mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Terry Bowman <terry.bowman@amd.com>
To: <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>, <terry.bowman@amd.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: [PATCH v9 15/16] CXL/PCI: Enable CXL protocol errors during CXL Port probe
Date: Tue, 3 Jun 2025 12:22:38 -0500	[thread overview]
Message-ID: <20250603172239.159260-16-terry.bowman@amd.com> (raw)
In-Reply-To: <20250603172239.159260-1-terry.bowman@amd.com>

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

Export the AER service driver's pci_aer_unmask_internal_errors().

Introduce cxl_unmask_prot_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>
---
 drivers/cxl/port.c     | 29 +++++++++++++++++++++++++++--
 drivers/pci/pcie/aer.c |  3 ++-
 include/linux/aer.h    |  1 +
 3 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 0f7c4010ba58..3687848ae772 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -3,6 +3,7 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/pci.h>
 
 #include "cxlmem.h"
 #include "cxlpci.h"
@@ -60,6 +61,21 @@ static int discover_region(struct device *dev, void *unused)
 
 #ifdef CONFIG_PCIEAER_CXL
 
+static void cxl_unmask_prot_interrupts(struct device *dev)
+{
+	struct pci_dev *pdev __free(pci_dev_put) =
+		pci_dev_get(to_pci_dev(dev));
+
+	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);
+}
+
 static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 {
 	resource_size_t aer_phys;
@@ -118,8 +134,12 @@ static void cxl_uport_init_ras_reporting(struct cxl_port *port,
 
 	map->host = host;
 	if (cxl_map_component_regs(map, &port->uport_regs,
-				   BIT(CXL_CM_CAP_CAP_ID_RAS)))
+				   BIT(CXL_CM_CAP_CAP_ID_RAS))) {
 		dev_dbg(&port->dev, "Failed to map RAS capability\n");
+		return;
+	}
+
+	cxl_unmask_prot_interrupts(port->uport_dev);
 }
 
 /**
@@ -144,9 +164,12 @@ void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
 	}
 
 	if (cxl_map_component_regs(&dport->reg_map, &dport->regs.component,
-				   BIT(CXL_CM_CAP_CAP_ID_RAS)))
+				   BIT(CXL_CM_CAP_CAP_ID_RAS))) {
 		dev_dbg(dport->dport_dev, "Failed to map RAS capability\n");
+		return;
+	}
 
+	cxl_unmask_prot_interrupts(dport->dport_dev);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
 
@@ -177,6 +200,8 @@ static void cxl_endpoint_port_init_ras(struct cxl_port *port)
 	}
 
 	cxl_dport_init_ras_reporting(dport, &cxlmd->dev);
+
+	cxl_unmask_prot_interrupts(cxlmd->cxlds->dev);
 }
 
 #else
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 5efe5a718960..2d202ad1453a 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -964,7 +964,7 @@ 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;
@@ -977,6 +977,7 @@ 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 c9a18eca16f8..74600e75705f 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -107,5 +107,6 @@ 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:[~2025-06-03 17:25 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
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 ` Terry Bowman [this message]
2025-06-06  0:51   ` [PATCH v9 15/16] CXL/PCI: Enable CXL protocol errors during CXL Port probe 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=20250603172239.159260-16-terry.bowman@amd.com \
    --to=terry.bowman@amd.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=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

all inboxes | Powered by JetHome®