On Fri, Nov 20, 2020 at 04:10:33PM -0800, Sean V Kelley wrote:
> From: Qiuxu Zhuo <qiuxu.z...@intel.com>
>
> When attempting error recovery for an RCiEP associated with an RCEC device,
> there needs to be a way to update the Root Error Status, the Uncorrectable
> Error Status and the Uncorrectable Error Severity of the parent RCEC. In
> some non-native cases in which there is no OS-visible device associated
> with the RCiEP, there is nothing to act upon as the firmware is acting
> before the OS.
>
> Add handling for the linked RCEC in AER/ERR while taking into account
> non-native cases.
>
> Co-developed-by: Sean V Kelley <sean.v.kel...@intel.com>
> Link:
> https://lore.kernel.org/r/20201002184735.1229220-12-seanvk....@oregontracks.org
> Signed-off-by: Sean V Kelley <sean.v.kel...@intel.com>
> Signed-off-by: Qiuxu Zhuo <qiuxu.z...@intel.com>
> Signed-off-by: Bjorn Helgaas <bhelg...@google.com>
> Reviewed-by: Jonathan Cameron <jonathan.came...@huawei.com>
> ---
> drivers/pci/pcie/aer.c | 46 +++++++++++++++++++++++++++++++-----------
> drivers/pci/pcie/err.c | 20 +++++++++---------
> 2 files changed, 44 insertions(+), 22 deletions(-)
>
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index 0ba0b47ae751..51389a6ee4ca 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -1358,29 +1358,51 @@ static int aer_probe(struct pcie_device *dev)
> */
> static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
> {
> - int aer = dev->aer_cap;
> + int type = pci_pcie_type(dev);
> + struct pci_dev *root;
> + int aer = 0;
> + int rc = 0;
> u32 reg32;
> - int rc;
>
> - if (pcie_aer_is_native(dev)) {
> + if (type == PCI_EXP_TYPE_RC_END)
> + /*
> + * The reset should only clear the Root Error Status
> + * of the RCEC. Only perform this for the
> + * native case, i.e., an RCEC is present.
> + */
> + root = dev->rcec;
> + else
> + root = dev;
> +
> + if (root)
> + aer = dev->aer_cap;
> +
> + if ((aer) && pcie_aer_is_native(dev)) {
> /* Disable Root's interrupt in response to error messages */
> - pci_read_config_dword(dev, aer + PCI_ERR_ROOT_COMMAND, ®32);
> + pci_read_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, ®32);
> reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
> - pci_write_config_dword(dev, aer + PCI_ERR_ROOT_COMMAND, reg32);
> + pci_write_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, reg32);
> }
>
> - rc = pci_bus_error_reset(dev);
> - pci_info(dev, "Root Port link has been reset (%d)\n", rc);
> + if (type == PCI_EXP_TYPE_RC_EC || type == PCI_EXP_TYPE_RC_END) {
> + if (pcie_has_flr(dev)) {
> + rc = pcie_flr(dev);
> + pci_info(dev, "has been reset (%d)\n", rc);
Maybe:
+ } else {
+ rc = -ENOTTY;
+ pci_info(dev, "not reset (no FLR support)\n");
Or do we want to pretend the device was reset and return
PCI_ERS_RESULT_RECOVERED?
> + } else {
> + rc = pci_bus_error_reset(dev);
> + pci_info(dev, "Root Port link has been reset (%d)\n", rc);
> + }
>
> - if (pcie_aer_is_native(dev)) {
> + if ((aer) && pcie_aer_is_native(dev)) {
> /* Clear Root Error Status */
> - pci_read_config_dword(dev, aer + PCI_ERR_ROOT_STATUS, ®32);
> - pci_write_config_dword(dev, aer + PCI_ERR_ROOT_STATUS, reg32);
> + pci_read_config_dword(root, aer + PCI_ERR_ROOT_STATUS, ®32);
> + pci_write_config_dword(root, aer + PCI_ERR_ROOT_STATUS, reg32);
>
> /* Enable Root Port's interrupt in response to error messages */
> - pci_read_config_dword(dev, aer + PCI_ERR_ROOT_COMMAND, ®32);
> + pci_read_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, ®32);
> reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
> - pci_write_config_dword(dev, aer + PCI_ERR_ROOT_COMMAND, reg32);
> + pci_write_config_dword(root, aer + PCI_ERR_ROOT_COMMAND, reg32);
> }
>
> return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
> diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
> index 7883c9791562..cbc5abfe767b 100644
> --- a/drivers/pci/pcie/err.c
> +++ b/drivers/pci/pcie/err.c
> @@ -148,10 +148,10 @@ static int report_resume(struct pci_dev *dev, void
> *data)
>
> /**
> * pci_walk_bridge - walk bridges potentially AER affected
> - * @bridge: bridge which may be a Port, an RCEC with associated RCiEPs,
> - * or an RCiEP associated with an RCEC
> - * @cb: callback to be called for each device found
> - * @userdata: arbitrary pointer to be passed to callback
> + * @bridge bridge which may be an RCEC with associated RCiEPs,
> + * or a Port.
> + * @cb callback to be called for each device found
> + * @userdata arbitrary pointer to be passed to callback.
> *
> * If the device provided is a bridge, walk the subordinate bus, including
> * any bridged devices on buses under this bus. Call the provided callback
> @@ -164,8 +164,14 @@ static void pci_walk_bridge(struct pci_dev *bridge,
> int (*cb)(struct pci_dev *, void *),
> void *userdata)
> {
> + /*
> + * In a non-native case where there is no OS-visible reporting
> + * device the bridge will be NULL, i.e., no RCEC, no Downstream Port.
I don't quite understand this comment. I see that in the non-native
case, the reporting device may not be OS-visible. But I don't
understand why the comment is *here*.
If "bridge" can be NULL here, we should test that before dereferencing
"bridge->subordinate".
> if (bridge->subordinate)
> pci_walk_bus(bridge->subordinate, cb, userdata);
> + else if (bridge->rcec)
> + cb(bridge->rcec, userdata);
And I don't understand what's going on here. In this case, I *think*
"bridge" is an RCiEP and "bridge->rcec" is the related RCEC, so it
looks like we'll call report_frozen_detected(), report_mmio_enabled(),
etc for the RCEC driver. I would think we'd want the RCiEP driver.
Sorry if I'm missing the obvious.
> else
> cb(bridge, userdata);
> }
> @@ -194,12 +200,6 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
> pci_dbg(bridge, "broadcast error_detected message\n");
> if (state == pci_channel_io_frozen) {
> pci_walk_bridge(bridge, report_frozen_detected, &status);
> - if (type == PCI_EXP_TYPE_RC_END) {
> - pci_warn(dev, "subordinate device reset not possible
> for RCiEP\n");
> - status = PCI_ERS_RESULT_NONE;
> - goto failed;
> - }
> -
> status = reset_subordinates(bridge);
> if (status != PCI_ERS_RESULT_RECOVERED) {
> pci_warn(bridge, "subordinate device reset failed\n");
> --
> 2.29.2
>
