23 files changed, 402 insertions, 96 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 488be461a380..60cc4058ed5f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -63,7 +63,6 @@ EXPORT_SYMBOL(acpi_disabled);
 int acpi_noirq;                         /* skip ACPI IRQ initialization */
 int acpi_pci_disabled;          /* skip ACPI PCI scan and IRQ initialization */
 EXPORT_SYMBOL(acpi_pci_disabled);
-int acpi_ht __initdata = 1;     /* enable HT */
 
 int acpi_lapic;
 int acpi_ioapic;
@@ -1501,9 +1500,8 @@ void __init acpi_boot_table_init(void)
 
         /*
          * If acpi_disabled, bail out
-         * One exception: acpi=ht continues far enough to enumerate LAPICs
          */
-        if (acpi_disabled && !acpi_ht)
+        if (acpi_disabled)
                 return; 
 
         /*
@@ -1534,9 +1532,8 @@ int __init early_acpi_boot_init(void)
 {
         /*
          * If acpi_disabled, bail out
-         * One exception: acpi=ht continues far enough to enumerate LAPICs
          */
-        if (acpi_disabled && !acpi_ht)
+        if (acpi_disabled)
                 return 1;
 
         /*
@@ -1554,9 +1551,8 @@ int __init acpi_boot_init(void)
 
         /*
          * If acpi_disabled, bail out
-         * One exception: acpi=ht continues far enough to enumerate LAPICs
          */
-        if (acpi_disabled && !acpi_ht)
+        if (acpi_disabled)
                 return 1;
 
         acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
@@ -1591,21 +1587,12 @@ static int __init parse_acpi(char *arg)
         /* acpi=force to over-ride black-list */
         else if (strcmp(arg, "force") == 0) {
                 acpi_force = 1;
-                acpi_ht = 1;
                 acpi_disabled = 0;
         }
         /* acpi=strict disables out-of-spec workarounds */
         else if (strcmp(arg, "strict") == 0) {
                 acpi_strict = 1;
         }
-        /* Limit ACPI just to boot-time to enable HT */
-        else if (strcmp(arg, "ht") == 0) {
-                if (!acpi_force) {
-                        printk(KERN_WARNING "acpi=ht will be removed in Linux-2.6.35\n");
-                        disable_acpi();
-                }
-                acpi_ht = 1;
-        }
         /* acpi=rsdt use RSDT instead of XSDT */
         else if (strcmp(arg, "rsdt") == 0) {
                 acpi_rsdt_forced = 1;
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index f9961034e557..82e508677b91 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -162,8 +162,6 @@ static int __init acpi_sleep_setup(char *str)
 #endif
                 if (strncmp(str, "old_ordering", 12) == 0)
                         acpi_old_suspend_ordering();
-                if (strncmp(str, "sci_force_enable", 16) == 0)
-                        acpi_set_sci_en_on_resume();
                 str = strchr(str, ',');
                 if (str != NULL)
                         str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 8ded418b0593..13ab720573e3 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -1,4 +1,4 @@
-        .section .text.page_aligned
+        .section .text..page_aligned
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/page_types.h>
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index fa5a1474cd18..0d20286d78c6 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1487,6 +1487,7 @@ static int __attach_device(struct device *dev,
                            struct protection_domain *domain)
 {
         struct iommu_dev_data *dev_data, *alias_data;
+        int ret;
 
         dev_data   = get_dev_data(dev);
         alias_data = get_dev_data(dev_data->alias);
@@ -1498,13 +1499,14 @@ static int __attach_device(struct device *dev,
         spin_lock(&domain->lock);
 
         /* Some sanity checks */
+        ret = -EBUSY;
         if (alias_data->domain != NULL &&
             alias_data->domain != domain)
-                return -EBUSY;
+                goto out_unlock;
 
         if (dev_data->domain != NULL &&
             dev_data->domain != domain)
-                return -EBUSY;
+                goto out_unlock;
 
         /* Do real assignment */
         if (dev_data->alias != dev) {
@@ -1520,10 +1522,14 @@ static int __attach_device(struct device *dev,
 
         atomic_inc(&dev_data->bind);
 
+        ret = 0;
+
+out_unlock:
+
         /* ready */
         spin_unlock(&domain->lock);
 
-        return 0;
+        return ret;
 }
 
 /*
@@ -2324,10 +2330,6 @@ int __init amd_iommu_init_dma_ops(void)
 
         iommu_detected = 1;
         swiotlb = 0;
-#ifdef CONFIG_GART_IOMMU
-        gart_iommu_aperture_disabled = 1;
-        gart_iommu_aperture = 0;
-#endif
 
         /* Make the driver finally visible to the drivers */
         dma_ops = &amd_iommu_dma_ops;
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 3bacb4d0844c..3cc63e2b8dd4 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -287,8 +287,12 @@ static u8 * __init iommu_map_mmio_space(u64 address)
 {
         u8 *ret;
 
-        if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu"))
+        if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) {
+                pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n",
+                        address);
+                pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n");
                 return NULL;
+        }
 
         ret = ioremap_nocache(address, MMIO_REGION_LENGTH);
         if (ret != NULL)
@@ -1314,7 +1318,7 @@ static int __init amd_iommu_init(void)
                 ret = amd_iommu_init_dma_ops();
 
         if (ret)
-                goto free;
+                goto free_disable;
 
         amd_iommu_init_api();
 
@@ -1332,9 +1336,10 @@ static int __init amd_iommu_init(void)
 out:
         return ret;
 
-free:
+free_disable:
         disable_iommus();
 
+free:
         amd_iommu_uninit_devices();
 
         free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
@@ -1353,6 +1358,15 @@ free:
 
         free_unity_maps();
 
+#ifdef CONFIG_GART_IOMMU
+        /*
+         * We failed to initialize the AMD IOMMU - try fallback to GART
+         * if possible.
+         */
+        gart_iommu_init();
+
+#endif
+
         goto out;
 }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e5a4a1e01618..c02cc692985c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -51,6 +51,7 @@
 #include <asm/smp.h>
 #include <asm/mce.h>
 #include <asm/kvm_para.h>
+#include <asm/tsc.h>
 
 unsigned int num_processors;
 
@@ -1151,8 +1152,13 @@ static void __cpuinit lapic_setup_esr(void)
  */
 void __cpuinit setup_local_APIC(void)
 {
-        unsigned int value;
-        int i, j;
+        unsigned int value, queued;
+        int i, j, acked = 0;
+        unsigned long long tsc = 0, ntsc;
+        long long max_loops = cpu_khz;
+
+        if (cpu_has_tsc)
+                rdtscll(tsc);
 
         if (disable_apic) {
                 arch_disable_smp_support();
@@ -1204,13 +1210,32 @@ void __cpuinit setup_local_APIC(void)
          * the interrupt. Hence a vector might get locked. It was noticed
          * for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
          */
-        for (i = APIC_ISR_NR - 1; i >= 0; i--) {
-                value = apic_read(APIC_ISR + i*0x10);
-                for (j = 31; j >= 0; j--) {
-                        if (value & (1<<j))
-                                ack_APIC_irq();
+        do {
+                queued = 0;
+                for (i = APIC_ISR_NR - 1; i >= 0; i--)
+                        queued |= apic_read(APIC_IRR + i*0x10);
+
+                for (i = APIC_ISR_NR - 1; i >= 0; i--) {
+                        value = apic_read(APIC_ISR + i*0x10);
+                        for (j = 31; j >= 0; j--) {
+                                if (value & (1<<j)) {
+                                        ack_APIC_irq();
+                                        acked++;
+                                }
+                        }
                 }
-        }
+                if (acked > 256) {
+                        printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n",
+                               acked);
+                        break;
+                }
+                if (cpu_has_tsc) {
+                        rdtscll(ntsc);
+                        max_loops = (cpu_khz << 10) - (ntsc - tsc);
+                } else
+                        max_loops--;
+        } while (queued && max_loops > 0);
+        WARN_ON(max_loops <= 0);
 
         /*
          * Now that we are all set up, enable the APIC
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index cc83a002786e..68e4a6f2211e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1121,9 +1121,9 @@ void __cpuinit cpu_init(void)
         oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
-        if (cpu != 0 && percpu_read(node_number) == 0 &&
-            cpu_to_node(cpu) != NUMA_NO_NODE)
-                percpu_write(node_number, cpu_to_node(cpu));
+        if (cpu != 0 && percpu_read(numa_node) == 0 &&
+            early_cpu_to_node(cpu) != NUMA_NO_NODE)
+                set_numa_node(early_cpu_to_node(cpu));
 #endif
 
         me = current;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 6f3dc8fbbfdc..7ec2123838e6 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1497,8 +1497,8 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
  * simply keep the boost-disable flag in sync with the current global
  * state.
  */
-static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action,
-                                void *hcpu)
+static int cpb_notify(struct notifier_block *nb, unsigned long action,
+                      void *hcpu)
 {
         unsigned cpu = (long)hcpu;
         u32 lo, hi;
@@ -1528,7 +1528,7 @@ static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action,
         return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata cpb_nb = {
+static struct notifier_block cpb_nb = {
         .notifier_call          = cpb_notify,
 };
 
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index 4ac6d48fe11b..bb34b03af252 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -7,3 +7,5 @@ obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
 obj-$(CONFIG_X86_MCE_INJECT)    += mce-inject.o
 
 obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
+
+obj-$(CONFIG_ACPI_APEI)         += mce-apei.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
new file mode 100644
index 000000000000..745b54f9be89
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -0,0 +1,138 @@
+/*
+ * Bridge between MCE and APEI
+ *
+ * On some machine, corrected memory errors are reported via APEI
+ * generic hardware error source (GHES) instead of corrected Machine
+ * Check. These corrected memory errors can be reported to user space
+ * through /dev/mcelog via faking a corrected Machine Check, so that
+ * the error memory page can be offlined by /sbin/mcelog if the error
+ * count for one page is beyond the threshold.
+ *
+ * For fatal MCE, save MCE record into persistent storage via ERST, so
+ * that the MCE record can be logged after reboot via ERST.
+ *
+ * Copyright 2010 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/acpi.h>
+#include <linux/cper.h>
+#include <acpi/apei.h>
+#include <asm/mce.h>
+
+#include "mce-internal.h"
+
+void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
+{
+        struct mce m;
+
+        /* Only corrected MC is reported */
+        if (!corrected)
+                return;
+
+        mce_setup(&m);
+        m.bank = 1;
+        /* Fake a memory read corrected error with unknown channel */
+        m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | 0x9f;
+        m.addr = mem_err->physical_addr;
+        mce_log(&m);
+        mce_notify_irq();
+}
+EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
+
+#define CPER_CREATOR_MCE                                                \
+        UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c,     \
+                0x64, 0x90, 0xb8, 0x9d)
+#define CPER_SECTION_TYPE_MCE                                           \
+        UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,     \
+                0x04, 0x4a, 0x38, 0xfc)
+
+/*
+ * CPER specification (in UEFI specification 2.3 appendix N) requires
+ * byte-packed.
+ */
+struct cper_mce_record {
+        struct cper_record_header hdr;
+        struct cper_section_descriptor sec_hdr;
+        struct mce mce;
+} __packed;
+
+int apei_write_mce(struct mce *m)
+{
+        struct cper_mce_record rcd;
+
+        memset(&rcd, 0, sizeof(rcd));
+        memcpy(rcd.hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
+        rcd.hdr.revision = CPER_RECORD_REV;
+        rcd.hdr.signature_end = CPER_SIG_END;
+        rcd.hdr.section_count = 1;
+        rcd.hdr.error_severity = CPER_SER_FATAL;
+        /* timestamp, platform_id, partition_id are all invalid */
+        rcd.hdr.validation_bits = 0;
+        rcd.hdr.record_length = sizeof(rcd);
+        rcd.hdr.creator_id = CPER_CREATOR_MCE;
+        rcd.hdr.notification_type = CPER_NOTIFY_MCE;
+        rcd.hdr.record_id = cper_next_record_id();
+        rcd.hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR;
+
+        rcd.sec_hdr.section_offset = (void *)&rcd.mce - (void *)&rcd;
+        rcd.sec_hdr.section_length = sizeof(rcd.mce);
+        rcd.sec_hdr.revision = CPER_SEC_REV;
+        /* fru_id and fru_text is invalid */
+        rcd.sec_hdr.validation_bits = 0;
+        rcd.sec_hdr.flags = CPER_SEC_PRIMARY;
+        rcd.sec_hdr.section_type = CPER_SECTION_TYPE_MCE;
+        rcd.sec_hdr.section_severity = CPER_SER_FATAL;
+
+        memcpy(&rcd.mce, m, sizeof(*m));
+
+        return erst_write(&rcd.hdr);
+}
+
+ssize_t apei_read_mce(struct mce *m, u64 *record_id)
+{
+        struct cper_mce_record rcd;
+        ssize_t len;
+
+        len = erst_read_next(&rcd.hdr, sizeof(rcd));
+        if (len <= 0)
+                return len;
+        /* Can not skip other records in storage via ERST unless clear them */
+        else if (len != sizeof(rcd) ||
+                 uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) {
+                if (printk_ratelimit())
+                        pr_warning(
+                        "MCE-APEI: Can not skip the unknown record in ERST");
+                return -EIO;
+        }
+
+        memcpy(m, &rcd.mce, sizeof(*m));
+        *record_id = rcd.hdr.record_id;
+
+        return sizeof(*m);
+}
+
+/* Check whether there is record in ERST */
+int apei_check_mce(void)
+{
+        return erst_get_record_count();
+}
+
+int apei_clear_mce(u64 record_id)
+{
+        return erst_clear(record_id);
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 32996f9fab67..fefcc69ee8b5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -28,3 +28,26 @@ extern int mce_ser;
 
 extern struct mce_bank *mce_banks;
 
+#ifdef CONFIG_ACPI_APEI
+int apei_write_mce(struct mce *m);
+ssize_t apei_read_mce(struct mce *m, u64 *record_id);
+int apei_check_mce(void);
+int apei_clear_mce(u64 record_id);
+#else
+static inline int apei_write_mce(struct mce *m)
+{
+        return -EINVAL;
+}
+static inline ssize_t apei_read_mce(struct mce *m, u64 *record_id)
+{
+        return 0;
+}
+static inline int apei_check_mce(void)
+{
+        return 0;
+}
+static inline int apei_clear_mce(u64 record_id)
+{
+        return -EINVAL;
+}
+#endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7a355ddcc64b..18cc42562250 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -36,6 +36,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/debugfs.h>
+#include <linux/edac_mce.h>
 
 #include <asm/processor.h>
 #include <asm/hw_irq.h>
@@ -169,6 +170,15 @@ void mce_log(struct mce *mce)
                 entry = rcu_dereference_check_mce(mcelog.next);
                 for (;;) {
                         /*
+                         * If edac_mce is enabled, it will check the error type
+                         * and will process it, if it is a known error.
+                         * Otherwise, the error will be sent through mcelog
+                         * interface
+                         */
+                        if (edac_mce_parse(mce))
+                                return;
+
+                        /*
                          * When the buffer fills up discard new entries.
                          * Assume that the earlier errors are the more
                          * interesting ones:
@@ -264,7 +274,7 @@ static void wait_for_panic(void)
 
 static void mce_panic(char *msg, struct mce *final, char *exp)
 {
-        int i;
+        int i, apei_err = 0;
 
         if (!fake_panic) {
                 /*
@@ -287,8 +297,11 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
                 struct mce *m = &mcelog.entry[i];
                 if (!(m->status & MCI_STATUS_VAL))
                         continue;
-                if (!(m->status & MCI_STATUS_UC))
+                if (!(m->status & MCI_STATUS_UC)) {
                         print_mce(m);
+                        if (!apei_err)
+                                apei_err = apei_write_mce(m);
+                }
         }
         /* Now print uncorrected but with the final one last */
         for (i = 0; i < MCE_LOG_LEN; i++) {
@@ -297,11 +310,17 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
                         continue;
                 if (!(m->status & MCI_STATUS_UC))
                         continue;
-                if (!final || memcmp(m, final, sizeof(struct mce)))
+                if (!final || memcmp(m, final, sizeof(struct mce))) {
                         print_mce(m);
+                        if (!apei_err)
+                                apei_err = apei_write_mce(m);
+                }
         }
-        if (final)
+        if (final) {
                 print_mce(final);
+                if (!apei_err)
+                        apei_err = apei_write_mce(final);
+        }
         if (cpu_missing)
                 printk(KERN_EMERG "Some CPUs didn't answer in synchronization\n");
         print_mce_tail();
@@ -1493,6 +1512,43 @@ static void collect_tscs(void *data)
         rdtscll(cpu_tsc[smp_processor_id()]);
 }
 
+static int mce_apei_read_done;
+
+/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
+static int __mce_read_apei(char __user **ubuf, size_t usize)
+{
+        int rc;
+        u64 record_id;
+        struct mce m;
+
+        if (usize < sizeof(struct mce))
+                return -EINVAL;
+
+        rc = apei_read_mce(&m, &record_id);
+        /* Error or no more MCE record */
+        if (rc <= 0) {
+                mce_apei_read_done = 1;
+                return rc;
+        }
+        rc = -EFAULT;
+        if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
+                return rc;
+        /*
+         * In fact, we should have cleared the record after that has
+         * been flushed to the disk or sent to network in
+         * /sbin/mcelog, but we have no interface to support that now,
+         * so just clear it to avoid duplication.
+         */
+        rc = apei_clear_mce(record_id);
+        if (rc) {
+                mce_apei_read_done = 1;
+                return rc;
+        }
+        *ubuf += sizeof(struct mce);
+
+        return 0;
+}
+
 static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
                         loff_t *off)
 {
@@ -1506,15 +1562,19 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
                 return -ENOMEM;
 
         mutex_lock(&mce_read_mutex);
+
+        if (!mce_apei_read_done) {
+                err = __mce_read_apei(&buf, usize);
+                if (err || buf != ubuf)
+                        goto out;
+        }
+
         next = rcu_dereference_check_mce(mcelog.next);
 
         /* Only supports full reads right now */
-        if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
-                mutex_unlock(&mce_read_mutex);
-                kfree(cpu_tsc);
-
-                return -EINVAL;
-        }
+        err = -EINVAL;
+        if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+                goto out;
 
         err = 0;
         prev = 0;
@@ -1562,10 +1622,15 @@ timeout:
                         memset(&mcelog.entry[i], 0, sizeof(struct mce));
                 }
         }
+
+        if (err)
+                err = -EFAULT;
+
+out:
         mutex_unlock(&mce_read_mutex);
         kfree(cpu_tsc);
 
-        return err ? -EFAULT : buf - ubuf;
+        return err ? err : buf - ubuf;
 }
 
 static unsigned int mce_poll(struct file *file, poll_table *wait)
@@ -1573,6 +1638,8 @@ static unsigned int mce_poll(struct file *file, poll_table *wait)
         poll_wait(file, &mce_wait, wait);
         if (rcu_dereference_check_mce(mcelog.next))
                 return POLLIN | POLLRDNORM;
+        if (!mce_apei_read_done && apei_check_mce())
+                return POLLIN | POLLRDNORM;
         return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 81c499eceb21..e1a0a3bf9716 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -190,7 +190,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
                 mutex_unlock(&therm_cpu_lock);
                 break;
         }
-        return err ? NOTIFY_BAD : NOTIFY_OK;
+        return notifier_from_errno(err);
 }
 
 static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index fd4db0db3708..5db5b7d65a18 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -106,6 +106,7 @@ struct cpu_hw_events {
 
         int                     n_events;
         int                     n_added;
+        int                     n_txn;
         int                     assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
         u64                     tags[X86_PMC_IDX_MAX];
         struct perf_event       *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
@@ -983,6 +984,7 @@ static int x86_pmu_enable(struct perf_event *event)
 out:
         cpuc->n_events = n;
         cpuc->n_added += n - n0;
+        cpuc->n_txn += n - n0;
 
         return 0;
 }
@@ -1089,6 +1091,14 @@ static void x86_pmu_disable(struct perf_event *event)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         int i;
 
+        /*
+         * If we're called during a txn, we don't need to do anything.
+         * The events never got scheduled and ->cancel_txn will truncate
+         * the event_list.
+         */
+        if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+                return;
+
         x86_pmu_stop(event);
 
         for (i = 0; i < cpuc->n_events; i++) {
@@ -1379,6 +1389,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
         cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+        cpuc->n_txn = 0;
 }
 
 /*
@@ -1391,6 +1402,11 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
         cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+        /*
+         * Truncate the collected events.
+         */
+        cpuc->n_added -= cpuc->n_txn;
+        cpuc->n_events -= cpuc->n_txn;
 }
 
 /*
@@ -1419,6 +1435,12 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
          */
         memcpy(cpuc->assign, assign, n*sizeof(int));
 
+        /*
+         * Clear out the txn count so that ->cancel_txn() which gets
+         * run after ->commit_txn() doesn't undo things.
+         */
+        cpuc->n_txn = 0;
+
         return 0;
 }
 
@@ -1717,7 +1739,11 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski
          */
         regs->bp = rewind_frame_pointer(skip + 1);
         regs->cs = __KERNEL_CS;
-        local_save_flags(regs->flags);
+        /*
+         * We abuse bit 3 to pass exact information, see perf_misc_flags
+         * and the comment with PERF_EFLAGS_EXACT.
+         */
+        regs->flags = 0;
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 424fc8de68e4..ae85d69644d1 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -465,15 +465,21 @@ out:
         return rc;
 }
 
-static inline void p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
+static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-        unsigned long dummy;
+        int overflow = 0;
+        u32 low, high;
 
-        rdmsrl(hwc->config_base + hwc->idx, dummy);
-        if (dummy & P4_CCCR_OVF) {
+        rdmsr(hwc->config_base + hwc->idx, low, high);
+
+        /* we need to check high bit for unflagged overflows */
+        if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
+                overflow = 1;
                 (void)checking_wrmsrl(hwc->config_base + hwc->idx,
-                        ((u64)dummy) & ~P4_CCCR_OVF);
+                        ((u64)low) & ~P4_CCCR_OVF);
         }
+
+        return overflow;
 }
 
 static inline void p4_pmu_disable_event(struct perf_event *event)
@@ -584,21 +590,15 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 
                 WARN_ON_ONCE(hwc->idx != idx);
 
-                /*
-                 * FIXME: Redundant call, actually not needed
-                 * but just to check if we're screwed
-                 */
-                p4_pmu_clear_cccr_ovf(hwc);
+                /* it might be unflagged overflow */
+                handled = p4_pmu_clear_cccr_ovf(hwc);
 
                 val = x86_perf_event_update(event);
-                if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
+                if (!handled && (val & (1ULL << (x86_pmu.cntval_bits - 1))))
                         continue;
 
-                /*
-                 * event overflow
-                 */
-                handled         = 1;
-                data.period     = event->hw.last_period;
+                /* event overflow for sure */
+                data.period = event->hw.last_period;
 
                 if (!x86_perf_event_set_period(event))
                         continue;
@@ -670,7 +670,7 @@ static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu)
 
 /*
  * ESCR address hashing is tricky, ESCRs are not sequential
- * in memory but all starts from MSR_P4_BSU_ESCR0 (0x03e0) and
+ * in memory but all starts from MSR_P4_BSU_ESCR0 (0x03a0) and
  * the metric between any ESCRs is laid in range [0xa0,0xe1]
  *
  * so we make ~70% filled hashtable
@@ -735,8 +735,9 @@ static int p4_get_escr_idx(unsigned int addr)
 {
         unsigned int idx = P4_ESCR_MSR_IDX(addr);
 
-        if (unlikely(idx >= P4_ESCR_MSR_TABLE_SIZE ||
-                        !p4_escr_table[idx])) {
+        if (unlikely(idx >= P4_ESCR_MSR_TABLE_SIZE      ||
+                        !p4_escr_table[idx]             ||
+                        p4_escr_table[idx] != addr)) {
                 WARN_ONCE(1, "P4 PMU: Wrong address passed: %x\n", addr);
                 return -1;
         }
@@ -762,7 +763,7 @@ static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign
 {
         unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
         unsigned long escr_mask[BITS_TO_LONGS(P4_ESCR_MSR_TABLE_SIZE)];
-        int cpu = raw_smp_processor_id();
+        int cpu = smp_processor_id();
         struct hw_perf_event *hwc;
         struct p4_event_bind *bind;
         unsigned int i, thread, num;
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 8b862d5900fe..1b7b31ab7d86 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -170,7 +170,7 @@ static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb,
                 cpuid_device_destroy(cpu);
                 break;
         }
-        return err ? NOTIFY_BAD : NOTIFY_OK;
+        return notifier_from_errno(err);
 }
 
 static struct notifier_block __refdata cpuid_class_cpu_notifier =
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index 3a54dcb9cd0e..43e9ccf44947 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -34,7 +34,7 @@ EXPORT_SYMBOL(init_task);
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
  * no more per-task TSS's. The TSS size is kept cacheline-aligned
- * so they are allowed to end up in the .data.cacheline_aligned
+ * so they are allowed to end up in the .data..cacheline_aligned
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 4d4468e9f47c..7bf2dc4c8f70 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -230,7 +230,7 @@ static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb,
                 msr_device_destroy(cpu);
                 break;
         }
-        return err ? NOTIFY_BAD : NOTIFY_OK;
+        return notifier_from_errno(err);
 }
 
 static struct notifier_block __refdata msr_class_cpu_notifier = {
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 7d2829dde20e..a5bc528d4328 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -31,8 +31,6 @@ static struct dma_map_ops swiotlb_dma_ops = {
         .free_coherent = swiotlb_free_coherent,
         .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
         .sync_single_for_device = swiotlb_sync_single_for_device,
-        .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
-        .sync_single_range_for_device = swiotlb_sync_single_range_for_device,
         .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
         .sync_sg_for_device = swiotlb_sync_sg_for_device,
         .map_sg = swiotlb_map_sg_attrs,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index e8029896309a..b4ae4acbd031 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -676,6 +676,17 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
                         DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
                 },
         },
+        /*
+         * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so
+         * match on the product name.
+         */
+        {
+                .callback = dmi_low_memory_corruption,
+                .ident = "Phoenix BIOS",
+                .matches = {
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"),
+                },
+        },
 #endif
         {}
 };
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index ef6370b00e70..de3b63ae3da2 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -21,12 +21,6 @@
 #include <asm/cpu.h>
 #include <asm/stackprotector.h>
 
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(fmt, ...) pr_dbg(fmt, ##__VA_ARGS__)
-#else
-# define DBG(fmt, ...) do { if (0) pr_dbg(fmt, ##__VA_ARGS__); } while (0)
-#endif
-
 DEFINE_PER_CPU(int, cpu_number);
 EXPORT_PER_CPU_SYMBOL(cpu_number);
 
@@ -247,7 +241,7 @@ void __init setup_per_cpu_areas(void)
 #endif
 #endif
                 /*
-                 * Up to this point, the boot CPU has been using .data.init
+                 * Up to this point, the boot CPU has been using .init.data
                  * area.  Reload any changed state for the boot CPU.
                  */
                 if (cpu == boot_cpu_id)
@@ -265,10 +259,10 @@ void __init setup_per_cpu_areas(void)
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
         /*
-         * make sure boot cpu node_number is right, when boot cpu is on the
+         * make sure boot cpu numa_node is right, when boot cpu is on the
          * node that doesn't have mem installed
          */
-        per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id);
+        set_cpu_numa_node(boot_cpu_id, early_cpu_to_node(boot_cpu_id));
 #endif
 
         /* Setup node to cpumask map */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 763d815e27a0..c4f33b2e77d6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -686,7 +686,7 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
 static void __cpuinit announce_cpu(int cpu, int apicid)
 {
         static int current_node = -1;
-        int node = cpu_to_node(cpu);
+        int node = early_cpu_to_node(cpu);
 
         if (system_state == SYSTEM_BOOTING) {
                 if (node != current_node) {
@@ -1215,9 +1215,17 @@ __init void prefill_possible_map(void)
         if (!num_processors)
                 num_processors = 1;
 
-        if (setup_possible_cpus == -1)
-                possible = num_processors + disabled_cpus;
-        else
+        i = setup_max_cpus ?: 1;
+        if (setup_possible_cpus == -1) {
+                possible = num_processors;
+#ifdef CONFIG_HOTPLUG_CPU
+                if (setup_max_cpus)
+                        possible += disabled_cpus;
+#else
+                if (possible > i)
+                        possible = i;
+#endif
+        } else
                 possible = setup_possible_cpus;
 
         total_cpus = max_t(int, possible, num_processors + disabled_cpus);
@@ -1230,11 +1238,23 @@ __init void prefill_possible_map(void)
                 possible = nr_cpu_ids;
         }
 
+#ifdef CONFIG_HOTPLUG_CPU
+        if (!setup_max_cpus)
+#endif
+        if (possible > i) {
+                printk(KERN_WARNING
+                        "%d Processors exceeds max_cpus limit of %u\n",
+                        possible, setup_max_cpus);
+                possible = i;
+        }
+
         printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n",
                 possible, max_t(int, possible - num_processors, 0));
 
         for (i = 0; i < possible; i++)
                 set_cpu_possible(i, true);
+        for (; i < NR_CPUS; i++)
+                set_cpu_possible(i, false);
 
         nr_cpu_ids = possible;
 }
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 2cc249718c46..d0bb52296fa3 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -97,7 +97,7 @@ SECTIONS
                 HEAD_TEXT
 #ifdef CONFIG_X86_32
                 . = ALIGN(PAGE_SIZE);
-                *(.text.page_aligned)
+                *(.text..page_aligned)
 #endif
                 . = ALIGN(8);
                 _stext = .;
@@ -305,7 +305,7 @@ SECTIONS
         . = ALIGN(PAGE_SIZE);
         .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
                 __bss_start = .;
-                *(.bss.page_aligned)
+                *(.bss..page_aligned)
                 *(.bss)
                 . = ALIGN(4);
                 __bss_stop = .;