Linux PCI subsystem development
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: Terry Bowman <terry.bowman@amd.com>, <dave@stgolabs.net>,
	<jonathan.cameron@huawei.com>, <dave.jiang@intel.com>,
	<alison.schofield@intel.com>, <dan.j.williams@intel.com>,
	<bhelgaas@google.com>, <shiju.jose@huawei.com>,
	<ming.li@zohomail.com>, <Smita.KoralahalliChannabasappa@amd.com>,
	<rrichter@amd.com>, <dan.carpenter@linaro.org>,
	<PradeepVineshReddy.Kodamati@amd.com>, <lukas@wunner.de>,
	<Benjamin.Cheatham@amd.com>,
	<sathyanarayanan.kuppuswamy@linux.intel.com>,
	<linux-cxl@vger.kernel.org>, <vishal.l.verma@intel.com>,
	<alucerop@amd.com>, <ira.weiny@intel.com>
Cc: <linux-kernel@vger.kernel.org>, <linux-pci@vger.kernel.org>,
	<terry.bowman@amd.com>
Subject: Re: [PATCH v16 10/10] cxl: Enable CXL protocol error reporting
Date: Sun, 29 Mar 2026 18:41:12 -0700	[thread overview]
Message-ID: <69c9d4b8e08f1_17890410047@dwillia2-mobl4.notmuch> (raw)
In-Reply-To: <20260302203648.2886956-11-terry.bowman@amd.com>

Terry Bowman wrote:
> CXL protocol errors are not enabled for all CXL devices after boot. These
> must be enabled inorder to process CXL protocol errors.
> 
> Introduce cxl_unmask_proto_interrupts() to call pci_aer_unmask_internal_errors().
> pci_aer_unmask_internal_errors() expects the pdev->aer_cap is initialized.
> But, dev->aer_cap is not initialized for CXL Upstream Switch Ports and CXL
> Downstream Switch Ports. Initialize the dev->aer_cap if necessary. Enable AER
> correctable internal errors and uncorrectable internal errors for all CXL
> devices.
> 
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
> Reviewed-by: Dave Jiang <dave.jiang@intel.com>
> Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com>
> 
> ---
>  drivers/cxl/core/port.c |  2 ++
>  drivers/cxl/core/ras.c  | 22 ++++++++++++++++++++++
>  drivers/cxl/cxlpci.h    |  4 ++++
>  3 files changed, 28 insertions(+)
> 
> diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
> index 27271402915f..c33d58fb7264 100644
> --- a/drivers/cxl/core/port.c
> +++ b/drivers/cxl/core/port.c
> @@ -1852,6 +1852,8 @@ int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd)
>  
>  			rc = cxl_add_ep(dport, &cxlmd->dev);
>  
> +			cxl_unmask_proto_interrupts(cxlmd->cxlds->dev);
> +

Why here? devm_cxl_port_ras_setup() will just redo it, right?

>  			/*
>  			 * If the endpoint already exists in the port's list,
>  			 * that's ok, it was added on a previous pass.
> diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
> index d6112b812c82..bfe6cb35154e 100644
> --- a/drivers/cxl/core/ras.c
> +++ b/drivers/cxl/core/ras.c
> @@ -119,6 +119,24 @@ 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);
>  
> +void cxl_unmask_proto_interrupts(struct device *dev)
> +{
> +	if (!dev || !dev_is_pci(dev))
> +		return;
> +
> +	struct pci_dev *pdev __free(pci_dev_put) = pci_dev_get(to_pci_dev(dev));

Why does this need to hold a reference for a simple to_pci_dev() conversion?

> +
> +	if (!pdev->aer_cap) {
> +		pdev->aer_cap = pci_find_ext_capability(pdev,
> +							PCI_EXT_CAP_ID_ERR);
> +		if (!pdev->aer_cap)
> +			return;
> +	}
> +
> +	pci_aer_unmask_internal_errors(pdev);
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_unmask_proto_interrupts, "CXL");

Why export? The only callers are internal to cxl_core.ko?

---
 drivers/cxl/cxlpci.h    | 4 ----
 drivers/cxl/core/port.c | 2 --
 drivers/cxl/core/ras.c  | 3 +--
 3 files changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index b7cf9d6137b3..184a95e96ea9 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -82,7 +82,6 @@ void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport);
 pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
 					pci_channel_state_t error);
 void devm_cxl_port_ras_setup(struct cxl_port *port);
-void cxl_unmask_proto_interrupts(struct device *dev);
 #else
 static inline pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
 						      pci_channel_state_t state)
@@ -97,9 +96,6 @@ static inline void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport)
 static inline void devm_cxl_port_ras_setup(struct cxl_port *port)
 {
 }
-static inline void cxl_unmask_proto_interrupts(struct device *dev)
-{
-}
 #endif
 
 #endif /* __CXL_PCI_H__ */
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index c33d58fb7264..27271402915f 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1852,8 +1852,6 @@ int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd)
 
 			rc = cxl_add_ep(dport, &cxlmd->dev);
 
-			cxl_unmask_proto_interrupts(cxlmd->cxlds->dev);
-
 			/*
 			 * If the endpoint already exists in the port's list,
 			 * that's ok, it was added on a previous pass.
diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index bfe6cb35154e..1f688110f0f4 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -119,7 +119,7 @@ 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);
 
-void cxl_unmask_proto_interrupts(struct device *dev)
+static void cxl_unmask_proto_interrupts(struct device *dev)
 {
 	if (!dev || !dev_is_pci(dev))
 		return;
@@ -135,7 +135,6 @@ void cxl_unmask_proto_interrupts(struct device *dev)
 
 	pci_aer_unmask_internal_errors(pdev);
 }
-EXPORT_SYMBOL_NS_GPL(cxl_unmask_proto_interrupts, "CXL");
 
 static void cxl_dport_map_ras(struct cxl_dport *dport)
 {
-- 
2.53.0

  reply	other threads:[~2026-03-30  1:41 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-02 20:36 [PATCH v16 00/10] Enable CXL PCIe Port Protocol Error handling and logging Terry Bowman
2026-03-02 20:36 ` [PATCH v16 01/10] PCI/AER: Introduce AER-CXL Kfifo Terry Bowman
2026-03-09 12:20   ` Jonathan Cameron
2026-03-28  0:28   ` Dan Williams
2026-03-29 20:33     ` Dan Williams
2026-03-30 15:33       ` Bowman, Terry
2026-03-30 15:15     ` Bowman, Terry
2026-03-02 20:36 ` [PATCH v16 02/10] PCI/CXL: Update unregistration for AER-CXL and CPER-CXL kfifos Terry Bowman
2026-03-09 12:27   ` Jonathan Cameron
2026-03-11 15:03     ` Bowman, Terry
2026-03-09 18:30   ` Dave Jiang
2026-03-29 21:27   ` Dan Williams
2026-03-02 20:36 ` [PATCH v16 03/10] cxl: Update CXL Endpoint tracing Terry Bowman
2026-03-29 21:44   ` Dan Williams
2026-03-02 20:36 ` [PATCH v16 04/10] PCI/ERR: Introduce PCI_ERS_RESULT_PANIC Terry Bowman
2026-03-29 21:57   ` Dan Williams
2026-03-30 16:40     ` Bowman, Terry
2026-03-02 20:36 ` [PATCH v16 05/10] PCI: Establish common CXL Port protocol error flow Terry Bowman
2026-03-09 12:45   ` [PATCH v16 05/10] PCI: Establish common CXL Port protocol error flowUIRE Jonathan Cameron
2026-03-30  0:08   ` [PATCH v16 05/10] PCI: Establish common CXL Port protocol error flow Dan Williams
2026-03-02 20:36 ` [PATCH v16 06/10] PCI/CXL: Add RCH support to CXL handlers Terry Bowman
2026-03-09 14:00   ` Jonathan Cameron
2026-03-11 15:21     ` Bowman, Terry
2026-03-30  0:31   ` Dan Williams
2026-03-30 17:02     ` Bowman, Terry
2026-03-02 20:36 ` [PATCH v16 07/10] cxl: Update error handlers to support CXL Port devices Terry Bowman
2026-03-09 14:05   ` Jonathan Cameron
2026-03-11 15:37     ` Bowman, Terry
2026-03-12 13:05       ` Jonathan Cameron
2026-03-30  1:07   ` Dan Williams
2026-03-30 16:31     ` Bowman, Terry
2026-03-31  2:11       ` Dan Williams
2026-03-02 20:36 ` [PATCH v16 08/10] cxl: Update Endpoint AER uncorrectable handler Terry Bowman
2026-03-09 14:12   ` Jonathan Cameron
2026-03-11 15:58     ` Bowman, Terry
2026-03-30  1:22   ` Dan Williams
2026-03-31 18:52     ` Bowman, Terry
2026-03-31 19:23       ` Dan Williams
2026-03-31 19:52         ` Bowman, Terry
2026-04-02  3:39           ` Dan Williams
2026-03-02 20:36 ` [PATCH v16 09/10] cxl: Remove Endpoint AER correctable handler Terry Bowman
2026-03-09 14:13   ` Jonathan Cameron
2026-03-09 18:55   ` Dave Jiang
2026-03-30  1:24   ` Dan Williams
2026-03-02 20:36 ` [PATCH v16 10/10] cxl: Enable CXL protocol error reporting Terry Bowman
2026-03-30  1:41   ` Dan Williams [this message]
2026-03-31 13:31     ` Bowman, Terry
2026-03-31 19:16       ` Dan Williams
2026-03-31 20:50         ` Bowman, Terry
2026-03-31 21:12         ` Bowman, Terry

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=69c9d4b8e08f1_17890410047@dwillia2-mobl4.notmuch \
    --to=dan.j.williams@intel.com \
    --cc=Benjamin.Cheatham@amd.com \
    --cc=PradeepVineshReddy.Kodamati@amd.com \
    --cc=Smita.KoralahalliChannabasappa@amd.com \
    --cc=alison.schofield@intel.com \
    --cc=alucerop@amd.com \
    --cc=bhelgaas@google.com \
    --cc=dan.carpenter@linaro.org \
    --cc=dave.jiang@intel.com \
    --cc=dave@stgolabs.net \
    --cc=ira.weiny@intel.com \
    --cc=jonathan.cameron@huawei.com \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=lukas@wunner.de \
    --cc=ming.li@zohomail.com \
    --cc=rrichter@amd.com \
    --cc=sathyanarayanan.kuppuswamy@linux.intel.com \
    --cc=shiju.jose@huawei.com \
    --cc=terry.bowman@amd.com \
    --cc=vishal.l.verma@intel.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