From bdb5ac85777de67c909c9ad4327f03f7648b543f Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Thu, 20 Sep 2018 10:27:12 -0600
Subject: [PATCH] PCI/ERR: Handle fatal error recovery
Git-commit: bdb5ac85777de67c909c9ad4327f03f7648b543f
Patch-mainline: v4.20-rc1
References: bsc#1161561
We don't need to be paranoid about the topology changing while handling an
error. If the device has changed in a hotplug capable slot, we can rely on
the presence detection handling to react to a changing topology.
Restore the fatal error handling behavior that existed before merging DPC
with AER with 7e9084b36740 ("PCI/AER: Handle ERR_FATAL with removal and
re-enumeration of devices").
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Acked-by: Takashi Iwai <tiwai@suse.de>
---
Documentation/PCI/pci-error-recovery.txt | 35 ++++----------
drivers/pci/pci.h | 4 -
drivers/pci/pcie/aer/aerdrv_core.c | 12 +++-
drivers/pci/pcie/dpc.c | 4 -
drivers/pci/pcie/err.c | 75 ++-----------------------------
5 files changed, 28 insertions(+), 102 deletions(-)
--- 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
event will be platform-dependent, but will follow the general
sequence described below.
-STEP 0: Error Event: ERR_NONFATAL
+STEP 0: Error Event
-------------------
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,
@@ -228,7 +228,13 @@ proceeds to either STEP3 (Link Reset) or
If any driver returned PCI_ERS_RESULT_NEED_RESET, then the platform
proceeds to STEP 4 (Slot Reset)
-STEP 3: 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
------------------
In response to a return value of PCI_ERS_RESULT_NEED_RESET, the
@@ -314,7 +320,7 @@ Failure).
>>> However, it probably should.
-STEP 4: Resume Operations
+STEP 5: Resume Operations
-------------------------
The platform will call the resume() callback on all affected device
drivers if all drivers on the segment have returned
@@ -326,7 +332,7 @@ a result code.
At this point, if a new error happens, the platform will restart
a new error recovery sequence.
-STEP 5: Permanent Failure
+STEP 6: Permanent Failure
-------------------------
A "permanent failure" has occurred, and the platform cannot recover
the device. The platform will call error_detected() with a
@@ -349,27 +355,6 @@ errors. See the discussion in powerpc/ee
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
---------------------------
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -404,8 +404,8 @@ static inline resource_size_t pci_resour
void pci_enable_acs(struct pci_dev *dev);
/* PCI error reporting and recovery */
-void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service);
-void pcie_do_nonfatal_recovery(struct pci_dev *dev);
+void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
+ u32 service);
bool pcie_wait_for_link(struct pci_dev *pdev, bool active);
#ifdef CONFIG_PCIEASPM
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -172,7 +172,7 @@ static irqreturn_t dpc_handler(int irq,
reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN) >> 1;
ext_reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT) >> 5;
- dev_warn(dev, "DPC %s detected, remove downstream devices\n",
+ dev_warn(dev, "DPC %s detected\n",
(reason == 0) ? "unmasked uncorrectable error" :
(reason == 1) ? "ERR_NONFATAL" :
(reason == 2) ? "ERR_FATAL" :
@@ -189,7 +189,7 @@ static irqreturn_t dpc_handler(int irq,
}
/* We configure DPC so it only triggers on ERR_FATAL */
- pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
+ pcie_do_recovery(pdev, pci_channel_io_frozen, PCIE_PORT_SERVICE_DPC);
return IRQ_HANDLED;
}
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -270,83 +270,20 @@ static pci_ers_result_t broadcast_error_
return result_data.result;
}
-/**
- * pcie_do_fatal_recovery - handle fatal error recovery process
- * @dev: pointer to a pci_dev data structure of agent detecting an error
- *
- * 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.
- */
-void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
-{
- 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_walk_bus(parent, pci_dev_set_disconnected, NULL);
-
- pci_lock_rescan_remove();
- pci_dev_get(dev);
- list_for_each_entry_safe_reverse(pdev, temp, &parent->devices,
- bus_list) {
- pci_stop_and_remove_bus_device(pdev);
- }
-
- result = reset_link(udev, service);
-
- if ((service == PCIE_PORT_SERVICE_AER) &&
- (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_aer_clear_fatal_status(dev);
- pci_aer_clear_device_status(dev);
- }
-
- if (result == PCI_ERS_RESULT_RECOVERED) {
- if (pcie_wait_for_link(udev, true))
- pci_rescan_bus(udev->bus);
- pci_info(dev, "Device recovery from fatal error successful\n");
- } else {
- pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
- pci_info(dev, "Device recovery from fatal error failed\n");
- }
-
- pci_dev_put(dev);
- pci_unlock_rescan_remove();
-}
-
-/**
- * pcie_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/fatal. Once being invoked, broadcast
- * error detected message to all downstream drivers within a hierarchy in
- * question and return the returned code.
- */
-void pcie_do_nonfatal_recovery(struct pci_dev *dev)
+void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
+ u32 service)
{
pci_ers_result_t status;
- enum pci_channel_state state;
-
- state = pci_channel_io_normal;
status = broadcast_error_message(dev,
state,
"error_detected",
report_error_detected);
+ if (state == pci_channel_io_frozen &&
+ reset_link(dev, service) != PCI_ERS_RESULT_RECOVERED)
+ goto failed;
+
if (status == PCI_ERS_RESULT_CAN_RECOVER)
status = broadcast_error_message(dev,
state,
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -296,9 +296,11 @@ static void handle_error_source(struct p
info->status);
pci_aer_clear_device_status(dev);
} else if (info->severity == AER_NONFATAL)
- pcie_do_nonfatal_recovery(dev);
+ pcie_do_recovery(dev, pci_channel_io_normal,
+ PCIE_PORT_SERVICE_AER);
else if (info->severity == AER_FATAL)
- pcie_do_fatal_recovery(dev, PCIE_PORT_SERVICE_AER);
+ pcie_do_recovery(dev, pci_channel_io_frozen,
+ PCIE_PORT_SERVICE_AER);
pci_dev_put(dev);
}
@@ -364,9 +366,11 @@ static void aer_recover_work_func(struct
}
cper_print_aer(pdev, entry.severity, entry.regs);
if (entry.severity == AER_NONFATAL)
- pcie_do_nonfatal_recovery(pdev);
+ pcie_do_recovery(pdev, pci_channel_io_normal,
+ PCIE_PORT_SERVICE_AER);
else if (entry.severity == AER_FATAL)
- pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_AER);
+ pcie_do_recovery(pdev, pci_channel_io_frozen,
+ PCIE_PORT_SERVICE_AER);
pci_dev_put(pdev);
}
}