35 files changed, 403 insertions, 127 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e0c619c55b4e..dcb0593b4a66 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -109,6 +109,9 @@ config SBUS
 config NEED_DMA_MAP_STATE
       def_bool (X86_64 || DMAR || DMA_API_DEBUG)
+config NEED_SG_DMA_LENGTH
+        def_bool y
 config GENERIC_ISA_DMA
        def_bool y
@@ -1703,6 +1706,10 @@ config HAVE_ARCH_EARLY_PFN_TO_NID
        def_bool X86_64
        depends on NUMA
+config USE_PERCPU_NUMA_NODE_ID
+        def_bool X86_64
+        depends on NUMA
 menu "Power management and ACPI options"
 config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 56f462cf22d2..aa2c39d968fc 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -85,7 +85,6 @@ extern int acpi_ioapic;
 extern int acpi_noirq;
 extern int acpi_strict;
 extern int acpi_disabled;
-extern int acpi_ht;
 extern int acpi_pci_disabled;
 extern int acpi_skip_timer_override;
 extern int acpi_use_timer_override;
@@ -97,7 +96,6 @@ void acpi_pic_sci_set_trigger(unsigned int, u16);
 static inline void disable_acpi(void)
 {
        acpi_disabled = 1;
-        acpi_ht = 0;
        acpi_pci_disabled = 1;
        acpi_noirq = 1;
 }
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index dca9c545f44e..468145914389 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -332,6 +332,7 @@ static __always_inline __pure bool __static_cpu_has(u8 bit)
 #endif
 }
+#if __GNUC__ >= 4
 #define static_cpu_has(bit)                                     \
 (                                                               \
        __builtin_constant_p(boot_cpu_has(bit)) ?               \
@@ -340,6 +341,12 @@ static __always_inline __pure bool __static_cpu_has(u8 bit)
                __static_cpu_has(bit) :                         \
                boot_cpu_has(bit)                               \
 )
+#else
+/*
+ * gcc 3.x is too stupid to do the static test; fall back to dynamic.
+ */
+#define static_cpu_has(bit) boot_cpu_has(bit)
+#endif
 #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 6c3fdd631ed3..f32a4301c4d4 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -225,5 +225,13 @@ extern void mcheck_intel_therm_init(void);
 static inline void mcheck_intel_therm_init(void) { }
 #endif
+/*
+ * Used by APEI to report memory error via /dev/mcelog
+ */
+struct cper_sec_mem_err;
+extern void apei_mce_report_mem_error(int corrected,
+                                      struct cper_sec_mem_err *mem_err);
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index b05400a542ff..64a8ebff06fc 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -89,7 +89,8 @@
        P4_CCCR_ENABLE)
 /* HT mask */
-#define P4_CCCR_MASK_HT (P4_CCCR_MASK | P4_CCCR_THREAD_ANY)
+#define P4_CCCR_MASK_HT                         \
+        (P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY)
 #define P4_GEN_ESCR_EMASK(class, name, bit)     \
        class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
diff --git a/arch/x86/include/asm/rdc321x_defs.h b/arch/x86/include/asm/rdc321x_defs.h
deleted file mode 100644
index c8e9c8bed3d0..000000000000
--- a/arch/x86/include/asm/rdc321x_defs.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#define PFX     "rdc321x: "
-/* General purpose configuration and data registers */
-#define RDC3210_CFGREG_ADDR     0x0CF8
-#define RDC3210_CFGREG_DATA     0x0CFC
-#define RDC321X_GPIO_CTRL_REG1  0x48
-#define RDC321X_GPIO_CTRL_REG2  0x84
-#define RDC321X_GPIO_DATA_REG1  0x4c
-#define RDC321X_GPIO_DATA_REG2  0x88
-#define RDC321X_MAX_GPIO        58
diff --git a/arch/x86/include/asm/scatterlist.h b/arch/x86/include/asm/scatterlist.h
index 75af592677ec..fb0b1874396f 100644
--- a/arch/x86/include/asm/scatterlist.h
+++ b/arch/x86/include/asm/scatterlist.h
@@ -1,8 +1,9 @@
 #ifndef _ASM_X86_SCATTERLIST_H
 #define _ASM_X86_SCATTERLIST_H
-#define ISA_DMA_THRESHOLD (0x00ffffff)
 #include <asm-generic/scatterlist.h>
+#define ISA_DMA_THRESHOLD (0x00ffffff)
+#define ARCH_HAS_SG_CHAIN
 #endif /* _ASM_X86_SCATTERLIST_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 62ba9400cc43..f0b6e5dbc5a0 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -239,8 +239,8 @@ static inline struct thread_info *current_thread_info(void)
 #define TS_USEDFPU              0x0001  /* FPU was used by this task
                                           this quantum (SMP) */
 #define TS_COMPAT               0x0002  /* 32bit syscall active (64BIT)*/
-#define TS_POLLING              0x0004  /* true if in idle loop
+#define TS_POLLING              0x0004  /* idle task polling need_resched,
-                                           and not sleeping */
+                                           skip sending interrupt */
 #define TS_RESTORE_SIGMASK      0x0008  /* restore signal mask in do_signal() */
 #define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index c5087d796587..21899cc31e52 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -53,33 +53,29 @@
 extern int cpu_to_node_map[];
 /* Returns the number of the node containing CPU 'cpu' */
-static inline int cpu_to_node(int cpu)
+static inline int __cpu_to_node(int cpu)
 {
        return cpu_to_node_map[cpu];
 }
-#define early_cpu_to_node(cpu)  cpu_to_node(cpu)
+#define early_cpu_to_node __cpu_to_node
+#define cpu_to_node __cpu_to_node
 #else /* CONFIG_X86_64 */
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
-/* Returns the number of the current Node. */
-DECLARE_PER_CPU(int, node_number);
-#define numa_node_id()          percpu_read(node_number)
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
-extern int cpu_to_node(int cpu);
+/*
+ * override generic percpu implementation of cpu_to_node
+ */
+extern int __cpu_to_node(int cpu);
+#define cpu_to_node __cpu_to_node
 extern int early_cpu_to_node(int cpu);
 #else   /* !CONFIG_DEBUG_PER_CPU_MAPS */
-/* Returns the number of the node containing CPU 'cpu' */
-static inline int cpu_to_node(int cpu)
-{
-        return per_cpu(x86_cpu_to_node_map, cpu);
-}
 /* Same function but used if called before per_cpu areas are setup */
 static inline int early_cpu_to_node(int cpu)
 {
@@ -170,6 +166,10 @@ static inline int numa_node_id(void)
 {
        return 0;
 }
+/*
+ * indicate override:
+ */
+#define numa_node_id numa_node_id
 static inline int early_cpu_to_node(int cpu)
 {
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/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;
+        unsigned int value, queued;
-        int i, j;
+        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--) {
+        do {
-                value = apic_read(APIC_ISR + i*0x10);
+                queued = 0;
-                for (j = 31; j >= 0; j--) {
+                for (i = APIC_ISR_NR - 1; i >= 0; i--)
-                        if (value & (1<<j))
+                        queued |= apic_read(APIC_IRR + i*0x10);
-                                ack_APIC_irq();
+                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 &&
+        if (cpu != 0 && percpu_read(numa_node) == 0 &&
-            cpu_to_node(cpu) != NUMA_NO_NODE)
+            early_cpu_to_node(cpu) != NUMA_NO_NODE)
-                percpu_write(node_number, cpu_to_node(cpu));
+                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,
+static int cpb_notify(struct notifier_block *nb, unsigned long action,
-                                void *hcpu)
+                      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..707165dbc203 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -264,7 +264,7 @@ 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 +287,11 @@ 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 +300,17 @@ 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 +1502,43 @@ 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 +1552,19 @@ 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)) {
+        err = -EINVAL;
-                mutex_unlock(&mce_read_mutex);
+        if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
-                kfree(cpu_tsc);
+                goto out;
-                return -EINVAL;
-        }
        err = 0;
        prev = 0;
@@ -1562,10 +1612,15 @@ 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 +1628,8 @@ 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..c77586061bcb 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1717,7 +1717,11 @@ 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);
+        rdmsr(hwc->config_base + hwc->idx, low, high);
-        if (dummy & P4_CCCR_OVF) {
+        /* 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);
-                /*
+                /* it might be unflagged overflow */
-                 * FIXME: Redundant call, actually not needed
+                handled = p4_pmu_clear_cccr_ovf(hwc);
-                 * but just to check if we're screwed
-                 */
-                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 for sure */
-                 * event overflow
+                data.period = event->hw.last_period;
-                 */
-                handled         = 1;
-                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 ||
+        if (unlikely(idx >= P4_ESCR_MSR_TABLE_SIZE      ||
-                        !p4_escr_table[idx])) {
+                        !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/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..a867940a6dfc 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -265,10 +265,10 @@ 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..37462f1ddba5 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1215,9 +1215,17 @@ __init void prefill_possible_map(void)
        if (!num_processors)
                num_processors = 1;
-        if (setup_possible_cpus == -1)
+        i = setup_max_cpus ?: 1;
-                possible = num_processors + disabled_cpus;
+        if (setup_possible_cpus == -1) {
-        else
+                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/lguest/boot.c b/arch/x86/lguest/boot.c
index 2bdf628066bd..9257510b4836 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1390,7 +1390,6 @@ __init void lguest_init(void)
 #endif
 #ifdef CONFIG_ACPI
        acpi_disabled = 1;
-        acpi_ht = 0;
 #endif
        /*
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 8948f47fde05..a7bcc23ef96c 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -33,9 +33,6 @@ int numa_off __initdata;
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
-DEFINE_PER_CPU(int, node_number) = 0;
-EXPORT_PER_CPU_SYMBOL(node_number);
 /*
 * Map cpu index to node index
 */
@@ -809,7 +806,7 @@ void __cpuinit numa_set_node(int cpu, int node)
        per_cpu(x86_cpu_to_node_map, cpu) = node;
        if (node != NUMA_NO_NODE)
-                per_cpu(node_number, cpu) = node;
+                set_cpu_numa_node(cpu, node);
 }
 void __cpuinit numa_clear_node(int cpu)
@@ -867,7 +864,7 @@ void __cpuinit numa_remove_cpu(int cpu)
        numa_set_cpumask(cpu, 0);
 }
-int cpu_to_node(int cpu)
+int __cpu_to_node(int cpu)
 {
        if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
                printk(KERN_WARNING
@@ -877,7 +874,7 @@ int cpu_to_node(int cpu)
        }
        return per_cpu(x86_cpu_to_node_map, cpu);
 }
-EXPORT_SYMBOL(cpu_to_node);
+EXPORT_SYMBOL(__cpu_to_node);
 /*
 * Same function as cpu_to_node() but used if called before the
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index bbe5502ee1cb..acc15b23b743 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -336,6 +336,7 @@ int free_memtype(u64 start, u64 end)
 {
        int err = -EINVAL;
        int is_range_ram;
+        struct memtype *entry;
        if (!pat_enabled)
                return 0;
@@ -355,17 +356,20 @@ int free_memtype(u64 start, u64 end)
        }
        spin_lock(&memtype_lock);
-        err = rbt_memtype_erase(start, end);
+        entry = rbt_memtype_erase(start, end);
        spin_unlock(&memtype_lock);
-        if (err) {
+        if (!entry) {
                printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n",
                        current->comm, current->pid, start, end);
+                return -EINVAL;
        }
+        kfree(entry);
        dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);
-        return err;
+        return 0;
 }
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index 4f39eefa3e61..77e5ba153fac 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -28,15 +28,15 @@ static inline char *cattr_name(unsigned long flags)
 #ifdef CONFIG_X86_PAT
 extern int rbt_memtype_check_insert(struct memtype *new,
                                        unsigned long *new_type);
-extern int rbt_memtype_erase(u64 start, u64 end);
+extern struct memtype *rbt_memtype_erase(u64 start, u64 end);
 extern struct memtype *rbt_memtype_lookup(u64 addr);
 extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos);
 #else
 static inline int rbt_memtype_check_insert(struct memtype *new,
                                        unsigned long *new_type)
 { return 0; }
-static inline int rbt_memtype_erase(u64 start, u64 end)
+static inline struct memtype *rbt_memtype_erase(u64 start, u64 end)
-{ return 0; }
+{ return NULL; }
 static inline struct memtype *rbt_memtype_lookup(u64 addr)
 { return NULL; }
 static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 07de4cb8cc30..f537087bb740 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -231,16 +231,17 @@ int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
        return err;
 }
-int rbt_memtype_erase(u64 start, u64 end)
+struct memtype *rbt_memtype_erase(u64 start, u64 end)
 {
        struct memtype *data;
        data = memtype_rb_exact_match(&memtype_rbroot, start, end);
        if (!data)
-                return -EINVAL;
+                goto out;
        rb_erase(&data->rb, &memtype_rbroot);
-        return 0;
+out:
+        return data;
 }
 struct memtype *rbt_memtype_lookup(u64 addr)
diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c
index df3d5c861cda..308e32570d84 100644
--- a/arch/x86/mm/pf_in.c
+++ b/arch/x86/mm/pf_in.c
@@ -34,7 +34,7 @@
 /* IA32 Manual 3, 2-1 */
 static unsigned char prefix_codes[] = {
        0xF0, 0xF2, 0xF3, 0x2E, 0x36, 0x3E, 0x26, 0x64,
-        0x65, 0x2E, 0x3E, 0x66, 0x67
+        0x65, 0x66, 0x67
 };
 /* IA32 Manual 3, 3-432*/
 static unsigned int reg_rop[] = {
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 792854003ed3..cac718499256 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -9,7 +9,6 @@
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 #include <linux/module.h>
-#include <linux/quicklist.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 31930fd30ea9..2ec04c424a62 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -207,10 +207,9 @@ get_current_resources(struct acpi_device *device, int busnum,
        if (!info.res)
                goto res_alloc_fail;
-        info.name = kmalloc(16, GFP_KERNEL);
+        info.name = kasprintf(GFP_KERNEL, "PCI Bus %04x:%02x", domain, busnum);
        if (!info.name)
                goto name_alloc_fail;
-        sprintf(info.name, "PCI Bus %04x:%02x", domain, busnum);
        info.res_num = 0;
        acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
@@ -224,8 +223,11 @@ res_alloc_fail:
        return;
 }
-struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int domain, int busnum)
+struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
 {
+        struct acpi_device *device = root->device;
+        int domain = root->segment;
+        int busnum = root->secondary.start;
        struct pci_bus *bus;
        struct pci_sysdata *sd;
        int node;