Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1481011

[PATCH 11/15] x86/mce/AMD: Save MCA_IPID in MCE struct on SMCA systems

From Borislav Petkov <bp@alien8.de>
Newsgroups linux.kernel
Subject [PATCH 11/15] x86/mce/AMD: Save MCA_IPID in MCE struct on SMCA systems
Date 2016-09-12 10:10 +0200
Message-ID <sguts-Fd-27@gated-at.bofh.it> (permalink)
References <sgujL-mJ-11@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


From: Yazen Ghannam <Yazen.Ghannam@amd.com>

The MCA_IPID register uniquely identifies a bank's type and instance
on Scalable MCA systems. We should save the value of this register
in struct mce along with the other relevant error information. This
ensures that we can decode errors without relying on system software to
correlate the bank to the type.

Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com>
Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: x86-ml <x86@kernel.org>
Link: http://lkml.kernel.org/r/1472680624-34221-1-git-send-email-Yazen.Ghannam@amd.com
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 arch/x86/include/uapi/asm/mce.h      | 1 +
 arch/x86/kernel/cpu/mcheck/mce.c     | 8 ++++++--
 arch/x86/kernel/cpu/mcheck/mce_amd.c | 8 ++++++--
 include/trace/events/mce.h           | 5 ++++-
 4 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 8c75fbc94c3f..69a6e07e3149 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -27,6 +27,7 @@ struct mce {
 	__u32 apicid;	/* CPU initial apic ID */
 	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
 	__u64 synd;	/* MCA_SYND MSR: only valid on SMCA systems */
+	__u64 ipid;	/* MCA_IPID MSR: only valid on SMCA systems */
 };
 
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7f11ea5b75fa..84cb9b5859e2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -582,8 +582,12 @@ static void mce_read_aux(struct mce *m, int i)
 		}
 	}
 
-	if (mce_flags.smca && (m->status & MCI_STATUS_SYNDV))
-		m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
+	if (mce_flags.smca) {
+		m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+
+		if (m->status & MCI_STATUS_SYNDV)
+			m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
+	}
 }
 
 static bool memory_error(struct mce *m)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 16766e09c2b7..d2f92ab5322f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -564,8 +564,12 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
 	if (m.status & MCI_STATUS_ADDRV)
 		rdmsrl(msr_addr, m.addr);
 
-	if (mce_flags.smca && (m.status & MCI_STATUS_SYNDV))
-		rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd);
+	if (mce_flags.smca) {
+		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid);
+
+		if (m.status & MCI_STATUS_SYNDV)
+			rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd);
+	}
 
 	mce_log(&m);
 
diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 8be5268caf28..70f02149808c 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -21,6 +21,7 @@ TRACE_EVENT(mce_record,
 		__field(	u64,		addr		)
 		__field(	u64,		misc		)
 		__field(	u64,		synd		)
+		__field(	u64,		ipid		)
 		__field(	u64,		ip		)
 		__field(	u64,		tsc		)
 		__field(	u64,		walltime	)
@@ -40,6 +41,7 @@ TRACE_EVENT(mce_record,
 		__entry->addr		= m->addr;
 		__entry->misc		= m->misc;
 		__entry->synd		= m->synd;
+		__entry->ipid		= m->ipid;
 		__entry->ip		= m->ip;
 		__entry->tsc		= m->tsc;
 		__entry->walltime	= m->time;
@@ -52,10 +54,11 @@ TRACE_EVENT(mce_record,
 		__entry->cpuvendor	= m->cpuvendor;
 	),
 
-	TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, ADDR/MISC/SYND: %016Lx/%016Lx/%016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PROCESSOR: %u:%x, TIME: %llu, SOCKET: %u, APIC: %x",
+	TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, IPID: %016Lx, ADDR/MISC/SYND: %016Lx/%016Lx/%016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PROCESSOR: %u:%x, TIME: %llu, SOCKET: %u, APIC: %x",
 		__entry->cpu,
 		__entry->mcgcap, __entry->mcgstatus,
 		__entry->bank, __entry->status,
+		__entry->ipid,
 		__entry->addr, __entry->misc, __entry->synd,
 		__entry->cs, __entry->ip,
 		__entry->tsc,
-- 
2.10.0

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH 00/15] x86/RAS queue for 4.9 Borislav Petkov <bp@alien8.de> - 2016-09-12 10:00 +0200
  [PATCH 13/15] x86/mce/AMD: Extract the error address on SMCA systems Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 15/15] x86/RAS/mce_amd_inj: Fix some W= warnings Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
    [tip:ras/core] x86/RAS/mce_amd_inj: Fix some W= warnings tip-bot for Borislav Petkov <tipbot@zytor.com> - 2016-09-13 15:40 +0200
  [PATCH 04/15] x86/RAS: Add syndrome support to mce_amd_inj Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 09/15] x86/mce/AMD: Update sysfs bank names for SMCA systems Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 07/15] EDAC/mce_amd: Use SMCA prefix for error descriptions arrays Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 10/15] x86/mce/AMD: Ensure the deferred error interrupt is of type APIC on SMCA systems Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 01/15] x86/mce/AMD: Use msr_ops.misc() in allocate_threshold_blocks() Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 06/15] EDAC/mce_amd: Add missing SMCA error descriptions Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 11/15] x86/mce/AMD: Save MCA_IPID in MCE struct on SMCA systems Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 03/15] EDAC/mce_amd: Print syndrome register value on SMCA systems Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 14/15] x86/MCE/AMD, EDAC: Handle reserved bank 4 on Fam17h properly Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 12/15] x86/mce, EDAC/mce_amd: Print MCA_SYND and MCA_IPID during MCE on SMCA systems Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 05/15] x86/mce/AMD: Read MSRs on the CPU allocating the threshold blocks Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 02/15] x86/mce: Add support for new MCA_SYND register Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200
  [PATCH 08/15] x86/mce/AMD, EDAC/mce_amd: Define and use tables for known SMCA IP types Borislav Petkov <bp@alien8.de> - 2016-09-12 10:10 +0200

csiph-web