[RFC PATCH 3/4] powerpc/pseries: Dump and flush SLB contents on SLB MCE errors.

Mahesh J Salgaonkar mahesh at linux.vnet.ibm.com
Wed Jun 6 14:37:15 AEST 2018


From: Mahesh Salgaonkar <mahesh at linux.vnet.ibm.com>

If we get a machine check exceptions due to SLB errors then dump the
current SLB contents which will be very much helpful in debugging the
root cause of SLB errors. On pseries, as of today system crashes on SLB
errors. These are soft errors and can be fixed by flushing the SLBs so
the kernel can continue to function instead of system crash. This patch
fixes that also.

With this patch the console will log SLB contents like below on SLB MCE
errors:

[  822.711728] slb contents:
[  822.711730] 00 c000000008000000 400ea1b217000500
[  822.711731]   1T  ESID=   c00000  VSID=      ea1b217 LLP:100
[  822.711732] 01 d000000008000000 400d43642f000510
[  822.711733]   1T  ESID=   d00000  VSID=      d43642f LLP:110
[  822.711734] 09 f000000008000000 400a86c85f000500
[  822.711736]   1T  ESID=   f00000  VSID=      a86c85f LLP:100
[  822.711737] 10 00007f0008000000 400d1f26e3000d90
[  822.711738]   1T  ESID=       7f  VSID=      d1f26e3 LLP:110
[  822.711739] 11 0000000018000000 000e3615f520fd90
[  822.711740]  256M ESID=        1  VSID=   e3615f520f LLP:110
[  822.711740] 12 d000000008000000 400d43642f000510
[  822.711741]   1T  ESID=   d00000  VSID=      d43642f LLP:110
[  822.711742] 13 d000000008000000 400d43642f000510
[  822.711743]   1T  ESID=   d00000  VSID=      d43642f LLP:110


Suggested-by: Aneesh Kumar K.V <aneesh.kumar at linux.vnet.ibm.com>
Suggested-by: Michael Ellerman <mpe at ellerman.id.au>
Signed-off-by: Mahesh Salgaonkar <mahesh at linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/mmu-hash.h |    1 +
 arch/powerpc/mm/slb.c                         |   35 +++++++++++++++++++++++++
 arch/powerpc/platforms/pseries/ras.c          |   29 ++++++++++++++++++++-
 3 files changed, 64 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 50ed64fba4ae..c0da68927235 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -487,6 +487,7 @@ extern void hpte_init_native(void);
 
 extern void slb_initialize(void);
 extern void slb_flush_and_rebolt(void);
+extern void slb_dump_contents(void);
 
 extern void slb_vmalloc_update(void);
 extern void slb_set_size(u16 size);
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 66577cc66dc9..799aa117cec3 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -145,6 +145,41 @@ void slb_flush_and_rebolt(void)
 	get_paca()->slb_cache_ptr = 0;
 }
 
+void slb_dump_contents(void)
+{
+	int i;
+	unsigned long e, v;
+	unsigned long llp;
+
+	pr_err("slb contents:\n");
+	for (i = 0; i < mmu_slb_size; i++) {
+		asm volatile("slbmfee  %0,%1" : "=r" (e) : "r" (i));
+		asm volatile("slbmfev  %0,%1" : "=r" (v) : "r" (i));
+
+		if (!e && !v)
+			continue;
+
+		pr_err("%02d %016lx %016lx", i, e, v);
+
+		if (!(e & SLB_ESID_V)) {
+			pr_err("\n");
+			continue;
+		}
+		llp = v & SLB_VSID_LLP;
+		if (v & SLB_VSID_B_1T) {
+			pr_err("  1T  ESID=%9lx  VSID=%13lx LLP:%3lx\n",
+				GET_ESID_1T(e),
+				(v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T,
+				llp);
+		} else {
+			pr_err(" 256M ESID=%9lx  VSID=%13lx LLP:%3lx\n",
+				GET_ESID(e),
+				(v & ~SLB_VSID_B) >> SLB_VSID_SHIFT,
+				llp);
+		}
+	}
+}
+
 void slb_vmalloc_update(void)
 {
 	unsigned long vflags;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 5e1ef9150182..7470a216cd6b 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -422,6 +422,31 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 	return 0; /* need to perform reset */
 }
 
+static int mce_handle_error(struct rtas_error_log *errp)
+{
+	struct pseries_errorlog *pseries_log;
+	struct pseries_mc_errorlog *mce_log;
+	int disposition = rtas_error_disposition(errp);
+	uint8_t error_type;
+
+	pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
+	if (pseries_log == NULL)
+		goto out;
+
+	mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
+	error_type = rtas_mc_error_type(mce_log);
+
+	if ((disposition == RTAS_DISP_NOT_RECOVERED) &&
+			(error_type == PSERIES_MC_ERROR_TYPE_SLB)) {
+		slb_dump_contents();
+		slb_flush_and_rebolt();
+		disposition = RTAS_DISP_FULLY_RECOVERED;
+	}
+
+out:
+	return disposition;
+}
+
 /*
  * See if we can recover from a machine check exception.
  * This is only called on power4 (or above) and only via
@@ -434,7 +459,9 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
 {
 	int recovered = 0;
-	int disposition = rtas_error_disposition(err);
+	int disposition;
+
+	disposition = mce_handle_error(err);
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */



More information about the Linuxppc-dev mailing list