Linux PCI subsystem development
 help / color / mirror / Atom feed
From: Terry Bowman <terry.bowman@amd.com>
To: <linux-cxl@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<linux-pci@vger.kernel.org>, <nifan.cxl@gmail.com>,
	<dave@stgolabs.net>, <jonathan.cameron@huawei.com>,
	<dave.jiang@intel.com>, <alison.schofield@intel.com>,
	<vishal.l.verma@intel.com>, <dan.j.williams@intel.com>,
	<bhelgaas@google.com>, <mahesh@linux.ibm.com>,
	<ira.weiny@intel.com>, <oohall@gmail.com>,
	<Benjamin.Cheatham@amd.com>, <rrichter@amd.com>,
	<nathan.fontenot@amd.com>, <terry.bowman@amd.com>,
	<Smita.KoralahalliChannabasappa@amd.com>, <lukas@wunner.de>,
	<ming.li@zohomail.com>, <PradeepVineshReddy.Kodamati@amd.com>
Subject: [PATCH v8 15/16] CXL/PCI: Enable CXL protocol errors during CXL Port probe
Date: Wed, 26 Mar 2025 20:47:16 -0500	[thread overview]
Message-ID: <20250327014717.2988633-16-terry.bowman@amd.com> (raw)
In-Reply-To: <20250327014717.2988633-1-terry.bowman@amd.com>

CXL protocol errors are not enabled for all CXL devices at boot. These
must be enabled inorder to process CXL protocol errors.

Export the AER service driver's pci_aer_unmask_internal_errors().

Introduce cxl_enable_port_errors() 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>
---
 drivers/cxl/cxl.h      |  2 ++
 drivers/cxl/port.c     | 22 ++++++++++++++++++++++
 drivers/pci/pcie/aer.c |  3 ++-
 include/linux/aer.h    |  1 +
 4 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index c1adf8a3cb9e..473267c19cd0 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -769,9 +769,11 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
 #ifdef CONFIG_PCIEAER_CXL
 void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport);
 void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host);
+void cxl_enable_prot_errors(struct device *dev);
 #else
 static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
 						struct device *host) { }
+static inline void cxl_enable_prot_errors(struct device *dev) { }
 #endif
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 8e2b70e73582..bb7a0526e609 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -83,6 +83,24 @@ static void cxl_assign_error_handlers(struct device *_dev,
 	pdrv->err_handler = handlers;
 }
 
+void cxl_enable_prot_errors(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct device *pci_dev __free(put_device) = get_device(&pdev->dev);
+
+	if (!pci_dev)
+		return;
+
+	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_enable_prot_errors, "CXL");
+
 static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 {
 	resource_size_t aer_phys;
@@ -147,6 +165,7 @@ static void cxl_uport_init_ras_reporting(struct cxl_port *port,
 	}
 
 	cxl_assign_error_handlers(&port->dev, &cxl_port_error_handlers);
+	cxl_enable_prot_errors(port->uport_dev);
 }
 
 /**
@@ -177,6 +196,7 @@ void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
 	}
 
 	cxl_assign_error_handlers(dport->dport_dev, &cxl_port_error_handlers);
+	cxl_enable_prot_errors(dport->dport_dev);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
 
@@ -201,6 +221,7 @@ static void cxl_endpoint_port_init_ras(struct cxl_port *port)
 	struct cxl_port *parent_port __free(put_cxl_port) =
 		cxl_mem_find_port(cxlmd, &dport);
 	struct device *cxlmd_dev __free(put_device) = &cxlmd->dev;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 
 	if (!dport || !dev_is_pci(dport->dport_dev)) {
 		dev_err(&port->dev, "CXL port topology not found\n");
@@ -210,6 +231,7 @@ static void cxl_endpoint_port_init_ras(struct cxl_port *port)
 	cxl_dport_init_ras_reporting(dport, cxlmd_dev);
 
 	cxl_assign_error_handlers(cxlmd_dev, &cxl_ep_error_handlers);
+	cxl_enable_prot_errors(cxlds->dev);
 }
 
 #else
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 763ec6aa1a9a..d3068f5cc767 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -962,7 +962,7 @@ static bool find_source_device(struct pci_dev *parent,
  * Note: AER must be enabled and supported by the device which must be
  * checked in advance, e.g. with pcie_aer_is_native().
  */
-static void pci_aer_unmask_internal_errors(struct pci_dev *dev)
+void pci_aer_unmask_internal_errors(struct pci_dev *dev)
 {
 	int aer = dev->aer_cap;
 	u32 mask;
@@ -975,6 +975,7 @@ static void pci_aer_unmask_internal_errors(struct pci_dev *dev)
 	mask &= ~PCI_ERR_COR_INTERNAL;
 	pci_write_config_dword(dev, aer + PCI_ERR_COR_MASK, mask);
 }
+EXPORT_SYMBOL_NS_GPL(pci_aer_unmask_internal_errors, "CXL");
 
 static bool is_cxl_mem_dev(struct pci_dev *dev)
 {
diff --git a/include/linux/aer.h b/include/linux/aer.h
index 8f815f34d447..a65fe324fad2 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -100,5 +100,6 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
 int cper_severity_to_aer(int cper_severity);
 void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 		       int severity, struct aer_capability_regs *aer_regs);
+void pci_aer_unmask_internal_errors(struct pci_dev *dev);
 #endif //_AER_H_
 
-- 
2.34.1


  parent reply	other threads:[~2025-03-27  1:50 UTC|newest]

Thread overview: 76+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-27  1:47 [PATCH v8 00/16] Enable CXL PCIe port protocol error handling and logging Terry Bowman
2025-03-27  1:47 ` [PATCH v8 01/16] PCI/CXL: Introduce PCIe helper function pcie_is_cxl() Terry Bowman
2025-03-27 15:11   ` Ira Weiny
2025-03-27 15:30     ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 02/16] PCI/AER: Modify AER driver logging to report CXL or PCIe bus error type Terry Bowman
2025-03-27 16:48   ` Bjorn Helgaas
2025-03-27 17:15     ` Bowman, Terry
2025-03-27 17:49       ` Bjorn Helgaas
2025-03-27 16:58   ` Ira Weiny
2025-03-27 17:17     ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 03/16] CXL/AER: Introduce Kfifo for forwarding CXL errors Terry Bowman
2025-03-27 17:08   ` Bjorn Helgaas
2025-03-27 18:12     ` Bowman, Terry
2025-03-28 17:02       ` Bjorn Helgaas
2025-03-28 17:36         ` Bowman, Terry
2025-03-28 17:01   ` Ira Weiny
2025-04-07 13:43     ` Bowman, Terry
2025-04-04 16:53   ` Jonathan Cameron
2025-04-23 14:33   ` Jonathan Cameron
2025-04-23 15:04   ` Jonathan Cameron
2025-04-23 22:12   ` Gregory Price
2025-03-27  1:47 ` [PATCH v8 04/16] cxl/aer: AER service driver forwards CXL error to CXL driver Terry Bowman
2025-03-27 17:13   ` Bjorn Helgaas
2025-04-07 14:00     ` Bowman, Terry
2025-04-23 15:04   ` Jonathan Cameron
2025-04-24 14:17     ` Bowman, Terry
2025-04-25 13:18       ` Jonathan Cameron
2025-04-25 21:03         ` Bowman, Terry
2025-05-15 21:52         ` Bowman, Terry
2025-05-20 11:04           ` Jonathan Cameron
2025-05-20 13:21             ` Bowman, Terry
2025-05-21 18:34               ` Jonathan Cameron
2025-05-21 23:30                 ` Bowman, Terry
2025-04-23 22:21   ` Gregory Price
2025-03-27  1:47 ` [PATCH v8 05/16] PCI/AER: CXL driver dequeues CXL error forwarded from AER service driver Terry Bowman
2025-03-27  4:43   ` kernel test robot
2025-04-23 16:28   ` Jonathan Cameron
2025-04-24 15:03     ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 06/16] CXL/PCI: Introduce CXL uncorrectable protocol error 'recovery' Terry Bowman
2025-03-27  3:37   ` kernel test robot
2025-03-27  4:19   ` kernel test robot
2025-04-23 16:35   ` Jonathan Cameron
2025-04-24 14:22     ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 07/16] cxl/pci: Move existing CXL RAS initialization to CXL's cxl_port driver Terry Bowman
2025-04-17 10:18   ` Jonathan Cameron
2025-04-24 14:25     ` Bowman, Terry
2025-05-12 14:47     ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 08/16] cxl/pci: Map CXL Endpoint Port and CXL Switch Port RAS registers Terry Bowman
2025-03-27  1:47 ` [PATCH v8 09/16] cxl/pci: Update RAS handler interfaces to also support CXL PCIe Ports Terry Bowman
2025-03-27  1:47 ` [PATCH v8 10/16] cxl/pci: Add log message if RAS registers are not mapped Terry Bowman
2025-04-23 16:41   ` Jonathan Cameron
2025-04-24 14:30     ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 11/16] cxl/pci: Unifi CXL trace logging for CXL Endpoints and CXL Ports Terry Bowman
2025-04-23 16:44   ` Jonathan Cameron
2025-05-07 16:28     ` Shiju Jose
2025-05-07 18:30       ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 12/16] cxl/pci: Assign CXL Port protocol error handlers Terry Bowman
2025-04-23 16:47   ` Jonathan Cameron
2025-03-27  1:47 ` [PATCH v8 13/16] cxl/pci: Assign CXL Endpoint " Terry Bowman
2025-03-27 19:46   ` kernel test robot
2025-04-23 16:49   ` Jonathan Cameron
2025-03-27  1:47 ` [PATCH v8 14/16] cxl/pci: Remove unnecessary CXL Endpoint handling helper functions Terry Bowman
2025-04-17 17:22   ` Jonathan Cameron
2025-03-27  1:47 ` Terry Bowman [this message]
2025-04-04 17:05   ` [PATCH v8 15/16] CXL/PCI: Enable CXL protocol errors during CXL Port probe Jonathan Cameron
2025-04-07 14:34     ` Bowman, Terry
2025-03-27  1:47 ` [PATCH v8 16/16] CXL/PCI: Disable CXL protocol errors during CXL Port cleanup Terry Bowman
2025-03-28  1:18   ` kernel test robot
2025-04-04 17:04   ` Jonathan Cameron
2025-04-07 14:25     ` Bowman, Terry
2025-04-17 10:13       ` Jonathan Cameron
2025-04-24 16:37         ` Bowman, Terry
2025-03-27 17:16 ` [PATCH v8 00/16] Enable CXL PCIe port protocol error handling and logging Bjorn Helgaas
2025-03-27 22:04   ` Bowman, Terry
2025-05-06 23:06 ` Gregory Price
2025-05-07 18:28   ` 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=20250327014717.2988633-16-terry.bowman@amd.com \
    --to=terry.bowman@amd.com \
    --cc=Benjamin.Cheatham@amd.com \
    --cc=PradeepVineshReddy.Kodamati@amd.com \
    --cc=Smita.KoralahalliChannabasappa@amd.com \
    --cc=alison.schofield@intel.com \
    --cc=bhelgaas@google.com \
    --cc=dan.j.williams@intel.com \
    --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=mahesh@linux.ibm.com \
    --cc=ming.li@zohomail.com \
    --cc=nathan.fontenot@amd.com \
    --cc=nifan.cxl@gmail.com \
    --cc=oohall@gmail.com \
    --cc=rrichter@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