From: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@linux.intel.com>
To: Terry Bowman <terry.bowman@amd.com>,
PradeepVineshReddy.Kodamati@amd.com, dave@stgolabs.net,
jonathan.cameron@huawei.com, dave.jiang@intel.com,
alison.schofield@intel.com, vishal.l.verma@intel.com,
ira.weiny@intel.com, dan.j.williams@intel.com,
bhelgaas@google.com, bp@alien8.de, ming.li@zohomail.com,
shiju.jose@huawei.com, dan.carpenter@linaro.org,
Smita.KoralahalliChannabasappa@amd.com,
kobayashi.da-06@fujitsu.com, yanfei.xu@intel.com,
rrichter@amd.com, peterz@infradead.org, colyli@suse.de,
uaisheng.ye@intel.com, fabio.m.de.francesco@linux.intel.com,
ilpo.jarvinen@linux.intel.com, yazen.ghannam@amd.com,
linux-cxl@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-pci@vger.kernel.org
Subject: Re: [PATCH v9 03/16] CXL/AER: Introduce kfifo for forwarding CXL errors
Date: Wed, 4 Jun 2025 15:50:42 -0700 [thread overview]
Message-ID: <52dfc3f1-b7e1-44f2-8f99-f3f37f44f00d@linux.intel.com> (raw)
In-Reply-To: <20250603172239.159260-4-terry.bowman@amd.com>
On 6/3/25 10:22 AM, Terry Bowman wrote:
> CXL error handling will soon be moved from the AER driver into the CXL
> driver. This requires a notification mechanism for the AER driver to share
> the AER interrupt with the CXL driver. The notification will be used
> as an indication for the CXL drivers to handle and log the CXL RAS errors.
>
> Add a kfifo work queue to be used by the AER driver and CXL driver. The AER
> driver will be the sole kfifo producer adding work and the cxl_core will be
> the sole kfifo consumer removing work. Add the boilerplate kfifo support.
>
> Add CXL work queue handler registration functions in the AER driver. Export
> the functions allowing CXL driver to access. Implement registration
> functions for the CXL driver to assign or clear the work handler function.
>
> Introduce function cxl_create_prot_err_info() and 'struct cxl_prot_err_info'.
> Implement cxl_create_prot_err_info() to populate a 'struct cxl_prot_err_info'
> instance with the AER severity and the erring device's PCI SBDF. The SBDF
> details will be used to rediscover the erring device after the CXL driver
> dequeues the kfifo work. The device rediscovery will be introduced along
> with the CXL handling in future patches.
>
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
> ---
> drivers/cxl/core/ras.c | 31 +++++++++-
> drivers/cxl/cxlpci.h | 1 +
> drivers/pci/pcie/aer.c | 132 ++++++++++++++++++++++++++++-------------
> include/linux/aer.h | 36 +++++++++++
> 4 files changed, 157 insertions(+), 43 deletions(-)
>
> diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
> index 485a831695c7..d35525e79e04 100644
> --- a/drivers/cxl/core/ras.c
> +++ b/drivers/cxl/core/ras.c
> @@ -5,6 +5,7 @@
> #include <linux/aer.h>
> #include <cxl/event.h>
> #include <cxlmem.h>
> +#include <cxlpci.h>
> #include "trace.h"
>
> static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
> @@ -107,13 +108,41 @@ static void cxl_cper_prot_err_work_fn(struct work_struct *work)
> }
> static DECLARE_WORK(cxl_cper_prot_err_work, cxl_cper_prot_err_work_fn);
>
> +#ifdef CONFIG_PCIEAER_CXL
> +
> +static void cxl_prot_err_work_fn(struct work_struct *work)
> +{
> +}
> +
> +#else
> +static void cxl_prot_err_work_fn(struct work_struct *work) { }
> +#endif /* CONFIG_PCIEAER_CXL */
> +
> +static struct work_struct cxl_prot_err_work;
> +static DECLARE_WORK(cxl_prot_err_work, cxl_prot_err_work_fn);
> +
> int cxl_ras_init(void)
> {
> - return cxl_cper_register_prot_err_work(&cxl_cper_prot_err_work);
> + int rc;
> +
> + rc = cxl_cper_register_prot_err_work(&cxl_cper_prot_err_work);
> + if (rc)
> + pr_err("Failed to register CPER AER kfifo (%x)", rc);
> +
> + rc = cxl_register_prot_err_work(&cxl_prot_err_work);
> + if (rc) {
> + pr_err("Failed to register native AER kfifo (%x)", rc);
> + return rc;
> + }
> +
> + return 0;
> }
>
> void cxl_ras_exit(void)
> {
> cxl_cper_unregister_prot_err_work(&cxl_cper_prot_err_work);
> cancel_work_sync(&cxl_cper_prot_err_work);
> +
> + cxl_unregister_prot_err_work();
> + cancel_work_sync(&cxl_prot_err_work);
> }
> diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
> index 54e219b0049e..6f1396ef7b77 100644
> --- a/drivers/cxl/cxlpci.h
> +++ b/drivers/cxl/cxlpci.h
> @@ -4,6 +4,7 @@
> #define __CXL_PCI_H__
> #include <linux/pci.h>
> #include "cxl.h"
> +#include "linux/aer.h"
>
> #define CXL_MEMORY_PROGIF 0x10
>
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index adb4b1123b9b..5350fa5be784 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -114,6 +114,14 @@ struct aer_stats {
> static int pcie_aer_disable;
> static pci_ers_result_t aer_root_reset(struct pci_dev *dev);
>
> +#if defined(CONFIG_PCIEAER_CXL)
> +#define CXL_ERROR_SOURCES_MAX 128
> +static DEFINE_KFIFO(cxl_prot_err_fifo, struct cxl_prot_err_work_data,
> + CXL_ERROR_SOURCES_MAX);
> +static DEFINE_SPINLOCK(cxl_prot_err_fifo_lock);
> +struct work_struct *cxl_prot_err_work;
> +#endif
> +
> void pci_no_aer(void)
> {
> pcie_aer_disable = 1;
> @@ -1004,45 +1012,17 @@ static bool is_internal_error(struct aer_err_info *info)
> return info->status & PCI_ERR_UNC_INTN;
> }
>
> -static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data)
> +static bool is_cxl_error(struct pci_dev *pdev, struct aer_err_info *info)
> {
> - struct aer_err_info *info = (struct aer_err_info *)data;
> - const struct pci_error_handlers *err_handler;
> + if (!info || !info->is_cxl)
> + return false;
>
> - if (!is_cxl_mem_dev(dev) || !cxl_error_is_native(dev))
> - return 0;
> + /* Only CXL Endpoints are currently supported */
> + if ((pci_pcie_type(pdev) != PCI_EXP_TYPE_ENDPOINT) &&
> + (pci_pcie_type(pdev) != PCI_EXP_TYPE_RC_EC))
> + return false;
>
> - /* Protect dev->driver */
> - device_lock(&dev->dev);
> -
> - err_handler = dev->driver ? dev->driver->err_handler : NULL;
> - if (!err_handler)
> - goto out;
> -
> - if (info->severity == AER_CORRECTABLE) {
> - if (err_handler->cor_error_detected)
> - err_handler->cor_error_detected(dev);
> - } else if (err_handler->error_detected) {
> - if (info->severity == AER_NONFATAL)
> - err_handler->error_detected(dev, pci_channel_io_normal);
> - else if (info->severity == AER_FATAL)
> - err_handler->error_detected(dev, pci_channel_io_frozen);
> - }
> -out:
> - device_unlock(&dev->dev);
> - return 0;
> -}
> -
> -static void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info)
> -{
> - /*
> - * Internal errors of an RCEC indicate an AER error in an
> - * RCH's downstream port. Check and handle them in the CXL.mem
> - * device driver.
> - */
> - if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC &&
> - is_internal_error(info))
> - pcie_walk_rcec(dev, cxl_rch_handle_error_iter, info);
> + return is_internal_error(info);
> }
>
> static int handles_cxl_error_iter(struct pci_dev *dev, void *data)
> @@ -1056,13 +1036,17 @@ static int handles_cxl_error_iter(struct pci_dev *dev, void *data)
> return *handles_cxl;
> }
>
> -static bool handles_cxl_errors(struct pci_dev *rcec)
> +static bool handles_cxl_errors(struct pci_dev *dev)
> {
> bool handles_cxl = false;
>
> - if (pci_pcie_type(rcec) == PCI_EXP_TYPE_RC_EC &&
> - pcie_aer_is_native(rcec))
> - pcie_walk_rcec(rcec, handles_cxl_error_iter, &handles_cxl);
> + if (!pcie_aer_is_native(dev))
> + return false;
> +
> + if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC)
> + pcie_walk_rcec(dev, handles_cxl_error_iter, &handles_cxl);
> + else
> + handles_cxl = pcie_is_cxl(dev);
>
> return handles_cxl;
> }
> @@ -1076,10 +1060,46 @@ static void cxl_rch_enable_rcec(struct pci_dev *rcec)
> pci_info(rcec, "CXL: Internal errors unmasked");
> }
>
> +static int cxl_create_prot_error_info(struct pci_dev *pdev,
> + struct aer_err_info *aer_err_info,
> + struct cxl_prot_error_info *cxl_err_info)
> +{
> + cxl_err_info->severity = aer_err_info->severity;
> +
> + cxl_err_info->function = PCI_FUNC(pdev->devfn);
> + cxl_err_info->device = PCI_SLOT(pdev->devfn);
> + cxl_err_info->bus = pdev->bus->number;
> + cxl_err_info->segment = pci_domain_nr(pdev->bus);
> +
> + return 0;
> +}
> +
> +static void forward_cxl_error(struct pci_dev *pdev, struct aer_err_info *aer_err_info)
> +{
> + struct cxl_prot_err_work_data wd;
> + struct cxl_prot_error_info *cxl_err_info = &wd.err_info;
> +
> + cxl_create_prot_error_info(pdev, aer_err_info, cxl_err_info);
> +
> + if (!kfifo_put(&cxl_prot_err_fifo, wd)) {
> + dev_err_ratelimited(&pdev->dev, "CXL kfifo overflow\n");
> + return;
> + }
> +
> + schedule_work(cxl_prot_err_work);
> +}
> +
> #else
> static inline void cxl_rch_enable_rcec(struct pci_dev *dev) { }
> static inline void cxl_rch_handle_error(struct pci_dev *dev,
> struct aer_err_info *info) { }
> +static inline void forward_cxl_error(struct pci_dev *dev,
> + struct aer_err_info *info) { }
> +static inline bool handles_cxl_errors(struct pci_dev *dev)
> +{
> + return false;
> +}
> +static bool is_cxl_error(struct pci_dev *pdev, struct aer_err_info *info) { return 0; };
> #endif
>
> /**
> @@ -1117,8 +1137,11 @@ static void pci_aer_handle_error(struct pci_dev *dev, struct aer_err_info *info)
>
> static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
> {
> - cxl_rch_handle_error(dev, info);
> - pci_aer_handle_error(dev, info);
> + if (is_cxl_error(dev, info))
> + forward_cxl_error(dev, info);
> + else
> + pci_aer_handle_error(dev, info);
> +
> pci_dev_put(dev);
> }
>
> @@ -1582,6 +1605,31 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
> return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
> }
>
> +#if defined(CONFIG_PCIEAER_CXL)
> +
> +int cxl_register_prot_err_work(struct work_struct *work)
> +{
> + guard(spinlock)(&cxl_prot_err_fifo_lock);
> + cxl_prot_err_work = work;
> + return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_register_prot_err_work, "CXL");
> +
> +int cxl_unregister_prot_err_work(void)
> +{
> + guard(spinlock)(&cxl_prot_err_fifo_lock);
> + cxl_prot_err_work = NULL;
> + return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_unregister_prot_err_work, "CXL");
> +
Above two functions can never fail, right? What not make them return void?
> +int cxl_prot_err_kfifo_get(struct cxl_prot_err_work_data *wd)
> +{
> + return kfifo_get(&cxl_prot_err_fifo, wd);
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_prot_err_kfifo_get, "CXL");
> +#endif
> +
> static struct pcie_port_service_driver aerdriver = {
> .name = "aer",
> .port_type = PCIE_ANY_PORT,
> diff --git a/include/linux/aer.h b/include/linux/aer.h
> index 02940be66324..550407240ab5 100644
> --- a/include/linux/aer.h
> +++ b/include/linux/aer.h
> @@ -10,6 +10,7 @@
>
> #include <linux/errno.h>
> #include <linux/types.h>
> +#include <linux/workqueue_types.h>
>
> #define AER_NONFATAL 0
> #define AER_FATAL 1
> @@ -53,6 +54,27 @@ struct aer_capability_regs {
> u16 uncor_err_source;
> };
>
> +/**
> + * struct cxl_prot_err_info - Error information used in CXL error handling
> + * @severity: AER severity
> + * @function: Device's PCI function
> + * @device: Device's PCI device
> + * @bus: Device's PCI bus
> + * @segment: Device's PCI segment
> + */
> +struct cxl_prot_error_info {
> + int severity;
> +
> + u8 function;
> + u8 device;
> + u8 bus;
> + u16 segment;
> +};
> +
> +struct cxl_prot_err_work_data {
> + struct cxl_prot_error_info err_info;
> +};
> +
> #if defined(CONFIG_PCIEAER)
> int pci_aer_clear_nonfatal_status(struct pci_dev *dev);
> int pcie_aer_is_native(struct pci_dev *dev);
> @@ -64,6 +86,20 @@ static inline int pci_aer_clear_nonfatal_status(struct pci_dev *dev)
> static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; }
> #endif
>
> +#if defined(CONFIG_PCIEAER_CXL)
> +int cxl_register_prot_err_work(struct work_struct *work);
> +int cxl_unregister_prot_err_work(void);
> +int cxl_prot_err_kfifo_get(struct cxl_prot_err_work_data *wd);
> +#else
> +static inline int
> +cxl_register_prot_err_work(struct work_struct *work)
> +{
> + return 0;
> +}
> +static inline int cxl_unregister_prot_err_work(void) { return 0; }
> +static inline int cxl_prot_err_kfifo_get(struct cxl_prot_err_work_data *wd) { return 0; }
> +#endif
> +
> void pci_print_aer(struct pci_dev *dev, int aer_severity,
> struct aer_capability_regs *aer);
> int cper_severity_to_aer(int cper_severity);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
next prev parent reply other threads:[~2025-06-04 22:50 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-03 17:22 [PATCH v9 00/16] Enable CXL PCIe port protocol error handling and logging Terry Bowman
2025-06-03 17:22 ` [PATCH v9 01/16] PCI/CXL: Add pcie_is_cxl() Terry Bowman
2025-06-04 19:06 ` Sathyanarayanan Kuppuswamy
2025-06-04 19:18 ` Bowman, Terry
2025-06-05 23:24 ` Dave Jiang
2025-06-03 17:22 ` [PATCH v9 02/16] PCI/AER: Report CXL or PCIe bus error type in trace logging Terry Bowman
2025-06-03 22:02 ` Sathyanarayanan Kuppuswamy
2025-06-04 14:32 ` Bowman, Terry
2025-06-04 19:24 ` Sathyanarayanan Kuppuswamy
2025-06-04 21:30 ` Bowman, Terry
2025-06-05 23:28 ` Dave Jiang
2025-06-03 17:22 ` [PATCH v9 03/16] CXL/AER: Introduce kfifo for forwarding CXL errors Terry Bowman
2025-06-04 6:01 ` Dan Carpenter
2025-06-04 14:37 ` Bowman, Terry
2025-06-04 17:24 ` Dan Carpenter
2025-06-04 19:21 ` Bowman, Terry
2025-06-04 22:50 ` Sathyanarayanan Kuppuswamy [this message]
2025-06-05 14:04 ` Bowman, Terry
2025-06-06 0:27 ` Dave Jiang
2025-06-06 14:27 ` Bowman, Terry
2025-06-06 14:36 ` Dave Jiang
2025-06-12 11:04 ` Jonathan Cameron
2025-06-12 14:29 ` Bowman, Terry
2025-06-03 17:22 ` [PATCH v9 04/16] PCI/AER: Dequeue forwarded CXL error Terry Bowman
2025-06-04 6:05 ` Dan Carpenter
2025-06-04 14:38 ` Bowman, Terry
2025-06-04 23:58 ` Sathyanarayanan Kuppuswamy
2025-06-06 15:57 ` Dave Jiang
2025-06-06 18:14 ` Bowman, Terry
2025-06-06 22:43 ` Dave Jiang
2025-06-09 19:57 ` Bowman, Terry
2025-06-09 20:34 ` Dave Jiang
2025-06-12 11:17 ` Jonathan Cameron
2025-06-06 21:08 ` Bowman, Terry
2025-06-06 23:15 ` Bowman, Terry
2025-06-09 20:17 ` Dave Jiang
2025-06-10 4:15 ` Lukas Wunner
2025-06-10 18:07 ` Bowman, Terry
2025-06-10 21:20 ` Bowman, Terry
2025-06-11 4:38 ` Lukas Wunner
2025-06-17 16:08 ` Dave Jiang
2025-06-17 18:20 ` Robert Richter
2025-06-12 11:36 ` Jonathan Cameron
2025-06-12 18:35 ` Bowman, Terry
2025-06-03 17:22 ` [PATCH v9 05/16] CXL/PCI: Introduce CXL uncorrectable protocol error recovery Terry Bowman
2025-06-05 15:14 ` Sathyanarayanan Kuppuswamy
2025-06-05 16:01 ` Bowman, Terry
2025-06-06 16:45 ` Dave Jiang
2025-06-06 18:16 ` Bowman, Terry
2025-06-12 16:06 ` Jonathan Cameron
2025-06-12 16:29 ` Bowman, Terry
2025-06-03 17:22 ` [PATCH v9 06/16] cxl/pci: Move RAS initialization to cxl_port driver Terry Bowman
2025-06-06 17:04 ` Dave Jiang
2025-06-06 18:17 ` Bowman, Terry
2025-06-03 17:22 ` [PATCH v9 07/16] cxl/pci: Map CXL Endpoint Port and CXL Switch Port RAS registers Terry Bowman
2025-06-03 17:22 ` [PATCH v9 08/16] cxl/pci: Update RAS handler interfaces to also support CXL Ports Terry Bowman
2025-06-05 16:42 ` Sathyanarayanan Kuppuswamy
2025-06-03 17:22 ` [PATCH v9 09/16] cxl/pci: Log message if RAS registers are unmapped Terry Bowman
2025-06-05 16:42 ` Sathyanarayanan Kuppuswamy
2025-06-06 17:27 ` Dave Jiang
2025-06-03 17:22 ` [PATCH v9 10/16] cxl/pci: Unify CXL trace logging for CXL Endpoints and CXL Ports Terry Bowman
2025-06-05 16:49 ` Sathyanarayanan Kuppuswamy
2025-06-06 9:08 ` Shiju Jose
2025-06-06 14:41 ` Bowman, Terry
2025-06-06 15:24 ` Bowman, Terry
2025-06-12 16:25 ` Jonathan Cameron
2025-06-03 17:22 ` [PATCH v9 11/16] cxl/pci: Update __cxl_handle_cor_ras() to return early if no RAS errors Terry Bowman
2025-06-05 18:37 ` Sathyanarayanan Kuppuswamy
2025-06-06 20:30 ` Dave Jiang
2025-06-06 20:55 ` Bowman, Terry
2025-06-06 22:38 ` Dave Jiang
2025-06-12 16:46 ` Jonathan Cameron
2025-06-16 20:30 ` Bowman, Terry
2025-06-03 17:22 ` [PATCH v9 12/16] cxl/pci: Introduce CXL Endpoint protocol error handlers Terry Bowman
2025-06-06 0:22 ` Sathyanarayanan Kuppuswamy
2025-06-12 16:55 ` Jonathan Cameron
2025-06-03 17:22 ` [PATCH v9 13/16] cxl/pci: Introduce CXL Port " Terry Bowman
2025-06-06 0:50 ` Sathyanarayanan Kuppuswamy
2025-06-12 17:14 ` Jonathan Cameron
2025-06-16 22:17 ` Bowman, Terry
2025-06-03 17:22 ` [PATCH v9 14/16] cxl/pci: Remove unnecessary CXL Endpoint handling helper functions Terry Bowman
2025-06-06 0:50 ` Sathyanarayanan Kuppuswamy
2025-06-12 17:16 ` Jonathan Cameron
2025-06-03 17:22 ` [PATCH v9 15/16] CXL/PCI: Enable CXL protocol errors during CXL Port probe Terry Bowman
2025-06-06 0:51 ` Sathyanarayanan Kuppuswamy
2025-06-03 17:22 ` [PATCH v9 16/16] CXL/PCI: Disable CXL protocol error interrupts during CXL Port cleanup Terry Bowman
2025-06-06 0:52 ` Sathyanarayanan Kuppuswamy
2025-06-06 13:51 ` Bowman, Terry
2025-06-06 22:59 ` Dave Jiang
2025-06-12 17:19 ` Jonathan Cameron
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=52dfc3f1-b7e1-44f2-8f99-f3f37f44f00d@linux.intel.com \
--to=sathyanarayanan.kuppuswamy@linux.intel.com \
--cc=PradeepVineshReddy.Kodamati@amd.com \
--cc=Smita.KoralahalliChannabasappa@amd.com \
--cc=alison.schofield@intel.com \
--cc=bhelgaas@google.com \
--cc=bp@alien8.de \
--cc=colyli@suse.de \
--cc=dan.carpenter@linaro.org \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=dave@stgolabs.net \
--cc=fabio.m.de.francesco@linux.intel.com \
--cc=ilpo.jarvinen@linux.intel.com \
--cc=ira.weiny@intel.com \
--cc=jonathan.cameron@huawei.com \
--cc=kobayashi.da-06@fujitsu.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=ming.li@zohomail.com \
--cc=peterz@infradead.org \
--cc=rrichter@amd.com \
--cc=shiju.jose@huawei.com \
--cc=terry.bowman@amd.com \
--cc=uaisheng.ye@intel.com \
--cc=vishal.l.verma@intel.com \
--cc=yanfei.xu@intel.com \
--cc=yazen.ghannam@amd.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).