Merge branch 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS changes from Ingo Molnar:
 "[ The reason for drivers/ updates is that Boris asked for the
    drivers/edac/ changes to go via x86/ras in this cycle ]

  Main changes:

   - AMD CPUs:
      . Add ECC event decoding support for new F15h models
      . Various erratum fixes
      . Fix single-channel on dual-channel-controllers bug.

   - Intel CPUs:
      . UC uncorrectable memory error parsing fix
      . Add support for CMC (Corrected Machine Check) 'FF' (Firmware
        First) flag in the APEI HEST

   - Various cleanups and fixes"

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  amd64_edac: Fix incorrect wraparounds
  amd64_edac: Correct erratum 505 range
  cpc925_edac: Use proper array termination
  x86/mce, acpi/apei: Only disable banks listed in HEST if mce is configured
  amd64_edac: Get rid of boot_cpu_data accesses
  amd64_edac: Add ECC decoding support for newer F15h models
  x86, amd_nb: Clarify F15h, model 30h GART and L3 support
  pci_ids: Add PCI device ID functions 3 and 4 for newer F15h models.
  x38_edac: Make a local function static
  i3200_edac: Make a local function static
  x86/mce: Pay no attention to 'F' bit in MCACOD when parsing 'UC' errors
  APEI/ERST: Fix error message formatting
  amd64_edac: Fix single-channel setups
  EDAC: Replace strict_strtol() with kstrtol()
  mce: acpi/apei: Soft-offline a page on firmware GHES notification
  mce: acpi/apei: Add a boot option to disable ff mode for corrected errors
  mce: acpi/apei: Honour Firmware First for MCA banks listed in APEI HEST CMC

3 files changed, 91 insertions, 37 deletions

diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 822b1ed3b00f..26311f23c824 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -39,7 +39,8 @@
 
 #include "apei-internal.h"
 
-#define ERST_PFX "ERST: "
+#undef pr_fmt
+#define pr_fmt(fmt) "ERST: " fmt
 
 /* ERST command status */
 #define ERST_STATUS_SUCCESS                     0x0
@@ -109,8 +110,7 @@ static inline int erst_errno(int command_status)
 static int erst_timedout(u64 *t, u64 spin_unit)
 {
         if ((s64)*t < spin_unit) {
-                pr_warning(FW_WARN ERST_PFX
-                           "Firmware does not respond in time\n");
+                pr_warn(FW_WARN "Firmware does not respond in time.\n");
                 return 1;
         }
         *t -= spin_unit;
@@ -186,8 +186,8 @@ static int erst_exec_stall(struct apei_exec_context *ctx,
 
         if (ctx->value > FIRMWARE_MAX_STALL) {
                 if (!in_nmi())
-                        pr_warning(FW_WARN ERST_PFX
-                        "Too long stall time for stall instruction: %llx.\n",
+                        pr_warn(FW_WARN
+                        "Too long stall time for stall instruction: 0x%llx.\n",
                                    ctx->value);
                 stall_time = FIRMWARE_MAX_STALL;
         } else
@@ -206,8 +206,8 @@ static int erst_exec_stall_while_true(struct apei_exec_context *ctx,
 
         if (ctx->var1 > FIRMWARE_MAX_STALL) {
                 if (!in_nmi())
-                        pr_warning(FW_WARN ERST_PFX
-                "Too long stall time for stall while true instruction: %llx.\n",
+                        pr_warn(FW_WARN
+                "Too long stall time for stall while true instruction: 0x%llx.\n",
                                    ctx->var1);
                 stall_time = FIRMWARE_MAX_STALL;
         } else
@@ -271,8 +271,7 @@ static int erst_exec_move_data(struct apei_exec_context *ctx,
 
         /* ioremap does not work in interrupt context */
         if (in_interrupt()) {
-                pr_warning(ERST_PFX
-                           "MOVE_DATA can not be used in interrupt context");
+                pr_warn("MOVE_DATA can not be used in interrupt context.\n");
                 return -EBUSY;
         }
 
@@ -524,8 +523,7 @@ retry:
                                      ERST_RECORD_ID_CACHE_SIZE_MAX);
                 if (new_size <= erst_record_id_cache.size) {
                         if (printk_ratelimit())
-                                pr_warning(FW_WARN ERST_PFX
-                                           "too many record ID!\n");
+                                pr_warn(FW_WARN "too many record IDs!\n");
                         return 0;
                 }
                 alloc_size = new_size * sizeof(entries[0]);
@@ -761,8 +759,7 @@ static int __erst_clear_from_storage(u64 record_id)
 static void pr_unimpl_nvram(void)
 {
         if (printk_ratelimit())
-                pr_warning(ERST_PFX
-                "NVRAM ERST Log Address Range is not implemented yet\n");
+                pr_warn("NVRAM ERST Log Address Range not implemented yet.\n");
 }
 
 static int __erst_write_to_nvram(const struct cper_record_header *record)
@@ -1133,7 +1130,7 @@ static int __init erst_init(void)
                 goto err;
 
         if (erst_disable) {
-                pr_info(ERST_PFX
+                pr_info(
         "Error Record Serialization Table (ERST) support is disabled.\n");
                 goto err;
         }
@@ -1144,14 +1141,14 @@ static int __init erst_init(void)
                 goto err;
         else if (ACPI_FAILURE(status)) {
                 const char *msg = acpi_format_exception(status);
-                pr_err(ERST_PFX "Failed to get table, %s\n", msg);
+                pr_err("Failed to get table, %s\n", msg);
                 rc = -EINVAL;
                 goto err;
         }
 
         rc = erst_check_table(erst_tab);
         if (rc) {
-                pr_err(FW_BUG ERST_PFX "ERST table is invalid\n");
+                pr_err(FW_BUG "ERST table is invalid.\n");
                 goto err;
         }
 
@@ -1169,21 +1166,19 @@ static int __init erst_init(void)
         rc = erst_get_erange(&erst_erange);
         if (rc) {
                 if (rc == -ENODEV)
-                        pr_info(ERST_PFX
+                        pr_info(
         "The corresponding hardware device or firmware implementation "
         "is not available.\n");
                 else
-                        pr_err(ERST_PFX
-                               "Failed to get Error Log Address Range.\n");
+                        pr_err("Failed to get Error Log Address Range.\n");
                 goto err_unmap_reg;
         }
 
         r = request_mem_region(erst_erange.base, erst_erange.size, "APEI ERST");
         if (!r) {
-                pr_err(ERST_PFX
-                "Can not request iomem region <0x%16llx-0x%16llx> for ERST.\n",
-                (unsigned long long)erst_erange.base,
-                (unsigned long long)erst_erange.base + erst_erange.size);
+                pr_err("Can not request [mem %#010llx-%#010llx] for ERST.\n",
+                       (unsigned long long)erst_erange.base,
+                       (unsigned long long)erst_erange.base + erst_erange.size - 1);
                 rc = -EIO;
                 goto err_unmap_reg;
         }
@@ -1193,7 +1188,7 @@ static int __init erst_init(void)
         if (!erst_erange.vaddr)
                 goto err_release_erange;
 
-        pr_info(ERST_PFX
+        pr_info(
         "Error Record Serialization Table (ERST) support is initialized.\n");
 
         buf = kmalloc(erst_erange.size, GFP_KERNEL);
@@ -1205,15 +1200,15 @@ static int __init erst_init(void)
                 rc = pstore_register(&erst_info);
                 if (rc) {
                         if (rc != -EPERM)
-                                pr_info(ERST_PFX
-                                "Could not register with persistent store\n");
+                                pr_info(
+                                "Could not register with persistent store.\n");
                         erst_info.buf = NULL;
                         erst_info.bufsize = 0;
                         kfree(buf);
                 }
         } else
-                pr_err(ERST_PFX
-                "Failed to allocate %lld bytes for persistent store error log\n",
+                pr_err(
+                "Failed to allocate %lld bytes for persistent store error log.\n",
                 erst_erange.size);
 
         return 0;
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..f5e37f32c71f 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 +122,41 @@ 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)
+{
+#ifdef CONFIG_X86_MCE
+        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);
+#endif
+        return 1;
+}
+
 struct ghes_arr {
         struct platform_device **ghes_devs;
         unsigned int count;
@@ -227,6 +263,9 @@ 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)