[v2,2/8] PCI/AER: Use the same log level for all messages

Commit Message

Jon Pan-Doh Feb. 14, 2025, 2:35 a.m. UTC

From: Karolina Stolarek <[e-mail]>

When reporting an AER error, we check its type multiple times
to determine the log level for each message. Do this check only
in the top-level function and propagate the result down the call
chain. Make aer_print_port_info output to match the level of the
reported error.

Signed-off-by: Karolina Stolarek <[e-mail]>
Reviewed-by: Jon Pan-Doh <[e-mail]>
---
 drivers/pci/pci.h      |  2 +-
 drivers/pci/pcie/aer.c | 43 ++++++++++++++++++++++--------------------
 drivers/pci/pcie/dpc.c |  2 +-
 3 files changed, 25 insertions(+), 22 deletions(-)

Comments

Karolina Stolarek Feb. 17, 2025, 11:25 a.m. UTC | #1

On 14/02/2025 03:35, Jon Pan-Doh wrote:
> From: Karolina Stolarek <[e-mail]>
> 
> When reporting an AER error, we check its type multiple times
> to determine the log level for each message. Do this check only
> in the top-level function and propagate the result down the call
> chain. Make aer_print_port_info output to match the level of the
> reported error.
> 
> Signed-off-by: Karolina Stolarek <[e-mail]>
> Reviewed-by: Jon Pan-Doh <[e-mail]>
> ---
>   drivers/pci/pci.h      |  2 +-
>   drivers/pci/pcie/aer.c | 43 ++++++++++++++++++++++--------------------
>   drivers/pci/pcie/dpc.c |  2 +-
>   3 files changed, 25 insertions(+), 22 deletions(-)

(...)

> @@ -773,13 +772,13 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>   	info.mask = mask;
>   	info.first_error = PCI_ERR_CAP_FEP(aer->cap_control);
>   
> -	pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
> -	__aer_print_error(dev, &info);
> -	pci_err(dev, "aer_layer=%s, aer_agent=%s\n",
> +	aer_printk(level, dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
> +	__aer_print_error(dev, &info, level);
> +	aer_printk(level, dev, "aer_layer=%s, aer_agent=%s\n",
>   		aer_error_layer[layer], aer_agent_string[agent]);

It seems that the printk's alignment is wonky after the rebase. 
Checkpatch agrees with me here...

>   
>   	if (aer_severity != AER_CORRECTABLE)
> -		pci_err(dev, "aer_uncor_severity: 0x%08x\n",
> +		aer_printk(level, dev, "aer_uncor_severity: 0x%08x\n",
>   			aer->uncor_severity);
...and here

All the best,
Karolina

Jon Pan-Doh Feb. 19, 2025, 2:48 a.m. UTC | #2

On Mon, Feb 17, 2025 at 3:25 AM Karolina Stolarek
<[e-mail]> wrote:
> It seems that the printk's alignment is wonky after the rebase.
> Checkpatch agrees with me here...

Odd. It passed checkpatch for me. These are the commands I used:

{Kernel home dir}$ scripts/checkpatch.pl {diff (e.g. downloaded from Patchwork)}
{Kernel home dir}$ scripts/checkpatch.pl -f drivers/pci/pcie/aer.c

Maybe I'm not using it correctly. Could you paste your checkpatch
command/output?

Thanks,
Jon

Patch

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 01e51db8d285..8cb816ee5388 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -550,7 +550,7 @@  struct aer_err_info {
 };
 
 int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
-void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info, const char *level);
 
 int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2,
 		      unsigned int tlp_len, struct pcie_tlp_log *log);
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 9a8cc81d01e4..f1fdaa052cf6 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -670,20 +670,18 @@  static void pci_rootport_aer_stats_incr(struct pci_dev *pdev,
 }
 
 static void __aer_print_error(struct pci_dev *dev,
-			      struct aer_err_info *info)
+			      struct aer_err_info *info,
+			      const char *level)
 {
 	const char **strings;
 	unsigned long status = info->status & ~info->mask;
-	const char *level, *errmsg;
+	const char *errmsg;
 	int i;
 
-	if (info->severity == AER_CORRECTABLE) {
+	if (info->severity == AER_CORRECTABLE)
 		strings = aer_correctable_error_string;
-		level = KERN_WARNING;
-	} else {
+	else
 		strings = aer_uncorrectable_error_string;
-		level = KERN_ERR;
-	}
 
 	for_each_set_bit(i, &status, 32) {
 		errmsg = strings[i];
@@ -696,11 +694,11 @@  static void __aer_print_error(struct pci_dev *dev,
 	pci_dev_aer_stats_incr(dev, info);
 }
 
-void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info,
+		     const char *level)
 {
 	int layer, agent;
 	int id = pci_dev_id(dev);
-	const char *level;
 
 	if (!info->status) {
 		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
@@ -711,8 +709,6 @@  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	layer = AER_GET_LAYER_ERROR(info->severity, info->status);
 	agent = AER_GET_AGENT(info->severity, info->status);
 
-	level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR;
-
 	aer_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
 		   aer_error_severity_string[info->severity],
 		   aer_error_layer[layer], aer_agent_string[agent]);
@@ -720,7 +716,7 @@  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	aer_printk(level, dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
 		   dev->vendor, dev->device, info->status, info->mask);
 
-	__aer_print_error(dev, info);
+	__aer_print_error(dev, info, level);
 
 	if (info->tlp_header_valid)
 		pcie_print_tlp_log(dev, &info->tlp, dev_fmt("  "));
@@ -753,15 +749,18 @@  void pci_print_aer(struct pci_dev *dev, int aer_severity,
 {
 	int layer, agent, tlp_header_valid = 0;
 	u32 status, mask;
+	const char *level;
 	struct aer_err_info info;
 
 	if (aer_severity == AER_CORRECTABLE) {
 		status = aer->cor_status;
 		mask = aer->cor_mask;
+		level = KERN_WARNING;
 	} else {
 		status = aer->uncor_status;
 		mask = aer->uncor_mask;
 		tlp_header_valid = status & AER_LOG_TLP_MASKS;
+		level = KERN_ERR;
 	}
 
 	layer = AER_GET_LAYER_ERROR(aer_severity, status);
@@ -773,13 +772,13 @@  void pci_print_aer(struct pci_dev *dev, int aer_severity,
 	info.mask = mask;
 	info.first_error = PCI_ERR_CAP_FEP(aer->cap_control);
 
-	pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
-	__aer_print_error(dev, &info);
-	pci_err(dev, "aer_layer=%s, aer_agent=%s\n",
+	aer_printk(level, dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
+	__aer_print_error(dev, &info, level);
+	aer_printk(level, dev, "aer_layer=%s, aer_agent=%s\n",
 		aer_error_layer[layer], aer_agent_string[agent]);
 
 	if (aer_severity != AER_CORRECTABLE)
-		pci_err(dev, "aer_uncor_severity: 0x%08x\n",
+		aer_printk(level, dev, "aer_uncor_severity: 0x%08x\n",
 			aer->uncor_severity);
 
 	if (tlp_header_valid)
@@ -1244,14 +1243,15 @@  int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 	return 1;
 }
 
-static inline void aer_process_err_devices(struct aer_err_info *e_info)
+static inline void aer_process_err_devices(struct aer_err_info *e_info,
+					   const char *level)
 {
 	int i;
 
 	/* Report all before handle them, not to lost records by reset etc. */
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
 		if (aer_get_device_error_info(e_info->dev[i], e_info))
-			aer_print_error(e_info->dev[i], e_info);
+			aer_print_error(e_info->dev[i], e_info, level);
 	}
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
 		if (aer_get_device_error_info(e_info->dev[i], e_info))
@@ -1269,6 +1269,7 @@  static void aer_isr_one_error(struct aer_rpc *rpc,
 {
 	struct pci_dev *pdev = rpc->rpd;
 	struct aer_err_info e_info;
+	const char *level;
 
 	pci_rootport_aer_stats_incr(pdev, e_src);
 
@@ -1279,6 +1280,7 @@  static void aer_isr_one_error(struct aer_rpc *rpc,
 	if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
 		e_info.id = ERR_COR_ID(e_src->id);
 		e_info.severity = AER_CORRECTABLE;
+		level = KERN_WARNING;
 
 		if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
 			e_info.multi_error_valid = 1;
@@ -1286,11 +1288,12 @@  static void aer_isr_one_error(struct aer_rpc *rpc,
 			e_info.multi_error_valid = 0;
 
 		if (find_source_device(pdev, &e_info))
-			aer_process_err_devices(&e_info);
+			aer_process_err_devices(&e_info, level);
 	}
 
 	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
 		e_info.id = ERR_UNCOR_ID(e_src->id);
+		level = KERN_ERR;
 
 		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
 			e_info.severity = AER_FATAL;
@@ -1303,7 +1306,7 @@  static void aer_isr_one_error(struct aer_rpc *rpc,
 			e_info.multi_error_valid = 0;
 
 		if (find_source_device(pdev, &e_info))
-			aer_process_err_devices(&e_info);
+			aer_process_err_devices(&e_info, level);
 	}
 }
 
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 242cabd5eeeb..f06fad95f2eb 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -287,7 +287,7 @@  void dpc_process_error(struct pci_dev *pdev)
 	else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR &&
 		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
 		 aer_get_device_error_info(pdev, &info)) {
-		aer_print_error(pdev, &info);
+		aer_print_error(pdev, &info, KERN_ERR);
 		pci_aer_clear_nonfatal_status(pdev);
 		pci_aer_clear_fatal_status(pdev);
 	}