diff --git a/Documentation/PCI/pci-error-recovery.txt b/Documentation/PCI/pci-error-recovery.txt
index 0b6bb3ef449ee7a8ee45afe9b4be61a2859ac8e3..688b69121e8294ca81d47689c25345e97d5de720 100644
--- a/Documentation/PCI/pci-error-recovery.txt
+++ b/Documentation/PCI/pci-error-recovery.txt
@@ -110,7 +110,7 @@ The actual steps taken by a platform to recover from a PCI error
event will be platform-dependent, but will follow the general
sequence described below.
-STEP 0: Error Event
+STEP 0: Error Event: ERR_NONFATAL
-------------------
A PCI bus error is detected by the PCI hardware. On powerpc, the slot
is isolated, in that all I/O is blocked: all reads return 0xffffffff,
@@ -228,13 +228,7 @@ proceeds to either STEP3 (Link Reset) or to STEP 5 (Resume Operations).
If any driver returned PCI_ERS_RESULT_NEED_RESET, then the platform
proceeds to STEP 4 (Slot Reset)
-STEP 3: Link Reset
-------------------
-The platform resets the link. This is a PCI-Express specific step
-and is done whenever a fatal error has been detected that can be
-"solved" by resetting the link.
-
-STEP 4: Slot Reset
+STEP 3: Slot Reset
------------------
In response to a return value of PCI_ERS_RESULT_NEED_RESET, the
@@ -320,7 +314,7 @@ Failure).
>>> However, it probably should.
-STEP 5: Resume Operations
+STEP 4: Resume Operations
-------------------------
The platform will call the resume() callback on all affected device
drivers if all drivers on the segment have returned
@@ -332,7 +326,7 @@ a result code.
At this point, if a new error happens, the platform will restart
a new error recovery sequence.
-STEP 6: Permanent Failure
+STEP 5: Permanent Failure
-------------------------
A "permanent failure" has occurred, and the platform cannot recover
the device. The platform will call error_detected() with a
@@ -355,6 +349,27 @@ errors. See the discussion in powerpc/eeh-pci-error-recovery.txt
for additional detail on real-life experience of the causes of
software errors.
+STEP 0: Error Event: ERR_FATAL
+-------------------
+PCI bus error is detected by the PCI hardware. On powerpc, the slot is
+isolated, in that all I/O is blocked: all reads return 0xffffffff, all
+writes are ignored.
+
+STEP 1: Remove devices
+--------------------
+Platform removes the devices depending on the error agent, it could be
+this port for all subordinates or upstream component (likely downstream
+port)
+
+STEP 2: Reset link
+--------------------
+The platform resets the link. This is a PCI-Express specific step and is
+done whenever a fatal error has been detected that can be "solved" by
+resetting the link.
+
+STEP 3: Re-enumerate the devices
+--------------------
+Initiates the re-enumeration.
Conclusion; General Remarks
---------------------------
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 779b3879b1b5edb28736e3cc555a5a82428a707e..377e576e4f416367a30c4b8775d592e4aff31553 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -353,10 +353,7 @@ static void aer_error_resume(struct pci_dev *dev)
pos = dev->aer_cap;
pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
- if (dev->error_state == pci_channel_io_normal)
- status &= ~mask; /* Clear corresponding nonfatal bits */
- else
- status &= mask; /* Clear corresponding fatal bits */
+ status &= ~mask; /* Clear corresponding nonfatal bits */
pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
}
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 0ea5acc40323385db1fbee15dbd4998e0ea54420..f64ebca0943959e635e061791a06d2bce30b0bc6 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -20,6 +20,7 @@
#include <linux/slab.h>
#include <linux/kfifo.h>
#include "aerdrv.h"
+#include "../../pci.h"
#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \
PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE)
@@ -475,35 +476,81 @@ static pci_ers_result_t reset_link(struct pci_dev *dev)
}
/**
- * do_recovery - handle nonfatal/fatal error recovery process
+ * do_fatal_recovery - handle fatal error recovery process
* @dev: pointer to a pci_dev data structure of agent detecting an error
- * @severity: error severity type
*
- * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast
+ * Invoked when an error is fatal. Once being invoked, removes the devices
+ * beneath this AER agent, followed by reset link e.g. secondary bus reset
+ * followed by re-enumeration of devices.
+ */
+static void do_fatal_recovery(struct pci_dev *dev)
+{
+ struct pci_dev *udev;
+ struct pci_bus *parent;
+ struct pci_dev *pdev, *temp;
+ pci_ers_result_t result;
+
+ if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+ udev = dev;
+ else
+ udev = dev->bus->self;
+
+ parent = udev->subordinate;
+ pci_lock_rescan_remove();
+ list_for_each_entry_safe_reverse(pdev, temp, &parent->devices,
+ bus_list) {
+ pci_dev_get(pdev);
+ pci_dev_set_disconnected(pdev, NULL);
+ if (pci_has_subordinate(pdev))
+ pci_walk_bus(pdev->subordinate,
+ pci_dev_set_disconnected, NULL);
+ pci_stop_and_remove_bus_device(pdev);
+ pci_dev_put(pdev);
+ }
+
+ result = reset_link(udev);
+
+ 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.
+ */
+ pci_cleanup_aer_uncorrect_error_status(dev);
+ }
+
+ if (result == PCI_ERS_RESULT_RECOVERED) {
+ if (pcie_wait_for_link(udev, true))
+ pci_rescan_bus(udev->bus);
+ } else {
+ pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
+ pci_info(dev, "AER: Device recovery from fatal error failed\n");
+ }
+
+ pci_unlock_rescan_remove();
+}
+
+/**
+ * do_nonfatal_recovery - handle nonfatal error recovery process
+ * @dev: pointer to a pci_dev data structure of agent detecting an error
+ *
+ * Invoked when an error is nonfatal. Once being invoked, broadcast
* error detected message to all downstream drivers within a hierarchy in
* question and return the returned code.
*/
-static void do_recovery(struct pci_dev *dev, int severity)
+static void do_nonfatal_recovery(struct pci_dev *dev)
{
- pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED;
+ pci_ers_result_t status;
enum pci_channel_state state;
- if (severity == AER_FATAL)
- state = pci_channel_io_frozen;
- else
- state = pci_channel_io_normal;
+ state = pci_channel_io_normal;
status = broadcast_error_message(dev,
state,
"error_detected",
report_error_detected);
- if (severity == AER_FATAL) {
- result = reset_link(dev);
- if (result != PCI_ERS_RESULT_RECOVERED)
- goto failed;
- }
-
if (status == PCI_ERS_RESULT_CAN_RECOVER)
status = broadcast_error_message(dev,
state,
@@ -562,8 +609,10 @@ static void handle_error_source(struct pcie_device *aerdev,
if (pos)
pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
info->status);
- } else
- do_recovery(dev, info->severity);
+ } else if (info->severity == AER_NONFATAL)
+ do_nonfatal_recovery(dev);
+ else if (info->severity == AER_FATAL)
+ do_fatal_recovery(dev);
}
#ifdef CONFIG_ACPI_APEI_PCIEAER
@@ -627,8 +676,10 @@ static void aer_recover_work_func(struct work_struct *work)
continue;
}
cper_print_aer(pdev, entry.severity, entry.regs);
- if (entry.severity != AER_CORRECTABLE)
- do_recovery(pdev, entry.severity);
+ if (entry.severity == AER_NONFATAL)
+ do_nonfatal_recovery(pdev);
+ else if (entry.severity == AER_FATAL)
+ do_fatal_recovery(pdev);
pci_dev_put(pdev);
}
}