Merge branch 'for-2.6.32' into for-2.6.33

20 files changed, 116 insertions, 49 deletions

diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
index 7da00b799cda..060fff8f5c5b 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
@@ -57,5 +57,8 @@ SECTIONS
                 *(.note*)
         }
 
+        /*
+         * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+         */
         . = ASSERT(_end <= WAKEUP_SIZE, "Wakeup too big!");
 }
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f5f5886a6b53..326c25477d3d 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -352,14 +352,14 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 
         for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
                 alias.v = uv_read_local_mmr(redir_addrs[i].alias);
-                if (alias.s.base == 0) {
+                if (alias.s.enable && alias.s.base == 0) {
                         *size = (1UL << alias.s.m_alias);
                         redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
                         *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
                         return;
                 }
         }
-        BUG();
+        *base = *size = 0;
 }
 
 enum map_type {map_wb, map_uc};
@@ -619,12 +619,12 @@ void __init uv_system_init(void)
                 uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
                 uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
                 uv_cpu_hub_info(cpu)->m_val = m_val;
-                uv_cpu_hub_info(cpu)->n_val = m_val;
+                uv_cpu_hub_info(cpu)->n_val = n_val;
                 uv_cpu_hub_info(cpu)->numa_blade_id = blade;
                 uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
                 uv_cpu_hub_info(cpu)->pnode = pnode;
                 uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
-                uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
+                uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
                 uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
                 uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
                 uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 183c3457d2f4..721a77ca8115 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -85,6 +85,18 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int                      cpu_missing;
 
+static void default_decode_mce(struct mce *m)
+{
+        pr_emerg("No human readable MCE decoding support on this CPU type.\n");
+        pr_emerg("Run the message through 'mcelog --ascii' to decode.\n");
+}
+
+/*
+ * CPU/chipset specific EDAC code can register a callback here to print
+ * MCE errors in a human-readable form:
+ */
+void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce;
+EXPORT_SYMBOL(x86_mce_decode_callback);
 
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
@@ -165,46 +177,46 @@ void mce_log(struct mce *mce)
         set_bit(0, &mce_need_notify);
 }
 
-void __weak decode_mce(struct mce *m)
-{
-        return;
-}
-
 static void print_mce(struct mce *m)
 {
-        printk(KERN_EMERG
-               "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
+        pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
                m->extcpu, m->mcgstatus, m->bank, m->status);
+
         if (m->ip) {
-                printk(KERN_EMERG "RIP%s %02x:<%016Lx> ",
-                       !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
-                       m->cs, m->ip);
+                pr_emerg("RIP%s %02x:<%016Lx> ",
+                        !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
+                                m->cs, m->ip);
+
                 if (m->cs == __KERNEL_CS)
                         print_symbol("{%s}", m->ip);
-                printk(KERN_CONT "\n");
+                pr_cont("\n");
         }
-        printk(KERN_EMERG "TSC %llx ", m->tsc);
+
+        pr_emerg("TSC %llx ", m->tsc);
         if (m->addr)
-                printk(KERN_CONT "ADDR %llx ", m->addr);
+                pr_cont("ADDR %llx ", m->addr);
         if (m->misc)
-                printk(KERN_CONT "MISC %llx ", m->misc);
-        printk(KERN_CONT "\n");
-        printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
-                        m->cpuvendor, m->cpuid, m->time, m->socketid,
-                        m->apicid);
+                pr_cont("MISC %llx ", m->misc);
 
-        decode_mce(m);
+        pr_cont("\n");
+        pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
+                m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid);
+
+        /*
+         * Print out human-readable details about the MCE error,
+         * (if the CPU has an implementation for that):
+         */
+        x86_mce_decode_callback(m);
 }
 
 static void print_mce_head(void)
 {
-        printk(KERN_EMERG "\nHARDWARE ERROR\n");
+        pr_emerg("\nHARDWARE ERROR\n");
 }
 
 static void print_mce_tail(void)
 {
-        printk(KERN_EMERG "This is not a software problem!\n"
-               "Run through mcelog --ascii to decode and contact your hardware vendor\n");
+        pr_emerg("This is not a software problem!\n");
 }
 
 #define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -218,6 +230,7 @@ static atomic_t mce_fake_paniced;
 static void wait_for_panic(void)
 {
         long timeout = PANIC_TIMEOUT*USEC_PER_SEC;
+
         preempt_disable();
         local_irq_enable();
         while (timeout-- > 0)
@@ -285,6 +298,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
 static int msr_to_offset(u32 msr)
 {
         unsigned bank = __get_cpu_var(injectm.bank);
+
         if (msr == rip_msr)
                 return offsetof(struct mce, ip);
         if (msr == MSR_IA32_MCx_STATUS(bank))
@@ -1200,7 +1214,8 @@ static int __cpuinit mce_cap_init(void)
         rdmsrl(MSR_IA32_MCG_CAP, cap);
 
         b = cap & MCG_BANKCNT_MASK;
-        printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);
+        if (!banks)
+                printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);
 
         if (b > MAX_NR_BANKS) {
                 printk(KERN_WARNING
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 889f665fe93d..7c785634af2b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
+#include <linux/sched.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index f04e72527604..3c1b12d461d1 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -96,17 +96,24 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
         unsigned long long base, size;
         char *ptr;
         char line[LINE_SIZE];
+        int length;
         size_t linelen;
 
         if (!capable(CAP_SYS_ADMIN))
                 return -EPERM;
-        if (!len)
-                return -EINVAL;
 
         memset(line, 0, LINE_SIZE);
-        if (len > LINE_SIZE)
-                len = LINE_SIZE;
-        if (copy_from_user(line, buf, len - 1))
+
+        length = len;
+        length--;
+
+        if (length > LINE_SIZE - 1)
+                length = LINE_SIZE - 1;
+
+        if (length < 0)
+                return -EINVAL;
+
+        if (copy_from_user(line, buf, length))
                 return -EFAULT;
 
         linelen = strlen(line);
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index f7cdb3b457aa..cd97ce18c29d 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -16,6 +16,22 @@ static void *kdump_buf_page;
 /* Stores the physical address of elf header of crash image. */
 unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
 
+static inline bool is_crashed_pfn_valid(unsigned long pfn)
+{
+#ifndef CONFIG_X86_PAE
+        /*
+         * non-PAE kdump kernel executed from a PAE one will crop high pte
+         * bits and poke unwanted space counting again from address 0, we
+         * don't want that. pte must fit into unsigned long. In fact the
+         * test checks high 12 bits for being zero (pfn will be shifted left
+         * by PAGE_SHIFT).
+         */
+        return pte_pfn(pfn_pte(pfn, __pgprot(0))) == pfn;
+#else
+        return true;
+#endif
+}
+
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
@@ -41,6 +57,9 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
         if (!csize)
                 return 0;
 
+        if (!is_crashed_pfn_valid(pfn))
+                return -EFAULT;
+
         vaddr = kmap_atomic_pfn(pfn, KM_PTE0);
 
         if (!userbuf) {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 85419bb7d4ab..d17d482a04f4 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1378,8 +1378,8 @@ static unsigned long ram_alignment(resource_size_t pos)
         if (mb < 16)
                 return 1024*1024;
 
-        /* To 32MB for anything above that */
-        return 32*1024*1024;
+        /* To 64MB for anything above that */
+        return 64*1024*1024;
 }
 
 #define MAX_RESOURCE_SIZE ((resource_size_t)-1)
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 41fd965c80c6..b9c830c12b4a 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -206,8 +206,11 @@ static int __init setup_early_printk(char *buf)
 
         while (*buf != '\0') {
                 if (!strncmp(buf, "serial", 6)) {
-                        early_serial_init(buf + 6);
+                        buf += 6;
+                        early_serial_init(buf);
                         early_console_register(&early_serial_console, keep);
+                        if (!strncmp(buf, ",ttyS", 5))
+                                buf += 5;
                 }
                 if (!strncmp(buf, "ttyS", 4)) {
                         early_serial_init(buf + 4);
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index ad5bd988fb79..cdcfb122f256 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -454,8 +454,10 @@ void __init efi_init(void)
         if (add_efi_memmap)
                 do_add_efi_memmap();
 
+#ifdef CONFIG_X86_32
         x86_platform.get_wallclock = efi_get_time;
         x86_platform.set_wallclock = efi_set_rtc_mmss;
+#endif
 
         /* Setup for EFI runtime service */
         reboot_type = BOOT_EFI;
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 1736c5a725aa..9c3bd4a2050e 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -15,8 +15,10 @@ EXPORT_SYMBOL(mcount);
  * the export, but dont use it from C code, it is used
  * by assembly code and is not using C calling convention!
  */
+#ifndef CONFIG_X86_CMPXCHG64
 extern void cmpxchg8b_emu(void);
 EXPORT_SYMBOL(cmpxchg8b_emu);
+#endif
 
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_partial_copy_generic);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 74656d1d4e30..04bbd5278568 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -63,10 +63,10 @@ static int show_other_interrupts(struct seq_file *p, int prec)
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
         seq_printf(p, "  Spurious interrupts\n");
-        seq_printf(p, "%*s: ", prec, "CNT");
+        seq_printf(p, "%*s: ", prec, "PMI");
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
-        seq_printf(p, "  Performance counter interrupts\n");
+        seq_printf(p, "  Performance monitoring interrupts\n");
         seq_printf(p, "%*s: ", prec, "PND");
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 64b838eac18c..b2a71dca5642 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -35,7 +35,7 @@ int iommu_detected __read_mostly = 0;
 
 /*
  * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA ranslation for
+ * If this variable is 1, IOMMU implementations do no DMA translation for
  * devices and allow every device to access to whole physical memory. This is
  * useful if a user want to use an IOMMU only for KVM device assignment to
  * guests and not for driver dma translation.
@@ -311,7 +311,7 @@ void pci_iommu_shutdown(void)
         amd_iommu_shutdown();
 }
 /* Must execute after PCI subsystem */
-fs_initcall(pci_iommu_init);
+rootfs_initcall(pci_iommu_init);
 
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 98a827ee9ed7..a7f1b64f86e0 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -16,6 +16,7 @@
 #include <linux/agp_backend.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 27349f92a6d7..a1a3cdda06e1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -4,6 +4,7 @@
 #include <linux/pm.h>
 #include <linux/efi.h>
 #include <linux/dmi.h>
+#include <linux/sched.h>
 #include <linux/tboot.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index dcb00d278512..be2573448ed9 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -38,7 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs)
 #ifdef CONFIG_FRAME_POINTER
                 return *(unsigned long *)(regs->bp + sizeof(long));
 #else
-                unsigned long *sp = (unsigned long *)regs->sp;
+                unsigned long *sp =
+                        (unsigned long *)kernel_stack_pointer(regs);
                 /*
                  * Return address is either directly at stack pointer
                  * or above a saved flags. Eflags has bits 22-31 zero,
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 503c1f2e8835..1740c85e24bb 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -23,8 +23,6 @@
 static struct bau_control       **uv_bau_table_bases __read_mostly;
 static int                      uv_bau_retry_limit __read_mostly;
 
-/* position of pnode (which is nasid>>1): */
-static int                      uv_nshift __read_mostly;
 /* base pnode in this partition */
 static int                      uv_partition_base_pnode __read_mostly;
 
@@ -723,7 +721,7 @@ uv_activation_descriptor_init(int node, int pnode)
         BUG_ON(!adp);
 
         pa = uv_gpa(adp); /* need the real nasid*/
-        n = pa >> uv_nshift;
+        n = uv_gpa_to_pnode(pa);
         m = pa & uv_mmask;
 
         uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
@@ -778,7 +776,7 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
          * need the pnode of where the memory was really allocated
          */
         pa = uv_gpa(pqp);
-        pn = pa >> uv_nshift;
+        pn = uv_gpa_to_pnode(pa);
         uv_write_global_mmr64(pnode,
                               UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST,
                               ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) |
@@ -843,8 +841,7 @@ static int __init uv_bau_init(void)
                                        GFP_KERNEL, cpu_to_node(cur_cpu));
 
         uv_bau_retry_limit = 1;
-        uv_nshift = uv_hub_info->n_val;
-        uv_mmask = (1UL << uv_hub_info->n_val) - 1;
+        uv_mmask = (1UL << uv_hub_info->m_val) - 1;
         nblades = uv_num_possible_blades();
 
         uv_bau_table_bases = (struct bau_control **)
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index 699f7eeb896a..cd022121cab6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -3,8 +3,16 @@
 #include <asm/trampoline.h>
 #include <asm/e820.h>
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
+#define __trampinit
+#define __trampinitdata
+#else
+#define __trampinit __cpuinit
+#define __trampinitdata __cpuinitdata
+#endif
+
 /* ready for x86_64 and x86 */
-unsigned char *__cpuinitdata trampoline_base = __va(TRAMPOLINE_BASE);
+unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE);
 
 void __init reserve_trampoline_memory(void)
 {
@@ -26,7 +34,7 @@ void __init reserve_trampoline_memory(void)
  * bootstrap into the page concerned. The caller
  * has made sure it's suitably aligned.
  */
-unsigned long __cpuinit setup_trampoline(void)
+unsigned long __trampinit setup_trampoline(void)
 {
         memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
         return virt_to_phys(trampoline_base);
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 596d54c660a5..3af2dff58b21 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -32,8 +32,12 @@
 #include <asm/segment.h>
 #include <asm/processor-flags.h>
 
+#ifdef CONFIG_ACPI_SLEEP
+.section .rodata, "a", @progbits
+#else
 /* We can free up the trampoline after bootup if cpu hotplug is not supported. */
 __CPUINITRODATA
+#endif
 .code16
 
 ENTRY(trampoline_data)
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 31e6f6cfe53e..d430e4c30193 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -648,7 +648,7 @@ static inline int __init activate_vmi(void)
 
         pv_info.paravirt_enabled = 1;
         pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-        pv_info.name = "vmi";
+        pv_info.name = "vmi [deprecated]";
 
         pv_init_ops.patch = vmi_patch;
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 92929fb3f9fa..3c68fe2d46cf 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -305,6 +305,9 @@ SECTIONS
 
 
 #ifdef CONFIG_X86_32
+/*
+ * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ */
 . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
            "kernel image bigger than KERNEL_IMAGE_SIZE");
 #else