	if (!dev) {
-		pr_err("PCI AER Cannot get PCI device %04x:%02x:%02x.%d\n",
-			pcie->device_id.segment, pcie->device_id.bus,
-			pcie->device_id.slot, pcie->device_id.function);
-		return;
-	}
-	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO)
-		cper_print_aer(pfx, dev, gdata->error_severity,
-				(struct aer_capability_regs *) pcie->aer_info);
-	pci_dev_put(dev);
-#endif
 }
 
 static const char *apei_estatus_section_flag_strs[] = {
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index d668a8a..403baf4 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -454,7 +454,9 @@  static void ghes_do_proc(struct ghes *ghes,
 				aer_severity = cper_severity_to_aer(sev);
 				aer_recover_queue(pcie_err->device_id.segment,
 						  pcie_err->device_id.bus,
-						  devfn, aer_severity);
+						  devfn, aer_severity,
+						  (struct aer_capability_regs *)
+						  pcie_err->aer_info);
 			}
 
 		}
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 564d97f..120549a 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -582,6 +582,7 @@  struct aer_recover_entry
 	u8	devfn;
 	u16	domain;
 	int	severity;
+	struct aer_capability_regs *regs;
 };
 
 static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry,
@@ -595,7 +596,7 @@  static DEFINE_SPINLOCK(aer_recover_ring_lock);
 static DECLARE_WORK(aer_recover_work, aer_recover_work_func);
 
 void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
-		       int severity)
+		       int severity, struct aer_capability_regs *aer_regs)
 {
 	unsigned long flags;
 	struct aer_recover_entry entry = {
@@ -603,6 +604,7 @@  void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 		.devfn		= devfn,
 		.domain		= domain,
 		.severity	= severity,
+		.regs		= aer_regs,
 	};
 
 	spin_lock_irqsave(&aer_recover_ring_lock, flags);
@@ -629,6 +631,7 @@  static void aer_recover_work_func(struct work_struct *work)
 			       PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
 			continue;
 		}
+		cper_print_aer(pdev, entry.severity, entry.regs);
 		do_recovery(pdev, entry.severity);
 		pci_dev_put(pdev);
 	}
diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
index 5ab1425..2c7c9f5 100644
--- a/drivers/pci/pcie/aer/aerdrv_errprint.c
+++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
@@ -220,7 +220,7 @@  int cper_severity_to_aer(int cper_severity)
 }
 EXPORT_SYMBOL_GPL(cper_severity_to_aer);
 
-void cper_print_aer(const char *prefix, struct pci_dev *dev, int cper_severity,
+void cper_print_aer(struct pci_dev *dev, int cper_severity,
 		    struct aer_capability_regs *aer)
 {
 	int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0;
@@ -244,7 +244,7 @@  void cper_print_aer(const char *prefix, struct pci_dev *dev, int cper_severity,
 	agent = AER_GET_AGENT(aer_severity, status);
 	dev_err(&dev->dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n",
 	       status, mask);
-	cper_print_bits(prefix, status, status_strs, status_strs_size);
+	cper_print_bits("", status, status_strs, status_strs_size);
 	dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n",
 	       aer_error_layer[layer], aer_agent_string[agent]);
 	if (aer_severity != AER_CORRECTABLE)
diff --git a/include/linux/aer.h b/include/linux/aer.h
index ec10e1b..737f90a 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -49,10 +49,11 @@  static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 #endif
 
-extern void cper_print_aer(const char *prefix, struct pci_dev *dev,
+extern void cper_print_aer(struct pci_dev *dev,
 			   int cper_severity, struct aer_capability_regs *aer);
 extern int cper_severity_to_aer(int cper_severity);
 extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
-			      int severity);
+			      int severity,
+			      struct aer_capability_regs *aer_regs);
 #endif //_AER_H_