From 5deed6b6a479ad5851d7ead6412dc6faa84a694e Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 23 Aug 2017 16:54:45 -0600 Subject: EDAC, ghes: Add platform check The ghes_edac driver was introduced in 2013 [1], but it has not been enabled by any distro yet. This driver obtains error info from firmware interfaces (APEI), which are not properly implemented on many platforms, as the driver says on load: This EDAC driver relies on BIOS to enumerate memory and get error reports. Unfortunately, not all BIOSes reflect the memory layout correctly. So, the end result of using this driver varies from vendor to vendor. If you find incorrect reports, please contact your hardware vendor to correct its BIOS. To get out from this situation, add a platform check to selectively enable the driver on platforms that are known to have proper APEI firmware implementation. "ghes_edac.force_load=1" skips this platform check. [1]: https://lkml.kernel.org/r/cover.1360931635.git.mchehab@redhat.com Signed-off-by: Toshi Kani Cc: Mauro Carvalho Chehab Cc: Tony Luck Cc: linux-acpi@vger.kernel.org Cc: linux-edac Link: http://lkml.kernel.org/r/20170823225447.15608-4-toshi.kani@hpe.com Signed-off-by: Borislav Petkov --- drivers/edac/ghes_edac.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) (limited to 'drivers/edac') diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 8d904df75ad8..68b6ee18bea6 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -38,6 +38,10 @@ static struct ghes_edac_pvt *ghes_pvt; */ static DEFINE_SPINLOCK(ghes_lock); +/* "ghes_edac.force_load=1" skips the platform check */ +static bool __read_mostly force_load; +module_param(force_load, bool, 0); + /* Memory Device - Type 17 of SMBIOS spec */ struct memdev_dmi_entry { u8 type; @@ -415,6 +419,14 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev, spin_unlock_irqrestore(&ghes_lock, flags); } +/* + * Known systems that are safe to enable this module. + */ +static struct acpi_platform_list plat_list[] = { + {"HPE ", "Server ", 0, ACPI_SIG_FADT, all_versions}, + { } /* End */ +}; + int ghes_edac_register(struct ghes *ghes, struct device *dev) { bool fake = false; @@ -422,6 +434,12 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) struct mem_ctl_info *mci; struct edac_mc_layer layers[1]; struct ghes_edac_dimm_fill dimm_fill; + int idx; + + /* Check if safe to enable on this system */ + idx = acpi_match_platform_list(plat_list); + if (!force_load && idx < 0) + return 0; /* * We have only one logical memory controller to which all DIMMs belong. @@ -460,17 +478,17 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) mci->ctl_name = "ghes_edac"; mci->dev_name = "ghes"; - if (!fake) { + if (fake) { + pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS.\n"); + pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would\n"); + pr_info("work on such system. Use this driver with caution\n"); + } else if (idx < 0) { pr_info("This EDAC driver relies on BIOS to enumerate memory and get error reports.\n"); pr_info("Unfortunately, not all BIOSes reflect the memory layout correctly.\n"); pr_info("So, the end result of using this driver varies from vendor to vendor.\n"); pr_info("If you find incorrect reports, please contact your hardware vendor\n"); pr_info("to correct its BIOS.\n"); pr_info("This system has %d DIMM sockets.\n", num_dimm); - } else { - pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS.\n"); - pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would\n"); - pr_info("work on such system. Use this driver with caution\n"); } if (!fake) { -- cgit v1.2.3