Merge branch 'x86/mce' into x86/ras

Pursue a single RAS/MCE topic branch on x86.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 67 insertions, 9 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ec9b57d428a1..8ec37bbdd699 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -409,6 +409,34 @@ static void ghes_clear_estatus(struct ghes *ghes)
         ghes->flags &= ~GHES_TO_CLEAR;
 }
 
+static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev)
+{
+#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
+        unsigned long pfn;
+        int sec_sev = ghes_severity(gdata->error_severity);
+        struct cper_sec_mem_err *mem_err;
+        mem_err = (struct cper_sec_mem_err *)(gdata + 1);
+
+        if (sec_sev == GHES_SEV_CORRECTED &&
+            (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
+            (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) {
+                pfn = mem_err->physical_addr >> PAGE_SHIFT;
+                if (pfn_valid(pfn))
+                        memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
+                else if (printk_ratelimit())
+                        pr_warn(FW_WARN GHES_PFX
+                        "Invalid address in generic error data: %#llx\n",
+                        mem_err->physical_addr);
+        }
+        if (sev == GHES_SEV_RECOVERABLE &&
+            sec_sev == GHES_SEV_RECOVERABLE &&
+            mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+                pfn = mem_err->physical_addr >> PAGE_SHIFT;
+                memory_failure_queue(pfn, 0, 0);
+        }
+#endif
+}
+
 static void ghes_do_proc(struct ghes *ghes,
                          const struct acpi_hest_generic_status *estatus)
 {
@@ -428,15 +456,7 @@ static void ghes_do_proc(struct ghes *ghes,
                         apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED,
                                                   mem_err);
 #endif
-#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
-                        if (sev == GHES_SEV_RECOVERABLE &&
-                            sec_sev == GHES_SEV_RECOVERABLE &&
-                            mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
-                                unsigned long pfn;
-                                pfn = mem_err->physical_addr >> PAGE_SHIFT;
-                                memory_failure_queue(pfn, 0, 0);
-                        }
-#endif
+                        ghes_handle_memory_failure(gdata, sev);
                 }
 #ifdef CONFIG_ACPI_APEI_PCIEAER
                 else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index f5ef5d54e4ac..502024502b13 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -36,6 +36,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <acpi/apei.h>
+#include <asm/mce.h>
 
 #include "apei-internal.h"
 
@@ -121,6 +122,40 @@ int apei_hest_parse(apei_hest_func_t func, void *data)
 }
 EXPORT_SYMBOL_GPL(apei_hest_parse);
 
+/*
+ * Check if firmware advertises firmware first mode. We need FF bit to be set
+ * along with a set of MC banks which work in FF mode.
+ */
+static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data)
+{
+        int i;
+        struct acpi_hest_ia_corrected *cmc;
+        struct acpi_hest_ia_error_bank *mc_bank;
+
+        if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
+                return 0;
+
+        cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
+        if (!cmc->enabled)
+                return 0;
+
+        /*
+         * We expect HEST to provide a list of MC banks that report errors
+         * in firmware first mode. Otherwise, return non-zero value to
+         * indicate that we are done parsing HEST.
+         */
+        if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks)
+                return 1;
+
+        pr_info(HEST_PFX "Enabling Firmware First mode for corrected errors.\n");
+
+        mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
+        for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
+                mce_disable_bank(mc_bank->bank_number);
+
+        return 1;
+}
+
 struct ghes_arr {
         struct platform_device **ghes_devs;
         unsigned int count;
@@ -227,6 +262,9 @@ void __init acpi_hest_init(void)
                 goto err;
         }
 
+        if (!acpi_disable_cmcff)
+                apei_hest_parse(hest_parse_cmc, NULL);
+
         if (!ghes_disable) {
                 rc = apei_hest_parse(hest_parse_ghes_count, &ghes_count);
                 if (rc)