ghes, EDAC: Fix ghes_edac registration

Tony reported seeing

  "Internal error: Can't find EDAC structure"

when injecting correctable errors due to the fact that ghes_edac would
still load even if the whitelist won't hit. Drop the pr_err() in
ghes_edac_report_mem_error() for now due to the hacky way how ghes_edac
depends on ghes.c.

While at it, make ghes_edac_register() return an error if it doesn't hit
in the whitelist as it is the only sensible thing to do in that
situation.

Furthermore, move the call to it to happen last in ghes_probe() so that
GHES initializing properly does not depend on ghes_edac init at all
as latter is only reporting errors and not required for GHES's proper
functioning.

Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Tested-by: Sughosh Ganu <sughosh.ganu@arm.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20180420182015.zao3olss4tvvlxki@agluck-desk

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 1efefe919555f7e70aef1e0fea59c94390c21497..88103333ee1b3c6910fa79eab193156a4a2d316a 100644 (file)
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -1087,10 +1087,6 @@ static int ghes_probe(struct platform_device *ghes_dev)
                goto err;
        }
 
-       rc = ghes_edac_register(ghes, &ghes_dev->dev);
-       if (rc < 0)
-               goto err;
-
        switch (generic->notify.type) {
        case ACPI_HEST_NOTIFY_POLLED:
                timer_setup(&ghes->timer, ghes_poll_func, TIMER_DEFERRABLE);
@@ -1102,14 +1098,14 @@ static int ghes_probe(struct platform_device *ghes_dev)
                if (rc) {
                        pr_err(GHES_PFX "Failed to map GSI to IRQ for generic hardware error source: %d\n",
                               generic->header.source_id);
-                       goto err_edac_unreg;
+                       goto err;
                }
                rc = request_irq(ghes->irq, ghes_irq_func, IRQF_SHARED,
                                 "GHES IRQ", ghes);
                if (rc) {
                        pr_err(GHES_PFX "Failed to register IRQ for generic hardware error source: %d\n",
                               generic->header.source_id);
-                       goto err_edac_unreg;
+                       goto err;
                }
                break;
 
@@ -1132,14 +1128,16 @@ static int ghes_probe(struct platform_device *ghes_dev)
        default:
                BUG();
        }
+
        platform_set_drvdata(ghes_dev, ghes);
 
+       ghes_edac_register(ghes, &ghes_dev->dev);
+
        /* Handle any pending errors right away */
        ghes_proc(ghes);
 
        return 0;
-err_edac_unreg:
-       ghes_edac_unregister(ghes);
+
 err:
        if (ghes) {
                ghes_fini(ghes);

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 68b6ee18bea644cb9adfe395424adb48ddfae4f4..7fdbfe871f5c78b3a24296ee05cc4a539bda131c 100644 (file)
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -183,10 +183,8 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
        char *p;
        u8 grain_bits;
 
-       if (!pvt) {
-               pr_err("Internal error: Can't find EDAC structure\n");
+       if (!pvt)
                return;
-       }
 
        /*
         * We can do the locking below because GHES defers error processing
@@ -439,7 +437,7 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
        /* Check if safe to enable on this system */
        idx = acpi_match_platform_list(plat_list);
        if (!force_load && idx < 0)
-               return 0;
+               return -ENODEV;
 
        /*
         * We have only one logical memory controller to which all DIMMs belong.

diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 8feb0c866ee059a65951874f83f5261a4b84501f..4fc92289f7f8a2fe90c109c82848ebab757c6b4e 100644 (file)
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -70,7 +70,7 @@ static inline void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 
 static inline int ghes_edac_register(struct ghes *ghes, struct device *dev)
 {
-       return 0;
+       return -ENODEV;
 }
 
 static inline void ghes_edac_unregister(struct ghes *ghes)