| Message ID | 20220822154048.188253-5-justin.he@arm.com |
|---|---|
| State | New |
| Headers | show |
| Series | Make ghes_edac a proper module | expand |
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@hpe.com> > Signed-off-by: Jia He <justin.he@arm.com> > --- > .../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.
> -----Original Message----- [...] > > +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 Ok, I will use module parameter 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... Sorry, should move pr_info after this line > > > @@ -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? > I tried to keep the previous same logic. if (fake) print_something - !fake && ghes not preferred. print_otherthings -- Cheers, Justin (Jia He)
Hi Borislav > -----Original Message----- [...] > > > > 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? > Another purpose for adjusting the pr_info hunk is to suppress the warning dmesg log on Arm server. On Arm, the ghes_edac_force_load (module parameter in ghes) should be true unconditionally. So I moved the following block in fake==true check, is this reasonable? +If (!fake) +... +else + 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"); + } What do you think of it? -- Cheers, Justin (Jia He)
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 + ghes_edac modules. + 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); + 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]; @@ -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; @@ -518,9 +514,6 @@ static void ghes_edac_unregister(struct ghes *ghes) struct mem_ctl_info *mci; unsigned long flags; - if (!force_load) - return; - mutex_lock(&ghes_reg_mutex); system_scanned = false; @@ -554,10 +547,7 @@ static int __init ghes_edac_init(void) { struct ghes *g, *g_tmp; - if (!IS_ENABLED(CONFIG_X86)) - force_load = true; - - ghes_devs = ghes_get_devices(force_load); + ghes_devs = ghes_get_devices(); if (!ghes_devs) return -ENODEV; diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 150c0b9500d6..e29327ee0b83 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -71,9 +71,12 @@ int ghes_register_vendor_record_notifier(struct notifier_block *nb); * @nb: pointer to the notifier_block structure of the vendor record handler. */ void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); -struct list_head *ghes_get_devices(bool force); + +struct list_head *ghes_get_devices(void); +extern bool ghes_edac_force; #else -static inline struct list_head *ghes_get_devices(bool force) { return NULL; } +static inline struct list_head *ghes_get_devices(void) { return NULL; } +static bool ghes_edac_force; #endif int ghes_estatus_pool_init(int num_ghes);
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@hpe.com> Signed-off-by: Jia He <justin.he@arm.com> --- .../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(-)