| Message ID | 1454699608-22760-7-git-send-email-tbaicar@codeaurora.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Fri, Feb 05, 2016 at 12:13:28PM -0700, Tyler Baicar wrote: > ARM APEI extension proposal added SEA (Synchrounous External > Abort) notification type for ARMv8. > > Add a new GHES error source handling function for SEA. If an error > source's notification type is SEA, then this function can be registered > into the SEA exception handler. That way GHES will parse and report > SEA exceptions when they occur. > > Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org> > Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org> > Signed-off-by: Naveen Kaje <nkaje@codeaurora.org> > --- > arch/arm64/Kconfig | 1 + > drivers/acpi/apei/Kconfig | 13 ++++++++ > drivers/acpi/apei/ghes.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++ > include/acpi/actbl1.h | 6 +++- > 4 files changed, 102 insertions(+), 1 deletion(-) > > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index 6e4a4f4..236f398 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -6,6 +6,7 @@ config ARM64 > select ACPI_REDUCED_HARDWARE_ONLY if ACPI > select ARCH_HAS_DEVMEM_IS_ALLOWED > select HAVE_ACPI_APEI if ACPI > + select HAVE_ACPI_APEI_SEA if ACPI > select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE > select ARCH_HAS_ELF_RANDOMIZE > select ARCH_HAS_GCOV_PROFILE_ALL > diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig > index a60bb00..bfcbb9e 100644 > --- a/drivers/acpi/apei/Kconfig > +++ b/drivers/acpi/apei/Kconfig > @@ -7,6 +7,19 @@ config HAVE_ACPI_APEI_NMI > config HAVE_ACPI_APEI_HEST_IA32 > bool > > +config HAVE_ACPI_APEI_SEA > + bool "APEI Synchronous External Abort logging/recovering support" > + help > + This option should be enabled if the system supports > + firmware first handling of SEA (Synchronous External Abort). > + SEA happens with certain faults of data abort or instruction > + abort synchronous exceptions on ARMv8 systems. If a system > + supports firmware first handling of SEA, the platform analyzes > + and handles hardware error notifications with SEA, and it may then > + form a HW error record for the OS to parse and handle. This > + option allows the OS to look for such HW error record, and > + take appropriate action. > + > config ACPI_APEI > bool "ACPI Platform Error Interface (APEI)" > select MISC_FILESYSTEMS > diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c > index 6c68100..ed64b97 100644 > --- a/drivers/acpi/apei/ghes.c > +++ b/drivers/acpi/apei/ghes.c > @@ -50,6 +50,10 @@ > #include <acpi/apei.h> > #include <asm/tlbflush.h> > > +#ifdef CONFIG_HAVE_ACPI_APEI_SEA > +#include <asm/system_misc.h> > +#endif > + > #include "apei-internal.h" > > #define GHES_PFX "GHES: " > @@ -784,6 +788,62 @@ static struct notifier_block ghes_notifier_sci = { > .notifier_call = ghes_notify_sci, > }; > > +#ifdef CONFIG_HAVE_ACPI_APEI_SEA > +static LIST_HEAD(ghes_sea); > + > +static int ghes_notify_sea(struct notifier_block *this, > + unsigned long event, void *data) > +{ > + struct ghes *ghes; > + int ret = NOTIFY_DONE; > + > + rcu_read_lock(); > + list_for_each_entry_rcu(ghes, &ghes_sea, list) { > + if (!ghes_proc(ghes)) > + ret = NOTIFY_OK; > + } > + rcu_read_unlock(); > + > + return ret; > +} > + > +static struct notifier_block ghes_notifier_sea = { > + .notifier_call = ghes_notify_sea, > +}; > + > +static int ghes_sea_add(struct ghes *ghes) > +{ > + mutex_lock(&ghes_list_mutex); Can you just use spin_lock, to be consistent with our other excception hooks? > + if (list_empty(&ghes_sea)) > + sea_register_handler_chain(&ghes_notifier_sea); > + list_add_rcu(&ghes->list, &ghes_sea); > + mutex_unlock(&ghes_list_mutex); > + return 0; > +} > + > +static void ghes_sea_remove(struct ghes *ghes) > +{ > + mutex_lock(&ghes_list_mutex); > + list_del_rcu(&ghes->list); > + if (list_empty(&ghes_sea)) > + sea_unregister_handler_chain(&ghes_notifier_sea); > + mutex_unlock(&ghes_list_mutex); > +} > +#else /* CONFIG_HAVE_ACPI_APEI_SEA */ > +static inline int ghes_sea_add(struct ghes *ghes) > +{ > + pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n", > + ghes->generic->header.source_id); > + return -ENOTSUPP; > +} > + > +static inline void ghes_sea_remove(struct ghes *ghes) > +{ > + pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n", > + ghes->generic->header.source_id); > +} Why are these getting called if !CONFIG_HAVE_ACPI_APEI_SEA? Will
On 2/10/2016 1:03 PM, Will Deacon wrote: > On Fri, Feb 05, 2016 at 12:13:28PM -0700, Tyler Baicar wrote: >> +#else /* CONFIG_HAVE_ACPI_APEI_SEA */ >> +static inline int ghes_sea_add(struct ghes *ghes) >> +{ >> + pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n", >> + ghes->generic->header.source_id); >> + return -ENOTSUPP; >> +} >> + >> +static inline void ghes_sea_remove(struct ghes *ghes) >> +{ >> + pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n", >> + ghes->generic->header.source_id); >> +} > > Why are these getting called if !CONFIG_HAVE_ACPI_APEI_SEA? > This was added to catch firmware bugs (i.e. bad ACPI tables). Since "SEA" is a valid GHES notify type in ACPI, it's just a number in an ACPI table. If someone incorrectly set SEA as their notify type in their HEST table on an Intel system, this would catch that error here. We may do this with less code by getting rid of the #else (as you suggest), but we need to add #ifdefs to eliminate the calls to ghes_sea_add and ghes_sea_remove to avoid compiler errors. Does the below change look better? >>@@ -1093,6 +1168,11 @@ static int ghes_probe(struct platform_device >>*ghes_dev) >> list_add_rcu(&ghes->list, &ghes_sci); >> mutex_unlock(&ghes_list_mutex); >> break; >> +#ifdef CONFIG_HAVE_ACPI_APEI_SEA >>+ case ACPI_HEST_NOTIFY_SEA: >>+ rc = ghes_sea_add(ghes); >>+ if (rc) >>+ goto err_edac_unreg; >>+ break; +#endif ... >>@@ -1135,6 +1215,9 @@ static int ghes_remove(struct platform_device >>*ghes_dev) >> >>unregister_acpi_hed_notifier(&ghes_notifier_sci); >> mutex_unlock(&ghes_list_mutex); >> break; +#ifdef CONFIG_HAVE_ACPI_APEI_SEA >>+ case ACPI_HEST_NOTIFY_SEA: >>+ ghes_sea_remove(ghes); >>+ break; +#endif Harb
Hello Will, On 2/10/2016 11:03 AM, Will Deacon wrote: > On Fri, Feb 05, 2016 at 12:13:28PM -0700, Tyler Baicar wrote: >> ARM APEI extension proposal added SEA (Synchrounous External >> Abort) notification type for ARMv8. >> >> Add a new GHES error source handling function for SEA. If an error >> source's notification type is SEA, then this function can be registered >> into the SEA exception handler. That way GHES will parse and report >> SEA exceptions when they occur. >> >> Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org> >> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org> >> Signed-off-by: Naveen Kaje <nkaje@codeaurora.org> >> --- >> arch/arm64/Kconfig | 1 + >> drivers/acpi/apei/Kconfig | 13 ++++++++ >> drivers/acpi/apei/ghes.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++ >> include/acpi/actbl1.h | 6 +++- >> 4 files changed, 102 insertions(+), 1 deletion(-) >> >> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig >> index 6e4a4f4..236f398 100644 >> --- a/arch/arm64/Kconfig >> +++ b/arch/arm64/Kconfig >> @@ -6,6 +6,7 @@ config ARM64 >> select ACPI_REDUCED_HARDWARE_ONLY if ACPI >> select ARCH_HAS_DEVMEM_IS_ALLOWED >> select HAVE_ACPI_APEI if ACPI >> + select HAVE_ACPI_APEI_SEA if ACPI >> select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE >> select ARCH_HAS_ELF_RANDOMIZE >> select ARCH_HAS_GCOV_PROFILE_ALL >> diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig >> index a60bb00..bfcbb9e 100644 >> --- a/drivers/acpi/apei/Kconfig >> +++ b/drivers/acpi/apei/Kconfig >> @@ -7,6 +7,19 @@ config HAVE_ACPI_APEI_NMI >> config HAVE_ACPI_APEI_HEST_IA32 >> bool >> >> +config HAVE_ACPI_APEI_SEA >> + bool "APEI Synchronous External Abort logging/recovering support" >> + help >> + This option should be enabled if the system supports >> + firmware first handling of SEA (Synchronous External Abort). >> + SEA happens with certain faults of data abort or instruction >> + abort synchronous exceptions on ARMv8 systems. If a system >> + supports firmware first handling of SEA, the platform analyzes >> + and handles hardware error notifications with SEA, and it may then >> + form a HW error record for the OS to parse and handle. This >> + option allows the OS to look for such HW error record, and >> + take appropriate action. >> + >> config ACPI_APEI >> bool "ACPI Platform Error Interface (APEI)" >> select MISC_FILESYSTEMS >> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c >> index 6c68100..ed64b97 100644 >> --- a/drivers/acpi/apei/ghes.c >> +++ b/drivers/acpi/apei/ghes.c >> @@ -50,6 +50,10 @@ >> #include <acpi/apei.h> >> #include <asm/tlbflush.h> >> >> +#ifdef CONFIG_HAVE_ACPI_APEI_SEA >> +#include <asm/system_misc.h> >> +#endif >> + >> #include "apei-internal.h" >> >> #define GHES_PFX "GHES: " >> @@ -784,6 +788,62 @@ static struct notifier_block ghes_notifier_sci = { >> .notifier_call = ghes_notify_sci, >> }; >> >> +#ifdef CONFIG_HAVE_ACPI_APEI_SEA >> +static LIST_HEAD(ghes_sea); >> + >> +static int ghes_notify_sea(struct notifier_block *this, >> + unsigned long event, void *data) >> +{ >> + struct ghes *ghes; >> + int ret = NOTIFY_DONE; >> + >> + rcu_read_lock(); >> + list_for_each_entry_rcu(ghes, &ghes_sea, list) { >> + if (!ghes_proc(ghes)) >> + ret = NOTIFY_OK; >> + } >> + rcu_read_unlock(); >> + >> + return ret; >> +} >> + >> +static struct notifier_block ghes_notifier_sea = { >> + .notifier_call = ghes_notify_sea, >> +}; >> + >> +static int ghes_sea_add(struct ghes *ghes) >> +{ >> + mutex_lock(&ghes_list_mutex); > Can you just use spin_lock, to be consistent with our other excception > hooks? This mutex is being used throughout ghes.c for editing the lists, so I think this is the proper (or at least consistent) implementation. This mutex was defined specifically for editing the lists according to the comment above the mutex definition: "All error sources notified with SCI shares one notifier function, so they need to be linked and checked one by one. This is applied to NMI too. RCU is used for these lists, so ghes_list_mutex is only used for list changing, not for traversing." The use of this mutex is identical to the way that SCI and NMI use it when adding or deleting from the lists. Should I add to this comment that this applies to SEA as well? > >> + if (list_empty(&ghes_sea)) >> + sea_register_handler_chain(&ghes_notifier_sea); >> + list_add_rcu(&ghes->list, &ghes_sea); >> + mutex_unlock(&ghes_list_mutex); >> + return 0; >> +} >> + >> +static void ghes_sea_remove(struct ghes *ghes) >> +{ >> + mutex_lock(&ghes_list_mutex); >> + list_del_rcu(&ghes->list); >> + if (list_empty(&ghes_sea)) >> + sea_unregister_handler_chain(&ghes_notifier_sea); >> + mutex_unlock(&ghes_list_mutex); >> +} >> +#else /* CONFIG_HAVE_ACPI_APEI_SEA */ >> +static inline int ghes_sea_add(struct ghes *ghes) >> +{ >> + pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n", >> + ghes->generic->header.source_id); >> + return -ENOTSUPP; >> +} >> + >> +static inline void ghes_sea_remove(struct ghes *ghes) >> +{ >> + pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n", >> + ghes->generic->header.source_id); >> +} > Why are these getting called if !CONFIG_HAVE_ACPI_APEI_SEA? > > Will Thanks, Tyler
On Thu, Feb 11, 2016 at 03:37:55PM -0700, Baicar, Tyler wrote: > On 2/10/2016 11:03 AM, Will Deacon wrote: > >On Fri, Feb 05, 2016 at 12:13:28PM -0700, Tyler Baicar wrote: > >>diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c > >>index 6c68100..ed64b97 100644 > >>--- a/drivers/acpi/apei/ghes.c > >>+++ b/drivers/acpi/apei/ghes.c > >>@@ -50,6 +50,10 @@ > >> #include <acpi/apei.h> > >> #include <asm/tlbflush.h> > >>+#ifdef CONFIG_HAVE_ACPI_APEI_SEA > >>+#include <asm/system_misc.h> > >>+#endif > >>+ > >> #include "apei-internal.h" > >> #define GHES_PFX "GHES: " > >>@@ -784,6 +788,62 @@ static struct notifier_block ghes_notifier_sci = { > >> .notifier_call = ghes_notify_sci, > >> }; > >>+#ifdef CONFIG_HAVE_ACPI_APEI_SEA > >>+static LIST_HEAD(ghes_sea); > >>+ > >>+static int ghes_notify_sea(struct notifier_block *this, > >>+ unsigned long event, void *data) > >>+{ > >>+ struct ghes *ghes; > >>+ int ret = NOTIFY_DONE; > >>+ > >>+ rcu_read_lock(); > >>+ list_for_each_entry_rcu(ghes, &ghes_sea, list) { > >>+ if (!ghes_proc(ghes)) > >>+ ret = NOTIFY_OK; > >>+ } > >>+ rcu_read_unlock(); > >>+ > >>+ return ret; > >>+} > >>+ > >>+static struct notifier_block ghes_notifier_sea = { > >>+ .notifier_call = ghes_notify_sea, > >>+}; > >>+ > >>+static int ghes_sea_add(struct ghes *ghes) > >>+{ > >>+ mutex_lock(&ghes_list_mutex); > >Can you just use spin_lock, to be consistent with our other excception > >hooks? > This mutex is being used throughout ghes.c for editing the lists, so I think > this is the proper (or at least consistent) implementation. This mutex was > defined specifically for editing the lists according to the comment above > the mutex definition: > > "All error sources notified with SCI shares one notifier function, so they > need to be linked and checked one by one. This is applied to NMI too. RCU is > used for these lists, so ghes_list_mutex is only used for list changing, not > for traversing." > > The use of this mutex is identical to the way that SCI and NMI use it when > adding or deleting from the lists. Should I add to this comment that this > applies to SEA as well? No, it's fine. I overlooked the fact that this was under drivers/acpi/, so if you're consistent with other code under there then there's no need to change anything. Will
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6e4a4f4..236f398 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -6,6 +6,7 @@ config ARM64 select ACPI_REDUCED_HARDWARE_ONLY if ACPI select ARCH_HAS_DEVMEM_IS_ALLOWED select HAVE_ACPI_APEI if ACPI + select HAVE_ACPI_APEI_SEA if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index a60bb00..bfcbb9e 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -7,6 +7,19 @@ config HAVE_ACPI_APEI_NMI config HAVE_ACPI_APEI_HEST_IA32 bool +config HAVE_ACPI_APEI_SEA + bool "APEI Synchronous External Abort logging/recovering support" + help + This option should be enabled if the system supports + firmware first handling of SEA (Synchronous External Abort). + SEA happens with certain faults of data abort or instruction + abort synchronous exceptions on ARMv8 systems. If a system + supports firmware first handling of SEA, the platform analyzes + and handles hardware error notifications with SEA, and it may then + form a HW error record for the OS to parse and handle. This + option allows the OS to look for such HW error record, and + take appropriate action. + config ACPI_APEI bool "ACPI Platform Error Interface (APEI)" select MISC_FILESYSTEMS diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 6c68100..ed64b97 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -50,6 +50,10 @@ #include <acpi/apei.h> #include <asm/tlbflush.h> +#ifdef CONFIG_HAVE_ACPI_APEI_SEA +#include <asm/system_misc.h> +#endif + #include "apei-internal.h" #define GHES_PFX "GHES: " @@ -784,6 +788,62 @@ static struct notifier_block ghes_notifier_sci = { .notifier_call = ghes_notify_sci, }; +#ifdef CONFIG_HAVE_ACPI_APEI_SEA +static LIST_HEAD(ghes_sea); + +static int ghes_notify_sea(struct notifier_block *this, + unsigned long event, void *data) +{ + struct ghes *ghes; + int ret = NOTIFY_DONE; + + rcu_read_lock(); + list_for_each_entry_rcu(ghes, &ghes_sea, list) { + if (!ghes_proc(ghes)) + ret = NOTIFY_OK; + } + rcu_read_unlock(); + + return ret; +} + +static struct notifier_block ghes_notifier_sea = { + .notifier_call = ghes_notify_sea, +}; + +static int ghes_sea_add(struct ghes *ghes) +{ + mutex_lock(&ghes_list_mutex); + if (list_empty(&ghes_sea)) + sea_register_handler_chain(&ghes_notifier_sea); + list_add_rcu(&ghes->list, &ghes_sea); + mutex_unlock(&ghes_list_mutex); + return 0; +} + +static void ghes_sea_remove(struct ghes *ghes) +{ + mutex_lock(&ghes_list_mutex); + list_del_rcu(&ghes->list); + if (list_empty(&ghes_sea)) + sea_unregister_handler_chain(&ghes_notifier_sea); + mutex_unlock(&ghes_list_mutex); +} +#else /* CONFIG_HAVE_ACPI_APEI_SEA */ +static inline int ghes_sea_add(struct ghes *ghes) +{ + pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n", + ghes->generic->header.source_id); + return -ENOTSUPP; +} + +static inline void ghes_sea_remove(struct ghes *ghes) +{ + pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n", + ghes->generic->header.source_id); +} +#endif /* CONFIG_HAVE_ACPI_APEI_SEA */ + #ifdef CONFIG_HAVE_ACPI_APEI_NMI /* * printk is not safe in NMI context. So in NMI handler, we allocate @@ -1028,6 +1088,14 @@ static int ghes_probe(struct platform_device *ghes_dev) case ACPI_HEST_NOTIFY_EXTERNAL: case ACPI_HEST_NOTIFY_SCI: break; + case ACPI_HEST_NOTIFY_SEA: + if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_SEA)) { + pr_warn(GHES_PFX "Generic hardware error source: %d notified via SEA is not supported\n", + generic->header.source_id); + rc = -ENOTSUPP; + goto err; + } + break; case ACPI_HEST_NOTIFY_NMI: if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) { pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n", @@ -1039,6 +1107,13 @@ static int ghes_probe(struct platform_device *ghes_dev) pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n", generic->header.source_id); goto err; + case ACPI_HEST_NOTIFY_GPIO: + case ACPI_HEST_NOTIFY_SEI: + case ACPI_HEST_NOTIFY_GSIV: + pr_warn(GHES_PFX "Generic hardware error source: %d notified via notification type %u is not supported\n", + generic->header.source_id, generic->header.source_id); + rc = -ENOTSUPP; + goto err; default: pr_warning(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n", generic->notify.type, generic->header.source_id); @@ -1093,6 +1168,11 @@ static int ghes_probe(struct platform_device *ghes_dev) list_add_rcu(&ghes->list, &ghes_sci); mutex_unlock(&ghes_list_mutex); break; + case ACPI_HEST_NOTIFY_SEA: + rc = ghes_sea_add(ghes); + if (rc) + goto err_edac_unreg; + break; case ACPI_HEST_NOTIFY_NMI: ghes_nmi_add(ghes); break; @@ -1135,6 +1215,9 @@ static int ghes_remove(struct platform_device *ghes_dev) unregister_acpi_hed_notifier(&ghes_notifier_sci); mutex_unlock(&ghes_list_mutex); break; + case ACPI_HEST_NOTIFY_SEA: + ghes_sea_remove(ghes); + break; case ACPI_HEST_NOTIFY_NMI: ghes_nmi_remove(ghes); break; diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 231ae1e..e5118fb 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -507,7 +507,11 @@ enum acpi_hest_notify_types { ACPI_HEST_NOTIFY_NMI = 4, ACPI_HEST_NOTIFY_CMCI = 5, /* ACPI 5.0 */ ACPI_HEST_NOTIFY_MCE = 6, /* ACPI 5.0 */ - ACPI_HEST_NOTIFY_RESERVED = 7 /* 7 and greater are reserved */ + ACPI_HEST_NOTIFY_GPIO = 7, /* ACPI 5.0 */ + ACPI_HEST_NOTIFY_SEA = 8, /* ACPI 6.x */ + ACPI_HEST_NOTIFY_SEI = 9, /* ACPI 6.x */ + ACPI_HEST_NOTIFY_GSIV = 10, /* ACPI 6.x */ + ACPI_HEST_NOTIFY_RESERVED = 11 /* 11 and greater are reserved */ }; /* Values for config_write_enable bitfield above */