diff mbox

[v7,2/3] aerdrv: Enhanced AER logging

Message ID 20121204210312.4515.13415.stgit@grignak.americas.hpqcorp.net (mailing list archive)
State New, archived
Delegated to: Bjorn Helgaas
Headers show

Commit Message

Lance Ortiz Dec. 4, 2012, 9:03 p.m. UTC 
This patch will provide a more reliable and easy way for user-space
applications to have access to AER logs rather than reading them from the
message buffer. It also provides a way to notify user-space when an AER
event occurs.

The aer driver is updated to generate a trace event of function 'aer_event'
when a PCIe error is reported over the AER interface.  The trace event was
added to both the interrupt based aer path and the firmware first path.

v1-v2 fix compile errors in ifdefs.
v2-v3 Update to new location of trace header. Update print to remove
warning.
v3-v4 Reworked logic when getting ready to call cper_print_aer
v6-v7 Change print from pr_info to pr_err if !dev
Signed-off-by: Lance Ortiz <lance.ortiz@hp.com>
---

 drivers/acpi/apei/cper.c               |   19 ++++++++++++++++---
 drivers/pci/pcie/aer/aerdrv_errprint.c |   10 +++++++++-
 include/linux/aer.h                    |    2 +-
 3 files changed, 26 insertions(+), 5 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

Borislav Petkov Dec. 5, 2012, 2:32 p.m. UTC | #1 
On Tue, Dec 04, 2012 at 02:03:12PM -0700, Lance Ortiz wrote:
> This patch will provide a more reliable and easy way for user-space
> applications to have access to AER logs rather than reading them from the
> message buffer. It also provides a way to notify user-space when an AER
> event occurs.
> 
> The aer driver is updated to generate a trace event of function 'aer_event'
> when a PCIe error is reported over the AER interface.  The trace event was
> added to both the interrupt based aer path and the firmware first path.
> 
> v1-v2 fix compile errors in ifdefs.
> v2-v3 Update to new location of trace header. Update print to remove
> warning.
> v3-v4 Reworked logic when getting ready to call cper_print_aer
> v6-v7 Change print from pr_info to pr_err if !dev
> Signed-off-by: Lance Ortiz <lance.ortiz@hp.com>
> ---
> 
>  drivers/acpi/apei/cper.c               |   19 ++++++++++++++++---
>  drivers/pci/pcie/aer/aerdrv_errprint.c |   10 +++++++++-
>  include/linux/aer.h                    |    2 +-
>  3 files changed, 26 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
> index e6defd8..b2f695b 100644
> --- a/drivers/acpi/apei/cper.c
> +++ b/drivers/acpi/apei/cper.c
> @@ -29,6 +29,7 @@
>  #include <linux/time.h>
>  #include <linux/cper.h>
>  #include <linux/acpi.h>
> +#include <linux/pci.h>
>  #include <linux/aer.h>
>  
>  /*
> @@ -249,6 +250,10 @@ 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) ?
> @@ -281,10 +286,18 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
>  	"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
>  	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
>  #ifdef CONFIG_ACPI_APEI_PCIEAER
> -	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) {
> -		struct aer_capability_regs *aer_regs = (void *)pcie->aer_info;
> -		cper_print_aer(pfx, gdata->error_severity, aer_regs);
> +	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(dev, gdata->error_severity,
> +				(struct aer_capability_regs *) pcie->aer_info);
> +	pci_dev_put(dev);
>  #endif
>  }
>  
> diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
> index 3ea5173..34d96e4 100644
> --- a/drivers/pci/pcie/aer/aerdrv_errprint.c
> +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
> @@ -23,6 +23,9 @@
>  
>  #include "aerdrv.h"
>  
> +#define CREATE_TRACE_POINTS
> +#include <trace/events/ras.h>
> +
>  #define AER_AGENT_RECEIVER		0
>  #define AER_AGENT_REQUESTER		1
>  #define AER_AGENT_COMPLETER		2
> @@ -194,6 +197,8 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  	if (info->id && info->error_dev_num > 1 && info->id == id)
>  		printk("%s""  Error of this Agent(%04x) is reported first\n",
>  			prefix, id);
> +	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
> +			info->severity);
>  }
>  
>  void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
> @@ -217,12 +222,13 @@ int cper_severity_to_aer(int cper_severity)
>  }
>  EXPORT_SYMBOL_GPL(cper_severity_to_aer);
>  
> -void cper_print_aer(const char *prefix, 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;
>  	u32 status, mask;
>  	const char **status_strs;
> +	char *prefix = NULL;

What are you doing here? You dropped the 'prefix' argument being passed
down in this function and are defining a local variable of the same name
which is used in the function later:

        printk("%s""aer_status: 0x%08x, aer_mask: 0x%08x\n",
               prefix, status, mask);

WTF?

Also, this function cper_print_aer() is too crammed and could use a
little spacing out between lines belonging logically together.

Finally, please wait a couple of days before resending the patchset
so that you can collect *all* feedback and can save yourself needless
iterations.

Thanks.
Ortiz, Lance E Dec. 5, 2012, 4:14 p.m. UTC | #2 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--
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
Borislav Petkov Dec. 5, 2012, 4:30 p.m. UTC | #3 
On Wed, Dec 05, 2012 at 04:14:14PM +0000, Ortiz, Lance E wrote:
> I removed the prefix argument because it was never used by its caller
> and never set. The reason I added the prefix variable and set it to
> NULL was to help in breaking up the patch and adding it would help the
> intermittent patch build without changing too much code. I knew I was
> actually going to use the variable in patch 3.

No, the correct way to do that is to keep all changes that belong
logically together in a single patch for ease of reviewing and avoid
breakages. And in your case this should be pretty easy: simply move all
the 'prefix' touching code to patch #3 and you're done, AFAICT.

Thanks.
Bjorn Helgaas Dec. 27, 2012, 1:33 a.m. UTC | #4 
On Wed, Dec 5, 2012 at 9:30 AM, Borislav Petkov <bp@alien8.de> wrote:
> On Wed, Dec 05, 2012 at 04:14:14PM +0000, Ortiz, Lance E wrote:
>> I removed the prefix argument because it was never used by its caller
>> and never set. The reason I added the prefix variable and set it to
>> NULL was to help in breaking up the patch and adding it would help the
>> intermittent patch build without changing too much code. I knew I was
>> actually going to use the variable in patch 3.
>
> No, the correct way to do that is to keep all changes that belong
> logically together in a single patch for ease of reviewing and avoid
> breakages. And in your case this should be pretty easy: simply move all
> the 'prefix' touching code to patch #3 and you're done, AFAICT.

Lance, you didn't add all the "prefix" stuff in AER, but since you're
touching it, I think things will make more sense if you clean it up at
the same time.  There are a lot of printk() calls there that should be
converted to dev_printk().

I think I see why it was done that way -- it sticks either
KERN_WARNING or KERN_ERR at the beginning of the prefix, then uses
plain printk() later.  I guess that means you only have to pass around
the prefix argument, rather than both a "level" and a "struct pci_dev
*".  But I think it will be simpler overall to pass both and take
advantage of dev_printk() and stop emulating it.

Bjorn
--
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 e6defd8..b2f695b 100644
--- a/drivers/acpi/apei/cper.c
+++ b/drivers/acpi/apei/cper.c
@@ -29,6 +29,7 @@ 
 #include <linux/time.h>
 #include <linux/cper.h>
 #include <linux/acpi.h>
+#include <linux/pci.h>
 #include <linux/aer.h>
 
 /*
@@ -249,6 +250,10 @@  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) ?
@@ -281,10 +286,18 @@  static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 #ifdef CONFIG_ACPI_APEI_PCIEAER
-	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) {
-		struct aer_capability_regs *aer_regs = (void *)pcie->aer_info;
-		cper_print_aer(pfx, gdata->error_severity, aer_regs);
+	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(dev, gdata->error_severity,
+				(struct aer_capability_regs *) pcie->aer_info);
+	pci_dev_put(dev);
 #endif
 }
 
diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
index 3ea5173..34d96e4 100644
--- a/drivers/pci/pcie/aer/aerdrv_errprint.c
+++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
@@ -23,6 +23,9 @@ 
 
 #include "aerdrv.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/ras.h>
+
 #define AER_AGENT_RECEIVER		0
 #define AER_AGENT_REQUESTER		1
 #define AER_AGENT_COMPLETER		2
@@ -194,6 +197,8 @@  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	if (info->id && info->error_dev_num > 1 && info->id == id)
 		printk("%s""  Error of this Agent(%04x) is reported first\n",
 			prefix, id);
+	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
+			info->severity);
 }
 
 void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
@@ -217,12 +222,13 @@  int cper_severity_to_aer(int cper_severity)
 }
 EXPORT_SYMBOL_GPL(cper_severity_to_aer);
 
-void cper_print_aer(const char *prefix, 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;
 	u32 status, mask;
 	const char **status_strs;
+	char *prefix = NULL;
 
 	aer_severity = cper_severity_to_aer(cper_severity);
 	if (aer_severity == AER_CORRECTABLE) {
@@ -259,5 +265,7 @@  void cper_print_aer(const char *prefix, int cper_severity,
 			*(tlp + 8), *(tlp + 15), *(tlp + 14),
 			*(tlp + 13), *(tlp + 12));
 	}
+	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+			aer_severity);
 }
 #endif
diff --git a/include/linux/aer.h b/include/linux/aer.h
index 544abdb..7b86dc6 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -49,7 +49,7 @@  static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 #endif
 
-extern void cper_print_aer(const char *prefix, int cper_severity,
+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,