On Mon, Aug 22, 2022 at 03:40:43PM +0000, Jia He wrote:
> ghes_edac_init() is too late to set this module flag ghes_edac.force_load.
> Also, other edac drivers should not be able to control this flag.
>
> Move this flag to setup parameter in ghes.
>
> Suggested-by: Toshi Kani <toshi.kani@xxxxxxx>
> Signed-off-by: Jia He <justin.he@xxxxxxx>
> ---
> .../admin-guide/kernel-parameters.txt | 5 +++
> drivers/acpi/apei/ghes.c | 24 +++++++++++-
> drivers/edac/ghes_edac.c | 38 +++++++------------
> include/acpi/ghes.h | 7 +++-
> 4 files changed, 46 insertions(+), 28 deletions(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index d7f30902fda0..a5f0ee0d7727 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1593,6 +1593,11 @@
> When zero, profiling data is discarded and associated
> debugfs files are removed at module unload time.
>
> + ghes_edac_force= [X86] Skip the platform check and forcibly load the
So there already is ghes.disable which is using the module param thing.
Why don't you do that too?
> + ghes_edac modules.
"module" - singular.
> + Format: <bool>
> + default: false (0)
> +
> goldfish [X86] Enable the goldfish android emulator platform.
> Don't use this when you are not running on the
> android emulator
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 9c52183e3ad9..e17e0ee8f842 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -94,6 +94,26 @@
> #define FIX_APEI_GHES_SDEI_CRITICAL __end_of_fixed_addresses
> #endif
>
> +/*
> + * "ghes_edac_force=1" forcibly loads ghes_edac and skips the platform
> + * check.
> + */
> +bool __read_mostly ghes_edac_force;
> +EXPORT_SYMBOL(ghes_edac_force);
> +
> +static int __init setup_ghes_edac_load(char *str)
> +{
> + if (str)
> + if (!strcmp("true", str) || !strcmp("1", str))
> + ghes_edac_force = true;
> +
> + if (!IS_ENABLED(CONFIG_X86))
> + ghes_edac_force = true;
> +
> + return 1;
> +}
> +__setup("ghes_edac_force=", setup_ghes_edac_load);
Why all that?
Isn't specifying
ghes.edac_force_load
on the kernel command line enough? I.e., you don't need to parse the
passed in option - just the presence of the parameter is enough.
> +
> static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
>
> static inline bool is_hest_type_generic_v2(struct ghes *ghes)
> @@ -1517,13 +1537,13 @@ static struct acpi_platform_list plat_list[] = {
> { } /* End */
> };
>
> -struct list_head *ghes_get_devices(bool force)
> +struct list_head *ghes_get_devices(void)
> {
> int idx = -1;
>
> if (IS_ENABLED(CONFIG_X86)) {
> idx = acpi_match_platform_list(plat_list);
> - if (idx < 0 && !force)
> + if (idx < 0 && !ghes_edac_force)
> return NULL;
> }
>
> diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
> index bb3ea42ba70b..6a2b54cc7240 100644
> --- a/drivers/edac/ghes_edac.c
> +++ b/drivers/edac/ghes_edac.c
> @@ -54,10 +54,6 @@ static DEFINE_MUTEX(ghes_reg_mutex);
> */
> 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);
> -
> static bool system_scanned;
>
> static struct list_head *ghes_devs;
> @@ -437,23 +433,12 @@ static int ghes_edac_register(struct device *dev)
> mci->ctl_name = "ghes_edac";
> mci->dev_name = "ghes";
>
> - 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 (force_load) {
> - 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", ghes_hw.num_dimms);
> - }
> -
> if (!fake) {
> struct dimm_info *src, *dst;
> int i = 0;
>
> + pr_info("This system has %d DIMM sockets.\n", ghes_hw.num_dimms);
> +
> mci_for_each_dimm(mci, dst) {
> src = &ghes_hw.dimms[i];
>
This hunk...
> @@ -478,6 +463,17 @@ static int ghes_edac_register(struct device *dev)
> } else {
> struct dimm_info *dimm = edac_get_dimm(mci, 0, 0, 0);
>
> + 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 (ghes_edac_force) {
> + pr_info("This EDAC driver relies on BIOS to enumerate memory and get\n");
> + pr_info("error reports. Unfortunately, not all BIOSes reflect the\n");
> + pr_info("memory layout correctly. If you find incorrect reports, please\n");
> + pr_info("contact your hardware vendor for its in correct BIOS.\n");
> + }
> +
> dimm->nr_pages = 1;
> dimm->grain = 128;
> dimm->mtype = MEM_UNKNOWN;
... and this hunk look unrelated to what this patch is doing. What are
they for?
Thx.
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
