powerpc/eeh: Dump PHB diag-data early

On PowerNV platform, PHB diag-data is dumped after stopping device
drivers. In case of recursive EEH errors, the kernel is usually
crashed before dumping PHB diag-data for the second EEH error. It's
hard to locate the root cause of the second EEH error without PHB
diag-data.

The patch adds one more EEH option "eeh=early_log", which helps
dumping PHB diag-data immediately once frozen PE is detected, in
order to get the PHB diag-data for the second EEH error.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

3 files changed, 15 insertions, 1 deletions

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 2e633b41712a..0652ebe117af 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -39,6 +39,7 @@ struct device_node;
 #define EEH_PROBE_MODE_DEV      0x04    /* From PCI device      */
 #define EEH_PROBE_MODE_DEVTREE  0x08    /* From device tree     */
 #define EEH_ENABLE_IO_FOR_LOG   0x10    /* Enable IO for log    */
+#define EEH_EARLY_DUMP_LOG      0x20    /* Dump log immediately */
 
 /*
  * Delay for PE reset, all in ms
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index f1c6b115cb37..05be77d9ea0e 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -143,6 +143,8 @@ static int __init eeh_setup(char *str)
 {
         if (!strcmp(str, "off"))
                 eeh_add_flag(EEH_FORCE_DISABLED);
+        else if (!strcmp(str, "early_log"))
+                eeh_add_flag(EEH_EARLY_DUMP_LOG);
 
         return 1;
 }
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index fb38fe4dba89..2809c9895288 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -353,6 +353,9 @@ static int ioda_eeh_get_phb_state(struct eeh_pe *pe)
         } else if (!(pe->state & EEH_PE_ISOLATED)) {
                 eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
                 ioda_eeh_phb_diag(pe);
+
+                if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+                        pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
         }
 
         return result;
@@ -451,6 +454,9 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 
                 eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
                 ioda_eeh_phb_diag(pe);
+
+                if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+                        pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
         }
 
         return result;
@@ -730,7 +736,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
                             char *drv_log, unsigned long len)
 {
-        pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+        if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
+                pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
         return 0;
 }
@@ -1086,6 +1093,10 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
                     !((*pe)->state & EEH_PE_ISOLATED)) {
                         eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
                         ioda_eeh_phb_diag(*pe);
+
+                        if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+                                pnv_pci_dump_phb_diag_data((*pe)->phb,
+                                                           (*pe)->data);
                 }
 
                 /*