Linux CXL
 help / color / mirror / Atom feed
From: Srirangan Madhavan <smadhavan@nvidia.com>
To: Alison Schofield <alison.schofield@intel.com>,
	Bjorn Helgaas <bhelgaas@google.com>,
	Dan Williams <djbw@kernel.org>, Dave Jiang <dave.jiang@intel.com>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Ira Weiny <ira.weiny@intel.com>,
	Jonathan Cameron <jic23@kernel.org>,
	Vishal Verma <vishal.l.verma@intel.com>,
	linux-cxl@vger.kernel.org, linux-pci@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: Alex Williamson <alex.williamson@redhat.com>,
	vsethi@nvidia.com, alwilliamson@nvidia.com,
	Sai Yashwanth Reddy Kancherla <skancherla@nvidia.com>,
	Vishal Aslot <vaslot@nvidia.com>,
	Manish Honap <mhonap@nvidia.com>, Jiandi An <jan@nvidia.com>,
	Richard Cheng <icheng@nvidia.com>,
	linux-tegra@vger.kernel.org,
	Srirangan Madhavan <smadhavan@nvidia.com>
Subject: [PATCH v11 12/12] PCI/CXL: Restore HDM state after CXL bus reset
Date: Wed,  2 Sep 2026 07:28:04 +0000	[thread overview]
Message-ID: <20260902072804.665639-13-smadhavan@nvidia.com> (raw)
In-Reply-To: <20260902072804.665639-1-smadhavan@nvidia.com>

CXL bus reset can clear HDM global control and decoder programming.
Restore cached HDM state after a successful cxl_bus reset while the
IOMMU reset block remains active.

Restore PCI config state first so BARs are valid before HDM MMIO access.
If HDM restore fails, save a disabled PCI command state so later PCI
restore does not reopen bus mastering over invalid decoder state.

Reject cxl_bus reset for multifunction devices, matching cxl_reset.

This restores only HDM component decoder state. It does not restore CXL
Device DVSEC range/control registers.

Reported-by: Alex Williamson <alex.williamson@redhat.com>
Tested-by: Richard Cheng <icheng@nvidia.com>
Signed-off-by: Srirangan Madhavan <smadhavan@nvidia.com>
---
 drivers/cxl/core/resource.c | 18 ++++++++++++++++++
 drivers/pci/pci.c           |  6 ++++++
 include/cxl/cxl.h           |  6 ++++++
 3 files changed, 30 insertions(+)

diff --git a/drivers/cxl/core/resource.c b/drivers/cxl/core/resource.c
index fe330b825c0b..92d56d8baeb9 100644
--- a/drivers/cxl/core/resource.c
+++ b/drivers/cxl/core/resource.c
@@ -850,6 +850,24 @@ static int cxl_pci_target_reset_prepare(struct pci_dev *pdev,
 	return 0;
 }
 
+int cxl_restore_hdm_after_pci_reset(struct pci_dev *pdev)
+{
+	u16 command;
+	int rc;
+
+	device_lock_assert(&pdev->dev);
+	guard(rwsem_write)(&cxl_rwsem.region);
+
+	cxl_restore_pci_state_for_hdm_restore(pdev, &command);
+	rc = cxl_restore_hdm(pdev);
+	if (rc) {
+		cxl_reset_save_disabled_state(pdev);
+		return rc;
+	}
+
+	return cxl_reset_save_restored_state(pdev, command);
+}
+
 static void cxl_hdm_range_context_init(struct cxl_hdm_range_context *ctx)
 {
 	INIT_LIST_HEAD(&ctx->ranges);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 157f06c576e9..0a3ffdc70466 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5027,6 +5027,9 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
 	if (!dvsec)
 		return -ENOTTY;
 
+	if (dev->multifunction)
+		return -ENOTTY;
+
 	if (probe)
 		return 0;
 
@@ -5054,6 +5057,9 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
 		pci_write_config_word(bridge, dvsec + PCI_DVSEC_CXL_PORT_CTL,
 				      reg);
 
+	if (!rc)
+		rc = cxl_restore_hdm_after_pci_reset(dev);
+
 	pci_dev_reset_iommu_done(dev);
 	return rc;
 }
diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
index d07afb789d63..c8b12f50f71c 100644
--- a/include/cxl/cxl.h
+++ b/include/cxl/cxl.h
@@ -162,6 +162,7 @@ struct cxl_hdm_info {
 #ifdef CONFIG_CXL_RESET
 void pci_cxl_hdm_init(struct pci_dev *pdev);
 void pci_cxl_hdm_release(struct pci_dev *pdev);
+int cxl_restore_hdm_after_pci_reset(struct pci_dev *pdev);
 int cxl_reset_function(struct pci_dev *pdev, bool probe);
 #else
 static inline void pci_cxl_hdm_init(struct pci_dev *pdev)
@@ -172,6 +173,11 @@ static inline void pci_cxl_hdm_release(struct pci_dev *pdev)
 {
 }
 
+static inline int cxl_restore_hdm_after_pci_reset(struct pci_dev *pdev)
+{
+	return 0;
+}
+
 static inline int cxl_reset_function(struct pci_dev *pdev, bool probe)
 {
 	return -ENOTTY;
-- 
2.43.0


  parent reply	other threads:[~2026-09-02  7:28 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-02  7:27 [PATCH v11 00/12] PCI/CXL: Add CXL reset support for Type 2 devices Srirangan Madhavan
2026-09-02  7:27 ` [PATCH v11 01/12] cxl: Move HDM decoder programming helpers Srirangan Madhavan
2026-09-02  8:00   ` sashiko-bot
2026-09-02  7:27 ` [PATCH v11 02/12] cxl: Make HDM commit helpers available to reset code Srirangan Madhavan
2026-09-02  7:37   ` sashiko-bot
2026-09-02  7:27 ` [PATCH v11 03/12] cxl: Share HDM decoder decode logic Srirangan Madhavan
2026-09-02  7:39   ` sashiko-bot
2026-09-02  7:27 ` [PATCH v11 04/12] cxl: Cache decoder settings on PCI devices Srirangan Madhavan
2026-09-02  7:40   ` sashiko-bot
2026-09-02  7:27 ` [PATCH v11 05/12] cxl: Cache endpoint decoder settings during PCI enumeration Srirangan Madhavan
2026-09-02  7:41   ` sashiko-bot
2026-09-02 14:03   ` Li Ming
2026-09-02  7:27 ` [PATCH v11 06/12] cxl: Add CXL Device Reset helper Srirangan Madhavan
2026-09-02  7:35   ` sashiko-bot
2026-09-02  7:27 ` [PATCH v11 07/12] cxl: Validate HDM ranges before CXL reset Srirangan Madhavan
2026-09-02  7:42   ` sashiko-bot
2026-09-04  9:19   ` Richard Cheng
2026-09-02  7:28 ` [PATCH v11 08/12] PCI/CXL: Reject CXL Reset on multifunction devices Srirangan Madhavan
2026-09-02  7:39   ` sashiko-bot
2026-09-04  9:26   ` Richard Cheng
2026-09-02  7:28 ` [PATCH v11 09/12] cxl: Restore CXL HDM state after PCI reset Srirangan Madhavan
2026-09-02  7:45   ` sashiko-bot
2026-09-04  9:23   ` Richard Cheng
2026-09-02  7:28 ` [PATCH v11 10/12] PCI/CXL: Expose CXL Reset as a PCI reset method Srirangan Madhavan
2026-09-02  7:51   ` sashiko-bot
2026-09-02  7:28 ` [PATCH v11 11/12] Documentation/ABI: Document CXL Reset " Srirangan Madhavan
2026-09-02  7:40   ` sashiko-bot
2026-09-02  7:28 ` Srirangan Madhavan [this message]
2026-09-02  7:54   ` [PATCH v11 12/12] PCI/CXL: Restore HDM state after CXL bus reset sashiko-bot
2026-09-04  9:15 ` [PATCH v11 00/12] PCI/CXL: Add CXL reset support for Type 2 devices Richard Cheng

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=20260902072804.665639-13-smadhavan@nvidia.com \
    --to=smadhavan@nvidia.com \
    --cc=alex.williamson@redhat.com \
    --cc=alison.schofield@intel.com \
    --cc=alwilliamson@nvidia.com \
    --cc=bhelgaas@google.com \
    --cc=dave.jiang@intel.com \
    --cc=dave@stgolabs.net \
    --cc=djbw@kernel.org \
    --cc=icheng@nvidia.com \
    --cc=ira.weiny@intel.com \
    --cc=jan@nvidia.com \
    --cc=jic23@kernel.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linux-tegra@vger.kernel.org \
    --cc=mhonap@nvidia.com \
    --cc=skancherla@nvidia.com \
    --cc=vaslot@nvidia.com \
    --cc=vishal.l.verma@intel.com \
    --cc=vsethi@nvidia.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