From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-pl1-f175.google.com (mail-pl1-f175.google.com [209.85.214.175]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CD32944999A for ; Thu, 9 Jul 2026 18:54:54 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.175 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1783623296; cv=none; b=ZjUjfPjq0mwcgOleULtrIlYrdBtL1Ke0Fy/icFIpgYFd0rMml1/7gqrGuBNDpshxJHtH0gc0qlI+v5i+2XpfSpKV9FJ0TxCLMQXftMNg2ADxb09Lsp/gsgD9ARPM3OO0IUBGLaJcw9JqA9mYxHJOM8rTSSRxEsPOZERmOsSxVpk= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1783623296; c=relaxed/simple; bh=82jIYnEBVnizznYZVjbcNxVtecRVdrYP/jvI4I8Tfmo=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=NIaFFN5hpIGxqVRXF5zax2X+vI4VCQK3fsPpjWUp7XuiPWwC9oAhUnZ02KsFl1eFBqCoQO+AJflBccb0sH4f9TPa8ple5zQdztkp/BWbkiFoBxgBlhqPg/zVPuwuzUdB8LL70Z1/U8puWp9Kn/jUYlDvxMLnT8sxNeuV1DerrF0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=arista.com; spf=pass smtp.mailfrom=arista.com; dkim=pass (2048-bit key) header.d=arista.com header.i=@arista.com header.b=R7uzgWq0; arc=none smtp.client-ip=209.85.214.175 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=arista.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arista.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=arista.com header.i=@arista.com header.b="R7uzgWq0" Received: by mail-pl1-f175.google.com with SMTP id d9443c01a7336-2ca70925c25so1307765ad.1 for ; Thu, 09 Jul 2026 11:54:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=arista.com; s=google; t=1783623294; x=1784228094; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to:content-type; bh=Z8Zy5PB6oCNiDdVLDyMMBSqbi/zOyH2nEGcV3a3Utlo=; b=R7uzgWq0sXvvN4P8M6DkCzqzEpOaZsBZqWFd2Flzx+LzZZGjIyPAV7wHX7inMvo3Sh AaA20j4aTOoZx9axJal8NsXhCngaUgIMUYYJZQo6+u4UdgcdXfR3BQdUfJKVUkmzY/dn UiNBjL5Ixy0e0AicyRqdcBIak4krPM1ZFNnCjPQ58N/4aeY2uSribDXIXprYqjcNlmea 0TVmMBJY+dEuvECiLuSlnzH+ih40CWB0Rk17ktek/OHNSzplC6R9LS4LPFO3LQUjQm/u 3rYApmsTc8xE9V9JVFZl+AR34hXHAMDZol+L+MdomQSFYEYpmSxQ8I7xCP+7SoJ6C0KH T1Ow== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1783623294; x=1784228094; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to:content-type; bh=Z8Zy5PB6oCNiDdVLDyMMBSqbi/zOyH2nEGcV3a3Utlo=; b=fL0y3Us95L5xAuQqdmz/zBNTOLSDLIZpdjdY6+mxVB2s2JKAhggWV73UhyjyclPbyG xJplXKiWXeN+TFlUMJiT7A6jAR/dBVLUn1qs6qVLc6u93BT7reQVvIHhV++5Zr7besGK gbNbAZca5iVv0j9zTjL5ALzY8wEDMTEknoOvNQOemxT/kCKK3TpFbFX8485RP6E3x/wQ 3Y7q2wRyWbQ1SkDjV8vsjI0nlC3FAKlpEDvBW0/usMyf2NmbxXr7J35ld0Z3r484eQfx Qk27pYKmNS3t0ywnrwlSr50CxUNBBwxc4TSXU5YfFHYiF+Yevc7BczP8SbpfBxVSOtpJ lDTA== X-Forwarded-Encrypted: i=1; AHgh+RoBLHUJN88PDux22LgUIgneE72nsa6fLE0ByymvaqjuvNqx5vXvBIQpRv1dYeA8nTJH0mD08qm9E2g=@vger.kernel.org X-Gm-Message-State: AOJu0YyKQu0S/pvBsqaPGUKXZgiY3h1TW4yCnOjTTSMzWYKPsutgUSmA 1WU07+CrIDZHdhpq4KURFHP0OEXHKDEmWJWVcG3MT0Ec/0XNnqa81rKSi5+wd1UGOw== X-Gm-Gg: AfdE7ckUlZWCcE2Vi7hWUT2GFA8RjIGxl4b4QLaE62ESZDbnV7ApLcYKmo9N0BaL89t uvBhVl7IHOLtQoONpfpRaaEvmFd7vIJDruXX7ZrnFccV7pQeTILYmVM2emfb4t0Bm6LoUjbh96+ zfVLYlkMmNmSQ2l4EmeWE/kida4Ky+C79ApYm10dIpewBTGxY2dUiuUkdTO1ZWOV06ouY4YE7A5 fRYyYsWVKf2MdVzh8EhpWtE1aiKpzP4x4+aDZDBB7O/h1dvydv3FUNjh6Ya/nqlKaJrNivbUKvp ty5KaGuMh3/G2VJAeJvbYMYrwAc6HXuu+hfDDk/SGyafU9YrVPp27FgQXRcQLUvcrwt2ZHbzNxk hehX5YO6zGbgu7ETWpuw5gVpG3L8uCi+ZFymL9h9TzVBHBRQEhBPfgnvtpcEydZaWB3pOLLbOLq yfNvIqLtPYaKZYBa54eDWZAl8/XqCWKNuSVgYaeKj5K89I X-Received: by 2002:a05:6a21:38e:b0:3b3:241f:66c4 with SMTP id adf61e73a8af0-3c0bd0028bfmr10439038637.28.1783623294191; Thu, 09 Jul 2026 11:54:54 -0700 (PDT) Received: from yurypm-home-4hjc6.sjc.aristanetworks.com ([74.123.28.16]) by smtp.gmail.com with ESMTPSA id 5a478bee46e88-311747f5975sm31297642eec.4.2026.07.09.11.54.52 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 09 Jul 2026 11:54:53 -0700 (PDT) From: Yury Murashka To: bhelgaas@google.com Cc: corbet@lwn.net, skhan@linuxfoundation.org, mahesh@linux.ibm.com, oohall@gmail.com, linux-pci@vger.kernel.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, Yury Murashka Subject: [PATCH v2 1/2] PCI: Add pci=noaer_recovery kernel boot option Date: Thu, 9 Jul 2026 18:54:28 +0000 Message-ID: <20260709185429.627968-2-yurypm@arista.com> X-Mailer: git-send-email 2.51.0 In-Reply-To: <20260709185429.627968-1-yurypm@arista.com> References: <20260709185429.627968-1-yurypm@arista.com> Precedence: bulk X-Mailing-List: linux-pci@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit AER error recovery is part of the AER error handling subsystem in the Linux kernel. On large modular systems with a complex PCIe tree, AER recovery could cause unexpected behavior and side effects. Sometimes it would be nice to have the option to keep the system in an unmodified state and be able to handle PCIe errors from userspace. Add pci=noaer_recovery kernel boot option to disable AER error recovery when an uncorrectable error is reported. When this option is set, the error is still logged but no recovery actions are taken. AER error status bits are preserved so userspace can inspect the error state. Signed-off-by: Yury Murashka --- .../admin-guide/kernel-parameters.txt | 6 ++++ drivers/pci/pci.c | 2 ++ drivers/pci/pci.h | 2 ++ drivers/pci/pcie/aer.c | 30 ++++++++++++------- 4 files changed, 30 insertions(+), 10 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b5493a7f8f22..13c6b53bb9ee 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5053,6 +5053,12 @@ Kernel parameters noaer [PCIE] If the PCIEAER kernel config parameter is enabled, this kernel boot option can be used to disable the use of PCIE advanced error reporting. + noaer_recovery [PCIE] If the PCIEAER kernel config parameter is + enabled, this kernel boot option can be used to + disable AER error recovery when an uncorrectable + error is reported. AER error status bits are + preserved so userspace can inspect the error + state. nodomains [PCI] Disable support for multiple PCI root domains (aka PCI segments, in ACPI-speak). nommconf [X86] Disable use of MMCONFIG for PCI diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 77b17b13ee61..a215dd567d5d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6756,6 +6756,8 @@ static int __init pci_setup(char *str) pcie_ats_disabled = true; } else if (!strcmp(str, "noaer")) { pci_no_aer(); + } else if (!strcmp(str, "noaer_recovery")) { + pci_no_aer_recovery(); } else if (!strcmp(str, "earlydump")) { pci_early_dump = true; } else if (!strncmp(str, "realloc=", 8)) { diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 4469e1a77f3c..c4a42bbc277b 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -1283,6 +1283,7 @@ static inline void of_pci_remove_host_bridge_node(struct pci_host_bridge *bridge #ifdef CONFIG_PCIEAER void pci_no_aer(void); +void pci_no_aer_recovery(void); void pci_aer_init(struct pci_dev *dev); void pci_aer_exit(struct pci_dev *dev); extern const struct attribute_group aer_stats_attr_group; @@ -1294,6 +1295,7 @@ void pci_save_aer_state(struct pci_dev *dev); void pci_restore_aer_state(struct pci_dev *dev); #else static inline void pci_no_aer(void) { } +static inline void pci_no_aer_recovery(void) { } static inline void pci_aer_init(struct pci_dev *d) { } static inline void pci_aer_exit(struct pci_dev *d) { } static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { } diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index c4fd9c0b2a54..fb79990ce8ff 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -128,6 +128,7 @@ struct aer_info { PCI_ERR_ROOT_MULTI_UNCOR_RCV) static bool pcie_aer_disable; +static bool pcie_aer_recovery_disable; static pci_ers_result_t aer_root_reset(struct pci_dev *dev); void pci_no_aer(void) @@ -135,6 +136,11 @@ void pci_no_aer(void) pcie_aer_disable = true; } +void pci_no_aer_recovery(void) +{ + pcie_aer_recovery_disable = true; +} + bool pci_aer_available(void) { return !pcie_aer_disable && pci_msi_enabled(); @@ -1187,10 +1193,12 @@ static void pci_aer_handle_error(struct pci_dev *dev, struct aer_err_info *info) pdrv->err_handler->cor_error_detected(dev); pcie_clear_device_status(dev); } - } else if (info->severity == AER_NONFATAL) - pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset); - else if (info->severity == AER_FATAL) - pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset); + } else if (!pcie_aer_recovery_disable) { + if (info->severity == AER_NONFATAL) + pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset); + else if (info->severity == AER_FATAL) + pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset); + } } static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info) @@ -1242,12 +1250,14 @@ static void aer_recover_work_func(struct work_struct *work) ghes_estatus_pool_region_free((unsigned long)entry.regs, sizeof(struct aer_capability_regs)); - if (entry.severity == AER_NONFATAL) - pcie_do_recovery(pdev, pci_channel_io_normal, - aer_root_reset); - else if (entry.severity == AER_FATAL) - pcie_do_recovery(pdev, pci_channel_io_frozen, - aer_root_reset); + if (!pcie_aer_recovery_disable) { + if (entry.severity == AER_NONFATAL) + pcie_do_recovery(pdev, pci_channel_io_normal, + aer_root_reset); + else if (entry.severity == AER_FATAL) + pcie_do_recovery(pdev, pci_channel_io_frozen, + aer_root_reset); + } pci_dev_put(pdev); } } -- 2.51.0