PCI/AER: Take reference on error devices

[ Upstream commit 60271ab0 ]

Error handling may be running in parallel with a hot removal.  Reference
count the device during AER handling so the device can not be freed while
AER wants to reference it.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/pci/pcie/aer.c

@@ -866,7 +866,7 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity,
 static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
 {
 	if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
-		e_info->dev[e_info->error_dev_num] = dev;
+		e_info->dev[e_info->error_dev_num] = pci_dev_get(dev);
 		e_info->error_dev_num++;
 		return 0;
 	}
@@ -1013,6 +1013,7 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
 		pcie_do_nonfatal_recovery(dev);
 	else if (info->severity == AER_FATAL)
 		pcie_do_fatal_recovery(dev, PCIE_PORT_SERVICE_AER);
+	pci_dev_put(dev);
 }
 
 #ifdef CONFIG_ACPI_APEI_PCIEAER