Skip to contentSkip to conversation

x86/mce: Add Zhaoxin MCE support

PATCH Superseded Tony W Wang-oc 2 participants 3 messages Sep 10, 2019 – Sep 11, 2019

Subsystems (3)

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/4 x86/mce: Add Zhaoxin MCE support

All Zhaoxin newer CPUs support MCE that compatible with Intel's "Machine-Check Architecture", so add support for Zhaoxin MCE in mce/core.c.

---
 arch/x86/kernel/cpu/mce/core.c | 30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)
arch/x86/kernel/cpu/mce/core.c +24 -6
index 743370e..3f878f6 100644
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
-	/* Checks after this one are Intel-specific: */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	/* Checks after this one are Intel/Zhaoxin-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 1;
 
 	if (!(m->status & MCI_STATUS_MISCV))
@@ -510,7 +511,8 @@ bool mce_is_memory_error(struct mce *m)
 	if (m->cpuvendor == X86_VENDOR_AMD ||
 	    m->cpuvendor == X86_VENDOR_HYGON) {
 		return amd_mce_is_memory_error(m);
-	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
+	} else if (m->cpuvendor == X86_VENDOR_INTEL ||
+		   m->cpuvendor == X86_VENDOR_ZHAOXIN) {
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *
@@ -1697,6 +1699,21 @@ 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;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+		 * synchronization with a one second timeout.
+		 */
+		if ((c->x86 == 6 && c->x86_model == 0x19 &&
+			(c->x86_stepping > 3 && c->x86_stepping < 8)) ||
+		    (c->x86 == 6 && c->x86_model == 0x1f) ||
+		     c->x86 > 6) {
+			if (cfg->monarch_timeout < 0)
+				cfg->monarch_timeout = USEC_PER_SEC;
+		}
+	}
+
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
 	if (cfg->bootlog != 0)
@@ -2014,15 +2031,16 @@ static void mce_disable_error_reporting(void)
 static void vendor_disable_error_reporting(void)
 {
 	/*
-	 * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
-	 * are socket-wide.
+	 * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these
+	 * MSRs are socket-wide.
 	 * Disabling them for just a single offlined CPU is bad, since it will
 	 * inhibit reporting for all shared resources on the socket like the
 	 * last level cache (LLC), the integrated memory controller (iMC), etc.
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN)
 		return;
 
 	mce_disable_error_reporting();
Signature · 1 line
2.7.4
maintainer
#1 lore raw
Quoted 26 lines · Tony W Wang-oc

All Zhaoxin newer CPUs support MCE that compatible with Intel's "Machine-Check Architecture", so add support for Zhaoxin MCE in mce/core.c.

---
 arch/x86/kernel/cpu/mce/core.c | 30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)
arch/x86/kernel/cpu/mce/core.c +3 -2
index 743370e..3f878f6 100644
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
-	/* Checks after this one are Intel-specific: */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	/* Checks after this one are Intel/Zhaoxin-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 1;
 
 	if (!(m->status & MCI_STATUS_MISCV))

arch/x86/kernel/cpu/mce/core.c bool mce_is_memory_error(struct mce *m) · line 518

Quoted 9 lines
arch/x86/kernel/cpu/mce/core.c +2 -1
@@ -510,7 +511,8 @@ bool mce_is_memory_error(struct mce *m)
 	if (m->cpuvendor == X86_VENDOR_AMD ||
 	    m->cpuvendor == X86_VENDOR_HYGON) {
 		return amd_mce_is_memory_error(m);
-	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
+	} else if (m->cpuvendor == X86_VENDOR_INTEL ||
+		   m->cpuvendor == X86_VENDOR_ZHAOXIN) {
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *

Make that a switch-case for better readability pls.

Quoted 4 lines
arch/x86/kernel/cpu/mce/core.c +0 -0
@@ -1697,6 +1699,21 @@ 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;
 	}

arch/x86/kernel/cpu/mce/core.c static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) · line 1711

Quoted 10 lines
arch/x86/kernel/cpu/mce/core.c +10 -0
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+		 * synchronization with a one second timeout.
+		 */
+		if ((c->x86 == 6 && c->x86_model == 0x19 &&
+			(c->x86_stepping > 3 && c->x86_stepping < 8)) ||
+		    (c->x86 == 6 && c->x86_model == 0x1f) ||
+		     c->x86 > 6) {

Can this be simplified into maybe something like this:

	if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f))

this is, of course, assuming that Zhaoxin doesn't do family < 6 and that the other steppings for model 0x19 don't matter because they don't exist or so...

Signature · 4 lines
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette
#2 lore raw
Quoted 25 lines · Borislav Petkov
Quoted 24 lines · Tony W Wang-oc

All Zhaoxin newer CPUs support MCE that compatible with Intel's "Machine-Check Architecture", so add support for Zhaoxin MCE in mce/core.c.

---
 arch/x86/kernel/cpu/mce/core.c | 30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)
arch/x86/kernel/cpu/mce/core.c +3 -2
index 743370e..3f878f6 100644
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
-	/* Checks after this one are Intel-specific: */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	/* Checks after this one are Intel/Zhaoxin-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 1;
 
Quoted 13 lines

arch/x86/kernel/cpu/mce/core.c bool mce_is_memory_error(struct mce *m) · line 518

Quoted 11 lines
arch/x86/kernel/cpu/mce/core.c +2 -1
 	if (!(m->status & MCI_STATUS_MISCV))
@@ -510,7 +511,8 @@ bool mce_is_memory_error(struct mce *m)
 	if (m->cpuvendor == X86_VENDOR_AMD ||
 	    m->cpuvendor == X86_VENDOR_HYGON) {
 		return amd_mce_is_memory_error(m);
-	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
+	} else if (m->cpuvendor == X86_VENDOR_INTEL ||
+		   m->cpuvendor == X86_VENDOR_ZHAOXIN) {
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *

Make that a switch-case for better readability pls.

Ok.

Quoted 19 lines

arch/x86/kernel/cpu/mce/core.c static int __mcheck_cpu_apply_quirks(struct

Quoted 2 lines
arch/x86/kernel/cpu/mce/core.c +0 -0
@@ -1697,6 +1699,21 @@ static int __mcheck_cpu_apply_quirks(struct

cpuinfo_x86 *c)

arch/x86/kernel/cpu/mce/core.c static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) · line 1711

Quoted 13 lines
arch/x86/kernel/cpu/mce/core.c +10 -0
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+		 * synchronization with a one second timeout.
+		 */
+		if ((c->x86 == 6 && c->x86_model == 0x19 &&
+			(c->x86_stepping > 3 && c->x86_stepping < 8)) ||
+		    (c->x86 == 6 && c->x86_model == 0x1f) ||
+		     c->x86 > 6) {

Can this be simplified into maybe something like this:

Quoted 6 lines
	if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f))

this is, of course, assuming that Zhaoxin doesn't do family < 6 and that the other steppings for model 0x19 don't matter because they don't exist or so...

Yes, Zhaoxin doesn't do family<6, and the other steppings for model 0x19 doesn't have MCA. So will simplified like this:
if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f))

Sincerely
TonyWWang-oc