Skip to content

Commit 0a86756

Browse files
Robert Richterdjbw
authored andcommitted
PCI/AER: Forward RCH downstream port-detected errors to the CXL.mem dev handler
In Restricted CXL Device (RCD) mode a CXL device is exposed as an RCiEP, but CXL downstream and upstream ports are not enumerated and not visible in the PCIe hierarchy. [1] Protocol and link errors from these non-enumerated ports are signaled as internal AER errors, either Uncorrectable Internal Error (UIE) or Corrected Internal Errors (CIE) via an RCEC. Restricted CXL host (RCH) downstream port-detected errors have the Requester ID of the RCEC set in the RCEC's AER Error Source ID register. A CXL handler must then inspect the error status in various CXL registers residing in the dport's component register space (CXL RAS capability) or the dport's RCRB (PCIe AER extended capability). [2] Errors showing up in the RCEC's error handler must be handled and connected to the CXL subsystem. Implement this by forwarding the error to all CXL devices below the RCEC. Since the entire CXL device is controlled only using PCIe Configuration Space of device 0, function 0, only pass it there [3]. The error handling is limited to currently supported devices with the Memory Device class code set (CXL Type 3 Device, PCI_CLASS_MEMORY_CXL, 502h), handle downstream port errors in the device's cxl_pci driver. Support for other CXL Device Types (e.g. a CXL.cache Device) can be added later. To handle downstream port errors in addition to errors directed to the CXL endpoint device, a handler must also inspect the CXL RAS and PCIe AER capabilities of the CXL downstream port the device is connected to. Since CXL downstream port errors are signaled using internal errors, the handler requires those errors to be unmasked. This is subject of a follow-on patch. The reason for choosing this implementation is that the AER service driver claims the RCEC device, but does not allow it to register a custom specific handler to support CXL. Connecting the RCEC hard-wired with a CXL handler does not work, as the CXL subsystem might not be present all the time. The alternative to add an implementation to the portdrv to allow the registration of a custom RCEC error handler isn't worth doing it as CXL would be its only user. Instead, just check for an CXL RCEC and pass it down to the connected CXL device's error handler. With this approach the code can entirely be implemented in the PCIe AER driver and is independent of the CXL subsystem. The CXL driver only provides the handler. [1] CXL 3.0 spec: 9.11.8 CXL Devices Attached to an RCH [2] CXL 3.0 spec, 12.2.1.1 RCH Downstream Port-detected Errors [3] CXL 3.0 spec, 8.1.3 PCIe DVSEC for CXL Devices Co-developed-by: Terry Bowman <terry.bowman@amd.com> Signed-off-by: Terry Bowman <terry.bowman@amd.com> Signed-off-by: Robert Richter <rrichter@amd.com> Cc: Oliver O'Halloran <oohall@gmail.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-pci@vger.kernel.org Acked-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/20231018171713.1883517-18-rrichter@amd.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
1 parent d1a9def commit 0a86756

File tree

2 files changed

+100
-2
lines changed

2 files changed

+100
-2
lines changed

drivers/pci/pcie/Kconfig

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -49,6 +49,15 @@ config PCIEAER_INJECT
4949
gotten from:
5050
https://git.kernel.org/cgit/linux/kernel/git/gong.chen/aer-inject.git/
5151

52+
config PCIEAER_CXL
53+
bool "PCI Express CXL RAS support"
54+
default y
55+
depends on PCIEAER && CXL_PCI
56+
help
57+
Enables CXL error handling.
58+
59+
If unsure, say Y.
60+
5261
#
5362
# PCI Express ECRC
5463
#

drivers/pci/pcie/aer.c

Lines changed: 91 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -934,14 +934,97 @@ static bool find_source_device(struct pci_dev *parent,
934934
return true;
935935
}
936936

937+
#ifdef CONFIG_PCIEAER_CXL
938+
939+
static bool is_cxl_mem_dev(struct pci_dev *dev)
940+
{
941+
/*
942+
* The capability, status, and control fields in Device 0,
943+
* Function 0 DVSEC control the CXL functionality of the
944+
* entire device (CXL 3.0, 8.1.3).
945+
*/
946+
if (dev->devfn != PCI_DEVFN(0, 0))
947+
return false;
948+
949+
/*
950+
* CXL Memory Devices must have the 502h class code set (CXL
951+
* 3.0, 8.1.12.1).
952+
*/
953+
if ((dev->class >> 8) != PCI_CLASS_MEMORY_CXL)
954+
return false;
955+
956+
return true;
957+
}
958+
959+
static bool cxl_error_is_native(struct pci_dev *dev)
960+
{
961+
struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
962+
963+
return (pcie_ports_native || host->native_aer);
964+
}
965+
966+
static bool is_internal_error(struct aer_err_info *info)
967+
{
968+
if (info->severity == AER_CORRECTABLE)
969+
return info->status & PCI_ERR_COR_INTERNAL;
970+
971+
return info->status & PCI_ERR_UNC_INTN;
972+
}
973+
974+
static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data)
975+
{
976+
struct aer_err_info *info = (struct aer_err_info *)data;
977+
const struct pci_error_handlers *err_handler;
978+
979+
if (!is_cxl_mem_dev(dev) || !cxl_error_is_native(dev))
980+
return 0;
981+
982+
/* protect dev->driver */
983+
device_lock(&dev->dev);
984+
985+
err_handler = dev->driver ? dev->driver->err_handler : NULL;
986+
if (!err_handler)
987+
goto out;
988+
989+
if (info->severity == AER_CORRECTABLE) {
990+
if (err_handler->cor_error_detected)
991+
err_handler->cor_error_detected(dev);
992+
} else if (err_handler->error_detected) {
993+
if (info->severity == AER_NONFATAL)
994+
err_handler->error_detected(dev, pci_channel_io_normal);
995+
else if (info->severity == AER_FATAL)
996+
err_handler->error_detected(dev, pci_channel_io_frozen);
997+
}
998+
out:
999+
device_unlock(&dev->dev);
1000+
return 0;
1001+
}
1002+
1003+
static void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info)
1004+
{
1005+
/*
1006+
* Internal errors of an RCEC indicate an AER error in an
1007+
* RCH's downstream port. Check and handle them in the CXL.mem
1008+
* device driver.
1009+
*/
1010+
if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC &&
1011+
is_internal_error(info))
1012+
pcie_walk_rcec(dev, cxl_rch_handle_error_iter, info);
1013+
}
1014+
1015+
#else
1016+
static inline void cxl_rch_handle_error(struct pci_dev *dev,
1017+
struct aer_err_info *info) { }
1018+
#endif
1019+
9371020
/**
938-
* handle_error_source - handle logging error into an event log
1021+
* pci_aer_handle_error - handle logging error into an event log
9391022
* @dev: pointer to pci_dev data structure of error source device
9401023
* @info: comprehensive error information
9411024
*
9421025
* Invoked when an error being detected by Root Port.
9431026
*/
944-
static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
1027+
static void pci_aer_handle_error(struct pci_dev *dev, struct aer_err_info *info)
9451028
{
9461029
int aer = dev->aer_cap;
9471030

@@ -965,6 +1048,12 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
9651048
pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset);
9661049
else if (info->severity == AER_FATAL)
9671050
pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset);
1051+
}
1052+
1053+
static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
1054+
{
1055+
cxl_rch_handle_error(dev, info);
1056+
pci_aer_handle_error(dev, info);
9681057
pci_dev_put(dev);
9691058
}
9701059

0 commit comments

Comments
 (0)