2 files changed, 44 insertions, 8 deletions
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 2db5893d6c97..29a6ff8bc7d3 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -5,21 +5,51 @@ only the AMD64 specific ones are listed here.
 Machine check
-   mce=off disable machine check
+   Please see Documentation/x86/x86_64/machinecheck for sysfs runtime tunables.
-   mce=bootlog Enable logging of machine checks left over from booting.
-               Disabled by default on AMD because some BIOS leave bogus ones.
+   mce=off
-               If your BIOS doesn't do that it's a good idea to enable though
+                Disable machine check
-               to make sure you log even machine check events that result
+   mce=no_cmci
-               in a reboot. On Intel systems it is enabled by default.
+                Disable CMCI(Corrected Machine Check Interrupt) that
+                Intel processor supports.  Usually this disablement is
+                not recommended, but it might be handy if your hardware
+                is misbehaving.
+                Note that you'll get more problems without CMCI than with
+                due to the shared banks, i.e. you might get duplicated
+                error logs.
+   mce=dont_log_ce
+                Don't make logs for corrected errors.  All events reported
+                as corrected are silently cleared by OS.
+                This option will be useful if you have no interest in any
+                of corrected errors.
+   mce=ignore_ce
+                Disable features for corrected errors, e.g. polling timer
+                and CMCI.  All events reported as corrected are not cleared
+                by OS and remained in its error banks.
+                Usually this disablement is not recommended, however if
+                there is an agent checking/clearing corrected errors
+                (e.g. BIOS or hardware monitoring applications), conflicting
+                with OS's error handling, and you cannot deactivate the agent,
+                then this option will be a help.
+   mce=bootlog
+                Enable logging of machine checks left over from booting.
+                Disabled by default on AMD because some BIOS leave bogus ones.
+                If your BIOS doesn't do that it's a good idea to enable though
+                to make sure you log even machine check events that result
+                in a reboot. On Intel systems it is enabled by default.
   mce=nobootlog
                Disable boot machine check logging.
-   mce=tolerancelevel (number)
+   mce=tolerancelevel[,monarchtimeout] (number,number)
+                tolerance levels:
                0: always panic on uncorrected errors, log corrected errors
                1: panic or SIGBUS on uncorrected errors, log corrected errors
                2: SIGBUS or log uncorrected errors, log corrected errors
                3: never panic or SIGBUS, log all errors (for testing only)
                Default is 1
                Can be also set using sysfs which is preferable.
+                monarchtimeout:
+                Sets the time in us to wait for other CPUs on machine checks. 0
+                to disable.
   nomce (for compatibility with i386): same as mce=off
diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck
index a05e58e7b159..b1fb30273286 100644
--- a/Documentation/x86/x86_64/machinecheck
+++ b/Documentation/x86/x86_64/machinecheck
@@ -41,7 +41,9 @@ check_interval
        the polling interval.  When the poller stops finding MCEs, it
        triggers an exponential backoff (poll less often) on the polling
        interval. The check_interval variable is both the initial and
-        maximum polling interval.
+        maximum polling interval. 0 means no polling for corrected machine
+        check errors (but some corrected errors might be still reported
+        in other ways)
 tolerant
        Tolerance level. When a machine check exception occurs for a non
@@ -67,6 +69,10 @@ trigger
        Program to run when a machine check event is detected.
        This is an alternative to running mcelog regularly from cron
        and allows to detect events faster.
+monarch_timeout
+        How long to wait for the other CPUs to machine check too on a
+        exception. 0 to disable waiting for other CPUs.
+        Unit: us
 TBD document entries for AMD threshold interrupt configuration

diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index 2db5893d6c97..29a6ff8bc7d3 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt
@@ -5,21 +5,51 @@ only the AMD64 specific ones are listed here.
5		5
6	Machine check	6	Machine check
7		7
8	mce=off disable machine check	8	Please see Documentation/x86/x86_64/machinecheck for sysfs runtime tunables.
9	mce=bootlog Enable logging of machine checks left over from booting.	9
10	Disabled by default on AMD because some BIOS leave bogus ones.	10	mce=off
11	If your BIOS doesn't do that it's a good idea to enable though	11	Disable machine check
12	to make sure you log even machine check events that result	12	mce=no_cmci
13	in a reboot. On Intel systems it is enabled by default.	13	Disable CMCI(Corrected Machine Check Interrupt) that
		14	Intel processor supports. Usually this disablement is
		15	not recommended, but it might be handy if your hardware
		16	is misbehaving.
		17	Note that you'll get more problems without CMCI than with
		18	due to the shared banks, i.e. you might get duplicated
		19	error logs.
		20	mce=dont_log_ce
		21	Don't make logs for corrected errors. All events reported
		22	as corrected are silently cleared by OS.
		23	This option will be useful if you have no interest in any
		24	of corrected errors.
		25	mce=ignore_ce
		26	Disable features for corrected errors, e.g. polling timer
		27	and CMCI. All events reported as corrected are not cleared
		28	by OS and remained in its error banks.
		29	Usually this disablement is not recommended, however if
		30	there is an agent checking/clearing corrected errors
		31	(e.g. BIOS or hardware monitoring applications), conflicting
		32	with OS's error handling, and you cannot deactivate the agent,
		33	then this option will be a help.
		34	mce=bootlog
		35	Enable logging of machine checks left over from booting.
		36	Disabled by default on AMD because some BIOS leave bogus ones.
		37	If your BIOS doesn't do that it's a good idea to enable though
		38	to make sure you log even machine check events that result
		39	in a reboot. On Intel systems it is enabled by default.
14	mce=nobootlog	40	mce=nobootlog
15	Disable boot machine check logging.	41	Disable boot machine check logging.
16	mce=tolerancelevel (number)	42	mce=tolerancelevel[,monarchtimeout] (number,number)
		43	tolerance levels:
17	0: always panic on uncorrected errors, log corrected errors	44	0: always panic on uncorrected errors, log corrected errors
18	1: panic or SIGBUS on uncorrected errors, log corrected errors	45	1: panic or SIGBUS on uncorrected errors, log corrected errors
19	2: SIGBUS or log uncorrected errors, log corrected errors	46	2: SIGBUS or log uncorrected errors, log corrected errors
20	3: never panic or SIGBUS, log all errors (for testing only)	47	3: never panic or SIGBUS, log all errors (for testing only)
21	Default is 1	48	Default is 1
22	Can be also set using sysfs which is preferable.	49	Can be also set using sysfs which is preferable.
		50	monarchtimeout:
		51	Sets the time in us to wait for other CPUs on machine checks. 0
		52	to disable.
23		53
24	nomce (for compatibility with i386): same as mce=off	54	nomce (for compatibility with i386): same as mce=off
25		55


diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck index a05e58e7b159..b1fb30273286 100644 --- a/Documentation/x86/x86_64/machinecheck +++ b/Documentation/x86/x86_64/machinecheck
@@ -41,7 +41,9 @@ check_interval
41	the polling interval. When the poller stops finding MCEs, it	41	the polling interval. When the poller stops finding MCEs, it
42	triggers an exponential backoff (poll less often) on the polling	42	triggers an exponential backoff (poll less often) on the polling
43	interval. The check_interval variable is both the initial and	43	interval. The check_interval variable is both the initial and
44	maximum polling interval.	44	maximum polling interval. 0 means no polling for corrected machine
		45	check errors (but some corrected errors might be still reported
		46	in other ways)
45		47
46	tolerant	48	tolerant
47	Tolerance level. When a machine check exception occurs for a non	49	Tolerance level. When a machine check exception occurs for a non
@@ -67,6 +69,10 @@ trigger
67	Program to run when a machine check event is detected.	69	Program to run when a machine check event is detected.
68	This is an alternative to running mcelog regularly from cron	70	This is an alternative to running mcelog regularly from cron
69	and allows to detect events faster.	71	and allows to detect events faster.
		72	monarch_timeout
		73	How long to wait for the other CPUs to machine check too on a
		74	exception. 0 to disable waiting for other CPUs.
		75	Unit: us
70		76
71	TBD document entries for AMD threshold interrupt configuration	77	TBD document entries for AMD threshold interrupt configuration
72		78