| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <9e602b57-c064-43a3-ab57-343773c07863@intel.com>
Date: Thu, 31 Oct 2024 09:37:15 -0700
From: Dave Jiang <dave.jiang@...el.com>
To: Terry Bowman <terry.bowman@....com>, ming4.li@...el.com,
linux-cxl@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-pci@...r.kernel.org, dave@...olabs.net, jonathan.cameron@...wei.com,
alison.schofield@...el.com, vishal.l.verma@...el.com,
dan.j.williams@...el.com, bhelgaas@...gle.com, mahesh@...ux.ibm.com,
ira.weiny@...el.com, oohall@...il.com, Benjamin.Cheatham@....com,
rrichter@....com, nathan.fontenot@....com,
Smita.KoralahalliChannabasappa@....com
Subject: Re: [PATCH v2 05/14] PCI/AER: Add CXL PCIe port correctable error
support in AER service driver
On 10/25/24 2:02 PM, Terry Bowman wrote:
> The AER service driver doesn't currently handle CXL protocol errors
> reported by CXL root ports, CXL upstream switch ports, and CXL downstream
> switch ports. Consequently, RAS protocol errors from CXL PCIe port devices
> are not properly logged or handled.
>
> These errors are reported to the OS via the root port's AER correctable
> and uncorrectable internal error fields. While the AER driver supports
> handling downstream port protocol errors in restricted CXL host (RCH) mode
> also known as CXL1.1, it lacks the same functionality for CXL PCIe ports
> operating in virtual hierarchy (VH) mode.
>
> To address this gap, update the AER driver to handle CXL PCIe port device
> protocol correctable errors (CE).
>
> Make this update alongside the existing downstream port RCH error handling
> logic, extending support to CXL PCIe ports in VH mode.
>
> is_internal_error() is currently limited by CONFIG_PCIEAER_CXL kernel
> config. Update is_internal_error()'s function declaration such that it is
> always available regardless if CONFIG_PCIEAER_CXL kernel config is enabled
> or disabled.
>
> The uncorrectable error (UCE) handling will be added in a future patch.
>
> [1] CXL 3.1 Spec, 12.2.2 CXL Root Ports, Downstream Switch Ports, and
> Upstream Switch Ports
>
> Signed-off-by: Terry Bowman <terry.bowman@....com>
With the commit log update from what Jonathan suggested,
Reviewed-by: Dave Jiang <dave.jiang@...el.com>
> ---
> drivers/pci/pcie/aer.c | 59 ++++++++++++++++++++++++++++--------------
> 1 file changed, 39 insertions(+), 20 deletions(-)
>
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index 53e9a11f6c0f..1d3e5b929661 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -941,8 +941,15 @@ static bool find_source_device(struct pci_dev *parent,
> return true;
> }
>
> -#ifdef CONFIG_PCIEAER_CXL
> +static bool is_internal_error(struct aer_err_info *info)
> +{
> + if (info->severity == AER_CORRECTABLE)
> + return info->status & PCI_ERR_COR_INTERNAL;
>
> + return info->status & PCI_ERR_UNC_INTN;
> +}
> +
> +#ifdef CONFIG_PCIEAER_CXL
> /**
> * pci_aer_unmask_internal_errors - unmask internal errors
> * @dev: pointer to the pcie_dev data structure
> @@ -994,14 +1001,6 @@ static bool cxl_error_is_native(struct pci_dev *dev)
> return (pcie_ports_native || host->native_aer);
> }
>
> -static bool is_internal_error(struct aer_err_info *info)
> -{
> - if (info->severity == AER_CORRECTABLE)
> - return info->status & PCI_ERR_COR_INTERNAL;
> -
> - return info->status & PCI_ERR_UNC_INTN;
> -}
> -
> static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data)
> {
> struct aer_err_info *info = (struct aer_err_info *)data;
> @@ -1033,14 +1032,23 @@ static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data)
>
> static void cxl_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))
> + if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC)
> pcie_walk_rcec(dev, cxl_rch_handle_error_iter, info);
> +
> + if (info->severity == AER_CORRECTABLE) {
> + struct pci_driver *pdrv = dev->driver;
> + int aer = dev->aer_cap;
> +
> + if (aer)
> + pci_write_config_dword(dev, aer + PCI_ERR_COR_STATUS,
> + info->status);
> +
> + if (pdrv && pdrv->cxl_err_handler &&
> + pdrv->cxl_err_handler->cor_error_detected)
> + pdrv->cxl_err_handler->cor_error_detected(dev);
> +
> + pcie_clear_device_status(dev);
> + }
> }
>
> static int handles_cxl_error_iter(struct pci_dev *dev, void *data)
> @@ -1058,9 +1066,13 @@ static bool handles_cxl_errors(struct pci_dev *dev)
> {
> bool handles_cxl = false;
>
> - if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC &&
> - pcie_aer_is_native(dev))
> + 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_port(dev);
>
> return handles_cxl;
> }
> @@ -1078,6 +1090,10 @@ static void cxl_enable_internal_errors(struct pci_dev *dev)
> static inline void cxl_enable_internal_errors(struct pci_dev *dev) { }
> static inline void cxl_handle_error(struct pci_dev *dev,
> struct aer_err_info *info) { }
> +static bool handles_cxl_errors(struct pci_dev *dev)
> +{
> + return false;
> +}
> #endif
>
> /**
> @@ -1115,8 +1131,11 @@ 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_handle_error(dev, info);
> - pci_aer_handle_error(dev, info);
> + if (is_internal_error(info) && handles_cxl_errors(dev))
> + cxl_handle_error(dev, info);
> + else
> + pci_aer_handle_error(dev, info);
> +
> pci_dev_put(dev);
> }
>
Powered by blists - more mailing lists