[PATCH v11 4/4] x86: Create a new synthetic cpu capability for machine check recovery

[Tony Luck]

The Intel Software Developer Manual describes bit 24 in the MCG_CAP
MSR:
   MCG_SER_P (software error recovery support present) flag,
   bit 24 â Indicates (when set) that the processor supports
   software error recovery
But only some models with this capability bit set will actually
generate recoverable machine checks.

Check the model name and set a synthetic capability bit. Provide
a command line option to set this bit anyway in case the kernel
doesn't recognise the model name.

Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 Documentation/x86/x86_64/boot-options.txt |  2 ++
 arch/x86/include/asm/cpufeature.h         |  1 +
 arch/x86/include/asm/mce.h                |  1 +
 arch/x86/kernel/cpu/mcheck/mce.c          | 13 +++++++++++++
 4 files changed, 17 insertions(+)

diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 68ed3114c363..0965a71f9942 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -60,6 +60,8 @@ Machine check
 		threshold to 1. Enabling this may make memory predictive failure
 		analysis less effective if the bios sets thresholds for memory
 		errors since we will not see details for all errors.
+   mce=recovery
+		Force-enable recoverable machine check code paths
 
    nomce (for compatibility with i386): same as mce=off
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 7ad8c9464297..06c6c2d2fea0 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -106,6 +106,7 @@
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
 #define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
 #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 2ea4527e462f..18d2ba9c8e44 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -113,6 +113,7 @@ struct mca_config {
 	bool ignore_ce;
 	bool disabled;
 	bool ser;
+	bool recovery;
 	bool bios_cmci_threshold;
 	u8 banks;
 	s8 bootlog;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 905f3070f412..15ff6f07bd92 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1578,6 +1578,17 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
+		/*
+		 * MCG_CAP.MCG_SER_P is necessary but not sufficient to know
+		 * whether this processor will actually generate recoverable
+		 * machine checks. Check to see if this is an E7 model Xeon.
+		 * We can't do a model number check because E5 and E7 use the
+		 * same model number. E5 doesn't support recovery, E7 does.
+		 */
+		if (mca_cfg.recovery || (mca_cfg.ser &&
+			!strncmp(c->x86_model_id,
+				 "Intel(R) Xeon(R) CPU E7-", 24)))
+			set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY);
 	}
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
@@ -2030,6 +2041,8 @@ static int __init mcheck_enable(char *str)
 		cfg->bootlog = (str[0] == 'b');
 	else if (!strcmp(str, "bios_cmci_threshold"))
 		cfg->bios_cmci_threshold = true;
+	else if (!strcmp(str, "recovery"))
+		cfg->recovery = true;
 	else if (isdigit(str[0])) {
 		if (get_option(&str, &cfg->tolerant) == 2)
 			get_option(&str, &(cfg->monarch_timeout));
-- 
2.5.0