[PATCH AUTOSEL 4.19 006/191] PCI/ACPI: Correct error message for ASPM disabling

[PATCH AUTOSEL 4.19 006/191] PCI/ACPI: Correct error message for ASPM disabling

[Sasha Levin]

From: Sinan Kaya <okaya@kernel.org>

[ Upstream commit 1ad61b612b95980a4d970c52022aa01dfc0f6068 ]

If _OSC execution fails today for platforms without an _OSC entry, code is
printing a misleading message saying disabling ASPM as follows:

  acpi PNP0A03:00: _OSC failed (AE_NOT_FOUND); disabling ASPM

We need to ensure that platform supports ASPM to begin with.

Reported-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sinan Kaya <okaya@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/acpi/pci_root.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 7433035ded955..e465e720eab20 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -455,8 +455,9 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
 	decode_osc_support(root, "OS supports", support);
 	status = acpi_pci_osc_support(root, support);
 	if (ACPI_FAILURE(status)) {
-		dev_info(&device->dev, "_OSC failed (%s); disabling ASPM\n",
-			 acpi_format_exception(status));
+		dev_info(&device->dev, "_OSC failed (%s)%s\n",
+			 acpi_format_exception(status),
+			 pcie_aspm_support_enabled() ? "; disabling ASPM" : "");
 		*no_aspm = 1;
 		return;
 	}
-- 
2.20.1

[PATCH AUTOSEL 4.19 008/191] PCI: mediatek: Fix unchecked return value

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>

[ Upstream commit 17a0a1e5f6c4bd6df17834312ff577c1373d87b8 ]

Check return value of devm_pci_remap_iospace().

Addresses-Coverity-ID: 1471965 ("Unchecked return value")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Honghui Zhang <honghui.zhang@mediatek.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pci/controller/pcie-mediatek.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index c5ff6ca65eab2..0d100f56cb884 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -1120,7 +1120,9 @@ static int mtk_pcie_request_resources(struct mtk_pcie *pcie)
 	if (err < 0)
 		return err;
 
-	devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start);
+	err = devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start);
+	if (err)
+		return err;
 
 	return 0;
 }
-- 
2.20.1

[PATCH AUTOSEL 4.19 061/191] PCI: portdrv: Initialize service drivers directly

[Sasha Levin]

From: Keith Busch <keith.busch@intel.com>

[ Upstream commit c29de84149aba5f74e87b6491c13ac7203c12f55 ]

The PCI port driver saves the PCI state after initializing the device with
the applicable service devices.  This was, however, before the service
drivers were even registered because PCI probe happens before the
device_initcall initialized those service drivers.  The config space state
that the services set up were not being saved.  The end result would cause
PCI devices to not react to events that the drivers think they did if the
PCI state ever needed to be restored.

Fix this by changing the service drivers from using the init calls to
having the portdrv driver calling the services directly.  This will get the
state saved as desired, while making the relationship between the port
driver and the services under it more explicit in the code.

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/hotplug/pciehp_core.c |  3 +--
 drivers/pci/pcie/aer.c            |  3 +--
 drivers/pci/pcie/dpc.c            |  3 +--
 drivers/pci/pcie/pme.c            |  3 +--
 drivers/pci/pcie/portdrv.h        | 24 ++++++++++++++++++++++++
 drivers/pci/pcie/portdrv_pci.c    |  9 +++++++++
 6 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index ec48c9433ae50..518c46f8e63b7 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -348,7 +348,7 @@ static struct pcie_port_service_driver hpdriver_portdrv = {
 #endif	/* PM */
 };
 
-static int __init pcied_init(void)
+int __init pcie_hp_init(void)
 {
 	int retval = 0;
 
@@ -359,4 +359,3 @@ static int __init pcied_init(void)
 
 	return retval;
 }
-device_initcall(pcied_init);
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 83180edd6ed47..637d638f73da5 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1569,10 +1569,9 @@ static struct pcie_port_service_driver aerdriver = {
  *
  * Invoked when AER root service driver is loaded.
  */
-static int __init aer_service_init(void)
+int __init pcie_aer_init(void)
 {
 	if (!pci_aer_available() || aer_acpi_firmware_first())
 		return -ENXIO;
 	return pcie_port_service_register(&aerdriver);
 }
-device_initcall(aer_service_init);
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 1908dd2978d3c..118b5bcae42ea 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -307,8 +307,7 @@ static struct pcie_port_service_driver dpcdriver = {
 	.reset_link	= dpc_reset_link,
 };
 
-static int __init dpc_service_init(void)
+int __init pcie_dpc_init(void)
 {
 	return pcie_port_service_register(&dpcdriver);
 }
-device_initcall(dpc_service_init);
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 6ac17f0c40775..54d593d10396f 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -455,8 +455,7 @@ static struct pcie_port_service_driver pcie_pme_driver = {
 /**
  * pcie_pme_service_init - Register the PCIe PME service driver.
  */
-static int __init pcie_pme_service_init(void)
+int __init pcie_pme_init(void)
 {
 	return pcie_port_service_register(&pcie_pme_driver);
 }
-device_initcall(pcie_pme_service_init);
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index d59afa42fc14b..2498b2d340095 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -23,6 +23,30 @@
 
 #define PCIE_PORT_DEVICE_MAXSERVICES   4
 
+#ifdef CONFIG_PCIEAER
+int pcie_aer_init(void);
+#else
+static inline int pcie_aer_init(void) { return 0; }
+#endif
+
+#ifdef CONFIG_HOTPLUG_PCI_PCIE
+int pcie_hp_init(void);
+#else
+static inline int pcie_hp_init(void) { return 0; }
+#endif
+
+#ifdef CONFIG_PCIE_PME
+int pcie_pme_init(void);
+#else
+static inline int pcie_pme_init(void) { return 0; }
+#endif
+
+#ifdef CONFIG_PCIE_DPC
+int pcie_dpc_init(void);
+#else
+static inline int pcie_dpc_init(void) { return 0; }
+#endif
+
 /* Port Type */
 #define PCIE_ANY_PORT			(~0)
 
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index eef22dc29140c..23a5a0c2c3fe9 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -226,11 +226,20 @@ static const struct dmi_system_id pcie_portdrv_dmi_table[] __initconst = {
 	 {}
 };
 
+static void __init pcie_init_services(void)
+{
+	pcie_aer_init();
+	pcie_pme_init();
+	pcie_dpc_init();
+	pcie_hp_init();
+}
+
 static int __init pcie_portdrv_init(void)
 {
 	if (pcie_ports_disabled)
 		return -EACCES;
 
+	pcie_init_services();
 	dmi_check_system(pcie_portdrv_dmi_table);
 
 	return pci_register_driver(&pcie_portdriver);
-- 
2.20.1

[PATCH AUTOSEL 4.19 079/191] PCI/AER: Take reference on error devices

[Sasha Levin]

From: Keith Busch <keith.busch@intel.com>

[ Upstream commit 60271ab044a53edb9dcbe76bebea2221c4ff04d9 ]

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 | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 637d638f73da5..ffbbd759683c5 100644
--- a/drivers/pci/pcie/aer.c
+++ b/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
-- 
2.20.1

[PATCH AUTOSEL 4.19 080/191] PCI/AER: Don't read upstream ports below fatal errors

[Sasha Levin]

From: Keith Busch <keith.busch@intel.com>

[ Upstream commit 9d938ea53b265ed6df6cdd1715d971f0235fdbfc ]

The AER driver has never read the config space of an endpoint that reported
a fatal error because the link to that device is considered unreliable.

An ERR_FATAL from an upstream port almost certainly indicates an error on
its upstream link, so we can't expect to reliably read its config space for
the same reason.

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 | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index ffbbd759683c5..5c3ea7254c6ae 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1116,8 +1116,9 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 			&info->mask);
 		if (!(info->status & ~info->mask))
 			return 0;
-	} else if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
-		info->severity == AER_NONFATAL) {
+	} else if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT ||
+	           pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM ||
+		   info->severity == AER_NONFATAL) {
 
 		/* Link is still healthy for IO reads */
 		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS,
-- 
2.20.1

[PATCH AUTOSEL 4.19 081/191] PCI/ERR: Use slot reset if available

[Sasha Levin]

From: Keith Busch <keith.busch@intel.com>

[ Upstream commit c4eed62a214330908eec11b0dc170d34fa50b412 ]

The secondary bus reset may have link side effects that a hotplug capable
port may incorrectly react to.  Use the slot specific reset for hotplug
ports, fixing the undesirable link down-up handling during error
recovering.

Signed-off-by: Keith Busch <keith.busch@intel.com>
[bhelgaas: fold in
https://lore.kernel.org/linux-pci/20180926152326.14821-1-keith.busch@intel.com
for issue reported by Stephen Rothwell <sfr@canb.auug.org.au>]
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/pci.c      | 37 +++++++++++++++++++++++++++++++++++++
 drivers/pci/pci.h      |  2 ++
 drivers/pci/pcie/aer.c |  2 +-
 drivers/pci/pcie/err.c |  2 +-
 drivers/pci/slot.c     |  1 -
 5 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 2baf1f82f8933..c9f51fc24563c 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -35,6 +35,8 @@
 #include <linux/aer.h>
 #include "pci.h"
 
+DEFINE_MUTEX(pci_slot_mutex);
+
 const char *pci_power_names[] = {
 	"error", "D0", "D1", "D2", "D3hot", "D3cold", "unknown",
 };
@@ -5191,6 +5193,41 @@ static int pci_bus_reset(struct pci_bus *bus, int probe)
 	return ret;
 }
 
+/**
+ * pci_bus_error_reset - reset the bridge's subordinate bus
+ * @bridge: The parent device that connects to the bus to reset
+ *
+ * This function will first try to reset the slots on this bus if the method is
+ * available. If slot reset fails or is not available, this will fall back to a
+ * secondary bus reset.
+ */
+int pci_bus_error_reset(struct pci_dev *bridge)
+{
+	struct pci_bus *bus = bridge->subordinate;
+	struct pci_slot *slot;
+
+	if (!bus)
+		return -ENOTTY;
+
+	mutex_lock(&pci_slot_mutex);
+	if (list_empty(&bus->slots))
+		goto bus_reset;
+
+	list_for_each_entry(slot, &bus->slots, list)
+		if (pci_probe_reset_slot(slot))
+			goto bus_reset;
+
+	list_for_each_entry(slot, &bus->slots, list)
+		if (pci_slot_reset(slot, 0))
+			goto bus_reset;
+
+	mutex_unlock(&pci_slot_mutex);
+	return 0;
+bus_reset:
+	mutex_unlock(&pci_slot_mutex);
+	return pci_bus_reset(bridge->subordinate, 0);
+}
+
 /**
  * pci_probe_reset_bus - probe whether a PCI bus can be reset
  * @bus: PCI bus to probe
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index ab25752f00d96..e9ede82ee2c25 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -35,6 +35,7 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai,
 
 int pci_probe_reset_function(struct pci_dev *dev);
 int pci_bridge_secondary_bus_reset(struct pci_dev *dev);
+int pci_bus_error_reset(struct pci_dev *dev);
 
 /**
  * struct pci_platform_pm_ops - Firmware PM callbacks
@@ -136,6 +137,7 @@ static inline void pci_remove_legacy_files(struct pci_bus *bus) { return; }
 
 /* Lock for read/write access to pci device and bus lists */
 extern struct rw_semaphore pci_bus_sem;
+extern struct mutex pci_slot_mutex;
 
 extern raw_spinlock_t pci_lock;
 
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 5c3ea7254c6ae..1563e22600eca 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1528,7 +1528,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	rc = pci_bridge_secondary_bus_reset(dev);
+	rc = pci_bus_error_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
 
 	/* Clear Root Error Status */
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 708fd3a0d6466..12c1205e1d804 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -177,7 +177,7 @@ static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 {
 	int rc;
 
-	rc = pci_bridge_secondary_bus_reset(dev);
+	rc = pci_bus_error_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n");
 	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index e634229ece895..a32897f83ee51 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -14,7 +14,6 @@
 
 struct kset *pci_slots_kset;
 EXPORT_SYMBOL_GPL(pci_slots_kset);
-static DEFINE_MUTEX(pci_slot_mutex);
 
 static ssize_t pci_slot_attr_show(struct kobject *kobj,
 					struct attribute *attr, char *buf)
-- 
2.20.1

[PATCH AUTOSEL 4.19 145/191] PCI/ERR: Run error recovery callbacks for all affected devices

[Sasha Levin]

From: Keith Busch <keith.busch@intel.com>

[ Upstream commit bfcb79fca19d267712e425af1dd48812c40dec0c ]

If an Endpoint reported an error with ERR_FATAL, we previously ran driver
error recovery callbacks only for the Endpoint's driver.  But if we reset a
Link to recover from the error, all downstream components are affected,
including the Endpoint, any multi-function peers, and children of those
peers.

Initiate the Link reset from the deepest Downstream Port that is
reliable, and call the error recovery callbacks for all its children.

If a Downstream Port (including a Root Port) reports an error, we assume
the Port itself is reliable and we need to reset its downstream Link.  In
all other cases (Switch Upstream Ports, Endpoints, Bridges, etc), we assume
the Link leading to the component needs to be reset, so we initiate the
reset at the parent Downstream Port.

This allows two other clean-ups.  First, we currently only use a Link
reset, which can only be initiated using a Downstream Port, so we can
remove checks for Endpoints.  Second, the Downstream Port where we initiate
the Link reset is reliable (unlike components downstream from it), so the
special cases for error detect and resume are no longer necessary.

Signed-off-by: Keith Busch <keith.busch@intel.com>
[bhelgaas: changelog]
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/err.c | 85 +++++++++++-------------------------------
 1 file changed, 21 insertions(+), 64 deletions(-)

diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 12c1205e1d804..2c3b5bd59b18f 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -63,30 +63,12 @@ static int report_error_detected(struct pci_dev *dev, void *data)
 	if (!dev->driver ||
 		!dev->driver->err_handler ||
 		!dev->driver->err_handler->error_detected) {
-		if (result_data->state == pci_channel_io_frozen &&
-			dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
-			/*
-			 * In case of fatal recovery, if one of down-
-			 * stream device has no driver. We might be
-			 * unable to recover because a later insmod
-			 * of a driver for this device is unaware of
-			 * its hw state.
-			 */
-			pci_printk(KERN_DEBUG, dev, "device has %s\n",
-				   dev->driver ?
-				   "no AER-aware driver" : "no driver");
-		}
-
 		/*
-		 * If there's any device in the subtree that does not
-		 * have an error_detected callback, returning
-		 * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of
-		 * the subsequent mmio_enabled/slot_reset/resume
-		 * callbacks of "any" device in the subtree. All the
-		 * devices in the subtree are left in the error state
-		 * without recovery.
+		 * If any device in the subtree does not have an error_detected
+		 * callback, PCI_ERS_RESULT_NO_AER_DRIVER prevents subsequent
+		 * error callbacks of "any" device in the subtree, and will
+		 * exit in the disconnected error state.
 		 */
-
 		if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
 			vote = PCI_ERS_RESULT_NO_AER_DRIVER;
 		else
@@ -184,34 +166,23 @@ static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 
 static pci_ers_result_t reset_link(struct pci_dev *dev, u32 service)
 {
-	struct pci_dev *udev;
 	pci_ers_result_t status;
 	struct pcie_port_service_driver *driver = NULL;
 
-	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		/* Reset this port for all subordinates */
-		udev = dev;
-	} else {
-		/* Reset the upstream component (likely downstream port) */
-		udev = dev->bus->self;
-	}
-
-	/* Use the aer driver of the component firstly */
-	driver = pcie_port_find_service(udev, service);
-
+	driver = pcie_port_find_service(dev, service);
 	if (driver && driver->reset_link) {
-		status = driver->reset_link(udev);
-	} else if (udev->has_secondary_link) {
-		status = default_reset_link(udev);
+		status = driver->reset_link(dev);
+	} else if (dev->has_secondary_link) {
+		status = default_reset_link(dev);
 	} else {
 		pci_printk(KERN_DEBUG, dev, "no link-reset support at upstream device %s\n",
-			pci_name(udev));
+			pci_name(dev));
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
 	if (status != PCI_ERS_RESULT_RECOVERED) {
 		pci_printk(KERN_DEBUG, dev, "link reset at upstream device %s failed\n",
-			pci_name(udev));
+			pci_name(dev));
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -243,31 +214,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 	else
 		result_data.result = PCI_ERS_RESULT_RECOVERED;
 
-	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		/*
-		 * If the error is reported by a bridge, we think this error
-		 * is related to the downstream link of the bridge, so we
-		 * do error recovery on all subordinates of the bridge instead
-		 * of the bridge and clear the error status of the bridge.
-		 */
-		if (cb == report_error_detected)
-			dev->error_state = state;
-		pci_walk_bus(dev->subordinate, cb, &result_data);
-		if (cb == report_resume) {
-			pci_aer_clear_device_status(dev);
-			pci_cleanup_aer_uncorrect_error_status(dev);
-			dev->error_state = pci_channel_io_normal;
-		}
-	} else {
-		/*
-		 * If the error is reported by an end point, we think this
-		 * error is related to the upstream link of the end point.
-		 * The error is non fatal so the bus is ok; just invoke
-		 * the callback for the function that logged the error.
-		 */
-		cb(dev, &result_data);
-	}
-
+	pci_walk_bus(dev->subordinate, cb, &result_data);
 	return result_data.result;
 }
 
@@ -347,6 +294,14 @@ void pcie_do_nonfatal_recovery(struct pci_dev *dev)
 
 	state = pci_channel_io_normal;
 
+	/*
+	 * Error recovery runs on all subordinates of the first downstream port.
+	 * If the downstream port detected the error, it is cleared at the end.
+	 */
+	if (!(pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT ||
+	      pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM))
+		dev = dev->bus->self;
+
 	status = broadcast_error_message(dev,
 			state,
 			"error_detected",
@@ -378,6 +333,8 @@ void pcie_do_nonfatal_recovery(struct pci_dev *dev)
 				"resume",
 				report_resume);
 
+	pci_aer_clear_device_status(dev);
+	pci_cleanup_aer_uncorrect_error_status(dev);
 	pci_info(dev, "AER: Device recovery successful\n");
 	return;
 
-- 
2.20.1