mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Terry Bowman <terry.bowman@amd.com>
To: <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>,
	<terry.bowman@amd.com>, <linux-cxl@vger.kernel.org>
Cc: <linux-kernel@vger.kernel.org>, <linux-pci@vger.kernel.org>
Subject: [PATCH v10 17/17] CXL/PCI: Disable CXL protocol error interrupts during CXL Port cleanup
Date: Thu, 26 Jun 2025 17:42:52 -0500	[thread overview]
Message-ID: <20250626224252.1415009-18-terry.bowman@amd.com> (raw)
In-Reply-To: <20250626224252.1415009-1-terry.bowman@amd.com>

During CXL device cleanup the CXL PCIe Port device interrupts remain
enabled. This potentially allows unnecessary interrupt processing on
behalf of the CXL errors while the device is destroyed.

Disable CXL protocol errors by setting the CXL devices' AER mask register.

Introduce pci_aer_mask_internal_errors() similar to pci_aer_unmask_internal_errors().

Introduce cxl_mask_proto_interrupts() to call pci_aer_mask_internal_errors().
Add calls to cxl_mask_proto_interrupts() within CXL Port teardown for CXL
Root Ports, CXL Downstream Switch Ports, CXL Upstream Switch Ports, and CXL
Endpoints. Follow the same "bottom-up" approach used during CXL Port
teardown.

Implement cxl_mask_proto_interrupts() in a header file to avoid introducing
Kconfig ifdefs in cxl/core/port.c.

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
---
 drivers/cxl/core/native_ras.c |  9 +++++++++
 drivers/cxl/core/port.c       |  6 ++++++
 drivers/cxl/cxl.h             |  3 +++
 drivers/pci/pcie/cxl_aer.c    | 21 +++++++++++++++++++++
 include/linux/aer.h           |  1 +
 5 files changed, 40 insertions(+)

diff --git a/drivers/cxl/core/native_ras.c b/drivers/cxl/core/native_ras.c
index c7f9a237a1a2..8b8c7b3fba6c 100644
--- a/drivers/cxl/core/native_ras.c
+++ b/drivers/cxl/core/native_ras.c
@@ -9,6 +9,15 @@
 #include <cxlpci.h>
 #include <core/core.h>
 
+void cxl_mask_proto_interrupts(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	guard(device)(dev);
+
+	pci_aer_mask_internal_errors(pdev);
+}
+
 int match_uport(struct device *dev, const void *data)
 {
 	const struct device *uport_dev = data;
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index c76a1289e24e..786a036d33cc 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1433,6 +1433,9 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, "CXL");
  */
 static void delete_switch_port(struct cxl_port *port)
 {
+	cxl_mask_proto_interrupts(port->uport_dev);
+	cxl_mask_proto_interrupts(port->parent_dport->dport_dev);
+
 	devm_release_action(port->dev.parent, cxl_unlink_parent_dport, port);
 	devm_release_action(port->dev.parent, cxl_unlink_uport, port);
 	devm_release_action(port->dev.parent, unregister_port, port);
@@ -1446,6 +1449,7 @@ static void reap_dports(struct cxl_port *port)
 	device_lock_assert(&port->dev);
 
 	xa_for_each(&port->dports, index, dport) {
+		cxl_mask_proto_interrupts(dport->dport_dev);
 		devm_release_action(&port->dev, cxl_dport_unlink, dport);
 		devm_release_action(&port->dev, cxl_dport_remove, dport);
 		devm_kfree(&port->dev, dport);
@@ -1476,6 +1480,8 @@ static void cxl_detach_ep(void *data)
 {
 	struct cxl_memdev *cxlmd = data;
 
+	cxl_mask_proto_interrupts(cxlmd->cxlds->dev);
+
 	for (int i = cxlmd->depth - 1; i >= 1; i--) {
 		struct cxl_port *port, *parent_port;
 		struct detach_ctx ctx = {
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 19eb33a7de6a..95843428be92 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -12,6 +12,7 @@
 #include <linux/node.h>
 #include <linux/io.h>
 #include <linux/pci.h>
+#include <linux/aer.h>
 
 extern const struct nvdimm_security_ops *cxl_security_ops;
 
@@ -771,9 +772,11 @@ 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_mask_proto_interrupts(struct device *dev);
 #else
 static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
 						struct device *host) { }
+static inline void cxl_mask_proto_interrupts(struct device *dev) { }
 #endif
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
diff --git a/drivers/pci/pcie/cxl_aer.c b/drivers/pci/pcie/cxl_aer.c
index 3c5bf162607c..bd6660eab87b 100644
--- a/drivers/pci/pcie/cxl_aer.c
+++ b/drivers/pci/pcie/cxl_aer.c
@@ -33,6 +33,27 @@ void pci_aer_unmask_internal_errors(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_NS_GPL(pci_aer_unmask_internal_errors, "CXL");
 
+/**
+ * pci_aer_mask_internal_errors - mask internal errors
+ * @dev: pointer to the pcie_dev data structure
+ *
+ * Masks internal errors in the Uncorrectable and Correctable Error
+ * Mask registers.
+ *
+ * Note: AER must be enabled and supported by the device which must be
+ * checked in advance, e.g. with pcie_aer_is_native().
+ */
+void pci_aer_mask_internal_errors(struct pci_dev *dev)
+{
+	int aer = dev->aer_cap;
+
+	pci_clear_and_set_config_dword(dev, aer + PCI_ERR_UNCOR_MASK,
+				       0, PCI_ERR_UNC_INTN);
+	pci_clear_and_set_config_dword(dev, aer + PCI_ERR_COR_MASK,
+				       0, PCI_ERR_COR_INTERNAL);
+}
+EXPORT_SYMBOL_NS_GPL(pci_aer_mask_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 8fb1eca97c37..c0fd627328ae 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -114,5 +114,6 @@ 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);
+void pci_aer_mask_internal_errors(struct pci_dev *dev);
 #endif //_AER_H_
 
-- 
2.34.1


  parent reply	other threads:[~2025-06-26 22:46 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-26 22:42 [PATCH v10 00/17] Enable CXL PCIe Port Protocol Error handling and logging Terry Bowman
2025-06-26 22:42 ` [PATCH v10 01/17] cxl/pci: Remove unnecessary CXL Endpoint handling helper functions Terry Bowman
2025-07-18 17:55   ` Dave Jiang
2025-07-23 21:58   ` dan.j.williams
2025-07-23 22:15     ` Dave Jiang
2025-06-26 22:42 ` [PATCH v10 02/17] PCI/CXL: Add pcie_is_cxl() Terry Bowman
2025-07-23 22:30   ` dan.j.williams
2025-08-09 10:56   ` Alejandro Lucero Palau
2025-08-11 19:14     ` Bowman, Terry
2025-08-11 23:14       ` dan.j.williams
2025-06-26 22:42 ` [PATCH v10 03/17] PCI/AER: Report CXL or PCIe bus error type in trace logging Terry Bowman
2025-06-26 23:25   ` Sathyanarayanan Kuppuswamy
2025-06-27  9:53   ` Jonathan Cameron
2025-07-02 16:00     ` Bowman, Terry
2025-06-27 11:32   ` Shiju Jose
2025-07-01 21:27   ` Dave Jiang
2025-07-23 22:56   ` dan.j.williams
2025-06-26 22:42 ` [PATCH v10 04/17] CXL/AER: Introduce CXL specific AER driver file Terry Bowman
2025-06-26 23:42   ` Sathyanarayanan Kuppuswamy
2025-06-27 10:12     ` Jonathan Cameron
2025-06-27 14:29     ` Bowman, Terry
2025-07-24  0:01   ` dan.j.williams
2025-07-24 17:06     ` Bowman, Terry
2025-07-24 20:32       ` dan.j.williams
2025-07-24  1:16   ` dan.j.williams
2025-07-24 17:02     ` Bowman, Terry
2025-07-24 20:23       ` dan.j.williams
2025-06-26 22:42 ` [PATCH v10 05/17] CXL/AER: Introduce kfifo for forwarding CXL errors Terry Bowman
2025-06-27 10:24   ` Jonathan Cameron
2025-07-02 16:21     ` Bowman, Terry
2025-07-02 19:54       ` Dan Carpenter
2025-07-02 19:57         ` Bowman, Terry
2025-07-03 10:06       ` Jonathan Cameron
2025-07-01 21:53   ` Dave Jiang
2025-07-02 17:10     ` Bowman, Terry
2025-07-24  2:01   ` dan.j.williams
2025-07-24 17:21     ` Bowman, Terry
2025-07-24 20:55       ` dan.j.williams
2025-06-26 22:42 ` [PATCH v10 06/17] PCI/AER: Dequeue forwarded CXL error Terry Bowman
2025-06-27 11:00   ` Jonathan Cameron
2025-07-02 17:51     ` Bowman, Terry
2025-07-01 23:04   ` Dave Jiang
2025-07-02 17:56     ` Bowman, Terry
2025-07-03 10:11       ` Jonathan Cameron
2025-07-25  0:38   ` dan.j.williams
2025-06-26 22:42 ` [PATCH v10 07/17] CXL/PCI: Introduce CXL uncorrectable protocol error recovery Terry Bowman
2025-06-27 11:05   ` Jonathan Cameron
2025-07-02 21:06     ` Bowman, Terry
2025-06-27 12:27   ` Shiju Jose
2025-07-02 21:34     ` Bowman, Terry
2025-06-26 22:42 ` [PATCH v10 08/17] cxl/pci: Move RAS initialization to cxl_port driver Terry Bowman
2025-06-27 11:12   ` Jonathan Cameron
2025-07-18 18:01   ` Dave Jiang
2025-06-26 22:42 ` [PATCH v10 09/17] cxl/pci: Map CXL Endpoint Port and CXL Switch Port RAS registers Terry Bowman
2025-06-27 11:17   ` Jonathan Cameron
2025-07-02 21:41     ` Bowman, Terry
2025-07-18 21:28   ` Dave Jiang
2025-07-18 21:55     ` Bowman, Terry
2025-07-18 22:01       ` Dave Jiang
2025-07-18 22:40         ` Bowman, Terry
2025-07-18 22:45           ` Dave Jiang
2025-06-26 22:42 ` [PATCH v10 10/17] cxl/pci: Update RAS handler interfaces to also support CXL Ports Terry Bowman
2025-06-26 22:42 ` [PATCH v10 11/17] cxl/pci: Log message if RAS registers are unmapped Terry Bowman
2025-07-21 21:56   ` Dave Jiang
2025-06-26 22:42 ` [PATCH v10 12/17] cxl/pci: Unify CXL trace logging for CXL Endpoints and CXL Ports Terry Bowman
2025-06-27 12:22   ` Shiju Jose
2025-07-02  1:18     ` Alison Schofield
2025-07-02 22:07       ` Bowman, Terry
2025-07-02 21:56     ` Bowman, Terry
2025-06-26 22:42 ` [PATCH v10 13/17] cxl/pci: Update cxl_handle_cor_ras() to return early if no RAS errors Terry Bowman
2025-06-27 11:48   ` Jonathan Cameron
2025-07-21 22:17   ` Dave Jiang
2025-06-26 22:42 ` [PATCH v10 14/17] cxl/pci: Introduce CXL Endpoint protocol error handlers Terry Bowman
2025-06-27 11:52   ` Jonathan Cameron
2025-06-27 12:27   ` Shiju Jose
2025-07-21 22:35   ` Dave Jiang
2025-07-22 18:23     ` Bowman, Terry
2025-06-26 22:42 ` [PATCH v10 15/17] CXL/PCI: Introduce CXL Port " Terry Bowman
2025-06-26 22:42 ` [PATCH v10 16/17] CXL/PCI: Enable CXL protocol errors during CXL Port probe Terry Bowman
2025-06-26 22:42 ` Terry Bowman [this message]
2025-07-23 21:55 ` [PATCH v10 00/17] Enable CXL PCIe Port Protocol Error handling and logging dan.j.williams
2025-08-18 15:18 ` Joshua Hahn

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=20250626224252.1415009-18-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.carpenter@linaro.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=dave@stgolabs.net \
    --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 \
    /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®