[PATCH v4 5/7] PCI/AER: Introduce ratelimit for error logs

[Jon Pan-Doh <pandoh@google.com>]

Spammy devices can flood kernel logs with AER errors and slow/stall
execution. Add per-device ratelimits for AER correctable and uncorrectable
errors that use the kernel defaults (10 per 5s).

Tested using aer-inject[1]. Sent 11 AER errors. Observed 10 errors logged
while AER stats (cat /sys/bus/pci/devices/<dev>/aer_dev_correctable) show
true count of 11.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/gong.chen/aer-inject.git

Signed-off-by: Jon Pan-Doh <pandoh@google.com>
Reviewed-by: Karolina Stolarek <karolina.stolarek@oracle.com>
---
 drivers/pci/pcie/aer.c | 74 +++++++++++++++++++++++++++++++++---------
 1 file changed, 58 insertions(+), 16 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 3069376b3553..081cef5fc678 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -28,6 +28,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/kfifo.h>
+#include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <acpi/apei.h>
 #include <acpi/ghes.h>
@@ -88,6 +89,10 @@ struct aer_report {
 	u64 rootport_total_cor_errs;
 	u64 rootport_total_fatal_errs;
 	u64 rootport_total_nonfatal_errs;
+
+	/* Ratelimits for errors */
+	struct ratelimit_state cor_log_ratelimit;
+	struct ratelimit_state uncor_log_ratelimit;
 };
 
 #define AER_LOG_TLP_MASKS		(PCI_ERR_UNC_POISON_TLP|	\
@@ -379,6 +384,15 @@ void pci_aer_init(struct pci_dev *dev)
 
 	dev->aer_report = kzalloc(sizeof(*dev->aer_report), GFP_KERNEL);
 
+	/*
+	 * Ratelimits are doubled as a given error produces 2 logs (root port
+	 * and endpoint) that should be under same ratelimit.
+	 */
+	ratelimit_state_init(&dev->aer_report->cor_log_ratelimit,
+			     DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST * 2);
+	ratelimit_state_init(&dev->aer_report->uncor_log_ratelimit,
+			     DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST * 2);
+
 	/*
 	 * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER,
 	 * PCI_ERR_COR_MASK, and PCI_ERR_CAP.  Root and Root Complex Event
@@ -668,6 +682,17 @@ static void pci_rootport_aer_stats_incr(struct pci_dev *pdev,
 	}
 }
 
+static int aer_ratelimit(struct pci_dev *dev, unsigned int severity)
+{
+	struct ratelimit_state *ratelimit;
+
+	if (severity == AER_CORRECTABLE)
+		ratelimit = &dev->aer_report->cor_log_ratelimit;
+	else
+		ratelimit = &dev->aer_report->uncor_log_ratelimit;
+	return __ratelimit(ratelimit);
+}
+
 static void __aer_print_error(struct pci_dev *dev,
 			      struct aer_err_info *info,
 			      const char *level)
@@ -698,6 +723,12 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info,
 	int layer, agent;
 	int id = pci_dev_id(dev);
 
+	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
+			info->severity, info->tlp_header_valid, &info->tlp);
+
+	if (!aer_ratelimit(dev, info->severity))
+		return;
+
 	if (!info->status) {
 		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
 			aer_error_severity_string[info->severity]);
@@ -722,21 +753,28 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info,
 out:
 	if (info->id && info->error_dev_num > 1 && info->id == id)
 		pci_err(dev, "  Error of this Agent is reported first\n");
-
-	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
-			info->severity, info->tlp_header_valid, &info->tlp);
 }
 
 static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
 {
 	u8 bus = info->id >> 8;
 	u8 devfn = info->id & 0xff;
+	struct pci_dev *endpoint;
+	int i;
+
+	/* extract endpoint device ratelimit */
+	for (i = 0; i < info->error_dev_num; i++) {
+		endpoint = info->dev[i];
+		if (info->id == pci_dev_id(endpoint))
+			break;
+	}
 
-	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
-		 info->multi_error_valid ? "Multiple " : "",
-		 aer_error_severity_string[info->severity],
-		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
-		 PCI_FUNC(devfn));
+	if (aer_ratelimit(endpoint, info->severity))
+		pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
+			 info->multi_error_valid ? "Multiple " : "",
+			 aer_error_severity_string[info->severity],
+			 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn));
 }
 
 #ifdef CONFIG_ACPI_APEI_PCIEAER
@@ -784,6 +822,12 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
 
 	pci_dev_aer_stats_incr(dev, &info);
 
+	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+			aer_severity, tlp_header_valid, &aer->header_log);
+
+	if (!aer_ratelimit(dev, aer_severity))
+		return;
+
 	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",
@@ -795,9 +839,6 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
 
 	if (tlp_header_valid)
 		pcie_print_tlp_log(dev, &aer->header_log, dev_fmt("  "));
-
-	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
-			aer_severity, tlp_header_valid, &aer->header_log);
 }
 EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
 
@@ -1299,10 +1340,11 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 			e_info.multi_error_valid = 1;
 		else
 			e_info.multi_error_valid = 0;
-		aer_print_port_info(pdev, &e_info);
 
-		if (find_source_device(pdev, &e_info))
+		if (find_source_device(pdev, &e_info)) {
+			aer_print_port_info(pdev, &e_info);
 			aer_process_err_devices(&e_info, KERN_WARNING);
+		}
 	}
 
 	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
@@ -1318,10 +1360,10 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 		else
 			e_info.multi_error_valid = 0;
 
-		aer_print_port_info(pdev, &e_info);
-
-		if (find_source_device(pdev, &e_info))
+		if (find_source_device(pdev, &e_info)) {
+			aer_print_port_info(pdev, &e_info);
 			aer_process_err_devices(&e_info, KERN_ERR);
+		}
 	}
 }
 
-- 
2.49.0.rc1.451.g8f38331e32-goog