mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Daniel Viaño" <danividanivi@gmail.com>
To: Tony Nguyen <anthony.l.nguyen@intel.com>,
	Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: intel-wired-lan@lists.osuosl.org, netdev@vger.kernel.org,
	"Bjorn Helgaas" <bhelgaas@google.com>,
	linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
	"Daniel Viaño" <danividanivi@gmail.com>
Subject: [PATCH net] igc: Disable PCIe L1.2 substate on I225-LMvP and I226-LMvP devices
Date: Fri, 25 Sep 2026 13:28:50 +0200	[thread overview]
Message-ID: <20260925112850.189302-1-danividanivi@gmail.com> (raw)

Commit 0325143b59c6 ("igc: disable L1.2 PCI-E link substate to avoid
performance issue") disabled the L1.2 substate on I226 controllers due
to hardware exit latency limitations. However, IGC_DEV_ID_I226_LMVP
(0x5503) was omitted from igc_is_device_id_i226(), and IGC_DEV_ID_I225_LMVP
(0x5502) exhibits the same L1.2 exit latency constraints.

On systems where I225-LMvP is connected behind Thunderbolt/USB4 bridges
(such as the HP Thunderbolt Dock G4), negotiating L1.2 triggers severe
BadDLLP packet framing errors, link timeouts, and system hangs during
shutdown. An earlier attempt ("igc: Mask replay rollover/timeout errors
in I225_LMVP") proposed masking AER reporting. However, as Bjorn
Helgaas noted in review of that patch, simply masking errors is
undesirable and fixing the root cause is preferable; disabling L1.2
prevents the link from entering the unstable substate entirely.

Include IGC_DEV_ID_I226_LMVP in igc_is_device_id_i226() and disable the
L1.2 substate for I225-LMvP across probe, resume, and error recovery to
ensure link stability without masking AER errors.

Fixes: 0325143b59c6 ("igc: disable L1.2 PCI-E link substate to avoid performance issue")
Link: https://lore.kernel.org/lkml/eb5a9805-3e53-ec22-696e-21c6b8cf0bfc@molgen.mpg.de/T/
Signed-off-by: Daniel Viaño <danividanivi@gmail.com>
---
 drivers/net/ethernet/intel/igc/igc_base.c | 1 +
 drivers/net/ethernet/intel/igc/igc_main.c | 8 ++++----
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index ab9120a3127f..6865fef4049f 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -447,6 +447,7 @@ bool igc_is_device_id_i226(struct igc_hw *hw)
 	case IGC_DEV_ID_I226_V:
 	case IGC_DEV_ID_I226_K:
 	case IGC_DEV_ID_I226_IT:
+	case IGC_DEV_ID_I226_LMVP:
 		return true;
 	default:
 		return false;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 1fb5f3cbe93c..6c4e04661068 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -7172,8 +7172,8 @@ static int igc_probe(struct pci_dev *pdev,
 	hw->subsystem_vendor_id = pdev->subsystem_vendor;
 	hw->subsystem_device_id = pdev->subsystem_device;
 
-	/* Disable ASPM L1.2 on I226 devices to avoid packet loss */
-	if (igc_is_device_id_i226(hw))
+	/* Disable ASPM L1.2 on I226 and I225-LMvP devices to avoid packet loss */
+	if (igc_is_device_id_i226(hw) || hw->device_id == IGC_DEV_ID_I225_LMVP)
 		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
 
 	err = pci_save_state(pdev);
@@ -7559,7 +7559,7 @@ static int __igc_resume(struct device *dev, bool rpm)
 	pci_enable_wake(pdev, PCI_D3hot, 0);
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
-	if (igc_is_device_id_i226(hw))
+	if (igc_is_device_id_i226(hw) || hw->device_id == IGC_DEV_ID_I225_LMVP)
 		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
 
 	if (igc_init_interrupt_scheme(adapter, true)) {
@@ -7688,7 +7688,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 		pci_enable_wake(pdev, PCI_D3hot, 0);
 		pci_enable_wake(pdev, PCI_D3cold, 0);
 
-		if (igc_is_device_id_i226(hw))
+		if (igc_is_device_id_i226(hw) || hw->device_id == IGC_DEV_ID_I225_LMVP)
 			pci_disable_link_state_locked(pdev, PCIE_LINK_STATE_L1_2);
 
 		/* In case of PCI error, adapter loses its HW address
-- 
2.53.0


                 reply	other threads:[~2026-09-25 11:29 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=20260925112850.189302-1-danividanivi@gmail.com \
    --to=danividanivi@gmail.com \
    --cc=anthony.l.nguyen@intel.com \
    --cc=bhelgaas@google.com \
    --cc=intel-wired-lan@lists.osuosl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=przemyslaw.kitszel@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

all inboxes | Powered by JetHome®