This patch series aims at fixing some of the AER error handling issues
we have.
Currently we have the following issues:
1. Confusing message in aer_print_error()
2. aer_err_info not being initialized completely in DPC path before
we print the AER logs
3. A bug [1] in clearing of AER registers in the native AER path
[1] https://lore.kernel.org/linux-pci/20151229155822.GA17321@localhost/
The patch series fixes the above things.
PATCH 1:
- Fixes the first issue
- This patch is independent of other patches and can be applied
seperately
PATCH 2 - 3:
- Fixes the second issue
- Patch 3 is depended on Patch 2 in the series
PATCH 4
- Fixes the bug in clearing of AER registers which leades to
AER message spew [1]
PATCH 5:
- Adds extra information (devctl register) in AER error logs.
- Patch 5 depends on Patch 4 of the series
Thanks,
Naveen Naidu
Changelog
=========
v5:
- Edit the commit message of Patch 1 and Patch 5 to include how to
test the AER messages using aer-inject.
- Edit Patch 3 to initialize info.id depending on the trigger
reason.
- Drop few patches (v4 4/8, 5/8 7/8) since they were wrong.
v4:
- Fix logical error in 6/8, in the previous version of the patch set
there was a bug, in how I added the devices to the queue.
v3:
- Edit the commit messages to be in imperative style and split the
commits to be more atomic.
v2:
- Add [PATCH 7] which includes the device control register
information in AER error logs.
Naveen Naidu (5):
[PATCH v5 1/5] PCI/AER: Remove ID from aer_agent_string[]
[PATCH v5 2/5] PCI: Cleanup struct aer_err_info
[PATCH v5 3/5] PCI/DPC: Initialize info.id in dpc_process_error()
[PATCH v5 4/5] PCI/AER: Clear error device AER registers in aer_irq()
[PATCH v5 5/5] PCI/AER: Include DEVCTL in aer_print_error()
drivers/pci/pci.h | 23 +++-
drivers/pci/pcie/aer.c | 269 ++++++++++++++++++++++++++++-------------
drivers/pci/pcie/dpc.c | 16 ++-
3 files changed, 214 insertions(+), 94 deletions(-)
--
2.25.1
The id, status and the mask fields of the struct aer_err_info comes
directly from the registers, hence their sizes should be explicit.
The length of these registers are:
- id: 16 bits - Represents the Error Source Requester ID
- status: 32 bits - COR/UNCOR Error Status
- mask: 32 bits - COR/UNCOR Error Mask
Since the length of the above registers are even, use u16 and u32
to represent their values.
Also remove the __pad fields.
"pahole" was run on the modified struct aer_err_info and the size
remains unchanged.
Signed-off-by: Naveen Naidu <[email protected]>
---
drivers/pci/pci.h | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 1cce56c2aea0..9be7a966fda7 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -427,18 +427,16 @@ struct aer_err_info {
struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
int error_dev_num;
- unsigned int id:16;
+ u16 id;
unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */
- unsigned int __pad1:5;
unsigned int multi_error_valid:1;
unsigned int first_error:5;
- unsigned int __pad2:2;
unsigned int tlp_header_valid:1;
- unsigned int status; /* COR/UNCOR Error Status */
- unsigned int mask; /* COR/UNCOR Error Mask */
+ u32 status; /* COR/UNCOR Error Status */
+ u32 mask; /* COR/UNCOR Error Mask */
struct aer_header_log_regs tlp; /* TLP Header */
};
--
2.25.1
Currently, we do not print the "id" field in the AER error logs. Yet the
aer_agent_string[] has the word "id" in it. The AER error log looks
like:
pcieport 0000:00:03.0: PCIe Bus Error: severity=Corrected, type=Data Link Layer, (Receiver ID)
Without the "id" field in the error log, The aer_agent_string[]
(eg: "Receiver ID") does not make sense. A user reading the
aer_agent_string[] in the log, might inadvertently look for an "id"
field and not finding it might lead to confusion.
Remove the "ID" from the aer_agent_string[].
It is easy to reproduce this by using aer-inject:
$ aer-inject -s 00:03:0 corr-err-file
The content of the corr-err-file file is as below:
AER
COR_STATUS BAD_TLP
HEADER_LOG 0 1 2 3
The following are sample dummy errors inject via aer-inject.
Before
=======
In 010caed4ccb6 ("PCI/AER: Decode Error Source Requester ID"),
the "id" field was removed from the AER error logs, so currently AER
logs look like:
pcieport 0000:00:03.0: AER: Corrected error received: 0000:00:03:0
pcieport 0000:00:03.0: PCIe Bus Error: severity=Corrected, type=Data Link Layer, (Receiver ID) <--- no id field
pcieport 0000:00:03.0: device [1b36:000c] error status/mask=00000040/0000e000
pcieport 0000:00:03.0: [ 6] BadTLP
After
======
pcieport 0000:00:03.0: AER: Corrected error received: 0000:00:03.0
pcieport 0000:00:03.0: PCIe Bus Error: severity=Corrected, type=Data Link Layer, (Receiver)
pcieport 0000:00:03.0: device [1b36:000c] error status/mask=00000040/0000e000
pcieport 0000:00:03.0: [ 6] BadTLP
Link: https://lore.kernel.org/linux-pci/20211021170317.GA2700910@bhelgaas/T/#m618bda4e54042d95a1a83fccc01cdb423f7590dc
Signed-off-by: Naveen Naidu <[email protected]>
---
drivers/pci/pcie/aer.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 9784fdcf3006..241ff361b43c 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -516,10 +516,10 @@ static const char *aer_uncorrectable_error_string[] = {
};
static const char *aer_agent_string[] = {
- "Receiver ID",
- "Requester ID",
- "Completer ID",
- "Transmitter ID"
+ "Receiver",
+ "Requester",
+ "Completer",
+ "Transmitter"
};
#define aer_stats_dev_attr(name, stats_array, strings_array, \
@@ -703,7 +703,7 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
const char *level;
if (!info->status) {
- pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
+ pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent)\n",
aer_error_severity_string[info->severity]);
goto out;
}
--
2.25.1
Print the contents of Device Control Register of the device which
detected the error. This might help in faster error diagnosis.
It is easy to test this by using aer-inject:
$ aer-inject -s 00:03:0 corr-err-file
The content of the corr-err-file is as below:
AER
COR_STATUS BAD_TLP
HEADER_LOG 0 1 2 3
Sample output from dummy error injected by aer-inject:
pcieport 0000:00:03.0: AER: Corrected error received: 0000:00:03.0
pcieport 0000:00:03.0: PCIe Bus Error: severity=Corrected, type=Data Link Layer, (Receiver)
pcieport 0000:00:03.0: device [1b36:000c] error status/mask=00000040/0000e000, devctl=0x000f <-- devctl added to the error log
pcieport 0000:00:03.0: [ 6] BadTLP
Signed-off-by: Naveen Naidu <[email protected]>
---
drivers/pci/pci.h | 2 ++
drivers/pci/pcie/aer.c | 10 ++++++++--
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index eb88d8bfeaf7..48ed7f91113b 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -437,6 +437,8 @@ struct aer_err_info {
u32 status; /* COR/UNCOR Error Status */
u32 mask; /* COR/UNCOR Error Mask */
struct aer_header_log_regs tlp; /* TLP Header */
+
+ u16 devctl;
};
/* Preliminary AER error information processed from Root port */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index d3937f5384e4..fdeef9deb016 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -729,8 +729,8 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
aer_error_severity_string[info->severity],
aer_error_layer[layer], aer_agent_string[agent]);
- pci_printk(level, dev, " device [%04x:%04x] error status/mask=%08x/%08x\n",
- dev->vendor, dev->device, info->status, info->mask);
+ pci_printk(level, dev, " device [%04x:%04x] error status/mask=%08x/%08x, devctl=%#06x\n",
+ dev->vendor, dev->device, info->status, info->mask, info->devctl);
__aer_print_error(dev, info);
@@ -1083,6 +1083,12 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
if (!aer)
return 0;
+ /*
+ * Cache the value of Device Control Register now, because later the
+ * device might not be available
+ */
+ pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &info->devctl);
+
if (info->severity == AER_CORRECTABLE) {
pci_read_config_dword(dev, aer + PCI_ERR_COR_STATUS,
&info->status);
--
2.25.1
Converge the APEI path and native AER path of clearing the AER registers
of the error device.
In APEI path, the system firmware clears the AER registers before
handing off the record to OS. But in "native AER" path, the execution
path of clearing the AER register is as follows:
aer_isr_one_error
aer_print_port_info
if (find_source_device())
aer_process_err_devices
handle_error_source
pci_write_config_dword(dev, PCI_ERR_COR_STATUS, ...)
The above path has a bug, if the find_source_device() fails, AER
registers are not cleared from the error device. This means, the error
device will keep reporting the error again and again and would lead
to message spew.
Related Bug Report:
https://lore.kernel.org/linux-pci/20151229155822.GA17321@localhost/
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1521173
The above bug could be avoided, if the AER registers are cleared during
the AER IRQ handler aer_irq(), which would provide guarantee that the AER
error registers are always cleared. This is similar to how APEI handles
these errors.
The main aim is that:
When an interrupt handler deals with a interrupt, it must *always*
clear the source of the interrupt.
Signed-off-by: Naveen Naidu <[email protected]>
---
drivers/pci/pci.h | 13 ++-
drivers/pci/pcie/aer.c | 249 ++++++++++++++++++++++++++++-------------
2 files changed, 184 insertions(+), 78 deletions(-)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 9be7a966fda7..eb88d8bfeaf7 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -424,7 +424,6 @@ static inline bool pci_dev_is_added(const struct pci_dev *dev)
#define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */
struct aer_err_info {
- struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
int error_dev_num;
u16 id;
@@ -440,6 +439,18 @@ struct aer_err_info {
struct aer_header_log_regs tlp; /* TLP Header */
};
+/* Preliminary AER error information processed from Root port */
+struct aer_devices_err_info {
+ struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+ struct aer_err_info err_info;
+};
+
+/* AER information associated with each error device */
+struct aer_dev_err_info {
+ struct pci_dev *dev;
+ struct aer_err_info err_info;
+};
+
int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
#endif /* CONFIG_PCIEAER */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 241ff361b43c..d3937f5384e4 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -36,6 +36,18 @@
#define AER_ERROR_SOURCES_MAX 128
+/*
+ * There can be 128 maximum error sources (AER_ERROR_SOURCES_MAX) and each
+ * error source can have maximum of 5 error devices (AER_MAX_MULTI_ERR_DEVICES)
+ * so the maximum error devices we can report is:
+ *
+ * AER_ERROR_DEVICES_MAX = AER_ERROR_SOURCES_MAX * AER_MAX_MULTI_ERR_DEVICES == (128 * 5) == 640
+ *
+ * But since, the size in KFIFO should be a power of two, the closest value
+ * to 640 is 1024
+ */
+# define AER_ERROR_DEVICES_MAX 1024
+
#define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */
#define AER_MAX_TYPEOF_UNCOR_ERRS 27 /* as per PCI_ERR_UNCOR_STATUS*/
@@ -46,7 +58,7 @@ struct aer_err_source {
struct aer_rpc {
struct pci_dev *rpd; /* Root Port device */
- DECLARE_KFIFO(aer_fifo, struct aer_err_source, AER_ERROR_SOURCES_MAX);
+ DECLARE_KFIFO(aer_fifo, struct aer_dev_err_info, AER_ERROR_DEVICES_MAX);
};
/* AER stats for the device */
@@ -803,14 +815,14 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity,
/**
* add_error_device - list device to be handled
- * @e_info: pointer to error info
+ * @e_dev: pointer to error info
* @dev: pointer to pci_dev to be added
*/
-static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
+static int add_error_device(struct aer_devices_err_info *e_dev, struct pci_dev *dev)
{
- if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
- e_info->dev[e_info->error_dev_num] = pci_dev_get(dev);
- e_info->error_dev_num++;
+ if (e_dev->err_info.error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
+ e_dev->dev[e_dev->err_info.error_dev_num] = pci_dev_get(dev);
+ e_dev->err_info.error_dev_num++;
return 0;
}
return -ENOSPC;
@@ -877,18 +889,18 @@ static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info)
static int find_device_iter(struct pci_dev *dev, void *data)
{
- struct aer_err_info *e_info = (struct aer_err_info *)data;
+ struct aer_devices_err_info *e_dev = (struct aer_devices_err_info *)data;
- if (is_error_source(dev, e_info)) {
+ if (is_error_source(dev, &e_dev->err_info)) {
/* List this device */
- if (add_error_device(e_info, dev)) {
+ if (add_error_device(e_dev, dev)) {
/* We cannot handle more... Stop iteration */
/* TODO: Should print error message here? */
return 1;
}
/* If there is only a single error, stop iteration */
- if (!e_info->multi_error_valid)
+ if (!e_dev->err_info.multi_error_valid)
return 1;
}
return 0;
@@ -897,7 +909,7 @@ static int find_device_iter(struct pci_dev *dev, void *data)
/**
* find_source_device - search through device hierarchy for source device
* @parent: pointer to Root Port pci_dev data structure
- * @e_info: including detailed error information such like id
+ * @e_dev: including detailed error information such like id
*
* Return true if found.
*
@@ -907,26 +919,26 @@ static int find_device_iter(struct pci_dev *dev, void *data)
* e_info->error_dev_num and e_info->dev[], based on the given information.
*/
static bool find_source_device(struct pci_dev *parent,
- struct aer_err_info *e_info)
+ struct aer_devices_err_info *e_dev)
{
struct pci_dev *dev = parent;
int result;
/* Must reset in this function */
- e_info->error_dev_num = 0;
+ e_dev->err_info.error_dev_num = 0;
/* Is Root Port an agent that sends error message? */
- result = find_device_iter(dev, e_info);
+ result = find_device_iter(dev, e_dev);
if (result)
return true;
if (pci_pcie_type(parent) == PCI_EXP_TYPE_RC_EC)
- pcie_walk_rcec(parent, find_device_iter, e_info);
+ pcie_walk_rcec(parent, find_device_iter, e_dev);
else
- pci_walk_bus(parent->subordinate, find_device_iter, e_info);
+ pci_walk_bus(parent->subordinate, find_device_iter, e_dev);
- if (!e_info->error_dev_num) {
- pci_info(parent, "can't find device of ID%04x\n", e_info->id);
+ if (!e_dev->err_info.error_dev_num) {
+ pci_info(parent, "can't find device of ID%04x\n", e_dev->err_info.id);
return false;
}
return true;
@@ -940,24 +952,42 @@ static bool find_source_device(struct pci_dev *parent,
* Invoked when an error being detected by Root Port.
*/
static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
+{
+ /*
+ * Correctable error does not need software intervention.
+ * No need to go through error recovery process.
+ */
+ if (info->severity == AER_NONFATAL)
+ pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset);
+ else if (info->severity == AER_FATAL)
+ pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset);
+ pci_dev_put(dev);
+}
+
+/**
+ * clear_error_source_aer_registers - clear AER registers of the error source device
+ * @dev: pointer to pci_dev data structure of error source device
+ * @info: comprehensive error information
+ *
+ * Invoked when an error being detected by Root Port but before we handle the
+ * error.
+ */
+static void clear_error_source_aer_registers(struct pci_dev *dev, struct aer_err_info info)
{
int aer = dev->aer_cap;
- if (info->severity == AER_CORRECTABLE) {
- /*
- * Correctable error does not need software intervention.
- * No need to go through error recovery process.
- */
+ if (info.severity == AER_CORRECTABLE) {
if (aer)
pci_write_config_dword(dev, aer + PCI_ERR_COR_STATUS,
- info->status);
+ info.status);
if (pcie_aer_is_native(dev))
pcie_clear_device_status(dev);
- } else if (info->severity == AER_NONFATAL)
- pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset);
- else if (info->severity == AER_FATAL)
- pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset);
- pci_dev_put(dev);
+ } else if (info.severity == AER_NONFATAL) {
+ pci_aer_clear_nonfatal_status(dev);
+ } else if (info.severity == AER_FATAL) {
+ pci_aer_clear_fatal_status(dev);
+ }
+
}
#ifdef CONFIG_ACPI_APEI_PCIEAER
@@ -1093,70 +1123,112 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
return 1;
}
-static inline void aer_process_err_devices(struct aer_err_info *e_info)
-{
- int i;
-
- /* Report all before handle them, not to lost records by reset etc. */
- for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
- if (aer_get_device_error_info(e_info->dev[i], e_info))
- aer_print_error(e_info->dev[i], e_info);
- }
- for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
- if (aer_get_device_error_info(e_info->dev[i], e_info))
- handle_error_source(e_info->dev[i], e_info);
- }
-}
-
/**
- * aer_isr_one_error - consume an error detected by root port
- * @rpc: pointer to the root port which holds an error
+ * aer_find_corr_error_source_device - find the error source which detected the corrected error
+ * @rp: pointer to Root Port pci_dev data structure
* @e_src: pointer to an error source
+ * @e_info: including detailed error information such like id
+ *
+ * Return true if found.
+ *
+ * Process the error information received at the Root Port, set these values
+ * in the aer_devices_err_info and find all the devices that are related to
+ * the error.
*/
-static void aer_isr_one_error(struct aer_rpc *rpc,
- struct aer_err_source *e_src)
+static bool aer_find_corr_error_source_device(struct pci_dev *rp,
+ struct aer_err_source *e_src,
+ struct aer_devices_err_info *e_info)
{
- struct pci_dev *pdev = rpc->rpd;
- struct aer_err_info e_info;
-
- pci_rootport_aer_stats_incr(pdev, e_src);
-
- /*
- * There is a possibility that both correctable error and
- * uncorrectable error being logged. Report correctable error first.
- */
if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
- e_info.id = ERR_COR_ID(e_src->id);
- e_info.severity = AER_CORRECTABLE;
+ e_info->err_info.id = ERR_COR_ID(e_src->id);
+ e_info->err_info.severity = AER_CORRECTABLE;
if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
- e_info.multi_error_valid = 1;
+ e_info->err_info.multi_error_valid = 1;
else
- e_info.multi_error_valid = 0;
- aer_print_port_info(pdev, &e_info);
+ e_info->err_info.multi_error_valid = 0;
- if (find_source_device(pdev, &e_info))
- aer_process_err_devices(&e_info);
+ if (!find_source_device(rp, e_info))
+ return false;
}
+ return true;
+}
+/**
+ * aer_find_uncorr_error_source_device - find the error source which detected the uncorrected error
+ * @rp: pointer to Root Port pci_dev data structure
+ * @e_src: pointer to an error source
+ * @e_info: including detailed error information such like id
+ *
+ * Return true if found.
+ *
+ * Process the error information received at the Root Port, set these values
+ * in the aer_devices_err_info and find all the devices that are related to
+ * the error.
+ */
+static bool aer_find_uncorr_error_source_device(struct pci_dev *rp,
+ struct aer_err_source *e_src,
+ struct aer_devices_err_info *e_info)
+{
if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
- e_info.id = ERR_UNCOR_ID(e_src->id);
+ e_info->err_info.id = ERR_UNCOR_ID(e_src->id);
if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
- e_info.severity = AER_FATAL;
+ e_info->err_info.severity = AER_FATAL;
else
- e_info.severity = AER_NONFATAL;
+ e_info->err_info.severity = AER_NONFATAL;
if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)
- e_info.multi_error_valid = 1;
+ e_info->err_info.multi_error_valid = 1;
else
- e_info.multi_error_valid = 0;
+ e_info->err_info.multi_error_valid = 0;
+
+ if (!find_source_device(rp, e_info))
+ return false;
+ }
- aer_print_port_info(pdev, &e_info);
+ return true;
+}
- if (find_source_device(pdev, &e_info))
- aer_process_err_devices(&e_info);
+/**
+ * aer_isr_one_error - consume an error detected by root port
+ * @rp: pointer to Root Port pci_dev data structure
+ * @e_dev: pointer to an error device
+ */
+static void aer_isr_one_error(struct pci_dev *rp, struct aer_dev_err_info *e_dev)
+{
+ aer_print_port_info(rp, &e_dev->err_info);
+ aer_print_error(e_dev->dev, &e_dev->err_info);
+ handle_error_source(e_dev->dev, &e_dev->err_info);
+}
+
+static bool aer_add_err_devices_to_queue(struct aer_rpc *rpc,
+ struct aer_devices_err_info *e_info)
+{
+ int i;
+ struct aer_dev_err_info *e_dev;
+
+ e_dev = kzalloc(sizeof(*e_dev), GFP_ATOMIC);
+ if (!e_dev)
+ return false;
+
+ for (i = 0; i < e_info->err_info.error_dev_num && e_info->dev[i]; i++) {
+ e_dev->err_info = e_info->err_info;
+ e_dev->dev = e_info->dev[i];
+
+ /*
+ * Store the AER register information for each error device on
+ * the queue
+ */
+ if (aer_get_device_error_info(e_dev->dev, &e_dev->err_info)) {
+ if (!kfifo_put(&rpc->aer_fifo, *e_dev))
+ return false;
+
+ clear_error_source_aer_registers(e_dev->dev, e_dev->err_info);
+ }
}
+
+ return true;
}
/**
@@ -1170,13 +1242,13 @@ static irqreturn_t aer_isr(int irq, void *context)
{
struct pcie_device *dev = (struct pcie_device *)context;
struct aer_rpc *rpc = get_service_data(dev);
- struct aer_err_source e_src;
+ struct aer_dev_err_info e_dev;
if (kfifo_is_empty(&rpc->aer_fifo))
return IRQ_NONE;
- while (kfifo_get(&rpc->aer_fifo, &e_src))
- aer_isr_one_error(rpc, &e_src);
+ while (kfifo_get(&rpc->aer_fifo, &e_dev))
+ aer_isr_one_error(rpc->rpd, &e_dev);
return IRQ_HANDLED;
}
@@ -1194,6 +1266,11 @@ static irqreturn_t aer_irq(int irq, void *context)
struct pci_dev *rp = rpc->rpd;
int aer = rp->aer_cap;
struct aer_err_source e_src = {};
+ struct aer_devices_err_info *e_info;
+
+ e_info = kzalloc(sizeof(*e_info), GFP_ATOMIC);
+ if (!e_info)
+ return IRQ_NONE;
pci_read_config_dword(rp, aer + PCI_ERR_ROOT_STATUS, &e_src.status);
if (!(e_src.status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV)))
@@ -1202,8 +1279,26 @@ static irqreturn_t aer_irq(int irq, void *context)
pci_read_config_dword(rp, aer + PCI_ERR_ROOT_ERR_SRC, &e_src.id);
pci_write_config_dword(rp, aer + PCI_ERR_ROOT_STATUS, e_src.status);
- if (!kfifo_put(&rpc->aer_fifo, e_src))
- return IRQ_HANDLED;
+ pci_rootport_aer_stats_incr(rp, &e_src);
+
+ /*
+ * There is a possibility that both correctable error and
+ * uncorrectable error are being logged. Find the devices which caused
+ * correctable errors first so that they can be added to the queue first
+ * and will be reported first.
+ *
+ * Before adding the error device to the queue to be handled, clear the
+ * AER status registers.
+ */
+ if (aer_find_corr_error_source_device(rp, &e_src, e_info)) {
+ if (!aer_add_err_devices_to_queue(rpc, e_info))
+ return IRQ_NONE;
+ }
+
+ if (aer_find_uncorr_error_source_device(rp, &e_src, e_info)) {
+ if (!aer_add_err_devices_to_queue(rpc, e_info))
+ return IRQ_NONE;
+ }
return IRQ_WAKE_THREAD;
}
--
2.25.1