| Message ID | 52657a78162905670f@agluck-desk.sc.intel.com (mailing list archive) |
|---|---|
| State | Not Applicable, archived |
| Headers | show |
On Mon, Oct 21, 2013 at 12:03 PM, Luck, Tony <tony.luck@intel.com> wrote: > So this is on top of the 9 patch series (using the V4 that Chen Gong > posted for part 4/9 and V3 for all the others). Obviously it should > be folded back into the series if we go this way. > > It's a bit simplistic right now - the registered function just returns > NOTIFY_DONE in all cases so it will not disturb processing by any other > registered functions - we can make it smarter later. I folded that back into the series. Also switched out the test on whether to print the "No further action is required" message to only do so for corrected errors. Cleaned up some of the commit messages, The result is sitting at: git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git eMCA Anything we missed? -Tony -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Oct 21, 2013 at 03:39:20PM -0700, Tony Luck wrote: > I folded that back into the series. Also switched out the test on > whether to print the "No further action is required" message to only > do so for corrected errors. Cleaned up some of the commit messages, > > The result is sitting at: > git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git eMCA > > Anything we missed? Doesn't look so, at a first glance. But I agree with you - this stuff will be subject to change as we go along and we make up our mind about what exactly is sufficient and necessary to do proper decoding. I like the idea of keeping an open mind about it. :-) Thanks. -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 10/22/2013 12:33 AM, Luck, Tony wrote: >> But yes, this is possible and it would make it all even cleaner >> and simpler by simply not needing the reg/dereg interfaces for >> mce_ext_err_print but adding it to the chain. > > So this is on top of the 9 patch series (using the V4 that Chen Gong > posted for part 4/9 and V3 for all the others). Obviously it should > be folded back into the series if we go this way. > > It's a bit simplistic right now - the registered function just returns > NOTIFY_DONE in all cases so it will not disturb processing by any other > registered functions - we can make it smarter later. Looks good. We obviously need to ensure this gets called before EDAC, if at all. The other question is w.r.t conflicts with EDAC, which we can re-visit as part of the discussions around a new trace event. Thanks, Naveen -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 072b2f80a345..8b8e72522737 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -188,9 +188,6 @@ enum mcp_flags { MCP_DONTLOG = (1 << 2), /* only clear, don't log */ }; -void register_elog_handler(int (*f)(const char *, int, int)); -void unregister_elog_handler(int (*f)(const char *, int, int)); - void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); int mce_notify_irq(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 981e0d3ed49d..b3218cdee95f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -48,8 +48,6 @@ #include "mce-internal.h" -static int (*mce_ext_err_print)(const char *, int, int); - static DEFINE_MUTEX(mce_chrdev_read_mutex); #define rcu_dereference_check_mce(p) \ @@ -578,21 +576,6 @@ static void mce_read_aux(struct mce *m, int i) DEFINE_PER_CPU(unsigned, mce_poll_count); -void register_elog_handler(int (*f)(const char *, int, int)) -{ - mce_ext_err_print = f; -} -EXPORT_SYMBOL_GPL(register_elog_handler); - -void unregister_elog_handler(int (*f)(const char *, int, int)) -{ - if (f) { - WARN_ON(mce_ext_err_print != f); - mce_ext_err_print = NULL; - } -} -EXPORT_SYMBOL_GPL(unregister_elog_handler); - /* * Poll for corrected events or events that happened before reset. * Those are just logged through /dev/mcelog. @@ -641,9 +624,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; - if (mce_ext_err_print) - mce_ext_err_print(NULL, m.extcpu, i); - mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 1bc657d3d053..eb0d7792ecc1 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -130,22 +130,26 @@ static int print_extlog_rcd(const char *pfx, return 1; } -static int extlog_print(const char *pfx, int cpu, int bank) +static int extlog_print(struct notifier_block *nb, unsigned long val, + void *data) { + struct mce *mce = (struct mce *)data; + int bank = mce->bank; + int cpu = mce->extcpu; struct acpi_generic_status *estatus; int rc; estatus = extlog_elog_entry_check(cpu, bank); if (estatus == NULL) - return -EINVAL; + return NOTIFY_DONE; memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN); /* clear record status to enable BIOS to update it again */ estatus->block_status = 0; - rc = print_extlog_rcd(pfx, (struct acpi_generic_status *)elog_buf, cpu); + rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu); - return rc; + return NOTIFY_DONE; } static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret) @@ -213,6 +217,9 @@ static bool extlog_get_l1addr(void) return true; } +static struct notifier_block extlog_mce_dec = { + .notifier_call = extlog_print, +}; static int __init extlog_init(void) { @@ -279,7 +286,7 @@ static int __init extlog_init(void) if (elog_buf == NULL) goto err_release_elog; - register_elog_handler(extlog_print); + mce_register_decode_chain(&extlog_mce_dec); /* enable OS to be involved to take over management from BIOS */ ((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN; @@ -300,7 +307,7 @@ err: static void __exit extlog_exit(void) { - unregister_elog_handler(extlog_print); + mce_unregister_decode_chain(&extlog_mce_dec); ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; if (extlog_l1_addr) acpi_os_unmap_memory(extlog_l1_addr, l1_size);