|
| 1 | +// SPDX-License-Identifier: GPL-2.0-only |
| 2 | +/* |
| 3 | + * NVIDIA GHES vendor record handler |
| 4 | + * |
| 5 | + * Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. |
| 6 | + */ |
| 7 | + |
| 8 | +#include <linux/acpi.h> |
| 9 | +#include <linux/module.h> |
| 10 | +#include <linux/platform_device.h> |
| 11 | +#include <linux/types.h> |
| 12 | +#include <linux/uuid.h> |
| 13 | +#include <acpi/ghes.h> |
| 14 | + |
| 15 | +static const guid_t nvidia_sec_guid = |
| 16 | + GUID_INIT(0x6d5244f2, 0x2712, 0x11ec, |
| 17 | + 0xbe, 0xa7, 0xcb, 0x3f, 0xdb, 0x95, 0xc7, 0x86); |
| 18 | + |
| 19 | +struct cper_sec_nvidia { |
| 20 | + char signature[16]; |
| 21 | + __le16 error_type; |
| 22 | + __le16 error_instance; |
| 23 | + u8 severity; |
| 24 | + u8 socket; |
| 25 | + u8 number_regs; |
| 26 | + u8 reserved; |
| 27 | + __le64 instance_base; |
| 28 | + struct { |
| 29 | + __le64 addr; |
| 30 | + __le64 val; |
| 31 | + } regs[] __counted_by(number_regs); |
| 32 | +}; |
| 33 | + |
| 34 | +struct nvidia_ghes_private { |
| 35 | + struct notifier_block nb; |
| 36 | + struct device *dev; |
| 37 | +}; |
| 38 | + |
| 39 | +static void nvidia_ghes_print_error(struct device *dev, |
| 40 | + const struct cper_sec_nvidia *nvidia_err, |
| 41 | + size_t error_data_length, bool fatal) |
| 42 | +{ |
| 43 | + const char *level = fatal ? KERN_ERR : KERN_INFO; |
| 44 | + size_t min_size; |
| 45 | + |
| 46 | + dev_printk(level, dev, "signature: %.16s\n", nvidia_err->signature); |
| 47 | + dev_printk(level, dev, "error_type: %u\n", le16_to_cpu(nvidia_err->error_type)); |
| 48 | + dev_printk(level, dev, "error_instance: %u\n", le16_to_cpu(nvidia_err->error_instance)); |
| 49 | + dev_printk(level, dev, "severity: %u\n", nvidia_err->severity); |
| 50 | + dev_printk(level, dev, "socket: %u\n", nvidia_err->socket); |
| 51 | + dev_printk(level, dev, "number_regs: %u\n", nvidia_err->number_regs); |
| 52 | + dev_printk(level, dev, "instance_base: 0x%016llx\n", |
| 53 | + le64_to_cpu(nvidia_err->instance_base)); |
| 54 | + |
| 55 | + if (nvidia_err->number_regs == 0) |
| 56 | + return; |
| 57 | + |
| 58 | + /* |
| 59 | + * Validate that all registers fit within error_data_length. |
| 60 | + * Each register pair is two little-endian u64s. |
| 61 | + */ |
| 62 | + min_size = struct_size(nvidia_err, regs, nvidia_err->number_regs); |
| 63 | + if (error_data_length < min_size) { |
| 64 | + dev_err(dev, "Invalid number_regs %u (section size %zu, need %zu)\n", |
| 65 | + nvidia_err->number_regs, error_data_length, min_size); |
| 66 | + return; |
| 67 | + } |
| 68 | + |
| 69 | + for (int i = 0; i < nvidia_err->number_regs; i++) |
| 70 | + dev_printk(level, dev, "register[%d]: address=0x%016llx value=0x%016llx\n", |
| 71 | + i, le64_to_cpu(nvidia_err->regs[i].addr), |
| 72 | + le64_to_cpu(nvidia_err->regs[i].val)); |
| 73 | +} |
| 74 | + |
| 75 | +static int nvidia_ghes_notify(struct notifier_block *nb, |
| 76 | + unsigned long event, void *data) |
| 77 | +{ |
| 78 | + struct acpi_hest_generic_data *gdata = data; |
| 79 | + struct nvidia_ghes_private *priv; |
| 80 | + const struct cper_sec_nvidia *nvidia_err; |
| 81 | + guid_t sec_guid; |
| 82 | + |
| 83 | + import_guid(&sec_guid, gdata->section_type); |
| 84 | + if (!guid_equal(&sec_guid, &nvidia_sec_guid)) |
| 85 | + return NOTIFY_DONE; |
| 86 | + |
| 87 | + priv = container_of(nb, struct nvidia_ghes_private, nb); |
| 88 | + |
| 89 | + if (acpi_hest_get_error_length(gdata) < sizeof(*nvidia_err)) { |
| 90 | + dev_err(priv->dev, "Section too small (%d < %zu)\n", |
| 91 | + acpi_hest_get_error_length(gdata), sizeof(*nvidia_err)); |
| 92 | + return NOTIFY_OK; |
| 93 | + } |
| 94 | + |
| 95 | + nvidia_err = acpi_hest_get_payload(gdata); |
| 96 | + |
| 97 | + if (event >= GHES_SEV_RECOVERABLE) |
| 98 | + dev_err(priv->dev, "NVIDIA CPER section, error_data_length: %u\n", |
| 99 | + acpi_hest_get_error_length(gdata)); |
| 100 | + else |
| 101 | + dev_info(priv->dev, "NVIDIA CPER section, error_data_length: %u\n", |
| 102 | + acpi_hest_get_error_length(gdata)); |
| 103 | + |
| 104 | + nvidia_ghes_print_error(priv->dev, nvidia_err, acpi_hest_get_error_length(gdata), |
| 105 | + event >= GHES_SEV_RECOVERABLE); |
| 106 | + |
| 107 | + return NOTIFY_OK; |
| 108 | +} |
| 109 | + |
| 110 | +static int nvidia_ghes_probe(struct platform_device *pdev) |
| 111 | +{ |
| 112 | + struct nvidia_ghes_private *priv; |
| 113 | + int ret; |
| 114 | + |
| 115 | + priv = devm_kmalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); |
| 116 | + if (!priv) |
| 117 | + return -ENOMEM; |
| 118 | + |
| 119 | + *priv = (struct nvidia_ghes_private) { |
| 120 | + .nb.notifier_call = nvidia_ghes_notify, |
| 121 | + .dev = &pdev->dev, |
| 122 | + }; |
| 123 | + |
| 124 | + ret = devm_ghes_register_vendor_record_notifier(&pdev->dev, &priv->nb); |
| 125 | + if (ret) |
| 126 | + return dev_err_probe(&pdev->dev, ret, |
| 127 | + "Failed to register NVIDIA GHES vendor record notifier\n"); |
| 128 | + |
| 129 | + return 0; |
| 130 | +} |
| 131 | + |
| 132 | +static const struct acpi_device_id nvidia_ghes_acpi_match[] = { |
| 133 | + { "NVDA2012" }, |
| 134 | + { } |
| 135 | +}; |
| 136 | +MODULE_DEVICE_TABLE(acpi, nvidia_ghes_acpi_match); |
| 137 | + |
| 138 | +static struct platform_driver nvidia_ghes_driver = { |
| 139 | + .driver = { |
| 140 | + .name = "nvidia-ghes", |
| 141 | + .acpi_match_table = nvidia_ghes_acpi_match, |
| 142 | + }, |
| 143 | + .probe = nvidia_ghes_probe, |
| 144 | +}; |
| 145 | +module_platform_driver(nvidia_ghes_driver); |
| 146 | + |
| 147 | +MODULE_AUTHOR("Kai-Heng Feng <kaihengf@nvidia.com>"); |
| 148 | +MODULE_DESCRIPTION("NVIDIA GHES vendor CPER record handler"); |
| 149 | +MODULE_LICENSE("GPL"); |
0 commit comments